From: Jason A. Donenfeld Date: Fri, 19 Feb 2021 13:29:04 +0000 (+0100) Subject: kernel: 5.4: import wireguard backport X-Git-Url: http://git.lede-project.org./?a=commitdiff_plain;h=3888fa78802354ab7bbd19b7d061fd80a16ce06b;p=openwrt%2Fstaging%2Fnbd.git kernel: 5.4: import wireguard backport Rather than using the clunky, old, slower wireguard-linux-compat out of tree module, this commit does a patch-by-patch backport of upstream's wireguard to 5.4. This specific backport is in widespread use, being part of SUSE's enterprise kernel, Oracle's enterprise kernel, Google's Android kernel, Gentoo's distro kernel, and probably more I've forgotten about. It's definately the "more proper" way of adding wireguard to a kernel than the ugly compat.h hell of the wireguard-linux-compat repo. And most importantly for OpenWRT, it allows using the same module configuration code for 5.10 as for 5.4, with no need for bifurcation. These patches are from the backport tree which is maintained in the open here: https://git.zx2c4.com/wireguard-linux/log/?h=backport-5.4.y I'll be sending PRs to update this as needed. Signed-off-by: Jason A. Donenfeld --- diff --git a/target/linux/generic/backport-5.4/080-wireguard-0001-crypto-lib-tidy-up-lib-crypto-Kconfig-and-Makefile.patch b/target/linux/generic/backport-5.4/080-wireguard-0001-crypto-lib-tidy-up-lib-crypto-Kconfig-and-Makefile.patch new file mode 100644 index 0000000000..9de7c9cb00 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0001-crypto-lib-tidy-up-lib-crypto-Kconfig-and-Makefile.patch @@ -0,0 +1,112 @@ +From 7b5de278d022b3f31bc5b42cd160bea2e8bc4c74 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:07 +0100 +Subject: [PATCH 001/124] crypto: lib - tidy up lib/crypto Kconfig and Makefile + +commit 746b2e024c67aa605ac12d135cd7085a49cf9dc4 upstream. + +In preparation of introducing a set of crypto library interfaces, tidy +up the Makefile and split off the Kconfig symbols into a separate file. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/Kconfig | 13 +------------ + lib/crypto/Kconfig | 15 +++++++++++++++ + lib/crypto/Makefile | 16 ++++++++-------- + 3 files changed, 24 insertions(+), 20 deletions(-) + create mode 100644 lib/crypto/Kconfig + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -878,9 +878,6 @@ config CRYPTO_SHA1_PPC_SPE + SHA-1 secure hash standard (DFIPS 180-4) implemented + using powerpc SPE SIMD instruction set. + +-config CRYPTO_LIB_SHA256 +- tristate +- + config CRYPTO_SHA256 + tristate "SHA224 and SHA256 digest algorithm" + select CRYPTO_HASH +@@ -1019,9 +1016,6 @@ config CRYPTO_GHASH_CLMUL_NI_INTEL + + comment "Ciphers" + +-config CRYPTO_LIB_AES +- tristate +- + config CRYPTO_AES + tristate "AES cipher algorithms" + select CRYPTO_ALGAPI +@@ -1150,9 +1144,6 @@ config CRYPTO_ANUBIS + + + +-config CRYPTO_LIB_ARC4 +- tristate +- + config CRYPTO_ARC4 + tristate "ARC4 cipher algorithm" + select CRYPTO_BLKCIPHER +@@ -1339,9 +1330,6 @@ config CRYPTO_CAST6_AVX_X86_64 + This module provides the Cast6 cipher algorithm that processes + eight blocks parallel using the AVX instruction set. + +-config CRYPTO_LIB_DES +- tristate +- + config CRYPTO_DES + tristate "DES and Triple DES EDE cipher algorithms" + select CRYPTO_ALGAPI +@@ -1845,6 +1833,7 @@ config CRYPTO_STATS + config CRYPTO_HASH_INFO + bool + ++source "lib/crypto/Kconfig" + source "drivers/crypto/Kconfig" + source "crypto/asymmetric_keys/Kconfig" + source "certs/Kconfig" +--- /dev/null ++++ b/lib/crypto/Kconfig +@@ -0,0 +1,15 @@ ++# SPDX-License-Identifier: GPL-2.0 ++ ++comment "Crypto library routines" ++ ++config CRYPTO_LIB_AES ++ tristate ++ ++config CRYPTO_LIB_ARC4 ++ tristate ++ ++config CRYPTO_LIB_DES ++ tristate ++ ++config CRYPTO_LIB_SHA256 ++ tristate +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -1,13 +1,13 @@ + # SPDX-License-Identifier: GPL-2.0 + +-obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o +-libaes-y := aes.o ++obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o ++libaes-y := aes.o + +-obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o +-libarc4-y := arc4.o ++obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o ++libarc4-y := arc4.o + +-obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o +-libdes-y := des.o ++obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o ++libdes-y := des.o + +-obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o +-libsha256-y := sha256.o ++obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o ++libsha256-y := sha256.o diff --git a/target/linux/generic/backport-5.4/080-wireguard-0002-crypto-chacha-move-existing-library-code-into-lib-cr.patch b/target/linux/generic/backport-5.4/080-wireguard-0002-crypto-chacha-move-existing-library-code-into-lib-cr.patch new file mode 100644 index 0000000000..a16ca08f56 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0002-crypto-chacha-move-existing-library-code-into-lib-cr.patch @@ -0,0 +1,669 @@ +From 6f71439c260ddd0f9a21fee3e34449fe9c017ab6 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:08 +0100 +Subject: [PATCH 002/124] crypto: chacha - move existing library code into + lib/crypto + +commit 5fb8ef25803ef33e2eb60b626435828b937bed75 upstream. + +Currently, our generic ChaCha implementation consists of a permute +function in lib/chacha.c that operates on the 64-byte ChaCha state +directly [and which is always included into the core kernel since it +is used by the /dev/random driver], and the crypto API plumbing to +expose it as a skcipher. + +In order to support in-kernel users that need the ChaCha streamcipher +but have no need [or tolerance] for going through the abstractions of +the crypto API, let's expose the streamcipher bits via a library API +as well, in a way that permits the implementation to be superseded by +an architecture specific one if provided. + +So move the streamcipher code into a separate module in lib/crypto, +and expose the init() and crypt() routines to users of the library. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/chacha-neon-glue.c | 2 +- + arch/arm64/crypto/chacha-neon-glue.c | 2 +- + arch/x86/crypto/chacha_glue.c | 2 +- + crypto/Kconfig | 1 + + crypto/chacha_generic.c | 60 ++-------------------- + include/crypto/chacha.h | 77 ++++++++++++++++++++++------ + include/crypto/internal/chacha.h | 53 +++++++++++++++++++ + lib/Makefile | 3 +- + lib/crypto/Kconfig | 26 ++++++++++ + lib/crypto/Makefile | 4 ++ + lib/{ => crypto}/chacha.c | 20 ++++---- + lib/crypto/libchacha.c | 35 +++++++++++++ + 12 files changed, 199 insertions(+), 86 deletions(-) + create mode 100644 include/crypto/internal/chacha.h + rename lib/{ => crypto}/chacha.c (88%) + create mode 100644 lib/crypto/libchacha.c + +--- a/arch/arm/crypto/chacha-neon-glue.c ++++ b/arch/arm/crypto/chacha-neon-glue.c +@@ -20,7 +20,7 @@ + */ + + #include +-#include ++#include + #include + #include + #include +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -20,7 +20,7 @@ + */ + + #include +-#include ++#include + #include + #include + #include +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -7,7 +7,7 @@ + */ + + #include +-#include ++#include + #include + #include + #include +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -1393,6 +1393,7 @@ config CRYPTO_SALSA20 + + config CRYPTO_CHACHA20 + tristate "ChaCha stream cipher algorithms" ++ select CRYPTO_LIB_CHACHA_GENERIC + select CRYPTO_BLKCIPHER + help + The ChaCha20, XChaCha20, and XChaCha12 stream cipher algorithms. +--- a/crypto/chacha_generic.c ++++ b/crypto/chacha_generic.c +@@ -8,29 +8,10 @@ + + #include + #include +-#include ++#include + #include + #include + +-static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src, +- unsigned int bytes, int nrounds) +-{ +- /* aligned to potentially speed up crypto_xor() */ +- u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long)); +- +- while (bytes >= CHACHA_BLOCK_SIZE) { +- chacha_block(state, stream, nrounds); +- crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE); +- bytes -= CHACHA_BLOCK_SIZE; +- dst += CHACHA_BLOCK_SIZE; +- src += CHACHA_BLOCK_SIZE; +- } +- if (bytes) { +- chacha_block(state, stream, nrounds); +- crypto_xor_cpy(dst, src, stream, bytes); +- } +-} +- + static int chacha_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv) + { +@@ -48,8 +29,8 @@ static int chacha_stream_xor(struct skci + if (nbytes < walk.total) + nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE); + +- chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr, +- nbytes, ctx->nrounds); ++ chacha_crypt_generic(state, walk.dst.virt.addr, ++ walk.src.virt.addr, nbytes, ctx->nrounds); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + +@@ -58,41 +39,10 @@ static int chacha_stream_xor(struct skci + + void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv) + { +- state[0] = 0x61707865; /* "expa" */ +- state[1] = 0x3320646e; /* "nd 3" */ +- state[2] = 0x79622d32; /* "2-by" */ +- state[3] = 0x6b206574; /* "te k" */ +- state[4] = ctx->key[0]; +- state[5] = ctx->key[1]; +- state[6] = ctx->key[2]; +- state[7] = ctx->key[3]; +- state[8] = ctx->key[4]; +- state[9] = ctx->key[5]; +- state[10] = ctx->key[6]; +- state[11] = ctx->key[7]; +- state[12] = get_unaligned_le32(iv + 0); +- state[13] = get_unaligned_le32(iv + 4); +- state[14] = get_unaligned_le32(iv + 8); +- state[15] = get_unaligned_le32(iv + 12); ++ chacha_init_generic(state, ctx->key, iv); + } + EXPORT_SYMBOL_GPL(crypto_chacha_init); + +-static int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize, int nrounds) +-{ +- struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); +- int i; +- +- if (keysize != CHACHA_KEY_SIZE) +- return -EINVAL; +- +- for (i = 0; i < ARRAY_SIZE(ctx->key); i++) +- ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32)); +- +- ctx->nrounds = nrounds; +- return 0; +-} +- + int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize) + { +@@ -126,7 +76,7 @@ int crypto_xchacha_crypt(struct skcipher + + /* Compute the subkey given the original key and first 128 nonce bits */ + crypto_chacha_init(state, ctx, req->iv); +- hchacha_block(state, subctx.key, ctx->nrounds); ++ hchacha_block_generic(state, subctx.key, ctx->nrounds); + subctx.nrounds = ctx->nrounds; + + /* Build the real IV */ +--- a/include/crypto/chacha.h ++++ b/include/crypto/chacha.h +@@ -15,9 +15,8 @@ + #ifndef _CRYPTO_CHACHA_H + #define _CRYPTO_CHACHA_H + +-#include ++#include + #include +-#include + + /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ + #define CHACHA_IV_SIZE 16 +@@ -29,26 +28,70 @@ + /* 192-bit nonce, then 64-bit stream position */ + #define XCHACHA_IV_SIZE 32 + +-struct chacha_ctx { +- u32 key[8]; +- int nrounds; +-}; +- +-void chacha_block(u32 *state, u8 *stream, int nrounds); ++void chacha_block_generic(u32 *state, u8 *stream, int nrounds); + static inline void chacha20_block(u32 *state, u8 *stream) + { +- chacha_block(state, stream, 20); ++ chacha_block_generic(state, stream, 20); + } +-void hchacha_block(const u32 *in, u32 *out, int nrounds); + +-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv); ++void hchacha_block_arch(const u32 *state, u32 *out, int nrounds); ++void hchacha_block_generic(const u32 *state, u32 *out, int nrounds); ++ ++static inline void hchacha_block(const u32 *state, u32 *out, int nrounds) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) ++ hchacha_block_arch(state, out, nrounds); ++ else ++ hchacha_block_generic(state, out, nrounds); ++} + +-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize); +-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize); ++void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv); ++static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv) ++{ ++ state[0] = 0x61707865; /* "expa" */ ++ state[1] = 0x3320646e; /* "nd 3" */ ++ state[2] = 0x79622d32; /* "2-by" */ ++ state[3] = 0x6b206574; /* "te k" */ ++ state[4] = key[0]; ++ state[5] = key[1]; ++ state[6] = key[2]; ++ state[7] = key[3]; ++ state[8] = key[4]; ++ state[9] = key[5]; ++ state[10] = key[6]; ++ state[11] = key[7]; ++ state[12] = get_unaligned_le32(iv + 0); ++ state[13] = get_unaligned_le32(iv + 4); ++ state[14] = get_unaligned_le32(iv + 8); ++ state[15] = get_unaligned_le32(iv + 12); ++} + +-int crypto_chacha_crypt(struct skcipher_request *req); +-int crypto_xchacha_crypt(struct skcipher_request *req); ++static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) ++ chacha_init_arch(state, key, iv); ++ else ++ chacha_init_generic(state, key, iv); ++} ++ ++void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, ++ unsigned int bytes, int nrounds); ++void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src, ++ unsigned int bytes, int nrounds); ++ ++static inline void chacha_crypt(u32 *state, u8 *dst, const u8 *src, ++ unsigned int bytes, int nrounds) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) ++ chacha_crypt_arch(state, dst, src, bytes, nrounds); ++ else ++ chacha_crypt_generic(state, dst, src, bytes, nrounds); ++} ++ ++static inline void chacha20_crypt(u32 *state, u8 *dst, const u8 *src, ++ unsigned int bytes) ++{ ++ chacha_crypt(state, dst, src, bytes, 20); ++} + + #endif /* _CRYPTO_CHACHA_H */ +--- /dev/null ++++ b/include/crypto/internal/chacha.h +@@ -0,0 +1,53 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++ ++#ifndef _CRYPTO_INTERNAL_CHACHA_H ++#define _CRYPTO_INTERNAL_CHACHA_H ++ ++#include ++#include ++#include ++ ++struct chacha_ctx { ++ u32 key[8]; ++ int nrounds; ++}; ++ ++void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv); ++ ++static inline int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize, int nrounds) ++{ ++ struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); ++ int i; ++ ++ if (keysize != CHACHA_KEY_SIZE) ++ return -EINVAL; ++ ++ for (i = 0; i < ARRAY_SIZE(ctx->key); i++) ++ ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32)); ++ ++ ctx->nrounds = nrounds; ++ return 0; ++} ++ ++static inline int chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize) ++{ ++ return chacha_setkey(tfm, key, keysize, 20); ++} ++ ++static int inline chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize) ++{ ++ return chacha_setkey(tfm, key, keysize, 12); ++} ++ ++int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize); ++int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize); ++ ++int crypto_chacha_crypt(struct skcipher_request *req); ++int crypto_xchacha_crypt(struct skcipher_request *req); ++ ++#endif /* _CRYPTO_CHACHA_H */ +--- a/lib/Makefile ++++ b/lib/Makefile +@@ -26,8 +26,7 @@ endif + + lib-y := ctype.o string.o vsprintf.o cmdline.o \ + rbtree.o radix-tree.o timerqueue.o xarray.o \ +- idr.o extable.o \ +- sha1.o chacha.o irq_regs.o argv_split.o \ ++ idr.o extable.o sha1.o irq_regs.o argv_split.o \ + flex_proportions.o ratelimit.o show_mem.o \ + is_single_threaded.o plist.o decompress.o kobject_uevent.o \ + earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -8,6 +8,32 @@ config CRYPTO_LIB_AES + config CRYPTO_LIB_ARC4 + tristate + ++config CRYPTO_ARCH_HAVE_LIB_CHACHA ++ tristate ++ help ++ Declares whether the architecture provides an arch-specific ++ accelerated implementation of the ChaCha library interface, ++ either builtin or as a module. ++ ++config CRYPTO_LIB_CHACHA_GENERIC ++ tristate ++ select CRYPTO_ALGAPI ++ help ++ This symbol can be depended upon by arch implementations of the ++ ChaCha library interface that require the generic code as a ++ fallback, e.g., for SIMD implementations. If no arch specific ++ implementation is enabled, this implementation serves the users ++ of CRYPTO_LIB_CHACHA. ++ ++config CRYPTO_LIB_CHACHA ++ tristate "ChaCha library interface" ++ depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA ++ select CRYPTO_LIB_CHACHA_GENERIC if CRYPTO_ARCH_HAVE_LIB_CHACHA=n ++ help ++ Enable the ChaCha library interface. This interface may be fulfilled ++ by either the generic implementation or an arch-specific one, if one ++ is available and enabled. ++ + config CRYPTO_LIB_DES + tristate + +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -1,5 +1,9 @@ + # SPDX-License-Identifier: GPL-2.0 + ++# chacha is used by the /dev/random driver which is always builtin ++obj-y += chacha.o ++obj-$(CONFIG_CRYPTO_LIB_CHACHA_GENERIC) += libchacha.o ++ + obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o + libaes-y := aes.o + +--- a/lib/chacha.c ++++ /dev/null +@@ -1,113 +0,0 @@ +-// SPDX-License-Identifier: GPL-2.0-or-later +-/* +- * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) +- * +- * Copyright (C) 2015 Martin Willi +- */ +- +-#include +-#include +-#include +-#include +-#include +-#include +- +-static void chacha_permute(u32 *x, int nrounds) +-{ +- int i; +- +- /* whitelist the allowed round counts */ +- WARN_ON_ONCE(nrounds != 20 && nrounds != 12); +- +- for (i = 0; i < nrounds; i += 2) { +- x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); +- x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); +- x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); +- x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); +- +- x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); +- x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); +- x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); +- x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); +- +- x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); +- x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); +- x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); +- x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); +- +- x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); +- x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); +- x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); +- x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); +- +- x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); +- x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); +- x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); +- x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); +- +- x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); +- x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); +- x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); +- x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); +- +- x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); +- x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); +- x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); +- x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); +- +- x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); +- x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); +- x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); +- x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); +- } +-} +- +-/** +- * chacha_block - generate one keystream block and increment block counter +- * @state: input state matrix (16 32-bit words) +- * @stream: output keystream block (64 bytes) +- * @nrounds: number of rounds (20 or 12; 20 is recommended) +- * +- * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. +- * The caller has already converted the endianness of the input. This function +- * also handles incrementing the block counter in the input matrix. +- */ +-void chacha_block(u32 *state, u8 *stream, int nrounds) +-{ +- u32 x[16]; +- int i; +- +- memcpy(x, state, 64); +- +- chacha_permute(x, nrounds); +- +- for (i = 0; i < ARRAY_SIZE(x); i++) +- put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); +- +- state[12]++; +-} +-EXPORT_SYMBOL(chacha_block); +- +-/** +- * hchacha_block - abbreviated ChaCha core, for XChaCha +- * @in: input state matrix (16 32-bit words) +- * @out: output (8 32-bit words) +- * @nrounds: number of rounds (20 or 12; 20 is recommended) +- * +- * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step +- * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha +- * skips the final addition of the initial state, and outputs only certain words +- * of the state. It should not be used for streaming directly. +- */ +-void hchacha_block(const u32 *in, u32 *out, int nrounds) +-{ +- u32 x[16]; +- +- memcpy(x, in, 64); +- +- chacha_permute(x, nrounds); +- +- memcpy(&out[0], &x[0], 16); +- memcpy(&out[4], &x[12], 16); +-} +-EXPORT_SYMBOL(hchacha_block); +--- /dev/null ++++ b/lib/crypto/chacha.c +@@ -0,0 +1,115 @@ ++// SPDX-License-Identifier: GPL-2.0-or-later ++/* ++ * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) ++ * ++ * Copyright (C) 2015 Martin Willi ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++static void chacha_permute(u32 *x, int nrounds) ++{ ++ int i; ++ ++ /* whitelist the allowed round counts */ ++ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); ++ ++ for (i = 0; i < nrounds; i += 2) { ++ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); ++ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); ++ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); ++ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); ++ ++ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); ++ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); ++ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); ++ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); ++ ++ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); ++ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); ++ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); ++ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); ++ ++ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); ++ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); ++ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); ++ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); ++ ++ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); ++ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); ++ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); ++ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); ++ ++ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); ++ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); ++ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); ++ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); ++ ++ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); ++ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); ++ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); ++ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); ++ ++ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); ++ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); ++ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); ++ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); ++ } ++} ++ ++/** ++ * chacha_block - generate one keystream block and increment block counter ++ * @state: input state matrix (16 32-bit words) ++ * @stream: output keystream block (64 bytes) ++ * @nrounds: number of rounds (20 or 12; 20 is recommended) ++ * ++ * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. ++ * The caller has already converted the endianness of the input. This function ++ * also handles incrementing the block counter in the input matrix. ++ */ ++void chacha_block_generic(u32 *state, u8 *stream, int nrounds) ++{ ++ u32 x[16]; ++ int i; ++ ++ memcpy(x, state, 64); ++ ++ chacha_permute(x, nrounds); ++ ++ for (i = 0; i < ARRAY_SIZE(x); i++) ++ put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); ++ ++ state[12]++; ++} ++EXPORT_SYMBOL(chacha_block_generic); ++ ++/** ++ * hchacha_block_generic - abbreviated ChaCha core, for XChaCha ++ * @state: input state matrix (16 32-bit words) ++ * @out: output (8 32-bit words) ++ * @nrounds: number of rounds (20 or 12; 20 is recommended) ++ * ++ * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step ++ * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha ++ * skips the final addition of the initial state, and outputs only certain words ++ * of the state. It should not be used for streaming directly. ++ */ ++void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds) ++{ ++ u32 x[16]; ++ ++ memcpy(x, state, 64); ++ ++ chacha_permute(x, nrounds); ++ ++ memcpy(&stream[0], &x[0], 16); ++ memcpy(&stream[4], &x[12], 16); ++} ++EXPORT_SYMBOL(hchacha_block_generic); +--- /dev/null ++++ b/lib/crypto/libchacha.c +@@ -0,0 +1,35 @@ ++// SPDX-License-Identifier: GPL-2.0-or-later ++/* ++ * The ChaCha stream cipher (RFC7539) ++ * ++ * Copyright (C) 2015 Martin Willi ++ */ ++ ++#include ++#include ++#include ++ ++#include // for crypto_xor_cpy ++#include ++ ++void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src, ++ unsigned int bytes, int nrounds) ++{ ++ /* aligned to potentially speed up crypto_xor() */ ++ u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long)); ++ ++ while (bytes >= CHACHA_BLOCK_SIZE) { ++ chacha_block_generic(state, stream, nrounds); ++ crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE); ++ bytes -= CHACHA_BLOCK_SIZE; ++ dst += CHACHA_BLOCK_SIZE; ++ src += CHACHA_BLOCK_SIZE; ++ } ++ if (bytes) { ++ chacha_block_generic(state, stream, nrounds); ++ crypto_xor_cpy(dst, src, stream, bytes); ++ } ++} ++EXPORT_SYMBOL(chacha_crypt_generic); ++ ++MODULE_LICENSE("GPL"); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0003-crypto-x86-chacha-depend-on-generic-chacha-library-i.patch b/target/linux/generic/backport-5.4/080-wireguard-0003-crypto-x86-chacha-depend-on-generic-chacha-library-i.patch new file mode 100644 index 0000000000..60339381b5 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0003-crypto-x86-chacha-depend-on-generic-chacha-library-i.patch @@ -0,0 +1,192 @@ +From 29c84baf5e125aa43265192a08cc4bd904db1d45 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:09 +0100 +Subject: [PATCH 003/124] crypto: x86/chacha - depend on generic chacha library + instead of crypto driver + +commit 28e8d89b1ce8d2e7badfb5f69971dd635acb8863 upstream. + +In preparation of extending the x86 ChaCha driver to also expose the ChaCha +library interface, drop the dependency on the chacha_generic crypto driver +as a non-SIMD fallback, and depend on the generic ChaCha library directly. +This way, we only pull in the code we actually need, without registering +a set of ChaCha skciphers that we will never use. + +Since turning the FPU on and off is cheap these days, simplify the SIMD +routine by dropping the per-page yield, which makes for a cleaner switch +to the library API as well. This also allows use to invoke the skcipher +walk routines in non-atomic mode. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/chacha_glue.c | 90 ++++++++++++++--------------------- + crypto/Kconfig | 2 +- + 2 files changed, 36 insertions(+), 56 deletions(-) + +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -123,37 +123,38 @@ static void chacha_dosimd(u32 *state, u8 + } + } + +-static int chacha_simd_stream_xor(struct skcipher_walk *walk, ++static int chacha_simd_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv) + { + u32 *state, state_buf[16 + 2] __aligned(8); +- int next_yield = 4096; /* bytes until next FPU yield */ +- int err = 0; ++ struct skcipher_walk walk; ++ int err; ++ ++ err = skcipher_walk_virt(&walk, req, false); + + BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16); + state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN); + +- crypto_chacha_init(state, ctx, iv); ++ chacha_init_generic(state, ctx->key, iv); + +- while (walk->nbytes > 0) { +- unsigned int nbytes = walk->nbytes; ++ while (walk.nbytes > 0) { ++ unsigned int nbytes = walk.nbytes; + +- if (nbytes < walk->total) { +- nbytes = round_down(nbytes, walk->stride); +- next_yield -= nbytes; +- } +- +- chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr, +- nbytes, ctx->nrounds); ++ if (nbytes < walk.total) ++ nbytes = round_down(nbytes, walk.stride); + +- if (next_yield <= 0) { +- /* temporarily allow preemption */ +- kernel_fpu_end(); ++ if (!crypto_simd_usable()) { ++ chacha_crypt_generic(state, walk.dst.virt.addr, ++ walk.src.virt.addr, nbytes, ++ ctx->nrounds); ++ } else { + kernel_fpu_begin(); +- next_yield = 4096; ++ chacha_dosimd(state, walk.dst.virt.addr, ++ walk.src.virt.addr, nbytes, ++ ctx->nrounds); ++ kernel_fpu_end(); + } +- +- err = skcipher_walk_done(walk, walk->nbytes - nbytes); ++ err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + return err; +@@ -163,55 +164,34 @@ static int chacha_simd(struct skcipher_r + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); +- struct skcipher_walk walk; +- int err; +- +- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) +- return crypto_chacha_crypt(req); + +- err = skcipher_walk_virt(&walk, req, true); +- if (err) +- return err; +- +- kernel_fpu_begin(); +- err = chacha_simd_stream_xor(&walk, ctx, req->iv); +- kernel_fpu_end(); +- return err; ++ return chacha_simd_stream_xor(req, ctx, req->iv); + } + + static int xchacha_simd(struct skcipher_request *req) + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); +- struct skcipher_walk walk; +- struct chacha_ctx subctx; + u32 *state, state_buf[16 + 2] __aligned(8); ++ struct chacha_ctx subctx; + u8 real_iv[16]; +- int err; +- +- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) +- return crypto_xchacha_crypt(req); +- +- err = skcipher_walk_virt(&walk, req, true); +- if (err) +- return err; + + BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16); + state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN); +- crypto_chacha_init(state, ctx, req->iv); ++ chacha_init_generic(state, ctx->key, req->iv); + +- kernel_fpu_begin(); +- +- hchacha_block_ssse3(state, subctx.key, ctx->nrounds); ++ if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) { ++ kernel_fpu_begin(); ++ hchacha_block_ssse3(state, subctx.key, ctx->nrounds); ++ kernel_fpu_end(); ++ } else { ++ hchacha_block_generic(state, subctx.key, ctx->nrounds); ++ } + subctx.nrounds = ctx->nrounds; + + memcpy(&real_iv[0], req->iv + 24, 8); + memcpy(&real_iv[8], req->iv + 16, 8); +- err = chacha_simd_stream_xor(&walk, &subctx, real_iv); +- +- kernel_fpu_end(); +- +- return err; ++ return chacha_simd_stream_xor(req, &subctx, real_iv); + } + + static struct skcipher_alg algs[] = { +@@ -227,7 +207,7 @@ static struct skcipher_alg algs[] = { + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha20_setkey, ++ .setkey = chacha20_setkey, + .encrypt = chacha_simd, + .decrypt = chacha_simd, + }, { +@@ -242,7 +222,7 @@ static struct skcipher_alg algs[] = { + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha20_setkey, ++ .setkey = chacha20_setkey, + .encrypt = xchacha_simd, + .decrypt = xchacha_simd, + }, { +@@ -257,7 +237,7 @@ static struct skcipher_alg algs[] = { + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha12_setkey, ++ .setkey = chacha12_setkey, + .encrypt = xchacha_simd, + .decrypt = xchacha_simd, + }, +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -1417,7 +1417,7 @@ config CRYPTO_CHACHA20_X86_64 + tristate "ChaCha stream cipher algorithms (x86_64/SSSE3/AVX2/AVX-512VL)" + depends on X86 && 64BIT + select CRYPTO_BLKCIPHER +- select CRYPTO_CHACHA20 ++ select CRYPTO_LIB_CHACHA_GENERIC + help + SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20, + XChaCha20, and XChaCha12 stream ciphers. diff --git a/target/linux/generic/backport-5.4/080-wireguard-0004-crypto-x86-chacha-expose-SIMD-ChaCha-routine-as-libr.patch b/target/linux/generic/backport-5.4/080-wireguard-0004-crypto-x86-chacha-expose-SIMD-ChaCha-routine-as-libr.patch new file mode 100644 index 0000000000..0e916c88cf --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0004-crypto-x86-chacha-expose-SIMD-ChaCha-routine-as-libr.patch @@ -0,0 +1,205 @@ +From e7f5b03590beee54da6d02aabe0e1392bc3251e4 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:10 +0100 +Subject: [PATCH 004/124] crypto: x86/chacha - expose SIMD ChaCha routine as + library function + +commit 84e03fa39fbe95a5567d43bff458c6d3b3a23ad1 upstream. + +Wire the existing x86 SIMD ChaCha code into the new ChaCha library +interface, so that users of the library interface will get the +accelerated version when available. + +Given that calls into the library API will always go through the +routines in this module if it is enabled, switch to static keys +to select the optimal implementation available (which may be none +at all, in which case we defer to the generic implementation for +all invocations). + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/chacha_glue.c | 91 +++++++++++++++++++++++++---------- + crypto/Kconfig | 1 + + include/crypto/chacha.h | 6 +++ + 3 files changed, 73 insertions(+), 25 deletions(-) + +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -21,24 +21,24 @@ asmlinkage void chacha_block_xor_ssse3(u + asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds); +-#ifdef CONFIG_AS_AVX2 ++ + asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); +-static bool chacha_use_avx2; +-#ifdef CONFIG_AS_AVX512 ++ + asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); +-static bool chacha_use_avx512vl; +-#endif +-#endif ++ ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl); + + static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks) + { +@@ -49,9 +49,8 @@ static unsigned int chacha_advance(unsig + static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) + { +-#ifdef CONFIG_AS_AVX2 +-#ifdef CONFIG_AS_AVX512 +- if (chacha_use_avx512vl) { ++ if (IS_ENABLED(CONFIG_AS_AVX512) && ++ static_branch_likely(&chacha_use_avx512vl)) { + while (bytes >= CHACHA_BLOCK_SIZE * 8) { + chacha_8block_xor_avx512vl(state, dst, src, bytes, + nrounds); +@@ -79,8 +78,9 @@ static void chacha_dosimd(u32 *state, u8 + return; + } + } +-#endif +- if (chacha_use_avx2) { ++ ++ if (IS_ENABLED(CONFIG_AS_AVX2) && ++ static_branch_likely(&chacha_use_avx2)) { + while (bytes >= CHACHA_BLOCK_SIZE * 8) { + chacha_8block_xor_avx2(state, dst, src, bytes, nrounds); + bytes -= CHACHA_BLOCK_SIZE * 8; +@@ -104,7 +104,7 @@ static void chacha_dosimd(u32 *state, u8 + return; + } + } +-#endif ++ + while (bytes >= CHACHA_BLOCK_SIZE * 4) { + chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds); + bytes -= CHACHA_BLOCK_SIZE * 4; +@@ -123,6 +123,43 @@ static void chacha_dosimd(u32 *state, u8 + } + } + ++void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds) ++{ ++ state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); ++ ++ if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) { ++ hchacha_block_generic(state, stream, nrounds); ++ } else { ++ kernel_fpu_begin(); ++ hchacha_block_ssse3(state, stream, nrounds); ++ kernel_fpu_end(); ++ } ++} ++EXPORT_SYMBOL(hchacha_block_arch); ++ ++void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv) ++{ ++ state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); ++ ++ 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) ++{ ++ state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); ++ ++ if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() || ++ bytes <= CHACHA_BLOCK_SIZE) ++ return chacha_crypt_generic(state, dst, src, bytes, nrounds); ++ ++ kernel_fpu_begin(); ++ chacha_dosimd(state, dst, src, bytes, nrounds); ++ kernel_fpu_end(); ++} ++EXPORT_SYMBOL(chacha_crypt_arch); ++ + static int chacha_simd_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv) + { +@@ -143,7 +180,8 @@ static int chacha_simd_stream_xor(struct + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); + +- if (!crypto_simd_usable()) { ++ if (!static_branch_likely(&chacha_use_simd) || ++ !crypto_simd_usable()) { + chacha_crypt_generic(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, + ctx->nrounds); +@@ -246,18 +284,21 @@ static struct skcipher_alg algs[] = { + static int __init chacha_simd_mod_init(void) + { + if (!boot_cpu_has(X86_FEATURE_SSSE3)) +- return -ENODEV; ++ return 0; + +-#ifdef CONFIG_AS_AVX2 +- chacha_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && +- boot_cpu_has(X86_FEATURE_AVX2) && +- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); +-#ifdef CONFIG_AS_AVX512 +- chacha_use_avx512vl = chacha_use_avx2 && +- boot_cpu_has(X86_FEATURE_AVX512VL) && +- boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */ +-#endif +-#endif ++ static_branch_enable(&chacha_use_simd); ++ ++ if (IS_ENABLED(CONFIG_AS_AVX2) && ++ boot_cpu_has(X86_FEATURE_AVX) && ++ boot_cpu_has(X86_FEATURE_AVX2) && ++ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { ++ static_branch_enable(&chacha_use_avx2); ++ ++ if (IS_ENABLED(CONFIG_AS_AVX512) && ++ boot_cpu_has(X86_FEATURE_AVX512VL) && ++ boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */ ++ static_branch_enable(&chacha_use_avx512vl); ++ } + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); + } + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -1418,6 +1418,7 @@ config CRYPTO_CHACHA20_X86_64 + depends on X86 && 64BIT + select CRYPTO_BLKCIPHER + select CRYPTO_LIB_CHACHA_GENERIC ++ select CRYPTO_ARCH_HAVE_LIB_CHACHA + help + SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20, + XChaCha20, and XChaCha12 stream ciphers. +--- a/include/crypto/chacha.h ++++ b/include/crypto/chacha.h +@@ -25,6 +25,12 @@ + #define CHACHA_BLOCK_SIZE 64 + #define CHACHAPOLY_IV_SIZE 12 + ++#ifdef CONFIG_X86_64 ++#define CHACHA_STATE_WORDS ((CHACHA_BLOCK_SIZE + 12) / sizeof(u32)) ++#else ++#define CHACHA_STATE_WORDS (CHACHA_BLOCK_SIZE / sizeof(u32)) ++#endif ++ + /* 192-bit nonce, then 64-bit stream position */ + #define XCHACHA_IV_SIZE 32 + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0005-crypto-arm64-chacha-depend-on-generic-chacha-library.patch b/target/linux/generic/backport-5.4/080-wireguard-0005-crypto-arm64-chacha-depend-on-generic-chacha-library.patch new file mode 100644 index 0000000000..eca55ed037 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0005-crypto-arm64-chacha-depend-on-generic-chacha-library.patch @@ -0,0 +1,129 @@ +From 527b7f4f3e244c58e07fdb7d850acb45821e1c52 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:11 +0100 +Subject: [PATCH 005/124] crypto: arm64/chacha - depend on generic chacha + library instead of crypto driver + +commit c77da4867cbb7841177275dbb250f5c09679fae4 upstream. + +Depend on the generic ChaCha library routines instead of pulling in the +generic ChaCha skcipher driver, which is more than we need, and makes +managing the dependencies between the generic library, generic driver, +accelerated library and driver more complicated. + +While at it, drop the logic to prefer the scalar code on short inputs. +Turning the NEON on and off is cheap these days, and one major use case +for ChaCha20 is ChaCha20-Poly1305, which is guaranteed to hit the scalar +path upon every invocation (when doing the Poly1305 nonce generation) + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm64/crypto/Kconfig | 2 +- + arch/arm64/crypto/chacha-neon-glue.c | 40 +++++++++++++++------------- + 2 files changed, 23 insertions(+), 19 deletions(-) + +--- a/arch/arm64/crypto/Kconfig ++++ b/arch/arm64/crypto/Kconfig +@@ -103,7 +103,7 @@ config CRYPTO_CHACHA20_NEON + tristate "ChaCha20, XChaCha20, and XChaCha12 stream ciphers using NEON instructions" + depends on KERNEL_MODE_NEON + select CRYPTO_BLKCIPHER +- select CRYPTO_CHACHA20 ++ select CRYPTO_LIB_CHACHA_GENERIC + + config CRYPTO_NHPOLY1305_NEON + tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)" +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -68,7 +68,7 @@ static int chacha_neon_stream_xor(struct + + err = skcipher_walk_virt(&walk, req, false); + +- crypto_chacha_init(state, ctx, iv); ++ chacha_init_generic(state, ctx->key, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; +@@ -76,10 +76,16 @@ static int chacha_neon_stream_xor(struct + if (nbytes < walk.total) + nbytes = rounddown(nbytes, walk.stride); + +- kernel_neon_begin(); +- chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr, +- nbytes, ctx->nrounds); +- kernel_neon_end(); ++ if (!crypto_simd_usable()) { ++ chacha_crypt_generic(state, walk.dst.virt.addr, ++ walk.src.virt.addr, nbytes, ++ ctx->nrounds); ++ } 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); + } + +@@ -91,9 +97,6 @@ static int chacha_neon(struct skcipher_r + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + +- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) +- return crypto_chacha_crypt(req); +- + return chacha_neon_stream_xor(req, ctx, req->iv); + } + +@@ -105,14 +108,15 @@ static int xchacha_neon(struct skcipher_ + u32 state[16]; + u8 real_iv[16]; + +- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) +- return crypto_xchacha_crypt(req); +- +- crypto_chacha_init(state, ctx, req->iv); ++ chacha_init_generic(state, ctx->key, req->iv); + +- kernel_neon_begin(); +- hchacha_block_neon(state, subctx.key, ctx->nrounds); +- kernel_neon_end(); ++ if (crypto_simd_usable()) { ++ kernel_neon_begin(); ++ hchacha_block_neon(state, subctx.key, ctx->nrounds); ++ kernel_neon_end(); ++ } else { ++ hchacha_block_generic(state, subctx.key, ctx->nrounds); ++ } + subctx.nrounds = ctx->nrounds; + + memcpy(&real_iv[0], req->iv + 24, 8); +@@ -134,7 +138,7 @@ static struct skcipher_alg algs[] = { + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 5 * CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha20_setkey, ++ .setkey = chacha20_setkey, + .encrypt = chacha_neon, + .decrypt = chacha_neon, + }, { +@@ -150,7 +154,7 @@ static struct skcipher_alg algs[] = { + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 5 * CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha20_setkey, ++ .setkey = chacha20_setkey, + .encrypt = xchacha_neon, + .decrypt = xchacha_neon, + }, { +@@ -166,7 +170,7 @@ static struct skcipher_alg algs[] = { + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 5 * CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha12_setkey, ++ .setkey = chacha12_setkey, + .encrypt = xchacha_neon, + .decrypt = xchacha_neon, + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0006-crypto-arm64-chacha-expose-arm64-ChaCha-routine-as-l.patch b/target/linux/generic/backport-5.4/080-wireguard-0006-crypto-arm64-chacha-expose-arm64-ChaCha-routine-as-l.patch new file mode 100644 index 0000000000..69583ec838 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0006-crypto-arm64-chacha-expose-arm64-ChaCha-routine-as-l.patch @@ -0,0 +1,138 @@ +From 8b3fda990212ced164ec776a3ba0acedae022614 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:12 +0100 +Subject: [PATCH 006/124] crypto: arm64/chacha - expose arm64 ChaCha routine as + library function + +commit b3aad5bad26a01a4bd8c49a5c5f52aec665f3b7c upstream. + +Expose the accelerated NEON ChaCha routine directly as a symbol +export so that users of the ChaCha library API can use it directly. + +Given that calls into the library API will always go through the +routines in this module if it is enabled, switch to static keys +to select the optimal implementation available (which may be none +at all, in which case we defer to the generic implementation for +all invocations). + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm64/crypto/Kconfig | 1 + + arch/arm64/crypto/chacha-neon-glue.c | 53 ++++++++++++++++++++++------ + 2 files changed, 43 insertions(+), 11 deletions(-) + +--- a/arch/arm64/crypto/Kconfig ++++ b/arch/arm64/crypto/Kconfig +@@ -104,6 +104,7 @@ config CRYPTO_CHACHA20_NEON + depends on KERNEL_MODE_NEON + select CRYPTO_BLKCIPHER + select CRYPTO_LIB_CHACHA_GENERIC ++ select CRYPTO_ARCH_HAVE_LIB_CHACHA + + config CRYPTO_NHPOLY1305_NEON + tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)" +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -23,6 +23,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -36,6 +37,8 @@ asmlinkage void chacha_4block_xor_neon(u + int nrounds, int bytes); + asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds); + ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); ++ + static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, + int bytes, int nrounds) + { +@@ -59,6 +62,37 @@ static void chacha_doneon(u32 *state, u8 + } + } + ++void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds) ++{ ++ if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) { ++ hchacha_block_generic(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 (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE || ++ !crypto_simd_usable()) ++ return chacha_crypt_generic(state, dst, src, bytes, nrounds); ++ ++ kernel_neon_begin(); ++ chacha_doneon(state, dst, src, bytes, nrounds); ++ kernel_neon_end(); ++} ++EXPORT_SYMBOL(chacha_crypt_arch); ++ + static int chacha_neon_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv) + { +@@ -76,7 +110,8 @@ static int chacha_neon_stream_xor(struct + if (nbytes < walk.total) + nbytes = rounddown(nbytes, walk.stride); + +- if (!crypto_simd_usable()) { ++ if (!static_branch_likely(&have_neon) || ++ !crypto_simd_usable()) { + chacha_crypt_generic(state, walk.dst.virt.addr, + walk.src.virt.addr, nbytes, + ctx->nrounds); +@@ -109,14 +144,7 @@ static int xchacha_neon(struct skcipher_ + u8 real_iv[16]; + + chacha_init_generic(state, ctx->key, req->iv); +- +- if (crypto_simd_usable()) { +- kernel_neon_begin(); +- hchacha_block_neon(state, subctx.key, ctx->nrounds); +- kernel_neon_end(); +- } else { +- hchacha_block_generic(state, subctx.key, ctx->nrounds); +- } ++ hchacha_block_arch(state, subctx.key, ctx->nrounds); + subctx.nrounds = ctx->nrounds; + + memcpy(&real_iv[0], req->iv + 24, 8); +@@ -179,14 +207,17 @@ static struct skcipher_alg algs[] = { + static int __init chacha_simd_mod_init(void) + { + if (!cpu_have_named_feature(ASIMD)) +- return -ENODEV; ++ return 0; ++ ++ static_branch_enable(&have_neon); + + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); + } + + static void __exit chacha_simd_mod_fini(void) + { +- crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); ++ if (cpu_have_named_feature(ASIMD)) ++ crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + } + + module_init(chacha_simd_mod_init); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0007-crypto-arm-chacha-import-Eric-Biggers-s-scalar-accel.patch b/target/linux/generic/backport-5.4/080-wireguard-0007-crypto-arm-chacha-import-Eric-Biggers-s-scalar-accel.patch new file mode 100644 index 0000000000..bf3ce3edaf --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0007-crypto-arm-chacha-import-Eric-Biggers-s-scalar-accel.patch @@ -0,0 +1,480 @@ +From 140ec1877054d2fe67538541b94b4967c0219ff4 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:13 +0100 +Subject: [PATCH 007/124] crypto: arm/chacha - import Eric Biggers's scalar + accelerated ChaCha code + +commit 29621d099f9c642b22a69dc8e7e20c108473a392 upstream. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/chacha-scalar-core.S | 461 +++++++++++++++++++++++++++ + 1 file changed, 461 insertions(+) + create mode 100644 arch/arm/crypto/chacha-scalar-core.S + +--- /dev/null ++++ b/arch/arm/crypto/chacha-scalar-core.S +@@ -0,0 +1,461 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2018 Google, Inc. ++ */ ++ ++#include ++#include ++ ++/* ++ * 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 ++ ++.Lexpand_32byte_k: ++ // "expand 32-byte k" ++ .word 0x61707865, 0x3320646e, 0x79622d32, 0x6b206574 ++ ++#ifdef __thumb2__ ++# define adrl adr ++#endif ++ ++.macro __rev out, in, t0, t1, t2 ++.if __LINUX_ARM_ARCH__ >= 6 ++ rev \out, \in ++.else ++ lsl \t0, \in, #24 ++ and \t1, \in, #0xff00 ++ and \t2, \in, #0xff0000 ++ orr \out, \t0, \in, lsr #24 ++ orr \out, \out, \t1, lsl #8 ++ orr \out, \out, \t2, lsr #8 ++.endif ++.endm ++ ++.macro _le32_bswap x, t0, t1, t2 ++#ifdef __ARMEB__ ++ __rev \x, \x, \t0, \t1, \t2 ++#endif ++.endm ++ ++.macro _le32_bswap_4x a, b, c, d, t0, t1, t2 ++ _le32_bswap \a, \t0, \t1, \t2 ++ _le32_bswap \b, \t0, \t1, \t2 ++ _le32_bswap \c, \t0, \t1, \t2 ++ _le32_bswap \d, \t0, \t1, \t2 ++.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, r9, r10 ++ 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, r9, r10 ++ 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, r9, r10 ++ 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, r10, r11 ++ 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, r9, r10 ++ 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, r9, r10 ++ 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, r9, r10 ++ 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, r10, r11 ++ 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 chacha20_arm(u8 *out, const u8 *in, size_t len, const u32 key[8], ++ * const u32 iv[4]); ++ */ ++ENTRY(chacha20_arm) ++ cmp r2, #0 // len == 0? ++ reteq lr ++ ++ push {r0-r2,r4-r11,lr} ++ ++ // Push state x0-x15 onto stack. ++ // Also store an extra copy of x10-x11 just before the state. ++ ++ ldr r4, [sp, #48] // iv ++ mov r0, sp ++ sub sp, #80 ++ ++ // iv: x12-x15 ++ ldm r4, {X12,X13,X14,X15} ++ stmdb r0!, {X12,X13,X14,X15} ++ ++ // key: x4-x11 ++ __ldrd X8_X10, X9_X11, r3, 24 ++ __strd X8_X10, X9_X11, sp, 8 ++ stmdb r0!, {X8_X10, X9_X11} ++ ldm r3, {X4-X9_X11} ++ stmdb r0!, {X4-X9_X11} ++ ++ // constants: x0-x3 ++ adrl X3, .Lexpand_32byte_k ++ ldm X3, {X0-X3} ++ __strd X0, X1, sp, 16 ++ __strd X2, X3, sp, 24 ++ ++ _chacha 20 ++ ++ add sp, #76 ++ pop {r4-r11, pc} ++ENDPROC(chacha20_arm) ++ ++/* ++ * void hchacha20_arm(const u32 state[16], u32 out[8]); ++ */ ++ENTRY(hchacha20_arm) ++ push {r1,r4-r11,lr} ++ ++ 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 ++ ++ _chacha_permute 20 ++ ++ // Skip over (unused0-unused1, x10-x11) ++ 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} ++ENDPROC(hchacha20_arm) diff --git a/target/linux/generic/backport-5.4/080-wireguard-0008-crypto-arm-chacha-remove-dependency-on-generic-ChaCh.patch b/target/linux/generic/backport-5.4/080-wireguard-0008-crypto-arm-chacha-remove-dependency-on-generic-ChaCh.patch new file mode 100644 index 0000000000..7f907f2364 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0008-crypto-arm-chacha-remove-dependency-on-generic-ChaCh.patch @@ -0,0 +1,691 @@ +From a92bd97c758d32511f0deeef84f25c3a1d5e7879 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:14 +0100 +Subject: [PATCH 008/124] crypto: arm/chacha - remove dependency on generic + ChaCha driver + +commit b36d8c09e710c71f6a9690b6586fea2d1c9e1e27 upstream. + +Instead of falling back to the generic ChaCha skcipher driver for +non-SIMD cases, use a fast scalar implementation for ARM authored +by Eric Biggers. This removes the module dependency on chacha-generic +altogether, which also simplifies things when we expose the ChaCha +library interface from this module. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/Kconfig | 4 +- + arch/arm/crypto/Makefile | 3 +- + arch/arm/crypto/chacha-glue.c | 304 +++++++++++++++++++++++++++ + arch/arm/crypto/chacha-neon-glue.c | 202 ------------------ + arch/arm/crypto/chacha-scalar-core.S | 65 +++--- + arch/arm64/crypto/chacha-neon-glue.c | 2 +- + 6 files changed, 340 insertions(+), 240 deletions(-) + create mode 100644 arch/arm/crypto/chacha-glue.c + delete mode 100644 arch/arm/crypto/chacha-neon-glue.c + +--- a/arch/arm/crypto/Kconfig ++++ b/arch/arm/crypto/Kconfig +@@ -127,10 +127,8 @@ config CRYPTO_CRC32_ARM_CE + select CRYPTO_HASH + + config CRYPTO_CHACHA20_NEON +- tristate "NEON accelerated ChaCha stream cipher algorithms" +- depends on KERNEL_MODE_NEON ++ tristate "NEON and scalar accelerated ChaCha stream cipher algorithms" + select CRYPTO_BLKCIPHER +- select CRYPTO_CHACHA20 + + config CRYPTO_NHPOLY1305_NEON + tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)" +--- a/arch/arm/crypto/Makefile ++++ b/arch/arm/crypto/Makefile +@@ -53,7 +53,8 @@ aes-arm-ce-y := aes-ce-core.o aes-ce-glu + 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-neon-core.o chacha-neon-glue.o ++chacha-neon-y := chacha-scalar-core.o chacha-glue.o ++chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o + nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o + + ifdef REGENERATE_ARM_CRYPTO +--- /dev/null ++++ b/arch/arm/crypto/chacha-glue.c +@@ -0,0 +1,304 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * ARM NEON accelerated ChaCha and XChaCha stream ciphers, ++ * including ChaCha20 (RFC7539) ++ * ++ * Copyright (C) 2016-2019 Linaro, Ltd. ++ * Copyright (C) 2015 Martin Willi ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include ++#include ++#include ++#include ++ ++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); ++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 inline bool neon_usable(void) ++{ ++ return 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 * 4) { ++ chacha_4block_xor_neon(state, dst, src, nrounds); ++ bytes -= CHACHA_BLOCK_SIZE * 4; ++ src += CHACHA_BLOCK_SIZE * 4; ++ dst += CHACHA_BLOCK_SIZE * 4; ++ state[12] += 4; ++ } ++ while (bytes >= CHACHA_BLOCK_SIZE) { ++ chacha_block_xor_neon(state, dst, src, nrounds); ++ bytes -= CHACHA_BLOCK_SIZE; ++ src += CHACHA_BLOCK_SIZE; ++ dst += CHACHA_BLOCK_SIZE; ++ state[12]++; ++ } ++ if (bytes) { ++ memcpy(buf, src, bytes); ++ chacha_block_xor_neon(state, buf, buf, nrounds); ++ memcpy(dst, buf, bytes); ++ } ++} ++ ++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 (!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 (!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; ++ ++ 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; ++ } ++ ++ 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) ++{ ++ 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 "); ++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 +--- a/arch/arm/crypto/chacha-neon-glue.c ++++ /dev/null +@@ -1,202 +0,0 @@ +-/* +- * ARM NEON accelerated ChaCha and XChaCha stream ciphers, +- * including ChaCha20 (RFC7539) +- * +- * Copyright (C) 2016 Linaro, Ltd. +- * +- * 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, SIMD glue code +- * +- * 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. +- */ +- +-#include +-#include +-#include +-#include +-#include +-#include +- +-#include +-#include +-#include +- +-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); +-asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds); +- +-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 * 4) { +- chacha_4block_xor_neon(state, dst, src, nrounds); +- bytes -= CHACHA_BLOCK_SIZE * 4; +- src += CHACHA_BLOCK_SIZE * 4; +- dst += CHACHA_BLOCK_SIZE * 4; +- state[12] += 4; +- } +- while (bytes >= CHACHA_BLOCK_SIZE) { +- chacha_block_xor_neon(state, dst, src, nrounds); +- bytes -= CHACHA_BLOCK_SIZE; +- src += CHACHA_BLOCK_SIZE; +- dst += CHACHA_BLOCK_SIZE; +- state[12]++; +- } +- if (bytes) { +- memcpy(buf, src, bytes); +- chacha_block_xor_neon(state, buf, buf, nrounds); +- memcpy(dst, buf, bytes); +- } +-} +- +-static int chacha_neon_stream_xor(struct skcipher_request *req, +- const struct chacha_ctx *ctx, const u8 *iv) +-{ +- struct skcipher_walk walk; +- u32 state[16]; +- int err; +- +- err = skcipher_walk_virt(&walk, req, false); +- +- crypto_chacha_init(state, ctx, iv); +- +- while (walk.nbytes > 0) { +- unsigned int nbytes = walk.nbytes; +- +- if (nbytes < walk.total) +- nbytes = round_down(nbytes, walk.stride); +- +- 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 chacha_neon(struct skcipher_request *req) +-{ +- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); +- struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); +- +- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) +- return crypto_chacha_crypt(req); +- +- return chacha_neon_stream_xor(req, ctx, req->iv); +-} +- +-static int xchacha_neon(struct skcipher_request *req) +-{ +- 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]; +- +- if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable()) +- return crypto_xchacha_crypt(req); +- +- crypto_chacha_init(state, ctx, req->iv); +- +- 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_neon_stream_xor(req, &subctx, real_iv); +-} +- +-static struct skcipher_alg 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 = crypto_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 = crypto_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 = crypto_chacha12_setkey, +- .encrypt = xchacha_neon, +- .decrypt = xchacha_neon, +- } +-}; +- +-static int __init chacha_simd_mod_init(void) +-{ +- if (!(elf_hwcap & HWCAP_NEON)) +- return -ENODEV; +- +- return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); +-} +- +-static void __exit chacha_simd_mod_fini(void) +-{ +- crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); +-} +- +-module_init(chacha_simd_mod_init); +-module_exit(chacha_simd_mod_fini); +- +-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)"); +-MODULE_AUTHOR("Ard Biesheuvel "); +-MODULE_LICENSE("GPL v2"); +-MODULE_ALIAS_CRYPTO("chacha20"); +-MODULE_ALIAS_CRYPTO("chacha20-neon"); +-MODULE_ALIAS_CRYPTO("xchacha20"); +-MODULE_ALIAS_CRYPTO("xchacha20-neon"); +-MODULE_ALIAS_CRYPTO("xchacha12"); +-MODULE_ALIAS_CRYPTO("xchacha12-neon"); +--- a/arch/arm/crypto/chacha-scalar-core.S ++++ b/arch/arm/crypto/chacha-scalar-core.S +@@ -41,14 +41,6 @@ + X14 .req r12 + X15 .req r14 + +-.Lexpand_32byte_k: +- // "expand 32-byte k" +- .word 0x61707865, 0x3320646e, 0x79622d32, 0x6b206574 +- +-#ifdef __thumb2__ +-# define adrl adr +-#endif +- + .macro __rev out, in, t0, t1, t2 + .if __LINUX_ARM_ARCH__ >= 6 + rev \out, \in +@@ -391,61 +383,65 @@ + .endm // _chacha + + /* +- * void chacha20_arm(u8 *out, const u8 *in, size_t len, const u32 key[8], +- * const u32 iv[4]); ++ * void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes, ++ * const u32 *state, int nrounds); + */ +-ENTRY(chacha20_arm) ++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. + +- ldr r4, [sp, #48] // iv +- mov r0, sp +- sub sp, #80 +- +- // iv: x12-x15 +- ldm r4, {X12,X13,X14,X15} +- stmdb r0!, {X12,X13,X14,X15} ++ add X12, r3, #48 ++ ldm X12, {X12,X13,X14,X15} ++ push {X12,X13,X14,X15} ++ sub sp, sp, #64 + +- // key: x4-x11 +- __ldrd X8_X10, X9_X11, r3, 24 ++ __ldrd X8_X10, X9_X11, r3, 40 + __strd X8_X10, X9_X11, sp, 8 +- stmdb r0!, {X8_X10, X9_X11} +- ldm r3, {X4-X9_X11} +- stmdb r0!, {X4-X9_X11} +- +- // constants: x0-x3 +- adrl X3, .Lexpand_32byte_k +- ldm X3, {X0-X3} ++ __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 + +- add sp, #76 ++0: add sp, #76 + pop {r4-r11, pc} +-ENDPROC(chacha20_arm) ++ ++1: _chacha 12 ++ b 0b ++ENDPROC(chacha_doarm) + + /* +- * void hchacha20_arm(const u32 state[16], u32 out[8]); ++ * void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds); + */ +-ENTRY(hchacha20_arm) ++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) +- add sp, #16 ++0: add sp, #16 + + // Fix up rotations of x12-x15 + ror X12, X12, #drot +@@ -458,4 +454,7 @@ ENTRY(hchacha20_arm) + stm r4, {X0,X1,X2,X3,X12,X13,X14,X15} + + pop {r4-r11,pc} +-ENDPROC(hchacha20_arm) ++ ++1: _chacha_permute 12 ++ b 0b ++ENDPROC(hchacha_block_arm) +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -1,5 +1,5 @@ + /* +- * ARM NEON accelerated ChaCha and XChaCha stream ciphers, ++ * ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers, + * including ChaCha20 (RFC7539) + * + * Copyright (C) 2016 - 2017 Linaro, Ltd. diff --git a/target/linux/generic/backport-5.4/080-wireguard-0009-crypto-arm-chacha-expose-ARM-ChaCha-routine-as-libra.patch b/target/linux/generic/backport-5.4/080-wireguard-0009-crypto-arm-chacha-expose-ARM-ChaCha-routine-as-libra.patch new file mode 100644 index 0000000000..072b50b498 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0009-crypto-arm-chacha-expose-ARM-ChaCha-routine-as-libra.patch @@ -0,0 +1,108 @@ +From 360be1a8f326ec5c0d20a134e228fb96a2eb351d Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:15 +0100 +Subject: [PATCH 009/124] crypto: arm/chacha - expose ARM ChaCha routine as + library function + +commit a44a3430d71bad4ee56788a59fff099b291ea54c upstream. + +Expose the accelerated NEON ChaCha routine directly as a symbol +export so that users of the ChaCha library API can use it directly. + +Given that calls into the library API will always go through the +routines in this module if it is enabled, switch to static keys +to select the optimal implementation available (which may be none +at all, in which case we defer to the generic implementation for +all invocations). + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/Kconfig | 1 + + arch/arm/crypto/chacha-glue.c | 41 ++++++++++++++++++++++++++++++++++- + 2 files changed, 41 insertions(+), 1 deletion(-) + +--- a/arch/arm/crypto/Kconfig ++++ b/arch/arm/crypto/Kconfig +@@ -129,6 +129,7 @@ config CRYPTO_CRC32_ARM_CE + config CRYPTO_CHACHA20_NEON + tristate "NEON and scalar accelerated ChaCha stream cipher algorithms" + select CRYPTO_BLKCIPHER ++ select CRYPTO_ARCH_HAVE_LIB_CHACHA + + config CRYPTO_NHPOLY1305_NEON + tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)" +--- a/arch/arm/crypto/chacha-glue.c ++++ b/arch/arm/crypto/chacha-glue.c +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -29,9 +30,11 @@ asmlinkage void hchacha_block_neon(const + 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 crypto_simd_usable(); ++ return static_branch_likely(&use_neon) && crypto_simd_usable(); + } + + static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, +@@ -60,6 +63,40 @@ static void chacha_doneon(u32 *state, u8 + } + } + ++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; ++ } ++ ++ kernel_neon_begin(); ++ chacha_doneon(state, dst, src, bytes, nrounds); ++ kernel_neon_end(); ++} ++EXPORT_SYMBOL(chacha_crypt_arch); ++ + static int chacha_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv, + bool neon) +@@ -269,6 +306,8 @@ static int __init chacha_simd_mod_init(v + for (i = 0; i < ARRAY_SIZE(neon_algs); i++) + neon_algs[i].base.cra_priority = 0; + break; ++ default: ++ static_branch_enable(&use_neon); + } + + err = crypto_register_skciphers(neon_algs, ARRAY_SIZE(neon_algs)); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0010-crypto-mips-chacha-import-32r2-ChaCha-code-from-Zinc.patch b/target/linux/generic/backport-5.4/080-wireguard-0010-crypto-mips-chacha-import-32r2-ChaCha-code-from-Zinc.patch new file mode 100644 index 0000000000..e6fb4d9dc9 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0010-crypto-mips-chacha-import-32r2-ChaCha-code-from-Zinc.patch @@ -0,0 +1,452 @@ +From f9b4c68865fdb7f3327f7d82fbc82c76c8773d53 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:16 +0100 +Subject: [PATCH 010/124] crypto: mips/chacha - import 32r2 ChaCha code from + Zinc +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit 49aa7c00eddf8d8f462b0256bd82e81762d7b0c6 upstream. + +This imports the accelerated MIPS 32r2 ChaCha20 implementation from the +Zinc patch set. + +Co-developed-by: René van Dorst +Signed-off-by: René van Dorst +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/mips/crypto/chacha-core.S | 424 +++++++++++++++++++++++++++++++++ + 1 file changed, 424 insertions(+) + create mode 100644 arch/mips/crypto/chacha-core.S + +--- /dev/null ++++ b/arch/mips/crypto/chacha-core.S +@@ -0,0 +1,424 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ ++/* ++ * Copyright (C) 2016-2018 René van Dorst . All Rights Reserved. ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#define MASK_U32 0x3c ++#define CHACHA20_BLOCK_SIZE 64 ++#define STACK_SIZE 32 ++ ++#define X0 $t0 ++#define X1 $t1 ++#define X2 $t2 ++#define X3 $t3 ++#define X4 $t4 ++#define X5 $t5 ++#define X6 $t6 ++#define X7 $t7 ++#define X8 $t8 ++#define X9 $t9 ++#define X10 $v1 ++#define X11 $s6 ++#define X12 $s5 ++#define X13 $s4 ++#define X14 $s3 ++#define X15 $s2 ++/* Use regs which are overwritten on exit for Tx so we don't leak clear data. */ ++#define T0 $s1 ++#define T1 $s0 ++#define T(n) T ## n ++#define X(n) X ## n ++ ++/* Input arguments */ ++#define STATE $a0 ++#define OUT $a1 ++#define IN $a2 ++#define BYTES $a3 ++ ++/* Output argument */ ++/* NONCE[0] is kept in a register and not in memory. ++ * We don't want to touch original value in memory. ++ * Must be incremented every loop iteration. ++ */ ++#define NONCE_0 $v0 ++ ++/* SAVED_X and SAVED_CA are set in the jump table. ++ * Use regs which are overwritten on exit else we don't leak clear data. ++ * They are used to handling the last bytes which are not multiple of 4. ++ */ ++#define SAVED_X X15 ++#define SAVED_CA $s7 ++ ++#define IS_UNALIGNED $s7 ++ ++#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ ++#define MSB 0 ++#define LSB 3 ++#define ROTx rotl ++#define ROTR(n) rotr n, 24 ++#define CPU_TO_LE32(n) \ ++ wsbh n; \ ++ rotr n, 16; ++#else ++#define MSB 3 ++#define LSB 0 ++#define ROTx rotr ++#define CPU_TO_LE32(n) ++#define ROTR(n) ++#endif ++ ++#define FOR_EACH_WORD(x) \ ++ x( 0); \ ++ x( 1); \ ++ x( 2); \ ++ x( 3); \ ++ x( 4); \ ++ x( 5); \ ++ x( 6); \ ++ x( 7); \ ++ x( 8); \ ++ x( 9); \ ++ x(10); \ ++ x(11); \ ++ x(12); \ ++ x(13); \ ++ x(14); \ ++ x(15); ++ ++#define FOR_EACH_WORD_REV(x) \ ++ x(15); \ ++ x(14); \ ++ x(13); \ ++ x(12); \ ++ x(11); \ ++ x(10); \ ++ x( 9); \ ++ x( 8); \ ++ x( 7); \ ++ x( 6); \ ++ x( 5); \ ++ x( 4); \ ++ x( 3); \ ++ x( 2); \ ++ x( 1); \ ++ x( 0); ++ ++#define PLUS_ONE_0 1 ++#define PLUS_ONE_1 2 ++#define PLUS_ONE_2 3 ++#define PLUS_ONE_3 4 ++#define PLUS_ONE_4 5 ++#define PLUS_ONE_5 6 ++#define PLUS_ONE_6 7 ++#define PLUS_ONE_7 8 ++#define PLUS_ONE_8 9 ++#define PLUS_ONE_9 10 ++#define PLUS_ONE_10 11 ++#define PLUS_ONE_11 12 ++#define PLUS_ONE_12 13 ++#define PLUS_ONE_13 14 ++#define PLUS_ONE_14 15 ++#define PLUS_ONE_15 16 ++#define PLUS_ONE(x) PLUS_ONE_ ## x ++#define _CONCAT3(a,b,c) a ## b ## c ++#define CONCAT3(a,b,c) _CONCAT3(a,b,c) ++ ++#define STORE_UNALIGNED(x) \ ++CONCAT3(.Lchacha20_mips_xor_unaligned_, PLUS_ONE(x), _b: ;) \ ++ .if (x != 12); \ ++ lw T0, (x*4)(STATE); \ ++ .endif; \ ++ lwl T1, (x*4)+MSB ## (IN); \ ++ lwr T1, (x*4)+LSB ## (IN); \ ++ .if (x == 12); \ ++ addu X ## x, NONCE_0; \ ++ .else; \ ++ addu X ## x, T0; \ ++ .endif; \ ++ CPU_TO_LE32(X ## x); \ ++ xor X ## x, T1; \ ++ swl X ## x, (x*4)+MSB ## (OUT); \ ++ swr X ## x, (x*4)+LSB ## (OUT); ++ ++#define STORE_ALIGNED(x) \ ++CONCAT3(.Lchacha20_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \ ++ .if (x != 12); \ ++ lw T0, (x*4)(STATE); \ ++ .endif; \ ++ lw T1, (x*4) ## (IN); \ ++ .if (x == 12); \ ++ addu X ## x, NONCE_0; \ ++ .else; \ ++ addu X ## x, T0; \ ++ .endif; \ ++ CPU_TO_LE32(X ## x); \ ++ xor X ## x, T1; \ ++ sw X ## x, (x*4) ## (OUT); ++ ++/* Jump table macro. ++ * Used for setup and handling the last bytes, which are not multiple of 4. ++ * X15 is free to store Xn ++ * Every jumptable entry must be equal in size. ++ */ ++#define JMPTBL_ALIGNED(x) \ ++.Lchacha20_mips_jmptbl_aligned_ ## x: ; \ ++ .set noreorder; \ ++ b .Lchacha20_mips_xor_aligned_ ## x ## _b; \ ++ .if (x == 12); \ ++ addu SAVED_X, X ## x, NONCE_0; \ ++ .else; \ ++ addu SAVED_X, X ## x, SAVED_CA; \ ++ .endif; \ ++ .set reorder ++ ++#define JMPTBL_UNALIGNED(x) \ ++.Lchacha20_mips_jmptbl_unaligned_ ## x: ; \ ++ .set noreorder; \ ++ b .Lchacha20_mips_xor_unaligned_ ## x ## _b; \ ++ .if (x == 12); \ ++ addu SAVED_X, X ## x, NONCE_0; \ ++ .else; \ ++ addu SAVED_X, X ## x, SAVED_CA; \ ++ .endif; \ ++ .set reorder ++ ++#define AXR(A, B, C, D, K, L, M, N, V, W, Y, Z, S) \ ++ addu X(A), X(K); \ ++ addu X(B), X(L); \ ++ addu X(C), X(M); \ ++ addu X(D), X(N); \ ++ xor X(V), X(A); \ ++ xor X(W), X(B); \ ++ xor X(Y), X(C); \ ++ xor X(Z), X(D); \ ++ rotl X(V), S; \ ++ rotl X(W), S; \ ++ rotl X(Y), S; \ ++ rotl X(Z), S; ++ ++.text ++.set reorder ++.set noat ++.globl chacha20_mips ++.ent chacha20_mips ++chacha20_mips: ++ .frame $sp, STACK_SIZE, $ra ++ ++ addiu $sp, -STACK_SIZE ++ ++ /* Return bytes = 0. */ ++ beqz BYTES, .Lchacha20_mips_end ++ ++ lw NONCE_0, 48(STATE) ++ ++ /* Save s0-s7 */ ++ sw $s0, 0($sp) ++ sw $s1, 4($sp) ++ sw $s2, 8($sp) ++ sw $s3, 12($sp) ++ sw $s4, 16($sp) ++ sw $s5, 20($sp) ++ sw $s6, 24($sp) ++ sw $s7, 28($sp) ++ ++ /* Test IN or OUT is unaligned. ++ * IS_UNALIGNED = ( IN | OUT ) & 0x00000003 ++ */ ++ or IS_UNALIGNED, IN, OUT ++ andi IS_UNALIGNED, 0x3 ++ ++ /* Set number of rounds */ ++ li $at, 20 ++ ++ b .Lchacha20_rounds_start ++ ++.align 4 ++.Loop_chacha20_rounds: ++ addiu IN, CHACHA20_BLOCK_SIZE ++ addiu OUT, CHACHA20_BLOCK_SIZE ++ addiu NONCE_0, 1 ++ ++.Lchacha20_rounds_start: ++ lw X0, 0(STATE) ++ lw X1, 4(STATE) ++ lw X2, 8(STATE) ++ lw X3, 12(STATE) ++ ++ lw X4, 16(STATE) ++ lw X5, 20(STATE) ++ lw X6, 24(STATE) ++ lw X7, 28(STATE) ++ lw X8, 32(STATE) ++ lw X9, 36(STATE) ++ lw X10, 40(STATE) ++ lw X11, 44(STATE) ++ ++ move X12, NONCE_0 ++ lw X13, 52(STATE) ++ lw X14, 56(STATE) ++ lw X15, 60(STATE) ++ ++.Loop_chacha20_xor_rounds: ++ addiu $at, -2 ++ AXR( 0, 1, 2, 3, 4, 5, 6, 7, 12,13,14,15, 16); ++ AXR( 8, 9,10,11, 12,13,14,15, 4, 5, 6, 7, 12); ++ AXR( 0, 1, 2, 3, 4, 5, 6, 7, 12,13,14,15, 8); ++ AXR( 8, 9,10,11, 12,13,14,15, 4, 5, 6, 7, 7); ++ AXR( 0, 1, 2, 3, 5, 6, 7, 4, 15,12,13,14, 16); ++ AXR(10,11, 8, 9, 15,12,13,14, 5, 6, 7, 4, 12); ++ AXR( 0, 1, 2, 3, 5, 6, 7, 4, 15,12,13,14, 8); ++ AXR(10,11, 8, 9, 15,12,13,14, 5, 6, 7, 4, 7); ++ bnez $at, .Loop_chacha20_xor_rounds ++ ++ addiu BYTES, -(CHACHA20_BLOCK_SIZE) ++ ++ /* Is data src/dst unaligned? Jump */ ++ bnez IS_UNALIGNED, .Loop_chacha20_unaligned ++ ++ /* Set number rounds here to fill delayslot. */ ++ li $at, 20 ++ ++ /* BYTES < 0, it has no full block. */ ++ bltz BYTES, .Lchacha20_mips_no_full_block_aligned ++ ++ FOR_EACH_WORD_REV(STORE_ALIGNED) ++ ++ /* BYTES > 0? Loop again. */ ++ bgtz BYTES, .Loop_chacha20_rounds ++ ++ /* Place this here to fill delay slot */ ++ addiu NONCE_0, 1 ++ ++ /* BYTES < 0? Handle last bytes */ ++ bltz BYTES, .Lchacha20_mips_xor_bytes ++ ++.Lchacha20_mips_xor_done: ++ /* Restore used registers */ ++ lw $s0, 0($sp) ++ lw $s1, 4($sp) ++ lw $s2, 8($sp) ++ lw $s3, 12($sp) ++ lw $s4, 16($sp) ++ lw $s5, 20($sp) ++ lw $s6, 24($sp) ++ lw $s7, 28($sp) ++ ++ /* Write NONCE_0 back to right location in state */ ++ sw NONCE_0, 48(STATE) ++ ++.Lchacha20_mips_end: ++ addiu $sp, STACK_SIZE ++ jr $ra ++ ++.Lchacha20_mips_no_full_block_aligned: ++ /* Restore the offset on BYTES */ ++ addiu BYTES, CHACHA20_BLOCK_SIZE ++ ++ /* Get number of full WORDS */ ++ andi $at, BYTES, MASK_U32 ++ ++ /* Load upper half of jump table addr */ ++ lui T0, %hi(.Lchacha20_mips_jmptbl_aligned_0) ++ ++ /* Calculate lower half jump table offset */ ++ ins T0, $at, 1, 6 ++ ++ /* Add offset to STATE */ ++ addu T1, STATE, $at ++ ++ /* Add lower half jump table addr */ ++ addiu T0, %lo(.Lchacha20_mips_jmptbl_aligned_0) ++ ++ /* Read value from STATE */ ++ lw SAVED_CA, 0(T1) ++ ++ /* Store remaining bytecounter as negative value */ ++ subu BYTES, $at, BYTES ++ ++ jr T0 ++ ++ /* Jump table */ ++ FOR_EACH_WORD(JMPTBL_ALIGNED) ++ ++ ++.Loop_chacha20_unaligned: ++ /* Set number rounds here to fill delayslot. */ ++ li $at, 20 ++ ++ /* BYTES > 0, it has no full block. */ ++ bltz BYTES, .Lchacha20_mips_no_full_block_unaligned ++ ++ FOR_EACH_WORD_REV(STORE_UNALIGNED) ++ ++ /* BYTES > 0? Loop again. */ ++ bgtz BYTES, .Loop_chacha20_rounds ++ ++ /* Write NONCE_0 back to right location in state */ ++ sw NONCE_0, 48(STATE) ++ ++ .set noreorder ++ /* Fall through to byte handling */ ++ bgez BYTES, .Lchacha20_mips_xor_done ++.Lchacha20_mips_xor_unaligned_0_b: ++.Lchacha20_mips_xor_aligned_0_b: ++ /* Place this here to fill delay slot */ ++ addiu NONCE_0, 1 ++ .set reorder ++ ++.Lchacha20_mips_xor_bytes: ++ addu IN, $at ++ addu OUT, $at ++ /* First byte */ ++ lbu T1, 0(IN) ++ addiu $at, BYTES, 1 ++ CPU_TO_LE32(SAVED_X) ++ ROTR(SAVED_X) ++ xor T1, SAVED_X ++ sb T1, 0(OUT) ++ beqz $at, .Lchacha20_mips_xor_done ++ /* Second byte */ ++ lbu T1, 1(IN) ++ addiu $at, BYTES, 2 ++ ROTx SAVED_X, 8 ++ xor T1, SAVED_X ++ sb T1, 1(OUT) ++ beqz $at, .Lchacha20_mips_xor_done ++ /* Third byte */ ++ lbu T1, 2(IN) ++ ROTx SAVED_X, 8 ++ xor T1, SAVED_X ++ sb T1, 2(OUT) ++ b .Lchacha20_mips_xor_done ++ ++.Lchacha20_mips_no_full_block_unaligned: ++ /* Restore the offset on BYTES */ ++ addiu BYTES, CHACHA20_BLOCK_SIZE ++ ++ /* Get number of full WORDS */ ++ andi $at, BYTES, MASK_U32 ++ ++ /* Load upper half of jump table addr */ ++ lui T0, %hi(.Lchacha20_mips_jmptbl_unaligned_0) ++ ++ /* Calculate lower half jump table offset */ ++ ins T0, $at, 1, 6 ++ ++ /* Add offset to STATE */ ++ addu T1, STATE, $at ++ ++ /* Add lower half jump table addr */ ++ addiu T0, %lo(.Lchacha20_mips_jmptbl_unaligned_0) ++ ++ /* Read value from STATE */ ++ lw SAVED_CA, 0(T1) ++ ++ /* Store remaining bytecounter as negative value */ ++ subu BYTES, $at, BYTES ++ ++ jr T0 ++ ++ /* Jump table */ ++ FOR_EACH_WORD(JMPTBL_UNALIGNED) ++.end chacha20_mips ++.set at diff --git a/target/linux/generic/backport-5.4/080-wireguard-0011-crypto-mips-chacha-wire-up-accelerated-32r2-code-fro.patch b/target/linux/generic/backport-5.4/080-wireguard-0011-crypto-mips-chacha-wire-up-accelerated-32r2-code-fro.patch new file mode 100644 index 0000000000..1abfc29fc7 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0011-crypto-mips-chacha-wire-up-accelerated-32r2-code-fro.patch @@ -0,0 +1,560 @@ +From 01c1104f551dae77125bb3d0f461f4084f2a98df Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:17 +0100 +Subject: [PATCH 011/124] crypto: mips/chacha - wire up accelerated 32r2 code + from Zinc +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit 3a2f58f3ba4f6f44e33d1a48240d5eadb882cb59 upstream. + +This integrates the accelerated MIPS 32r2 implementation of ChaCha +into both the API and library interfaces of the kernel crypto stack. + +The significance of this is that, in addition to becoming available +as an accelerated library implementation, it can also be used by +existing crypto API code such as Adiantum (for block encryption on +ultra low performance cores) or IPsec using chacha20poly1305. These +are use cases that have already opted into using the abstract crypto +API. In order to support Adiantum, the core assembler routine has +been adapted to take the round count as a function argument rather +than hardcoding it to 20. + +Co-developed-by: René van Dorst +Signed-off-by: René van Dorst +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/mips/Makefile | 2 +- + arch/mips/crypto/Makefile | 4 + + arch/mips/crypto/chacha-core.S | 159 ++++++++++++++++++++++++--------- + arch/mips/crypto/chacha-glue.c | 150 +++++++++++++++++++++++++++++++ + crypto/Kconfig | 6 ++ + 5 files changed, 277 insertions(+), 44 deletions(-) + create mode 100644 arch/mips/crypto/chacha-glue.c + +--- a/arch/mips/Makefile ++++ b/arch/mips/Makefile +@@ -334,7 +334,7 @@ libs-$(CONFIG_MIPS_FP_SUPPORT) += arch/m + # See arch/mips/Kbuild for content of core part of the kernel + core-y += arch/mips/ + +-drivers-$(CONFIG_MIPS_CRC_SUPPORT) += arch/mips/crypto/ ++drivers-y += arch/mips/crypto/ + drivers-$(CONFIG_OPROFILE) += arch/mips/oprofile/ + + # suspend and hibernation support +--- a/arch/mips/crypto/Makefile ++++ b/arch/mips/crypto/Makefile +@@ -4,3 +4,7 @@ + # + + obj-$(CONFIG_CRYPTO_CRC32_MIPS) += crc32-mips.o ++ ++obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o ++chacha-mips-y := chacha-core.o chacha-glue.o ++AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots +--- a/arch/mips/crypto/chacha-core.S ++++ b/arch/mips/crypto/chacha-core.S +@@ -125,7 +125,7 @@ + #define CONCAT3(a,b,c) _CONCAT3(a,b,c) + + #define STORE_UNALIGNED(x) \ +-CONCAT3(.Lchacha20_mips_xor_unaligned_, PLUS_ONE(x), _b: ;) \ ++CONCAT3(.Lchacha_mips_xor_unaligned_, PLUS_ONE(x), _b: ;) \ + .if (x != 12); \ + lw T0, (x*4)(STATE); \ + .endif; \ +@@ -142,7 +142,7 @@ CONCAT3(.Lchacha20_mips_xor_unaligned_, + swr X ## x, (x*4)+LSB ## (OUT); + + #define STORE_ALIGNED(x) \ +-CONCAT3(.Lchacha20_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \ ++CONCAT3(.Lchacha_mips_xor_aligned_, PLUS_ONE(x), _b: ;) \ + .if (x != 12); \ + lw T0, (x*4)(STATE); \ + .endif; \ +@@ -162,9 +162,9 @@ CONCAT3(.Lchacha20_mips_xor_aligned_, PL + * Every jumptable entry must be equal in size. + */ + #define JMPTBL_ALIGNED(x) \ +-.Lchacha20_mips_jmptbl_aligned_ ## x: ; \ ++.Lchacha_mips_jmptbl_aligned_ ## x: ; \ + .set noreorder; \ +- b .Lchacha20_mips_xor_aligned_ ## x ## _b; \ ++ b .Lchacha_mips_xor_aligned_ ## x ## _b; \ + .if (x == 12); \ + addu SAVED_X, X ## x, NONCE_0; \ + .else; \ +@@ -173,9 +173,9 @@ CONCAT3(.Lchacha20_mips_xor_aligned_, PL + .set reorder + + #define JMPTBL_UNALIGNED(x) \ +-.Lchacha20_mips_jmptbl_unaligned_ ## x: ; \ ++.Lchacha_mips_jmptbl_unaligned_ ## x: ; \ + .set noreorder; \ +- b .Lchacha20_mips_xor_unaligned_ ## x ## _b; \ ++ b .Lchacha_mips_xor_unaligned_ ## x ## _b; \ + .if (x == 12); \ + addu SAVED_X, X ## x, NONCE_0; \ + .else; \ +@@ -200,15 +200,18 @@ CONCAT3(.Lchacha20_mips_xor_aligned_, PL + .text + .set reorder + .set noat +-.globl chacha20_mips +-.ent chacha20_mips +-chacha20_mips: ++.globl chacha_crypt_arch ++.ent chacha_crypt_arch ++chacha_crypt_arch: + .frame $sp, STACK_SIZE, $ra + ++ /* Load number of rounds */ ++ lw $at, 16($sp) ++ + addiu $sp, -STACK_SIZE + + /* Return bytes = 0. */ +- beqz BYTES, .Lchacha20_mips_end ++ beqz BYTES, .Lchacha_mips_end + + lw NONCE_0, 48(STATE) + +@@ -228,18 +231,15 @@ chacha20_mips: + or IS_UNALIGNED, IN, OUT + andi IS_UNALIGNED, 0x3 + +- /* Set number of rounds */ +- li $at, 20 +- +- b .Lchacha20_rounds_start ++ b .Lchacha_rounds_start + + .align 4 +-.Loop_chacha20_rounds: ++.Loop_chacha_rounds: + addiu IN, CHACHA20_BLOCK_SIZE + addiu OUT, CHACHA20_BLOCK_SIZE + addiu NONCE_0, 1 + +-.Lchacha20_rounds_start: ++.Lchacha_rounds_start: + lw X0, 0(STATE) + lw X1, 4(STATE) + lw X2, 8(STATE) +@@ -259,7 +259,7 @@ chacha20_mips: + lw X14, 56(STATE) + lw X15, 60(STATE) + +-.Loop_chacha20_xor_rounds: ++.Loop_chacha_xor_rounds: + addiu $at, -2 + AXR( 0, 1, 2, 3, 4, 5, 6, 7, 12,13,14,15, 16); + AXR( 8, 9,10,11, 12,13,14,15, 4, 5, 6, 7, 12); +@@ -269,31 +269,31 @@ chacha20_mips: + AXR(10,11, 8, 9, 15,12,13,14, 5, 6, 7, 4, 12); + AXR( 0, 1, 2, 3, 5, 6, 7, 4, 15,12,13,14, 8); + AXR(10,11, 8, 9, 15,12,13,14, 5, 6, 7, 4, 7); +- bnez $at, .Loop_chacha20_xor_rounds ++ bnez $at, .Loop_chacha_xor_rounds + + addiu BYTES, -(CHACHA20_BLOCK_SIZE) + + /* Is data src/dst unaligned? Jump */ +- bnez IS_UNALIGNED, .Loop_chacha20_unaligned ++ bnez IS_UNALIGNED, .Loop_chacha_unaligned + + /* Set number rounds here to fill delayslot. */ +- li $at, 20 ++ lw $at, (STACK_SIZE+16)($sp) + + /* BYTES < 0, it has no full block. */ +- bltz BYTES, .Lchacha20_mips_no_full_block_aligned ++ bltz BYTES, .Lchacha_mips_no_full_block_aligned + + FOR_EACH_WORD_REV(STORE_ALIGNED) + + /* BYTES > 0? Loop again. */ +- bgtz BYTES, .Loop_chacha20_rounds ++ bgtz BYTES, .Loop_chacha_rounds + + /* Place this here to fill delay slot */ + addiu NONCE_0, 1 + + /* BYTES < 0? Handle last bytes */ +- bltz BYTES, .Lchacha20_mips_xor_bytes ++ bltz BYTES, .Lchacha_mips_xor_bytes + +-.Lchacha20_mips_xor_done: ++.Lchacha_mips_xor_done: + /* Restore used registers */ + lw $s0, 0($sp) + lw $s1, 4($sp) +@@ -307,11 +307,11 @@ chacha20_mips: + /* Write NONCE_0 back to right location in state */ + sw NONCE_0, 48(STATE) + +-.Lchacha20_mips_end: ++.Lchacha_mips_end: + addiu $sp, STACK_SIZE + jr $ra + +-.Lchacha20_mips_no_full_block_aligned: ++.Lchacha_mips_no_full_block_aligned: + /* Restore the offset on BYTES */ + addiu BYTES, CHACHA20_BLOCK_SIZE + +@@ -319,7 +319,7 @@ chacha20_mips: + andi $at, BYTES, MASK_U32 + + /* Load upper half of jump table addr */ +- lui T0, %hi(.Lchacha20_mips_jmptbl_aligned_0) ++ lui T0, %hi(.Lchacha_mips_jmptbl_aligned_0) + + /* Calculate lower half jump table offset */ + ins T0, $at, 1, 6 +@@ -328,7 +328,7 @@ chacha20_mips: + addu T1, STATE, $at + + /* Add lower half jump table addr */ +- addiu T0, %lo(.Lchacha20_mips_jmptbl_aligned_0) ++ addiu T0, %lo(.Lchacha_mips_jmptbl_aligned_0) + + /* Read value from STATE */ + lw SAVED_CA, 0(T1) +@@ -342,31 +342,31 @@ chacha20_mips: + FOR_EACH_WORD(JMPTBL_ALIGNED) + + +-.Loop_chacha20_unaligned: ++.Loop_chacha_unaligned: + /* Set number rounds here to fill delayslot. */ +- li $at, 20 ++ lw $at, (STACK_SIZE+16)($sp) + + /* BYTES > 0, it has no full block. */ +- bltz BYTES, .Lchacha20_mips_no_full_block_unaligned ++ bltz BYTES, .Lchacha_mips_no_full_block_unaligned + + FOR_EACH_WORD_REV(STORE_UNALIGNED) + + /* BYTES > 0? Loop again. */ +- bgtz BYTES, .Loop_chacha20_rounds ++ bgtz BYTES, .Loop_chacha_rounds + + /* Write NONCE_0 back to right location in state */ + sw NONCE_0, 48(STATE) + + .set noreorder + /* Fall through to byte handling */ +- bgez BYTES, .Lchacha20_mips_xor_done +-.Lchacha20_mips_xor_unaligned_0_b: +-.Lchacha20_mips_xor_aligned_0_b: ++ bgez BYTES, .Lchacha_mips_xor_done ++.Lchacha_mips_xor_unaligned_0_b: ++.Lchacha_mips_xor_aligned_0_b: + /* Place this here to fill delay slot */ + addiu NONCE_0, 1 + .set reorder + +-.Lchacha20_mips_xor_bytes: ++.Lchacha_mips_xor_bytes: + addu IN, $at + addu OUT, $at + /* First byte */ +@@ -376,22 +376,22 @@ chacha20_mips: + ROTR(SAVED_X) + xor T1, SAVED_X + sb T1, 0(OUT) +- beqz $at, .Lchacha20_mips_xor_done ++ beqz $at, .Lchacha_mips_xor_done + /* Second byte */ + lbu T1, 1(IN) + addiu $at, BYTES, 2 + ROTx SAVED_X, 8 + xor T1, SAVED_X + sb T1, 1(OUT) +- beqz $at, .Lchacha20_mips_xor_done ++ beqz $at, .Lchacha_mips_xor_done + /* Third byte */ + lbu T1, 2(IN) + ROTx SAVED_X, 8 + xor T1, SAVED_X + sb T1, 2(OUT) +- b .Lchacha20_mips_xor_done ++ b .Lchacha_mips_xor_done + +-.Lchacha20_mips_no_full_block_unaligned: ++.Lchacha_mips_no_full_block_unaligned: + /* Restore the offset on BYTES */ + addiu BYTES, CHACHA20_BLOCK_SIZE + +@@ -399,7 +399,7 @@ chacha20_mips: + andi $at, BYTES, MASK_U32 + + /* Load upper half of jump table addr */ +- lui T0, %hi(.Lchacha20_mips_jmptbl_unaligned_0) ++ lui T0, %hi(.Lchacha_mips_jmptbl_unaligned_0) + + /* Calculate lower half jump table offset */ + ins T0, $at, 1, 6 +@@ -408,7 +408,7 @@ chacha20_mips: + addu T1, STATE, $at + + /* Add lower half jump table addr */ +- addiu T0, %lo(.Lchacha20_mips_jmptbl_unaligned_0) ++ addiu T0, %lo(.Lchacha_mips_jmptbl_unaligned_0) + + /* Read value from STATE */ + lw SAVED_CA, 0(T1) +@@ -420,5 +420,78 @@ chacha20_mips: + + /* Jump table */ + FOR_EACH_WORD(JMPTBL_UNALIGNED) +-.end chacha20_mips ++.end chacha_crypt_arch ++.set at ++ ++/* Input arguments ++ * STATE $a0 ++ * OUT $a1 ++ * NROUND $a2 ++ */ ++ ++#undef X12 ++#undef X13 ++#undef X14 ++#undef X15 ++ ++#define X12 $a3 ++#define X13 $at ++#define X14 $v0 ++#define X15 STATE ++ ++.set noat ++.globl hchacha_block_arch ++.ent hchacha_block_arch ++hchacha_block_arch: ++ .frame $sp, STACK_SIZE, $ra ++ ++ addiu $sp, -STACK_SIZE ++ ++ /* Save X11(s6) */ ++ sw X11, 0($sp) ++ ++ lw X0, 0(STATE) ++ lw X1, 4(STATE) ++ lw X2, 8(STATE) ++ lw X3, 12(STATE) ++ lw X4, 16(STATE) ++ lw X5, 20(STATE) ++ lw X6, 24(STATE) ++ lw X7, 28(STATE) ++ lw X8, 32(STATE) ++ lw X9, 36(STATE) ++ lw X10, 40(STATE) ++ lw X11, 44(STATE) ++ lw X12, 48(STATE) ++ lw X13, 52(STATE) ++ lw X14, 56(STATE) ++ lw X15, 60(STATE) ++ ++.Loop_hchacha_xor_rounds: ++ addiu $a2, -2 ++ AXR( 0, 1, 2, 3, 4, 5, 6, 7, 12,13,14,15, 16); ++ AXR( 8, 9,10,11, 12,13,14,15, 4, 5, 6, 7, 12); ++ AXR( 0, 1, 2, 3, 4, 5, 6, 7, 12,13,14,15, 8); ++ AXR( 8, 9,10,11, 12,13,14,15, 4, 5, 6, 7, 7); ++ AXR( 0, 1, 2, 3, 5, 6, 7, 4, 15,12,13,14, 16); ++ AXR(10,11, 8, 9, 15,12,13,14, 5, 6, 7, 4, 12); ++ AXR( 0, 1, 2, 3, 5, 6, 7, 4, 15,12,13,14, 8); ++ AXR(10,11, 8, 9, 15,12,13,14, 5, 6, 7, 4, 7); ++ bnez $a2, .Loop_hchacha_xor_rounds ++ ++ /* Restore used register */ ++ lw X11, 0($sp) ++ ++ sw X0, 0(OUT) ++ sw X1, 4(OUT) ++ sw X2, 8(OUT) ++ sw X3, 12(OUT) ++ sw X12, 16(OUT) ++ sw X13, 20(OUT) ++ sw X14, 24(OUT) ++ sw X15, 28(OUT) ++ ++ addiu $sp, STACK_SIZE ++ jr $ra ++.end hchacha_block_arch + .set at +--- /dev/null ++++ b/arch/mips/crypto/chacha-glue.c +@@ -0,0 +1,150 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * MIPS accelerated ChaCha and XChaCha stream ciphers, ++ * including ChaCha20 (RFC7539) ++ * ++ * Copyright (C) 2019 Linaro, Ltd. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++asmlinkage void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, ++ unsigned int bytes, int nrounds); ++EXPORT_SYMBOL(chacha_crypt_arch); ++ ++asmlinkage void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds); ++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); ++ ++static int chacha_mips_stream_xor(struct skcipher_request *req, ++ const struct chacha_ctx *ctx, const u8 *iv) ++{ ++ 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); ++ ++ chacha_crypt(state, walk.dst.virt.addr, walk.src.virt.addr, ++ nbytes, ctx->nrounds); ++ err = skcipher_walk_done(&walk, walk.nbytes - nbytes); ++ } ++ ++ return err; ++} ++ ++static int chacha_mips(struct skcipher_request *req) ++{ ++ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); ++ struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); ++ ++ return chacha_mips_stream_xor(req, ctx, req->iv); ++} ++ ++static int xchacha_mips(struct skcipher_request *req) ++{ ++ 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); ++ ++ hchacha_block(state, subctx.key, ctx->nrounds); ++ subctx.nrounds = ctx->nrounds; ++ ++ memcpy(&real_iv[0], req->iv + 24, 8); ++ memcpy(&real_iv[8], req->iv + 16, 8); ++ return chacha_mips_stream_xor(req, &subctx, real_iv); ++} ++ ++static struct skcipher_alg algs[] = { ++ { ++ .base.cra_name = "chacha20", ++ .base.cra_driver_name = "chacha20-mips", ++ .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_mips, ++ .decrypt = chacha_mips, ++ }, { ++ .base.cra_name = "xchacha20", ++ .base.cra_driver_name = "xchacha20-mips", ++ .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_mips, ++ .decrypt = xchacha_mips, ++ }, { ++ .base.cra_name = "xchacha12", ++ .base.cra_driver_name = "xchacha12-mips", ++ .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_mips, ++ .decrypt = xchacha_mips, ++ } ++}; ++ ++static int __init chacha_simd_mod_init(void) ++{ ++ return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); ++} ++ ++static void __exit chacha_simd_mod_fini(void) ++{ ++ crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); ++} ++ ++module_init(chacha_simd_mod_init); ++module_exit(chacha_simd_mod_fini); ++ ++MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (MIPS accelerated)"); ++MODULE_AUTHOR("Ard Biesheuvel "); ++MODULE_LICENSE("GPL v2"); ++MODULE_ALIAS_CRYPTO("chacha20"); ++MODULE_ALIAS_CRYPTO("chacha20-mips"); ++MODULE_ALIAS_CRYPTO("xchacha20"); ++MODULE_ALIAS_CRYPTO("xchacha20-mips"); ++MODULE_ALIAS_CRYPTO("xchacha12"); ++MODULE_ALIAS_CRYPTO("xchacha12-mips"); +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -1423,6 +1423,12 @@ config CRYPTO_CHACHA20_X86_64 + SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20, + XChaCha20, and XChaCha12 stream ciphers. + ++config CRYPTO_CHACHA_MIPS ++ tristate "ChaCha stream cipher algorithms (MIPS 32r2 optimized)" ++ depends on CPU_MIPS32_R2 ++ select CRYPTO_BLKCIPHER ++ select CRYPTO_ARCH_HAVE_LIB_CHACHA ++ + config CRYPTO_SEED + tristate "SEED cipher algorithm" + select CRYPTO_ALGAPI diff --git a/target/linux/generic/backport-5.4/080-wireguard-0012-crypto-chacha-unexport-chacha_generic-routines.patch b/target/linux/generic/backport-5.4/080-wireguard-0012-crypto-chacha-unexport-chacha_generic-routines.patch new file mode 100644 index 0000000000..23a1e41529 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0012-crypto-chacha-unexport-chacha_generic-routines.patch @@ -0,0 +1,115 @@ +From 53b97caa431974880c3ea592be870a62e9ef444a Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:18 +0100 +Subject: [PATCH 012/124] crypto: chacha - unexport chacha_generic routines + +commit 22cf705360707ced15f9fe5423938f313c7df536 upstream. + +Now that all users of generic ChaCha code have moved to the core library, +there is no longer a need for the generic ChaCha skcpiher driver to +export parts of it implementation for reuse by other drivers. So drop +the exports, and make the symbols static. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/chacha_generic.c | 26 ++++++++------------------ + include/crypto/internal/chacha.h | 10 ---------- + 2 files changed, 8 insertions(+), 28 deletions(-) + +--- a/crypto/chacha_generic.c ++++ b/crypto/chacha_generic.c +@@ -21,7 +21,7 @@ static int chacha_stream_xor(struct skci + + err = skcipher_walk_virt(&walk, req, false); + +- crypto_chacha_init(state, ctx, iv); ++ chacha_init_generic(state, ctx->key, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; +@@ -37,36 +37,27 @@ static int chacha_stream_xor(struct skci + return err; + } + +-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv) +-{ +- chacha_init_generic(state, ctx->key, iv); +-} +-EXPORT_SYMBOL_GPL(crypto_chacha_init); +- +-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize) ++static int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize) + { + return chacha_setkey(tfm, key, keysize, 20); + } +-EXPORT_SYMBOL_GPL(crypto_chacha20_setkey); + +-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize) ++static int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, ++ unsigned int keysize) + { + return chacha_setkey(tfm, key, keysize, 12); + } +-EXPORT_SYMBOL_GPL(crypto_chacha12_setkey); + +-int crypto_chacha_crypt(struct skcipher_request *req) ++static int crypto_chacha_crypt(struct skcipher_request *req) + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + + return chacha_stream_xor(req, ctx, req->iv); + } +-EXPORT_SYMBOL_GPL(crypto_chacha_crypt); + +-int crypto_xchacha_crypt(struct skcipher_request *req) ++static int crypto_xchacha_crypt(struct skcipher_request *req) + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); +@@ -75,7 +66,7 @@ int crypto_xchacha_crypt(struct skcipher + u8 real_iv[16]; + + /* Compute the subkey given the original key and first 128 nonce bits */ +- crypto_chacha_init(state, ctx, req->iv); ++ chacha_init_generic(state, ctx->key, req->iv); + hchacha_block_generic(state, subctx.key, ctx->nrounds); + subctx.nrounds = ctx->nrounds; + +@@ -86,7 +77,6 @@ int crypto_xchacha_crypt(struct skcipher + /* Generate the stream and XOR it with the data */ + return chacha_stream_xor(req, &subctx, real_iv); + } +-EXPORT_SYMBOL_GPL(crypto_xchacha_crypt); + + static struct skcipher_alg algs[] = { + { +--- a/include/crypto/internal/chacha.h ++++ b/include/crypto/internal/chacha.h +@@ -12,8 +12,6 @@ struct chacha_ctx { + int nrounds; + }; + +-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv); +- + static inline int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize, int nrounds) + { +@@ -42,12 +40,4 @@ static int inline chacha12_setkey(struct + return chacha_setkey(tfm, key, keysize, 12); + } + +-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize); +-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize); +- +-int crypto_chacha_crypt(struct skcipher_request *req); +-int crypto_xchacha_crypt(struct skcipher_request *req); +- + #endif /* _CRYPTO_CHACHA_H */ diff --git a/target/linux/generic/backport-5.4/080-wireguard-0013-crypto-poly1305-move-core-routines-into-a-separate-l.patch b/target/linux/generic/backport-5.4/080-wireguard-0013-crypto-poly1305-move-core-routines-into-a-separate-l.patch new file mode 100644 index 0000000000..a522704b4a --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0013-crypto-poly1305-move-core-routines-into-a-separate-l.patch @@ -0,0 +1,650 @@ +From 905432633564215220707ee97f64ffb249a029f2 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:19 +0100 +Subject: [PATCH 013/124] crypto: poly1305 - move core routines into a separate + library + +commit 48ea8c6ebc96bc0990e12ee1c43d0832c23576bb upstream. + +Move the core Poly1305 routines shared between the generic Poly1305 +shash driver and the Adiantum and NHPoly1305 drivers into a separate +library so that using just this pieces does not pull in the crypto +API pieces of the generic Poly1305 routine. + +In a subsequent patch, we will augment this generic library with +init/update/final routines so that Poyl1305 algorithm can be used +directly without the need for using the crypto API's shash abstraction. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 2 +- + crypto/Kconfig | 5 +- + crypto/adiantum.c | 5 +- + crypto/nhpoly1305.c | 3 +- + crypto/poly1305_generic.c | 195 ++--------------------------- + include/crypto/internal/poly1305.h | 67 ++++++++++ + include/crypto/poly1305.h | 23 ---- + lib/crypto/Kconfig | 3 + + lib/crypto/Makefile | 3 + + lib/crypto/poly1305.c | 158 +++++++++++++++++++++++ + 10 files changed, 248 insertions(+), 216 deletions(-) + create mode 100644 include/crypto/internal/poly1305.h + create mode 100644 lib/crypto/poly1305.c + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -7,8 +7,8 @@ + + #include + #include ++#include + #include +-#include + #include + #include + #include +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -446,7 +446,7 @@ config CRYPTO_KEYWRAP + config CRYPTO_NHPOLY1305 + tristate + select CRYPTO_HASH +- select CRYPTO_POLY1305 ++ select CRYPTO_LIB_POLY1305_GENERIC + + config CRYPTO_NHPOLY1305_SSE2 + tristate "NHPoly1305 hash function (x86_64 SSE2 implementation)" +@@ -467,7 +467,7 @@ config CRYPTO_NHPOLY1305_AVX2 + config CRYPTO_ADIANTUM + tristate "Adiantum support" + select CRYPTO_CHACHA20 +- select CRYPTO_POLY1305 ++ select CRYPTO_LIB_POLY1305_GENERIC + select CRYPTO_NHPOLY1305 + select CRYPTO_MANAGER + help +@@ -686,6 +686,7 @@ config CRYPTO_GHASH + config CRYPTO_POLY1305 + tristate "Poly1305 authenticator algorithm" + select CRYPTO_HASH ++ select CRYPTO_LIB_POLY1305_GENERIC + help + Poly1305 authenticator algorithm, RFC7539. + +--- a/crypto/adiantum.c ++++ b/crypto/adiantum.c +@@ -33,6 +33,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -242,11 +243,11 @@ static void adiantum_hash_header(struct + + BUILD_BUG_ON(sizeof(header) % POLY1305_BLOCK_SIZE != 0); + poly1305_core_blocks(&state, &tctx->header_hash_key, +- &header, sizeof(header) / POLY1305_BLOCK_SIZE); ++ &header, sizeof(header) / POLY1305_BLOCK_SIZE, 1); + + BUILD_BUG_ON(TWEAK_SIZE % POLY1305_BLOCK_SIZE != 0); + poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv, +- TWEAK_SIZE / POLY1305_BLOCK_SIZE); ++ TWEAK_SIZE / POLY1305_BLOCK_SIZE, 1); + + poly1305_core_emit(&state, &rctx->header_hash); + } +--- a/crypto/nhpoly1305.c ++++ b/crypto/nhpoly1305.c +@@ -33,6 +33,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -78,7 +79,7 @@ static void process_nh_hash_value(struct + BUILD_BUG_ON(NH_HASH_BYTES % POLY1305_BLOCK_SIZE != 0); + + poly1305_core_blocks(&state->poly_state, &key->poly_key, state->nh_hash, +- NH_HASH_BYTES / POLY1305_BLOCK_SIZE); ++ NH_HASH_BYTES / POLY1305_BLOCK_SIZE, 1); + } + + /* +--- a/crypto/poly1305_generic.c ++++ b/crypto/poly1305_generic.c +@@ -13,27 +13,12 @@ + + #include + #include +-#include ++#include + #include + #include + #include + #include + +-static inline u64 mlt(u64 a, u64 b) +-{ +- return a * b; +-} +- +-static inline u32 sr(u64 v, u_char n) +-{ +- return v >> n; +-} +- +-static inline u32 and(u32 v, u32 mask) +-{ +- return v & mask; +-} +- + int crypto_poly1305_init(struct shash_desc *desc) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); +@@ -47,124 +32,8 @@ int crypto_poly1305_init(struct shash_de + } + EXPORT_SYMBOL_GPL(crypto_poly1305_init); + +-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key) +-{ +- /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ +- key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff; +- key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03; +- key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff; +- key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff; +- key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff; +-} +-EXPORT_SYMBOL_GPL(poly1305_core_setkey); +- +-/* +- * Poly1305 requires a unique key for each tag, which implies that we can't set +- * it on the tfm that gets accessed by multiple users simultaneously. Instead we +- * expect the key as the first 32 bytes in the update() call. +- */ +-unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen) +-{ +- if (!dctx->sset) { +- if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_core_setkey(&dctx->r, src); +- src += POLY1305_BLOCK_SIZE; +- srclen -= POLY1305_BLOCK_SIZE; +- dctx->rset = true; +- } +- if (srclen >= 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; +- srclen -= POLY1305_BLOCK_SIZE; +- dctx->sset = true; +- } +- } +- return srclen; +-} +-EXPORT_SYMBOL_GPL(crypto_poly1305_setdesckey); +- +-static void poly1305_blocks_internal(struct poly1305_state *state, +- const struct poly1305_key *key, +- const void *src, unsigned int nblocks, +- u32 hibit) +-{ +- u32 r0, r1, r2, r3, r4; +- u32 s1, s2, s3, s4; +- u32 h0, h1, h2, h3, h4; +- u64 d0, d1, d2, d3, d4; +- +- if (!nblocks) +- return; +- +- r0 = key->r[0]; +- r1 = key->r[1]; +- r2 = key->r[2]; +- r3 = key->r[3]; +- r4 = key->r[4]; +- +- s1 = r1 * 5; +- s2 = r2 * 5; +- s3 = r3 * 5; +- s4 = r4 * 5; +- +- h0 = state->h[0]; +- h1 = state->h[1]; +- h2 = state->h[2]; +- h3 = state->h[3]; +- h4 = state->h[4]; +- +- do { +- /* h += m[i] */ +- h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff; +- h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff; +- h2 += (get_unaligned_le32(src + 6) >> 4) & 0x3ffffff; +- h3 += (get_unaligned_le32(src + 9) >> 6) & 0x3ffffff; +- h4 += (get_unaligned_le32(src + 12) >> 8) | hibit; +- +- /* h *= r */ +- d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + +- mlt(h3, s2) + mlt(h4, s1); +- d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) + +- mlt(h3, s3) + mlt(h4, s2); +- d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) + +- mlt(h3, s4) + mlt(h4, s3); +- d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) + +- mlt(h3, r0) + mlt(h4, s4); +- d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) + +- mlt(h3, r1) + mlt(h4, r0); +- +- /* (partial) h %= p */ +- d1 += sr(d0, 26); h0 = and(d0, 0x3ffffff); +- d2 += sr(d1, 26); h1 = and(d1, 0x3ffffff); +- d3 += sr(d2, 26); h2 = and(d2, 0x3ffffff); +- d4 += sr(d3, 26); h3 = and(d3, 0x3ffffff); +- h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff); +- h1 += h0 >> 26; h0 = h0 & 0x3ffffff; +- +- src += POLY1305_BLOCK_SIZE; +- } while (--nblocks); +- +- state->h[0] = h0; +- state->h[1] = h1; +- state->h[2] = h2; +- state->h[3] = h3; +- state->h[4] = h4; +-} +- +-void poly1305_core_blocks(struct poly1305_state *state, +- const struct poly1305_key *key, +- const void *src, unsigned int nblocks) +-{ +- poly1305_blocks_internal(state, key, src, nblocks, 1 << 24); +-} +-EXPORT_SYMBOL_GPL(poly1305_core_blocks); +- +-static void poly1305_blocks(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen, u32 hibit) ++static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src, ++ unsigned int srclen) + { + unsigned int datalen; + +@@ -174,8 +43,8 @@ static void poly1305_blocks(struct poly1 + srclen = datalen; + } + +- poly1305_blocks_internal(&dctx->h, &dctx->r, +- src, srclen / POLY1305_BLOCK_SIZE, hibit); ++ poly1305_core_blocks(&dctx->h, &dctx->r, src, ++ srclen / POLY1305_BLOCK_SIZE, 1); + } + + int crypto_poly1305_update(struct shash_desc *desc, +@@ -193,13 +62,13 @@ int crypto_poly1305_update(struct shash_ + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { + poly1305_blocks(dctx, dctx->buf, +- POLY1305_BLOCK_SIZE, 1 << 24); ++ POLY1305_BLOCK_SIZE); + dctx->buflen = 0; + } + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { +- poly1305_blocks(dctx, src, srclen, 1 << 24); ++ poly1305_blocks(dctx, src, srclen); + src += srclen - (srclen % POLY1305_BLOCK_SIZE); + srclen %= POLY1305_BLOCK_SIZE; + } +@@ -213,54 +82,6 @@ int crypto_poly1305_update(struct shash_ + } + EXPORT_SYMBOL_GPL(crypto_poly1305_update); + +-void poly1305_core_emit(const struct poly1305_state *state, void *dst) +-{ +- u32 h0, h1, h2, h3, h4; +- u32 g0, g1, g2, g3, g4; +- u32 mask; +- +- /* fully carry h */ +- h0 = state->h[0]; +- h1 = state->h[1]; +- h2 = state->h[2]; +- h3 = state->h[3]; +- h4 = state->h[4]; +- +- h2 += (h1 >> 26); h1 = h1 & 0x3ffffff; +- h3 += (h2 >> 26); h2 = h2 & 0x3ffffff; +- h4 += (h3 >> 26); h3 = h3 & 0x3ffffff; +- h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff; +- h1 += (h0 >> 26); h0 = h0 & 0x3ffffff; +- +- /* compute h + -p */ +- g0 = h0 + 5; +- g1 = h1 + (g0 >> 26); g0 &= 0x3ffffff; +- g2 = h2 + (g1 >> 26); g1 &= 0x3ffffff; +- g3 = h3 + (g2 >> 26); g2 &= 0x3ffffff; +- g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff; +- +- /* select h if h < p, or h + -p if h >= p */ +- mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1; +- g0 &= mask; +- g1 &= mask; +- g2 &= mask; +- g3 &= mask; +- g4 &= mask; +- mask = ~mask; +- h0 = (h0 & mask) | g0; +- h1 = (h1 & mask) | g1; +- h2 = (h2 & mask) | g2; +- h3 = (h3 & mask) | g3; +- h4 = (h4 & mask) | g4; +- +- /* h = h % (2^128) */ +- put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0); +- put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4); +- put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8); +- put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12); +-} +-EXPORT_SYMBOL_GPL(poly1305_core_emit); +- + int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); +@@ -274,7 +95,7 @@ int crypto_poly1305_final(struct shash_d + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, + POLY1305_BLOCK_SIZE - dctx->buflen); +- poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0); ++ poly1305_core_blocks(&dctx->h, &dctx->r, dctx->buf, 1, 0); + } + + poly1305_core_emit(&dctx->h, digest); +--- /dev/null ++++ b/include/crypto/internal/poly1305.h +@@ -0,0 +1,67 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Common values for the Poly1305 algorithm ++ */ ++ ++#ifndef _CRYPTO_INTERNAL_POLY1305_H ++#define _CRYPTO_INTERNAL_POLY1305_H ++ ++#include ++#include ++#include ++ ++struct shash_desc; ++ ++/* ++ * Poly1305 core functions. These implement the ε-almost-∆-universal hash ++ * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce ++ * ("s key") at the end. They also only support block-aligned inputs. ++ */ ++void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key); ++static inline void poly1305_core_init(struct poly1305_state *state) ++{ ++ *state = (struct poly1305_state){}; ++} ++ ++void poly1305_core_blocks(struct poly1305_state *state, ++ const struct poly1305_key *key, const void *src, ++ unsigned int nblocks, u32 hibit); ++void poly1305_core_emit(const struct poly1305_state *state, void *dst); ++ ++/* Crypto API helper functions for the Poly1305 MAC */ ++int crypto_poly1305_init(struct shash_desc *desc); ++ ++int crypto_poly1305_update(struct shash_desc *desc, ++ const u8 *src, unsigned int srclen); ++int crypto_poly1305_final(struct shash_desc *desc, u8 *dst); ++ ++/* ++ * Poly1305 requires a unique key for each tag, which implies that we can't set ++ * it on the tfm that gets accessed by multiple users simultaneously. Instead we ++ * expect the key as the first 32 bytes in the update() call. ++ */ ++static inline ++unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, ++ const u8 *src, unsigned int srclen) ++{ ++ if (!dctx->sset) { ++ if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { ++ poly1305_core_setkey(&dctx->r, src); ++ src += POLY1305_BLOCK_SIZE; ++ srclen -= POLY1305_BLOCK_SIZE; ++ dctx->rset = true; ++ } ++ if (srclen >= 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; ++ srclen -= POLY1305_BLOCK_SIZE; ++ dctx->sset = true; ++ } ++ } ++ return srclen; ++} ++ ++#endif +--- a/include/crypto/poly1305.h ++++ b/include/crypto/poly1305.h +@@ -38,27 +38,4 @@ struct poly1305_desc_ctx { + bool sset; + }; + +-/* +- * Poly1305 core functions. These implement the ε-almost-∆-universal hash +- * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce +- * ("s key") at the end. They also only support block-aligned inputs. +- */ +-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key); +-static inline void poly1305_core_init(struct poly1305_state *state) +-{ +- memset(state->h, 0, sizeof(state->h)); +-} +-void poly1305_core_blocks(struct poly1305_state *state, +- const struct poly1305_key *key, +- const void *src, unsigned int nblocks); +-void poly1305_core_emit(const struct poly1305_state *state, void *dst); +- +-/* Crypto API helper functions for the Poly1305 MAC */ +-int crypto_poly1305_init(struct shash_desc *desc); +-unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen); +-int crypto_poly1305_update(struct shash_desc *desc, +- const u8 *src, unsigned int srclen); +-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst); +- + #endif +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -37,5 +37,8 @@ config CRYPTO_LIB_CHACHA + config CRYPTO_LIB_DES + tristate + ++config CRYPTO_LIB_POLY1305_GENERIC ++ tristate ++ + config CRYPTO_LIB_SHA256 + tristate +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -13,5 +13,8 @@ libarc4-y := arc4.o + obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o + libdes-y := des.o + ++obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC) += libpoly1305.o ++libpoly1305-y := poly1305.o ++ + obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o + libsha256-y := sha256.o +--- /dev/null ++++ b/lib/crypto/poly1305.c +@@ -0,0 +1,158 @@ ++// SPDX-License-Identifier: GPL-2.0-or-later ++/* ++ * Poly1305 authenticator algorithm, RFC7539 ++ * ++ * Copyright (C) 2015 Martin Willi ++ * ++ * Based on public domain code by Andrew Moon and Daniel J. Bernstein. ++ */ ++ ++#include ++#include ++#include ++#include ++ ++static inline u64 mlt(u64 a, u64 b) ++{ ++ return a * b; ++} ++ ++static inline u32 sr(u64 v, u_char n) ++{ ++ return v >> n; ++} ++ ++static inline u32 and(u32 v, u32 mask) ++{ ++ return v & mask; ++} ++ ++void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key) ++{ ++ /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ ++ key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff; ++ key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03; ++ key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff; ++ key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff; ++ key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff; ++} ++EXPORT_SYMBOL_GPL(poly1305_core_setkey); ++ ++void poly1305_core_blocks(struct poly1305_state *state, ++ const struct poly1305_key *key, const void *src, ++ unsigned int nblocks, u32 hibit) ++{ ++ u32 r0, r1, r2, r3, r4; ++ u32 s1, s2, s3, s4; ++ u32 h0, h1, h2, h3, h4; ++ u64 d0, d1, d2, d3, d4; ++ ++ if (!nblocks) ++ return; ++ ++ r0 = key->r[0]; ++ r1 = key->r[1]; ++ r2 = key->r[2]; ++ r3 = key->r[3]; ++ r4 = key->r[4]; ++ ++ s1 = r1 * 5; ++ s2 = r2 * 5; ++ s3 = r3 * 5; ++ s4 = r4 * 5; ++ ++ h0 = state->h[0]; ++ h1 = state->h[1]; ++ h2 = state->h[2]; ++ h3 = state->h[3]; ++ h4 = state->h[4]; ++ ++ do { ++ /* h += m[i] */ ++ h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff; ++ h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff; ++ h2 += (get_unaligned_le32(src + 6) >> 4) & 0x3ffffff; ++ h3 += (get_unaligned_le32(src + 9) >> 6) & 0x3ffffff; ++ h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24); ++ ++ /* h *= r */ ++ d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + ++ mlt(h3, s2) + mlt(h4, s1); ++ d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) + ++ mlt(h3, s3) + mlt(h4, s2); ++ d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) + ++ mlt(h3, s4) + mlt(h4, s3); ++ d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) + ++ mlt(h3, r0) + mlt(h4, s4); ++ d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) + ++ mlt(h3, r1) + mlt(h4, r0); ++ ++ /* (partial) h %= p */ ++ d1 += sr(d0, 26); h0 = and(d0, 0x3ffffff); ++ d2 += sr(d1, 26); h1 = and(d1, 0x3ffffff); ++ d3 += sr(d2, 26); h2 = and(d2, 0x3ffffff); ++ d4 += sr(d3, 26); h3 = and(d3, 0x3ffffff); ++ h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff); ++ h1 += h0 >> 26; h0 = h0 & 0x3ffffff; ++ ++ src += POLY1305_BLOCK_SIZE; ++ } while (--nblocks); ++ ++ state->h[0] = h0; ++ state->h[1] = h1; ++ state->h[2] = h2; ++ state->h[3] = h3; ++ state->h[4] = h4; ++} ++EXPORT_SYMBOL_GPL(poly1305_core_blocks); ++ ++void poly1305_core_emit(const struct poly1305_state *state, void *dst) ++{ ++ u32 h0, h1, h2, h3, h4; ++ u32 g0, g1, g2, g3, g4; ++ u32 mask; ++ ++ /* fully carry h */ ++ h0 = state->h[0]; ++ h1 = state->h[1]; ++ h2 = state->h[2]; ++ h3 = state->h[3]; ++ h4 = state->h[4]; ++ ++ h2 += (h1 >> 26); h1 = h1 & 0x3ffffff; ++ h3 += (h2 >> 26); h2 = h2 & 0x3ffffff; ++ h4 += (h3 >> 26); h3 = h3 & 0x3ffffff; ++ h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff; ++ h1 += (h0 >> 26); h0 = h0 & 0x3ffffff; ++ ++ /* compute h + -p */ ++ g0 = h0 + 5; ++ g1 = h1 + (g0 >> 26); g0 &= 0x3ffffff; ++ g2 = h2 + (g1 >> 26); g1 &= 0x3ffffff; ++ g3 = h3 + (g2 >> 26); g2 &= 0x3ffffff; ++ g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff; ++ ++ /* select h if h < p, or h + -p if h >= p */ ++ mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1; ++ g0 &= mask; ++ g1 &= mask; ++ g2 &= mask; ++ g3 &= mask; ++ g4 &= mask; ++ mask = ~mask; ++ h0 = (h0 & mask) | g0; ++ h1 = (h1 & mask) | g1; ++ h2 = (h2 & mask) | g2; ++ h3 = (h3 & mask) | g3; ++ h4 = (h4 & mask) | g4; ++ ++ /* h = h % (2^128) */ ++ put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0); ++ put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4); ++ put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8); ++ put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12); ++} ++EXPORT_SYMBOL_GPL(poly1305_core_emit); ++ ++MODULE_LICENSE("GPL"); ++MODULE_AUTHOR("Martin Willi "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0014-crypto-x86-poly1305-unify-Poly1305-state-struct-with.patch b/target/linux/generic/backport-5.4/080-wireguard-0014-crypto-x86-poly1305-unify-Poly1305-state-struct-with.patch new file mode 100644 index 0000000000..5a879f0434 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0014-crypto-x86-poly1305-unify-Poly1305-state-struct-with.patch @@ -0,0 +1,251 @@ +From 1017a880df176730e7f8e32f28300eea2a6c27a4 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:20 +0100 +Subject: [PATCH 014/124] crypto: x86/poly1305 - unify Poly1305 state struct + with generic code + +commit ad8f5b88383ea685f2b8df2a12ee3e08089a1287 upstream. + +In preparation of exposing a Poly1305 library interface directly from +the accelerated x86 driver, align the state descriptor of the x86 code +with the one used by the generic driver. This is needed to make the +library interface unified between all implementations. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 88 ++++++++++-------------------- + crypto/poly1305_generic.c | 6 +- + include/crypto/internal/poly1305.h | 4 +- + include/crypto/poly1305.h | 18 +++--- + 4 files changed, 43 insertions(+), 73 deletions(-) + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -14,40 +14,14 @@ + #include + #include + +-struct poly1305_simd_desc_ctx { +- struct poly1305_desc_ctx base; +- /* derived key u set? */ +- bool uset; +-#ifdef CONFIG_AS_AVX2 +- /* derived keys r^3, r^4 set? */ +- bool wset; +-#endif +- /* derived Poly1305 key r^2 */ +- u32 u[5]; +- /* ... silently appended r^3 and r^4 when using AVX2 */ +-}; +- + asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src, + const u32 *r, unsigned int blocks); + asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); +-#ifdef CONFIG_AS_AVX2 + asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); +-static bool poly1305_use_avx2; +-#endif + +-static int poly1305_simd_init(struct shash_desc *desc) +-{ +- struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc); +- +- sctx->uset = false; +-#ifdef CONFIG_AS_AVX2 +- sctx->wset = false; +-#endif +- +- return crypto_poly1305_init(desc); +-} ++static bool poly1305_use_avx2 __ro_after_init; + + static void poly1305_simd_mult(u32 *a, const u32 *b) + { +@@ -63,53 +37,49 @@ static void poly1305_simd_mult(u32 *a, c + static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, + const u8 *src, unsigned int srclen) + { +- struct poly1305_simd_desc_ctx *sctx; + unsigned int blocks, datalen; + +- BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base)); +- sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base); +- + if (unlikely(!dctx->sset)) { + datalen = crypto_poly1305_setdesckey(dctx, src, srclen); + src += srclen - datalen; + srclen = datalen; + } + +-#ifdef CONFIG_AS_AVX2 +- if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) { +- if (unlikely(!sctx->wset)) { +- if (!sctx->uset) { +- memcpy(sctx->u, dctx->r.r, sizeof(sctx->u)); +- poly1305_simd_mult(sctx->u, dctx->r.r); +- sctx->uset = true; ++ if (IS_ENABLED(CONFIG_AS_AVX2) && ++ poly1305_use_avx2 && ++ srclen >= POLY1305_BLOCK_SIZE * 4) { ++ if (unlikely(dctx->rset < 4)) { ++ if (dctx->rset < 2) { ++ dctx->r[1] = dctx->r[0]; ++ poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r); + } +- memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u)); +- poly1305_simd_mult(sctx->u + 5, dctx->r.r); +- memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u)); +- poly1305_simd_mult(sctx->u + 10, dctx->r.r); +- sctx->wset = true; ++ dctx->r[2] = dctx->r[1]; ++ poly1305_simd_mult(dctx->r[2].r, dctx->r[0].r); ++ dctx->r[3] = dctx->r[2]; ++ poly1305_simd_mult(dctx->r[3].r, dctx->r[0].r); ++ dctx->rset = 4; + } + blocks = srclen / (POLY1305_BLOCK_SIZE * 4); +- poly1305_4block_avx2(dctx->h.h, src, dctx->r.r, blocks, +- sctx->u); ++ poly1305_4block_avx2(dctx->h.h, src, dctx->r[0].r, blocks, ++ dctx->r[1].r); + src += POLY1305_BLOCK_SIZE * 4 * blocks; + srclen -= POLY1305_BLOCK_SIZE * 4 * blocks; + } +-#endif ++ + if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) { +- if (unlikely(!sctx->uset)) { +- memcpy(sctx->u, dctx->r.r, sizeof(sctx->u)); +- poly1305_simd_mult(sctx->u, dctx->r.r); +- sctx->uset = true; ++ if (unlikely(dctx->rset < 2)) { ++ dctx->r[1] = dctx->r[0]; ++ poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r); ++ dctx->rset = 2; + } + blocks = srclen / (POLY1305_BLOCK_SIZE * 2); +- poly1305_2block_sse2(dctx->h.h, src, dctx->r.r, blocks, +- sctx->u); ++ poly1305_2block_sse2(dctx->h.h, src, dctx->r[0].r, ++ blocks, dctx->r[1].r); + src += POLY1305_BLOCK_SIZE * 2 * blocks; + srclen -= POLY1305_BLOCK_SIZE * 2 * blocks; + } + if (srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_block_sse2(dctx->h.h, src, dctx->r.r, 1); ++ poly1305_block_sse2(dctx->h.h, src, dctx->r[0].r, 1); + srclen -= POLY1305_BLOCK_SIZE; + } + return srclen; +@@ -159,10 +129,10 @@ static int poly1305_simd_update(struct s + + static struct shash_alg alg = { + .digestsize = POLY1305_DIGEST_SIZE, +- .init = poly1305_simd_init, ++ .init = crypto_poly1305_init, + .update = poly1305_simd_update, + .final = crypto_poly1305_final, +- .descsize = sizeof(struct poly1305_simd_desc_ctx), ++ .descsize = sizeof(struct poly1305_desc_ctx), + .base = { + .cra_name = "poly1305", + .cra_driver_name = "poly1305-simd", +@@ -177,14 +147,14 @@ static int __init poly1305_simd_mod_init + if (!boot_cpu_has(X86_FEATURE_XMM2)) + return -ENODEV; + +-#ifdef CONFIG_AS_AVX2 +- poly1305_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) && ++ poly1305_use_avx2 = IS_ENABLED(CONFIG_AS_AVX2) && ++ boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); +- alg.descsize = sizeof(struct poly1305_simd_desc_ctx); ++ alg.descsize = sizeof(struct poly1305_desc_ctx) + 5 * sizeof(u32); + if (poly1305_use_avx2) + alg.descsize += 10 * sizeof(u32); +-#endif ++ + return crypto_register_shash(&alg); + } + +--- a/crypto/poly1305_generic.c ++++ b/crypto/poly1305_generic.c +@@ -25,7 +25,7 @@ int crypto_poly1305_init(struct shash_de + + poly1305_core_init(&dctx->h); + dctx->buflen = 0; +- dctx->rset = false; ++ dctx->rset = 0; + dctx->sset = false; + + return 0; +@@ -43,7 +43,7 @@ static void poly1305_blocks(struct poly1 + srclen = datalen; + } + +- poly1305_core_blocks(&dctx->h, &dctx->r, src, ++ poly1305_core_blocks(&dctx->h, dctx->r, src, + srclen / POLY1305_BLOCK_SIZE, 1); + } + +@@ -95,7 +95,7 @@ int crypto_poly1305_final(struct shash_d + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, + POLY1305_BLOCK_SIZE - dctx->buflen); +- poly1305_core_blocks(&dctx->h, &dctx->r, dctx->buf, 1, 0); ++ poly1305_core_blocks(&dctx->h, dctx->r, dctx->buf, 1, 0); + } + + poly1305_core_emit(&dctx->h, digest); +--- a/include/crypto/internal/poly1305.h ++++ b/include/crypto/internal/poly1305.h +@@ -46,10 +46,10 @@ unsigned int crypto_poly1305_setdesckey( + { + if (!dctx->sset) { + if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_core_setkey(&dctx->r, src); ++ poly1305_core_setkey(dctx->r, src); + src += POLY1305_BLOCK_SIZE; + srclen -= POLY1305_BLOCK_SIZE; +- dctx->rset = true; ++ dctx->rset = 1; + } + if (srclen >= POLY1305_BLOCK_SIZE) { + dctx->s[0] = get_unaligned_le32(src + 0); +--- a/include/crypto/poly1305.h ++++ b/include/crypto/poly1305.h +@@ -22,20 +22,20 @@ struct poly1305_state { + }; + + struct poly1305_desc_ctx { +- /* key */ +- struct poly1305_key r; +- /* finalize key */ +- u32 s[4]; +- /* accumulator */ +- struct poly1305_state h; + /* partial buffer */ + u8 buf[POLY1305_BLOCK_SIZE]; + /* bytes used in partial buffer */ + unsigned int buflen; +- /* r key has been set */ +- bool rset; +- /* s key has been set */ ++ /* how many keys have been set in r[] */ ++ unsigned short rset; ++ /* whether s[] has been set */ + bool sset; ++ /* finalize key */ ++ u32 s[4]; ++ /* accumulator */ ++ struct poly1305_state h; ++ /* key */ ++ struct poly1305_key r[1]; + }; + + #endif diff --git a/target/linux/generic/backport-5.4/080-wireguard-0015-crypto-poly1305-expose-init-update-final-library-int.patch b/target/linux/generic/backport-5.4/080-wireguard-0015-crypto-poly1305-expose-init-update-final-library-int.patch new file mode 100644 index 0000000000..66c276267c --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0015-crypto-poly1305-expose-init-update-final-library-int.patch @@ -0,0 +1,225 @@ +From fd966ddf025b8b62aab20d2e4eb242fe51ad5137 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:21 +0100 +Subject: [PATCH 015/124] crypto: poly1305 - expose init/update/final library + interface + +commit a1d93064094cc5e24d64e35cf093e7191d0c9344 upstream. + +Expose the existing generic Poly1305 code via a init/update/final +library interface so that callers are not required to go through +the crypto API's shash abstraction to access it. At the same time, +make some preparations so that the library implementation can be +superseded by an accelerated arch-specific version in the future. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/poly1305_generic.c | 22 +----------- + include/crypto/poly1305.h | 38 +++++++++++++++++++- + lib/crypto/Kconfig | 26 ++++++++++++++ + lib/crypto/poly1305.c | 74 +++++++++++++++++++++++++++++++++++++++ + 4 files changed, 138 insertions(+), 22 deletions(-) + +--- a/crypto/poly1305_generic.c ++++ b/crypto/poly1305_generic.c +@@ -85,31 +85,11 @@ EXPORT_SYMBOL_GPL(crypto_poly1305_update + int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); +- __le32 digest[4]; +- u64 f = 0; + + if (unlikely(!dctx->sset)) + return -ENOKEY; + +- if (unlikely(dctx->buflen)) { +- dctx->buf[dctx->buflen++] = 1; +- memset(dctx->buf + dctx->buflen, 0, +- POLY1305_BLOCK_SIZE - dctx->buflen); +- poly1305_core_blocks(&dctx->h, dctx->r, dctx->buf, 1, 0); +- } +- +- poly1305_core_emit(&dctx->h, digest); +- +- /* mac = (h + s) % (2^128) */ +- f = (f >> 32) + le32_to_cpu(digest[0]) + dctx->s[0]; +- put_unaligned_le32(f, dst + 0); +- f = (f >> 32) + le32_to_cpu(digest[1]) + dctx->s[1]; +- put_unaligned_le32(f, dst + 4); +- f = (f >> 32) + le32_to_cpu(digest[2]) + dctx->s[2]; +- put_unaligned_le32(f, dst + 8); +- f = (f >> 32) + le32_to_cpu(digest[3]) + dctx->s[3]; +- put_unaligned_le32(f, dst + 12); +- ++ poly1305_final_generic(dctx, dst); + return 0; + } + EXPORT_SYMBOL_GPL(crypto_poly1305_final); +--- a/include/crypto/poly1305.h ++++ b/include/crypto/poly1305.h +@@ -35,7 +35,43 @@ struct poly1305_desc_ctx { + /* accumulator */ + struct poly1305_state h; + /* key */ +- struct poly1305_key r[1]; ++ struct poly1305_key r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE]; + }; + ++void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key); ++void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key); ++ ++static inline void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305)) ++ poly1305_init_arch(desc, key); ++ else ++ poly1305_init_generic(desc, key); ++} ++ ++void poly1305_update_arch(struct poly1305_desc_ctx *desc, const u8 *src, ++ unsigned int nbytes); ++void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src, ++ unsigned int nbytes); ++ ++static inline void poly1305_update(struct poly1305_desc_ctx *desc, ++ const u8 *src, unsigned int nbytes) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305)) ++ poly1305_update_arch(desc, src, nbytes); ++ else ++ poly1305_update_generic(desc, src, nbytes); ++} ++ ++void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest); ++void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *digest); ++ ++static inline void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305)) ++ poly1305_final_arch(desc, digest); ++ else ++ poly1305_final_generic(desc, digest); ++} ++ + #endif +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -37,8 +37,34 @@ config CRYPTO_LIB_CHACHA + config CRYPTO_LIB_DES + tristate + ++config CRYPTO_LIB_POLY1305_RSIZE ++ int ++ default 1 ++ ++config CRYPTO_ARCH_HAVE_LIB_POLY1305 ++ tristate ++ help ++ Declares whether the architecture provides an arch-specific ++ accelerated implementation of the Poly1305 library interface, ++ either builtin or as a module. ++ + config CRYPTO_LIB_POLY1305_GENERIC + tristate ++ help ++ This symbol can be depended upon by arch implementations of the ++ Poly1305 library interface that require the generic code as a ++ fallback, e.g., for SIMD implementations. If no arch specific ++ implementation is enabled, this implementation serves the users ++ of CRYPTO_LIB_POLY1305. ++ ++config CRYPTO_LIB_POLY1305 ++ tristate "Poly1305 library interface" ++ depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305 ++ select CRYPTO_LIB_POLY1305_GENERIC if CRYPTO_ARCH_HAVE_LIB_POLY1305=n ++ help ++ Enable the Poly1305 library interface. This interface may be fulfilled ++ by either the generic implementation or an arch-specific one, if one ++ is available and enabled. + + config CRYPTO_LIB_SHA256 + tristate +--- a/lib/crypto/poly1305.c ++++ b/lib/crypto/poly1305.c +@@ -154,5 +154,79 @@ void poly1305_core_emit(const struct pol + } + EXPORT_SYMBOL_GPL(poly1305_core_emit); + ++void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key) ++{ ++ poly1305_core_setkey(desc->r, key); ++ desc->s[0] = get_unaligned_le32(key + 16); ++ desc->s[1] = get_unaligned_le32(key + 20); ++ desc->s[2] = get_unaligned_le32(key + 24); ++ desc->s[3] = get_unaligned_le32(key + 28); ++ poly1305_core_init(&desc->h); ++ desc->buflen = 0; ++ desc->sset = true; ++ desc->rset = 1; ++} ++EXPORT_SYMBOL_GPL(poly1305_init_generic); ++ ++void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src, ++ unsigned int nbytes) ++{ ++ unsigned int bytes; ++ ++ if (unlikely(desc->buflen)) { ++ bytes = min(nbytes, POLY1305_BLOCK_SIZE - desc->buflen); ++ memcpy(desc->buf + desc->buflen, src, bytes); ++ src += bytes; ++ nbytes -= bytes; ++ desc->buflen += bytes; ++ ++ if (desc->buflen == POLY1305_BLOCK_SIZE) { ++ poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 1); ++ desc->buflen = 0; ++ } ++ } ++ ++ if (likely(nbytes >= POLY1305_BLOCK_SIZE)) { ++ poly1305_core_blocks(&desc->h, desc->r, src, ++ nbytes / POLY1305_BLOCK_SIZE, 1); ++ src += nbytes - (nbytes % POLY1305_BLOCK_SIZE); ++ nbytes %= POLY1305_BLOCK_SIZE; ++ } ++ ++ if (unlikely(nbytes)) { ++ desc->buflen = nbytes; ++ memcpy(desc->buf, src, nbytes); ++ } ++} ++EXPORT_SYMBOL_GPL(poly1305_update_generic); ++ ++void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *dst) ++{ ++ __le32 digest[4]; ++ u64 f = 0; ++ ++ if (unlikely(desc->buflen)) { ++ desc->buf[desc->buflen++] = 1; ++ memset(desc->buf + desc->buflen, 0, ++ POLY1305_BLOCK_SIZE - desc->buflen); ++ poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 0); ++ } ++ ++ poly1305_core_emit(&desc->h, digest); ++ ++ /* mac = (h + s) % (2^128) */ ++ f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0]; ++ put_unaligned_le32(f, dst + 0); ++ f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1]; ++ put_unaligned_le32(f, dst + 4); ++ f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2]; ++ put_unaligned_le32(f, dst + 8); ++ f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3]; ++ put_unaligned_le32(f, dst + 12); ++ ++ *desc = (struct poly1305_desc_ctx){}; ++} ++EXPORT_SYMBOL_GPL(poly1305_final_generic); ++ + MODULE_LICENSE("GPL"); + MODULE_AUTHOR("Martin Willi "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0016-crypto-x86-poly1305-depend-on-generic-library-not-ge.patch b/target/linux/generic/backport-5.4/080-wireguard-0016-crypto-x86-poly1305-depend-on-generic-library-not-ge.patch new file mode 100644 index 0000000000..a1fe77cd5a --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0016-crypto-x86-poly1305-depend-on-generic-library-not-ge.patch @@ -0,0 +1,217 @@ +From 0e610172b19b8f7c1ce829247ce5f302b25ad100 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:22 +0100 +Subject: [PATCH 016/124] crypto: x86/poly1305 - depend on generic library not + generic shash + +commit 1b2c6a5120489d41c8ea3b8dacd0b4586289b158 upstream. + +Remove the dependency on the generic Poly1305 driver. Instead, depend +on the generic library so that we only reuse code without pulling in +the generic skcipher implementation as well. + +While at it, remove the logic that prefers the non-SIMD path for short +inputs - this is no longer necessary after recent FPU handling changes +on x86. + +Since this removes the last remaining user of the routines exported +by the generic shash driver, unexport them and make them static. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 66 +++++++++++++++++++++++++----- + crypto/Kconfig | 2 +- + crypto/poly1305_generic.c | 11 ++--- + include/crypto/internal/poly1305.h | 9 ---- + 4 files changed, 60 insertions(+), 28 deletions(-) + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -34,6 +34,24 @@ static void poly1305_simd_mult(u32 *a, c + poly1305_block_sse2(a, m, b, 1); + } + ++static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx, ++ const u8 *src, unsigned int srclen) ++{ ++ unsigned int datalen; ++ ++ if (unlikely(!dctx->sset)) { ++ datalen = crypto_poly1305_setdesckey(dctx, src, srclen); ++ src += srclen - datalen; ++ srclen = datalen; ++ } ++ if (srclen >= POLY1305_BLOCK_SIZE) { ++ poly1305_core_blocks(&dctx->h, dctx->r, src, ++ srclen / POLY1305_BLOCK_SIZE, 1); ++ srclen %= POLY1305_BLOCK_SIZE; ++ } ++ return srclen; ++} ++ + static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, + const u8 *src, unsigned int srclen) + { +@@ -91,12 +109,6 @@ static int poly1305_simd_update(struct s + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int bytes; + +- /* kernel_fpu_begin/end is costly, use fallback for small updates */ +- if (srclen <= 288 || !crypto_simd_usable()) +- return crypto_poly1305_update(desc, src, srclen); +- +- kernel_fpu_begin(); +- + if (unlikely(dctx->buflen)) { + bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen); + memcpy(dctx->buf + dctx->buflen, src, bytes); +@@ -105,25 +117,57 @@ static int poly1305_simd_update(struct s + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { +- poly1305_simd_blocks(dctx, dctx->buf, +- POLY1305_BLOCK_SIZE); ++ if (likely(crypto_simd_usable())) { ++ kernel_fpu_begin(); ++ poly1305_simd_blocks(dctx, dctx->buf, ++ POLY1305_BLOCK_SIZE); ++ kernel_fpu_end(); ++ } else { ++ poly1305_scalar_blocks(dctx, dctx->buf, ++ POLY1305_BLOCK_SIZE); ++ } + dctx->buflen = 0; + } + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { +- bytes = poly1305_simd_blocks(dctx, src, srclen); ++ if (likely(crypto_simd_usable())) { ++ kernel_fpu_begin(); ++ bytes = poly1305_simd_blocks(dctx, src, srclen); ++ kernel_fpu_end(); ++ } else { ++ bytes = poly1305_scalar_blocks(dctx, src, srclen); ++ } + src += srclen - bytes; + srclen = bytes; + } + +- kernel_fpu_end(); +- + if (unlikely(srclen)) { + dctx->buflen = srclen; + memcpy(dctx->buf, src, srclen); + } ++} ++ ++static int crypto_poly1305_init(struct shash_desc *desc) ++{ ++ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); ++ ++ poly1305_core_init(&dctx->h); ++ dctx->buflen = 0; ++ dctx->rset = 0; ++ dctx->sset = false; ++ ++ return 0; ++} ++ ++static int crypto_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_generic(dctx, dst); + return 0; + } + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -697,7 +697,7 @@ config CRYPTO_POLY1305 + config CRYPTO_POLY1305_X86_64 + tristate "Poly1305 authenticator algorithm (x86_64/SSE2/AVX2)" + depends on X86 && 64BIT +- select CRYPTO_POLY1305 ++ select CRYPTO_LIB_POLY1305_GENERIC + help + Poly1305 authenticator algorithm, RFC7539. + +--- a/crypto/poly1305_generic.c ++++ b/crypto/poly1305_generic.c +@@ -19,7 +19,7 @@ + #include + #include + +-int crypto_poly1305_init(struct shash_desc *desc) ++static int crypto_poly1305_init(struct shash_desc *desc) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + +@@ -30,7 +30,6 @@ int crypto_poly1305_init(struct shash_de + + return 0; + } +-EXPORT_SYMBOL_GPL(crypto_poly1305_init); + + static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src, + unsigned int srclen) +@@ -47,8 +46,8 @@ static void poly1305_blocks(struct poly1 + srclen / POLY1305_BLOCK_SIZE, 1); + } + +-int crypto_poly1305_update(struct shash_desc *desc, +- const u8 *src, unsigned int srclen) ++static int crypto_poly1305_update(struct shash_desc *desc, ++ const u8 *src, unsigned int srclen) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int bytes; +@@ -80,9 +79,8 @@ int crypto_poly1305_update(struct shash_ + + return 0; + } +-EXPORT_SYMBOL_GPL(crypto_poly1305_update); + +-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) ++static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + +@@ -92,7 +90,6 @@ int crypto_poly1305_final(struct shash_d + poly1305_final_generic(dctx, dst); + return 0; + } +-EXPORT_SYMBOL_GPL(crypto_poly1305_final); + + static struct shash_alg poly1305_alg = { + .digestsize = POLY1305_DIGEST_SIZE, +--- a/include/crypto/internal/poly1305.h ++++ b/include/crypto/internal/poly1305.h +@@ -10,8 +10,6 @@ + #include + #include + +-struct shash_desc; +- + /* + * Poly1305 core functions. These implement the ε-almost-∆-universal hash + * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce +@@ -28,13 +26,6 @@ void poly1305_core_blocks(struct poly130 + unsigned int nblocks, u32 hibit); + void poly1305_core_emit(const struct poly1305_state *state, void *dst); + +-/* Crypto API helper functions for the Poly1305 MAC */ +-int crypto_poly1305_init(struct shash_desc *desc); +- +-int crypto_poly1305_update(struct shash_desc *desc, +- const u8 *src, unsigned int srclen); +-int crypto_poly1305_final(struct shash_desc *desc, u8 *dst); +- + /* + * Poly1305 requires a unique key for each tag, which implies that we can't set + * it on the tfm that gets accessed by multiple users simultaneously. Instead we diff --git a/target/linux/generic/backport-5.4/080-wireguard-0017-crypto-x86-poly1305-expose-existing-driver-as-poly13.patch b/target/linux/generic/backport-5.4/080-wireguard-0017-crypto-x86-poly1305-expose-existing-driver-as-poly13.patch new file mode 100644 index 0000000000..01037a6ee6 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0017-crypto-x86-poly1305-expose-existing-driver-as-poly13.patch @@ -0,0 +1,163 @@ +From 2ceb2e26de65cce974875e0487dde20bc5f1826c Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:23 +0100 +Subject: [PATCH 017/124] crypto: x86/poly1305 - expose existing driver as + poly1305 library + +commit f0e89bcfbb894e5844cd1bbf6b3cf7c63cb0f5ac upstream. + +Implement the arch init/update/final Poly1305 library routines in the +accelerated SIMD driver for x86 so they are accessible to users of +the Poly1305 library interface as well. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 57 ++++++++++++++++++++++++--------- + crypto/Kconfig | 1 + + lib/crypto/Kconfig | 1 + + 3 files changed, 43 insertions(+), 16 deletions(-) + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -21,7 +22,8 @@ asmlinkage void poly1305_2block_sse2(u32 + asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); + +-static bool poly1305_use_avx2 __ro_after_init; ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_simd); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2); + + static void poly1305_simd_mult(u32 *a, const u32 *b) + { +@@ -64,7 +66,7 @@ static unsigned int poly1305_simd_blocks + } + + if (IS_ENABLED(CONFIG_AS_AVX2) && +- poly1305_use_avx2 && ++ static_branch_likely(&poly1305_use_avx2) && + srclen >= POLY1305_BLOCK_SIZE * 4) { + if (unlikely(dctx->rset < 4)) { + if (dctx->rset < 2) { +@@ -103,10 +105,15 @@ static unsigned int poly1305_simd_blocks + return srclen; + } + +-static int poly1305_simd_update(struct shash_desc *desc, +- const u8 *src, unsigned int srclen) ++void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key) ++{ ++ poly1305_init_generic(desc, key); ++} ++EXPORT_SYMBOL(poly1305_init_arch); ++ ++void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, ++ unsigned int srclen) + { +- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int bytes; + + if (unlikely(dctx->buflen)) { +@@ -117,7 +124,8 @@ static int poly1305_simd_update(struct s + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { +- if (likely(crypto_simd_usable())) { ++ if (static_branch_likely(&poly1305_use_simd) && ++ likely(crypto_simd_usable())) { + kernel_fpu_begin(); + poly1305_simd_blocks(dctx, dctx->buf, + POLY1305_BLOCK_SIZE); +@@ -131,7 +139,8 @@ static int poly1305_simd_update(struct s + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { +- if (likely(crypto_simd_usable())) { ++ if (static_branch_likely(&poly1305_use_simd) && ++ likely(crypto_simd_usable())) { + kernel_fpu_begin(); + bytes = poly1305_simd_blocks(dctx, src, srclen); + kernel_fpu_end(); +@@ -147,6 +156,13 @@ static int poly1305_simd_update(struct s + memcpy(dctx->buf, src, srclen); + } + } ++EXPORT_SYMBOL(poly1305_update_arch); ++ ++void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest) ++{ ++ poly1305_final_generic(desc, digest); ++} ++EXPORT_SYMBOL(poly1305_final_arch); + + static int crypto_poly1305_init(struct shash_desc *desc) + { +@@ -171,6 +187,15 @@ static int crypto_poly1305_final(struct + return 0; + } + ++static int poly1305_simd_update(struct shash_desc *desc, ++ const u8 *src, unsigned int srclen) ++{ ++ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); ++ ++ poly1305_update_arch(dctx, src, srclen); ++ return 0; ++} ++ + static struct shash_alg alg = { + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_poly1305_init, +@@ -189,15 +214,15 @@ static struct shash_alg alg = { + static int __init poly1305_simd_mod_init(void) + { + if (!boot_cpu_has(X86_FEATURE_XMM2)) +- return -ENODEV; ++ return 0; + +- poly1305_use_avx2 = IS_ENABLED(CONFIG_AS_AVX2) && +- boot_cpu_has(X86_FEATURE_AVX) && +- boot_cpu_has(X86_FEATURE_AVX2) && +- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); +- alg.descsize = sizeof(struct poly1305_desc_ctx) + 5 * sizeof(u32); +- if (poly1305_use_avx2) +- alg.descsize += 10 * sizeof(u32); ++ static_branch_enable(&poly1305_use_simd); ++ ++ if (IS_ENABLED(CONFIG_AS_AVX2) && ++ boot_cpu_has(X86_FEATURE_AVX) && ++ boot_cpu_has(X86_FEATURE_AVX2) && ++ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) ++ static_branch_enable(&poly1305_use_avx2); + + return crypto_register_shash(&alg); + } +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -698,6 +698,7 @@ config CRYPTO_POLY1305_X86_64 + tristate "Poly1305 authenticator algorithm (x86_64/SSE2/AVX2)" + depends on X86 && 64BIT + select CRYPTO_LIB_POLY1305_GENERIC ++ select CRYPTO_ARCH_HAVE_LIB_POLY1305 + help + Poly1305 authenticator algorithm, RFC7539. + +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -39,6 +39,7 @@ config CRYPTO_LIB_DES + + config CRYPTO_LIB_POLY1305_RSIZE + int ++ default 4 if X86_64 + default 1 + + config CRYPTO_ARCH_HAVE_LIB_POLY1305 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0018-crypto-arm64-poly1305-incorporate-OpenSSL-CRYPTOGAMS.patch b/target/linux/generic/backport-5.4/080-wireguard-0018-crypto-arm64-poly1305-incorporate-OpenSSL-CRYPTOGAMS.patch new file mode 100644 index 0000000000..6596441950 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0018-crypto-arm64-poly1305-incorporate-OpenSSL-CRYPTOGAMS.patch @@ -0,0 +1,2083 @@ +From 335ed336e74d7dcb152025ab65c2ffeceb15c690 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:24 +0100 +Subject: [PATCH 018/124] crypto: arm64/poly1305 - incorporate + OpenSSL/CRYPTOGAMS NEON implementation + +commit f569ca16475155013525686d0f73bc379c67e635 upstream. + +This is a straight import of the OpenSSL/CRYPTOGAMS Poly1305 implementation +for NEON authored by Andy Polyakov, and contributed by him to the OpenSSL +project. The file 'poly1305-armv8.pl' is taken straight from this upstream +GitHub repository [0] at commit ec55a08dc0244ce570c4fc7cade330c60798952f, +and already contains all the changes required to build it as part of a +Linux kernel module. + +[0] https://github.com/dot-asm/cryptogams + +Co-developed-by: Andy Polyakov +Signed-off-by: Andy Polyakov +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm64/crypto/Kconfig | 6 + + arch/arm64/crypto/Makefile | 10 +- + arch/arm64/crypto/poly1305-armv8.pl | 913 ++++++++++++++++++++++ + arch/arm64/crypto/poly1305-core.S_shipped | 835 ++++++++++++++++++++ + arch/arm64/crypto/poly1305-glue.c | 237 ++++++ + lib/crypto/Kconfig | 1 + + 6 files changed, 2001 insertions(+), 1 deletion(-) + create mode 100644 arch/arm64/crypto/poly1305-armv8.pl + create mode 100644 arch/arm64/crypto/poly1305-core.S_shipped + create mode 100644 arch/arm64/crypto/poly1305-glue.c + +--- a/arch/arm64/crypto/Kconfig ++++ b/arch/arm64/crypto/Kconfig +@@ -106,6 +106,12 @@ config CRYPTO_CHACHA20_NEON + select CRYPTO_LIB_CHACHA_GENERIC + select CRYPTO_ARCH_HAVE_LIB_CHACHA + ++config CRYPTO_POLY1305_NEON ++ tristate "Poly1305 hash function using scalar or NEON instructions" ++ depends on KERNEL_MODE_NEON ++ select CRYPTO_HASH ++ select CRYPTO_ARCH_HAVE_LIB_POLY1305 ++ + config CRYPTO_NHPOLY1305_NEON + tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)" + depends on KERNEL_MODE_NEON +--- a/arch/arm64/crypto/Makefile ++++ b/arch/arm64/crypto/Makefile +@@ -50,6 +50,10 @@ sha512-arm64-y := sha512-glue.o sha512-c + obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o + chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o + ++obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o ++poly1305-neon-y := poly1305-core.o poly1305-glue.o ++AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64 ++ + obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o + nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o + +@@ -68,11 +72,15 @@ ifdef REGENERATE_ARM64_CRYPTO + quiet_cmd_perlasm = PERLASM $@ + cmd_perlasm = $(PERL) $(<) void $(@) + ++$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv8.pl ++ $(call cmd,perlasm) ++ + $(src)/sha256-core.S_shipped: $(src)/sha512-armv8.pl + $(call cmd,perlasm) + + $(src)/sha512-core.S_shipped: $(src)/sha512-armv8.pl + $(call cmd,perlasm) ++ + endif + +-clean-files += sha256-core.S sha512-core.S ++clean-files += poly1305-core.S sha256-core.S sha512-core.S +--- /dev/null ++++ b/arch/arm64/crypto/poly1305-armv8.pl +@@ -0,0 +1,913 @@ ++#!/usr/bin/env perl ++# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause ++# ++# ==================================================================== ++# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL ++# project. ++# ==================================================================== ++# ++# This module implements Poly1305 hash for ARMv8. ++# ++# June 2015 ++# ++# Numbers are cycles per processed byte with poly1305_blocks alone. ++# ++# IALU/gcc-4.9 NEON ++# ++# Apple A7 1.86/+5% 0.72 ++# Cortex-A53 2.69/+58% 1.47 ++# Cortex-A57 2.70/+7% 1.14 ++# Denver 1.64/+50% 1.18(*) ++# X-Gene 2.13/+68% 2.27 ++# Mongoose 1.77/+75% 1.12 ++# Kryo 2.70/+55% 1.13 ++# ThunderX2 1.17/+95% 1.36 ++# ++# (*) estimate based on resources availability is less than 1.0, ++# i.e. measured result is worse than expected, presumably binary ++# translator is not almighty; ++ ++$flavour=shift; ++$output=shift; ++ ++if ($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"; ++} ++ ++my ($ctx,$inp,$len,$padbit) = map("x$_",(0..3)); ++my ($mac,$nonce)=($inp,$len); ++ ++my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14)); ++ ++$code.=<<___; ++#ifndef __KERNEL__ ++# include "arm_arch.h" ++.extern OPENSSL_armcap_P ++#endif ++ ++.text ++ ++// forward "declarations" are required for Apple ++.globl poly1305_blocks ++.globl poly1305_emit ++ ++.globl poly1305_init ++.type poly1305_init,%function ++.align 5 ++poly1305_init: ++ cmp $inp,xzr ++ stp xzr,xzr,[$ctx] // zero hash value ++ stp xzr,xzr,[$ctx,#16] // [along with is_base2_26] ++ ++ csel x0,xzr,x0,eq ++ b.eq .Lno_key ++ ++#ifndef __KERNEL__ ++ adrp x17,OPENSSL_armcap_P ++ ldr w17,[x17,#:lo12:OPENSSL_armcap_P] ++#endif ++ ++ ldp $r0,$r1,[$inp] // load key ++ mov $s1,#0xfffffffc0fffffff ++ movk $s1,#0x0fff,lsl#48 ++#ifdef __AARCH64EB__ ++ rev $r0,$r0 // flip bytes ++ rev $r1,$r1 ++#endif ++ and $r0,$r0,$s1 // &=0ffffffc0fffffff ++ and $s1,$s1,#-4 ++ and $r1,$r1,$s1 // &=0ffffffc0ffffffc ++ mov w#$s1,#-1 ++ stp $r0,$r1,[$ctx,#32] // save key value ++ str w#$s1,[$ctx,#48] // impossible key power value ++ ++#ifndef __KERNEL__ ++ tst w17,#ARMV7_NEON ++ ++ adr $d0,.Lpoly1305_blocks ++ adr $r0,.Lpoly1305_blocks_neon ++ adr $d1,.Lpoly1305_emit ++ ++ csel $d0,$d0,$r0,eq ++ ++# ifdef __ILP32__ ++ stp w#$d0,w#$d1,[$len] ++# else ++ stp $d0,$d1,[$len] ++# endif ++#endif ++ mov x0,#1 ++.Lno_key: ++ ret ++.size poly1305_init,.-poly1305_init ++ ++.type poly1305_blocks,%function ++.align 5 ++poly1305_blocks: ++.Lpoly1305_blocks: ++ ands $len,$len,#-16 ++ b.eq .Lno_data ++ ++ ldp $h0,$h1,[$ctx] // load hash value ++ ldp $h2,x17,[$ctx,#16] // [along with is_base2_26] ++ ldp $r0,$r1,[$ctx,#32] // load key value ++ ++#ifdef __AARCH64EB__ ++ lsr $d0,$h0,#32 ++ mov w#$d1,w#$h0 ++ lsr $d2,$h1,#32 ++ mov w15,w#$h1 ++ lsr x16,$h2,#32 ++#else ++ mov w#$d0,w#$h0 ++ lsr $d1,$h0,#32 ++ mov w#$d2,w#$h1 ++ lsr x15,$h1,#32 ++ mov w16,w#$h2 ++#endif ++ ++ add $d0,$d0,$d1,lsl#26 // base 2^26 -> base 2^64 ++ lsr $d1,$d2,#12 ++ adds $d0,$d0,$d2,lsl#52 ++ add $d1,$d1,x15,lsl#14 ++ adc $d1,$d1,xzr ++ lsr $d2,x16,#24 ++ adds $d1,$d1,x16,lsl#40 ++ adc $d2,$d2,xzr ++ ++ cmp x17,#0 // is_base2_26? ++ add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) ++ csel $h0,$h0,$d0,eq // choose between radixes ++ csel $h1,$h1,$d1,eq ++ csel $h2,$h2,$d2,eq ++ ++.Loop: ++ ldp $t0,$t1,[$inp],#16 // load input ++ sub $len,$len,#16 ++#ifdef __AARCH64EB__ ++ rev $t0,$t0 ++ rev $t1,$t1 ++#endif ++ adds $h0,$h0,$t0 // accumulate input ++ adcs $h1,$h1,$t1 ++ ++ mul $d0,$h0,$r0 // h0*r0 ++ adc $h2,$h2,$padbit ++ umulh $d1,$h0,$r0 ++ ++ mul $t0,$h1,$s1 // h1*5*r1 ++ umulh $t1,$h1,$s1 ++ ++ adds $d0,$d0,$t0 ++ mul $t0,$h0,$r1 // h0*r1 ++ adc $d1,$d1,$t1 ++ umulh $d2,$h0,$r1 ++ ++ adds $d1,$d1,$t0 ++ mul $t0,$h1,$r0 // h1*r0 ++ adc $d2,$d2,xzr ++ umulh $t1,$h1,$r0 ++ ++ adds $d1,$d1,$t0 ++ mul $t0,$h2,$s1 // h2*5*r1 ++ adc $d2,$d2,$t1 ++ mul $t1,$h2,$r0 // h2*r0 ++ ++ adds $d1,$d1,$t0 ++ adc $d2,$d2,$t1 ++ ++ and $t0,$d2,#-4 // final reduction ++ and $h2,$d2,#3 ++ add $t0,$t0,$d2,lsr#2 ++ adds $h0,$d0,$t0 ++ adcs $h1,$d1,xzr ++ adc $h2,$h2,xzr ++ ++ cbnz $len,.Loop ++ ++ stp $h0,$h1,[$ctx] // store hash value ++ stp $h2,xzr,[$ctx,#16] // [and clear is_base2_26] ++ ++.Lno_data: ++ ret ++.size poly1305_blocks,.-poly1305_blocks ++ ++.type poly1305_emit,%function ++.align 5 ++poly1305_emit: ++.Lpoly1305_emit: ++ ldp $h0,$h1,[$ctx] // load hash base 2^64 ++ ldp $h2,$r0,[$ctx,#16] // [along with is_base2_26] ++ ldp $t0,$t1,[$nonce] // load nonce ++ ++#ifdef __AARCH64EB__ ++ lsr $d0,$h0,#32 ++ mov w#$d1,w#$h0 ++ lsr $d2,$h1,#32 ++ mov w15,w#$h1 ++ lsr x16,$h2,#32 ++#else ++ mov w#$d0,w#$h0 ++ lsr $d1,$h0,#32 ++ mov w#$d2,w#$h1 ++ lsr x15,$h1,#32 ++ mov w16,w#$h2 ++#endif ++ ++ add $d0,$d0,$d1,lsl#26 // base 2^26 -> base 2^64 ++ lsr $d1,$d2,#12 ++ adds $d0,$d0,$d2,lsl#52 ++ add $d1,$d1,x15,lsl#14 ++ adc $d1,$d1,xzr ++ lsr $d2,x16,#24 ++ adds $d1,$d1,x16,lsl#40 ++ adc $d2,$d2,xzr ++ ++ cmp $r0,#0 // is_base2_26? ++ csel $h0,$h0,$d0,eq // choose between radixes ++ csel $h1,$h1,$d1,eq ++ csel $h2,$h2,$d2,eq ++ ++ adds $d0,$h0,#5 // compare to modulus ++ adcs $d1,$h1,xzr ++ adc $d2,$h2,xzr ++ ++ tst $d2,#-4 // see if it's carried/borrowed ++ ++ csel $h0,$h0,$d0,eq ++ csel $h1,$h1,$d1,eq ++ ++#ifdef __AARCH64EB__ ++ ror $t0,$t0,#32 // flip nonce words ++ ror $t1,$t1,#32 ++#endif ++ adds $h0,$h0,$t0 // accumulate nonce ++ adc $h1,$h1,$t1 ++#ifdef __AARCH64EB__ ++ rev $h0,$h0 // flip output bytes ++ rev $h1,$h1 ++#endif ++ stp $h0,$h1,[$mac] // write result ++ ++ ret ++.size poly1305_emit,.-poly1305_emit ++___ ++my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("v$_.4s",(0..8)); ++my ($IN01_0,$IN01_1,$IN01_2,$IN01_3,$IN01_4) = map("v$_.2s",(9..13)); ++my ($IN23_0,$IN23_1,$IN23_2,$IN23_3,$IN23_4) = map("v$_.2s",(14..18)); ++my ($ACC0,$ACC1,$ACC2,$ACC3,$ACC4) = map("v$_.2d",(19..23)); ++my ($H0,$H1,$H2,$H3,$H4) = map("v$_.2s",(24..28)); ++my ($T0,$T1,$MASK) = map("v$_",(29..31)); ++ ++my ($in2,$zeros)=("x16","x17"); ++my $is_base2_26 = $zeros; # borrow ++ ++$code.=<<___; ++.type poly1305_mult,%function ++.align 5 ++poly1305_mult: ++ mul $d0,$h0,$r0 // h0*r0 ++ umulh $d1,$h0,$r0 ++ ++ mul $t0,$h1,$s1 // h1*5*r1 ++ umulh $t1,$h1,$s1 ++ ++ adds $d0,$d0,$t0 ++ mul $t0,$h0,$r1 // h0*r1 ++ adc $d1,$d1,$t1 ++ umulh $d2,$h0,$r1 ++ ++ adds $d1,$d1,$t0 ++ mul $t0,$h1,$r0 // h1*r0 ++ adc $d2,$d2,xzr ++ umulh $t1,$h1,$r0 ++ ++ adds $d1,$d1,$t0 ++ mul $t0,$h2,$s1 // h2*5*r1 ++ adc $d2,$d2,$t1 ++ mul $t1,$h2,$r0 // h2*r0 ++ ++ adds $d1,$d1,$t0 ++ adc $d2,$d2,$t1 ++ ++ and $t0,$d2,#-4 // final reduction ++ and $h2,$d2,#3 ++ add $t0,$t0,$d2,lsr#2 ++ adds $h0,$d0,$t0 ++ adcs $h1,$d1,xzr ++ adc $h2,$h2,xzr ++ ++ ret ++.size poly1305_mult,.-poly1305_mult ++ ++.type poly1305_splat,%function ++.align 4 ++poly1305_splat: ++ and x12,$h0,#0x03ffffff // base 2^64 -> base 2^26 ++ ubfx x13,$h0,#26,#26 ++ extr x14,$h1,$h0,#52 ++ and x14,x14,#0x03ffffff ++ ubfx x15,$h1,#14,#26 ++ extr x16,$h2,$h1,#40 ++ ++ str w12,[$ctx,#16*0] // r0 ++ add w12,w13,w13,lsl#2 // r1*5 ++ str w13,[$ctx,#16*1] // r1 ++ add w13,w14,w14,lsl#2 // r2*5 ++ str w12,[$ctx,#16*2] // s1 ++ str w14,[$ctx,#16*3] // r2 ++ add w14,w15,w15,lsl#2 // r3*5 ++ str w13,[$ctx,#16*4] // s2 ++ str w15,[$ctx,#16*5] // r3 ++ add w15,w16,w16,lsl#2 // r4*5 ++ str w14,[$ctx,#16*6] // s3 ++ str w16,[$ctx,#16*7] // r4 ++ str w15,[$ctx,#16*8] // s4 ++ ++ ret ++.size poly1305_splat,.-poly1305_splat ++ ++#ifdef __KERNEL__ ++.globl poly1305_blocks_neon ++#endif ++.type poly1305_blocks_neon,%function ++.align 5 ++poly1305_blocks_neon: ++.Lpoly1305_blocks_neon: ++ ldr $is_base2_26,[$ctx,#24] ++ cmp $len,#128 ++ b.lo .Lpoly1305_blocks ++ ++ .inst 0xd503233f // paciasp ++ stp x29,x30,[sp,#-80]! ++ add x29,sp,#0 ++ ++ stp d8,d9,[sp,#16] // meet ABI requirements ++ stp d10,d11,[sp,#32] ++ stp d12,d13,[sp,#48] ++ stp d14,d15,[sp,#64] ++ ++ cbz $is_base2_26,.Lbase2_64_neon ++ ++ ldp w10,w11,[$ctx] // load hash value base 2^26 ++ ldp w12,w13,[$ctx,#8] ++ ldr w14,[$ctx,#16] ++ ++ tst $len,#31 ++ b.eq .Leven_neon ++ ++ ldp $r0,$r1,[$ctx,#32] // load key value ++ ++ add $h0,x10,x11,lsl#26 // base 2^26 -> base 2^64 ++ lsr $h1,x12,#12 ++ adds $h0,$h0,x12,lsl#52 ++ add $h1,$h1,x13,lsl#14 ++ adc $h1,$h1,xzr ++ lsr $h2,x14,#24 ++ adds $h1,$h1,x14,lsl#40 ++ adc $d2,$h2,xzr // can be partially reduced... ++ ++ ldp $d0,$d1,[$inp],#16 // load input ++ sub $len,$len,#16 ++ add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) ++ ++#ifdef __AARCH64EB__ ++ rev $d0,$d0 ++ rev $d1,$d1 ++#endif ++ adds $h0,$h0,$d0 // accumulate input ++ adcs $h1,$h1,$d1 ++ adc $h2,$h2,$padbit ++ ++ bl poly1305_mult ++ ++ and x10,$h0,#0x03ffffff // base 2^64 -> base 2^26 ++ ubfx x11,$h0,#26,#26 ++ extr x12,$h1,$h0,#52 ++ and x12,x12,#0x03ffffff ++ ubfx x13,$h1,#14,#26 ++ extr x14,$h2,$h1,#40 ++ ++ b .Leven_neon ++ ++.align 4 ++.Lbase2_64_neon: ++ ldp $r0,$r1,[$ctx,#32] // load key value ++ ++ ldp $h0,$h1,[$ctx] // load hash value base 2^64 ++ ldr $h2,[$ctx,#16] ++ ++ tst $len,#31 ++ b.eq .Linit_neon ++ ++ ldp $d0,$d1,[$inp],#16 // load input ++ sub $len,$len,#16 ++ add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) ++#ifdef __AARCH64EB__ ++ rev $d0,$d0 ++ rev $d1,$d1 ++#endif ++ adds $h0,$h0,$d0 // accumulate input ++ adcs $h1,$h1,$d1 ++ adc $h2,$h2,$padbit ++ ++ bl poly1305_mult ++ ++.Linit_neon: ++ ldr w17,[$ctx,#48] // first table element ++ and x10,$h0,#0x03ffffff // base 2^64 -> base 2^26 ++ ubfx x11,$h0,#26,#26 ++ extr x12,$h1,$h0,#52 ++ and x12,x12,#0x03ffffff ++ ubfx x13,$h1,#14,#26 ++ extr x14,$h2,$h1,#40 ++ ++ cmp w17,#-1 // is value impossible? ++ b.ne .Leven_neon ++ ++ fmov ${H0},x10 ++ fmov ${H1},x11 ++ fmov ${H2},x12 ++ fmov ${H3},x13 ++ fmov ${H4},x14 ++ ++ ////////////////////////////////// initialize r^n table ++ mov $h0,$r0 // r^1 ++ add $s1,$r1,$r1,lsr#2 // s1 = r1 + (r1 >> 2) ++ mov $h1,$r1 ++ mov $h2,xzr ++ add $ctx,$ctx,#48+12 ++ bl poly1305_splat ++ ++ bl poly1305_mult // r^2 ++ sub $ctx,$ctx,#4 ++ bl poly1305_splat ++ ++ bl poly1305_mult // r^3 ++ sub $ctx,$ctx,#4 ++ bl poly1305_splat ++ ++ bl poly1305_mult // r^4 ++ sub $ctx,$ctx,#4 ++ bl poly1305_splat ++ sub $ctx,$ctx,#48 // restore original $ctx ++ b .Ldo_neon ++ ++.align 4 ++.Leven_neon: ++ fmov ${H0},x10 ++ fmov ${H1},x11 ++ fmov ${H2},x12 ++ fmov ${H3},x13 ++ fmov ${H4},x14 ++ ++.Ldo_neon: ++ ldp x8,x12,[$inp,#32] // inp[2:3] ++ subs $len,$len,#64 ++ ldp x9,x13,[$inp,#48] ++ add $in2,$inp,#96 ++ adr $zeros,.Lzeros ++ ++ lsl $padbit,$padbit,#24 ++ add x15,$ctx,#48 ++ ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ and x5,x9,#0x03ffffff ++ ubfx x6,x8,#26,#26 ++ ubfx x7,x9,#26,#26 ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ extr x8,x12,x8,#52 ++ extr x9,x13,x9,#52 ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ fmov $IN23_0,x4 ++ and x8,x8,#0x03ffffff ++ and x9,x9,#0x03ffffff ++ ubfx x10,x12,#14,#26 ++ ubfx x11,x13,#14,#26 ++ add x12,$padbit,x12,lsr#40 ++ add x13,$padbit,x13,lsr#40 ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ fmov $IN23_1,x6 ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ fmov $IN23_2,x8 ++ fmov $IN23_3,x10 ++ fmov $IN23_4,x12 ++ ++ ldp x8,x12,[$inp],#16 // inp[0:1] ++ ldp x9,x13,[$inp],#48 ++ ++ ld1 {$R0,$R1,$S1,$R2},[x15],#64 ++ ld1 {$S2,$R3,$S3,$R4},[x15],#64 ++ ld1 {$S4},[x15] ++ ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ and x5,x9,#0x03ffffff ++ ubfx x6,x8,#26,#26 ++ ubfx x7,x9,#26,#26 ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ extr x8,x12,x8,#52 ++ extr x9,x13,x9,#52 ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ fmov $IN01_0,x4 ++ and x8,x8,#0x03ffffff ++ and x9,x9,#0x03ffffff ++ ubfx x10,x12,#14,#26 ++ ubfx x11,x13,#14,#26 ++ add x12,$padbit,x12,lsr#40 ++ add x13,$padbit,x13,lsr#40 ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ fmov $IN01_1,x6 ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ movi $MASK.2d,#-1 ++ fmov $IN01_2,x8 ++ fmov $IN01_3,x10 ++ fmov $IN01_4,x12 ++ ushr $MASK.2d,$MASK.2d,#38 ++ ++ b.ls .Lskip_loop ++ ++.align 4 ++.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 = h0*r4 + h1*r3 + h2*r2 + h3*r1 + h4*r0 ++ // d3 = h0*r3 + h1*r2 + h2*r1 + h3*r0 + h4*5*r4 ++ // d2 = h0*r2 + h1*r1 + h2*r0 + h3*5*r4 + h4*5*r3 ++ // d1 = h0*r1 + h1*r0 + h2*5*r4 + h3*5*r3 + h4*5*r2 ++ // d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1 ++ ++ subs $len,$len,#64 ++ umull $ACC4,$IN23_0,${R4}[2] ++ csel $in2,$zeros,$in2,lo ++ umull $ACC3,$IN23_0,${R3}[2] ++ umull $ACC2,$IN23_0,${R2}[2] ++ ldp x8,x12,[$in2],#16 // inp[2:3] (or zero) ++ umull $ACC1,$IN23_0,${R1}[2] ++ ldp x9,x13,[$in2],#48 ++ umull $ACC0,$IN23_0,${R0}[2] ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ ++ umlal $ACC4,$IN23_1,${R3}[2] ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ umlal $ACC3,$IN23_1,${R2}[2] ++ and x5,x9,#0x03ffffff ++ umlal $ACC2,$IN23_1,${R1}[2] ++ ubfx x6,x8,#26,#26 ++ umlal $ACC1,$IN23_1,${R0}[2] ++ ubfx x7,x9,#26,#26 ++ umlal $ACC0,$IN23_1,${S4}[2] ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ ++ umlal $ACC4,$IN23_2,${R2}[2] ++ extr x8,x12,x8,#52 ++ umlal $ACC3,$IN23_2,${R1}[2] ++ extr x9,x13,x9,#52 ++ umlal $ACC2,$IN23_2,${R0}[2] ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ umlal $ACC1,$IN23_2,${S4}[2] ++ fmov $IN23_0,x4 ++ umlal $ACC0,$IN23_2,${S3}[2] ++ and x8,x8,#0x03ffffff ++ ++ umlal $ACC4,$IN23_3,${R1}[2] ++ and x9,x9,#0x03ffffff ++ umlal $ACC3,$IN23_3,${R0}[2] ++ ubfx x10,x12,#14,#26 ++ umlal $ACC2,$IN23_3,${S4}[2] ++ ubfx x11,x13,#14,#26 ++ umlal $ACC1,$IN23_3,${S3}[2] ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ umlal $ACC0,$IN23_3,${S2}[2] ++ fmov $IN23_1,x6 ++ ++ add $IN01_2,$IN01_2,$H2 ++ add x12,$padbit,x12,lsr#40 ++ umlal $ACC4,$IN23_4,${R0}[2] ++ add x13,$padbit,x13,lsr#40 ++ umlal $ACC3,$IN23_4,${S4}[2] ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ umlal $ACC2,$IN23_4,${S3}[2] ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ umlal $ACC1,$IN23_4,${S2}[2] ++ fmov $IN23_2,x8 ++ umlal $ACC0,$IN23_4,${S1}[2] ++ fmov $IN23_3,x10 ++ ++ //////////////////////////////////////////////////////////////// ++ // (hash+inp[0:1])*r^4 and accumulate ++ ++ add $IN01_0,$IN01_0,$H0 ++ fmov $IN23_4,x12 ++ umlal $ACC3,$IN01_2,${R1}[0] ++ ldp x8,x12,[$inp],#16 // inp[0:1] ++ umlal $ACC0,$IN01_2,${S3}[0] ++ ldp x9,x13,[$inp],#48 ++ umlal $ACC4,$IN01_2,${R2}[0] ++ umlal $ACC1,$IN01_2,${S4}[0] ++ umlal $ACC2,$IN01_2,${R0}[0] ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ ++ add $IN01_1,$IN01_1,$H1 ++ umlal $ACC3,$IN01_0,${R3}[0] ++ umlal $ACC4,$IN01_0,${R4}[0] ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ umlal $ACC2,$IN01_0,${R2}[0] ++ and x5,x9,#0x03ffffff ++ umlal $ACC0,$IN01_0,${R0}[0] ++ ubfx x6,x8,#26,#26 ++ umlal $ACC1,$IN01_0,${R1}[0] ++ ubfx x7,x9,#26,#26 ++ ++ add $IN01_3,$IN01_3,$H3 ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ umlal $ACC3,$IN01_1,${R2}[0] ++ extr x8,x12,x8,#52 ++ umlal $ACC4,$IN01_1,${R3}[0] ++ extr x9,x13,x9,#52 ++ umlal $ACC0,$IN01_1,${S4}[0] ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ umlal $ACC2,$IN01_1,${R1}[0] ++ fmov $IN01_0,x4 ++ umlal $ACC1,$IN01_1,${R0}[0] ++ and x8,x8,#0x03ffffff ++ ++ add $IN01_4,$IN01_4,$H4 ++ and x9,x9,#0x03ffffff ++ umlal $ACC3,$IN01_3,${R0}[0] ++ ubfx x10,x12,#14,#26 ++ umlal $ACC0,$IN01_3,${S2}[0] ++ ubfx x11,x13,#14,#26 ++ umlal $ACC4,$IN01_3,${R1}[0] ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ umlal $ACC1,$IN01_3,${S3}[0] ++ fmov $IN01_1,x6 ++ umlal $ACC2,$IN01_3,${S4}[0] ++ add x12,$padbit,x12,lsr#40 ++ ++ umlal $ACC3,$IN01_4,${S4}[0] ++ add x13,$padbit,x13,lsr#40 ++ umlal $ACC0,$IN01_4,${S1}[0] ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ umlal $ACC4,$IN01_4,${R0}[0] ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ umlal $ACC1,$IN01_4,${S2}[0] ++ fmov $IN01_2,x8 ++ umlal $ACC2,$IN01_4,${S3}[0] ++ fmov $IN01_3,x10 ++ fmov $IN01_4,x12 ++ ++ ///////////////////////////////////////////////////////////////// ++ // lazy reduction as discussed in "NEON crypto" by D.J. Bernstein ++ // and P. Schwabe ++ // ++ // [see discussion in poly1305-armv4 module] ++ ++ ushr $T0.2d,$ACC3,#26 ++ xtn $H3,$ACC3 ++ ushr $T1.2d,$ACC0,#26 ++ and $ACC0,$ACC0,$MASK.2d ++ add $ACC4,$ACC4,$T0.2d // h3 -> h4 ++ bic $H3,#0xfc,lsl#24 // &=0x03ffffff ++ add $ACC1,$ACC1,$T1.2d // h0 -> h1 ++ ++ ushr $T0.2d,$ACC4,#26 ++ xtn $H4,$ACC4 ++ ushr $T1.2d,$ACC1,#26 ++ xtn $H1,$ACC1 ++ bic $H4,#0xfc,lsl#24 ++ add $ACC2,$ACC2,$T1.2d // h1 -> h2 ++ ++ add $ACC0,$ACC0,$T0.2d ++ shl $T0.2d,$T0.2d,#2 ++ shrn $T1.2s,$ACC2,#26 ++ xtn $H2,$ACC2 ++ add $ACC0,$ACC0,$T0.2d // h4 -> h0 ++ bic $H1,#0xfc,lsl#24 ++ add $H3,$H3,$T1.2s // h2 -> h3 ++ bic $H2,#0xfc,lsl#24 ++ ++ shrn $T0.2s,$ACC0,#26 ++ xtn $H0,$ACC0 ++ ushr $T1.2s,$H3,#26 ++ bic $H3,#0xfc,lsl#24 ++ bic $H0,#0xfc,lsl#24 ++ add $H1,$H1,$T0.2s // h0 -> h1 ++ add $H4,$H4,$T1.2s // h3 -> h4 ++ ++ b.hi .Loop_neon ++ ++.Lskip_loop: ++ dup $IN23_2,${IN23_2}[0] ++ add $IN01_2,$IN01_2,$H2 ++ ++ //////////////////////////////////////////////////////////////// ++ // multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 ++ ++ adds $len,$len,#32 ++ b.ne .Long_tail ++ ++ dup $IN23_2,${IN01_2}[0] ++ add $IN23_0,$IN01_0,$H0 ++ add $IN23_3,$IN01_3,$H3 ++ add $IN23_1,$IN01_1,$H1 ++ add $IN23_4,$IN01_4,$H4 ++ ++.Long_tail: ++ dup $IN23_0,${IN23_0}[0] ++ umull2 $ACC0,$IN23_2,${S3} ++ umull2 $ACC3,$IN23_2,${R1} ++ umull2 $ACC4,$IN23_2,${R2} ++ umull2 $ACC2,$IN23_2,${R0} ++ umull2 $ACC1,$IN23_2,${S4} ++ ++ dup $IN23_1,${IN23_1}[0] ++ umlal2 $ACC0,$IN23_0,${R0} ++ umlal2 $ACC2,$IN23_0,${R2} ++ umlal2 $ACC3,$IN23_0,${R3} ++ umlal2 $ACC4,$IN23_0,${R4} ++ umlal2 $ACC1,$IN23_0,${R1} ++ ++ dup $IN23_3,${IN23_3}[0] ++ umlal2 $ACC0,$IN23_1,${S4} ++ umlal2 $ACC3,$IN23_1,${R2} ++ umlal2 $ACC2,$IN23_1,${R1} ++ umlal2 $ACC4,$IN23_1,${R3} ++ umlal2 $ACC1,$IN23_1,${R0} ++ ++ dup $IN23_4,${IN23_4}[0] ++ umlal2 $ACC3,$IN23_3,${R0} ++ umlal2 $ACC4,$IN23_3,${R1} ++ umlal2 $ACC0,$IN23_3,${S2} ++ umlal2 $ACC1,$IN23_3,${S3} ++ umlal2 $ACC2,$IN23_3,${S4} ++ ++ umlal2 $ACC3,$IN23_4,${S4} ++ umlal2 $ACC0,$IN23_4,${S1} ++ umlal2 $ACC4,$IN23_4,${R0} ++ umlal2 $ACC1,$IN23_4,${S2} ++ umlal2 $ACC2,$IN23_4,${S3} ++ ++ b.eq .Lshort_tail ++ ++ //////////////////////////////////////////////////////////////// ++ // (hash+inp[0:1])*r^4:r^3 and accumulate ++ ++ add $IN01_0,$IN01_0,$H0 ++ umlal $ACC3,$IN01_2,${R1} ++ umlal $ACC0,$IN01_2,${S3} ++ umlal $ACC4,$IN01_2,${R2} ++ umlal $ACC1,$IN01_2,${S4} ++ umlal $ACC2,$IN01_2,${R0} ++ ++ add $IN01_1,$IN01_1,$H1 ++ umlal $ACC3,$IN01_0,${R3} ++ umlal $ACC0,$IN01_0,${R0} ++ umlal $ACC4,$IN01_0,${R4} ++ umlal $ACC1,$IN01_0,${R1} ++ umlal $ACC2,$IN01_0,${R2} ++ ++ add $IN01_3,$IN01_3,$H3 ++ umlal $ACC3,$IN01_1,${R2} ++ umlal $ACC0,$IN01_1,${S4} ++ umlal $ACC4,$IN01_1,${R3} ++ umlal $ACC1,$IN01_1,${R0} ++ umlal $ACC2,$IN01_1,${R1} ++ ++ add $IN01_4,$IN01_4,$H4 ++ umlal $ACC3,$IN01_3,${R0} ++ umlal $ACC0,$IN01_3,${S2} ++ umlal $ACC4,$IN01_3,${R1} ++ umlal $ACC1,$IN01_3,${S3} ++ umlal $ACC2,$IN01_3,${S4} ++ ++ umlal $ACC3,$IN01_4,${S4} ++ umlal $ACC0,$IN01_4,${S1} ++ umlal $ACC4,$IN01_4,${R0} ++ umlal $ACC1,$IN01_4,${S2} ++ umlal $ACC2,$IN01_4,${S3} ++ ++.Lshort_tail: ++ //////////////////////////////////////////////////////////////// ++ // horizontal add ++ ++ addp $ACC3,$ACC3,$ACC3 ++ ldp d8,d9,[sp,#16] // meet ABI requirements ++ addp $ACC0,$ACC0,$ACC0 ++ ldp d10,d11,[sp,#32] ++ addp $ACC4,$ACC4,$ACC4 ++ ldp d12,d13,[sp,#48] ++ addp $ACC1,$ACC1,$ACC1 ++ ldp d14,d15,[sp,#64] ++ addp $ACC2,$ACC2,$ACC2 ++ ldr x30,[sp,#8] ++ .inst 0xd50323bf // autiasp ++ ++ //////////////////////////////////////////////////////////////// ++ // lazy reduction, but without narrowing ++ ++ ushr $T0.2d,$ACC3,#26 ++ and $ACC3,$ACC3,$MASK.2d ++ ushr $T1.2d,$ACC0,#26 ++ and $ACC0,$ACC0,$MASK.2d ++ ++ add $ACC4,$ACC4,$T0.2d // h3 -> h4 ++ add $ACC1,$ACC1,$T1.2d // h0 -> h1 ++ ++ ushr $T0.2d,$ACC4,#26 ++ and $ACC4,$ACC4,$MASK.2d ++ ushr $T1.2d,$ACC1,#26 ++ and $ACC1,$ACC1,$MASK.2d ++ add $ACC2,$ACC2,$T1.2d // h1 -> h2 ++ ++ add $ACC0,$ACC0,$T0.2d ++ shl $T0.2d,$T0.2d,#2 ++ ushr $T1.2d,$ACC2,#26 ++ and $ACC2,$ACC2,$MASK.2d ++ add $ACC0,$ACC0,$T0.2d // h4 -> h0 ++ add $ACC3,$ACC3,$T1.2d // h2 -> h3 ++ ++ ushr $T0.2d,$ACC0,#26 ++ and $ACC0,$ACC0,$MASK.2d ++ ushr $T1.2d,$ACC3,#26 ++ and $ACC3,$ACC3,$MASK.2d ++ add $ACC1,$ACC1,$T0.2d // h0 -> h1 ++ add $ACC4,$ACC4,$T1.2d // h3 -> h4 ++ ++ //////////////////////////////////////////////////////////////// ++ // write the result, can be partially reduced ++ ++ st4 {$ACC0,$ACC1,$ACC2,$ACC3}[0],[$ctx],#16 ++ mov x4,#1 ++ st1 {$ACC4}[0],[$ctx] ++ str x4,[$ctx,#8] // set is_base2_26 ++ ++ ldr x29,[sp],#80 ++ ret ++.size poly1305_blocks_neon,.-poly1305_blocks_neon ++ ++.align 5 ++.Lzeros: ++.long 0,0,0,0,0,0,0,0 ++.asciz "Poly1305 for ARMv8, CRYPTOGAMS by \@dot-asm" ++.align 2 ++#if !defined(__KERNEL__) && !defined(_WIN64) ++.comm OPENSSL_armcap_P,4,4 ++.hidden OPENSSL_armcap_P ++#endif ++___ ++ ++foreach (split("\n",$code)) { ++ s/\b(shrn\s+v[0-9]+)\.[24]d/$1.2s/ or ++ s/\b(fmov\s+)v([0-9]+)[^,]*,\s*x([0-9]+)/$1d$2,x$3/ or ++ (m/\bdup\b/ and (s/\.[24]s/.2d/g or 1)) or ++ (m/\b(eor|and)/ and (s/\.[248][sdh]/.16b/g or 1)) or ++ (m/\bum(ul|la)l\b/ and (s/\.4s/.2s/g or 1)) or ++ (m/\bum(ul|la)l2\b/ and (s/\.2s/.4s/g or 1)) or ++ (m/\bst[1-4]\s+{[^}]+}\[/ and (s/\.[24]d/.s/g or 1)); ++ ++ s/\.[124]([sd])\[/.$1\[/; ++ s/w#x([0-9]+)/w$1/g; ++ ++ print $_,"\n"; ++} ++close STDOUT; +--- /dev/null ++++ b/arch/arm64/crypto/poly1305-core.S_shipped +@@ -0,0 +1,835 @@ ++#ifndef __KERNEL__ ++# include "arm_arch.h" ++.extern OPENSSL_armcap_P ++#endif ++ ++.text ++ ++// forward "declarations" are required for Apple ++.globl poly1305_blocks ++.globl poly1305_emit ++ ++.globl poly1305_init ++.type poly1305_init,%function ++.align 5 ++poly1305_init: ++ cmp x1,xzr ++ stp xzr,xzr,[x0] // zero hash value ++ stp xzr,xzr,[x0,#16] // [along with is_base2_26] ++ ++ csel x0,xzr,x0,eq ++ b.eq .Lno_key ++ ++#ifndef __KERNEL__ ++ adrp x17,OPENSSL_armcap_P ++ ldr w17,[x17,#:lo12:OPENSSL_armcap_P] ++#endif ++ ++ ldp x7,x8,[x1] // load key ++ mov x9,#0xfffffffc0fffffff ++ movk x9,#0x0fff,lsl#48 ++#ifdef __AARCH64EB__ ++ rev x7,x7 // flip bytes ++ rev x8,x8 ++#endif ++ and x7,x7,x9 // &=0ffffffc0fffffff ++ and x9,x9,#-4 ++ and x8,x8,x9 // &=0ffffffc0ffffffc ++ mov w9,#-1 ++ stp x7,x8,[x0,#32] // save key value ++ str w9,[x0,#48] // impossible key power value ++ ++#ifndef __KERNEL__ ++ tst w17,#ARMV7_NEON ++ ++ adr x12,.Lpoly1305_blocks ++ adr x7,.Lpoly1305_blocks_neon ++ adr x13,.Lpoly1305_emit ++ ++ csel x12,x12,x7,eq ++ ++# ifdef __ILP32__ ++ stp w12,w13,[x2] ++# else ++ stp x12,x13,[x2] ++# endif ++#endif ++ mov x0,#1 ++.Lno_key: ++ ret ++.size poly1305_init,.-poly1305_init ++ ++.type poly1305_blocks,%function ++.align 5 ++poly1305_blocks: ++.Lpoly1305_blocks: ++ ands x2,x2,#-16 ++ b.eq .Lno_data ++ ++ ldp x4,x5,[x0] // load hash value ++ ldp x6,x17,[x0,#16] // [along with is_base2_26] ++ ldp x7,x8,[x0,#32] // load key value ++ ++#ifdef __AARCH64EB__ ++ lsr x12,x4,#32 ++ mov w13,w4 ++ lsr x14,x5,#32 ++ mov w15,w5 ++ lsr x16,x6,#32 ++#else ++ mov w12,w4 ++ lsr x13,x4,#32 ++ mov w14,w5 ++ lsr x15,x5,#32 ++ mov w16,w6 ++#endif ++ ++ add x12,x12,x13,lsl#26 // base 2^26 -> base 2^64 ++ lsr x13,x14,#12 ++ adds x12,x12,x14,lsl#52 ++ add x13,x13,x15,lsl#14 ++ adc x13,x13,xzr ++ lsr x14,x16,#24 ++ adds x13,x13,x16,lsl#40 ++ adc x14,x14,xzr ++ ++ cmp x17,#0 // is_base2_26? ++ add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) ++ csel x4,x4,x12,eq // choose between radixes ++ csel x5,x5,x13,eq ++ csel x6,x6,x14,eq ++ ++.Loop: ++ ldp x10,x11,[x1],#16 // load input ++ sub x2,x2,#16 ++#ifdef __AARCH64EB__ ++ rev x10,x10 ++ rev x11,x11 ++#endif ++ adds x4,x4,x10 // accumulate input ++ adcs x5,x5,x11 ++ ++ mul x12,x4,x7 // h0*r0 ++ adc x6,x6,x3 ++ umulh x13,x4,x7 ++ ++ mul x10,x5,x9 // h1*5*r1 ++ umulh x11,x5,x9 ++ ++ adds x12,x12,x10 ++ mul x10,x4,x8 // h0*r1 ++ adc x13,x13,x11 ++ umulh x14,x4,x8 ++ ++ adds x13,x13,x10 ++ mul x10,x5,x7 // h1*r0 ++ adc x14,x14,xzr ++ umulh x11,x5,x7 ++ ++ adds x13,x13,x10 ++ mul x10,x6,x9 // h2*5*r1 ++ adc x14,x14,x11 ++ mul x11,x6,x7 // h2*r0 ++ ++ adds x13,x13,x10 ++ adc x14,x14,x11 ++ ++ and x10,x14,#-4 // final reduction ++ and x6,x14,#3 ++ add x10,x10,x14,lsr#2 ++ adds x4,x12,x10 ++ adcs x5,x13,xzr ++ adc x6,x6,xzr ++ ++ cbnz x2,.Loop ++ ++ stp x4,x5,[x0] // store hash value ++ stp x6,xzr,[x0,#16] // [and clear is_base2_26] ++ ++.Lno_data: ++ ret ++.size poly1305_blocks,.-poly1305_blocks ++ ++.type poly1305_emit,%function ++.align 5 ++poly1305_emit: ++.Lpoly1305_emit: ++ ldp x4,x5,[x0] // load hash base 2^64 ++ ldp x6,x7,[x0,#16] // [along with is_base2_26] ++ ldp x10,x11,[x2] // load nonce ++ ++#ifdef __AARCH64EB__ ++ lsr x12,x4,#32 ++ mov w13,w4 ++ lsr x14,x5,#32 ++ mov w15,w5 ++ lsr x16,x6,#32 ++#else ++ mov w12,w4 ++ lsr x13,x4,#32 ++ mov w14,w5 ++ lsr x15,x5,#32 ++ mov w16,w6 ++#endif ++ ++ add x12,x12,x13,lsl#26 // base 2^26 -> base 2^64 ++ lsr x13,x14,#12 ++ adds x12,x12,x14,lsl#52 ++ add x13,x13,x15,lsl#14 ++ adc x13,x13,xzr ++ lsr x14,x16,#24 ++ adds x13,x13,x16,lsl#40 ++ adc x14,x14,xzr ++ ++ cmp x7,#0 // is_base2_26? ++ csel x4,x4,x12,eq // choose between radixes ++ csel x5,x5,x13,eq ++ csel x6,x6,x14,eq ++ ++ adds x12,x4,#5 // compare to modulus ++ adcs x13,x5,xzr ++ adc x14,x6,xzr ++ ++ tst x14,#-4 // see if it's carried/borrowed ++ ++ csel x4,x4,x12,eq ++ csel x5,x5,x13,eq ++ ++#ifdef __AARCH64EB__ ++ ror x10,x10,#32 // flip nonce words ++ ror x11,x11,#32 ++#endif ++ adds x4,x4,x10 // accumulate nonce ++ adc x5,x5,x11 ++#ifdef __AARCH64EB__ ++ rev x4,x4 // flip output bytes ++ rev x5,x5 ++#endif ++ stp x4,x5,[x1] // write result ++ ++ ret ++.size poly1305_emit,.-poly1305_emit ++.type poly1305_mult,%function ++.align 5 ++poly1305_mult: ++ mul x12,x4,x7 // h0*r0 ++ umulh x13,x4,x7 ++ ++ mul x10,x5,x9 // h1*5*r1 ++ umulh x11,x5,x9 ++ ++ adds x12,x12,x10 ++ mul x10,x4,x8 // h0*r1 ++ adc x13,x13,x11 ++ umulh x14,x4,x8 ++ ++ adds x13,x13,x10 ++ mul x10,x5,x7 // h1*r0 ++ adc x14,x14,xzr ++ umulh x11,x5,x7 ++ ++ adds x13,x13,x10 ++ mul x10,x6,x9 // h2*5*r1 ++ adc x14,x14,x11 ++ mul x11,x6,x7 // h2*r0 ++ ++ adds x13,x13,x10 ++ adc x14,x14,x11 ++ ++ and x10,x14,#-4 // final reduction ++ and x6,x14,#3 ++ add x10,x10,x14,lsr#2 ++ adds x4,x12,x10 ++ adcs x5,x13,xzr ++ adc x6,x6,xzr ++ ++ ret ++.size poly1305_mult,.-poly1305_mult ++ ++.type poly1305_splat,%function ++.align 4 ++poly1305_splat: ++ and x12,x4,#0x03ffffff // base 2^64 -> base 2^26 ++ ubfx x13,x4,#26,#26 ++ extr x14,x5,x4,#52 ++ and x14,x14,#0x03ffffff ++ ubfx x15,x5,#14,#26 ++ extr x16,x6,x5,#40 ++ ++ str w12,[x0,#16*0] // r0 ++ add w12,w13,w13,lsl#2 // r1*5 ++ str w13,[x0,#16*1] // r1 ++ add w13,w14,w14,lsl#2 // r2*5 ++ str w12,[x0,#16*2] // s1 ++ str w14,[x0,#16*3] // r2 ++ add w14,w15,w15,lsl#2 // r3*5 ++ str w13,[x0,#16*4] // s2 ++ str w15,[x0,#16*5] // r3 ++ add w15,w16,w16,lsl#2 // r4*5 ++ str w14,[x0,#16*6] // s3 ++ str w16,[x0,#16*7] // r4 ++ str w15,[x0,#16*8] // s4 ++ ++ ret ++.size poly1305_splat,.-poly1305_splat ++ ++#ifdef __KERNEL__ ++.globl poly1305_blocks_neon ++#endif ++.type poly1305_blocks_neon,%function ++.align 5 ++poly1305_blocks_neon: ++.Lpoly1305_blocks_neon: ++ ldr x17,[x0,#24] ++ cmp x2,#128 ++ b.lo .Lpoly1305_blocks ++ ++ .inst 0xd503233f // paciasp ++ stp x29,x30,[sp,#-80]! ++ add x29,sp,#0 ++ ++ stp d8,d9,[sp,#16] // meet ABI requirements ++ stp d10,d11,[sp,#32] ++ stp d12,d13,[sp,#48] ++ stp d14,d15,[sp,#64] ++ ++ cbz x17,.Lbase2_64_neon ++ ++ ldp w10,w11,[x0] // load hash value base 2^26 ++ ldp w12,w13,[x0,#8] ++ ldr w14,[x0,#16] ++ ++ tst x2,#31 ++ b.eq .Leven_neon ++ ++ ldp x7,x8,[x0,#32] // load key value ++ ++ add x4,x10,x11,lsl#26 // base 2^26 -> base 2^64 ++ lsr x5,x12,#12 ++ adds x4,x4,x12,lsl#52 ++ add x5,x5,x13,lsl#14 ++ adc x5,x5,xzr ++ lsr x6,x14,#24 ++ adds x5,x5,x14,lsl#40 ++ adc x14,x6,xzr // can be partially reduced... ++ ++ ldp x12,x13,[x1],#16 // load input ++ sub x2,x2,#16 ++ add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) ++ ++#ifdef __AARCH64EB__ ++ rev x12,x12 ++ rev x13,x13 ++#endif ++ adds x4,x4,x12 // accumulate input ++ adcs x5,x5,x13 ++ adc x6,x6,x3 ++ ++ bl poly1305_mult ++ ++ and x10,x4,#0x03ffffff // base 2^64 -> base 2^26 ++ ubfx x11,x4,#26,#26 ++ extr x12,x5,x4,#52 ++ and x12,x12,#0x03ffffff ++ ubfx x13,x5,#14,#26 ++ extr x14,x6,x5,#40 ++ ++ b .Leven_neon ++ ++.align 4 ++.Lbase2_64_neon: ++ ldp x7,x8,[x0,#32] // load key value ++ ++ ldp x4,x5,[x0] // load hash value base 2^64 ++ ldr x6,[x0,#16] ++ ++ tst x2,#31 ++ b.eq .Linit_neon ++ ++ ldp x12,x13,[x1],#16 // load input ++ sub x2,x2,#16 ++ add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) ++#ifdef __AARCH64EB__ ++ rev x12,x12 ++ rev x13,x13 ++#endif ++ adds x4,x4,x12 // accumulate input ++ adcs x5,x5,x13 ++ adc x6,x6,x3 ++ ++ bl poly1305_mult ++ ++.Linit_neon: ++ ldr w17,[x0,#48] // first table element ++ and x10,x4,#0x03ffffff // base 2^64 -> base 2^26 ++ ubfx x11,x4,#26,#26 ++ extr x12,x5,x4,#52 ++ and x12,x12,#0x03ffffff ++ ubfx x13,x5,#14,#26 ++ extr x14,x6,x5,#40 ++ ++ cmp w17,#-1 // is value impossible? ++ b.ne .Leven_neon ++ ++ fmov d24,x10 ++ fmov d25,x11 ++ fmov d26,x12 ++ fmov d27,x13 ++ fmov d28,x14 ++ ++ ////////////////////////////////// initialize r^n table ++ mov x4,x7 // r^1 ++ add x9,x8,x8,lsr#2 // s1 = r1 + (r1 >> 2) ++ mov x5,x8 ++ mov x6,xzr ++ add x0,x0,#48+12 ++ bl poly1305_splat ++ ++ bl poly1305_mult // r^2 ++ sub x0,x0,#4 ++ bl poly1305_splat ++ ++ bl poly1305_mult // r^3 ++ sub x0,x0,#4 ++ bl poly1305_splat ++ ++ bl poly1305_mult // r^4 ++ sub x0,x0,#4 ++ bl poly1305_splat ++ sub x0,x0,#48 // restore original x0 ++ b .Ldo_neon ++ ++.align 4 ++.Leven_neon: ++ fmov d24,x10 ++ fmov d25,x11 ++ fmov d26,x12 ++ fmov d27,x13 ++ fmov d28,x14 ++ ++.Ldo_neon: ++ ldp x8,x12,[x1,#32] // inp[2:3] ++ subs x2,x2,#64 ++ ldp x9,x13,[x1,#48] ++ add x16,x1,#96 ++ adr x17,.Lzeros ++ ++ lsl x3,x3,#24 ++ add x15,x0,#48 ++ ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ and x5,x9,#0x03ffffff ++ ubfx x6,x8,#26,#26 ++ ubfx x7,x9,#26,#26 ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ extr x8,x12,x8,#52 ++ extr x9,x13,x9,#52 ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ fmov d14,x4 ++ and x8,x8,#0x03ffffff ++ and x9,x9,#0x03ffffff ++ ubfx x10,x12,#14,#26 ++ ubfx x11,x13,#14,#26 ++ add x12,x3,x12,lsr#40 ++ add x13,x3,x13,lsr#40 ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ fmov d15,x6 ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ fmov d16,x8 ++ fmov d17,x10 ++ fmov d18,x12 ++ ++ ldp x8,x12,[x1],#16 // inp[0:1] ++ ldp x9,x13,[x1],#48 ++ ++ ld1 {v0.4s,v1.4s,v2.4s,v3.4s},[x15],#64 ++ ld1 {v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64 ++ ld1 {v8.4s},[x15] ++ ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ and x5,x9,#0x03ffffff ++ ubfx x6,x8,#26,#26 ++ ubfx x7,x9,#26,#26 ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ extr x8,x12,x8,#52 ++ extr x9,x13,x9,#52 ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ fmov d9,x4 ++ and x8,x8,#0x03ffffff ++ and x9,x9,#0x03ffffff ++ ubfx x10,x12,#14,#26 ++ ubfx x11,x13,#14,#26 ++ add x12,x3,x12,lsr#40 ++ add x13,x3,x13,lsr#40 ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ fmov d10,x6 ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ movi v31.2d,#-1 ++ fmov d11,x8 ++ fmov d12,x10 ++ fmov d13,x12 ++ ushr v31.2d,v31.2d,#38 ++ ++ b.ls .Lskip_loop ++ ++.align 4 ++.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 = h0*r4 + h1*r3 + h2*r2 + h3*r1 + h4*r0 ++ // d3 = h0*r3 + h1*r2 + h2*r1 + h3*r0 + h4*5*r4 ++ // d2 = h0*r2 + h1*r1 + h2*r0 + h3*5*r4 + h4*5*r3 ++ // d1 = h0*r1 + h1*r0 + h2*5*r4 + h3*5*r3 + h4*5*r2 ++ // d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1 ++ ++ subs x2,x2,#64 ++ umull v23.2d,v14.2s,v7.s[2] ++ csel x16,x17,x16,lo ++ umull v22.2d,v14.2s,v5.s[2] ++ umull v21.2d,v14.2s,v3.s[2] ++ ldp x8,x12,[x16],#16 // inp[2:3] (or zero) ++ umull v20.2d,v14.2s,v1.s[2] ++ ldp x9,x13,[x16],#48 ++ umull v19.2d,v14.2s,v0.s[2] ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ ++ umlal v23.2d,v15.2s,v5.s[2] ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ umlal v22.2d,v15.2s,v3.s[2] ++ and x5,x9,#0x03ffffff ++ umlal v21.2d,v15.2s,v1.s[2] ++ ubfx x6,x8,#26,#26 ++ umlal v20.2d,v15.2s,v0.s[2] ++ ubfx x7,x9,#26,#26 ++ umlal v19.2d,v15.2s,v8.s[2] ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ ++ umlal v23.2d,v16.2s,v3.s[2] ++ extr x8,x12,x8,#52 ++ umlal v22.2d,v16.2s,v1.s[2] ++ extr x9,x13,x9,#52 ++ umlal v21.2d,v16.2s,v0.s[2] ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ umlal v20.2d,v16.2s,v8.s[2] ++ fmov d14,x4 ++ umlal v19.2d,v16.2s,v6.s[2] ++ and x8,x8,#0x03ffffff ++ ++ umlal v23.2d,v17.2s,v1.s[2] ++ and x9,x9,#0x03ffffff ++ umlal v22.2d,v17.2s,v0.s[2] ++ ubfx x10,x12,#14,#26 ++ umlal v21.2d,v17.2s,v8.s[2] ++ ubfx x11,x13,#14,#26 ++ umlal v20.2d,v17.2s,v6.s[2] ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ umlal v19.2d,v17.2s,v4.s[2] ++ fmov d15,x6 ++ ++ add v11.2s,v11.2s,v26.2s ++ add x12,x3,x12,lsr#40 ++ umlal v23.2d,v18.2s,v0.s[2] ++ add x13,x3,x13,lsr#40 ++ umlal v22.2d,v18.2s,v8.s[2] ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ umlal v21.2d,v18.2s,v6.s[2] ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ umlal v20.2d,v18.2s,v4.s[2] ++ fmov d16,x8 ++ umlal v19.2d,v18.2s,v2.s[2] ++ fmov d17,x10 ++ ++ //////////////////////////////////////////////////////////////// ++ // (hash+inp[0:1])*r^4 and accumulate ++ ++ add v9.2s,v9.2s,v24.2s ++ fmov d18,x12 ++ umlal v22.2d,v11.2s,v1.s[0] ++ ldp x8,x12,[x1],#16 // inp[0:1] ++ umlal v19.2d,v11.2s,v6.s[0] ++ ldp x9,x13,[x1],#48 ++ umlal v23.2d,v11.2s,v3.s[0] ++ umlal v20.2d,v11.2s,v8.s[0] ++ umlal v21.2d,v11.2s,v0.s[0] ++#ifdef __AARCH64EB__ ++ rev x8,x8 ++ rev x12,x12 ++ rev x9,x9 ++ rev x13,x13 ++#endif ++ ++ add v10.2s,v10.2s,v25.2s ++ umlal v22.2d,v9.2s,v5.s[0] ++ umlal v23.2d,v9.2s,v7.s[0] ++ and x4,x8,#0x03ffffff // base 2^64 -> base 2^26 ++ umlal v21.2d,v9.2s,v3.s[0] ++ and x5,x9,#0x03ffffff ++ umlal v19.2d,v9.2s,v0.s[0] ++ ubfx x6,x8,#26,#26 ++ umlal v20.2d,v9.2s,v1.s[0] ++ ubfx x7,x9,#26,#26 ++ ++ add v12.2s,v12.2s,v27.2s ++ add x4,x4,x5,lsl#32 // bfi x4,x5,#32,#32 ++ umlal v22.2d,v10.2s,v3.s[0] ++ extr x8,x12,x8,#52 ++ umlal v23.2d,v10.2s,v5.s[0] ++ extr x9,x13,x9,#52 ++ umlal v19.2d,v10.2s,v8.s[0] ++ add x6,x6,x7,lsl#32 // bfi x6,x7,#32,#32 ++ umlal v21.2d,v10.2s,v1.s[0] ++ fmov d9,x4 ++ umlal v20.2d,v10.2s,v0.s[0] ++ and x8,x8,#0x03ffffff ++ ++ add v13.2s,v13.2s,v28.2s ++ and x9,x9,#0x03ffffff ++ umlal v22.2d,v12.2s,v0.s[0] ++ ubfx x10,x12,#14,#26 ++ umlal v19.2d,v12.2s,v4.s[0] ++ ubfx x11,x13,#14,#26 ++ umlal v23.2d,v12.2s,v1.s[0] ++ add x8,x8,x9,lsl#32 // bfi x8,x9,#32,#32 ++ umlal v20.2d,v12.2s,v6.s[0] ++ fmov d10,x6 ++ umlal v21.2d,v12.2s,v8.s[0] ++ add x12,x3,x12,lsr#40 ++ ++ umlal v22.2d,v13.2s,v8.s[0] ++ add x13,x3,x13,lsr#40 ++ umlal v19.2d,v13.2s,v2.s[0] ++ add x10,x10,x11,lsl#32 // bfi x10,x11,#32,#32 ++ umlal v23.2d,v13.2s,v0.s[0] ++ add x12,x12,x13,lsl#32 // bfi x12,x13,#32,#32 ++ umlal v20.2d,v13.2s,v4.s[0] ++ fmov d11,x8 ++ umlal v21.2d,v13.2s,v6.s[0] ++ fmov d12,x10 ++ fmov d13,x12 ++ ++ ///////////////////////////////////////////////////////////////// ++ // lazy reduction as discussed in "NEON crypto" by D.J. Bernstein ++ // and P. Schwabe ++ // ++ // [see discussion in poly1305-armv4 module] ++ ++ ushr v29.2d,v22.2d,#26 ++ xtn v27.2s,v22.2d ++ ushr v30.2d,v19.2d,#26 ++ and v19.16b,v19.16b,v31.16b ++ add v23.2d,v23.2d,v29.2d // h3 -> h4 ++ bic v27.2s,#0xfc,lsl#24 // &=0x03ffffff ++ add v20.2d,v20.2d,v30.2d // h0 -> h1 ++ ++ ushr v29.2d,v23.2d,#26 ++ xtn v28.2s,v23.2d ++ ushr v30.2d,v20.2d,#26 ++ xtn v25.2s,v20.2d ++ bic v28.2s,#0xfc,lsl#24 ++ add v21.2d,v21.2d,v30.2d // h1 -> h2 ++ ++ add v19.2d,v19.2d,v29.2d ++ shl v29.2d,v29.2d,#2 ++ shrn v30.2s,v21.2d,#26 ++ xtn v26.2s,v21.2d ++ add v19.2d,v19.2d,v29.2d // h4 -> h0 ++ bic v25.2s,#0xfc,lsl#24 ++ add v27.2s,v27.2s,v30.2s // h2 -> h3 ++ bic v26.2s,#0xfc,lsl#24 ++ ++ shrn v29.2s,v19.2d,#26 ++ xtn v24.2s,v19.2d ++ ushr v30.2s,v27.2s,#26 ++ bic v27.2s,#0xfc,lsl#24 ++ bic v24.2s,#0xfc,lsl#24 ++ add v25.2s,v25.2s,v29.2s // h0 -> h1 ++ add v28.2s,v28.2s,v30.2s // h3 -> h4 ++ ++ b.hi .Loop_neon ++ ++.Lskip_loop: ++ dup v16.2d,v16.d[0] ++ add v11.2s,v11.2s,v26.2s ++ ++ //////////////////////////////////////////////////////////////// ++ // multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 ++ ++ adds x2,x2,#32 ++ b.ne .Long_tail ++ ++ dup v16.2d,v11.d[0] ++ add v14.2s,v9.2s,v24.2s ++ add v17.2s,v12.2s,v27.2s ++ add v15.2s,v10.2s,v25.2s ++ add v18.2s,v13.2s,v28.2s ++ ++.Long_tail: ++ dup v14.2d,v14.d[0] ++ umull2 v19.2d,v16.4s,v6.4s ++ umull2 v22.2d,v16.4s,v1.4s ++ umull2 v23.2d,v16.4s,v3.4s ++ umull2 v21.2d,v16.4s,v0.4s ++ umull2 v20.2d,v16.4s,v8.4s ++ ++ dup v15.2d,v15.d[0] ++ umlal2 v19.2d,v14.4s,v0.4s ++ umlal2 v21.2d,v14.4s,v3.4s ++ umlal2 v22.2d,v14.4s,v5.4s ++ umlal2 v23.2d,v14.4s,v7.4s ++ umlal2 v20.2d,v14.4s,v1.4s ++ ++ dup v17.2d,v17.d[0] ++ umlal2 v19.2d,v15.4s,v8.4s ++ umlal2 v22.2d,v15.4s,v3.4s ++ umlal2 v21.2d,v15.4s,v1.4s ++ umlal2 v23.2d,v15.4s,v5.4s ++ umlal2 v20.2d,v15.4s,v0.4s ++ ++ dup v18.2d,v18.d[0] ++ umlal2 v22.2d,v17.4s,v0.4s ++ umlal2 v23.2d,v17.4s,v1.4s ++ umlal2 v19.2d,v17.4s,v4.4s ++ umlal2 v20.2d,v17.4s,v6.4s ++ umlal2 v21.2d,v17.4s,v8.4s ++ ++ umlal2 v22.2d,v18.4s,v8.4s ++ umlal2 v19.2d,v18.4s,v2.4s ++ umlal2 v23.2d,v18.4s,v0.4s ++ umlal2 v20.2d,v18.4s,v4.4s ++ umlal2 v21.2d,v18.4s,v6.4s ++ ++ b.eq .Lshort_tail ++ ++ //////////////////////////////////////////////////////////////// ++ // (hash+inp[0:1])*r^4:r^3 and accumulate ++ ++ add v9.2s,v9.2s,v24.2s ++ umlal v22.2d,v11.2s,v1.2s ++ umlal v19.2d,v11.2s,v6.2s ++ umlal v23.2d,v11.2s,v3.2s ++ umlal v20.2d,v11.2s,v8.2s ++ umlal v21.2d,v11.2s,v0.2s ++ ++ add v10.2s,v10.2s,v25.2s ++ umlal v22.2d,v9.2s,v5.2s ++ umlal v19.2d,v9.2s,v0.2s ++ umlal v23.2d,v9.2s,v7.2s ++ umlal v20.2d,v9.2s,v1.2s ++ umlal v21.2d,v9.2s,v3.2s ++ ++ add v12.2s,v12.2s,v27.2s ++ umlal v22.2d,v10.2s,v3.2s ++ umlal v19.2d,v10.2s,v8.2s ++ umlal v23.2d,v10.2s,v5.2s ++ umlal v20.2d,v10.2s,v0.2s ++ umlal v21.2d,v10.2s,v1.2s ++ ++ add v13.2s,v13.2s,v28.2s ++ umlal v22.2d,v12.2s,v0.2s ++ umlal v19.2d,v12.2s,v4.2s ++ umlal v23.2d,v12.2s,v1.2s ++ umlal v20.2d,v12.2s,v6.2s ++ umlal v21.2d,v12.2s,v8.2s ++ ++ umlal v22.2d,v13.2s,v8.2s ++ umlal v19.2d,v13.2s,v2.2s ++ umlal v23.2d,v13.2s,v0.2s ++ umlal v20.2d,v13.2s,v4.2s ++ umlal v21.2d,v13.2s,v6.2s ++ ++.Lshort_tail: ++ //////////////////////////////////////////////////////////////// ++ // horizontal add ++ ++ addp v22.2d,v22.2d,v22.2d ++ ldp d8,d9,[sp,#16] // meet ABI requirements ++ addp v19.2d,v19.2d,v19.2d ++ ldp d10,d11,[sp,#32] ++ addp v23.2d,v23.2d,v23.2d ++ ldp d12,d13,[sp,#48] ++ addp v20.2d,v20.2d,v20.2d ++ ldp d14,d15,[sp,#64] ++ addp v21.2d,v21.2d,v21.2d ++ ldr x30,[sp,#8] ++ .inst 0xd50323bf // autiasp ++ ++ //////////////////////////////////////////////////////////////// ++ // lazy reduction, but without narrowing ++ ++ ushr v29.2d,v22.2d,#26 ++ and v22.16b,v22.16b,v31.16b ++ ushr v30.2d,v19.2d,#26 ++ and v19.16b,v19.16b,v31.16b ++ ++ add v23.2d,v23.2d,v29.2d // h3 -> h4 ++ add v20.2d,v20.2d,v30.2d // h0 -> h1 ++ ++ ushr v29.2d,v23.2d,#26 ++ and v23.16b,v23.16b,v31.16b ++ ushr v30.2d,v20.2d,#26 ++ and v20.16b,v20.16b,v31.16b ++ add v21.2d,v21.2d,v30.2d // h1 -> h2 ++ ++ add v19.2d,v19.2d,v29.2d ++ shl v29.2d,v29.2d,#2 ++ ushr v30.2d,v21.2d,#26 ++ and v21.16b,v21.16b,v31.16b ++ add v19.2d,v19.2d,v29.2d // h4 -> h0 ++ add v22.2d,v22.2d,v30.2d // h2 -> h3 ++ ++ ushr v29.2d,v19.2d,#26 ++ and v19.16b,v19.16b,v31.16b ++ ushr v30.2d,v22.2d,#26 ++ and v22.16b,v22.16b,v31.16b ++ add v20.2d,v20.2d,v29.2d // h0 -> h1 ++ add v23.2d,v23.2d,v30.2d // h3 -> h4 ++ ++ //////////////////////////////////////////////////////////////// ++ // write the result, can be partially reduced ++ ++ st4 {v19.s,v20.s,v21.s,v22.s}[0],[x0],#16 ++ mov x4,#1 ++ st1 {v23.s}[0],[x0] ++ str x4,[x0,#8] // set is_base2_26 ++ ++ ldr x29,[sp],#80 ++ ret ++.size poly1305_blocks_neon,.-poly1305_blocks_neon ++ ++.align 5 ++.Lzeros: ++.long 0,0,0,0,0,0,0,0 ++.asciz "Poly1305 for ARMv8, CRYPTOGAMS by @dot-asm" ++.align 2 ++#if !defined(__KERNEL__) && !defined(_WIN64) ++.comm OPENSSL_armcap_P,4,4 ++.hidden OPENSSL_armcap_P ++#endif +--- /dev/null ++++ b/arch/arm64/crypto/poly1305-glue.c +@@ -0,0 +1,237 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64 ++ * ++ * Copyright (C) 2019 Linaro Ltd. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++asmlinkage void poly1305_init_arm64(void *state, const u8 *key); ++asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit); ++asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit); ++asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce); ++ ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); ++ ++void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) ++{ ++ poly1305_init_arm64(&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 neon_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 neon_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_arch(dctx, 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(&dctx->h, src, len, hibit); ++} ++ ++static void neon_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) { ++ neon_poly1305_blocks(dctx, dctx->buf, ++ POLY1305_BLOCK_SIZE, 1, false); ++ dctx->buflen = 0; ++ } ++ } ++ ++ if (likely(len >= POLY1305_BLOCK_SIZE)) { ++ neon_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 neon_poly1305_update(struct shash_desc *desc, ++ const u8 *src, unsigned int srclen) ++{ ++ bool do_neon = crypto_simd_usable() && srclen > 128; ++ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); ++ ++ if (static_branch_likely(&have_neon) && do_neon) ++ kernel_neon_begin(); ++ neon_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) ++{ ++ 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(&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) && crypto_simd_usable()) { ++ kernel_neon_begin(); ++ poly1305_blocks_neon(&dctx->h, src, len, 1); ++ kernel_neon_end(); ++ } else { ++ poly1305_blocks(&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) ++{ ++ __le32 digest[4]; ++ u64 f = 0; ++ ++ if (unlikely(dctx->buflen)) { ++ dctx->buf[dctx->buflen++] = 1; ++ memset(dctx->buf + dctx->buflen, 0, ++ POLY1305_BLOCK_SIZE - dctx->buflen); ++ poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); ++ } ++ ++ poly1305_emit(&dctx->h, digest, dctx->s); ++ ++ /* mac = (h + s) % (2^128) */ ++ f = (f >> 32) + le32_to_cpu(digest[0]); ++ put_unaligned_le32(f, dst); ++ f = (f >> 32) + le32_to_cpu(digest[1]); ++ put_unaligned_le32(f, dst + 4); ++ f = (f >> 32) + le32_to_cpu(digest[2]); ++ put_unaligned_le32(f, dst + 8); ++ f = (f >> 32) + le32_to_cpu(digest[3]); ++ put_unaligned_le32(f, dst + 12); ++ ++ *dctx = (struct poly1305_desc_ctx){}; ++} ++EXPORT_SYMBOL(poly1305_final_arch); ++ ++static int neon_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 neon_poly1305_alg = { ++ .init = neon_poly1305_init, ++ .update = neon_poly1305_update, ++ .final = neon_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, ++}; ++ ++static int __init neon_poly1305_mod_init(void) ++{ ++ if (!cpu_have_named_feature(ASIMD)) ++ return 0; ++ ++ static_branch_enable(&have_neon); ++ ++ return crypto_register_shash(&neon_poly1305_alg); ++} ++ ++static void __exit neon_poly1305_mod_exit(void) ++{ ++ if (cpu_have_named_feature(ASIMD)) ++ crypto_unregister_shash(&neon_poly1305_alg); ++} ++ ++module_init(neon_poly1305_mod_init); ++module_exit(neon_poly1305_mod_exit); ++ ++MODULE_LICENSE("GPL v2"); ++MODULE_ALIAS_CRYPTO("poly1305"); ++MODULE_ALIAS_CRYPTO("poly1305-neon"); +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -40,6 +40,7 @@ config CRYPTO_LIB_DES + config CRYPTO_LIB_POLY1305_RSIZE + int + default 4 if X86_64 ++ default 9 if ARM64 + default 1 + + config CRYPTO_ARCH_HAVE_LIB_POLY1305 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0019-crypto-arm-poly1305-incorporate-OpenSSL-CRYPTOGAMS-N.patch b/target/linux/generic/backport-5.4/080-wireguard-0019-crypto-arm-poly1305-incorporate-OpenSSL-CRYPTOGAMS-N.patch new file mode 100644 index 0000000000..d48235ca94 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0019-crypto-arm-poly1305-incorporate-OpenSSL-CRYPTOGAMS-N.patch @@ -0,0 +1,2776 @@ +From 588765ccad76f9f65f09e1dcadc464d22441c889 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:25 +0100 +Subject: [PATCH 019/124] crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS + NEON implementation + +commit a6b803b3ddc793d6db0c16f12fc12d30d20fa9cc upstream. + +This is a straight import of the OpenSSL/CRYPTOGAMS Poly1305 implementation +for NEON authored by Andy Polyakov, and contributed by him to the OpenSSL +project. The file 'poly1305-armv4.pl' is taken straight from this upstream +GitHub repository [0] at commit ec55a08dc0244ce570c4fc7cade330c60798952f, +and already contains all the changes required to build it as part of a +Linux kernel module. + +[0] https://github.com/dot-asm/cryptogams + +Co-developed-by: Andy Polyakov +Signed-off-by: Andy Polyakov +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/Kconfig | 5 + + arch/arm/crypto/Makefile | 12 +- + arch/arm/crypto/poly1305-armv4.pl | 1236 +++++++++++++++++++++++ + arch/arm/crypto/poly1305-core.S_shipped | 1158 +++++++++++++++++++++ + arch/arm/crypto/poly1305-glue.c | 276 +++++ + lib/crypto/Kconfig | 2 +- + 6 files changed, 2687 insertions(+), 2 deletions(-) + create mode 100644 arch/arm/crypto/poly1305-armv4.pl + create mode 100644 arch/arm/crypto/poly1305-core.S_shipped + create mode 100644 arch/arm/crypto/poly1305-glue.c + +--- a/arch/arm/crypto/Kconfig ++++ b/arch/arm/crypto/Kconfig +@@ -131,6 +131,11 @@ config CRYPTO_CHACHA20_NEON + select CRYPTO_BLKCIPHER + select CRYPTO_ARCH_HAVE_LIB_CHACHA + ++config CRYPTO_POLY1305_ARM ++ tristate "Accelerated scalar and SIMD Poly1305 hash implementations" ++ select CRYPTO_HASH ++ select CRYPTO_ARCH_HAVE_LIB_POLY1305 ++ + config CRYPTO_NHPOLY1305_NEON + tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)" + depends on KERNEL_MODE_NEON +--- a/arch/arm/crypto/Makefile ++++ b/arch/arm/crypto/Makefile +@@ -10,6 +10,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sh + obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o + obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o + obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o ++obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o + obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o + + ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o +@@ -55,12 +56,16 @@ crct10dif-arm-ce-y := crct10dif-ce-core. + 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 + + ifdef REGENERATE_ARM_CRYPTO + quiet_cmd_perl = PERL $@ + cmd_perl = $(PERL) $(<) > $(@) + ++$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv4.pl ++ $(call cmd,perl) ++ + $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl + $(call cmd,perl) + +@@ -68,4 +73,9 @@ $(src)/sha512-core.S_shipped: $(src)/sha + $(call cmd,perl) + endif + +-clean-files += sha256-core.S sha512-core.S ++clean-files += poly1305-core.S sha256-core.S sha512-core.S ++ ++# massage the perlasm code a bit so we only get the NEON routine if we need it ++poly1305-aflags-$(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 += $(poly1305-aflags-y) +--- /dev/null ++++ b/arch/arm/crypto/poly1305-armv4.pl +@@ -0,0 +1,1236 @@ ++#!/usr/bin/env perl ++# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause ++# ++# ==================================================================== ++# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL ++# project. ++# ==================================================================== ++# ++# IALU(*)/gcc-4.4 NEON ++# ++# ARM11xx(ARMv6) 7.78/+100% - ++# Cortex-A5 6.35/+130% 3.00 ++# Cortex-A8 6.25/+115% 2.36 ++# Cortex-A9 5.10/+95% 2.55 ++# Cortex-A15 3.85/+85% 1.25(**) ++# Snapdragon S4 5.70/+100% 1.48(**) ++# ++# (*) this is for -march=armv6, i.e. with bunch of ldrb loading data; ++# (**) these are trade-off results, they can be improved by ~8% but at ++# the cost of 15/12% regression on Cortex-A5/A7, it's even possible ++# to improve Cortex-A9 result, but then A5/A7 loose more than 20%; ++ ++$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 +--- /dev/null ++++ b/arch/arm/crypto/poly1305-core.S_shipped +@@ -0,0 +1,1158 @@ ++#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 r1,#0 ++ str r3,[r0,#0] @ zero hash value ++ str r3,[r0,#4] ++ str r3,[r0,#8] ++ str r3,[r0,#12] ++ str r3,[r0,#16] ++ str r3,[r0,#36] @ clear is_base2_26 ++ add r0,r0,#20 ++ ++#ifdef __thumb2__ ++ it eq ++#endif ++ moveq r0,#0 ++ beq .Lno_key ++ ++#if __ARM_MAX_ARCH__>=7 ++ mov r3,#-1 ++ str r3,[r0,#28] @ impossible key power value ++# ifndef __KERNEL__ ++ adr r11,.Lpoly1305_init ++ ldr r12,.LOPENSSL_armcap ++# endif ++#endif ++ ldrb r4,[r1,#0] ++ mov r10,#0x0fffffff ++ ldrb r5,[r1,#1] ++ and r3,r10,#-4 @ 0x0ffffffc ++ ldrb r6,[r1,#2] ++ ldrb r7,[r1,#3] ++ orr r4,r4,r5,lsl#8 ++ ldrb r5,[r1,#4] ++ orr r4,r4,r6,lsl#16 ++ ldrb r6,[r1,#5] ++ orr r4,r4,r7,lsl#24 ++ ldrb r7,[r1,#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,[r1,#7] ++ orr r5,r5,r6,lsl#8 ++ ldrb r6,[r1,#8] ++ orr r5,r5,r7,lsl#16 ++ ldrb r7,[r1,#9] ++ orr r5,r5,r8,lsl#24 ++ ldrb r8,[r1,#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,[r1,#11] ++ orr r6,r6,r7,lsl#8 ++ ldrb r7,[r1,#12] ++ orr r6,r6,r8,lsl#16 ++ ldrb r8,[r1,#13] ++ orr r6,r6,r9,lsl#24 ++ ldrb r9,[r1,#14] ++ and r6,r6,r3 ++ ++ ldrb r10,[r1,#15] ++ orr r7,r7,r8,lsl#8 ++ str r4,[r0,#0] ++ orr r7,r7,r9,lsl#16 ++ str r5,[r0,#4] ++ orr r7,r7,r10,lsl#24 ++ str r6,[r0,#8] ++ and r7,r7,r3 ++ str r7,[r0,#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 ++ bx lr @ bx lr ++#else ++ tst lr,#1 ++ moveq pc,lr @ be binary compatible with V4, yet ++ .word 0xe12fff1e @ interoperable with Thumb ISA:-) ++#endif ++.size poly1305_init,.-poly1305_init ++.type poly1305_blocks,%function ++.align 5 ++poly1305_blocks: ++.Lpoly1305_blocks: ++ stmdb sp!,{r3-r11,lr} ++ ++ ands r2,r2,#-16 ++ beq .Lno_data ++ ++ add r2,r2,r1 @ end pointer ++ sub sp,sp,#32 ++ ++#if __ARM_ARCH__<7 ++ ldmia r0,{r4-r12} @ load context ++ add r0,r0,#20 ++ str r2,[sp,#16] @ offload stuff ++ str r0,[sp,#12] ++#else ++ ldr lr,[r0,#36] @ is_base2_26 ++ ldmia r0!,{r4-r8} @ load hash value ++ str r2,[sp,#16] @ offload stuff ++ str r0,[sp,#12] ++ ++ adds r9,r4,r5,lsl#26 @ base 2^26 -> base 2^32 ++ mov r10,r5,lsr#6 ++ adcs r10,r10,r6,lsl#20 ++ mov r11,r6,lsr#12 ++ adcs r11,r11,r7,lsl#14 ++ mov r12,r7,lsr#18 ++ adcs r12,r12,r8,lsl#8 ++ mov r2,#0 ++ teq lr,#0 ++ str r2,[r0,#16] @ clear is_base2_26 ++ adc r2,r2,r8,lsr#24 ++ ++ itttt ne ++ movne r4,r9 @ choose between radixes ++ movne r5,r10 ++ movne r6,r11 ++ movne r7,r12 ++ ldmia r0,{r9-r12} @ load key ++ it ne ++ movne r8,r2 ++#endif ++ ++ mov lr,r1 ++ cmp r3,#0 ++ str r10,[sp,#20] ++ str r11,[sp,#24] ++ str r12,[sp,#28] ++ b .Loop ++ ++.align 4 ++.Loop: ++#if __ARM_ARCH__<7 ++ ldrb r0,[lr],#16 @ load input ++# ifdef __thumb2__ ++ it hi ++# endif ++ addhi r8,r8,#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 r4,r4,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 r5,r5,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 r6,r6,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 r10,r10,r10,lsr#2 ++ orr r3,r2,r3,lsl#24 ++#else ++ ldr r0,[lr],#16 @ load input ++ it hi ++ addhi r8,r8,#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 r4,r4,r0 @ accumulate input ++ str lr,[sp,#8] @ offload input pointer ++ adcs r5,r5,r1 ++ add r10,r10,r10,lsr#2 ++ adcs r6,r6,r2 ++#endif ++ add r11,r11,r11,lsr#2 ++ adcs r7,r7,r3 ++ add r12,r12,r12,lsr#2 ++ ++ umull r2,r3,r5,r9 ++ adc r8,r8,#0 ++ umull r0,r1,r4,r9 ++ umlal r2,r3,r8,r10 ++ umlal r0,r1,r7,r10 ++ ldr r10,[sp,#20] @ reload r10 ++ umlal r2,r3,r6,r12 ++ umlal r0,r1,r5,r12 ++ umlal r2,r3,r7,r11 ++ umlal r0,r1,r6,r11 ++ umlal r2,r3,r4,r10 ++ str r0,[sp,#0] @ future r4 ++ mul r0,r11,r8 ++ ldr r11,[sp,#24] @ reload r11 ++ adds r2,r2,r1 @ d1+=d0>>32 ++ eor r1,r1,r1 ++ adc lr,r3,#0 @ future r6 ++ str r2,[sp,#4] @ future r5 ++ ++ mul r2,r12,r8 ++ eor r3,r3,r3 ++ umlal r0,r1,r7,r12 ++ ldr r12,[sp,#28] @ reload r12 ++ umlal r2,r3,r7,r9 ++ umlal r0,r1,r6,r9 ++ umlal r2,r3,r6,r10 ++ umlal r0,r1,r5,r10 ++ umlal r2,r3,r5,r11 ++ umlal r0,r1,r4,r11 ++ umlal r2,r3,r4,r12 ++ ldr r4,[sp,#0] ++ mul r8,r9,r8 ++ ldr r5,[sp,#4] ++ ++ adds r6,lr,r0 @ d2+=d1>>32 ++ ldr lr,[sp,#8] @ reload input pointer ++ adc r1,r1,#0 ++ adds r7,r2,r1 @ d3+=d2>>32 ++ ldr r0,[sp,#16] @ reload end pointer ++ adc r3,r3,#0 ++ add r8,r8,r3 @ h4+=d3>>32 ++ ++ and r1,r8,#-4 ++ and r8,r8,#3 ++ add r1,r1,r1,lsr#2 @ *=5 ++ adds r4,r4,r1 ++ adcs r5,r5,#0 ++ adcs r6,r6,#0 ++ adcs r7,r7,#0 ++ adc r8,r8,#0 ++ ++ cmp r0,lr @ done yet? ++ bhi .Loop ++ ++ ldr r0,[sp,#12] ++ add sp,sp,#32 ++ stmdb r0,{r4-r8} @ 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 ++ .word 0xe12fff1e @ interoperable with Thumb ISA:-) ++#endif ++.size poly1305_blocks,.-poly1305_blocks ++.type poly1305_emit,%function ++.align 5 ++poly1305_emit: ++.Lpoly1305_emit: ++ stmdb sp!,{r4-r11} ++ ++ ldmia r0,{r3-r7} ++ ++#if __ARM_ARCH__>=7 ++ ldr ip,[r0,#36] @ is_base2_26 ++ ++ adds r8,r3,r4,lsl#26 @ base 2^26 -> base 2^32 ++ mov r9,r4,lsr#6 ++ adcs r9,r9,r5,lsl#20 ++ mov r10,r5,lsr#12 ++ adcs r10,r10,r6,lsl#14 ++ mov r11,r6,lsr#18 ++ adcs r11,r11,r7,lsl#8 ++ mov r0,#0 ++ adc r0,r0,r7,lsr#24 ++ ++ tst ip,ip ++ itttt ne ++ movne r3,r8 ++ movne r4,r9 ++ movne r5,r10 ++ movne r6,r11 ++ it ne ++ movne r7,r0 ++#endif ++ ++ adds r8,r3,#5 @ compare to modulus ++ adcs r9,r4,#0 ++ adcs r10,r5,#0 ++ adcs r11,r6,#0 ++ adc r0,r7,#0 ++ tst r0,#4 @ did it carry/borrow? ++ ++#ifdef __thumb2__ ++ it ne ++#endif ++ movne r3,r8 ++ ldr r8,[r2,#0] ++#ifdef __thumb2__ ++ it ne ++#endif ++ movne r4,r9 ++ ldr r9,[r2,#4] ++#ifdef __thumb2__ ++ it ne ++#endif ++ movne r5,r10 ++ ldr r10,[r2,#8] ++#ifdef __thumb2__ ++ it ne ++#endif ++ movne r6,r11 ++ ldr r11,[r2,#12] ++ ++ adds r3,r3,r8 ++ adcs r4,r4,r9 ++ adcs r5,r5,r10 ++ adc r6,r6,r11 ++ ++#if __ARM_ARCH__>=7 ++# ifdef __ARMEB__ ++ rev r3,r3 ++ rev r4,r4 ++ rev r5,r5 ++ rev r6,r6 ++# endif ++ str r3,[r1,#0] ++ str r4,[r1,#4] ++ str r5,[r1,#8] ++ str r6,[r1,#12] ++#else ++ strb r3,[r1,#0] ++ mov r3,r3,lsr#8 ++ strb r4,[r1,#4] ++ mov r4,r4,lsr#8 ++ strb r5,[r1,#8] ++ mov r5,r5,lsr#8 ++ strb r6,[r1,#12] ++ mov r6,r6,lsr#8 ++ ++ strb r3,[r1,#1] ++ mov r3,r3,lsr#8 ++ strb r4,[r1,#5] ++ mov r4,r4,lsr#8 ++ strb r5,[r1,#9] ++ mov r5,r5,lsr#8 ++ strb r6,[r1,#13] ++ mov r6,r6,lsr#8 ++ ++ strb r3,[r1,#2] ++ mov r3,r3,lsr#8 ++ strb r4,[r1,#6] ++ mov r4,r4,lsr#8 ++ strb r5,[r1,#10] ++ mov r5,r5,lsr#8 ++ strb r6,[r1,#14] ++ mov r6,r6,lsr#8 ++ ++ strb r3,[r1,#3] ++ strb r4,[r1,#7] ++ strb r5,[r1,#11] ++ strb r6,[r1,#15] ++#endif ++ ldmia sp!,{r4-r11} ++#if __ARM_ARCH__>=5 ++ bx lr @ bx lr ++#else ++ tst lr,#1 ++ moveq pc,lr @ be binary compatible with V4, yet ++ .word 0xe12fff1e @ interoperable with Thumb ISA:-) ++#endif ++.size poly1305_emit,.-poly1305_emit ++#if __ARM_MAX_ARCH__>=7 ++.fpu neon ++ ++.type poly1305_init_neon,%function ++.align 5 ++poly1305_init_neon: ++.Lpoly1305_init_neon: ++ ldr r3,[r0,#48] @ first table element ++ cmp r3,#-1 @ is value impossible? ++ bne .Lno_init_neon ++ ++ ldr r4,[r0,#20] @ load key base 2^32 ++ ldr r5,[r0,#24] ++ ldr r6,[r0,#28] ++ ldr r7,[r0,#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 d0,r2 @ r^1 in both lanes ++ add r2,r3,r3,lsl#2 @ *5 ++ vdup.32 d1,r3 ++ add r3,r4,r4,lsl#2 ++ vdup.32 d2,r2 ++ vdup.32 d3,r4 ++ add r4,r5,r5,lsl#2 ++ vdup.32 d4,r3 ++ vdup.32 d5,r5 ++ add r5,r6,r6,lsl#2 ++ vdup.32 d6,r4 ++ vdup.32 d7,r6 ++ vdup.32 d8,r5 ++ ++ mov r5,#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 q5,d0,d0[1] ++ vmull.u32 q6,d1,d0[1] ++ vmull.u32 q7,d3,d0[1] ++ vmull.u32 q8,d5,d0[1] ++ vmull.u32 q9,d7,d0[1] ++ ++ vmlal.u32 q5,d7,d2[1] ++ vmlal.u32 q6,d0,d1[1] ++ vmlal.u32 q7,d1,d1[1] ++ vmlal.u32 q8,d3,d1[1] ++ vmlal.u32 q9,d5,d1[1] ++ ++ vmlal.u32 q5,d5,d4[1] ++ vmlal.u32 q6,d7,d4[1] ++ vmlal.u32 q8,d1,d3[1] ++ vmlal.u32 q7,d0,d3[1] ++ vmlal.u32 q9,d3,d3[1] ++ ++ vmlal.u32 q5,d3,d6[1] ++ vmlal.u32 q8,d0,d5[1] ++ vmlal.u32 q6,d5,d6[1] ++ vmlal.u32 q7,d7,d6[1] ++ vmlal.u32 q9,d1,d5[1] ++ ++ vmlal.u32 q8,d7,d8[1] ++ vmlal.u32 q5,d1,d8[1] ++ vmlal.u32 q6,d3,d8[1] ++ vmlal.u32 q7,d5,d8[1] ++ vmlal.u32 q9,d0,d7[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 q15,q8,#26 ++ vmovn.i64 d16,q8 ++ vshr.u64 q4,q5,#26 ++ vmovn.i64 d10,q5 ++ vadd.i64 q9,q9,q15 @ h3 -> h4 ++ vbic.i32 d16,#0xfc000000 @ &=0x03ffffff ++ vadd.i64 q6,q6,q4 @ h0 -> h1 ++ vbic.i32 d10,#0xfc000000 ++ ++ vshrn.u64 d30,q9,#26 ++ vmovn.i64 d18,q9 ++ vshr.u64 q4,q6,#26 ++ vmovn.i64 d12,q6 ++ vadd.i64 q7,q7,q4 @ h1 -> h2 ++ vbic.i32 d18,#0xfc000000 ++ vbic.i32 d12,#0xfc000000 ++ ++ vadd.i32 d10,d10,d30 ++ vshl.u32 d30,d30,#2 ++ vshrn.u64 d8,q7,#26 ++ vmovn.i64 d14,q7 ++ vadd.i32 d10,d10,d30 @ h4 -> h0 ++ vadd.i32 d16,d16,d8 @ h2 -> h3 ++ vbic.i32 d14,#0xfc000000 ++ ++ vshr.u32 d30,d10,#26 ++ vbic.i32 d10,#0xfc000000 ++ vshr.u32 d8,d16,#26 ++ vbic.i32 d16,#0xfc000000 ++ vadd.i32 d12,d12,d30 @ h0 -> h1 ++ vadd.i32 d18,d18,d8 @ h3 -> h4 ++ ++ subs r5,r5,#1 ++ beq .Lsquare_break_neon ++ ++ add r6,r0,#(48+0*9*4) ++ add r7,r0,#(48+1*9*4) ++ ++ vtrn.32 d0,d10 @ r^2:r^1 ++ vtrn.32 d3,d14 ++ vtrn.32 d5,d16 ++ vtrn.32 d1,d12 ++ vtrn.32 d7,d18 ++ ++ vshl.u32 d4,d3,#2 @ *5 ++ vshl.u32 d6,d5,#2 ++ vshl.u32 d2,d1,#2 ++ vshl.u32 d8,d7,#2 ++ vadd.i32 d4,d4,d3 ++ vadd.i32 d2,d2,d1 ++ vadd.i32 d6,d6,d5 ++ vadd.i32 d8,d8,d7 ++ ++ vst4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! ++ vst4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! ++ vst4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]! ++ vst4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]! ++ vst1.32 {d8[0]},[r6,:32] ++ vst1.32 {d8[1]},[r7,:32] ++ ++ b .Lsquare_neon ++ ++.align 4 ++.Lsquare_break_neon: ++ add r6,r0,#(48+2*4*9) ++ add r7,r0,#(48+3*4*9) ++ ++ vmov d0,d10 @ r^4:r^3 ++ vshl.u32 d2,d12,#2 @ *5 ++ vmov d1,d12 ++ vshl.u32 d4,d14,#2 ++ vmov d3,d14 ++ vshl.u32 d6,d16,#2 ++ vmov d5,d16 ++ vshl.u32 d8,d18,#2 ++ vmov d7,d18 ++ vadd.i32 d2,d2,d12 ++ vadd.i32 d4,d4,d14 ++ vadd.i32 d6,d6,d16 ++ vadd.i32 d8,d8,d18 ++ ++ vst4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! ++ vst4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! ++ vst4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]! ++ vst4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]! ++ vst1.32 {d8[0]},[r6] ++ vst1.32 {d8[1]},[r7] ++ ++.Lno_init_neon: ++ bx lr @ bx lr ++.size poly1305_init_neon,.-poly1305_init_neon ++ ++.type poly1305_blocks_neon,%function ++.align 5 ++poly1305_blocks_neon: ++.Lpoly1305_blocks_neon: ++ ldr ip,[r0,#36] @ is_base2_26 ++ ++ cmp r2,#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,[r0,#0] @ load hash value base 2^32 ++ ldr r5,[r0,#4] ++ ldr r6,[r0,#8] ++ ldr r7,[r0,#12] ++ ldr ip,[r0,#16] ++ ++ and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26 ++ mov r3,r4,lsr#26 ++ veor d10,d10,d10 ++ mov r4,r5,lsr#20 ++ orr r3,r3,r5,lsl#6 ++ veor d12,d12,d12 ++ mov r5,r6,lsr#14 ++ orr r4,r4,r6,lsl#12 ++ veor d14,d14,d14 ++ mov r6,r7,lsr#8 ++ orr r5,r5,r7,lsl#18 ++ veor d16,d16,d16 ++ and r3,r3,#0x03ffffff ++ orr r6,r6,ip,lsl#24 ++ veor d18,d18,d18 ++ and r4,r4,#0x03ffffff ++ mov r1,#1 ++ and r5,r5,#0x03ffffff ++ str r1,[r0,#36] @ set is_base2_26 ++ ++ vmov.32 d10[0],r2 ++ vmov.32 d12[0],r3 ++ vmov.32 d14[0],r4 ++ vmov.32 d16[0],r5 ++ vmov.32 d18[0],r6 ++ adr r5,.Lzeros ++ ++ ldmia sp!,{r1-r3,lr} ++ b .Lhash_loaded ++ ++.align 4 ++.Lbase2_26_neon: ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ load hash value ++ ++ veor d10,d10,d10 ++ veor d12,d12,d12 ++ veor d14,d14,d14 ++ veor d16,d16,d16 ++ veor d18,d18,d18 ++ vld4.32 {d10[0],d12[0],d14[0],d16[0]},[r0]! ++ adr r5,.Lzeros ++ vld1.32 {d18[0]},[r0] ++ sub r0,r0,#16 @ rewind ++ ++.Lhash_loaded: ++ add r4,r1,#32 ++ mov r3,r3,lsl#24 ++ tst r2,#31 ++ beq .Leven ++ ++ vld4.32 {d20[0],d22[0],d24[0],d26[0]},[r1]! ++ vmov.32 d28[0],r3 ++ sub r2,r2,#16 ++ add r4,r1,#32 ++ ++# ifdef __ARMEB__ ++ vrev32.8 q10,q10 ++ vrev32.8 q13,q13 ++ vrev32.8 q11,q11 ++ vrev32.8 q12,q12 ++# endif ++ vsri.u32 d28,d26,#8 @ base 2^32 -> base 2^26 ++ vshl.u32 d26,d26,#18 ++ ++ vsri.u32 d26,d24,#14 ++ vshl.u32 d24,d24,#12 ++ vadd.i32 d29,d28,d18 @ add hash value and move to #hi ++ ++ vbic.i32 d26,#0xfc000000 ++ vsri.u32 d24,d22,#20 ++ vshl.u32 d22,d22,#6 ++ ++ vbic.i32 d24,#0xfc000000 ++ vsri.u32 d22,d20,#26 ++ vadd.i32 d27,d26,d16 ++ ++ vbic.i32 d20,#0xfc000000 ++ vbic.i32 d22,#0xfc000000 ++ vadd.i32 d25,d24,d14 ++ ++ vadd.i32 d21,d20,d10 ++ vadd.i32 d23,d22,d12 ++ ++ mov r7,r5 ++ add r6,r0,#48 ++ ++ cmp r2,r2 ++ b .Long_tail ++ ++.align 4 ++.Leven: ++ subs r2,r2,#64 ++ it lo ++ movlo r4,r5 ++ ++ vmov.i32 q14,#1<<24 @ padbit, yes, always ++ vld4.32 {d20,d22,d24,d26},[r1] @ inp[0:1] ++ add r1,r1,#64 ++ vld4.32 {d21,d23,d25,d27},[r4] @ inp[2:3] (or 0) ++ add r4,r4,#64 ++ itt hi ++ addhi r7,r0,#(48+1*9*4) ++ addhi r6,r0,#(48+3*9*4) ++ ++# ifdef __ARMEB__ ++ vrev32.8 q10,q10 ++ vrev32.8 q13,q13 ++ vrev32.8 q11,q11 ++ vrev32.8 q12,q12 ++# endif ++ vsri.u32 q14,q13,#8 @ base 2^32 -> base 2^26 ++ vshl.u32 q13,q13,#18 ++ ++ vsri.u32 q13,q12,#14 ++ vshl.u32 q12,q12,#12 ++ ++ vbic.i32 q13,#0xfc000000 ++ vsri.u32 q12,q11,#20 ++ vshl.u32 q11,q11,#6 ++ ++ vbic.i32 q12,#0xfc000000 ++ vsri.u32 q11,q10,#26 ++ ++ vbic.i32 q10,#0xfc000000 ++ vbic.i32 q11,#0xfc000000 ++ ++ bls .Lskip_loop ++ ++ vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^2 ++ vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^4 ++ vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]! ++ vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]! ++ 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 d24,d24,d14 @ accumulate inp[0:1] ++ vmull.u32 q7,d25,d0[1] ++ vadd.i32 d20,d20,d10 ++ vmull.u32 q5,d21,d0[1] ++ vadd.i32 d26,d26,d16 ++ vmull.u32 q8,d27,d0[1] ++ vmlal.u32 q7,d23,d1[1] ++ vadd.i32 d22,d22,d12 ++ vmull.u32 q6,d23,d0[1] ++ ++ vadd.i32 d28,d28,d18 ++ vmull.u32 q9,d29,d0[1] ++ subs r2,r2,#64 ++ vmlal.u32 q5,d29,d2[1] ++ it lo ++ movlo r4,r5 ++ vmlal.u32 q8,d25,d1[1] ++ vld1.32 d8[1],[r7,:32] ++ vmlal.u32 q6,d21,d1[1] ++ vmlal.u32 q9,d27,d1[1] ++ ++ vmlal.u32 q5,d27,d4[1] ++ vmlal.u32 q8,d23,d3[1] ++ vmlal.u32 q9,d25,d3[1] ++ vmlal.u32 q6,d29,d4[1] ++ vmlal.u32 q7,d21,d3[1] ++ ++ vmlal.u32 q8,d21,d5[1] ++ vmlal.u32 q5,d25,d6[1] ++ vmlal.u32 q9,d23,d5[1] ++ vmlal.u32 q6,d27,d6[1] ++ vmlal.u32 q7,d29,d6[1] ++ ++ vmlal.u32 q8,d29,d8[1] ++ vmlal.u32 q5,d23,d8[1] ++ vmlal.u32 q9,d21,d7[1] ++ vmlal.u32 q6,d25,d8[1] ++ vmlal.u32 q7,d27,d8[1] ++ ++ vld4.32 {d21,d23,d25,d27},[r4] @ inp[2:3] (or 0) ++ add r4,r4,#64 ++ ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ (hash+inp[0:1])*r^4 and accumulate ++ ++ vmlal.u32 q8,d26,d0[0] ++ vmlal.u32 q5,d20,d0[0] ++ vmlal.u32 q9,d28,d0[0] ++ vmlal.u32 q6,d22,d0[0] ++ vmlal.u32 q7,d24,d0[0] ++ vld1.32 d8[0],[r6,:32] ++ ++ vmlal.u32 q8,d24,d1[0] ++ vmlal.u32 q5,d28,d2[0] ++ vmlal.u32 q9,d26,d1[0] ++ vmlal.u32 q6,d20,d1[0] ++ vmlal.u32 q7,d22,d1[0] ++ ++ vmlal.u32 q8,d22,d3[0] ++ vmlal.u32 q5,d26,d4[0] ++ vmlal.u32 q9,d24,d3[0] ++ vmlal.u32 q6,d28,d4[0] ++ vmlal.u32 q7,d20,d3[0] ++ ++ vmlal.u32 q8,d20,d5[0] ++ vmlal.u32 q5,d24,d6[0] ++ vmlal.u32 q9,d22,d5[0] ++ vmlal.u32 q6,d26,d6[0] ++ vmlal.u32 q8,d28,d8[0] ++ ++ vmlal.u32 q7,d28,d6[0] ++ vmlal.u32 q5,d22,d8[0] ++ vmlal.u32 q9,d20,d7[0] ++ vmov.i32 q14,#1<<24 @ padbit, yes, always ++ vmlal.u32 q6,d24,d8[0] ++ vmlal.u32 q7,d26,d8[0] ++ ++ vld4.32 {d20,d22,d24,d26},[r1] @ inp[0:1] ++ add r1,r1,#64 ++# ifdef __ARMEB__ ++ vrev32.8 q10,q10 ++ vrev32.8 q11,q11 ++ vrev32.8 q12,q12 ++ vrev32.8 q13,q13 ++# endif ++ ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ lazy reduction interleaved with base 2^32 -> base 2^26 of ++ @ inp[0:3] previously loaded to q10-q13 and smashed to q10-q14. ++ ++ vshr.u64 q15,q8,#26 ++ vmovn.i64 d16,q8 ++ vshr.u64 q4,q5,#26 ++ vmovn.i64 d10,q5 ++ vadd.i64 q9,q9,q15 @ h3 -> h4 ++ vbic.i32 d16,#0xfc000000 ++ vsri.u32 q14,q13,#8 @ base 2^32 -> base 2^26 ++ vadd.i64 q6,q6,q4 @ h0 -> h1 ++ vshl.u32 q13,q13,#18 ++ vbic.i32 d10,#0xfc000000 ++ ++ vshrn.u64 d30,q9,#26 ++ vmovn.i64 d18,q9 ++ vshr.u64 q4,q6,#26 ++ vmovn.i64 d12,q6 ++ vadd.i64 q7,q7,q4 @ h1 -> h2 ++ vsri.u32 q13,q12,#14 ++ vbic.i32 d18,#0xfc000000 ++ vshl.u32 q12,q12,#12 ++ vbic.i32 d12,#0xfc000000 ++ ++ vadd.i32 d10,d10,d30 ++ vshl.u32 d30,d30,#2 ++ vbic.i32 q13,#0xfc000000 ++ vshrn.u64 d8,q7,#26 ++ vmovn.i64 d14,q7 ++ vaddl.u32 q5,d10,d30 @ h4 -> h0 [widen for a sec] ++ vsri.u32 q12,q11,#20 ++ vadd.i32 d16,d16,d8 @ h2 -> h3 ++ vshl.u32 q11,q11,#6 ++ vbic.i32 d14,#0xfc000000 ++ vbic.i32 q12,#0xfc000000 ++ ++ vshrn.u64 d30,q5,#26 @ re-narrow ++ vmovn.i64 d10,q5 ++ vsri.u32 q11,q10,#26 ++ vbic.i32 q10,#0xfc000000 ++ vshr.u32 d8,d16,#26 ++ vbic.i32 d16,#0xfc000000 ++ vbic.i32 d10,#0xfc000000 ++ vadd.i32 d12,d12,d30 @ h0 -> h1 ++ vadd.i32 d18,d18,d8 @ h3 -> h4 ++ vbic.i32 q11,#0xfc000000 ++ ++ bhi .Loop_neon ++ ++.Lskip_loop: ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 ++ ++ add r7,r0,#(48+0*9*4) ++ add r6,r0,#(48+1*9*4) ++ adds r2,r2,#32 ++ it ne ++ movne r2,#0 ++ bne .Long_tail ++ ++ vadd.i32 d25,d24,d14 @ add hash value and move to #hi ++ vadd.i32 d21,d20,d10 ++ vadd.i32 d27,d26,d16 ++ vadd.i32 d23,d22,d12 ++ vadd.i32 d29,d28,d18 ++ ++.Long_tail: ++ vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^1 ++ vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^2 ++ ++ vadd.i32 d24,d24,d14 @ can be redundant ++ vmull.u32 q7,d25,d0 ++ vadd.i32 d20,d20,d10 ++ vmull.u32 q5,d21,d0 ++ vadd.i32 d26,d26,d16 ++ vmull.u32 q8,d27,d0 ++ vadd.i32 d22,d22,d12 ++ vmull.u32 q6,d23,d0 ++ vadd.i32 d28,d28,d18 ++ vmull.u32 q9,d29,d0 ++ ++ vmlal.u32 q5,d29,d2 ++ vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]! ++ vmlal.u32 q8,d25,d1 ++ vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]! ++ vmlal.u32 q6,d21,d1 ++ vmlal.u32 q9,d27,d1 ++ vmlal.u32 q7,d23,d1 ++ ++ vmlal.u32 q8,d23,d3 ++ vld1.32 d8[1],[r7,:32] ++ vmlal.u32 q5,d27,d4 ++ vld1.32 d8[0],[r6,:32] ++ vmlal.u32 q9,d25,d3 ++ vmlal.u32 q6,d29,d4 ++ vmlal.u32 q7,d21,d3 ++ ++ vmlal.u32 q8,d21,d5 ++ it ne ++ addne r7,r0,#(48+2*9*4) ++ vmlal.u32 q5,d25,d6 ++ it ne ++ addne r6,r0,#(48+3*9*4) ++ vmlal.u32 q9,d23,d5 ++ vmlal.u32 q6,d27,d6 ++ vmlal.u32 q7,d29,d6 ++ ++ vmlal.u32 q8,d29,d8 ++ vorn q0,q0,q0 @ all-ones, can be redundant ++ vmlal.u32 q5,d23,d8 ++ vshr.u64 q0,q0,#38 ++ vmlal.u32 q9,d21,d7 ++ vmlal.u32 q6,d25,d8 ++ vmlal.u32 q7,d27,d8 ++ ++ beq .Lshort_tail ++ ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ (hash+inp[0:1])*r^4:r^3 and accumulate ++ ++ vld4.32 {d0[1],d1[1],d2[1],d3[1]},[r7]! @ load r^3 ++ vld4.32 {d0[0],d1[0],d2[0],d3[0]},[r6]! @ load r^4 ++ ++ vmlal.u32 q7,d24,d0 ++ vmlal.u32 q5,d20,d0 ++ vmlal.u32 q8,d26,d0 ++ vmlal.u32 q6,d22,d0 ++ vmlal.u32 q9,d28,d0 ++ ++ vmlal.u32 q5,d28,d2 ++ vld4.32 {d4[1],d5[1],d6[1],d7[1]},[r7]! ++ vmlal.u32 q8,d24,d1 ++ vld4.32 {d4[0],d5[0],d6[0],d7[0]},[r6]! ++ vmlal.u32 q6,d20,d1 ++ vmlal.u32 q9,d26,d1 ++ vmlal.u32 q7,d22,d1 ++ ++ vmlal.u32 q8,d22,d3 ++ vld1.32 d8[1],[r7,:32] ++ vmlal.u32 q5,d26,d4 ++ vld1.32 d8[0],[r6,:32] ++ vmlal.u32 q9,d24,d3 ++ vmlal.u32 q6,d28,d4 ++ vmlal.u32 q7,d20,d3 ++ ++ vmlal.u32 q8,d20,d5 ++ vmlal.u32 q5,d24,d6 ++ vmlal.u32 q9,d22,d5 ++ vmlal.u32 q6,d26,d6 ++ vmlal.u32 q7,d28,d6 ++ ++ vmlal.u32 q8,d28,d8 ++ vorn q0,q0,q0 @ all-ones ++ vmlal.u32 q5,d22,d8 ++ vshr.u64 q0,q0,#38 ++ vmlal.u32 q9,d20,d7 ++ vmlal.u32 q6,d24,d8 ++ vmlal.u32 q7,d26,d8 ++ ++.Lshort_tail: ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ horizontal addition ++ ++ vadd.i64 d16,d16,d17 ++ vadd.i64 d10,d10,d11 ++ vadd.i64 d18,d18,d19 ++ vadd.i64 d12,d12,d13 ++ vadd.i64 d14,d14,d15 ++ ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ lazy reduction, but without narrowing ++ ++ vshr.u64 q15,q8,#26 ++ vand.i64 q8,q8,q0 ++ vshr.u64 q4,q5,#26 ++ vand.i64 q5,q5,q0 ++ vadd.i64 q9,q9,q15 @ h3 -> h4 ++ vadd.i64 q6,q6,q4 @ h0 -> h1 ++ ++ vshr.u64 q15,q9,#26 ++ vand.i64 q9,q9,q0 ++ vshr.u64 q4,q6,#26 ++ vand.i64 q6,q6,q0 ++ vadd.i64 q7,q7,q4 @ h1 -> h2 ++ ++ vadd.i64 q5,q5,q15 ++ vshl.u64 q15,q15,#2 ++ vshr.u64 q4,q7,#26 ++ vand.i64 q7,q7,q0 ++ vadd.i64 q5,q5,q15 @ h4 -> h0 ++ vadd.i64 q8,q8,q4 @ h2 -> h3 ++ ++ vshr.u64 q15,q5,#26 ++ vand.i64 q5,q5,q0 ++ vshr.u64 q4,q8,#26 ++ vand.i64 q8,q8,q0 ++ vadd.i64 q6,q6,q15 @ h0 -> h1 ++ vadd.i64 q9,q9,q4 @ h3 -> h4 ++ ++ cmp r2,#0 ++ bne .Leven ++ ++ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ ++ @ store hash value ++ ++ vst4.32 {d10[0],d12[0],d14[0],d16[0]},[r0]! ++ vst1.32 {d18[0]},[r0] ++ ++ vldmia sp!,{d8-d15} @ epilogue ++ ldmia sp!,{r4-r7} ++ bx lr @ 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 ++.asciz "Poly1305 for ARMv4/NEON, CRYPTOGAMS by @dot-asm" ++.align 2 +--- /dev/null ++++ b/arch/arm/crypto/poly1305-glue.c +@@ -0,0 +1,276 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM ++ * ++ * Copyright (C) 2019 Linaro Ltd. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++void poly1305_init_arm(void *state, const u8 *key); ++void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit); ++void poly1305_emit_arm(void *state, __le32 *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_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) { ++ kernel_neon_begin(); ++ poly1305_blocks_neon(&dctx->h, src, len, 1); ++ kernel_neon_end(); ++ } 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) ++{ ++ __le32 digest[4]; ++ u64 f = 0; ++ ++ 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, digest, dctx->s); ++ ++ /* mac = (h + s) % (2^128) */ ++ f = (f >> 32) + le32_to_cpu(digest[0]); ++ put_unaligned_le32(f, dst); ++ f = (f >> 32) + le32_to_cpu(digest[1]); ++ put_unaligned_le32(f, dst + 4); ++ f = (f >> 32) + le32_to_cpu(digest[2]); ++ put_unaligned_le32(f, dst + 8); ++ f = (f >> 32) + le32_to_cpu(digest[3]); ++ put_unaligned_le32(f, dst + 12); ++ ++ *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 ++ /* register only the first entry */ ++ return crypto_register_shash(&arm_poly1305_algs[0]); ++ ++ return crypto_register_shashes(arm_poly1305_algs, ++ ARRAY_SIZE(arm_poly1305_algs)); ++} ++ ++static void __exit arm_poly1305_mod_exit(void) ++{ ++ 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"); +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -40,7 +40,7 @@ config CRYPTO_LIB_DES + config CRYPTO_LIB_POLY1305_RSIZE + int + default 4 if X86_64 +- default 9 if ARM64 ++ default 9 if ARM || ARM64 + default 1 + + config CRYPTO_ARCH_HAVE_LIB_POLY1305 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0020-crypto-mips-poly1305-incorporate-OpenSSL-CRYPTOGAMS-.patch b/target/linux/generic/backport-5.4/080-wireguard-0020-crypto-mips-poly1305-incorporate-OpenSSL-CRYPTOGAMS-.patch new file mode 100644 index 0000000000..68cac9cc57 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0020-crypto-mips-poly1305-incorporate-OpenSSL-CRYPTOGAMS-.patch @@ -0,0 +1,1563 @@ +From a338793df36990e97ab0b824fad6fbf6ef171f94 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:26 +0100 +Subject: [PATCH 020/124] crypto: mips/poly1305 - incorporate + OpenSSL/CRYPTOGAMS optimized implementation +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit a11d055e7a64ac34a5e99b6fe731299449cbcd58 upstream. + +This is a straight import of the OpenSSL/CRYPTOGAMS Poly1305 implementation for +MIPS authored by Andy Polyakov, a prior 64-bit only version of which has been +contributed by him to the OpenSSL project. The file 'poly1305-mips.pl' is taken +straight from this upstream GitHub repository [0] at commit +d22ade312a7af958ec955620b0d241cf42c37feb, and already contains all the changes +required to build it as part of a Linux kernel module. + +[0] https://github.com/dot-asm/cryptogams + +Co-developed-by: Andy Polyakov +Signed-off-by: Andy Polyakov +Co-developed-by: René van Dorst +Signed-off-by: René van Dorst +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/mips/crypto/Makefile | 14 + + arch/mips/crypto/poly1305-glue.c | 203 +++++ + arch/mips/crypto/poly1305-mips.pl | 1273 +++++++++++++++++++++++++++++ + crypto/Kconfig | 5 + + lib/crypto/Kconfig | 1 + + 5 files changed, 1496 insertions(+) + create mode 100644 arch/mips/crypto/poly1305-glue.c + create mode 100644 arch/mips/crypto/poly1305-mips.pl + +--- a/arch/mips/crypto/Makefile ++++ b/arch/mips/crypto/Makefile +@@ -8,3 +8,17 @@ obj-$(CONFIG_CRYPTO_CRC32_MIPS) += crc32 + obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o + chacha-mips-y := chacha-core.o chacha-glue.o + AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots ++ ++obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o ++poly1305-mips-y := poly1305-core.o poly1305-glue.o ++ ++perlasm-flavour-$(CONFIG_CPU_MIPS32) := o32 ++perlasm-flavour-$(CONFIG_CPU_MIPS64) := 64 ++ ++quiet_cmd_perlasm = PERLASM $@ ++ cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@) ++ ++$(obj)/poly1305-core.S: $(src)/poly1305-mips.pl FORCE ++ $(call if_changed,perlasm) ++ ++targets += poly1305-core.S +--- /dev/null ++++ b/arch/mips/crypto/poly1305-glue.c +@@ -0,0 +1,203 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * OpenSSL/Cryptogams accelerated Poly1305 transform for MIPS ++ * ++ * Copyright (C) 2019 Linaro Ltd. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++asmlinkage void poly1305_init_mips(void *state, const u8 *key); ++asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit); ++asmlinkage void poly1305_emit_mips(void *state, __le32 *digest, const u32 *nonce); ++ ++void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) ++{ ++ poly1305_init_mips(&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 mips_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 mips_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src, ++ u32 len, u32 hibit) ++{ ++ if (unlikely(!dctx->sset)) { ++ if (!dctx->rset) { ++ poly1305_init_mips(&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); ++ ++ poly1305_blocks_mips(&dctx->h, src, len, hibit); ++} ++ ++static int mips_poly1305_update(struct shash_desc *desc, const u8 *src, ++ unsigned int len) ++{ ++ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); ++ ++ 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) { ++ mips_poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 1); ++ dctx->buflen = 0; ++ } ++ } ++ ++ if (likely(len >= POLY1305_BLOCK_SIZE)) { ++ mips_poly1305_blocks(dctx, src, len, 1); ++ src += round_down(len, POLY1305_BLOCK_SIZE); ++ len %= POLY1305_BLOCK_SIZE; ++ } ++ ++ if (unlikely(len)) { ++ dctx->buflen = len; ++ memcpy(dctx->buf, src, len); ++ } ++ return 0; ++} ++ ++void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, ++ unsigned int nbytes) ++{ ++ 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_mips(&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); ++ ++ poly1305_blocks_mips(&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) ++{ ++ __le32 digest[4]; ++ u64 f = 0; ++ ++ if (unlikely(dctx->buflen)) { ++ dctx->buf[dctx->buflen++] = 1; ++ memset(dctx->buf + dctx->buflen, 0, ++ POLY1305_BLOCK_SIZE - dctx->buflen); ++ poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); ++ } ++ ++ poly1305_emit_mips(&dctx->h, digest, dctx->s); ++ ++ /* mac = (h + s) % (2^128) */ ++ f = (f >> 32) + le32_to_cpu(digest[0]); ++ put_unaligned_le32(f, dst); ++ f = (f >> 32) + le32_to_cpu(digest[1]); ++ put_unaligned_le32(f, dst + 4); ++ f = (f >> 32) + le32_to_cpu(digest[2]); ++ put_unaligned_le32(f, dst + 8); ++ f = (f >> 32) + le32_to_cpu(digest[3]); ++ put_unaligned_le32(f, dst + 12); ++ ++ *dctx = (struct poly1305_desc_ctx){}; ++} ++EXPORT_SYMBOL(poly1305_final_arch); ++ ++static int mips_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 mips_poly1305_alg = { ++ .init = mips_poly1305_init, ++ .update = mips_poly1305_update, ++ .final = mips_poly1305_final, ++ .digestsize = POLY1305_DIGEST_SIZE, ++ .descsize = sizeof(struct poly1305_desc_ctx), ++ ++ .base.cra_name = "poly1305", ++ .base.cra_driver_name = "poly1305-mips", ++ .base.cra_priority = 200, ++ .base.cra_blocksize = POLY1305_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++}; ++ ++static int __init mips_poly1305_mod_init(void) ++{ ++ return crypto_register_shash(&mips_poly1305_alg); ++} ++ ++static void __exit mips_poly1305_mod_exit(void) ++{ ++ crypto_unregister_shash(&mips_poly1305_alg); ++} ++ ++module_init(mips_poly1305_mod_init); ++module_exit(mips_poly1305_mod_exit); ++ ++MODULE_LICENSE("GPL v2"); ++MODULE_ALIAS_CRYPTO("poly1305"); ++MODULE_ALIAS_CRYPTO("poly1305-mips"); +--- /dev/null ++++ b/arch/mips/crypto/poly1305-mips.pl +@@ -0,0 +1,1273 @@ ++#!/usr/bin/env perl ++# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause ++# ++# ==================================================================== ++# Written by Andy Polyakov, @dot-asm, originally for the OpenSSL ++# project. ++# ==================================================================== ++ ++# Poly1305 hash for MIPS. ++# ++# May 2016 ++# ++# Numbers are cycles per processed byte with poly1305_blocks alone. ++# ++# IALU/gcc ++# R1x000 ~5.5/+130% (big-endian) ++# Octeon II 2.50/+70% (little-endian) ++# ++# March 2019 ++# ++# Add 32-bit code path. ++# ++# October 2019 ++# ++# Modulo-scheduling reduction allows to omit dependency chain at the ++# end of inner loop and improve performance. Also optimize MIPS32R2 ++# code path for MIPS 1004K core. Per René von Dorst's suggestions. ++# ++# IALU/gcc ++# R1x000 ~9.8/? (big-endian) ++# Octeon II 3.65/+140% (little-endian) ++# MT7621/1004K 4.75/? (little-endian) ++# ++###################################################################### ++# There is a number of MIPS ABI in use, O32 and N32/64 are most ++# widely used. Then there is a new contender: NUBI. It appears that if ++# one picks the latter, it's possible to arrange code in ABI neutral ++# manner. Therefore let's stick to NUBI register layout: ++# ++($zero,$at,$t0,$t1,$t2)=map("\$$_",(0..2,24,25)); ++($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11)); ++($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7,$s8,$s9,$s10,$s11)=map("\$$_",(12..23)); ++($gp,$tp,$sp,$fp,$ra)=map("\$$_",(3,28..31)); ++# ++# The return value is placed in $a0. Following coding rules facilitate ++# interoperability: ++# ++# - never ever touch $tp, "thread pointer", former $gp [o32 can be ++# excluded from the rule, because it's specified volatile]; ++# - copy return value to $t0, former $v0 [or to $a0 if you're adapting ++# old code]; ++# - on O32 populate $a4-$a7 with 'lw $aN,4*N($sp)' if necessary; ++# ++# For reference here is register layout for N32/64 MIPS ABIs: ++# ++# ($zero,$at,$v0,$v1)=map("\$$_",(0..3)); ++# ($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11)); ++# ($t0,$t1,$t2,$t3,$t8,$t9)=map("\$$_",(12..15,24,25)); ++# ($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7)=map("\$$_",(16..23)); ++# ($gp,$sp,$fp,$ra)=map("\$$_",(28..31)); ++# ++# ++# ++###################################################################### ++ ++$flavour = shift || "64"; # supported flavours are o32,n32,64,nubi32,nubi64 ++ ++$v0 = ($flavour =~ /nubi/i) ? $a0 : $t0; ++ ++if ($flavour =~ /64|n32/i) {{{ ++###################################################################### ++# 64-bit code path ++# ++ ++my ($ctx,$inp,$len,$padbit) = ($a0,$a1,$a2,$a3); ++my ($in0,$in1,$tmp0,$tmp1,$tmp2,$tmp3,$tmp4) = ($a4,$a5,$a6,$a7,$at,$t0,$t1); ++ ++$code.=<<___; ++#if (defined(_MIPS_ARCH_MIPS64R3) || defined(_MIPS_ARCH_MIPS64R5) || \\ ++ defined(_MIPS_ARCH_MIPS64R6)) \\ ++ && !defined(_MIPS_ARCH_MIPS64R2) ++# define _MIPS_ARCH_MIPS64R2 ++#endif ++ ++#if defined(_MIPS_ARCH_MIPS64R6) ++# define dmultu(rs,rt) ++# define mflo(rd,rs,rt) dmulu rd,rs,rt ++# define mfhi(rd,rs,rt) dmuhu rd,rs,rt ++#else ++# define dmultu(rs,rt) dmultu rs,rt ++# define mflo(rd,rs,rt) mflo rd ++# define mfhi(rd,rs,rt) mfhi rd ++#endif ++ ++#ifdef __KERNEL__ ++# define poly1305_init poly1305_init_mips ++# define poly1305_blocks poly1305_blocks_mips ++# define poly1305_emit poly1305_emit_mips ++#endif ++ ++#if defined(__MIPSEB__) && !defined(MIPSEB) ++# define MIPSEB ++#endif ++ ++#ifdef MIPSEB ++# define MSB 0 ++# define LSB 7 ++#else ++# define MSB 7 ++# define LSB 0 ++#endif ++ ++.text ++.set noat ++.set noreorder ++ ++.align 5 ++.globl poly1305_init ++.ent poly1305_init ++poly1305_init: ++ .frame $sp,0,$ra ++ .set reorder ++ ++ sd $zero,0($ctx) ++ sd $zero,8($ctx) ++ sd $zero,16($ctx) ++ ++ beqz $inp,.Lno_key ++ ++#if defined(_MIPS_ARCH_MIPS64R6) ++ andi $tmp0,$inp,7 # $inp % 8 ++ dsubu $inp,$inp,$tmp0 # align $inp ++ sll $tmp0,$tmp0,3 # byte to bit offset ++ ld $in0,0($inp) ++ ld $in1,8($inp) ++ beqz $tmp0,.Laligned_key ++ ld $tmp2,16($inp) ++ ++ subu $tmp1,$zero,$tmp0 ++# ifdef MIPSEB ++ dsllv $in0,$in0,$tmp0 ++ dsrlv $tmp3,$in1,$tmp1 ++ dsllv $in1,$in1,$tmp0 ++ dsrlv $tmp2,$tmp2,$tmp1 ++# else ++ dsrlv $in0,$in0,$tmp0 ++ dsllv $tmp3,$in1,$tmp1 ++ dsrlv $in1,$in1,$tmp0 ++ dsllv $tmp2,$tmp2,$tmp1 ++# endif ++ or $in0,$in0,$tmp3 ++ or $in1,$in1,$tmp2 ++.Laligned_key: ++#else ++ ldl $in0,0+MSB($inp) ++ ldl $in1,8+MSB($inp) ++ ldr $in0,0+LSB($inp) ++ ldr $in1,8+LSB($inp) ++#endif ++#ifdef MIPSEB ++# if defined(_MIPS_ARCH_MIPS64R2) ++ dsbh $in0,$in0 # byte swap ++ dsbh $in1,$in1 ++ dshd $in0,$in0 ++ dshd $in1,$in1 ++# else ++ ori $tmp0,$zero,0xFF ++ dsll $tmp2,$tmp0,32 ++ or $tmp0,$tmp2 # 0x000000FF000000FF ++ ++ and $tmp1,$in0,$tmp0 # byte swap ++ and $tmp3,$in1,$tmp0 ++ dsrl $tmp2,$in0,24 ++ dsrl $tmp4,$in1,24 ++ dsll $tmp1,24 ++ dsll $tmp3,24 ++ and $tmp2,$tmp0 ++ and $tmp4,$tmp0 ++ dsll $tmp0,8 # 0x0000FF000000FF00 ++ or $tmp1,$tmp2 ++ or $tmp3,$tmp4 ++ and $tmp2,$in0,$tmp0 ++ and $tmp4,$in1,$tmp0 ++ dsrl $in0,8 ++ dsrl $in1,8 ++ dsll $tmp2,8 ++ dsll $tmp4,8 ++ and $in0,$tmp0 ++ and $in1,$tmp0 ++ or $tmp1,$tmp2 ++ or $tmp3,$tmp4 ++ or $in0,$tmp1 ++ or $in1,$tmp3 ++ dsrl $tmp1,$in0,32 ++ dsrl $tmp3,$in1,32 ++ dsll $in0,32 ++ dsll $in1,32 ++ or $in0,$tmp1 ++ or $in1,$tmp3 ++# endif ++#endif ++ li $tmp0,1 ++ dsll $tmp0,32 # 0x0000000100000000 ++ daddiu $tmp0,-63 # 0x00000000ffffffc1 ++ dsll $tmp0,28 # 0x0ffffffc10000000 ++ daddiu $tmp0,-1 # 0x0ffffffc0fffffff ++ ++ and $in0,$tmp0 ++ daddiu $tmp0,-3 # 0x0ffffffc0ffffffc ++ and $in1,$tmp0 ++ ++ sd $in0,24($ctx) ++ dsrl $tmp0,$in1,2 ++ sd $in1,32($ctx) ++ daddu $tmp0,$in1 # s1 = r1 + (r1 >> 2) ++ sd $tmp0,40($ctx) ++ ++.Lno_key: ++ li $v0,0 # return 0 ++ jr $ra ++.end poly1305_init ++___ ++{ ++my $SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0x0003f000" : "0x00030000"; ++ ++my ($h0,$h1,$h2,$r0,$r1,$rs1,$d0,$d1,$d2) = ++ ($s0,$s1,$s2,$s3,$s4,$s5,$in0,$in1,$t2); ++my ($shr,$shl) = ($s6,$s7); # used on R6 ++ ++$code.=<<___; ++.align 5 ++.globl poly1305_blocks ++.ent poly1305_blocks ++poly1305_blocks: ++ .set noreorder ++ dsrl $len,4 # number of complete blocks ++ bnez $len,poly1305_blocks_internal ++ nop ++ jr $ra ++ nop ++.end poly1305_blocks ++ ++.align 5 ++.ent poly1305_blocks_internal ++poly1305_blocks_internal: ++ .set noreorder ++#if defined(_MIPS_ARCH_MIPS64R6) ++ .frame $sp,8*8,$ra ++ .mask $SAVED_REGS_MASK|0x000c0000,-8 ++ dsubu $sp,8*8 ++ sd $s7,56($sp) ++ sd $s6,48($sp) ++#else ++ .frame $sp,6*8,$ra ++ .mask $SAVED_REGS_MASK,-8 ++ dsubu $sp,6*8 ++#endif ++ sd $s5,40($sp) ++ sd $s4,32($sp) ++___ ++$code.=<<___ if ($flavour =~ /nubi/i); # optimize non-nubi prologue ++ sd $s3,24($sp) ++ sd $s2,16($sp) ++ sd $s1,8($sp) ++ sd $s0,0($sp) ++___ ++$code.=<<___; ++ .set reorder ++ ++#if defined(_MIPS_ARCH_MIPS64R6) ++ andi $shr,$inp,7 ++ dsubu $inp,$inp,$shr # align $inp ++ sll $shr,$shr,3 # byte to bit offset ++ subu $shl,$zero,$shr ++#endif ++ ++ ld $h0,0($ctx) # load hash value ++ ld $h1,8($ctx) ++ ld $h2,16($ctx) ++ ++ ld $r0,24($ctx) # load key ++ ld $r1,32($ctx) ++ ld $rs1,40($ctx) ++ ++ dsll $len,4 ++ daddu $len,$inp # end of buffer ++ b .Loop ++ ++.align 4 ++.Loop: ++#if defined(_MIPS_ARCH_MIPS64R6) ++ ld $in0,0($inp) # load input ++ ld $in1,8($inp) ++ beqz $shr,.Laligned_inp ++ ++ ld $tmp2,16($inp) ++# ifdef MIPSEB ++ dsllv $in0,$in0,$shr ++ dsrlv $tmp3,$in1,$shl ++ dsllv $in1,$in1,$shr ++ dsrlv $tmp2,$tmp2,$shl ++# else ++ dsrlv $in0,$in0,$shr ++ dsllv $tmp3,$in1,$shl ++ dsrlv $in1,$in1,$shr ++ dsllv $tmp2,$tmp2,$shl ++# endif ++ or $in0,$in0,$tmp3 ++ or $in1,$in1,$tmp2 ++.Laligned_inp: ++#else ++ ldl $in0,0+MSB($inp) # load input ++ ldl $in1,8+MSB($inp) ++ ldr $in0,0+LSB($inp) ++ ldr $in1,8+LSB($inp) ++#endif ++ daddiu $inp,16 ++#ifdef MIPSEB ++# if defined(_MIPS_ARCH_MIPS64R2) ++ dsbh $in0,$in0 # byte swap ++ dsbh $in1,$in1 ++ dshd $in0,$in0 ++ dshd $in1,$in1 ++# else ++ ori $tmp0,$zero,0xFF ++ dsll $tmp2,$tmp0,32 ++ or $tmp0,$tmp2 # 0x000000FF000000FF ++ ++ and $tmp1,$in0,$tmp0 # byte swap ++ and $tmp3,$in1,$tmp0 ++ dsrl $tmp2,$in0,24 ++ dsrl $tmp4,$in1,24 ++ dsll $tmp1,24 ++ dsll $tmp3,24 ++ and $tmp2,$tmp0 ++ and $tmp4,$tmp0 ++ dsll $tmp0,8 # 0x0000FF000000FF00 ++ or $tmp1,$tmp2 ++ or $tmp3,$tmp4 ++ and $tmp2,$in0,$tmp0 ++ and $tmp4,$in1,$tmp0 ++ dsrl $in0,8 ++ dsrl $in1,8 ++ dsll $tmp2,8 ++ dsll $tmp4,8 ++ and $in0,$tmp0 ++ and $in1,$tmp0 ++ or $tmp1,$tmp2 ++ or $tmp3,$tmp4 ++ or $in0,$tmp1 ++ or $in1,$tmp3 ++ dsrl $tmp1,$in0,32 ++ dsrl $tmp3,$in1,32 ++ dsll $in0,32 ++ dsll $in1,32 ++ or $in0,$tmp1 ++ or $in1,$tmp3 ++# endif ++#endif ++ dsrl $tmp1,$h2,2 # modulo-scheduled reduction ++ andi $h2,$h2,3 ++ dsll $tmp0,$tmp1,2 ++ ++ daddu $d0,$h0,$in0 # accumulate input ++ daddu $tmp1,$tmp0 ++ sltu $tmp0,$d0,$h0 ++ daddu $d0,$d0,$tmp1 # ... and residue ++ sltu $tmp1,$d0,$tmp1 ++ daddu $d1,$h1,$in1 ++ daddu $tmp0,$tmp1 ++ sltu $tmp1,$d1,$h1 ++ daddu $d1,$tmp0 ++ ++ dmultu ($r0,$d0) # h0*r0 ++ daddu $d2,$h2,$padbit ++ sltu $tmp0,$d1,$tmp0 ++ mflo ($h0,$r0,$d0) ++ mfhi ($h1,$r0,$d0) ++ ++ dmultu ($rs1,$d1) # h1*5*r1 ++ daddu $d2,$tmp1 ++ daddu $d2,$tmp0 ++ mflo ($tmp0,$rs1,$d1) ++ mfhi ($tmp1,$rs1,$d1) ++ ++ dmultu ($r1,$d0) # h0*r1 ++ mflo ($tmp2,$r1,$d0) ++ mfhi ($h2,$r1,$d0) ++ daddu $h0,$tmp0 ++ daddu $h1,$tmp1 ++ sltu $tmp0,$h0,$tmp0 ++ ++ dmultu ($r0,$d1) # h1*r0 ++ daddu $h1,$tmp0 ++ daddu $h1,$tmp2 ++ mflo ($tmp0,$r0,$d1) ++ mfhi ($tmp1,$r0,$d1) ++ ++ dmultu ($rs1,$d2) # h2*5*r1 ++ sltu $tmp2,$h1,$tmp2 ++ daddu $h2,$tmp2 ++ mflo ($tmp2,$rs1,$d2) ++ ++ dmultu ($r0,$d2) # h2*r0 ++ daddu $h1,$tmp0 ++ daddu $h2,$tmp1 ++ mflo ($tmp3,$r0,$d2) ++ sltu $tmp0,$h1,$tmp0 ++ daddu $h2,$tmp0 ++ ++ daddu $h1,$tmp2 ++ sltu $tmp2,$h1,$tmp2 ++ daddu $h2,$tmp2 ++ daddu $h2,$tmp3 ++ ++ bne $inp,$len,.Loop ++ ++ sd $h0,0($ctx) # store hash value ++ sd $h1,8($ctx) ++ sd $h2,16($ctx) ++ ++ .set noreorder ++#if defined(_MIPS_ARCH_MIPS64R6) ++ ld $s7,56($sp) ++ ld $s6,48($sp) ++#endif ++ ld $s5,40($sp) # epilogue ++ ld $s4,32($sp) ++___ ++$code.=<<___ if ($flavour =~ /nubi/i); # optimize non-nubi epilogue ++ ld $s3,24($sp) ++ ld $s2,16($sp) ++ ld $s1,8($sp) ++ ld $s0,0($sp) ++___ ++$code.=<<___; ++ jr $ra ++#if defined(_MIPS_ARCH_MIPS64R6) ++ daddu $sp,8*8 ++#else ++ daddu $sp,6*8 ++#endif ++.end poly1305_blocks_internal ++___ ++} ++{ ++my ($ctx,$mac,$nonce) = ($a0,$a1,$a2); ++ ++$code.=<<___; ++.align 5 ++.globl poly1305_emit ++.ent poly1305_emit ++poly1305_emit: ++ .frame $sp,0,$ra ++ .set reorder ++ ++ ld $tmp2,16($ctx) ++ ld $tmp0,0($ctx) ++ ld $tmp1,8($ctx) ++ ++ li $in0,-4 # final reduction ++ dsrl $in1,$tmp2,2 ++ and $in0,$tmp2 ++ andi $tmp2,$tmp2,3 ++ daddu $in0,$in1 ++ ++ daddu $tmp0,$tmp0,$in0 ++ sltu $in1,$tmp0,$in0 ++ daddiu $in0,$tmp0,5 # compare to modulus ++ daddu $tmp1,$tmp1,$in1 ++ sltiu $tmp3,$in0,5 ++ sltu $tmp4,$tmp1,$in1 ++ daddu $in1,$tmp1,$tmp3 ++ daddu $tmp2,$tmp2,$tmp4 ++ sltu $tmp3,$in1,$tmp3 ++ daddu $tmp2,$tmp2,$tmp3 ++ ++ dsrl $tmp2,2 # see if it carried/borrowed ++ dsubu $tmp2,$zero,$tmp2 ++ ++ xor $in0,$tmp0 ++ xor $in1,$tmp1 ++ and $in0,$tmp2 ++ and $in1,$tmp2 ++ xor $in0,$tmp0 ++ xor $in1,$tmp1 ++ ++ lwu $tmp0,0($nonce) # load nonce ++ lwu $tmp1,4($nonce) ++ lwu $tmp2,8($nonce) ++ lwu $tmp3,12($nonce) ++ dsll $tmp1,32 ++ dsll $tmp3,32 ++ or $tmp0,$tmp1 ++ or $tmp2,$tmp3 ++ ++ daddu $in0,$tmp0 # accumulate nonce ++ daddu $in1,$tmp2 ++ sltu $tmp0,$in0,$tmp0 ++ daddu $in1,$tmp0 ++ ++ dsrl $tmp0,$in0,8 # write mac value ++ dsrl $tmp1,$in0,16 ++ dsrl $tmp2,$in0,24 ++ sb $in0,0($mac) ++ dsrl $tmp3,$in0,32 ++ sb $tmp0,1($mac) ++ dsrl $tmp0,$in0,40 ++ sb $tmp1,2($mac) ++ dsrl $tmp1,$in0,48 ++ sb $tmp2,3($mac) ++ dsrl $tmp2,$in0,56 ++ sb $tmp3,4($mac) ++ dsrl $tmp3,$in1,8 ++ sb $tmp0,5($mac) ++ dsrl $tmp0,$in1,16 ++ sb $tmp1,6($mac) ++ dsrl $tmp1,$in1,24 ++ sb $tmp2,7($mac) ++ ++ sb $in1,8($mac) ++ dsrl $tmp2,$in1,32 ++ sb $tmp3,9($mac) ++ dsrl $tmp3,$in1,40 ++ sb $tmp0,10($mac) ++ dsrl $tmp0,$in1,48 ++ sb $tmp1,11($mac) ++ dsrl $tmp1,$in1,56 ++ sb $tmp2,12($mac) ++ sb $tmp3,13($mac) ++ sb $tmp0,14($mac) ++ sb $tmp1,15($mac) ++ ++ jr $ra ++.end poly1305_emit ++.rdata ++.asciiz "Poly1305 for MIPS64, CRYPTOGAMS by \@dot-asm" ++.align 2 ++___ ++} ++}}} else {{{ ++###################################################################### ++# 32-bit code path ++# ++ ++my ($ctx,$inp,$len,$padbit) = ($a0,$a1,$a2,$a3); ++my ($in0,$in1,$in2,$in3,$tmp0,$tmp1,$tmp2,$tmp3) = ++ ($a4,$a5,$a6,$a7,$at,$t0,$t1,$t2); ++ ++$code.=<<___; ++#if (defined(_MIPS_ARCH_MIPS32R3) || defined(_MIPS_ARCH_MIPS32R5) || \\ ++ defined(_MIPS_ARCH_MIPS32R6)) \\ ++ && !defined(_MIPS_ARCH_MIPS32R2) ++# define _MIPS_ARCH_MIPS32R2 ++#endif ++ ++#if defined(_MIPS_ARCH_MIPS32R6) ++# define multu(rs,rt) ++# define mflo(rd,rs,rt) mulu rd,rs,rt ++# define mfhi(rd,rs,rt) muhu rd,rs,rt ++#else ++# define multu(rs,rt) multu rs,rt ++# define mflo(rd,rs,rt) mflo rd ++# define mfhi(rd,rs,rt) mfhi rd ++#endif ++ ++#ifdef __KERNEL__ ++# define poly1305_init poly1305_init_mips ++# define poly1305_blocks poly1305_blocks_mips ++# define poly1305_emit poly1305_emit_mips ++#endif ++ ++#if defined(__MIPSEB__) && !defined(MIPSEB) ++# define MIPSEB ++#endif ++ ++#ifdef MIPSEB ++# define MSB 0 ++# define LSB 3 ++#else ++# define MSB 3 ++# define LSB 0 ++#endif ++ ++.text ++.set noat ++.set noreorder ++ ++.align 5 ++.globl poly1305_init ++.ent poly1305_init ++poly1305_init: ++ .frame $sp,0,$ra ++ .set reorder ++ ++ sw $zero,0($ctx) ++ sw $zero,4($ctx) ++ sw $zero,8($ctx) ++ sw $zero,12($ctx) ++ sw $zero,16($ctx) ++ ++ beqz $inp,.Lno_key ++ ++#if defined(_MIPS_ARCH_MIPS32R6) ++ andi $tmp0,$inp,3 # $inp % 4 ++ subu $inp,$inp,$tmp0 # align $inp ++ sll $tmp0,$tmp0,3 # byte to bit offset ++ lw $in0,0($inp) ++ lw $in1,4($inp) ++ lw $in2,8($inp) ++ lw $in3,12($inp) ++ beqz $tmp0,.Laligned_key ++ ++ lw $tmp2,16($inp) ++ subu $tmp1,$zero,$tmp0 ++# ifdef MIPSEB ++ sllv $in0,$in0,$tmp0 ++ srlv $tmp3,$in1,$tmp1 ++ sllv $in1,$in1,$tmp0 ++ or $in0,$in0,$tmp3 ++ srlv $tmp3,$in2,$tmp1 ++ sllv $in2,$in2,$tmp0 ++ or $in1,$in1,$tmp3 ++ srlv $tmp3,$in3,$tmp1 ++ sllv $in3,$in3,$tmp0 ++ or $in2,$in2,$tmp3 ++ srlv $tmp2,$tmp2,$tmp1 ++ or $in3,$in3,$tmp2 ++# else ++ srlv $in0,$in0,$tmp0 ++ sllv $tmp3,$in1,$tmp1 ++ srlv $in1,$in1,$tmp0 ++ or $in0,$in0,$tmp3 ++ sllv $tmp3,$in2,$tmp1 ++ srlv $in2,$in2,$tmp0 ++ or $in1,$in1,$tmp3 ++ sllv $tmp3,$in3,$tmp1 ++ srlv $in3,$in3,$tmp0 ++ or $in2,$in2,$tmp3 ++ sllv $tmp2,$tmp2,$tmp1 ++ or $in3,$in3,$tmp2 ++# endif ++.Laligned_key: ++#else ++ lwl $in0,0+MSB($inp) ++ lwl $in1,4+MSB($inp) ++ lwl $in2,8+MSB($inp) ++ lwl $in3,12+MSB($inp) ++ lwr $in0,0+LSB($inp) ++ lwr $in1,4+LSB($inp) ++ lwr $in2,8+LSB($inp) ++ lwr $in3,12+LSB($inp) ++#endif ++#ifdef MIPSEB ++# if defined(_MIPS_ARCH_MIPS32R2) ++ wsbh $in0,$in0 # byte swap ++ wsbh $in1,$in1 ++ wsbh $in2,$in2 ++ wsbh $in3,$in3 ++ rotr $in0,$in0,16 ++ rotr $in1,$in1,16 ++ rotr $in2,$in2,16 ++ rotr $in3,$in3,16 ++# else ++ srl $tmp0,$in0,24 # byte swap ++ srl $tmp1,$in0,8 ++ andi $tmp2,$in0,0xFF00 ++ sll $in0,$in0,24 ++ andi $tmp1,0xFF00 ++ sll $tmp2,$tmp2,8 ++ or $in0,$tmp0 ++ srl $tmp0,$in1,24 ++ or $tmp1,$tmp2 ++ srl $tmp2,$in1,8 ++ or $in0,$tmp1 ++ andi $tmp1,$in1,0xFF00 ++ sll $in1,$in1,24 ++ andi $tmp2,0xFF00 ++ sll $tmp1,$tmp1,8 ++ or $in1,$tmp0 ++ srl $tmp0,$in2,24 ++ or $tmp2,$tmp1 ++ srl $tmp1,$in2,8 ++ or $in1,$tmp2 ++ andi $tmp2,$in2,0xFF00 ++ sll $in2,$in2,24 ++ andi $tmp1,0xFF00 ++ sll $tmp2,$tmp2,8 ++ or $in2,$tmp0 ++ srl $tmp0,$in3,24 ++ or $tmp1,$tmp2 ++ srl $tmp2,$in3,8 ++ or $in2,$tmp1 ++ andi $tmp1,$in3,0xFF00 ++ sll $in3,$in3,24 ++ andi $tmp2,0xFF00 ++ sll $tmp1,$tmp1,8 ++ or $in3,$tmp0 ++ or $tmp2,$tmp1 ++ or $in3,$tmp2 ++# endif ++#endif ++ lui $tmp0,0x0fff ++ ori $tmp0,0xffff # 0x0fffffff ++ and $in0,$in0,$tmp0 ++ subu $tmp0,3 # 0x0ffffffc ++ and $in1,$in1,$tmp0 ++ and $in2,$in2,$tmp0 ++ and $in3,$in3,$tmp0 ++ ++ sw $in0,20($ctx) ++ sw $in1,24($ctx) ++ sw $in2,28($ctx) ++ sw $in3,32($ctx) ++ ++ srl $tmp1,$in1,2 ++ srl $tmp2,$in2,2 ++ srl $tmp3,$in3,2 ++ addu $in1,$in1,$tmp1 # s1 = r1 + (r1 >> 2) ++ addu $in2,$in2,$tmp2 ++ addu $in3,$in3,$tmp3 ++ sw $in1,36($ctx) ++ sw $in2,40($ctx) ++ sw $in3,44($ctx) ++.Lno_key: ++ li $v0,0 ++ jr $ra ++.end poly1305_init ++___ ++{ ++my $SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0x00fff000" : "0x00ff0000"; ++ ++my ($h0,$h1,$h2,$h3,$h4, $r0,$r1,$r2,$r3, $rs1,$rs2,$rs3) = ++ ($s0,$s1,$s2,$s3,$s4, $s5,$s6,$s7,$s8, $s9,$s10,$s11); ++my ($d0,$d1,$d2,$d3) = ++ ($a4,$a5,$a6,$a7); ++my $shr = $t2; # used on R6 ++my $one = $t2; # used on R2 ++ ++$code.=<<___; ++.globl poly1305_blocks ++.align 5 ++.ent poly1305_blocks ++poly1305_blocks: ++ .frame $sp,16*4,$ra ++ .mask $SAVED_REGS_MASK,-4 ++ .set noreorder ++ subu $sp, $sp,4*12 ++ sw $s11,4*11($sp) ++ sw $s10,4*10($sp) ++ sw $s9, 4*9($sp) ++ sw $s8, 4*8($sp) ++ sw $s7, 4*7($sp) ++ sw $s6, 4*6($sp) ++ sw $s5, 4*5($sp) ++ sw $s4, 4*4($sp) ++___ ++$code.=<<___ if ($flavour =~ /nubi/i); # optimize non-nubi prologue ++ sw $s3, 4*3($sp) ++ sw $s2, 4*2($sp) ++ sw $s1, 4*1($sp) ++ sw $s0, 4*0($sp) ++___ ++$code.=<<___; ++ .set reorder ++ ++ srl $len,4 # number of complete blocks ++ li $one,1 ++ beqz $len,.Labort ++ ++#if defined(_MIPS_ARCH_MIPS32R6) ++ andi $shr,$inp,3 ++ subu $inp,$inp,$shr # align $inp ++ sll $shr,$shr,3 # byte to bit offset ++#endif ++ ++ lw $h0,0($ctx) # load hash value ++ lw $h1,4($ctx) ++ lw $h2,8($ctx) ++ lw $h3,12($ctx) ++ lw $h4,16($ctx) ++ ++ lw $r0,20($ctx) # load key ++ lw $r1,24($ctx) ++ lw $r2,28($ctx) ++ lw $r3,32($ctx) ++ lw $rs1,36($ctx) ++ lw $rs2,40($ctx) ++ lw $rs3,44($ctx) ++ ++ sll $len,4 ++ addu $len,$len,$inp # end of buffer ++ b .Loop ++ ++.align 4 ++.Loop: ++#if defined(_MIPS_ARCH_MIPS32R6) ++ lw $d0,0($inp) # load input ++ lw $d1,4($inp) ++ lw $d2,8($inp) ++ lw $d3,12($inp) ++ beqz $shr,.Laligned_inp ++ ++ lw $t0,16($inp) ++ subu $t1,$zero,$shr ++# ifdef MIPSEB ++ sllv $d0,$d0,$shr ++ srlv $at,$d1,$t1 ++ sllv $d1,$d1,$shr ++ or $d0,$d0,$at ++ srlv $at,$d2,$t1 ++ sllv $d2,$d2,$shr ++ or $d1,$d1,$at ++ srlv $at,$d3,$t1 ++ sllv $d3,$d3,$shr ++ or $d2,$d2,$at ++ srlv $t0,$t0,$t1 ++ or $d3,$d3,$t0 ++# else ++ srlv $d0,$d0,$shr ++ sllv $at,$d1,$t1 ++ srlv $d1,$d1,$shr ++ or $d0,$d0,$at ++ sllv $at,$d2,$t1 ++ srlv $d2,$d2,$shr ++ or $d1,$d1,$at ++ sllv $at,$d3,$t1 ++ srlv $d3,$d3,$shr ++ or $d2,$d2,$at ++ sllv $t0,$t0,$t1 ++ or $d3,$d3,$t0 ++# endif ++.Laligned_inp: ++#else ++ lwl $d0,0+MSB($inp) # load input ++ lwl $d1,4+MSB($inp) ++ lwl $d2,8+MSB($inp) ++ lwl $d3,12+MSB($inp) ++ lwr $d0,0+LSB($inp) ++ lwr $d1,4+LSB($inp) ++ lwr $d2,8+LSB($inp) ++ lwr $d3,12+LSB($inp) ++#endif ++#ifdef MIPSEB ++# if defined(_MIPS_ARCH_MIPS32R2) ++ wsbh $d0,$d0 # byte swap ++ wsbh $d1,$d1 ++ wsbh $d2,$d2 ++ wsbh $d3,$d3 ++ rotr $d0,$d0,16 ++ rotr $d1,$d1,16 ++ rotr $d2,$d2,16 ++ rotr $d3,$d3,16 ++# else ++ srl $at,$d0,24 # byte swap ++ srl $t0,$d0,8 ++ andi $t1,$d0,0xFF00 ++ sll $d0,$d0,24 ++ andi $t0,0xFF00 ++ sll $t1,$t1,8 ++ or $d0,$at ++ srl $at,$d1,24 ++ or $t0,$t1 ++ srl $t1,$d1,8 ++ or $d0,$t0 ++ andi $t0,$d1,0xFF00 ++ sll $d1,$d1,24 ++ andi $t1,0xFF00 ++ sll $t0,$t0,8 ++ or $d1,$at ++ srl $at,$d2,24 ++ or $t1,$t0 ++ srl $t0,$d2,8 ++ or $d1,$t1 ++ andi $t1,$d2,0xFF00 ++ sll $d2,$d2,24 ++ andi $t0,0xFF00 ++ sll $t1,$t1,8 ++ or $d2,$at ++ srl $at,$d3,24 ++ or $t0,$t1 ++ srl $t1,$d3,8 ++ or $d2,$t0 ++ andi $t0,$d3,0xFF00 ++ sll $d3,$d3,24 ++ andi $t1,0xFF00 ++ sll $t0,$t0,8 ++ or $d3,$at ++ or $t1,$t0 ++ or $d3,$t1 ++# endif ++#endif ++ srl $t0,$h4,2 # modulo-scheduled reduction ++ andi $h4,$h4,3 ++ sll $at,$t0,2 ++ ++ addu $d0,$d0,$h0 # accumulate input ++ addu $t0,$t0,$at ++ sltu $h0,$d0,$h0 ++ addu $d0,$d0,$t0 # ... and residue ++ sltu $at,$d0,$t0 ++ ++ addu $d1,$d1,$h1 ++ addu $h0,$h0,$at # carry ++ sltu $h1,$d1,$h1 ++ addu $d1,$d1,$h0 ++ sltu $h0,$d1,$h0 ++ ++ addu $d2,$d2,$h2 ++ addu $h1,$h1,$h0 # carry ++ sltu $h2,$d2,$h2 ++ addu $d2,$d2,$h1 ++ sltu $h1,$d2,$h1 ++ ++ addu $d3,$d3,$h3 ++ addu $h2,$h2,$h1 # carry ++ sltu $h3,$d3,$h3 ++ addu $d3,$d3,$h2 ++ ++#if defined(_MIPS_ARCH_MIPS32R2) && !defined(_MIPS_ARCH_MIPS32R6) ++ multu $r0,$d0 # d0*r0 ++ sltu $h2,$d3,$h2 ++ maddu $rs3,$d1 # d1*s3 ++ addu $h3,$h3,$h2 # carry ++ maddu $rs2,$d2 # d2*s2 ++ addu $h4,$h4,$padbit ++ maddu $rs1,$d3 # d3*s1 ++ addu $h4,$h4,$h3 ++ mfhi $at ++ mflo $h0 ++ ++ multu $r1,$d0 # d0*r1 ++ maddu $r0,$d1 # d1*r0 ++ maddu $rs3,$d2 # d2*s3 ++ maddu $rs2,$d3 # d3*s2 ++ maddu $rs1,$h4 # h4*s1 ++ maddu $at,$one # hi*1 ++ mfhi $at ++ mflo $h1 ++ ++ multu $r2,$d0 # d0*r2 ++ maddu $r1,$d1 # d1*r1 ++ maddu $r0,$d2 # d2*r0 ++ maddu $rs3,$d3 # d3*s3 ++ maddu $rs2,$h4 # h4*s2 ++ maddu $at,$one # hi*1 ++ mfhi $at ++ mflo $h2 ++ ++ mul $t0,$r0,$h4 # h4*r0 ++ ++ multu $r3,$d0 # d0*r3 ++ maddu $r2,$d1 # d1*r2 ++ maddu $r1,$d2 # d2*r1 ++ maddu $r0,$d3 # d3*r0 ++ maddu $rs3,$h4 # h4*s3 ++ maddu $at,$one # hi*1 ++ mfhi $at ++ mflo $h3 ++ ++ addiu $inp,$inp,16 ++ ++ addu $h4,$t0,$at ++#else ++ multu ($r0,$d0) # d0*r0 ++ mflo ($h0,$r0,$d0) ++ mfhi ($h1,$r0,$d0) ++ ++ sltu $h2,$d3,$h2 ++ addu $h3,$h3,$h2 # carry ++ ++ multu ($rs3,$d1) # d1*s3 ++ mflo ($at,$rs3,$d1) ++ mfhi ($t0,$rs3,$d1) ++ ++ addu $h4,$h4,$padbit ++ addiu $inp,$inp,16 ++ addu $h4,$h4,$h3 ++ ++ multu ($rs2,$d2) # d2*s2 ++ mflo ($a3,$rs2,$d2) ++ mfhi ($t1,$rs2,$d2) ++ addu $h0,$h0,$at ++ addu $h1,$h1,$t0 ++ multu ($rs1,$d3) # d3*s1 ++ sltu $at,$h0,$at ++ addu $h1,$h1,$at ++ ++ mflo ($at,$rs1,$d3) ++ mfhi ($t0,$rs1,$d3) ++ addu $h0,$h0,$a3 ++ addu $h1,$h1,$t1 ++ multu ($r1,$d0) # d0*r1 ++ sltu $a3,$h0,$a3 ++ addu $h1,$h1,$a3 ++ ++ ++ mflo ($a3,$r1,$d0) ++ mfhi ($h2,$r1,$d0) ++ addu $h0,$h0,$at ++ addu $h1,$h1,$t0 ++ multu ($r0,$d1) # d1*r0 ++ sltu $at,$h0,$at ++ addu $h1,$h1,$at ++ ++ mflo ($at,$r0,$d1) ++ mfhi ($t0,$r0,$d1) ++ addu $h1,$h1,$a3 ++ sltu $a3,$h1,$a3 ++ multu ($rs3,$d2) # d2*s3 ++ addu $h2,$h2,$a3 ++ ++ mflo ($a3,$rs3,$d2) ++ mfhi ($t1,$rs3,$d2) ++ addu $h1,$h1,$at ++ addu $h2,$h2,$t0 ++ multu ($rs2,$d3) # d3*s2 ++ sltu $at,$h1,$at ++ addu $h2,$h2,$at ++ ++ mflo ($at,$rs2,$d3) ++ mfhi ($t0,$rs2,$d3) ++ addu $h1,$h1,$a3 ++ addu $h2,$h2,$t1 ++ multu ($rs1,$h4) # h4*s1 ++ sltu $a3,$h1,$a3 ++ addu $h2,$h2,$a3 ++ ++ mflo ($a3,$rs1,$h4) ++ addu $h1,$h1,$at ++ addu $h2,$h2,$t0 ++ multu ($r2,$d0) # d0*r2 ++ sltu $at,$h1,$at ++ addu $h2,$h2,$at ++ ++ ++ mflo ($at,$r2,$d0) ++ mfhi ($h3,$r2,$d0) ++ addu $h1,$h1,$a3 ++ sltu $a3,$h1,$a3 ++ multu ($r1,$d1) # d1*r1 ++ addu $h2,$h2,$a3 ++ ++ mflo ($a3,$r1,$d1) ++ mfhi ($t1,$r1,$d1) ++ addu $h2,$h2,$at ++ sltu $at,$h2,$at ++ multu ($r0,$d2) # d2*r0 ++ addu $h3,$h3,$at ++ ++ mflo ($at,$r0,$d2) ++ mfhi ($t0,$r0,$d2) ++ addu $h2,$h2,$a3 ++ addu $h3,$h3,$t1 ++ multu ($rs3,$d3) # d3*s3 ++ sltu $a3,$h2,$a3 ++ addu $h3,$h3,$a3 ++ ++ mflo ($a3,$rs3,$d3) ++ mfhi ($t1,$rs3,$d3) ++ addu $h2,$h2,$at ++ addu $h3,$h3,$t0 ++ multu ($rs2,$h4) # h4*s2 ++ sltu $at,$h2,$at ++ addu $h3,$h3,$at ++ ++ mflo ($at,$rs2,$h4) ++ addu $h2,$h2,$a3 ++ addu $h3,$h3,$t1 ++ multu ($r3,$d0) # d0*r3 ++ sltu $a3,$h2,$a3 ++ addu $h3,$h3,$a3 ++ ++ ++ mflo ($a3,$r3,$d0) ++ mfhi ($t1,$r3,$d0) ++ addu $h2,$h2,$at ++ sltu $at,$h2,$at ++ multu ($r2,$d1) # d1*r2 ++ addu $h3,$h3,$at ++ ++ mflo ($at,$r2,$d1) ++ mfhi ($t0,$r2,$d1) ++ addu $h3,$h3,$a3 ++ sltu $a3,$h3,$a3 ++ multu ($r0,$d3) # d3*r0 ++ addu $t1,$t1,$a3 ++ ++ mflo ($a3,$r0,$d3) ++ mfhi ($d3,$r0,$d3) ++ addu $h3,$h3,$at ++ addu $t1,$t1,$t0 ++ multu ($r1,$d2) # d2*r1 ++ sltu $at,$h3,$at ++ addu $t1,$t1,$at ++ ++ mflo ($at,$r1,$d2) ++ mfhi ($t0,$r1,$d2) ++ addu $h3,$h3,$a3 ++ addu $t1,$t1,$d3 ++ multu ($rs3,$h4) # h4*s3 ++ sltu $a3,$h3,$a3 ++ addu $t1,$t1,$a3 ++ ++ mflo ($a3,$rs3,$h4) ++ addu $h3,$h3,$at ++ addu $t1,$t1,$t0 ++ multu ($r0,$h4) # h4*r0 ++ sltu $at,$h3,$at ++ addu $t1,$t1,$at ++ ++ ++ mflo ($h4,$r0,$h4) ++ addu $h3,$h3,$a3 ++ sltu $a3,$h3,$a3 ++ addu $t1,$t1,$a3 ++ addu $h4,$h4,$t1 ++ ++ li $padbit,1 # if we loop, padbit is 1 ++#endif ++ bne $inp,$len,.Loop ++ ++ sw $h0,0($ctx) # store hash value ++ sw $h1,4($ctx) ++ sw $h2,8($ctx) ++ sw $h3,12($ctx) ++ sw $h4,16($ctx) ++ ++ .set noreorder ++.Labort: ++ lw $s11,4*11($sp) ++ lw $s10,4*10($sp) ++ lw $s9, 4*9($sp) ++ lw $s8, 4*8($sp) ++ lw $s7, 4*7($sp) ++ lw $s6, 4*6($sp) ++ lw $s5, 4*5($sp) ++ lw $s4, 4*4($sp) ++___ ++$code.=<<___ if ($flavour =~ /nubi/i); # optimize non-nubi prologue ++ lw $s3, 4*3($sp) ++ lw $s2, 4*2($sp) ++ lw $s1, 4*1($sp) ++ lw $s0, 4*0($sp) ++___ ++$code.=<<___; ++ jr $ra ++ addu $sp,$sp,4*12 ++.end poly1305_blocks ++___ ++} ++{ ++my ($ctx,$mac,$nonce,$tmp4) = ($a0,$a1,$a2,$a3); ++ ++$code.=<<___; ++.align 5 ++.globl poly1305_emit ++.ent poly1305_emit ++poly1305_emit: ++ .frame $sp,0,$ra ++ .set reorder ++ ++ lw $tmp4,16($ctx) ++ lw $tmp0,0($ctx) ++ lw $tmp1,4($ctx) ++ lw $tmp2,8($ctx) ++ lw $tmp3,12($ctx) ++ ++ li $in0,-4 # final reduction ++ srl $ctx,$tmp4,2 ++ and $in0,$in0,$tmp4 ++ andi $tmp4,$tmp4,3 ++ addu $ctx,$ctx,$in0 ++ ++ addu $tmp0,$tmp0,$ctx ++ sltu $ctx,$tmp0,$ctx ++ addiu $in0,$tmp0,5 # compare to modulus ++ addu $tmp1,$tmp1,$ctx ++ sltiu $in1,$in0,5 ++ sltu $ctx,$tmp1,$ctx ++ addu $in1,$in1,$tmp1 ++ addu $tmp2,$tmp2,$ctx ++ sltu $in2,$in1,$tmp1 ++ sltu $ctx,$tmp2,$ctx ++ addu $in2,$in2,$tmp2 ++ addu $tmp3,$tmp3,$ctx ++ sltu $in3,$in2,$tmp2 ++ sltu $ctx,$tmp3,$ctx ++ addu $in3,$in3,$tmp3 ++ addu $tmp4,$tmp4,$ctx ++ sltu $ctx,$in3,$tmp3 ++ addu $ctx,$tmp4 ++ ++ srl $ctx,2 # see if it carried/borrowed ++ subu $ctx,$zero,$ctx ++ ++ xor $in0,$tmp0 ++ xor $in1,$tmp1 ++ xor $in2,$tmp2 ++ xor $in3,$tmp3 ++ and $in0,$ctx ++ and $in1,$ctx ++ and $in2,$ctx ++ and $in3,$ctx ++ xor $in0,$tmp0 ++ xor $in1,$tmp1 ++ xor $in2,$tmp2 ++ xor $in3,$tmp3 ++ ++ lw $tmp0,0($nonce) # load nonce ++ lw $tmp1,4($nonce) ++ lw $tmp2,8($nonce) ++ lw $tmp3,12($nonce) ++ ++ addu $in0,$tmp0 # accumulate nonce ++ sltu $ctx,$in0,$tmp0 ++ ++ addu $in1,$tmp1 ++ sltu $tmp1,$in1,$tmp1 ++ addu $in1,$ctx ++ sltu $ctx,$in1,$ctx ++ addu $ctx,$tmp1 ++ ++ addu $in2,$tmp2 ++ sltu $tmp2,$in2,$tmp2 ++ addu $in2,$ctx ++ sltu $ctx,$in2,$ctx ++ addu $ctx,$tmp2 ++ ++ addu $in3,$tmp3 ++ addu $in3,$ctx ++ ++ srl $tmp0,$in0,8 # write mac value ++ srl $tmp1,$in0,16 ++ srl $tmp2,$in0,24 ++ sb $in0, 0($mac) ++ sb $tmp0,1($mac) ++ srl $tmp0,$in1,8 ++ sb $tmp1,2($mac) ++ srl $tmp1,$in1,16 ++ sb $tmp2,3($mac) ++ srl $tmp2,$in1,24 ++ sb $in1, 4($mac) ++ sb $tmp0,5($mac) ++ srl $tmp0,$in2,8 ++ sb $tmp1,6($mac) ++ srl $tmp1,$in2,16 ++ sb $tmp2,7($mac) ++ srl $tmp2,$in2,24 ++ sb $in2, 8($mac) ++ sb $tmp0,9($mac) ++ srl $tmp0,$in3,8 ++ sb $tmp1,10($mac) ++ srl $tmp1,$in3,16 ++ sb $tmp2,11($mac) ++ srl $tmp2,$in3,24 ++ sb $in3, 12($mac) ++ sb $tmp0,13($mac) ++ sb $tmp1,14($mac) ++ sb $tmp2,15($mac) ++ ++ jr $ra ++.end poly1305_emit ++.rdata ++.asciiz "Poly1305 for MIPS32, CRYPTOGAMS by \@dot-asm" ++.align 2 ++___ ++} ++}}} ++ ++$output=pop and open STDOUT,">$output"; ++print $code; ++close STDOUT; +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -707,6 +707,11 @@ config CRYPTO_POLY1305_X86_64 + in IETF protocols. This is the x86_64 assembler implementation using SIMD + instructions. + ++config CRYPTO_POLY1305_MIPS ++ tristate "Poly1305 authenticator algorithm (MIPS optimized)" ++ depends on CPU_MIPS32 || (CPU_MIPS64 && 64BIT) ++ select CRYPTO_ARCH_HAVE_LIB_POLY1305 ++ + config CRYPTO_MD4 + tristate "MD4 digest algorithm" + select CRYPTO_HASH +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -39,6 +39,7 @@ config CRYPTO_LIB_DES + + config CRYPTO_LIB_POLY1305_RSIZE + int ++ default 2 if MIPS + default 4 if X86_64 + default 9 if ARM || ARM64 + default 1 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0021-crypto-blake2s-generic-C-library-implementation-and-.patch b/target/linux/generic/backport-5.4/080-wireguard-0021-crypto-blake2s-generic-C-library-implementation-and-.patch new file mode 100644 index 0000000000..a78a9645be --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0021-crypto-blake2s-generic-C-library-implementation-and-.patch @@ -0,0 +1,1097 @@ +From 41138d5e49eedc77ff1c4985891b78baba02a874 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:28 +0100 +Subject: [PATCH 021/124] crypto: blake2s - generic C library implementation + and selftest + +commit 66d7fb94e4ffe5acc589e0b2b4710aecc1f07a28 upstream. + +The C implementation was originally based on Samuel Neves' public +domain reference implementation but has since been heavily modified +for the kernel. We're able to do compile-time optimizations by moving +some scaffolding around the final function into the header file. + +Information: https://blake2.net/ + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Samuel Neves +Co-developed-by: Samuel Neves +[ardb: - move from lib/zinc to lib/crypto + - remove simd handling + - rewrote selftest for better coverage + - use fixed digest length for blake2s_hmac() and rename to + blake2s256_hmac() ] +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + include/crypto/blake2s.h | 106 +++++ + include/crypto/internal/blake2s.h | 19 + + lib/crypto/Kconfig | 25 ++ + lib/crypto/Makefile | 10 + + lib/crypto/blake2s-generic.c | 111 ++++++ + lib/crypto/blake2s-selftest.c | 622 ++++++++++++++++++++++++++++++ + lib/crypto/blake2s.c | 126 ++++++ + 7 files changed, 1019 insertions(+) + create mode 100644 include/crypto/blake2s.h + create mode 100644 include/crypto/internal/blake2s.h + create mode 100644 lib/crypto/blake2s-generic.c + create mode 100644 lib/crypto/blake2s-selftest.c + create mode 100644 lib/crypto/blake2s.c + +--- /dev/null ++++ b/include/crypto/blake2s.h +@@ -0,0 +1,106 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef BLAKE2S_H ++#define BLAKE2S_H ++ ++#include ++#include ++#include ++ ++#include ++ ++enum blake2s_lengths { ++ BLAKE2S_BLOCK_SIZE = 64, ++ BLAKE2S_HASH_SIZE = 32, ++ BLAKE2S_KEY_SIZE = 32, ++ ++ BLAKE2S_128_HASH_SIZE = 16, ++ BLAKE2S_160_HASH_SIZE = 20, ++ BLAKE2S_224_HASH_SIZE = 28, ++ BLAKE2S_256_HASH_SIZE = 32, ++}; ++ ++struct blake2s_state { ++ u32 h[8]; ++ u32 t[2]; ++ u32 f[2]; ++ u8 buf[BLAKE2S_BLOCK_SIZE]; ++ unsigned int buflen; ++ unsigned int outlen; ++}; ++ ++enum blake2s_iv { ++ BLAKE2S_IV0 = 0x6A09E667UL, ++ BLAKE2S_IV1 = 0xBB67AE85UL, ++ BLAKE2S_IV2 = 0x3C6EF372UL, ++ BLAKE2S_IV3 = 0xA54FF53AUL, ++ BLAKE2S_IV4 = 0x510E527FUL, ++ BLAKE2S_IV5 = 0x9B05688CUL, ++ BLAKE2S_IV6 = 0x1F83D9ABUL, ++ BLAKE2S_IV7 = 0x5BE0CD19UL, ++}; ++ ++void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen); ++void blake2s_final(struct blake2s_state *state, u8 *out); ++ ++static inline void blake2s_init_param(struct blake2s_state *state, ++ const u32 param) ++{ ++ *state = (struct blake2s_state){{ ++ BLAKE2S_IV0 ^ param, ++ BLAKE2S_IV1, ++ BLAKE2S_IV2, ++ BLAKE2S_IV3, ++ BLAKE2S_IV4, ++ BLAKE2S_IV5, ++ BLAKE2S_IV6, ++ BLAKE2S_IV7, ++ }}; ++} ++ ++static inline void blake2s_init(struct blake2s_state *state, ++ const size_t outlen) ++{ ++ blake2s_init_param(state, 0x01010000 | outlen); ++ state->outlen = outlen; ++} ++ ++static inline void blake2s_init_key(struct blake2s_state *state, ++ const size_t outlen, const void *key, ++ const size_t keylen) ++{ ++ WARN_ON(IS_ENABLED(DEBUG) && (!outlen || outlen > BLAKE2S_HASH_SIZE || ++ !key || !keylen || keylen > BLAKE2S_KEY_SIZE)); ++ ++ blake2s_init_param(state, 0x01010000 | keylen << 8 | outlen); ++ memcpy(state->buf, key, keylen); ++ state->buflen = BLAKE2S_BLOCK_SIZE; ++ state->outlen = outlen; ++} ++ ++static inline void blake2s(u8 *out, const u8 *in, const u8 *key, ++ const size_t outlen, const size_t inlen, ++ const size_t keylen) ++{ ++ struct blake2s_state state; ++ ++ WARN_ON(IS_ENABLED(DEBUG) && ((!in && inlen > 0) || !out || !outlen || ++ outlen > BLAKE2S_HASH_SIZE || keylen > BLAKE2S_KEY_SIZE || ++ (!key && keylen))); ++ ++ if (keylen) ++ blake2s_init_key(&state, outlen, key, keylen); ++ else ++ blake2s_init(&state, outlen); ++ ++ blake2s_update(&state, in, inlen); ++ blake2s_final(&state, out); ++} ++ ++void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, ++ const size_t keylen); ++ ++#endif /* BLAKE2S_H */ +--- /dev/null ++++ b/include/crypto/internal/blake2s.h +@@ -0,0 +1,19 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ ++ ++#ifndef BLAKE2S_INTERNAL_H ++#define BLAKE2S_INTERNAL_H ++ ++#include ++ ++void blake2s_compress_generic(struct blake2s_state *state,const u8 *block, ++ size_t nblocks, const u32 inc); ++ ++void blake2s_compress_arch(struct blake2s_state *state,const u8 *block, ++ size_t nblocks, const u32 inc); ++ ++static inline void blake2s_set_lastblock(struct blake2s_state *state) ++{ ++ state->f[0] = -1; ++} ++ ++#endif /* BLAKE2S_INTERNAL_H */ +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -8,6 +8,31 @@ config CRYPTO_LIB_AES + config CRYPTO_LIB_ARC4 + tristate + ++config CRYPTO_ARCH_HAVE_LIB_BLAKE2S ++ tristate ++ help ++ Declares whether the architecture provides an arch-specific ++ accelerated implementation of the Blake2s library interface, ++ either builtin or as a module. ++ ++config CRYPTO_LIB_BLAKE2S_GENERIC ++ tristate ++ help ++ This symbol can be depended upon by arch implementations of the ++ Blake2s library interface that require the generic code as a ++ fallback, e.g., for SIMD implementations. If no arch specific ++ implementation is enabled, this implementation serves the users ++ of CRYPTO_LIB_BLAKE2S. ++ ++config CRYPTO_LIB_BLAKE2S ++ tristate "BLAKE2s hash function library" ++ depends on CRYPTO_ARCH_HAVE_LIB_BLAKE2S || !CRYPTO_ARCH_HAVE_LIB_BLAKE2S ++ select CRYPTO_LIB_BLAKE2S_GENERIC if CRYPTO_ARCH_HAVE_LIB_BLAKE2S=n ++ help ++ Enable the Blake2s library interface. This interface may be fulfilled ++ by either the generic implementation or an arch-specific one, if one ++ is available and enabled. ++ + config CRYPTO_ARCH_HAVE_LIB_CHACHA + tristate + help +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -10,6 +10,12 @@ libaes-y := aes.o + obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o + libarc4-y := arc4.o + ++obj-$(CONFIG_CRYPTO_LIB_BLAKE2S_GENERIC) += libblake2s-generic.o ++libblake2s-generic-y += blake2s-generic.o ++ ++obj-$(CONFIG_CRYPTO_LIB_BLAKE2S) += libblake2s.o ++libblake2s-y += blake2s.o ++ + obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o + libdes-y := des.o + +@@ -18,3 +24,7 @@ libpoly1305-y := poly1305.o + + obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o + libsha256-y := sha256.o ++ ++ifneq ($(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS),y) ++libblake2s-y += blake2s-selftest.o ++endif +--- /dev/null ++++ b/lib/crypto/blake2s-generic.c +@@ -0,0 +1,111 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is an implementation of the BLAKE2s hash and PRF functions. ++ * ++ * Information: https://blake2.net/ ++ * ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++static const u8 blake2s_sigma[10][16] = { ++ { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, ++ { 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 }, ++ { 11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4 }, ++ { 7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8 }, ++ { 9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13 }, ++ { 2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9 }, ++ { 12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11 }, ++ { 13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10 }, ++ { 6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5 }, ++ { 10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0 }, ++}; ++ ++static inline void blake2s_increment_counter(struct blake2s_state *state, ++ const u32 inc) ++{ ++ state->t[0] += inc; ++ state->t[1] += (state->t[0] < inc); ++} ++ ++void blake2s_compress_generic(struct blake2s_state *state,const u8 *block, ++ size_t nblocks, const u32 inc) ++{ ++ u32 m[16]; ++ u32 v[16]; ++ int i; ++ ++ WARN_ON(IS_ENABLED(DEBUG) && ++ (nblocks > 1 && inc != BLAKE2S_BLOCK_SIZE)); ++ ++ while (nblocks > 0) { ++ blake2s_increment_counter(state, inc); ++ memcpy(m, block, BLAKE2S_BLOCK_SIZE); ++ le32_to_cpu_array(m, ARRAY_SIZE(m)); ++ memcpy(v, state->h, 32); ++ v[ 8] = BLAKE2S_IV0; ++ v[ 9] = BLAKE2S_IV1; ++ v[10] = BLAKE2S_IV2; ++ v[11] = BLAKE2S_IV3; ++ v[12] = BLAKE2S_IV4 ^ state->t[0]; ++ v[13] = BLAKE2S_IV5 ^ state->t[1]; ++ v[14] = BLAKE2S_IV6 ^ state->f[0]; ++ v[15] = BLAKE2S_IV7 ^ state->f[1]; ++ ++#define G(r, i, a, b, c, d) do { \ ++ a += b + m[blake2s_sigma[r][2 * i + 0]]; \ ++ d = ror32(d ^ a, 16); \ ++ c += d; \ ++ b = ror32(b ^ c, 12); \ ++ a += b + m[blake2s_sigma[r][2 * i + 1]]; \ ++ d = ror32(d ^ a, 8); \ ++ c += d; \ ++ b = ror32(b ^ c, 7); \ ++} while (0) ++ ++#define ROUND(r) do { \ ++ G(r, 0, v[0], v[ 4], v[ 8], v[12]); \ ++ G(r, 1, v[1], v[ 5], v[ 9], v[13]); \ ++ G(r, 2, v[2], v[ 6], v[10], v[14]); \ ++ G(r, 3, v[3], v[ 7], v[11], v[15]); \ ++ G(r, 4, v[0], v[ 5], v[10], v[15]); \ ++ G(r, 5, v[1], v[ 6], v[11], v[12]); \ ++ G(r, 6, v[2], v[ 7], v[ 8], v[13]); \ ++ G(r, 7, v[3], v[ 4], v[ 9], v[14]); \ ++} while (0) ++ ROUND(0); ++ ROUND(1); ++ ROUND(2); ++ ROUND(3); ++ ROUND(4); ++ ROUND(5); ++ ROUND(6); ++ ROUND(7); ++ ROUND(8); ++ ROUND(9); ++ ++#undef G ++#undef ROUND ++ ++ for (i = 0; i < 8; ++i) ++ state->h[i] ^= v[i] ^ v[i + 8]; ++ ++ block += BLAKE2S_BLOCK_SIZE; ++ --nblocks; ++ } ++} ++ ++EXPORT_SYMBOL(blake2s_compress_generic); ++ ++MODULE_LICENSE("GPL v2"); ++MODULE_DESCRIPTION("BLAKE2s hash function"); ++MODULE_AUTHOR("Jason A. Donenfeld "); +--- /dev/null ++++ b/lib/crypto/blake2s-selftest.c +@@ -0,0 +1,622 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include ++#include ++ ++/* ++ * blake2s_testvecs[] generated with the program below (using libb2-dev and ++ * libssl-dev [OpenSSL]) ++ * ++ * #include ++ * #include ++ * #include ++ * ++ * #include ++ * #include ++ * ++ * #define BLAKE2S_TESTVEC_COUNT 256 ++ * ++ * static void print_vec(const uint8_t vec[], int len) ++ * { ++ * int i; ++ * ++ * printf(" { "); ++ * for (i = 0; i < len; i++) { ++ * if (i && (i % 12) == 0) ++ * printf("\n "); ++ * printf("0x%02x, ", vec[i]); ++ * } ++ * printf("},\n"); ++ * } ++ * ++ * int main(void) ++ * { ++ * uint8_t key[BLAKE2S_KEYBYTES]; ++ * uint8_t buf[BLAKE2S_TESTVEC_COUNT]; ++ * uint8_t hash[BLAKE2S_OUTBYTES]; ++ * int i, j; ++ * ++ * key[0] = key[1] = 1; ++ * for (i = 2; i < BLAKE2S_KEYBYTES; ++i) ++ * key[i] = key[i - 2] + key[i - 1]; ++ * ++ * for (i = 0; i < BLAKE2S_TESTVEC_COUNT; ++i) ++ * buf[i] = (uint8_t)i; ++ * ++ * printf("static const u8 blake2s_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {\n"); ++ * ++ * for (i = 0; i < BLAKE2S_TESTVEC_COUNT; ++i) { ++ * int outlen = 1 + i % BLAKE2S_OUTBYTES; ++ * int keylen = (13 * i) % (BLAKE2S_KEYBYTES + 1); ++ * ++ * blake2s(hash, buf, key + BLAKE2S_KEYBYTES - keylen, outlen, i, ++ * keylen); ++ * print_vec(hash, outlen); ++ * } ++ * printf("};\n\n"); ++ * ++ * printf("static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = {\n"); ++ * ++ * HMAC(EVP_blake2s256(), key, sizeof(key), buf, sizeof(buf), hash, NULL); ++ * print_vec(hash, BLAKE2S_OUTBYTES); ++ * ++ * HMAC(EVP_blake2s256(), buf, sizeof(buf), key, sizeof(key), hash, NULL); ++ * print_vec(hash, BLAKE2S_OUTBYTES); ++ * ++ * printf("};\n"); ++ * ++ * return 0; ++ *} ++ */ ++static const u8 blake2s_testvecs[][BLAKE2S_HASH_SIZE] __initconst = { ++ { 0xa1, }, ++ { 0x7c, 0x89, }, ++ { 0x74, 0x0e, 0xd4, }, ++ { 0x47, 0x0c, 0x21, 0x15, }, ++ { 0x18, 0xd6, 0x9c, 0xa6, 0xc4, }, ++ { 0x13, 0x5d, 0x16, 0x63, 0x2e, 0xf9, }, ++ { 0x2c, 0xb5, 0x04, 0xb7, 0x99, 0xe2, 0x73, }, ++ { 0x9a, 0x0f, 0xd2, 0x39, 0xd6, 0x68, 0x1b, 0x92, }, ++ { 0xc8, 0xde, 0x7a, 0xea, 0x2f, 0xf4, 0xd2, 0xe3, 0x2b, }, ++ { 0x5b, 0xf9, 0x43, 0x52, 0x0c, 0x12, 0xba, 0xb5, 0x93, 0x9f, }, ++ { 0xc6, 0x2c, 0x4e, 0x80, 0xfc, 0x32, 0x5b, 0x33, 0xb8, 0xb8, 0x0a, }, ++ { 0xa7, 0x5c, 0xfd, 0x3a, 0xcc, 0xbf, 0x90, 0xca, 0xb7, 0x97, 0xde, 0xd8, }, ++ { 0x66, 0xca, 0x3c, 0xc4, 0x19, 0xef, 0x92, 0x66, 0x3f, 0x21, 0x8f, 0xda, ++ 0xb7, }, ++ { 0xba, 0xe5, 0xbb, 0x30, 0x25, 0x94, 0x6d, 0xc3, 0x89, 0x09, 0xc4, 0x25, ++ 0x52, 0x3e, }, ++ { 0xa2, 0xef, 0x0e, 0x52, 0x0b, 0x5f, 0xa2, 0x01, 0x6d, 0x0a, 0x25, 0xbc, ++ 0x57, 0xe2, 0x27, }, ++ { 0x4f, 0xe0, 0xf9, 0x52, 0x12, 0xda, 0x84, 0xb7, 0xab, 0xae, 0xb0, 0xa6, ++ 0x47, 0x2a, 0xc7, 0xf5, }, ++ { 0x56, 0xe7, 0xa8, 0x1c, 0x4c, 0xca, 0xed, 0x90, 0x31, 0xec, 0x87, 0x43, ++ 0xe7, 0x72, 0x08, 0xec, 0xbe, }, ++ { 0x7e, 0xdf, 0x80, 0x1c, 0x93, 0x33, 0xfd, 0x53, 0x44, 0xba, 0xfd, 0x96, ++ 0xe1, 0xbb, 0xb5, 0x65, 0xa5, 0x00, }, ++ { 0xec, 0x6b, 0xed, 0xf7, 0x7b, 0x62, 0x1d, 0x7d, 0xf4, 0x82, 0xf3, 0x1e, ++ 0x18, 0xff, 0x2b, 0xc4, 0x06, 0x20, 0x2a, }, ++ { 0x74, 0x98, 0xd7, 0x68, 0x63, 0xed, 0x87, 0xe4, 0x5d, 0x8d, 0x9e, 0x1d, ++ 0xfd, 0x2a, 0xbb, 0x86, 0xac, 0xe9, 0x2a, 0x89, }, ++ { 0x89, 0xc3, 0x88, 0xce, 0x2b, 0x33, 0x1e, 0x10, 0xd1, 0x37, 0x20, 0x86, ++ 0x28, 0x43, 0x70, 0xd9, 0xfb, 0x96, 0xd9, 0xb5, 0xd3, }, ++ { 0xcb, 0x56, 0x74, 0x41, 0x8d, 0x80, 0x01, 0x9a, 0x6b, 0x38, 0xe1, 0x41, ++ 0xad, 0x9c, 0x62, 0x74, 0xce, 0x35, 0xd5, 0x6c, 0x89, 0x6e, }, ++ { 0x79, 0xaf, 0x94, 0x59, 0x99, 0x26, 0xe1, 0xc9, 0x34, 0xfe, 0x7c, 0x22, ++ 0xf7, 0x43, 0xd7, 0x65, 0xd4, 0x48, 0x18, 0xac, 0x3d, 0xfd, 0x93, }, ++ { 0x85, 0x0d, 0xff, 0xb8, 0x3e, 0x87, 0x41, 0xb0, 0x95, 0xd3, 0x3d, 0x00, ++ 0x47, 0x55, 0x9e, 0xd2, 0x69, 0xea, 0xbf, 0xe9, 0x7a, 0x2d, 0x61, 0x45, }, ++ { 0x03, 0xe0, 0x85, 0xec, 0x54, 0xb5, 0x16, 0x53, 0xa8, 0xc4, 0x71, 0xe9, ++ 0x6a, 0xe7, 0xcb, 0xc4, 0x15, 0x02, 0xfc, 0x34, 0xa4, 0xa4, 0x28, 0x13, ++ 0xd1, }, ++ { 0xe3, 0x34, 0x4b, 0xe1, 0xd0, 0x4b, 0x55, 0x61, 0x8f, 0xc0, 0x24, 0x05, ++ 0xe6, 0xe0, 0x3d, 0x70, 0x24, 0x4d, 0xda, 0xb8, 0x91, 0x05, 0x29, 0x07, ++ 0x01, 0x3e, }, ++ { 0x61, 0xff, 0x01, 0x72, 0xb1, 0x4d, 0xf6, 0xfe, 0xd1, 0xd1, 0x08, 0x74, ++ 0xe6, 0x91, 0x44, 0xeb, 0x61, 0xda, 0x40, 0xaf, 0xfc, 0x8c, 0x91, 0x6b, ++ 0xec, 0x13, 0xed, }, ++ { 0xd4, 0x40, 0xd2, 0xa0, 0x7f, 0xc1, 0x58, 0x0c, 0x85, 0xa0, 0x86, 0xc7, ++ 0x86, 0xb9, 0x61, 0xc9, 0xea, 0x19, 0x86, 0x1f, 0xab, 0x07, 0xce, 0x37, ++ 0x72, 0x67, 0x09, 0xfc, }, ++ { 0x9e, 0xf8, 0x18, 0x67, 0x93, 0x10, 0x9b, 0x39, 0x75, 0xe8, 0x8b, 0x38, ++ 0x82, 0x7d, 0xb8, 0xb7, 0xa5, 0xaf, 0xe6, 0x6a, 0x22, 0x5e, 0x1f, 0x9c, ++ 0x95, 0x29, 0x19, 0xf2, 0x4b, }, ++ { 0xc8, 0x62, 0x25, 0xf5, 0x98, 0xc9, 0xea, 0xe5, 0x29, 0x3a, 0xd3, 0x22, ++ 0xeb, 0xeb, 0x07, 0x7c, 0x15, 0x07, 0xee, 0x15, 0x61, 0xbb, 0x05, 0x30, ++ 0x99, 0x7f, 0x11, 0xf6, 0x0a, 0x1d, }, ++ { 0x68, 0x70, 0xf7, 0x90, 0xa1, 0x8b, 0x1f, 0x0f, 0xbb, 0xce, 0xd2, 0x0e, ++ 0x33, 0x1f, 0x7f, 0xa9, 0x78, 0xa8, 0xa6, 0x81, 0x66, 0xab, 0x8d, 0xcd, ++ 0x58, 0x55, 0x3a, 0x0b, 0x7a, 0xdb, 0xb5, }, ++ { 0xdd, 0x35, 0xd2, 0xb4, 0xf6, 0xc7, 0xea, 0xab, 0x64, 0x24, 0x4e, 0xfe, ++ 0xe5, 0x3d, 0x4e, 0x95, 0x8b, 0x6d, 0x6c, 0xbc, 0xb0, 0xf8, 0x88, 0x61, ++ 0x09, 0xb7, 0x78, 0xa3, 0x31, 0xfe, 0xd9, 0x2f, }, ++ { 0x0a, }, ++ { 0x6e, 0xd4, }, ++ { 0x64, 0xe9, 0xd1, }, ++ { 0x30, 0xdd, 0x71, 0xef, }, ++ { 0x11, 0xb5, 0x0c, 0x87, 0xc9, }, ++ { 0x06, 0x1c, 0x6d, 0x04, 0x82, 0xd0, }, ++ { 0x5c, 0x42, 0x0b, 0xee, 0xc5, 0x9c, 0xb2, }, ++ { 0xe8, 0x29, 0xd6, 0xb4, 0x5d, 0xf7, 0x2b, 0x93, }, ++ { 0x18, 0xca, 0x27, 0x72, 0x43, 0x39, 0x16, 0xbc, 0x6a, }, ++ { 0x39, 0x8f, 0xfd, 0x64, 0xf5, 0x57, 0x23, 0xb0, 0x45, 0xf8, }, ++ { 0xbb, 0x3a, 0x78, 0x6b, 0x02, 0x1d, 0x0b, 0x16, 0xe3, 0xb2, 0x9a, }, ++ { 0xb8, 0xb4, 0x0b, 0xe5, 0xd4, 0x1d, 0x0d, 0x85, 0x49, 0x91, 0x35, 0xfa, }, ++ { 0x6d, 0x48, 0x2a, 0x0c, 0x42, 0x08, 0xbd, 0xa9, 0x78, 0x6f, 0x18, 0xaf, ++ 0xe2, }, ++ { 0x10, 0x45, 0xd4, 0x58, 0x88, 0xec, 0x4e, 0x1e, 0xf6, 0x14, 0x92, 0x64, ++ 0x7e, 0xb0, }, ++ { 0x8b, 0x0b, 0x95, 0xee, 0x92, 0xc6, 0x3b, 0x91, 0xf1, 0x1e, 0xeb, 0x51, ++ 0x98, 0x0a, 0x8d, }, ++ { 0xa3, 0x50, 0x4d, 0xa5, 0x1d, 0x03, 0x68, 0xe9, 0x57, 0x78, 0xd6, 0x04, ++ 0xf1, 0xc3, 0x94, 0xd8, }, ++ { 0xb8, 0x66, 0x6e, 0xdd, 0x46, 0x15, 0xae, 0x3d, 0x83, 0x7e, 0xcf, 0xe7, ++ 0x2c, 0xe8, 0x8f, 0xc7, 0x34, }, ++ { 0x2e, 0xc0, 0x1f, 0x29, 0xea, 0xf6, 0xb9, 0xe2, 0xc2, 0x93, 0xeb, 0x41, ++ 0x0d, 0xf0, 0x0a, 0x13, 0x0e, 0xa2, }, ++ { 0x71, 0xb8, 0x33, 0xa9, 0x1b, 0xac, 0xf1, 0xb5, 0x42, 0x8f, 0x5e, 0x81, ++ 0x34, 0x43, 0xb7, 0xa4, 0x18, 0x5c, 0x47, }, ++ { 0xda, 0x45, 0xb8, 0x2e, 0x82, 0x1e, 0xc0, 0x59, 0x77, 0x9d, 0xfa, 0xb4, ++ 0x1c, 0x5e, 0xa0, 0x2b, 0x33, 0x96, 0x5a, 0x58, }, ++ { 0xe3, 0x09, 0x05, 0xa9, 0xeb, 0x48, 0x13, 0xad, 0x71, 0x88, 0x81, 0x9a, ++ 0x3e, 0x2c, 0xe1, 0x23, 0x99, 0x13, 0x35, 0x9f, 0xb5, }, ++ { 0xb7, 0x86, 0x2d, 0x16, 0xe1, 0x04, 0x00, 0x47, 0x47, 0x61, 0x31, 0xfb, ++ 0x14, 0xac, 0xd8, 0xe9, 0xe3, 0x49, 0xbd, 0xf7, 0x9c, 0x3f, }, ++ { 0x7f, 0xd9, 0x95, 0xa8, 0xa7, 0xa0, 0xcc, 0xba, 0xef, 0xb1, 0x0a, 0xa9, ++ 0x21, 0x62, 0x08, 0x0f, 0x1b, 0xff, 0x7b, 0x9d, 0xae, 0xb2, 0x95, }, ++ { 0x85, 0x99, 0xea, 0x33, 0xe0, 0x56, 0xff, 0x13, 0xc6, 0x61, 0x8c, 0xf9, ++ 0x57, 0x05, 0x03, 0x11, 0xf9, 0xfb, 0x3a, 0xf7, 0xce, 0xbb, 0x52, 0x30, }, ++ { 0xb2, 0x72, 0x9c, 0xf8, 0x77, 0x4e, 0x8f, 0x6b, 0x01, 0x6c, 0xff, 0x4e, ++ 0x4f, 0x02, 0xd2, 0xbc, 0xeb, 0x51, 0x28, 0x99, 0x50, 0xab, 0xc4, 0x42, ++ 0xe3, }, ++ { 0x8b, 0x0a, 0xb5, 0x90, 0x8f, 0xf5, 0x7b, 0xdd, 0xba, 0x47, 0x37, 0xc9, ++ 0x2a, 0xd5, 0x4b, 0x25, 0x08, 0x8b, 0x02, 0x17, 0xa7, 0x9e, 0x6b, 0x6e, ++ 0xe3, 0x90, }, ++ { 0x90, 0xdd, 0xf7, 0x75, 0xa7, 0xa3, 0x99, 0x5e, 0x5b, 0x7d, 0x75, 0xc3, ++ 0x39, 0x6b, 0xa0, 0xe2, 0x44, 0x53, 0xb1, 0x9e, 0xc8, 0xf1, 0x77, 0x10, ++ 0x58, 0x06, 0x9a, }, ++ { 0x99, 0x52, 0xf0, 0x49, 0xa8, 0x8c, 0xec, 0xa6, 0x97, 0x32, 0x13, 0xb5, ++ 0xf7, 0xa3, 0x8e, 0xfb, 0x4b, 0x59, 0x31, 0x3d, 0x01, 0x59, 0x98, 0x5d, ++ 0x53, 0x03, 0x1a, 0x39, }, ++ { 0x9f, 0xe0, 0xc2, 0xe5, 0x5d, 0x93, 0xd6, 0x9b, 0x47, 0x8f, 0x9b, 0xe0, ++ 0x26, 0x35, 0x84, 0x20, 0x1d, 0xc5, 0x53, 0x10, 0x0f, 0x22, 0xb9, 0xb5, ++ 0xd4, 0x36, 0xb1, 0xac, 0x73, }, ++ { 0x30, 0x32, 0x20, 0x3b, 0x10, 0x28, 0xec, 0x1f, 0x4f, 0x9b, 0x47, 0x59, ++ 0xeb, 0x7b, 0xee, 0x45, 0xfb, 0x0c, 0x49, 0xd8, 0x3d, 0x69, 0xbd, 0x90, ++ 0x2c, 0xf0, 0x9e, 0x8d, 0xbf, 0xd5, }, ++ { 0x2a, 0x37, 0x73, 0x7f, 0xf9, 0x96, 0x19, 0xaa, 0x25, 0xd8, 0x13, 0x28, ++ 0x01, 0x29, 0x89, 0xdf, 0x6e, 0x0c, 0x9b, 0x43, 0x44, 0x51, 0xe9, 0x75, ++ 0x26, 0x0c, 0xb7, 0x87, 0x66, 0x0b, 0x5f, }, ++ { 0x23, 0xdf, 0x96, 0x68, 0x91, 0x86, 0xd0, 0x93, 0x55, 0x33, 0x24, 0xf6, ++ 0xba, 0x08, 0x75, 0x5b, 0x59, 0x11, 0x69, 0xb8, 0xb9, 0xe5, 0x2c, 0x77, ++ 0x02, 0xf6, 0x47, 0xee, 0x81, 0xdd, 0xb9, 0x06, }, ++ { 0x9d, }, ++ { 0x9d, 0x7d, }, ++ { 0xfd, 0xc3, 0xda, }, ++ { 0xe8, 0x82, 0xcd, 0x21, }, ++ { 0xc3, 0x1d, 0x42, 0x4c, 0x74, }, ++ { 0xe9, 0xda, 0xf1, 0xa2, 0xe5, 0x7c, }, ++ { 0x52, 0xb8, 0x6f, 0x81, 0x5c, 0x3a, 0x4c, }, ++ { 0x5b, 0x39, 0x26, 0xfc, 0x92, 0x5e, 0xe0, 0x49, }, ++ { 0x59, 0xe4, 0x7c, 0x93, 0x1c, 0xf9, 0x28, 0x93, 0xde, }, ++ { 0xde, 0xdf, 0xb2, 0x43, 0x61, 0x0b, 0x86, 0x16, 0x4c, 0x2e, }, ++ { 0x14, 0x8f, 0x75, 0x51, 0xaf, 0xb9, 0xee, 0x51, 0x5a, 0xae, 0x23, }, ++ { 0x43, 0x5f, 0x50, 0xd5, 0x70, 0xb0, 0x5b, 0x87, 0xf5, 0xd9, 0xb3, 0x6d, }, ++ { 0x66, 0x0a, 0x64, 0x93, 0x79, 0x71, 0x94, 0x40, 0xb7, 0x68, 0x2d, 0xd3, ++ 0x63, }, ++ { 0x15, 0x00, 0xc4, 0x0c, 0x7d, 0x1b, 0x10, 0xa9, 0x73, 0x1b, 0x90, 0x6f, ++ 0xe6, 0xa9, }, ++ { 0x34, 0x75, 0xf3, 0x86, 0x8f, 0x56, 0xcf, 0x2a, 0x0a, 0xf2, 0x62, 0x0a, ++ 0xf6, 0x0e, 0x20, }, ++ { 0xb1, 0xde, 0xc9, 0xf5, 0xdb, 0xf3, 0x2f, 0x4c, 0xd6, 0x41, 0x7d, 0x39, ++ 0x18, 0x3e, 0xc7, 0xc3, }, ++ { 0xc5, 0x89, 0xb2, 0xf8, 0xb8, 0xc0, 0xa3, 0xb9, 0x3b, 0x10, 0x6d, 0x7c, ++ 0x92, 0xfc, 0x7f, 0x34, 0x41, }, ++ { 0xc4, 0xd8, 0xef, 0xba, 0xef, 0xd2, 0xaa, 0xc5, 0x6c, 0x8e, 0x3e, 0xbb, ++ 0x12, 0xfc, 0x0f, 0x72, 0xbf, 0x0f, }, ++ { 0xdd, 0x91, 0xd1, 0x15, 0x9e, 0x7d, 0xf8, 0xc1, 0xb9, 0x14, 0x63, 0x96, ++ 0xb5, 0xcb, 0x83, 0x1d, 0x35, 0x1c, 0xec, }, ++ { 0xa9, 0xf8, 0x52, 0xc9, 0x67, 0x76, 0x2b, 0xad, 0xfb, 0xd8, 0x3a, 0xa6, ++ 0x74, 0x02, 0xae, 0xb8, 0x25, 0x2c, 0x63, 0x49, }, ++ { 0x77, 0x1f, 0x66, 0x70, 0xfd, 0x50, 0x29, 0xaa, 0xeb, 0xdc, 0xee, 0xba, ++ 0x75, 0x98, 0xdc, 0x93, 0x12, 0x3f, 0xdc, 0x7c, 0x38, }, ++ { 0xe2, 0xe1, 0x89, 0x5c, 0x37, 0x38, 0x6a, 0xa3, 0x40, 0xac, 0x3f, 0xb0, ++ 0xca, 0xfc, 0xa7, 0xf3, 0xea, 0xf9, 0x0f, 0x5d, 0x8e, 0x39, }, ++ { 0x0f, 0x67, 0xc8, 0x38, 0x01, 0xb1, 0xb7, 0xb8, 0xa2, 0xe7, 0x0a, 0x6d, ++ 0xd2, 0x63, 0x69, 0x9e, 0xcc, 0xf0, 0xf2, 0xbe, 0x9b, 0x98, 0xdd, }, ++ { 0x13, 0xe1, 0x36, 0x30, 0xfe, 0xc6, 0x01, 0x8a, 0xa1, 0x63, 0x96, 0x59, ++ 0xc2, 0xa9, 0x68, 0x3f, 0x58, 0xd4, 0x19, 0x0c, 0x40, 0xf3, 0xde, 0x02, }, ++ { 0xa3, 0x9e, 0xce, 0xda, 0x42, 0xee, 0x8c, 0x6c, 0x5a, 0x7d, 0xdc, 0x89, ++ 0x02, 0x77, 0xdd, 0xe7, 0x95, 0xbb, 0xff, 0x0d, 0xa4, 0xb5, 0x38, 0x1e, ++ 0xaf, }, ++ { 0x9a, 0xf6, 0xb5, 0x9a, 0x4f, 0xa9, 0x4f, 0x2c, 0x35, 0x3c, 0x24, 0xdc, ++ 0x97, 0x6f, 0xd9, 0xa1, 0x7d, 0x1a, 0x85, 0x0b, 0xf5, 0xda, 0x2e, 0xe7, ++ 0xb1, 0x1d, }, ++ { 0x84, 0x1e, 0x8e, 0x3d, 0x45, 0xa5, 0xf2, 0x27, 0xf3, 0x31, 0xfe, 0xb9, ++ 0xfb, 0xc5, 0x45, 0x99, 0x99, 0xdd, 0x93, 0x43, 0x02, 0xee, 0x58, 0xaf, ++ 0xee, 0x6a, 0xbe, }, ++ { 0x07, 0x2f, 0xc0, 0xa2, 0x04, 0xc4, 0xab, 0x7c, 0x26, 0xbb, 0xa8, 0xd8, ++ 0xe3, 0x1c, 0x75, 0x15, 0x64, 0x5d, 0x02, 0x6a, 0xf0, 0x86, 0xe9, 0xcd, ++ 0x5c, 0xef, 0xa3, 0x25, }, ++ { 0x2f, 0x3b, 0x1f, 0xb5, 0x91, 0x8f, 0x86, 0xe0, 0xdc, 0x31, 0x48, 0xb6, ++ 0xa1, 0x8c, 0xfd, 0x75, 0xbb, 0x7d, 0x3d, 0xc1, 0xf0, 0x10, 0x9a, 0xd8, ++ 0x4b, 0x0e, 0xe3, 0x94, 0x9f, }, ++ { 0x29, 0xbb, 0x8f, 0x6c, 0xd1, 0xf2, 0xb6, 0xaf, 0xe5, 0xe3, 0x2d, 0xdc, ++ 0x6f, 0xa4, 0x53, 0x88, 0xd8, 0xcf, 0x4d, 0x45, 0x42, 0x62, 0xdb, 0xdf, ++ 0xf8, 0x45, 0xc2, 0x13, 0xec, 0x35, }, ++ { 0x06, 0x3c, 0xe3, 0x2c, 0x15, 0xc6, 0x43, 0x03, 0x81, 0xfb, 0x08, 0x76, ++ 0x33, 0xcb, 0x02, 0xc1, 0xba, 0x33, 0xe5, 0xe0, 0xd1, 0x92, 0xa8, 0x46, ++ 0x28, 0x3f, 0x3e, 0x9d, 0x2c, 0x44, 0x54, }, ++ { 0xea, 0xbb, 0x96, 0xf8, 0xd1, 0x8b, 0x04, 0x11, 0x40, 0x78, 0x42, 0x02, ++ 0x19, 0xd1, 0xbc, 0x65, 0x92, 0xd3, 0xc3, 0xd6, 0xd9, 0x19, 0xe7, 0xc3, ++ 0x40, 0x97, 0xbd, 0xd4, 0xed, 0xfa, 0x5e, 0x28, }, ++ { 0x02, }, ++ { 0x52, 0xa8, }, ++ { 0x38, 0x25, 0x0d, }, ++ { 0xe3, 0x04, 0xd4, 0x92, }, ++ { 0x97, 0xdb, 0xf7, 0x81, 0xca, }, ++ { 0x8a, 0x56, 0x9d, 0x62, 0x56, 0xcc, }, ++ { 0xa1, 0x8e, 0x3c, 0x72, 0x8f, 0x63, 0x03, }, ++ { 0xf7, 0xf3, 0x39, 0x09, 0x0a, 0xa1, 0xbb, 0x23, }, ++ { 0x6b, 0x03, 0xc0, 0xe9, 0xd9, 0x83, 0x05, 0x22, 0x01, }, ++ { 0x1b, 0x4b, 0xf5, 0xd6, 0x4f, 0x05, 0x75, 0x91, 0x4c, 0x7f, }, ++ { 0x4c, 0x8c, 0x25, 0x20, 0x21, 0xcb, 0xc2, 0x4b, 0x3a, 0x5b, 0x8d, }, ++ { 0x56, 0xe2, 0x77, 0xa0, 0xb6, 0x9f, 0x81, 0xec, 0x83, 0x75, 0xc4, 0xf9, }, ++ { 0x71, 0x70, 0x0f, 0xad, 0x4d, 0x35, 0x81, 0x9d, 0x88, 0x69, 0xf9, 0xaa, ++ 0xd3, }, ++ { 0x50, 0x6e, 0x86, 0x6e, 0x43, 0xc0, 0xc2, 0x44, 0xc2, 0xe2, 0xa0, 0x1c, ++ 0xb7, 0x9a, }, ++ { 0xe4, 0x7e, 0x72, 0xc6, 0x12, 0x8e, 0x7c, 0xfc, 0xbd, 0xe2, 0x08, 0x31, ++ 0x3d, 0x47, 0x3d, }, ++ { 0x08, 0x97, 0x5b, 0x80, 0xae, 0xc4, 0x1d, 0x50, 0x77, 0xdf, 0x1f, 0xd0, ++ 0x24, 0xf0, 0x17, 0xc0, }, ++ { 0x01, 0xb6, 0x29, 0xf4, 0xaf, 0x78, 0x5f, 0xb6, 0x91, 0xdd, 0x76, 0x76, ++ 0xd2, 0xfd, 0x0c, 0x47, 0x40, }, ++ { 0xa1, 0xd8, 0x09, 0x97, 0x7a, 0xa6, 0xc8, 0x94, 0xf6, 0x91, 0x7b, 0xae, ++ 0x2b, 0x9f, 0x0d, 0x83, 0x48, 0xf7, }, ++ { 0x12, 0xd5, 0x53, 0x7d, 0x9a, 0xb0, 0xbe, 0xd9, 0xed, 0xe9, 0x9e, 0xee, ++ 0x61, 0x5b, 0x42, 0xf2, 0xc0, 0x73, 0xc0, }, ++ { 0xd5, 0x77, 0xd6, 0x5c, 0x6e, 0xa5, 0x69, 0x2b, 0x3b, 0x8c, 0xd6, 0x7d, ++ 0x1d, 0xbe, 0x2c, 0xa1, 0x02, 0x21, 0xcd, 0x29, }, ++ { 0xa4, 0x98, 0x80, 0xca, 0x22, 0xcf, 0x6a, 0xab, 0x5e, 0x40, 0x0d, 0x61, ++ 0x08, 0x21, 0xef, 0xc0, 0x6c, 0x52, 0xb4, 0xb0, 0x53, }, ++ { 0xbf, 0xaf, 0x8f, 0x3b, 0x7a, 0x97, 0x33, 0xe5, 0xca, 0x07, 0x37, 0xfd, ++ 0x15, 0xdf, 0xce, 0x26, 0x2a, 0xb1, 0xa7, 0x0b, 0xb3, 0xac, }, ++ { 0x16, 0x22, 0xe1, 0xbc, 0x99, 0x4e, 0x01, 0xf0, 0xfa, 0xff, 0x8f, 0xa5, ++ 0x0c, 0x61, 0xb0, 0xad, 0xcc, 0xb1, 0xe1, 0x21, 0x46, 0xfa, 0x2e, }, ++ { 0x11, 0x5b, 0x0b, 0x2b, 0xe6, 0x14, 0xc1, 0xd5, 0x4d, 0x71, 0x5e, 0x17, ++ 0xea, 0x23, 0xdd, 0x6c, 0xbd, 0x1d, 0xbe, 0x12, 0x1b, 0xee, 0x4c, 0x1a, }, ++ { 0x40, 0x88, 0x22, 0xf3, 0x20, 0x6c, 0xed, 0xe1, 0x36, 0x34, 0x62, 0x2c, ++ 0x98, 0x83, 0x52, 0xe2, 0x25, 0xee, 0xe9, 0xf5, 0xe1, 0x17, 0xf0, 0x5c, ++ 0xae, }, ++ { 0xc3, 0x76, 0x37, 0xde, 0x95, 0x8c, 0xca, 0x2b, 0x0c, 0x23, 0xe7, 0xb5, ++ 0x38, 0x70, 0x61, 0xcc, 0xff, 0xd3, 0x95, 0x7b, 0xf3, 0xff, 0x1f, 0x9d, ++ 0x59, 0x00, }, ++ { 0x0c, 0x19, 0x52, 0x05, 0x22, 0x53, 0xcb, 0x48, 0xd7, 0x10, 0x0e, 0x7e, ++ 0x14, 0x69, 0xb5, 0xa2, 0x92, 0x43, 0xa3, 0x9e, 0x4b, 0x8f, 0x51, 0x2c, ++ 0x5a, 0x2c, 0x3b, }, ++ { 0xe1, 0x9d, 0x70, 0x70, 0x28, 0xec, 0x86, 0x40, 0x55, 0x33, 0x56, 0xda, ++ 0x88, 0xca, 0xee, 0xc8, 0x6a, 0x20, 0xb1, 0xe5, 0x3d, 0x57, 0xf8, 0x3c, ++ 0x10, 0x07, 0x2a, 0xc4, }, ++ { 0x0b, 0xae, 0xf1, 0xc4, 0x79, 0xee, 0x1b, 0x3d, 0x27, 0x35, 0x8d, 0x14, ++ 0xd6, 0xae, 0x4e, 0x3c, 0xe9, 0x53, 0x50, 0xb5, 0xcc, 0x0c, 0xf7, 0xdf, ++ 0xee, 0xa1, 0x74, 0xd6, 0x71, }, ++ { 0xe6, 0xa4, 0xf4, 0x99, 0x98, 0xb9, 0x80, 0xea, 0x96, 0x7f, 0x4f, 0x33, ++ 0xcf, 0x74, 0x25, 0x6f, 0x17, 0x6c, 0xbf, 0xf5, 0x5c, 0x38, 0xd0, 0xff, ++ 0x96, 0xcb, 0x13, 0xf9, 0xdf, 0xfd, }, ++ { 0xbe, 0x92, 0xeb, 0xba, 0x44, 0x2c, 0x24, 0x74, 0xd4, 0x03, 0x27, 0x3c, ++ 0x5d, 0x5b, 0x03, 0x30, 0x87, 0x63, 0x69, 0xe0, 0xb8, 0x94, 0xf4, 0x44, ++ 0x7e, 0xad, 0xcd, 0x20, 0x12, 0x16, 0x79, }, ++ { 0x30, 0xf1, 0xc4, 0x8e, 0x05, 0x90, 0x2a, 0x97, 0x63, 0x94, 0x46, 0xff, ++ 0xce, 0xd8, 0x67, 0xa7, 0xac, 0x33, 0x8c, 0x95, 0xb7, 0xcd, 0xa3, 0x23, ++ 0x98, 0x9d, 0x76, 0x6c, 0x9d, 0xa8, 0xd6, 0x8a, }, ++ { 0xbe, }, ++ { 0x17, 0x6c, }, ++ { 0x1a, 0x42, 0x4f, }, ++ { 0xba, 0xaf, 0xb7, 0x65, }, ++ { 0xc2, 0x63, 0x43, 0x6a, 0xea, }, ++ { 0xe4, 0x4d, 0xad, 0xf2, 0x0b, 0x02, }, ++ { 0x04, 0xc7, 0xc4, 0x7f, 0xa9, 0x2b, 0xce, }, ++ { 0x66, 0xf6, 0x67, 0xcb, 0x03, 0x53, 0xc8, 0xf1, }, ++ { 0x56, 0xa3, 0x60, 0x78, 0xc9, 0x5f, 0x70, 0x1b, 0x5e, }, ++ { 0x99, 0xff, 0x81, 0x7c, 0x13, 0x3c, 0x29, 0x79, 0x4b, 0x65, }, ++ { 0x51, 0x10, 0x50, 0x93, 0x01, 0x93, 0xb7, 0x01, 0xc9, 0x18, 0xb7, }, ++ { 0x8e, 0x3c, 0x42, 0x1e, 0x5e, 0x7d, 0xc1, 0x50, 0x70, 0x1f, 0x00, 0x98, }, ++ { 0x5f, 0xd9, 0x9b, 0xc8, 0xd7, 0xb2, 0x72, 0x62, 0x1a, 0x1e, 0xba, 0x92, ++ 0xe9, }, ++ { 0x70, 0x2b, 0xba, 0xfe, 0xad, 0x5d, 0x96, 0x3f, 0x27, 0xc2, 0x41, 0x6d, ++ 0xc4, 0xb3, }, ++ { 0xae, 0xe0, 0xd5, 0xd4, 0xc7, 0xae, 0x15, 0x5e, 0xdc, 0xdd, 0x33, 0x60, ++ 0xd7, 0xd3, 0x5e, }, ++ { 0x79, 0x8e, 0xbc, 0x9e, 0x20, 0xb9, 0x19, 0x4b, 0x63, 0x80, 0xf3, 0x16, ++ 0xaf, 0x39, 0xbd, 0x92, }, ++ { 0xc2, 0x0e, 0x85, 0xa0, 0x0b, 0x9a, 0xb0, 0xec, 0xde, 0x38, 0xd3, 0x10, ++ 0xd9, 0xa7, 0x66, 0x27, 0xcf, }, ++ { 0x0e, 0x3b, 0x75, 0x80, 0x67, 0x14, 0x0c, 0x02, 0x90, 0xd6, 0xb3, 0x02, ++ 0x81, 0xf6, 0xa6, 0x87, 0xce, 0x58, }, ++ { 0x79, 0xb5, 0xe9, 0x5d, 0x52, 0x4d, 0xf7, 0x59, 0xf4, 0x2e, 0x27, 0xdd, ++ 0xb3, 0xed, 0x57, 0x5b, 0x82, 0xea, 0x6f, }, ++ { 0xa2, 0x97, 0xf5, 0x80, 0x02, 0x3d, 0xde, 0xa3, 0xf9, 0xf6, 0xab, 0xe3, ++ 0x57, 0x63, 0x7b, 0x9b, 0x10, 0x42, 0x6f, 0xf2, }, ++ { 0x12, 0x7a, 0xfc, 0xb7, 0x67, 0x06, 0x0c, 0x78, 0x1a, 0xfe, 0x88, 0x4f, ++ 0xc6, 0xac, 0x52, 0x96, 0x64, 0x28, 0x97, 0x84, 0x06, }, ++ { 0xc5, 0x04, 0x44, 0x6b, 0xb2, 0xa5, 0xa4, 0x66, 0xe1, 0x76, 0xa2, 0x51, ++ 0xf9, 0x59, 0x69, 0x97, 0x56, 0x0b, 0xbf, 0x50, 0xb3, 0x34, }, ++ { 0x21, 0x32, 0x6b, 0x42, 0xb5, 0xed, 0x71, 0x8d, 0xf7, 0x5a, 0x35, 0xe3, ++ 0x90, 0xe2, 0xee, 0xaa, 0x89, 0xf6, 0xc9, 0x9c, 0x4d, 0x73, 0xf4, }, ++ { 0x4c, 0xa6, 0x09, 0xf4, 0x48, 0xe7, 0x46, 0xbc, 0x49, 0xfc, 0xe5, 0xda, ++ 0xd1, 0x87, 0x13, 0x17, 0x4c, 0x59, 0x71, 0x26, 0x5b, 0x2c, 0x42, 0xb7, }, ++ { 0x13, 0x63, 0xf3, 0x40, 0x02, 0xe5, 0xa3, 0x3a, 0x5e, 0x8e, 0xf8, 0xb6, ++ 0x8a, 0x49, 0x60, 0x76, 0x34, 0x72, 0x94, 0x73, 0xf6, 0xd9, 0x21, 0x6a, ++ 0x26, }, ++ { 0xdf, 0x75, 0x16, 0x10, 0x1b, 0x5e, 0x81, 0xc3, 0xc8, 0xde, 0x34, 0x24, ++ 0xb0, 0x98, 0xeb, 0x1b, 0x8f, 0xa1, 0x9b, 0x05, 0xee, 0xa5, 0xe9, 0x35, ++ 0xf4, 0x1d, }, ++ { 0xcd, 0x21, 0x93, 0x6e, 0x5b, 0xa0, 0x26, 0x2b, 0x21, 0x0e, 0xa0, 0xb9, ++ 0x1c, 0xb5, 0xbb, 0xb8, 0xf8, 0x1e, 0xff, 0x5c, 0xa8, 0xf9, 0x39, 0x46, ++ 0x4e, 0x29, 0x26, }, ++ { 0x73, 0x7f, 0x0e, 0x3b, 0x0b, 0x5c, 0xf9, 0x60, 0xaa, 0x88, 0xa1, 0x09, ++ 0xb1, 0x5d, 0x38, 0x7b, 0x86, 0x8f, 0x13, 0x7a, 0x8d, 0x72, 0x7a, 0x98, ++ 0x1a, 0x5b, 0xff, 0xc9, }, ++ { 0xd3, 0x3c, 0x61, 0x71, 0x44, 0x7e, 0x31, 0x74, 0x98, 0x9d, 0x9a, 0xd2, ++ 0x27, 0xf3, 0x46, 0x43, 0x42, 0x51, 0xd0, 0x5f, 0xe9, 0x1c, 0x5c, 0x69, ++ 0xbf, 0xf6, 0xbe, 0x3c, 0x40, }, ++ { 0x31, 0x99, 0x31, 0x9f, 0xaa, 0x43, 0x2e, 0x77, 0x3e, 0x74, 0x26, 0x31, ++ 0x5e, 0x61, 0xf1, 0x87, 0xe2, 0xeb, 0x9b, 0xcd, 0xd0, 0x3a, 0xee, 0x20, ++ 0x7e, 0x10, 0x0a, 0x0b, 0x7e, 0xfa, }, ++ { 0xa4, 0x27, 0x80, 0x67, 0x81, 0x2a, 0xa7, 0x62, 0xf7, 0x6e, 0xda, 0xd4, ++ 0x5c, 0x39, 0x74, 0xad, 0x7e, 0xbe, 0xad, 0xa5, 0x84, 0x7f, 0xa9, 0x30, ++ 0x5d, 0xdb, 0xe2, 0x05, 0x43, 0xf7, 0x1b, }, ++ { 0x0b, 0x37, 0xd8, 0x02, 0xe1, 0x83, 0xd6, 0x80, 0xf2, 0x35, 0xc2, 0xb0, ++ 0x37, 0xef, 0xef, 0x5e, 0x43, 0x93, 0xf0, 0x49, 0x45, 0x0a, 0xef, 0xb5, ++ 0x76, 0x70, 0x12, 0x44, 0xc4, 0xdb, 0xf5, 0x7a, }, ++ { 0x1f, }, ++ { 0x82, 0x60, }, ++ { 0xcc, 0xe3, 0x08, }, ++ { 0x56, 0x17, 0xe4, 0x59, }, ++ { 0xe2, 0xd7, 0x9e, 0xc4, 0x4c, }, ++ { 0xb2, 0xad, 0xd3, 0x78, 0x58, 0x5a, }, ++ { 0xce, 0x43, 0xb4, 0x02, 0x96, 0xab, 0x3c, }, ++ { 0xe6, 0x05, 0x1a, 0x73, 0x22, 0x32, 0xbb, 0x77, }, ++ { 0x23, 0xe7, 0xda, 0xfe, 0x2c, 0xef, 0x8c, 0x22, 0xec, }, ++ { 0xe9, 0x8e, 0x55, 0x38, 0xd1, 0xd7, 0x35, 0x23, 0x98, 0xc7, }, ++ { 0xb5, 0x81, 0x1a, 0xe5, 0xb5, 0xa5, 0xd9, 0x4d, 0xca, 0x41, 0xe7, }, ++ { 0x41, 0x16, 0x16, 0x95, 0x8d, 0x9e, 0x0c, 0xea, 0x8c, 0x71, 0x9a, 0xc1, }, ++ { 0x7c, 0x33, 0xc0, 0xa4, 0x00, 0x62, 0xea, 0x60, 0x67, 0xe4, 0x20, 0xbc, ++ 0x5b, }, ++ { 0xdb, 0xb1, 0xdc, 0xfd, 0x08, 0xc0, 0xde, 0x82, 0xd1, 0xde, 0x38, 0xc0, ++ 0x90, 0x48, }, ++ { 0x37, 0x18, 0x2e, 0x0d, 0x61, 0xaa, 0x61, 0xd7, 0x86, 0x20, 0x16, 0x60, ++ 0x04, 0xd9, 0xd5, }, ++ { 0xb0, 0xcf, 0x2c, 0x4c, 0x5e, 0x5b, 0x4f, 0x2a, 0x23, 0x25, 0x58, 0x47, ++ 0xe5, 0x31, 0x06, 0x70, }, ++ { 0x91, 0xa0, 0xa3, 0x86, 0x4e, 0xe0, 0x72, 0x38, 0x06, 0x67, 0x59, 0x5c, ++ 0x70, 0x25, 0xdb, 0x33, 0x27, }, ++ { 0x44, 0x58, 0x66, 0xb8, 0x58, 0xc7, 0x13, 0xed, 0x4c, 0xc0, 0xf4, 0x9a, ++ 0x1e, 0x67, 0x75, 0x33, 0xb6, 0xb8, }, ++ { 0x7f, 0x98, 0x4a, 0x8e, 0x50, 0xa2, 0x5c, 0xcd, 0x59, 0xde, 0x72, 0xb3, ++ 0x9d, 0xc3, 0x09, 0x8a, 0xab, 0x56, 0xf1, }, ++ { 0x80, 0x96, 0x49, 0x1a, 0x59, 0xa2, 0xc5, 0xd5, 0xa7, 0x20, 0x8a, 0xb7, ++ 0x27, 0x62, 0x84, 0x43, 0xc6, 0xe1, 0x1b, 0x5d, }, ++ { 0x6b, 0xb7, 0x2b, 0x26, 0x62, 0x14, 0x70, 0x19, 0x3d, 0x4d, 0xac, 0xac, ++ 0x63, 0x58, 0x5e, 0x94, 0xb5, 0xb7, 0xe8, 0xe8, 0xa2, }, ++ { 0x20, 0xa8, 0xc0, 0xfd, 0x63, 0x3d, 0x6e, 0x98, 0xcf, 0x0c, 0x49, 0x98, ++ 0xe4, 0x5a, 0xfe, 0x8c, 0xaa, 0x70, 0x82, 0x1c, 0x7b, 0x74, }, ++ { 0xc8, 0xe8, 0xdd, 0xdf, 0x69, 0x30, 0x01, 0xc2, 0x0f, 0x7e, 0x2f, 0x11, ++ 0xcc, 0x3e, 0x17, 0xa5, 0x69, 0x40, 0x3f, 0x0e, 0x79, 0x7f, 0xcf, }, ++ { 0xdb, 0x61, 0xc0, 0xe2, 0x2e, 0x49, 0x07, 0x31, 0x1d, 0x91, 0x42, 0x8a, ++ 0xfc, 0x5e, 0xd3, 0xf8, 0x56, 0x1f, 0x2b, 0x73, 0xfd, 0x9f, 0xb2, 0x8e, }, ++ { 0x0c, 0x89, 0x55, 0x0c, 0x1f, 0x59, 0x2c, 0x9d, 0x1b, 0x29, 0x1d, 0x41, ++ 0x1d, 0xe6, 0x47, 0x8f, 0x8c, 0x2b, 0xea, 0x8f, 0xf0, 0xff, 0x21, 0x70, ++ 0x88, }, ++ { 0x12, 0x18, 0x95, 0xa6, 0x59, 0xb1, 0x31, 0x24, 0x45, 0x67, 0x55, 0xa4, ++ 0x1a, 0x2d, 0x48, 0x67, 0x1b, 0x43, 0x88, 0x2d, 0x8e, 0xa0, 0x70, 0xb3, ++ 0xc6, 0xbb, }, ++ { 0xe7, 0xb1, 0x1d, 0xb2, 0x76, 0x4d, 0x68, 0x68, 0x68, 0x23, 0x02, 0x55, ++ 0x3a, 0xe2, 0xe5, 0xd5, 0x4b, 0x43, 0xf9, 0x34, 0x77, 0x5c, 0xa1, 0xf5, ++ 0x55, 0xfd, 0x4f, }, ++ { 0x8c, 0x87, 0x5a, 0x08, 0x3a, 0x73, 0xad, 0x61, 0xe1, 0xe7, 0x99, 0x7e, ++ 0xf0, 0x5d, 0xe9, 0x5d, 0x16, 0x43, 0x80, 0x2f, 0xd0, 0x66, 0x34, 0xe2, ++ 0x42, 0x64, 0x3b, 0x1a, }, ++ { 0x39, 0xc1, 0x99, 0xcf, 0x22, 0xbf, 0x16, 0x8f, 0x9f, 0x80, 0x7f, 0x95, ++ 0x0a, 0x05, 0x67, 0x27, 0xe7, 0x15, 0xdf, 0x9d, 0xb2, 0xfe, 0x1c, 0xb5, ++ 0x1d, 0x60, 0x8f, 0x8a, 0x1d, }, ++ { 0x9b, 0x6e, 0x08, 0x09, 0x06, 0x73, 0xab, 0x68, 0x02, 0x62, 0x1a, 0xe4, ++ 0xd4, 0xdf, 0xc7, 0x02, 0x4c, 0x6a, 0x5f, 0xfd, 0x23, 0xac, 0xae, 0x6d, ++ 0x43, 0xa4, 0x7a, 0x50, 0x60, 0x3c, }, ++ { 0x1d, 0xb4, 0xc6, 0xe1, 0xb1, 0x4b, 0xe3, 0xf2, 0xe2, 0x1a, 0x73, 0x1b, ++ 0xa0, 0x92, 0xa7, 0xf5, 0xff, 0x8f, 0x8b, 0x5d, 0xdf, 0xa8, 0x04, 0xb3, ++ 0xb0, 0xf7, 0xcc, 0x12, 0xfa, 0x35, 0x46, }, ++ { 0x49, 0x45, 0x97, 0x11, 0x0f, 0x1c, 0x60, 0x8e, 0xe8, 0x47, 0x30, 0xcf, ++ 0x60, 0xa8, 0x71, 0xc5, 0x1b, 0xe9, 0x39, 0x4d, 0x49, 0xb6, 0x12, 0x1f, ++ 0x24, 0xab, 0x37, 0xff, 0x83, 0xc2, 0xe1, 0x3a, }, ++ { 0x60, }, ++ { 0x24, 0x26, }, ++ { 0x47, 0xeb, 0xc9, }, ++ { 0x4a, 0xd0, 0xbc, 0xf0, }, ++ { 0x8e, 0x2b, 0xc9, 0x85, 0x3c, }, ++ { 0xa2, 0x07, 0x15, 0xb8, 0x12, 0x74, }, ++ { 0x0f, 0xdb, 0x5b, 0x33, 0x69, 0xfe, 0x4b, }, ++ { 0xa2, 0x86, 0x54, 0xf4, 0xfd, 0xb2, 0xd4, 0xe6, }, ++ { 0xbb, 0x84, 0x78, 0x49, 0x27, 0x8e, 0x61, 0xda, 0x60, }, ++ { 0x04, 0xc3, 0xcd, 0xaa, 0x8f, 0xa7, 0x03, 0xc9, 0xf9, 0xb6, }, ++ { 0xf8, 0x27, 0x1d, 0x61, 0xdc, 0x21, 0x42, 0xdd, 0xad, 0x92, 0x40, }, ++ { 0x12, 0x87, 0xdf, 0xc2, 0x41, 0x45, 0x5a, 0x36, 0x48, 0x5b, 0x51, 0x2b, }, ++ { 0xbb, 0x37, 0x5d, 0x1f, 0xf1, 0x68, 0x7a, 0xc4, 0xa5, 0xd2, 0xa4, 0x91, ++ 0x8d, }, ++ { 0x5b, 0x27, 0xd1, 0x04, 0x54, 0x52, 0x9f, 0xa3, 0x47, 0x86, 0x33, 0x33, ++ 0xbf, 0xa0, }, ++ { 0xcf, 0x04, 0xea, 0xf8, 0x03, 0x2a, 0x43, 0xff, 0xa6, 0x68, 0x21, 0x4c, ++ 0xd5, 0x4b, 0xed, }, ++ { 0xaf, 0xb8, 0xbc, 0x63, 0x0f, 0x18, 0x4d, 0xe2, 0x7a, 0xdd, 0x46, 0x44, ++ 0xc8, 0x24, 0x0a, 0xb7, }, ++ { 0x3e, 0xdc, 0x36, 0xe4, 0x89, 0xb1, 0xfa, 0xc6, 0x40, 0x93, 0x2e, 0x75, ++ 0xb2, 0x15, 0xd1, 0xb1, 0x10, }, ++ { 0x6c, 0xd8, 0x20, 0x3b, 0x82, 0x79, 0xf9, 0xc8, 0xbc, 0x9d, 0xe0, 0x35, ++ 0xbe, 0x1b, 0x49, 0x1a, 0xbc, 0x3a, }, ++ { 0x78, 0x65, 0x2c, 0xbe, 0x35, 0x67, 0xdc, 0x78, 0xd4, 0x41, 0xf6, 0xc9, ++ 0xde, 0xde, 0x1f, 0x18, 0x13, 0x31, 0x11, }, ++ { 0x8a, 0x7f, 0xb1, 0x33, 0x8f, 0x0c, 0x3c, 0x0a, 0x06, 0x61, 0xf0, 0x47, ++ 0x29, 0x1b, 0x29, 0xbc, 0x1c, 0x47, 0xef, 0x7a, }, ++ { 0x65, 0x91, 0xf1, 0xe6, 0xb3, 0x96, 0xd3, 0x8c, 0xc2, 0x4a, 0x59, 0x35, ++ 0x72, 0x8e, 0x0b, 0x9a, 0x87, 0xca, 0x34, 0x7b, 0x63, }, ++ { 0x5f, 0x08, 0x87, 0x80, 0x56, 0x25, 0x89, 0x77, 0x61, 0x8c, 0x64, 0xa1, ++ 0x59, 0x6d, 0x59, 0x62, 0xe8, 0x4a, 0xc8, 0x58, 0x99, 0xd1, }, ++ { 0x23, 0x87, 0x1d, 0xed, 0x6f, 0xf2, 0x91, 0x90, 0xe2, 0xfe, 0x43, 0x21, ++ 0xaf, 0x97, 0xc6, 0xbc, 0xd7, 0x15, 0xc7, 0x2d, 0x08, 0x77, 0x91, }, ++ { 0x90, 0x47, 0x9a, 0x9e, 0x3a, 0xdf, 0xf3, 0xc9, 0x4c, 0x1e, 0xa7, 0xd4, ++ 0x6a, 0x32, 0x90, 0xfe, 0xb7, 0xb6, 0x7b, 0xfa, 0x96, 0x61, 0xfb, 0xa4, }, ++ { 0xb1, 0x67, 0x60, 0x45, 0xb0, 0x96, 0xc5, 0x15, 0x9f, 0x4d, 0x26, 0xd7, ++ 0x9d, 0xf1, 0xf5, 0x6d, 0x21, 0x00, 0x94, 0x31, 0x64, 0x94, 0xd3, 0xa7, ++ 0xd3, }, ++ { 0x02, 0x3e, 0xaf, 0xf3, 0x79, 0x73, 0xa5, 0xf5, 0xcc, 0x7a, 0x7f, 0xfb, ++ 0x79, 0x2b, 0x85, 0x8c, 0x88, 0x72, 0x06, 0xbe, 0xfe, 0xaf, 0xc1, 0x16, ++ 0xa6, 0xd6, }, ++ { 0x2a, 0xb0, 0x1a, 0xe5, 0xaa, 0x6e, 0xb3, 0xae, 0x53, 0x85, 0x33, 0x80, ++ 0x75, 0xae, 0x30, 0xe6, 0xb8, 0x72, 0x42, 0xf6, 0x25, 0x4f, 0x38, 0x88, ++ 0x55, 0xd1, 0xa9, }, ++ { 0x90, 0xd8, 0x0c, 0xc0, 0x93, 0x4b, 0x4f, 0x9e, 0x65, 0x6c, 0xa1, 0x54, ++ 0xa6, 0xf6, 0x6e, 0xca, 0xd2, 0xbb, 0x7e, 0x6a, 0x1c, 0xd3, 0xce, 0x46, ++ 0xef, 0xb0, 0x00, 0x8d, }, ++ { 0xed, 0x9c, 0x49, 0xcd, 0xc2, 0xde, 0x38, 0x0e, 0xe9, 0x98, 0x6c, 0xc8, ++ 0x90, 0x9e, 0x3c, 0xd4, 0xd3, 0xeb, 0x88, 0x32, 0xc7, 0x28, 0xe3, 0x94, ++ 0x1c, 0x9f, 0x8b, 0xf3, 0xcb, }, ++ { 0xac, 0xe7, 0x92, 0x16, 0xb4, 0x14, 0xa0, 0xe4, 0x04, 0x79, 0xa2, 0xf4, ++ 0x31, 0xe6, 0x0c, 0x26, 0xdc, 0xbf, 0x2f, 0x69, 0x1b, 0x55, 0x94, 0x67, ++ 0xda, 0x0c, 0xd7, 0x32, 0x1f, 0xef, }, ++ { 0x68, 0x63, 0x85, 0x57, 0x95, 0x9e, 0x42, 0x27, 0x41, 0x43, 0x42, 0x02, ++ 0xa5, 0x78, 0xa7, 0xc6, 0x43, 0xc1, 0x6a, 0xba, 0x70, 0x80, 0xcd, 0x04, ++ 0xb6, 0x78, 0x76, 0x29, 0xf3, 0xe8, 0xa0, }, ++ { 0xe6, 0xac, 0x8d, 0x9d, 0xf0, 0xc0, 0xf7, 0xf7, 0xe3, 0x3e, 0x4e, 0x28, ++ 0x0f, 0x59, 0xb2, 0x67, 0x9e, 0x84, 0x34, 0x42, 0x96, 0x30, 0x2b, 0xca, ++ 0x49, 0xb6, 0xc5, 0x9a, 0x84, 0x59, 0xa7, 0x81, }, ++ { 0x7e, }, ++ { 0x1e, 0x21, }, ++ { 0x26, 0xd3, 0xdd, }, ++ { 0x2c, 0xd4, 0xb3, 0x3d, }, ++ { 0x86, 0x7b, 0x76, 0x3c, 0xf0, }, ++ { 0x12, 0xc3, 0x70, 0x1d, 0x55, 0x18, }, ++ { 0x96, 0xc2, 0xbd, 0x61, 0x55, 0xf4, 0x24, }, ++ { 0x20, 0x51, 0xf7, 0x86, 0x58, 0x8f, 0x07, 0x2a, }, ++ { 0x93, 0x15, 0xa8, 0x1d, 0xda, 0x97, 0xee, 0x0e, 0x6c, }, ++ { 0x39, 0x93, 0xdf, 0xd5, 0x0e, 0xca, 0xdc, 0x7a, 0x92, 0xce, }, ++ { 0x60, 0xd5, 0xfd, 0xf5, 0x1b, 0x26, 0x82, 0x26, 0x73, 0x02, 0xbc, }, ++ { 0x98, 0xf2, 0x34, 0xe1, 0xf5, 0xfb, 0x00, 0xac, 0x10, 0x4a, 0x38, 0x9f, }, ++ { 0xda, 0x3a, 0x92, 0x8a, 0xd0, 0xcd, 0x12, 0xcd, 0x15, 0xbb, 0xab, 0x77, ++ 0x66, }, ++ { 0xa2, 0x92, 0x1a, 0xe5, 0xca, 0x0c, 0x30, 0x75, 0xeb, 0xaf, 0x00, 0x31, ++ 0x55, 0x66, }, ++ { 0x06, 0xea, 0xfd, 0x3e, 0x86, 0x38, 0x62, 0x4e, 0xa9, 0x12, 0xa4, 0x12, ++ 0x43, 0xbf, 0xa1, }, ++ { 0xe4, 0x71, 0x7b, 0x94, 0xdb, 0xa0, 0xd2, 0xff, 0x9b, 0xeb, 0xad, 0x8e, ++ 0x95, 0x8a, 0xc5, 0xed, }, ++ { 0x25, 0x5a, 0x77, 0x71, 0x41, 0x0e, 0x7a, 0xe9, 0xed, 0x0c, 0x10, 0xef, ++ 0xf6, 0x2b, 0x3a, 0xba, 0x60, }, ++ { 0xee, 0xe2, 0xa3, 0x67, 0x64, 0x1d, 0xc6, 0x04, 0xc4, 0xe1, 0x68, 0xd2, ++ 0x6e, 0xd2, 0x91, 0x75, 0x53, 0x07, }, ++ { 0xe0, 0xf6, 0x4d, 0x8f, 0x68, 0xfc, 0x06, 0x7e, 0x18, 0x79, 0x7f, 0x2b, ++ 0x6d, 0xef, 0x46, 0x7f, 0xab, 0xb2, 0xad, }, ++ { 0x3d, 0x35, 0x88, 0x9f, 0x2e, 0xcf, 0x96, 0x45, 0x07, 0x60, 0x71, 0x94, ++ 0x00, 0x8d, 0xbf, 0xf4, 0xef, 0x46, 0x2e, 0x3c, }, ++ { 0x43, 0xcf, 0x98, 0xf7, 0x2d, 0xf4, 0x17, 0xe7, 0x8c, 0x05, 0x2d, 0x9b, ++ 0x24, 0xfb, 0x4d, 0xea, 0x4a, 0xec, 0x01, 0x25, 0x29, }, ++ { 0x8e, 0x73, 0x9a, 0x78, 0x11, 0xfe, 0x48, 0xa0, 0x3b, 0x1a, 0x26, 0xdf, ++ 0x25, 0xe9, 0x59, 0x1c, 0x70, 0x07, 0x9f, 0xdc, 0xa0, 0xa6, }, ++ { 0xe8, 0x47, 0x71, 0xc7, 0x3e, 0xdf, 0xb5, 0x13, 0xb9, 0x85, 0x13, 0xa8, ++ 0x54, 0x47, 0x6e, 0x59, 0x96, 0x09, 0x13, 0x5f, 0x82, 0x16, 0x0b, }, ++ { 0xfb, 0xc0, 0x8c, 0x03, 0x21, 0xb3, 0xc4, 0xb5, 0x43, 0x32, 0x6c, 0xea, ++ 0x7f, 0xa8, 0x43, 0x91, 0xe8, 0x4e, 0x3f, 0xbf, 0x45, 0x58, 0x6a, 0xa3, }, ++ { 0x55, 0xf8, 0xf3, 0x00, 0x76, 0x09, 0xef, 0x69, 0x5d, 0xd2, 0x8a, 0xf2, ++ 0x65, 0xc3, 0xcb, 0x9b, 0x43, 0xfd, 0xb1, 0x7e, 0x7f, 0xa1, 0x94, 0xb0, ++ 0xd7, }, ++ { 0xaa, 0x13, 0xc1, 0x51, 0x40, 0x6d, 0x8d, 0x4c, 0x0a, 0x95, 0x64, 0x7b, ++ 0xd1, 0x96, 0xb6, 0x56, 0xb4, 0x5b, 0xcf, 0xd6, 0xd9, 0x15, 0x97, 0xdd, ++ 0xb6, 0xef, }, ++ { 0xaf, 0xb7, 0x36, 0xb0, 0x04, 0xdb, 0xd7, 0x9c, 0x9a, 0x44, 0xc4, 0xf6, ++ 0x1f, 0x12, 0x21, 0x2d, 0x59, 0x30, 0x54, 0xab, 0x27, 0x61, 0xa3, 0x57, ++ 0xef, 0xf8, 0x53, }, ++ { 0x97, 0x34, 0x45, 0x3e, 0xce, 0x7c, 0x35, 0xa2, 0xda, 0x9f, 0x4b, 0x46, ++ 0x6c, 0x11, 0x67, 0xff, 0x2f, 0x76, 0x58, 0x15, 0x71, 0xfa, 0x44, 0x89, ++ 0x89, 0xfd, 0xf7, 0x99, }, ++ { 0x1f, 0xb1, 0x62, 0xeb, 0x83, 0xc5, 0x9c, 0x89, 0xf9, 0x2c, 0xd2, 0x03, ++ 0x61, 0xbc, 0xbb, 0xa5, 0x74, 0x0e, 0x9b, 0x7e, 0x82, 0x3e, 0x70, 0x0a, ++ 0xa9, 0x8f, 0x2b, 0x59, 0xfb, }, ++ { 0xf8, 0xca, 0x5e, 0x3a, 0x4f, 0x9e, 0x10, 0x69, 0x10, 0xd5, 0x4c, 0xeb, ++ 0x1a, 0x0f, 0x3c, 0x6a, 0x98, 0xf5, 0xb0, 0x97, 0x5b, 0x37, 0x2f, 0x0d, ++ 0xbd, 0x42, 0x4b, 0x69, 0xa1, 0x82, }, ++ { 0x12, 0x8c, 0x6d, 0x52, 0x08, 0xef, 0x74, 0xb2, 0xe6, 0xaa, 0xd3, 0xb0, ++ 0x26, 0xb0, 0xd9, 0x94, 0xb6, 0x11, 0x45, 0x0e, 0x36, 0x71, 0x14, 0x2d, ++ 0x41, 0x8c, 0x21, 0x53, 0x31, 0xe9, 0x68, }, ++ { 0xee, 0xea, 0x0d, 0x89, 0x47, 0x7e, 0x72, 0xd1, 0xd8, 0xce, 0x58, 0x4c, ++ 0x94, 0x1f, 0x0d, 0x51, 0x08, 0xa3, 0xb6, 0x3d, 0xe7, 0x82, 0x46, 0x92, ++ 0xd6, 0x98, 0x6b, 0x07, 0x10, 0x65, 0x52, 0x65, }, ++}; ++ ++static const u8 blake2s_hmac_testvecs[][BLAKE2S_HASH_SIZE] __initconst = { ++ { 0xce, 0xe1, 0x57, 0x69, 0x82, 0xdc, 0xbf, 0x43, 0xad, 0x56, 0x4c, 0x70, ++ 0xed, 0x68, 0x16, 0x96, 0xcf, 0xa4, 0x73, 0xe8, 0xe8, 0xfc, 0x32, 0x79, ++ 0x08, 0x0a, 0x75, 0x82, 0xda, 0x3f, 0x05, 0x11, }, ++ { 0x77, 0x2f, 0x0c, 0x71, 0x41, 0xf4, 0x4b, 0x2b, 0xb3, 0xc6, 0xb6, 0xf9, ++ 0x60, 0xde, 0xe4, 0x52, 0x38, 0x66, 0xe8, 0xbf, 0x9b, 0x96, 0xc4, 0x9f, ++ 0x60, 0xd9, 0x24, 0x37, 0x99, 0xd6, 0xec, 0x31, }, ++}; ++ ++bool __init blake2s_selftest(void) ++{ ++ u8 key[BLAKE2S_KEY_SIZE]; ++ u8 buf[ARRAY_SIZE(blake2s_testvecs)]; ++ u8 hash[BLAKE2S_HASH_SIZE]; ++ struct blake2s_state state; ++ bool success = true; ++ int i, l; ++ ++ key[0] = key[1] = 1; ++ for (i = 2; i < sizeof(key); ++i) ++ key[i] = key[i - 2] + key[i - 1]; ++ ++ for (i = 0; i < sizeof(buf); ++i) ++ buf[i] = (u8)i; ++ ++ for (i = l = 0; i < ARRAY_SIZE(blake2s_testvecs); l = (l + 37) % ++i) { ++ int outlen = 1 + i % BLAKE2S_HASH_SIZE; ++ int keylen = (13 * i) % (BLAKE2S_KEY_SIZE + 1); ++ ++ blake2s(hash, buf, key + BLAKE2S_KEY_SIZE - keylen, outlen, i, ++ keylen); ++ if (memcmp(hash, blake2s_testvecs[i], outlen)) { ++ pr_err("blake2s self-test %d: FAIL\n", i + 1); ++ success = false; ++ } ++ ++ if (!keylen) ++ blake2s_init(&state, outlen); ++ else ++ blake2s_init_key(&state, outlen, ++ key + BLAKE2S_KEY_SIZE - keylen, ++ keylen); ++ ++ blake2s_update(&state, buf, l); ++ blake2s_update(&state, buf + l, i - l); ++ blake2s_final(&state, hash); ++ if (memcmp(hash, blake2s_testvecs[i], outlen)) { ++ pr_err("blake2s init/update/final self-test %d: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } ++ ++ if (success) { ++ blake2s256_hmac(hash, buf, key, sizeof(buf), sizeof(key)); ++ success &= !memcmp(hash, blake2s_hmac_testvecs[0], BLAKE2S_HASH_SIZE); ++ ++ blake2s256_hmac(hash, key, buf, sizeof(key), sizeof(buf)); ++ success &= !memcmp(hash, blake2s_hmac_testvecs[1], BLAKE2S_HASH_SIZE); ++ ++ if (!success) ++ pr_err("blake2s256_hmac self-test: FAIL\n"); ++ } ++ ++ return success; ++} +--- /dev/null ++++ b/lib/crypto/blake2s.c +@@ -0,0 +1,126 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is an implementation of the BLAKE2s hash and PRF functions. ++ * ++ * Information: https://blake2.net/ ++ * ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++bool blake2s_selftest(void); ++ ++void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) ++{ ++ const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; ++ ++ if (unlikely(!inlen)) ++ return; ++ if (inlen > fill) { ++ memcpy(state->buf + state->buflen, in, fill); ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)) ++ blake2s_compress_arch(state, state->buf, 1, ++ BLAKE2S_BLOCK_SIZE); ++ else ++ blake2s_compress_generic(state, state->buf, 1, ++ BLAKE2S_BLOCK_SIZE); ++ state->buflen = 0; ++ in += fill; ++ inlen -= fill; ++ } ++ if (inlen > BLAKE2S_BLOCK_SIZE) { ++ const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); ++ /* Hash one less (full) block than strictly possible */ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)) ++ blake2s_compress_arch(state, in, nblocks - 1, ++ BLAKE2S_BLOCK_SIZE); ++ else ++ blake2s_compress_generic(state, in, nblocks - 1, ++ BLAKE2S_BLOCK_SIZE); ++ in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); ++ inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); ++ } ++ memcpy(state->buf + state->buflen, in, inlen); ++ state->buflen += inlen; ++} ++EXPORT_SYMBOL(blake2s_update); ++ ++void blake2s_final(struct blake2s_state *state, u8 *out) ++{ ++ WARN_ON(IS_ENABLED(DEBUG) && !out); ++ blake2s_set_lastblock(state); ++ memset(state->buf + state->buflen, 0, ++ BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)) ++ blake2s_compress_arch(state, state->buf, 1, state->buflen); ++ else ++ blake2s_compress_generic(state, state->buf, 1, state->buflen); ++ cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); ++ memcpy(out, state->h, state->outlen); ++ memzero_explicit(state, sizeof(*state)); ++} ++EXPORT_SYMBOL(blake2s_final); ++ ++void blake2s256_hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, ++ const size_t keylen) ++{ ++ struct blake2s_state state; ++ u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 }; ++ u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32)); ++ int i; ++ ++ if (keylen > BLAKE2S_BLOCK_SIZE) { ++ blake2s_init(&state, BLAKE2S_HASH_SIZE); ++ blake2s_update(&state, key, keylen); ++ blake2s_final(&state, x_key); ++ } else ++ memcpy(x_key, key, keylen); ++ ++ for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) ++ x_key[i] ^= 0x36; ++ ++ blake2s_init(&state, BLAKE2S_HASH_SIZE); ++ blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); ++ blake2s_update(&state, in, inlen); ++ blake2s_final(&state, i_hash); ++ ++ for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) ++ x_key[i] ^= 0x5c ^ 0x36; ++ ++ blake2s_init(&state, BLAKE2S_HASH_SIZE); ++ blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); ++ blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE); ++ blake2s_final(&state, i_hash); ++ ++ memcpy(out, i_hash, BLAKE2S_HASH_SIZE); ++ memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE); ++ memzero_explicit(i_hash, BLAKE2S_HASH_SIZE); ++} ++EXPORT_SYMBOL(blake2s256_hmac); ++ ++static int __init mod_init(void) ++{ ++ if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && ++ WARN_ON(!blake2s_selftest())) ++ return -ENODEV; ++ return 0; ++} ++ ++static void __exit mod_exit(void) ++{ ++} ++ ++module_init(mod_init); ++module_exit(mod_exit); ++MODULE_LICENSE("GPL v2"); ++MODULE_DESCRIPTION("BLAKE2s hash function"); ++MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0022-crypto-testmgr-add-test-cases-for-Blake2s.patch b/target/linux/generic/backport-5.4/080-wireguard-0022-crypto-testmgr-add-test-cases-for-Blake2s.patch new file mode 100644 index 0000000000..95ace4b295 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0022-crypto-testmgr-add-test-cases-for-Blake2s.patch @@ -0,0 +1,322 @@ +From 4852555d88528a86fc20ac63da7aca29f9071193 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:29 +0100 +Subject: [PATCH 022/124] crypto: testmgr - add test cases for Blake2s + +commit 17e1df67023a5c9ccaeb5de8bf5b88f63127ecf7 upstream. + +As suggested by Eric for the Blake2b implementation contributed by +David, introduce a set of test vectors for Blake2s covering different +digest and key sizes. + + blake2s-128 blake2s-160 blake2s-224 blake2s-256 + --------------------------------------------------- +len=0 | klen=0 klen=1 klen=16 klen=32 +len=1 | klen=16 klen=32 klen=0 klen=1 +len=7 | klen=32 klen=0 klen=1 klen=16 +len=15 | klen=1 klen=16 klen=32 klen=0 +len=64 | klen=0 klen=1 klen=16 klen=32 +len=247 | klen=16 klen=32 klen=0 klen=1 +len=256 | klen=32 klen=0 klen=1 klen=16 + +Cc: David Sterba +Cc: Eric Biggers +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/testmgr.c | 24 +++++ + crypto/testmgr.h | 251 +++++++++++++++++++++++++++++++++++++++++++++++ + 2 files changed, 275 insertions(+) + +--- a/crypto/testmgr.c ++++ b/crypto/testmgr.c +@@ -4035,6 +4035,30 @@ static const struct alg_test_desc alg_te + .test = alg_test_null, + .fips_allowed = 1, + }, { ++ .alg = "blake2s-128", ++ .test = alg_test_hash, ++ .suite = { ++ .hash = __VECS(blakes2s_128_tv_template) ++ } ++ }, { ++ .alg = "blake2s-160", ++ .test = alg_test_hash, ++ .suite = { ++ .hash = __VECS(blakes2s_160_tv_template) ++ } ++ }, { ++ .alg = "blake2s-224", ++ .test = alg_test_hash, ++ .suite = { ++ .hash = __VECS(blakes2s_224_tv_template) ++ } ++ }, { ++ .alg = "blake2s-256", ++ .test = alg_test_hash, ++ .suite = { ++ .hash = __VECS(blakes2s_256_tv_template) ++ } ++ }, { + .alg = "cbc(aes)", + .test = alg_test_skcipher, + .fips_allowed = 1, +--- a/crypto/testmgr.h ++++ b/crypto/testmgr.h +@@ -31567,4 +31567,255 @@ static const struct aead_testvec essiv_h + }, + }; + ++static const char blake2_ordered_sequence[] = ++ "\x00\x01\x02\x03\x04\x05\x06\x07" ++ "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" ++ "\x10\x11\x12\x13\x14\x15\x16\x17" ++ "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" ++ "\x20\x21\x22\x23\x24\x25\x26\x27" ++ "\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f" ++ "\x30\x31\x32\x33\x34\x35\x36\x37" ++ "\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f" ++ "\x40\x41\x42\x43\x44\x45\x46\x47" ++ "\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f" ++ "\x50\x51\x52\x53\x54\x55\x56\x57" ++ "\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f" ++ "\x60\x61\x62\x63\x64\x65\x66\x67" ++ "\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f" ++ "\x70\x71\x72\x73\x74\x75\x76\x77" ++ "\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f" ++ "\x80\x81\x82\x83\x84\x85\x86\x87" ++ "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" ++ "\x90\x91\x92\x93\x94\x95\x96\x97" ++ "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" ++ "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7" ++ "\xa8\xa9\xaa\xab\xac\xad\xae\xaf" ++ "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7" ++ "\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" ++ "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7" ++ "\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" ++ "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7" ++ "\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" ++ "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7" ++ "\xe8\xe9\xea\xeb\xec\xed\xee\xef" ++ "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7" ++ "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"; ++ ++static const struct hash_testvec blakes2s_128_tv_template[] = {{ ++ .digest = (u8[]){ 0x64, 0x55, 0x0d, 0x6f, 0xfe, 0x2c, 0x0a, 0x01, ++ 0xa1, 0x4a, 0xba, 0x1e, 0xad, 0xe0, 0x20, 0x0c, }, ++}, { ++ .plaintext = blake2_ordered_sequence, ++ .psize = 64, ++ .digest = (u8[]){ 0xdc, 0x66, 0xca, 0x8f, 0x03, 0x86, 0x58, 0x01, ++ 0xb0, 0xff, 0xe0, 0x6e, 0xd8, 0xa1, 0xa9, 0x0e, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 1, ++ .digest = (u8[]){ 0x88, 0x1e, 0x42, 0xe7, 0xbb, 0x35, 0x80, 0x82, ++ 0x63, 0x7c, 0x0a, 0x0f, 0xd7, 0xec, 0x6c, 0x2f, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 7, ++ .digest = (u8[]){ 0xcf, 0x9e, 0x07, 0x2a, 0xd5, 0x22, 0xf2, 0xcd, ++ 0xa2, 0xd8, 0x25, 0x21, 0x80, 0x86, 0x73, 0x1c, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .plaintext = blake2_ordered_sequence, ++ .psize = 15, ++ .digest = (u8[]){ 0xf6, 0x33, 0x5a, 0x2c, 0x22, 0xa0, 0x64, 0xb2, ++ 0xb6, 0x3f, 0xeb, 0xbc, 0xd1, 0xc3, 0xe5, 0xb2, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 247, ++ .digest = (u8[]){ 0x72, 0x66, 0x49, 0x60, 0xf9, 0x4a, 0xea, 0xbe, ++ 0x1f, 0xf4, 0x60, 0xce, 0xb7, 0x81, 0xcb, 0x09, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 256, ++ .digest = (u8[]){ 0xd5, 0xa4, 0x0e, 0xc3, 0x16, 0xc7, 0x51, 0xa6, ++ 0x3c, 0xd0, 0xd9, 0x11, 0x57, 0xfa, 0x1e, 0xbb, }, ++}}; ++ ++static const struct hash_testvec blakes2s_160_tv_template[] = {{ ++ .plaintext = blake2_ordered_sequence, ++ .psize = 7, ++ .digest = (u8[]){ 0xb4, 0xf2, 0x03, 0x49, 0x37, 0xed, 0xb1, 0x3e, ++ 0x5b, 0x2a, 0xca, 0x64, 0x82, 0x74, 0xf6, 0x62, ++ 0xe3, 0xf2, 0x84, 0xff, }, ++}, { ++ .plaintext = blake2_ordered_sequence, ++ .psize = 256, ++ .digest = (u8[]){ 0xaa, 0x56, 0x9b, 0xdc, 0x98, 0x17, 0x75, 0xf2, ++ 0xb3, 0x68, 0x83, 0xb7, 0x9b, 0x8d, 0x48, 0xb1, ++ 0x9b, 0x2d, 0x35, 0x05, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .digest = (u8[]){ 0x50, 0x16, 0xe7, 0x0c, 0x01, 0xd0, 0xd3, 0xc3, ++ 0xf4, 0x3e, 0xb1, 0x6e, 0x97, 0xa9, 0x4e, 0xd1, ++ 0x79, 0x65, 0x32, 0x93, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 1, ++ .digest = (u8[]){ 0x1c, 0x2b, 0xcd, 0x9a, 0x68, 0xca, 0x8c, 0x71, ++ 0x90, 0x29, 0x6c, 0x54, 0xfa, 0x56, 0x4a, 0xef, ++ 0xa2, 0x3a, 0x56, 0x9c, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 15, ++ .digest = (u8[]){ 0x36, 0xc3, 0x5f, 0x9a, 0xdc, 0x7e, 0xbf, 0x19, ++ 0x68, 0xaa, 0xca, 0xd8, 0x81, 0xbf, 0x09, 0x34, ++ 0x83, 0x39, 0x0f, 0x30, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .plaintext = blake2_ordered_sequence, ++ .psize = 64, ++ .digest = (u8[]){ 0x86, 0x80, 0x78, 0xa4, 0x14, 0xec, 0x03, 0xe5, ++ 0xb6, 0x9a, 0x52, 0x0e, 0x42, 0xee, 0x39, 0x9d, ++ 0xac, 0xa6, 0x81, 0x63, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 247, ++ .digest = (u8[]){ 0x2d, 0xd8, 0xd2, 0x53, 0x66, 0xfa, 0xa9, 0x01, ++ 0x1c, 0x9c, 0xaf, 0xa3, 0xe2, 0x9d, 0x9b, 0x10, ++ 0x0a, 0xf6, 0x73, 0xe8, }, ++}}; ++ ++static const struct hash_testvec blakes2s_224_tv_template[] = {{ ++ .plaintext = blake2_ordered_sequence, ++ .psize = 1, ++ .digest = (u8[]){ 0x61, 0xb9, 0x4e, 0xc9, 0x46, 0x22, 0xa3, 0x91, ++ 0xd2, 0xae, 0x42, 0xe6, 0x45, 0x6c, 0x90, 0x12, ++ 0xd5, 0x80, 0x07, 0x97, 0xb8, 0x86, 0x5a, 0xfc, ++ 0x48, 0x21, 0x97, 0xbb, }, ++}, { ++ .plaintext = blake2_ordered_sequence, ++ .psize = 247, ++ .digest = (u8[]){ 0x9e, 0xda, 0xc7, 0x20, 0x2c, 0xd8, 0x48, 0x2e, ++ 0x31, 0x94, 0xab, 0x46, 0x6d, 0x94, 0xd8, 0xb4, ++ 0x69, 0xcd, 0xae, 0x19, 0x6d, 0x9e, 0x41, 0xcc, ++ 0x2b, 0xa4, 0xd5, 0xf6, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .digest = (u8[]){ 0x32, 0xc0, 0xac, 0xf4, 0x3b, 0xd3, 0x07, 0x9f, ++ 0xbe, 0xfb, 0xfa, 0x4d, 0x6b, 0x4e, 0x56, 0xb3, ++ 0xaa, 0xd3, 0x27, 0xf6, 0x14, 0xbf, 0xb9, 0x32, ++ 0xa7, 0x19, 0xfc, 0xb8, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .plaintext = blake2_ordered_sequence, ++ .psize = 7, ++ .digest = (u8[]){ 0x73, 0xad, 0x5e, 0x6d, 0xb9, 0x02, 0x8e, 0x76, ++ 0xf2, 0x66, 0x42, 0x4b, 0x4c, 0xfa, 0x1f, 0xe6, ++ 0x2e, 0x56, 0x40, 0xe5, 0xa2, 0xb0, 0x3c, 0xe8, ++ 0x7b, 0x45, 0xfe, 0x05, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 15, ++ .digest = (u8[]){ 0x16, 0x60, 0xfb, 0x92, 0x54, 0xb3, 0x6e, 0x36, ++ 0x81, 0xf4, 0x16, 0x41, 0xc3, 0x3d, 0xd3, 0x43, ++ 0x84, 0xed, 0x10, 0x6f, 0x65, 0x80, 0x7a, 0x3e, ++ 0x25, 0xab, 0xc5, 0x02, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 64, ++ .digest = (u8[]){ 0xca, 0xaa, 0x39, 0x67, 0x9c, 0xf7, 0x6b, 0xc7, ++ 0xb6, 0x82, 0xca, 0x0e, 0x65, 0x36, 0x5b, 0x7c, ++ 0x24, 0x00, 0xfa, 0x5f, 0xda, 0x06, 0x91, 0x93, ++ 0x6a, 0x31, 0x83, 0xb5, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .plaintext = blake2_ordered_sequence, ++ .psize = 256, ++ .digest = (u8[]){ 0x90, 0x02, 0x26, 0xb5, 0x06, 0x9c, 0x36, 0x86, ++ 0x94, 0x91, 0x90, 0x1e, 0x7d, 0x2a, 0x71, 0xb2, ++ 0x48, 0xb5, 0xe8, 0x16, 0xfd, 0x64, 0x33, 0x45, ++ 0xb3, 0xd7, 0xec, 0xcc, }, ++}}; ++ ++static const struct hash_testvec blakes2s_256_tv_template[] = {{ ++ .plaintext = blake2_ordered_sequence, ++ .psize = 15, ++ .digest = (u8[]){ 0xd9, 0x7c, 0x82, 0x8d, 0x81, 0x82, 0xa7, 0x21, ++ 0x80, 0xa0, 0x6a, 0x78, 0x26, 0x83, 0x30, 0x67, ++ 0x3f, 0x7c, 0x4e, 0x06, 0x35, 0x94, 0x7c, 0x04, ++ 0xc0, 0x23, 0x23, 0xfd, 0x45, 0xc0, 0xa5, 0x2d, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .digest = (u8[]){ 0x48, 0xa8, 0x99, 0x7d, 0xa4, 0x07, 0x87, 0x6b, ++ 0x3d, 0x79, 0xc0, 0xd9, 0x23, 0x25, 0xad, 0x3b, ++ 0x89, 0xcb, 0xb7, 0x54, 0xd8, 0x6a, 0xb7, 0x1a, ++ 0xee, 0x04, 0x7a, 0xd3, 0x45, 0xfd, 0x2c, 0x49, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .plaintext = blake2_ordered_sequence, ++ .psize = 1, ++ .digest = (u8[]){ 0x22, 0x27, 0xae, 0xaa, 0x6e, 0x81, 0x56, 0x03, ++ 0xa7, 0xe3, 0xa1, 0x18, 0xa5, 0x9a, 0x2c, 0x18, ++ 0xf4, 0x63, 0xbc, 0x16, 0x70, 0xf1, 0xe7, 0x4b, ++ 0x00, 0x6d, 0x66, 0x16, 0xae, 0x9e, 0x74, 0x4e, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 7, ++ .digest = (u8[]){ 0x58, 0x5d, 0xa8, 0x60, 0x1c, 0xa4, 0xd8, 0x03, ++ 0x86, 0x86, 0x84, 0x64, 0xd7, 0xa0, 0x8e, 0x15, ++ 0x2f, 0x05, 0xa2, 0x1b, 0xbc, 0xef, 0x7a, 0x34, ++ 0xb3, 0xc5, 0xbc, 0x4b, 0xf0, 0x32, 0xeb, 0x12, }, ++}, { ++ .ksize = 32, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 64, ++ .digest = (u8[]){ 0x89, 0x75, 0xb0, 0x57, 0x7f, 0xd3, 0x55, 0x66, ++ 0xd7, 0x50, 0xb3, 0x62, 0xb0, 0x89, 0x7a, 0x26, ++ 0xc3, 0x99, 0x13, 0x6d, 0xf0, 0x7b, 0xab, 0xab, ++ 0xbd, 0xe6, 0x20, 0x3f, 0xf2, 0x95, 0x4e, 0xd4, }, ++}, { ++ .ksize = 1, ++ .key = "B", ++ .plaintext = blake2_ordered_sequence, ++ .psize = 247, ++ .digest = (u8[]){ 0x2e, 0x74, 0x1c, 0x1d, 0x03, 0xf4, 0x9d, 0x84, ++ 0x6f, 0xfc, 0x86, 0x32, 0x92, 0x49, 0x7e, 0x66, ++ 0xd7, 0xc3, 0x10, 0x88, 0xfe, 0x28, 0xb3, 0xe0, ++ 0xbf, 0x50, 0x75, 0xad, 0x8e, 0xa4, 0xe6, 0xb2, }, ++}, { ++ .ksize = 16, ++ .key = blake2_ordered_sequence, ++ .plaintext = blake2_ordered_sequence, ++ .psize = 256, ++ .digest = (u8[]){ 0xb9, 0xd2, 0x81, 0x0e, 0x3a, 0xb1, 0x62, 0x9b, ++ 0xad, 0x44, 0x05, 0xf4, 0x92, 0x2e, 0x99, 0xc1, ++ 0x4a, 0x47, 0xbb, 0x5b, 0x6f, 0xb2, 0x96, 0xed, ++ 0xd5, 0x06, 0xb5, 0x3a, 0x7c, 0x7a, 0x65, 0x1d, }, ++}}; ++ + #endif /* _CRYPTO_TESTMGR_H */ diff --git a/target/linux/generic/backport-5.4/080-wireguard-0023-crypto-blake2s-implement-generic-shash-driver.patch b/target/linux/generic/backport-5.4/080-wireguard-0023-crypto-blake2s-implement-generic-shash-driver.patch new file mode 100644 index 0000000000..4116973631 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0023-crypto-blake2s-implement-generic-shash-driver.patch @@ -0,0 +1,245 @@ +From af5b936f5e17306da571f703bdef1f011a602b57 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:30 +0100 +Subject: [PATCH 023/124] crypto: blake2s - implement generic shash driver + +commit 7f9b0880925f1f9d7d59504ea0892d2ae9cfc233 upstream. + +Wire up our newly added Blake2s implementation via the shash API. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/Kconfig | 18 ++++ + crypto/Makefile | 1 + + crypto/blake2s_generic.c | 171 ++++++++++++++++++++++++++++++ + include/crypto/internal/blake2s.h | 5 + + 4 files changed, 195 insertions(+) + create mode 100644 crypto/blake2s_generic.c + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -639,6 +639,24 @@ config CRYPTO_XXHASH + xxHash non-cryptographic hash algorithm. Extremely fast, working at + speeds close to RAM limits. + ++config CRYPTO_BLAKE2S ++ tristate "BLAKE2s digest algorithm" ++ select CRYPTO_LIB_BLAKE2S_GENERIC ++ select CRYPTO_HASH ++ help ++ Implementation of cryptographic hash function BLAKE2s ++ optimized for 8-32bit platforms and can produce digests of any size ++ between 1 to 32. The keyed hash is also implemented. ++ ++ This module provides the following algorithms: ++ ++ - blake2s-128 ++ - blake2s-160 ++ - blake2s-224 ++ - blake2s-256 ++ ++ See https://blake2.net for further information. ++ + config CRYPTO_CRCT10DIF + tristate "CRCT10DIF algorithm" + select CRYPTO_HASH +--- a/crypto/Makefile ++++ b/crypto/Makefile +@@ -74,6 +74,7 @@ obj-$(CONFIG_CRYPTO_STREEBOG) += streebo + obj-$(CONFIG_CRYPTO_WP512) += wp512.o + CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149 + obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o ++obj-$(CONFIG_CRYPTO_BLAKE2S) += blake2s_generic.o + obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o + obj-$(CONFIG_CRYPTO_ECB) += ecb.o + obj-$(CONFIG_CRYPTO_CBC) += cbc.o +--- /dev/null ++++ b/crypto/blake2s_generic.c +@@ -0,0 +1,171 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include ++#include ++#include ++ ++#include ++#include ++#include ++#include ++ ++static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key, ++ unsigned int keylen) ++{ ++ struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); ++ ++ if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) { ++ crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); ++ return -EINVAL; ++ } ++ ++ memcpy(tctx->key, key, keylen); ++ tctx->keylen = keylen; ++ ++ return 0; ++} ++ ++static int crypto_blake2s_init(struct shash_desc *desc) ++{ ++ struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); ++ struct blake2s_state *state = shash_desc_ctx(desc); ++ const int outlen = crypto_shash_digestsize(desc->tfm); ++ ++ if (tctx->keylen) ++ blake2s_init_key(state, outlen, tctx->key, tctx->keylen); ++ else ++ blake2s_init(state, outlen); ++ ++ return 0; ++} ++ ++static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, ++ unsigned int inlen) ++{ ++ struct blake2s_state *state = shash_desc_ctx(desc); ++ const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; ++ ++ if (unlikely(!inlen)) ++ return 0; ++ if (inlen > fill) { ++ memcpy(state->buf + state->buflen, in, fill); ++ blake2s_compress_generic(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); ++ state->buflen = 0; ++ in += fill; ++ inlen -= fill; ++ } ++ if (inlen > BLAKE2S_BLOCK_SIZE) { ++ const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); ++ /* Hash one less (full) block than strictly possible */ ++ blake2s_compress_generic(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); ++ in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); ++ inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); ++ } ++ memcpy(state->buf + state->buflen, in, inlen); ++ state->buflen += inlen; ++ ++ return 0; ++} ++ ++static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) ++{ ++ struct blake2s_state *state = shash_desc_ctx(desc); ++ ++ blake2s_set_lastblock(state); ++ memset(state->buf + state->buflen, 0, ++ BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ ++ blake2s_compress_generic(state, state->buf, 1, state->buflen); ++ cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); ++ memcpy(out, state->h, state->outlen); ++ memzero_explicit(state, sizeof(*state)); ++ ++ return 0; ++} ++ ++static struct shash_alg blake2s_algs[] = {{ ++ .base.cra_name = "blake2s-128", ++ .base.cra_driver_name = "blake2s-128-generic", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_128_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}, { ++ .base.cra_name = "blake2s-160", ++ .base.cra_driver_name = "blake2s-160-generic", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_160_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}, { ++ .base.cra_name = "blake2s-224", ++ .base.cra_driver_name = "blake2s-224-generic", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_224_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}, { ++ .base.cra_name = "blake2s-256", ++ .base.cra_driver_name = "blake2s-256-generic", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_256_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}}; ++ ++static int __init blake2s_mod_init(void) ++{ ++ return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); ++} ++ ++static void __exit blake2s_mod_exit(void) ++{ ++ crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); ++} ++ ++subsys_initcall(blake2s_mod_init); ++module_exit(blake2s_mod_exit); ++ ++MODULE_ALIAS_CRYPTO("blake2s-128"); ++MODULE_ALIAS_CRYPTO("blake2s-128-generic"); ++MODULE_ALIAS_CRYPTO("blake2s-160"); ++MODULE_ALIAS_CRYPTO("blake2s-160-generic"); ++MODULE_ALIAS_CRYPTO("blake2s-224"); ++MODULE_ALIAS_CRYPTO("blake2s-224-generic"); ++MODULE_ALIAS_CRYPTO("blake2s-256"); ++MODULE_ALIAS_CRYPTO("blake2s-256-generic"); ++MODULE_LICENSE("GPL v2"); +--- a/include/crypto/internal/blake2s.h ++++ b/include/crypto/internal/blake2s.h +@@ -5,6 +5,11 @@ + + #include + ++struct blake2s_tfm_ctx { ++ u8 key[BLAKE2S_KEY_SIZE]; ++ unsigned int keylen; ++}; ++ + void blake2s_compress_generic(struct blake2s_state *state,const u8 *block, + size_t nblocks, const u32 inc); + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0024-crypto-blake2s-x86_64-SIMD-implementation.patch b/target/linux/generic/backport-5.4/080-wireguard-0024-crypto-blake2s-x86_64-SIMD-implementation.patch new file mode 100644 index 0000000000..80bf831f81 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0024-crypto-blake2s-x86_64-SIMD-implementation.patch @@ -0,0 +1,557 @@ +From 7960239adcaf7b56b081426ea3aa0ebf17398375 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:31 +0100 +Subject: [PATCH 024/124] crypto: blake2s - x86_64 SIMD implementation + +commit ed0356eda153f6a95649e11feb7b07083caf9e20 upstream. + +These implementations from Samuel Neves support AVX and AVX-512VL. +Originally this used AVX-512F, but Skylake thermal throttling made +AVX-512VL more attractive and possible to do with negligable difference. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Samuel Neves +Co-developed-by: Samuel Neves +[ardb: move to arch/x86/crypto, wire into lib/crypto framework] +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/Makefile | 2 + + arch/x86/crypto/blake2s-core.S | 258 +++++++++++++++++++++++++++++++++ + arch/x86/crypto/blake2s-glue.c | 233 +++++++++++++++++++++++++++++ + crypto/Kconfig | 6 + + 4 files changed, 499 insertions(+) + create mode 100644 arch/x86/crypto/blake2s-core.S + create mode 100644 arch/x86/crypto/blake2s-glue.c + +--- a/arch/x86/crypto/Makefile ++++ b/arch/x86/crypto/Makefile +@@ -48,6 +48,7 @@ ifeq ($(avx_supported),yes) + obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o + obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o + obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o ++ obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o + endif + + # These modules require assembler to support AVX2. +@@ -70,6 +71,7 @@ serpent-sse2-x86_64-y := serpent-sse2-x8 + aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o + + nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o ++blake2s-x86_64-y := blake2s-core.o blake2s-glue.o + + ifeq ($(avx_supported),yes) + camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \ +--- /dev/null ++++ b/arch/x86/crypto/blake2s-core.S +@@ -0,0 +1,258 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * Copyright (C) 2017-2019 Samuel Neves . All Rights Reserved. ++ */ ++ ++#include ++ ++.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32 ++.align 32 ++IV: .octa 0xA54FF53A3C6EF372BB67AE856A09E667 ++ .octa 0x5BE0CD191F83D9AB9B05688C510E527F ++.section .rodata.cst16.ROT16, "aM", @progbits, 16 ++.align 16 ++ROT16: .octa 0x0D0C0F0E09080B0A0504070601000302 ++.section .rodata.cst16.ROR328, "aM", @progbits, 16 ++.align 16 ++ROR328: .octa 0x0C0F0E0D080B0A090407060500030201 ++.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160 ++.align 64 ++SIGMA: ++.byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13 ++.byte 14, 4, 9, 13, 10, 8, 15, 6, 5, 1, 0, 11, 3, 12, 2, 7 ++.byte 11, 12, 5, 15, 8, 0, 2, 13, 9, 10, 3, 7, 4, 14, 6, 1 ++.byte 7, 3, 13, 11, 9, 1, 12, 14, 15, 2, 5, 4, 8, 6, 10, 0 ++.byte 9, 5, 2, 10, 0, 7, 4, 15, 3, 14, 11, 6, 13, 1, 12, 8 ++.byte 2, 6, 0, 8, 12, 10, 11, 3, 1, 4, 7, 15, 9, 13, 5, 14 ++.byte 12, 1, 14, 4, 5, 15, 13, 10, 8, 0, 6, 9, 11, 7, 3, 2 ++.byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6 ++.byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4 ++.byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12 ++#ifdef CONFIG_AS_AVX512 ++.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640 ++.align 64 ++SIGMA2: ++.long 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13 ++.long 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7 ++.long 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9 ++.long 11, 10, 7, 0, 8, 15, 1, 13, 3, 6, 2, 12, 4, 14, 9, 5 ++.long 4, 10, 9, 14, 15, 0, 11, 8, 1, 7, 3, 13, 2, 5, 6, 12 ++.long 2, 11, 4, 15, 14, 3, 10, 8, 13, 6, 5, 7, 0, 12, 1, 9 ++.long 4, 8, 15, 9, 14, 11, 13, 5, 3, 2, 1, 12, 6, 10, 7, 0 ++.long 6, 13, 0, 14, 12, 2, 1, 11, 15, 4, 5, 8, 7, 9, 3, 10 ++.long 15, 5, 4, 13, 10, 7, 3, 11, 12, 2, 0, 6, 9, 8, 1, 14 ++.long 8, 7, 14, 11, 13, 15, 0, 12, 10, 4, 5, 6, 3, 2, 1, 9 ++#endif /* CONFIG_AS_AVX512 */ ++ ++.text ++#ifdef CONFIG_AS_SSSE3 ++ENTRY(blake2s_compress_ssse3) ++ testq %rdx,%rdx ++ je .Lendofloop ++ movdqu (%rdi),%xmm0 ++ movdqu 0x10(%rdi),%xmm1 ++ movdqa ROT16(%rip),%xmm12 ++ movdqa ROR328(%rip),%xmm13 ++ movdqu 0x20(%rdi),%xmm14 ++ movq %rcx,%xmm15 ++ leaq SIGMA+0xa0(%rip),%r8 ++ jmp .Lbeginofloop ++ .align 32 ++.Lbeginofloop: ++ movdqa %xmm0,%xmm10 ++ movdqa %xmm1,%xmm11 ++ paddq %xmm15,%xmm14 ++ movdqa IV(%rip),%xmm2 ++ movdqa %xmm14,%xmm3 ++ pxor IV+0x10(%rip),%xmm3 ++ leaq SIGMA(%rip),%rcx ++.Lroundloop: ++ movzbl (%rcx),%eax ++ movd (%rsi,%rax,4),%xmm4 ++ movzbl 0x1(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm5 ++ movzbl 0x2(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm6 ++ movzbl 0x3(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm7 ++ punpckldq %xmm5,%xmm4 ++ punpckldq %xmm7,%xmm6 ++ punpcklqdq %xmm6,%xmm4 ++ paddd %xmm4,%xmm0 ++ paddd %xmm1,%xmm0 ++ pxor %xmm0,%xmm3 ++ pshufb %xmm12,%xmm3 ++ paddd %xmm3,%xmm2 ++ pxor %xmm2,%xmm1 ++ movdqa %xmm1,%xmm8 ++ psrld $0xc,%xmm1 ++ pslld $0x14,%xmm8 ++ por %xmm8,%xmm1 ++ movzbl 0x4(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm5 ++ movzbl 0x5(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm6 ++ movzbl 0x6(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm7 ++ movzbl 0x7(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm4 ++ punpckldq %xmm6,%xmm5 ++ punpckldq %xmm4,%xmm7 ++ punpcklqdq %xmm7,%xmm5 ++ paddd %xmm5,%xmm0 ++ paddd %xmm1,%xmm0 ++ pxor %xmm0,%xmm3 ++ pshufb %xmm13,%xmm3 ++ paddd %xmm3,%xmm2 ++ pxor %xmm2,%xmm1 ++ movdqa %xmm1,%xmm8 ++ psrld $0x7,%xmm1 ++ pslld $0x19,%xmm8 ++ por %xmm8,%xmm1 ++ pshufd $0x93,%xmm0,%xmm0 ++ pshufd $0x4e,%xmm3,%xmm3 ++ pshufd $0x39,%xmm2,%xmm2 ++ movzbl 0x8(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm6 ++ movzbl 0x9(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm7 ++ movzbl 0xa(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm4 ++ movzbl 0xb(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm5 ++ punpckldq %xmm7,%xmm6 ++ punpckldq %xmm5,%xmm4 ++ punpcklqdq %xmm4,%xmm6 ++ paddd %xmm6,%xmm0 ++ paddd %xmm1,%xmm0 ++ pxor %xmm0,%xmm3 ++ pshufb %xmm12,%xmm3 ++ paddd %xmm3,%xmm2 ++ pxor %xmm2,%xmm1 ++ movdqa %xmm1,%xmm8 ++ psrld $0xc,%xmm1 ++ pslld $0x14,%xmm8 ++ por %xmm8,%xmm1 ++ movzbl 0xc(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm7 ++ movzbl 0xd(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm4 ++ movzbl 0xe(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm5 ++ movzbl 0xf(%rcx),%eax ++ movd (%rsi,%rax,4),%xmm6 ++ punpckldq %xmm4,%xmm7 ++ punpckldq %xmm6,%xmm5 ++ punpcklqdq %xmm5,%xmm7 ++ paddd %xmm7,%xmm0 ++ paddd %xmm1,%xmm0 ++ pxor %xmm0,%xmm3 ++ pshufb %xmm13,%xmm3 ++ paddd %xmm3,%xmm2 ++ pxor %xmm2,%xmm1 ++ movdqa %xmm1,%xmm8 ++ psrld $0x7,%xmm1 ++ pslld $0x19,%xmm8 ++ por %xmm8,%xmm1 ++ pshufd $0x39,%xmm0,%xmm0 ++ pshufd $0x4e,%xmm3,%xmm3 ++ pshufd $0x93,%xmm2,%xmm2 ++ addq $0x10,%rcx ++ cmpq %r8,%rcx ++ jnz .Lroundloop ++ pxor %xmm2,%xmm0 ++ pxor %xmm3,%xmm1 ++ pxor %xmm10,%xmm0 ++ pxor %xmm11,%xmm1 ++ addq $0x40,%rsi ++ decq %rdx ++ jnz .Lbeginofloop ++ movdqu %xmm0,(%rdi) ++ movdqu %xmm1,0x10(%rdi) ++ movdqu %xmm14,0x20(%rdi) ++.Lendofloop: ++ ret ++ENDPROC(blake2s_compress_ssse3) ++#endif /* CONFIG_AS_SSSE3 */ ++ ++#ifdef CONFIG_AS_AVX512 ++ENTRY(blake2s_compress_avx512) ++ vmovdqu (%rdi),%xmm0 ++ vmovdqu 0x10(%rdi),%xmm1 ++ vmovdqu 0x20(%rdi),%xmm4 ++ vmovq %rcx,%xmm5 ++ vmovdqa IV(%rip),%xmm14 ++ vmovdqa IV+16(%rip),%xmm15 ++ jmp .Lblake2s_compress_avx512_mainloop ++.align 32 ++.Lblake2s_compress_avx512_mainloop: ++ vmovdqa %xmm0,%xmm10 ++ vmovdqa %xmm1,%xmm11 ++ vpaddq %xmm5,%xmm4,%xmm4 ++ vmovdqa %xmm14,%xmm2 ++ vpxor %xmm15,%xmm4,%xmm3 ++ vmovdqu (%rsi),%ymm6 ++ vmovdqu 0x20(%rsi),%ymm7 ++ addq $0x40,%rsi ++ leaq SIGMA2(%rip),%rax ++ movb $0xa,%cl ++.Lblake2s_compress_avx512_roundloop: ++ addq $0x40,%rax ++ vmovdqa -0x40(%rax),%ymm8 ++ vmovdqa -0x20(%rax),%ymm9 ++ vpermi2d %ymm7,%ymm6,%ymm8 ++ vpermi2d %ymm7,%ymm6,%ymm9 ++ vmovdqa %ymm8,%ymm6 ++ vmovdqa %ymm9,%ymm7 ++ vpaddd %xmm8,%xmm0,%xmm0 ++ vpaddd %xmm1,%xmm0,%xmm0 ++ vpxor %xmm0,%xmm3,%xmm3 ++ vprord $0x10,%xmm3,%xmm3 ++ vpaddd %xmm3,%xmm2,%xmm2 ++ vpxor %xmm2,%xmm1,%xmm1 ++ vprord $0xc,%xmm1,%xmm1 ++ vextracti128 $0x1,%ymm8,%xmm8 ++ vpaddd %xmm8,%xmm0,%xmm0 ++ vpaddd %xmm1,%xmm0,%xmm0 ++ vpxor %xmm0,%xmm3,%xmm3 ++ vprord $0x8,%xmm3,%xmm3 ++ vpaddd %xmm3,%xmm2,%xmm2 ++ vpxor %xmm2,%xmm1,%xmm1 ++ vprord $0x7,%xmm1,%xmm1 ++ vpshufd $0x93,%xmm0,%xmm0 ++ vpshufd $0x4e,%xmm3,%xmm3 ++ vpshufd $0x39,%xmm2,%xmm2 ++ vpaddd %xmm9,%xmm0,%xmm0 ++ vpaddd %xmm1,%xmm0,%xmm0 ++ vpxor %xmm0,%xmm3,%xmm3 ++ vprord $0x10,%xmm3,%xmm3 ++ vpaddd %xmm3,%xmm2,%xmm2 ++ vpxor %xmm2,%xmm1,%xmm1 ++ vprord $0xc,%xmm1,%xmm1 ++ vextracti128 $0x1,%ymm9,%xmm9 ++ vpaddd %xmm9,%xmm0,%xmm0 ++ vpaddd %xmm1,%xmm0,%xmm0 ++ vpxor %xmm0,%xmm3,%xmm3 ++ vprord $0x8,%xmm3,%xmm3 ++ vpaddd %xmm3,%xmm2,%xmm2 ++ vpxor %xmm2,%xmm1,%xmm1 ++ vprord $0x7,%xmm1,%xmm1 ++ vpshufd $0x39,%xmm0,%xmm0 ++ vpshufd $0x4e,%xmm3,%xmm3 ++ vpshufd $0x93,%xmm2,%xmm2 ++ decb %cl ++ jne .Lblake2s_compress_avx512_roundloop ++ vpxor %xmm10,%xmm0,%xmm0 ++ vpxor %xmm11,%xmm1,%xmm1 ++ vpxor %xmm2,%xmm0,%xmm0 ++ vpxor %xmm3,%xmm1,%xmm1 ++ decq %rdx ++ jne .Lblake2s_compress_avx512_mainloop ++ vmovdqu %xmm0,(%rdi) ++ vmovdqu %xmm1,0x10(%rdi) ++ vmovdqu %xmm4,0x20(%rdi) ++ vzeroupper ++ retq ++ENDPROC(blake2s_compress_avx512) ++#endif /* CONFIG_AS_AVX512 */ +--- /dev/null ++++ b/arch/x86/crypto/blake2s-glue.c +@@ -0,0 +1,233 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include ++#include ++#include ++ ++#include ++#include ++#include ++#include ++ ++#include ++#include ++#include ++#include ++ ++asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state, ++ const u8 *block, const size_t nblocks, ++ const u32 inc); ++asmlinkage void blake2s_compress_avx512(struct blake2s_state *state, ++ const u8 *block, const size_t nblocks, ++ const u32 inc); ++ ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512); ++ ++void blake2s_compress_arch(struct blake2s_state *state, ++ const u8 *block, size_t nblocks, ++ const u32 inc) ++{ ++ /* SIMD disables preemption, so relax after processing each page. */ ++ BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); ++ ++ if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { ++ blake2s_compress_generic(state, block, nblocks, inc); ++ return; ++ } ++ ++ for (;;) { ++ const size_t blocks = min_t(size_t, nblocks, ++ PAGE_SIZE / BLAKE2S_BLOCK_SIZE); ++ ++ kernel_fpu_begin(); ++ if (IS_ENABLED(CONFIG_AS_AVX512) && ++ static_branch_likely(&blake2s_use_avx512)) ++ blake2s_compress_avx512(state, block, blocks, inc); ++ else ++ blake2s_compress_ssse3(state, block, blocks, inc); ++ kernel_fpu_end(); ++ ++ nblocks -= blocks; ++ if (!nblocks) ++ break; ++ block += blocks * BLAKE2S_BLOCK_SIZE; ++ } ++} ++EXPORT_SYMBOL(blake2s_compress_arch); ++ ++static int crypto_blake2s_setkey(struct crypto_shash *tfm, const u8 *key, ++ unsigned int keylen) ++{ ++ struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(tfm); ++ ++ if (keylen == 0 || keylen > BLAKE2S_KEY_SIZE) { ++ crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); ++ return -EINVAL; ++ } ++ ++ memcpy(tctx->key, key, keylen); ++ tctx->keylen = keylen; ++ ++ return 0; ++} ++ ++static int crypto_blake2s_init(struct shash_desc *desc) ++{ ++ struct blake2s_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); ++ struct blake2s_state *state = shash_desc_ctx(desc); ++ const int outlen = crypto_shash_digestsize(desc->tfm); ++ ++ if (tctx->keylen) ++ blake2s_init_key(state, outlen, tctx->key, tctx->keylen); ++ else ++ blake2s_init(state, outlen); ++ ++ return 0; ++} ++ ++static int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, ++ unsigned int inlen) ++{ ++ struct blake2s_state *state = shash_desc_ctx(desc); ++ const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; ++ ++ if (unlikely(!inlen)) ++ return 0; ++ if (inlen > fill) { ++ memcpy(state->buf + state->buflen, in, fill); ++ blake2s_compress_arch(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); ++ state->buflen = 0; ++ in += fill; ++ inlen -= fill; ++ } ++ if (inlen > BLAKE2S_BLOCK_SIZE) { ++ const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); ++ /* Hash one less (full) block than strictly possible */ ++ blake2s_compress_arch(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); ++ in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); ++ inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); ++ } ++ memcpy(state->buf + state->buflen, in, inlen); ++ state->buflen += inlen; ++ ++ return 0; ++} ++ ++static int crypto_blake2s_final(struct shash_desc *desc, u8 *out) ++{ ++ struct blake2s_state *state = shash_desc_ctx(desc); ++ ++ blake2s_set_lastblock(state); ++ memset(state->buf + state->buflen, 0, ++ BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ ++ blake2s_compress_arch(state, state->buf, 1, state->buflen); ++ cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); ++ memcpy(out, state->h, state->outlen); ++ memzero_explicit(state, sizeof(*state)); ++ ++ return 0; ++} ++ ++static struct shash_alg blake2s_algs[] = {{ ++ .base.cra_name = "blake2s-128", ++ .base.cra_driver_name = "blake2s-128-x86", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_128_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}, { ++ .base.cra_name = "blake2s-160", ++ .base.cra_driver_name = "blake2s-160-x86", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_160_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}, { ++ .base.cra_name = "blake2s-224", ++ .base.cra_driver_name = "blake2s-224-x86", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_224_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}, { ++ .base.cra_name = "blake2s-256", ++ .base.cra_driver_name = "blake2s-256-x86", ++ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, ++ .base.cra_ctxsize = sizeof(struct blake2s_tfm_ctx), ++ .base.cra_priority = 200, ++ .base.cra_blocksize = BLAKE2S_BLOCK_SIZE, ++ .base.cra_module = THIS_MODULE, ++ ++ .digestsize = BLAKE2S_256_HASH_SIZE, ++ .setkey = crypto_blake2s_setkey, ++ .init = crypto_blake2s_init, ++ .update = crypto_blake2s_update, ++ .final = crypto_blake2s_final, ++ .descsize = sizeof(struct blake2s_state), ++}}; ++ ++static int __init blake2s_mod_init(void) ++{ ++ if (!boot_cpu_has(X86_FEATURE_SSSE3)) ++ return 0; ++ ++ static_branch_enable(&blake2s_use_ssse3); ++ ++ if (IS_ENABLED(CONFIG_AS_AVX512) && ++ boot_cpu_has(X86_FEATURE_AVX) && ++ boot_cpu_has(X86_FEATURE_AVX2) && ++ boot_cpu_has(X86_FEATURE_AVX512F) && ++ boot_cpu_has(X86_FEATURE_AVX512VL) && ++ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | ++ XFEATURE_MASK_AVX512, NULL)) ++ static_branch_enable(&blake2s_use_avx512); ++ ++ return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); ++} ++ ++static void __exit blake2s_mod_exit(void) ++{ ++ if (boot_cpu_has(X86_FEATURE_SSSE3)) ++ crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); ++} ++ ++module_init(blake2s_mod_init); ++module_exit(blake2s_mod_exit); ++ ++MODULE_ALIAS_CRYPTO("blake2s-128"); ++MODULE_ALIAS_CRYPTO("blake2s-128-x86"); ++MODULE_ALIAS_CRYPTO("blake2s-160"); ++MODULE_ALIAS_CRYPTO("blake2s-160-x86"); ++MODULE_ALIAS_CRYPTO("blake2s-224"); ++MODULE_ALIAS_CRYPTO("blake2s-224-x86"); ++MODULE_ALIAS_CRYPTO("blake2s-256"); ++MODULE_ALIAS_CRYPTO("blake2s-256-x86"); ++MODULE_LICENSE("GPL v2"); +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -657,6 +657,12 @@ config CRYPTO_BLAKE2S + + See https://blake2.net for further information. + ++config CRYPTO_BLAKE2S_X86 ++ tristate "BLAKE2s digest algorithm (x86 accelerated version)" ++ depends on X86 && 64BIT ++ select CRYPTO_LIB_BLAKE2S_GENERIC ++ select CRYPTO_ARCH_HAVE_LIB_BLAKE2S ++ + config CRYPTO_CRCT10DIF + tristate "CRCT10DIF algorithm" + select CRYPTO_HASH diff --git a/target/linux/generic/backport-5.4/080-wireguard-0025-crypto-curve25519-generic-C-library-implementations.patch b/target/linux/generic/backport-5.4/080-wireguard-0025-crypto-curve25519-generic-C-library-implementations.patch new file mode 100644 index 0000000000..87d4d41c96 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0025-crypto-curve25519-generic-C-library-implementations.patch @@ -0,0 +1,1850 @@ +From feadb4076186623fb4ca14d8f70759637c4df1f2 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:32 +0100 +Subject: [PATCH 025/124] crypto: curve25519 - generic C library + implementations + +commit 0ed42a6f431e930b2e8fae21955406e09fe75d70 upstream. + +This contains two formally verified C implementations of the Curve25519 +scalar multiplication function, one for 32-bit systems, and one for +64-bit systems whose compiler supports efficient 128-bit integer types. +Not only are these implementations formally verified, but they are also +the fastest available C implementations. They have been modified to be +friendly to kernel space and to be generally less horrendous looking, +but still an effort has been made to retain their formally verified +characteristic, and so the C might look slightly unidiomatic. + +The 64-bit version comes from HACL*: https://github.com/project-everest/hacl-star +The 32-bit version comes from Fiat: https://github.com/mit-plv/fiat-crypto + +Information: https://cr.yp.to/ecdh.html + +Signed-off-by: Jason A. Donenfeld +[ardb: - move from lib/zinc to lib/crypto + - replace .c #includes with Kconfig based object selection + - drop simd handling and simplify support for per-arch versions ] +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + include/crypto/curve25519.h | 71 +++ + lib/crypto/Kconfig | 25 + + lib/crypto/Makefile | 5 + + lib/crypto/curve25519-fiat32.c | 864 +++++++++++++++++++++++++++++++++ + lib/crypto/curve25519-hacl64.c | 788 ++++++++++++++++++++++++++++++ + lib/crypto/curve25519.c | 25 + + 6 files changed, 1778 insertions(+) + create mode 100644 include/crypto/curve25519.h + create mode 100644 lib/crypto/curve25519-fiat32.c + create mode 100644 lib/crypto/curve25519-hacl64.c + create mode 100644 lib/crypto/curve25519.c + +--- /dev/null ++++ b/include/crypto/curve25519.h +@@ -0,0 +1,71 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef CURVE25519_H ++#define CURVE25519_H ++ ++#include // For crypto_memneq. ++#include ++#include ++ ++enum curve25519_lengths { ++ CURVE25519_KEY_SIZE = 32 ++}; ++ ++extern const u8 curve25519_null_point[]; ++extern const u8 curve25519_base_point[]; ++ ++void curve25519_generic(u8 out[CURVE25519_KEY_SIZE], ++ const u8 scalar[CURVE25519_KEY_SIZE], ++ const u8 point[CURVE25519_KEY_SIZE]); ++ ++void curve25519_arch(u8 out[CURVE25519_KEY_SIZE], ++ const u8 scalar[CURVE25519_KEY_SIZE], ++ const u8 point[CURVE25519_KEY_SIZE]); ++ ++void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], ++ const u8 secret[CURVE25519_KEY_SIZE]); ++ ++static inline ++bool __must_check curve25519(u8 mypublic[CURVE25519_KEY_SIZE], ++ const u8 secret[CURVE25519_KEY_SIZE], ++ const u8 basepoint[CURVE25519_KEY_SIZE]) ++{ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) ++ curve25519_arch(mypublic, secret, basepoint); ++ else ++ curve25519_generic(mypublic, secret, basepoint); ++ return crypto_memneq(mypublic, curve25519_null_point, ++ CURVE25519_KEY_SIZE); ++} ++ ++static inline bool ++__must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE], ++ const u8 secret[CURVE25519_KEY_SIZE]) ++{ ++ if (unlikely(!crypto_memneq(secret, curve25519_null_point, ++ CURVE25519_KEY_SIZE))) ++ return false; ++ ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) ++ curve25519_base_arch(pub, secret); ++ else ++ curve25519_generic(pub, secret, curve25519_base_point); ++ return crypto_memneq(pub, curve25519_null_point, CURVE25519_KEY_SIZE); ++} ++ ++static inline void curve25519_clamp_secret(u8 secret[CURVE25519_KEY_SIZE]) ++{ ++ secret[0] &= 248; ++ secret[31] = (secret[31] & 127) | 64; ++} ++ ++static inline void curve25519_generate_secret(u8 secret[CURVE25519_KEY_SIZE]) ++{ ++ get_random_bytes_wait(secret, CURVE25519_KEY_SIZE); ++ curve25519_clamp_secret(secret); ++} ++ ++#endif /* CURVE25519_H */ +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -59,6 +59,31 @@ config CRYPTO_LIB_CHACHA + by either the generic implementation or an arch-specific one, if one + is available and enabled. + ++config CRYPTO_ARCH_HAVE_LIB_CURVE25519 ++ tristate ++ help ++ Declares whether the architecture provides an arch-specific ++ accelerated implementation of the Curve25519 library interface, ++ either builtin or as a module. ++ ++config CRYPTO_LIB_CURVE25519_GENERIC ++ tristate ++ help ++ This symbol can be depended upon by arch implementations of the ++ Curve25519 library interface that require the generic code as a ++ fallback, e.g., for SIMD implementations. If no arch specific ++ implementation is enabled, this implementation serves the users ++ of CRYPTO_LIB_CURVE25519. ++ ++config CRYPTO_LIB_CURVE25519 ++ tristate "Curve25519 scalar multiplication library" ++ depends on CRYPTO_ARCH_HAVE_LIB_CURVE25519 || !CRYPTO_ARCH_HAVE_LIB_CURVE25519 ++ select CRYPTO_LIB_CURVE25519_GENERIC if CRYPTO_ARCH_HAVE_LIB_CURVE25519=n ++ help ++ Enable the Curve25519 library interface. This interface may be ++ fulfilled by either the generic implementation or an arch-specific ++ one, if one is available and enabled. ++ + config CRYPTO_LIB_DES + tristate + +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -16,6 +16,11 @@ libblake2s-generic-y += blake2s-gener + obj-$(CONFIG_CRYPTO_LIB_BLAKE2S) += libblake2s.o + libblake2s-y += blake2s.o + ++obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC) += libcurve25519.o ++libcurve25519-y := curve25519-fiat32.o ++libcurve25519-$(CONFIG_ARCH_SUPPORTS_INT128) := curve25519-hacl64.o ++libcurve25519-y += curve25519.o ++ + obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o + libdes-y := des.o + +--- /dev/null ++++ b/lib/crypto/curve25519-fiat32.c +@@ -0,0 +1,864 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2016 The fiat-crypto Authors. ++ * Copyright (C) 2018-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is a machine-generated formally verified implementation of Curve25519 ++ * ECDH from: . Though originally ++ * machine generated, it has been tweaked to be suitable for use in the kernel. ++ * It is optimized for 32-bit machines and machines that cannot work efficiently ++ * with 128-bit integer types. ++ */ ++ ++#include ++#include ++#include ++ ++/* fe means field element. Here the field is \Z/(2^255-19). An element t, ++ * entries t[0]...t[9], represents the integer t[0]+2^26 t[1]+2^51 t[2]+2^77 ++ * t[3]+2^102 t[4]+...+2^230 t[9]. ++ * fe limbs are bounded by 1.125*2^26,1.125*2^25,1.125*2^26,1.125*2^25,etc. ++ * Multiplication and carrying produce fe from fe_loose. ++ */ ++typedef struct fe { u32 v[10]; } fe; ++ ++/* fe_loose limbs are bounded by 3.375*2^26,3.375*2^25,3.375*2^26,3.375*2^25,etc ++ * Addition and subtraction produce fe_loose from (fe, fe). ++ */ ++typedef struct fe_loose { u32 v[10]; } fe_loose; ++ ++static __always_inline void fe_frombytes_impl(u32 h[10], const u8 *s) ++{ ++ /* Ignores top bit of s. */ ++ u32 a0 = get_unaligned_le32(s); ++ u32 a1 = get_unaligned_le32(s+4); ++ u32 a2 = get_unaligned_le32(s+8); ++ u32 a3 = get_unaligned_le32(s+12); ++ u32 a4 = get_unaligned_le32(s+16); ++ u32 a5 = get_unaligned_le32(s+20); ++ u32 a6 = get_unaligned_le32(s+24); ++ u32 a7 = get_unaligned_le32(s+28); ++ h[0] = a0&((1<<26)-1); /* 26 used, 32-26 left. 26 */ ++ h[1] = (a0>>26) | ((a1&((1<<19)-1))<< 6); /* (32-26) + 19 = 6+19 = 25 */ ++ h[2] = (a1>>19) | ((a2&((1<<13)-1))<<13); /* (32-19) + 13 = 13+13 = 26 */ ++ h[3] = (a2>>13) | ((a3&((1<< 6)-1))<<19); /* (32-13) + 6 = 19+ 6 = 25 */ ++ h[4] = (a3>> 6); /* (32- 6) = 26 */ ++ h[5] = a4&((1<<25)-1); /* 25 */ ++ h[6] = (a4>>25) | ((a5&((1<<19)-1))<< 7); /* (32-25) + 19 = 7+19 = 26 */ ++ h[7] = (a5>>19) | ((a6&((1<<12)-1))<<13); /* (32-19) + 12 = 13+12 = 25 */ ++ h[8] = (a6>>12) | ((a7&((1<< 6)-1))<<20); /* (32-12) + 6 = 20+ 6 = 26 */ ++ h[9] = (a7>> 6)&((1<<25)-1); /* 25 */ ++} ++ ++static __always_inline void fe_frombytes(fe *h, const u8 *s) ++{ ++ fe_frombytes_impl(h->v, s); ++} ++ ++static __always_inline u8 /*bool*/ ++addcarryx_u25(u8 /*bool*/ c, u32 a, u32 b, u32 *low) ++{ ++ /* This function extracts 25 bits of result and 1 bit of carry ++ * (26 total), so a 32-bit intermediate is sufficient. ++ */ ++ u32 x = a + b + c; ++ *low = x & ((1 << 25) - 1); ++ return (x >> 25) & 1; ++} ++ ++static __always_inline u8 /*bool*/ ++addcarryx_u26(u8 /*bool*/ c, u32 a, u32 b, u32 *low) ++{ ++ /* This function extracts 26 bits of result and 1 bit of carry ++ * (27 total), so a 32-bit intermediate is sufficient. ++ */ ++ u32 x = a + b + c; ++ *low = x & ((1 << 26) - 1); ++ return (x >> 26) & 1; ++} ++ ++static __always_inline u8 /*bool*/ ++subborrow_u25(u8 /*bool*/ c, u32 a, u32 b, u32 *low) ++{ ++ /* This function extracts 25 bits of result and 1 bit of borrow ++ * (26 total), so a 32-bit intermediate is sufficient. ++ */ ++ u32 x = a - b - c; ++ *low = x & ((1 << 25) - 1); ++ return x >> 31; ++} ++ ++static __always_inline u8 /*bool*/ ++subborrow_u26(u8 /*bool*/ c, u32 a, u32 b, u32 *low) ++{ ++ /* This function extracts 26 bits of result and 1 bit of borrow ++ *(27 total), so a 32-bit intermediate is sufficient. ++ */ ++ u32 x = a - b - c; ++ *low = x & ((1 << 26) - 1); ++ return x >> 31; ++} ++ ++static __always_inline u32 cmovznz32(u32 t, u32 z, u32 nz) ++{ ++ t = -!!t; /* all set if nonzero, 0 if 0 */ ++ return (t&nz) | ((~t)&z); ++} ++ ++static __always_inline void fe_freeze(u32 out[10], const u32 in1[10]) ++{ ++ { const u32 x17 = in1[9]; ++ { const u32 x18 = in1[8]; ++ { const u32 x16 = in1[7]; ++ { const u32 x14 = in1[6]; ++ { const u32 x12 = in1[5]; ++ { const u32 x10 = in1[4]; ++ { const u32 x8 = in1[3]; ++ { const u32 x6 = in1[2]; ++ { const u32 x4 = in1[1]; ++ { const u32 x2 = in1[0]; ++ { u32 x20; u8/*bool*/ x21 = subborrow_u26(0x0, x2, 0x3ffffed, &x20); ++ { u32 x23; u8/*bool*/ x24 = subborrow_u25(x21, x4, 0x1ffffff, &x23); ++ { u32 x26; u8/*bool*/ x27 = subborrow_u26(x24, x6, 0x3ffffff, &x26); ++ { u32 x29; u8/*bool*/ x30 = subborrow_u25(x27, x8, 0x1ffffff, &x29); ++ { u32 x32; u8/*bool*/ x33 = subborrow_u26(x30, x10, 0x3ffffff, &x32); ++ { u32 x35; u8/*bool*/ x36 = subborrow_u25(x33, x12, 0x1ffffff, &x35); ++ { u32 x38; u8/*bool*/ x39 = subborrow_u26(x36, x14, 0x3ffffff, &x38); ++ { u32 x41; u8/*bool*/ x42 = subborrow_u25(x39, x16, 0x1ffffff, &x41); ++ { u32 x44; u8/*bool*/ x45 = subborrow_u26(x42, x18, 0x3ffffff, &x44); ++ { u32 x47; u8/*bool*/ x48 = subborrow_u25(x45, x17, 0x1ffffff, &x47); ++ { u32 x49 = cmovznz32(x48, 0x0, 0xffffffff); ++ { u32 x50 = (x49 & 0x3ffffed); ++ { u32 x52; u8/*bool*/ x53 = addcarryx_u26(0x0, x20, x50, &x52); ++ { u32 x54 = (x49 & 0x1ffffff); ++ { u32 x56; u8/*bool*/ x57 = addcarryx_u25(x53, x23, x54, &x56); ++ { u32 x58 = (x49 & 0x3ffffff); ++ { u32 x60; u8/*bool*/ x61 = addcarryx_u26(x57, x26, x58, &x60); ++ { u32 x62 = (x49 & 0x1ffffff); ++ { u32 x64; u8/*bool*/ x65 = addcarryx_u25(x61, x29, x62, &x64); ++ { u32 x66 = (x49 & 0x3ffffff); ++ { u32 x68; u8/*bool*/ x69 = addcarryx_u26(x65, x32, x66, &x68); ++ { u32 x70 = (x49 & 0x1ffffff); ++ { u32 x72; u8/*bool*/ x73 = addcarryx_u25(x69, x35, x70, &x72); ++ { u32 x74 = (x49 & 0x3ffffff); ++ { u32 x76; u8/*bool*/ x77 = addcarryx_u26(x73, x38, x74, &x76); ++ { u32 x78 = (x49 & 0x1ffffff); ++ { u32 x80; u8/*bool*/ x81 = addcarryx_u25(x77, x41, x78, &x80); ++ { u32 x82 = (x49 & 0x3ffffff); ++ { u32 x84; u8/*bool*/ x85 = addcarryx_u26(x81, x44, x82, &x84); ++ { u32 x86 = (x49 & 0x1ffffff); ++ { u32 x88; addcarryx_u25(x85, x47, x86, &x88); ++ out[0] = x52; ++ out[1] = x56; ++ out[2] = x60; ++ out[3] = x64; ++ out[4] = x68; ++ out[5] = x72; ++ out[6] = x76; ++ out[7] = x80; ++ out[8] = x84; ++ out[9] = x88; ++ }}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}} ++} ++ ++static __always_inline void fe_tobytes(u8 s[32], const fe *f) ++{ ++ u32 h[10]; ++ fe_freeze(h, f->v); ++ s[0] = h[0] >> 0; ++ s[1] = h[0] >> 8; ++ s[2] = h[0] >> 16; ++ s[3] = (h[0] >> 24) | (h[1] << 2); ++ s[4] = h[1] >> 6; ++ s[5] = h[1] >> 14; ++ s[6] = (h[1] >> 22) | (h[2] << 3); ++ s[7] = h[2] >> 5; ++ s[8] = h[2] >> 13; ++ s[9] = (h[2] >> 21) | (h[3] << 5); ++ s[10] = h[3] >> 3; ++ s[11] = h[3] >> 11; ++ s[12] = (h[3] >> 19) | (h[4] << 6); ++ s[13] = h[4] >> 2; ++ s[14] = h[4] >> 10; ++ s[15] = h[4] >> 18; ++ s[16] = h[5] >> 0; ++ s[17] = h[5] >> 8; ++ s[18] = h[5] >> 16; ++ s[19] = (h[5] >> 24) | (h[6] << 1); ++ s[20] = h[6] >> 7; ++ s[21] = h[6] >> 15; ++ s[22] = (h[6] >> 23) | (h[7] << 3); ++ s[23] = h[7] >> 5; ++ s[24] = h[7] >> 13; ++ s[25] = (h[7] >> 21) | (h[8] << 4); ++ s[26] = h[8] >> 4; ++ s[27] = h[8] >> 12; ++ s[28] = (h[8] >> 20) | (h[9] << 6); ++ s[29] = h[9] >> 2; ++ s[30] = h[9] >> 10; ++ s[31] = h[9] >> 18; ++} ++ ++/* h = f */ ++static __always_inline void fe_copy(fe *h, const fe *f) ++{ ++ memmove(h, f, sizeof(u32) * 10); ++} ++ ++static __always_inline void fe_copy_lt(fe_loose *h, const fe *f) ++{ ++ memmove(h, f, sizeof(u32) * 10); ++} ++ ++/* h = 0 */ ++static __always_inline void fe_0(fe *h) ++{ ++ memset(h, 0, sizeof(u32) * 10); ++} ++ ++/* h = 1 */ ++static __always_inline void fe_1(fe *h) ++{ ++ memset(h, 0, sizeof(u32) * 10); ++ h->v[0] = 1; ++} ++ ++static void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) ++{ ++ { const u32 x20 = in1[9]; ++ { const u32 x21 = in1[8]; ++ { const u32 x19 = in1[7]; ++ { const u32 x17 = in1[6]; ++ { const u32 x15 = in1[5]; ++ { const u32 x13 = in1[4]; ++ { const u32 x11 = in1[3]; ++ { const u32 x9 = in1[2]; ++ { const u32 x7 = in1[1]; ++ { const u32 x5 = in1[0]; ++ { const u32 x38 = in2[9]; ++ { const u32 x39 = in2[8]; ++ { const u32 x37 = in2[7]; ++ { const u32 x35 = in2[6]; ++ { const u32 x33 = in2[5]; ++ { const u32 x31 = in2[4]; ++ { const u32 x29 = in2[3]; ++ { const u32 x27 = in2[2]; ++ { const u32 x25 = in2[1]; ++ { const u32 x23 = in2[0]; ++ out[0] = (x5 + x23); ++ out[1] = (x7 + x25); ++ out[2] = (x9 + x27); ++ out[3] = (x11 + x29); ++ out[4] = (x13 + x31); ++ out[5] = (x15 + x33); ++ out[6] = (x17 + x35); ++ out[7] = (x19 + x37); ++ out[8] = (x21 + x39); ++ out[9] = (x20 + x38); ++ }}}}}}}}}}}}}}}}}}}} ++} ++ ++/* h = f + g ++ * Can overlap h with f or g. ++ */ ++static __always_inline void fe_add(fe_loose *h, const fe *f, const fe *g) ++{ ++ fe_add_impl(h->v, f->v, g->v); ++} ++ ++static void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) ++{ ++ { const u32 x20 = in1[9]; ++ { const u32 x21 = in1[8]; ++ { const u32 x19 = in1[7]; ++ { const u32 x17 = in1[6]; ++ { const u32 x15 = in1[5]; ++ { const u32 x13 = in1[4]; ++ { const u32 x11 = in1[3]; ++ { const u32 x9 = in1[2]; ++ { const u32 x7 = in1[1]; ++ { const u32 x5 = in1[0]; ++ { const u32 x38 = in2[9]; ++ { const u32 x39 = in2[8]; ++ { const u32 x37 = in2[7]; ++ { const u32 x35 = in2[6]; ++ { const u32 x33 = in2[5]; ++ { const u32 x31 = in2[4]; ++ { const u32 x29 = in2[3]; ++ { const u32 x27 = in2[2]; ++ { const u32 x25 = in2[1]; ++ { const u32 x23 = in2[0]; ++ out[0] = ((0x7ffffda + x5) - x23); ++ out[1] = ((0x3fffffe + x7) - x25); ++ out[2] = ((0x7fffffe + x9) - x27); ++ out[3] = ((0x3fffffe + x11) - x29); ++ out[4] = ((0x7fffffe + x13) - x31); ++ out[5] = ((0x3fffffe + x15) - x33); ++ out[6] = ((0x7fffffe + x17) - x35); ++ out[7] = ((0x3fffffe + x19) - x37); ++ out[8] = ((0x7fffffe + x21) - x39); ++ out[9] = ((0x3fffffe + x20) - x38); ++ }}}}}}}}}}}}}}}}}}}} ++} ++ ++/* h = f - g ++ * Can overlap h with f or g. ++ */ ++static __always_inline void fe_sub(fe_loose *h, const fe *f, const fe *g) ++{ ++ fe_sub_impl(h->v, f->v, g->v); ++} ++ ++static void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) ++{ ++ { const u32 x20 = in1[9]; ++ { const u32 x21 = in1[8]; ++ { const u32 x19 = in1[7]; ++ { const u32 x17 = in1[6]; ++ { const u32 x15 = in1[5]; ++ { const u32 x13 = in1[4]; ++ { const u32 x11 = in1[3]; ++ { const u32 x9 = in1[2]; ++ { const u32 x7 = in1[1]; ++ { const u32 x5 = in1[0]; ++ { const u32 x38 = in2[9]; ++ { const u32 x39 = in2[8]; ++ { const u32 x37 = in2[7]; ++ { const u32 x35 = in2[6]; ++ { const u32 x33 = in2[5]; ++ { const u32 x31 = in2[4]; ++ { const u32 x29 = in2[3]; ++ { const u32 x27 = in2[2]; ++ { const u32 x25 = in2[1]; ++ { const u32 x23 = in2[0]; ++ { u64 x40 = ((u64)x23 * x5); ++ { u64 x41 = (((u64)x23 * x7) + ((u64)x25 * x5)); ++ { u64 x42 = ((((u64)(0x2 * x25) * x7) + ((u64)x23 * x9)) + ((u64)x27 * x5)); ++ { u64 x43 = (((((u64)x25 * x9) + ((u64)x27 * x7)) + ((u64)x23 * x11)) + ((u64)x29 * x5)); ++ { u64 x44 = (((((u64)x27 * x9) + (0x2 * (((u64)x25 * x11) + ((u64)x29 * x7)))) + ((u64)x23 * x13)) + ((u64)x31 * x5)); ++ { u64 x45 = (((((((u64)x27 * x11) + ((u64)x29 * x9)) + ((u64)x25 * x13)) + ((u64)x31 * x7)) + ((u64)x23 * x15)) + ((u64)x33 * x5)); ++ { u64 x46 = (((((0x2 * ((((u64)x29 * x11) + ((u64)x25 * x15)) + ((u64)x33 * x7))) + ((u64)x27 * x13)) + ((u64)x31 * x9)) + ((u64)x23 * x17)) + ((u64)x35 * x5)); ++ { u64 x47 = (((((((((u64)x29 * x13) + ((u64)x31 * x11)) + ((u64)x27 * x15)) + ((u64)x33 * x9)) + ((u64)x25 * x17)) + ((u64)x35 * x7)) + ((u64)x23 * x19)) + ((u64)x37 * x5)); ++ { u64 x48 = (((((((u64)x31 * x13) + (0x2 * (((((u64)x29 * x15) + ((u64)x33 * x11)) + ((u64)x25 * x19)) + ((u64)x37 * x7)))) + ((u64)x27 * x17)) + ((u64)x35 * x9)) + ((u64)x23 * x21)) + ((u64)x39 * x5)); ++ { u64 x49 = (((((((((((u64)x31 * x15) + ((u64)x33 * x13)) + ((u64)x29 * x17)) + ((u64)x35 * x11)) + ((u64)x27 * x19)) + ((u64)x37 * x9)) + ((u64)x25 * x21)) + ((u64)x39 * x7)) + ((u64)x23 * x20)) + ((u64)x38 * x5)); ++ { u64 x50 = (((((0x2 * ((((((u64)x33 * x15) + ((u64)x29 * x19)) + ((u64)x37 * x11)) + ((u64)x25 * x20)) + ((u64)x38 * x7))) + ((u64)x31 * x17)) + ((u64)x35 * x13)) + ((u64)x27 * x21)) + ((u64)x39 * x9)); ++ { u64 x51 = (((((((((u64)x33 * x17) + ((u64)x35 * x15)) + ((u64)x31 * x19)) + ((u64)x37 * x13)) + ((u64)x29 * x21)) + ((u64)x39 * x11)) + ((u64)x27 * x20)) + ((u64)x38 * x9)); ++ { u64 x52 = (((((u64)x35 * x17) + (0x2 * (((((u64)x33 * x19) + ((u64)x37 * x15)) + ((u64)x29 * x20)) + ((u64)x38 * x11)))) + ((u64)x31 * x21)) + ((u64)x39 * x13)); ++ { u64 x53 = (((((((u64)x35 * x19) + ((u64)x37 * x17)) + ((u64)x33 * x21)) + ((u64)x39 * x15)) + ((u64)x31 * x20)) + ((u64)x38 * x13)); ++ { u64 x54 = (((0x2 * ((((u64)x37 * x19) + ((u64)x33 * x20)) + ((u64)x38 * x15))) + ((u64)x35 * x21)) + ((u64)x39 * x17)); ++ { u64 x55 = (((((u64)x37 * x21) + ((u64)x39 * x19)) + ((u64)x35 * x20)) + ((u64)x38 * x17)); ++ { u64 x56 = (((u64)x39 * x21) + (0x2 * (((u64)x37 * x20) + ((u64)x38 * x19)))); ++ { u64 x57 = (((u64)x39 * x20) + ((u64)x38 * x21)); ++ { u64 x58 = ((u64)(0x2 * x38) * x20); ++ { u64 x59 = (x48 + (x58 << 0x4)); ++ { u64 x60 = (x59 + (x58 << 0x1)); ++ { u64 x61 = (x60 + x58); ++ { u64 x62 = (x47 + (x57 << 0x4)); ++ { u64 x63 = (x62 + (x57 << 0x1)); ++ { u64 x64 = (x63 + x57); ++ { u64 x65 = (x46 + (x56 << 0x4)); ++ { u64 x66 = (x65 + (x56 << 0x1)); ++ { u64 x67 = (x66 + x56); ++ { u64 x68 = (x45 + (x55 << 0x4)); ++ { u64 x69 = (x68 + (x55 << 0x1)); ++ { u64 x70 = (x69 + x55); ++ { u64 x71 = (x44 + (x54 << 0x4)); ++ { u64 x72 = (x71 + (x54 << 0x1)); ++ { u64 x73 = (x72 + x54); ++ { u64 x74 = (x43 + (x53 << 0x4)); ++ { u64 x75 = (x74 + (x53 << 0x1)); ++ { u64 x76 = (x75 + x53); ++ { u64 x77 = (x42 + (x52 << 0x4)); ++ { u64 x78 = (x77 + (x52 << 0x1)); ++ { u64 x79 = (x78 + x52); ++ { u64 x80 = (x41 + (x51 << 0x4)); ++ { u64 x81 = (x80 + (x51 << 0x1)); ++ { u64 x82 = (x81 + x51); ++ { u64 x83 = (x40 + (x50 << 0x4)); ++ { u64 x84 = (x83 + (x50 << 0x1)); ++ { u64 x85 = (x84 + x50); ++ { u64 x86 = (x85 >> 0x1a); ++ { u32 x87 = ((u32)x85 & 0x3ffffff); ++ { u64 x88 = (x86 + x82); ++ { u64 x89 = (x88 >> 0x19); ++ { u32 x90 = ((u32)x88 & 0x1ffffff); ++ { u64 x91 = (x89 + x79); ++ { u64 x92 = (x91 >> 0x1a); ++ { u32 x93 = ((u32)x91 & 0x3ffffff); ++ { u64 x94 = (x92 + x76); ++ { u64 x95 = (x94 >> 0x19); ++ { u32 x96 = ((u32)x94 & 0x1ffffff); ++ { u64 x97 = (x95 + x73); ++ { u64 x98 = (x97 >> 0x1a); ++ { u32 x99 = ((u32)x97 & 0x3ffffff); ++ { u64 x100 = (x98 + x70); ++ { u64 x101 = (x100 >> 0x19); ++ { u32 x102 = ((u32)x100 & 0x1ffffff); ++ { u64 x103 = (x101 + x67); ++ { u64 x104 = (x103 >> 0x1a); ++ { u32 x105 = ((u32)x103 & 0x3ffffff); ++ { u64 x106 = (x104 + x64); ++ { u64 x107 = (x106 >> 0x19); ++ { u32 x108 = ((u32)x106 & 0x1ffffff); ++ { u64 x109 = (x107 + x61); ++ { u64 x110 = (x109 >> 0x1a); ++ { u32 x111 = ((u32)x109 & 0x3ffffff); ++ { u64 x112 = (x110 + x49); ++ { u64 x113 = (x112 >> 0x19); ++ { u32 x114 = ((u32)x112 & 0x1ffffff); ++ { u64 x115 = (x87 + (0x13 * x113)); ++ { u32 x116 = (u32) (x115 >> 0x1a); ++ { u32 x117 = ((u32)x115 & 0x3ffffff); ++ { u32 x118 = (x116 + x90); ++ { u32 x119 = (x118 >> 0x19); ++ { u32 x120 = (x118 & 0x1ffffff); ++ out[0] = x117; ++ out[1] = x120; ++ out[2] = (x119 + x93); ++ out[3] = x96; ++ out[4] = x99; ++ out[5] = x102; ++ out[6] = x105; ++ out[7] = x108; ++ out[8] = x111; ++ out[9] = x114; ++ }}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}} ++} ++ ++static __always_inline void fe_mul_ttt(fe *h, const fe *f, const fe *g) ++{ ++ fe_mul_impl(h->v, f->v, g->v); ++} ++ ++static __always_inline void fe_mul_tlt(fe *h, const fe_loose *f, const fe *g) ++{ ++ fe_mul_impl(h->v, f->v, g->v); ++} ++ ++static __always_inline void ++fe_mul_tll(fe *h, const fe_loose *f, const fe_loose *g) ++{ ++ fe_mul_impl(h->v, f->v, g->v); ++} ++ ++static void fe_sqr_impl(u32 out[10], const u32 in1[10]) ++{ ++ { const u32 x17 = in1[9]; ++ { const u32 x18 = in1[8]; ++ { const u32 x16 = in1[7]; ++ { const u32 x14 = in1[6]; ++ { const u32 x12 = in1[5]; ++ { const u32 x10 = in1[4]; ++ { const u32 x8 = in1[3]; ++ { const u32 x6 = in1[2]; ++ { const u32 x4 = in1[1]; ++ { const u32 x2 = in1[0]; ++ { u64 x19 = ((u64)x2 * x2); ++ { u64 x20 = ((u64)(0x2 * x2) * x4); ++ { u64 x21 = (0x2 * (((u64)x4 * x4) + ((u64)x2 * x6))); ++ { u64 x22 = (0x2 * (((u64)x4 * x6) + ((u64)x2 * x8))); ++ { u64 x23 = ((((u64)x6 * x6) + ((u64)(0x4 * x4) * x8)) + ((u64)(0x2 * x2) * x10)); ++ { u64 x24 = (0x2 * ((((u64)x6 * x8) + ((u64)x4 * x10)) + ((u64)x2 * x12))); ++ { u64 x25 = (0x2 * (((((u64)x8 * x8) + ((u64)x6 * x10)) + ((u64)x2 * x14)) + ((u64)(0x2 * x4) * x12))); ++ { u64 x26 = (0x2 * (((((u64)x8 * x10) + ((u64)x6 * x12)) + ((u64)x4 * x14)) + ((u64)x2 * x16))); ++ { u64 x27 = (((u64)x10 * x10) + (0x2 * ((((u64)x6 * x14) + ((u64)x2 * x18)) + (0x2 * (((u64)x4 * x16) + ((u64)x8 * x12)))))); ++ { u64 x28 = (0x2 * ((((((u64)x10 * x12) + ((u64)x8 * x14)) + ((u64)x6 * x16)) + ((u64)x4 * x18)) + ((u64)x2 * x17))); ++ { u64 x29 = (0x2 * (((((u64)x12 * x12) + ((u64)x10 * x14)) + ((u64)x6 * x18)) + (0x2 * (((u64)x8 * x16) + ((u64)x4 * x17))))); ++ { u64 x30 = (0x2 * (((((u64)x12 * x14) + ((u64)x10 * x16)) + ((u64)x8 * x18)) + ((u64)x6 * x17))); ++ { u64 x31 = (((u64)x14 * x14) + (0x2 * (((u64)x10 * x18) + (0x2 * (((u64)x12 * x16) + ((u64)x8 * x17)))))); ++ { u64 x32 = (0x2 * ((((u64)x14 * x16) + ((u64)x12 * x18)) + ((u64)x10 * x17))); ++ { u64 x33 = (0x2 * ((((u64)x16 * x16) + ((u64)x14 * x18)) + ((u64)(0x2 * x12) * x17))); ++ { u64 x34 = (0x2 * (((u64)x16 * x18) + ((u64)x14 * x17))); ++ { u64 x35 = (((u64)x18 * x18) + ((u64)(0x4 * x16) * x17)); ++ { u64 x36 = ((u64)(0x2 * x18) * x17); ++ { u64 x37 = ((u64)(0x2 * x17) * x17); ++ { u64 x38 = (x27 + (x37 << 0x4)); ++ { u64 x39 = (x38 + (x37 << 0x1)); ++ { u64 x40 = (x39 + x37); ++ { u64 x41 = (x26 + (x36 << 0x4)); ++ { u64 x42 = (x41 + (x36 << 0x1)); ++ { u64 x43 = (x42 + x36); ++ { u64 x44 = (x25 + (x35 << 0x4)); ++ { u64 x45 = (x44 + (x35 << 0x1)); ++ { u64 x46 = (x45 + x35); ++ { u64 x47 = (x24 + (x34 << 0x4)); ++ { u64 x48 = (x47 + (x34 << 0x1)); ++ { u64 x49 = (x48 + x34); ++ { u64 x50 = (x23 + (x33 << 0x4)); ++ { u64 x51 = (x50 + (x33 << 0x1)); ++ { u64 x52 = (x51 + x33); ++ { u64 x53 = (x22 + (x32 << 0x4)); ++ { u64 x54 = (x53 + (x32 << 0x1)); ++ { u64 x55 = (x54 + x32); ++ { u64 x56 = (x21 + (x31 << 0x4)); ++ { u64 x57 = (x56 + (x31 << 0x1)); ++ { u64 x58 = (x57 + x31); ++ { u64 x59 = (x20 + (x30 << 0x4)); ++ { u64 x60 = (x59 + (x30 << 0x1)); ++ { u64 x61 = (x60 + x30); ++ { u64 x62 = (x19 + (x29 << 0x4)); ++ { u64 x63 = (x62 + (x29 << 0x1)); ++ { u64 x64 = (x63 + x29); ++ { u64 x65 = (x64 >> 0x1a); ++ { u32 x66 = ((u32)x64 & 0x3ffffff); ++ { u64 x67 = (x65 + x61); ++ { u64 x68 = (x67 >> 0x19); ++ { u32 x69 = ((u32)x67 & 0x1ffffff); ++ { u64 x70 = (x68 + x58); ++ { u64 x71 = (x70 >> 0x1a); ++ { u32 x72 = ((u32)x70 & 0x3ffffff); ++ { u64 x73 = (x71 + x55); ++ { u64 x74 = (x73 >> 0x19); ++ { u32 x75 = ((u32)x73 & 0x1ffffff); ++ { u64 x76 = (x74 + x52); ++ { u64 x77 = (x76 >> 0x1a); ++ { u32 x78 = ((u32)x76 & 0x3ffffff); ++ { u64 x79 = (x77 + x49); ++ { u64 x80 = (x79 >> 0x19); ++ { u32 x81 = ((u32)x79 & 0x1ffffff); ++ { u64 x82 = (x80 + x46); ++ { u64 x83 = (x82 >> 0x1a); ++ { u32 x84 = ((u32)x82 & 0x3ffffff); ++ { u64 x85 = (x83 + x43); ++ { u64 x86 = (x85 >> 0x19); ++ { u32 x87 = ((u32)x85 & 0x1ffffff); ++ { u64 x88 = (x86 + x40); ++ { u64 x89 = (x88 >> 0x1a); ++ { u32 x90 = ((u32)x88 & 0x3ffffff); ++ { u64 x91 = (x89 + x28); ++ { u64 x92 = (x91 >> 0x19); ++ { u32 x93 = ((u32)x91 & 0x1ffffff); ++ { u64 x94 = (x66 + (0x13 * x92)); ++ { u32 x95 = (u32) (x94 >> 0x1a); ++ { u32 x96 = ((u32)x94 & 0x3ffffff); ++ { u32 x97 = (x95 + x69); ++ { u32 x98 = (x97 >> 0x19); ++ { u32 x99 = (x97 & 0x1ffffff); ++ out[0] = x96; ++ out[1] = x99; ++ out[2] = (x98 + x72); ++ out[3] = x75; ++ out[4] = x78; ++ out[5] = x81; ++ out[6] = x84; ++ out[7] = x87; ++ out[8] = x90; ++ out[9] = x93; ++ }}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}} ++} ++ ++static __always_inline void fe_sq_tl(fe *h, const fe_loose *f) ++{ ++ fe_sqr_impl(h->v, f->v); ++} ++ ++static __always_inline void fe_sq_tt(fe *h, const fe *f) ++{ ++ fe_sqr_impl(h->v, f->v); ++} ++ ++static __always_inline void fe_loose_invert(fe *out, const fe_loose *z) ++{ ++ fe t0; ++ fe t1; ++ fe t2; ++ fe t3; ++ int i; ++ ++ fe_sq_tl(&t0, z); ++ fe_sq_tt(&t1, &t0); ++ for (i = 1; i < 2; ++i) ++ fe_sq_tt(&t1, &t1); ++ fe_mul_tlt(&t1, z, &t1); ++ fe_mul_ttt(&t0, &t0, &t1); ++ fe_sq_tt(&t2, &t0); ++ fe_mul_ttt(&t1, &t1, &t2); ++ fe_sq_tt(&t2, &t1); ++ for (i = 1; i < 5; ++i) ++ fe_sq_tt(&t2, &t2); ++ fe_mul_ttt(&t1, &t2, &t1); ++ fe_sq_tt(&t2, &t1); ++ for (i = 1; i < 10; ++i) ++ fe_sq_tt(&t2, &t2); ++ fe_mul_ttt(&t2, &t2, &t1); ++ fe_sq_tt(&t3, &t2); ++ for (i = 1; i < 20; ++i) ++ fe_sq_tt(&t3, &t3); ++ fe_mul_ttt(&t2, &t3, &t2); ++ fe_sq_tt(&t2, &t2); ++ for (i = 1; i < 10; ++i) ++ fe_sq_tt(&t2, &t2); ++ fe_mul_ttt(&t1, &t2, &t1); ++ fe_sq_tt(&t2, &t1); ++ for (i = 1; i < 50; ++i) ++ fe_sq_tt(&t2, &t2); ++ fe_mul_ttt(&t2, &t2, &t1); ++ fe_sq_tt(&t3, &t2); ++ for (i = 1; i < 100; ++i) ++ fe_sq_tt(&t3, &t3); ++ fe_mul_ttt(&t2, &t3, &t2); ++ fe_sq_tt(&t2, &t2); ++ for (i = 1; i < 50; ++i) ++ fe_sq_tt(&t2, &t2); ++ fe_mul_ttt(&t1, &t2, &t1); ++ fe_sq_tt(&t1, &t1); ++ for (i = 1; i < 5; ++i) ++ fe_sq_tt(&t1, &t1); ++ fe_mul_ttt(out, &t1, &t0); ++} ++ ++static __always_inline void fe_invert(fe *out, const fe *z) ++{ ++ fe_loose l; ++ fe_copy_lt(&l, z); ++ fe_loose_invert(out, &l); ++} ++ ++/* Replace (f,g) with (g,f) if b == 1; ++ * replace (f,g) with (f,g) if b == 0. ++ * ++ * Preconditions: b in {0,1} ++ */ ++static __always_inline void fe_cswap(fe *f, fe *g, unsigned int b) ++{ ++ unsigned i; ++ b = 0 - b; ++ for (i = 0; i < 10; i++) { ++ u32 x = f->v[i] ^ g->v[i]; ++ x &= b; ++ f->v[i] ^= x; ++ g->v[i] ^= x; ++ } ++} ++ ++/* NOTE: based on fiat-crypto fe_mul, edited for in2=121666, 0, 0.*/ ++static __always_inline void fe_mul_121666_impl(u32 out[10], const u32 in1[10]) ++{ ++ { const u32 x20 = in1[9]; ++ { const u32 x21 = in1[8]; ++ { const u32 x19 = in1[7]; ++ { const u32 x17 = in1[6]; ++ { const u32 x15 = in1[5]; ++ { const u32 x13 = in1[4]; ++ { const u32 x11 = in1[3]; ++ { const u32 x9 = in1[2]; ++ { const u32 x7 = in1[1]; ++ { const u32 x5 = in1[0]; ++ { const u32 x38 = 0; ++ { const u32 x39 = 0; ++ { const u32 x37 = 0; ++ { const u32 x35 = 0; ++ { const u32 x33 = 0; ++ { const u32 x31 = 0; ++ { const u32 x29 = 0; ++ { const u32 x27 = 0; ++ { const u32 x25 = 0; ++ { const u32 x23 = 121666; ++ { u64 x40 = ((u64)x23 * x5); ++ { u64 x41 = (((u64)x23 * x7) + ((u64)x25 * x5)); ++ { u64 x42 = ((((u64)(0x2 * x25) * x7) + ((u64)x23 * x9)) + ((u64)x27 * x5)); ++ { u64 x43 = (((((u64)x25 * x9) + ((u64)x27 * x7)) + ((u64)x23 * x11)) + ((u64)x29 * x5)); ++ { u64 x44 = (((((u64)x27 * x9) + (0x2 * (((u64)x25 * x11) + ((u64)x29 * x7)))) + ((u64)x23 * x13)) + ((u64)x31 * x5)); ++ { u64 x45 = (((((((u64)x27 * x11) + ((u64)x29 * x9)) + ((u64)x25 * x13)) + ((u64)x31 * x7)) + ((u64)x23 * x15)) + ((u64)x33 * x5)); ++ { u64 x46 = (((((0x2 * ((((u64)x29 * x11) + ((u64)x25 * x15)) + ((u64)x33 * x7))) + ((u64)x27 * x13)) + ((u64)x31 * x9)) + ((u64)x23 * x17)) + ((u64)x35 * x5)); ++ { u64 x47 = (((((((((u64)x29 * x13) + ((u64)x31 * x11)) + ((u64)x27 * x15)) + ((u64)x33 * x9)) + ((u64)x25 * x17)) + ((u64)x35 * x7)) + ((u64)x23 * x19)) + ((u64)x37 * x5)); ++ { u64 x48 = (((((((u64)x31 * x13) + (0x2 * (((((u64)x29 * x15) + ((u64)x33 * x11)) + ((u64)x25 * x19)) + ((u64)x37 * x7)))) + ((u64)x27 * x17)) + ((u64)x35 * x9)) + ((u64)x23 * x21)) + ((u64)x39 * x5)); ++ { u64 x49 = (((((((((((u64)x31 * x15) + ((u64)x33 * x13)) + ((u64)x29 * x17)) + ((u64)x35 * x11)) + ((u64)x27 * x19)) + ((u64)x37 * x9)) + ((u64)x25 * x21)) + ((u64)x39 * x7)) + ((u64)x23 * x20)) + ((u64)x38 * x5)); ++ { u64 x50 = (((((0x2 * ((((((u64)x33 * x15) + ((u64)x29 * x19)) + ((u64)x37 * x11)) + ((u64)x25 * x20)) + ((u64)x38 * x7))) + ((u64)x31 * x17)) + ((u64)x35 * x13)) + ((u64)x27 * x21)) + ((u64)x39 * x9)); ++ { u64 x51 = (((((((((u64)x33 * x17) + ((u64)x35 * x15)) + ((u64)x31 * x19)) + ((u64)x37 * x13)) + ((u64)x29 * x21)) + ((u64)x39 * x11)) + ((u64)x27 * x20)) + ((u64)x38 * x9)); ++ { u64 x52 = (((((u64)x35 * x17) + (0x2 * (((((u64)x33 * x19) + ((u64)x37 * x15)) + ((u64)x29 * x20)) + ((u64)x38 * x11)))) + ((u64)x31 * x21)) + ((u64)x39 * x13)); ++ { u64 x53 = (((((((u64)x35 * x19) + ((u64)x37 * x17)) + ((u64)x33 * x21)) + ((u64)x39 * x15)) + ((u64)x31 * x20)) + ((u64)x38 * x13)); ++ { u64 x54 = (((0x2 * ((((u64)x37 * x19) + ((u64)x33 * x20)) + ((u64)x38 * x15))) + ((u64)x35 * x21)) + ((u64)x39 * x17)); ++ { u64 x55 = (((((u64)x37 * x21) + ((u64)x39 * x19)) + ((u64)x35 * x20)) + ((u64)x38 * x17)); ++ { u64 x56 = (((u64)x39 * x21) + (0x2 * (((u64)x37 * x20) + ((u64)x38 * x19)))); ++ { u64 x57 = (((u64)x39 * x20) + ((u64)x38 * x21)); ++ { u64 x58 = ((u64)(0x2 * x38) * x20); ++ { u64 x59 = (x48 + (x58 << 0x4)); ++ { u64 x60 = (x59 + (x58 << 0x1)); ++ { u64 x61 = (x60 + x58); ++ { u64 x62 = (x47 + (x57 << 0x4)); ++ { u64 x63 = (x62 + (x57 << 0x1)); ++ { u64 x64 = (x63 + x57); ++ { u64 x65 = (x46 + (x56 << 0x4)); ++ { u64 x66 = (x65 + (x56 << 0x1)); ++ { u64 x67 = (x66 + x56); ++ { u64 x68 = (x45 + (x55 << 0x4)); ++ { u64 x69 = (x68 + (x55 << 0x1)); ++ { u64 x70 = (x69 + x55); ++ { u64 x71 = (x44 + (x54 << 0x4)); ++ { u64 x72 = (x71 + (x54 << 0x1)); ++ { u64 x73 = (x72 + x54); ++ { u64 x74 = (x43 + (x53 << 0x4)); ++ { u64 x75 = (x74 + (x53 << 0x1)); ++ { u64 x76 = (x75 + x53); ++ { u64 x77 = (x42 + (x52 << 0x4)); ++ { u64 x78 = (x77 + (x52 << 0x1)); ++ { u64 x79 = (x78 + x52); ++ { u64 x80 = (x41 + (x51 << 0x4)); ++ { u64 x81 = (x80 + (x51 << 0x1)); ++ { u64 x82 = (x81 + x51); ++ { u64 x83 = (x40 + (x50 << 0x4)); ++ { u64 x84 = (x83 + (x50 << 0x1)); ++ { u64 x85 = (x84 + x50); ++ { u64 x86 = (x85 >> 0x1a); ++ { u32 x87 = ((u32)x85 & 0x3ffffff); ++ { u64 x88 = (x86 + x82); ++ { u64 x89 = (x88 >> 0x19); ++ { u32 x90 = ((u32)x88 & 0x1ffffff); ++ { u64 x91 = (x89 + x79); ++ { u64 x92 = (x91 >> 0x1a); ++ { u32 x93 = ((u32)x91 & 0x3ffffff); ++ { u64 x94 = (x92 + x76); ++ { u64 x95 = (x94 >> 0x19); ++ { u32 x96 = ((u32)x94 & 0x1ffffff); ++ { u64 x97 = (x95 + x73); ++ { u64 x98 = (x97 >> 0x1a); ++ { u32 x99 = ((u32)x97 & 0x3ffffff); ++ { u64 x100 = (x98 + x70); ++ { u64 x101 = (x100 >> 0x19); ++ { u32 x102 = ((u32)x100 & 0x1ffffff); ++ { u64 x103 = (x101 + x67); ++ { u64 x104 = (x103 >> 0x1a); ++ { u32 x105 = ((u32)x103 & 0x3ffffff); ++ { u64 x106 = (x104 + x64); ++ { u64 x107 = (x106 >> 0x19); ++ { u32 x108 = ((u32)x106 & 0x1ffffff); ++ { u64 x109 = (x107 + x61); ++ { u64 x110 = (x109 >> 0x1a); ++ { u32 x111 = ((u32)x109 & 0x3ffffff); ++ { u64 x112 = (x110 + x49); ++ { u64 x113 = (x112 >> 0x19); ++ { u32 x114 = ((u32)x112 & 0x1ffffff); ++ { u64 x115 = (x87 + (0x13 * x113)); ++ { u32 x116 = (u32) (x115 >> 0x1a); ++ { u32 x117 = ((u32)x115 & 0x3ffffff); ++ { u32 x118 = (x116 + x90); ++ { u32 x119 = (x118 >> 0x19); ++ { u32 x120 = (x118 & 0x1ffffff); ++ out[0] = x117; ++ out[1] = x120; ++ out[2] = (x119 + x93); ++ out[3] = x96; ++ out[4] = x99; ++ out[5] = x102; ++ out[6] = x105; ++ out[7] = x108; ++ out[8] = x111; ++ out[9] = x114; ++ }}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}} ++} ++ ++static __always_inline void fe_mul121666(fe *h, const fe_loose *f) ++{ ++ fe_mul_121666_impl(h->v, f->v); ++} ++ ++void curve25519_generic(u8 out[CURVE25519_KEY_SIZE], ++ const u8 scalar[CURVE25519_KEY_SIZE], ++ const u8 point[CURVE25519_KEY_SIZE]) ++{ ++ fe x1, x2, z2, x3, z3; ++ fe_loose x2l, z2l, x3l; ++ unsigned swap = 0; ++ int pos; ++ u8 e[32]; ++ ++ memcpy(e, scalar, 32); ++ curve25519_clamp_secret(e); ++ ++ /* The following implementation was transcribed to Coq and proven to ++ * correspond to unary scalar multiplication in affine coordinates given ++ * that x1 != 0 is the x coordinate of some point on the curve. It was ++ * also checked in Coq that doing a ladderstep with x1 = x3 = 0 gives ++ * z2' = z3' = 0, and z2 = z3 = 0 gives z2' = z3' = 0. The statement was ++ * quantified over the underlying field, so it applies to Curve25519 ++ * itself and the quadratic twist of Curve25519. It was not proven in ++ * Coq that prime-field arithmetic correctly simulates extension-field ++ * arithmetic on prime-field values. The decoding of the byte array ++ * representation of e was not considered. ++ * ++ * Specification of Montgomery curves in affine coordinates: ++ * ++ * ++ * Proof that these form a group that is isomorphic to a Weierstrass ++ * curve: ++ * ++ * ++ * Coq transcription and correctness proof of the loop ++ * (where scalarbits=255): ++ * ++ * ++ * preconditions: 0 <= e < 2^255 (not necessarily e < order), ++ * fe_invert(0) = 0 ++ */ ++ fe_frombytes(&x1, point); ++ fe_1(&x2); ++ fe_0(&z2); ++ fe_copy(&x3, &x1); ++ fe_1(&z3); ++ ++ for (pos = 254; pos >= 0; --pos) { ++ fe tmp0, tmp1; ++ fe_loose tmp0l, tmp1l; ++ /* loop invariant as of right before the test, for the case ++ * where x1 != 0: ++ * pos >= -1; if z2 = 0 then x2 is nonzero; if z3 = 0 then x3 ++ * is nonzero ++ * let r := e >> (pos+1) in the following equalities of ++ * projective points: ++ * to_xz (r*P) === if swap then (x3, z3) else (x2, z2) ++ * to_xz ((r+1)*P) === if swap then (x2, z2) else (x3, z3) ++ * x1 is the nonzero x coordinate of the nonzero ++ * point (r*P-(r+1)*P) ++ */ ++ unsigned b = 1 & (e[pos / 8] >> (pos & 7)); ++ swap ^= b; ++ fe_cswap(&x2, &x3, swap); ++ fe_cswap(&z2, &z3, swap); ++ swap = b; ++ /* Coq transcription of ladderstep formula (called from ++ * transcribed loop): ++ * ++ * ++ * x1 != 0 ++ * x1 = 0 ++ */ ++ fe_sub(&tmp0l, &x3, &z3); ++ fe_sub(&tmp1l, &x2, &z2); ++ fe_add(&x2l, &x2, &z2); ++ fe_add(&z2l, &x3, &z3); ++ fe_mul_tll(&z3, &tmp0l, &x2l); ++ fe_mul_tll(&z2, &z2l, &tmp1l); ++ fe_sq_tl(&tmp0, &tmp1l); ++ fe_sq_tl(&tmp1, &x2l); ++ fe_add(&x3l, &z3, &z2); ++ fe_sub(&z2l, &z3, &z2); ++ fe_mul_ttt(&x2, &tmp1, &tmp0); ++ fe_sub(&tmp1l, &tmp1, &tmp0); ++ fe_sq_tl(&z2, &z2l); ++ fe_mul121666(&z3, &tmp1l); ++ fe_sq_tl(&x3, &x3l); ++ fe_add(&tmp0l, &tmp0, &z3); ++ fe_mul_ttt(&z3, &x1, &z2); ++ fe_mul_tll(&z2, &tmp1l, &tmp0l); ++ } ++ /* here pos=-1, so r=e, so to_xz (e*P) === if swap then (x3, z3) ++ * else (x2, z2) ++ */ ++ fe_cswap(&x2, &x3, swap); ++ fe_cswap(&z2, &z3, swap); ++ ++ fe_invert(&z2, &z2); ++ fe_mul_ttt(&x2, &x2, &z2); ++ fe_tobytes(out, &x2); ++ ++ memzero_explicit(&x1, sizeof(x1)); ++ memzero_explicit(&x2, sizeof(x2)); ++ memzero_explicit(&z2, sizeof(z2)); ++ memzero_explicit(&x3, sizeof(x3)); ++ memzero_explicit(&z3, sizeof(z3)); ++ memzero_explicit(&x2l, sizeof(x2l)); ++ memzero_explicit(&z2l, sizeof(z2l)); ++ memzero_explicit(&x3l, sizeof(x3l)); ++ memzero_explicit(&e, sizeof(e)); ++} +--- /dev/null ++++ b/lib/crypto/curve25519-hacl64.c +@@ -0,0 +1,788 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2016-2017 INRIA and Microsoft Corporation. ++ * Copyright (C) 2018-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is a machine-generated formally verified implementation of Curve25519 ++ * ECDH from: . Though originally machine ++ * generated, it has been tweaked to be suitable for use in the kernel. It is ++ * optimized for 64-bit machines that can efficiently work with 128-bit ++ * integer types. ++ */ ++ ++#include ++#include ++#include ++ ++typedef __uint128_t u128; ++ ++static __always_inline u64 u64_eq_mask(u64 a, u64 b) ++{ ++ u64 x = a ^ b; ++ u64 minus_x = ~x + (u64)1U; ++ u64 x_or_minus_x = x | minus_x; ++ u64 xnx = x_or_minus_x >> (u32)63U; ++ u64 c = xnx - (u64)1U; ++ return c; ++} ++ ++static __always_inline u64 u64_gte_mask(u64 a, u64 b) ++{ ++ u64 x = a; ++ u64 y = b; ++ u64 x_xor_y = x ^ y; ++ u64 x_sub_y = x - y; ++ u64 x_sub_y_xor_y = x_sub_y ^ y; ++ u64 q = x_xor_y | x_sub_y_xor_y; ++ u64 x_xor_q = x ^ q; ++ u64 x_xor_q_ = x_xor_q >> (u32)63U; ++ u64 c = x_xor_q_ - (u64)1U; ++ return c; ++} ++ ++static __always_inline void modulo_carry_top(u64 *b) ++{ ++ u64 b4 = b[4]; ++ u64 b0 = b[0]; ++ u64 b4_ = b4 & 0x7ffffffffffffLLU; ++ u64 b0_ = b0 + 19 * (b4 >> 51); ++ b[4] = b4_; ++ b[0] = b0_; ++} ++ ++static __always_inline void fproduct_copy_from_wide_(u64 *output, u128 *input) ++{ ++ { ++ u128 xi = input[0]; ++ output[0] = ((u64)(xi)); ++ } ++ { ++ u128 xi = input[1]; ++ output[1] = ((u64)(xi)); ++ } ++ { ++ u128 xi = input[2]; ++ output[2] = ((u64)(xi)); ++ } ++ { ++ u128 xi = input[3]; ++ output[3] = ((u64)(xi)); ++ } ++ { ++ u128 xi = input[4]; ++ output[4] = ((u64)(xi)); ++ } ++} ++ ++static __always_inline void ++fproduct_sum_scalar_multiplication_(u128 *output, u64 *input, u64 s) ++{ ++ output[0] += (u128)input[0] * s; ++ output[1] += (u128)input[1] * s; ++ output[2] += (u128)input[2] * s; ++ output[3] += (u128)input[3] * s; ++ output[4] += (u128)input[4] * s; ++} ++ ++static __always_inline void fproduct_carry_wide_(u128 *tmp) ++{ ++ { ++ u32 ctr = 0; ++ u128 tctr = tmp[ctr]; ++ u128 tctrp1 = tmp[ctr + 1]; ++ u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU; ++ u128 c = ((tctr) >> (51)); ++ tmp[ctr] = ((u128)(r0)); ++ tmp[ctr + 1] = ((tctrp1) + (c)); ++ } ++ { ++ u32 ctr = 1; ++ u128 tctr = tmp[ctr]; ++ u128 tctrp1 = tmp[ctr + 1]; ++ u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU; ++ u128 c = ((tctr) >> (51)); ++ tmp[ctr] = ((u128)(r0)); ++ tmp[ctr + 1] = ((tctrp1) + (c)); ++ } ++ ++ { ++ u32 ctr = 2; ++ u128 tctr = tmp[ctr]; ++ u128 tctrp1 = tmp[ctr + 1]; ++ u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU; ++ u128 c = ((tctr) >> (51)); ++ tmp[ctr] = ((u128)(r0)); ++ tmp[ctr + 1] = ((tctrp1) + (c)); ++ } ++ { ++ u32 ctr = 3; ++ u128 tctr = tmp[ctr]; ++ u128 tctrp1 = tmp[ctr + 1]; ++ u64 r0 = ((u64)(tctr)) & 0x7ffffffffffffLLU; ++ u128 c = ((tctr) >> (51)); ++ tmp[ctr] = ((u128)(r0)); ++ tmp[ctr + 1] = ((tctrp1) + (c)); ++ } ++} ++ ++static __always_inline void fmul_shift_reduce(u64 *output) ++{ ++ u64 tmp = output[4]; ++ u64 b0; ++ { ++ u32 ctr = 5 - 0 - 1; ++ u64 z = output[ctr - 1]; ++ output[ctr] = z; ++ } ++ { ++ u32 ctr = 5 - 1 - 1; ++ u64 z = output[ctr - 1]; ++ output[ctr] = z; ++ } ++ { ++ u32 ctr = 5 - 2 - 1; ++ u64 z = output[ctr - 1]; ++ output[ctr] = z; ++ } ++ { ++ u32 ctr = 5 - 3 - 1; ++ u64 z = output[ctr - 1]; ++ output[ctr] = z; ++ } ++ output[0] = tmp; ++ b0 = output[0]; ++ output[0] = 19 * b0; ++} ++ ++static __always_inline void fmul_mul_shift_reduce_(u128 *output, u64 *input, ++ u64 *input21) ++{ ++ u32 i; ++ u64 input2i; ++ { ++ u64 input2i = input21[0]; ++ fproduct_sum_scalar_multiplication_(output, input, input2i); ++ fmul_shift_reduce(input); ++ } ++ { ++ u64 input2i = input21[1]; ++ fproduct_sum_scalar_multiplication_(output, input, input2i); ++ fmul_shift_reduce(input); ++ } ++ { ++ u64 input2i = input21[2]; ++ fproduct_sum_scalar_multiplication_(output, input, input2i); ++ fmul_shift_reduce(input); ++ } ++ { ++ u64 input2i = input21[3]; ++ fproduct_sum_scalar_multiplication_(output, input, input2i); ++ fmul_shift_reduce(input); ++ } ++ i = 4; ++ input2i = input21[i]; ++ fproduct_sum_scalar_multiplication_(output, input, input2i); ++} ++ ++static __always_inline void fmul_fmul(u64 *output, u64 *input, u64 *input21) ++{ ++ u64 tmp[5] = { input[0], input[1], input[2], input[3], input[4] }; ++ { ++ u128 b4; ++ u128 b0; ++ u128 b4_; ++ u128 b0_; ++ u64 i0; ++ u64 i1; ++ u64 i0_; ++ u64 i1_; ++ u128 t[5] = { 0 }; ++ fmul_mul_shift_reduce_(t, tmp, input21); ++ fproduct_carry_wide_(t); ++ b4 = t[4]; ++ b0 = t[0]; ++ b4_ = ((b4) & (((u128)(0x7ffffffffffffLLU)))); ++ b0_ = ((b0) + (((u128)(19) * (((u64)(((b4) >> (51)))))))); ++ t[4] = b4_; ++ t[0] = b0_; ++ fproduct_copy_from_wide_(output, t); ++ i0 = output[0]; ++ i1 = output[1]; ++ i0_ = i0 & 0x7ffffffffffffLLU; ++ i1_ = i1 + (i0 >> 51); ++ output[0] = i0_; ++ output[1] = i1_; ++ } ++} ++ ++static __always_inline void fsquare_fsquare__(u128 *tmp, u64 *output) ++{ ++ u64 r0 = output[0]; ++ u64 r1 = output[1]; ++ u64 r2 = output[2]; ++ u64 r3 = output[3]; ++ u64 r4 = output[4]; ++ u64 d0 = r0 * 2; ++ u64 d1 = r1 * 2; ++ u64 d2 = r2 * 2 * 19; ++ u64 d419 = r4 * 19; ++ u64 d4 = d419 * 2; ++ u128 s0 = ((((((u128)(r0) * (r0))) + (((u128)(d4) * (r1))))) + ++ (((u128)(d2) * (r3)))); ++ u128 s1 = ((((((u128)(d0) * (r1))) + (((u128)(d4) * (r2))))) + ++ (((u128)(r3 * 19) * (r3)))); ++ u128 s2 = ((((((u128)(d0) * (r2))) + (((u128)(r1) * (r1))))) + ++ (((u128)(d4) * (r3)))); ++ u128 s3 = ((((((u128)(d0) * (r3))) + (((u128)(d1) * (r2))))) + ++ (((u128)(r4) * (d419)))); ++ u128 s4 = ((((((u128)(d0) * (r4))) + (((u128)(d1) * (r3))))) + ++ (((u128)(r2) * (r2)))); ++ tmp[0] = s0; ++ tmp[1] = s1; ++ tmp[2] = s2; ++ tmp[3] = s3; ++ tmp[4] = s4; ++} ++ ++static __always_inline void fsquare_fsquare_(u128 *tmp, u64 *output) ++{ ++ u128 b4; ++ u128 b0; ++ u128 b4_; ++ u128 b0_; ++ u64 i0; ++ u64 i1; ++ u64 i0_; ++ u64 i1_; ++ fsquare_fsquare__(tmp, output); ++ fproduct_carry_wide_(tmp); ++ b4 = tmp[4]; ++ b0 = tmp[0]; ++ b4_ = ((b4) & (((u128)(0x7ffffffffffffLLU)))); ++ b0_ = ((b0) + (((u128)(19) * (((u64)(((b4) >> (51)))))))); ++ tmp[4] = b4_; ++ tmp[0] = b0_; ++ fproduct_copy_from_wide_(output, tmp); ++ i0 = output[0]; ++ i1 = output[1]; ++ i0_ = i0 & 0x7ffffffffffffLLU; ++ i1_ = i1 + (i0 >> 51); ++ output[0] = i0_; ++ output[1] = i1_; ++} ++ ++static __always_inline void fsquare_fsquare_times_(u64 *output, u128 *tmp, ++ u32 count1) ++{ ++ u32 i; ++ fsquare_fsquare_(tmp, output); ++ for (i = 1; i < count1; ++i) ++ fsquare_fsquare_(tmp, output); ++} ++ ++static __always_inline void fsquare_fsquare_times(u64 *output, u64 *input, ++ u32 count1) ++{ ++ u128 t[5]; ++ memcpy(output, input, 5 * sizeof(*input)); ++ fsquare_fsquare_times_(output, t, count1); ++} ++ ++static __always_inline void fsquare_fsquare_times_inplace(u64 *output, ++ u32 count1) ++{ ++ u128 t[5]; ++ fsquare_fsquare_times_(output, t, count1); ++} ++ ++static __always_inline void crecip_crecip(u64 *out, u64 *z) ++{ ++ u64 buf[20] = { 0 }; ++ u64 *a0 = buf; ++ u64 *t00 = buf + 5; ++ u64 *b0 = buf + 10; ++ u64 *t01; ++ u64 *b1; ++ u64 *c0; ++ u64 *a; ++ u64 *t0; ++ u64 *b; ++ u64 *c; ++ fsquare_fsquare_times(a0, z, 1); ++ fsquare_fsquare_times(t00, a0, 2); ++ fmul_fmul(b0, t00, z); ++ fmul_fmul(a0, b0, a0); ++ fsquare_fsquare_times(t00, a0, 1); ++ fmul_fmul(b0, t00, b0); ++ fsquare_fsquare_times(t00, b0, 5); ++ t01 = buf + 5; ++ b1 = buf + 10; ++ c0 = buf + 15; ++ fmul_fmul(b1, t01, b1); ++ fsquare_fsquare_times(t01, b1, 10); ++ fmul_fmul(c0, t01, b1); ++ fsquare_fsquare_times(t01, c0, 20); ++ fmul_fmul(t01, t01, c0); ++ fsquare_fsquare_times_inplace(t01, 10); ++ fmul_fmul(b1, t01, b1); ++ fsquare_fsquare_times(t01, b1, 50); ++ a = buf; ++ t0 = buf + 5; ++ b = buf + 10; ++ c = buf + 15; ++ fmul_fmul(c, t0, b); ++ fsquare_fsquare_times(t0, c, 100); ++ fmul_fmul(t0, t0, c); ++ fsquare_fsquare_times_inplace(t0, 50); ++ fmul_fmul(t0, t0, b); ++ fsquare_fsquare_times_inplace(t0, 5); ++ fmul_fmul(out, t0, a); ++} ++ ++static __always_inline void fsum(u64 *a, u64 *b) ++{ ++ a[0] += b[0]; ++ a[1] += b[1]; ++ a[2] += b[2]; ++ a[3] += b[3]; ++ a[4] += b[4]; ++} ++ ++static __always_inline void fdifference(u64 *a, u64 *b) ++{ ++ u64 tmp[5] = { 0 }; ++ u64 b0; ++ u64 b1; ++ u64 b2; ++ u64 b3; ++ u64 b4; ++ memcpy(tmp, b, 5 * sizeof(*b)); ++ b0 = tmp[0]; ++ b1 = tmp[1]; ++ b2 = tmp[2]; ++ b3 = tmp[3]; ++ b4 = tmp[4]; ++ tmp[0] = b0 + 0x3fffffffffff68LLU; ++ tmp[1] = b1 + 0x3ffffffffffff8LLU; ++ tmp[2] = b2 + 0x3ffffffffffff8LLU; ++ tmp[3] = b3 + 0x3ffffffffffff8LLU; ++ tmp[4] = b4 + 0x3ffffffffffff8LLU; ++ { ++ u64 xi = a[0]; ++ u64 yi = tmp[0]; ++ a[0] = yi - xi; ++ } ++ { ++ u64 xi = a[1]; ++ u64 yi = tmp[1]; ++ a[1] = yi - xi; ++ } ++ { ++ u64 xi = a[2]; ++ u64 yi = tmp[2]; ++ a[2] = yi - xi; ++ } ++ { ++ u64 xi = a[3]; ++ u64 yi = tmp[3]; ++ a[3] = yi - xi; ++ } ++ { ++ u64 xi = a[4]; ++ u64 yi = tmp[4]; ++ a[4] = yi - xi; ++ } ++} ++ ++static __always_inline void fscalar(u64 *output, u64 *b, u64 s) ++{ ++ u128 tmp[5]; ++ u128 b4; ++ u128 b0; ++ u128 b4_; ++ u128 b0_; ++ { ++ u64 xi = b[0]; ++ tmp[0] = ((u128)(xi) * (s)); ++ } ++ { ++ u64 xi = b[1]; ++ tmp[1] = ((u128)(xi) * (s)); ++ } ++ { ++ u64 xi = b[2]; ++ tmp[2] = ((u128)(xi) * (s)); ++ } ++ { ++ u64 xi = b[3]; ++ tmp[3] = ((u128)(xi) * (s)); ++ } ++ { ++ u64 xi = b[4]; ++ tmp[4] = ((u128)(xi) * (s)); ++ } ++ fproduct_carry_wide_(tmp); ++ b4 = tmp[4]; ++ b0 = tmp[0]; ++ b4_ = ((b4) & (((u128)(0x7ffffffffffffLLU)))); ++ b0_ = ((b0) + (((u128)(19) * (((u64)(((b4) >> (51)))))))); ++ tmp[4] = b4_; ++ tmp[0] = b0_; ++ fproduct_copy_from_wide_(output, tmp); ++} ++ ++static __always_inline void fmul(u64 *output, u64 *a, u64 *b) ++{ ++ fmul_fmul(output, a, b); ++} ++ ++static __always_inline void crecip(u64 *output, u64 *input) ++{ ++ crecip_crecip(output, input); ++} ++ ++static __always_inline void point_swap_conditional_step(u64 *a, u64 *b, ++ u64 swap1, u32 ctr) ++{ ++ u32 i = ctr - 1; ++ u64 ai = a[i]; ++ u64 bi = b[i]; ++ u64 x = swap1 & (ai ^ bi); ++ u64 ai1 = ai ^ x; ++ u64 bi1 = bi ^ x; ++ a[i] = ai1; ++ b[i] = bi1; ++} ++ ++static __always_inline void point_swap_conditional5(u64 *a, u64 *b, u64 swap1) ++{ ++ point_swap_conditional_step(a, b, swap1, 5); ++ point_swap_conditional_step(a, b, swap1, 4); ++ point_swap_conditional_step(a, b, swap1, 3); ++ point_swap_conditional_step(a, b, swap1, 2); ++ point_swap_conditional_step(a, b, swap1, 1); ++} ++ ++static __always_inline void point_swap_conditional(u64 *a, u64 *b, u64 iswap) ++{ ++ u64 swap1 = 0 - iswap; ++ point_swap_conditional5(a, b, swap1); ++ point_swap_conditional5(a + 5, b + 5, swap1); ++} ++ ++static __always_inline void point_copy(u64 *output, u64 *input) ++{ ++ memcpy(output, input, 5 * sizeof(*input)); ++ memcpy(output + 5, input + 5, 5 * sizeof(*input)); ++} ++ ++static __always_inline void addanddouble_fmonty(u64 *pp, u64 *ppq, u64 *p, ++ u64 *pq, u64 *qmqp) ++{ ++ u64 *qx = qmqp; ++ u64 *x2 = pp; ++ u64 *z2 = pp + 5; ++ u64 *x3 = ppq; ++ u64 *z3 = ppq + 5; ++ u64 *x = p; ++ u64 *z = p + 5; ++ u64 *xprime = pq; ++ u64 *zprime = pq + 5; ++ u64 buf[40] = { 0 }; ++ u64 *origx = buf; ++ u64 *origxprime0 = buf + 5; ++ u64 *xxprime0; ++ u64 *zzprime0; ++ u64 *origxprime; ++ xxprime0 = buf + 25; ++ zzprime0 = buf + 30; ++ memcpy(origx, x, 5 * sizeof(*x)); ++ fsum(x, z); ++ fdifference(z, origx); ++ memcpy(origxprime0, xprime, 5 * sizeof(*xprime)); ++ fsum(xprime, zprime); ++ fdifference(zprime, origxprime0); ++ fmul(xxprime0, xprime, z); ++ fmul(zzprime0, x, zprime); ++ origxprime = buf + 5; ++ { ++ u64 *xx0; ++ u64 *zz0; ++ u64 *xxprime; ++ u64 *zzprime; ++ u64 *zzzprime; ++ xx0 = buf + 15; ++ zz0 = buf + 20; ++ xxprime = buf + 25; ++ zzprime = buf + 30; ++ zzzprime = buf + 35; ++ memcpy(origxprime, xxprime, 5 * sizeof(*xxprime)); ++ fsum(xxprime, zzprime); ++ fdifference(zzprime, origxprime); ++ fsquare_fsquare_times(x3, xxprime, 1); ++ fsquare_fsquare_times(zzzprime, zzprime, 1); ++ fmul(z3, zzzprime, qx); ++ fsquare_fsquare_times(xx0, x, 1); ++ fsquare_fsquare_times(zz0, z, 1); ++ { ++ u64 *zzz; ++ u64 *xx; ++ u64 *zz; ++ u64 scalar; ++ zzz = buf + 10; ++ xx = buf + 15; ++ zz = buf + 20; ++ fmul(x2, xx, zz); ++ fdifference(zz, xx); ++ scalar = 121665; ++ fscalar(zzz, zz, scalar); ++ fsum(zzz, xx); ++ fmul(z2, zzz, zz); ++ } ++ } ++} ++ ++static __always_inline void ++ladder_smallloop_cmult_small_loop_step(u64 *nq, u64 *nqpq, u64 *nq2, u64 *nqpq2, ++ u64 *q, u8 byt) ++{ ++ u64 bit0 = (u64)(byt >> 7); ++ u64 bit; ++ point_swap_conditional(nq, nqpq, bit0); ++ addanddouble_fmonty(nq2, nqpq2, nq, nqpq, q); ++ bit = (u64)(byt >> 7); ++ point_swap_conditional(nq2, nqpq2, bit); ++} ++ ++static __always_inline void ++ladder_smallloop_cmult_small_loop_double_step(u64 *nq, u64 *nqpq, u64 *nq2, ++ u64 *nqpq2, u64 *q, u8 byt) ++{ ++ u8 byt1; ++ ladder_smallloop_cmult_small_loop_step(nq, nqpq, nq2, nqpq2, q, byt); ++ byt1 = byt << 1; ++ ladder_smallloop_cmult_small_loop_step(nq2, nqpq2, nq, nqpq, q, byt1); ++} ++ ++static __always_inline void ++ladder_smallloop_cmult_small_loop(u64 *nq, u64 *nqpq, u64 *nq2, u64 *nqpq2, ++ u64 *q, u8 byt, u32 i) ++{ ++ while (i--) { ++ ladder_smallloop_cmult_small_loop_double_step(nq, nqpq, nq2, ++ nqpq2, q, byt); ++ byt <<= 2; ++ } ++} ++ ++static __always_inline void ladder_bigloop_cmult_big_loop(u8 *n1, u64 *nq, ++ u64 *nqpq, u64 *nq2, ++ u64 *nqpq2, u64 *q, ++ u32 i) ++{ ++ while (i--) { ++ u8 byte = n1[i]; ++ ladder_smallloop_cmult_small_loop(nq, nqpq, nq2, nqpq2, q, ++ byte, 4); ++ } ++} ++ ++static void ladder_cmult(u64 *result, u8 *n1, u64 *q) ++{ ++ u64 point_buf[40] = { 0 }; ++ u64 *nq = point_buf; ++ u64 *nqpq = point_buf + 10; ++ u64 *nq2 = point_buf + 20; ++ u64 *nqpq2 = point_buf + 30; ++ point_copy(nqpq, q); ++ nq[0] = 1; ++ ladder_bigloop_cmult_big_loop(n1, nq, nqpq, nq2, nqpq2, q, 32); ++ point_copy(result, nq); ++} ++ ++static __always_inline void format_fexpand(u64 *output, const u8 *input) ++{ ++ const u8 *x00 = input + 6; ++ const u8 *x01 = input + 12; ++ const u8 *x02 = input + 19; ++ const u8 *x0 = input + 24; ++ u64 i0, i1, i2, i3, i4, output0, output1, output2, output3, output4; ++ i0 = get_unaligned_le64(input); ++ i1 = get_unaligned_le64(x00); ++ i2 = get_unaligned_le64(x01); ++ i3 = get_unaligned_le64(x02); ++ i4 = get_unaligned_le64(x0); ++ output0 = i0 & 0x7ffffffffffffLLU; ++ output1 = i1 >> 3 & 0x7ffffffffffffLLU; ++ output2 = i2 >> 6 & 0x7ffffffffffffLLU; ++ output3 = i3 >> 1 & 0x7ffffffffffffLLU; ++ output4 = i4 >> 12 & 0x7ffffffffffffLLU; ++ output[0] = output0; ++ output[1] = output1; ++ output[2] = output2; ++ output[3] = output3; ++ output[4] = output4; ++} ++ ++static __always_inline void format_fcontract_first_carry_pass(u64 *input) ++{ ++ u64 t0 = input[0]; ++ u64 t1 = input[1]; ++ u64 t2 = input[2]; ++ u64 t3 = input[3]; ++ u64 t4 = input[4]; ++ u64 t1_ = t1 + (t0 >> 51); ++ u64 t0_ = t0 & 0x7ffffffffffffLLU; ++ u64 t2_ = t2 + (t1_ >> 51); ++ u64 t1__ = t1_ & 0x7ffffffffffffLLU; ++ u64 t3_ = t3 + (t2_ >> 51); ++ u64 t2__ = t2_ & 0x7ffffffffffffLLU; ++ u64 t4_ = t4 + (t3_ >> 51); ++ u64 t3__ = t3_ & 0x7ffffffffffffLLU; ++ input[0] = t0_; ++ input[1] = t1__; ++ input[2] = t2__; ++ input[3] = t3__; ++ input[4] = t4_; ++} ++ ++static __always_inline void format_fcontract_first_carry_full(u64 *input) ++{ ++ format_fcontract_first_carry_pass(input); ++ modulo_carry_top(input); ++} ++ ++static __always_inline void format_fcontract_second_carry_pass(u64 *input) ++{ ++ u64 t0 = input[0]; ++ u64 t1 = input[1]; ++ u64 t2 = input[2]; ++ u64 t3 = input[3]; ++ u64 t4 = input[4]; ++ u64 t1_ = t1 + (t0 >> 51); ++ u64 t0_ = t0 & 0x7ffffffffffffLLU; ++ u64 t2_ = t2 + (t1_ >> 51); ++ u64 t1__ = t1_ & 0x7ffffffffffffLLU; ++ u64 t3_ = t3 + (t2_ >> 51); ++ u64 t2__ = t2_ & 0x7ffffffffffffLLU; ++ u64 t4_ = t4 + (t3_ >> 51); ++ u64 t3__ = t3_ & 0x7ffffffffffffLLU; ++ input[0] = t0_; ++ input[1] = t1__; ++ input[2] = t2__; ++ input[3] = t3__; ++ input[4] = t4_; ++} ++ ++static __always_inline void format_fcontract_second_carry_full(u64 *input) ++{ ++ u64 i0; ++ u64 i1; ++ u64 i0_; ++ u64 i1_; ++ format_fcontract_second_carry_pass(input); ++ modulo_carry_top(input); ++ i0 = input[0]; ++ i1 = input[1]; ++ i0_ = i0 & 0x7ffffffffffffLLU; ++ i1_ = i1 + (i0 >> 51); ++ input[0] = i0_; ++ input[1] = i1_; ++} ++ ++static __always_inline void format_fcontract_trim(u64 *input) ++{ ++ u64 a0 = input[0]; ++ u64 a1 = input[1]; ++ u64 a2 = input[2]; ++ u64 a3 = input[3]; ++ u64 a4 = input[4]; ++ u64 mask0 = u64_gte_mask(a0, 0x7ffffffffffedLLU); ++ u64 mask1 = u64_eq_mask(a1, 0x7ffffffffffffLLU); ++ u64 mask2 = u64_eq_mask(a2, 0x7ffffffffffffLLU); ++ u64 mask3 = u64_eq_mask(a3, 0x7ffffffffffffLLU); ++ u64 mask4 = u64_eq_mask(a4, 0x7ffffffffffffLLU); ++ u64 mask = (((mask0 & mask1) & mask2) & mask3) & mask4; ++ u64 a0_ = a0 - (0x7ffffffffffedLLU & mask); ++ u64 a1_ = a1 - (0x7ffffffffffffLLU & mask); ++ u64 a2_ = a2 - (0x7ffffffffffffLLU & mask); ++ u64 a3_ = a3 - (0x7ffffffffffffLLU & mask); ++ u64 a4_ = a4 - (0x7ffffffffffffLLU & mask); ++ input[0] = a0_; ++ input[1] = a1_; ++ input[2] = a2_; ++ input[3] = a3_; ++ input[4] = a4_; ++} ++ ++static __always_inline void format_fcontract_store(u8 *output, u64 *input) ++{ ++ u64 t0 = input[0]; ++ u64 t1 = input[1]; ++ u64 t2 = input[2]; ++ u64 t3 = input[3]; ++ u64 t4 = input[4]; ++ u64 o0 = t1 << 51 | t0; ++ u64 o1 = t2 << 38 | t1 >> 13; ++ u64 o2 = t3 << 25 | t2 >> 26; ++ u64 o3 = t4 << 12 | t3 >> 39; ++ u8 *b0 = output; ++ u8 *b1 = output + 8; ++ u8 *b2 = output + 16; ++ u8 *b3 = output + 24; ++ put_unaligned_le64(o0, b0); ++ put_unaligned_le64(o1, b1); ++ put_unaligned_le64(o2, b2); ++ put_unaligned_le64(o3, b3); ++} ++ ++static __always_inline void format_fcontract(u8 *output, u64 *input) ++{ ++ format_fcontract_first_carry_full(input); ++ format_fcontract_second_carry_full(input); ++ format_fcontract_trim(input); ++ format_fcontract_store(output, input); ++} ++ ++static __always_inline void format_scalar_of_point(u8 *scalar, u64 *point) ++{ ++ u64 *x = point; ++ u64 *z = point + 5; ++ u64 buf[10] __aligned(32) = { 0 }; ++ u64 *zmone = buf; ++ u64 *sc = buf + 5; ++ crecip(zmone, z); ++ fmul(sc, x, zmone); ++ format_fcontract(scalar, sc); ++} ++ ++void curve25519_generic(u8 mypublic[CURVE25519_KEY_SIZE], ++ const u8 secret[CURVE25519_KEY_SIZE], ++ const u8 basepoint[CURVE25519_KEY_SIZE]) ++{ ++ u64 buf0[10] __aligned(32) = { 0 }; ++ u64 *x0 = buf0; ++ u64 *z = buf0 + 5; ++ u64 *q; ++ format_fexpand(x0, basepoint); ++ z[0] = 1; ++ q = buf0; ++ { ++ u8 e[32] __aligned(32) = { 0 }; ++ u8 *scalar; ++ memcpy(e, secret, 32); ++ curve25519_clamp_secret(e); ++ scalar = e; ++ { ++ u64 buf[15] = { 0 }; ++ u64 *nq = buf; ++ u64 *x = nq; ++ x[0] = 1; ++ ladder_cmult(nq, scalar, q); ++ format_scalar_of_point(mypublic, nq); ++ memzero_explicit(buf, sizeof(buf)); ++ } ++ memzero_explicit(e, sizeof(e)); ++ } ++ memzero_explicit(buf0, sizeof(buf0)); ++} +--- /dev/null ++++ b/lib/crypto/curve25519.c +@@ -0,0 +1,25 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is an implementation of the Curve25519 ECDH algorithm, using either ++ * a 32-bit implementation or a 64-bit implementation with 128-bit integers, ++ * depending on what is supported by the target compiler. ++ * ++ * Information: https://cr.yp.to/ecdh.html ++ */ ++ ++#include ++#include ++#include ++ ++const u8 curve25519_null_point[CURVE25519_KEY_SIZE] __aligned(32) = { 0 }; ++const u8 curve25519_base_point[CURVE25519_KEY_SIZE] __aligned(32) = { 9 }; ++ ++EXPORT_SYMBOL(curve25519_null_point); ++EXPORT_SYMBOL(curve25519_base_point); ++EXPORT_SYMBOL(curve25519_generic); ++ ++MODULE_LICENSE("GPL v2"); ++MODULE_DESCRIPTION("Curve25519 scalar multiplication"); ++MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0026-crypto-curve25519-add-kpp-selftest.patch b/target/linux/generic/backport-5.4/080-wireguard-0026-crypto-curve25519-add-kpp-selftest.patch new file mode 100644 index 0000000000..66c144e321 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0026-crypto-curve25519-add-kpp-selftest.patch @@ -0,0 +1,1268 @@ +From c8ff08024112b37805ab5b1edbd7e451de35a17d Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:33 +0100 +Subject: [PATCH 026/124] crypto: curve25519 - add kpp selftest + +commit f613457a7af085728297bef71233c37faf3c01b1 upstream. + +In preparation of introducing KPP implementations of Curve25519, import +the set of test cases proposed by the Zinc patch set, but converted to +the KPP format. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/testmgr.c | 6 + + crypto/testmgr.h | 1225 ++++++++++++++++++++++++++++++++++++++++++++++ + 2 files changed, 1231 insertions(+) + +--- a/crypto/testmgr.c ++++ b/crypto/testmgr.c +@@ -4296,6 +4296,12 @@ static const struct alg_test_desc alg_te + .test = alg_test_null, + .fips_allowed = 1, + }, { ++ .alg = "curve25519", ++ .test = alg_test_kpp, ++ .suite = { ++ .kpp = __VECS(curve25519_tv_template) ++ } ++ }, { + .alg = "deflate", + .test = alg_test_comp, + .fips_allowed = 1, +--- a/crypto/testmgr.h ++++ b/crypto/testmgr.h +@@ -1030,6 +1030,1231 @@ static const struct kpp_testvec dh_tv_te + } + }; + ++static const struct kpp_testvec curve25519_tv_template[] = { ++{ ++ .secret = (u8[32]){ 0x77, 0x07, 0x6d, 0x0a, 0x73, 0x18, 0xa5, 0x7d, ++ 0x3c, 0x16, 0xc1, 0x72, 0x51, 0xb2, 0x66, 0x45, ++ 0xdf, 0x4c, 0x2f, 0x87, 0xeb, 0xc0, 0x99, 0x2a, ++ 0xb1, 0x77, 0xfb, 0xa5, 0x1d, 0xb9, 0x2c, 0x2a }, ++ .b_public = (u8[32]){ 0xde, 0x9e, 0xdb, 0x7d, 0x7b, 0x7d, 0xc1, 0xb4, ++ 0xd3, 0x5b, 0x61, 0xc2, 0xec, 0xe4, 0x35, 0x37, ++ 0x3f, 0x83, 0x43, 0xc8, 0x5b, 0x78, 0x67, 0x4d, ++ 0xad, 0xfc, 0x7e, 0x14, 0x6f, 0x88, 0x2b, 0x4f }, ++ .expected_ss = (u8[32]){ 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1, ++ 0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25, ++ 0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33, ++ 0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++{ ++ .secret = (u8[32]){ 0x5d, 0xab, 0x08, 0x7e, 0x62, 0x4a, 0x8a, 0x4b, ++ 0x79, 0xe1, 0x7f, 0x8b, 0x83, 0x80, 0x0e, 0xe6, ++ 0x6f, 0x3b, 0xb1, 0x29, 0x26, 0x18, 0xb6, 0xfd, ++ 0x1c, 0x2f, 0x8b, 0x27, 0xff, 0x88, 0xe0, 0xeb }, ++ .b_public = (u8[32]){ 0x85, 0x20, 0xf0, 0x09, 0x89, 0x30, 0xa7, 0x54, ++ 0x74, 0x8b, 0x7d, 0xdc, 0xb4, 0x3e, 0xf7, 0x5a, ++ 0x0d, 0xbf, 0x3a, 0x0d, 0x26, 0x38, 0x1a, 0xf4, ++ 0xeb, 0xa4, 0xa9, 0x8e, 0xaa, 0x9b, 0x4e, 0x6a }, ++ .expected_ss = (u8[32]){ 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1, ++ 0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25, ++ 0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33, ++ 0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++{ ++ .secret = (u8[32]){ 1 }, ++ .b_public = (u8[32]){ 0x25, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .expected_ss = (u8[32]){ 0x3c, 0x77, 0x77, 0xca, 0xf9, 0x97, 0xb2, 0x64, ++ 0x41, 0x60, 0x77, 0x66, 0x5b, 0x4e, 0x22, 0x9d, ++ 0x0b, 0x95, 0x48, 0xdc, 0x0c, 0xd8, 0x19, 0x98, ++ 0xdd, 0xcd, 0xc5, 0xc8, 0x53, 0x3c, 0x79, 0x7f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++{ ++ .secret = (u8[32]){ 1 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0xb3, 0x2d, 0x13, 0x62, 0xc2, 0x48, 0xd6, 0x2f, ++ 0xe6, 0x26, 0x19, 0xcf, 0xf0, 0x4d, 0xd4, 0x3d, ++ 0xb7, 0x3f, 0xfc, 0x1b, 0x63, 0x08, 0xed, 0xe3, ++ 0x0b, 0x78, 0xd8, 0x73, 0x80, 0xf1, 0xe8, 0x34 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++{ ++ .secret = (u8[32]){ 0xa5, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d, ++ 0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd, ++ 0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18, ++ 0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0xc4 }, ++ .b_public = (u8[32]){ 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb, ++ 0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c, ++ 0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b, ++ 0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c }, ++ .expected_ss = (u8[32]){ 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90, ++ 0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f, ++ 0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7, ++ 0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++{ ++ .secret = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0x0a, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0x0a, 0x00, 0xfb, 0x9f }, ++ .expected_ss = (u8[32]){ 0x77, 0x52, 0xb6, 0x18, 0xc1, 0x2d, 0x48, 0xd2, ++ 0xc6, 0x93, 0x46, 0x83, 0x81, 0x7c, 0xc6, 0x57, ++ 0xf3, 0x31, 0x03, 0x19, 0x49, 0x48, 0x20, 0x05, ++ 0x42, 0x2b, 0x4e, 0xae, 0x8d, 0x1d, 0x43, 0x23 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++{ ++ .secret = (u8[32]){ 0x8e, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .b_public = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8e, 0x06 }, ++ .expected_ss = (u8[32]){ 0x5a, 0xdf, 0xaa, 0x25, 0x86, 0x8e, 0x32, 0x3d, ++ 0xae, 0x49, 0x62, 0xc1, 0x01, 0x5c, 0xb3, 0x12, ++ 0xe1, 0xc5, 0xc7, 0x9e, 0x95, 0x3f, 0x03, 0x99, ++ 0xb0, 0xba, 0x16, 0x22, 0xf3, 0xb6, 0xf7, 0x0c }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - normal case */ ++{ ++ .secret = (u8[32]){ 0x48, 0x52, 0x83, 0x4d, 0x9d, 0x6b, 0x77, 0xda, ++ 0xde, 0xab, 0xaa, 0xf2, 0xe1, 0x1d, 0xca, 0x66, ++ 0xd1, 0x9f, 0xe7, 0x49, 0x93, 0xa7, 0xbe, 0xc3, ++ 0x6c, 0x6e, 0x16, 0xa0, 0x98, 0x3f, 0xea, 0xba }, ++ .b_public = (u8[32]){ 0x9c, 0x64, 0x7d, 0x9a, 0xe5, 0x89, 0xb9, 0xf5, ++ 0x8f, 0xdc, 0x3c, 0xa4, 0x94, 0x7e, 0xfb, 0xc9, ++ 0x15, 0xc4, 0xb2, 0xe0, 0x8e, 0x74, 0x4a, 0x0e, ++ 0xdf, 0x46, 0x9d, 0xac, 0x59, 0xc8, 0xf8, 0x5a }, ++ .expected_ss = (u8[32]){ 0x87, 0xb7, 0xf2, 0x12, 0xb6, 0x27, 0xf7, 0xa5, ++ 0x4c, 0xa5, 0xe0, 0xbc, 0xda, 0xdd, 0xd5, 0x38, ++ 0x9d, 0x9d, 0xe6, 0x15, 0x6c, 0xdb, 0xcf, 0x8e, ++ 0xbe, 0x14, 0xff, 0xbc, 0xfb, 0x43, 0x65, 0x51 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key on twist */ ++{ ++ .secret = (u8[32]){ 0x58, 0x8c, 0x06, 0x1a, 0x50, 0x80, 0x4a, 0xc4, ++ 0x88, 0xad, 0x77, 0x4a, 0xc7, 0x16, 0xc3, 0xf5, ++ 0xba, 0x71, 0x4b, 0x27, 0x12, 0xe0, 0x48, 0x49, ++ 0x13, 0x79, 0xa5, 0x00, 0x21, 0x19, 0x98, 0xa8 }, ++ .b_public = (u8[32]){ 0x63, 0xaa, 0x40, 0xc6, 0xe3, 0x83, 0x46, 0xc5, ++ 0xca, 0xf2, 0x3a, 0x6d, 0xf0, 0xa5, 0xe6, 0xc8, ++ 0x08, 0x89, 0xa0, 0x86, 0x47, 0xe5, 0x51, 0xb3, ++ 0x56, 0x34, 0x49, 0xbe, 0xfc, 0xfc, 0x97, 0x33 }, ++ .expected_ss = (u8[32]){ 0xb1, 0xa7, 0x07, 0x51, 0x94, 0x95, 0xff, 0xff, ++ 0xb2, 0x98, 0xff, 0x94, 0x17, 0x16, 0xb0, 0x6d, ++ 0xfa, 0xb8, 0x7c, 0xf8, 0xd9, 0x11, 0x23, 0xfe, ++ 0x2b, 0xe9, 0xa2, 0x33, 0xdd, 0xa2, 0x22, 0x12 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key on twist */ ++{ ++ .secret = (u8[32]){ 0xb0, 0x5b, 0xfd, 0x32, 0xe5, 0x53, 0x25, 0xd9, ++ 0xfd, 0x64, 0x8c, 0xb3, 0x02, 0x84, 0x80, 0x39, ++ 0x00, 0x0b, 0x39, 0x0e, 0x44, 0xd5, 0x21, 0xe5, ++ 0x8a, 0xab, 0x3b, 0x29, 0xa6, 0x96, 0x0b, 0xa8 }, ++ .b_public = (u8[32]){ 0x0f, 0x83, 0xc3, 0x6f, 0xde, 0xd9, 0xd3, 0x2f, ++ 0xad, 0xf4, 0xef, 0xa3, 0xae, 0x93, 0xa9, 0x0b, ++ 0xb5, 0xcf, 0xa6, 0x68, 0x93, 0xbc, 0x41, 0x2c, ++ 0x43, 0xfa, 0x72, 0x87, 0xdb, 0xb9, 0x97, 0x79 }, ++ .expected_ss = (u8[32]){ 0x67, 0xdd, 0x4a, 0x6e, 0x16, 0x55, 0x33, 0x53, ++ 0x4c, 0x0e, 0x3f, 0x17, 0x2e, 0x4a, 0xb8, 0x57, ++ 0x6b, 0xca, 0x92, 0x3a, 0x5f, 0x07, 0xb2, 0xc0, ++ 0x69, 0xb4, 0xc3, 0x10, 0xff, 0x2e, 0x93, 0x5b }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key on twist */ ++{ ++ .secret = (u8[32]){ 0x70, 0xe3, 0x4b, 0xcb, 0xe1, 0xf4, 0x7f, 0xbc, ++ 0x0f, 0xdd, 0xfd, 0x7c, 0x1e, 0x1a, 0xa5, 0x3d, ++ 0x57, 0xbf, 0xe0, 0xf6, 0x6d, 0x24, 0x30, 0x67, ++ 0xb4, 0x24, 0xbb, 0x62, 0x10, 0xbe, 0xd1, 0x9c }, ++ .b_public = (u8[32]){ 0x0b, 0x82, 0x11, 0xa2, 0xb6, 0x04, 0x90, 0x97, ++ 0xf6, 0x87, 0x1c, 0x6c, 0x05, 0x2d, 0x3c, 0x5f, ++ 0xc1, 0xba, 0x17, 0xda, 0x9e, 0x32, 0xae, 0x45, ++ 0x84, 0x03, 0xb0, 0x5b, 0xb2, 0x83, 0x09, 0x2a }, ++ .expected_ss = (u8[32]){ 0x4a, 0x06, 0x38, 0xcf, 0xaa, 0x9e, 0xf1, 0x93, ++ 0x3b, 0x47, 0xf8, 0x93, 0x92, 0x96, 0xa6, 0xb2, ++ 0x5b, 0xe5, 0x41, 0xef, 0x7f, 0x70, 0xe8, 0x44, ++ 0xc0, 0xbc, 0xc0, 0x0b, 0x13, 0x4d, 0xe6, 0x4a }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key on twist */ ++{ ++ .secret = (u8[32]){ 0x68, 0xc1, 0xf3, 0xa6, 0x53, 0xa4, 0xcd, 0xb1, ++ 0xd3, 0x7b, 0xba, 0x94, 0x73, 0x8f, 0x8b, 0x95, ++ 0x7a, 0x57, 0xbe, 0xb2, 0x4d, 0x64, 0x6e, 0x99, ++ 0x4d, 0xc2, 0x9a, 0x27, 0x6a, 0xad, 0x45, 0x8d }, ++ .b_public = (u8[32]){ 0x34, 0x3a, 0xc2, 0x0a, 0x3b, 0x9c, 0x6a, 0x27, ++ 0xb1, 0x00, 0x81, 0x76, 0x50, 0x9a, 0xd3, 0x07, ++ 0x35, 0x85, 0x6e, 0xc1, 0xc8, 0xd8, 0xfc, 0xae, ++ 0x13, 0x91, 0x2d, 0x08, 0xd1, 0x52, 0xf4, 0x6c }, ++ .expected_ss = (u8[32]){ 0x39, 0x94, 0x91, 0xfc, 0xe8, 0xdf, 0xab, 0x73, ++ 0xb4, 0xf9, 0xf6, 0x11, 0xde, 0x8e, 0xa0, 0xb2, ++ 0x7b, 0x28, 0xf8, 0x59, 0x94, 0x25, 0x0b, 0x0f, ++ 0x47, 0x5d, 0x58, 0x5d, 0x04, 0x2a, 0xc2, 0x07 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key on twist */ ++{ ++ .secret = (u8[32]){ 0xd8, 0x77, 0xb2, 0x6d, 0x06, 0xdf, 0xf9, 0xd9, ++ 0xf7, 0xfd, 0x4c, 0x5b, 0x37, 0x69, 0xf8, 0xcd, ++ 0xd5, 0xb3, 0x05, 0x16, 0xa5, 0xab, 0x80, 0x6b, ++ 0xe3, 0x24, 0xff, 0x3e, 0xb6, 0x9e, 0xa0, 0xb2 }, ++ .b_public = (u8[32]){ 0xfa, 0x69, 0x5f, 0xc7, 0xbe, 0x8d, 0x1b, 0xe5, ++ 0xbf, 0x70, 0x48, 0x98, 0xf3, 0x88, 0xc4, 0x52, ++ 0xba, 0xfd, 0xd3, 0xb8, 0xea, 0xe8, 0x05, 0xf8, ++ 0x68, 0x1a, 0x8d, 0x15, 0xc2, 0xd4, 0xe1, 0x42 }, ++ .expected_ss = (u8[32]){ 0x2c, 0x4f, 0xe1, 0x1d, 0x49, 0x0a, 0x53, 0x86, ++ 0x17, 0x76, 0xb1, 0x3b, 0x43, 0x54, 0xab, 0xd4, ++ 0xcf, 0x5a, 0x97, 0x69, 0x9d, 0xb6, 0xe6, 0xc6, ++ 0x8c, 0x16, 0x26, 0xd0, 0x76, 0x62, 0xf7, 0x58 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case on twist */ ++{ ++ .secret = (u8[32]){ 0x38, 0xdd, 0xe9, 0xf3, 0xe7, 0xb7, 0x99, 0x04, ++ 0x5f, 0x9a, 0xc3, 0x79, 0x3d, 0x4a, 0x92, 0x77, ++ 0xda, 0xde, 0xad, 0xc4, 0x1b, 0xec, 0x02, 0x90, ++ 0xf8, 0x1f, 0x74, 0x4f, 0x73, 0x77, 0x5f, 0x84 }, ++ .b_public = (u8[32]){ 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .expected_ss = (u8[32]){ 0x9a, 0x2c, 0xfe, 0x84, 0xff, 0x9c, 0x4a, 0x97, ++ 0x39, 0x62, 0x5c, 0xae, 0x4a, 0x3b, 0x82, 0xa9, ++ 0x06, 0x87, 0x7a, 0x44, 0x19, 0x46, 0xf8, 0xd7, ++ 0xb3, 0xd7, 0x95, 0xfe, 0x8f, 0x5d, 0x16, 0x39 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case on twist */ ++{ ++ .secret = (u8[32]){ 0x98, 0x57, 0xa9, 0x14, 0xe3, 0xc2, 0x90, 0x36, ++ 0xfd, 0x9a, 0x44, 0x2b, 0xa5, 0x26, 0xb5, 0xcd, ++ 0xcd, 0xf2, 0x82, 0x16, 0x15, 0x3e, 0x63, 0x6c, ++ 0x10, 0x67, 0x7a, 0xca, 0xb6, 0xbd, 0x6a, 0xa5 }, ++ .b_public = (u8[32]){ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .expected_ss = (u8[32]){ 0x4d, 0xa4, 0xe0, 0xaa, 0x07, 0x2c, 0x23, 0x2e, ++ 0xe2, 0xf0, 0xfa, 0x4e, 0x51, 0x9a, 0xe5, 0x0b, ++ 0x52, 0xc1, 0xed, 0xd0, 0x8a, 0x53, 0x4d, 0x4e, ++ 0xf3, 0x46, 0xc2, 0xe1, 0x06, 0xd2, 0x1d, 0x60 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case on twist */ ++{ ++ .secret = (u8[32]){ 0x48, 0xe2, 0x13, 0x0d, 0x72, 0x33, 0x05, 0xed, ++ 0x05, 0xe6, 0xe5, 0x89, 0x4d, 0x39, 0x8a, 0x5e, ++ 0x33, 0x36, 0x7a, 0x8c, 0x6a, 0xac, 0x8f, 0xcd, ++ 0xf0, 0xa8, 0x8e, 0x4b, 0x42, 0x82, 0x0d, 0xb7 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0x03, 0x00, 0x00, 0xf8, 0xff, ++ 0xff, 0x1f, 0x00, 0x00, 0xc0, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0xfe, 0xff, 0xff, 0x07, 0x00, ++ 0x00, 0xf0, 0xff, 0xff, 0x3f, 0x00, 0x00, 0x00 }, ++ .expected_ss = (u8[32]){ 0x9e, 0xd1, 0x0c, 0x53, 0x74, 0x7f, 0x64, 0x7f, ++ 0x82, 0xf4, 0x51, 0x25, 0xd3, 0xde, 0x15, 0xa1, ++ 0xe6, 0xb8, 0x24, 0x49, 0x6a, 0xb4, 0x04, 0x10, ++ 0xff, 0xcc, 0x3c, 0xfe, 0x95, 0x76, 0x0f, 0x3b }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case on twist */ ++{ ++ .secret = (u8[32]){ 0x28, 0xf4, 0x10, 0x11, 0x69, 0x18, 0x51, 0xb3, ++ 0xa6, 0x2b, 0x64, 0x15, 0x53, 0xb3, 0x0d, 0x0d, ++ 0xfd, 0xdc, 0xb8, 0xff, 0xfc, 0xf5, 0x37, 0x00, ++ 0xa7, 0xbe, 0x2f, 0x6a, 0x87, 0x2e, 0x9f, 0xb0 }, ++ .b_public = (u8[32]){ 0x00, 0x00, 0x00, 0xfc, 0xff, 0xff, 0x07, 0x00, ++ 0x00, 0xe0, 0xff, 0xff, 0x3f, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0x01, 0x00, 0x00, 0xf8, 0xff, ++ 0xff, 0x0f, 0x00, 0x00, 0xc0, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0xcf, 0x72, 0xb4, 0xaa, 0x6a, 0xa1, 0xc9, 0xf8, ++ 0x94, 0xf4, 0x16, 0x5b, 0x86, 0x10, 0x9a, 0xa4, ++ 0x68, 0x51, 0x76, 0x48, 0xe1, 0xf0, 0xcc, 0x70, ++ 0xe1, 0xab, 0x08, 0x46, 0x01, 0x76, 0x50, 0x6b }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case on twist */ ++{ ++ .secret = (u8[32]){ 0x18, 0xa9, 0x3b, 0x64, 0x99, 0xb9, 0xf6, 0xb3, ++ 0x22, 0x5c, 0xa0, 0x2f, 0xef, 0x41, 0x0e, 0x0a, ++ 0xde, 0xc2, 0x35, 0x32, 0x32, 0x1d, 0x2d, 0x8e, ++ 0xf1, 0xa6, 0xd6, 0x02, 0xa8, 0xc6, 0x5b, 0x83 }, ++ .b_public = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0x5d, 0x50, 0xb6, 0x28, 0x36, 0xbb, 0x69, 0x57, ++ 0x94, 0x10, 0x38, 0x6c, 0xf7, 0xbb, 0x81, 0x1c, ++ 0x14, 0xbf, 0x85, 0xb1, 0xc7, 0xb1, 0x7e, 0x59, ++ 0x24, 0xc7, 0xff, 0xea, 0x91, 0xef, 0x9e, 0x12 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case on twist */ ++{ ++ .secret = (u8[32]){ 0xc0, 0x1d, 0x13, 0x05, 0xa1, 0x33, 0x8a, 0x1f, ++ 0xca, 0xc2, 0xba, 0x7e, 0x2e, 0x03, 0x2b, 0x42, ++ 0x7e, 0x0b, 0x04, 0x90, 0x31, 0x65, 0xac, 0xa9, ++ 0x57, 0xd8, 0xd0, 0x55, 0x3d, 0x87, 0x17, 0xb0 }, ++ .b_public = (u8[32]){ 0xea, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0x19, 0x23, 0x0e, 0xb1, 0x48, 0xd5, 0xd6, 0x7c, ++ 0x3c, 0x22, 0xab, 0x1d, 0xae, 0xff, 0x80, 0xa5, ++ 0x7e, 0xae, 0x42, 0x65, 0xce, 0x28, 0x72, 0x65, ++ 0x7b, 0x2c, 0x80, 0x99, 0xfc, 0x69, 0x8e, 0x50 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0x38, 0x6f, 0x7f, 0x16, 0xc5, 0x07, 0x31, 0xd6, ++ 0x4f, 0x82, 0xe6, 0xa1, 0x70, 0xb1, 0x42, 0xa4, ++ 0xe3, 0x4f, 0x31, 0xfd, 0x77, 0x68, 0xfc, 0xb8, ++ 0x90, 0x29, 0x25, 0xe7, 0xd1, 0xe2, 0x1a, 0xbe }, ++ .b_public = (u8[32]){ 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .expected_ss = (u8[32]){ 0x0f, 0xca, 0xb5, 0xd8, 0x42, 0xa0, 0x78, 0xd7, ++ 0xa7, 0x1f, 0xc5, 0x9b, 0x57, 0xbf, 0xb4, 0xca, ++ 0x0b, 0xe6, 0x87, 0x3b, 0x49, 0xdc, 0xdb, 0x9f, ++ 0x44, 0xe1, 0x4a, 0xe8, 0xfb, 0xdf, 0xa5, 0x42 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0xe0, 0x23, 0xa2, 0x89, 0xbd, 0x5e, 0x90, 0xfa, ++ 0x28, 0x04, 0xdd, 0xc0, 0x19, 0xa0, 0x5e, 0xf3, ++ 0xe7, 0x9d, 0x43, 0x4b, 0xb6, 0xea, 0x2f, 0x52, ++ 0x2e, 0xcb, 0x64, 0x3a, 0x75, 0x29, 0x6e, 0x95 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }, ++ .expected_ss = (u8[32]){ 0x54, 0xce, 0x8f, 0x22, 0x75, 0xc0, 0x77, 0xe3, ++ 0xb1, 0x30, 0x6a, 0x39, 0x39, 0xc5, 0xe0, 0x3e, ++ 0xef, 0x6b, 0xbb, 0x88, 0x06, 0x05, 0x44, 0x75, ++ 0x8d, 0x9f, 0xef, 0x59, 0xb0, 0xbc, 0x3e, 0x4f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0x68, 0xf0, 0x10, 0xd6, 0x2e, 0xe8, 0xd9, 0x26, ++ 0x05, 0x3a, 0x36, 0x1c, 0x3a, 0x75, 0xc6, 0xea, ++ 0x4e, 0xbd, 0xc8, 0x60, 0x6a, 0xb2, 0x85, 0x00, ++ 0x3a, 0x6f, 0x8f, 0x40, 0x76, 0xb0, 0x1e, 0x83 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x03 }, ++ .expected_ss = (u8[32]){ 0xf1, 0x36, 0x77, 0x5c, 0x5b, 0xeb, 0x0a, 0xf8, ++ 0x11, 0x0a, 0xf1, 0x0b, 0x20, 0x37, 0x23, 0x32, ++ 0x04, 0x3c, 0xab, 0x75, 0x24, 0x19, 0x67, 0x87, ++ 0x75, 0xa2, 0x23, 0xdf, 0x57, 0xc9, 0xd3, 0x0d }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0x58, 0xeb, 0xcb, 0x35, 0xb0, 0xf8, 0x84, 0x5c, ++ 0xaf, 0x1e, 0xc6, 0x30, 0xf9, 0x65, 0x76, 0xb6, ++ 0x2c, 0x4b, 0x7b, 0x6c, 0x36, 0xb2, 0x9d, 0xeb, ++ 0x2c, 0xb0, 0x08, 0x46, 0x51, 0x75, 0x5c, 0x96 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xfb, 0xff, 0xff, 0xfb, 0xff, ++ 0xff, 0xdf, 0xff, 0xff, 0xdf, 0xff, 0xff, 0xff, ++ 0xfe, 0xff, 0xff, 0xfe, 0xff, 0xff, 0xf7, 0xff, ++ 0xff, 0xf7, 0xff, 0xff, 0xbf, 0xff, 0xff, 0x3f }, ++ .expected_ss = (u8[32]){ 0xbf, 0x9a, 0xff, 0xd0, 0x6b, 0x84, 0x40, 0x85, ++ 0x58, 0x64, 0x60, 0x96, 0x2e, 0xf2, 0x14, 0x6f, ++ 0xf3, 0xd4, 0x53, 0x3d, 0x94, 0x44, 0xaa, 0xb0, ++ 0x06, 0xeb, 0x88, 0xcc, 0x30, 0x54, 0x40, 0x7d }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0x18, 0x8c, 0x4b, 0xc5, 0xb9, 0xc4, 0x4b, 0x38, ++ 0xbb, 0x65, 0x8b, 0x9b, 0x2a, 0xe8, 0x2d, 0x5b, ++ 0x01, 0x01, 0x5e, 0x09, 0x31, 0x84, 0xb1, 0x7c, ++ 0xb7, 0x86, 0x35, 0x03, 0xa7, 0x83, 0xe1, 0xbb }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .expected_ss = (u8[32]){ 0xd4, 0x80, 0xde, 0x04, 0xf6, 0x99, 0xcb, 0x3b, ++ 0xe0, 0x68, 0x4a, 0x9c, 0xc2, 0xe3, 0x12, 0x81, ++ 0xea, 0x0b, 0xc5, 0xa9, 0xdc, 0xc1, 0x57, 0xd3, ++ 0xd2, 0x01, 0x58, 0xd4, 0x6c, 0xa5, 0x24, 0x6d }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0xe0, 0x6c, 0x11, 0xbb, 0x2e, 0x13, 0xce, 0x3d, ++ 0xc7, 0x67, 0x3f, 0x67, 0xf5, 0x48, 0x22, 0x42, ++ 0x90, 0x94, 0x23, 0xa9, 0xae, 0x95, 0xee, 0x98, ++ 0x6a, 0x98, 0x8d, 0x98, 0xfa, 0xee, 0x23, 0xa2 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0x4c, 0x44, 0x01, 0xcc, 0xe6, 0xb5, 0x1e, 0x4c, ++ 0xb1, 0x8f, 0x27, 0x90, 0x24, 0x6c, 0x9b, 0xf9, ++ 0x14, 0xdb, 0x66, 0x77, 0x50, 0xa1, 0xcb, 0x89, ++ 0x06, 0x90, 0x92, 0xaf, 0x07, 0x29, 0x22, 0x76 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for public key */ ++{ ++ .secret = (u8[32]){ 0xc0, 0x65, 0x8c, 0x46, 0xdd, 0xe1, 0x81, 0x29, ++ 0x29, 0x38, 0x77, 0x53, 0x5b, 0x11, 0x62, 0xb6, ++ 0xf9, 0xf5, 0x41, 0x4a, 0x23, 0xcf, 0x4d, 0x2c, ++ 0xbc, 0x14, 0x0a, 0x4d, 0x99, 0xda, 0x2b, 0x8f }, ++ .b_public = (u8[32]){ 0xeb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0x57, 0x8b, 0xa8, 0xcc, 0x2d, 0xbd, 0xc5, 0x75, ++ 0xaf, 0xcf, 0x9d, 0xf2, 0xb3, 0xee, 0x61, 0x89, ++ 0xf5, 0x33, 0x7d, 0x68, 0x54, 0xc7, 0x9b, 0x4c, ++ 0xe1, 0x65, 0xea, 0x12, 0x29, 0x3b, 0x3a, 0x0f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0xf0, 0x1e, 0x48, 0xda, 0xfa, 0xc9, 0xd7, 0xbc, ++ 0xf5, 0x89, 0xcb, 0xc3, 0x82, 0xc8, 0x78, 0xd1, ++ 0x8b, 0xda, 0x35, 0x50, 0x58, 0x9f, 0xfb, 0x5d, ++ 0x50, 0xb5, 0x23, 0xbe, 0xbe, 0x32, 0x9d, 0xae }, ++ .b_public = (u8[32]){ 0xef, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0xbd, 0x36, 0xa0, 0x79, 0x0e, 0xb8, 0x83, 0x09, ++ 0x8c, 0x98, 0x8b, 0x21, 0x78, 0x67, 0x73, 0xde, ++ 0x0b, 0x3a, 0x4d, 0xf1, 0x62, 0x28, 0x2c, 0xf1, ++ 0x10, 0xde, 0x18, 0xdd, 0x48, 0x4c, 0xe7, 0x4b }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x28, 0x87, 0x96, 0xbc, 0x5a, 0xff, 0x4b, 0x81, ++ 0xa3, 0x75, 0x01, 0x75, 0x7b, 0xc0, 0x75, 0x3a, ++ 0x3c, 0x21, 0x96, 0x47, 0x90, 0xd3, 0x86, 0x99, ++ 0x30, 0x8d, 0xeb, 0xc1, 0x7a, 0x6e, 0xaf, 0x8d }, ++ .b_public = (u8[32]){ 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0xb4, 0xe0, 0xdd, 0x76, 0xda, 0x7b, 0x07, 0x17, ++ 0x28, 0xb6, 0x1f, 0x85, 0x67, 0x71, 0xaa, 0x35, ++ 0x6e, 0x57, 0xed, 0xa7, 0x8a, 0x5b, 0x16, 0x55, ++ 0xcc, 0x38, 0x20, 0xfb, 0x5f, 0x85, 0x4c, 0x5c }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x98, 0xdf, 0x84, 0x5f, 0x66, 0x51, 0xbf, 0x11, ++ 0x38, 0x22, 0x1f, 0x11, 0x90, 0x41, 0xf7, 0x2b, ++ 0x6d, 0xbc, 0x3c, 0x4a, 0xce, 0x71, 0x43, 0xd9, ++ 0x9f, 0xd5, 0x5a, 0xd8, 0x67, 0x48, 0x0d, 0xa8 }, ++ .b_public = (u8[32]){ 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0x6f, 0xdf, 0x6c, 0x37, 0x61, 0x1d, 0xbd, 0x53, ++ 0x04, 0xdc, 0x0f, 0x2e, 0xb7, 0xc9, 0x51, 0x7e, ++ 0xb3, 0xc5, 0x0e, 0x12, 0xfd, 0x05, 0x0a, 0xc6, ++ 0xde, 0xc2, 0x70, 0x71, 0xd4, 0xbf, 0xc0, 0x34 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0xf0, 0x94, 0x98, 0xe4, 0x6f, 0x02, 0xf8, 0x78, ++ 0x82, 0x9e, 0x78, 0xb8, 0x03, 0xd3, 0x16, 0xa2, ++ 0xed, 0x69, 0x5d, 0x04, 0x98, 0xa0, 0x8a, 0xbd, ++ 0xf8, 0x27, 0x69, 0x30, 0xe2, 0x4e, 0xdc, 0xb0 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .expected_ss = (u8[32]){ 0x4c, 0x8f, 0xc4, 0xb1, 0xc6, 0xab, 0x88, 0xfb, ++ 0x21, 0xf1, 0x8f, 0x6d, 0x4c, 0x81, 0x02, 0x40, ++ 0xd4, 0xe9, 0x46, 0x51, 0xba, 0x44, 0xf7, 0xa2, ++ 0xc8, 0x63, 0xce, 0xc7, 0xdc, 0x56, 0x60, 0x2d }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x18, 0x13, 0xc1, 0x0a, 0x5c, 0x7f, 0x21, 0xf9, ++ 0x6e, 0x17, 0xf2, 0x88, 0xc0, 0xcc, 0x37, 0x60, ++ 0x7c, 0x04, 0xc5, 0xf5, 0xae, 0xa2, 0xdb, 0x13, ++ 0x4f, 0x9e, 0x2f, 0xfc, 0x66, 0xbd, 0x9d, 0xb8 }, ++ .b_public = (u8[32]){ 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .expected_ss = (u8[32]){ 0x1c, 0xd0, 0xb2, 0x82, 0x67, 0xdc, 0x54, 0x1c, ++ 0x64, 0x2d, 0x6d, 0x7d, 0xca, 0x44, 0xa8, 0xb3, ++ 0x8a, 0x63, 0x73, 0x6e, 0xef, 0x5c, 0x4e, 0x65, ++ 0x01, 0xff, 0xbb, 0xb1, 0x78, 0x0c, 0x03, 0x3c }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x78, 0x57, 0xfb, 0x80, 0x86, 0x53, 0x64, 0x5a, ++ 0x0b, 0xeb, 0x13, 0x8a, 0x64, 0xf5, 0xf4, 0xd7, ++ 0x33, 0xa4, 0x5e, 0xa8, 0x4c, 0x3c, 0xda, 0x11, ++ 0xa9, 0xc0, 0x6f, 0x7e, 0x71, 0x39, 0x14, 0x9e }, ++ .b_public = (u8[32]){ 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .expected_ss = (u8[32]){ 0x87, 0x55, 0xbe, 0x01, 0xc6, 0x0a, 0x7e, 0x82, ++ 0x5c, 0xff, 0x3e, 0x0e, 0x78, 0xcb, 0x3a, 0xa4, ++ 0x33, 0x38, 0x61, 0x51, 0x6a, 0xa5, 0x9b, 0x1c, ++ 0x51, 0xa8, 0xb2, 0xa5, 0x43, 0xdf, 0xa8, 0x22 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0xe0, 0x3a, 0xa8, 0x42, 0xe2, 0xab, 0xc5, 0x6e, ++ 0x81, 0xe8, 0x7b, 0x8b, 0x9f, 0x41, 0x7b, 0x2a, ++ 0x1e, 0x59, 0x13, 0xc7, 0x23, 0xee, 0xd2, 0x8d, ++ 0x75, 0x2f, 0x8d, 0x47, 0xa5, 0x9f, 0x49, 0x8f }, ++ .b_public = (u8[32]){ 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .expected_ss = (u8[32]){ 0x54, 0xc9, 0xa1, 0xed, 0x95, 0xe5, 0x46, 0xd2, ++ 0x78, 0x22, 0xa3, 0x60, 0x93, 0x1d, 0xda, 0x60, ++ 0xa1, 0xdf, 0x04, 0x9d, 0xa6, 0xf9, 0x04, 0x25, ++ 0x3c, 0x06, 0x12, 0xbb, 0xdc, 0x08, 0x74, 0x76 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0xf8, 0xf7, 0x07, 0xb7, 0x99, 0x9b, 0x18, 0xcb, ++ 0x0d, 0x6b, 0x96, 0x12, 0x4f, 0x20, 0x45, 0x97, ++ 0x2c, 0xa2, 0x74, 0xbf, 0xc1, 0x54, 0xad, 0x0c, ++ 0x87, 0x03, 0x8c, 0x24, 0xc6, 0xd0, 0xd4, 0xb2 }, ++ .b_public = (u8[32]){ 0xda, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0xcc, 0x1f, 0x40, 0xd7, 0x43, 0xcd, 0xc2, 0x23, ++ 0x0e, 0x10, 0x43, 0xda, 0xba, 0x8b, 0x75, 0xe8, ++ 0x10, 0xf1, 0xfb, 0xab, 0x7f, 0x25, 0x52, 0x69, ++ 0xbd, 0x9e, 0xbb, 0x29, 0xe6, 0xbf, 0x49, 0x4f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0xa0, 0x34, 0xf6, 0x84, 0xfa, 0x63, 0x1e, 0x1a, ++ 0x34, 0x81, 0x18, 0xc1, 0xce, 0x4c, 0x98, 0x23, ++ 0x1f, 0x2d, 0x9e, 0xec, 0x9b, 0xa5, 0x36, 0x5b, ++ 0x4a, 0x05, 0xd6, 0x9a, 0x78, 0x5b, 0x07, 0x96 }, ++ .b_public = (u8[32]){ 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0x54, 0x99, 0x8e, 0xe4, 0x3a, 0x5b, 0x00, 0x7b, ++ 0xf4, 0x99, 0xf0, 0x78, 0xe7, 0x36, 0x52, 0x44, ++ 0x00, 0xa8, 0xb5, 0xc7, 0xe9, 0xb9, 0xb4, 0x37, ++ 0x71, 0x74, 0x8c, 0x7c, 0xdf, 0x88, 0x04, 0x12 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x30, 0xb6, 0xc6, 0xa0, 0xf2, 0xff, 0xa6, 0x80, ++ 0x76, 0x8f, 0x99, 0x2b, 0xa8, 0x9e, 0x15, 0x2d, ++ 0x5b, 0xc9, 0x89, 0x3d, 0x38, 0xc9, 0x11, 0x9b, ++ 0xe4, 0xf7, 0x67, 0xbf, 0xab, 0x6e, 0x0c, 0xa5 }, ++ .b_public = (u8[32]){ 0xdc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0xea, 0xd9, 0xb3, 0x8e, 0xfd, 0xd7, 0x23, 0x63, ++ 0x79, 0x34, 0xe5, 0x5a, 0xb7, 0x17, 0xa7, 0xae, ++ 0x09, 0xeb, 0x86, 0xa2, 0x1d, 0xc3, 0x6a, 0x3f, ++ 0xee, 0xb8, 0x8b, 0x75, 0x9e, 0x39, 0x1e, 0x09 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x90, 0x1b, 0x9d, 0xcf, 0x88, 0x1e, 0x01, 0xe0, ++ 0x27, 0x57, 0x50, 0x35, 0xd4, 0x0b, 0x43, 0xbd, ++ 0xc1, 0xc5, 0x24, 0x2e, 0x03, 0x08, 0x47, 0x49, ++ 0x5b, 0x0c, 0x72, 0x86, 0x46, 0x9b, 0x65, 0x91 }, ++ .b_public = (u8[32]){ 0xea, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0x60, 0x2f, 0xf4, 0x07, 0x89, 0xb5, 0x4b, 0x41, ++ 0x80, 0x59, 0x15, 0xfe, 0x2a, 0x62, 0x21, 0xf0, ++ 0x7a, 0x50, 0xff, 0xc2, 0xc3, 0xfc, 0x94, 0xcf, ++ 0x61, 0xf1, 0x3d, 0x79, 0x04, 0xe8, 0x8e, 0x0e }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x80, 0x46, 0x67, 0x7c, 0x28, 0xfd, 0x82, 0xc9, ++ 0xa1, 0xbd, 0xb7, 0x1a, 0x1a, 0x1a, 0x34, 0xfa, ++ 0xba, 0x12, 0x25, 0xe2, 0x50, 0x7f, 0xe3, 0xf5, ++ 0x4d, 0x10, 0xbd, 0x5b, 0x0d, 0x86, 0x5f, 0x8e }, ++ .b_public = (u8[32]){ 0xeb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0xe0, 0x0a, 0xe8, 0xb1, 0x43, 0x47, 0x12, 0x47, ++ 0xba, 0x24, 0xf1, 0x2c, 0x88, 0x55, 0x36, 0xc3, ++ 0xcb, 0x98, 0x1b, 0x58, 0xe1, 0xe5, 0x6b, 0x2b, ++ 0xaf, 0x35, 0xc1, 0x2a, 0xe1, 0xf7, 0x9c, 0x26 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x60, 0x2f, 0x7e, 0x2f, 0x68, 0xa8, 0x46, 0xb8, ++ 0x2c, 0xc2, 0x69, 0xb1, 0xd4, 0x8e, 0x93, 0x98, ++ 0x86, 0xae, 0x54, 0xfd, 0x63, 0x6c, 0x1f, 0xe0, ++ 0x74, 0xd7, 0x10, 0x12, 0x7d, 0x47, 0x24, 0x91 }, ++ .b_public = (u8[32]){ 0xef, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0x98, 0xcb, 0x9b, 0x50, 0xdd, 0x3f, 0xc2, 0xb0, ++ 0xd4, 0xf2, 0xd2, 0xbf, 0x7c, 0x5c, 0xfd, 0xd1, ++ 0x0c, 0x8f, 0xcd, 0x31, 0xfc, 0x40, 0xaf, 0x1a, ++ 0xd4, 0x4f, 0x47, 0xc1, 0x31, 0x37, 0x63, 0x62 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x60, 0x88, 0x7b, 0x3d, 0xc7, 0x24, 0x43, 0x02, ++ 0x6e, 0xbe, 0xdb, 0xbb, 0xb7, 0x06, 0x65, 0xf4, ++ 0x2b, 0x87, 0xad, 0xd1, 0x44, 0x0e, 0x77, 0x68, ++ 0xfb, 0xd7, 0xe8, 0xe2, 0xce, 0x5f, 0x63, 0x9d }, ++ .b_public = (u8[32]){ 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0x38, 0xd6, 0x30, 0x4c, 0x4a, 0x7e, 0x6d, 0x9f, ++ 0x79, 0x59, 0x33, 0x4f, 0xb5, 0x24, 0x5b, 0xd2, ++ 0xc7, 0x54, 0x52, 0x5d, 0x4c, 0x91, 0xdb, 0x95, ++ 0x02, 0x06, 0x92, 0x62, 0x34, 0xc1, 0xf6, 0x33 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0x78, 0xd3, 0x1d, 0xfa, 0x85, 0x44, 0x97, 0xd7, ++ 0x2d, 0x8d, 0xef, 0x8a, 0x1b, 0x7f, 0xb0, 0x06, ++ 0xce, 0xc2, 0xd8, 0xc4, 0x92, 0x46, 0x47, 0xc9, ++ 0x38, 0x14, 0xae, 0x56, 0xfa, 0xed, 0xa4, 0x95 }, ++ .b_public = (u8[32]){ 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0x78, 0x6c, 0xd5, 0x49, 0x96, 0xf0, 0x14, 0xa5, ++ 0xa0, 0x31, 0xec, 0x14, 0xdb, 0x81, 0x2e, 0xd0, ++ 0x83, 0x55, 0x06, 0x1f, 0xdb, 0x5d, 0xe6, 0x80, ++ 0xa8, 0x00, 0xac, 0x52, 0x1f, 0x31, 0x8e, 0x23 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - public key >= p */ ++{ ++ .secret = (u8[32]){ 0xc0, 0x4c, 0x5b, 0xae, 0xfa, 0x83, 0x02, 0xdd, ++ 0xde, 0xd6, 0xa4, 0xbb, 0x95, 0x77, 0x61, 0xb4, ++ 0xeb, 0x97, 0xae, 0xfa, 0x4f, 0xc3, 0xb8, 0x04, ++ 0x30, 0x85, 0xf9, 0x6a, 0x56, 0x59, 0xb3, 0xa5 }, ++ .b_public = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .expected_ss = (u8[32]){ 0x29, 0xae, 0x8b, 0xc7, 0x3e, 0x9b, 0x10, 0xa0, ++ 0x8b, 0x4f, 0x68, 0x1c, 0x43, 0xc3, 0xe0, 0xac, ++ 0x1a, 0x17, 0x1d, 0x31, 0xb3, 0x8f, 0x1a, 0x48, ++ 0xef, 0xba, 0x29, 0xae, 0x63, 0x9e, 0xa1, 0x34 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - RFC 7748 */ ++{ ++ .secret = (u8[32]){ 0xa0, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d, ++ 0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd, ++ 0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18, ++ 0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0x44 }, ++ .b_public = (u8[32]){ 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb, ++ 0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c, ++ 0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b, ++ 0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c }, ++ .expected_ss = (u8[32]){ 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90, ++ 0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f, ++ 0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7, ++ 0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - RFC 7748 */ ++{ ++ .secret = (u8[32]){ 0x48, 0x66, 0xe9, 0xd4, 0xd1, 0xb4, 0x67, 0x3c, ++ 0x5a, 0xd2, 0x26, 0x91, 0x95, 0x7d, 0x6a, 0xf5, ++ 0xc1, 0x1b, 0x64, 0x21, 0xe0, 0xea, 0x01, 0xd4, ++ 0x2c, 0xa4, 0x16, 0x9e, 0x79, 0x18, 0xba, 0x4d }, ++ .b_public = (u8[32]){ 0xe5, 0x21, 0x0f, 0x12, 0x78, 0x68, 0x11, 0xd3, ++ 0xf4, 0xb7, 0x95, 0x9d, 0x05, 0x38, 0xae, 0x2c, ++ 0x31, 0xdb, 0xe7, 0x10, 0x6f, 0xc0, 0x3c, 0x3e, ++ 0xfc, 0x4c, 0xd5, 0x49, 0xc7, 0x15, 0xa4, 0x13 }, ++ .expected_ss = (u8[32]){ 0x95, 0xcb, 0xde, 0x94, 0x76, 0xe8, 0x90, 0x7d, ++ 0x7a, 0xad, 0xe4, 0x5c, 0xb4, 0xb8, 0x73, 0xf8, ++ 0x8b, 0x59, 0x5a, 0x68, 0x79, 0x9f, 0xa1, 0x52, ++ 0xe6, 0xf8, 0xf7, 0x64, 0x7a, 0xac, 0x79, 0x57 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x0a, 0xb4, 0xe7, 0x63, 0x80, 0xd8, 0x4d, 0xde, ++ 0x4f, 0x68, 0x33, 0xc5, 0x8f, 0x2a, 0x9f, 0xb8, ++ 0xf8, 0x3b, 0xb0, 0x16, 0x9b, 0x17, 0x2b, 0xe4, ++ 0xb6, 0xe0, 0x59, 0x28, 0x87, 0x74, 0x1a, 0x36 }, ++ .expected_ss = (u8[32]){ 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x89, 0xe1, 0x0d, 0x57, 0x01, 0xb4, 0x33, 0x7d, ++ 0x2d, 0x03, 0x21, 0x81, 0x53, 0x8b, 0x10, 0x64, ++ 0xbd, 0x40, 0x84, 0x40, 0x1c, 0xec, 0xa1, 0xfd, ++ 0x12, 0x66, 0x3a, 0x19, 0x59, 0x38, 0x80, 0x00 }, ++ .expected_ss = (u8[32]){ 0x09, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x2b, 0x55, 0xd3, 0xaa, 0x4a, 0x8f, 0x80, 0xc8, ++ 0xc0, 0xb2, 0xae, 0x5f, 0x93, 0x3e, 0x85, 0xaf, ++ 0x49, 0xbe, 0xac, 0x36, 0xc2, 0xfa, 0x73, 0x94, ++ 0xba, 0xb7, 0x6c, 0x89, 0x33, 0xf8, 0xf8, 0x1d }, ++ .expected_ss = (u8[32]){ 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x63, 0xe5, 0xb1, 0xfe, 0x96, 0x01, 0xfe, 0x84, ++ 0x38, 0x5d, 0x88, 0x66, 0xb0, 0x42, 0x12, 0x62, ++ 0xf7, 0x8f, 0xbf, 0xa5, 0xaf, 0xf9, 0x58, 0x5e, ++ 0x62, 0x66, 0x79, 0xb1, 0x85, 0x47, 0xd9, 0x59 }, ++ .expected_ss = (u8[32]){ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0xe4, 0x28, 0xf3, 0xda, 0xc1, 0x78, 0x09, 0xf8, ++ 0x27, 0xa5, 0x22, 0xce, 0x32, 0x35, 0x50, 0x58, ++ 0xd0, 0x73, 0x69, 0x36, 0x4a, 0xa7, 0x89, 0x02, ++ 0xee, 0x10, 0x13, 0x9b, 0x9f, 0x9d, 0xd6, 0x53 }, ++ .expected_ss = (u8[32]){ 0xfc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0xb3, 0xb5, 0x0e, 0x3e, 0xd3, 0xa4, 0x07, 0xb9, ++ 0x5d, 0xe9, 0x42, 0xef, 0x74, 0x57, 0x5b, 0x5a, ++ 0xb8, 0xa1, 0x0c, 0x09, 0xee, 0x10, 0x35, 0x44, ++ 0xd6, 0x0b, 0xdf, 0xed, 0x81, 0x38, 0xab, 0x2b }, ++ .expected_ss = (u8[32]){ 0xf9, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x21, 0x3f, 0xff, 0xe9, 0x3d, 0x5e, 0xa8, 0xcd, ++ 0x24, 0x2e, 0x46, 0x28, 0x44, 0x02, 0x99, 0x22, ++ 0xc4, 0x3c, 0x77, 0xc9, 0xe3, 0xe4, 0x2f, 0x56, ++ 0x2f, 0x48, 0x5d, 0x24, 0xc5, 0x01, 0xa2, 0x0b }, ++ .expected_ss = (u8[32]){ 0xf3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x91, 0xb2, 0x32, 0xa1, 0x78, 0xb3, 0xcd, 0x53, ++ 0x09, 0x32, 0x44, 0x1e, 0x61, 0x39, 0x41, 0x8f, ++ 0x72, 0x17, 0x22, 0x92, 0xf1, 0xda, 0x4c, 0x18, ++ 0x34, 0xfc, 0x5e, 0xbf, 0xef, 0xb5, 0x1e, 0x3f }, ++ .expected_ss = (u8[32]){ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x03 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x04, 0x5c, 0x6e, 0x11, 0xc5, 0xd3, 0x32, 0x55, ++ 0x6c, 0x78, 0x22, 0xfe, 0x94, 0xeb, 0xf8, 0x9b, ++ 0x56, 0xa3, 0x87, 0x8d, 0xc2, 0x7c, 0xa0, 0x79, ++ 0x10, 0x30, 0x58, 0x84, 0x9f, 0xab, 0xcb, 0x4f }, ++ .expected_ss = (u8[32]){ 0xe5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x1c, 0xa2, 0x19, 0x0b, 0x71, 0x16, 0x35, 0x39, ++ 0x06, 0x3c, 0x35, 0x77, 0x3b, 0xda, 0x0c, 0x9c, ++ 0x92, 0x8e, 0x91, 0x36, 0xf0, 0x62, 0x0a, 0xeb, ++ 0x09, 0x3f, 0x09, 0x91, 0x97, 0xb7, 0xf7, 0x4e }, ++ .expected_ss = (u8[32]){ 0xe3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0xf7, 0x6e, 0x90, 0x10, 0xac, 0x33, 0xc5, 0x04, ++ 0x3b, 0x2d, 0x3b, 0x76, 0xa8, 0x42, 0x17, 0x10, ++ 0x00, 0xc4, 0x91, 0x62, 0x22, 0xe9, 0xe8, 0x58, ++ 0x97, 0xa0, 0xae, 0xc7, 0xf6, 0x35, 0x0b, 0x3c }, ++ .expected_ss = (u8[32]){ 0xdd, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0xbb, 0x72, 0x68, 0x8d, 0x8f, 0x8a, 0xa7, 0xa3, ++ 0x9c, 0xd6, 0x06, 0x0c, 0xd5, 0xc8, 0x09, 0x3c, ++ 0xde, 0xc6, 0xfe, 0x34, 0x19, 0x37, 0xc3, 0x88, ++ 0x6a, 0x99, 0x34, 0x6c, 0xd0, 0x7f, 0xaa, 0x55 }, ++ .expected_ss = (u8[32]){ 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x88, 0xfd, 0xde, 0xa1, 0x93, 0x39, 0x1c, 0x6a, ++ 0x59, 0x33, 0xef, 0x9b, 0x71, 0x90, 0x15, 0x49, ++ 0x44, 0x72, 0x05, 0xaa, 0xe9, 0xda, 0x92, 0x8a, ++ 0x6b, 0x91, 0xa3, 0x52, 0xba, 0x10, 0xf4, 0x1f }, ++ .expected_ss = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - edge case for shared secret */ ++{ ++ .secret = (u8[32]){ 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .b_public = (u8[32]){ 0x30, 0x3b, 0x39, 0x2f, 0x15, 0x31, 0x16, 0xca, ++ 0xd9, 0xcc, 0x68, 0x2a, 0x00, 0xcc, 0xc4, 0x4c, ++ 0x95, 0xff, 0x0d, 0x3b, 0xbe, 0x56, 0x8b, 0xeb, ++ 0x6c, 0x4e, 0x73, 0x9b, 0xaf, 0xdc, 0x2c, 0x68 }, ++ .expected_ss = (u8[32]){ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - checking for overflow */ ++{ ++ .secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .b_public = (u8[32]){ 0xfd, 0x30, 0x0a, 0xeb, 0x40, 0xe1, 0xfa, 0x58, ++ 0x25, 0x18, 0x41, 0x2b, 0x49, 0xb2, 0x08, 0xa7, ++ 0x84, 0x2b, 0x1e, 0x1f, 0x05, 0x6a, 0x04, 0x01, ++ 0x78, 0xea, 0x41, 0x41, 0x53, 0x4f, 0x65, 0x2d }, ++ .expected_ss = (u8[32]){ 0xb7, 0x34, 0x10, 0x5d, 0xc2, 0x57, 0x58, 0x5d, ++ 0x73, 0xb5, 0x66, 0xcc, 0xb7, 0x6f, 0x06, 0x27, ++ 0x95, 0xcc, 0xbe, 0xc8, 0x91, 0x28, 0xe5, 0x2b, ++ 0x02, 0xf3, 0xe5, 0x96, 0x39, 0xf1, 0x3c, 0x46 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - checking for overflow */ ++{ ++ .secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .b_public = (u8[32]){ 0xc8, 0xef, 0x79, 0xb5, 0x14, 0xd7, 0x68, 0x26, ++ 0x77, 0xbc, 0x79, 0x31, 0xe0, 0x6e, 0xe5, 0xc2, ++ 0x7c, 0x9b, 0x39, 0x2b, 0x4a, 0xe9, 0x48, 0x44, ++ 0x73, 0xf5, 0x54, 0xe6, 0x67, 0x8e, 0xcc, 0x2e }, ++ .expected_ss = (u8[32]){ 0x64, 0x7a, 0x46, 0xb6, 0xfc, 0x3f, 0x40, 0xd6, ++ 0x21, 0x41, 0xee, 0x3c, 0xee, 0x70, 0x6b, 0x4d, ++ 0x7a, 0x92, 0x71, 0x59, 0x3a, 0x7b, 0x14, 0x3e, ++ 0x8e, 0x2e, 0x22, 0x79, 0x88, 0x3e, 0x45, 0x50 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - checking for overflow */ ++{ ++ .secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .b_public = (u8[32]){ 0x64, 0xae, 0xac, 0x25, 0x04, 0x14, 0x48, 0x61, ++ 0x53, 0x2b, 0x7b, 0xbc, 0xb6, 0xc8, 0x7d, 0x67, ++ 0xdd, 0x4c, 0x1f, 0x07, 0xeb, 0xc2, 0xe0, 0x6e, ++ 0xff, 0xb9, 0x5a, 0xec, 0xc6, 0x17, 0x0b, 0x2c }, ++ .expected_ss = (u8[32]){ 0x4f, 0xf0, 0x3d, 0x5f, 0xb4, 0x3c, 0xd8, 0x65, ++ 0x7a, 0x3c, 0xf3, 0x7c, 0x13, 0x8c, 0xad, 0xce, ++ 0xcc, 0xe5, 0x09, 0xe4, 0xeb, 0xa0, 0x89, 0xd0, ++ 0xef, 0x40, 0xb4, 0xe4, 0xfb, 0x94, 0x61, 0x55 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - checking for overflow */ ++{ ++ .secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .b_public = (u8[32]){ 0xbf, 0x68, 0xe3, 0x5e, 0x9b, 0xdb, 0x7e, 0xee, ++ 0x1b, 0x50, 0x57, 0x02, 0x21, 0x86, 0x0f, 0x5d, ++ 0xcd, 0xad, 0x8a, 0xcb, 0xab, 0x03, 0x1b, 0x14, ++ 0x97, 0x4c, 0xc4, 0x90, 0x13, 0xc4, 0x98, 0x31 }, ++ .expected_ss = (u8[32]){ 0x21, 0xce, 0xe5, 0x2e, 0xfd, 0xbc, 0x81, 0x2e, ++ 0x1d, 0x02, 0x1a, 0x4a, 0xf1, 0xe1, 0xd8, 0xbc, ++ 0x4d, 0xb3, 0xc4, 0x00, 0xe4, 0xd2, 0xa2, 0xc5, ++ 0x6a, 0x39, 0x26, 0xdb, 0x4d, 0x99, 0xc6, 0x5b }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - checking for overflow */ ++{ ++ .secret = (u8[32]){ 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .b_public = (u8[32]){ 0x53, 0x47, 0xc4, 0x91, 0x33, 0x1a, 0x64, 0xb4, ++ 0x3d, 0xdc, 0x68, 0x30, 0x34, 0xe6, 0x77, 0xf5, ++ 0x3d, 0xc3, 0x2b, 0x52, 0xa5, 0x2a, 0x57, 0x7c, ++ 0x15, 0xa8, 0x3b, 0xf2, 0x98, 0xe9, 0x9f, 0x19 }, ++ .expected_ss = (u8[32]){ 0x18, 0xcb, 0x89, 0xe4, 0xe2, 0x0c, 0x0c, 0x2b, ++ 0xd3, 0x24, 0x30, 0x52, 0x45, 0x26, 0x6c, 0x93, ++ 0x27, 0x69, 0x0b, 0xbe, 0x79, 0xac, 0xb8, 0x8f, ++ 0x5b, 0x8f, 0xb3, 0xf7, 0x4e, 0xca, 0x3e, 0x52 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - private key == -1 (mod order) */ ++{ ++ .secret = (u8[32]){ 0xa0, 0x23, 0xcd, 0xd0, 0x83, 0xef, 0x5b, 0xb8, ++ 0x2f, 0x10, 0xd6, 0x2e, 0x59, 0xe1, 0x5a, 0x68, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50 }, ++ .b_public = (u8[32]){ 0x25, 0x8e, 0x04, 0x52, 0x3b, 0x8d, 0x25, 0x3e, ++ 0xe6, 0x57, 0x19, 0xfc, 0x69, 0x06, 0xc6, 0x57, ++ 0x19, 0x2d, 0x80, 0x71, 0x7e, 0xdc, 0x82, 0x8f, ++ 0xa0, 0xaf, 0x21, 0x68, 0x6e, 0x2f, 0xaa, 0x75 }, ++ .expected_ss = (u8[32]){ 0x25, 0x8e, 0x04, 0x52, 0x3b, 0x8d, 0x25, 0x3e, ++ 0xe6, 0x57, 0x19, 0xfc, 0x69, 0x06, 0xc6, 0x57, ++ 0x19, 0x2d, 0x80, 0x71, 0x7e, 0xdc, 0x82, 0x8f, ++ 0xa0, 0xaf, 0x21, 0x68, 0x6e, 0x2f, 0xaa, 0x75 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++}, ++/* wycheproof - private key == 1 (mod order) on twist */ ++{ ++ .secret = (u8[32]){ 0x58, 0x08, 0x3d, 0xd2, 0x61, 0xad, 0x91, 0xef, ++ 0xf9, 0x52, 0x32, 0x2e, 0xc8, 0x24, 0xc6, 0x82, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5f }, ++ .b_public = (u8[32]){ 0x2e, 0xae, 0x5e, 0xc3, 0xdd, 0x49, 0x4e, 0x9f, ++ 0x2d, 0x37, 0xd2, 0x58, 0xf8, 0x73, 0xa8, 0xe6, ++ 0xe9, 0xd0, 0xdb, 0xd1, 0xe3, 0x83, 0xef, 0x64, ++ 0xd9, 0x8b, 0xb9, 0x1b, 0x3e, 0x0b, 0xe0, 0x35 }, ++ .expected_ss = (u8[32]){ 0x2e, 0xae, 0x5e, 0xc3, 0xdd, 0x49, 0x4e, 0x9f, ++ 0x2d, 0x37, 0xd2, 0x58, 0xf8, 0x73, 0xa8, 0xe6, ++ 0xe9, 0xd0, 0xdb, 0xd1, 0xe3, 0x83, 0xef, 0x64, ++ 0xd9, 0x8b, 0xb9, 0x1b, 0x3e, 0x0b, 0xe0, 0x35 }, ++ .secret_size = 32, ++ .b_public_size = 32, ++ .expected_ss_size = 32, ++ ++} ++}; ++ + static const struct kpp_testvec ecdh_tv_template[] = { + { + #ifndef CONFIG_CRYPTO_FIPS diff --git a/target/linux/generic/backport-5.4/080-wireguard-0027-crypto-curve25519-implement-generic-KPP-driver.patch b/target/linux/generic/backport-5.4/080-wireguard-0027-crypto-curve25519-implement-generic-KPP-driver.patch new file mode 100644 index 0000000000..2d6de581ee --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0027-crypto-curve25519-implement-generic-KPP-driver.patch @@ -0,0 +1,136 @@ +From 54bdc995d525de6ae20f74af36d079f8b79e52fa Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:34 +0100 +Subject: [PATCH 027/124] crypto: curve25519 - implement generic KPP driver + +commit ee772cb641135739c1530647391d5a04c39db192 upstream. + +Expose the generic Curve25519 library via the crypto API KPP interface. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/Kconfig | 5 +++ + crypto/Makefile | 1 + + crypto/curve25519-generic.c | 90 +++++++++++++++++++++++++++++++++++++ + 3 files changed, 96 insertions(+) + create mode 100644 crypto/curve25519-generic.c + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -264,6 +264,11 @@ config CRYPTO_ECRDSA + standard algorithms (called GOST algorithms). Only signature verification + is implemented. + ++config CRYPTO_CURVE25519 ++ tristate "Curve25519 algorithm" ++ select CRYPTO_KPP ++ select CRYPTO_LIB_CURVE25519_GENERIC ++ + comment "Authenticated Encryption with Associated Data" + + config CRYPTO_CCM +--- a/crypto/Makefile ++++ b/crypto/Makefile +@@ -167,6 +167,7 @@ obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o + obj-$(CONFIG_CRYPTO_OFB) += ofb.o + obj-$(CONFIG_CRYPTO_ECC) += ecc.o + obj-$(CONFIG_CRYPTO_ESSIV) += essiv.o ++obj-$(CONFIG_CRYPTO_CURVE25519) += curve25519-generic.o + + ecdh_generic-y += ecdh.o + ecdh_generic-y += ecdh_helper.o +--- /dev/null ++++ b/crypto/curve25519-generic.c +@@ -0,0 +1,90 @@ ++// SPDX-License-Identifier: GPL-2.0-or-later ++ ++#include ++#include ++#include ++#include ++#include ++ ++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_generic(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-generic", ++ .base.cra_priority = 100, ++ .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 curve25519_init(void) ++{ ++ return crypto_register_kpp(&curve25519_alg); ++} ++ ++static void curve25519_exit(void) ++{ ++ crypto_unregister_kpp(&curve25519_alg); ++} ++ ++subsys_initcall(curve25519_init); ++module_exit(curve25519_exit); ++ ++MODULE_ALIAS_CRYPTO("curve25519"); ++MODULE_ALIAS_CRYPTO("curve25519-generic"); ++MODULE_LICENSE("GPL"); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0028-crypto-lib-curve25519-work-around-Clang-stack-spilli.patch b/target/linux/generic/backport-5.4/080-wireguard-0028-crypto-lib-curve25519-work-around-Clang-stack-spilli.patch new file mode 100644 index 0000000000..b38f3f74f0 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0028-crypto-lib-curve25519-work-around-Clang-stack-spilli.patch @@ -0,0 +1,75 @@ +From 3c710fa0cdbf9362df4e3b36be338779662b30a6 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:35 +0100 +Subject: [PATCH 028/124] crypto: lib/curve25519 - work around Clang stack + spilling issue + +commit 660bb8e1f833ea63185fe80fde847e3e42f18e3b upstream. + +Arnd reports that the 32-bit generic library code for Curve25119 ends +up using an excessive amount of stack space when built with Clang: + + lib/crypto/curve25519-fiat32.c:756:6: error: stack frame size + of 1384 bytes in function 'curve25519_generic' + [-Werror,-Wframe-larger-than=] + +Let's give some hints to the compiler regarding which routines should +not be inlined, to prevent it from running out of registers and spilling +to the stack. The resulting code performs identically under both GCC +and Clang, and makes the warning go away. + +Suggested-by: Arnd Bergmann +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/curve25519-fiat32.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +--- a/lib/crypto/curve25519-fiat32.c ++++ b/lib/crypto/curve25519-fiat32.c +@@ -223,7 +223,7 @@ static __always_inline void fe_1(fe *h) + h->v[0] = 1; + } + +-static void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) ++static noinline void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) + { + { const u32 x20 = in1[9]; + { const u32 x21 = in1[8]; +@@ -266,7 +266,7 @@ static __always_inline void fe_add(fe_lo + fe_add_impl(h->v, f->v, g->v); + } + +-static void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) ++static noinline void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) + { + { const u32 x20 = in1[9]; + { const u32 x21 = in1[8]; +@@ -309,7 +309,7 @@ static __always_inline void fe_sub(fe_lo + fe_sub_impl(h->v, f->v, g->v); + } + +-static void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) ++static noinline void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10]) + { + { const u32 x20 = in1[9]; + { const u32 x21 = in1[8]; +@@ -441,7 +441,7 @@ fe_mul_tll(fe *h, const fe_loose *f, con + fe_mul_impl(h->v, f->v, g->v); + } + +-static void fe_sqr_impl(u32 out[10], const u32 in1[10]) ++static noinline void fe_sqr_impl(u32 out[10], const u32 in1[10]) + { + { const u32 x17 = in1[9]; + { const u32 x18 = in1[8]; +@@ -619,7 +619,7 @@ static __always_inline void fe_invert(fe + * + * Preconditions: b in {0,1} + */ +-static __always_inline void fe_cswap(fe *f, fe *g, unsigned int b) ++static noinline void fe_cswap(fe *f, fe *g, unsigned int b) + { + unsigned i; + b = 0 - b; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0029-crypto-curve25519-x86_64-library-and-KPP-implementat.patch b/target/linux/generic/backport-5.4/080-wireguard-0029-crypto-curve25519-x86_64-library-and-KPP-implementat.patch new file mode 100644 index 0000000000..fd06cb1260 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0029-crypto-curve25519-x86_64-library-and-KPP-implementat.patch @@ -0,0 +1,2537 @@ +From 0195e7650ebe0fdb5e1d5891274c203cb6cee0b6 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:36 +0100 +Subject: [PATCH 029/124] crypto: curve25519 - x86_64 library and KPP + implementations +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit bb611bdfd6be34d9f822c73305fcc83720499d38 upstream. + +This implementation is the fastest available x86_64 implementation, and +unlike Sandy2x, it doesn't requie use of the floating point registers at +all. Instead it makes use of BMI2 and ADX, available on recent +microarchitectures. The implementation was written by Armando +Faz-Hernández with contributions (upstream) from Samuel Neves and me, +in addition to further changes in the kernel implementation from us. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Samuel Neves +Co-developed-by: Samuel Neves +[ardb: - move to arch/x86/crypto + - wire into lib/crypto framework + - implement crypto API KPP hooks ] +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/Makefile | 1 + + arch/x86/crypto/curve25519-x86_64.c | 2475 +++++++++++++++++++++++++++ + crypto/Kconfig | 6 + + 3 files changed, 2482 insertions(+) + create mode 100644 arch/x86/crypto/curve25519-x86_64.c + +--- a/arch/x86/crypto/Makefile ++++ b/arch/x86/crypto/Makefile +@@ -39,6 +39,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) + + obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o + obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o ++obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o + + # These modules require assembler to support AVX. + ifeq ($(avx_supported),yes) +--- /dev/null ++++ b/arch/x86/crypto/curve25519-x86_64.c +@@ -0,0 +1,2475 @@ ++// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause ++/* ++ * Copyright (c) 2017 Armando Faz . All Rights Reserved. ++ * Copyright (C) 2018-2019 Jason A. Donenfeld . All Rights Reserved. ++ * Copyright (C) 2018 Samuel Neves . All Rights Reserved. ++ */ ++ ++#include ++#include ++ ++#include ++#include ++#include ++#include ++ ++#include ++#include ++ ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_adx); ++ ++enum { NUM_WORDS_ELTFP25519 = 4 }; ++typedef __aligned(32) u64 eltfp25519_1w[NUM_WORDS_ELTFP25519]; ++typedef __aligned(32) u64 eltfp25519_1w_buffer[2 * NUM_WORDS_ELTFP25519]; ++ ++#define mul_eltfp25519_1w_adx(c, a, b) do { \ ++ mul_256x256_integer_adx(m.buffer, a, b); \ ++ red_eltfp25519_1w_adx(c, m.buffer); \ ++} while (0) ++ ++#define mul_eltfp25519_1w_bmi2(c, a, b) do { \ ++ mul_256x256_integer_bmi2(m.buffer, a, b); \ ++ red_eltfp25519_1w_bmi2(c, m.buffer); \ ++} while (0) ++ ++#define sqr_eltfp25519_1w_adx(a) do { \ ++ sqr_256x256_integer_adx(m.buffer, a); \ ++ red_eltfp25519_1w_adx(a, m.buffer); \ ++} while (0) ++ ++#define sqr_eltfp25519_1w_bmi2(a) do { \ ++ sqr_256x256_integer_bmi2(m.buffer, a); \ ++ red_eltfp25519_1w_bmi2(a, m.buffer); \ ++} while (0) ++ ++#define mul_eltfp25519_2w_adx(c, a, b) do { \ ++ mul2_256x256_integer_adx(m.buffer, a, b); \ ++ red_eltfp25519_2w_adx(c, m.buffer); \ ++} while (0) ++ ++#define mul_eltfp25519_2w_bmi2(c, a, b) do { \ ++ mul2_256x256_integer_bmi2(m.buffer, a, b); \ ++ red_eltfp25519_2w_bmi2(c, m.buffer); \ ++} while (0) ++ ++#define sqr_eltfp25519_2w_adx(a) do { \ ++ sqr2_256x256_integer_adx(m.buffer, a); \ ++ red_eltfp25519_2w_adx(a, m.buffer); \ ++} while (0) ++ ++#define sqr_eltfp25519_2w_bmi2(a) do { \ ++ sqr2_256x256_integer_bmi2(m.buffer, a); \ ++ red_eltfp25519_2w_bmi2(a, m.buffer); \ ++} while (0) ++ ++#define sqrn_eltfp25519_1w_adx(a, times) do { \ ++ int ____counter = (times); \ ++ while (____counter-- > 0) \ ++ sqr_eltfp25519_1w_adx(a); \ ++} while (0) ++ ++#define sqrn_eltfp25519_1w_bmi2(a, times) do { \ ++ int ____counter = (times); \ ++ while (____counter-- > 0) \ ++ sqr_eltfp25519_1w_bmi2(a); \ ++} while (0) ++ ++#define copy_eltfp25519_1w(C, A) do { \ ++ (C)[0] = (A)[0]; \ ++ (C)[1] = (A)[1]; \ ++ (C)[2] = (A)[2]; \ ++ (C)[3] = (A)[3]; \ ++} while (0) ++ ++#define setzero_eltfp25519_1w(C) do { \ ++ (C)[0] = 0; \ ++ (C)[1] = 0; \ ++ (C)[2] = 0; \ ++ (C)[3] = 0; \ ++} while (0) ++ ++__aligned(32) static const u64 table_ladder_8k[252 * NUM_WORDS_ELTFP25519] = { ++ /* 1 */ 0xfffffffffffffff3UL, 0xffffffffffffffffUL, ++ 0xffffffffffffffffUL, 0x5fffffffffffffffUL, ++ /* 2 */ 0x6b8220f416aafe96UL, 0x82ebeb2b4f566a34UL, ++ 0xd5a9a5b075a5950fUL, 0x5142b2cf4b2488f4UL, ++ /* 3 */ 0x6aaebc750069680cUL, 0x89cf7820a0f99c41UL, ++ 0x2a58d9183b56d0f4UL, 0x4b5aca80e36011a4UL, ++ /* 4 */ 0x329132348c29745dUL, 0xf4a2e616e1642fd7UL, ++ 0x1e45bb03ff67bc34UL, 0x306912d0f42a9b4aUL, ++ /* 5 */ 0xff886507e6af7154UL, 0x04f50e13dfeec82fUL, ++ 0xaa512fe82abab5ceUL, 0x174e251a68d5f222UL, ++ /* 6 */ 0xcf96700d82028898UL, 0x1743e3370a2c02c5UL, ++ 0x379eec98b4e86eaaUL, 0x0c59888a51e0482eUL, ++ /* 7 */ 0xfbcbf1d699b5d189UL, 0xacaef0d58e9fdc84UL, ++ 0xc1c20d06231f7614UL, 0x2938218da274f972UL, ++ /* 8 */ 0xf6af49beff1d7f18UL, 0xcc541c22387ac9c2UL, ++ 0x96fcc9ef4015c56bUL, 0x69c1627c690913a9UL, ++ /* 9 */ 0x7a86fd2f4733db0eUL, 0xfdb8c4f29e087de9UL, ++ 0x095e4b1a8ea2a229UL, 0x1ad7a7c829b37a79UL, ++ /* 10 */ 0x342d89cad17ea0c0UL, 0x67bedda6cced2051UL, ++ 0x19ca31bf2bb42f74UL, 0x3df7b4c84980acbbUL, ++ /* 11 */ 0xa8c6444dc80ad883UL, 0xb91e440366e3ab85UL, ++ 0xc215cda00164f6d8UL, 0x3d867c6ef247e668UL, ++ /* 12 */ 0xc7dd582bcc3e658cUL, 0xfd2c4748ee0e5528UL, ++ 0xa0fd9b95cc9f4f71UL, 0x7529d871b0675ddfUL, ++ /* 13 */ 0xb8f568b42d3cbd78UL, 0x1233011b91f3da82UL, ++ 0x2dce6ccd4a7c3b62UL, 0x75e7fc8e9e498603UL, ++ /* 14 */ 0x2f4f13f1fcd0b6ecUL, 0xf1a8ca1f29ff7a45UL, ++ 0xc249c1a72981e29bUL, 0x6ebe0dbb8c83b56aUL, ++ /* 15 */ 0x7114fa8d170bb222UL, 0x65a2dcd5bf93935fUL, ++ 0xbdc41f68b59c979aUL, 0x2f0eef79a2ce9289UL, ++ /* 16 */ 0x42ecbf0c083c37ceUL, 0x2930bc09ec496322UL, ++ 0xf294b0c19cfeac0dUL, 0x3780aa4bedfabb80UL, ++ /* 17 */ 0x56c17d3e7cead929UL, 0xe7cb4beb2e5722c5UL, ++ 0x0ce931732dbfe15aUL, 0x41b883c7621052f8UL, ++ /* 18 */ 0xdbf75ca0c3d25350UL, 0x2936be086eb1e351UL, ++ 0xc936e03cb4a9b212UL, 0x1d45bf82322225aaUL, ++ /* 19 */ 0xe81ab1036a024cc5UL, 0xe212201c304c9a72UL, ++ 0xc5d73fba6832b1fcUL, 0x20ffdb5a4d839581UL, ++ /* 20 */ 0xa283d367be5d0fadUL, 0x6c2b25ca8b164475UL, ++ 0x9d4935467caaf22eUL, 0x5166408eee85ff49UL, ++ /* 21 */ 0x3c67baa2fab4e361UL, 0xb3e433c67ef35cefUL, ++ 0x5259729241159b1cUL, 0x6a621892d5b0ab33UL, ++ /* 22 */ 0x20b74a387555cdcbUL, 0x532aa10e1208923fUL, ++ 0xeaa17b7762281dd1UL, 0x61ab3443f05c44bfUL, ++ /* 23 */ 0x257a6c422324def8UL, 0x131c6c1017e3cf7fUL, ++ 0x23758739f630a257UL, 0x295a407a01a78580UL, ++ /* 24 */ 0xf8c443246d5da8d9UL, 0x19d775450c52fa5dUL, ++ 0x2afcfc92731bf83dUL, 0x7d10c8e81b2b4700UL, ++ /* 25 */ 0xc8e0271f70baa20bUL, 0x993748867ca63957UL, ++ 0x5412efb3cb7ed4bbUL, 0x3196d36173e62975UL, ++ /* 26 */ 0xde5bcad141c7dffcUL, 0x47cc8cd2b395c848UL, ++ 0xa34cd942e11af3cbUL, 0x0256dbf2d04ecec2UL, ++ /* 27 */ 0x875ab7e94b0e667fUL, 0xcad4dd83c0850d10UL, ++ 0x47f12e8f4e72c79fUL, 0x5f1a87bb8c85b19bUL, ++ /* 28 */ 0x7ae9d0b6437f51b8UL, 0x12c7ce5518879065UL, ++ 0x2ade09fe5cf77aeeUL, 0x23a05a2f7d2c5627UL, ++ /* 29 */ 0x5908e128f17c169aUL, 0xf77498dd8ad0852dUL, ++ 0x74b4c4ceab102f64UL, 0x183abadd10139845UL, ++ /* 30 */ 0xb165ba8daa92aaacUL, 0xd5c5ef9599386705UL, ++ 0xbe2f8f0cf8fc40d1UL, 0x2701e635ee204514UL, ++ /* 31 */ 0x629fa80020156514UL, 0xf223868764a8c1ceUL, ++ 0x5b894fff0b3f060eUL, 0x60d9944cf708a3faUL, ++ /* 32 */ 0xaeea001a1c7a201fUL, 0xebf16a633ee2ce63UL, ++ 0x6f7709594c7a07e1UL, 0x79b958150d0208cbUL, ++ /* 33 */ 0x24b55e5301d410e7UL, 0xe3a34edff3fdc84dUL, ++ 0xd88768e4904032d8UL, 0x131384427b3aaeecUL, ++ /* 34 */ 0x8405e51286234f14UL, 0x14dc4739adb4c529UL, ++ 0xb8a2b5b250634ffdUL, 0x2fe2a94ad8a7ff93UL, ++ /* 35 */ 0xec5c57efe843faddUL, 0x2843ce40f0bb9918UL, ++ 0xa4b561d6cf3d6305UL, 0x743629bde8fb777eUL, ++ /* 36 */ 0x343edd46bbaf738fUL, 0xed981828b101a651UL, ++ 0xa401760b882c797aUL, 0x1fc223e28dc88730UL, ++ /* 37 */ 0x48604e91fc0fba0eUL, 0xb637f78f052c6fa4UL, ++ 0x91ccac3d09e9239cUL, 0x23f7eed4437a687cUL, ++ /* 38 */ 0x5173b1118d9bd800UL, 0x29d641b63189d4a7UL, ++ 0xfdbf177988bbc586UL, 0x2959894fcad81df5UL, ++ /* 39 */ 0xaebc8ef3b4bbc899UL, 0x4148995ab26992b9UL, ++ 0x24e20b0134f92cfbUL, 0x40d158894a05dee8UL, ++ /* 40 */ 0x46b00b1185af76f6UL, 0x26bac77873187a79UL, ++ 0x3dc0bf95ab8fff5fUL, 0x2a608bd8945524d7UL, ++ /* 41 */ 0x26449588bd446302UL, 0x7c4bc21c0388439cUL, ++ 0x8e98a4f383bd11b2UL, 0x26218d7bc9d876b9UL, ++ /* 42 */ 0xe3081542997c178aUL, 0x3c2d29a86fb6606fUL, ++ 0x5c217736fa279374UL, 0x7dde05734afeb1faUL, ++ /* 43 */ 0x3bf10e3906d42babUL, 0xe4f7803e1980649cUL, ++ 0xe6053bf89595bf7aUL, 0x394faf38da245530UL, ++ /* 44 */ 0x7a8efb58896928f4UL, 0xfbc778e9cc6a113cUL, ++ 0x72670ce330af596fUL, 0x48f222a81d3d6cf7UL, ++ /* 45 */ 0xf01fce410d72caa7UL, 0x5a20ecc7213b5595UL, ++ 0x7bc21165c1fa1483UL, 0x07f89ae31da8a741UL, ++ /* 46 */ 0x05d2c2b4c6830ff9UL, 0xd43e330fc6316293UL, ++ 0xa5a5590a96d3a904UL, 0x705edb91a65333b6UL, ++ /* 47 */ 0x048ee15e0bb9a5f7UL, 0x3240cfca9e0aaf5dUL, ++ 0x8f4b71ceedc4a40bUL, 0x621c0da3de544a6dUL, ++ /* 48 */ 0x92872836a08c4091UL, 0xce8375b010c91445UL, ++ 0x8a72eb524f276394UL, 0x2667fcfa7ec83635UL, ++ /* 49 */ 0x7f4c173345e8752aUL, 0x061b47feee7079a5UL, ++ 0x25dd9afa9f86ff34UL, 0x3780cef5425dc89cUL, ++ /* 50 */ 0x1a46035a513bb4e9UL, 0x3e1ef379ac575adaUL, ++ 0xc78c5f1c5fa24b50UL, 0x321a967634fd9f22UL, ++ /* 51 */ 0x946707b8826e27faUL, 0x3dca84d64c506fd0UL, ++ 0xc189218075e91436UL, 0x6d9284169b3b8484UL, ++ /* 52 */ 0x3a67e840383f2ddfUL, 0x33eec9a30c4f9b75UL, ++ 0x3ec7c86fa783ef47UL, 0x26ec449fbac9fbc4UL, ++ /* 53 */ 0x5c0f38cba09b9e7dUL, 0x81168cc762a3478cUL, ++ 0x3e23b0d306fc121cUL, 0x5a238aa0a5efdcddUL, ++ /* 54 */ 0x1ba26121c4ea43ffUL, 0x36f8c77f7c8832b5UL, ++ 0x88fbea0b0adcf99aUL, 0x5ca9938ec25bebf9UL, ++ /* 55 */ 0xd5436a5e51fccda0UL, 0x1dbc4797c2cd893bUL, ++ 0x19346a65d3224a08UL, 0x0f5034e49b9af466UL, ++ /* 56 */ 0xf23c3967a1e0b96eUL, 0xe58b08fa867a4d88UL, ++ 0xfb2fabc6a7341679UL, 0x2a75381eb6026946UL, ++ /* 57 */ 0xc80a3be4c19420acUL, 0x66b1f6c681f2b6dcUL, ++ 0x7cf7036761e93388UL, 0x25abbbd8a660a4c4UL, ++ /* 58 */ 0x91ea12ba14fd5198UL, 0x684950fc4a3cffa9UL, ++ 0xf826842130f5ad28UL, 0x3ea988f75301a441UL, ++ /* 59 */ 0xc978109a695f8c6fUL, 0x1746eb4a0530c3f3UL, ++ 0x444d6d77b4459995UL, 0x75952b8c054e5cc7UL, ++ /* 60 */ 0xa3703f7915f4d6aaUL, 0x66c346202f2647d8UL, ++ 0xd01469df811d644bUL, 0x77fea47d81a5d71fUL, ++ /* 61 */ 0xc5e9529ef57ca381UL, 0x6eeeb4b9ce2f881aUL, ++ 0xb6e91a28e8009bd6UL, 0x4b80be3e9afc3fecUL, ++ /* 62 */ 0x7e3773c526aed2c5UL, 0x1b4afcb453c9a49dUL, ++ 0xa920bdd7baffb24dUL, 0x7c54699f122d400eUL, ++ /* 63 */ 0xef46c8e14fa94bc8UL, 0xe0b074ce2952ed5eUL, ++ 0xbea450e1dbd885d5UL, 0x61b68649320f712cUL, ++ /* 64 */ 0x8a485f7309ccbdd1UL, 0xbd06320d7d4d1a2dUL, ++ 0x25232973322dbef4UL, 0x445dc4758c17f770UL, ++ /* 65 */ 0xdb0434177cc8933cUL, 0xed6fe82175ea059fUL, ++ 0x1efebefdc053db34UL, 0x4adbe867c65daf99UL, ++ /* 66 */ 0x3acd71a2a90609dfUL, 0xe5e991856dd04050UL, ++ 0x1ec69b688157c23cUL, 0x697427f6885cfe4dUL, ++ /* 67 */ 0xd7be7b9b65e1a851UL, 0xa03d28d522c536ddUL, ++ 0x28399d658fd2b645UL, 0x49e5b7e17c2641e1UL, ++ /* 68 */ 0x6f8c3a98700457a4UL, 0x5078f0a25ebb6778UL, ++ 0xd13c3ccbc382960fUL, 0x2e003258a7df84b1UL, ++ /* 69 */ 0x8ad1f39be6296a1cUL, 0xc1eeaa652a5fbfb2UL, ++ 0x33ee0673fd26f3cbUL, 0x59256173a69d2cccUL, ++ /* 70 */ 0x41ea07aa4e18fc41UL, 0xd9fc19527c87a51eUL, ++ 0xbdaacb805831ca6fUL, 0x445b652dc916694fUL, ++ /* 71 */ 0xce92a3a7f2172315UL, 0x1edc282de11b9964UL, ++ 0xa1823aafe04c314aUL, 0x790a2d94437cf586UL, ++ /* 72 */ 0x71c447fb93f6e009UL, 0x8922a56722845276UL, ++ 0xbf70903b204f5169UL, 0x2f7a89891ba319feUL, ++ /* 73 */ 0x02a08eb577e2140cUL, 0xed9a4ed4427bdcf4UL, ++ 0x5253ec44e4323cd1UL, 0x3e88363c14e9355bUL, ++ /* 74 */ 0xaa66c14277110b8cUL, 0x1ae0391610a23390UL, ++ 0x2030bd12c93fc2a2UL, 0x3ee141579555c7abUL, ++ /* 75 */ 0x9214de3a6d6e7d41UL, 0x3ccdd88607f17efeUL, ++ 0x674f1288f8e11217UL, 0x5682250f329f93d0UL, ++ /* 76 */ 0x6cf00b136d2e396eUL, 0x6e4cf86f1014debfUL, ++ 0x5930b1b5bfcc4e83UL, 0x047069b48aba16b6UL, ++ /* 77 */ 0x0d4ce4ab69b20793UL, 0xb24db91a97d0fb9eUL, ++ 0xcdfa50f54e00d01dUL, 0x221b1085368bddb5UL, ++ /* 78 */ 0xe7e59468b1e3d8d2UL, 0x53c56563bd122f93UL, ++ 0xeee8a903e0663f09UL, 0x61efa662cbbe3d42UL, ++ /* 79 */ 0x2cf8ddddde6eab2aUL, 0x9bf80ad51435f231UL, ++ 0x5deadacec9f04973UL, 0x29275b5d41d29b27UL, ++ /* 80 */ 0xcfde0f0895ebf14fUL, 0xb9aab96b054905a7UL, ++ 0xcae80dd9a1c420fdUL, 0x0a63bf2f1673bbc7UL, ++ /* 81 */ 0x092f6e11958fbc8cUL, 0x672a81e804822fadUL, ++ 0xcac8351560d52517UL, 0x6f3f7722c8f192f8UL, ++ /* 82 */ 0xf8ba90ccc2e894b7UL, 0x2c7557a438ff9f0dUL, ++ 0x894d1d855ae52359UL, 0x68e122157b743d69UL, ++ /* 83 */ 0xd87e5570cfb919f3UL, 0x3f2cdecd95798db9UL, ++ 0x2121154710c0a2ceUL, 0x3c66a115246dc5b2UL, ++ /* 84 */ 0xcbedc562294ecb72UL, 0xba7143c36a280b16UL, ++ 0x9610c2efd4078b67UL, 0x6144735d946a4b1eUL, ++ /* 85 */ 0x536f111ed75b3350UL, 0x0211db8c2041d81bUL, ++ 0xf93cb1000e10413cUL, 0x149dfd3c039e8876UL, ++ /* 86 */ 0xd479dde46b63155bUL, 0xb66e15e93c837976UL, ++ 0xdafde43b1f13e038UL, 0x5fafda1a2e4b0b35UL, ++ /* 87 */ 0x3600bbdf17197581UL, 0x3972050bbe3cd2c2UL, ++ 0x5938906dbdd5be86UL, 0x34fce5e43f9b860fUL, ++ /* 88 */ 0x75a8a4cd42d14d02UL, 0x828dabc53441df65UL, ++ 0x33dcabedd2e131d3UL, 0x3ebad76fb814d25fUL, ++ /* 89 */ 0xd4906f566f70e10fUL, 0x5d12f7aa51690f5aUL, ++ 0x45adb16e76cefcf2UL, 0x01f768aead232999UL, ++ /* 90 */ 0x2b6cc77b6248febdUL, 0x3cd30628ec3aaffdUL, ++ 0xce1c0b80d4ef486aUL, 0x4c3bff2ea6f66c23UL, ++ /* 91 */ 0x3f2ec4094aeaeb5fUL, 0x61b19b286e372ca7UL, ++ 0x5eefa966de2a701dUL, 0x23b20565de55e3efUL, ++ /* 92 */ 0xe301ca5279d58557UL, 0x07b2d4ce27c2874fUL, ++ 0xa532cd8a9dcf1d67UL, 0x2a52fee23f2bff56UL, ++ /* 93 */ 0x8624efb37cd8663dUL, 0xbbc7ac20ffbd7594UL, ++ 0x57b85e9c82d37445UL, 0x7b3052cb86a6ec66UL, ++ /* 94 */ 0x3482f0ad2525e91eUL, 0x2cb68043d28edca0UL, ++ 0xaf4f6d052e1b003aUL, 0x185f8c2529781b0aUL, ++ /* 95 */ 0xaa41de5bd80ce0d6UL, 0x9407b2416853e9d6UL, ++ 0x563ec36e357f4c3aUL, 0x4cc4b8dd0e297bceUL, ++ /* 96 */ 0xa2fc1a52ffb8730eUL, 0x1811f16e67058e37UL, ++ 0x10f9a366cddf4ee1UL, 0x72f4a0c4a0b9f099UL, ++ /* 97 */ 0x8c16c06f663f4ea7UL, 0x693b3af74e970fbaUL, ++ 0x2102e7f1d69ec345UL, 0x0ba53cbc968a8089UL, ++ /* 98 */ 0xca3d9dc7fea15537UL, 0x4c6824bb51536493UL, ++ 0xb9886314844006b1UL, 0x40d2a72ab454cc60UL, ++ /* 99 */ 0x5936a1b712570975UL, 0x91b9d648debda657UL, ++ 0x3344094bb64330eaUL, 0x006ba10d12ee51d0UL, ++ /* 100 */ 0x19228468f5de5d58UL, 0x0eb12f4c38cc05b0UL, ++ 0xa1039f9dd5601990UL, 0x4502d4ce4fff0e0bUL, ++ /* 101 */ 0xeb2054106837c189UL, 0xd0f6544c6dd3b93cUL, ++ 0x40727064c416d74fUL, 0x6e15c6114b502ef0UL, ++ /* 102 */ 0x4df2a398cfb1a76bUL, 0x11256c7419f2f6b1UL, ++ 0x4a497962066e6043UL, 0x705b3aab41355b44UL, ++ /* 103 */ 0x365ef536d797b1d8UL, 0x00076bd622ddf0dbUL, ++ 0x3bbf33b0e0575a88UL, 0x3777aa05c8e4ca4dUL, ++ /* 104 */ 0x392745c85578db5fUL, 0x6fda4149dbae5ae2UL, ++ 0xb1f0b00b8adc9867UL, 0x09963437d36f1da3UL, ++ /* 105 */ 0x7e824e90a5dc3853UL, 0xccb5f6641f135cbdUL, ++ 0x6736d86c87ce8fccUL, 0x625f3ce26604249fUL, ++ /* 106 */ 0xaf8ac8059502f63fUL, 0x0c05e70a2e351469UL, ++ 0x35292e9c764b6305UL, 0x1a394360c7e23ac3UL, ++ /* 107 */ 0xd5c6d53251183264UL, 0x62065abd43c2b74fUL, ++ 0xb5fbf5d03b973f9bUL, 0x13a3da3661206e5eUL, ++ /* 108 */ 0xc6bd5837725d94e5UL, 0x18e30912205016c5UL, ++ 0x2088ce1570033c68UL, 0x7fba1f495c837987UL, ++ /* 109 */ 0x5a8c7423f2f9079dUL, 0x1735157b34023fc5UL, ++ 0xe4f9b49ad2fab351UL, 0x6691ff72c878e33cUL, ++ /* 110 */ 0x122c2adedc5eff3eUL, 0xf8dd4bf1d8956cf4UL, ++ 0xeb86205d9e9e5bdaUL, 0x049b92b9d975c743UL, ++ /* 111 */ 0xa5379730b0f6c05aUL, 0x72a0ffacc6f3a553UL, ++ 0xb0032c34b20dcd6dUL, 0x470e9dbc88d5164aUL, ++ /* 112 */ 0xb19cf10ca237c047UL, 0xb65466711f6c81a2UL, ++ 0xb3321bd16dd80b43UL, 0x48c14f600c5fbe8eUL, ++ /* 113 */ 0x66451c264aa6c803UL, 0xb66e3904a4fa7da6UL, ++ 0xd45f19b0b3128395UL, 0x31602627c3c9bc10UL, ++ /* 114 */ 0x3120dc4832e4e10dUL, 0xeb20c46756c717f7UL, ++ 0x00f52e3f67280294UL, 0x566d4fc14730c509UL, ++ /* 115 */ 0x7e3a5d40fd837206UL, 0xc1e926dc7159547aUL, ++ 0x216730fba68d6095UL, 0x22e8c3843f69cea7UL, ++ /* 116 */ 0x33d074e8930e4b2bUL, 0xb6e4350e84d15816UL, ++ 0x5534c26ad6ba2365UL, 0x7773c12f89f1f3f3UL, ++ /* 117 */ 0x8cba404da57962aaUL, 0x5b9897a81999ce56UL, ++ 0x508e862f121692fcUL, 0x3a81907fa093c291UL, ++ /* 118 */ 0x0dded0ff4725a510UL, 0x10d8cc10673fc503UL, ++ 0x5b9d151c9f1f4e89UL, 0x32a5c1d5cb09a44cUL, ++ /* 119 */ 0x1e0aa442b90541fbUL, 0x5f85eb7cc1b485dbUL, ++ 0xbee595ce8a9df2e5UL, 0x25e496c722422236UL, ++ /* 120 */ 0x5edf3c46cd0fe5b9UL, 0x34e75a7ed2a43388UL, ++ 0xe488de11d761e352UL, 0x0e878a01a085545cUL, ++ /* 121 */ 0xba493c77e021bb04UL, 0x2b4d1843c7df899aUL, ++ 0x9ea37a487ae80d67UL, 0x67a9958011e41794UL, ++ /* 122 */ 0x4b58051a6697b065UL, 0x47e33f7d8d6ba6d4UL, ++ 0xbb4da8d483ca46c1UL, 0x68becaa181c2db0dUL, ++ /* 123 */ 0x8d8980e90b989aa5UL, 0xf95eb14a2c93c99bUL, ++ 0x51c6c7c4796e73a2UL, 0x6e228363b5efb569UL, ++ /* 124 */ 0xc6bbc0b02dd624c8UL, 0x777eb47dec8170eeUL, ++ 0x3cde15a004cfafa9UL, 0x1dc6bc087160bf9bUL, ++ /* 125 */ 0x2e07e043eec34002UL, 0x18e9fc677a68dc7fUL, ++ 0xd8da03188bd15b9aUL, 0x48fbc3bb00568253UL, ++ /* 126 */ 0x57547d4cfb654ce1UL, 0xd3565b82a058e2adUL, ++ 0xf63eaf0bbf154478UL, 0x47531ef114dfbb18UL, ++ /* 127 */ 0xe1ec630a4278c587UL, 0x5507d546ca8e83f3UL, ++ 0x85e135c63adc0c2bUL, 0x0aa7efa85682844eUL, ++ /* 128 */ 0x72691ba8b3e1f615UL, 0x32b4e9701fbe3ffaUL, ++ 0x97b6d92e39bb7868UL, 0x2cfe53dea02e39e8UL, ++ /* 129 */ 0x687392cd85cd52b0UL, 0x27ff66c910e29831UL, ++ 0x97134556a9832d06UL, 0x269bb0360a84f8a0UL, ++ /* 130 */ 0x706e55457643f85cUL, 0x3734a48c9b597d1bUL, ++ 0x7aee91e8c6efa472UL, 0x5cd6abc198a9d9e0UL, ++ /* 131 */ 0x0e04de06cb3ce41aUL, 0xd8c6eb893402e138UL, ++ 0x904659bb686e3772UL, 0x7215c371746ba8c8UL, ++ /* 132 */ 0xfd12a97eeae4a2d9UL, 0x9514b7516394f2c5UL, ++ 0x266fd5809208f294UL, 0x5c847085619a26b9UL, ++ /* 133 */ 0x52985410fed694eaUL, 0x3c905b934a2ed254UL, ++ 0x10bb47692d3be467UL, 0x063b3d2d69e5e9e1UL, ++ /* 134 */ 0x472726eedda57debUL, 0xefb6c4ae10f41891UL, ++ 0x2b1641917b307614UL, 0x117c554fc4f45b7cUL, ++ /* 135 */ 0xc07cf3118f9d8812UL, 0x01dbd82050017939UL, ++ 0xd7e803f4171b2827UL, 0x1015e87487d225eaUL, ++ /* 136 */ 0xc58de3fed23acc4dUL, 0x50db91c294a7be2dUL, ++ 0x0b94d43d1c9cf457UL, 0x6b1640fa6e37524aUL, ++ /* 137 */ 0x692f346c5fda0d09UL, 0x200b1c59fa4d3151UL, ++ 0xb8c46f760777a296UL, 0x4b38395f3ffdfbcfUL, ++ /* 138 */ 0x18d25e00be54d671UL, 0x60d50582bec8aba6UL, ++ 0x87ad8f263b78b982UL, 0x50fdf64e9cda0432UL, ++ /* 139 */ 0x90f567aac578dcf0UL, 0xef1e9b0ef2a3133bUL, ++ 0x0eebba9242d9de71UL, 0x15473c9bf03101c7UL, ++ /* 140 */ 0x7c77e8ae56b78095UL, 0xb678e7666e6f078eUL, ++ 0x2da0b9615348ba1fUL, 0x7cf931c1ff733f0bUL, ++ /* 141 */ 0x26b357f50a0a366cUL, 0xe9708cf42b87d732UL, ++ 0xc13aeea5f91cb2c0UL, 0x35d90c991143bb4cUL, ++ /* 142 */ 0x47c1c404a9a0d9dcUL, 0x659e58451972d251UL, ++ 0x3875a8c473b38c31UL, 0x1fbd9ed379561f24UL, ++ /* 143 */ 0x11fabc6fd41ec28dUL, 0x7ef8dfe3cd2a2dcaUL, ++ 0x72e73b5d8c404595UL, 0x6135fa4954b72f27UL, ++ /* 144 */ 0xccfc32a2de24b69cUL, 0x3f55698c1f095d88UL, ++ 0xbe3350ed5ac3f929UL, 0x5e9bf806ca477eebUL, ++ /* 145 */ 0xe9ce8fb63c309f68UL, 0x5376f63565e1f9f4UL, ++ 0xd1afcfb35a6393f1UL, 0x6632a1ede5623506UL, ++ /* 146 */ 0x0b7d6c390c2ded4cUL, 0x56cb3281df04cb1fUL, ++ 0x66305a1249ecc3c7UL, 0x5d588b60a38ca72aUL, ++ /* 147 */ 0xa6ecbf78e8e5f42dUL, 0x86eeb44b3c8a3eecUL, ++ 0xec219c48fbd21604UL, 0x1aaf1af517c36731UL, ++ /* 148 */ 0xc306a2836769bde7UL, 0x208280622b1e2adbUL, ++ 0x8027f51ffbff94a6UL, 0x76cfa1ce1124f26bUL, ++ /* 149 */ 0x18eb00562422abb6UL, 0xf377c4d58f8c29c3UL, ++ 0x4dbbc207f531561aUL, 0x0253b7f082128a27UL, ++ /* 150 */ 0x3d1f091cb62c17e0UL, 0x4860e1abd64628a9UL, ++ 0x52d17436309d4253UL, 0x356f97e13efae576UL, ++ /* 151 */ 0xd351e11aa150535bUL, 0x3e6b45bb1dd878ccUL, ++ 0x0c776128bed92c98UL, 0x1d34ae93032885b8UL, ++ /* 152 */ 0x4ba0488ca85ba4c3UL, 0x985348c33c9ce6ceUL, ++ 0x66124c6f97bda770UL, 0x0f81a0290654124aUL, ++ /* 153 */ 0x9ed09ca6569b86fdUL, 0x811009fd18af9a2dUL, ++ 0xff08d03f93d8c20aUL, 0x52a148199faef26bUL, ++ /* 154 */ 0x3e03f9dc2d8d1b73UL, 0x4205801873961a70UL, ++ 0xc0d987f041a35970UL, 0x07aa1f15a1c0d549UL, ++ /* 155 */ 0xdfd46ce08cd27224UL, 0x6d0a024f934e4239UL, ++ 0x808a7a6399897b59UL, 0x0a4556e9e13d95a2UL, ++ /* 156 */ 0xd21a991fe9c13045UL, 0x9b0e8548fe7751b8UL, ++ 0x5da643cb4bf30035UL, 0x77db28d63940f721UL, ++ /* 157 */ 0xfc5eeb614adc9011UL, 0x5229419ae8c411ebUL, ++ 0x9ec3e7787d1dcf74UL, 0x340d053e216e4cb5UL, ++ /* 158 */ 0xcac7af39b48df2b4UL, 0xc0faec2871a10a94UL, ++ 0x140a69245ca575edUL, 0x0cf1c37134273a4cUL, ++ /* 159 */ 0xc8ee306ac224b8a5UL, 0x57eaee7ccb4930b0UL, ++ 0xa1e806bdaacbe74fUL, 0x7d9a62742eeb657dUL, ++ /* 160 */ 0x9eb6b6ef546c4830UL, 0x885cca1fddb36e2eUL, ++ 0xe6b9f383ef0d7105UL, 0x58654fef9d2e0412UL, ++ /* 161 */ 0xa905c4ffbe0e8e26UL, 0x942de5df9b31816eUL, ++ 0x497d723f802e88e1UL, 0x30684dea602f408dUL, ++ /* 162 */ 0x21e5a278a3e6cb34UL, 0xaefb6e6f5b151dc4UL, ++ 0xb30b8e049d77ca15UL, 0x28c3c9cf53b98981UL, ++ /* 163 */ 0x287fb721556cdd2aUL, 0x0d317ca897022274UL, ++ 0x7468c7423a543258UL, 0x4a7f11464eb5642fUL, ++ /* 164 */ 0xa237a4774d193aa6UL, 0xd865986ea92129a1UL, ++ 0x24c515ecf87c1a88UL, 0x604003575f39f5ebUL, ++ /* 165 */ 0x47b9f189570a9b27UL, 0x2b98cede465e4b78UL, ++ 0x026df551dbb85c20UL, 0x74fcd91047e21901UL, ++ /* 166 */ 0x13e2a90a23c1bfa3UL, 0x0cb0074e478519f6UL, ++ 0x5ff1cbbe3af6cf44UL, 0x67fe5438be812dbeUL, ++ /* 167 */ 0xd13cf64fa40f05b0UL, 0x054dfb2f32283787UL, ++ 0x4173915b7f0d2aeaUL, 0x482f144f1f610d4eUL, ++ /* 168 */ 0xf6210201b47f8234UL, 0x5d0ae1929e70b990UL, ++ 0xdcd7f455b049567cUL, 0x7e93d0f1f0916f01UL, ++ /* 169 */ 0xdd79cbf18a7db4faUL, 0xbe8391bf6f74c62fUL, ++ 0x027145d14b8291bdUL, 0x585a73ea2cbf1705UL, ++ /* 170 */ 0x485ca03e928a0db2UL, 0x10fc01a5742857e7UL, ++ 0x2f482edbd6d551a7UL, 0x0f0433b5048fdb8aUL, ++ /* 171 */ 0x60da2e8dd7dc6247UL, 0x88b4c9d38cd4819aUL, ++ 0x13033ac001f66697UL, 0x273b24fe3b367d75UL, ++ /* 172 */ 0xc6e8f66a31b3b9d4UL, 0x281514a494df49d5UL, ++ 0xd1726fdfc8b23da7UL, 0x4b3ae7d103dee548UL, ++ /* 173 */ 0xc6256e19ce4b9d7eUL, 0xff5c5cf186e3c61cUL, ++ 0xacc63ca34b8ec145UL, 0x74621888fee66574UL, ++ /* 174 */ 0x956f409645290a1eUL, 0xef0bf8e3263a962eUL, ++ 0xed6a50eb5ec2647bUL, 0x0694283a9dca7502UL, ++ /* 175 */ 0x769b963643a2dcd1UL, 0x42b7c8ea09fc5353UL, ++ 0x4f002aee13397eabUL, 0x63005e2c19b7d63aUL, ++ /* 176 */ 0xca6736da63023beaUL, 0x966c7f6db12a99b7UL, ++ 0xace09390c537c5e1UL, 0x0b696063a1aa89eeUL, ++ /* 177 */ 0xebb03e97288c56e5UL, 0x432a9f9f938c8be8UL, ++ 0xa6a5a93d5b717f71UL, 0x1a5fb4c3e18f9d97UL, ++ /* 178 */ 0x1c94e7ad1c60cdceUL, 0xee202a43fc02c4a0UL, ++ 0x8dafe4d867c46a20UL, 0x0a10263c8ac27b58UL, ++ /* 179 */ 0xd0dea9dfe4432a4aUL, 0x856af87bbe9277c5UL, ++ 0xce8472acc212c71aUL, 0x6f151b6d9bbb1e91UL, ++ /* 180 */ 0x26776c527ceed56aUL, 0x7d211cb7fbf8faecUL, ++ 0x37ae66a6fd4609ccUL, 0x1f81b702d2770c42UL, ++ /* 181 */ 0x2fb0b057eac58392UL, 0xe1dd89fe29744e9dUL, ++ 0xc964f8eb17beb4f8UL, 0x29571073c9a2d41eUL, ++ /* 182 */ 0xa948a18981c0e254UL, 0x2df6369b65b22830UL, ++ 0xa33eb2d75fcfd3c6UL, 0x078cd6ec4199a01fUL, ++ /* 183 */ 0x4a584a41ad900d2fUL, 0x32142b78e2c74c52UL, ++ 0x68c4e8338431c978UL, 0x7f69ea9008689fc2UL, ++ /* 184 */ 0x52f2c81e46a38265UL, 0xfd78072d04a832fdUL, ++ 0x8cd7d5fa25359e94UL, 0x4de71b7454cc29d2UL, ++ /* 185 */ 0x42eb60ad1eda6ac9UL, 0x0aad37dfdbc09c3aUL, ++ 0x81004b71e33cc191UL, 0x44e6be345122803cUL, ++ /* 186 */ 0x03fe8388ba1920dbUL, 0xf5d57c32150db008UL, ++ 0x49c8c4281af60c29UL, 0x21edb518de701aeeUL, ++ /* 187 */ 0x7fb63e418f06dc99UL, 0xa4460d99c166d7b8UL, ++ 0x24dd5248ce520a83UL, 0x5ec3ad712b928358UL, ++ /* 188 */ 0x15022a5fbd17930fUL, 0xa4f64a77d82570e3UL, ++ 0x12bc8d6915783712UL, 0x498194c0fc620abbUL, ++ /* 189 */ 0x38a2d9d255686c82UL, 0x785c6bd9193e21f0UL, ++ 0xe4d5c81ab24a5484UL, 0x56307860b2e20989UL, ++ /* 190 */ 0x429d55f78b4d74c4UL, 0x22f1834643350131UL, ++ 0x1e60c24598c71fffUL, 0x59f2f014979983efUL, ++ /* 191 */ 0x46a47d56eb494a44UL, 0x3e22a854d636a18eUL, ++ 0xb346e15274491c3bUL, 0x2ceafd4e5390cde7UL, ++ /* 192 */ 0xba8a8538be0d6675UL, 0x4b9074bb50818e23UL, ++ 0xcbdab89085d304c3UL, 0x61a24fe0e56192c4UL, ++ /* 193 */ 0xcb7615e6db525bcbUL, 0xdd7d8c35a567e4caUL, ++ 0xe6b4153acafcdd69UL, 0x2d668e097f3c9766UL, ++ /* 194 */ 0xa57e7e265ce55ef0UL, 0x5d9f4e527cd4b967UL, ++ 0xfbc83606492fd1e5UL, 0x090d52beb7c3f7aeUL, ++ /* 195 */ 0x09b9515a1e7b4d7cUL, 0x1f266a2599da44c0UL, ++ 0xa1c49548e2c55504UL, 0x7ef04287126f15ccUL, ++ /* 196 */ 0xfed1659dbd30ef15UL, 0x8b4ab9eec4e0277bUL, ++ 0x884d6236a5df3291UL, 0x1fd96ea6bf5cf788UL, ++ /* 197 */ 0x42a161981f190d9aUL, 0x61d849507e6052c1UL, ++ 0x9fe113bf285a2cd5UL, 0x7c22d676dbad85d8UL, ++ /* 198 */ 0x82e770ed2bfbd27dUL, 0x4c05b2ece996f5a5UL, ++ 0xcd40a9c2b0900150UL, 0x5895319213d9bf64UL, ++ /* 199 */ 0xe7cc5d703fea2e08UL, 0xb50c491258e2188cUL, ++ 0xcce30baa48205bf0UL, 0x537c659ccfa32d62UL, ++ /* 200 */ 0x37b6623a98cfc088UL, 0xfe9bed1fa4d6aca4UL, ++ 0x04d29b8e56a8d1b0UL, 0x725f71c40b519575UL, ++ /* 201 */ 0x28c7f89cd0339ce6UL, 0x8367b14469ddc18bUL, ++ 0x883ada83a6a1652cUL, 0x585f1974034d6c17UL, ++ /* 202 */ 0x89cfb266f1b19188UL, 0xe63b4863e7c35217UL, ++ 0xd88c9da6b4c0526aUL, 0x3e035c9df0954635UL, ++ /* 203 */ 0xdd9d5412fb45de9dUL, 0xdd684532e4cff40dUL, ++ 0x4b5c999b151d671cUL, 0x2d8c2cc811e7f690UL, ++ /* 204 */ 0x7f54be1d90055d40UL, 0xa464c5df464aaf40UL, ++ 0x33979624f0e917beUL, 0x2c018dc527356b30UL, ++ /* 205 */ 0xa5415024e330b3d4UL, 0x73ff3d96691652d3UL, ++ 0x94ec42c4ef9b59f1UL, 0x0747201618d08e5aUL, ++ /* 206 */ 0x4d6ca48aca411c53UL, 0x66415f2fcfa66119UL, ++ 0x9c4dd40051e227ffUL, 0x59810bc09a02f7ebUL, ++ /* 207 */ 0x2a7eb171b3dc101dUL, 0x441c5ab99ffef68eUL, ++ 0x32025c9b93b359eaUL, 0x5e8ce0a71e9d112fUL, ++ /* 208 */ 0xbfcccb92429503fdUL, 0xd271ba752f095d55UL, ++ 0x345ead5e972d091eUL, 0x18c8df11a83103baUL, ++ /* 209 */ 0x90cd949a9aed0f4cUL, 0xc5d1f4cb6660e37eUL, ++ 0xb8cac52d56c52e0bUL, 0x6e42e400c5808e0dUL, ++ /* 210 */ 0xa3b46966eeaefd23UL, 0x0c4f1f0be39ecdcaUL, ++ 0x189dc8c9d683a51dUL, 0x51f27f054c09351bUL, ++ /* 211 */ 0x4c487ccd2a320682UL, 0x587ea95bb3df1c96UL, ++ 0xc8ccf79e555cb8e8UL, 0x547dc829a206d73dUL, ++ /* 212 */ 0xb822a6cd80c39b06UL, 0xe96d54732000d4c6UL, ++ 0x28535b6f91463b4dUL, 0x228f4660e2486e1dUL, ++ /* 213 */ 0x98799538de8d3abfUL, 0x8cd8330045ebca6eUL, ++ 0x79952a008221e738UL, 0x4322e1a7535cd2bbUL, ++ /* 214 */ 0xb114c11819d1801cUL, 0x2016e4d84f3f5ec7UL, ++ 0xdd0e2df409260f4cUL, 0x5ec362c0ae5f7266UL, ++ /* 215 */ 0xc0462b18b8b2b4eeUL, 0x7cc8d950274d1afbUL, ++ 0xf25f7105436b02d2UL, 0x43bbf8dcbff9ccd3UL, ++ /* 216 */ 0xb6ad1767a039e9dfUL, 0xb0714da8f69d3583UL, ++ 0x5e55fa18b42931f5UL, 0x4ed5558f33c60961UL, ++ /* 217 */ 0x1fe37901c647a5ddUL, 0x593ddf1f8081d357UL, ++ 0x0249a4fd813fd7a6UL, 0x69acca274e9caf61UL, ++ /* 218 */ 0x047ba3ea330721c9UL, 0x83423fc20e7e1ea0UL, ++ 0x1df4c0af01314a60UL, 0x09a62dab89289527UL, ++ /* 219 */ 0xa5b325a49cc6cb00UL, 0xe94b5dc654b56cb6UL, ++ 0x3be28779adc994a0UL, 0x4296e8f8ba3a4aadUL, ++ /* 220 */ 0x328689761e451eabUL, 0x2e4d598bff59594aUL, ++ 0x49b96853d7a7084aUL, 0x4980a319601420a8UL, ++ /* 221 */ 0x9565b9e12f552c42UL, 0x8a5318db7100fe96UL, ++ 0x05c90b4d43add0d7UL, 0x538b4cd66a5d4edaUL, ++ /* 222 */ 0xf4e94fc3e89f039fUL, 0x592c9af26f618045UL, ++ 0x08a36eb5fd4b9550UL, 0x25fffaf6c2ed1419UL, ++ /* 223 */ 0x34434459cc79d354UL, 0xeeecbfb4b1d5476bUL, ++ 0xddeb34a061615d99UL, 0x5129cecceb64b773UL, ++ /* 224 */ 0xee43215894993520UL, 0x772f9c7cf14c0b3bUL, ++ 0xd2e2fce306bedad5UL, 0x715f42b546f06a97UL, ++ /* 225 */ 0x434ecdceda5b5f1aUL, 0x0da17115a49741a9UL, ++ 0x680bd77c73edad2eUL, 0x487c02354edd9041UL, ++ /* 226 */ 0xb8efeff3a70ed9c4UL, 0x56a32aa3e857e302UL, ++ 0xdf3a68bd48a2a5a0UL, 0x07f650b73176c444UL, ++ /* 227 */ 0xe38b9b1626e0ccb1UL, 0x79e053c18b09fb36UL, ++ 0x56d90319c9f94964UL, 0x1ca941e7ac9ff5c4UL, ++ /* 228 */ 0x49c4df29162fa0bbUL, 0x8488cf3282b33305UL, ++ 0x95dfda14cabb437dUL, 0x3391f78264d5ad86UL, ++ /* 229 */ 0x729ae06ae2b5095dUL, 0xd58a58d73259a946UL, ++ 0xe9834262d13921edUL, 0x27fedafaa54bb592UL, ++ /* 230 */ 0xa99dc5b829ad48bbUL, 0x5f025742499ee260UL, ++ 0x802c8ecd5d7513fdUL, 0x78ceb3ef3f6dd938UL, ++ /* 231 */ 0xc342f44f8a135d94UL, 0x7b9edb44828cdda3UL, ++ 0x9436d11a0537cfe7UL, 0x5064b164ec1ab4c8UL, ++ /* 232 */ 0x7020eccfd37eb2fcUL, 0x1f31ea3ed90d25fcUL, ++ 0x1b930d7bdfa1bb34UL, 0x5344467a48113044UL, ++ /* 233 */ 0x70073170f25e6dfbUL, 0xe385dc1a50114cc8UL, ++ 0x2348698ac8fc4f00UL, 0x2a77a55284dd40d8UL, ++ /* 234 */ 0xfe06afe0c98c6ce4UL, 0xc235df96dddfd6e4UL, ++ 0x1428d01e33bf1ed3UL, 0x785768ec9300bdafUL, ++ /* 235 */ 0x9702e57a91deb63bUL, 0x61bdb8bfe5ce8b80UL, ++ 0x645b426f3d1d58acUL, 0x4804a82227a557bcUL, ++ /* 236 */ 0x8e57048ab44d2601UL, 0x68d6501a4b3a6935UL, ++ 0xc39c9ec3f9e1c293UL, 0x4172f257d4de63e2UL, ++ /* 237 */ 0xd368b450330c6401UL, 0x040d3017418f2391UL, ++ 0x2c34bb6090b7d90dUL, 0x16f649228fdfd51fUL, ++ /* 238 */ 0xbea6818e2b928ef5UL, 0xe28ccf91cdc11e72UL, ++ 0x594aaa68e77a36cdUL, 0x313034806c7ffd0fUL, ++ /* 239 */ 0x8a9d27ac2249bd65UL, 0x19a3b464018e9512UL, ++ 0xc26ccff352b37ec7UL, 0x056f68341d797b21UL, ++ /* 240 */ 0x5e79d6757efd2327UL, 0xfabdbcb6553afe15UL, ++ 0xd3e7222c6eaf5a60UL, 0x7046c76d4dae743bUL, ++ /* 241 */ 0x660be872b18d4a55UL, 0x19992518574e1496UL, ++ 0xc103053a302bdcbbUL, 0x3ed8e9800b218e8eUL, ++ /* 242 */ 0x7b0b9239fa75e03eUL, 0xefe9fb684633c083UL, ++ 0x98a35fbe391a7793UL, 0x6065510fe2d0fe34UL, ++ /* 243 */ 0x55cb668548abad0cUL, 0xb4584548da87e527UL, ++ 0x2c43ecea0107c1ddUL, 0x526028809372de35UL, ++ /* 244 */ 0x3415c56af9213b1fUL, 0x5bee1a4d017e98dbUL, ++ 0x13f6b105b5cf709bUL, 0x5ff20e3482b29ab6UL, ++ /* 245 */ 0x0aa29c75cc2e6c90UL, 0xfc7d73ca3a70e206UL, ++ 0x899fc38fc4b5c515UL, 0x250386b124ffc207UL, ++ /* 246 */ 0x54ea28d5ae3d2b56UL, 0x9913149dd6de60ceUL, ++ 0x16694fc58f06d6c1UL, 0x46b23975eb018fc7UL, ++ /* 247 */ 0x470a6a0fb4b7b4e2UL, 0x5d92475a8f7253deUL, ++ 0xabeee5b52fbd3adbUL, 0x7fa20801a0806968UL, ++ /* 248 */ 0x76f3faf19f7714d2UL, 0xb3e840c12f4660c3UL, ++ 0x0fb4cd8df212744eUL, 0x4b065a251d3a2dd2UL, ++ /* 249 */ 0x5cebde383d77cd4aUL, 0x6adf39df882c9cb1UL, ++ 0xa2dd242eb09af759UL, 0x3147c0e50e5f6422UL, ++ /* 250 */ 0x164ca5101d1350dbUL, 0xf8d13479c33fc962UL, ++ 0xe640ce4d13e5da08UL, 0x4bdee0c45061f8baUL, ++ /* 251 */ 0xd7c46dc1a4edb1c9UL, 0x5514d7b6437fd98aUL, ++ 0x58942f6bb2a1c00bUL, 0x2dffb2ab1d70710eUL, ++ /* 252 */ 0xccdfcf2fc18b6d68UL, 0xa8ebcba8b7806167UL, ++ 0x980697f95e2937e3UL, 0x02fbba1cd0126e8cUL ++}; ++ ++/* c is two 512-bit products: c0[0:7]=a0[0:3]*b0[0:3] and c1[8:15]=a1[4:7]*b1[4:7] ++ * a is two 256-bit integers: a0[0:3] and a1[4:7] ++ * b is two 256-bit integers: b0[0:3] and b1[4:7] ++ */ ++static void mul2_256x256_integer_adx(u64 *const c, const u64 *const a, ++ const u64 *const b) ++{ ++ asm volatile( ++ "xorl %%r14d, %%r14d ;" ++ "movq (%1), %%rdx; " /* A[0] */ ++ "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ ++ "xorl %%r10d, %%r10d ;" ++ "movq %%r8, (%0) ;" ++ "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ ++ "adox %%r10, %%r15 ;" ++ "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ ++ "adox %%r8, %%rax ;" ++ "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ ++ "adox %%r10, %%rbx ;" ++ /******************************************/ ++ "adox %%r14, %%rcx ;" ++ ++ "movq 8(%1), %%rdx; " /* A[1] */ ++ "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ ++ "adox %%r15, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ ++ "adox %%r10, %%r9 ;" ++ "adcx %%r9, %%rax ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ ++ "adox %%r8, %%r11 ;" ++ "adcx %%r11, %%rbx ;" ++ "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ ++ "adox %%r10, %%r13 ;" ++ "adcx %%r13, %%rcx ;" ++ /******************************************/ ++ "adox %%r14, %%r15 ;" ++ "adcx %%r14, %%r15 ;" ++ ++ "movq 16(%1), %%rdx; " /* A[2] */ ++ "xorl %%r10d, %%r10d ;" ++ "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ ++ "adox %%rax, %%r8 ;" ++ "movq %%r8, 16(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ ++ "adox %%r10, %%r9 ;" ++ "adcx %%r9, %%rbx ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ ++ "adox %%r8, %%r11 ;" ++ "adcx %%r11, %%rcx ;" ++ "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ ++ "adox %%r10, %%r13 ;" ++ "adcx %%r13, %%r15 ;" ++ /******************************************/ ++ "adox %%r14, %%rax ;" ++ "adcx %%r14, %%rax ;" ++ ++ "movq 24(%1), %%rdx; " /* A[3] */ ++ "xorl %%r10d, %%r10d ;" ++ "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ ++ "adox %%rbx, %%r8 ;" ++ "movq %%r8, 24(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ ++ "adox %%r10, %%r9 ;" ++ "adcx %%r9, %%rcx ;" ++ "movq %%rcx, 32(%0) ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ ++ "adox %%r8, %%r11 ;" ++ "adcx %%r11, %%r15 ;" ++ "movq %%r15, 40(%0) ;" ++ "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ ++ "adox %%r10, %%r13 ;" ++ "adcx %%r13, %%rax ;" ++ "movq %%rax, 48(%0) ;" ++ /******************************************/ ++ "adox %%r14, %%rbx ;" ++ "adcx %%r14, %%rbx ;" ++ "movq %%rbx, 56(%0) ;" ++ ++ "movq 32(%1), %%rdx; " /* C[0] */ ++ "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ ++ "xorl %%r10d, %%r10d ;" ++ "movq %%r8, 64(%0);" ++ "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ ++ "adox %%r10, %%r15 ;" ++ "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ ++ "adox %%r8, %%rax ;" ++ "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ ++ "adox %%r10, %%rbx ;" ++ /******************************************/ ++ "adox %%r14, %%rcx ;" ++ ++ "movq 40(%1), %%rdx; " /* C[1] */ ++ "xorl %%r10d, %%r10d ;" ++ "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ ++ "adox %%r15, %%r8 ;" ++ "movq %%r8, 72(%0);" ++ "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ ++ "adox %%r10, %%r9 ;" ++ "adcx %%r9, %%rax ;" ++ "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ ++ "adox %%r8, %%r11 ;" ++ "adcx %%r11, %%rbx ;" ++ "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ ++ "adox %%r10, %%r13 ;" ++ "adcx %%r13, %%rcx ;" ++ /******************************************/ ++ "adox %%r14, %%r15 ;" ++ "adcx %%r14, %%r15 ;" ++ ++ "movq 48(%1), %%rdx; " /* C[2] */ ++ "xorl %%r10d, %%r10d ;" ++ "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ ++ "adox %%rax, %%r8 ;" ++ "movq %%r8, 80(%0);" ++ "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ ++ "adox %%r10, %%r9 ;" ++ "adcx %%r9, %%rbx ;" ++ "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ ++ "adox %%r8, %%r11 ;" ++ "adcx %%r11, %%rcx ;" ++ "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ ++ "adox %%r10, %%r13 ;" ++ "adcx %%r13, %%r15 ;" ++ /******************************************/ ++ "adox %%r14, %%rax ;" ++ "adcx %%r14, %%rax ;" ++ ++ "movq 56(%1), %%rdx; " /* C[3] */ ++ "xorl %%r10d, %%r10d ;" ++ "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ ++ "adox %%rbx, %%r8 ;" ++ "movq %%r8, 88(%0);" ++ "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ ++ "adox %%r10, %%r9 ;" ++ "adcx %%r9, %%rcx ;" ++ "movq %%rcx, 96(%0) ;" ++ "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ ++ "adox %%r8, %%r11 ;" ++ "adcx %%r11, %%r15 ;" ++ "movq %%r15, 104(%0) ;" ++ "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ ++ "adox %%r10, %%r13 ;" ++ "adcx %%r13, %%rax ;" ++ "movq %%rax, 112(%0) ;" ++ /******************************************/ ++ "adox %%r14, %%rbx ;" ++ "adcx %%r14, %%rbx ;" ++ "movq %%rbx, 120(%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11", "%r13", "%r14", "%r15"); ++} ++ ++static void mul2_256x256_integer_bmi2(u64 *const c, const u64 *const a, ++ const u64 *const b) ++{ ++ asm volatile( ++ "movq (%1), %%rdx; " /* A[0] */ ++ "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ ++ "movq %%r8, (%0) ;" ++ "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ ++ "addq %%r10, %%r15 ;" ++ "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ ++ "adcq %%r8, %%rax ;" ++ "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ ++ "adcq %%r10, %%rbx ;" ++ /******************************************/ ++ "adcq $0, %%rcx ;" ++ ++ "movq 8(%1), %%rdx; " /* A[1] */ ++ "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ ++ "addq %%r15, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%r15 ;" ++ ++ "addq %%r9, %%rax ;" ++ "adcq %%r11, %%rbx ;" ++ "adcq %%r13, %%rcx ;" ++ "adcq $0, %%r15 ;" ++ ++ "movq 16(%1), %%rdx; " /* A[2] */ ++ "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ ++ "addq %%rax, %%r8 ;" ++ "movq %%r8, 16(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%rax ;" ++ ++ "addq %%r9, %%rbx ;" ++ "adcq %%r11, %%rcx ;" ++ "adcq %%r13, %%r15 ;" ++ "adcq $0, %%rax ;" ++ ++ "movq 24(%1), %%rdx; " /* A[3] */ ++ "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ ++ "addq %%rbx, %%r8 ;" ++ "movq %%r8, 24(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%rbx ;" ++ ++ "addq %%r9, %%rcx ;" ++ "movq %%rcx, 32(%0) ;" ++ "adcq %%r11, %%r15 ;" ++ "movq %%r15, 40(%0) ;" ++ "adcq %%r13, %%rax ;" ++ "movq %%rax, 48(%0) ;" ++ "adcq $0, %%rbx ;" ++ "movq %%rbx, 56(%0) ;" ++ ++ "movq 32(%1), %%rdx; " /* C[0] */ ++ "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ ++ "movq %%r8, 64(%0) ;" ++ "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ ++ "addq %%r10, %%r15 ;" ++ "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ ++ "adcq %%r8, %%rax ;" ++ "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ ++ "adcq %%r10, %%rbx ;" ++ /******************************************/ ++ "adcq $0, %%rcx ;" ++ ++ "movq 40(%1), %%rdx; " /* C[1] */ ++ "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ ++ "addq %%r15, %%r8 ;" ++ "movq %%r8, 72(%0) ;" ++ "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%r15 ;" ++ ++ "addq %%r9, %%rax ;" ++ "adcq %%r11, %%rbx ;" ++ "adcq %%r13, %%rcx ;" ++ "adcq $0, %%r15 ;" ++ ++ "movq 48(%1), %%rdx; " /* C[2] */ ++ "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ ++ "addq %%rax, %%r8 ;" ++ "movq %%r8, 80(%0) ;" ++ "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%rax ;" ++ ++ "addq %%r9, %%rbx ;" ++ "adcq %%r11, %%rcx ;" ++ "adcq %%r13, %%r15 ;" ++ "adcq $0, %%rax ;" ++ ++ "movq 56(%1), %%rdx; " /* C[3] */ ++ "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ ++ "addq %%rbx, %%r8 ;" ++ "movq %%r8, 88(%0) ;" ++ "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%rbx ;" ++ ++ "addq %%r9, %%rcx ;" ++ "movq %%rcx, 96(%0) ;" ++ "adcq %%r11, %%r15 ;" ++ "movq %%r15, 104(%0) ;" ++ "adcq %%r13, %%rax ;" ++ "movq %%rax, 112(%0) ;" ++ "adcq $0, %%rbx ;" ++ "movq %%rbx, 120(%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11", "%r13", "%r15"); ++} ++ ++static void sqr2_256x256_integer_adx(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movq (%1), %%rdx ;" /* A[0] */ ++ "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ ++ "xorl %%r15d, %%r15d;" ++ "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ ++ "adcx %%r14, %%r9 ;" ++ "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ ++ "adcx %%rax, %%r10 ;" ++ "movq 24(%1), %%rdx ;" /* A[3] */ ++ "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ ++ "adcx %%rcx, %%r11 ;" ++ "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ ++ "adcx %%rax, %%rbx ;" ++ "movq 8(%1), %%rdx ;" /* A[1] */ ++ "adcx %%r15, %%r13 ;" ++ "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ ++ "movq $0, %%r14 ;" ++ /******************************************/ ++ "adcx %%r15, %%r14 ;" ++ ++ "xorl %%r15d, %%r15d;" ++ "adox %%rax, %%r10 ;" ++ "adcx %%r8, %%r8 ;" ++ "adox %%rcx, %%r11 ;" ++ "adcx %%r9, %%r9 ;" ++ "adox %%r15, %%rbx ;" ++ "adcx %%r10, %%r10 ;" ++ "adox %%r15, %%r13 ;" ++ "adcx %%r11, %%r11 ;" ++ "adox %%r15, %%r14 ;" ++ "adcx %%rbx, %%rbx ;" ++ "adcx %%r13, %%r13 ;" ++ "adcx %%r14, %%r14 ;" ++ ++ "movq (%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ ++ /*******************/ ++ "movq %%rax, 0(%0) ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "movq 8(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ ++ "adcq %%rax, %%r9 ;" ++ "movq %%r9, 16(%0) ;" ++ "adcq %%rcx, %%r10 ;" ++ "movq %%r10, 24(%0) ;" ++ "movq 16(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ ++ "adcq %%rax, %%r11 ;" ++ "movq %%r11, 32(%0) ;" ++ "adcq %%rcx, %%rbx ;" ++ "movq %%rbx, 40(%0) ;" ++ "movq 24(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ ++ "adcq %%rax, %%r13 ;" ++ "movq %%r13, 48(%0) ;" ++ "adcq %%rcx, %%r14 ;" ++ "movq %%r14, 56(%0) ;" ++ ++ ++ "movq 32(%1), %%rdx ;" /* B[0] */ ++ "mulx 40(%1), %%r8, %%r14 ;" /* B[1]*B[0] */ ++ "xorl %%r15d, %%r15d;" ++ "mulx 48(%1), %%r9, %%r10 ;" /* B[2]*B[0] */ ++ "adcx %%r14, %%r9 ;" ++ "mulx 56(%1), %%rax, %%rcx ;" /* B[3]*B[0] */ ++ "adcx %%rax, %%r10 ;" ++ "movq 56(%1), %%rdx ;" /* B[3] */ ++ "mulx 40(%1), %%r11, %%rbx ;" /* B[1]*B[3] */ ++ "adcx %%rcx, %%r11 ;" ++ "mulx 48(%1), %%rax, %%r13 ;" /* B[2]*B[3] */ ++ "adcx %%rax, %%rbx ;" ++ "movq 40(%1), %%rdx ;" /* B[1] */ ++ "adcx %%r15, %%r13 ;" ++ "mulx 48(%1), %%rax, %%rcx ;" /* B[2]*B[1] */ ++ "movq $0, %%r14 ;" ++ /******************************************/ ++ "adcx %%r15, %%r14 ;" ++ ++ "xorl %%r15d, %%r15d;" ++ "adox %%rax, %%r10 ;" ++ "adcx %%r8, %%r8 ;" ++ "adox %%rcx, %%r11 ;" ++ "adcx %%r9, %%r9 ;" ++ "adox %%r15, %%rbx ;" ++ "adcx %%r10, %%r10 ;" ++ "adox %%r15, %%r13 ;" ++ "adcx %%r11, %%r11 ;" ++ "adox %%r15, %%r14 ;" ++ "adcx %%rbx, %%rbx ;" ++ "adcx %%r13, %%r13 ;" ++ "adcx %%r14, %%r14 ;" ++ ++ "movq 32(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* B[0]^2 */ ++ /*******************/ ++ "movq %%rax, 64(%0) ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 72(%0) ;" ++ "movq 40(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* B[1]^2 */ ++ "adcq %%rax, %%r9 ;" ++ "movq %%r9, 80(%0) ;" ++ "adcq %%rcx, %%r10 ;" ++ "movq %%r10, 88(%0) ;" ++ "movq 48(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* B[2]^2 */ ++ "adcq %%rax, %%r11 ;" ++ "movq %%r11, 96(%0) ;" ++ "adcq %%rcx, %%rbx ;" ++ "movq %%rbx, 104(%0) ;" ++ "movq 56(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* B[3]^2 */ ++ "adcq %%rax, %%r13 ;" ++ "movq %%r13, 112(%0) ;" ++ "adcq %%rcx, %%r14 ;" ++ "movq %%r14, 120(%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11", "%r13", "%r14", "%r15"); ++} ++ ++static void sqr2_256x256_integer_bmi2(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movq 8(%1), %%rdx ;" /* A[1] */ ++ "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ ++ "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ ++ "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ ++ ++ "movq 16(%1), %%rdx ;" /* A[2] */ ++ "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ ++ "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ ++ ++ "addq %%rax, %%r9 ;" ++ "adcq %%rdx, %%r10 ;" ++ "adcq %%rcx, %%r11 ;" ++ "adcq %%r14, %%r15 ;" ++ "adcq $0, %%r13 ;" ++ "movq $0, %%r14 ;" ++ "adcq $0, %%r14 ;" ++ ++ "movq (%1), %%rdx ;" /* A[0] */ ++ "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ ++ ++ "addq %%rax, %%r10 ;" ++ "adcq %%rcx, %%r11 ;" ++ "adcq $0, %%r15 ;" ++ "adcq $0, %%r13 ;" ++ "adcq $0, %%r14 ;" ++ ++ "shldq $1, %%r13, %%r14 ;" ++ "shldq $1, %%r15, %%r13 ;" ++ "shldq $1, %%r11, %%r15 ;" ++ "shldq $1, %%r10, %%r11 ;" ++ "shldq $1, %%r9, %%r10 ;" ++ "shldq $1, %%r8, %%r9 ;" ++ "shlq $1, %%r8 ;" ++ ++ /*******************/ ++ "mulx %%rdx, %%rax, %%rcx ; " /* A[0]^2 */ ++ /*******************/ ++ "movq %%rax, 0(%0) ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "movq 8(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ; " /* A[1]^2 */ ++ "adcq %%rax, %%r9 ;" ++ "movq %%r9, 16(%0) ;" ++ "adcq %%rcx, %%r10 ;" ++ "movq %%r10, 24(%0) ;" ++ "movq 16(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ; " /* A[2]^2 */ ++ "adcq %%rax, %%r11 ;" ++ "movq %%r11, 32(%0) ;" ++ "adcq %%rcx, %%r15 ;" ++ "movq %%r15, 40(%0) ;" ++ "movq 24(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ; " /* A[3]^2 */ ++ "adcq %%rax, %%r13 ;" ++ "movq %%r13, 48(%0) ;" ++ "adcq %%rcx, %%r14 ;" ++ "movq %%r14, 56(%0) ;" ++ ++ "movq 40(%1), %%rdx ;" /* B[1] */ ++ "mulx 32(%1), %%r8, %%r9 ;" /* B[0]*B[1] */ ++ "mulx 48(%1), %%r10, %%r11 ;" /* B[2]*B[1] */ ++ "mulx 56(%1), %%rcx, %%r14 ;" /* B[3]*B[1] */ ++ ++ "movq 48(%1), %%rdx ;" /* B[2] */ ++ "mulx 56(%1), %%r15, %%r13 ;" /* B[3]*B[2] */ ++ "mulx 32(%1), %%rax, %%rdx ;" /* B[0]*B[2] */ ++ ++ "addq %%rax, %%r9 ;" ++ "adcq %%rdx, %%r10 ;" ++ "adcq %%rcx, %%r11 ;" ++ "adcq %%r14, %%r15 ;" ++ "adcq $0, %%r13 ;" ++ "movq $0, %%r14 ;" ++ "adcq $0, %%r14 ;" ++ ++ "movq 32(%1), %%rdx ;" /* B[0] */ ++ "mulx 56(%1), %%rax, %%rcx ;" /* B[0]*B[3] */ ++ ++ "addq %%rax, %%r10 ;" ++ "adcq %%rcx, %%r11 ;" ++ "adcq $0, %%r15 ;" ++ "adcq $0, %%r13 ;" ++ "adcq $0, %%r14 ;" ++ ++ "shldq $1, %%r13, %%r14 ;" ++ "shldq $1, %%r15, %%r13 ;" ++ "shldq $1, %%r11, %%r15 ;" ++ "shldq $1, %%r10, %%r11 ;" ++ "shldq $1, %%r9, %%r10 ;" ++ "shldq $1, %%r8, %%r9 ;" ++ "shlq $1, %%r8 ;" ++ ++ /*******************/ ++ "mulx %%rdx, %%rax, %%rcx ; " /* B[0]^2 */ ++ /*******************/ ++ "movq %%rax, 64(%0) ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 72(%0) ;" ++ "movq 40(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ; " /* B[1]^2 */ ++ "adcq %%rax, %%r9 ;" ++ "movq %%r9, 80(%0) ;" ++ "adcq %%rcx, %%r10 ;" ++ "movq %%r10, 88(%0) ;" ++ "movq 48(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ; " /* B[2]^2 */ ++ "adcq %%rax, %%r11 ;" ++ "movq %%r11, 96(%0) ;" ++ "adcq %%rcx, %%r15 ;" ++ "movq %%r15, 104(%0) ;" ++ "movq 56(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ; " /* B[3]^2 */ ++ "adcq %%rax, %%r13 ;" ++ "movq %%r13, 112(%0) ;" ++ "adcq %%rcx, %%r14 ;" ++ "movq %%r14, 120(%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", ++ "%r11", "%r13", "%r14", "%r15"); ++} ++ ++static void red_eltfp25519_2w_adx(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movl $38, %%edx; " /* 2*c = 38 = 2^256 */ ++ "mulx 32(%1), %%r8, %%r10; " /* c*C[4] */ ++ "xorl %%ebx, %%ebx ;" ++ "adox (%1), %%r8 ;" ++ "mulx 40(%1), %%r9, %%r11; " /* c*C[5] */ ++ "adcx %%r10, %%r9 ;" ++ "adox 8(%1), %%r9 ;" ++ "mulx 48(%1), %%r10, %%rax; " /* c*C[6] */ ++ "adcx %%r11, %%r10 ;" ++ "adox 16(%1), %%r10 ;" ++ "mulx 56(%1), %%r11, %%rcx; " /* c*C[7] */ ++ "adcx %%rax, %%r11 ;" ++ "adox 24(%1), %%r11 ;" ++ /***************************************/ ++ "adcx %%rbx, %%rcx ;" ++ "adox %%rbx, %%rcx ;" ++ "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ ++ "adcx %%rcx, %%r8 ;" ++ "adcx %%rbx, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcx %%rbx, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcx %%rbx, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ ++ "mulx 96(%1), %%r8, %%r10; " /* c*C[4] */ ++ "xorl %%ebx, %%ebx ;" ++ "adox 64(%1), %%r8 ;" ++ "mulx 104(%1), %%r9, %%r11; " /* c*C[5] */ ++ "adcx %%r10, %%r9 ;" ++ "adox 72(%1), %%r9 ;" ++ "mulx 112(%1), %%r10, %%rax; " /* c*C[6] */ ++ "adcx %%r11, %%r10 ;" ++ "adox 80(%1), %%r10 ;" ++ "mulx 120(%1), %%r11, %%rcx; " /* c*C[7] */ ++ "adcx %%rax, %%r11 ;" ++ "adox 88(%1), %%r11 ;" ++ /****************************************/ ++ "adcx %%rbx, %%rcx ;" ++ "adox %%rbx, %%rcx ;" ++ "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ ++ "adcx %%rcx, %%r8 ;" ++ "adcx %%rbx, %%r9 ;" ++ "movq %%r9, 40(%0) ;" ++ "adcx %%rbx, %%r10 ;" ++ "movq %%r10, 48(%0) ;" ++ "adcx %%rbx, %%r11 ;" ++ "movq %%r11, 56(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 32(%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11"); ++} ++ ++static void red_eltfp25519_2w_bmi2(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movl $38, %%edx ; " /* 2*c = 38 = 2^256 */ ++ "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ ++ "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ ++ "addq %%r10, %%r9 ;" ++ "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ ++ "adcq %%r11, %%r10 ;" ++ "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ ++ "adcq %%rax, %%r11 ;" ++ /***************************************/ ++ "adcq $0, %%rcx ;" ++ "addq (%1), %%r8 ;" ++ "adcq 8(%1), %%r9 ;" ++ "adcq 16(%1), %%r10 ;" ++ "adcq 24(%1), %%r11 ;" ++ "adcq $0, %%rcx ;" ++ "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ ++ "addq %%rcx, %%r8 ;" ++ "adcq $0, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcq $0, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcq $0, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ ++ "mulx 96(%1), %%r8, %%r10 ;" /* c*C[4] */ ++ "mulx 104(%1), %%r9, %%r11 ;" /* c*C[5] */ ++ "addq %%r10, %%r9 ;" ++ "mulx 112(%1), %%r10, %%rax ;" /* c*C[6] */ ++ "adcq %%r11, %%r10 ;" ++ "mulx 120(%1), %%r11, %%rcx ;" /* c*C[7] */ ++ "adcq %%rax, %%r11 ;" ++ /****************************************/ ++ "adcq $0, %%rcx ;" ++ "addq 64(%1), %%r8 ;" ++ "adcq 72(%1), %%r9 ;" ++ "adcq 80(%1), %%r10 ;" ++ "adcq 88(%1), %%r11 ;" ++ "adcq $0, %%rcx ;" ++ "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ ++ "addq %%rcx, %%r8 ;" ++ "adcq $0, %%r9 ;" ++ "movq %%r9, 40(%0) ;" ++ "adcq $0, %%r10 ;" ++ "movq %%r10, 48(%0) ;" ++ "adcq $0, %%r11 ;" ++ "movq %%r11, 56(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 32(%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", ++ "%r11"); ++} ++ ++static void mul_256x256_integer_adx(u64 *const c, const u64 *const a, ++ const u64 *const b) ++{ ++ asm volatile( ++ "movq (%1), %%rdx; " /* A[0] */ ++ "mulx (%2), %%r8, %%r9; " /* A[0]*B[0] */ ++ "xorl %%r10d, %%r10d ;" ++ "movq %%r8, (%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[0]*B[1] */ ++ "adox %%r9, %%r10 ;" ++ "movq %%r10, 8(%0) ;" ++ "mulx 16(%2), %%r15, %%r13; " /* A[0]*B[2] */ ++ "adox %%r11, %%r15 ;" ++ "mulx 24(%2), %%r14, %%rdx; " /* A[0]*B[3] */ ++ "adox %%r13, %%r14 ;" ++ "movq $0, %%rax ;" ++ /******************************************/ ++ "adox %%rdx, %%rax ;" ++ ++ "movq 8(%1), %%rdx; " /* A[1] */ ++ "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ ++ "xorl %%r10d, %%r10d ;" ++ "adcx 8(%0), %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ ++ "adox %%r9, %%r10 ;" ++ "adcx %%r15, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "mulx 16(%2), %%r15, %%r13; " /* A[1]*B[2] */ ++ "adox %%r11, %%r15 ;" ++ "adcx %%r14, %%r15 ;" ++ "movq $0, %%r8 ;" ++ "mulx 24(%2), %%r14, %%rdx; " /* A[1]*B[3] */ ++ "adox %%r13, %%r14 ;" ++ "adcx %%rax, %%r14 ;" ++ "movq $0, %%rax ;" ++ /******************************************/ ++ "adox %%rdx, %%rax ;" ++ "adcx %%r8, %%rax ;" ++ ++ "movq 16(%1), %%rdx; " /* A[2] */ ++ "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ ++ "xorl %%r10d, %%r10d ;" ++ "adcx 16(%0), %%r8 ;" ++ "movq %%r8, 16(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ ++ "adox %%r9, %%r10 ;" ++ "adcx %%r15, %%r10 ;" ++ "movq %%r10, 24(%0) ;" ++ "mulx 16(%2), %%r15, %%r13; " /* A[2]*B[2] */ ++ "adox %%r11, %%r15 ;" ++ "adcx %%r14, %%r15 ;" ++ "movq $0, %%r8 ;" ++ "mulx 24(%2), %%r14, %%rdx; " /* A[2]*B[3] */ ++ "adox %%r13, %%r14 ;" ++ "adcx %%rax, %%r14 ;" ++ "movq $0, %%rax ;" ++ /******************************************/ ++ "adox %%rdx, %%rax ;" ++ "adcx %%r8, %%rax ;" ++ ++ "movq 24(%1), %%rdx; " /* A[3] */ ++ "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ ++ "xorl %%r10d, %%r10d ;" ++ "adcx 24(%0), %%r8 ;" ++ "movq %%r8, 24(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ ++ "adox %%r9, %%r10 ;" ++ "adcx %%r15, %%r10 ;" ++ "movq %%r10, 32(%0) ;" ++ "mulx 16(%2), %%r15, %%r13; " /* A[3]*B[2] */ ++ "adox %%r11, %%r15 ;" ++ "adcx %%r14, %%r15 ;" ++ "movq %%r15, 40(%0) ;" ++ "movq $0, %%r8 ;" ++ "mulx 24(%2), %%r14, %%rdx; " /* A[3]*B[3] */ ++ "adox %%r13, %%r14 ;" ++ "adcx %%rax, %%r14 ;" ++ "movq %%r14, 48(%0) ;" ++ "movq $0, %%rax ;" ++ /******************************************/ ++ "adox %%rdx, %%rax ;" ++ "adcx %%r8, %%rax ;" ++ "movq %%rax, 56(%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", ++ "%r13", "%r14", "%r15"); ++} ++ ++static void mul_256x256_integer_bmi2(u64 *const c, const u64 *const a, ++ const u64 *const b) ++{ ++ asm volatile( ++ "movq (%1), %%rdx; " /* A[0] */ ++ "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ ++ "movq %%r8, (%0) ;" ++ "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ ++ "addq %%r10, %%r15 ;" ++ "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ ++ "adcq %%r8, %%rax ;" ++ "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ ++ "adcq %%r10, %%rbx ;" ++ /******************************************/ ++ "adcq $0, %%rcx ;" ++ ++ "movq 8(%1), %%rdx; " /* A[1] */ ++ "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ ++ "addq %%r15, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%r15 ;" ++ ++ "addq %%r9, %%rax ;" ++ "adcq %%r11, %%rbx ;" ++ "adcq %%r13, %%rcx ;" ++ "adcq $0, %%r15 ;" ++ ++ "movq 16(%1), %%rdx; " /* A[2] */ ++ "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ ++ "addq %%rax, %%r8 ;" ++ "movq %%r8, 16(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%rax ;" ++ ++ "addq %%r9, %%rbx ;" ++ "adcq %%r11, %%rcx ;" ++ "adcq %%r13, %%r15 ;" ++ "adcq $0, %%rax ;" ++ ++ "movq 24(%1), %%rdx; " /* A[3] */ ++ "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ ++ "addq %%rbx, %%r8 ;" ++ "movq %%r8, 24(%0) ;" ++ "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ ++ "adcq %%r10, %%r9 ;" ++ "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ ++ "adcq %%r8, %%r11 ;" ++ "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ ++ "adcq %%r10, %%r13 ;" ++ /******************************************/ ++ "adcq $0, %%rbx ;" ++ ++ "addq %%r9, %%rcx ;" ++ "movq %%rcx, 32(%0) ;" ++ "adcq %%r11, %%r15 ;" ++ "movq %%r15, 40(%0) ;" ++ "adcq %%r13, %%rax ;" ++ "movq %%rax, 48(%0) ;" ++ "adcq $0, %%rbx ;" ++ "movq %%rbx, 56(%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11", "%r13", "%r15"); ++} ++ ++static void sqr_256x256_integer_adx(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movq (%1), %%rdx ;" /* A[0] */ ++ "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ ++ "xorl %%r15d, %%r15d;" ++ "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ ++ "adcx %%r14, %%r9 ;" ++ "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ ++ "adcx %%rax, %%r10 ;" ++ "movq 24(%1), %%rdx ;" /* A[3] */ ++ "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ ++ "adcx %%rcx, %%r11 ;" ++ "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ ++ "adcx %%rax, %%rbx ;" ++ "movq 8(%1), %%rdx ;" /* A[1] */ ++ "adcx %%r15, %%r13 ;" ++ "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ ++ "movq $0, %%r14 ;" ++ /******************************************/ ++ "adcx %%r15, %%r14 ;" ++ ++ "xorl %%r15d, %%r15d;" ++ "adox %%rax, %%r10 ;" ++ "adcx %%r8, %%r8 ;" ++ "adox %%rcx, %%r11 ;" ++ "adcx %%r9, %%r9 ;" ++ "adox %%r15, %%rbx ;" ++ "adcx %%r10, %%r10 ;" ++ "adox %%r15, %%r13 ;" ++ "adcx %%r11, %%r11 ;" ++ "adox %%r15, %%r14 ;" ++ "adcx %%rbx, %%rbx ;" ++ "adcx %%r13, %%r13 ;" ++ "adcx %%r14, %%r14 ;" ++ ++ "movq (%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ ++ /*******************/ ++ "movq %%rax, 0(%0) ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "movq 8(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ ++ "adcq %%rax, %%r9 ;" ++ "movq %%r9, 16(%0) ;" ++ "adcq %%rcx, %%r10 ;" ++ "movq %%r10, 24(%0) ;" ++ "movq 16(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ ++ "adcq %%rax, %%r11 ;" ++ "movq %%r11, 32(%0) ;" ++ "adcq %%rcx, %%rbx ;" ++ "movq %%rbx, 40(%0) ;" ++ "movq 24(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ ++ "adcq %%rax, %%r13 ;" ++ "movq %%r13, 48(%0) ;" ++ "adcq %%rcx, %%r14 ;" ++ "movq %%r14, 56(%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11", "%r13", "%r14", "%r15"); ++} ++ ++static void sqr_256x256_integer_bmi2(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movq 8(%1), %%rdx ;" /* A[1] */ ++ "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ ++ "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ ++ "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ ++ ++ "movq 16(%1), %%rdx ;" /* A[2] */ ++ "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ ++ "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ ++ ++ "addq %%rax, %%r9 ;" ++ "adcq %%rdx, %%r10 ;" ++ "adcq %%rcx, %%r11 ;" ++ "adcq %%r14, %%r15 ;" ++ "adcq $0, %%r13 ;" ++ "movq $0, %%r14 ;" ++ "adcq $0, %%r14 ;" ++ ++ "movq (%1), %%rdx ;" /* A[0] */ ++ "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ ++ ++ "addq %%rax, %%r10 ;" ++ "adcq %%rcx, %%r11 ;" ++ "adcq $0, %%r15 ;" ++ "adcq $0, %%r13 ;" ++ "adcq $0, %%r14 ;" ++ ++ "shldq $1, %%r13, %%r14 ;" ++ "shldq $1, %%r15, %%r13 ;" ++ "shldq $1, %%r11, %%r15 ;" ++ "shldq $1, %%r10, %%r11 ;" ++ "shldq $1, %%r9, %%r10 ;" ++ "shldq $1, %%r8, %%r9 ;" ++ "shlq $1, %%r8 ;" ++ ++ /*******************/ ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ ++ /*******************/ ++ "movq %%rax, 0(%0) ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, 8(%0) ;" ++ "movq 8(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ ++ "adcq %%rax, %%r9 ;" ++ "movq %%r9, 16(%0) ;" ++ "adcq %%rcx, %%r10 ;" ++ "movq %%r10, 24(%0) ;" ++ "movq 16(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ ++ "adcq %%rax, %%r11 ;" ++ "movq %%r11, 32(%0) ;" ++ "adcq %%rcx, %%r15 ;" ++ "movq %%r15, 40(%0) ;" ++ "movq 24(%1), %%rdx ;" ++ "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ ++ "adcq %%rax, %%r13 ;" ++ "movq %%r13, 48(%0) ;" ++ "adcq %%rcx, %%r14 ;" ++ "movq %%r14, 56(%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", ++ "%r11", "%r13", "%r14", "%r15"); ++} ++ ++static void red_eltfp25519_1w_adx(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ ++ "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ ++ "xorl %%ebx, %%ebx ;" ++ "adox (%1), %%r8 ;" ++ "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ ++ "adcx %%r10, %%r9 ;" ++ "adox 8(%1), %%r9 ;" ++ "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ ++ "adcx %%r11, %%r10 ;" ++ "adox 16(%1), %%r10 ;" ++ "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ ++ "adcx %%rax, %%r11 ;" ++ "adox 24(%1), %%r11 ;" ++ /***************************************/ ++ "adcx %%rbx, %%rcx ;" ++ "adox %%rbx, %%rcx ;" ++ "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ ++ "adcx %%rcx, %%r8 ;" ++ "adcx %%rbx, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcx %%rbx, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcx %%rbx, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", ++ "%r10", "%r11"); ++} ++ ++static void red_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) ++{ ++ asm volatile( ++ "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ ++ "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ ++ "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ ++ "addq %%r10, %%r9 ;" ++ "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ ++ "adcq %%r11, %%r10 ;" ++ "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ ++ "adcq %%rax, %%r11 ;" ++ /***************************************/ ++ "adcq $0, %%rcx ;" ++ "addq (%1), %%r8 ;" ++ "adcq 8(%1), %%r9 ;" ++ "adcq 16(%1), %%r10 ;" ++ "adcq 24(%1), %%r11 ;" ++ "adcq $0, %%rcx ;" ++ "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ ++ "addq %%rcx, %%r8 ;" ++ "adcq $0, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcq $0, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcq $0, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ : ++ : "r"(c), "r"(a) ++ : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", ++ "%r11"); ++} ++ ++static __always_inline void ++add_eltfp25519_1w_adx(u64 *const c, const u64 *const a, const u64 *const b) ++{ ++ asm volatile( ++ "mov $38, %%eax ;" ++ "xorl %%ecx, %%ecx ;" ++ "movq (%2), %%r8 ;" ++ "adcx (%1), %%r8 ;" ++ "movq 8(%2), %%r9 ;" ++ "adcx 8(%1), %%r9 ;" ++ "movq 16(%2), %%r10 ;" ++ "adcx 16(%1), %%r10 ;" ++ "movq 24(%2), %%r11 ;" ++ "adcx 24(%1), %%r11 ;" ++ "cmovc %%eax, %%ecx ;" ++ "xorl %%eax, %%eax ;" ++ "adcx %%rcx, %%r8 ;" ++ "adcx %%rax, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcx %%rax, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcx %%rax, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $38, %%ecx ;" ++ "cmovc %%ecx, %%eax ;" ++ "addq %%rax, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); ++} ++ ++static __always_inline void ++add_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a, const u64 *const b) ++{ ++ asm volatile( ++ "mov $38, %%eax ;" ++ "movq (%2), %%r8 ;" ++ "addq (%1), %%r8 ;" ++ "movq 8(%2), %%r9 ;" ++ "adcq 8(%1), %%r9 ;" ++ "movq 16(%2), %%r10 ;" ++ "adcq 16(%1), %%r10 ;" ++ "movq 24(%2), %%r11 ;" ++ "adcq 24(%1), %%r11 ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%eax, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "adcq $0, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcq $0, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcq $0, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%eax, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); ++} ++ ++static __always_inline void ++sub_eltfp25519_1w(u64 *const c, const u64 *const a, const u64 *const b) ++{ ++ asm volatile( ++ "mov $38, %%eax ;" ++ "movq (%1), %%r8 ;" ++ "subq (%2), %%r8 ;" ++ "movq 8(%1), %%r9 ;" ++ "sbbq 8(%2), %%r9 ;" ++ "movq 16(%1), %%r10 ;" ++ "sbbq 16(%2), %%r10 ;" ++ "movq 24(%1), %%r11 ;" ++ "sbbq 24(%2), %%r11 ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%eax, %%ecx ;" ++ "subq %%rcx, %%r8 ;" ++ "sbbq $0, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "sbbq $0, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "sbbq $0, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%eax, %%ecx ;" ++ "subq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(b) ++ : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); ++} ++ ++/* Multiplication by a24 = (A+2)/4 = (486662+2)/4 = 121666 */ ++static __always_inline void ++mul_a24_eltfp25519_1w(u64 *const c, const u64 *const a) ++{ ++ const u64 a24 = 121666; ++ asm volatile( ++ "movq %2, %%rdx ;" ++ "mulx (%1), %%r8, %%r10 ;" ++ "mulx 8(%1), %%r9, %%r11 ;" ++ "addq %%r10, %%r9 ;" ++ "mulx 16(%1), %%r10, %%rax ;" ++ "adcq %%r11, %%r10 ;" ++ "mulx 24(%1), %%r11, %%rcx ;" ++ "adcq %%rax, %%r11 ;" ++ /**************************/ ++ "adcq $0, %%rcx ;" ++ "movl $38, %%edx ;" /* 2*c = 38 = 2^256 mod 2^255-19*/ ++ "imul %%rdx, %%rcx ;" ++ "addq %%rcx, %%r8 ;" ++ "adcq $0, %%r9 ;" ++ "movq %%r9, 8(%0) ;" ++ "adcq $0, %%r10 ;" ++ "movq %%r10, 16(%0) ;" ++ "adcq $0, %%r11 ;" ++ "movq %%r11, 24(%0) ;" ++ "mov $0, %%ecx ;" ++ "cmovc %%edx, %%ecx ;" ++ "addq %%rcx, %%r8 ;" ++ "movq %%r8, (%0) ;" ++ : ++ : "r"(c), "r"(a), "r"(a24) ++ : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", ++ "%r11"); ++} ++ ++static void inv_eltfp25519_1w_adx(u64 *const c, const u64 *const a) ++{ ++ struct { ++ eltfp25519_1w_buffer buffer; ++ eltfp25519_1w x0, x1, x2; ++ } __aligned(32) m; ++ u64 *T[4]; ++ ++ T[0] = m.x0; ++ T[1] = c; /* x^(-1) */ ++ T[2] = m.x1; ++ T[3] = m.x2; ++ ++ copy_eltfp25519_1w(T[1], a); ++ sqrn_eltfp25519_1w_adx(T[1], 1); ++ copy_eltfp25519_1w(T[2], T[1]); ++ sqrn_eltfp25519_1w_adx(T[2], 2); ++ mul_eltfp25519_1w_adx(T[0], a, T[2]); ++ mul_eltfp25519_1w_adx(T[1], T[1], T[0]); ++ copy_eltfp25519_1w(T[2], T[1]); ++ sqrn_eltfp25519_1w_adx(T[2], 1); ++ mul_eltfp25519_1w_adx(T[0], T[0], T[2]); ++ copy_eltfp25519_1w(T[2], T[0]); ++ sqrn_eltfp25519_1w_adx(T[2], 5); ++ mul_eltfp25519_1w_adx(T[0], T[0], T[2]); ++ copy_eltfp25519_1w(T[2], T[0]); ++ sqrn_eltfp25519_1w_adx(T[2], 10); ++ mul_eltfp25519_1w_adx(T[2], T[2], T[0]); ++ copy_eltfp25519_1w(T[3], T[2]); ++ sqrn_eltfp25519_1w_adx(T[3], 20); ++ mul_eltfp25519_1w_adx(T[3], T[3], T[2]); ++ sqrn_eltfp25519_1w_adx(T[3], 10); ++ mul_eltfp25519_1w_adx(T[3], T[3], T[0]); ++ copy_eltfp25519_1w(T[0], T[3]); ++ sqrn_eltfp25519_1w_adx(T[0], 50); ++ mul_eltfp25519_1w_adx(T[0], T[0], T[3]); ++ copy_eltfp25519_1w(T[2], T[0]); ++ sqrn_eltfp25519_1w_adx(T[2], 100); ++ mul_eltfp25519_1w_adx(T[2], T[2], T[0]); ++ sqrn_eltfp25519_1w_adx(T[2], 50); ++ mul_eltfp25519_1w_adx(T[2], T[2], T[3]); ++ sqrn_eltfp25519_1w_adx(T[2], 5); ++ mul_eltfp25519_1w_adx(T[1], T[1], T[2]); ++ ++ memzero_explicit(&m, sizeof(m)); ++} ++ ++static void inv_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) ++{ ++ struct { ++ eltfp25519_1w_buffer buffer; ++ eltfp25519_1w x0, x1, x2; ++ } __aligned(32) m; ++ u64 *T[5]; ++ ++ T[0] = m.x0; ++ T[1] = c; /* x^(-1) */ ++ T[2] = m.x1; ++ T[3] = m.x2; ++ ++ copy_eltfp25519_1w(T[1], a); ++ sqrn_eltfp25519_1w_bmi2(T[1], 1); ++ copy_eltfp25519_1w(T[2], T[1]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 2); ++ mul_eltfp25519_1w_bmi2(T[0], a, T[2]); ++ mul_eltfp25519_1w_bmi2(T[1], T[1], T[0]); ++ copy_eltfp25519_1w(T[2], T[1]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 1); ++ mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); ++ copy_eltfp25519_1w(T[2], T[0]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 5); ++ mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); ++ copy_eltfp25519_1w(T[2], T[0]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 10); ++ mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); ++ copy_eltfp25519_1w(T[3], T[2]); ++ sqrn_eltfp25519_1w_bmi2(T[3], 20); ++ mul_eltfp25519_1w_bmi2(T[3], T[3], T[2]); ++ sqrn_eltfp25519_1w_bmi2(T[3], 10); ++ mul_eltfp25519_1w_bmi2(T[3], T[3], T[0]); ++ copy_eltfp25519_1w(T[0], T[3]); ++ sqrn_eltfp25519_1w_bmi2(T[0], 50); ++ mul_eltfp25519_1w_bmi2(T[0], T[0], T[3]); ++ copy_eltfp25519_1w(T[2], T[0]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 100); ++ mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 50); ++ mul_eltfp25519_1w_bmi2(T[2], T[2], T[3]); ++ sqrn_eltfp25519_1w_bmi2(T[2], 5); ++ mul_eltfp25519_1w_bmi2(T[1], T[1], T[2]); ++ ++ memzero_explicit(&m, sizeof(m)); ++} ++ ++/* Given c, a 256-bit number, fred_eltfp25519_1w updates c ++ * with a number such that 0 <= C < 2**255-19. ++ */ ++static __always_inline void fred_eltfp25519_1w(u64 *const c) ++{ ++ u64 tmp0 = 38, tmp1 = 19; ++ asm volatile( ++ "btrq $63, %3 ;" /* Put bit 255 in carry flag and clear */ ++ "cmovncl %k5, %k4 ;" /* c[255] ? 38 : 19 */ ++ ++ /* Add either 19 or 38 to c */ ++ "addq %4, %0 ;" ++ "adcq $0, %1 ;" ++ "adcq $0, %2 ;" ++ "adcq $0, %3 ;" ++ ++ /* Test for bit 255 again; only triggered on overflow modulo 2^255-19 */ ++ "movl $0, %k4 ;" ++ "cmovnsl %k5, %k4 ;" /* c[255] ? 0 : 19 */ ++ "btrq $63, %3 ;" /* Clear bit 255 */ ++ ++ /* Subtract 19 if necessary */ ++ "subq %4, %0 ;" ++ "sbbq $0, %1 ;" ++ "sbbq $0, %2 ;" ++ "sbbq $0, %3 ;" ++ ++ : "+r"(c[0]), "+r"(c[1]), "+r"(c[2]), "+r"(c[3]), "+r"(tmp0), ++ "+r"(tmp1) ++ : ++ : "memory", "cc"); ++} ++ ++static __always_inline void cswap(u8 bit, u64 *const px, u64 *const py) ++{ ++ u64 temp; ++ asm volatile( ++ "test %9, %9 ;" ++ "movq %0, %8 ;" ++ "cmovnzq %4, %0 ;" ++ "cmovnzq %8, %4 ;" ++ "movq %1, %8 ;" ++ "cmovnzq %5, %1 ;" ++ "cmovnzq %8, %5 ;" ++ "movq %2, %8 ;" ++ "cmovnzq %6, %2 ;" ++ "cmovnzq %8, %6 ;" ++ "movq %3, %8 ;" ++ "cmovnzq %7, %3 ;" ++ "cmovnzq %8, %7 ;" ++ : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]), ++ "+r"(py[0]), "+r"(py[1]), "+r"(py[2]), "+r"(py[3]), ++ "=r"(temp) ++ : "r"(bit) ++ : "cc" ++ ); ++} ++ ++static __always_inline void cselect(u8 bit, u64 *const px, const u64 *const py) ++{ ++ asm volatile( ++ "test %4, %4 ;" ++ "cmovnzq %5, %0 ;" ++ "cmovnzq %6, %1 ;" ++ "cmovnzq %7, %2 ;" ++ "cmovnzq %8, %3 ;" ++ : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]) ++ : "r"(bit), "rm"(py[0]), "rm"(py[1]), "rm"(py[2]), "rm"(py[3]) ++ : "cc" ++ ); ++} ++ ++static void curve25519_adx(u8 shared[CURVE25519_KEY_SIZE], ++ const u8 private_key[CURVE25519_KEY_SIZE], ++ const u8 session_key[CURVE25519_KEY_SIZE]) ++{ ++ struct { ++ u64 buffer[4 * NUM_WORDS_ELTFP25519]; ++ u64 coordinates[4 * NUM_WORDS_ELTFP25519]; ++ u64 workspace[6 * NUM_WORDS_ELTFP25519]; ++ u8 session[CURVE25519_KEY_SIZE]; ++ u8 private[CURVE25519_KEY_SIZE]; ++ } __aligned(32) m; ++ ++ int i = 0, j = 0; ++ u64 prev = 0; ++ u64 *const X1 = (u64 *)m.session; ++ u64 *const key = (u64 *)m.private; ++ u64 *const Px = m.coordinates + 0; ++ u64 *const Pz = m.coordinates + 4; ++ u64 *const Qx = m.coordinates + 8; ++ u64 *const Qz = m.coordinates + 12; ++ u64 *const X2 = Qx; ++ u64 *const Z2 = Qz; ++ u64 *const X3 = Px; ++ u64 *const Z3 = Pz; ++ u64 *const X2Z2 = Qx; ++ u64 *const X3Z3 = Px; ++ ++ u64 *const A = m.workspace + 0; ++ u64 *const B = m.workspace + 4; ++ u64 *const D = m.workspace + 8; ++ u64 *const C = m.workspace + 12; ++ u64 *const DA = m.workspace + 16; ++ u64 *const CB = m.workspace + 20; ++ u64 *const AB = A; ++ u64 *const DC = D; ++ u64 *const DACB = DA; ++ ++ memcpy(m.private, private_key, sizeof(m.private)); ++ memcpy(m.session, session_key, sizeof(m.session)); ++ ++ curve25519_clamp_secret(m.private); ++ ++ /* As in the draft: ++ * When receiving such an array, implementations of curve25519 ++ * MUST mask the most-significant bit in the final byte. This ++ * is done to preserve compatibility with point formats which ++ * reserve the sign bit for use in other protocols and to ++ * increase resistance to implementation fingerprinting ++ */ ++ m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; ++ ++ copy_eltfp25519_1w(Px, X1); ++ setzero_eltfp25519_1w(Pz); ++ setzero_eltfp25519_1w(Qx); ++ setzero_eltfp25519_1w(Qz); ++ ++ Pz[0] = 1; ++ Qx[0] = 1; ++ ++ /* main-loop */ ++ prev = 0; ++ j = 62; ++ for (i = 3; i >= 0; --i) { ++ while (j >= 0) { ++ u64 bit = (key[i] >> j) & 0x1; ++ u64 swap = bit ^ prev; ++ prev = bit; ++ ++ add_eltfp25519_1w_adx(A, X2, Z2); /* A = (X2+Z2) */ ++ sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ ++ add_eltfp25519_1w_adx(C, X3, Z3); /* C = (X3+Z3) */ ++ sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ ++ mul_eltfp25519_2w_adx(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ ++ ++ cselect(swap, A, C); ++ cselect(swap, B, D); ++ ++ sqr_eltfp25519_2w_adx(AB); /* [AA|BB] = [A^2|B^2] */ ++ add_eltfp25519_1w_adx(X3, DA, CB); /* X3 = (DA+CB) */ ++ sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ ++ sqr_eltfp25519_2w_adx(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ ++ ++ copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ ++ sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ ++ ++ mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ ++ add_eltfp25519_1w_adx(B, B, X2); /* B = a24*E+B */ ++ mul_eltfp25519_2w_adx(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ ++ mul_eltfp25519_1w_adx(Z3, Z3, X1); /* Z3 = Z3*X1 */ ++ --j; ++ } ++ j = 63; ++ } ++ ++ inv_eltfp25519_1w_adx(A, Qz); ++ mul_eltfp25519_1w_adx((u64 *)shared, Qx, A); ++ fred_eltfp25519_1w((u64 *)shared); ++ ++ memzero_explicit(&m, sizeof(m)); ++} ++ ++static void curve25519_adx_base(u8 session_key[CURVE25519_KEY_SIZE], ++ const u8 private_key[CURVE25519_KEY_SIZE]) ++{ ++ struct { ++ u64 buffer[4 * NUM_WORDS_ELTFP25519]; ++ u64 coordinates[4 * NUM_WORDS_ELTFP25519]; ++ u64 workspace[4 * NUM_WORDS_ELTFP25519]; ++ u8 private[CURVE25519_KEY_SIZE]; ++ } __aligned(32) m; ++ ++ const int ite[4] = { 64, 64, 64, 63 }; ++ const int q = 3; ++ u64 swap = 1; ++ ++ int i = 0, j = 0, k = 0; ++ u64 *const key = (u64 *)m.private; ++ u64 *const Ur1 = m.coordinates + 0; ++ u64 *const Zr1 = m.coordinates + 4; ++ u64 *const Ur2 = m.coordinates + 8; ++ u64 *const Zr2 = m.coordinates + 12; ++ ++ u64 *const UZr1 = m.coordinates + 0; ++ u64 *const ZUr2 = m.coordinates + 8; ++ ++ u64 *const A = m.workspace + 0; ++ u64 *const B = m.workspace + 4; ++ u64 *const C = m.workspace + 8; ++ u64 *const D = m.workspace + 12; ++ ++ u64 *const AB = m.workspace + 0; ++ u64 *const CD = m.workspace + 8; ++ ++ const u64 *const P = table_ladder_8k; ++ ++ memcpy(m.private, private_key, sizeof(m.private)); ++ ++ curve25519_clamp_secret(m.private); ++ ++ setzero_eltfp25519_1w(Ur1); ++ setzero_eltfp25519_1w(Zr1); ++ setzero_eltfp25519_1w(Zr2); ++ Ur1[0] = 1; ++ Zr1[0] = 1; ++ Zr2[0] = 1; ++ ++ /* G-S */ ++ Ur2[3] = 0x1eaecdeee27cab34UL; ++ Ur2[2] = 0xadc7a0b9235d48e2UL; ++ Ur2[1] = 0xbbf095ae14b2edf8UL; ++ Ur2[0] = 0x7e94e1fec82faabdUL; ++ ++ /* main-loop */ ++ j = q; ++ for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { ++ while (j < ite[i]) { ++ u64 bit = (key[i] >> j) & 0x1; ++ k = (64 * i + j - q); ++ swap = swap ^ bit; ++ cswap(swap, Ur1, Ur2); ++ cswap(swap, Zr1, Zr2); ++ swap = bit; ++ /* Addition */ ++ sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ ++ add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ ++ mul_eltfp25519_1w_adx(C, &P[4 * k], B); /* C = M0-B */ ++ sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ ++ add_eltfp25519_1w_adx(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ ++ sqr_eltfp25519_2w_adx(AB); /* A = A^2 | B = B^2 */ ++ mul_eltfp25519_2w_adx(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ ++ ++j; ++ } ++ j = 0; ++ } ++ ++ /* Doubling */ ++ for (i = 0; i < q; ++i) { ++ add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ ++ sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ ++ sqr_eltfp25519_2w_adx(AB); /* A = A**2 B = B**2 */ ++ copy_eltfp25519_1w(C, B); /* C = B */ ++ sub_eltfp25519_1w(B, A, B); /* B = A-B */ ++ mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ ++ add_eltfp25519_1w_adx(D, D, C); /* D = D+C */ ++ mul_eltfp25519_2w_adx(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ ++ } ++ ++ /* Convert to affine coordinates */ ++ inv_eltfp25519_1w_adx(A, Zr1); ++ mul_eltfp25519_1w_adx((u64 *)session_key, Ur1, A); ++ fred_eltfp25519_1w((u64 *)session_key); ++ ++ memzero_explicit(&m, sizeof(m)); ++} ++ ++static void curve25519_bmi2(u8 shared[CURVE25519_KEY_SIZE], ++ const u8 private_key[CURVE25519_KEY_SIZE], ++ const u8 session_key[CURVE25519_KEY_SIZE]) ++{ ++ struct { ++ u64 buffer[4 * NUM_WORDS_ELTFP25519]; ++ u64 coordinates[4 * NUM_WORDS_ELTFP25519]; ++ u64 workspace[6 * NUM_WORDS_ELTFP25519]; ++ u8 session[CURVE25519_KEY_SIZE]; ++ u8 private[CURVE25519_KEY_SIZE]; ++ } __aligned(32) m; ++ ++ int i = 0, j = 0; ++ u64 prev = 0; ++ u64 *const X1 = (u64 *)m.session; ++ u64 *const key = (u64 *)m.private; ++ u64 *const Px = m.coordinates + 0; ++ u64 *const Pz = m.coordinates + 4; ++ u64 *const Qx = m.coordinates + 8; ++ u64 *const Qz = m.coordinates + 12; ++ u64 *const X2 = Qx; ++ u64 *const Z2 = Qz; ++ u64 *const X3 = Px; ++ u64 *const Z3 = Pz; ++ u64 *const X2Z2 = Qx; ++ u64 *const X3Z3 = Px; ++ ++ u64 *const A = m.workspace + 0; ++ u64 *const B = m.workspace + 4; ++ u64 *const D = m.workspace + 8; ++ u64 *const C = m.workspace + 12; ++ u64 *const DA = m.workspace + 16; ++ u64 *const CB = m.workspace + 20; ++ u64 *const AB = A; ++ u64 *const DC = D; ++ u64 *const DACB = DA; ++ ++ memcpy(m.private, private_key, sizeof(m.private)); ++ memcpy(m.session, session_key, sizeof(m.session)); ++ ++ curve25519_clamp_secret(m.private); ++ ++ /* As in the draft: ++ * When receiving such an array, implementations of curve25519 ++ * MUST mask the most-significant bit in the final byte. This ++ * is done to preserve compatibility with point formats which ++ * reserve the sign bit for use in other protocols and to ++ * increase resistance to implementation fingerprinting ++ */ ++ m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; ++ ++ copy_eltfp25519_1w(Px, X1); ++ setzero_eltfp25519_1w(Pz); ++ setzero_eltfp25519_1w(Qx); ++ setzero_eltfp25519_1w(Qz); ++ ++ Pz[0] = 1; ++ Qx[0] = 1; ++ ++ /* main-loop */ ++ prev = 0; ++ j = 62; ++ for (i = 3; i >= 0; --i) { ++ while (j >= 0) { ++ u64 bit = (key[i] >> j) & 0x1; ++ u64 swap = bit ^ prev; ++ prev = bit; ++ ++ add_eltfp25519_1w_bmi2(A, X2, Z2); /* A = (X2+Z2) */ ++ sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ ++ add_eltfp25519_1w_bmi2(C, X3, Z3); /* C = (X3+Z3) */ ++ sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ ++ mul_eltfp25519_2w_bmi2(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ ++ ++ cselect(swap, A, C); ++ cselect(swap, B, D); ++ ++ sqr_eltfp25519_2w_bmi2(AB); /* [AA|BB] = [A^2|B^2] */ ++ add_eltfp25519_1w_bmi2(X3, DA, CB); /* X3 = (DA+CB) */ ++ sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ ++ sqr_eltfp25519_2w_bmi2(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ ++ ++ copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ ++ sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ ++ ++ mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ ++ add_eltfp25519_1w_bmi2(B, B, X2); /* B = a24*E+B */ ++ mul_eltfp25519_2w_bmi2(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ ++ mul_eltfp25519_1w_bmi2(Z3, Z3, X1); /* Z3 = Z3*X1 */ ++ --j; ++ } ++ j = 63; ++ } ++ ++ inv_eltfp25519_1w_bmi2(A, Qz); ++ mul_eltfp25519_1w_bmi2((u64 *)shared, Qx, A); ++ fred_eltfp25519_1w((u64 *)shared); ++ ++ memzero_explicit(&m, sizeof(m)); ++} ++ ++static void curve25519_bmi2_base(u8 session_key[CURVE25519_KEY_SIZE], ++ const u8 private_key[CURVE25519_KEY_SIZE]) ++{ ++ struct { ++ u64 buffer[4 * NUM_WORDS_ELTFP25519]; ++ u64 coordinates[4 * NUM_WORDS_ELTFP25519]; ++ u64 workspace[4 * NUM_WORDS_ELTFP25519]; ++ u8 private[CURVE25519_KEY_SIZE]; ++ } __aligned(32) m; ++ ++ const int ite[4] = { 64, 64, 64, 63 }; ++ const int q = 3; ++ u64 swap = 1; ++ ++ int i = 0, j = 0, k = 0; ++ u64 *const key = (u64 *)m.private; ++ u64 *const Ur1 = m.coordinates + 0; ++ u64 *const Zr1 = m.coordinates + 4; ++ u64 *const Ur2 = m.coordinates + 8; ++ u64 *const Zr2 = m.coordinates + 12; ++ ++ u64 *const UZr1 = m.coordinates + 0; ++ u64 *const ZUr2 = m.coordinates + 8; ++ ++ u64 *const A = m.workspace + 0; ++ u64 *const B = m.workspace + 4; ++ u64 *const C = m.workspace + 8; ++ u64 *const D = m.workspace + 12; ++ ++ u64 *const AB = m.workspace + 0; ++ u64 *const CD = m.workspace + 8; ++ ++ const u64 *const P = table_ladder_8k; ++ ++ memcpy(m.private, private_key, sizeof(m.private)); ++ ++ curve25519_clamp_secret(m.private); ++ ++ setzero_eltfp25519_1w(Ur1); ++ setzero_eltfp25519_1w(Zr1); ++ setzero_eltfp25519_1w(Zr2); ++ Ur1[0] = 1; ++ Zr1[0] = 1; ++ Zr2[0] = 1; ++ ++ /* G-S */ ++ Ur2[3] = 0x1eaecdeee27cab34UL; ++ Ur2[2] = 0xadc7a0b9235d48e2UL; ++ Ur2[1] = 0xbbf095ae14b2edf8UL; ++ Ur2[0] = 0x7e94e1fec82faabdUL; ++ ++ /* main-loop */ ++ j = q; ++ for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { ++ while (j < ite[i]) { ++ u64 bit = (key[i] >> j) & 0x1; ++ k = (64 * i + j - q); ++ swap = swap ^ bit; ++ cswap(swap, Ur1, Ur2); ++ cswap(swap, Zr1, Zr2); ++ swap = bit; ++ /* Addition */ ++ sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ ++ add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ ++ mul_eltfp25519_1w_bmi2(C, &P[4 * k], B);/* C = M0-B */ ++ sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ ++ add_eltfp25519_1w_bmi2(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ ++ sqr_eltfp25519_2w_bmi2(AB); /* A = A^2 | B = B^2 */ ++ mul_eltfp25519_2w_bmi2(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ ++ ++j; ++ } ++ j = 0; ++ } ++ ++ /* Doubling */ ++ for (i = 0; i < q; ++i) { ++ add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ ++ sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ ++ sqr_eltfp25519_2w_bmi2(AB); /* A = A**2 B = B**2 */ ++ copy_eltfp25519_1w(C, B); /* C = B */ ++ sub_eltfp25519_1w(B, A, B); /* B = A-B */ ++ mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ ++ add_eltfp25519_1w_bmi2(D, D, C); /* D = D+C */ ++ mul_eltfp25519_2w_bmi2(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ ++ } ++ ++ /* Convert to affine coordinates */ ++ inv_eltfp25519_1w_bmi2(A, Zr1); ++ mul_eltfp25519_1w_bmi2((u64 *)session_key, Ur1, A); ++ fred_eltfp25519_1w((u64 *)session_key); ++ ++ memzero_explicit(&m, sizeof(m)); ++} ++ ++void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE], ++ const u8 secret[CURVE25519_KEY_SIZE], ++ const u8 basepoint[CURVE25519_KEY_SIZE]) ++{ ++ if (static_branch_likely(&curve25519_use_adx)) ++ curve25519_adx(mypublic, secret, basepoint); ++ else if (static_branch_likely(&curve25519_use_bmi2)) ++ curve25519_bmi2(mypublic, secret, basepoint); ++ else ++ curve25519_generic(mypublic, secret, basepoint); ++} ++EXPORT_SYMBOL(curve25519_arch); ++ ++void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], ++ const u8 secret[CURVE25519_KEY_SIZE]) ++{ ++ if (static_branch_likely(&curve25519_use_adx)) ++ curve25519_adx_base(pub, secret); ++ else if (static_branch_likely(&curve25519_use_bmi2)) ++ curve25519_bmi2_base(pub, secret); ++ else ++ curve25519_generic(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_generate_public_key(struct kpp_request *req) ++{ ++ struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); ++ const u8 *secret = kpp_tfm_ctx(tfm); ++ u8 buf[CURVE25519_KEY_SIZE]; ++ int copied, nbytes; ++ ++ if (req->src) ++ return -EINVAL; ++ ++ curve25519_base_arch(buf, secret); ++ ++ /* 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 int curve25519_compute_shared_secret(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; ++ ++ if (!req->src) ++ return -EINVAL; ++ ++ 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; ++ ++ curve25519_arch(buf, secret, public_key); ++ ++ /* 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-x86", ++ .base.cra_priority = 200, ++ .base.cra_module = THIS_MODULE, ++ .base.cra_ctxsize = CURVE25519_KEY_SIZE, ++ ++ .set_secret = curve25519_set_secret, ++ .generate_public_key = curve25519_generate_public_key, ++ .compute_shared_secret = curve25519_compute_shared_secret, ++ .max_size = curve25519_max_size, ++}; ++ ++static int __init curve25519_mod_init(void) ++{ ++ if (boot_cpu_has(X86_FEATURE_BMI2)) ++ static_branch_enable(&curve25519_use_bmi2); ++ else if (boot_cpu_has(X86_FEATURE_ADX)) ++ static_branch_enable(&curve25519_use_adx); ++ else ++ return 0; ++ return crypto_register_kpp(&curve25519_alg); ++} ++ ++static void __exit curve25519_mod_exit(void) ++{ ++ if (boot_cpu_has(X86_FEATURE_BMI2) || ++ boot_cpu_has(X86_FEATURE_ADX)) ++ crypto_unregister_kpp(&curve25519_alg); ++} ++ ++module_init(curve25519_mod_init); ++module_exit(curve25519_mod_exit); ++ ++MODULE_ALIAS_CRYPTO("curve25519"); ++MODULE_ALIAS_CRYPTO("curve25519-x86"); ++MODULE_LICENSE("GPL v2"); +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -269,6 +269,12 @@ config CRYPTO_CURVE25519 + select CRYPTO_KPP + select CRYPTO_LIB_CURVE25519_GENERIC + ++config CRYPTO_CURVE25519_X86 ++ tristate "x86_64 accelerated Curve25519 scalar multiplication library" ++ depends on X86 && 64BIT ++ select CRYPTO_LIB_CURVE25519_GENERIC ++ select CRYPTO_ARCH_HAVE_LIB_CURVE25519 ++ + comment "Authenticated Encryption with Associated Data" + + config CRYPTO_CCM diff --git a/target/linux/generic/backport-5.4/080-wireguard-0030-crypto-arm-curve25519-import-Bernstein-and-Schwabe-s.patch b/target/linux/generic/backport-5.4/080-wireguard-0030-crypto-arm-curve25519-import-Bernstein-and-Schwabe-s.patch new file mode 100644 index 0000000000..b15a32b5cb --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0030-crypto-arm-curve25519-import-Bernstein-and-Schwabe-s.patch @@ -0,0 +1,2135 @@ +From bfc49f5ecdd60f2b37cd2f21a6f4de6ea91625e5 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:37 +0100 +Subject: [PATCH 030/124] crypto: arm/curve25519 - import Bernstein and + Schwabe's Curve25519 ARM implementation + +commit f0fb006b604f98e2309a30f34ef455ac734f7c1c upstream. + +This comes from Dan Bernstein and Peter Schwabe's public domain NEON +code, and is included here in raw form so that subsequent commits that +fix these up for the kernel can see how it has changed. This code does +have some entirely cosmetic formatting differences, adding indentation +and so forth, so that when we actually port it for use in the kernel in +the subsequent commit, it's obvious what's changed in the process. + +This code originates from SUPERCOP 20180818, available at +. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/curve25519-core.S | 2105 +++++++++++++++++++++++++++++ + 1 file changed, 2105 insertions(+) + create mode 100644 arch/arm/crypto/curve25519-core.S + +--- /dev/null ++++ b/arch/arm/crypto/curve25519-core.S +@@ -0,0 +1,2105 @@ ++/* ++ * Public domain code from Daniel J. Bernstein and Peter Schwabe, from ++ * SUPERCOP's curve25519/neon2/scalarmult.s. ++ */ ++ ++.fpu neon ++.text ++.align 4 ++.global _crypto_scalarmult_curve25519_neon2 ++.global crypto_scalarmult_curve25519_neon2 ++.type _crypto_scalarmult_curve25519_neon2 STT_FUNC ++.type crypto_scalarmult_curve25519_neon2 STT_FUNC ++ _crypto_scalarmult_curve25519_neon2: ++ crypto_scalarmult_curve25519_neon2: ++ vpush {q4, q5, q6, q7} ++ mov r12, sp ++ sub sp, sp, #736 ++ and sp, sp, #0xffffffe0 ++ strd r4, [sp, #0] ++ strd r6, [sp, #8] ++ strd r8, [sp, #16] ++ strd r10, [sp, #24] ++ str r12, [sp, #480] ++ str r14, [sp, #484] ++ mov r0, r0 ++ mov r1, r1 ++ mov r2, r2 ++ add r3, sp, #32 ++ ldr r4, =0 ++ ldr 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, #512 ++ vst1.8 {d2-d3}, [r6, : 128] ++ add r6, sp, #528 ++ vst1.8 {d0-d1}, [r6, : 128] ++ add r6, sp, #544 ++ 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 ++ ldr r7, =960 ++ sub r7, r7, #2 ++ neg r7, r7 ++ sub r7, r7, r7, LSL #7 ++ str r7, [r6] ++ add r6, sp, #704 ++ 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] ++._mainloop: ++ 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, #488] ++ eor r4, r4, r2 ++ str r2, [sp, #492] ++ 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, #544 ++ 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, #512 ++ 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 ++ add r2, sp, #528 ++ 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, #560 ++ vadd.i32 q10, q10, q2 ++ vtrn.32 d24, d25 ++ vst1.8 {d12-d13}, [r2, : 128] ++ vshl.i32 q6, q13, #1 ++ add r2, sp, #576 ++ vst1.8 {d20-d21}, [r2, : 128] ++ vshl.i32 q10, q14, #1 ++ add r2, sp, #592 ++ 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 ++ add r2, sp, #608 ++ 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 ++ add r2, sp, #624 ++ 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 ++ add r2, sp, #640 ++ 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 ++ add r2, sp, #656 ++ 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 ++ add r2, sp, #672 ++ 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, #576 ++ 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 ++ add r2, sp, #576 ++ vst1.8 {d14-d15}, [r2, : 128] ++ vmull.s32 q7, d18, d6 ++ vmlal.s32 q7, d26, d0 ++ add r2, sp, #656 ++ vld1.8 {d30-d31}, [r2, : 128] ++ vmlal.s32 q2, d30, d21 ++ vmlal.s32 q7, d19, d21 ++ vmlal.s32 q7, d27, d20 ++ add r2, sp, #624 ++ 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, #608 ++ 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 ++ add r2, sp, #608 ++ vst1.8 {d8-d9}, [r2, : 128] ++ add r2, sp, #560 ++ 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, #640 ++ vld1.8 {d18-d19}, [r2, : 128] ++ vmlal.s32 q2, d18, d7 ++ vmlal.s32 q2, d19, d6 ++ vmlal.s32 q5, d18, d6 ++ vmlal.s32 q5, d19, d21 ++ vmlal.s32 q1, d18, d21 ++ vmlal.s32 q1, d19, d29 ++ vmlal.s32 q0, d18, d28 ++ vmlal.s32 q0, d19, d9 ++ vmlal.s32 q6, d18, d29 ++ vmlal.s32 q6, d19, d28 ++ add r2, sp, #592 ++ vld1.8 {d18-d19}, [r2, : 128] ++ add r2, sp, #512 ++ 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, #528 ++ vld1.8 {d6-d7}, [r2, : 128] ++ vmlal.s32 q6, d19, d21 ++ add r2, sp, #576 ++ vld1.8 {d18-d19}, [r2, : 128] ++ vmlal.s32 q0, d30, d8 ++ add r2, sp, #672 ++ vld1.8 {d20-d21}, [r2, : 128] ++ vmlal.s32 q5, d30, d29 ++ add r2, sp, #608 ++ 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, #560 ++ vadd.i32 q10, q10, q2 ++ vtrn.32 d24, d25 ++ vst1.8 {d12-d13}, [r2, : 128] ++ vshl.i32 q6, q13, #1 ++ add r2, sp, #576 ++ vst1.8 {d20-d21}, [r2, : 128] ++ vshl.i32 q10, q14, #1 ++ add r2, sp, #592 ++ 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 ++ add r2, sp, #608 ++ 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 ++ add r2, sp, #624 ++ 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 ++ add r2, sp, #640 ++ 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 ++ add r2, sp, #656 ++ 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 ++ add r2, sp, #672 ++ 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, #576 ++ 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 ++ add r2, sp, #576 ++ vst1.8 {d14-d15}, [r2, : 128] ++ vmull.s32 q7, d18, d6 ++ vmlal.s32 q7, d26, d0 ++ add r2, sp, #656 ++ vld1.8 {d30-d31}, [r2, : 128] ++ vmlal.s32 q2, d30, d21 ++ vmlal.s32 q7, d19, d21 ++ vmlal.s32 q7, d27, d20 ++ add r2, sp, #624 ++ 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, #608 ++ 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 ++ add r2, sp, #608 ++ vst1.8 {d8-d9}, [r2, : 128] ++ add r2, sp, #560 ++ 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, #640 ++ vld1.8 {d18-d19}, [r2, : 128] ++ vmlal.s32 q2, d18, d7 ++ vmlal.s32 q2, d19, d6 ++ vmlal.s32 q5, d18, d6 ++ vmlal.s32 q5, d19, d21 ++ vmlal.s32 q1, d18, d21 ++ vmlal.s32 q1, d19, d29 ++ vmlal.s32 q0, d18, d28 ++ vmlal.s32 q0, d19, d9 ++ vmlal.s32 q6, d18, d29 ++ vmlal.s32 q6, d19, d28 ++ add r2, sp, #592 ++ vld1.8 {d18-d19}, [r2, : 128] ++ add r2, sp, #512 ++ 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, #528 ++ vld1.8 {d6-d7}, [r2, : 128] ++ vmlal.s32 q6, d19, d21 ++ add r2, sp, #576 ++ vld1.8 {d18-d19}, [r2, : 128] ++ vmlal.s32 q0, d30, d8 ++ add r2, sp, #672 ++ vld1.8 {d20-d21}, [r2, : 128] ++ vmlal.s32 q5, d30, d29 ++ add r2, sp, #608 ++ 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, #544 ++ 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, #512 ++ 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 ++ add r2, sp, #528 ++ 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, #560 ++ vadd.i32 q10, q10, q2 ++ vtrn.32 d24, d25 ++ vst1.8 {d12-d13}, [r2, : 128] ++ vshl.i32 q6, q13, #1 ++ add r2, sp, #576 ++ vst1.8 {d20-d21}, [r2, : 128] ++ vshl.i32 q10, q14, #1 ++ add r2, sp, #592 ++ 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 ++ add r2, sp, #608 ++ 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 ++ add r2, sp, #624 ++ 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 ++ add r2, sp, #640 ++ 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 ++ add r2, sp, #656 ++ 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 ++ add r2, sp, #672 ++ 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, #576 ++ 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 ++ add r2, sp, #576 ++ vst1.8 {d14-d15}, [r2, : 128] ++ vmull.s32 q7, d18, d6 ++ vmlal.s32 q7, d26, d0 ++ add r2, sp, #656 ++ vld1.8 {d30-d31}, [r2, : 128] ++ vmlal.s32 q2, d30, d21 ++ vmlal.s32 q7, d19, d21 ++ vmlal.s32 q7, d27, d20 ++ add r2, sp, #624 ++ 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, #608 ++ 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 ++ add r2, sp, #608 ++ vst1.8 {d8-d9}, [r2, : 128] ++ add r2, sp, #560 ++ 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, #640 ++ vld1.8 {d18-d19}, [r2, : 128] ++ vmlal.s32 q2, d18, d7 ++ vmlal.s32 q2, d19, d6 ++ vmlal.s32 q5, d18, d6 ++ vmlal.s32 q5, d19, d21 ++ vmlal.s32 q1, d18, d21 ++ vmlal.s32 q1, d19, d29 ++ vmlal.s32 q0, d18, d28 ++ vmlal.s32 q0, d19, d9 ++ vmlal.s32 q6, d18, d29 ++ vmlal.s32 q6, d19, d28 ++ add r2, sp, #592 ++ vld1.8 {d18-d19}, [r2, : 128] ++ add r2, sp, #512 ++ 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, #528 ++ vld1.8 {d6-d7}, [r2, : 128] ++ vmlal.s32 q6, d19, d21 ++ add r2, sp, #576 ++ vld1.8 {d18-d19}, [r2, : 128] ++ vmlal.s32 q0, d30, d8 ++ add r2, sp, #672 ++ vld1.8 {d20-d21}, [r2, : 128] ++ vmlal.s32 q5, d30, d29 ++ add r2, sp, #608 ++ 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, #488] ++ ldr r4, [sp, #492] ++ subs r5, r2, #1 ++ bge ._mainloop ++ 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] ++ ldr r1, =0 ++._invertloop: ++ add r2, r3, #144 ++ ldr r4, =0 ++ ldr r5, =2 ++ cmp r1, #1 ++ ldreq r5, =1 ++ addeq r2, r3, #336 ++ addeq r4, r3, #48 ++ cmp r1, #2 ++ ldreq r5, =1 ++ addeq r2, r3, #48 ++ cmp r1, #3 ++ ldreq r5, =5 ++ addeq r4, r3, #336 ++ cmp r1, #4 ++ ldreq r5, =10 ++ cmp r1, #5 ++ ldreq r5, =20 ++ cmp r1, #6 ++ ldreq r5, =10 ++ addeq r2, r3, #336 ++ addeq r4, r3, #336 ++ cmp r1, #7 ++ ldreq r5, =50 ++ cmp r1, #8 ++ ldreq r5, =100 ++ cmp r1, #9 ++ ldreq r5, =50 ++ addeq r2, r3, #336 ++ cmp r1, #10 ++ ldreq r5, =5 ++ addeq r2, r3, #48 ++ cmp r1, #11 ++ ldreq 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 ._skipsquaringloop ++._squaringloop: ++ 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, #416 ++ 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, #512 ++ 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, #528 ++ 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 ._squaringloop ++._skipsquaringloop: ++ 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, #416 ++ 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, #512 ++ 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, #528 ++ 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 ._skippostcopy ++ 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] ++._skippostcopy: ++ cmp r1, #1 ++ bne ._skipfinalcopy ++ 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] ++._skipfinalcopy: ++ add r1, r1, #1 ++ cmp r1, #12 ++ blo ._invertloop ++ 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], #4 ++ str r3, [r0], #4 ++ str r4, [r0], #4 ++ str r5, [r0], #4 ++ str r6, [r0], #4 ++ str r7, [r0], #4 ++ str r8, [r0], #4 ++ str r1, [r0] ++ ldrd r4, [sp, #0] ++ ldrd r6, [sp, #8] ++ ldrd r8, [sp, #16] ++ ldrd r10, [sp, #24] ++ ldr r12, [sp, #480] ++ ldr r14, [sp, #484] ++ ldr r0, =0 ++ mov sp, r12 ++ vpop {q4, q5, q6, q7} ++ bx lr diff --git a/target/linux/generic/backport-5.4/080-wireguard-0031-crypto-arm-curve25519-wire-up-NEON-implementation.patch b/target/linux/generic/backport-5.4/080-wireguard-0031-crypto-arm-curve25519-wire-up-NEON-implementation.patch new file mode 100644 index 0000000000..14a75e10eb --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0031-crypto-arm-curve25519-wire-up-NEON-implementation.patch @@ -0,0 +1,1058 @@ +From ec96c25c1ce09c78e44bd4627bc0a3e610b7f5d8 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 8 Nov 2019 13:22:38 +0100 +Subject: [PATCH 031/124] crypto: arm/curve25519 - wire up NEON implementation + +commit d8f1308a025fc7e00414194ed742d5f05a21e13c upstream. + +This ports the SUPERCOP implementation for usage in kernel space. In +addition to the usual header, macro, and style changes required for +kernel space, it makes a few small changes to the code: + + - The stack alignment is relaxed to 16 bytes. + - Superfluous mov statements have been removed. + - ldr for constants has been replaced with movw. + - ldreq has been replaced with moveq. + - The str epilogue has been made more idiomatic. + - SIMD registers are not pushed and popped at the beginning and end. + - The prologue and epilogue have been made idiomatic. + - A hole has been removed from the stack, saving 32 bytes. + - We write-back the base register whenever possible for vld1.8. + - Some multiplications have been reordered for better A7 performance. + +There are more opportunities for cleanup, since this code is from qhasm, +which doesn't always do the most opportune thing. But even prior to +extensive hand optimizations, this code delivers significant performance +improvements (given in get_cycles() per call): + + ----------- ------------- + | generic C | this commit | + ------------ ----------- ------------- + | Cortex-A7 | 49136 | 22395 | + ------------ ----------- ------------- + | Cortex-A17 | 17326 | 4983 | + ------------ ----------- ------------- + +Signed-off-by: Jason A. Donenfeld +[ardb: - move to arch/arm/crypto + - wire into lib/crypto framework + - implement crypto API KPP hooks ] +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/Kconfig | 6 + + arch/arm/crypto/Makefile | 2 + + arch/arm/crypto/curve25519-core.S | 347 +++++++++++++----------------- + arch/arm/crypto/curve25519-glue.c | 127 +++++++++++ + 4 files changed, 287 insertions(+), 195 deletions(-) + create mode 100644 arch/arm/crypto/curve25519-glue.c + +--- a/arch/arm/crypto/Kconfig ++++ b/arch/arm/crypto/Kconfig +@@ -141,4 +141,10 @@ config CRYPTO_NHPOLY1305_NEON + depends on KERNEL_MODE_NEON + select CRYPTO_NHPOLY1305 + ++config CRYPTO_CURVE25519_NEON ++ tristate "NEON accelerated Curve25519 scalar multiplication library" ++ depends on KERNEL_MODE_NEON ++ select CRYPTO_LIB_CURVE25519_GENERIC ++ select CRYPTO_ARCH_HAVE_LIB_CURVE25519 ++ + endif +--- a/arch/arm/crypto/Makefile ++++ b/arch/arm/crypto/Makefile +@@ -12,6 +12,7 @@ obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha51 + 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 + + ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o + ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o +@@ -58,6 +59,7 @@ chacha-neon-y := chacha-scalar-core.o ch + 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 + + ifdef REGENERATE_ARM_CRYPTO + quiet_cmd_perl = PERL $@ +--- a/arch/arm/crypto/curve25519-core.S ++++ b/arch/arm/crypto/curve25519-core.S +@@ -1,43 +1,35 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + /* +- * Public domain code from Daniel J. Bernstein and Peter Schwabe, from +- * SUPERCOP's curve25519/neon2/scalarmult.s. ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . 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. + */ + +-.fpu neon ++#include ++ + .text ++.fpu neon ++.arch armv7-a + .align 4 +-.global _crypto_scalarmult_curve25519_neon2 +-.global crypto_scalarmult_curve25519_neon2 +-.type _crypto_scalarmult_curve25519_neon2 STT_FUNC +-.type crypto_scalarmult_curve25519_neon2 STT_FUNC +- _crypto_scalarmult_curve25519_neon2: +- crypto_scalarmult_curve25519_neon2: +- vpush {q4, q5, q6, q7} +- mov r12, sp +- sub sp, sp, #736 +- and sp, sp, #0xffffffe0 +- strd r4, [sp, #0] +- strd r6, [sp, #8] +- strd r8, [sp, #16] +- strd r10, [sp, #24] +- str r12, [sp, #480] +- str r14, [sp, #484] +- mov r0, r0 +- mov r1, r1 +- mov r2, r2 +- add r3, sp, #32 +- ldr r4, =0 +- ldr r5, =254 ++ ++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, #512 +- vst1.8 {d2-d3}, [r6, : 128] +- add r6, sp, #528 +- vst1.8 {d0-d1}, [r6, : 128] +- add r6, sp, #544 ++ 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 +@@ -45,12 +37,12 @@ + vst1.8 {d4-d5}, [r6, : 128]! + vst1.8 d4, [r6, : 64] + add r6, r3, #0 +- ldr r7, =960 ++ movw r7, #960 + sub r7, r7, #2 + neg r7, r7 + sub r7, r7, r7, LSL #7 + str r7, [r6] +- add r6, sp, #704 ++ add r6, sp, #672 + vld1.8 {d4-d5}, [r1]! + vld1.8 {d6-d7}, [r1] + vst1.8 {d4-d5}, [r6, : 128]! +@@ -212,15 +204,15 @@ + vst1.8 {d0-d1}, [r6, : 128]! + vst1.8 {d2-d3}, [r6, : 128]! + vst1.8 d4, [r6, : 64] +-._mainloop: ++.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, #488] ++ str r5, [sp, #456] + eor r4, r4, r2 +- str r2, [sp, #492] ++ str r2, [sp, #460] + neg r2, r4 + add r4, r3, #96 + add r5, r3, #192 +@@ -291,7 +283,7 @@ + vsub.i32 q0, q1, q3 + vst1.8 d4, [r4, : 64] + vst1.8 d0, [r6, : 64] +- add r2, sp, #544 ++ add r2, sp, #512 + add r4, r3, #96 + add r5, r3, #144 + vld1.8 {d0-d1}, [r2, : 128] +@@ -361,14 +353,13 @@ + vmlal.s32 q0, d12, d8 + vmlal.s32 q0, d13, d17 + vmlal.s32 q0, d6, d6 +- add r2, sp, #512 +- vld1.8 {d18-d19}, [r2, : 128] ++ 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 +- add r2, sp, #528 + vld1.8 {d8-d9}, [r2, : 128] + vadd.i64 q5, q12, q9 + vadd.i64 q6, q15, q9 +@@ -502,22 +493,19 @@ + vadd.i32 q5, q5, q0 + vtrn.32 q11, q14 + vadd.i32 q6, q6, q3 +- add r2, sp, #560 ++ add r2, sp, #528 + vadd.i32 q10, q10, q2 + vtrn.32 d24, d25 +- vst1.8 {d12-d13}, [r2, : 128] ++ vst1.8 {d12-d13}, [r2, : 128]! + vshl.i32 q6, q13, #1 +- add r2, sp, #576 +- vst1.8 {d20-d21}, [r2, : 128] ++ vst1.8 {d20-d21}, [r2, : 128]! + vshl.i32 q10, q14, #1 +- add r2, sp, #592 +- vst1.8 {d12-d13}, [r2, : 128] ++ 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 +- add r2, sp, #608 +- vst1.8 {d16-d17}, [r2, : 128] ++ vst1.8 {d16-d17}, [r2, : 128]! + vmull.s32 q8, d18, d5 + vmlal.s32 q8, d26, d4 + vmlal.s32 q8, d19, d9 +@@ -528,8 +516,7 @@ + vmlal.s32 q8, d29, d1 + vmlal.s32 q8, d24, d6 + vmlal.s32 q8, d25, d0 +- add r2, sp, #624 +- vst1.8 {d14-d15}, [r2, : 128] ++ vst1.8 {d14-d15}, [r2, : 128]! + vmull.s32 q2, d18, d4 + vmlal.s32 q2, d12, d9 + vmlal.s32 q2, d13, d8 +@@ -537,8 +524,7 @@ + vmlal.s32 q2, d22, d2 + vmlal.s32 q2, d23, d1 + vmlal.s32 q2, d24, d0 +- add r2, sp, #640 +- vst1.8 {d20-d21}, [r2, : 128] ++ vst1.8 {d20-d21}, [r2, : 128]! + vmull.s32 q7, d18, d9 + vmlal.s32 q7, d26, d3 + vmlal.s32 q7, d19, d8 +@@ -547,14 +533,12 @@ + vmlal.s32 q7, d28, d1 + vmlal.s32 q7, d23, d6 + vmlal.s32 q7, d29, d0 +- add r2, sp, #656 +- vst1.8 {d10-d11}, [r2, : 128] ++ 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 +- add r2, sp, #672 + vst1.8 {d16-d17}, [r2, : 128] + vmull.s32 q4, d18, d8 + vmlal.s32 q4, d26, d2 +@@ -566,7 +550,7 @@ + vmlal.s32 q8, d26, d1 + vmlal.s32 q8, d19, d6 + vmlal.s32 q8, d27, d0 +- add r2, sp, #576 ++ add r2, sp, #544 + vld1.8 {d20-d21}, [r2, : 128] + vmlal.s32 q7, d24, d21 + vmlal.s32 q7, d25, d20 +@@ -575,32 +559,30 @@ + vmlal.s32 q8, d22, d21 + vmlal.s32 q8, d28, d20 + vmlal.s32 q5, d24, d20 +- add r2, sp, #576 + vst1.8 {d14-d15}, [r2, : 128] + vmull.s32 q7, d18, d6 + vmlal.s32 q7, d26, d0 +- add r2, sp, #656 ++ 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, #624 ++ 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, #608 ++ 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 +- add r2, sp, #608 + vst1.8 {d8-d9}, [r2, : 128] +- add r2, sp, #560 ++ add r2, sp, #528 + vld1.8 {d8-d9}, [r2, : 128] + vmlal.s32 q7, d24, d9 + vmlal.s32 q7, d25, d31 +@@ -621,36 +603,36 @@ + vmlal.s32 q0, d23, d26 + vmlal.s32 q0, d24, d31 + vmlal.s32 q0, d19, d20 +- add r2, sp, #640 ++ add r2, sp, #608 + vld1.8 {d18-d19}, [r2, : 128] + vmlal.s32 q2, d18, d7 +- vmlal.s32 q2, d19, d6 + vmlal.s32 q5, d18, d6 +- vmlal.s32 q5, d19, d21 + vmlal.s32 q1, d18, d21 +- vmlal.s32 q1, d19, d29 + vmlal.s32 q0, d18, d28 +- vmlal.s32 q0, d19, d9 + 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, #592 ++ add r2, sp, #560 + vld1.8 {d18-d19}, [r2, : 128] +- add r2, sp, #512 ++ 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, #528 ++ add r2, sp, #496 + vld1.8 {d6-d7}, [r2, : 128] + vmlal.s32 q6, d19, d21 +- add r2, sp, #576 ++ add r2, sp, #544 + vld1.8 {d18-d19}, [r2, : 128] + vmlal.s32 q0, d30, d8 +- add r2, sp, #672 ++ add r2, sp, #640 + vld1.8 {d20-d21}, [r2, : 128] + vmlal.s32 q5, d30, d29 +- add r2, sp, #608 ++ add r2, sp, #576 + vld1.8 {d24-d25}, [r2, : 128] + vmlal.s32 q1, d30, d28 + vadd.i64 q13, q0, q11 +@@ -823,22 +805,19 @@ + vadd.i32 q5, q5, q0 + vtrn.32 q11, q14 + vadd.i32 q6, q6, q3 +- add r2, sp, #560 ++ add r2, sp, #528 + vadd.i32 q10, q10, q2 + vtrn.32 d24, d25 +- vst1.8 {d12-d13}, [r2, : 128] ++ vst1.8 {d12-d13}, [r2, : 128]! + vshl.i32 q6, q13, #1 +- add r2, sp, #576 +- vst1.8 {d20-d21}, [r2, : 128] ++ vst1.8 {d20-d21}, [r2, : 128]! + vshl.i32 q10, q14, #1 +- add r2, sp, #592 +- vst1.8 {d12-d13}, [r2, : 128] ++ 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 +- add r2, sp, #608 +- vst1.8 {d16-d17}, [r2, : 128] ++ vst1.8 {d16-d17}, [r2, : 128]! + vmull.s32 q8, d18, d5 + vmlal.s32 q8, d26, d4 + vmlal.s32 q8, d19, d9 +@@ -849,8 +828,7 @@ + vmlal.s32 q8, d29, d1 + vmlal.s32 q8, d24, d6 + vmlal.s32 q8, d25, d0 +- add r2, sp, #624 +- vst1.8 {d14-d15}, [r2, : 128] ++ vst1.8 {d14-d15}, [r2, : 128]! + vmull.s32 q2, d18, d4 + vmlal.s32 q2, d12, d9 + vmlal.s32 q2, d13, d8 +@@ -858,8 +836,7 @@ + vmlal.s32 q2, d22, d2 + vmlal.s32 q2, d23, d1 + vmlal.s32 q2, d24, d0 +- add r2, sp, #640 +- vst1.8 {d20-d21}, [r2, : 128] ++ vst1.8 {d20-d21}, [r2, : 128]! + vmull.s32 q7, d18, d9 + vmlal.s32 q7, d26, d3 + vmlal.s32 q7, d19, d8 +@@ -868,15 +845,13 @@ + vmlal.s32 q7, d28, d1 + vmlal.s32 q7, d23, d6 + vmlal.s32 q7, d29, d0 +- add r2, sp, #656 +- vst1.8 {d10-d11}, [r2, : 128] ++ 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 +- add r2, sp, #672 +- vst1.8 {d16-d17}, [r2, : 128] ++ vst1.8 {d16-d17}, [r2, : 128]! + vmull.s32 q4, d18, d8 + vmlal.s32 q4, d26, d2 + vmlal.s32 q4, d19, d7 +@@ -887,7 +862,7 @@ + vmlal.s32 q8, d26, d1 + vmlal.s32 q8, d19, d6 + vmlal.s32 q8, d27, d0 +- add r2, sp, #576 ++ add r2, sp, #544 + vld1.8 {d20-d21}, [r2, : 128] + vmlal.s32 q7, d24, d21 + vmlal.s32 q7, d25, d20 +@@ -896,32 +871,30 @@ + vmlal.s32 q8, d22, d21 + vmlal.s32 q8, d28, d20 + vmlal.s32 q5, d24, d20 +- add r2, sp, #576 + vst1.8 {d14-d15}, [r2, : 128] + vmull.s32 q7, d18, d6 + vmlal.s32 q7, d26, d0 +- add r2, sp, #656 ++ 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, #624 ++ 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, #608 ++ 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 +- add r2, sp, #608 + vst1.8 {d8-d9}, [r2, : 128] +- add r2, sp, #560 ++ add r2, sp, #528 + vld1.8 {d8-d9}, [r2, : 128] + vmlal.s32 q7, d24, d9 + vmlal.s32 q7, d25, d31 +@@ -942,36 +915,36 @@ + vmlal.s32 q0, d23, d26 + vmlal.s32 q0, d24, d31 + vmlal.s32 q0, d19, d20 +- add r2, sp, #640 ++ add r2, sp, #608 + vld1.8 {d18-d19}, [r2, : 128] + vmlal.s32 q2, d18, d7 +- vmlal.s32 q2, d19, d6 + vmlal.s32 q5, d18, d6 +- vmlal.s32 q5, d19, d21 + vmlal.s32 q1, d18, d21 +- vmlal.s32 q1, d19, d29 + vmlal.s32 q0, d18, d28 +- vmlal.s32 q0, d19, d9 + 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, #592 ++ add r2, sp, #560 + vld1.8 {d18-d19}, [r2, : 128] +- add r2, sp, #512 ++ 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, #528 ++ add r2, sp, #496 + vld1.8 {d6-d7}, [r2, : 128] + vmlal.s32 q6, d19, d21 +- add r2, sp, #576 ++ add r2, sp, #544 + vld1.8 {d18-d19}, [r2, : 128] + vmlal.s32 q0, d30, d8 +- add r2, sp, #672 ++ add r2, sp, #640 + vld1.8 {d20-d21}, [r2, : 128] + vmlal.s32 q5, d30, d29 +- add r2, sp, #608 ++ add r2, sp, #576 + vld1.8 {d24-d25}, [r2, : 128] + vmlal.s32 q1, d30, d28 + vadd.i64 q13, q0, q11 +@@ -1069,7 +1042,7 @@ + sub r4, r4, #24 + vst1.8 d0, [r2, : 64] + vst1.8 d1, [r4, : 64] +- add r2, sp, #544 ++ add r2, sp, #512 + add r4, r3, #144 + add r5, r3, #192 + vld1.8 {d0-d1}, [r2, : 128] +@@ -1139,14 +1112,13 @@ + vmlal.s32 q0, d12, d8 + vmlal.s32 q0, d13, d17 + vmlal.s32 q0, d6, d6 +- add r2, sp, #512 +- vld1.8 {d18-d19}, [r2, : 128] ++ 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 +- add r2, sp, #528 + vld1.8 {d8-d9}, [r2, : 128] + vadd.i64 q5, q12, q9 + vadd.i64 q6, q15, q9 +@@ -1295,22 +1267,19 @@ + vadd.i32 q5, q5, q0 + vtrn.32 q11, q14 + vadd.i32 q6, q6, q3 +- add r2, sp, #560 ++ add r2, sp, #528 + vadd.i32 q10, q10, q2 + vtrn.32 d24, d25 +- vst1.8 {d12-d13}, [r2, : 128] ++ vst1.8 {d12-d13}, [r2, : 128]! + vshl.i32 q6, q13, #1 +- add r2, sp, #576 +- vst1.8 {d20-d21}, [r2, : 128] ++ vst1.8 {d20-d21}, [r2, : 128]! + vshl.i32 q10, q14, #1 +- add r2, sp, #592 +- vst1.8 {d12-d13}, [r2, : 128] ++ 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 +- add r2, sp, #608 +- vst1.8 {d16-d17}, [r2, : 128] ++ vst1.8 {d16-d17}, [r2, : 128]! + vmull.s32 q8, d18, d5 + vmlal.s32 q8, d26, d4 + vmlal.s32 q8, d19, d9 +@@ -1321,8 +1290,7 @@ + vmlal.s32 q8, d29, d1 + vmlal.s32 q8, d24, d6 + vmlal.s32 q8, d25, d0 +- add r2, sp, #624 +- vst1.8 {d14-d15}, [r2, : 128] ++ vst1.8 {d14-d15}, [r2, : 128]! + vmull.s32 q2, d18, d4 + vmlal.s32 q2, d12, d9 + vmlal.s32 q2, d13, d8 +@@ -1330,8 +1298,7 @@ + vmlal.s32 q2, d22, d2 + vmlal.s32 q2, d23, d1 + vmlal.s32 q2, d24, d0 +- add r2, sp, #640 +- vst1.8 {d20-d21}, [r2, : 128] ++ vst1.8 {d20-d21}, [r2, : 128]! + vmull.s32 q7, d18, d9 + vmlal.s32 q7, d26, d3 + vmlal.s32 q7, d19, d8 +@@ -1340,15 +1307,13 @@ + vmlal.s32 q7, d28, d1 + vmlal.s32 q7, d23, d6 + vmlal.s32 q7, d29, d0 +- add r2, sp, #656 +- vst1.8 {d10-d11}, [r2, : 128] ++ 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 +- add r2, sp, #672 +- vst1.8 {d16-d17}, [r2, : 128] ++ vst1.8 {d16-d17}, [r2, : 128]! + vmull.s32 q4, d18, d8 + vmlal.s32 q4, d26, d2 + vmlal.s32 q4, d19, d7 +@@ -1359,7 +1324,7 @@ + vmlal.s32 q8, d26, d1 + vmlal.s32 q8, d19, d6 + vmlal.s32 q8, d27, d0 +- add r2, sp, #576 ++ add r2, sp, #544 + vld1.8 {d20-d21}, [r2, : 128] + vmlal.s32 q7, d24, d21 + vmlal.s32 q7, d25, d20 +@@ -1368,32 +1333,30 @@ + vmlal.s32 q8, d22, d21 + vmlal.s32 q8, d28, d20 + vmlal.s32 q5, d24, d20 +- add r2, sp, #576 + vst1.8 {d14-d15}, [r2, : 128] + vmull.s32 q7, d18, d6 + vmlal.s32 q7, d26, d0 +- add r2, sp, #656 ++ 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, #624 ++ 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, #608 ++ 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 +- add r2, sp, #608 + vst1.8 {d8-d9}, [r2, : 128] +- add r2, sp, #560 ++ add r2, sp, #528 + vld1.8 {d8-d9}, [r2, : 128] + vmlal.s32 q7, d24, d9 + vmlal.s32 q7, d25, d31 +@@ -1414,36 +1377,36 @@ + vmlal.s32 q0, d23, d26 + vmlal.s32 q0, d24, d31 + vmlal.s32 q0, d19, d20 +- add r2, sp, #640 ++ add r2, sp, #608 + vld1.8 {d18-d19}, [r2, : 128] + vmlal.s32 q2, d18, d7 +- vmlal.s32 q2, d19, d6 + vmlal.s32 q5, d18, d6 +- vmlal.s32 q5, d19, d21 + vmlal.s32 q1, d18, d21 +- vmlal.s32 q1, d19, d29 + vmlal.s32 q0, d18, d28 +- vmlal.s32 q0, d19, d9 + 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, #592 ++ add r2, sp, #560 + vld1.8 {d18-d19}, [r2, : 128] +- add r2, sp, #512 ++ 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, #528 ++ add r2, sp, #496 + vld1.8 {d6-d7}, [r2, : 128] + vmlal.s32 q6, d19, d21 +- add r2, sp, #576 ++ add r2, sp, #544 + vld1.8 {d18-d19}, [r2, : 128] + vmlal.s32 q0, d30, d8 +- add r2, sp, #672 ++ add r2, sp, #640 + vld1.8 {d20-d21}, [r2, : 128] + vmlal.s32 q5, d30, d29 +- add r2, sp, #608 ++ add r2, sp, #576 + vld1.8 {d24-d25}, [r2, : 128] + vmlal.s32 q1, d30, d28 + vadd.i64 q13, q0, q11 +@@ -1541,10 +1504,10 @@ + sub r4, r4, #24 + vst1.8 d0, [r2, : 64] + vst1.8 d1, [r4, : 64] +- ldr r2, [sp, #488] +- ldr r4, [sp, #492] ++ ldr r2, [sp, #456] ++ ldr r4, [sp, #460] + subs r5, r2, #1 +- bge ._mainloop ++ bge .Lmainloop + add r1, r3, #144 + add r2, r3, #336 + vld1.8 {d0-d1}, [r1, : 128]! +@@ -1553,41 +1516,41 @@ + vst1.8 {d0-d1}, [r2, : 128]! + vst1.8 {d2-d3}, [r2, : 128]! + vst1.8 d4, [r2, : 64] +- ldr r1, =0 +-._invertloop: ++ movw r1, #0 ++.Linvertloop: + add r2, r3, #144 +- ldr r4, =0 +- ldr r5, =2 ++ movw r4, #0 ++ movw r5, #2 + cmp r1, #1 +- ldreq r5, =1 ++ moveq r5, #1 + addeq r2, r3, #336 + addeq r4, r3, #48 + cmp r1, #2 +- ldreq r5, =1 ++ moveq r5, #1 + addeq r2, r3, #48 + cmp r1, #3 +- ldreq r5, =5 ++ moveq r5, #5 + addeq r4, r3, #336 + cmp r1, #4 +- ldreq r5, =10 ++ moveq r5, #10 + cmp r1, #5 +- ldreq r5, =20 ++ moveq r5, #20 + cmp r1, #6 +- ldreq r5, =10 ++ moveq r5, #10 + addeq r2, r3, #336 + addeq r4, r3, #336 + cmp r1, #7 +- ldreq r5, =50 ++ moveq r5, #50 + cmp r1, #8 +- ldreq r5, =100 ++ moveq r5, #100 + cmp r1, #9 +- ldreq r5, =50 ++ moveq r5, #50 + addeq r2, r3, #336 + cmp r1, #10 +- ldreq r5, =5 ++ moveq r5, #5 + addeq r2, r3, #48 + cmp r1, #11 +- ldreq r5, =0 ++ moveq r5, #0 + addeq r2, r3, #96 + add r6, r3, #144 + add r7, r3, #288 +@@ -1598,8 +1561,8 @@ + vst1.8 {d2-d3}, [r7, : 128]! + vst1.8 d4, [r7, : 64] + cmp r5, #0 +- beq ._skipsquaringloop +-._squaringloop: ++ beq .Lskipsquaringloop ++.Lsquaringloop: + add r6, r3, #288 + add r7, r3, #288 + add r8, r3, #288 +@@ -1611,7 +1574,7 @@ + vld1.8 {d6-d7}, [r7, : 128]! + vld1.8 {d9}, [r7, : 64] + vld1.8 {d10-d11}, [r6, : 128]! +- add r7, sp, #416 ++ add r7, sp, #384 + vld1.8 {d12-d13}, [r6, : 128]! + vmul.i32 q7, q2, q0 + vld1.8 {d8}, [r6, : 64] +@@ -1726,7 +1689,7 @@ + vext.32 d10, d6, d6, #0 + vmov.i32 q1, #0xffffffff + vshl.i64 q4, q1, #25 +- add r7, sp, #512 ++ add r7, sp, #480 + vld1.8 {d14-d15}, [r7, : 128] + vadd.i64 q9, q2, q7 + vshl.i64 q1, q1, #26 +@@ -1735,7 +1698,7 @@ + vadd.i64 q5, q5, q10 + vand q9, q9, q1 + vld1.8 {d16}, [r6, : 64]! +- add r6, sp, #528 ++ add r6, sp, #496 + vld1.8 {d20-d21}, [r6, : 128] + vadd.i64 q11, q5, q10 + vsub.i64 q2, q2, q9 +@@ -1789,8 +1752,8 @@ + sub r6, r6, #32 + vst1.8 d4, [r6, : 64] + subs r5, r5, #1 +- bhi ._squaringloop +-._skipsquaringloop: ++ bhi .Lsquaringloop ++.Lskipsquaringloop: + mov r2, r2 + add r5, r3, #288 + add r6, r3, #144 +@@ -1802,7 +1765,7 @@ + vld1.8 {d6-d7}, [r5, : 128]! + vld1.8 {d9}, [r5, : 64] + vld1.8 {d10-d11}, [r2, : 128]! +- add r5, sp, #416 ++ add r5, sp, #384 + vld1.8 {d12-d13}, [r2, : 128]! + vmul.i32 q7, q2, q0 + vld1.8 {d8}, [r2, : 64] +@@ -1917,7 +1880,7 @@ + vext.32 d10, d6, d6, #0 + vmov.i32 q1, #0xffffffff + vshl.i64 q4, q1, #25 +- add r5, sp, #512 ++ add r5, sp, #480 + vld1.8 {d14-d15}, [r5, : 128] + vadd.i64 q9, q2, q7 + vshl.i64 q1, q1, #26 +@@ -1926,7 +1889,7 @@ + vadd.i64 q5, q5, q10 + vand q9, q9, q1 + vld1.8 {d16}, [r2, : 64]! +- add r2, sp, #528 ++ add r2, sp, #496 + vld1.8 {d20-d21}, [r2, : 128] + vadd.i64 q11, q5, q10 + vsub.i64 q2, q2, q9 +@@ -1980,7 +1943,7 @@ + sub r2, r2, #32 + vst1.8 d4, [r2, : 64] + cmp r4, #0 +- beq ._skippostcopy ++ beq .Lskippostcopy + add r2, r3, #144 + mov r4, r4 + vld1.8 {d0-d1}, [r2, : 128]! +@@ -1989,9 +1952,9 @@ + vst1.8 {d0-d1}, [r4, : 128]! + vst1.8 {d2-d3}, [r4, : 128]! + vst1.8 d4, [r4, : 64] +-._skippostcopy: ++.Lskippostcopy: + cmp r1, #1 +- bne ._skipfinalcopy ++ bne .Lskipfinalcopy + add r2, r3, #288 + add r4, r3, #144 + vld1.8 {d0-d1}, [r2, : 128]! +@@ -2000,10 +1963,10 @@ + vst1.8 {d0-d1}, [r4, : 128]! + vst1.8 {d2-d3}, [r4, : 128]! + vst1.8 d4, [r4, : 64] +-._skipfinalcopy: ++.Lskipfinalcopy: + add r1, r1, #1 + cmp r1, #12 +- blo ._invertloop ++ blo .Linvertloop + add r1, r3, #144 + ldr r2, [r1], #4 + ldr r3, [r1], #4 +@@ -2085,21 +2048,15 @@ + add r8, r8, r10, LSL #12 + mov r9, r10, LSR #20 + add r1, r9, r1, LSL #6 +- str r2, [r0], #4 +- str r3, [r0], #4 +- str r4, [r0], #4 +- str r5, [r0], #4 +- str r6, [r0], #4 +- str r7, [r0], #4 +- str r8, [r0], #4 +- str r1, [r0] +- ldrd r4, [sp, #0] +- ldrd r6, [sp, #8] +- ldrd r8, [sp, #16] +- ldrd r10, [sp, #24] +- ldr r12, [sp, #480] +- ldr r14, [sp, #484] +- ldr r0, =0 +- mov sp, r12 +- vpop {q4, q5, q6, q7} +- bx lr ++ 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) +--- /dev/null ++++ b/arch/arm/crypto/curve25519-glue.c +@@ -0,0 +1,127 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . 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 ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++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); ++ ++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 mod_init(void) ++{ ++ if (elf_hwcap & HWCAP_NEON) { ++ static_branch_enable(&have_neon); ++ return crypto_register_kpp(&curve25519_alg); ++ } ++ return 0; ++} ++ ++static void __exit mod_exit(void) ++{ ++ if (elf_hwcap & HWCAP_NEON) ++ crypto_unregister_kpp(&curve25519_alg); ++} ++ ++module_init(mod_init); ++module_exit(mod_exit); ++ ++MODULE_ALIAS_CRYPTO("curve25519"); ++MODULE_ALIAS_CRYPTO("curve25519-neon"); ++MODULE_LICENSE("GPL v2"); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0032-crypto-chacha20poly1305-import-construction-and-self.patch b/target/linux/generic/backport-5.4/080-wireguard-0032-crypto-chacha20poly1305-import-construction-and-self.patch new file mode 100644 index 0000000000..dde774a68d --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0032-crypto-chacha20poly1305-import-construction-and-self.patch @@ -0,0 +1,7677 @@ +From d276ee98ad5275f3e1efb4f8a9f2e3fbece23a5a Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:39 +0100 +Subject: [PATCH 032/124] crypto: chacha20poly1305 - import construction and + selftest from Zinc + +commit ed20078b7e3331e82828be357147af6a3282e4ce upstream. + +This incorporates the chacha20poly1305 from the Zinc library, retaining +the library interface, but replacing the implementation with calls into +the code that already existed in the kernel's crypto API. + +Note that this library API does not implement RFC7539 fully, given that +it is limited to 64-bit nonces. (The 96-bit nonce version that was part +of the selftest only has been removed, along with the 96-bit nonce test +vectors that only tested the selftest but not the actual library itself) + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + include/crypto/chacha20poly1305.h | 37 + + lib/crypto/Kconfig | 7 + + lib/crypto/Makefile | 4 + + lib/crypto/chacha20poly1305-selftest.c | 7348 ++++++++++++++++++++++++ + lib/crypto/chacha20poly1305.c | 219 + + 5 files changed, 7615 insertions(+) + create mode 100644 include/crypto/chacha20poly1305.h + create mode 100644 lib/crypto/chacha20poly1305-selftest.c + create mode 100644 lib/crypto/chacha20poly1305.c + +--- /dev/null ++++ b/include/crypto/chacha20poly1305.h +@@ -0,0 +1,37 @@ ++/* SPDX-License-Identifier: GPL-2.0 OR MIT */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef __CHACHA20POLY1305_H ++#define __CHACHA20POLY1305_H ++ ++#include ++ ++enum chacha20poly1305_lengths { ++ XCHACHA20POLY1305_NONCE_SIZE = 24, ++ CHACHA20POLY1305_KEY_SIZE = 32, ++ CHACHA20POLY1305_AUTHTAG_SIZE = 16 ++}; ++ ++void chacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]); ++ ++bool __must_check ++chacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]); ++ ++void xchacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE], ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]); ++ ++bool __must_check xchacha20poly1305_decrypt( ++ u8 *dst, const u8 *src, const size_t src_len, const u8 *ad, ++ const size_t ad_len, const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE], ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]); ++ ++#endif /* __CHACHA20POLY1305_H */ +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -119,5 +119,12 @@ config CRYPTO_LIB_POLY1305 + by either the generic implementation or an arch-specific one, if one + is available and enabled. + ++config CRYPTO_LIB_CHACHA20POLY1305 ++ tristate "ChaCha20-Poly1305 AEAD support (8-byte nonce library version)" ++ depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA ++ depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305 ++ select CRYPTO_LIB_CHACHA ++ select CRYPTO_LIB_POLY1305 ++ + config CRYPTO_LIB_SHA256 + tristate +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -16,6 +16,9 @@ libblake2s-generic-y += blake2s-gener + obj-$(CONFIG_CRYPTO_LIB_BLAKE2S) += libblake2s.o + libblake2s-y += blake2s.o + ++obj-$(CONFIG_CRYPTO_LIB_CHACHA20POLY1305) += libchacha20poly1305.o ++libchacha20poly1305-y += chacha20poly1305.o ++ + obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC) += libcurve25519.o + libcurve25519-y := curve25519-fiat32.o + libcurve25519-$(CONFIG_ARCH_SUPPORTS_INT128) := curve25519-hacl64.o +@@ -32,4 +35,5 @@ libsha256-y := sha256.o + + ifneq ($(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS),y) + libblake2s-y += blake2s-selftest.o ++libchacha20poly1305-y += chacha20poly1305-selftest.o + endif +--- /dev/null ++++ b/lib/crypto/chacha20poly1305-selftest.c +@@ -0,0 +1,7348 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include ++#include ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++struct chacha20poly1305_testvec { ++ const u8 *input, *output, *assoc, *nonce, *key; ++ size_t ilen, alen, nlen; ++ bool failure; ++}; ++ ++/* The first of these are the ChaCha20-Poly1305 AEAD test vectors from RFC7539 ++ * 2.8.2. After they are generated by reference implementations. And the final ++ * marked ones are taken from wycheproof, but we only do these for the encrypt ++ * side, because mostly we're stressing the primitives rather than the actual ++ * chapoly construction. ++ */ ++ ++static const u8 enc_input001[] __initconst = { ++ 0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74, ++ 0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20, ++ 0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66, ++ 0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69, ++ 0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20, ++ 0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20, ++ 0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d, ++ 0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e, ++ 0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65, ++ 0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64, ++ 0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63, ++ 0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f, ++ 0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64, ++ 0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65, ++ 0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61, ++ 0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e, ++ 0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69, ++ 0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72, ++ 0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20, ++ 0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65, ++ 0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61, ++ 0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72, ++ 0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65, ++ 0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61, ++ 0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20, ++ 0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65, ++ 0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20, ++ 0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20, ++ 0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b, ++ 0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67, ++ 0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80, ++ 0x9d ++}; ++static const u8 enc_output001[] __initconst = { ++ 0x64, 0xa0, 0x86, 0x15, 0x75, 0x86, 0x1a, 0xf4, ++ 0x60, 0xf0, 0x62, 0xc7, 0x9b, 0xe6, 0x43, 0xbd, ++ 0x5e, 0x80, 0x5c, 0xfd, 0x34, 0x5c, 0xf3, 0x89, ++ 0xf1, 0x08, 0x67, 0x0a, 0xc7, 0x6c, 0x8c, 0xb2, ++ 0x4c, 0x6c, 0xfc, 0x18, 0x75, 0x5d, 0x43, 0xee, ++ 0xa0, 0x9e, 0xe9, 0x4e, 0x38, 0x2d, 0x26, 0xb0, ++ 0xbd, 0xb7, 0xb7, 0x3c, 0x32, 0x1b, 0x01, 0x00, ++ 0xd4, 0xf0, 0x3b, 0x7f, 0x35, 0x58, 0x94, 0xcf, ++ 0x33, 0x2f, 0x83, 0x0e, 0x71, 0x0b, 0x97, 0xce, ++ 0x98, 0xc8, 0xa8, 0x4a, 0xbd, 0x0b, 0x94, 0x81, ++ 0x14, 0xad, 0x17, 0x6e, 0x00, 0x8d, 0x33, 0xbd, ++ 0x60, 0xf9, 0x82, 0xb1, 0xff, 0x37, 0xc8, 0x55, ++ 0x97, 0x97, 0xa0, 0x6e, 0xf4, 0xf0, 0xef, 0x61, ++ 0xc1, 0x86, 0x32, 0x4e, 0x2b, 0x35, 0x06, 0x38, ++ 0x36, 0x06, 0x90, 0x7b, 0x6a, 0x7c, 0x02, 0xb0, ++ 0xf9, 0xf6, 0x15, 0x7b, 0x53, 0xc8, 0x67, 0xe4, ++ 0xb9, 0x16, 0x6c, 0x76, 0x7b, 0x80, 0x4d, 0x46, ++ 0xa5, 0x9b, 0x52, 0x16, 0xcd, 0xe7, 0xa4, 0xe9, ++ 0x90, 0x40, 0xc5, 0xa4, 0x04, 0x33, 0x22, 0x5e, ++ 0xe2, 0x82, 0xa1, 0xb0, 0xa0, 0x6c, 0x52, 0x3e, ++ 0xaf, 0x45, 0x34, 0xd7, 0xf8, 0x3f, 0xa1, 0x15, ++ 0x5b, 0x00, 0x47, 0x71, 0x8c, 0xbc, 0x54, 0x6a, ++ 0x0d, 0x07, 0x2b, 0x04, 0xb3, 0x56, 0x4e, 0xea, ++ 0x1b, 0x42, 0x22, 0x73, 0xf5, 0x48, 0x27, 0x1a, ++ 0x0b, 0xb2, 0x31, 0x60, 0x53, 0xfa, 0x76, 0x99, ++ 0x19, 0x55, 0xeb, 0xd6, 0x31, 0x59, 0x43, 0x4e, ++ 0xce, 0xbb, 0x4e, 0x46, 0x6d, 0xae, 0x5a, 0x10, ++ 0x73, 0xa6, 0x72, 0x76, 0x27, 0x09, 0x7a, 0x10, ++ 0x49, 0xe6, 0x17, 0xd9, 0x1d, 0x36, 0x10, 0x94, ++ 0xfa, 0x68, 0xf0, 0xff, 0x77, 0x98, 0x71, 0x30, ++ 0x30, 0x5b, 0xea, 0xba, 0x2e, 0xda, 0x04, 0xdf, ++ 0x99, 0x7b, 0x71, 0x4d, 0x6c, 0x6f, 0x2c, 0x29, ++ 0xa6, 0xad, 0x5c, 0xb4, 0x02, 0x2b, 0x02, 0x70, ++ 0x9b, 0xee, 0xad, 0x9d, 0x67, 0x89, 0x0c, 0xbb, ++ 0x22, 0x39, 0x23, 0x36, 0xfe, 0xa1, 0x85, 0x1f, ++ 0x38 ++}; ++static const u8 enc_assoc001[] __initconst = { ++ 0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x4e, 0x91 ++}; ++static const u8 enc_nonce001[] __initconst = { ++ 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08 ++}; ++static const u8 enc_key001[] __initconst = { ++ 0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a, ++ 0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0, ++ 0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09, ++ 0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0 ++}; ++ ++static const u8 enc_input002[] __initconst = { }; ++static const u8 enc_output002[] __initconst = { ++ 0xea, 0xe0, 0x1e, 0x9e, 0x2c, 0x91, 0xaa, 0xe1, ++ 0xdb, 0x5d, 0x99, 0x3f, 0x8a, 0xf7, 0x69, 0x92 ++}; ++static const u8 enc_assoc002[] __initconst = { }; ++static const u8 enc_nonce002[] __initconst = { ++ 0xca, 0xbf, 0x33, 0x71, 0x32, 0x45, 0x77, 0x8e ++}; ++static const u8 enc_key002[] __initconst = { ++ 0x4c, 0xf5, 0x96, 0x83, 0x38, 0xe6, 0xae, 0x7f, ++ 0x2d, 0x29, 0x25, 0x76, 0xd5, 0x75, 0x27, 0x86, ++ 0x91, 0x9a, 0x27, 0x7a, 0xfb, 0x46, 0xc5, 0xef, ++ 0x94, 0x81, 0x79, 0x57, 0x14, 0x59, 0x40, 0x68 ++}; ++ ++static const u8 enc_input003[] __initconst = { }; ++static const u8 enc_output003[] __initconst = { ++ 0xdd, 0x6b, 0x3b, 0x82, 0xce, 0x5a, 0xbd, 0xd6, ++ 0xa9, 0x35, 0x83, 0xd8, 0x8c, 0x3d, 0x85, 0x77 ++}; ++static const u8 enc_assoc003[] __initconst = { ++ 0x33, 0x10, 0x41, 0x12, 0x1f, 0xf3, 0xd2, 0x6b ++}; ++static const u8 enc_nonce003[] __initconst = { ++ 0x3d, 0x86, 0xb5, 0x6b, 0xc8, 0xa3, 0x1f, 0x1d ++}; ++static const u8 enc_key003[] __initconst = { ++ 0x2d, 0xb0, 0x5d, 0x40, 0xc8, 0xed, 0x44, 0x88, ++ 0x34, 0xd1, 0x13, 0xaf, 0x57, 0xa1, 0xeb, 0x3a, ++ 0x2a, 0x80, 0x51, 0x36, 0xec, 0x5b, 0xbc, 0x08, ++ 0x93, 0x84, 0x21, 0xb5, 0x13, 0x88, 0x3c, 0x0d ++}; ++ ++static const u8 enc_input004[] __initconst = { ++ 0xa4 ++}; ++static const u8 enc_output004[] __initconst = { ++ 0xb7, 0x1b, 0xb0, 0x73, 0x59, 0xb0, 0x84, 0xb2, ++ 0x6d, 0x8e, 0xab, 0x94, 0x31, 0xa1, 0xae, 0xac, ++ 0x89 ++}; ++static const u8 enc_assoc004[] __initconst = { ++ 0x6a, 0xe2, 0xad, 0x3f, 0x88, 0x39, 0x5a, 0x40 ++}; ++static const u8 enc_nonce004[] __initconst = { ++ 0xd2, 0x32, 0x1f, 0x29, 0x28, 0xc6, 0xc4, 0xc4 ++}; ++static const u8 enc_key004[] __initconst = { ++ 0x4b, 0x28, 0x4b, 0xa3, 0x7b, 0xbe, 0xe9, 0xf8, ++ 0x31, 0x80, 0x82, 0xd7, 0xd8, 0xe8, 0xb5, 0xa1, ++ 0xe2, 0x18, 0x18, 0x8a, 0x9c, 0xfa, 0xa3, 0x3d, ++ 0x25, 0x71, 0x3e, 0x40, 0xbc, 0x54, 0x7a, 0x3e ++}; ++ ++static const u8 enc_input005[] __initconst = { ++ 0x2d ++}; ++static const u8 enc_output005[] __initconst = { ++ 0xbf, 0xe1, 0x5b, 0x0b, 0xdb, 0x6b, 0xf5, 0x5e, ++ 0x6c, 0x5d, 0x84, 0x44, 0x39, 0x81, 0xc1, 0x9c, ++ 0xac ++}; ++static const u8 enc_assoc005[] __initconst = { }; ++static const u8 enc_nonce005[] __initconst = { ++ 0x20, 0x1c, 0xaa, 0x5f, 0x9c, 0xbf, 0x92, 0x30 ++}; ++static const u8 enc_key005[] __initconst = { ++ 0x66, 0xca, 0x9c, 0x23, 0x2a, 0x4b, 0x4b, 0x31, ++ 0x0e, 0x92, 0x89, 0x8b, 0xf4, 0x93, 0xc7, 0x87, ++ 0x98, 0xa3, 0xd8, 0x39, 0xf8, 0xf4, 0xa7, 0x01, ++ 0xc0, 0x2e, 0x0a, 0xa6, 0x7e, 0x5a, 0x78, 0x87 ++}; ++ ++static const u8 enc_input006[] __initconst = { ++ 0x33, 0x2f, 0x94, 0xc1, 0xa4, 0xef, 0xcc, 0x2a, ++ 0x5b, 0xa6, 0xe5, 0x8f, 0x1d, 0x40, 0xf0, 0x92, ++ 0x3c, 0xd9, 0x24, 0x11, 0xa9, 0x71, 0xf9, 0x37, ++ 0x14, 0x99, 0xfa, 0xbe, 0xe6, 0x80, 0xde, 0x50, ++ 0xc9, 0x96, 0xd4, 0xb0, 0xec, 0x9e, 0x17, 0xec, ++ 0xd2, 0x5e, 0x72, 0x99, 0xfc, 0x0a, 0xe1, 0xcb, ++ 0x48, 0xd2, 0x85, 0xdd, 0x2f, 0x90, 0xe0, 0x66, ++ 0x3b, 0xe6, 0x20, 0x74, 0xbe, 0x23, 0x8f, 0xcb, ++ 0xb4, 0xe4, 0xda, 0x48, 0x40, 0xa6, 0xd1, 0x1b, ++ 0xc7, 0x42, 0xce, 0x2f, 0x0c, 0xa6, 0x85, 0x6e, ++ 0x87, 0x37, 0x03, 0xb1, 0x7c, 0x25, 0x96, 0xa3, ++ 0x05, 0xd8, 0xb0, 0xf4, 0xed, 0xea, 0xc2, 0xf0, ++ 0x31, 0x98, 0x6c, 0xd1, 0x14, 0x25, 0xc0, 0xcb, ++ 0x01, 0x74, 0xd0, 0x82, 0xf4, 0x36, 0xf5, 0x41, ++ 0xd5, 0xdc, 0xca, 0xc5, 0xbb, 0x98, 0xfe, 0xfc, ++ 0x69, 0x21, 0x70, 0xd8, 0xa4, 0x4b, 0xc8, 0xde, ++ 0x8f ++}; ++static const u8 enc_output006[] __initconst = { ++ 0x8b, 0x06, 0xd3, 0x31, 0xb0, 0x93, 0x45, 0xb1, ++ 0x75, 0x6e, 0x26, 0xf9, 0x67, 0xbc, 0x90, 0x15, ++ 0x81, 0x2c, 0xb5, 0xf0, 0xc6, 0x2b, 0xc7, 0x8c, ++ 0x56, 0xd1, 0xbf, 0x69, 0x6c, 0x07, 0xa0, 0xda, ++ 0x65, 0x27, 0xc9, 0x90, 0x3d, 0xef, 0x4b, 0x11, ++ 0x0f, 0x19, 0x07, 0xfd, 0x29, 0x92, 0xd9, 0xc8, ++ 0xf7, 0x99, 0x2e, 0x4a, 0xd0, 0xb8, 0x2c, 0xdc, ++ 0x93, 0xf5, 0x9e, 0x33, 0x78, 0xd1, 0x37, 0xc3, ++ 0x66, 0xd7, 0x5e, 0xbc, 0x44, 0xbf, 0x53, 0xa5, ++ 0xbc, 0xc4, 0xcb, 0x7b, 0x3a, 0x8e, 0x7f, 0x02, ++ 0xbd, 0xbb, 0xe7, 0xca, 0xa6, 0x6c, 0x6b, 0x93, ++ 0x21, 0x93, 0x10, 0x61, 0xe7, 0x69, 0xd0, 0x78, ++ 0xf3, 0x07, 0x5a, 0x1a, 0x8f, 0x73, 0xaa, 0xb1, ++ 0x4e, 0xd3, 0xda, 0x4f, 0xf3, 0x32, 0xe1, 0x66, ++ 0x3e, 0x6c, 0xc6, 0x13, 0xba, 0x06, 0x5b, 0xfc, ++ 0x6a, 0xe5, 0x6f, 0x60, 0xfb, 0x07, 0x40, 0xb0, ++ 0x8c, 0x9d, 0x84, 0x43, 0x6b, 0xc1, 0xf7, 0x8d, ++ 0x8d, 0x31, 0xf7, 0x7a, 0x39, 0x4d, 0x8f, 0x9a, ++ 0xeb ++}; ++static const u8 enc_assoc006[] __initconst = { ++ 0x70, 0xd3, 0x33, 0xf3, 0x8b, 0x18, 0x0b ++}; ++static const u8 enc_nonce006[] __initconst = { ++ 0xdf, 0x51, 0x84, 0x82, 0x42, 0x0c, 0x75, 0x9c ++}; ++static const u8 enc_key006[] __initconst = { ++ 0x68, 0x7b, 0x8d, 0x8e, 0xe3, 0xc4, 0xdd, 0xae, ++ 0xdf, 0x72, 0x7f, 0x53, 0x72, 0x25, 0x1e, 0x78, ++ 0x91, 0xcb, 0x69, 0x76, 0x1f, 0x49, 0x93, 0xf9, ++ 0x6f, 0x21, 0xcc, 0x39, 0x9c, 0xad, 0xb1, 0x01 ++}; ++ ++static const u8 enc_input007[] __initconst = { ++ 0x9b, 0x18, 0xdb, 0xdd, 0x9a, 0x0f, 0x3e, 0xa5, ++ 0x15, 0x17, 0xde, 0xdf, 0x08, 0x9d, 0x65, 0x0a, ++ 0x67, 0x30, 0x12, 0xe2, 0x34, 0x77, 0x4b, 0xc1, ++ 0xd9, 0xc6, 0x1f, 0xab, 0xc6, 0x18, 0x50, 0x17, ++ 0xa7, 0x9d, 0x3c, 0xa6, 0xc5, 0x35, 0x8c, 0x1c, ++ 0xc0, 0xa1, 0x7c, 0x9f, 0x03, 0x89, 0xca, 0xe1, ++ 0xe6, 0xe9, 0xd4, 0xd3, 0x88, 0xdb, 0xb4, 0x51, ++ 0x9d, 0xec, 0xb4, 0xfc, 0x52, 0xee, 0x6d, 0xf1, ++ 0x75, 0x42, 0xc6, 0xfd, 0xbd, 0x7a, 0x8e, 0x86, ++ 0xfc, 0x44, 0xb3, 0x4f, 0xf3, 0xea, 0x67, 0x5a, ++ 0x41, 0x13, 0xba, 0xb0, 0xdc, 0xe1, 0xd3, 0x2a, ++ 0x7c, 0x22, 0xb3, 0xca, 0xac, 0x6a, 0x37, 0x98, ++ 0x3e, 0x1d, 0x40, 0x97, 0xf7, 0x9b, 0x1d, 0x36, ++ 0x6b, 0xb3, 0x28, 0xbd, 0x60, 0x82, 0x47, 0x34, ++ 0xaa, 0x2f, 0x7d, 0xe9, 0xa8, 0x70, 0x81, 0x57, ++ 0xd4, 0xb9, 0x77, 0x0a, 0x9d, 0x29, 0xa7, 0x84, ++ 0x52, 0x4f, 0xc2, 0x4a, 0x40, 0x3b, 0x3c, 0xd4, ++ 0xc9, 0x2a, 0xdb, 0x4a, 0x53, 0xc4, 0xbe, 0x80, ++ 0xe9, 0x51, 0x7f, 0x8f, 0xc7, 0xa2, 0xce, 0x82, ++ 0x5c, 0x91, 0x1e, 0x74, 0xd9, 0xd0, 0xbd, 0xd5, ++ 0xf3, 0xfd, 0xda, 0x4d, 0x25, 0xb4, 0xbb, 0x2d, ++ 0xac, 0x2f, 0x3d, 0x71, 0x85, 0x7b, 0xcf, 0x3c, ++ 0x7b, 0x3e, 0x0e, 0x22, 0x78, 0x0c, 0x29, 0xbf, ++ 0xe4, 0xf4, 0x57, 0xb3, 0xcb, 0x49, 0xa0, 0xfc, ++ 0x1e, 0x05, 0x4e, 0x16, 0xbc, 0xd5, 0xa8, 0xa3, ++ 0xee, 0x05, 0x35, 0xc6, 0x7c, 0xab, 0x60, 0x14, ++ 0x55, 0x1a, 0x8e, 0xc5, 0x88, 0x5d, 0xd5, 0x81, ++ 0xc2, 0x81, 0xa5, 0xc4, 0x60, 0xdb, 0xaf, 0x77, ++ 0x91, 0xe1, 0xce, 0xa2, 0x7e, 0x7f, 0x42, 0xe3, ++ 0xb0, 0x13, 0x1c, 0x1f, 0x25, 0x60, 0x21, 0xe2, ++ 0x40, 0x5f, 0x99, 0xb7, 0x73, 0xec, 0x9b, 0x2b, ++ 0xf0, 0x65, 0x11, 0xc8, 0xd0, 0x0a, 0x9f, 0xd3 ++}; ++static const u8 enc_output007[] __initconst = { ++ 0x85, 0x04, 0xc2, 0xed, 0x8d, 0xfd, 0x97, 0x5c, ++ 0xd2, 0xb7, 0xe2, 0xc1, 0x6b, 0xa3, 0xba, 0xf8, ++ 0xc9, 0x50, 0xc3, 0xc6, 0xa5, 0xe3, 0xa4, 0x7c, ++ 0xc3, 0x23, 0x49, 0x5e, 0xa9, 0xb9, 0x32, 0xeb, ++ 0x8a, 0x7c, 0xca, 0xe5, 0xec, 0xfb, 0x7c, 0xc0, ++ 0xcb, 0x7d, 0xdc, 0x2c, 0x9d, 0x92, 0x55, 0x21, ++ 0x0a, 0xc8, 0x43, 0x63, 0x59, 0x0a, 0x31, 0x70, ++ 0x82, 0x67, 0x41, 0x03, 0xf8, 0xdf, 0xf2, 0xac, ++ 0xa7, 0x02, 0xd4, 0xd5, 0x8a, 0x2d, 0xc8, 0x99, ++ 0x19, 0x66, 0xd0, 0xf6, 0x88, 0x2c, 0x77, 0xd9, ++ 0xd4, 0x0d, 0x6c, 0xbd, 0x98, 0xde, 0xe7, 0x7f, ++ 0xad, 0x7e, 0x8a, 0xfb, 0xe9, 0x4b, 0xe5, 0xf7, ++ 0xe5, 0x50, 0xa0, 0x90, 0x3f, 0xd6, 0x22, 0x53, ++ 0xe3, 0xfe, 0x1b, 0xcc, 0x79, 0x3b, 0xec, 0x12, ++ 0x47, 0x52, 0xa7, 0xd6, 0x04, 0xe3, 0x52, 0xe6, ++ 0x93, 0x90, 0x91, 0x32, 0x73, 0x79, 0xb8, 0xd0, ++ 0x31, 0xde, 0x1f, 0x9f, 0x2f, 0x05, 0x38, 0x54, ++ 0x2f, 0x35, 0x04, 0x39, 0xe0, 0xa7, 0xba, 0xc6, ++ 0x52, 0xf6, 0x37, 0x65, 0x4c, 0x07, 0xa9, 0x7e, ++ 0xb3, 0x21, 0x6f, 0x74, 0x8c, 0xc9, 0xde, 0xdb, ++ 0x65, 0x1b, 0x9b, 0xaa, 0x60, 0xb1, 0x03, 0x30, ++ 0x6b, 0xb2, 0x03, 0xc4, 0x1c, 0x04, 0xf8, 0x0f, ++ 0x64, 0xaf, 0x46, 0xe4, 0x65, 0x99, 0x49, 0xe2, ++ 0xea, 0xce, 0x78, 0x00, 0xd8, 0x8b, 0xd5, 0x2e, ++ 0xcf, 0xfc, 0x40, 0x49, 0xe8, 0x58, 0xdc, 0x34, ++ 0x9c, 0x8c, 0x61, 0xbf, 0x0a, 0x8e, 0xec, 0x39, ++ 0xa9, 0x30, 0x05, 0x5a, 0xd2, 0x56, 0x01, 0xc7, ++ 0xda, 0x8f, 0x4e, 0xbb, 0x43, 0xa3, 0x3a, 0xf9, ++ 0x15, 0x2a, 0xd0, 0xa0, 0x7a, 0x87, 0x34, 0x82, ++ 0xfe, 0x8a, 0xd1, 0x2d, 0x5e, 0xc7, 0xbf, 0x04, ++ 0x53, 0x5f, 0x3b, 0x36, 0xd4, 0x25, 0x5c, 0x34, ++ 0x7a, 0x8d, 0xd5, 0x05, 0xce, 0x72, 0xca, 0xef, ++ 0x7a, 0x4b, 0xbc, 0xb0, 0x10, 0x5c, 0x96, 0x42, ++ 0x3a, 0x00, 0x98, 0xcd, 0x15, 0xe8, 0xb7, 0x53 ++}; ++static const u8 enc_assoc007[] __initconst = { }; ++static const u8 enc_nonce007[] __initconst = { ++ 0xde, 0x7b, 0xef, 0xc3, 0x65, 0x1b, 0x68, 0xb0 ++}; ++static const u8 enc_key007[] __initconst = { ++ 0x8d, 0xb8, 0x91, 0x48, 0xf0, 0xe7, 0x0a, 0xbd, ++ 0xf9, 0x3f, 0xcd, 0xd9, 0xa0, 0x1e, 0x42, 0x4c, ++ 0xe7, 0xde, 0x25, 0x3d, 0xa3, 0xd7, 0x05, 0x80, ++ 0x8d, 0xf2, 0x82, 0xac, 0x44, 0x16, 0x51, 0x01 ++}; ++ ++static const u8 enc_input008[] __initconst = { ++ 0xc3, 0x09, 0x94, 0x62, 0xe6, 0x46, 0x2e, 0x10, ++ 0xbe, 0x00, 0xe4, 0xfc, 0xf3, 0x40, 0xa3, 0xe2, ++ 0x0f, 0xc2, 0x8b, 0x28, 0xdc, 0xba, 0xb4, 0x3c, ++ 0xe4, 0x21, 0x58, 0x61, 0xcd, 0x8b, 0xcd, 0xfb, ++ 0xac, 0x94, 0xa1, 0x45, 0xf5, 0x1c, 0xe1, 0x12, ++ 0xe0, 0x3b, 0x67, 0x21, 0x54, 0x5e, 0x8c, 0xaa, ++ 0xcf, 0xdb, 0xb4, 0x51, 0xd4, 0x13, 0xda, 0xe6, ++ 0x83, 0x89, 0xb6, 0x92, 0xe9, 0x21, 0x76, 0xa4, ++ 0x93, 0x7d, 0x0e, 0xfd, 0x96, 0x36, 0x03, 0x91, ++ 0x43, 0x5c, 0x92, 0x49, 0x62, 0x61, 0x7b, 0xeb, ++ 0x43, 0x89, 0xb8, 0x12, 0x20, 0x43, 0xd4, 0x47, ++ 0x06, 0x84, 0xee, 0x47, 0xe9, 0x8a, 0x73, 0x15, ++ 0x0f, 0x72, 0xcf, 0xed, 0xce, 0x96, 0xb2, 0x7f, ++ 0x21, 0x45, 0x76, 0xeb, 0x26, 0x28, 0x83, 0x6a, ++ 0xad, 0xaa, 0xa6, 0x81, 0xd8, 0x55, 0xb1, 0xa3, ++ 0x85, 0xb3, 0x0c, 0xdf, 0xf1, 0x69, 0x2d, 0x97, ++ 0x05, 0x2a, 0xbc, 0x7c, 0x7b, 0x25, 0xf8, 0x80, ++ 0x9d, 0x39, 0x25, 0xf3, 0x62, 0xf0, 0x66, 0x5e, ++ 0xf4, 0xa0, 0xcf, 0xd8, 0xfd, 0x4f, 0xb1, 0x1f, ++ 0x60, 0x3a, 0x08, 0x47, 0xaf, 0xe1, 0xf6, 0x10, ++ 0x77, 0x09, 0xa7, 0x27, 0x8f, 0x9a, 0x97, 0x5a, ++ 0x26, 0xfa, 0xfe, 0x41, 0x32, 0x83, 0x10, 0xe0, ++ 0x1d, 0xbf, 0x64, 0x0d, 0xf4, 0x1c, 0x32, 0x35, ++ 0xe5, 0x1b, 0x36, 0xef, 0xd4, 0x4a, 0x93, 0x4d, ++ 0x00, 0x7c, 0xec, 0x02, 0x07, 0x8b, 0x5d, 0x7d, ++ 0x1b, 0x0e, 0xd1, 0xa6, 0xa5, 0x5d, 0x7d, 0x57, ++ 0x88, 0xa8, 0xcc, 0x81, 0xb4, 0x86, 0x4e, 0xb4, ++ 0x40, 0xe9, 0x1d, 0xc3, 0xb1, 0x24, 0x3e, 0x7f, ++ 0xcc, 0x8a, 0x24, 0x9b, 0xdf, 0x6d, 0xf0, 0x39, ++ 0x69, 0x3e, 0x4c, 0xc0, 0x96, 0xe4, 0x13, 0xda, ++ 0x90, 0xda, 0xf4, 0x95, 0x66, 0x8b, 0x17, 0x17, ++ 0xfe, 0x39, 0x43, 0x25, 0xaa, 0xda, 0xa0, 0x43, ++ 0x3c, 0xb1, 0x41, 0x02, 0xa3, 0xf0, 0xa7, 0x19, ++ 0x59, 0xbc, 0x1d, 0x7d, 0x6c, 0x6d, 0x91, 0x09, ++ 0x5c, 0xb7, 0x5b, 0x01, 0xd1, 0x6f, 0x17, 0x21, ++ 0x97, 0xbf, 0x89, 0x71, 0xa5, 0xb0, 0x6e, 0x07, ++ 0x45, 0xfd, 0x9d, 0xea, 0x07, 0xf6, 0x7a, 0x9f, ++ 0x10, 0x18, 0x22, 0x30, 0x73, 0xac, 0xd4, 0x6b, ++ 0x72, 0x44, 0xed, 0xd9, 0x19, 0x9b, 0x2d, 0x4a, ++ 0x41, 0xdd, 0xd1, 0x85, 0x5e, 0x37, 0x19, 0xed, ++ 0xd2, 0x15, 0x8f, 0x5e, 0x91, 0xdb, 0x33, 0xf2, ++ 0xe4, 0xdb, 0xff, 0x98, 0xfb, 0xa3, 0xb5, 0xca, ++ 0x21, 0x69, 0x08, 0xe7, 0x8a, 0xdf, 0x90, 0xff, ++ 0x3e, 0xe9, 0x20, 0x86, 0x3c, 0xe9, 0xfc, 0x0b, ++ 0xfe, 0x5c, 0x61, 0xaa, 0x13, 0x92, 0x7f, 0x7b, ++ 0xec, 0xe0, 0x6d, 0xa8, 0x23, 0x22, 0xf6, 0x6b, ++ 0x77, 0xc4, 0xfe, 0x40, 0x07, 0x3b, 0xb6, 0xf6, ++ 0x8e, 0x5f, 0xd4, 0xb9, 0xb7, 0x0f, 0x21, 0x04, ++ 0xef, 0x83, 0x63, 0x91, 0x69, 0x40, 0xa3, 0x48, ++ 0x5c, 0xd2, 0x60, 0xf9, 0x4f, 0x6c, 0x47, 0x8b, ++ 0x3b, 0xb1, 0x9f, 0x8e, 0xee, 0x16, 0x8a, 0x13, ++ 0xfc, 0x46, 0x17, 0xc3, 0xc3, 0x32, 0x56, 0xf8, ++ 0x3c, 0x85, 0x3a, 0xb6, 0x3e, 0xaa, 0x89, 0x4f, ++ 0xb3, 0xdf, 0x38, 0xfd, 0xf1, 0xe4, 0x3a, 0xc0, ++ 0xe6, 0x58, 0xb5, 0x8f, 0xc5, 0x29, 0xa2, 0x92, ++ 0x4a, 0xb6, 0xa0, 0x34, 0x7f, 0xab, 0xb5, 0x8a, ++ 0x90, 0xa1, 0xdb, 0x4d, 0xca, 0xb6, 0x2c, 0x41, ++ 0x3c, 0xf7, 0x2b, 0x21, 0xc3, 0xfd, 0xf4, 0x17, ++ 0x5c, 0xb5, 0x33, 0x17, 0x68, 0x2b, 0x08, 0x30, ++ 0xf3, 0xf7, 0x30, 0x3c, 0x96, 0xe6, 0x6a, 0x20, ++ 0x97, 0xe7, 0x4d, 0x10, 0x5f, 0x47, 0x5f, 0x49, ++ 0x96, 0x09, 0xf0, 0x27, 0x91, 0xc8, 0xf8, 0x5a, ++ 0x2e, 0x79, 0xb5, 0xe2, 0xb8, 0xe8, 0xb9, 0x7b, ++ 0xd5, 0x10, 0xcb, 0xff, 0x5d, 0x14, 0x73, 0xf3 ++}; ++static const u8 enc_output008[] __initconst = { ++ 0x14, 0xf6, 0x41, 0x37, 0xa6, 0xd4, 0x27, 0xcd, ++ 0xdb, 0x06, 0x3e, 0x9a, 0x4e, 0xab, 0xd5, 0xb1, ++ 0x1e, 0x6b, 0xd2, 0xbc, 0x11, 0xf4, 0x28, 0x93, ++ 0x63, 0x54, 0xef, 0xbb, 0x5e, 0x1d, 0x3a, 0x1d, ++ 0x37, 0x3c, 0x0a, 0x6c, 0x1e, 0xc2, 0xd1, 0x2c, ++ 0xb5, 0xa3, 0xb5, 0x7b, 0xb8, 0x8f, 0x25, 0xa6, ++ 0x1b, 0x61, 0x1c, 0xec, 0x28, 0x58, 0x26, 0xa4, ++ 0xa8, 0x33, 0x28, 0x25, 0x5c, 0x45, 0x05, 0xe5, ++ 0x6c, 0x99, 0xe5, 0x45, 0xc4, 0xa2, 0x03, 0x84, ++ 0x03, 0x73, 0x1e, 0x8c, 0x49, 0xac, 0x20, 0xdd, ++ 0x8d, 0xb3, 0xc4, 0xf5, 0xe7, 0x4f, 0xf1, 0xed, ++ 0xa1, 0x98, 0xde, 0xa4, 0x96, 0xdd, 0x2f, 0xab, ++ 0xab, 0x97, 0xcf, 0x3e, 0xd2, 0x9e, 0xb8, 0x13, ++ 0x07, 0x28, 0x29, 0x19, 0xaf, 0xfd, 0xf2, 0x49, ++ 0x43, 0xea, 0x49, 0x26, 0x91, 0xc1, 0x07, 0xd6, ++ 0xbb, 0x81, 0x75, 0x35, 0x0d, 0x24, 0x7f, 0xc8, ++ 0xda, 0xd4, 0xb7, 0xeb, 0xe8, 0x5c, 0x09, 0xa2, ++ 0x2f, 0xdc, 0x28, 0x7d, 0x3a, 0x03, 0xfa, 0x94, ++ 0xb5, 0x1d, 0x17, 0x99, 0x36, 0xc3, 0x1c, 0x18, ++ 0x34, 0xe3, 0x9f, 0xf5, 0x55, 0x7c, 0xb0, 0x60, ++ 0x9d, 0xff, 0xac, 0xd4, 0x61, 0xf2, 0xad, 0xf8, ++ 0xce, 0xc7, 0xbe, 0x5c, 0xd2, 0x95, 0xa8, 0x4b, ++ 0x77, 0x13, 0x19, 0x59, 0x26, 0xc9, 0xb7, 0x8f, ++ 0x6a, 0xcb, 0x2d, 0x37, 0x91, 0xea, 0x92, 0x9c, ++ 0x94, 0x5b, 0xda, 0x0b, 0xce, 0xfe, 0x30, 0x20, ++ 0xf8, 0x51, 0xad, 0xf2, 0xbe, 0xe7, 0xc7, 0xff, ++ 0xb3, 0x33, 0x91, 0x6a, 0xc9, 0x1a, 0x41, 0xc9, ++ 0x0f, 0xf3, 0x10, 0x0e, 0xfd, 0x53, 0xff, 0x6c, ++ 0x16, 0x52, 0xd9, 0xf3, 0xf7, 0x98, 0x2e, 0xc9, ++ 0x07, 0x31, 0x2c, 0x0c, 0x72, 0xd7, 0xc5, 0xc6, ++ 0x08, 0x2a, 0x7b, 0xda, 0xbd, 0x7e, 0x02, 0xea, ++ 0x1a, 0xbb, 0xf2, 0x04, 0x27, 0x61, 0x28, 0x8e, ++ 0xf5, 0x04, 0x03, 0x1f, 0x4c, 0x07, 0x55, 0x82, ++ 0xec, 0x1e, 0xd7, 0x8b, 0x2f, 0x65, 0x56, 0xd1, ++ 0xd9, 0x1e, 0x3c, 0xe9, 0x1f, 0x5e, 0x98, 0x70, ++ 0x38, 0x4a, 0x8c, 0x49, 0xc5, 0x43, 0xa0, 0xa1, ++ 0x8b, 0x74, 0x9d, 0x4c, 0x62, 0x0d, 0x10, 0x0c, ++ 0xf4, 0x6c, 0x8f, 0xe0, 0xaa, 0x9a, 0x8d, 0xb7, ++ 0xe0, 0xbe, 0x4c, 0x87, 0xf1, 0x98, 0x2f, 0xcc, ++ 0xed, 0xc0, 0x52, 0x29, 0xdc, 0x83, 0xf8, 0xfc, ++ 0x2c, 0x0e, 0xa8, 0x51, 0x4d, 0x80, 0x0d, 0xa3, ++ 0xfe, 0xd8, 0x37, 0xe7, 0x41, 0x24, 0xfc, 0xfb, ++ 0x75, 0xe3, 0x71, 0x7b, 0x57, 0x45, 0xf5, 0x97, ++ 0x73, 0x65, 0x63, 0x14, 0x74, 0xb8, 0x82, 0x9f, ++ 0xf8, 0x60, 0x2f, 0x8a, 0xf2, 0x4e, 0xf1, 0x39, ++ 0xda, 0x33, 0x91, 0xf8, 0x36, 0xe0, 0x8d, 0x3f, ++ 0x1f, 0x3b, 0x56, 0xdc, 0xa0, 0x8f, 0x3c, 0x9d, ++ 0x71, 0x52, 0xa7, 0xb8, 0xc0, 0xa5, 0xc6, 0xa2, ++ 0x73, 0xda, 0xf4, 0x4b, 0x74, 0x5b, 0x00, 0x3d, ++ 0x99, 0xd7, 0x96, 0xba, 0xe6, 0xe1, 0xa6, 0x96, ++ 0x38, 0xad, 0xb3, 0xc0, 0xd2, 0xba, 0x91, 0x6b, ++ 0xf9, 0x19, 0xdd, 0x3b, 0xbe, 0xbe, 0x9c, 0x20, ++ 0x50, 0xba, 0xa1, 0xd0, 0xce, 0x11, 0xbd, 0x95, ++ 0xd8, 0xd1, 0xdd, 0x33, 0x85, 0x74, 0xdc, 0xdb, ++ 0x66, 0x76, 0x44, 0xdc, 0x03, 0x74, 0x48, 0x35, ++ 0x98, 0xb1, 0x18, 0x47, 0x94, 0x7d, 0xff, 0x62, ++ 0xe4, 0x58, 0x78, 0xab, 0xed, 0x95, 0x36, 0xd9, ++ 0x84, 0x91, 0x82, 0x64, 0x41, 0xbb, 0x58, 0xe6, ++ 0x1c, 0x20, 0x6d, 0x15, 0x6b, 0x13, 0x96, 0xe8, ++ 0x35, 0x7f, 0xdc, 0x40, 0x2c, 0xe9, 0xbc, 0x8a, ++ 0x4f, 0x92, 0xec, 0x06, 0x2d, 0x50, 0xdf, 0x93, ++ 0x5d, 0x65, 0x5a, 0xa8, 0xfc, 0x20, 0x50, 0x14, ++ 0xa9, 0x8a, 0x7e, 0x1d, 0x08, 0x1f, 0xe2, 0x99, ++ 0xd0, 0xbe, 0xfb, 0x3a, 0x21, 0x9d, 0xad, 0x86, ++ 0x54, 0xfd, 0x0d, 0x98, 0x1c, 0x5a, 0x6f, 0x1f, ++ 0x9a, 0x40, 0xcd, 0xa2, 0xff, 0x6a, 0xf1, 0x54 ++}; ++static const u8 enc_assoc008[] __initconst = { }; ++static const u8 enc_nonce008[] __initconst = { ++ 0x0e, 0x0d, 0x57, 0xbb, 0x7b, 0x40, 0x54, 0x02 ++}; ++static const u8 enc_key008[] __initconst = { ++ 0xf2, 0xaa, 0x4f, 0x99, 0xfd, 0x3e, 0xa8, 0x53, ++ 0xc1, 0x44, 0xe9, 0x81, 0x18, 0xdc, 0xf5, 0xf0, ++ 0x3e, 0x44, 0x15, 0x59, 0xe0, 0xc5, 0x44, 0x86, ++ 0xc3, 0x91, 0xa8, 0x75, 0xc0, 0x12, 0x46, 0xba ++}; ++ ++static const u8 enc_input009[] __initconst = { ++ 0xe6, 0xc3, 0xdb, 0x63, 0x55, 0x15, 0xe3, 0x5b, ++ 0xb7, 0x4b, 0x27, 0x8b, 0x5a, 0xdd, 0xc2, 0xe8, ++ 0x3a, 0x6b, 0xd7, 0x81, 0x96, 0x35, 0x97, 0xca, ++ 0xd7, 0x68, 0xe8, 0xef, 0xce, 0xab, 0xda, 0x09, ++ 0x6e, 0xd6, 0x8e, 0xcb, 0x55, 0xb5, 0xe1, 0xe5, ++ 0x57, 0xfd, 0xc4, 0xe3, 0xe0, 0x18, 0x4f, 0x85, ++ 0xf5, 0x3f, 0x7e, 0x4b, 0x88, 0xc9, 0x52, 0x44, ++ 0x0f, 0xea, 0xaf, 0x1f, 0x71, 0x48, 0x9f, 0x97, ++ 0x6d, 0xb9, 0x6f, 0x00, 0xa6, 0xde, 0x2b, 0x77, ++ 0x8b, 0x15, 0xad, 0x10, 0xa0, 0x2b, 0x7b, 0x41, ++ 0x90, 0x03, 0x2d, 0x69, 0xae, 0xcc, 0x77, 0x7c, ++ 0xa5, 0x9d, 0x29, 0x22, 0xc2, 0xea, 0xb4, 0x00, ++ 0x1a, 0xd2, 0x7a, 0x98, 0x8a, 0xf9, 0xf7, 0x82, ++ 0xb0, 0xab, 0xd8, 0xa6, 0x94, 0x8d, 0x58, 0x2f, ++ 0x01, 0x9e, 0x00, 0x20, 0xfc, 0x49, 0xdc, 0x0e, ++ 0x03, 0xe8, 0x45, 0x10, 0xd6, 0xa8, 0xda, 0x55, ++ 0x10, 0x9a, 0xdf, 0x67, 0x22, 0x8b, 0x43, 0xab, ++ 0x00, 0xbb, 0x02, 0xc8, 0xdd, 0x7b, 0x97, 0x17, ++ 0xd7, 0x1d, 0x9e, 0x02, 0x5e, 0x48, 0xde, 0x8e, ++ 0xcf, 0x99, 0x07, 0x95, 0x92, 0x3c, 0x5f, 0x9f, ++ 0xc5, 0x8a, 0xc0, 0x23, 0xaa, 0xd5, 0x8c, 0x82, ++ 0x6e, 0x16, 0x92, 0xb1, 0x12, 0x17, 0x07, 0xc3, ++ 0xfb, 0x36, 0xf5, 0x6c, 0x35, 0xd6, 0x06, 0x1f, ++ 0x9f, 0xa7, 0x94, 0xa2, 0x38, 0x63, 0x9c, 0xb0, ++ 0x71, 0xb3, 0xa5, 0xd2, 0xd8, 0xba, 0x9f, 0x08, ++ 0x01, 0xb3, 0xff, 0x04, 0x97, 0x73, 0x45, 0x1b, ++ 0xd5, 0xa9, 0x9c, 0x80, 0xaf, 0x04, 0x9a, 0x85, ++ 0xdb, 0x32, 0x5b, 0x5d, 0x1a, 0xc1, 0x36, 0x28, ++ 0x10, 0x79, 0xf1, 0x3c, 0xbf, 0x1a, 0x41, 0x5c, ++ 0x4e, 0xdf, 0xb2, 0x7c, 0x79, 0x3b, 0x7a, 0x62, ++ 0x3d, 0x4b, 0xc9, 0x9b, 0x2a, 0x2e, 0x7c, 0xa2, ++ 0xb1, 0x11, 0x98, 0xa7, 0x34, 0x1a, 0x00, 0xf3, ++ 0xd1, 0xbc, 0x18, 0x22, 0xba, 0x02, 0x56, 0x62, ++ 0x31, 0x10, 0x11, 0x6d, 0xe0, 0x54, 0x9d, 0x40, ++ 0x1f, 0x26, 0x80, 0x41, 0xca, 0x3f, 0x68, 0x0f, ++ 0x32, 0x1d, 0x0a, 0x8e, 0x79, 0xd8, 0xa4, 0x1b, ++ 0x29, 0x1c, 0x90, 0x8e, 0xc5, 0xe3, 0xb4, 0x91, ++ 0x37, 0x9a, 0x97, 0x86, 0x99, 0xd5, 0x09, 0xc5, ++ 0xbb, 0xa3, 0x3f, 0x21, 0x29, 0x82, 0x14, 0x5c, ++ 0xab, 0x25, 0xfb, 0xf2, 0x4f, 0x58, 0x26, 0xd4, ++ 0x83, 0xaa, 0x66, 0x89, 0x67, 0x7e, 0xc0, 0x49, ++ 0xe1, 0x11, 0x10, 0x7f, 0x7a, 0xda, 0x29, 0x04, ++ 0xff, 0xf0, 0xcb, 0x09, 0x7c, 0x9d, 0xfa, 0x03, ++ 0x6f, 0x81, 0x09, 0x31, 0x60, 0xfb, 0x08, 0xfa, ++ 0x74, 0xd3, 0x64, 0x44, 0x7c, 0x55, 0x85, 0xec, ++ 0x9c, 0x6e, 0x25, 0xb7, 0x6c, 0xc5, 0x37, 0xb6, ++ 0x83, 0x87, 0x72, 0x95, 0x8b, 0x9d, 0xe1, 0x69, ++ 0x5c, 0x31, 0x95, 0x42, 0xa6, 0x2c, 0xd1, 0x36, ++ 0x47, 0x1f, 0xec, 0x54, 0xab, 0xa2, 0x1c, 0xd8, ++ 0x00, 0xcc, 0xbc, 0x0d, 0x65, 0xe2, 0x67, 0xbf, ++ 0xbc, 0xea, 0xee, 0x9e, 0xe4, 0x36, 0x95, 0xbe, ++ 0x73, 0xd9, 0xa6, 0xd9, 0x0f, 0xa0, 0xcc, 0x82, ++ 0x76, 0x26, 0xad, 0x5b, 0x58, 0x6c, 0x4e, 0xab, ++ 0x29, 0x64, 0xd3, 0xd9, 0xa9, 0x08, 0x8c, 0x1d, ++ 0xa1, 0x4f, 0x80, 0xd8, 0x3f, 0x94, 0xfb, 0xd3, ++ 0x7b, 0xfc, 0xd1, 0x2b, 0xc3, 0x21, 0xeb, 0xe5, ++ 0x1c, 0x84, 0x23, 0x7f, 0x4b, 0xfa, 0xdb, 0x34, ++ 0x18, 0xa2, 0xc2, 0xe5, 0x13, 0xfe, 0x6c, 0x49, ++ 0x81, 0xd2, 0x73, 0xe7, 0xe2, 0xd7, 0xe4, 0x4f, ++ 0x4b, 0x08, 0x6e, 0xb1, 0x12, 0x22, 0x10, 0x9d, ++ 0xac, 0x51, 0x1e, 0x17, 0xd9, 0x8a, 0x0b, 0x42, ++ 0x88, 0x16, 0x81, 0x37, 0x7c, 0x6a, 0xf7, 0xef, ++ 0x2d, 0xe3, 0xd9, 0xf8, 0x5f, 0xe0, 0x53, 0x27, ++ 0x74, 0xb9, 0xe2, 0xd6, 0x1c, 0x80, 0x2c, 0x52, ++ 0x65 ++}; ++static const u8 enc_output009[] __initconst = { ++ 0xfd, 0x81, 0x8d, 0xd0, 0x3d, 0xb4, 0xd5, 0xdf, ++ 0xd3, 0x42, 0x47, 0x5a, 0x6d, 0x19, 0x27, 0x66, ++ 0x4b, 0x2e, 0x0c, 0x27, 0x9c, 0x96, 0x4c, 0x72, ++ 0x02, 0xa3, 0x65, 0xc3, 0xb3, 0x6f, 0x2e, 0xbd, ++ 0x63, 0x8a, 0x4a, 0x5d, 0x29, 0xa2, 0xd0, 0x28, ++ 0x48, 0xc5, 0x3d, 0x98, 0xa3, 0xbc, 0xe0, 0xbe, ++ 0x3b, 0x3f, 0xe6, 0x8a, 0xa4, 0x7f, 0x53, 0x06, ++ 0xfa, 0x7f, 0x27, 0x76, 0x72, 0x31, 0xa1, 0xf5, ++ 0xd6, 0x0c, 0x52, 0x47, 0xba, 0xcd, 0x4f, 0xd7, ++ 0xeb, 0x05, 0x48, 0x0d, 0x7c, 0x35, 0x4a, 0x09, ++ 0xc9, 0x76, 0x71, 0x02, 0xa3, 0xfb, 0xb7, 0x1a, ++ 0x65, 0xb7, 0xed, 0x98, 0xc6, 0x30, 0x8a, 0x00, ++ 0xae, 0xa1, 0x31, 0xe5, 0xb5, 0x9e, 0x6d, 0x62, ++ 0xda, 0xda, 0x07, 0x0f, 0x38, 0x38, 0xd3, 0xcb, ++ 0xc1, 0xb0, 0xad, 0xec, 0x72, 0xec, 0xb1, 0xa2, ++ 0x7b, 0x59, 0xf3, 0x3d, 0x2b, 0xef, 0xcd, 0x28, ++ 0x5b, 0x83, 0xcc, 0x18, 0x91, 0x88, 0xb0, 0x2e, ++ 0xf9, 0x29, 0x31, 0x18, 0xf9, 0x4e, 0xe9, 0x0a, ++ 0x91, 0x92, 0x9f, 0xae, 0x2d, 0xad, 0xf4, 0xe6, ++ 0x1a, 0xe2, 0xa4, 0xee, 0x47, 0x15, 0xbf, 0x83, ++ 0x6e, 0xd7, 0x72, 0x12, 0x3b, 0x2d, 0x24, 0xe9, ++ 0xb2, 0x55, 0xcb, 0x3c, 0x10, 0xf0, 0x24, 0x8a, ++ 0x4a, 0x02, 0xea, 0x90, 0x25, 0xf0, 0xb4, 0x79, ++ 0x3a, 0xef, 0x6e, 0xf5, 0x52, 0xdf, 0xb0, 0x0a, ++ 0xcd, 0x24, 0x1c, 0xd3, 0x2e, 0x22, 0x74, 0xea, ++ 0x21, 0x6f, 0xe9, 0xbd, 0xc8, 0x3e, 0x36, 0x5b, ++ 0x19, 0xf1, 0xca, 0x99, 0x0a, 0xb4, 0xa7, 0x52, ++ 0x1a, 0x4e, 0xf2, 0xad, 0x8d, 0x56, 0x85, 0xbb, ++ 0x64, 0x89, 0xba, 0x26, 0xf9, 0xc7, 0xe1, 0x89, ++ 0x19, 0x22, 0x77, 0xc3, 0xa8, 0xfc, 0xff, 0xad, ++ 0xfe, 0xb9, 0x48, 0xae, 0x12, 0x30, 0x9f, 0x19, ++ 0xfb, 0x1b, 0xef, 0x14, 0x87, 0x8a, 0x78, 0x71, ++ 0xf3, 0xf4, 0xb7, 0x00, 0x9c, 0x1d, 0xb5, 0x3d, ++ 0x49, 0x00, 0x0c, 0x06, 0xd4, 0x50, 0xf9, 0x54, ++ 0x45, 0xb2, 0x5b, 0x43, 0xdb, 0x6d, 0xcf, 0x1a, ++ 0xe9, 0x7a, 0x7a, 0xcf, 0xfc, 0x8a, 0x4e, 0x4d, ++ 0x0b, 0x07, 0x63, 0x28, 0xd8, 0xe7, 0x08, 0x95, ++ 0xdf, 0xa6, 0x72, 0x93, 0x2e, 0xbb, 0xa0, 0x42, ++ 0x89, 0x16, 0xf1, 0xd9, 0x0c, 0xf9, 0xa1, 0x16, ++ 0xfd, 0xd9, 0x03, 0xb4, 0x3b, 0x8a, 0xf5, 0xf6, ++ 0xe7, 0x6b, 0x2e, 0x8e, 0x4c, 0x3d, 0xe2, 0xaf, ++ 0x08, 0x45, 0x03, 0xff, 0x09, 0xb6, 0xeb, 0x2d, ++ 0xc6, 0x1b, 0x88, 0x94, 0xac, 0x3e, 0xf1, 0x9f, ++ 0x0e, 0x0e, 0x2b, 0xd5, 0x00, 0x4d, 0x3f, 0x3b, ++ 0x53, 0xae, 0xaf, 0x1c, 0x33, 0x5f, 0x55, 0x6e, ++ 0x8d, 0xaf, 0x05, 0x7a, 0x10, 0x34, 0xc9, 0xf4, ++ 0x66, 0xcb, 0x62, 0x12, 0xa6, 0xee, 0xe8, 0x1c, ++ 0x5d, 0x12, 0x86, 0xdb, 0x6f, 0x1c, 0x33, 0xc4, ++ 0x1c, 0xda, 0x82, 0x2d, 0x3b, 0x59, 0xfe, 0xb1, ++ 0xa4, 0x59, 0x41, 0x86, 0xd0, 0xef, 0xae, 0xfb, ++ 0xda, 0x6d, 0x11, 0xb8, 0xca, 0xe9, 0x6e, 0xff, ++ 0xf7, 0xa9, 0xd9, 0x70, 0x30, 0xfc, 0x53, 0xe2, ++ 0xd7, 0xa2, 0x4e, 0xc7, 0x91, 0xd9, 0x07, 0x06, ++ 0xaa, 0xdd, 0xb0, 0x59, 0x28, 0x1d, 0x00, 0x66, ++ 0xc5, 0x54, 0xc2, 0xfc, 0x06, 0xda, 0x05, 0x90, ++ 0x52, 0x1d, 0x37, 0x66, 0xee, 0xf0, 0xb2, 0x55, ++ 0x8a, 0x5d, 0xd2, 0x38, 0x86, 0x94, 0x9b, 0xfc, ++ 0x10, 0x4c, 0xa1, 0xb9, 0x64, 0x3e, 0x44, 0xb8, ++ 0x5f, 0xb0, 0x0c, 0xec, 0xe0, 0xc9, 0xe5, 0x62, ++ 0x75, 0x3f, 0x09, 0xd5, 0xf5, 0xd9, 0x26, 0xba, ++ 0x9e, 0xd2, 0xf4, 0xb9, 0x48, 0x0a, 0xbc, 0xa2, ++ 0xd6, 0x7c, 0x36, 0x11, 0x7d, 0x26, 0x81, 0x89, ++ 0xcf, 0xa4, 0xad, 0x73, 0x0e, 0xee, 0xcc, 0x06, ++ 0xa9, 0xdb, 0xb1, 0xfd, 0xfb, 0x09, 0x7f, 0x90, ++ 0x42, 0x37, 0x2f, 0xe1, 0x9c, 0x0f, 0x6f, 0xcf, ++ 0x43, 0xb5, 0xd9, 0x90, 0xe1, 0x85, 0xf5, 0xa8, ++ 0xae ++}; ++static const u8 enc_assoc009[] __initconst = { ++ 0x5a, 0x27, 0xff, 0xeb, 0xdf, 0x84, 0xb2, 0x9e, ++ 0xef ++}; ++static const u8 enc_nonce009[] __initconst = { ++ 0xef, 0x2d, 0x63, 0xee, 0x6b, 0x80, 0x8b, 0x78 ++}; ++static const u8 enc_key009[] __initconst = { ++ 0xea, 0xbc, 0x56, 0x99, 0xe3, 0x50, 0xff, 0xc5, ++ 0xcc, 0x1a, 0xd7, 0xc1, 0x57, 0x72, 0xea, 0x86, ++ 0x5b, 0x89, 0x88, 0x61, 0x3d, 0x2f, 0x9b, 0xb2, ++ 0xe7, 0x9c, 0xec, 0x74, 0x6e, 0x3e, 0xf4, 0x3b ++}; ++ ++static const u8 enc_input010[] __initconst = { ++ 0x42, 0x93, 0xe4, 0xeb, 0x97, 0xb0, 0x57, 0xbf, ++ 0x1a, 0x8b, 0x1f, 0xe4, 0x5f, 0x36, 0x20, 0x3c, ++ 0xef, 0x0a, 0xa9, 0x48, 0x5f, 0x5f, 0x37, 0x22, ++ 0x3a, 0xde, 0xe3, 0xae, 0xbe, 0xad, 0x07, 0xcc, ++ 0xb1, 0xf6, 0xf5, 0xf9, 0x56, 0xdd, 0xe7, 0x16, ++ 0x1e, 0x7f, 0xdf, 0x7a, 0x9e, 0x75, 0xb7, 0xc7, ++ 0xbe, 0xbe, 0x8a, 0x36, 0x04, 0xc0, 0x10, 0xf4, ++ 0x95, 0x20, 0x03, 0xec, 0xdc, 0x05, 0xa1, 0x7d, ++ 0xc4, 0xa9, 0x2c, 0x82, 0xd0, 0xbc, 0x8b, 0xc5, ++ 0xc7, 0x45, 0x50, 0xf6, 0xa2, 0x1a, 0xb5, 0x46, ++ 0x3b, 0x73, 0x02, 0xa6, 0x83, 0x4b, 0x73, 0x82, ++ 0x58, 0x5e, 0x3b, 0x65, 0x2f, 0x0e, 0xfd, 0x2b, ++ 0x59, 0x16, 0xce, 0xa1, 0x60, 0x9c, 0xe8, 0x3a, ++ 0x99, 0xed, 0x8d, 0x5a, 0xcf, 0xf6, 0x83, 0xaf, ++ 0xba, 0xd7, 0x73, 0x73, 0x40, 0x97, 0x3d, 0xca, ++ 0xef, 0x07, 0x57, 0xe6, 0xd9, 0x70, 0x0e, 0x95, ++ 0xae, 0xa6, 0x8d, 0x04, 0xcc, 0xee, 0xf7, 0x09, ++ 0x31, 0x77, 0x12, 0xa3, 0x23, 0x97, 0x62, 0xb3, ++ 0x7b, 0x32, 0xfb, 0x80, 0x14, 0x48, 0x81, 0xc3, ++ 0xe5, 0xea, 0x91, 0x39, 0x52, 0x81, 0xa2, 0x4f, ++ 0xe4, 0xb3, 0x09, 0xff, 0xde, 0x5e, 0xe9, 0x58, ++ 0x84, 0x6e, 0xf9, 0x3d, 0xdf, 0x25, 0xea, 0xad, ++ 0xae, 0xe6, 0x9a, 0xd1, 0x89, 0x55, 0xd3, 0xde, ++ 0x6c, 0x52, 0xdb, 0x70, 0xfe, 0x37, 0xce, 0x44, ++ 0x0a, 0xa8, 0x25, 0x5f, 0x92, 0xc1, 0x33, 0x4a, ++ 0x4f, 0x9b, 0x62, 0x35, 0xff, 0xce, 0xc0, 0xa9, ++ 0x60, 0xce, 0x52, 0x00, 0x97, 0x51, 0x35, 0x26, ++ 0x2e, 0xb9, 0x36, 0xa9, 0x87, 0x6e, 0x1e, 0xcc, ++ 0x91, 0x78, 0x53, 0x98, 0x86, 0x5b, 0x9c, 0x74, ++ 0x7d, 0x88, 0x33, 0xe1, 0xdf, 0x37, 0x69, 0x2b, ++ 0xbb, 0xf1, 0x4d, 0xf4, 0xd1, 0xf1, 0x39, 0x93, ++ 0x17, 0x51, 0x19, 0xe3, 0x19, 0x1e, 0x76, 0x37, ++ 0x25, 0xfb, 0x09, 0x27, 0x6a, 0xab, 0x67, 0x6f, ++ 0x14, 0x12, 0x64, 0xe7, 0xc4, 0x07, 0xdf, 0x4d, ++ 0x17, 0xbb, 0x6d, 0xe0, 0xe9, 0xb9, 0xab, 0xca, ++ 0x10, 0x68, 0xaf, 0x7e, 0xb7, 0x33, 0x54, 0x73, ++ 0x07, 0x6e, 0xf7, 0x81, 0x97, 0x9c, 0x05, 0x6f, ++ 0x84, 0x5f, 0xd2, 0x42, 0xfb, 0x38, 0xcf, 0xd1, ++ 0x2f, 0x14, 0x30, 0x88, 0x98, 0x4d, 0x5a, 0xa9, ++ 0x76, 0xd5, 0x4f, 0x3e, 0x70, 0x6c, 0x85, 0x76, ++ 0xd7, 0x01, 0xa0, 0x1a, 0xc8, 0x4e, 0xaa, 0xac, ++ 0x78, 0xfe, 0x46, 0xde, 0x6a, 0x05, 0x46, 0xa7, ++ 0x43, 0x0c, 0xb9, 0xde, 0xb9, 0x68, 0xfb, 0xce, ++ 0x42, 0x99, 0x07, 0x4d, 0x0b, 0x3b, 0x5a, 0x30, ++ 0x35, 0xa8, 0xf9, 0x3a, 0x73, 0xef, 0x0f, 0xdb, ++ 0x1e, 0x16, 0x42, 0xc4, 0xba, 0xae, 0x58, 0xaa, ++ 0xf8, 0xe5, 0x75, 0x2f, 0x1b, 0x15, 0x5c, 0xfd, ++ 0x0a, 0x97, 0xd0, 0xe4, 0x37, 0x83, 0x61, 0x5f, ++ 0x43, 0xa6, 0xc7, 0x3f, 0x38, 0x59, 0xe6, 0xeb, ++ 0xa3, 0x90, 0xc3, 0xaa, 0xaa, 0x5a, 0xd3, 0x34, ++ 0xd4, 0x17, 0xc8, 0x65, 0x3e, 0x57, 0xbc, 0x5e, ++ 0xdd, 0x9e, 0xb7, 0xf0, 0x2e, 0x5b, 0xb2, 0x1f, ++ 0x8a, 0x08, 0x0d, 0x45, 0x91, 0x0b, 0x29, 0x53, ++ 0x4f, 0x4c, 0x5a, 0x73, 0x56, 0xfe, 0xaf, 0x41, ++ 0x01, 0x39, 0x0a, 0x24, 0x3c, 0x7e, 0xbe, 0x4e, ++ 0x53, 0xf3, 0xeb, 0x06, 0x66, 0x51, 0x28, 0x1d, ++ 0xbd, 0x41, 0x0a, 0x01, 0xab, 0x16, 0x47, 0x27, ++ 0x47, 0x47, 0xf7, 0xcb, 0x46, 0x0a, 0x70, 0x9e, ++ 0x01, 0x9c, 0x09, 0xe1, 0x2a, 0x00, 0x1a, 0xd8, ++ 0xd4, 0x79, 0x9d, 0x80, 0x15, 0x8e, 0x53, 0x2a, ++ 0x65, 0x83, 0x78, 0x3e, 0x03, 0x00, 0x07, 0x12, ++ 0x1f, 0x33, 0x3e, 0x7b, 0x13, 0x37, 0xf1, 0xc3, ++ 0xef, 0xb7, 0xc1, 0x20, 0x3c, 0x3e, 0x67, 0x66, ++ 0x5d, 0x88, 0xa7, 0x7d, 0x33, 0x50, 0x77, 0xb0, ++ 0x28, 0x8e, 0xe7, 0x2c, 0x2e, 0x7a, 0xf4, 0x3c, ++ 0x8d, 0x74, 0x83, 0xaf, 0x8e, 0x87, 0x0f, 0xe4, ++ 0x50, 0xff, 0x84, 0x5c, 0x47, 0x0c, 0x6a, 0x49, ++ 0xbf, 0x42, 0x86, 0x77, 0x15, 0x48, 0xa5, 0x90, ++ 0x5d, 0x93, 0xd6, 0x2a, 0x11, 0xd5, 0xd5, 0x11, ++ 0xaa, 0xce, 0xe7, 0x6f, 0xa5, 0xb0, 0x09, 0x2c, ++ 0x8d, 0xd3, 0x92, 0xf0, 0x5a, 0x2a, 0xda, 0x5b, ++ 0x1e, 0xd5, 0x9a, 0xc4, 0xc4, 0xf3, 0x49, 0x74, ++ 0x41, 0xca, 0xe8, 0xc1, 0xf8, 0x44, 0xd6, 0x3c, ++ 0xae, 0x6c, 0x1d, 0x9a, 0x30, 0x04, 0x4d, 0x27, ++ 0x0e, 0xb1, 0x5f, 0x59, 0xa2, 0x24, 0xe8, 0xe1, ++ 0x98, 0xc5, 0x6a, 0x4c, 0xfe, 0x41, 0xd2, 0x27, ++ 0x42, 0x52, 0xe1, 0xe9, 0x7d, 0x62, 0xe4, 0x88, ++ 0x0f, 0xad, 0xb2, 0x70, 0xcb, 0x9d, 0x4c, 0x27, ++ 0x2e, 0x76, 0x1e, 0x1a, 0x63, 0x65, 0xf5, 0x3b, ++ 0xf8, 0x57, 0x69, 0xeb, 0x5b, 0x38, 0x26, 0x39, ++ 0x33, 0x25, 0x45, 0x3e, 0x91, 0xb8, 0xd8, 0xc7, ++ 0xd5, 0x42, 0xc0, 0x22, 0x31, 0x74, 0xf4, 0xbc, ++ 0x0c, 0x23, 0xf1, 0xca, 0xc1, 0x8d, 0xd7, 0xbe, ++ 0xc9, 0x62, 0xe4, 0x08, 0x1a, 0xcf, 0x36, 0xd5, ++ 0xfe, 0x55, 0x21, 0x59, 0x91, 0x87, 0x87, 0xdf, ++ 0x06, 0xdb, 0xdf, 0x96, 0x45, 0x58, 0xda, 0x05, ++ 0xcd, 0x50, 0x4d, 0xd2, 0x7d, 0x05, 0x18, 0x73, ++ 0x6a, 0x8d, 0x11, 0x85, 0xa6, 0x88, 0xe8, 0xda, ++ 0xe6, 0x30, 0x33, 0xa4, 0x89, 0x31, 0x75, 0xbe, ++ 0x69, 0x43, 0x84, 0x43, 0x50, 0x87, 0xdd, 0x71, ++ 0x36, 0x83, 0xc3, 0x78, 0x74, 0x24, 0x0a, 0xed, ++ 0x7b, 0xdb, 0xa4, 0x24, 0x0b, 0xb9, 0x7e, 0x5d, ++ 0xff, 0xde, 0xb1, 0xef, 0x61, 0x5a, 0x45, 0x33, ++ 0xf6, 0x17, 0x07, 0x08, 0x98, 0x83, 0x92, 0x0f, ++ 0x23, 0x6d, 0xe6, 0xaa, 0x17, 0x54, 0xad, 0x6a, ++ 0xc8, 0xdb, 0x26, 0xbe, 0xb8, 0xb6, 0x08, 0xfa, ++ 0x68, 0xf1, 0xd7, 0x79, 0x6f, 0x18, 0xb4, 0x9e, ++ 0x2d, 0x3f, 0x1b, 0x64, 0xaf, 0x8d, 0x06, 0x0e, ++ 0x49, 0x28, 0xe0, 0x5d, 0x45, 0x68, 0x13, 0x87, ++ 0xfa, 0xde, 0x40, 0x7b, 0xd2, 0xc3, 0x94, 0xd5, ++ 0xe1, 0xd9, 0xc2, 0xaf, 0x55, 0x89, 0xeb, 0xb4, ++ 0x12, 0x59, 0xa8, 0xd4, 0xc5, 0x29, 0x66, 0x38, ++ 0xe6, 0xac, 0x22, 0x22, 0xd9, 0x64, 0x9b, 0x34, ++ 0x0a, 0x32, 0x9f, 0xc2, 0xbf, 0x17, 0x6c, 0x3f, ++ 0x71, 0x7a, 0x38, 0x6b, 0x98, 0xfb, 0x49, 0x36, ++ 0x89, 0xc9, 0xe2, 0xd6, 0xc7, 0x5d, 0xd0, 0x69, ++ 0x5f, 0x23, 0x35, 0xc9, 0x30, 0xe2, 0xfd, 0x44, ++ 0x58, 0x39, 0xd7, 0x97, 0xfb, 0x5c, 0x00, 0xd5, ++ 0x4f, 0x7a, 0x1a, 0x95, 0x8b, 0x62, 0x4b, 0xce, ++ 0xe5, 0x91, 0x21, 0x7b, 0x30, 0x00, 0xd6, 0xdd, ++ 0x6d, 0x02, 0x86, 0x49, 0x0f, 0x3c, 0x1a, 0x27, ++ 0x3c, 0xd3, 0x0e, 0x71, 0xf2, 0xff, 0xf5, 0x2f, ++ 0x87, 0xac, 0x67, 0x59, 0x81, 0xa3, 0xf7, 0xf8, ++ 0xd6, 0x11, 0x0c, 0x84, 0xa9, 0x03, 0xee, 0x2a, ++ 0xc4, 0xf3, 0x22, 0xab, 0x7c, 0xe2, 0x25, 0xf5, ++ 0x67, 0xa3, 0xe4, 0x11, 0xe0, 0x59, 0xb3, 0xca, ++ 0x87, 0xa0, 0xae, 0xc9, 0xa6, 0x62, 0x1b, 0x6e, ++ 0x4d, 0x02, 0x6b, 0x07, 0x9d, 0xfd, 0xd0, 0x92, ++ 0x06, 0xe1, 0xb2, 0x9a, 0x4a, 0x1f, 0x1f, 0x13, ++ 0x49, 0x99, 0x97, 0x08, 0xde, 0x7f, 0x98, 0xaf, ++ 0x51, 0x98, 0xee, 0x2c, 0xcb, 0xf0, 0x0b, 0xc6, ++ 0xb6, 0xb7, 0x2d, 0x9a, 0xb1, 0xac, 0xa6, 0xe3, ++ 0x15, 0x77, 0x9d, 0x6b, 0x1a, 0xe4, 0xfc, 0x8b, ++ 0xf2, 0x17, 0x59, 0x08, 0x04, 0x58, 0x81, 0x9d, ++ 0x1b, 0x1b, 0x69, 0x55, 0xc2, 0xb4, 0x3c, 0x1f, ++ 0x50, 0xf1, 0x7f, 0x77, 0x90, 0x4c, 0x66, 0x40, ++ 0x5a, 0xc0, 0x33, 0x1f, 0xcb, 0x05, 0x6d, 0x5c, ++ 0x06, 0x87, 0x52, 0xa2, 0x8f, 0x26, 0xd5, 0x4f ++}; ++static const u8 enc_output010[] __initconst = { ++ 0xe5, 0x26, 0xa4, 0x3d, 0xbd, 0x33, 0xd0, 0x4b, ++ 0x6f, 0x05, 0xa7, 0x6e, 0x12, 0x7a, 0xd2, 0x74, ++ 0xa6, 0xdd, 0xbd, 0x95, 0xeb, 0xf9, 0xa4, 0xf1, ++ 0x59, 0x93, 0x91, 0x70, 0xd9, 0xfe, 0x9a, 0xcd, ++ 0x53, 0x1f, 0x3a, 0xab, 0xa6, 0x7c, 0x9f, 0xa6, ++ 0x9e, 0xbd, 0x99, 0xd9, 0xb5, 0x97, 0x44, 0xd5, ++ 0x14, 0x48, 0x4d, 0x9d, 0xc0, 0xd0, 0x05, 0x96, ++ 0xeb, 0x4c, 0x78, 0x55, 0x09, 0x08, 0x01, 0x02, ++ 0x30, 0x90, 0x7b, 0x96, 0x7a, 0x7b, 0x5f, 0x30, ++ 0x41, 0x24, 0xce, 0x68, 0x61, 0x49, 0x86, 0x57, ++ 0x82, 0xdd, 0x53, 0x1c, 0x51, 0x28, 0x2b, 0x53, ++ 0x6e, 0x2d, 0xc2, 0x20, 0x4c, 0xdd, 0x8f, 0x65, ++ 0x10, 0x20, 0x50, 0xdd, 0x9d, 0x50, 0xe5, 0x71, ++ 0x40, 0x53, 0x69, 0xfc, 0x77, 0x48, 0x11, 0xb9, ++ 0xde, 0xa4, 0x8d, 0x58, 0xe4, 0xa6, 0x1a, 0x18, ++ 0x47, 0x81, 0x7e, 0xfc, 0xdd, 0xf6, 0xef, 0xce, ++ 0x2f, 0x43, 0x68, 0xd6, 0x06, 0xe2, 0x74, 0x6a, ++ 0xad, 0x90, 0xf5, 0x37, 0xf3, 0x3d, 0x82, 0x69, ++ 0x40, 0xe9, 0x6b, 0xa7, 0x3d, 0xa8, 0x1e, 0xd2, ++ 0x02, 0x7c, 0xb7, 0x9b, 0xe4, 0xda, 0x8f, 0x95, ++ 0x06, 0xc5, 0xdf, 0x73, 0xa3, 0x20, 0x9a, 0x49, ++ 0xde, 0x9c, 0xbc, 0xee, 0x14, 0x3f, 0x81, 0x5e, ++ 0xf8, 0x3b, 0x59, 0x3c, 0xe1, 0x68, 0x12, 0x5a, ++ 0x3a, 0x76, 0x3a, 0x3f, 0xf7, 0x87, 0x33, 0x0a, ++ 0x01, 0xb8, 0xd4, 0xed, 0xb6, 0xbe, 0x94, 0x5e, ++ 0x70, 0x40, 0x56, 0x67, 0x1f, 0x50, 0x44, 0x19, ++ 0xce, 0x82, 0x70, 0x10, 0x87, 0x13, 0x20, 0x0b, ++ 0x4c, 0x5a, 0xb6, 0xf6, 0xa7, 0xae, 0x81, 0x75, ++ 0x01, 0x81, 0xe6, 0x4b, 0x57, 0x7c, 0xdd, 0x6d, ++ 0xf8, 0x1c, 0x29, 0x32, 0xf7, 0xda, 0x3c, 0x2d, ++ 0xf8, 0x9b, 0x25, 0x6e, 0x00, 0xb4, 0xf7, 0x2f, ++ 0xf7, 0x04, 0xf7, 0xa1, 0x56, 0xac, 0x4f, 0x1a, ++ 0x64, 0xb8, 0x47, 0x55, 0x18, 0x7b, 0x07, 0x4d, ++ 0xbd, 0x47, 0x24, 0x80, 0x5d, 0xa2, 0x70, 0xc5, ++ 0xdd, 0x8e, 0x82, 0xd4, 0xeb, 0xec, 0xb2, 0x0c, ++ 0x39, 0xd2, 0x97, 0xc1, 0xcb, 0xeb, 0xf4, 0x77, ++ 0x59, 0xb4, 0x87, 0xef, 0xcb, 0x43, 0x2d, 0x46, ++ 0x54, 0xd1, 0xa7, 0xd7, 0x15, 0x99, 0x0a, 0x43, ++ 0xa1, 0xe0, 0x99, 0x33, 0x71, 0xc1, 0xed, 0xfe, ++ 0x72, 0x46, 0x33, 0x8e, 0x91, 0x08, 0x9f, 0xc8, ++ 0x2e, 0xca, 0xfa, 0xdc, 0x59, 0xd5, 0xc3, 0x76, ++ 0x84, 0x9f, 0xa3, 0x37, 0x68, 0xc3, 0xf0, 0x47, ++ 0x2c, 0x68, 0xdb, 0x5e, 0xc3, 0x49, 0x4c, 0xe8, ++ 0x92, 0x85, 0xe2, 0x23, 0xd3, 0x3f, 0xad, 0x32, ++ 0xe5, 0x2b, 0x82, 0xd7, 0x8f, 0x99, 0x0a, 0x59, ++ 0x5c, 0x45, 0xd9, 0xb4, 0x51, 0x52, 0xc2, 0xae, ++ 0xbf, 0x80, 0xcf, 0xc9, 0xc9, 0x51, 0x24, 0x2a, ++ 0x3b, 0x3a, 0x4d, 0xae, 0xeb, 0xbd, 0x22, 0xc3, ++ 0x0e, 0x0f, 0x59, 0x25, 0x92, 0x17, 0xe9, 0x74, ++ 0xc7, 0x8b, 0x70, 0x70, 0x36, 0x55, 0x95, 0x75, ++ 0x4b, 0xad, 0x61, 0x2b, 0x09, 0xbc, 0x82, 0xf2, ++ 0x6e, 0x94, 0x43, 0xae, 0xc3, 0xd5, 0xcd, 0x8e, ++ 0xfe, 0x5b, 0x9a, 0x88, 0x43, 0x01, 0x75, 0xb2, ++ 0x23, 0x09, 0xf7, 0x89, 0x83, 0xe7, 0xfa, 0xf9, ++ 0xb4, 0x9b, 0xf8, 0xef, 0xbd, 0x1c, 0x92, 0xc1, ++ 0xda, 0x7e, 0xfe, 0x05, 0xba, 0x5a, 0xcd, 0x07, ++ 0x6a, 0x78, 0x9e, 0x5d, 0xfb, 0x11, 0x2f, 0x79, ++ 0x38, 0xb6, 0xc2, 0x5b, 0x6b, 0x51, 0xb4, 0x71, ++ 0xdd, 0xf7, 0x2a, 0xe4, 0xf4, 0x72, 0x76, 0xad, ++ 0xc2, 0xdd, 0x64, 0x5d, 0x79, 0xb6, 0xf5, 0x7a, ++ 0x77, 0x20, 0x05, 0x3d, 0x30, 0x06, 0xd4, 0x4c, ++ 0x0a, 0x2c, 0x98, 0x5a, 0xb9, 0xd4, 0x98, 0xa9, ++ 0x3f, 0xc6, 0x12, 0xea, 0x3b, 0x4b, 0xc5, 0x79, ++ 0x64, 0x63, 0x6b, 0x09, 0x54, 0x3b, 0x14, 0x27, ++ 0xba, 0x99, 0x80, 0xc8, 0x72, 0xa8, 0x12, 0x90, ++ 0x29, 0xba, 0x40, 0x54, 0x97, 0x2b, 0x7b, 0xfe, ++ 0xeb, 0xcd, 0x01, 0x05, 0x44, 0x72, 0xdb, 0x99, ++ 0xe4, 0x61, 0xc9, 0x69, 0xd6, 0xb9, 0x28, 0xd1, ++ 0x05, 0x3e, 0xf9, 0x0b, 0x49, 0x0a, 0x49, 0xe9, ++ 0x8d, 0x0e, 0xa7, 0x4a, 0x0f, 0xaf, 0x32, 0xd0, ++ 0xe0, 0xb2, 0x3a, 0x55, 0x58, 0xfe, 0x5c, 0x28, ++ 0x70, 0x51, 0x23, 0xb0, 0x7b, 0x6a, 0x5f, 0x1e, ++ 0xb8, 0x17, 0xd7, 0x94, 0x15, 0x8f, 0xee, 0x20, ++ 0xc7, 0x42, 0x25, 0x3e, 0x9a, 0x14, 0xd7, 0x60, ++ 0x72, 0x39, 0x47, 0x48, 0xa9, 0xfe, 0xdd, 0x47, ++ 0x0a, 0xb1, 0xe6, 0x60, 0x28, 0x8c, 0x11, 0x68, ++ 0xe1, 0xff, 0xd7, 0xce, 0xc8, 0xbe, 0xb3, 0xfe, ++ 0x27, 0x30, 0x09, 0x70, 0xd7, 0xfa, 0x02, 0x33, ++ 0x3a, 0x61, 0x2e, 0xc7, 0xff, 0xa4, 0x2a, 0xa8, ++ 0x6e, 0xb4, 0x79, 0x35, 0x6d, 0x4c, 0x1e, 0x38, ++ 0xf8, 0xee, 0xd4, 0x84, 0x4e, 0x6e, 0x28, 0xa7, ++ 0xce, 0xc8, 0xc1, 0xcf, 0x80, 0x05, 0xf3, 0x04, ++ 0xef, 0xc8, 0x18, 0x28, 0x2e, 0x8d, 0x5e, 0x0c, ++ 0xdf, 0xb8, 0x5f, 0x96, 0xe8, 0xc6, 0x9c, 0x2f, ++ 0xe5, 0xa6, 0x44, 0xd7, 0xe7, 0x99, 0x44, 0x0c, ++ 0xec, 0xd7, 0x05, 0x60, 0x97, 0xbb, 0x74, 0x77, ++ 0x58, 0xd5, 0xbb, 0x48, 0xde, 0x5a, 0xb2, 0x54, ++ 0x7f, 0x0e, 0x46, 0x70, 0x6a, 0x6f, 0x78, 0xa5, ++ 0x08, 0x89, 0x05, 0x4e, 0x7e, 0xa0, 0x69, 0xb4, ++ 0x40, 0x60, 0x55, 0x77, 0x75, 0x9b, 0x19, 0xf2, ++ 0xd5, 0x13, 0x80, 0x77, 0xf9, 0x4b, 0x3f, 0x1e, ++ 0xee, 0xe6, 0x76, 0x84, 0x7b, 0x8c, 0xe5, 0x27, ++ 0xa8, 0x0a, 0x91, 0x01, 0x68, 0x71, 0x8a, 0x3f, ++ 0x06, 0xab, 0xf6, 0xa9, 0xa5, 0xe6, 0x72, 0x92, ++ 0xe4, 0x67, 0xe2, 0xa2, 0x46, 0x35, 0x84, 0x55, ++ 0x7d, 0xca, 0xa8, 0x85, 0xd0, 0xf1, 0x3f, 0xbe, ++ 0xd7, 0x34, 0x64, 0xfc, 0xae, 0xe3, 0xe4, 0x04, ++ 0x9f, 0x66, 0x02, 0xb9, 0x88, 0x10, 0xd9, 0xc4, ++ 0x4c, 0x31, 0x43, 0x7a, 0x93, 0xe2, 0x9b, 0x56, ++ 0x43, 0x84, 0xdc, 0xdc, 0xde, 0x1d, 0xa4, 0x02, ++ 0x0e, 0xc2, 0xef, 0xc3, 0xf8, 0x78, 0xd1, 0xb2, ++ 0x6b, 0x63, 0x18, 0xc9, 0xa9, 0xe5, 0x72, 0xd8, ++ 0xf3, 0xb9, 0xd1, 0x8a, 0xc7, 0x1a, 0x02, 0x27, ++ 0x20, 0x77, 0x10, 0xe5, 0xc8, 0xd4, 0x4a, 0x47, ++ 0xe5, 0xdf, 0x5f, 0x01, 0xaa, 0xb0, 0xd4, 0x10, ++ 0xbb, 0x69, 0xe3, 0x36, 0xc8, 0xe1, 0x3d, 0x43, ++ 0xfb, 0x86, 0xcd, 0xcc, 0xbf, 0xf4, 0x88, 0xe0, ++ 0x20, 0xca, 0xb7, 0x1b, 0xf1, 0x2f, 0x5c, 0xee, ++ 0xd4, 0xd3, 0xa3, 0xcc, 0xa4, 0x1e, 0x1c, 0x47, ++ 0xfb, 0xbf, 0xfc, 0xa2, 0x41, 0x55, 0x9d, 0xf6, ++ 0x5a, 0x5e, 0x65, 0x32, 0x34, 0x7b, 0x52, 0x8d, ++ 0xd5, 0xd0, 0x20, 0x60, 0x03, 0xab, 0x3f, 0x8c, ++ 0xd4, 0x21, 0xea, 0x2a, 0xd9, 0xc4, 0xd0, 0xd3, ++ 0x65, 0xd8, 0x7a, 0x13, 0x28, 0x62, 0x32, 0x4b, ++ 0x2c, 0x87, 0x93, 0xa8, 0xb4, 0x52, 0x45, 0x09, ++ 0x44, 0xec, 0xec, 0xc3, 0x17, 0xdb, 0x9a, 0x4d, ++ 0x5c, 0xa9, 0x11, 0xd4, 0x7d, 0xaf, 0x9e, 0xf1, ++ 0x2d, 0xb2, 0x66, 0xc5, 0x1d, 0xed, 0xb7, 0xcd, ++ 0x0b, 0x25, 0x5e, 0x30, 0x47, 0x3f, 0x40, 0xf4, ++ 0xa1, 0xa0, 0x00, 0x94, 0x10, 0xc5, 0x6a, 0x63, ++ 0x1a, 0xd5, 0x88, 0x92, 0x8e, 0x82, 0x39, 0x87, ++ 0x3c, 0x78, 0x65, 0x58, 0x42, 0x75, 0x5b, 0xdd, ++ 0x77, 0x3e, 0x09, 0x4e, 0x76, 0x5b, 0xe6, 0x0e, ++ 0x4d, 0x38, 0xb2, 0xc0, 0xb8, 0x95, 0x01, 0x7a, ++ 0x10, 0xe0, 0xfb, 0x07, 0xf2, 0xab, 0x2d, 0x8c, ++ 0x32, 0xed, 0x2b, 0xc0, 0x46, 0xc2, 0xf5, 0x38, ++ 0x83, 0xf0, 0x17, 0xec, 0xc1, 0x20, 0x6a, 0x9a, ++ 0x0b, 0x00, 0xa0, 0x98, 0x22, 0x50, 0x23, 0xd5, ++ 0x80, 0x6b, 0xf6, 0x1f, 0xc3, 0xcc, 0x97, 0xc9, ++ 0x24, 0x9f, 0xf3, 0xaf, 0x43, 0x14, 0xd5, 0xa0 ++}; ++static const u8 enc_assoc010[] __initconst = { ++ 0xd2, 0xa1, 0x70, 0xdb, 0x7a, 0xf8, 0xfa, 0x27, ++ 0xba, 0x73, 0x0f, 0xbf, 0x3d, 0x1e, 0x82, 0xb2 ++}; ++static const u8 enc_nonce010[] __initconst = { ++ 0xdb, 0x92, 0x0f, 0x7f, 0x17, 0x54, 0x0c, 0x30 ++}; ++static const u8 enc_key010[] __initconst = { ++ 0x47, 0x11, 0xeb, 0x86, 0x2b, 0x2c, 0xab, 0x44, ++ 0x34, 0xda, 0x7f, 0x57, 0x03, 0x39, 0x0c, 0xaf, ++ 0x2c, 0x14, 0xfd, 0x65, 0x23, 0xe9, 0x8e, 0x74, ++ 0xd5, 0x08, 0x68, 0x08, 0xe7, 0xb4, 0x72, 0xd7 ++}; ++ ++static const u8 enc_input011[] __initconst = { ++ 0x7a, 0x57, 0xf2, 0xc7, 0x06, 0x3f, 0x50, 0x7b, ++ 0x36, 0x1a, 0x66, 0x5c, 0xb9, 0x0e, 0x5e, 0x3b, ++ 0x45, 0x60, 0xbe, 0x9a, 0x31, 0x9f, 0xff, 0x5d, ++ 0x66, 0x34, 0xb4, 0xdc, 0xfb, 0x9d, 0x8e, 0xee, ++ 0x6a, 0x33, 0xa4, 0x07, 0x3c, 0xf9, 0x4c, 0x30, ++ 0xa1, 0x24, 0x52, 0xf9, 0x50, 0x46, 0x88, 0x20, ++ 0x02, 0x32, 0x3a, 0x0e, 0x99, 0x63, 0xaf, 0x1f, ++ 0x15, 0x28, 0x2a, 0x05, 0xff, 0x57, 0x59, 0x5e, ++ 0x18, 0xa1, 0x1f, 0xd0, 0x92, 0x5c, 0x88, 0x66, ++ 0x1b, 0x00, 0x64, 0xa5, 0x93, 0x8d, 0x06, 0x46, ++ 0xb0, 0x64, 0x8b, 0x8b, 0xef, 0x99, 0x05, 0x35, ++ 0x85, 0xb3, 0xf3, 0x33, 0xbb, 0xec, 0x66, 0xb6, ++ 0x3d, 0x57, 0x42, 0xe3, 0xb4, 0xc6, 0xaa, 0xb0, ++ 0x41, 0x2a, 0xb9, 0x59, 0xa9, 0xf6, 0x3e, 0x15, ++ 0x26, 0x12, 0x03, 0x21, 0x4c, 0x74, 0x43, 0x13, ++ 0x2a, 0x03, 0x27, 0x09, 0xb4, 0xfb, 0xe7, 0xb7, ++ 0x40, 0xff, 0x5e, 0xce, 0x48, 0x9a, 0x60, 0xe3, ++ 0x8b, 0x80, 0x8c, 0x38, 0x2d, 0xcb, 0x93, 0x37, ++ 0x74, 0x05, 0x52, 0x6f, 0x73, 0x3e, 0xc3, 0xbc, ++ 0xca, 0x72, 0x0a, 0xeb, 0xf1, 0x3b, 0xa0, 0x95, ++ 0xdc, 0x8a, 0xc4, 0xa9, 0xdc, 0xca, 0x44, 0xd8, ++ 0x08, 0x63, 0x6a, 0x36, 0xd3, 0x3c, 0xb8, 0xac, ++ 0x46, 0x7d, 0xfd, 0xaa, 0xeb, 0x3e, 0x0f, 0x45, ++ 0x8f, 0x49, 0xda, 0x2b, 0xf2, 0x12, 0xbd, 0xaf, ++ 0x67, 0x8a, 0x63, 0x48, 0x4b, 0x55, 0x5f, 0x6d, ++ 0x8c, 0xb9, 0x76, 0x34, 0x84, 0xae, 0xc2, 0xfc, ++ 0x52, 0x64, 0x82, 0xf7, 0xb0, 0x06, 0xf0, 0x45, ++ 0x73, 0x12, 0x50, 0x30, 0x72, 0xea, 0x78, 0x9a, ++ 0xa8, 0xaf, 0xb5, 0xe3, 0xbb, 0x77, 0x52, 0xec, ++ 0x59, 0x84, 0xbf, 0x6b, 0x8f, 0xce, 0x86, 0x5e, ++ 0x1f, 0x23, 0xe9, 0xfb, 0x08, 0x86, 0xf7, 0x10, ++ 0xb9, 0xf2, 0x44, 0x96, 0x44, 0x63, 0xa9, 0xa8, ++ 0x78, 0x00, 0x23, 0xd6, 0xc7, 0xe7, 0x6e, 0x66, ++ 0x4f, 0xcc, 0xee, 0x15, 0xb3, 0xbd, 0x1d, 0xa0, ++ 0xe5, 0x9c, 0x1b, 0x24, 0x2c, 0x4d, 0x3c, 0x62, ++ 0x35, 0x9c, 0x88, 0x59, 0x09, 0xdd, 0x82, 0x1b, ++ 0xcf, 0x0a, 0x83, 0x6b, 0x3f, 0xae, 0x03, 0xc4, ++ 0xb4, 0xdd, 0x7e, 0x5b, 0x28, 0x76, 0x25, 0x96, ++ 0xd9, 0xc9, 0x9d, 0x5f, 0x86, 0xfa, 0xf6, 0xd7, ++ 0xd2, 0xe6, 0x76, 0x1d, 0x0f, 0xa1, 0xdc, 0x74, ++ 0x05, 0x1b, 0x1d, 0xe0, 0xcd, 0x16, 0xb0, 0xa8, ++ 0x8a, 0x34, 0x7b, 0x15, 0x11, 0x77, 0xe5, 0x7b, ++ 0x7e, 0x20, 0xf7, 0xda, 0x38, 0xda, 0xce, 0x70, ++ 0xe9, 0xf5, 0x6c, 0xd9, 0xbe, 0x0c, 0x4c, 0x95, ++ 0x4c, 0xc2, 0x9b, 0x34, 0x55, 0x55, 0xe1, 0xf3, ++ 0x46, 0x8e, 0x48, 0x74, 0x14, 0x4f, 0x9d, 0xc9, ++ 0xf5, 0xe8, 0x1a, 0xf0, 0x11, 0x4a, 0xc1, 0x8d, ++ 0xe0, 0x93, 0xa0, 0xbe, 0x09, 0x1c, 0x2b, 0x4e, ++ 0x0f, 0xb2, 0x87, 0x8b, 0x84, 0xfe, 0x92, 0x32, ++ 0x14, 0xd7, 0x93, 0xdf, 0xe7, 0x44, 0xbc, 0xc5, ++ 0xae, 0x53, 0x69, 0xd8, 0xb3, 0x79, 0x37, 0x80, ++ 0xe3, 0x17, 0x5c, 0xec, 0x53, 0x00, 0x9a, 0xe3, ++ 0x8e, 0xdc, 0x38, 0xb8, 0x66, 0xf0, 0xd3, 0xad, ++ 0x1d, 0x02, 0x96, 0x86, 0x3e, 0x9d, 0x3b, 0x5d, ++ 0xa5, 0x7f, 0x21, 0x10, 0xf1, 0x1f, 0x13, 0x20, ++ 0xf9, 0x57, 0x87, 0x20, 0xf5, 0x5f, 0xf1, 0x17, ++ 0x48, 0x0a, 0x51, 0x5a, 0xcd, 0x19, 0x03, 0xa6, ++ 0x5a, 0xd1, 0x12, 0x97, 0xe9, 0x48, 0xe2, 0x1d, ++ 0x83, 0x75, 0x50, 0xd9, 0x75, 0x7d, 0x6a, 0x82, ++ 0xa1, 0xf9, 0x4e, 0x54, 0x87, 0x89, 0xc9, 0x0c, ++ 0xb7, 0x5b, 0x6a, 0x91, 0xc1, 0x9c, 0xb2, 0xa9, ++ 0xdc, 0x9a, 0xa4, 0x49, 0x0a, 0x6d, 0x0d, 0xbb, ++ 0xde, 0x86, 0x44, 0xdd, 0x5d, 0x89, 0x2b, 0x96, ++ 0x0f, 0x23, 0x95, 0xad, 0xcc, 0xa2, 0xb3, 0xb9, ++ 0x7e, 0x74, 0x38, 0xba, 0x9f, 0x73, 0xae, 0x5f, ++ 0xf8, 0x68, 0xa2, 0xe0, 0xa9, 0xce, 0xbd, 0x40, ++ 0xd4, 0x4c, 0x6b, 0xd2, 0x56, 0x62, 0xb0, 0xcc, ++ 0x63, 0x7e, 0x5b, 0xd3, 0xae, 0xd1, 0x75, 0xce, ++ 0xbb, 0xb4, 0x5b, 0xa8, 0xf8, 0xb4, 0xac, 0x71, ++ 0x75, 0xaa, 0xc9, 0x9f, 0xbb, 0x6c, 0xad, 0x0f, ++ 0x55, 0x5d, 0xe8, 0x85, 0x7d, 0xf9, 0x21, 0x35, ++ 0xea, 0x92, 0x85, 0x2b, 0x00, 0xec, 0x84, 0x90, ++ 0x0a, 0x63, 0x96, 0xe4, 0x6b, 0xa9, 0x77, 0xb8, ++ 0x91, 0xf8, 0x46, 0x15, 0x72, 0x63, 0x70, 0x01, ++ 0x40, 0xa3, 0xa5, 0x76, 0x62, 0x2b, 0xbf, 0xf1, ++ 0xe5, 0x8d, 0x9f, 0xa3, 0xfa, 0x9b, 0x03, 0xbe, ++ 0xfe, 0x65, 0x6f, 0xa2, 0x29, 0x0d, 0x54, 0xb4, ++ 0x71, 0xce, 0xa9, 0xd6, 0x3d, 0x88, 0xf9, 0xaf, ++ 0x6b, 0xa8, 0x9e, 0xf4, 0x16, 0x96, 0x36, 0xb9, ++ 0x00, 0xdc, 0x10, 0xab, 0xb5, 0x08, 0x31, 0x1f, ++ 0x00, 0xb1, 0x3c, 0xd9, 0x38, 0x3e, 0xc6, 0x04, ++ 0xa7, 0x4e, 0xe8, 0xae, 0xed, 0x98, 0xc2, 0xf7, ++ 0xb9, 0x00, 0x5f, 0x8c, 0x60, 0xd1, 0xe5, 0x15, ++ 0xf7, 0xae, 0x1e, 0x84, 0x88, 0xd1, 0xf6, 0xbc, ++ 0x3a, 0x89, 0x35, 0x22, 0x83, 0x7c, 0xca, 0xf0, ++ 0x33, 0x82, 0x4c, 0x79, 0x3c, 0xfd, 0xb1, 0xae, ++ 0x52, 0x62, 0x55, 0xd2, 0x41, 0x60, 0xc6, 0xbb, ++ 0xfa, 0x0e, 0x59, 0xd6, 0xa8, 0xfe, 0x5d, 0xed, ++ 0x47, 0x3d, 0xe0, 0xea, 0x1f, 0x6e, 0x43, 0x51, ++ 0xec, 0x10, 0x52, 0x56, 0x77, 0x42, 0x6b, 0x52, ++ 0x87, 0xd8, 0xec, 0xe0, 0xaa, 0x76, 0xa5, 0x84, ++ 0x2a, 0x22, 0x24, 0xfd, 0x92, 0x40, 0x88, 0xd5, ++ 0x85, 0x1c, 0x1f, 0x6b, 0x47, 0xa0, 0xc4, 0xe4, ++ 0xef, 0xf4, 0xea, 0xd7, 0x59, 0xac, 0x2a, 0x9e, ++ 0x8c, 0xfa, 0x1f, 0x42, 0x08, 0xfe, 0x4f, 0x74, ++ 0xa0, 0x26, 0xf5, 0xb3, 0x84, 0xf6, 0x58, 0x5f, ++ 0x26, 0x66, 0x3e, 0xd7, 0xe4, 0x22, 0x91, 0x13, ++ 0xc8, 0xac, 0x25, 0x96, 0x23, 0xd8, 0x09, 0xea, ++ 0x45, 0x75, 0x23, 0xb8, 0x5f, 0xc2, 0x90, 0x8b, ++ 0x09, 0xc4, 0xfc, 0x47, 0x6c, 0x6d, 0x0a, 0xef, ++ 0x69, 0xa4, 0x38, 0x19, 0xcf, 0x7d, 0xf9, 0x09, ++ 0x73, 0x9b, 0x60, 0x5a, 0xf7, 0x37, 0xb5, 0xfe, ++ 0x9f, 0xe3, 0x2b, 0x4c, 0x0d, 0x6e, 0x19, 0xf1, ++ 0xd6, 0xc0, 0x70, 0xf3, 0x9d, 0x22, 0x3c, 0xf9, ++ 0x49, 0xce, 0x30, 0x8e, 0x44, 0xb5, 0x76, 0x15, ++ 0x8f, 0x52, 0xfd, 0xa5, 0x04, 0xb8, 0x55, 0x6a, ++ 0x36, 0x59, 0x7c, 0xc4, 0x48, 0xb8, 0xd7, 0xab, ++ 0x05, 0x66, 0xe9, 0x5e, 0x21, 0x6f, 0x6b, 0x36, ++ 0x29, 0xbb, 0xe9, 0xe3, 0xa2, 0x9a, 0xa8, 0xcd, ++ 0x55, 0x25, 0x11, 0xba, 0x5a, 0x58, 0xa0, 0xde, ++ 0xae, 0x19, 0x2a, 0x48, 0x5a, 0xff, 0x36, 0xcd, ++ 0x6d, 0x16, 0x7a, 0x73, 0x38, 0x46, 0xe5, 0x47, ++ 0x59, 0xc8, 0xa2, 0xf6, 0xe2, 0x6c, 0x83, 0xc5, ++ 0x36, 0x2c, 0x83, 0x7d, 0xb4, 0x01, 0x05, 0x69, ++ 0xe7, 0xaf, 0x5c, 0xc4, 0x64, 0x82, 0x12, 0x21, ++ 0xef, 0xf7, 0xd1, 0x7d, 0xb8, 0x8d, 0x8c, 0x98, ++ 0x7c, 0x5f, 0x7d, 0x92, 0x88, 0xb9, 0x94, 0x07, ++ 0x9c, 0xd8, 0xe9, 0x9c, 0x17, 0x38, 0xe3, 0x57, ++ 0x6c, 0xe0, 0xdc, 0xa5, 0x92, 0x42, 0xb3, 0xbd, ++ 0x50, 0xa2, 0x7e, 0xb5, 0xb1, 0x52, 0x72, 0x03, ++ 0x97, 0xd8, 0xaa, 0x9a, 0x1e, 0x75, 0x41, 0x11, ++ 0xa3, 0x4f, 0xcc, 0xd4, 0xe3, 0x73, 0xad, 0x96, ++ 0xdc, 0x47, 0x41, 0x9f, 0xb0, 0xbe, 0x79, 0x91, ++ 0xf5, 0xb6, 0x18, 0xfe, 0xc2, 0x83, 0x18, 0x7d, ++ 0x73, 0xd9, 0x4f, 0x83, 0x84, 0x03, 0xb3, 0xf0, ++ 0x77, 0x66, 0x3d, 0x83, 0x63, 0x2e, 0x2c, 0xf9, ++ 0xdd, 0xa6, 0x1f, 0x89, 0x82, 0xb8, 0x23, 0x42, ++ 0xeb, 0xe2, 0xca, 0x70, 0x82, 0x61, 0x41, 0x0a, ++ 0x6d, 0x5f, 0x75, 0xc5, 0xe2, 0xc4, 0x91, 0x18, ++ 0x44, 0x22, 0xfa, 0x34, 0x10, 0xf5, 0x20, 0xdc, ++ 0xb7, 0xdd, 0x2a, 0x20, 0x77, 0xf5, 0xf9, 0xce, ++ 0xdb, 0xa0, 0x0a, 0x52, 0x2a, 0x4e, 0xdd, 0xcc, ++ 0x97, 0xdf, 0x05, 0xe4, 0x5e, 0xb7, 0xaa, 0xf0, ++ 0xe2, 0x80, 0xff, 0xba, 0x1a, 0x0f, 0xac, 0xdf, ++ 0x02, 0x32, 0xe6, 0xf7, 0xc7, 0x17, 0x13, 0xb7, ++ 0xfc, 0x98, 0x48, 0x8c, 0x0d, 0x82, 0xc9, 0x80, ++ 0x7a, 0xe2, 0x0a, 0xc5, 0xb4, 0xde, 0x7c, 0x3c, ++ 0x79, 0x81, 0x0e, 0x28, 0x65, 0x79, 0x67, 0x82, ++ 0x69, 0x44, 0x66, 0x09, 0xf7, 0x16, 0x1a, 0xf9, ++ 0x7d, 0x80, 0xa1, 0x79, 0x14, 0xa9, 0xc8, 0x20, ++ 0xfb, 0xa2, 0x46, 0xbe, 0x08, 0x35, 0x17, 0x58, ++ 0xc1, 0x1a, 0xda, 0x2a, 0x6b, 0x2e, 0x1e, 0xe6, ++ 0x27, 0x55, 0x7b, 0x19, 0xe2, 0xfb, 0x64, 0xfc, ++ 0x5e, 0x15, 0x54, 0x3c, 0xe7, 0xc2, 0x11, 0x50, ++ 0x30, 0xb8, 0x72, 0x03, 0x0b, 0x1a, 0x9f, 0x86, ++ 0x27, 0x11, 0x5c, 0x06, 0x2b, 0xbd, 0x75, 0x1a, ++ 0x0a, 0xda, 0x01, 0xfa, 0x5c, 0x4a, 0xc1, 0x80, ++ 0x3a, 0x6e, 0x30, 0xc8, 0x2c, 0xeb, 0x56, 0xec, ++ 0x89, 0xfa, 0x35, 0x7b, 0xb2, 0xf0, 0x97, 0x08, ++ 0x86, 0x53, 0xbe, 0xbd, 0x40, 0x41, 0x38, 0x1c, ++ 0xb4, 0x8b, 0x79, 0x2e, 0x18, 0x96, 0x94, 0xde, ++ 0xe8, 0xca, 0xe5, 0x9f, 0x92, 0x9f, 0x15, 0x5d, ++ 0x56, 0x60, 0x5c, 0x09, 0xf9, 0x16, 0xf4, 0x17, ++ 0x0f, 0xf6, 0x4c, 0xda, 0xe6, 0x67, 0x89, 0x9f, ++ 0xca, 0x6c, 0xe7, 0x9b, 0x04, 0x62, 0x0e, 0x26, ++ 0xa6, 0x52, 0xbd, 0x29, 0xff, 0xc7, 0xa4, 0x96, ++ 0xe6, 0x6a, 0x02, 0xa5, 0x2e, 0x7b, 0xfe, 0x97, ++ 0x68, 0x3e, 0x2e, 0x5f, 0x3b, 0x0f, 0x36, 0xd6, ++ 0x98, 0x19, 0x59, 0x48, 0xd2, 0xc6, 0xe1, 0x55, ++ 0x1a, 0x6e, 0xd6, 0xed, 0x2c, 0xba, 0xc3, 0x9e, ++ 0x64, 0xc9, 0x95, 0x86, 0x35, 0x5e, 0x3e, 0x88, ++ 0x69, 0x99, 0x4b, 0xee, 0xbe, 0x9a, 0x99, 0xb5, ++ 0x6e, 0x58, 0xae, 0xdd, 0x22, 0xdb, 0xdd, 0x6b, ++ 0xfc, 0xaf, 0x90, 0xa3, 0x3d, 0xa4, 0xc1, 0x15, ++ 0x92, 0x18, 0x8d, 0xd2, 0x4b, 0x7b, 0x06, 0xd1, ++ 0x37, 0xb5, 0xe2, 0x7c, 0x2c, 0xf0, 0x25, 0xe4, ++ 0x94, 0x2a, 0xbd, 0xe3, 0x82, 0x70, 0x78, 0xa3, ++ 0x82, 0x10, 0x5a, 0x90, 0xd7, 0xa4, 0xfa, 0xaf, ++ 0x1a, 0x88, 0x59, 0xdc, 0x74, 0x12, 0xb4, 0x8e, ++ 0xd7, 0x19, 0x46, 0xf4, 0x84, 0x69, 0x9f, 0xbb, ++ 0x70, 0xa8, 0x4c, 0x52, 0x81, 0xa9, 0xff, 0x76, ++ 0x1c, 0xae, 0xd8, 0x11, 0x3d, 0x7f, 0x7d, 0xc5, ++ 0x12, 0x59, 0x28, 0x18, 0xc2, 0xa2, 0xb7, 0x1c, ++ 0x88, 0xf8, 0xd6, 0x1b, 0xa6, 0x7d, 0x9e, 0xde, ++ 0x29, 0xf8, 0xed, 0xff, 0xeb, 0x92, 0x24, 0x4f, ++ 0x05, 0xaa, 0xd9, 0x49, 0xba, 0x87, 0x59, 0x51, ++ 0xc9, 0x20, 0x5c, 0x9b, 0x74, 0xcf, 0x03, 0xd9, ++ 0x2d, 0x34, 0xc7, 0x5b, 0xa5, 0x40, 0xb2, 0x99, ++ 0xf5, 0xcb, 0xb4, 0xf6, 0xb7, 0x72, 0x4a, 0xd6, ++ 0xbd, 0xb0, 0xf3, 0x93, 0xe0, 0x1b, 0xa8, 0x04, ++ 0x1e, 0x35, 0xd4, 0x80, 0x20, 0xf4, 0x9c, 0x31, ++ 0x6b, 0x45, 0xb9, 0x15, 0xb0, 0x5e, 0xdd, 0x0a, ++ 0x33, 0x9c, 0x83, 0xcd, 0x58, 0x89, 0x50, 0x56, ++ 0xbb, 0x81, 0x00, 0x91, 0x32, 0xf3, 0x1b, 0x3e, ++ 0xcf, 0x45, 0xe1, 0xf9, 0xe1, 0x2c, 0x26, 0x78, ++ 0x93, 0x9a, 0x60, 0x46, 0xc9, 0xb5, 0x5e, 0x6a, ++ 0x28, 0x92, 0x87, 0x3f, 0x63, 0x7b, 0xdb, 0xf7, ++ 0xd0, 0x13, 0x9d, 0x32, 0x40, 0x5e, 0xcf, 0xfb, ++ 0x79, 0x68, 0x47, 0x4c, 0xfd, 0x01, 0x17, 0xe6, ++ 0x97, 0x93, 0x78, 0xbb, 0xa6, 0x27, 0xa3, 0xe8, ++ 0x1a, 0xe8, 0x94, 0x55, 0x7d, 0x08, 0xe5, 0xdc, ++ 0x66, 0xa3, 0x69, 0xc8, 0xca, 0xc5, 0xa1, 0x84, ++ 0x55, 0xde, 0x08, 0x91, 0x16, 0x3a, 0x0c, 0x86, ++ 0xab, 0x27, 0x2b, 0x64, 0x34, 0x02, 0x6c, 0x76, ++ 0x8b, 0xc6, 0xaf, 0xcc, 0xe1, 0xd6, 0x8c, 0x2a, ++ 0x18, 0x3d, 0xa6, 0x1b, 0x37, 0x75, 0x45, 0x73, ++ 0xc2, 0x75, 0xd7, 0x53, 0x78, 0x3a, 0xd6, 0xe8, ++ 0x29, 0xd2, 0x4a, 0xa8, 0x1e, 0x82, 0xf6, 0xb6, ++ 0x81, 0xde, 0x21, 0xed, 0x2b, 0x56, 0xbb, 0xf2, ++ 0xd0, 0x57, 0xc1, 0x7c, 0xd2, 0x6a, 0xd2, 0x56, ++ 0xf5, 0x13, 0x5f, 0x1c, 0x6a, 0x0b, 0x74, 0xfb, ++ 0xe9, 0xfe, 0x9e, 0xea, 0x95, 0xb2, 0x46, 0xab, ++ 0x0a, 0xfc, 0xfd, 0xf3, 0xbb, 0x04, 0x2b, 0x76, ++ 0x1b, 0xa4, 0x74, 0xb0, 0xc1, 0x78, 0xc3, 0x69, ++ 0xe2, 0xb0, 0x01, 0xe1, 0xde, 0x32, 0x4c, 0x8d, ++ 0x1a, 0xb3, 0x38, 0x08, 0xd5, 0xfc, 0x1f, 0xdc, ++ 0x0e, 0x2c, 0x9c, 0xb1, 0xa1, 0x63, 0x17, 0x22, ++ 0xf5, 0x6c, 0x93, 0x70, 0x74, 0x00, 0xf8, 0x39, ++ 0x01, 0x94, 0xd1, 0x32, 0x23, 0x56, 0x5d, 0xa6, ++ 0x02, 0x76, 0x76, 0x93, 0xce, 0x2f, 0x19, 0xe9, ++ 0x17, 0x52, 0xae, 0x6e, 0x2c, 0x6d, 0x61, 0x7f, ++ 0x3b, 0xaa, 0xe0, 0x52, 0x85, 0xc5, 0x65, 0xc1, ++ 0xbb, 0x8e, 0x5b, 0x21, 0xd5, 0xc9, 0x78, 0x83, ++ 0x07, 0x97, 0x4c, 0x62, 0x61, 0x41, 0xd4, 0xfc, ++ 0xc9, 0x39, 0xe3, 0x9b, 0xd0, 0xcc, 0x75, 0xc4, ++ 0x97, 0xe6, 0xdd, 0x2a, 0x5f, 0xa6, 0xe8, 0x59, ++ 0x6c, 0x98, 0xb9, 0x02, 0xe2, 0xa2, 0xd6, 0x68, ++ 0xee, 0x3b, 0x1d, 0xe3, 0x4d, 0x5b, 0x30, 0xef, ++ 0x03, 0xf2, 0xeb, 0x18, 0x57, 0x36, 0xe8, 0xa1, ++ 0xf4, 0x47, 0xfb, 0xcb, 0x8f, 0xcb, 0xc8, 0xf3, ++ 0x4f, 0x74, 0x9d, 0x9d, 0xb1, 0x8d, 0x14, 0x44, ++ 0xd9, 0x19, 0xb4, 0x54, 0x4f, 0x75, 0x19, 0x09, ++ 0xa0, 0x75, 0xbc, 0x3b, 0x82, 0xc6, 0x3f, 0xb8, ++ 0x83, 0x19, 0x6e, 0xd6, 0x37, 0xfe, 0x6e, 0x8a, ++ 0x4e, 0xe0, 0x4a, 0xab, 0x7b, 0xc8, 0xb4, 0x1d, ++ 0xf4, 0xed, 0x27, 0x03, 0x65, 0xa2, 0xa1, 0xae, ++ 0x11, 0xe7, 0x98, 0x78, 0x48, 0x91, 0xd2, 0xd2, ++ 0xd4, 0x23, 0x78, 0x50, 0xb1, 0x5b, 0x85, 0x10, ++ 0x8d, 0xca, 0x5f, 0x0f, 0x71, 0xae, 0x72, 0x9a, ++ 0xf6, 0x25, 0x19, 0x60, 0x06, 0xf7, 0x10, 0x34, ++ 0x18, 0x0d, 0xc9, 0x9f, 0x7b, 0x0c, 0x9b, 0x8f, ++ 0x91, 0x1b, 0x9f, 0xcd, 0x10, 0xee, 0x75, 0xf9, ++ 0x97, 0x66, 0xfc, 0x4d, 0x33, 0x6e, 0x28, 0x2b, ++ 0x92, 0x85, 0x4f, 0xab, 0x43, 0x8d, 0x8f, 0x7d, ++ 0x86, 0xa7, 0xc7, 0xd8, 0xd3, 0x0b, 0x8b, 0x57, ++ 0xb6, 0x1d, 0x95, 0x0d, 0xe9, 0xbc, 0xd9, 0x03, ++ 0xd9, 0x10, 0x19, 0xc3, 0x46, 0x63, 0x55, 0x87, ++ 0x61, 0x79, 0x6c, 0x95, 0x0e, 0x9c, 0xdd, 0xca, ++ 0xc3, 0xf3, 0x64, 0xf0, 0x7d, 0x76, 0xb7, 0x53, ++ 0x67, 0x2b, 0x1e, 0x44, 0x56, 0x81, 0xea, 0x8f, ++ 0x5c, 0x42, 0x16, 0xb8, 0x28, 0xeb, 0x1b, 0x61, ++ 0x10, 0x1e, 0xbf, 0xec, 0xa8 ++}; ++static const u8 enc_output011[] __initconst = { ++ 0x6a, 0xfc, 0x4b, 0x25, 0xdf, 0xc0, 0xe4, 0xe8, ++ 0x17, 0x4d, 0x4c, 0xc9, 0x7e, 0xde, 0x3a, 0xcc, ++ 0x3c, 0xba, 0x6a, 0x77, 0x47, 0xdb, 0xe3, 0x74, ++ 0x7a, 0x4d, 0x5f, 0x8d, 0x37, 0x55, 0x80, 0x73, ++ 0x90, 0x66, 0x5d, 0x3a, 0x7d, 0x5d, 0x86, 0x5e, ++ 0x8d, 0xfd, 0x83, 0xff, 0x4e, 0x74, 0x6f, 0xf9, ++ 0xe6, 0x70, 0x17, 0x70, 0x3e, 0x96, 0xa7, 0x7e, ++ 0xcb, 0xab, 0x8f, 0x58, 0x24, 0x9b, 0x01, 0xfd, ++ 0xcb, 0xe6, 0x4d, 0x9b, 0xf0, 0x88, 0x94, 0x57, ++ 0x66, 0xef, 0x72, 0x4c, 0x42, 0x6e, 0x16, 0x19, ++ 0x15, 0xea, 0x70, 0x5b, 0xac, 0x13, 0xdb, 0x9f, ++ 0x18, 0xe2, 0x3c, 0x26, 0x97, 0xbc, 0xdc, 0x45, ++ 0x8c, 0x6c, 0x24, 0x69, 0x9c, 0xf7, 0x65, 0x1e, ++ 0x18, 0x59, 0x31, 0x7c, 0xe4, 0x73, 0xbc, 0x39, ++ 0x62, 0xc6, 0x5c, 0x9f, 0xbf, 0xfa, 0x90, 0x03, ++ 0xc9, 0x72, 0x26, 0xb6, 0x1b, 0xc2, 0xb7, 0x3f, ++ 0xf2, 0x13, 0x77, 0xf2, 0x8d, 0xb9, 0x47, 0xd0, ++ 0x53, 0xdd, 0xc8, 0x91, 0x83, 0x8b, 0xb1, 0xce, ++ 0xa3, 0xfe, 0xcd, 0xd9, 0xdd, 0x92, 0x7b, 0xdb, ++ 0xb8, 0xfb, 0xc9, 0x2d, 0x01, 0x59, 0x39, 0x52, ++ 0xad, 0x1b, 0xec, 0xcf, 0xd7, 0x70, 0x13, 0x21, ++ 0xf5, 0x47, 0xaa, 0x18, 0x21, 0x5c, 0xc9, 0x9a, ++ 0xd2, 0x6b, 0x05, 0x9c, 0x01, 0xa1, 0xda, 0x35, ++ 0x5d, 0xb3, 0x70, 0xe6, 0xa9, 0x80, 0x8b, 0x91, ++ 0xb7, 0xb3, 0x5f, 0x24, 0x9a, 0xb7, 0xd1, 0x6b, ++ 0xa1, 0x1c, 0x50, 0xba, 0x49, 0xe0, 0xee, 0x2e, ++ 0x75, 0xac, 0x69, 0xc0, 0xeb, 0x03, 0xdd, 0x19, ++ 0xe5, 0xf6, 0x06, 0xdd, 0xc3, 0xd7, 0x2b, 0x07, ++ 0x07, 0x30, 0xa7, 0x19, 0x0c, 0xbf, 0xe6, 0x18, ++ 0xcc, 0xb1, 0x01, 0x11, 0x85, 0x77, 0x1d, 0x96, ++ 0xa7, 0xa3, 0x00, 0x84, 0x02, 0xa2, 0x83, 0x68, ++ 0xda, 0x17, 0x27, 0xc8, 0x7f, 0x23, 0xb7, 0xf4, ++ 0x13, 0x85, 0xcf, 0xdd, 0x7a, 0x7d, 0x24, 0x57, ++ 0xfe, 0x05, 0x93, 0xf5, 0x74, 0xce, 0xed, 0x0c, ++ 0x20, 0x98, 0x8d, 0x92, 0x30, 0xa1, 0x29, 0x23, ++ 0x1a, 0xa0, 0x4f, 0x69, 0x56, 0x4c, 0xe1, 0xc8, ++ 0xce, 0xf6, 0x9a, 0x0c, 0xa4, 0xfa, 0x04, 0xf6, ++ 0x62, 0x95, 0xf2, 0xfa, 0xc7, 0x40, 0x68, 0x40, ++ 0x8f, 0x41, 0xda, 0xb4, 0x26, 0x6f, 0x70, 0xab, ++ 0x40, 0x61, 0xa4, 0x0e, 0x75, 0xfb, 0x86, 0xeb, ++ 0x9d, 0x9a, 0x1f, 0xec, 0x76, 0x99, 0xe7, 0xea, ++ 0xaa, 0x1e, 0x2d, 0xb5, 0xd4, 0xa6, 0x1a, 0xb8, ++ 0x61, 0x0a, 0x1d, 0x16, 0x5b, 0x98, 0xc2, 0x31, ++ 0x40, 0xe7, 0x23, 0x1d, 0x66, 0x99, 0xc8, 0xc0, ++ 0xd7, 0xce, 0xf3, 0x57, 0x40, 0x04, 0x3f, 0xfc, ++ 0xea, 0xb3, 0xfc, 0xd2, 0xd3, 0x99, 0xa4, 0x94, ++ 0x69, 0xa0, 0xef, 0xd1, 0x85, 0xb3, 0xa6, 0xb1, ++ 0x28, 0xbf, 0x94, 0x67, 0x22, 0xc3, 0x36, 0x46, ++ 0xf8, 0xd2, 0x0f, 0x5f, 0xf4, 0x59, 0x80, 0xe6, ++ 0x2d, 0x43, 0x08, 0x7d, 0x19, 0x09, 0x97, 0xa7, ++ 0x4c, 0x3d, 0x8d, 0xba, 0x65, 0x62, 0xa3, 0x71, ++ 0x33, 0x29, 0x62, 0xdb, 0xc1, 0x33, 0x34, 0x1a, ++ 0x63, 0x33, 0x16, 0xb6, 0x64, 0x7e, 0xab, 0x33, ++ 0xf0, 0xe6, 0x26, 0x68, 0xba, 0x1d, 0x2e, 0x38, ++ 0x08, 0xe6, 0x02, 0xd3, 0x25, 0x2c, 0x47, 0x23, ++ 0x58, 0x34, 0x0f, 0x9d, 0x63, 0x4f, 0x63, 0xbb, ++ 0x7f, 0x3b, 0x34, 0x38, 0xa7, 0xb5, 0x8d, 0x65, ++ 0xd9, 0x9f, 0x79, 0x55, 0x3e, 0x4d, 0xe7, 0x73, ++ 0xd8, 0xf6, 0x98, 0x97, 0x84, 0x60, 0x9c, 0xc8, ++ 0xa9, 0x3c, 0xf6, 0xdc, 0x12, 0x5c, 0xe1, 0xbb, ++ 0x0b, 0x8b, 0x98, 0x9c, 0x9d, 0x26, 0x7c, 0x4a, ++ 0xe6, 0x46, 0x36, 0x58, 0x21, 0x4a, 0xee, 0xca, ++ 0xd7, 0x3b, 0xc2, 0x6c, 0x49, 0x2f, 0xe5, 0xd5, ++ 0x03, 0x59, 0x84, 0x53, 0xcb, 0xfe, 0x92, 0x71, ++ 0x2e, 0x7c, 0x21, 0xcc, 0x99, 0x85, 0x7f, 0xb8, ++ 0x74, 0x90, 0x13, 0x42, 0x3f, 0xe0, 0x6b, 0x1d, ++ 0xf2, 0x4d, 0x54, 0xd4, 0xfc, 0x3a, 0x05, 0xe6, ++ 0x74, 0xaf, 0xa6, 0xa0, 0x2a, 0x20, 0x23, 0x5d, ++ 0x34, 0x5c, 0xd9, 0x3e, 0x4e, 0xfa, 0x93, 0xe7, ++ 0xaa, 0xe9, 0x6f, 0x08, 0x43, 0x67, 0x41, 0xc5, ++ 0xad, 0xfb, 0x31, 0x95, 0x82, 0x73, 0x32, 0xd8, ++ 0xa6, 0xa3, 0xed, 0x0e, 0x2d, 0xf6, 0x5f, 0xfd, ++ 0x80, 0xa6, 0x7a, 0xe0, 0xdf, 0x78, 0x15, 0x29, ++ 0x74, 0x33, 0xd0, 0x9e, 0x83, 0x86, 0x72, 0x22, ++ 0x57, 0x29, 0xb9, 0x9e, 0x5d, 0xd3, 0x1a, 0xb5, ++ 0x96, 0x72, 0x41, 0x3d, 0xf1, 0x64, 0x43, 0x67, ++ 0xee, 0xaa, 0x5c, 0xd3, 0x9a, 0x96, 0x13, 0x11, ++ 0x5d, 0xf3, 0x0c, 0x87, 0x82, 0x1e, 0x41, 0x9e, ++ 0xd0, 0x27, 0xd7, 0x54, 0x3b, 0x67, 0x73, 0x09, ++ 0x91, 0xe9, 0xd5, 0x36, 0xa7, 0xb5, 0x55, 0xe4, ++ 0xf3, 0x21, 0x51, 0x49, 0x22, 0x07, 0x55, 0x4f, ++ 0x44, 0x4b, 0xd2, 0x15, 0x93, 0x17, 0x2a, 0xfa, ++ 0x4d, 0x4a, 0x57, 0xdb, 0x4c, 0xa6, 0xeb, 0xec, ++ 0x53, 0x25, 0x6c, 0x21, 0xed, 0x00, 0x4c, 0x3b, ++ 0xca, 0x14, 0x57, 0xa9, 0xd6, 0x6a, 0xcd, 0x8d, ++ 0x5e, 0x74, 0xac, 0x72, 0xc1, 0x97, 0xe5, 0x1b, ++ 0x45, 0x4e, 0xda, 0xfc, 0xcc, 0x40, 0xe8, 0x48, ++ 0x88, 0x0b, 0xa3, 0xe3, 0x8d, 0x83, 0x42, 0xc3, ++ 0x23, 0xfd, 0x68, 0xb5, 0x8e, 0xf1, 0x9d, 0x63, ++ 0x77, 0xe9, 0xa3, 0x8e, 0x8c, 0x26, 0x6b, 0xbd, ++ 0x72, 0x73, 0x35, 0x0c, 0x03, 0xf8, 0x43, 0x78, ++ 0x52, 0x71, 0x15, 0x1f, 0x71, 0x5d, 0x6e, 0xed, ++ 0xb9, 0xcc, 0x86, 0x30, 0xdb, 0x2b, 0xd3, 0x82, ++ 0x88, 0x23, 0x71, 0x90, 0x53, 0x5c, 0xa9, 0x2f, ++ 0x76, 0x01, 0xb7, 0x9a, 0xfe, 0x43, 0x55, 0xa3, ++ 0x04, 0x9b, 0x0e, 0xe4, 0x59, 0xdf, 0xc9, 0xe9, ++ 0xb1, 0xea, 0x29, 0x28, 0x3c, 0x5c, 0xae, 0x72, ++ 0x84, 0xb6, 0xc6, 0xeb, 0x0c, 0x27, 0x07, 0x74, ++ 0x90, 0x0d, 0x31, 0xb0, 0x00, 0x77, 0xe9, 0x40, ++ 0x70, 0x6f, 0x68, 0xa7, 0xfd, 0x06, 0xec, 0x4b, ++ 0xc0, 0xb7, 0xac, 0xbc, 0x33, 0xb7, 0x6d, 0x0a, ++ 0xbd, 0x12, 0x1b, 0x59, 0xcb, 0xdd, 0x32, 0xf5, ++ 0x1d, 0x94, 0x57, 0x76, 0x9e, 0x0c, 0x18, 0x98, ++ 0x71, 0xd7, 0x2a, 0xdb, 0x0b, 0x7b, 0xa7, 0x71, ++ 0xb7, 0x67, 0x81, 0x23, 0x96, 0xae, 0xb9, 0x7e, ++ 0x32, 0x43, 0x92, 0x8a, 0x19, 0xa0, 0xc4, 0xd4, ++ 0x3b, 0x57, 0xf9, 0x4a, 0x2c, 0xfb, 0x51, 0x46, ++ 0xbb, 0xcb, 0x5d, 0xb3, 0xef, 0x13, 0x93, 0x6e, ++ 0x68, 0x42, 0x54, 0x57, 0xd3, 0x6a, 0x3a, 0x8f, ++ 0x9d, 0x66, 0xbf, 0xbd, 0x36, 0x23, 0xf5, 0x93, ++ 0x83, 0x7b, 0x9c, 0xc0, 0xdd, 0xc5, 0x49, 0xc0, ++ 0x64, 0xed, 0x07, 0x12, 0xb3, 0xe6, 0xe4, 0xe5, ++ 0x38, 0x95, 0x23, 0xb1, 0xa0, 0x3b, 0x1a, 0x61, ++ 0xda, 0x17, 0xac, 0xc3, 0x58, 0xdd, 0x74, 0x64, ++ 0x22, 0x11, 0xe8, 0x32, 0x1d, 0x16, 0x93, 0x85, ++ 0x99, 0xa5, 0x9c, 0x34, 0x55, 0xb1, 0xe9, 0x20, ++ 0x72, 0xc9, 0x28, 0x7b, 0x79, 0x00, 0xa1, 0xa6, ++ 0xa3, 0x27, 0x40, 0x18, 0x8a, 0x54, 0xe0, 0xcc, ++ 0xe8, 0x4e, 0x8e, 0x43, 0x96, 0xe7, 0x3f, 0xc8, ++ 0xe9, 0xb2, 0xf9, 0xc9, 0xda, 0x04, 0x71, 0x50, ++ 0x47, 0xe4, 0xaa, 0xce, 0xa2, 0x30, 0xc8, 0xe4, ++ 0xac, 0xc7, 0x0d, 0x06, 0x2e, 0xe6, 0xe8, 0x80, ++ 0x36, 0x29, 0x9e, 0x01, 0xb8, 0xc3, 0xf0, 0xa0, ++ 0x5d, 0x7a, 0xca, 0x4d, 0xa0, 0x57, 0xbd, 0x2a, ++ 0x45, 0xa7, 0x7f, 0x9c, 0x93, 0x07, 0x8f, 0x35, ++ 0x67, 0x92, 0xe3, 0xe9, 0x7f, 0xa8, 0x61, 0x43, ++ 0x9e, 0x25, 0x4f, 0x33, 0x76, 0x13, 0x6e, 0x12, ++ 0xb9, 0xdd, 0xa4, 0x7c, 0x08, 0x9f, 0x7c, 0xe7, ++ 0x0a, 0x8d, 0x84, 0x06, 0xa4, 0x33, 0x17, 0x34, ++ 0x5e, 0x10, 0x7c, 0xc0, 0xa8, 0x3d, 0x1f, 0x42, ++ 0x20, 0x51, 0x65, 0x5d, 0x09, 0xc3, 0xaa, 0xc0, ++ 0xc8, 0x0d, 0xf0, 0x79, 0xbc, 0x20, 0x1b, 0x95, ++ 0xe7, 0x06, 0x7d, 0x47, 0x20, 0x03, 0x1a, 0x74, ++ 0xdd, 0xe2, 0xd4, 0xae, 0x38, 0x71, 0x9b, 0xf5, ++ 0x80, 0xec, 0x08, 0x4e, 0x56, 0xba, 0x76, 0x12, ++ 0x1a, 0xdf, 0x48, 0xf3, 0xae, 0xb3, 0xe6, 0xe6, ++ 0xbe, 0xc0, 0x91, 0x2e, 0x01, 0xb3, 0x01, 0x86, ++ 0xa2, 0xb9, 0x52, 0xd1, 0x21, 0xae, 0xd4, 0x97, ++ 0x1d, 0xef, 0x41, 0x12, 0x95, 0x3d, 0x48, 0x45, ++ 0x1c, 0x56, 0x32, 0x8f, 0xb8, 0x43, 0xbb, 0x19, ++ 0xf3, 0xca, 0xe9, 0xeb, 0x6d, 0x84, 0xbe, 0x86, ++ 0x06, 0xe2, 0x36, 0xb2, 0x62, 0x9d, 0xd3, 0x4c, ++ 0x48, 0x18, 0x54, 0x13, 0x4e, 0xcf, 0xfd, 0xba, ++ 0x84, 0xb9, 0x30, 0x53, 0xcf, 0xfb, 0xb9, 0x29, ++ 0x8f, 0xdc, 0x9f, 0xef, 0x60, 0x0b, 0x64, 0xf6, ++ 0x8b, 0xee, 0xa6, 0x91, 0xc2, 0x41, 0x6c, 0xf6, ++ 0xfa, 0x79, 0x67, 0x4b, 0xc1, 0x3f, 0xaf, 0x09, ++ 0x81, 0xd4, 0x5d, 0xcb, 0x09, 0xdf, 0x36, 0x31, ++ 0xc0, 0x14, 0x3c, 0x7c, 0x0e, 0x65, 0x95, 0x99, ++ 0x6d, 0xa3, 0xf4, 0xd7, 0x38, 0xee, 0x1a, 0x2b, ++ 0x37, 0xe2, 0xa4, 0x3b, 0x4b, 0xd0, 0x65, 0xca, ++ 0xf8, 0xc3, 0xe8, 0x15, 0x20, 0xef, 0xf2, 0x00, ++ 0xfd, 0x01, 0x09, 0xc5, 0xc8, 0x17, 0x04, 0x93, ++ 0xd0, 0x93, 0x03, 0x55, 0xc5, 0xfe, 0x32, 0xa3, ++ 0x3e, 0x28, 0x2d, 0x3b, 0x93, 0x8a, 0xcc, 0x07, ++ 0x72, 0x80, 0x8b, 0x74, 0x16, 0x24, 0xbb, 0xda, ++ 0x94, 0x39, 0x30, 0x8f, 0xb1, 0xcd, 0x4a, 0x90, ++ 0x92, 0x7c, 0x14, 0x8f, 0x95, 0x4e, 0xac, 0x9b, ++ 0xd8, 0x8f, 0x1a, 0x87, 0xa4, 0x32, 0x27, 0x8a, ++ 0xba, 0xf7, 0x41, 0xcf, 0x84, 0x37, 0x19, 0xe6, ++ 0x06, 0xf5, 0x0e, 0xcf, 0x36, 0xf5, 0x9e, 0x6c, ++ 0xde, 0xbc, 0xff, 0x64, 0x7e, 0x4e, 0x59, 0x57, ++ 0x48, 0xfe, 0x14, 0xf7, 0x9c, 0x93, 0x5d, 0x15, ++ 0xad, 0xcc, 0x11, 0xb1, 0x17, 0x18, 0xb2, 0x7e, ++ 0xcc, 0xab, 0xe9, 0xce, 0x7d, 0x77, 0x5b, 0x51, ++ 0x1b, 0x1e, 0x20, 0xa8, 0x32, 0x06, 0x0e, 0x75, ++ 0x93, 0xac, 0xdb, 0x35, 0x37, 0x1f, 0xe9, 0x19, ++ 0x1d, 0xb4, 0x71, 0x97, 0xd6, 0x4e, 0x2c, 0x08, ++ 0xa5, 0x13, 0xf9, 0x0e, 0x7e, 0x78, 0x6e, 0x14, ++ 0xe0, 0xa9, 0xb9, 0x96, 0x4c, 0x80, 0x82, 0xba, ++ 0x17, 0xb3, 0x9d, 0x69, 0xb0, 0x84, 0x46, 0xff, ++ 0xf9, 0x52, 0x79, 0x94, 0x58, 0x3a, 0x62, 0x90, ++ 0x15, 0x35, 0x71, 0x10, 0x37, 0xed, 0xa1, 0x8e, ++ 0x53, 0x6e, 0xf4, 0x26, 0x57, 0x93, 0x15, 0x93, ++ 0xf6, 0x81, 0x2c, 0x5a, 0x10, 0xda, 0x92, 0xad, ++ 0x2f, 0xdb, 0x28, 0x31, 0x2d, 0x55, 0x04, 0xd2, ++ 0x06, 0x28, 0x8c, 0x1e, 0xdc, 0xea, 0x54, 0xac, ++ 0xff, 0xb7, 0x6c, 0x30, 0x15, 0xd4, 0xb4, 0x0d, ++ 0x00, 0x93, 0x57, 0xdd, 0xd2, 0x07, 0x07, 0x06, ++ 0xd9, 0x43, 0x9b, 0xcd, 0x3a, 0xf4, 0x7d, 0x4c, ++ 0x36, 0x5d, 0x23, 0xa2, 0xcc, 0x57, 0x40, 0x91, ++ 0xe9, 0x2c, 0x2f, 0x2c, 0xd5, 0x30, 0x9b, 0x17, ++ 0xb0, 0xc9, 0xf7, 0xa7, 0x2f, 0xd1, 0x93, 0x20, ++ 0x6b, 0xc6, 0xc1, 0xe4, 0x6f, 0xcb, 0xd1, 0xe7, ++ 0x09, 0x0f, 0x9e, 0xdc, 0xaa, 0x9f, 0x2f, 0xdf, ++ 0x56, 0x9f, 0xd4, 0x33, 0x04, 0xaf, 0xd3, 0x6c, ++ 0x58, 0x61, 0xf0, 0x30, 0xec, 0xf2, 0x7f, 0xf2, ++ 0x9c, 0xdf, 0x39, 0xbb, 0x6f, 0xa2, 0x8c, 0x7e, ++ 0xc4, 0x22, 0x51, 0x71, 0xc0, 0x4d, 0x14, 0x1a, ++ 0xc4, 0xcd, 0x04, 0xd9, 0x87, 0x08, 0x50, 0x05, ++ 0xcc, 0xaf, 0xf6, 0xf0, 0x8f, 0x92, 0x54, 0x58, ++ 0xc2, 0xc7, 0x09, 0x7a, 0x59, 0x02, 0x05, 0xe8, ++ 0xb0, 0x86, 0xd9, 0xbf, 0x7b, 0x35, 0x51, 0x4d, ++ 0xaf, 0x08, 0x97, 0x2c, 0x65, 0xda, 0x2a, 0x71, ++ 0x3a, 0xa8, 0x51, 0xcc, 0xf2, 0x73, 0x27, 0xc3, ++ 0xfd, 0x62, 0xcf, 0xe3, 0xb2, 0xca, 0xcb, 0xbe, ++ 0x1a, 0x0a, 0xa1, 0x34, 0x7b, 0x77, 0xc4, 0x62, ++ 0x68, 0x78, 0x5f, 0x94, 0x07, 0x04, 0x65, 0x16, ++ 0x4b, 0x61, 0xcb, 0xff, 0x75, 0x26, 0x50, 0x66, ++ 0x1f, 0x6e, 0x93, 0xf8, 0xc5, 0x51, 0xeb, 0xa4, ++ 0x4a, 0x48, 0x68, 0x6b, 0xe2, 0x5e, 0x44, 0xb2, ++ 0x50, 0x2c, 0x6c, 0xae, 0x79, 0x4e, 0x66, 0x35, ++ 0x81, 0x50, 0xac, 0xbc, 0x3f, 0xb1, 0x0c, 0xf3, ++ 0x05, 0x3c, 0x4a, 0xa3, 0x6c, 0x2a, 0x79, 0xb4, ++ 0xb7, 0xab, 0xca, 0xc7, 0x9b, 0x8e, 0xcd, 0x5f, ++ 0x11, 0x03, 0xcb, 0x30, 0xa3, 0xab, 0xda, 0xfe, ++ 0x64, 0xb9, 0xbb, 0xd8, 0x5e, 0x3a, 0x1a, 0x56, ++ 0xe5, 0x05, 0x48, 0x90, 0x1e, 0x61, 0x69, 0x1b, ++ 0x22, 0xe6, 0x1a, 0x3c, 0x75, 0xad, 0x1f, 0x37, ++ 0x28, 0xdc, 0xe4, 0x6d, 0xbd, 0x42, 0xdc, 0xd3, ++ 0xc8, 0xb6, 0x1c, 0x48, 0xfe, 0x94, 0x77, 0x7f, ++ 0xbd, 0x62, 0xac, 0xa3, 0x47, 0x27, 0xcf, 0x5f, ++ 0xd9, 0xdb, 0xaf, 0xec, 0xf7, 0x5e, 0xc1, 0xb0, ++ 0x9d, 0x01, 0x26, 0x99, 0x7e, 0x8f, 0x03, 0x70, ++ 0xb5, 0x42, 0xbe, 0x67, 0x28, 0x1b, 0x7c, 0xbd, ++ 0x61, 0x21, 0x97, 0xcc, 0x5c, 0xe1, 0x97, 0x8f, ++ 0x8d, 0xde, 0x2b, 0xaa, 0xa7, 0x71, 0x1d, 0x1e, ++ 0x02, 0x73, 0x70, 0x58, 0x32, 0x5b, 0x1d, 0x67, ++ 0x3d, 0xe0, 0x74, 0x4f, 0x03, 0xf2, 0x70, 0x51, ++ 0x79, 0xf1, 0x61, 0x70, 0x15, 0x74, 0x9d, 0x23, ++ 0x89, 0xde, 0xac, 0xfd, 0xde, 0xd0, 0x1f, 0xc3, ++ 0x87, 0x44, 0x35, 0x4b, 0xe5, 0xb0, 0x60, 0xc5, ++ 0x22, 0xe4, 0x9e, 0xca, 0xeb, 0xd5, 0x3a, 0x09, ++ 0x45, 0xa4, 0xdb, 0xfa, 0x3f, 0xeb, 0x1b, 0xc7, ++ 0xc8, 0x14, 0x99, 0x51, 0x92, 0x10, 0xed, 0xed, ++ 0x28, 0xe0, 0xa1, 0xf8, 0x26, 0xcf, 0xcd, 0xcb, ++ 0x63, 0xa1, 0x3b, 0xe3, 0xdf, 0x7e, 0xfe, 0xa6, ++ 0xf0, 0x81, 0x9a, 0xbf, 0x55, 0xde, 0x54, 0xd5, ++ 0x56, 0x60, 0x98, 0x10, 0x68, 0xf4, 0x38, 0x96, ++ 0x8e, 0x6f, 0x1d, 0x44, 0x7f, 0xd6, 0x2f, 0xfe, ++ 0x55, 0xfb, 0x0c, 0x7e, 0x67, 0xe2, 0x61, 0x44, ++ 0xed, 0xf2, 0x35, 0x30, 0x5d, 0xe9, 0xc7, 0xd6, ++ 0x6d, 0xe0, 0xa0, 0xed, 0xf3, 0xfc, 0xd8, 0x3e, ++ 0x0a, 0x7b, 0xcd, 0xaf, 0x65, 0x68, 0x18, 0xc0, ++ 0xec, 0x04, 0x1c, 0x74, 0x6d, 0xe2, 0x6e, 0x79, ++ 0xd4, 0x11, 0x2b, 0x62, 0xd5, 0x27, 0xad, 0x4f, ++ 0x01, 0x59, 0x73, 0xcc, 0x6a, 0x53, 0xfb, 0x2d, ++ 0xd5, 0x4e, 0x99, 0x21, 0x65, 0x4d, 0xf5, 0x82, ++ 0xf7, 0xd8, 0x42, 0xce, 0x6f, 0x3d, 0x36, 0x47, ++ 0xf1, 0x05, 0x16, 0xe8, 0x1b, 0x6a, 0x8f, 0x93, ++ 0xf2, 0x8f, 0x37, 0x40, 0x12, 0x28, 0xa3, 0xe6, ++ 0xb9, 0x17, 0x4a, 0x1f, 0xb1, 0xd1, 0x66, 0x69, ++ 0x86, 0xc4, 0xfc, 0x97, 0xae, 0x3f, 0x8f, 0x1e, ++ 0x2b, 0xdf, 0xcd, 0xf9, 0x3c ++}; ++static const u8 enc_assoc011[] __initconst = { ++ 0xd6, 0x31, 0xda, 0x5d, 0x42, 0x5e, 0xd7 ++}; ++static const u8 enc_nonce011[] __initconst = { ++ 0xfd, 0x87, 0xd4, 0xd8, 0x62, 0xfd, 0xec, 0xaa ++}; ++static const u8 enc_key011[] __initconst = { ++ 0x35, 0x4e, 0xb5, 0x70, 0x50, 0x42, 0x8a, 0x85, ++ 0xf2, 0xfb, 0xed, 0x7b, 0xd0, 0x9e, 0x97, 0xca, ++ 0xfa, 0x98, 0x66, 0x63, 0xee, 0x37, 0xcc, 0x52, ++ 0xfe, 0xd1, 0xdf, 0x95, 0x15, 0x34, 0x29, 0x38 ++}; ++ ++static const u8 enc_input012[] __initconst = { ++ 0x74, 0xa6, 0x3e, 0xe4, 0xb1, 0xcb, 0xaf, 0xb0, ++ 0x40, 0xe5, 0x0f, 0x9e, 0xf1, 0xf2, 0x89, 0xb5, ++ 0x42, 0x34, 0x8a, 0xa1, 0x03, 0xb7, 0xe9, 0x57, ++ 0x46, 0xbe, 0x20, 0xe4, 0x6e, 0xb0, 0xeb, 0xff, ++ 0xea, 0x07, 0x7e, 0xef, 0xe2, 0x55, 0x9f, 0xe5, ++ 0x78, 0x3a, 0xb7, 0x83, 0xc2, 0x18, 0x40, 0x7b, ++ 0xeb, 0xcd, 0x81, 0xfb, 0x90, 0x12, 0x9e, 0x46, ++ 0xa9, 0xd6, 0x4a, 0xba, 0xb0, 0x62, 0xdb, 0x6b, ++ 0x99, 0xc4, 0xdb, 0x54, 0x4b, 0xb8, 0xa5, 0x71, ++ 0xcb, 0xcd, 0x63, 0x32, 0x55, 0xfb, 0x31, 0xf0, ++ 0x38, 0xf5, 0xbe, 0x78, 0xe4, 0x45, 0xce, 0x1b, ++ 0x6a, 0x5b, 0x0e, 0xf4, 0x16, 0xe4, 0xb1, 0x3d, ++ 0xf6, 0x63, 0x7b, 0xa7, 0x0c, 0xde, 0x6f, 0x8f, ++ 0x74, 0xdf, 0xe0, 0x1e, 0x9d, 0xce, 0x8f, 0x24, ++ 0xef, 0x23, 0x35, 0x33, 0x7b, 0x83, 0x34, 0x23, ++ 0x58, 0x74, 0x14, 0x77, 0x1f, 0xc2, 0x4f, 0x4e, ++ 0xc6, 0x89, 0xf9, 0x52, 0x09, 0x37, 0x64, 0x14, ++ 0xc4, 0x01, 0x6b, 0x9d, 0x77, 0xe8, 0x90, 0x5d, ++ 0xa8, 0x4a, 0x2a, 0xef, 0x5c, 0x7f, 0xeb, 0xbb, ++ 0xb2, 0xc6, 0x93, 0x99, 0x66, 0xdc, 0x7f, 0xd4, ++ 0x9e, 0x2a, 0xca, 0x8d, 0xdb, 0xe7, 0x20, 0xcf, ++ 0xe4, 0x73, 0xae, 0x49, 0x7d, 0x64, 0x0f, 0x0e, ++ 0x28, 0x46, 0xa9, 0xa8, 0x32, 0xe4, 0x0e, 0xf6, ++ 0x51, 0x53, 0xb8, 0x3c, 0xb1, 0xff, 0xa3, 0x33, ++ 0x41, 0x75, 0xff, 0xf1, 0x6f, 0xf1, 0xfb, 0xbb, ++ 0x83, 0x7f, 0x06, 0x9b, 0xe7, 0x1b, 0x0a, 0xe0, ++ 0x5c, 0x33, 0x60, 0x5b, 0xdb, 0x5b, 0xed, 0xfe, ++ 0xa5, 0x16, 0x19, 0x72, 0xa3, 0x64, 0x23, 0x00, ++ 0x02, 0xc7, 0xf3, 0x6a, 0x81, 0x3e, 0x44, 0x1d, ++ 0x79, 0x15, 0x5f, 0x9a, 0xde, 0xe2, 0xfd, 0x1b, ++ 0x73, 0xc1, 0xbc, 0x23, 0xba, 0x31, 0xd2, 0x50, ++ 0xd5, 0xad, 0x7f, 0x74, 0xa7, 0xc9, 0xf8, 0x3e, ++ 0x2b, 0x26, 0x10, 0xf6, 0x03, 0x36, 0x74, 0xe4, ++ 0x0e, 0x6a, 0x72, 0xb7, 0x73, 0x0a, 0x42, 0x28, ++ 0xc2, 0xad, 0x5e, 0x03, 0xbe, 0xb8, 0x0b, 0xa8, ++ 0x5b, 0xd4, 0xb8, 0xba, 0x52, 0x89, 0xb1, 0x9b, ++ 0xc1, 0xc3, 0x65, 0x87, 0xed, 0xa5, 0xf4, 0x86, ++ 0xfd, 0x41, 0x80, 0x91, 0x27, 0x59, 0x53, 0x67, ++ 0x15, 0x78, 0x54, 0x8b, 0x2d, 0x3d, 0xc7, 0xff, ++ 0x02, 0x92, 0x07, 0x5f, 0x7a, 0x4b, 0x60, 0x59, ++ 0x3c, 0x6f, 0x5c, 0xd8, 0xec, 0x95, 0xd2, 0xfe, ++ 0xa0, 0x3b, 0xd8, 0x3f, 0xd1, 0x69, 0xa6, 0xd6, ++ 0x41, 0xb2, 0xf4, 0x4d, 0x12, 0xf4, 0x58, 0x3e, ++ 0x66, 0x64, 0x80, 0x31, 0x9b, 0xa8, 0x4c, 0x8b, ++ 0x07, 0xb2, 0xec, 0x66, 0x94, 0x66, 0x47, 0x50, ++ 0x50, 0x5f, 0x18, 0x0b, 0x0e, 0xd6, 0xc0, 0x39, ++ 0x21, 0x13, 0x9e, 0x33, 0xbc, 0x79, 0x36, 0x02, ++ 0x96, 0x70, 0xf0, 0x48, 0x67, 0x2f, 0x26, 0xe9, ++ 0x6d, 0x10, 0xbb, 0xd6, 0x3f, 0xd1, 0x64, 0x7a, ++ 0x2e, 0xbe, 0x0c, 0x61, 0xf0, 0x75, 0x42, 0x38, ++ 0x23, 0xb1, 0x9e, 0x9f, 0x7c, 0x67, 0x66, 0xd9, ++ 0x58, 0x9a, 0xf1, 0xbb, 0x41, 0x2a, 0x8d, 0x65, ++ 0x84, 0x94, 0xfc, 0xdc, 0x6a, 0x50, 0x64, 0xdb, ++ 0x56, 0x33, 0x76, 0x00, 0x10, 0xed, 0xbe, 0xd2, ++ 0x12, 0xf6, 0xf6, 0x1b, 0xa2, 0x16, 0xde, 0xae, ++ 0x31, 0x95, 0xdd, 0xb1, 0x08, 0x7e, 0x4e, 0xee, ++ 0xe7, 0xf9, 0xa5, 0xfb, 0x5b, 0x61, 0x43, 0x00, ++ 0x40, 0xf6, 0x7e, 0x02, 0x04, 0x32, 0x4e, 0x0c, ++ 0xe2, 0x66, 0x0d, 0xd7, 0x07, 0x98, 0x0e, 0xf8, ++ 0x72, 0x34, 0x6d, 0x95, 0x86, 0xd7, 0xcb, 0x31, ++ 0x54, 0x47, 0xd0, 0x38, 0x29, 0x9c, 0x5a, 0x68, ++ 0xd4, 0x87, 0x76, 0xc9, 0xe7, 0x7e, 0xe3, 0xf4, ++ 0x81, 0x6d, 0x18, 0xcb, 0xc9, 0x05, 0xaf, 0xa0, ++ 0xfb, 0x66, 0xf7, 0xf1, 0x1c, 0xc6, 0x14, 0x11, ++ 0x4f, 0x2b, 0x79, 0x42, 0x8b, 0xbc, 0xac, 0xe7, ++ 0x6c, 0xfe, 0x0f, 0x58, 0xe7, 0x7c, 0x78, 0x39, ++ 0x30, 0xb0, 0x66, 0x2c, 0x9b, 0x6d, 0x3a, 0xe1, ++ 0xcf, 0xc9, 0xa4, 0x0e, 0x6d, 0x6d, 0x8a, 0xa1, ++ 0x3a, 0xe7, 0x28, 0xd4, 0x78, 0x4c, 0xa6, 0xa2, ++ 0x2a, 0xa6, 0x03, 0x30, 0xd7, 0xa8, 0x25, 0x66, ++ 0x87, 0x2f, 0x69, 0x5c, 0x4e, 0xdd, 0xa5, 0x49, ++ 0x5d, 0x37, 0x4a, 0x59, 0xc4, 0xaf, 0x1f, 0xa2, ++ 0xe4, 0xf8, 0xa6, 0x12, 0x97, 0xd5, 0x79, 0xf5, ++ 0xe2, 0x4a, 0x2b, 0x5f, 0x61, 0xe4, 0x9e, 0xe3, ++ 0xee, 0xb8, 0xa7, 0x5b, 0x2f, 0xf4, 0x9e, 0x6c, ++ 0xfb, 0xd1, 0xc6, 0x56, 0x77, 0xba, 0x75, 0xaa, ++ 0x3d, 0x1a, 0xa8, 0x0b, 0xb3, 0x68, 0x24, 0x00, ++ 0x10, 0x7f, 0xfd, 0xd7, 0xa1, 0x8d, 0x83, 0x54, ++ 0x4f, 0x1f, 0xd8, 0x2a, 0xbe, 0x8a, 0x0c, 0x87, ++ 0xab, 0xa2, 0xde, 0xc3, 0x39, 0xbf, 0x09, 0x03, ++ 0xa5, 0xf3, 0x05, 0x28, 0xe1, 0xe1, 0xee, 0x39, ++ 0x70, 0x9c, 0xd8, 0x81, 0x12, 0x1e, 0x02, 0x40, ++ 0xd2, 0x6e, 0xf0, 0xeb, 0x1b, 0x3d, 0x22, 0xc6, ++ 0xe5, 0xe3, 0xb4, 0x5a, 0x98, 0xbb, 0xf0, 0x22, ++ 0x28, 0x8d, 0xe5, 0xd3, 0x16, 0x48, 0x24, 0xa5, ++ 0xe6, 0x66, 0x0c, 0xf9, 0x08, 0xf9, 0x7e, 0x1e, ++ 0xe1, 0x28, 0x26, 0x22, 0xc7, 0xc7, 0x0a, 0x32, ++ 0x47, 0xfa, 0xa3, 0xbe, 0x3c, 0xc4, 0xc5, 0x53, ++ 0x0a, 0xd5, 0x94, 0x4a, 0xd7, 0x93, 0xd8, 0x42, ++ 0x99, 0xb9, 0x0a, 0xdb, 0x56, 0xf7, 0xb9, 0x1c, ++ 0x53, 0x4f, 0xfa, 0xd3, 0x74, 0xad, 0xd9, 0x68, ++ 0xf1, 0x1b, 0xdf, 0x61, 0xc6, 0x5e, 0xa8, 0x48, ++ 0xfc, 0xd4, 0x4a, 0x4c, 0x3c, 0x32, 0xf7, 0x1c, ++ 0x96, 0x21, 0x9b, 0xf9, 0xa3, 0xcc, 0x5a, 0xce, ++ 0xd5, 0xd7, 0x08, 0x24, 0xf6, 0x1c, 0xfd, 0xdd, ++ 0x38, 0xc2, 0x32, 0xe9, 0xb8, 0xe7, 0xb6, 0xfa, ++ 0x9d, 0x45, 0x13, 0x2c, 0x83, 0xfd, 0x4a, 0x69, ++ 0x82, 0xcd, 0xdc, 0xb3, 0x76, 0x0c, 0x9e, 0xd8, ++ 0xf4, 0x1b, 0x45, 0x15, 0xb4, 0x97, 0xe7, 0x58, ++ 0x34, 0xe2, 0x03, 0x29, 0x5a, 0xbf, 0xb6, 0xe0, ++ 0x5d, 0x13, 0xd9, 0x2b, 0xb4, 0x80, 0xb2, 0x45, ++ 0x81, 0x6a, 0x2e, 0x6c, 0x89, 0x7d, 0xee, 0xbb, ++ 0x52, 0xdd, 0x1f, 0x18, 0xe7, 0x13, 0x6b, 0x33, ++ 0x0e, 0xea, 0x36, 0x92, 0x77, 0x7b, 0x6d, 0x9c, ++ 0x5a, 0x5f, 0x45, 0x7b, 0x7b, 0x35, 0x62, 0x23, ++ 0xd1, 0xbf, 0x0f, 0xd0, 0x08, 0x1b, 0x2b, 0x80, ++ 0x6b, 0x7e, 0xf1, 0x21, 0x47, 0xb0, 0x57, 0xd1, ++ 0x98, 0x72, 0x90, 0x34, 0x1c, 0x20, 0x04, 0xff, ++ 0x3d, 0x5c, 0xee, 0x0e, 0x57, 0x5f, 0x6f, 0x24, ++ 0x4e, 0x3c, 0xea, 0xfc, 0xa5, 0xa9, 0x83, 0xc9, ++ 0x61, 0xb4, 0x51, 0x24, 0xf8, 0x27, 0x5e, 0x46, ++ 0x8c, 0xb1, 0x53, 0x02, 0x96, 0x35, 0xba, 0xb8, ++ 0x4c, 0x71, 0xd3, 0x15, 0x59, 0x35, 0x22, 0x20, ++ 0xad, 0x03, 0x9f, 0x66, 0x44, 0x3b, 0x9c, 0x35, ++ 0x37, 0x1f, 0x9b, 0xbb, 0xf3, 0xdb, 0x35, 0x63, ++ 0x30, 0x64, 0xaa, 0xa2, 0x06, 0xa8, 0x5d, 0xbb, ++ 0xe1, 0x9f, 0x70, 0xec, 0x82, 0x11, 0x06, 0x36, ++ 0xec, 0x8b, 0x69, 0x66, 0x24, 0x44, 0xc9, 0x4a, ++ 0x57, 0xbb, 0x9b, 0x78, 0x13, 0xce, 0x9c, 0x0c, ++ 0xba, 0x92, 0x93, 0x63, 0xb8, 0xe2, 0x95, 0x0f, ++ 0x0f, 0x16, 0x39, 0x52, 0xfd, 0x3a, 0x6d, 0x02, ++ 0x4b, 0xdf, 0x13, 0xd3, 0x2a, 0x22, 0xb4, 0x03, ++ 0x7c, 0x54, 0x49, 0x96, 0x68, 0x54, 0x10, 0xfa, ++ 0xef, 0xaa, 0x6c, 0xe8, 0x22, 0xdc, 0x71, 0x16, ++ 0x13, 0x1a, 0xf6, 0x28, 0xe5, 0x6d, 0x77, 0x3d, ++ 0xcd, 0x30, 0x63, 0xb1, 0x70, 0x52, 0xa1, 0xc5, ++ 0x94, 0x5f, 0xcf, 0xe8, 0xb8, 0x26, 0x98, 0xf7, ++ 0x06, 0xa0, 0x0a, 0x70, 0xfa, 0x03, 0x80, 0xac, ++ 0xc1, 0xec, 0xd6, 0x4c, 0x54, 0xd7, 0xfe, 0x47, ++ 0xb6, 0x88, 0x4a, 0xf7, 0x71, 0x24, 0xee, 0xf3, ++ 0xd2, 0xc2, 0x4a, 0x7f, 0xfe, 0x61, 0xc7, 0x35, ++ 0xc9, 0x37, 0x67, 0xcb, 0x24, 0x35, 0xda, 0x7e, ++ 0xca, 0x5f, 0xf3, 0x8d, 0xd4, 0x13, 0x8e, 0xd6, ++ 0xcb, 0x4d, 0x53, 0x8f, 0x53, 0x1f, 0xc0, 0x74, ++ 0xf7, 0x53, 0xb9, 0x5e, 0x23, 0x37, 0xba, 0x6e, ++ 0xe3, 0x9d, 0x07, 0x55, 0x25, 0x7b, 0xe6, 0x2a, ++ 0x64, 0xd1, 0x32, 0xdd, 0x54, 0x1b, 0x4b, 0xc0, ++ 0xe1, 0xd7, 0x69, 0x58, 0xf8, 0x93, 0x29, 0xc4, ++ 0xdd, 0x23, 0x2f, 0xa5, 0xfc, 0x9d, 0x7e, 0xf8, ++ 0xd4, 0x90, 0xcd, 0x82, 0x55, 0xdc, 0x16, 0x16, ++ 0x9f, 0x07, 0x52, 0x9b, 0x9d, 0x25, 0xed, 0x32, ++ 0xc5, 0x7b, 0xdf, 0xf6, 0x83, 0x46, 0x3d, 0x65, ++ 0xb7, 0xef, 0x87, 0x7a, 0x12, 0x69, 0x8f, 0x06, ++ 0x7c, 0x51, 0x15, 0x4a, 0x08, 0xe8, 0xac, 0x9a, ++ 0x0c, 0x24, 0xa7, 0x27, 0xd8, 0x46, 0x2f, 0xe7, ++ 0x01, 0x0e, 0x1c, 0xc6, 0x91, 0xb0, 0x6e, 0x85, ++ 0x65, 0xf0, 0x29, 0x0d, 0x2e, 0x6b, 0x3b, 0xfb, ++ 0x4b, 0xdf, 0xe4, 0x80, 0x93, 0x03, 0x66, 0x46, ++ 0x3e, 0x8a, 0x6e, 0xf3, 0x5e, 0x4d, 0x62, 0x0e, ++ 0x49, 0x05, 0xaf, 0xd4, 0xf8, 0x21, 0x20, 0x61, ++ 0x1d, 0x39, 0x17, 0xf4, 0x61, 0x47, 0x95, 0xfb, ++ 0x15, 0x2e, 0xb3, 0x4f, 0xd0, 0x5d, 0xf5, 0x7d, ++ 0x40, 0xda, 0x90, 0x3c, 0x6b, 0xcb, 0x17, 0x00, ++ 0x13, 0x3b, 0x64, 0x34, 0x1b, 0xf0, 0xf2, 0xe5, ++ 0x3b, 0xb2, 0xc7, 0xd3, 0x5f, 0x3a, 0x44, 0xa6, ++ 0x9b, 0xb7, 0x78, 0x0e, 0x42, 0x5d, 0x4c, 0xc1, ++ 0xe9, 0xd2, 0xcb, 0xb7, 0x78, 0xd1, 0xfe, 0x9a, ++ 0xb5, 0x07, 0xe9, 0xe0, 0xbe, 0xe2, 0x8a, 0xa7, ++ 0x01, 0x83, 0x00, 0x8c, 0x5c, 0x08, 0xe6, 0x63, ++ 0x12, 0x92, 0xb7, 0xb7, 0xa6, 0x19, 0x7d, 0x38, ++ 0x13, 0x38, 0x92, 0x87, 0x24, 0xf9, 0x48, 0xb3, ++ 0x5e, 0x87, 0x6a, 0x40, 0x39, 0x5c, 0x3f, 0xed, ++ 0x8f, 0xee, 0xdb, 0x15, 0x82, 0x06, 0xda, 0x49, ++ 0x21, 0x2b, 0xb5, 0xbf, 0x32, 0x7c, 0x9f, 0x42, ++ 0x28, 0x63, 0xcf, 0xaf, 0x1e, 0xf8, 0xc6, 0xa0, ++ 0xd1, 0x02, 0x43, 0x57, 0x62, 0xec, 0x9b, 0x0f, ++ 0x01, 0x9e, 0x71, 0xd8, 0x87, 0x9d, 0x01, 0xc1, ++ 0x58, 0x77, 0xd9, 0xaf, 0xb1, 0x10, 0x7e, 0xdd, ++ 0xa6, 0x50, 0x96, 0xe5, 0xf0, 0x72, 0x00, 0x6d, ++ 0x4b, 0xf8, 0x2a, 0x8f, 0x19, 0xf3, 0x22, 0x88, ++ 0x11, 0x4a, 0x8b, 0x7c, 0xfd, 0xb7, 0xed, 0xe1, ++ 0xf6, 0x40, 0x39, 0xe0, 0xe9, 0xf6, 0x3d, 0x25, ++ 0xe6, 0x74, 0x3c, 0x58, 0x57, 0x7f, 0xe1, 0x22, ++ 0x96, 0x47, 0x31, 0x91, 0xba, 0x70, 0x85, 0x28, ++ 0x6b, 0x9f, 0x6e, 0x25, 0xac, 0x23, 0x66, 0x2f, ++ 0x29, 0x88, 0x28, 0xce, 0x8c, 0x5c, 0x88, 0x53, ++ 0xd1, 0x3b, 0xcc, 0x6a, 0x51, 0xb2, 0xe1, 0x28, ++ 0x3f, 0x91, 0xb4, 0x0d, 0x00, 0x3a, 0xe3, 0xf8, ++ 0xc3, 0x8f, 0xd7, 0x96, 0x62, 0x0e, 0x2e, 0xfc, ++ 0xc8, 0x6c, 0x77, 0xa6, 0x1d, 0x22, 0xc1, 0xb8, ++ 0xe6, 0x61, 0xd7, 0x67, 0x36, 0x13, 0x7b, 0xbb, ++ 0x9b, 0x59, 0x09, 0xa6, 0xdf, 0xf7, 0x6b, 0xa3, ++ 0x40, 0x1a, 0xf5, 0x4f, 0xb4, 0xda, 0xd3, 0xf3, ++ 0x81, 0x93, 0xc6, 0x18, 0xd9, 0x26, 0xee, 0xac, ++ 0xf0, 0xaa, 0xdf, 0xc5, 0x9c, 0xca, 0xc2, 0xa2, ++ 0xcc, 0x7b, 0x5c, 0x24, 0xb0, 0xbc, 0xd0, 0x6a, ++ 0x4d, 0x89, 0x09, 0xb8, 0x07, 0xfe, 0x87, 0xad, ++ 0x0a, 0xea, 0xb8, 0x42, 0xf9, 0x5e, 0xb3, 0x3e, ++ 0x36, 0x4c, 0xaf, 0x75, 0x9e, 0x1c, 0xeb, 0xbd, ++ 0xbc, 0xbb, 0x80, 0x40, 0xa7, 0x3a, 0x30, 0xbf, ++ 0xa8, 0x44, 0xf4, 0xeb, 0x38, 0xad, 0x29, 0xba, ++ 0x23, 0xed, 0x41, 0x0c, 0xea, 0xd2, 0xbb, 0x41, ++ 0x18, 0xd6, 0xb9, 0xba, 0x65, 0x2b, 0xa3, 0x91, ++ 0x6d, 0x1f, 0xa9, 0xf4, 0xd1, 0x25, 0x8d, 0x4d, ++ 0x38, 0xff, 0x64, 0xa0, 0xec, 0xde, 0xa6, 0xb6, ++ 0x79, 0xab, 0x8e, 0x33, 0x6c, 0x47, 0xde, 0xaf, ++ 0x94, 0xa4, 0xa5, 0x86, 0x77, 0x55, 0x09, 0x92, ++ 0x81, 0x31, 0x76, 0xc7, 0x34, 0x22, 0x89, 0x8e, ++ 0x3d, 0x26, 0x26, 0xd7, 0xfc, 0x1e, 0x16, 0x72, ++ 0x13, 0x33, 0x63, 0xd5, 0x22, 0xbe, 0xb8, 0x04, ++ 0x34, 0x84, 0x41, 0xbb, 0x80, 0xd0, 0x9f, 0x46, ++ 0x48, 0x07, 0xa7, 0xfc, 0x2b, 0x3a, 0x75, 0x55, ++ 0x8c, 0xc7, 0x6a, 0xbd, 0x7e, 0x46, 0x08, 0x84, ++ 0x0f, 0xd5, 0x74, 0xc0, 0x82, 0x8e, 0xaa, 0x61, ++ 0x05, 0x01, 0xb2, 0x47, 0x6e, 0x20, 0x6a, 0x2d, ++ 0x58, 0x70, 0x48, 0x32, 0xa7, 0x37, 0xd2, 0xb8, ++ 0x82, 0x1a, 0x51, 0xb9, 0x61, 0xdd, 0xfd, 0x9d, ++ 0x6b, 0x0e, 0x18, 0x97, 0xf8, 0x45, 0x5f, 0x87, ++ 0x10, 0xcf, 0x34, 0x72, 0x45, 0x26, 0x49, 0x70, ++ 0xe7, 0xa3, 0x78, 0xe0, 0x52, 0x89, 0x84, 0x94, ++ 0x83, 0x82, 0xc2, 0x69, 0x8f, 0xe3, 0xe1, 0x3f, ++ 0x60, 0x74, 0x88, 0xc4, 0xf7, 0x75, 0x2c, 0xfb, ++ 0xbd, 0xb6, 0xc4, 0x7e, 0x10, 0x0a, 0x6c, 0x90, ++ 0x04, 0x9e, 0xc3, 0x3f, 0x59, 0x7c, 0xce, 0x31, ++ 0x18, 0x60, 0x57, 0x73, 0x46, 0x94, 0x7d, 0x06, ++ 0xa0, 0x6d, 0x44, 0xec, 0xa2, 0x0a, 0x9e, 0x05, ++ 0x15, 0xef, 0xca, 0x5c, 0xbf, 0x00, 0xeb, 0xf7, ++ 0x3d, 0x32, 0xd4, 0xa5, 0xef, 0x49, 0x89, 0x5e, ++ 0x46, 0xb0, 0xa6, 0x63, 0x5b, 0x8a, 0x73, 0xae, ++ 0x6f, 0xd5, 0x9d, 0xf8, 0x4f, 0x40, 0xb5, 0xb2, ++ 0x6e, 0xd3, 0xb6, 0x01, 0xa9, 0x26, 0xa2, 0x21, ++ 0xcf, 0x33, 0x7a, 0x3a, 0xa4, 0x23, 0x13, 0xb0, ++ 0x69, 0x6a, 0xee, 0xce, 0xd8, 0x9d, 0x01, 0x1d, ++ 0x50, 0xc1, 0x30, 0x6c, 0xb1, 0xcd, 0xa0, 0xf0, ++ 0xf0, 0xa2, 0x64, 0x6f, 0xbb, 0xbf, 0x5e, 0xe6, ++ 0xab, 0x87, 0xb4, 0x0f, 0x4f, 0x15, 0xaf, 0xb5, ++ 0x25, 0xa1, 0xb2, 0xd0, 0x80, 0x2c, 0xfb, 0xf9, ++ 0xfe, 0xd2, 0x33, 0xbb, 0x76, 0xfe, 0x7c, 0xa8, ++ 0x66, 0xf7, 0xe7, 0x85, 0x9f, 0x1f, 0x85, 0x57, ++ 0x88, 0xe1, 0xe9, 0x63, 0xe4, 0xd8, 0x1c, 0xa1, ++ 0xfb, 0xda, 0x44, 0x05, 0x2e, 0x1d, 0x3a, 0x1c, ++ 0xff, 0xc8, 0x3b, 0xc0, 0xfe, 0xda, 0x22, 0x0b, ++ 0x43, 0xd6, 0x88, 0x39, 0x4c, 0x4a, 0xa6, 0x69, ++ 0x18, 0x93, 0x42, 0x4e, 0xb5, 0xcc, 0x66, 0x0d, ++ 0x09, 0xf8, 0x1e, 0x7c, 0xd3, 0x3c, 0x99, 0x0d, ++ 0x50, 0x1d, 0x62, 0xe9, 0x57, 0x06, 0xbf, 0x19, ++ 0x88, 0xdd, 0xad, 0x7b, 0x4f, 0xf9, 0xc7, 0x82, ++ 0x6d, 0x8d, 0xc8, 0xc4, 0xc5, 0x78, 0x17, 0x20, ++ 0x15, 0xc5, 0x52, 0x41, 0xcf, 0x5b, 0xd6, 0x7f, ++ 0x94, 0x02, 0x41, 0xe0, 0x40, 0x22, 0x03, 0x5e, ++ 0xd1, 0x53, 0xd4, 0x86, 0xd3, 0x2c, 0x9f, 0x0f, ++ 0x96, 0xe3, 0x6b, 0x9a, 0x76, 0x32, 0x06, 0x47, ++ 0x4b, 0x11, 0xb3, 0xdd, 0x03, 0x65, 0xbd, 0x9b, ++ 0x01, 0xda, 0x9c, 0xb9, 0x7e, 0x3f, 0x6a, 0xc4, ++ 0x7b, 0xea, 0xd4, 0x3c, 0xb9, 0xfb, 0x5c, 0x6b, ++ 0x64, 0x33, 0x52, 0xba, 0x64, 0x78, 0x8f, 0xa4, ++ 0xaf, 0x7a, 0x61, 0x8d, 0xbc, 0xc5, 0x73, 0xe9, ++ 0x6b, 0x58, 0x97, 0x4b, 0xbf, 0x63, 0x22, 0xd3, ++ 0x37, 0x02, 0x54, 0xc5, 0xb9, 0x16, 0x4a, 0xf0, ++ 0x19, 0xd8, 0x94, 0x57, 0xb8, 0x8a, 0xb3, 0x16, ++ 0x3b, 0xd0, 0x84, 0x8e, 0x67, 0xa6, 0xa3, 0x7d, ++ 0x78, 0xec, 0x00 ++}; ++static const u8 enc_output012[] __initconst = { ++ 0x52, 0x34, 0xb3, 0x65, 0x3b, 0xb7, 0xe5, 0xd3, ++ 0xab, 0x49, 0x17, 0x60, 0xd2, 0x52, 0x56, 0xdf, ++ 0xdf, 0x34, 0x56, 0x82, 0xe2, 0xbe, 0xe5, 0xe1, ++ 0x28, 0xd1, 0x4e, 0x5f, 0x4f, 0x01, 0x7d, 0x3f, ++ 0x99, 0x6b, 0x30, 0x6e, 0x1a, 0x7c, 0x4c, 0x8e, ++ 0x62, 0x81, 0xae, 0x86, 0x3f, 0x6b, 0xd0, 0xb5, ++ 0xa9, 0xcf, 0x50, 0xf1, 0x02, 0x12, 0xa0, 0x0b, ++ 0x24, 0xe9, 0xe6, 0x72, 0x89, 0x2c, 0x52, 0x1b, ++ 0x34, 0x38, 0xf8, 0x75, 0x5f, 0xa0, 0x74, 0xe2, ++ 0x99, 0xdd, 0xa6, 0x4b, 0x14, 0x50, 0x4e, 0xf1, ++ 0xbe, 0xd6, 0x9e, 0xdb, 0xb2, 0x24, 0x27, 0x74, ++ 0x12, 0x4a, 0x78, 0x78, 0x17, 0xa5, 0x58, 0x8e, ++ 0x2f, 0xf9, 0xf4, 0x8d, 0xee, 0x03, 0x88, 0xae, ++ 0xb8, 0x29, 0xa1, 0x2f, 0x4b, 0xee, 0x92, 0xbd, ++ 0x87, 0xb3, 0xce, 0x34, 0x21, 0x57, 0x46, 0x04, ++ 0x49, 0x0c, 0x80, 0xf2, 0x01, 0x13, 0xa1, 0x55, ++ 0xb3, 0xff, 0x44, 0x30, 0x3c, 0x1c, 0xd0, 0xef, ++ 0xbc, 0x18, 0x74, 0x26, 0xad, 0x41, 0x5b, 0x5b, ++ 0x3e, 0x9a, 0x7a, 0x46, 0x4f, 0x16, 0xd6, 0x74, ++ 0x5a, 0xb7, 0x3a, 0x28, 0x31, 0xd8, 0xae, 0x26, ++ 0xac, 0x50, 0x53, 0x86, 0xf2, 0x56, 0xd7, 0x3f, ++ 0x29, 0xbc, 0x45, 0x68, 0x8e, 0xcb, 0x98, 0x64, ++ 0xdd, 0xc9, 0xba, 0xb8, 0x4b, 0x7b, 0x82, 0xdd, ++ 0x14, 0xa7, 0xcb, 0x71, 0x72, 0x00, 0x5c, 0xad, ++ 0x7b, 0x6a, 0x89, 0xa4, 0x3d, 0xbf, 0xb5, 0x4b, ++ 0x3e, 0x7c, 0x5a, 0xcf, 0xb8, 0xa1, 0xc5, 0x6e, ++ 0xc8, 0xb6, 0x31, 0x57, 0x7b, 0xdf, 0xa5, 0x7e, ++ 0xb1, 0xd6, 0x42, 0x2a, 0x31, 0x36, 0xd1, 0xd0, ++ 0x3f, 0x7a, 0xe5, 0x94, 0xd6, 0x36, 0xa0, 0x6f, ++ 0xb7, 0x40, 0x7d, 0x37, 0xc6, 0x55, 0x7c, 0x50, ++ 0x40, 0x6d, 0x29, 0x89, 0xe3, 0x5a, 0xae, 0x97, ++ 0xe7, 0x44, 0x49, 0x6e, 0xbd, 0x81, 0x3d, 0x03, ++ 0x93, 0x06, 0x12, 0x06, 0xe2, 0x41, 0x12, 0x4a, ++ 0xf1, 0x6a, 0xa4, 0x58, 0xa2, 0xfb, 0xd2, 0x15, ++ 0xba, 0xc9, 0x79, 0xc9, 0xce, 0x5e, 0x13, 0xbb, ++ 0xf1, 0x09, 0x04, 0xcc, 0xfd, 0xe8, 0x51, 0x34, ++ 0x6a, 0xe8, 0x61, 0x88, 0xda, 0xed, 0x01, 0x47, ++ 0x84, 0xf5, 0x73, 0x25, 0xf9, 0x1c, 0x42, 0x86, ++ 0x07, 0xf3, 0x5b, 0x1a, 0x01, 0xb3, 0xeb, 0x24, ++ 0x32, 0x8d, 0xf6, 0xed, 0x7c, 0x4b, 0xeb, 0x3c, ++ 0x36, 0x42, 0x28, 0xdf, 0xdf, 0xb6, 0xbe, 0xd9, ++ 0x8c, 0x52, 0xd3, 0x2b, 0x08, 0x90, 0x8c, 0xe7, ++ 0x98, 0x31, 0xe2, 0x32, 0x8e, 0xfc, 0x11, 0x48, ++ 0x00, 0xa8, 0x6a, 0x42, 0x4a, 0x02, 0xc6, 0x4b, ++ 0x09, 0xf1, 0xe3, 0x49, 0xf3, 0x45, 0x1f, 0x0e, ++ 0xbc, 0x56, 0xe2, 0xe4, 0xdf, 0xfb, 0xeb, 0x61, ++ 0xfa, 0x24, 0xc1, 0x63, 0x75, 0xbb, 0x47, 0x75, ++ 0xaf, 0xe1, 0x53, 0x16, 0x96, 0x21, 0x85, 0x26, ++ 0x11, 0xb3, 0x76, 0xe3, 0x23, 0xa1, 0x6b, 0x74, ++ 0x37, 0xd0, 0xde, 0x06, 0x90, 0x71, 0x5d, 0x43, ++ 0x88, 0x9b, 0x00, 0x54, 0xa6, 0x75, 0x2f, 0xa1, ++ 0xc2, 0x0b, 0x73, 0x20, 0x1d, 0xb6, 0x21, 0x79, ++ 0x57, 0x3f, 0xfa, 0x09, 0xbe, 0x8a, 0x33, 0xc3, ++ 0x52, 0xf0, 0x1d, 0x82, 0x31, 0xd1, 0x55, 0xb5, ++ 0x6c, 0x99, 0x25, 0xcf, 0x5c, 0x32, 0xce, 0xe9, ++ 0x0d, 0xfa, 0x69, 0x2c, 0xd5, 0x0d, 0xc5, 0x6d, ++ 0x86, 0xd0, 0x0c, 0x3b, 0x06, 0x50, 0x79, 0xe8, ++ 0xc3, 0xae, 0x04, 0xe6, 0xcd, 0x51, 0xe4, 0x26, ++ 0x9b, 0x4f, 0x7e, 0xa6, 0x0f, 0xab, 0xd8, 0xe5, ++ 0xde, 0xa9, 0x00, 0x95, 0xbe, 0xa3, 0x9d, 0x5d, ++ 0xb2, 0x09, 0x70, 0x18, 0x1c, 0xf0, 0xac, 0x29, ++ 0x23, 0x02, 0x29, 0x28, 0xd2, 0x74, 0x35, 0x57, ++ 0x62, 0x0f, 0x24, 0xea, 0x5e, 0x33, 0xc2, 0x92, ++ 0xf3, 0x78, 0x4d, 0x30, 0x1e, 0xa1, 0x99, 0xa9, ++ 0x82, 0xb0, 0x42, 0x31, 0x8d, 0xad, 0x8a, 0xbc, ++ 0xfc, 0xd4, 0x57, 0x47, 0x3e, 0xb4, 0x50, 0xdd, ++ 0x6e, 0x2c, 0x80, 0x4d, 0x22, 0xf1, 0xfb, 0x57, ++ 0xc4, 0xdd, 0x17, 0xe1, 0x8a, 0x36, 0x4a, 0xb3, ++ 0x37, 0xca, 0xc9, 0x4e, 0xab, 0xd5, 0x69, 0xc4, ++ 0xf4, 0xbc, 0x0b, 0x3b, 0x44, 0x4b, 0x29, 0x9c, ++ 0xee, 0xd4, 0x35, 0x22, 0x21, 0xb0, 0x1f, 0x27, ++ 0x64, 0xa8, 0x51, 0x1b, 0xf0, 0x9f, 0x19, 0x5c, ++ 0xfb, 0x5a, 0x64, 0x74, 0x70, 0x45, 0x09, 0xf5, ++ 0x64, 0xfe, 0x1a, 0x2d, 0xc9, 0x14, 0x04, 0x14, ++ 0xcf, 0xd5, 0x7d, 0x60, 0xaf, 0x94, 0x39, 0x94, ++ 0xe2, 0x7d, 0x79, 0x82, 0xd0, 0x65, 0x3b, 0x6b, ++ 0x9c, 0x19, 0x84, 0xb4, 0x6d, 0xb3, 0x0c, 0x99, ++ 0xc0, 0x56, 0xa8, 0xbd, 0x73, 0xce, 0x05, 0x84, ++ 0x3e, 0x30, 0xaa, 0xc4, 0x9b, 0x1b, 0x04, 0x2a, ++ 0x9f, 0xd7, 0x43, 0x2b, 0x23, 0xdf, 0xbf, 0xaa, ++ 0xd5, 0xc2, 0x43, 0x2d, 0x70, 0xab, 0xdc, 0x75, ++ 0xad, 0xac, 0xf7, 0xc0, 0xbe, 0x67, 0xb2, 0x74, ++ 0xed, 0x67, 0x10, 0x4a, 0x92, 0x60, 0xc1, 0x40, ++ 0x50, 0x19, 0x8a, 0x8a, 0x8c, 0x09, 0x0e, 0x72, ++ 0xe1, 0x73, 0x5e, 0xe8, 0x41, 0x85, 0x63, 0x9f, ++ 0x3f, 0xd7, 0x7d, 0xc4, 0xfb, 0x22, 0x5d, 0x92, ++ 0x6c, 0xb3, 0x1e, 0xe2, 0x50, 0x2f, 0x82, 0xa8, ++ 0x28, 0xc0, 0xb5, 0xd7, 0x5f, 0x68, 0x0d, 0x2c, ++ 0x2d, 0xaf, 0x7e, 0xfa, 0x2e, 0x08, 0x0f, 0x1f, ++ 0x70, 0x9f, 0xe9, 0x19, 0x72, 0x55, 0xf8, 0xfb, ++ 0x51, 0xd2, 0x33, 0x5d, 0xa0, 0xd3, 0x2b, 0x0a, ++ 0x6c, 0xbc, 0x4e, 0xcf, 0x36, 0x4d, 0xdc, 0x3b, ++ 0xe9, 0x3e, 0x81, 0x7c, 0x61, 0xdb, 0x20, 0x2d, ++ 0x3a, 0xc3, 0xb3, 0x0c, 0x1e, 0x00, 0xb9, 0x7c, ++ 0xf5, 0xca, 0x10, 0x5f, 0x3a, 0x71, 0xb3, 0xe4, ++ 0x20, 0xdb, 0x0c, 0x2a, 0x98, 0x63, 0x45, 0x00, ++ 0x58, 0xf6, 0x68, 0xe4, 0x0b, 0xda, 0x13, 0x3b, ++ 0x60, 0x5c, 0x76, 0xdb, 0xb9, 0x97, 0x71, 0xe4, ++ 0xd9, 0xb7, 0xdb, 0xbd, 0x68, 0xc7, 0x84, 0x84, ++ 0xaa, 0x7c, 0x68, 0x62, 0x5e, 0x16, 0xfc, 0xba, ++ 0x72, 0xaa, 0x9a, 0xa9, 0xeb, 0x7c, 0x75, 0x47, ++ 0x97, 0x7e, 0xad, 0xe2, 0xd9, 0x91, 0xe8, 0xe4, ++ 0xa5, 0x31, 0xd7, 0x01, 0x8e, 0xa2, 0x11, 0x88, ++ 0x95, 0xb9, 0xf2, 0x9b, 0xd3, 0x7f, 0x1b, 0x81, ++ 0x22, 0xf7, 0x98, 0x60, 0x0a, 0x64, 0xa6, 0xc1, ++ 0xf6, 0x49, 0xc7, 0xe3, 0x07, 0x4d, 0x94, 0x7a, ++ 0xcf, 0x6e, 0x68, 0x0c, 0x1b, 0x3f, 0x6e, 0x2e, ++ 0xee, 0x92, 0xfa, 0x52, 0xb3, 0x59, 0xf8, 0xf1, ++ 0x8f, 0x6a, 0x66, 0xa3, 0x82, 0x76, 0x4a, 0x07, ++ 0x1a, 0xc7, 0xdd, 0xf5, 0xda, 0x9c, 0x3c, 0x24, ++ 0xbf, 0xfd, 0x42, 0xa1, 0x10, 0x64, 0x6a, 0x0f, ++ 0x89, 0xee, 0x36, 0xa5, 0xce, 0x99, 0x48, 0x6a, ++ 0xf0, 0x9f, 0x9e, 0x69, 0xa4, 0x40, 0x20, 0xe9, ++ 0x16, 0x15, 0xf7, 0xdb, 0x75, 0x02, 0xcb, 0xe9, ++ 0x73, 0x8b, 0x3b, 0x49, 0x2f, 0xf0, 0xaf, 0x51, ++ 0x06, 0x5c, 0xdf, 0x27, 0x27, 0x49, 0x6a, 0xd1, ++ 0xcc, 0xc7, 0xb5, 0x63, 0xb5, 0xfc, 0xb8, 0x5c, ++ 0x87, 0x7f, 0x84, 0xb4, 0xcc, 0x14, 0xa9, 0x53, ++ 0xda, 0xa4, 0x56, 0xf8, 0xb6, 0x1b, 0xcc, 0x40, ++ 0x27, 0x52, 0x06, 0x5a, 0x13, 0x81, 0xd7, 0x3a, ++ 0xd4, 0x3b, 0xfb, 0x49, 0x65, 0x31, 0x33, 0xb2, ++ 0xfa, 0xcd, 0xad, 0x58, 0x4e, 0x2b, 0xae, 0xd2, ++ 0x20, 0xfb, 0x1a, 0x48, 0xb4, 0x3f, 0x9a, 0xd8, ++ 0x7a, 0x35, 0x4a, 0xc8, 0xee, 0x88, 0x5e, 0x07, ++ 0x66, 0x54, 0xb9, 0xec, 0x9f, 0xa3, 0xe3, 0xb9, ++ 0x37, 0xaa, 0x49, 0x76, 0x31, 0xda, 0x74, 0x2d, ++ 0x3c, 0xa4, 0x65, 0x10, 0x32, 0x38, 0xf0, 0xde, ++ 0xd3, 0x99, 0x17, 0xaa, 0x71, 0xaa, 0x8f, 0x0f, ++ 0x8c, 0xaf, 0xa2, 0xf8, 0x5d, 0x64, 0xba, 0x1d, ++ 0xa3, 0xef, 0x96, 0x73, 0xe8, 0xa1, 0x02, 0x8d, ++ 0x0c, 0x6d, 0xb8, 0x06, 0x90, 0xb8, 0x08, 0x56, ++ 0x2c, 0xa7, 0x06, 0xc9, 0xc2, 0x38, 0xdb, 0x7c, ++ 0x63, 0xb1, 0x57, 0x8e, 0xea, 0x7c, 0x79, 0xf3, ++ 0x49, 0x1d, 0xfe, 0x9f, 0xf3, 0x6e, 0xb1, 0x1d, ++ 0xba, 0x19, 0x80, 0x1a, 0x0a, 0xd3, 0xb0, 0x26, ++ 0x21, 0x40, 0xb1, 0x7c, 0xf9, 0x4d, 0x8d, 0x10, ++ 0xc1, 0x7e, 0xf4, 0xf6, 0x3c, 0xa8, 0xfd, 0x7c, ++ 0xa3, 0x92, 0xb2, 0x0f, 0xaa, 0xcc, 0xa6, 0x11, ++ 0xfe, 0x04, 0xe3, 0xd1, 0x7a, 0x32, 0x89, 0xdf, ++ 0x0d, 0xc4, 0x8f, 0x79, 0x6b, 0xca, 0x16, 0x7c, ++ 0x6e, 0xf9, 0xad, 0x0f, 0xf6, 0xfe, 0x27, 0xdb, ++ 0xc4, 0x13, 0x70, 0xf1, 0x62, 0x1a, 0x4f, 0x79, ++ 0x40, 0xc9, 0x9b, 0x8b, 0x21, 0xea, 0x84, 0xfa, ++ 0xf5, 0xf1, 0x89, 0xce, 0xb7, 0x55, 0x0a, 0x80, ++ 0x39, 0x2f, 0x55, 0x36, 0x16, 0x9c, 0x7b, 0x08, ++ 0xbd, 0x87, 0x0d, 0xa5, 0x32, 0xf1, 0x52, 0x7c, ++ 0xe8, 0x55, 0x60, 0x5b, 0xd7, 0x69, 0xe4, 0xfc, ++ 0xfa, 0x12, 0x85, 0x96, 0xea, 0x50, 0x28, 0xab, ++ 0x8a, 0xf7, 0xbb, 0x0e, 0x53, 0x74, 0xca, 0xa6, ++ 0x27, 0x09, 0xc2, 0xb5, 0xde, 0x18, 0x14, 0xd9, ++ 0xea, 0xe5, 0x29, 0x1c, 0x40, 0x56, 0xcf, 0xd7, ++ 0xae, 0x05, 0x3f, 0x65, 0xaf, 0x05, 0x73, 0xe2, ++ 0x35, 0x96, 0x27, 0x07, 0x14, 0xc0, 0xad, 0x33, ++ 0xf1, 0xdc, 0x44, 0x7a, 0x89, 0x17, 0x77, 0xd2, ++ 0x9c, 0x58, 0x60, 0xf0, 0x3f, 0x7b, 0x2d, 0x2e, ++ 0x57, 0x95, 0x54, 0x87, 0xed, 0xf2, 0xc7, 0x4c, ++ 0xf0, 0xae, 0x56, 0x29, 0x19, 0x7d, 0x66, 0x4b, ++ 0x9b, 0x83, 0x84, 0x42, 0x3b, 0x01, 0x25, 0x66, ++ 0x8e, 0x02, 0xde, 0xb9, 0x83, 0x54, 0x19, 0xf6, ++ 0x9f, 0x79, 0x0d, 0x67, 0xc5, 0x1d, 0x7a, 0x44, ++ 0x02, 0x98, 0xa7, 0x16, 0x1c, 0x29, 0x0d, 0x74, ++ 0xff, 0x85, 0x40, 0x06, 0xef, 0x2c, 0xa9, 0xc6, ++ 0xf5, 0x53, 0x07, 0x06, 0xae, 0xe4, 0xfa, 0x5f, ++ 0xd8, 0x39, 0x4d, 0xf1, 0x9b, 0x6b, 0xd9, 0x24, ++ 0x84, 0xfe, 0x03, 0x4c, 0xb2, 0x3f, 0xdf, 0xa1, ++ 0x05, 0x9e, 0x50, 0x14, 0x5a, 0xd9, 0x1a, 0xa2, ++ 0xa7, 0xfa, 0xfa, 0x17, 0xf7, 0x78, 0xd6, 0xb5, ++ 0x92, 0x61, 0x91, 0xac, 0x36, 0xfa, 0x56, 0x0d, ++ 0x38, 0x32, 0x18, 0x85, 0x08, 0x58, 0x37, 0xf0, ++ 0x4b, 0xdb, 0x59, 0xe7, 0xa4, 0x34, 0xc0, 0x1b, ++ 0x01, 0xaf, 0x2d, 0xde, 0xa1, 0xaa, 0x5d, 0xd3, ++ 0xec, 0xe1, 0xd4, 0xf7, 0xe6, 0x54, 0x68, 0xf0, ++ 0x51, 0x97, 0xa7, 0x89, 0xea, 0x24, 0xad, 0xd3, ++ 0x6e, 0x47, 0x93, 0x8b, 0x4b, 0xb4, 0xf7, 0x1c, ++ 0x42, 0x06, 0x67, 0xe8, 0x99, 0xf6, 0xf5, 0x7b, ++ 0x85, 0xb5, 0x65, 0xb5, 0xb5, 0xd2, 0x37, 0xf5, ++ 0xf3, 0x02, 0xa6, 0x4d, 0x11, 0xa7, 0xdc, 0x51, ++ 0x09, 0x7f, 0xa0, 0xd8, 0x88, 0x1c, 0x13, 0x71, ++ 0xae, 0x9c, 0xb7, 0x7b, 0x34, 0xd6, 0x4e, 0x68, ++ 0x26, 0x83, 0x51, 0xaf, 0x1d, 0xee, 0x8b, 0xbb, ++ 0x69, 0x43, 0x2b, 0x9e, 0x8a, 0xbc, 0x02, 0x0e, ++ 0xa0, 0x1b, 0xe0, 0xa8, 0x5f, 0x6f, 0xaf, 0x1b, ++ 0x8f, 0xe7, 0x64, 0x71, 0x74, 0x11, 0x7e, 0xa8, ++ 0xd8, 0xf9, 0x97, 0x06, 0xc3, 0xb6, 0xfb, 0xfb, ++ 0xb7, 0x3d, 0x35, 0x9d, 0x3b, 0x52, 0xed, 0x54, ++ 0xca, 0xf4, 0x81, 0x01, 0x2d, 0x1b, 0xc3, 0xa7, ++ 0x00, 0x3d, 0x1a, 0x39, 0x54, 0xe1, 0xf6, 0xff, ++ 0xed, 0x6f, 0x0b, 0x5a, 0x68, 0xda, 0x58, 0xdd, ++ 0xa9, 0xcf, 0x5c, 0x4a, 0xe5, 0x09, 0x4e, 0xde, ++ 0x9d, 0xbc, 0x3e, 0xee, 0x5a, 0x00, 0x3b, 0x2c, ++ 0x87, 0x10, 0x65, 0x60, 0xdd, 0xd7, 0x56, 0xd1, ++ 0x4c, 0x64, 0x45, 0xe4, 0x21, 0xec, 0x78, 0xf8, ++ 0x25, 0x7a, 0x3e, 0x16, 0x5d, 0x09, 0x53, 0x14, ++ 0xbe, 0x4f, 0xae, 0x87, 0xd8, 0xd1, 0xaa, 0x3c, ++ 0xf6, 0x3e, 0xa4, 0x70, 0x8c, 0x5e, 0x70, 0xa4, ++ 0xb3, 0x6b, 0x66, 0x73, 0xd3, 0xbf, 0x31, 0x06, ++ 0x19, 0x62, 0x93, 0x15, 0xf2, 0x86, 0xe4, 0x52, ++ 0x7e, 0x53, 0x4c, 0x12, 0x38, 0xcc, 0x34, 0x7d, ++ 0x57, 0xf6, 0x42, 0x93, 0x8a, 0xc4, 0xee, 0x5c, ++ 0x8a, 0xe1, 0x52, 0x8f, 0x56, 0x64, 0xf6, 0xa6, ++ 0xd1, 0x91, 0x57, 0x70, 0xcd, 0x11, 0x76, 0xf5, ++ 0x59, 0x60, 0x60, 0x3c, 0xc1, 0xc3, 0x0b, 0x7f, ++ 0x58, 0x1a, 0x50, 0x91, 0xf1, 0x68, 0x8f, 0x6e, ++ 0x74, 0x74, 0xa8, 0x51, 0x0b, 0xf7, 0x7a, 0x98, ++ 0x37, 0xf2, 0x0a, 0x0e, 0xa4, 0x97, 0x04, 0xb8, ++ 0x9b, 0xfd, 0xa0, 0xea, 0xf7, 0x0d, 0xe1, 0xdb, ++ 0x03, 0xf0, 0x31, 0x29, 0xf8, 0xdd, 0x6b, 0x8b, ++ 0x5d, 0xd8, 0x59, 0xa9, 0x29, 0xcf, 0x9a, 0x79, ++ 0x89, 0x19, 0x63, 0x46, 0x09, 0x79, 0x6a, 0x11, ++ 0xda, 0x63, 0x68, 0x48, 0x77, 0x23, 0xfb, 0x7d, ++ 0x3a, 0x43, 0xcb, 0x02, 0x3b, 0x7a, 0x6d, 0x10, ++ 0x2a, 0x9e, 0xac, 0xf1, 0xd4, 0x19, 0xf8, 0x23, ++ 0x64, 0x1d, 0x2c, 0x5f, 0xf2, 0xb0, 0x5c, 0x23, ++ 0x27, 0xf7, 0x27, 0x30, 0x16, 0x37, 0xb1, 0x90, ++ 0xab, 0x38, 0xfb, 0x55, 0xcd, 0x78, 0x58, 0xd4, ++ 0x7d, 0x43, 0xf6, 0x45, 0x5e, 0x55, 0x8d, 0xb1, ++ 0x02, 0x65, 0x58, 0xb4, 0x13, 0x4b, 0x36, 0xf7, ++ 0xcc, 0xfe, 0x3d, 0x0b, 0x82, 0xe2, 0x12, 0x11, ++ 0xbb, 0xe6, 0xb8, 0x3a, 0x48, 0x71, 0xc7, 0x50, ++ 0x06, 0x16, 0x3a, 0xe6, 0x7c, 0x05, 0xc7, 0xc8, ++ 0x4d, 0x2f, 0x08, 0x6a, 0x17, 0x9a, 0x95, 0x97, ++ 0x50, 0x68, 0xdc, 0x28, 0x18, 0xc4, 0x61, 0x38, ++ 0xb9, 0xe0, 0x3e, 0x78, 0xdb, 0x29, 0xe0, 0x9f, ++ 0x52, 0xdd, 0xf8, 0x4f, 0x91, 0xc1, 0xd0, 0x33, ++ 0xa1, 0x7a, 0x8e, 0x30, 0x13, 0x82, 0x07, 0x9f, ++ 0xd3, 0x31, 0x0f, 0x23, 0xbe, 0x32, 0x5a, 0x75, ++ 0xcf, 0x96, 0xb2, 0xec, 0xb5, 0x32, 0xac, 0x21, ++ 0xd1, 0x82, 0x33, 0xd3, 0x15, 0x74, 0xbd, 0x90, ++ 0xf1, 0x2c, 0xe6, 0x5f, 0x8d, 0xe3, 0x02, 0xe8, ++ 0xe9, 0xc4, 0xca, 0x96, 0xeb, 0x0e, 0xbc, 0x91, ++ 0xf4, 0xb9, 0xea, 0xd9, 0x1b, 0x75, 0xbd, 0xe1, ++ 0xac, 0x2a, 0x05, 0x37, 0x52, 0x9b, 0x1b, 0x3f, ++ 0x5a, 0xdc, 0x21, 0xc3, 0x98, 0xbb, 0xaf, 0xa3, ++ 0xf2, 0x00, 0xbf, 0x0d, 0x30, 0x89, 0x05, 0xcc, ++ 0xa5, 0x76, 0xf5, 0x06, 0xf0, 0xc6, 0x54, 0x8a, ++ 0x5d, 0xd4, 0x1e, 0xc1, 0xf2, 0xce, 0xb0, 0x62, ++ 0xc8, 0xfc, 0x59, 0x42, 0x9a, 0x90, 0x60, 0x55, ++ 0xfe, 0x88, 0xa5, 0x8b, 0xb8, 0x33, 0x0c, 0x23, ++ 0x24, 0x0d, 0x15, 0x70, 0x37, 0x1e, 0x3d, 0xf6, ++ 0xd2, 0xea, 0x92, 0x10, 0xb2, 0xc4, 0x51, 0xac, ++ 0xf2, 0xac, 0xf3, 0x6b, 0x6c, 0xaa, 0xcf, 0x12, ++ 0xc5, 0x6c, 0x90, 0x50, 0xb5, 0x0c, 0xfc, 0x1a, ++ 0x15, 0x52, 0xe9, 0x26, 0xc6, 0x52, 0xa4, 0xe7, ++ 0x81, 0x69, 0xe1, 0xe7, 0x9e, 0x30, 0x01, 0xec, ++ 0x84, 0x89, 0xb2, 0x0d, 0x66, 0xdd, 0xce, 0x28, ++ 0x5c, 0xec, 0x98, 0x46, 0x68, 0x21, 0x9f, 0x88, ++ 0x3f, 0x1f, 0x42, 0x77, 0xce, 0xd0, 0x61, 0xd4, ++ 0x20, 0xa7, 0xff, 0x53, 0xad, 0x37, 0xd0, 0x17, ++ 0x35, 0xc9, 0xfc, 0xba, 0x0a, 0x78, 0x3f, 0xf2, ++ 0xcc, 0x86, 0x89, 0xe8, 0x4b, 0x3c, 0x48, 0x33, ++ 0x09, 0x7f, 0xc6, 0xc0, 0xdd, 0xb8, 0xfd, 0x7a, ++ 0x66, 0x66, 0x65, 0xeb, 0x47, 0xa7, 0x04, 0x28, ++ 0xa3, 0x19, 0x8e, 0xa9, 0xb1, 0x13, 0x67, 0x62, ++ 0x70, 0xcf, 0xd6 ++}; ++static const u8 enc_assoc012[] __initconst = { ++ 0xb1, 0x69, 0x83, 0x87, 0x30, 0xaa, 0x5d, 0xb8, ++ 0x77, 0xe8, 0x21, 0xff, 0x06, 0x59, 0x35, 0xce, ++ 0x75, 0xfe, 0x38, 0xef, 0xb8, 0x91, 0x43, 0x8c, ++ 0xcf, 0x70, 0xdd, 0x0a, 0x68, 0xbf, 0xd4, 0xbc, ++ 0x16, 0x76, 0x99, 0x36, 0x1e, 0x58, 0x79, 0x5e, ++ 0xd4, 0x29, 0xf7, 0x33, 0x93, 0x48, 0xdb, 0x5f, ++ 0x01, 0xae, 0x9c, 0xb6, 0xe4, 0x88, 0x6d, 0x2b, ++ 0x76, 0x75, 0xe0, 0xf3, 0x74, 0xe2, 0xc9 ++}; ++static const u8 enc_nonce012[] __initconst = { ++ 0x05, 0xa3, 0x93, 0xed, 0x30, 0xc5, 0xa2, 0x06 ++}; ++static const u8 enc_key012[] __initconst = { ++ 0xb3, 0x35, 0x50, 0x03, 0x54, 0x2e, 0x40, 0x5e, ++ 0x8f, 0x59, 0x8e, 0xc5, 0x90, 0xd5, 0x27, 0x2d, ++ 0xba, 0x29, 0x2e, 0xcb, 0x1b, 0x70, 0x44, 0x1e, ++ 0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input053[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83, ++ 0x55, 0xd3, 0x04, 0x84, 0x64, 0x43, 0xfe, 0xe8, ++ 0xdf, 0x99, 0x47, 0x03, 0x03, 0xfb, 0x3b, 0x7b, ++ 0x80, 0xe0, 0x30, 0xbe, 0xeb, 0xd3, 0x29, 0xbe ++}; ++static const u8 enc_output053[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0xe6, 0xd3, 0xd7, 0x32, 0x4a, 0x1c, 0xbb, 0xa7, ++ 0x77, 0xbb, 0xb0, 0xec, 0xdd, 0xa3, 0x78, 0x07 ++}; ++static const u8 enc_assoc053[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_nonce053[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key053[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input054[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83, ++ 0x55, 0xd3, 0x04, 0x84, 0x64, 0x43, 0xfe, 0xe8, ++ 0xdf, 0x99, 0x47, 0x03, 0x03, 0xfb, 0x3b, 0x7b, ++ 0x80, 0xe0, 0x30, 0xbe, 0xeb, 0xd3, 0x29, 0xbe, ++ 0xe3, 0xbc, 0xdb, 0x5b, 0x1e, 0xde, 0xfc, 0xfe, ++ 0x8b, 0xcd, 0xa1, 0xb6, 0xa1, 0x5c, 0x8c, 0x2b, ++ 0x08, 0x69, 0xff, 0xd2, 0xec, 0x5e, 0x26, 0xe5, ++ 0x53, 0xb7, 0xb2, 0x27, 0xfe, 0x87, 0xfd, 0xbd ++}; ++static const u8 enc_output054[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x06, 0x2d, 0xe6, 0x79, 0x5f, 0x27, 0x4f, 0xd2, ++ 0xa3, 0x05, 0xd7, 0x69, 0x80, 0xbc, 0x9c, 0xce ++}; ++static const u8 enc_assoc054[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_nonce054[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key054[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input055[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83, ++ 0x55, 0xd3, 0x04, 0x84, 0x64, 0x43, 0xfe, 0xe8, ++ 0xdf, 0x99, 0x47, 0x03, 0x03, 0xfb, 0x3b, 0x7b, ++ 0x80, 0xe0, 0x30, 0xbe, 0xeb, 0xd3, 0x29, 0xbe, ++ 0xe3, 0xbc, 0xdb, 0x5b, 0x1e, 0xde, 0xfc, 0xfe, ++ 0x8b, 0xcd, 0xa1, 0xb6, 0xa1, 0x5c, 0x8c, 0x2b, ++ 0x08, 0x69, 0xff, 0xd2, 0xec, 0x5e, 0x26, 0xe5, ++ 0x53, 0xb7, 0xb2, 0x27, 0xfe, 0x87, 0xfd, 0xbd, ++ 0x7a, 0xda, 0x44, 0x42, 0x42, 0x69, 0xbf, 0xfa, ++ 0x55, 0x27, 0xf2, 0x70, 0xac, 0xf6, 0x85, 0x02, ++ 0xb7, 0x4c, 0x5a, 0xe2, 0xe6, 0x0c, 0x05, 0x80, ++ 0x98, 0x1a, 0x49, 0x38, 0x45, 0x93, 0x92, 0xc4, ++ 0x9b, 0xb2, 0xf2, 0x84, 0xb6, 0x46, 0xef, 0xc7, ++ 0xf3, 0xf0, 0xb1, 0x36, 0x1d, 0xc3, 0x48, 0xed, ++ 0x77, 0xd3, 0x0b, 0xc5, 0x76, 0x92, 0xed, 0x38, ++ 0xfb, 0xac, 0x01, 0x88, 0x38, 0x04, 0x88, 0xc7 ++}; ++static const u8 enc_output055[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0xd8, 0xb4, 0x79, 0x02, 0xba, 0xae, 0xaf, 0xb3, ++ 0x42, 0x03, 0x05, 0x15, 0x29, 0xaf, 0x28, 0x2e ++}; ++static const u8 enc_assoc055[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_nonce055[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key055[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input056[] __initconst = { ++ 0xda, 0x92, 0xbf, 0x77, 0x7f, 0x6b, 0xe8, 0x7c, ++ 0xaa, 0x2c, 0xfb, 0x7b, 0x9b, 0xbc, 0x01, 0x17, ++ 0x20, 0x66, 0xb8, 0xfc, 0xfc, 0x04, 0xc4, 0x84, ++ 0x7f, 0x1f, 0xcf, 0x41, 0x14, 0x2c, 0xd6, 0x41 ++}; ++static const u8 enc_output056[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xb3, 0x89, 0x1c, 0x84, 0x9c, 0xb5, 0x2c, 0x27, ++ 0x74, 0x7e, 0xdf, 0xcf, 0x31, 0x21, 0x3b, 0xb6 ++}; ++static const u8 enc_assoc056[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce056[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key056[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input057[] __initconst = { ++ 0xda, 0x92, 0xbf, 0x77, 0x7f, 0x6b, 0xe8, 0x7c, ++ 0xaa, 0x2c, 0xfb, 0x7b, 0x9b, 0xbc, 0x01, 0x17, ++ 0x20, 0x66, 0xb8, 0xfc, 0xfc, 0x04, 0xc4, 0x84, ++ 0x7f, 0x1f, 0xcf, 0x41, 0x14, 0x2c, 0xd6, 0x41, ++ 0x1c, 0x43, 0x24, 0xa4, 0xe1, 0x21, 0x03, 0x01, ++ 0x74, 0x32, 0x5e, 0x49, 0x5e, 0xa3, 0x73, 0xd4, ++ 0xf7, 0x96, 0x00, 0x2d, 0x13, 0xa1, 0xd9, 0x1a, ++ 0xac, 0x48, 0x4d, 0xd8, 0x01, 0x78, 0x02, 0x42 ++}; ++static const u8 enc_output057[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xf0, 0xc1, 0x2d, 0x26, 0xef, 0x03, 0x02, 0x9b, ++ 0x62, 0xc0, 0x08, 0xda, 0x27, 0xc5, 0xdc, 0x68 ++}; ++static const u8 enc_assoc057[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce057[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key057[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input058[] __initconst = { ++ 0xda, 0x92, 0xbf, 0x77, 0x7f, 0x6b, 0xe8, 0x7c, ++ 0xaa, 0x2c, 0xfb, 0x7b, 0x9b, 0xbc, 0x01, 0x17, ++ 0x20, 0x66, 0xb8, 0xfc, 0xfc, 0x04, 0xc4, 0x84, ++ 0x7f, 0x1f, 0xcf, 0x41, 0x14, 0x2c, 0xd6, 0x41, ++ 0x1c, 0x43, 0x24, 0xa4, 0xe1, 0x21, 0x03, 0x01, ++ 0x74, 0x32, 0x5e, 0x49, 0x5e, 0xa3, 0x73, 0xd4, ++ 0xf7, 0x96, 0x00, 0x2d, 0x13, 0xa1, 0xd9, 0x1a, ++ 0xac, 0x48, 0x4d, 0xd8, 0x01, 0x78, 0x02, 0x42, ++ 0x85, 0x25, 0xbb, 0xbd, 0xbd, 0x96, 0x40, 0x05, ++ 0xaa, 0xd8, 0x0d, 0x8f, 0x53, 0x09, 0x7a, 0xfd, ++ 0x48, 0xb3, 0xa5, 0x1d, 0x19, 0xf3, 0xfa, 0x7f, ++ 0x67, 0xe5, 0xb6, 0xc7, 0xba, 0x6c, 0x6d, 0x3b, ++ 0x64, 0x4d, 0x0d, 0x7b, 0x49, 0xb9, 0x10, 0x38, ++ 0x0c, 0x0f, 0x4e, 0xc9, 0xe2, 0x3c, 0xb7, 0x12, ++ 0x88, 0x2c, 0xf4, 0x3a, 0x89, 0x6d, 0x12, 0xc7, ++ 0x04, 0x53, 0xfe, 0x77, 0xc7, 0xfb, 0x77, 0x38 ++}; ++static const u8 enc_output058[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xee, 0x65, 0x78, 0x30, 0x01, 0xc2, 0x56, 0x91, ++ 0xfa, 0x28, 0xd0, 0xf5, 0xf1, 0xc1, 0xd7, 0x62 ++}; ++static const u8 enc_assoc058[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce058[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key058[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input059[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x08, 0x80, 0x94, 0x17, 0x03, ++ 0x55, 0xd3, 0x04, 0x04, 0x64, 0x43, 0xfe, 0x68, ++ 0xdf, 0x99, 0x47, 0x83, 0x03, 0xfb, 0x3b, 0xfb, ++ 0x80, 0xe0, 0x30, 0x3e, 0xeb, 0xd3, 0x29, 0x3e ++}; ++static const u8 enc_output059[] __initconst = { ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x79, 0xba, 0x7a, 0x29, 0xf5, 0xa7, 0xbb, 0x75, ++ 0x79, 0x7a, 0xf8, 0x7a, 0x61, 0x01, 0x29, 0xa4 ++}; ++static const u8 enc_assoc059[] __initconst = { ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80 ++}; ++static const u8 enc_nonce059[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key059[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input060[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x08, 0x80, 0x94, 0x17, 0x03, ++ 0x55, 0xd3, 0x04, 0x04, 0x64, 0x43, 0xfe, 0x68, ++ 0xdf, 0x99, 0x47, 0x83, 0x03, 0xfb, 0x3b, 0xfb, ++ 0x80, 0xe0, 0x30, 0x3e, 0xeb, 0xd3, 0x29, 0x3e, ++ 0xe3, 0xbc, 0xdb, 0xdb, 0x1e, 0xde, 0xfc, 0x7e, ++ 0x8b, 0xcd, 0xa1, 0x36, 0xa1, 0x5c, 0x8c, 0xab, ++ 0x08, 0x69, 0xff, 0x52, 0xec, 0x5e, 0x26, 0x65, ++ 0x53, 0xb7, 0xb2, 0xa7, 0xfe, 0x87, 0xfd, 0x3d ++}; ++static const u8 enc_output060[] __initconst = { ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x36, 0xb1, 0x74, 0x38, 0x19, 0xe1, 0xb9, 0xba, ++ 0x15, 0x51, 0xe8, 0xed, 0x92, 0x2a, 0x95, 0x9a ++}; ++static const u8 enc_assoc060[] __initconst = { ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80 ++}; ++static const u8 enc_nonce060[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key060[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input061[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x08, 0x80, 0x94, 0x17, 0x03, ++ 0x55, 0xd3, 0x04, 0x04, 0x64, 0x43, 0xfe, 0x68, ++ 0xdf, 0x99, 0x47, 0x83, 0x03, 0xfb, 0x3b, 0xfb, ++ 0x80, 0xe0, 0x30, 0x3e, 0xeb, 0xd3, 0x29, 0x3e, ++ 0xe3, 0xbc, 0xdb, 0xdb, 0x1e, 0xde, 0xfc, 0x7e, ++ 0x8b, 0xcd, 0xa1, 0x36, 0xa1, 0x5c, 0x8c, 0xab, ++ 0x08, 0x69, 0xff, 0x52, 0xec, 0x5e, 0x26, 0x65, ++ 0x53, 0xb7, 0xb2, 0xa7, 0xfe, 0x87, 0xfd, 0x3d, ++ 0x7a, 0xda, 0x44, 0xc2, 0x42, 0x69, 0xbf, 0x7a, ++ 0x55, 0x27, 0xf2, 0xf0, 0xac, 0xf6, 0x85, 0x82, ++ 0xb7, 0x4c, 0x5a, 0x62, 0xe6, 0x0c, 0x05, 0x00, ++ 0x98, 0x1a, 0x49, 0xb8, 0x45, 0x93, 0x92, 0x44, ++ 0x9b, 0xb2, 0xf2, 0x04, 0xb6, 0x46, 0xef, 0x47, ++ 0xf3, 0xf0, 0xb1, 0xb6, 0x1d, 0xc3, 0x48, 0x6d, ++ 0x77, 0xd3, 0x0b, 0x45, 0x76, 0x92, 0xed, 0xb8, ++ 0xfb, 0xac, 0x01, 0x08, 0x38, 0x04, 0x88, 0x47 ++}; ++static const u8 enc_output061[] __initconst = { ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0xfe, 0xac, 0x49, 0x55, 0x55, 0x4e, 0x80, 0x6f, ++ 0x3a, 0x19, 0x02, 0xe2, 0x44, 0x32, 0xc0, 0x8a ++}; ++static const u8 enc_assoc061[] __initconst = { ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80 ++}; ++static const u8 enc_nonce061[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key061[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input062[] __initconst = { ++ 0xda, 0x92, 0xbf, 0xf7, 0x7f, 0x6b, 0xe8, 0xfc, ++ 0xaa, 0x2c, 0xfb, 0xfb, 0x9b, 0xbc, 0x01, 0x97, ++ 0x20, 0x66, 0xb8, 0x7c, 0xfc, 0x04, 0xc4, 0x04, ++ 0x7f, 0x1f, 0xcf, 0xc1, 0x14, 0x2c, 0xd6, 0xc1 ++}; ++static const u8 enc_output062[] __initconst = { ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0x20, 0xa3, 0x79, 0x8d, 0xf1, 0x29, 0x2c, 0x59, ++ 0x72, 0xbf, 0x97, 0x41, 0xae, 0xc3, 0x8a, 0x19 ++}; ++static const u8 enc_assoc062[] __initconst = { ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f ++}; ++static const u8 enc_nonce062[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key062[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input063[] __initconst = { ++ 0xda, 0x92, 0xbf, 0xf7, 0x7f, 0x6b, 0xe8, 0xfc, ++ 0xaa, 0x2c, 0xfb, 0xfb, 0x9b, 0xbc, 0x01, 0x97, ++ 0x20, 0x66, 0xb8, 0x7c, 0xfc, 0x04, 0xc4, 0x04, ++ 0x7f, 0x1f, 0xcf, 0xc1, 0x14, 0x2c, 0xd6, 0xc1, ++ 0x1c, 0x43, 0x24, 0x24, 0xe1, 0x21, 0x03, 0x81, ++ 0x74, 0x32, 0x5e, 0xc9, 0x5e, 0xa3, 0x73, 0x54, ++ 0xf7, 0x96, 0x00, 0xad, 0x13, 0xa1, 0xd9, 0x9a, ++ 0xac, 0x48, 0x4d, 0x58, 0x01, 0x78, 0x02, 0xc2 ++}; ++static const u8 enc_output063[] __initconst = { ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xc0, 0x3d, 0x9f, 0x67, 0x35, 0x4a, 0x97, 0xb2, ++ 0xf0, 0x74, 0xf7, 0x55, 0x15, 0x57, 0xe4, 0x9c ++}; ++static const u8 enc_assoc063[] __initconst = { ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f ++}; ++static const u8 enc_nonce063[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key063[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input064[] __initconst = { ++ 0xda, 0x92, 0xbf, 0xf7, 0x7f, 0x6b, 0xe8, 0xfc, ++ 0xaa, 0x2c, 0xfb, 0xfb, 0x9b, 0xbc, 0x01, 0x97, ++ 0x20, 0x66, 0xb8, 0x7c, 0xfc, 0x04, 0xc4, 0x04, ++ 0x7f, 0x1f, 0xcf, 0xc1, 0x14, 0x2c, 0xd6, 0xc1, ++ 0x1c, 0x43, 0x24, 0x24, 0xe1, 0x21, 0x03, 0x81, ++ 0x74, 0x32, 0x5e, 0xc9, 0x5e, 0xa3, 0x73, 0x54, ++ 0xf7, 0x96, 0x00, 0xad, 0x13, 0xa1, 0xd9, 0x9a, ++ 0xac, 0x48, 0x4d, 0x58, 0x01, 0x78, 0x02, 0xc2, ++ 0x85, 0x25, 0xbb, 0x3d, 0xbd, 0x96, 0x40, 0x85, ++ 0xaa, 0xd8, 0x0d, 0x0f, 0x53, 0x09, 0x7a, 0x7d, ++ 0x48, 0xb3, 0xa5, 0x9d, 0x19, 0xf3, 0xfa, 0xff, ++ 0x67, 0xe5, 0xb6, 0x47, 0xba, 0x6c, 0x6d, 0xbb, ++ 0x64, 0x4d, 0x0d, 0xfb, 0x49, 0xb9, 0x10, 0xb8, ++ 0x0c, 0x0f, 0x4e, 0x49, 0xe2, 0x3c, 0xb7, 0x92, ++ 0x88, 0x2c, 0xf4, 0xba, 0x89, 0x6d, 0x12, 0x47, ++ 0x04, 0x53, 0xfe, 0xf7, 0xc7, 0xfb, 0x77, 0xb8 ++}; ++static const u8 enc_output064[] __initconst = { ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xc8, 0x6d, 0xa8, 0xdd, 0x65, 0x22, 0x86, 0xd5, ++ 0x02, 0x13, 0xd3, 0x28, 0xd6, 0x3e, 0x40, 0x06 ++}; ++static const u8 enc_assoc064[] __initconst = { ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f ++}; ++static const u8 enc_nonce064[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key064[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input065[] __initconst = { ++ 0x5a, 0x92, 0xbf, 0x77, 0xff, 0x6b, 0xe8, 0x7c, ++ 0x2a, 0x2c, 0xfb, 0x7b, 0x1b, 0xbc, 0x01, 0x17, ++ 0xa0, 0x66, 0xb8, 0xfc, 0x7c, 0x04, 0xc4, 0x84, ++ 0xff, 0x1f, 0xcf, 0x41, 0x94, 0x2c, 0xd6, 0x41 ++}; ++static const u8 enc_output065[] __initconst = { ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0xbe, 0xde, 0x90, 0x83, 0xce, 0xb3, 0x6d, 0xdf, ++ 0xe5, 0xfa, 0x81, 0x1f, 0x95, 0x47, 0x1c, 0x67 ++}; ++static const u8 enc_assoc065[] __initconst = { ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce065[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key065[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input066[] __initconst = { ++ 0x5a, 0x92, 0xbf, 0x77, 0xff, 0x6b, 0xe8, 0x7c, ++ 0x2a, 0x2c, 0xfb, 0x7b, 0x1b, 0xbc, 0x01, 0x17, ++ 0xa0, 0x66, 0xb8, 0xfc, 0x7c, 0x04, 0xc4, 0x84, ++ 0xff, 0x1f, 0xcf, 0x41, 0x94, 0x2c, 0xd6, 0x41, ++ 0x9c, 0x43, 0x24, 0xa4, 0x61, 0x21, 0x03, 0x01, ++ 0xf4, 0x32, 0x5e, 0x49, 0xde, 0xa3, 0x73, 0xd4, ++ 0x77, 0x96, 0x00, 0x2d, 0x93, 0xa1, 0xd9, 0x1a, ++ 0x2c, 0x48, 0x4d, 0xd8, 0x81, 0x78, 0x02, 0x42 ++}; ++static const u8 enc_output066[] __initconst = { ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x30, 0x08, 0x74, 0xbb, 0x06, 0x92, 0xb6, 0x89, ++ 0xde, 0xad, 0x9a, 0xe1, 0x5b, 0x06, 0x73, 0x90 ++}; ++static const u8 enc_assoc066[] __initconst = { ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce066[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key066[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input067[] __initconst = { ++ 0x5a, 0x92, 0xbf, 0x77, 0xff, 0x6b, 0xe8, 0x7c, ++ 0x2a, 0x2c, 0xfb, 0x7b, 0x1b, 0xbc, 0x01, 0x17, ++ 0xa0, 0x66, 0xb8, 0xfc, 0x7c, 0x04, 0xc4, 0x84, ++ 0xff, 0x1f, 0xcf, 0x41, 0x94, 0x2c, 0xd6, 0x41, ++ 0x9c, 0x43, 0x24, 0xa4, 0x61, 0x21, 0x03, 0x01, ++ 0xf4, 0x32, 0x5e, 0x49, 0xde, 0xa3, 0x73, 0xd4, ++ 0x77, 0x96, 0x00, 0x2d, 0x93, 0xa1, 0xd9, 0x1a, ++ 0x2c, 0x48, 0x4d, 0xd8, 0x81, 0x78, 0x02, 0x42, ++ 0x05, 0x25, 0xbb, 0xbd, 0x3d, 0x96, 0x40, 0x05, ++ 0x2a, 0xd8, 0x0d, 0x8f, 0xd3, 0x09, 0x7a, 0xfd, ++ 0xc8, 0xb3, 0xa5, 0x1d, 0x99, 0xf3, 0xfa, 0x7f, ++ 0xe7, 0xe5, 0xb6, 0xc7, 0x3a, 0x6c, 0x6d, 0x3b, ++ 0xe4, 0x4d, 0x0d, 0x7b, 0xc9, 0xb9, 0x10, 0x38, ++ 0x8c, 0x0f, 0x4e, 0xc9, 0x62, 0x3c, 0xb7, 0x12, ++ 0x08, 0x2c, 0xf4, 0x3a, 0x09, 0x6d, 0x12, 0xc7, ++ 0x84, 0x53, 0xfe, 0x77, 0x47, 0xfb, 0x77, 0x38 ++}; ++static const u8 enc_output067[] __initconst = { ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x99, 0xca, 0xd8, 0x5f, 0x45, 0xca, 0x40, 0x94, ++ 0x2d, 0x0d, 0x4d, 0x5e, 0x95, 0x0a, 0xde, 0x22 ++}; ++static const u8 enc_assoc067[] __initconst = { ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, ++ 0x7f, 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce067[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key067[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input068[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x88, 0x7f, 0x6b, 0xe8, 0x7c, ++ 0x55, 0xd3, 0x04, 0x84, 0x9b, 0xbc, 0x01, 0x17, ++ 0xdf, 0x99, 0x47, 0x03, 0xfc, 0x04, 0xc4, 0x84, ++ 0x80, 0xe0, 0x30, 0xbe, 0x14, 0x2c, 0xd6, 0x41 ++}; ++static const u8 enc_output068[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x8b, 0xbe, 0x14, 0x52, 0x72, 0xe7, 0xc2, 0xd9, ++ 0xa1, 0x89, 0x1a, 0x3a, 0xb0, 0x98, 0x3d, 0x9d ++}; ++static const u8 enc_assoc068[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce068[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key068[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input069[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x88, 0x7f, 0x6b, 0xe8, 0x7c, ++ 0x55, 0xd3, 0x04, 0x84, 0x9b, 0xbc, 0x01, 0x17, ++ 0xdf, 0x99, 0x47, 0x03, 0xfc, 0x04, 0xc4, 0x84, ++ 0x80, 0xe0, 0x30, 0xbe, 0x14, 0x2c, 0xd6, 0x41, ++ 0xe3, 0xbc, 0xdb, 0x5b, 0xe1, 0x21, 0x03, 0x01, ++ 0x8b, 0xcd, 0xa1, 0xb6, 0x5e, 0xa3, 0x73, 0xd4, ++ 0x08, 0x69, 0xff, 0xd2, 0x13, 0xa1, 0xd9, 0x1a, ++ 0x53, 0xb7, 0xb2, 0x27, 0x01, 0x78, 0x02, 0x42 ++}; ++static const u8 enc_output069[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x3b, 0x41, 0x86, 0x19, 0x13, 0xa8, 0xf6, 0xde, ++ 0x7f, 0x61, 0xe2, 0x25, 0x63, 0x1b, 0xc3, 0x82 ++}; ++static const u8 enc_assoc069[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce069[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key069[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input070[] __initconst = { ++ 0x25, 0x6d, 0x40, 0x88, 0x7f, 0x6b, 0xe8, 0x7c, ++ 0x55, 0xd3, 0x04, 0x84, 0x9b, 0xbc, 0x01, 0x17, ++ 0xdf, 0x99, 0x47, 0x03, 0xfc, 0x04, 0xc4, 0x84, ++ 0x80, 0xe0, 0x30, 0xbe, 0x14, 0x2c, 0xd6, 0x41, ++ 0xe3, 0xbc, 0xdb, 0x5b, 0xe1, 0x21, 0x03, 0x01, ++ 0x8b, 0xcd, 0xa1, 0xb6, 0x5e, 0xa3, 0x73, 0xd4, ++ 0x08, 0x69, 0xff, 0xd2, 0x13, 0xa1, 0xd9, 0x1a, ++ 0x53, 0xb7, 0xb2, 0x27, 0x01, 0x78, 0x02, 0x42, ++ 0x7a, 0xda, 0x44, 0x42, 0xbd, 0x96, 0x40, 0x05, ++ 0x55, 0x27, 0xf2, 0x70, 0x53, 0x09, 0x7a, 0xfd, ++ 0xb7, 0x4c, 0x5a, 0xe2, 0x19, 0xf3, 0xfa, 0x7f, ++ 0x98, 0x1a, 0x49, 0x38, 0xba, 0x6c, 0x6d, 0x3b, ++ 0x9b, 0xb2, 0xf2, 0x84, 0x49, 0xb9, 0x10, 0x38, ++ 0xf3, 0xf0, 0xb1, 0x36, 0xe2, 0x3c, 0xb7, 0x12, ++ 0x77, 0xd3, 0x0b, 0xc5, 0x89, 0x6d, 0x12, 0xc7, ++ 0xfb, 0xac, 0x01, 0x88, 0xc7, 0xfb, 0x77, 0x38 ++}; ++static const u8 enc_output070[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x84, 0x28, 0xbc, 0xf0, 0x23, 0xec, 0x6b, 0xf3, ++ 0x1f, 0xd9, 0xef, 0xb2, 0x03, 0xff, 0x08, 0x71 ++}; ++static const u8 enc_assoc070[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce070[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key070[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input071[] __initconst = { ++ 0xda, 0x92, 0xbf, 0x77, 0x80, 0x94, 0x17, 0x83, ++ 0xaa, 0x2c, 0xfb, 0x7b, 0x64, 0x43, 0xfe, 0xe8, ++ 0x20, 0x66, 0xb8, 0xfc, 0x03, 0xfb, 0x3b, 0x7b, ++ 0x7f, 0x1f, 0xcf, 0x41, 0xeb, 0xd3, 0x29, 0xbe ++}; ++static const u8 enc_output071[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0x13, 0x9f, 0xdf, 0x64, 0x74, 0xea, 0x24, 0xf5, ++ 0x49, 0xb0, 0x75, 0x82, 0x5f, 0x2c, 0x76, 0x20 ++}; ++static const u8 enc_assoc071[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_nonce071[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key071[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input072[] __initconst = { ++ 0xda, 0x92, 0xbf, 0x77, 0x80, 0x94, 0x17, 0x83, ++ 0xaa, 0x2c, 0xfb, 0x7b, 0x64, 0x43, 0xfe, 0xe8, ++ 0x20, 0x66, 0xb8, 0xfc, 0x03, 0xfb, 0x3b, 0x7b, ++ 0x7f, 0x1f, 0xcf, 0x41, 0xeb, 0xd3, 0x29, 0xbe, ++ 0x1c, 0x43, 0x24, 0xa4, 0x1e, 0xde, 0xfc, 0xfe, ++ 0x74, 0x32, 0x5e, 0x49, 0xa1, 0x5c, 0x8c, 0x2b, ++ 0xf7, 0x96, 0x00, 0x2d, 0xec, 0x5e, 0x26, 0xe5, ++ 0xac, 0x48, 0x4d, 0xd8, 0xfe, 0x87, 0xfd, 0xbd ++}; ++static const u8 enc_output072[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xbb, 0xad, 0x8d, 0x86, 0x3b, 0x83, 0x5a, 0x8e, ++ 0x86, 0x64, 0xfd, 0x1d, 0x45, 0x66, 0xb6, 0xb4 ++}; ++static const u8 enc_assoc072[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_nonce072[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key072[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input073[] __initconst = { ++ 0xda, 0x92, 0xbf, 0x77, 0x80, 0x94, 0x17, 0x83, ++ 0xaa, 0x2c, 0xfb, 0x7b, 0x64, 0x43, 0xfe, 0xe8, ++ 0x20, 0x66, 0xb8, 0xfc, 0x03, 0xfb, 0x3b, 0x7b, ++ 0x7f, 0x1f, 0xcf, 0x41, 0xeb, 0xd3, 0x29, 0xbe, ++ 0x1c, 0x43, 0x24, 0xa4, 0x1e, 0xde, 0xfc, 0xfe, ++ 0x74, 0x32, 0x5e, 0x49, 0xa1, 0x5c, 0x8c, 0x2b, ++ 0xf7, 0x96, 0x00, 0x2d, 0xec, 0x5e, 0x26, 0xe5, ++ 0xac, 0x48, 0x4d, 0xd8, 0xfe, 0x87, 0xfd, 0xbd, ++ 0x85, 0x25, 0xbb, 0xbd, 0x42, 0x69, 0xbf, 0xfa, ++ 0xaa, 0xd8, 0x0d, 0x8f, 0xac, 0xf6, 0x85, 0x02, ++ 0x48, 0xb3, 0xa5, 0x1d, 0xe6, 0x0c, 0x05, 0x80, ++ 0x67, 0xe5, 0xb6, 0xc7, 0x45, 0x93, 0x92, 0xc4, ++ 0x64, 0x4d, 0x0d, 0x7b, 0xb6, 0x46, 0xef, 0xc7, ++ 0x0c, 0x0f, 0x4e, 0xc9, 0x1d, 0xc3, 0x48, 0xed, ++ 0x88, 0x2c, 0xf4, 0x3a, 0x76, 0x92, 0xed, 0x38, ++ 0x04, 0x53, 0xfe, 0x77, 0x38, 0x04, 0x88, 0xc7 ++}; ++static const u8 enc_output073[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0x42, 0xf2, 0x35, 0x42, 0x97, 0x84, 0x9a, 0x51, ++ 0x1d, 0x53, 0xe5, 0x57, 0x17, 0x72, 0xf7, 0x1f ++}; ++static const u8 enc_assoc073[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_nonce073[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0xee, 0x32, 0x00 ++}; ++static const u8 enc_key073[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input076[] __initconst = { ++ 0x1b, 0x99, 0x6f, 0x9a, 0x3c, 0xcc, 0x67, 0x85, ++ 0xde, 0x22, 0xff, 0x5b, 0x8a, 0xdd, 0x95, 0x02, ++ 0xce, 0x03, 0xa0, 0xfa, 0xf5, 0x99, 0x2a, 0x09, ++ 0x52, 0x2c, 0xdd, 0x12, 0x06, 0xd2, 0x20, 0xb8, ++ 0xf8, 0xbd, 0x07, 0xd1, 0xf1, 0xf5, 0xa1, 0xbd, ++ 0x9a, 0x71, 0xd1, 0x1c, 0x7f, 0x57, 0x9b, 0x85, ++ 0x58, 0x18, 0xc0, 0x8d, 0x4d, 0xe0, 0x36, 0x39, ++ 0x31, 0x83, 0xb7, 0xf5, 0x90, 0xb3, 0x35, 0xae, ++ 0xd8, 0xde, 0x5b, 0x57, 0xb1, 0x3c, 0x5f, 0xed, ++ 0xe2, 0x44, 0x1c, 0x3e, 0x18, 0x4a, 0xa9, 0xd4, ++ 0x6e, 0x61, 0x59, 0x85, 0x06, 0xb3, 0xe1, 0x1c, ++ 0x43, 0xc6, 0x2c, 0xbc, 0xac, 0xec, 0xed, 0x33, ++ 0x19, 0x08, 0x75, 0xb0, 0x12, 0x21, 0x8b, 0x19, ++ 0x30, 0xfb, 0x7c, 0x38, 0xec, 0x45, 0xac, 0x11, ++ 0xc3, 0x53, 0xd0, 0xcf, 0x93, 0x8d, 0xcc, 0xb9, ++ 0xef, 0xad, 0x8f, 0xed, 0xbe, 0x46, 0xda, 0xa5 ++}; ++static const u8 enc_output076[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x4b, 0x0b, 0xda, 0x8a, 0xd0, 0x43, 0x83, 0x0d, ++ 0x83, 0x19, 0xab, 0x82, 0xc5, 0x0c, 0x76, 0x63 ++}; ++static const u8 enc_assoc076[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce076[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x07, 0xb4, 0xf0 ++}; ++static const u8 enc_key076[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input077[] __initconst = { ++ 0x86, 0xcb, 0xac, 0xae, 0x4d, 0x3f, 0x74, 0xae, ++ 0x01, 0x21, 0x3e, 0x05, 0x51, 0xcc, 0x15, 0x16, ++ 0x0e, 0xa1, 0xbe, 0x84, 0x08, 0xe3, 0xd5, 0xd7, ++ 0x4f, 0x01, 0x46, 0x49, 0x95, 0xa6, 0x9e, 0x61, ++ 0x76, 0xcb, 0x9e, 0x02, 0xb2, 0x24, 0x7e, 0xd2, ++ 0x99, 0x89, 0x2f, 0x91, 0x82, 0xa4, 0x5c, 0xaf, ++ 0x4c, 0x69, 0x40, 0x56, 0x11, 0x76, 0x6e, 0xdf, ++ 0xaf, 0xdc, 0x28, 0x55, 0x19, 0xea, 0x30, 0x48, ++ 0x0c, 0x44, 0xf0, 0x5e, 0x78, 0x1e, 0xac, 0xf8, ++ 0xfc, 0xec, 0xc7, 0x09, 0x0a, 0xbb, 0x28, 0xfa, ++ 0x5f, 0xd5, 0x85, 0xac, 0x8c, 0xda, 0x7e, 0x87, ++ 0x72, 0xe5, 0x94, 0xe4, 0xce, 0x6c, 0x88, 0x32, ++ 0x81, 0x93, 0x2e, 0x0f, 0x89, 0xf8, 0x77, 0xa1, ++ 0xf0, 0x4d, 0x9c, 0x32, 0xb0, 0x6c, 0xf9, 0x0b, ++ 0x0e, 0x76, 0x2b, 0x43, 0x0c, 0x4d, 0x51, 0x7c, ++ 0x97, 0x10, 0x70, 0x68, 0xf4, 0x98, 0xef, 0x7f ++}; ++static const u8 enc_output077[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x4b, 0xc9, 0x8f, 0x72, 0xc4, 0x94, 0xc2, 0xa4, ++ 0x3c, 0x2b, 0x15, 0xa1, 0x04, 0x3f, 0x1c, 0xfa ++}; ++static const u8 enc_assoc077[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce077[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x20, 0xfb, 0x66 ++}; ++static const u8 enc_key077[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input078[] __initconst = { ++ 0xfa, 0xb1, 0xcd, 0xdf, 0x4f, 0xe1, 0x98, 0xef, ++ 0x63, 0xad, 0xd8, 0x81, 0xd6, 0xea, 0xd6, 0xc5, ++ 0x76, 0x37, 0xbb, 0xe9, 0x20, 0x18, 0xca, 0x7c, ++ 0x0b, 0x96, 0xfb, 0xa0, 0x87, 0x1e, 0x93, 0x2d, ++ 0xb1, 0xfb, 0xf9, 0x07, 0x61, 0xbe, 0x25, 0xdf, ++ 0x8d, 0xfa, 0xf9, 0x31, 0xce, 0x57, 0x57, 0xe6, ++ 0x17, 0xb3, 0xd7, 0xa9, 0xf0, 0xbf, 0x0f, 0xfe, ++ 0x5d, 0x59, 0x1a, 0x33, 0xc1, 0x43, 0xb8, 0xf5, ++ 0x3f, 0xd0, 0xb5, 0xa1, 0x96, 0x09, 0xfd, 0x62, ++ 0xe5, 0xc2, 0x51, 0xa4, 0x28, 0x1a, 0x20, 0x0c, ++ 0xfd, 0xc3, 0x4f, 0x28, 0x17, 0x10, 0x40, 0x6f, ++ 0x4e, 0x37, 0x62, 0x54, 0x46, 0xff, 0x6e, 0xf2, ++ 0x24, 0x91, 0x3d, 0xeb, 0x0d, 0x89, 0xaf, 0x33, ++ 0x71, 0x28, 0xe3, 0xd1, 0x55, 0xd1, 0x6d, 0x3e, ++ 0xc3, 0x24, 0x60, 0x41, 0x43, 0x21, 0x43, 0xe9, ++ 0xab, 0x3a, 0x6d, 0x2c, 0xcc, 0x2f, 0x4d, 0x62 ++}; ++static const u8 enc_output078[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xf7, 0xe9, 0xe1, 0x51, 0xb0, 0x25, 0x33, 0xc7, ++ 0x46, 0x58, 0xbf, 0xc7, 0x73, 0x7c, 0x68, 0x0d ++}; ++static const u8 enc_assoc078[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce078[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0xbb, 0x90 ++}; ++static const u8 enc_key078[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input079[] __initconst = { ++ 0x22, 0x72, 0x02, 0xbe, 0x7f, 0x35, 0x15, 0xe9, ++ 0xd1, 0xc0, 0x2e, 0xea, 0x2f, 0x19, 0x50, 0xb6, ++ 0x48, 0x1b, 0x04, 0x8a, 0x4c, 0x91, 0x50, 0x6c, ++ 0xb4, 0x0d, 0x50, 0x4e, 0x6c, 0x94, 0x9f, 0x82, ++ 0xd1, 0x97, 0xc2, 0x5a, 0xd1, 0x7d, 0xc7, 0x21, ++ 0x65, 0x11, 0x25, 0x78, 0x2a, 0xc7, 0xa7, 0x12, ++ 0x47, 0xfe, 0xae, 0xf3, 0x2f, 0x1f, 0x25, 0x0c, ++ 0xe4, 0xbb, 0x8f, 0x79, 0xac, 0xaa, 0x17, 0x9d, ++ 0x45, 0xa7, 0xb0, 0x54, 0x5f, 0x09, 0x24, 0x32, ++ 0x5e, 0xfa, 0x87, 0xd5, 0xe4, 0x41, 0xd2, 0x84, ++ 0x78, 0xc6, 0x1f, 0x22, 0x23, 0xee, 0x67, 0xc3, ++ 0xb4, 0x1f, 0x43, 0x94, 0x53, 0x5e, 0x2a, 0x24, ++ 0x36, 0x9a, 0x2e, 0x16, 0x61, 0x3c, 0x45, 0x94, ++ 0x90, 0xc1, 0x4f, 0xb1, 0xd7, 0x55, 0xfe, 0x53, ++ 0xfb, 0xe1, 0xee, 0x45, 0xb1, 0xb2, 0x1f, 0x71, ++ 0x62, 0xe2, 0xfc, 0xaa, 0x74, 0x2a, 0xbe, 0xfd ++}; ++static const u8 enc_output079[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x79, 0x5b, 0xcf, 0xf6, 0x47, 0xc5, 0x53, 0xc2, ++ 0xe4, 0xeb, 0x6e, 0x0e, 0xaf, 0xd9, 0xe0, 0x4e ++}; ++static const u8 enc_assoc079[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce079[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x48, 0x4a ++}; ++static const u8 enc_key079[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input080[] __initconst = { ++ 0xfa, 0xe5, 0x83, 0x45, 0xc1, 0x6c, 0xb0, 0xf5, ++ 0xcc, 0x53, 0x7f, 0x2b, 0x1b, 0x34, 0x69, 0xc9, ++ 0x69, 0x46, 0x3b, 0x3e, 0xa7, 0x1b, 0xcf, 0x6b, ++ 0x98, 0xd6, 0x69, 0xa8, 0xe6, 0x0e, 0x04, 0xfc, ++ 0x08, 0xd5, 0xfd, 0x06, 0x9c, 0x36, 0x26, 0x38, ++ 0xe3, 0x40, 0x0e, 0xf4, 0xcb, 0x24, 0x2e, 0x27, ++ 0xe2, 0x24, 0x5e, 0x68, 0xcb, 0x9e, 0xc5, 0x83, ++ 0xda, 0x53, 0x40, 0xb1, 0x2e, 0xdf, 0x42, 0x3b, ++ 0x73, 0x26, 0xad, 0x20, 0xfe, 0xeb, 0x57, 0xda, ++ 0xca, 0x2e, 0x04, 0x67, 0xa3, 0x28, 0x99, 0xb4, ++ 0x2d, 0xf8, 0xe5, 0x6d, 0x84, 0xe0, 0x06, 0xbc, ++ 0x8a, 0x7a, 0xcc, 0x73, 0x1e, 0x7c, 0x1f, 0x6b, ++ 0xec, 0xb5, 0x71, 0x9f, 0x70, 0x77, 0xf0, 0xd4, ++ 0xf4, 0xc6, 0x1a, 0xb1, 0x1e, 0xba, 0xc1, 0x00, ++ 0x18, 0x01, 0xce, 0x33, 0xc4, 0xe4, 0xa7, 0x7d, ++ 0x83, 0x1d, 0x3c, 0xe3, 0x4e, 0x84, 0x10, 0xe1 ++}; ++static const u8 enc_output080[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x19, 0x46, 0xd6, 0x53, 0x96, 0x0f, 0x94, 0x7a, ++ 0x74, 0xd3, 0xe8, 0x09, 0x3c, 0xf4, 0x85, 0x02 ++}; ++static const u8 enc_assoc080[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce080[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x93, 0x2f, 0x40 ++}; ++static const u8 enc_key080[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input081[] __initconst = { ++ 0xeb, 0xb2, 0x16, 0xdd, 0xd7, 0xca, 0x70, 0x92, ++ 0x15, 0xf5, 0x03, 0xdf, 0x9c, 0xe6, 0x3c, 0x5c, ++ 0xd2, 0x19, 0x4e, 0x7d, 0x90, 0x99, 0xe8, 0xa9, ++ 0x0b, 0x2a, 0xfa, 0xad, 0x5e, 0xba, 0x35, 0x06, ++ 0x99, 0x25, 0xa6, 0x03, 0xfd, 0xbc, 0x34, 0x1a, ++ 0xae, 0xd4, 0x15, 0x05, 0xb1, 0x09, 0x41, 0xfa, ++ 0x38, 0x56, 0xa7, 0xe2, 0x47, 0xb1, 0x04, 0x07, ++ 0x09, 0x74, 0x6c, 0xfc, 0x20, 0x96, 0xca, 0xa6, ++ 0x31, 0xb2, 0xff, 0xf4, 0x1c, 0x25, 0x05, 0x06, ++ 0xd8, 0x89, 0xc1, 0xc9, 0x06, 0x71, 0xad, 0xe8, ++ 0x53, 0xee, 0x63, 0x94, 0xc1, 0x91, 0x92, 0xa5, ++ 0xcf, 0x37, 0x10, 0xd1, 0x07, 0x30, 0x99, 0xe5, ++ 0xbc, 0x94, 0x65, 0x82, 0xfc, 0x0f, 0xab, 0x9f, ++ 0x54, 0x3c, 0x71, 0x6a, 0xe2, 0x48, 0x6a, 0x86, ++ 0x83, 0xfd, 0xca, 0x39, 0xd2, 0xe1, 0x4f, 0x23, ++ 0xd0, 0x0a, 0x58, 0x26, 0x64, 0xf4, 0xec, 0xb1 ++}; ++static const u8 enc_output081[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x36, 0xc3, 0x00, 0x29, 0x85, 0xdd, 0x21, 0xba, ++ 0xf8, 0x95, 0xd6, 0x33, 0x57, 0x3f, 0x12, 0xc0 ++}; ++static const u8 enc_assoc081[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce081[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0xe2, 0x93, 0x35 ++}; ++static const u8 enc_key081[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input082[] __initconst = { ++ 0x40, 0x8a, 0xe6, 0xef, 0x1c, 0x7e, 0xf0, 0xfb, ++ 0x2c, 0x2d, 0x61, 0x08, 0x16, 0xfc, 0x78, 0x49, ++ 0xef, 0xa5, 0x8f, 0x78, 0x27, 0x3f, 0x5f, 0x16, ++ 0x6e, 0xa6, 0x5f, 0x81, 0xb5, 0x75, 0x74, 0x7d, ++ 0x03, 0x5b, 0x30, 0x40, 0xfe, 0xde, 0x1e, 0xb9, ++ 0x45, 0x97, 0x88, 0x66, 0x97, 0x88, 0x40, 0x8e, ++ 0x00, 0x41, 0x3b, 0x3e, 0x37, 0x6d, 0x15, 0x2d, ++ 0x20, 0x4a, 0xa2, 0xb7, 0xa8, 0x35, 0x58, 0xfc, ++ 0xd4, 0x8a, 0x0e, 0xf7, 0xa2, 0x6b, 0x1c, 0xd6, ++ 0xd3, 0x5d, 0x23, 0xb3, 0xf5, 0xdf, 0xe0, 0xca, ++ 0x77, 0xa4, 0xce, 0x32, 0xb9, 0x4a, 0xbf, 0x83, ++ 0xda, 0x2a, 0xef, 0xca, 0xf0, 0x68, 0x38, 0x08, ++ 0x79, 0xe8, 0x9f, 0xb0, 0xa3, 0x82, 0x95, 0x95, ++ 0xcf, 0x44, 0xc3, 0x85, 0x2a, 0xe2, 0xcc, 0x66, ++ 0x2b, 0x68, 0x9f, 0x93, 0x55, 0xd9, 0xc1, 0x83, ++ 0x80, 0x1f, 0x6a, 0xcc, 0x31, 0x3f, 0x89, 0x07 ++}; ++static const u8 enc_output082[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x65, 0x14, 0x51, 0x8e, 0x0a, 0x26, 0x41, 0x42, ++ 0xe0, 0xb7, 0x35, 0x1f, 0x96, 0x7f, 0xc2, 0xae ++}; ++static const u8 enc_assoc082[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce082[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0xf7, 0xd5 ++}; ++static const u8 enc_key082[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input083[] __initconst = { ++ 0x0a, 0x0a, 0x24, 0x49, 0x9b, 0xca, 0xde, 0x58, ++ 0xcf, 0x15, 0x76, 0xc3, 0x12, 0xac, 0xa9, 0x84, ++ 0x71, 0x8c, 0xb4, 0xcc, 0x7e, 0x01, 0x53, 0xf5, ++ 0xa9, 0x01, 0x58, 0x10, 0x85, 0x96, 0x44, 0xdf, ++ 0xc0, 0x21, 0x17, 0x4e, 0x0b, 0x06, 0x0a, 0x39, ++ 0x74, 0x48, 0xde, 0x8b, 0x48, 0x4a, 0x86, 0x03, ++ 0xbe, 0x68, 0x0a, 0x69, 0x34, 0xc0, 0x90, 0x6f, ++ 0x30, 0xdd, 0x17, 0xea, 0xe2, 0xd4, 0xc5, 0xfa, ++ 0xa7, 0x77, 0xf8, 0xca, 0x53, 0x37, 0x0e, 0x08, ++ 0x33, 0x1b, 0x88, 0xc3, 0x42, 0xba, 0xc9, 0x59, ++ 0x78, 0x7b, 0xbb, 0x33, 0x93, 0x0e, 0x3b, 0x56, ++ 0xbe, 0x86, 0xda, 0x7f, 0x2a, 0x6e, 0xb1, 0xf9, ++ 0x40, 0x89, 0xd1, 0xd1, 0x81, 0x07, 0x4d, 0x43, ++ 0x02, 0xf8, 0xe0, 0x55, 0x2d, 0x0d, 0xe1, 0xfa, ++ 0xb3, 0x06, 0xa2, 0x1b, 0x42, 0xd4, 0xc3, 0xba, ++ 0x6e, 0x6f, 0x0c, 0xbc, 0xc8, 0x1e, 0x87, 0x7a ++}; ++static const u8 enc_output083[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x4c, 0x19, 0x4d, 0xa6, 0xa9, 0x9f, 0xd6, 0x5b, ++ 0x40, 0xe9, 0xca, 0xd7, 0x98, 0xf4, 0x4b, 0x19 ++}; ++static const u8 enc_assoc083[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce083[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x3d, 0xfc, 0xe4 ++}; ++static const u8 enc_key083[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input084[] __initconst = { ++ 0x4a, 0x0a, 0xaf, 0xf8, 0x49, 0x47, 0x29, 0x18, ++ 0x86, 0x91, 0x70, 0x13, 0x40, 0xf3, 0xce, 0x2b, ++ 0x8a, 0x78, 0xee, 0xd3, 0xa0, 0xf0, 0x65, 0x99, ++ 0x4b, 0x72, 0x48, 0x4e, 0x79, 0x91, 0xd2, 0x5c, ++ 0x29, 0xaa, 0x07, 0x5e, 0xb1, 0xfc, 0x16, 0xde, ++ 0x93, 0xfe, 0x06, 0x90, 0x58, 0x11, 0x2a, 0xb2, ++ 0x84, 0xa3, 0xed, 0x18, 0x78, 0x03, 0x26, 0xd1, ++ 0x25, 0x8a, 0x47, 0x22, 0x2f, 0xa6, 0x33, 0xd8, ++ 0xb2, 0x9f, 0x3b, 0xd9, 0x15, 0x0b, 0x23, 0x9b, ++ 0x15, 0x46, 0xc2, 0xbb, 0x9b, 0x9f, 0x41, 0x0f, ++ 0xeb, 0xea, 0xd3, 0x96, 0x00, 0x0e, 0xe4, 0x77, ++ 0x70, 0x15, 0x32, 0xc3, 0xd0, 0xf5, 0xfb, 0xf8, ++ 0x95, 0xd2, 0x80, 0x19, 0x6d, 0x2f, 0x73, 0x7c, ++ 0x5e, 0x9f, 0xec, 0x50, 0xd9, 0x2b, 0xb0, 0xdf, ++ 0x5d, 0x7e, 0x51, 0x3b, 0xe5, 0xb8, 0xea, 0x97, ++ 0x13, 0x10, 0xd5, 0xbf, 0x16, 0xba, 0x7a, 0xee ++}; ++static const u8 enc_output084[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xc8, 0xae, 0x77, 0x88, 0xcd, 0x28, 0x74, 0xab, ++ 0xc1, 0x38, 0x54, 0x1e, 0x11, 0xfd, 0x05, 0x87 ++}; ++static const u8 enc_assoc084[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce084[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x01, 0x84, 0x86, 0xa8 ++}; ++static const u8 enc_key084[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input085[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x78, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x9f, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x9c, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0x47, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0xd4, 0xd2, 0x06, 0x61, 0x6f, 0x92, 0x93, 0xf6, ++ 0x5b, 0x45, 0xdb, 0xbc, 0x74, 0xe7, 0xc2, 0xed, ++ 0xfb, 0xcb, 0xbf, 0x1c, 0xfb, 0x67, 0x9b, 0xb7, ++ 0x39, 0xa5, 0x86, 0x2d, 0xe2, 0xbc, 0xb9, 0x37, ++ 0xf7, 0x4d, 0x5b, 0xf8, 0x67, 0x1c, 0x5a, 0x8a, ++ 0x50, 0x92, 0xf6, 0x1d, 0x54, 0xc9, 0xaa, 0x5b ++}; ++static const u8 enc_output085[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x93, 0x3a, 0x51, 0x63, 0xc7, 0xf6, 0x23, 0x68, ++ 0x32, 0x7b, 0x3f, 0xbc, 0x10, 0x36, 0xc9, 0x43 ++}; ++static const u8 enc_assoc085[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce085[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key085[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input093[] __initconst = { ++ 0x00, 0x52, 0x35, 0xd2, 0xa9, 0x19, 0xf2, 0x8d, ++ 0x3d, 0xb7, 0x66, 0x4a, 0x34, 0xae, 0x6b, 0x44, ++ 0x4d, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x5b, 0x8b, 0x94, 0x50, 0x9e, 0x2b, 0x74, 0xa3, ++ 0x6d, 0x34, 0x6e, 0x33, 0xd5, 0x72, 0x65, 0x9b, ++ 0xa9, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0x83, 0xdc, 0xe9, 0xf3, 0x07, 0x3e, 0xfa, 0xdb, ++ 0x7d, 0x23, 0xb8, 0x7a, 0xce, 0x35, 0x16, 0x8c ++}; ++static const u8 enc_output093[] __initconst = { ++ 0x00, 0x39, 0xe2, 0xfd, 0x2f, 0xd3, 0x12, 0x14, ++ 0x9e, 0x98, 0x98, 0x80, 0x88, 0x48, 0x13, 0xe7, ++ 0xca, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x3b, 0x0e, 0x86, 0x9a, 0xaa, 0x8e, 0xa4, 0x96, ++ 0x32, 0xff, 0xff, 0x37, 0xb9, 0xe8, 0xce, 0x00, ++ 0xca, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x3b, 0x0e, 0x86, 0x9a, 0xaa, 0x8e, 0xa4, 0x96, ++ 0x32, 0xff, 0xff, 0x37, 0xb9, 0xe8, 0xce, 0x00, ++ 0xa5, 0x19, 0xac, 0x1a, 0x35, 0xb4, 0xa5, 0x77, ++ 0x87, 0x51, 0x0a, 0xf7, 0x8d, 0x8d, 0x20, 0x0a ++}; ++static const u8 enc_assoc093[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce093[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key093[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input094[] __initconst = { ++ 0xd3, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xe5, 0xda, 0x78, 0x76, 0x6f, 0xa1, 0x92, 0x90, ++ 0xc0, 0x31, 0xf7, 0x52, 0x08, 0x50, 0x67, 0x45, ++ 0xae, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x49, 0x6d, 0xde, 0xb0, 0x55, 0x09, 0xc6, 0xef, ++ 0xff, 0xab, 0x75, 0xeb, 0x2d, 0xf4, 0xab, 0x09, ++ 0x76, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x01, 0x49, 0xef, 0x50, 0x4b, 0x71, 0xb1, 0x20, ++ 0xca, 0x4f, 0xf3, 0x95, 0x19, 0xc2, 0xc2, 0x10 ++}; ++static const u8 enc_output094[] __initconst = { ++ 0xd3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x62, 0x18, 0xb2, 0x7f, 0x83, 0xb8, 0xb4, 0x66, ++ 0x02, 0xf6, 0xe1, 0xd8, 0x34, 0x20, 0x7b, 0x02, ++ 0xce, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x2a, 0x64, 0x16, 0xce, 0xdb, 0x1c, 0xdd, 0x29, ++ 0x6e, 0xf5, 0xd7, 0xd6, 0x92, 0xda, 0xff, 0x02, ++ 0xce, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x2a, 0x64, 0x16, 0xce, 0xdb, 0x1c, 0xdd, 0x29, ++ 0x6e, 0xf5, 0xd7, 0xd6, 0x92, 0xda, 0xff, 0x02, ++ 0x30, 0x2f, 0xe8, 0x2a, 0xb0, 0xa0, 0x9a, 0xf6, ++ 0x44, 0x00, 0xd0, 0x15, 0xae, 0x83, 0xd9, 0xcc ++}; ++static const u8 enc_assoc094[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce094[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key094[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input095[] __initconst = { ++ 0xe9, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x6d, 0xf1, 0x39, 0x4e, 0xdc, 0x53, 0x9b, 0x5b, ++ 0x3a, 0x09, 0x57, 0xbe, 0x0f, 0xb8, 0x59, 0x46, ++ 0x80, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0xd1, 0x76, 0x9f, 0xe8, 0x06, 0xbb, 0xfe, 0xb6, ++ 0xf5, 0x90, 0x95, 0x0f, 0x2e, 0xac, 0x9e, 0x0a, ++ 0x58, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x99, 0x52, 0xae, 0x08, 0x18, 0xc3, 0x89, 0x79, ++ 0xc0, 0x74, 0x13, 0x71, 0x1a, 0x9a, 0xf7, 0x13 ++}; ++static const u8 enc_output095[] __initconst = { ++ 0xe9, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xea, 0x33, 0xf3, 0x47, 0x30, 0x4a, 0xbd, 0xad, ++ 0xf8, 0xce, 0x41, 0x34, 0x33, 0xc8, 0x45, 0x01, ++ 0xe0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xb2, 0x7f, 0x57, 0x96, 0x88, 0xae, 0xe5, 0x70, ++ 0x64, 0xce, 0x37, 0x32, 0x91, 0x82, 0xca, 0x01, ++ 0xe0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xb2, 0x7f, 0x57, 0x96, 0x88, 0xae, 0xe5, 0x70, ++ 0x64, 0xce, 0x37, 0x32, 0x91, 0x82, 0xca, 0x01, ++ 0x98, 0xa7, 0xe8, 0x36, 0xe0, 0xee, 0x4d, 0x02, ++ 0x35, 0x00, 0xd0, 0x55, 0x7e, 0xc2, 0xcb, 0xe0 ++}; ++static const u8 enc_assoc095[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce095[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key095[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input096[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x64, 0xf9, 0x0f, 0x5b, 0x26, 0x92, 0xb8, 0x60, ++ 0xd4, 0x59, 0x6f, 0xf4, 0xb3, 0x40, 0x2c, 0x5c, ++ 0x00, 0xb9, 0xbb, 0x53, 0x70, 0x7a, 0xa6, 0x67, ++ 0xd3, 0x56, 0xfe, 0x50, 0xc7, 0x19, 0x96, 0x94, ++ 0x03, 0x35, 0x61, 0xe7, 0xca, 0xca, 0x6d, 0x94, ++ 0x1d, 0xc3, 0xcd, 0x69, 0x14, 0xad, 0x69, 0x04 ++}; ++static const u8 enc_output096[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xe3, 0x3b, 0xc5, 0x52, 0xca, 0x8b, 0x9e, 0x96, ++ 0x16, 0x9e, 0x79, 0x7e, 0x8f, 0x30, 0x30, 0x1b, ++ 0x60, 0x3c, 0xa9, 0x99, 0x44, 0xdf, 0x76, 0x52, ++ 0x8c, 0x9d, 0x6f, 0x54, 0xab, 0x83, 0x3d, 0x0f, ++ 0x60, 0x3c, 0xa9, 0x99, 0x44, 0xdf, 0x76, 0x52, ++ 0x8c, 0x9d, 0x6f, 0x54, 0xab, 0x83, 0x3d, 0x0f, ++ 0x6a, 0xb8, 0xdc, 0xe2, 0xc5, 0x9d, 0xa4, 0x73, ++ 0x71, 0x30, 0xb0, 0x25, 0x2f, 0x68, 0xa8, 0xd8 ++}; ++static const u8 enc_assoc096[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce096[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key096[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input097[] __initconst = { ++ 0x68, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xb0, 0x8f, 0x25, 0x67, 0x5b, 0x9b, 0xcb, 0xf6, ++ 0xe3, 0x84, 0x07, 0xde, 0x2e, 0xc7, 0x5a, 0x47, ++ 0x9f, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x2d, 0x2a, 0xf7, 0xcd, 0x6b, 0x08, 0x05, 0x01, ++ 0xd3, 0x1b, 0xa5, 0x4f, 0xb2, 0xeb, 0x75, 0x96, ++ 0x47, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x65, 0x0e, 0xc6, 0x2d, 0x75, 0x70, 0x72, 0xce, ++ 0xe6, 0xff, 0x23, 0x31, 0x86, 0xdd, 0x1c, 0x8f ++}; ++static const u8 enc_output097[] __initconst = { ++ 0x68, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x37, 0x4d, 0xef, 0x6e, 0xb7, 0x82, 0xed, 0x00, ++ 0x21, 0x43, 0x11, 0x54, 0x12, 0xb7, 0x46, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x4e, 0x23, 0x3f, 0xb3, 0xe5, 0x1d, 0x1e, 0xc7, ++ 0x42, 0x45, 0x07, 0x72, 0x0d, 0xc5, 0x21, 0x9d, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x4e, 0x23, 0x3f, 0xb3, 0xe5, 0x1d, 0x1e, 0xc7, ++ 0x42, 0x45, 0x07, 0x72, 0x0d, 0xc5, 0x21, 0x9d, ++ 0x04, 0x4d, 0xea, 0x60, 0x88, 0x80, 0x41, 0x2b, ++ 0xfd, 0xff, 0xcf, 0x35, 0x57, 0x9e, 0x9b, 0x26 ++}; ++static const u8 enc_assoc097[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce097[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key097[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input098[] __initconst = { ++ 0x6d, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xa1, 0x61, 0xb5, 0xab, 0x04, 0x09, 0x00, 0x62, ++ 0x9e, 0xfe, 0xff, 0x78, 0xd7, 0xd8, 0x6b, 0x45, ++ 0x9f, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0xc6, 0xf8, 0x07, 0x8c, 0xc8, 0xef, 0x12, 0xa0, ++ 0xff, 0x65, 0x7d, 0x6d, 0x08, 0xdb, 0x10, 0xb8, ++ 0x47, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x8e, 0xdc, 0x36, 0x6c, 0xd6, 0x97, 0x65, 0x6f, ++ 0xca, 0x81, 0xfb, 0x13, 0x3c, 0xed, 0x79, 0xa1 ++}; ++static const u8 enc_output098[] __initconst = { ++ 0x6d, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x26, 0xa3, 0x7f, 0xa2, 0xe8, 0x10, 0x26, 0x94, ++ 0x5c, 0x39, 0xe9, 0xf2, 0xeb, 0xa8, 0x77, 0x02, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xa5, 0xf1, 0xcf, 0xf2, 0x46, 0xfa, 0x09, 0x66, ++ 0x6e, 0x3b, 0xdf, 0x50, 0xb7, 0xf5, 0x44, 0xb3, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xa5, 0xf1, 0xcf, 0xf2, 0x46, 0xfa, 0x09, 0x66, ++ 0x6e, 0x3b, 0xdf, 0x50, 0xb7, 0xf5, 0x44, 0xb3, ++ 0x1e, 0x6b, 0xea, 0x63, 0x14, 0x54, 0x2e, 0x2e, ++ 0xf9, 0xff, 0xcf, 0x45, 0x0b, 0x2e, 0x98, 0x2b ++}; ++static const u8 enc_assoc098[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce098[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key098[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input099[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xfc, 0x01, 0xb8, 0x91, 0xe5, 0xf0, 0xf9, 0x12, ++ 0x8d, 0x7d, 0x1c, 0x57, 0x91, 0x92, 0xb6, 0x98, ++ 0x63, 0x41, 0x44, 0x15, 0xb6, 0x99, 0x68, 0x95, ++ 0x9a, 0x72, 0x91, 0xb7, 0xa5, 0xaf, 0x13, 0x48, ++ 0x60, 0xcd, 0x9e, 0xa1, 0x0c, 0x29, 0xa3, 0x66, ++ 0x54, 0xe7, 0xa2, 0x8e, 0x76, 0x1b, 0xec, 0xd8 ++}; ++static const u8 enc_output099[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x7b, 0xc3, 0x72, 0x98, 0x09, 0xe9, 0xdf, 0xe4, ++ 0x4f, 0xba, 0x0a, 0xdd, 0xad, 0xe2, 0xaa, 0xdf, ++ 0x03, 0xc4, 0x56, 0xdf, 0x82, 0x3c, 0xb8, 0xa0, ++ 0xc5, 0xb9, 0x00, 0xb3, 0xc9, 0x35, 0xb8, 0xd3, ++ 0x03, 0xc4, 0x56, 0xdf, 0x82, 0x3c, 0xb8, 0xa0, ++ 0xc5, 0xb9, 0x00, 0xb3, 0xc9, 0x35, 0xb8, 0xd3, ++ 0xed, 0x20, 0x17, 0xc8, 0xdb, 0xa4, 0x77, 0x56, ++ 0x29, 0x04, 0x9d, 0x78, 0x6e, 0x3b, 0xce, 0xb1 ++}; ++static const u8 enc_assoc099[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce099[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key099[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input100[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x6b, 0x6d, 0xc9, 0xd2, 0x1a, 0x81, 0x9e, 0x70, ++ 0xb5, 0x77, 0xf4, 0x41, 0x37, 0xd3, 0xd6, 0xbd, ++ 0x13, 0x35, 0xf5, 0xeb, 0x44, 0x49, 0x40, 0x77, ++ 0xb2, 0x64, 0x49, 0xa5, 0x4b, 0x6c, 0x7c, 0x75, ++ 0x10, 0xb9, 0x2f, 0x5f, 0xfe, 0xf9, 0x8b, 0x84, ++ 0x7c, 0xf1, 0x7a, 0x9c, 0x98, 0xd8, 0x83, 0xe5 ++}; ++static const u8 enc_output100[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xec, 0xaf, 0x03, 0xdb, 0xf6, 0x98, 0xb8, 0x86, ++ 0x77, 0xb0, 0xe2, 0xcb, 0x0b, 0xa3, 0xca, 0xfa, ++ 0x73, 0xb0, 0xe7, 0x21, 0x70, 0xec, 0x90, 0x42, ++ 0xed, 0xaf, 0xd8, 0xa1, 0x27, 0xf6, 0xd7, 0xee, ++ 0x73, 0xb0, 0xe7, 0x21, 0x70, 0xec, 0x90, 0x42, ++ 0xed, 0xaf, 0xd8, 0xa1, 0x27, 0xf6, 0xd7, 0xee, ++ 0x07, 0x3f, 0x17, 0xcb, 0x67, 0x78, 0x64, 0x59, ++ 0x25, 0x04, 0x9d, 0x88, 0x22, 0xcb, 0xca, 0xb6 ++}; ++static const u8 enc_assoc100[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce100[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key100[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input101[] __initconst = { ++ 0xff, 0xcb, 0x2b, 0x11, 0x06, 0xf8, 0x23, 0x4c, ++ 0x5e, 0x99, 0xd4, 0xdb, 0x4c, 0x70, 0x48, 0xde, ++ 0x32, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x16, 0xe9, 0x88, 0x4a, 0x11, 0x4f, 0x0e, 0x92, ++ 0x66, 0xce, 0xa3, 0x88, 0x5f, 0xe3, 0x6b, 0x9f, ++ 0xd6, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0xce, 0xbe, 0xf5, 0xe9, 0x88, 0x5a, 0x80, 0xea, ++ 0x76, 0xd9, 0x75, 0xc1, 0x44, 0xa4, 0x18, 0x88 ++}; ++static const u8 enc_output101[] __initconst = { ++ 0xff, 0xa0, 0xfc, 0x3e, 0x80, 0x32, 0xc3, 0xd5, ++ 0xfd, 0xb6, 0x2a, 0x11, 0xf0, 0x96, 0x30, 0x7d, ++ 0xb5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x76, 0x6c, 0x9a, 0x80, 0x25, 0xea, 0xde, 0xa7, ++ 0x39, 0x05, 0x32, 0x8c, 0x33, 0x79, 0xc0, 0x04, ++ 0xb5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x76, 0x6c, 0x9a, 0x80, 0x25, 0xea, 0xde, 0xa7, ++ 0x39, 0x05, 0x32, 0x8c, 0x33, 0x79, 0xc0, 0x04, ++ 0x8b, 0x9b, 0xb4, 0xb4, 0x86, 0x12, 0x89, 0x65, ++ 0x8c, 0x69, 0x6a, 0x83, 0x40, 0x15, 0x04, 0x05 ++}; ++static const u8 enc_assoc101[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce101[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key101[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input102[] __initconst = { ++ 0x6f, 0x9e, 0x70, 0xed, 0x3b, 0x8b, 0xac, 0xa0, ++ 0x26, 0xe4, 0x6a, 0x5a, 0x09, 0x43, 0x15, 0x8d, ++ 0x21, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x0c, 0x61, 0x2c, 0x5e, 0x8d, 0x89, 0xa8, 0x73, ++ 0xdb, 0xca, 0xad, 0x5b, 0x73, 0x46, 0x42, 0x9b, ++ 0xc5, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0xd4, 0x36, 0x51, 0xfd, 0x14, 0x9c, 0x26, 0x0b, ++ 0xcb, 0xdd, 0x7b, 0x12, 0x68, 0x01, 0x31, 0x8c ++}; ++static const u8 enc_output102[] __initconst = { ++ 0x6f, 0xf5, 0xa7, 0xc2, 0xbd, 0x41, 0x4c, 0x39, ++ 0x85, 0xcb, 0x94, 0x90, 0xb5, 0xa5, 0x6d, 0x2e, ++ 0xa6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x6c, 0xe4, 0x3e, 0x94, 0xb9, 0x2c, 0x78, 0x46, ++ 0x84, 0x01, 0x3c, 0x5f, 0x1f, 0xdc, 0xe9, 0x00, ++ 0xa6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x6c, 0xe4, 0x3e, 0x94, 0xb9, 0x2c, 0x78, 0x46, ++ 0x84, 0x01, 0x3c, 0x5f, 0x1f, 0xdc, 0xe9, 0x00, ++ 0x8b, 0x3b, 0xbd, 0x51, 0x64, 0x44, 0x59, 0x56, ++ 0x8d, 0x81, 0xca, 0x1f, 0xa7, 0x2c, 0xe4, 0x04 ++}; ++static const u8 enc_assoc102[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce102[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key102[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input103[] __initconst = { ++ 0x41, 0x2b, 0x08, 0x0a, 0x3e, 0x19, 0xc1, 0x0d, ++ 0x44, 0xa1, 0xaf, 0x1e, 0xab, 0xde, 0xb4, 0xce, ++ 0x35, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x6b, 0x83, 0x94, 0x33, 0x09, 0x21, 0x48, 0x6c, ++ 0xa1, 0x1d, 0x29, 0x1c, 0x3e, 0x97, 0xee, 0x9a, ++ 0xd1, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0xb3, 0xd4, 0xe9, 0x90, 0x90, 0x34, 0xc6, 0x14, ++ 0xb1, 0x0a, 0xff, 0x55, 0x25, 0xd0, 0x9d, 0x8d ++}; ++static const u8 enc_output103[] __initconst = { ++ 0x41, 0x40, 0xdf, 0x25, 0xb8, 0xd3, 0x21, 0x94, ++ 0xe7, 0x8e, 0x51, 0xd4, 0x17, 0x38, 0xcc, 0x6d, ++ 0xb2, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x0b, 0x06, 0x86, 0xf9, 0x3d, 0x84, 0x98, 0x59, ++ 0xfe, 0xd6, 0xb8, 0x18, 0x52, 0x0d, 0x45, 0x01, ++ 0xb2, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x0b, 0x06, 0x86, 0xf9, 0x3d, 0x84, 0x98, 0x59, ++ 0xfe, 0xd6, 0xb8, 0x18, 0x52, 0x0d, 0x45, 0x01, ++ 0x86, 0xfb, 0xab, 0x2b, 0x4a, 0x94, 0xf4, 0x7a, ++ 0xa5, 0x6f, 0x0a, 0xea, 0x65, 0xd1, 0x10, 0x08 ++}; ++static const u8 enc_assoc103[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce103[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key103[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input104[] __initconst = { ++ 0xb2, 0x47, 0xa7, 0x47, 0x23, 0x49, 0x1a, 0xac, ++ 0xac, 0xaa, 0xd7, 0x09, 0xc9, 0x1e, 0x93, 0x2b, ++ 0x31, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x9a, 0xde, 0x04, 0xe7, 0x5b, 0xb7, 0x01, 0xd9, ++ 0x66, 0x06, 0x01, 0xb3, 0x47, 0x65, 0xde, 0x98, ++ 0xd5, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0x42, 0x89, 0x79, 0x44, 0xc2, 0xa2, 0x8f, 0xa1, ++ 0x76, 0x11, 0xd7, 0xfa, 0x5c, 0x22, 0xad, 0x8f ++}; ++static const u8 enc_output104[] __initconst = { ++ 0xb2, 0x2c, 0x70, 0x68, 0xa5, 0x83, 0xfa, 0x35, ++ 0x0f, 0x85, 0x29, 0xc3, 0x75, 0xf8, 0xeb, 0x88, ++ 0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xfa, 0x5b, 0x16, 0x2d, 0x6f, 0x12, 0xd1, 0xec, ++ 0x39, 0xcd, 0x90, 0xb7, 0x2b, 0xff, 0x75, 0x03, ++ 0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xfa, 0x5b, 0x16, 0x2d, 0x6f, 0x12, 0xd1, 0xec, ++ 0x39, 0xcd, 0x90, 0xb7, 0x2b, 0xff, 0x75, 0x03, ++ 0xa0, 0x19, 0xac, 0x2e, 0xd6, 0x67, 0xe1, 0x7d, ++ 0xa1, 0x6f, 0x0a, 0xfa, 0x19, 0x61, 0x0d, 0x0d ++}; ++static const u8 enc_assoc104[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce104[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key104[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input105[] __initconst = { ++ 0x74, 0x0f, 0x9e, 0x49, 0xf6, 0x10, 0xef, 0xa5, ++ 0x85, 0xb6, 0x59, 0xca, 0x6e, 0xd8, 0xb4, 0x99, ++ 0x2d, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x41, 0x2d, 0x96, 0xaf, 0xbe, 0x80, 0xec, 0x3e, ++ 0x79, 0xd4, 0x51, 0xb0, 0x0a, 0x2d, 0xb2, 0x9a, ++ 0xc9, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0x99, 0x7a, 0xeb, 0x0c, 0x27, 0x95, 0x62, 0x46, ++ 0x69, 0xc3, 0x87, 0xf9, 0x11, 0x6a, 0xc1, 0x8d ++}; ++static const u8 enc_output105[] __initconst = { ++ 0x74, 0x64, 0x49, 0x66, 0x70, 0xda, 0x0f, 0x3c, ++ 0x26, 0x99, 0xa7, 0x00, 0xd2, 0x3e, 0xcc, 0x3a, ++ 0xaa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x21, 0xa8, 0x84, 0x65, 0x8a, 0x25, 0x3c, 0x0b, ++ 0x26, 0x1f, 0xc0, 0xb4, 0x66, 0xb7, 0x19, 0x01, ++ 0xaa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x21, 0xa8, 0x84, 0x65, 0x8a, 0x25, 0x3c, 0x0b, ++ 0x26, 0x1f, 0xc0, 0xb4, 0x66, 0xb7, 0x19, 0x01, ++ 0x73, 0x6e, 0x18, 0x18, 0x16, 0x96, 0xa5, 0x88, ++ 0x9c, 0x31, 0x59, 0xfa, 0xab, 0xab, 0x20, 0xfd ++}; ++static const u8 enc_assoc105[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce105[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key105[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input106[] __initconst = { ++ 0xad, 0xba, 0x5d, 0x10, 0x5b, 0xc8, 0xaa, 0x06, ++ 0x2c, 0x23, 0x36, 0xcb, 0x88, 0x9d, 0xdb, 0xd5, ++ 0x37, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x17, 0x7c, 0x5f, 0xfe, 0x28, 0x75, 0xf4, 0x68, ++ 0xf6, 0xc2, 0x96, 0x57, 0x48, 0xf3, 0x59, 0x9a, ++ 0xd3, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0xcf, 0x2b, 0x22, 0x5d, 0xb1, 0x60, 0x7a, 0x10, ++ 0xe6, 0xd5, 0x40, 0x1e, 0x53, 0xb4, 0x2a, 0x8d ++}; ++static const u8 enc_output106[] __initconst = { ++ 0xad, 0xd1, 0x8a, 0x3f, 0xdd, 0x02, 0x4a, 0x9f, ++ 0x8f, 0x0c, 0xc8, 0x01, 0x34, 0x7b, 0xa3, 0x76, ++ 0xb0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x77, 0xf9, 0x4d, 0x34, 0x1c, 0xd0, 0x24, 0x5d, ++ 0xa9, 0x09, 0x07, 0x53, 0x24, 0x69, 0xf2, 0x01, ++ 0xb0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x77, 0xf9, 0x4d, 0x34, 0x1c, 0xd0, 0x24, 0x5d, ++ 0xa9, 0x09, 0x07, 0x53, 0x24, 0x69, 0xf2, 0x01, ++ 0xba, 0xd5, 0x8f, 0x10, 0xa9, 0x1e, 0x6a, 0x88, ++ 0x9a, 0xba, 0x32, 0xfd, 0x17, 0xd8, 0x33, 0x1a ++}; ++static const u8 enc_assoc106[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce106[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key106[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input107[] __initconst = { ++ 0xfe, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xc0, 0x01, 0xed, 0xc5, 0xda, 0x44, 0x2e, 0x71, ++ 0x9b, 0xce, 0x9a, 0xbe, 0x27, 0x3a, 0xf1, 0x44, ++ 0xb4, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x48, 0x02, 0x5f, 0x41, 0xfa, 0x4e, 0x33, 0x6c, ++ 0x78, 0x69, 0x57, 0xa2, 0xa7, 0xc4, 0x93, 0x0a, ++ 0x6c, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x00, 0x26, 0x6e, 0xa1, 0xe4, 0x36, 0x44, 0xa3, ++ 0x4d, 0x8d, 0xd1, 0xdc, 0x93, 0xf2, 0xfa, 0x13 ++}; ++static const u8 enc_output107[] __initconst = { ++ 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x47, 0xc3, 0x27, 0xcc, 0x36, 0x5d, 0x08, 0x87, ++ 0x59, 0x09, 0x8c, 0x34, 0x1b, 0x4a, 0xed, 0x03, ++ 0xd4, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x2b, 0x0b, 0x97, 0x3f, 0x74, 0x5b, 0x28, 0xaa, ++ 0xe9, 0x37, 0xf5, 0x9f, 0x18, 0xea, 0xc7, 0x01, ++ 0xd4, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x2b, 0x0b, 0x97, 0x3f, 0x74, 0x5b, 0x28, 0xaa, ++ 0xe9, 0x37, 0xf5, 0x9f, 0x18, 0xea, 0xc7, 0x01, ++ 0xd6, 0x8c, 0xe1, 0x74, 0x07, 0x9a, 0xdd, 0x02, ++ 0x8d, 0xd0, 0x5c, 0xf8, 0x14, 0x63, 0x04, 0x88 ++}; ++static const u8 enc_assoc107[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce107[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key107[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input108[] __initconst = { ++ 0xb5, 0x13, 0xb0, 0x6a, 0xb9, 0xac, 0x14, 0x43, ++ 0x5a, 0xcb, 0x8a, 0xa3, 0xa3, 0x7a, 0xfd, 0xb6, ++ 0x54, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x61, 0x95, 0x01, 0x93, 0xb1, 0xbf, 0x03, 0x11, ++ 0xff, 0x11, 0x79, 0x89, 0xae, 0xd9, 0xa9, 0x99, ++ 0xb0, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0xb9, 0xc2, 0x7c, 0x30, 0x28, 0xaa, 0x8d, 0x69, ++ 0xef, 0x06, 0xaf, 0xc0, 0xb5, 0x9e, 0xda, 0x8e ++}; ++static const u8 enc_output108[] __initconst = { ++ 0xb5, 0x78, 0x67, 0x45, 0x3f, 0x66, 0xf4, 0xda, ++ 0xf9, 0xe4, 0x74, 0x69, 0x1f, 0x9c, 0x85, 0x15, ++ 0xd3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x01, 0x10, 0x13, 0x59, 0x85, 0x1a, 0xd3, 0x24, ++ 0xa0, 0xda, 0xe8, 0x8d, 0xc2, 0x43, 0x02, 0x02, ++ 0xd3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x01, 0x10, 0x13, 0x59, 0x85, 0x1a, 0xd3, 0x24, ++ 0xa0, 0xda, 0xe8, 0x8d, 0xc2, 0x43, 0x02, 0x02, ++ 0xaa, 0x48, 0xa3, 0x88, 0x7d, 0x4b, 0x05, 0x96, ++ 0x99, 0xc2, 0xfd, 0xf9, 0xc6, 0x78, 0x7e, 0x0a ++}; ++static const u8 enc_assoc108[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce108[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key108[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input109[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xd4, 0xf1, 0x09, 0xe8, 0x14, 0xce, 0xa8, 0x5a, ++ 0x08, 0xc0, 0x11, 0xd8, 0x50, 0xdd, 0x1d, 0xcb, ++ 0xcf, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x53, 0x40, 0xb8, 0x5a, 0x9a, 0xa0, 0x82, 0x96, ++ 0xb7, 0x7a, 0x5f, 0xc3, 0x96, 0x1f, 0x66, 0x0f, ++ 0x17, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x1b, 0x64, 0x89, 0xba, 0x84, 0xd8, 0xf5, 0x59, ++ 0x82, 0x9e, 0xd9, 0xbd, 0xa2, 0x29, 0x0f, 0x16 ++}; ++static const u8 enc_output109[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x53, 0x33, 0xc3, 0xe1, 0xf8, 0xd7, 0x8e, 0xac, ++ 0xca, 0x07, 0x07, 0x52, 0x6c, 0xad, 0x01, 0x8c, ++ 0xaf, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x30, 0x49, 0x70, 0x24, 0x14, 0xb5, 0x99, 0x50, ++ 0x26, 0x24, 0xfd, 0xfe, 0x29, 0x31, 0x32, 0x04, ++ 0xaf, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x30, 0x49, 0x70, 0x24, 0x14, 0xb5, 0x99, 0x50, ++ 0x26, 0x24, 0xfd, 0xfe, 0x29, 0x31, 0x32, 0x04, ++ 0xb9, 0x36, 0xa8, 0x17, 0xf2, 0x21, 0x1a, 0xf1, ++ 0x29, 0xe2, 0xcf, 0x16, 0x0f, 0xd4, 0x2b, 0xcb ++}; ++static const u8 enc_assoc109[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce109[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key109[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input110[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xdf, 0x4c, 0x62, 0x03, 0x2d, 0x41, 0x19, 0xb5, ++ 0x88, 0x47, 0x7e, 0x99, 0x92, 0x5a, 0x56, 0xd9, ++ 0xd6, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0xfa, 0x84, 0xf0, 0x64, 0x55, 0x36, 0x42, 0x1b, ++ 0x2b, 0xb9, 0x24, 0x6e, 0xc2, 0x19, 0xed, 0x0b, ++ 0x0e, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0xb2, 0xa0, 0xc1, 0x84, 0x4b, 0x4e, 0x35, 0xd4, ++ 0x1e, 0x5d, 0xa2, 0x10, 0xf6, 0x2f, 0x84, 0x12 ++}; ++static const u8 enc_output110[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x58, 0x8e, 0xa8, 0x0a, 0xc1, 0x58, 0x3f, 0x43, ++ 0x4a, 0x80, 0x68, 0x13, 0xae, 0x2a, 0x4a, 0x9e, ++ 0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x99, 0x8d, 0x38, 0x1a, 0xdb, 0x23, 0x59, 0xdd, ++ 0xba, 0xe7, 0x86, 0x53, 0x7d, 0x37, 0xb9, 0x00, ++ 0xb6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x99, 0x8d, 0x38, 0x1a, 0xdb, 0x23, 0x59, 0xdd, ++ 0xba, 0xe7, 0x86, 0x53, 0x7d, 0x37, 0xb9, 0x00, ++ 0x9f, 0x7a, 0xc4, 0x35, 0x1f, 0x6b, 0x91, 0xe6, ++ 0x30, 0x97, 0xa7, 0x13, 0x11, 0x5d, 0x05, 0xbe ++}; ++static const u8 enc_assoc110[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce110[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key110[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input111[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x13, 0xf8, 0x0a, 0x00, 0x6d, 0xc1, 0xbb, 0xda, ++ 0xd6, 0x39, 0xa9, 0x2f, 0xc7, 0xec, 0xa6, 0x55, ++ 0xf7, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x63, 0x48, 0xb8, 0xfd, 0x29, 0xbf, 0x96, 0xd5, ++ 0x63, 0xa5, 0x17, 0xe2, 0x7d, 0x7b, 0xfc, 0x0f, ++ 0x2f, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x2b, 0x6c, 0x89, 0x1d, 0x37, 0xc7, 0xe1, 0x1a, ++ 0x56, 0x41, 0x91, 0x9c, 0x49, 0x4d, 0x95, 0x16 ++}; ++static const u8 enc_output111[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x94, 0x3a, 0xc0, 0x09, 0x81, 0xd8, 0x9d, 0x2c, ++ 0x14, 0xfe, 0xbf, 0xa5, 0xfb, 0x9c, 0xba, 0x12, ++ 0x97, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x41, 0x70, 0x83, 0xa7, 0xaa, 0x8d, 0x13, ++ 0xf2, 0xfb, 0xb5, 0xdf, 0xc2, 0x55, 0xa8, 0x04, ++ 0x97, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x41, 0x70, 0x83, 0xa7, 0xaa, 0x8d, 0x13, ++ 0xf2, 0xfb, 0xb5, 0xdf, 0xc2, 0x55, 0xa8, 0x04, ++ 0x9a, 0x18, 0xa8, 0x28, 0x07, 0x02, 0x69, 0xf4, ++ 0x47, 0x00, 0xd0, 0x09, 0xe7, 0x17, 0x1c, 0xc9 ++}; ++static const u8 enc_assoc111[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce111[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key111[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input112[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x82, 0xe5, 0x9b, 0x45, 0x82, 0x91, 0x50, 0x38, ++ 0xf9, 0x33, 0x81, 0x1e, 0x65, 0x2d, 0xc6, 0x6a, ++ 0xfc, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0xb6, 0x71, 0xc8, 0xca, 0xc2, 0x70, 0xc2, 0x65, ++ 0xa0, 0xac, 0x2f, 0x53, 0x57, 0x99, 0x88, 0x0a, ++ 0x24, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0xfe, 0x55, 0xf9, 0x2a, 0xdc, 0x08, 0xb5, 0xaa, ++ 0x95, 0x48, 0xa9, 0x2d, 0x63, 0xaf, 0xe1, 0x13 ++}; ++static const u8 enc_output112[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x05, 0x27, 0x51, 0x4c, 0x6e, 0x88, 0x76, 0xce, ++ 0x3b, 0xf4, 0x97, 0x94, 0x59, 0x5d, 0xda, 0x2d, ++ 0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xd5, 0x78, 0x00, 0xb4, 0x4c, 0x65, 0xd9, 0xa3, ++ 0x31, 0xf2, 0x8d, 0x6e, 0xe8, 0xb7, 0xdc, 0x01, ++ 0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xd5, 0x78, 0x00, 0xb4, 0x4c, 0x65, 0xd9, 0xa3, ++ 0x31, 0xf2, 0x8d, 0x6e, 0xe8, 0xb7, 0xdc, 0x01, ++ 0xb4, 0x36, 0xa8, 0x2b, 0x93, 0xd5, 0x55, 0xf7, ++ 0x43, 0x00, 0xd0, 0x19, 0x9b, 0xa7, 0x18, 0xce ++}; ++static const u8 enc_assoc112[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce112[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key112[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input113[] __initconst = { ++ 0xff, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0xf1, 0xd1, 0x28, 0x87, 0xb7, 0x21, 0x69, 0x86, ++ 0xa1, 0x2d, 0x79, 0x09, 0x8b, 0x6d, 0xe6, 0x0f, ++ 0xc0, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0xa7, 0xc7, 0x58, 0x99, 0xf3, 0xe6, 0x0a, 0xf1, ++ 0xfc, 0xb6, 0xc7, 0x30, 0x7d, 0x87, 0x59, 0x0f, ++ 0x18, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0xef, 0xe3, 0x69, 0x79, 0xed, 0x9e, 0x7d, 0x3e, ++ 0xc9, 0x52, 0x41, 0x4e, 0x49, 0xb1, 0x30, 0x16 ++}; ++static const u8 enc_output113[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x76, 0x13, 0xe2, 0x8e, 0x5b, 0x38, 0x4f, 0x70, ++ 0x63, 0xea, 0x6f, 0x83, 0xb7, 0x1d, 0xfa, 0x48, ++ 0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xc4, 0xce, 0x90, 0xe7, 0x7d, 0xf3, 0x11, 0x37, ++ 0x6d, 0xe8, 0x65, 0x0d, 0xc2, 0xa9, 0x0d, 0x04, ++ 0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xc4, 0xce, 0x90, 0xe7, 0x7d, 0xf3, 0x11, 0x37, ++ 0x6d, 0xe8, 0x65, 0x0d, 0xc2, 0xa9, 0x0d, 0x04, ++ 0xce, 0x54, 0xa8, 0x2e, 0x1f, 0xa9, 0x42, 0xfa, ++ 0x3f, 0x00, 0xd0, 0x29, 0x4f, 0x37, 0x15, 0xd3 ++}; ++static const u8 enc_assoc113[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce113[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key113[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input114[] __initconst = { ++ 0xcb, 0xf1, 0xda, 0x9e, 0x0b, 0xa9, 0x37, 0x73, ++ 0x74, 0xe6, 0x9e, 0x1c, 0x0e, 0x60, 0x0c, 0xfc, ++ 0x34, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0xbe, 0x3f, 0xa6, 0x6b, 0x6c, 0xe7, 0x80, 0x8a, ++ 0xa3, 0xe4, 0x59, 0x49, 0xf9, 0x44, 0x64, 0x9f, ++ 0xd0, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0x66, 0x68, 0xdb, 0xc8, 0xf5, 0xf2, 0x0e, 0xf2, ++ 0xb3, 0xf3, 0x8f, 0x00, 0xe2, 0x03, 0x17, 0x88 ++}; ++static const u8 enc_output114[] __initconst = { ++ 0xcb, 0x9a, 0x0d, 0xb1, 0x8d, 0x63, 0xd7, 0xea, ++ 0xd7, 0xc9, 0x60, 0xd6, 0xb2, 0x86, 0x74, 0x5f, ++ 0xb3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xde, 0xba, 0xb4, 0xa1, 0x58, 0x42, 0x50, 0xbf, ++ 0xfc, 0x2f, 0xc8, 0x4d, 0x95, 0xde, 0xcf, 0x04, ++ 0xb3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xde, 0xba, 0xb4, 0xa1, 0x58, 0x42, 0x50, 0xbf, ++ 0xfc, 0x2f, 0xc8, 0x4d, 0x95, 0xde, 0xcf, 0x04, ++ 0x23, 0x83, 0xab, 0x0b, 0x79, 0x92, 0x05, 0x69, ++ 0x9b, 0x51, 0x0a, 0xa7, 0x09, 0xbf, 0x31, 0xf1 ++}; ++static const u8 enc_assoc114[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce114[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key114[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input115[] __initconst = { ++ 0x8f, 0x27, 0x86, 0x94, 0xc4, 0xe9, 0xda, 0xeb, ++ 0xd5, 0x8d, 0x3e, 0x5b, 0x96, 0x6e, 0x8b, 0x68, ++ 0x42, 0x3d, 0x35, 0xf6, 0x13, 0xe6, 0xd9, 0x09, ++ 0x3d, 0x38, 0xe9, 0x75, 0xc3, 0x8f, 0xe3, 0xb8, ++ 0x06, 0x53, 0xe7, 0xa3, 0x31, 0x71, 0x88, 0x33, ++ 0xac, 0xc3, 0xb9, 0xad, 0xff, 0x1c, 0x31, 0x98, ++ 0xa6, 0xf6, 0x37, 0x81, 0x71, 0xea, 0xe4, 0x39, ++ 0x6e, 0xa1, 0x5d, 0xc2, 0x40, 0xd1, 0xab, 0xf4, ++ 0xde, 0x04, 0x9a, 0x00, 0xa8, 0x64, 0x06, 0x4b, ++ 0xbc, 0xd4, 0x6f, 0xe4, 0xe4, 0x5b, 0x42, 0x8f ++}; ++static const u8 enc_output115[] __initconst = { ++ 0x8f, 0x4c, 0x51, 0xbb, 0x42, 0x23, 0x3a, 0x72, ++ 0x76, 0xa2, 0xc0, 0x91, 0x2a, 0x88, 0xf3, 0xcb, ++ 0xc5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x66, 0xd6, 0xf5, 0x69, 0x05, 0xd4, 0x58, 0x06, ++ 0xf3, 0x08, 0x28, 0xa9, 0x93, 0x86, 0x9a, 0x03, ++ 0xc5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x66, 0xd6, 0xf5, 0x69, 0x05, 0xd4, 0x58, 0x06, ++ 0xf3, 0x08, 0x28, 0xa9, 0x93, 0x86, 0x9a, 0x03, ++ 0x8b, 0xfb, 0xab, 0x17, 0xa9, 0xe0, 0xb8, 0x74, ++ 0x8b, 0x51, 0x0a, 0xe7, 0xd9, 0xfd, 0x23, 0x05 ++}; ++static const u8 enc_assoc115[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce115[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key115[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input116[] __initconst = { ++ 0xd5, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x9a, 0x22, 0xd7, 0x0a, 0x48, 0xe2, 0x4f, 0xdd, ++ 0xcd, 0xd4, 0x41, 0x9d, 0xe6, 0x4c, 0x8f, 0x44, ++ 0xfc, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x77, 0xb5, 0xc9, 0x07, 0xd9, 0xc9, 0xe1, 0xea, ++ 0x51, 0x85, 0x1a, 0x20, 0x4a, 0xad, 0x9f, 0x0a, ++ 0x24, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x3f, 0x91, 0xf8, 0xe7, 0xc7, 0xb1, 0x96, 0x25, ++ 0x64, 0x61, 0x9c, 0x5e, 0x7e, 0x9b, 0xf6, 0x13 ++}; ++static const u8 enc_output116[] __initconst = { ++ 0xd5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x1d, 0xe0, 0x1d, 0x03, 0xa4, 0xfb, 0x69, 0x2b, ++ 0x0f, 0x13, 0x57, 0x17, 0xda, 0x3c, 0x93, 0x03, ++ 0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x14, 0xbc, 0x01, 0x79, 0x57, 0xdc, 0xfa, 0x2c, ++ 0xc0, 0xdb, 0xb8, 0x1d, 0xf5, 0x83, 0xcb, 0x01, ++ 0x9c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x14, 0xbc, 0x01, 0x79, 0x57, 0xdc, 0xfa, 0x2c, ++ 0xc0, 0xdb, 0xb8, 0x1d, 0xf5, 0x83, 0xcb, 0x01, ++ 0x49, 0xbc, 0x6e, 0x9f, 0xc5, 0x1c, 0x4d, 0x50, ++ 0x30, 0x36, 0x64, 0x4d, 0x84, 0x27, 0x73, 0xd2 ++}; ++static const u8 enc_assoc116[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce116[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key116[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input117[] __initconst = { ++ 0xdb, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x75, 0xd5, 0x64, 0x3a, 0xa5, 0xaf, 0x93, 0x4d, ++ 0x8c, 0xce, 0x39, 0x2c, 0xc3, 0xee, 0xdb, 0x47, ++ 0xc0, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0x60, 0x1b, 0x5a, 0xd2, 0x06, 0x7f, 0x28, 0x06, ++ 0x6a, 0x8f, 0x32, 0x81, 0x71, 0x5b, 0xa8, 0x08, ++ 0x18, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x28, 0x3f, 0x6b, 0x32, 0x18, 0x07, 0x5f, 0xc9, ++ 0x5f, 0x6b, 0xb4, 0xff, 0x45, 0x6d, 0xc1, 0x11 ++}; ++static const u8 enc_output117[] __initconst = { ++ 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xf2, 0x17, 0xae, 0x33, 0x49, 0xb6, 0xb5, 0xbb, ++ 0x4e, 0x09, 0x2f, 0xa6, 0xff, 0x9e, 0xc7, 0x00, ++ 0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x03, 0x12, 0x92, 0xac, 0x88, 0x6a, 0x33, 0xc0, ++ 0xfb, 0xd1, 0x90, 0xbc, 0xce, 0x75, 0xfc, 0x03, ++ 0xa0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x03, 0x12, 0x92, 0xac, 0x88, 0x6a, 0x33, 0xc0, ++ 0xfb, 0xd1, 0x90, 0xbc, 0xce, 0x75, 0xfc, 0x03, ++ 0x63, 0xda, 0x6e, 0xa2, 0x51, 0xf0, 0x39, 0x53, ++ 0x2c, 0x36, 0x64, 0x5d, 0x38, 0xb7, 0x6f, 0xd7 ++}; ++static const u8 enc_assoc117[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce117[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key117[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - edge case intermediate sums in poly1305 */ ++static const u8 enc_input118[] __initconst = { ++ 0x93, 0x94, 0x28, 0xd0, 0x79, 0x35, 0x1f, 0x66, ++ 0x5c, 0xd0, 0x01, 0x35, 0x43, 0x19, 0x87, 0x5c, ++ 0x62, 0x48, 0x39, 0x60, 0x42, 0x16, 0xe4, 0x03, ++ 0xeb, 0xcc, 0x6a, 0xf5, 0x59, 0xec, 0x8b, 0x43, ++ 0x97, 0x7a, 0xed, 0x35, 0xcb, 0x5a, 0x2f, 0xca, ++ 0xa0, 0x34, 0x6e, 0xfb, 0x93, 0x65, 0x54, 0x64, ++ 0xd8, 0xc8, 0xc3, 0xfa, 0x1a, 0x9e, 0x47, 0x4a, ++ 0xbe, 0x52, 0xd0, 0x2c, 0x81, 0x87, 0xe9, 0x0f, ++ 0x4f, 0x2d, 0x90, 0x96, 0x52, 0x4f, 0xa1, 0xb2, ++ 0xb0, 0x23, 0xb8, 0xb2, 0x88, 0x22, 0x27, 0x73, ++ 0x90, 0xec, 0xf2, 0x1a, 0x04, 0xe6, 0x30, 0x85, ++ 0x8b, 0xb6, 0x56, 0x52, 0xb5, 0xb1, 0x80, 0x16 ++}; ++static const u8 enc_output118[] __initconst = { ++ 0x93, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xe5, 0x8a, 0xf3, 0x69, 0xae, 0x0f, 0xc2, 0xf5, ++ 0x29, 0x0b, 0x7c, 0x7f, 0x65, 0x9c, 0x97, 0x04, ++ 0xf7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xbb, 0xc1, 0x0b, 0x84, 0x94, 0x8b, 0x5c, 0x8c, ++ 0x2f, 0x0c, 0x72, 0x11, 0x3e, 0xa9, 0xbd, 0x04, ++ 0xf7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xbb, 0xc1, 0x0b, 0x84, 0x94, 0x8b, 0x5c, 0x8c, ++ 0x2f, 0x0c, 0x72, 0x11, 0x3e, 0xa9, 0xbd, 0x04, ++ 0x73, 0xeb, 0x27, 0x24, 0xb5, 0xc4, 0x05, 0xf0, ++ 0x4d, 0x00, 0xd0, 0xf1, 0x58, 0x40, 0xa1, 0xc1 ++}; ++static const u8 enc_assoc118[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce118[] __initconst = { ++ 0x00, 0x00, 0x00, 0x00, 0x06, 0x4c, 0x2d, 0x52 ++}; ++static const u8 enc_key118[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++static const struct chacha20poly1305_testvec ++chacha20poly1305_enc_vectors[] __initconst = { ++ { enc_input001, enc_output001, enc_assoc001, enc_nonce001, enc_key001, ++ sizeof(enc_input001), sizeof(enc_assoc001), sizeof(enc_nonce001) }, ++ { enc_input002, enc_output002, enc_assoc002, enc_nonce002, enc_key002, ++ sizeof(enc_input002), sizeof(enc_assoc002), sizeof(enc_nonce002) }, ++ { enc_input003, enc_output003, enc_assoc003, enc_nonce003, enc_key003, ++ sizeof(enc_input003), sizeof(enc_assoc003), sizeof(enc_nonce003) }, ++ { enc_input004, enc_output004, enc_assoc004, enc_nonce004, enc_key004, ++ sizeof(enc_input004), sizeof(enc_assoc004), sizeof(enc_nonce004) }, ++ { enc_input005, enc_output005, enc_assoc005, enc_nonce005, enc_key005, ++ sizeof(enc_input005), sizeof(enc_assoc005), sizeof(enc_nonce005) }, ++ { enc_input006, enc_output006, enc_assoc006, enc_nonce006, enc_key006, ++ sizeof(enc_input006), sizeof(enc_assoc006), sizeof(enc_nonce006) }, ++ { enc_input007, enc_output007, enc_assoc007, enc_nonce007, enc_key007, ++ sizeof(enc_input007), sizeof(enc_assoc007), sizeof(enc_nonce007) }, ++ { enc_input008, enc_output008, enc_assoc008, enc_nonce008, enc_key008, ++ sizeof(enc_input008), sizeof(enc_assoc008), sizeof(enc_nonce008) }, ++ { enc_input009, enc_output009, enc_assoc009, enc_nonce009, enc_key009, ++ sizeof(enc_input009), sizeof(enc_assoc009), sizeof(enc_nonce009) }, ++ { enc_input010, enc_output010, enc_assoc010, enc_nonce010, enc_key010, ++ sizeof(enc_input010), sizeof(enc_assoc010), sizeof(enc_nonce010) }, ++ { enc_input011, enc_output011, enc_assoc011, enc_nonce011, enc_key011, ++ sizeof(enc_input011), sizeof(enc_assoc011), sizeof(enc_nonce011) }, ++ { enc_input012, enc_output012, enc_assoc012, enc_nonce012, enc_key012, ++ sizeof(enc_input012), sizeof(enc_assoc012), sizeof(enc_nonce012) }, ++ { enc_input053, enc_output053, enc_assoc053, enc_nonce053, enc_key053, ++ sizeof(enc_input053), sizeof(enc_assoc053), sizeof(enc_nonce053) }, ++ { enc_input054, enc_output054, enc_assoc054, enc_nonce054, enc_key054, ++ sizeof(enc_input054), sizeof(enc_assoc054), sizeof(enc_nonce054) }, ++ { enc_input055, enc_output055, enc_assoc055, enc_nonce055, enc_key055, ++ sizeof(enc_input055), sizeof(enc_assoc055), sizeof(enc_nonce055) }, ++ { enc_input056, enc_output056, enc_assoc056, enc_nonce056, enc_key056, ++ sizeof(enc_input056), sizeof(enc_assoc056), sizeof(enc_nonce056) }, ++ { enc_input057, enc_output057, enc_assoc057, enc_nonce057, enc_key057, ++ sizeof(enc_input057), sizeof(enc_assoc057), sizeof(enc_nonce057) }, ++ { enc_input058, enc_output058, enc_assoc058, enc_nonce058, enc_key058, ++ sizeof(enc_input058), sizeof(enc_assoc058), sizeof(enc_nonce058) }, ++ { enc_input059, enc_output059, enc_assoc059, enc_nonce059, enc_key059, ++ sizeof(enc_input059), sizeof(enc_assoc059), sizeof(enc_nonce059) }, ++ { enc_input060, enc_output060, enc_assoc060, enc_nonce060, enc_key060, ++ sizeof(enc_input060), sizeof(enc_assoc060), sizeof(enc_nonce060) }, ++ { enc_input061, enc_output061, enc_assoc061, enc_nonce061, enc_key061, ++ sizeof(enc_input061), sizeof(enc_assoc061), sizeof(enc_nonce061) }, ++ { enc_input062, enc_output062, enc_assoc062, enc_nonce062, enc_key062, ++ sizeof(enc_input062), sizeof(enc_assoc062), sizeof(enc_nonce062) }, ++ { enc_input063, enc_output063, enc_assoc063, enc_nonce063, enc_key063, ++ sizeof(enc_input063), sizeof(enc_assoc063), sizeof(enc_nonce063) }, ++ { enc_input064, enc_output064, enc_assoc064, enc_nonce064, enc_key064, ++ sizeof(enc_input064), sizeof(enc_assoc064), sizeof(enc_nonce064) }, ++ { enc_input065, enc_output065, enc_assoc065, enc_nonce065, enc_key065, ++ sizeof(enc_input065), sizeof(enc_assoc065), sizeof(enc_nonce065) }, ++ { enc_input066, enc_output066, enc_assoc066, enc_nonce066, enc_key066, ++ sizeof(enc_input066), sizeof(enc_assoc066), sizeof(enc_nonce066) }, ++ { enc_input067, enc_output067, enc_assoc067, enc_nonce067, enc_key067, ++ sizeof(enc_input067), sizeof(enc_assoc067), sizeof(enc_nonce067) }, ++ { enc_input068, enc_output068, enc_assoc068, enc_nonce068, enc_key068, ++ sizeof(enc_input068), sizeof(enc_assoc068), sizeof(enc_nonce068) }, ++ { enc_input069, enc_output069, enc_assoc069, enc_nonce069, enc_key069, ++ sizeof(enc_input069), sizeof(enc_assoc069), sizeof(enc_nonce069) }, ++ { enc_input070, enc_output070, enc_assoc070, enc_nonce070, enc_key070, ++ sizeof(enc_input070), sizeof(enc_assoc070), sizeof(enc_nonce070) }, ++ { enc_input071, enc_output071, enc_assoc071, enc_nonce071, enc_key071, ++ sizeof(enc_input071), sizeof(enc_assoc071), sizeof(enc_nonce071) }, ++ { enc_input072, enc_output072, enc_assoc072, enc_nonce072, enc_key072, ++ sizeof(enc_input072), sizeof(enc_assoc072), sizeof(enc_nonce072) }, ++ { enc_input073, enc_output073, enc_assoc073, enc_nonce073, enc_key073, ++ sizeof(enc_input073), sizeof(enc_assoc073), sizeof(enc_nonce073) }, ++ { enc_input076, enc_output076, enc_assoc076, enc_nonce076, enc_key076, ++ sizeof(enc_input076), sizeof(enc_assoc076), sizeof(enc_nonce076) }, ++ { enc_input077, enc_output077, enc_assoc077, enc_nonce077, enc_key077, ++ sizeof(enc_input077), sizeof(enc_assoc077), sizeof(enc_nonce077) }, ++ { enc_input078, enc_output078, enc_assoc078, enc_nonce078, enc_key078, ++ sizeof(enc_input078), sizeof(enc_assoc078), sizeof(enc_nonce078) }, ++ { enc_input079, enc_output079, enc_assoc079, enc_nonce079, enc_key079, ++ sizeof(enc_input079), sizeof(enc_assoc079), sizeof(enc_nonce079) }, ++ { enc_input080, enc_output080, enc_assoc080, enc_nonce080, enc_key080, ++ sizeof(enc_input080), sizeof(enc_assoc080), sizeof(enc_nonce080) }, ++ { enc_input081, enc_output081, enc_assoc081, enc_nonce081, enc_key081, ++ sizeof(enc_input081), sizeof(enc_assoc081), sizeof(enc_nonce081) }, ++ { enc_input082, enc_output082, enc_assoc082, enc_nonce082, enc_key082, ++ sizeof(enc_input082), sizeof(enc_assoc082), sizeof(enc_nonce082) }, ++ { enc_input083, enc_output083, enc_assoc083, enc_nonce083, enc_key083, ++ sizeof(enc_input083), sizeof(enc_assoc083), sizeof(enc_nonce083) }, ++ { enc_input084, enc_output084, enc_assoc084, enc_nonce084, enc_key084, ++ sizeof(enc_input084), sizeof(enc_assoc084), sizeof(enc_nonce084) }, ++ { enc_input085, enc_output085, enc_assoc085, enc_nonce085, enc_key085, ++ sizeof(enc_input085), sizeof(enc_assoc085), sizeof(enc_nonce085) }, ++ { enc_input093, enc_output093, enc_assoc093, enc_nonce093, enc_key093, ++ sizeof(enc_input093), sizeof(enc_assoc093), sizeof(enc_nonce093) }, ++ { enc_input094, enc_output094, enc_assoc094, enc_nonce094, enc_key094, ++ sizeof(enc_input094), sizeof(enc_assoc094), sizeof(enc_nonce094) }, ++ { enc_input095, enc_output095, enc_assoc095, enc_nonce095, enc_key095, ++ sizeof(enc_input095), sizeof(enc_assoc095), sizeof(enc_nonce095) }, ++ { enc_input096, enc_output096, enc_assoc096, enc_nonce096, enc_key096, ++ sizeof(enc_input096), sizeof(enc_assoc096), sizeof(enc_nonce096) }, ++ { enc_input097, enc_output097, enc_assoc097, enc_nonce097, enc_key097, ++ sizeof(enc_input097), sizeof(enc_assoc097), sizeof(enc_nonce097) }, ++ { enc_input098, enc_output098, enc_assoc098, enc_nonce098, enc_key098, ++ sizeof(enc_input098), sizeof(enc_assoc098), sizeof(enc_nonce098) }, ++ { enc_input099, enc_output099, enc_assoc099, enc_nonce099, enc_key099, ++ sizeof(enc_input099), sizeof(enc_assoc099), sizeof(enc_nonce099) }, ++ { enc_input100, enc_output100, enc_assoc100, enc_nonce100, enc_key100, ++ sizeof(enc_input100), sizeof(enc_assoc100), sizeof(enc_nonce100) }, ++ { enc_input101, enc_output101, enc_assoc101, enc_nonce101, enc_key101, ++ sizeof(enc_input101), sizeof(enc_assoc101), sizeof(enc_nonce101) }, ++ { enc_input102, enc_output102, enc_assoc102, enc_nonce102, enc_key102, ++ sizeof(enc_input102), sizeof(enc_assoc102), sizeof(enc_nonce102) }, ++ { enc_input103, enc_output103, enc_assoc103, enc_nonce103, enc_key103, ++ sizeof(enc_input103), sizeof(enc_assoc103), sizeof(enc_nonce103) }, ++ { enc_input104, enc_output104, enc_assoc104, enc_nonce104, enc_key104, ++ sizeof(enc_input104), sizeof(enc_assoc104), sizeof(enc_nonce104) }, ++ { enc_input105, enc_output105, enc_assoc105, enc_nonce105, enc_key105, ++ sizeof(enc_input105), sizeof(enc_assoc105), sizeof(enc_nonce105) }, ++ { enc_input106, enc_output106, enc_assoc106, enc_nonce106, enc_key106, ++ sizeof(enc_input106), sizeof(enc_assoc106), sizeof(enc_nonce106) }, ++ { enc_input107, enc_output107, enc_assoc107, enc_nonce107, enc_key107, ++ sizeof(enc_input107), sizeof(enc_assoc107), sizeof(enc_nonce107) }, ++ { enc_input108, enc_output108, enc_assoc108, enc_nonce108, enc_key108, ++ sizeof(enc_input108), sizeof(enc_assoc108), sizeof(enc_nonce108) }, ++ { enc_input109, enc_output109, enc_assoc109, enc_nonce109, enc_key109, ++ sizeof(enc_input109), sizeof(enc_assoc109), sizeof(enc_nonce109) }, ++ { enc_input110, enc_output110, enc_assoc110, enc_nonce110, enc_key110, ++ sizeof(enc_input110), sizeof(enc_assoc110), sizeof(enc_nonce110) }, ++ { enc_input111, enc_output111, enc_assoc111, enc_nonce111, enc_key111, ++ sizeof(enc_input111), sizeof(enc_assoc111), sizeof(enc_nonce111) }, ++ { enc_input112, enc_output112, enc_assoc112, enc_nonce112, enc_key112, ++ sizeof(enc_input112), sizeof(enc_assoc112), sizeof(enc_nonce112) }, ++ { enc_input113, enc_output113, enc_assoc113, enc_nonce113, enc_key113, ++ sizeof(enc_input113), sizeof(enc_assoc113), sizeof(enc_nonce113) }, ++ { enc_input114, enc_output114, enc_assoc114, enc_nonce114, enc_key114, ++ sizeof(enc_input114), sizeof(enc_assoc114), sizeof(enc_nonce114) }, ++ { enc_input115, enc_output115, enc_assoc115, enc_nonce115, enc_key115, ++ sizeof(enc_input115), sizeof(enc_assoc115), sizeof(enc_nonce115) }, ++ { enc_input116, enc_output116, enc_assoc116, enc_nonce116, enc_key116, ++ sizeof(enc_input116), sizeof(enc_assoc116), sizeof(enc_nonce116) }, ++ { enc_input117, enc_output117, enc_assoc117, enc_nonce117, enc_key117, ++ sizeof(enc_input117), sizeof(enc_assoc117), sizeof(enc_nonce117) }, ++ { enc_input118, enc_output118, enc_assoc118, enc_nonce118, enc_key118, ++ sizeof(enc_input118), sizeof(enc_assoc118), sizeof(enc_nonce118) } ++}; ++ ++static const u8 dec_input001[] __initconst = { ++ 0x64, 0xa0, 0x86, 0x15, 0x75, 0x86, 0x1a, 0xf4, ++ 0x60, 0xf0, 0x62, 0xc7, 0x9b, 0xe6, 0x43, 0xbd, ++ 0x5e, 0x80, 0x5c, 0xfd, 0x34, 0x5c, 0xf3, 0x89, ++ 0xf1, 0x08, 0x67, 0x0a, 0xc7, 0x6c, 0x8c, 0xb2, ++ 0x4c, 0x6c, 0xfc, 0x18, 0x75, 0x5d, 0x43, 0xee, ++ 0xa0, 0x9e, 0xe9, 0x4e, 0x38, 0x2d, 0x26, 0xb0, ++ 0xbd, 0xb7, 0xb7, 0x3c, 0x32, 0x1b, 0x01, 0x00, ++ 0xd4, 0xf0, 0x3b, 0x7f, 0x35, 0x58, 0x94, 0xcf, ++ 0x33, 0x2f, 0x83, 0x0e, 0x71, 0x0b, 0x97, 0xce, ++ 0x98, 0xc8, 0xa8, 0x4a, 0xbd, 0x0b, 0x94, 0x81, ++ 0x14, 0xad, 0x17, 0x6e, 0x00, 0x8d, 0x33, 0xbd, ++ 0x60, 0xf9, 0x82, 0xb1, 0xff, 0x37, 0xc8, 0x55, ++ 0x97, 0x97, 0xa0, 0x6e, 0xf4, 0xf0, 0xef, 0x61, ++ 0xc1, 0x86, 0x32, 0x4e, 0x2b, 0x35, 0x06, 0x38, ++ 0x36, 0x06, 0x90, 0x7b, 0x6a, 0x7c, 0x02, 0xb0, ++ 0xf9, 0xf6, 0x15, 0x7b, 0x53, 0xc8, 0x67, 0xe4, ++ 0xb9, 0x16, 0x6c, 0x76, 0x7b, 0x80, 0x4d, 0x46, ++ 0xa5, 0x9b, 0x52, 0x16, 0xcd, 0xe7, 0xa4, 0xe9, ++ 0x90, 0x40, 0xc5, 0xa4, 0x04, 0x33, 0x22, 0x5e, ++ 0xe2, 0x82, 0xa1, 0xb0, 0xa0, 0x6c, 0x52, 0x3e, ++ 0xaf, 0x45, 0x34, 0xd7, 0xf8, 0x3f, 0xa1, 0x15, ++ 0x5b, 0x00, 0x47, 0x71, 0x8c, 0xbc, 0x54, 0x6a, ++ 0x0d, 0x07, 0x2b, 0x04, 0xb3, 0x56, 0x4e, 0xea, ++ 0x1b, 0x42, 0x22, 0x73, 0xf5, 0x48, 0x27, 0x1a, ++ 0x0b, 0xb2, 0x31, 0x60, 0x53, 0xfa, 0x76, 0x99, ++ 0x19, 0x55, 0xeb, 0xd6, 0x31, 0x59, 0x43, 0x4e, ++ 0xce, 0xbb, 0x4e, 0x46, 0x6d, 0xae, 0x5a, 0x10, ++ 0x73, 0xa6, 0x72, 0x76, 0x27, 0x09, 0x7a, 0x10, ++ 0x49, 0xe6, 0x17, 0xd9, 0x1d, 0x36, 0x10, 0x94, ++ 0xfa, 0x68, 0xf0, 0xff, 0x77, 0x98, 0x71, 0x30, ++ 0x30, 0x5b, 0xea, 0xba, 0x2e, 0xda, 0x04, 0xdf, ++ 0x99, 0x7b, 0x71, 0x4d, 0x6c, 0x6f, 0x2c, 0x29, ++ 0xa6, 0xad, 0x5c, 0xb4, 0x02, 0x2b, 0x02, 0x70, ++ 0x9b, 0xee, 0xad, 0x9d, 0x67, 0x89, 0x0c, 0xbb, ++ 0x22, 0x39, 0x23, 0x36, 0xfe, 0xa1, 0x85, 0x1f, ++ 0x38 ++}; ++static const u8 dec_output001[] __initconst = { ++ 0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74, ++ 0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20, ++ 0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66, ++ 0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69, ++ 0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20, ++ 0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20, ++ 0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d, ++ 0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e, ++ 0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65, ++ 0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64, ++ 0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63, ++ 0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f, ++ 0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64, ++ 0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65, ++ 0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61, ++ 0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e, ++ 0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69, ++ 0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72, ++ 0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20, ++ 0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65, ++ 0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61, ++ 0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72, ++ 0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65, ++ 0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61, ++ 0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20, ++ 0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65, ++ 0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20, ++ 0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20, ++ 0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b, ++ 0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67, ++ 0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80, ++ 0x9d ++}; ++static const u8 dec_assoc001[] __initconst = { ++ 0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x4e, 0x91 ++}; ++static const u8 dec_nonce001[] __initconst = { ++ 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08 ++}; ++static const u8 dec_key001[] __initconst = { ++ 0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a, ++ 0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0, ++ 0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09, ++ 0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0 ++}; ++ ++static const u8 dec_input002[] __initconst = { ++ 0xea, 0xe0, 0x1e, 0x9e, 0x2c, 0x91, 0xaa, 0xe1, ++ 0xdb, 0x5d, 0x99, 0x3f, 0x8a, 0xf7, 0x69, 0x92 ++}; ++static const u8 dec_output002[] __initconst = { }; ++static const u8 dec_assoc002[] __initconst = { }; ++static const u8 dec_nonce002[] __initconst = { ++ 0xca, 0xbf, 0x33, 0x71, 0x32, 0x45, 0x77, 0x8e ++}; ++static const u8 dec_key002[] __initconst = { ++ 0x4c, 0xf5, 0x96, 0x83, 0x38, 0xe6, 0xae, 0x7f, ++ 0x2d, 0x29, 0x25, 0x76, 0xd5, 0x75, 0x27, 0x86, ++ 0x91, 0x9a, 0x27, 0x7a, 0xfb, 0x46, 0xc5, 0xef, ++ 0x94, 0x81, 0x79, 0x57, 0x14, 0x59, 0x40, 0x68 ++}; ++ ++static const u8 dec_input003[] __initconst = { ++ 0xdd, 0x6b, 0x3b, 0x82, 0xce, 0x5a, 0xbd, 0xd6, ++ 0xa9, 0x35, 0x83, 0xd8, 0x8c, 0x3d, 0x85, 0x77 ++}; ++static const u8 dec_output003[] __initconst = { }; ++static const u8 dec_assoc003[] __initconst = { ++ 0x33, 0x10, 0x41, 0x12, 0x1f, 0xf3, 0xd2, 0x6b ++}; ++static const u8 dec_nonce003[] __initconst = { ++ 0x3d, 0x86, 0xb5, 0x6b, 0xc8, 0xa3, 0x1f, 0x1d ++}; ++static const u8 dec_key003[] __initconst = { ++ 0x2d, 0xb0, 0x5d, 0x40, 0xc8, 0xed, 0x44, 0x88, ++ 0x34, 0xd1, 0x13, 0xaf, 0x57, 0xa1, 0xeb, 0x3a, ++ 0x2a, 0x80, 0x51, 0x36, 0xec, 0x5b, 0xbc, 0x08, ++ 0x93, 0x84, 0x21, 0xb5, 0x13, 0x88, 0x3c, 0x0d ++}; ++ ++static const u8 dec_input004[] __initconst = { ++ 0xb7, 0x1b, 0xb0, 0x73, 0x59, 0xb0, 0x84, 0xb2, ++ 0x6d, 0x8e, 0xab, 0x94, 0x31, 0xa1, 0xae, 0xac, ++ 0x89 ++}; ++static const u8 dec_output004[] __initconst = { ++ 0xa4 ++}; ++static const u8 dec_assoc004[] __initconst = { ++ 0x6a, 0xe2, 0xad, 0x3f, 0x88, 0x39, 0x5a, 0x40 ++}; ++static const u8 dec_nonce004[] __initconst = { ++ 0xd2, 0x32, 0x1f, 0x29, 0x28, 0xc6, 0xc4, 0xc4 ++}; ++static const u8 dec_key004[] __initconst = { ++ 0x4b, 0x28, 0x4b, 0xa3, 0x7b, 0xbe, 0xe9, 0xf8, ++ 0x31, 0x80, 0x82, 0xd7, 0xd8, 0xe8, 0xb5, 0xa1, ++ 0xe2, 0x18, 0x18, 0x8a, 0x9c, 0xfa, 0xa3, 0x3d, ++ 0x25, 0x71, 0x3e, 0x40, 0xbc, 0x54, 0x7a, 0x3e ++}; ++ ++static const u8 dec_input005[] __initconst = { ++ 0xbf, 0xe1, 0x5b, 0x0b, 0xdb, 0x6b, 0xf5, 0x5e, ++ 0x6c, 0x5d, 0x84, 0x44, 0x39, 0x81, 0xc1, 0x9c, ++ 0xac ++}; ++static const u8 dec_output005[] __initconst = { ++ 0x2d ++}; ++static const u8 dec_assoc005[] __initconst = { }; ++static const u8 dec_nonce005[] __initconst = { ++ 0x20, 0x1c, 0xaa, 0x5f, 0x9c, 0xbf, 0x92, 0x30 ++}; ++static const u8 dec_key005[] __initconst = { ++ 0x66, 0xca, 0x9c, 0x23, 0x2a, 0x4b, 0x4b, 0x31, ++ 0x0e, 0x92, 0x89, 0x8b, 0xf4, 0x93, 0xc7, 0x87, ++ 0x98, 0xa3, 0xd8, 0x39, 0xf8, 0xf4, 0xa7, 0x01, ++ 0xc0, 0x2e, 0x0a, 0xa6, 0x7e, 0x5a, 0x78, 0x87 ++}; ++ ++static const u8 dec_input006[] __initconst = { ++ 0x8b, 0x06, 0xd3, 0x31, 0xb0, 0x93, 0x45, 0xb1, ++ 0x75, 0x6e, 0x26, 0xf9, 0x67, 0xbc, 0x90, 0x15, ++ 0x81, 0x2c, 0xb5, 0xf0, 0xc6, 0x2b, 0xc7, 0x8c, ++ 0x56, 0xd1, 0xbf, 0x69, 0x6c, 0x07, 0xa0, 0xda, ++ 0x65, 0x27, 0xc9, 0x90, 0x3d, 0xef, 0x4b, 0x11, ++ 0x0f, 0x19, 0x07, 0xfd, 0x29, 0x92, 0xd9, 0xc8, ++ 0xf7, 0x99, 0x2e, 0x4a, 0xd0, 0xb8, 0x2c, 0xdc, ++ 0x93, 0xf5, 0x9e, 0x33, 0x78, 0xd1, 0x37, 0xc3, ++ 0x66, 0xd7, 0x5e, 0xbc, 0x44, 0xbf, 0x53, 0xa5, ++ 0xbc, 0xc4, 0xcb, 0x7b, 0x3a, 0x8e, 0x7f, 0x02, ++ 0xbd, 0xbb, 0xe7, 0xca, 0xa6, 0x6c, 0x6b, 0x93, ++ 0x21, 0x93, 0x10, 0x61, 0xe7, 0x69, 0xd0, 0x78, ++ 0xf3, 0x07, 0x5a, 0x1a, 0x8f, 0x73, 0xaa, 0xb1, ++ 0x4e, 0xd3, 0xda, 0x4f, 0xf3, 0x32, 0xe1, 0x66, ++ 0x3e, 0x6c, 0xc6, 0x13, 0xba, 0x06, 0x5b, 0xfc, ++ 0x6a, 0xe5, 0x6f, 0x60, 0xfb, 0x07, 0x40, 0xb0, ++ 0x8c, 0x9d, 0x84, 0x43, 0x6b, 0xc1, 0xf7, 0x8d, ++ 0x8d, 0x31, 0xf7, 0x7a, 0x39, 0x4d, 0x8f, 0x9a, ++ 0xeb ++}; ++static const u8 dec_output006[] __initconst = { ++ 0x33, 0x2f, 0x94, 0xc1, 0xa4, 0xef, 0xcc, 0x2a, ++ 0x5b, 0xa6, 0xe5, 0x8f, 0x1d, 0x40, 0xf0, 0x92, ++ 0x3c, 0xd9, 0x24, 0x11, 0xa9, 0x71, 0xf9, 0x37, ++ 0x14, 0x99, 0xfa, 0xbe, 0xe6, 0x80, 0xde, 0x50, ++ 0xc9, 0x96, 0xd4, 0xb0, 0xec, 0x9e, 0x17, 0xec, ++ 0xd2, 0x5e, 0x72, 0x99, 0xfc, 0x0a, 0xe1, 0xcb, ++ 0x48, 0xd2, 0x85, 0xdd, 0x2f, 0x90, 0xe0, 0x66, ++ 0x3b, 0xe6, 0x20, 0x74, 0xbe, 0x23, 0x8f, 0xcb, ++ 0xb4, 0xe4, 0xda, 0x48, 0x40, 0xa6, 0xd1, 0x1b, ++ 0xc7, 0x42, 0xce, 0x2f, 0x0c, 0xa6, 0x85, 0x6e, ++ 0x87, 0x37, 0x03, 0xb1, 0x7c, 0x25, 0x96, 0xa3, ++ 0x05, 0xd8, 0xb0, 0xf4, 0xed, 0xea, 0xc2, 0xf0, ++ 0x31, 0x98, 0x6c, 0xd1, 0x14, 0x25, 0xc0, 0xcb, ++ 0x01, 0x74, 0xd0, 0x82, 0xf4, 0x36, 0xf5, 0x41, ++ 0xd5, 0xdc, 0xca, 0xc5, 0xbb, 0x98, 0xfe, 0xfc, ++ 0x69, 0x21, 0x70, 0xd8, 0xa4, 0x4b, 0xc8, 0xde, ++ 0x8f ++}; ++static const u8 dec_assoc006[] __initconst = { ++ 0x70, 0xd3, 0x33, 0xf3, 0x8b, 0x18, 0x0b ++}; ++static const u8 dec_nonce006[] __initconst = { ++ 0xdf, 0x51, 0x84, 0x82, 0x42, 0x0c, 0x75, 0x9c ++}; ++static const u8 dec_key006[] __initconst = { ++ 0x68, 0x7b, 0x8d, 0x8e, 0xe3, 0xc4, 0xdd, 0xae, ++ 0xdf, 0x72, 0x7f, 0x53, 0x72, 0x25, 0x1e, 0x78, ++ 0x91, 0xcb, 0x69, 0x76, 0x1f, 0x49, 0x93, 0xf9, ++ 0x6f, 0x21, 0xcc, 0x39, 0x9c, 0xad, 0xb1, 0x01 ++}; ++ ++static const u8 dec_input007[] __initconst = { ++ 0x85, 0x04, 0xc2, 0xed, 0x8d, 0xfd, 0x97, 0x5c, ++ 0xd2, 0xb7, 0xe2, 0xc1, 0x6b, 0xa3, 0xba, 0xf8, ++ 0xc9, 0x50, 0xc3, 0xc6, 0xa5, 0xe3, 0xa4, 0x7c, ++ 0xc3, 0x23, 0x49, 0x5e, 0xa9, 0xb9, 0x32, 0xeb, ++ 0x8a, 0x7c, 0xca, 0xe5, 0xec, 0xfb, 0x7c, 0xc0, ++ 0xcb, 0x7d, 0xdc, 0x2c, 0x9d, 0x92, 0x55, 0x21, ++ 0x0a, 0xc8, 0x43, 0x63, 0x59, 0x0a, 0x31, 0x70, ++ 0x82, 0x67, 0x41, 0x03, 0xf8, 0xdf, 0xf2, 0xac, ++ 0xa7, 0x02, 0xd4, 0xd5, 0x8a, 0x2d, 0xc8, 0x99, ++ 0x19, 0x66, 0xd0, 0xf6, 0x88, 0x2c, 0x77, 0xd9, ++ 0xd4, 0x0d, 0x6c, 0xbd, 0x98, 0xde, 0xe7, 0x7f, ++ 0xad, 0x7e, 0x8a, 0xfb, 0xe9, 0x4b, 0xe5, 0xf7, ++ 0xe5, 0x50, 0xa0, 0x90, 0x3f, 0xd6, 0x22, 0x53, ++ 0xe3, 0xfe, 0x1b, 0xcc, 0x79, 0x3b, 0xec, 0x12, ++ 0x47, 0x52, 0xa7, 0xd6, 0x04, 0xe3, 0x52, 0xe6, ++ 0x93, 0x90, 0x91, 0x32, 0x73, 0x79, 0xb8, 0xd0, ++ 0x31, 0xde, 0x1f, 0x9f, 0x2f, 0x05, 0x38, 0x54, ++ 0x2f, 0x35, 0x04, 0x39, 0xe0, 0xa7, 0xba, 0xc6, ++ 0x52, 0xf6, 0x37, 0x65, 0x4c, 0x07, 0xa9, 0x7e, ++ 0xb3, 0x21, 0x6f, 0x74, 0x8c, 0xc9, 0xde, 0xdb, ++ 0x65, 0x1b, 0x9b, 0xaa, 0x60, 0xb1, 0x03, 0x30, ++ 0x6b, 0xb2, 0x03, 0xc4, 0x1c, 0x04, 0xf8, 0x0f, ++ 0x64, 0xaf, 0x46, 0xe4, 0x65, 0x99, 0x49, 0xe2, ++ 0xea, 0xce, 0x78, 0x00, 0xd8, 0x8b, 0xd5, 0x2e, ++ 0xcf, 0xfc, 0x40, 0x49, 0xe8, 0x58, 0xdc, 0x34, ++ 0x9c, 0x8c, 0x61, 0xbf, 0x0a, 0x8e, 0xec, 0x39, ++ 0xa9, 0x30, 0x05, 0x5a, 0xd2, 0x56, 0x01, 0xc7, ++ 0xda, 0x8f, 0x4e, 0xbb, 0x43, 0xa3, 0x3a, 0xf9, ++ 0x15, 0x2a, 0xd0, 0xa0, 0x7a, 0x87, 0x34, 0x82, ++ 0xfe, 0x8a, 0xd1, 0x2d, 0x5e, 0xc7, 0xbf, 0x04, ++ 0x53, 0x5f, 0x3b, 0x36, 0xd4, 0x25, 0x5c, 0x34, ++ 0x7a, 0x8d, 0xd5, 0x05, 0xce, 0x72, 0xca, 0xef, ++ 0x7a, 0x4b, 0xbc, 0xb0, 0x10, 0x5c, 0x96, 0x42, ++ 0x3a, 0x00, 0x98, 0xcd, 0x15, 0xe8, 0xb7, 0x53 ++}; ++static const u8 dec_output007[] __initconst = { ++ 0x9b, 0x18, 0xdb, 0xdd, 0x9a, 0x0f, 0x3e, 0xa5, ++ 0x15, 0x17, 0xde, 0xdf, 0x08, 0x9d, 0x65, 0x0a, ++ 0x67, 0x30, 0x12, 0xe2, 0x34, 0x77, 0x4b, 0xc1, ++ 0xd9, 0xc6, 0x1f, 0xab, 0xc6, 0x18, 0x50, 0x17, ++ 0xa7, 0x9d, 0x3c, 0xa6, 0xc5, 0x35, 0x8c, 0x1c, ++ 0xc0, 0xa1, 0x7c, 0x9f, 0x03, 0x89, 0xca, 0xe1, ++ 0xe6, 0xe9, 0xd4, 0xd3, 0x88, 0xdb, 0xb4, 0x51, ++ 0x9d, 0xec, 0xb4, 0xfc, 0x52, 0xee, 0x6d, 0xf1, ++ 0x75, 0x42, 0xc6, 0xfd, 0xbd, 0x7a, 0x8e, 0x86, ++ 0xfc, 0x44, 0xb3, 0x4f, 0xf3, 0xea, 0x67, 0x5a, ++ 0x41, 0x13, 0xba, 0xb0, 0xdc, 0xe1, 0xd3, 0x2a, ++ 0x7c, 0x22, 0xb3, 0xca, 0xac, 0x6a, 0x37, 0x98, ++ 0x3e, 0x1d, 0x40, 0x97, 0xf7, 0x9b, 0x1d, 0x36, ++ 0x6b, 0xb3, 0x28, 0xbd, 0x60, 0x82, 0x47, 0x34, ++ 0xaa, 0x2f, 0x7d, 0xe9, 0xa8, 0x70, 0x81, 0x57, ++ 0xd4, 0xb9, 0x77, 0x0a, 0x9d, 0x29, 0xa7, 0x84, ++ 0x52, 0x4f, 0xc2, 0x4a, 0x40, 0x3b, 0x3c, 0xd4, ++ 0xc9, 0x2a, 0xdb, 0x4a, 0x53, 0xc4, 0xbe, 0x80, ++ 0xe9, 0x51, 0x7f, 0x8f, 0xc7, 0xa2, 0xce, 0x82, ++ 0x5c, 0x91, 0x1e, 0x74, 0xd9, 0xd0, 0xbd, 0xd5, ++ 0xf3, 0xfd, 0xda, 0x4d, 0x25, 0xb4, 0xbb, 0x2d, ++ 0xac, 0x2f, 0x3d, 0x71, 0x85, 0x7b, 0xcf, 0x3c, ++ 0x7b, 0x3e, 0x0e, 0x22, 0x78, 0x0c, 0x29, 0xbf, ++ 0xe4, 0xf4, 0x57, 0xb3, 0xcb, 0x49, 0xa0, 0xfc, ++ 0x1e, 0x05, 0x4e, 0x16, 0xbc, 0xd5, 0xa8, 0xa3, ++ 0xee, 0x05, 0x35, 0xc6, 0x7c, 0xab, 0x60, 0x14, ++ 0x55, 0x1a, 0x8e, 0xc5, 0x88, 0x5d, 0xd5, 0x81, ++ 0xc2, 0x81, 0xa5, 0xc4, 0x60, 0xdb, 0xaf, 0x77, ++ 0x91, 0xe1, 0xce, 0xa2, 0x7e, 0x7f, 0x42, 0xe3, ++ 0xb0, 0x13, 0x1c, 0x1f, 0x25, 0x60, 0x21, 0xe2, ++ 0x40, 0x5f, 0x99, 0xb7, 0x73, 0xec, 0x9b, 0x2b, ++ 0xf0, 0x65, 0x11, 0xc8, 0xd0, 0x0a, 0x9f, 0xd3 ++}; ++static const u8 dec_assoc007[] __initconst = { }; ++static const u8 dec_nonce007[] __initconst = { ++ 0xde, 0x7b, 0xef, 0xc3, 0x65, 0x1b, 0x68, 0xb0 ++}; ++static const u8 dec_key007[] __initconst = { ++ 0x8d, 0xb8, 0x91, 0x48, 0xf0, 0xe7, 0x0a, 0xbd, ++ 0xf9, 0x3f, 0xcd, 0xd9, 0xa0, 0x1e, 0x42, 0x4c, ++ 0xe7, 0xde, 0x25, 0x3d, 0xa3, 0xd7, 0x05, 0x80, ++ 0x8d, 0xf2, 0x82, 0xac, 0x44, 0x16, 0x51, 0x01 ++}; ++ ++static const u8 dec_input008[] __initconst = { ++ 0x14, 0xf6, 0x41, 0x37, 0xa6, 0xd4, 0x27, 0xcd, ++ 0xdb, 0x06, 0x3e, 0x9a, 0x4e, 0xab, 0xd5, 0xb1, ++ 0x1e, 0x6b, 0xd2, 0xbc, 0x11, 0xf4, 0x28, 0x93, ++ 0x63, 0x54, 0xef, 0xbb, 0x5e, 0x1d, 0x3a, 0x1d, ++ 0x37, 0x3c, 0x0a, 0x6c, 0x1e, 0xc2, 0xd1, 0x2c, ++ 0xb5, 0xa3, 0xb5, 0x7b, 0xb8, 0x8f, 0x25, 0xa6, ++ 0x1b, 0x61, 0x1c, 0xec, 0x28, 0x58, 0x26, 0xa4, ++ 0xa8, 0x33, 0x28, 0x25, 0x5c, 0x45, 0x05, 0xe5, ++ 0x6c, 0x99, 0xe5, 0x45, 0xc4, 0xa2, 0x03, 0x84, ++ 0x03, 0x73, 0x1e, 0x8c, 0x49, 0xac, 0x20, 0xdd, ++ 0x8d, 0xb3, 0xc4, 0xf5, 0xe7, 0x4f, 0xf1, 0xed, ++ 0xa1, 0x98, 0xde, 0xa4, 0x96, 0xdd, 0x2f, 0xab, ++ 0xab, 0x97, 0xcf, 0x3e, 0xd2, 0x9e, 0xb8, 0x13, ++ 0x07, 0x28, 0x29, 0x19, 0xaf, 0xfd, 0xf2, 0x49, ++ 0x43, 0xea, 0x49, 0x26, 0x91, 0xc1, 0x07, 0xd6, ++ 0xbb, 0x81, 0x75, 0x35, 0x0d, 0x24, 0x7f, 0xc8, ++ 0xda, 0xd4, 0xb7, 0xeb, 0xe8, 0x5c, 0x09, 0xa2, ++ 0x2f, 0xdc, 0x28, 0x7d, 0x3a, 0x03, 0xfa, 0x94, ++ 0xb5, 0x1d, 0x17, 0x99, 0x36, 0xc3, 0x1c, 0x18, ++ 0x34, 0xe3, 0x9f, 0xf5, 0x55, 0x7c, 0xb0, 0x60, ++ 0x9d, 0xff, 0xac, 0xd4, 0x61, 0xf2, 0xad, 0xf8, ++ 0xce, 0xc7, 0xbe, 0x5c, 0xd2, 0x95, 0xa8, 0x4b, ++ 0x77, 0x13, 0x19, 0x59, 0x26, 0xc9, 0xb7, 0x8f, ++ 0x6a, 0xcb, 0x2d, 0x37, 0x91, 0xea, 0x92, 0x9c, ++ 0x94, 0x5b, 0xda, 0x0b, 0xce, 0xfe, 0x30, 0x20, ++ 0xf8, 0x51, 0xad, 0xf2, 0xbe, 0xe7, 0xc7, 0xff, ++ 0xb3, 0x33, 0x91, 0x6a, 0xc9, 0x1a, 0x41, 0xc9, ++ 0x0f, 0xf3, 0x10, 0x0e, 0xfd, 0x53, 0xff, 0x6c, ++ 0x16, 0x52, 0xd9, 0xf3, 0xf7, 0x98, 0x2e, 0xc9, ++ 0x07, 0x31, 0x2c, 0x0c, 0x72, 0xd7, 0xc5, 0xc6, ++ 0x08, 0x2a, 0x7b, 0xda, 0xbd, 0x7e, 0x02, 0xea, ++ 0x1a, 0xbb, 0xf2, 0x04, 0x27, 0x61, 0x28, 0x8e, ++ 0xf5, 0x04, 0x03, 0x1f, 0x4c, 0x07, 0x55, 0x82, ++ 0xec, 0x1e, 0xd7, 0x8b, 0x2f, 0x65, 0x56, 0xd1, ++ 0xd9, 0x1e, 0x3c, 0xe9, 0x1f, 0x5e, 0x98, 0x70, ++ 0x38, 0x4a, 0x8c, 0x49, 0xc5, 0x43, 0xa0, 0xa1, ++ 0x8b, 0x74, 0x9d, 0x4c, 0x62, 0x0d, 0x10, 0x0c, ++ 0xf4, 0x6c, 0x8f, 0xe0, 0xaa, 0x9a, 0x8d, 0xb7, ++ 0xe0, 0xbe, 0x4c, 0x87, 0xf1, 0x98, 0x2f, 0xcc, ++ 0xed, 0xc0, 0x52, 0x29, 0xdc, 0x83, 0xf8, 0xfc, ++ 0x2c, 0x0e, 0xa8, 0x51, 0x4d, 0x80, 0x0d, 0xa3, ++ 0xfe, 0xd8, 0x37, 0xe7, 0x41, 0x24, 0xfc, 0xfb, ++ 0x75, 0xe3, 0x71, 0x7b, 0x57, 0x45, 0xf5, 0x97, ++ 0x73, 0x65, 0x63, 0x14, 0x74, 0xb8, 0x82, 0x9f, ++ 0xf8, 0x60, 0x2f, 0x8a, 0xf2, 0x4e, 0xf1, 0x39, ++ 0xda, 0x33, 0x91, 0xf8, 0x36, 0xe0, 0x8d, 0x3f, ++ 0x1f, 0x3b, 0x56, 0xdc, 0xa0, 0x8f, 0x3c, 0x9d, ++ 0x71, 0x52, 0xa7, 0xb8, 0xc0, 0xa5, 0xc6, 0xa2, ++ 0x73, 0xda, 0xf4, 0x4b, 0x74, 0x5b, 0x00, 0x3d, ++ 0x99, 0xd7, 0x96, 0xba, 0xe6, 0xe1, 0xa6, 0x96, ++ 0x38, 0xad, 0xb3, 0xc0, 0xd2, 0xba, 0x91, 0x6b, ++ 0xf9, 0x19, 0xdd, 0x3b, 0xbe, 0xbe, 0x9c, 0x20, ++ 0x50, 0xba, 0xa1, 0xd0, 0xce, 0x11, 0xbd, 0x95, ++ 0xd8, 0xd1, 0xdd, 0x33, 0x85, 0x74, 0xdc, 0xdb, ++ 0x66, 0x76, 0x44, 0xdc, 0x03, 0x74, 0x48, 0x35, ++ 0x98, 0xb1, 0x18, 0x47, 0x94, 0x7d, 0xff, 0x62, ++ 0xe4, 0x58, 0x78, 0xab, 0xed, 0x95, 0x36, 0xd9, ++ 0x84, 0x91, 0x82, 0x64, 0x41, 0xbb, 0x58, 0xe6, ++ 0x1c, 0x20, 0x6d, 0x15, 0x6b, 0x13, 0x96, 0xe8, ++ 0x35, 0x7f, 0xdc, 0x40, 0x2c, 0xe9, 0xbc, 0x8a, ++ 0x4f, 0x92, 0xec, 0x06, 0x2d, 0x50, 0xdf, 0x93, ++ 0x5d, 0x65, 0x5a, 0xa8, 0xfc, 0x20, 0x50, 0x14, ++ 0xa9, 0x8a, 0x7e, 0x1d, 0x08, 0x1f, 0xe2, 0x99, ++ 0xd0, 0xbe, 0xfb, 0x3a, 0x21, 0x9d, 0xad, 0x86, ++ 0x54, 0xfd, 0x0d, 0x98, 0x1c, 0x5a, 0x6f, 0x1f, ++ 0x9a, 0x40, 0xcd, 0xa2, 0xff, 0x6a, 0xf1, 0x54 ++}; ++static const u8 dec_output008[] __initconst = { ++ 0xc3, 0x09, 0x94, 0x62, 0xe6, 0x46, 0x2e, 0x10, ++ 0xbe, 0x00, 0xe4, 0xfc, 0xf3, 0x40, 0xa3, 0xe2, ++ 0x0f, 0xc2, 0x8b, 0x28, 0xdc, 0xba, 0xb4, 0x3c, ++ 0xe4, 0x21, 0x58, 0x61, 0xcd, 0x8b, 0xcd, 0xfb, ++ 0xac, 0x94, 0xa1, 0x45, 0xf5, 0x1c, 0xe1, 0x12, ++ 0xe0, 0x3b, 0x67, 0x21, 0x54, 0x5e, 0x8c, 0xaa, ++ 0xcf, 0xdb, 0xb4, 0x51, 0xd4, 0x13, 0xda, 0xe6, ++ 0x83, 0x89, 0xb6, 0x92, 0xe9, 0x21, 0x76, 0xa4, ++ 0x93, 0x7d, 0x0e, 0xfd, 0x96, 0x36, 0x03, 0x91, ++ 0x43, 0x5c, 0x92, 0x49, 0x62, 0x61, 0x7b, 0xeb, ++ 0x43, 0x89, 0xb8, 0x12, 0x20, 0x43, 0xd4, 0x47, ++ 0x06, 0x84, 0xee, 0x47, 0xe9, 0x8a, 0x73, 0x15, ++ 0x0f, 0x72, 0xcf, 0xed, 0xce, 0x96, 0xb2, 0x7f, ++ 0x21, 0x45, 0x76, 0xeb, 0x26, 0x28, 0x83, 0x6a, ++ 0xad, 0xaa, 0xa6, 0x81, 0xd8, 0x55, 0xb1, 0xa3, ++ 0x85, 0xb3, 0x0c, 0xdf, 0xf1, 0x69, 0x2d, 0x97, ++ 0x05, 0x2a, 0xbc, 0x7c, 0x7b, 0x25, 0xf8, 0x80, ++ 0x9d, 0x39, 0x25, 0xf3, 0x62, 0xf0, 0x66, 0x5e, ++ 0xf4, 0xa0, 0xcf, 0xd8, 0xfd, 0x4f, 0xb1, 0x1f, ++ 0x60, 0x3a, 0x08, 0x47, 0xaf, 0xe1, 0xf6, 0x10, ++ 0x77, 0x09, 0xa7, 0x27, 0x8f, 0x9a, 0x97, 0x5a, ++ 0x26, 0xfa, 0xfe, 0x41, 0x32, 0x83, 0x10, 0xe0, ++ 0x1d, 0xbf, 0x64, 0x0d, 0xf4, 0x1c, 0x32, 0x35, ++ 0xe5, 0x1b, 0x36, 0xef, 0xd4, 0x4a, 0x93, 0x4d, ++ 0x00, 0x7c, 0xec, 0x02, 0x07, 0x8b, 0x5d, 0x7d, ++ 0x1b, 0x0e, 0xd1, 0xa6, 0xa5, 0x5d, 0x7d, 0x57, ++ 0x88, 0xa8, 0xcc, 0x81, 0xb4, 0x86, 0x4e, 0xb4, ++ 0x40, 0xe9, 0x1d, 0xc3, 0xb1, 0x24, 0x3e, 0x7f, ++ 0xcc, 0x8a, 0x24, 0x9b, 0xdf, 0x6d, 0xf0, 0x39, ++ 0x69, 0x3e, 0x4c, 0xc0, 0x96, 0xe4, 0x13, 0xda, ++ 0x90, 0xda, 0xf4, 0x95, 0x66, 0x8b, 0x17, 0x17, ++ 0xfe, 0x39, 0x43, 0x25, 0xaa, 0xda, 0xa0, 0x43, ++ 0x3c, 0xb1, 0x41, 0x02, 0xa3, 0xf0, 0xa7, 0x19, ++ 0x59, 0xbc, 0x1d, 0x7d, 0x6c, 0x6d, 0x91, 0x09, ++ 0x5c, 0xb7, 0x5b, 0x01, 0xd1, 0x6f, 0x17, 0x21, ++ 0x97, 0xbf, 0x89, 0x71, 0xa5, 0xb0, 0x6e, 0x07, ++ 0x45, 0xfd, 0x9d, 0xea, 0x07, 0xf6, 0x7a, 0x9f, ++ 0x10, 0x18, 0x22, 0x30, 0x73, 0xac, 0xd4, 0x6b, ++ 0x72, 0x44, 0xed, 0xd9, 0x19, 0x9b, 0x2d, 0x4a, ++ 0x41, 0xdd, 0xd1, 0x85, 0x5e, 0x37, 0x19, 0xed, ++ 0xd2, 0x15, 0x8f, 0x5e, 0x91, 0xdb, 0x33, 0xf2, ++ 0xe4, 0xdb, 0xff, 0x98, 0xfb, 0xa3, 0xb5, 0xca, ++ 0x21, 0x69, 0x08, 0xe7, 0x8a, 0xdf, 0x90, 0xff, ++ 0x3e, 0xe9, 0x20, 0x86, 0x3c, 0xe9, 0xfc, 0x0b, ++ 0xfe, 0x5c, 0x61, 0xaa, 0x13, 0x92, 0x7f, 0x7b, ++ 0xec, 0xe0, 0x6d, 0xa8, 0x23, 0x22, 0xf6, 0x6b, ++ 0x77, 0xc4, 0xfe, 0x40, 0x07, 0x3b, 0xb6, 0xf6, ++ 0x8e, 0x5f, 0xd4, 0xb9, 0xb7, 0x0f, 0x21, 0x04, ++ 0xef, 0x83, 0x63, 0x91, 0x69, 0x40, 0xa3, 0x48, ++ 0x5c, 0xd2, 0x60, 0xf9, 0x4f, 0x6c, 0x47, 0x8b, ++ 0x3b, 0xb1, 0x9f, 0x8e, 0xee, 0x16, 0x8a, 0x13, ++ 0xfc, 0x46, 0x17, 0xc3, 0xc3, 0x32, 0x56, 0xf8, ++ 0x3c, 0x85, 0x3a, 0xb6, 0x3e, 0xaa, 0x89, 0x4f, ++ 0xb3, 0xdf, 0x38, 0xfd, 0xf1, 0xe4, 0x3a, 0xc0, ++ 0xe6, 0x58, 0xb5, 0x8f, 0xc5, 0x29, 0xa2, 0x92, ++ 0x4a, 0xb6, 0xa0, 0x34, 0x7f, 0xab, 0xb5, 0x8a, ++ 0x90, 0xa1, 0xdb, 0x4d, 0xca, 0xb6, 0x2c, 0x41, ++ 0x3c, 0xf7, 0x2b, 0x21, 0xc3, 0xfd, 0xf4, 0x17, ++ 0x5c, 0xb5, 0x33, 0x17, 0x68, 0x2b, 0x08, 0x30, ++ 0xf3, 0xf7, 0x30, 0x3c, 0x96, 0xe6, 0x6a, 0x20, ++ 0x97, 0xe7, 0x4d, 0x10, 0x5f, 0x47, 0x5f, 0x49, ++ 0x96, 0x09, 0xf0, 0x27, 0x91, 0xc8, 0xf8, 0x5a, ++ 0x2e, 0x79, 0xb5, 0xe2, 0xb8, 0xe8, 0xb9, 0x7b, ++ 0xd5, 0x10, 0xcb, 0xff, 0x5d, 0x14, 0x73, 0xf3 ++}; ++static const u8 dec_assoc008[] __initconst = { }; ++static const u8 dec_nonce008[] __initconst = { ++ 0x0e, 0x0d, 0x57, 0xbb, 0x7b, 0x40, 0x54, 0x02 ++}; ++static const u8 dec_key008[] __initconst = { ++ 0xf2, 0xaa, 0x4f, 0x99, 0xfd, 0x3e, 0xa8, 0x53, ++ 0xc1, 0x44, 0xe9, 0x81, 0x18, 0xdc, 0xf5, 0xf0, ++ 0x3e, 0x44, 0x15, 0x59, 0xe0, 0xc5, 0x44, 0x86, ++ 0xc3, 0x91, 0xa8, 0x75, 0xc0, 0x12, 0x46, 0xba ++}; ++ ++static const u8 dec_input009[] __initconst = { ++ 0xfd, 0x81, 0x8d, 0xd0, 0x3d, 0xb4, 0xd5, 0xdf, ++ 0xd3, 0x42, 0x47, 0x5a, 0x6d, 0x19, 0x27, 0x66, ++ 0x4b, 0x2e, 0x0c, 0x27, 0x9c, 0x96, 0x4c, 0x72, ++ 0x02, 0xa3, 0x65, 0xc3, 0xb3, 0x6f, 0x2e, 0xbd, ++ 0x63, 0x8a, 0x4a, 0x5d, 0x29, 0xa2, 0xd0, 0x28, ++ 0x48, 0xc5, 0x3d, 0x98, 0xa3, 0xbc, 0xe0, 0xbe, ++ 0x3b, 0x3f, 0xe6, 0x8a, 0xa4, 0x7f, 0x53, 0x06, ++ 0xfa, 0x7f, 0x27, 0x76, 0x72, 0x31, 0xa1, 0xf5, ++ 0xd6, 0x0c, 0x52, 0x47, 0xba, 0xcd, 0x4f, 0xd7, ++ 0xeb, 0x05, 0x48, 0x0d, 0x7c, 0x35, 0x4a, 0x09, ++ 0xc9, 0x76, 0x71, 0x02, 0xa3, 0xfb, 0xb7, 0x1a, ++ 0x65, 0xb7, 0xed, 0x98, 0xc6, 0x30, 0x8a, 0x00, ++ 0xae, 0xa1, 0x31, 0xe5, 0xb5, 0x9e, 0x6d, 0x62, ++ 0xda, 0xda, 0x07, 0x0f, 0x38, 0x38, 0xd3, 0xcb, ++ 0xc1, 0xb0, 0xad, 0xec, 0x72, 0xec, 0xb1, 0xa2, ++ 0x7b, 0x59, 0xf3, 0x3d, 0x2b, 0xef, 0xcd, 0x28, ++ 0x5b, 0x83, 0xcc, 0x18, 0x91, 0x88, 0xb0, 0x2e, ++ 0xf9, 0x29, 0x31, 0x18, 0xf9, 0x4e, 0xe9, 0x0a, ++ 0x91, 0x92, 0x9f, 0xae, 0x2d, 0xad, 0xf4, 0xe6, ++ 0x1a, 0xe2, 0xa4, 0xee, 0x47, 0x15, 0xbf, 0x83, ++ 0x6e, 0xd7, 0x72, 0x12, 0x3b, 0x2d, 0x24, 0xe9, ++ 0xb2, 0x55, 0xcb, 0x3c, 0x10, 0xf0, 0x24, 0x8a, ++ 0x4a, 0x02, 0xea, 0x90, 0x25, 0xf0, 0xb4, 0x79, ++ 0x3a, 0xef, 0x6e, 0xf5, 0x52, 0xdf, 0xb0, 0x0a, ++ 0xcd, 0x24, 0x1c, 0xd3, 0x2e, 0x22, 0x74, 0xea, ++ 0x21, 0x6f, 0xe9, 0xbd, 0xc8, 0x3e, 0x36, 0x5b, ++ 0x19, 0xf1, 0xca, 0x99, 0x0a, 0xb4, 0xa7, 0x52, ++ 0x1a, 0x4e, 0xf2, 0xad, 0x8d, 0x56, 0x85, 0xbb, ++ 0x64, 0x89, 0xba, 0x26, 0xf9, 0xc7, 0xe1, 0x89, ++ 0x19, 0x22, 0x77, 0xc3, 0xa8, 0xfc, 0xff, 0xad, ++ 0xfe, 0xb9, 0x48, 0xae, 0x12, 0x30, 0x9f, 0x19, ++ 0xfb, 0x1b, 0xef, 0x14, 0x87, 0x8a, 0x78, 0x71, ++ 0xf3, 0xf4, 0xb7, 0x00, 0x9c, 0x1d, 0xb5, 0x3d, ++ 0x49, 0x00, 0x0c, 0x06, 0xd4, 0x50, 0xf9, 0x54, ++ 0x45, 0xb2, 0x5b, 0x43, 0xdb, 0x6d, 0xcf, 0x1a, ++ 0xe9, 0x7a, 0x7a, 0xcf, 0xfc, 0x8a, 0x4e, 0x4d, ++ 0x0b, 0x07, 0x63, 0x28, 0xd8, 0xe7, 0x08, 0x95, ++ 0xdf, 0xa6, 0x72, 0x93, 0x2e, 0xbb, 0xa0, 0x42, ++ 0x89, 0x16, 0xf1, 0xd9, 0x0c, 0xf9, 0xa1, 0x16, ++ 0xfd, 0xd9, 0x03, 0xb4, 0x3b, 0x8a, 0xf5, 0xf6, ++ 0xe7, 0x6b, 0x2e, 0x8e, 0x4c, 0x3d, 0xe2, 0xaf, ++ 0x08, 0x45, 0x03, 0xff, 0x09, 0xb6, 0xeb, 0x2d, ++ 0xc6, 0x1b, 0x88, 0x94, 0xac, 0x3e, 0xf1, 0x9f, ++ 0x0e, 0x0e, 0x2b, 0xd5, 0x00, 0x4d, 0x3f, 0x3b, ++ 0x53, 0xae, 0xaf, 0x1c, 0x33, 0x5f, 0x55, 0x6e, ++ 0x8d, 0xaf, 0x05, 0x7a, 0x10, 0x34, 0xc9, 0xf4, ++ 0x66, 0xcb, 0x62, 0x12, 0xa6, 0xee, 0xe8, 0x1c, ++ 0x5d, 0x12, 0x86, 0xdb, 0x6f, 0x1c, 0x33, 0xc4, ++ 0x1c, 0xda, 0x82, 0x2d, 0x3b, 0x59, 0xfe, 0xb1, ++ 0xa4, 0x59, 0x41, 0x86, 0xd0, 0xef, 0xae, 0xfb, ++ 0xda, 0x6d, 0x11, 0xb8, 0xca, 0xe9, 0x6e, 0xff, ++ 0xf7, 0xa9, 0xd9, 0x70, 0x30, 0xfc, 0x53, 0xe2, ++ 0xd7, 0xa2, 0x4e, 0xc7, 0x91, 0xd9, 0x07, 0x06, ++ 0xaa, 0xdd, 0xb0, 0x59, 0x28, 0x1d, 0x00, 0x66, ++ 0xc5, 0x54, 0xc2, 0xfc, 0x06, 0xda, 0x05, 0x90, ++ 0x52, 0x1d, 0x37, 0x66, 0xee, 0xf0, 0xb2, 0x55, ++ 0x8a, 0x5d, 0xd2, 0x38, 0x86, 0x94, 0x9b, 0xfc, ++ 0x10, 0x4c, 0xa1, 0xb9, 0x64, 0x3e, 0x44, 0xb8, ++ 0x5f, 0xb0, 0x0c, 0xec, 0xe0, 0xc9, 0xe5, 0x62, ++ 0x75, 0x3f, 0x09, 0xd5, 0xf5, 0xd9, 0x26, 0xba, ++ 0x9e, 0xd2, 0xf4, 0xb9, 0x48, 0x0a, 0xbc, 0xa2, ++ 0xd6, 0x7c, 0x36, 0x11, 0x7d, 0x26, 0x81, 0x89, ++ 0xcf, 0xa4, 0xad, 0x73, 0x0e, 0xee, 0xcc, 0x06, ++ 0xa9, 0xdb, 0xb1, 0xfd, 0xfb, 0x09, 0x7f, 0x90, ++ 0x42, 0x37, 0x2f, 0xe1, 0x9c, 0x0f, 0x6f, 0xcf, ++ 0x43, 0xb5, 0xd9, 0x90, 0xe1, 0x85, 0xf5, 0xa8, ++ 0xae ++}; ++static const u8 dec_output009[] __initconst = { ++ 0xe6, 0xc3, 0xdb, 0x63, 0x55, 0x15, 0xe3, 0x5b, ++ 0xb7, 0x4b, 0x27, 0x8b, 0x5a, 0xdd, 0xc2, 0xe8, ++ 0x3a, 0x6b, 0xd7, 0x81, 0x96, 0x35, 0x97, 0xca, ++ 0xd7, 0x68, 0xe8, 0xef, 0xce, 0xab, 0xda, 0x09, ++ 0x6e, 0xd6, 0x8e, 0xcb, 0x55, 0xb5, 0xe1, 0xe5, ++ 0x57, 0xfd, 0xc4, 0xe3, 0xe0, 0x18, 0x4f, 0x85, ++ 0xf5, 0x3f, 0x7e, 0x4b, 0x88, 0xc9, 0x52, 0x44, ++ 0x0f, 0xea, 0xaf, 0x1f, 0x71, 0x48, 0x9f, 0x97, ++ 0x6d, 0xb9, 0x6f, 0x00, 0xa6, 0xde, 0x2b, 0x77, ++ 0x8b, 0x15, 0xad, 0x10, 0xa0, 0x2b, 0x7b, 0x41, ++ 0x90, 0x03, 0x2d, 0x69, 0xae, 0xcc, 0x77, 0x7c, ++ 0xa5, 0x9d, 0x29, 0x22, 0xc2, 0xea, 0xb4, 0x00, ++ 0x1a, 0xd2, 0x7a, 0x98, 0x8a, 0xf9, 0xf7, 0x82, ++ 0xb0, 0xab, 0xd8, 0xa6, 0x94, 0x8d, 0x58, 0x2f, ++ 0x01, 0x9e, 0x00, 0x20, 0xfc, 0x49, 0xdc, 0x0e, ++ 0x03, 0xe8, 0x45, 0x10, 0xd6, 0xa8, 0xda, 0x55, ++ 0x10, 0x9a, 0xdf, 0x67, 0x22, 0x8b, 0x43, 0xab, ++ 0x00, 0xbb, 0x02, 0xc8, 0xdd, 0x7b, 0x97, 0x17, ++ 0xd7, 0x1d, 0x9e, 0x02, 0x5e, 0x48, 0xde, 0x8e, ++ 0xcf, 0x99, 0x07, 0x95, 0x92, 0x3c, 0x5f, 0x9f, ++ 0xc5, 0x8a, 0xc0, 0x23, 0xaa, 0xd5, 0x8c, 0x82, ++ 0x6e, 0x16, 0x92, 0xb1, 0x12, 0x17, 0x07, 0xc3, ++ 0xfb, 0x36, 0xf5, 0x6c, 0x35, 0xd6, 0x06, 0x1f, ++ 0x9f, 0xa7, 0x94, 0xa2, 0x38, 0x63, 0x9c, 0xb0, ++ 0x71, 0xb3, 0xa5, 0xd2, 0xd8, 0xba, 0x9f, 0x08, ++ 0x01, 0xb3, 0xff, 0x04, 0x97, 0x73, 0x45, 0x1b, ++ 0xd5, 0xa9, 0x9c, 0x80, 0xaf, 0x04, 0x9a, 0x85, ++ 0xdb, 0x32, 0x5b, 0x5d, 0x1a, 0xc1, 0x36, 0x28, ++ 0x10, 0x79, 0xf1, 0x3c, 0xbf, 0x1a, 0x41, 0x5c, ++ 0x4e, 0xdf, 0xb2, 0x7c, 0x79, 0x3b, 0x7a, 0x62, ++ 0x3d, 0x4b, 0xc9, 0x9b, 0x2a, 0x2e, 0x7c, 0xa2, ++ 0xb1, 0x11, 0x98, 0xa7, 0x34, 0x1a, 0x00, 0xf3, ++ 0xd1, 0xbc, 0x18, 0x22, 0xba, 0x02, 0x56, 0x62, ++ 0x31, 0x10, 0x11, 0x6d, 0xe0, 0x54, 0x9d, 0x40, ++ 0x1f, 0x26, 0x80, 0x41, 0xca, 0x3f, 0x68, 0x0f, ++ 0x32, 0x1d, 0x0a, 0x8e, 0x79, 0xd8, 0xa4, 0x1b, ++ 0x29, 0x1c, 0x90, 0x8e, 0xc5, 0xe3, 0xb4, 0x91, ++ 0x37, 0x9a, 0x97, 0x86, 0x99, 0xd5, 0x09, 0xc5, ++ 0xbb, 0xa3, 0x3f, 0x21, 0x29, 0x82, 0x14, 0x5c, ++ 0xab, 0x25, 0xfb, 0xf2, 0x4f, 0x58, 0x26, 0xd4, ++ 0x83, 0xaa, 0x66, 0x89, 0x67, 0x7e, 0xc0, 0x49, ++ 0xe1, 0x11, 0x10, 0x7f, 0x7a, 0xda, 0x29, 0x04, ++ 0xff, 0xf0, 0xcb, 0x09, 0x7c, 0x9d, 0xfa, 0x03, ++ 0x6f, 0x81, 0x09, 0x31, 0x60, 0xfb, 0x08, 0xfa, ++ 0x74, 0xd3, 0x64, 0x44, 0x7c, 0x55, 0x85, 0xec, ++ 0x9c, 0x6e, 0x25, 0xb7, 0x6c, 0xc5, 0x37, 0xb6, ++ 0x83, 0x87, 0x72, 0x95, 0x8b, 0x9d, 0xe1, 0x69, ++ 0x5c, 0x31, 0x95, 0x42, 0xa6, 0x2c, 0xd1, 0x36, ++ 0x47, 0x1f, 0xec, 0x54, 0xab, 0xa2, 0x1c, 0xd8, ++ 0x00, 0xcc, 0xbc, 0x0d, 0x65, 0xe2, 0x67, 0xbf, ++ 0xbc, 0xea, 0xee, 0x9e, 0xe4, 0x36, 0x95, 0xbe, ++ 0x73, 0xd9, 0xa6, 0xd9, 0x0f, 0xa0, 0xcc, 0x82, ++ 0x76, 0x26, 0xad, 0x5b, 0x58, 0x6c, 0x4e, 0xab, ++ 0x29, 0x64, 0xd3, 0xd9, 0xa9, 0x08, 0x8c, 0x1d, ++ 0xa1, 0x4f, 0x80, 0xd8, 0x3f, 0x94, 0xfb, 0xd3, ++ 0x7b, 0xfc, 0xd1, 0x2b, 0xc3, 0x21, 0xeb, 0xe5, ++ 0x1c, 0x84, 0x23, 0x7f, 0x4b, 0xfa, 0xdb, 0x34, ++ 0x18, 0xa2, 0xc2, 0xe5, 0x13, 0xfe, 0x6c, 0x49, ++ 0x81, 0xd2, 0x73, 0xe7, 0xe2, 0xd7, 0xe4, 0x4f, ++ 0x4b, 0x08, 0x6e, 0xb1, 0x12, 0x22, 0x10, 0x9d, ++ 0xac, 0x51, 0x1e, 0x17, 0xd9, 0x8a, 0x0b, 0x42, ++ 0x88, 0x16, 0x81, 0x37, 0x7c, 0x6a, 0xf7, 0xef, ++ 0x2d, 0xe3, 0xd9, 0xf8, 0x5f, 0xe0, 0x53, 0x27, ++ 0x74, 0xb9, 0xe2, 0xd6, 0x1c, 0x80, 0x2c, 0x52, ++ 0x65 ++}; ++static const u8 dec_assoc009[] __initconst = { ++ 0x5a, 0x27, 0xff, 0xeb, 0xdf, 0x84, 0xb2, 0x9e, ++ 0xef ++}; ++static const u8 dec_nonce009[] __initconst = { ++ 0xef, 0x2d, 0x63, 0xee, 0x6b, 0x80, 0x8b, 0x78 ++}; ++static const u8 dec_key009[] __initconst = { ++ 0xea, 0xbc, 0x56, 0x99, 0xe3, 0x50, 0xff, 0xc5, ++ 0xcc, 0x1a, 0xd7, 0xc1, 0x57, 0x72, 0xea, 0x86, ++ 0x5b, 0x89, 0x88, 0x61, 0x3d, 0x2f, 0x9b, 0xb2, ++ 0xe7, 0x9c, 0xec, 0x74, 0x6e, 0x3e, 0xf4, 0x3b ++}; ++ ++static const u8 dec_input010[] __initconst = { ++ 0xe5, 0x26, 0xa4, 0x3d, 0xbd, 0x33, 0xd0, 0x4b, ++ 0x6f, 0x05, 0xa7, 0x6e, 0x12, 0x7a, 0xd2, 0x74, ++ 0xa6, 0xdd, 0xbd, 0x95, 0xeb, 0xf9, 0xa4, 0xf1, ++ 0x59, 0x93, 0x91, 0x70, 0xd9, 0xfe, 0x9a, 0xcd, ++ 0x53, 0x1f, 0x3a, 0xab, 0xa6, 0x7c, 0x9f, 0xa6, ++ 0x9e, 0xbd, 0x99, 0xd9, 0xb5, 0x97, 0x44, 0xd5, ++ 0x14, 0x48, 0x4d, 0x9d, 0xc0, 0xd0, 0x05, 0x96, ++ 0xeb, 0x4c, 0x78, 0x55, 0x09, 0x08, 0x01, 0x02, ++ 0x30, 0x90, 0x7b, 0x96, 0x7a, 0x7b, 0x5f, 0x30, ++ 0x41, 0x24, 0xce, 0x68, 0x61, 0x49, 0x86, 0x57, ++ 0x82, 0xdd, 0x53, 0x1c, 0x51, 0x28, 0x2b, 0x53, ++ 0x6e, 0x2d, 0xc2, 0x20, 0x4c, 0xdd, 0x8f, 0x65, ++ 0x10, 0x20, 0x50, 0xdd, 0x9d, 0x50, 0xe5, 0x71, ++ 0x40, 0x53, 0x69, 0xfc, 0x77, 0x48, 0x11, 0xb9, ++ 0xde, 0xa4, 0x8d, 0x58, 0xe4, 0xa6, 0x1a, 0x18, ++ 0x47, 0x81, 0x7e, 0xfc, 0xdd, 0xf6, 0xef, 0xce, ++ 0x2f, 0x43, 0x68, 0xd6, 0x06, 0xe2, 0x74, 0x6a, ++ 0xad, 0x90, 0xf5, 0x37, 0xf3, 0x3d, 0x82, 0x69, ++ 0x40, 0xe9, 0x6b, 0xa7, 0x3d, 0xa8, 0x1e, 0xd2, ++ 0x02, 0x7c, 0xb7, 0x9b, 0xe4, 0xda, 0x8f, 0x95, ++ 0x06, 0xc5, 0xdf, 0x73, 0xa3, 0x20, 0x9a, 0x49, ++ 0xde, 0x9c, 0xbc, 0xee, 0x14, 0x3f, 0x81, 0x5e, ++ 0xf8, 0x3b, 0x59, 0x3c, 0xe1, 0x68, 0x12, 0x5a, ++ 0x3a, 0x76, 0x3a, 0x3f, 0xf7, 0x87, 0x33, 0x0a, ++ 0x01, 0xb8, 0xd4, 0xed, 0xb6, 0xbe, 0x94, 0x5e, ++ 0x70, 0x40, 0x56, 0x67, 0x1f, 0x50, 0x44, 0x19, ++ 0xce, 0x82, 0x70, 0x10, 0x87, 0x13, 0x20, 0x0b, ++ 0x4c, 0x5a, 0xb6, 0xf6, 0xa7, 0xae, 0x81, 0x75, ++ 0x01, 0x81, 0xe6, 0x4b, 0x57, 0x7c, 0xdd, 0x6d, ++ 0xf8, 0x1c, 0x29, 0x32, 0xf7, 0xda, 0x3c, 0x2d, ++ 0xf8, 0x9b, 0x25, 0x6e, 0x00, 0xb4, 0xf7, 0x2f, ++ 0xf7, 0x04, 0xf7, 0xa1, 0x56, 0xac, 0x4f, 0x1a, ++ 0x64, 0xb8, 0x47, 0x55, 0x18, 0x7b, 0x07, 0x4d, ++ 0xbd, 0x47, 0x24, 0x80, 0x5d, 0xa2, 0x70, 0xc5, ++ 0xdd, 0x8e, 0x82, 0xd4, 0xeb, 0xec, 0xb2, 0x0c, ++ 0x39, 0xd2, 0x97, 0xc1, 0xcb, 0xeb, 0xf4, 0x77, ++ 0x59, 0xb4, 0x87, 0xef, 0xcb, 0x43, 0x2d, 0x46, ++ 0x54, 0xd1, 0xa7, 0xd7, 0x15, 0x99, 0x0a, 0x43, ++ 0xa1, 0xe0, 0x99, 0x33, 0x71, 0xc1, 0xed, 0xfe, ++ 0x72, 0x46, 0x33, 0x8e, 0x91, 0x08, 0x9f, 0xc8, ++ 0x2e, 0xca, 0xfa, 0xdc, 0x59, 0xd5, 0xc3, 0x76, ++ 0x84, 0x9f, 0xa3, 0x37, 0x68, 0xc3, 0xf0, 0x47, ++ 0x2c, 0x68, 0xdb, 0x5e, 0xc3, 0x49, 0x4c, 0xe8, ++ 0x92, 0x85, 0xe2, 0x23, 0xd3, 0x3f, 0xad, 0x32, ++ 0xe5, 0x2b, 0x82, 0xd7, 0x8f, 0x99, 0x0a, 0x59, ++ 0x5c, 0x45, 0xd9, 0xb4, 0x51, 0x52, 0xc2, 0xae, ++ 0xbf, 0x80, 0xcf, 0xc9, 0xc9, 0x51, 0x24, 0x2a, ++ 0x3b, 0x3a, 0x4d, 0xae, 0xeb, 0xbd, 0x22, 0xc3, ++ 0x0e, 0x0f, 0x59, 0x25, 0x92, 0x17, 0xe9, 0x74, ++ 0xc7, 0x8b, 0x70, 0x70, 0x36, 0x55, 0x95, 0x75, ++ 0x4b, 0xad, 0x61, 0x2b, 0x09, 0xbc, 0x82, 0xf2, ++ 0x6e, 0x94, 0x43, 0xae, 0xc3, 0xd5, 0xcd, 0x8e, ++ 0xfe, 0x5b, 0x9a, 0x88, 0x43, 0x01, 0x75, 0xb2, ++ 0x23, 0x09, 0xf7, 0x89, 0x83, 0xe7, 0xfa, 0xf9, ++ 0xb4, 0x9b, 0xf8, 0xef, 0xbd, 0x1c, 0x92, 0xc1, ++ 0xda, 0x7e, 0xfe, 0x05, 0xba, 0x5a, 0xcd, 0x07, ++ 0x6a, 0x78, 0x9e, 0x5d, 0xfb, 0x11, 0x2f, 0x79, ++ 0x38, 0xb6, 0xc2, 0x5b, 0x6b, 0x51, 0xb4, 0x71, ++ 0xdd, 0xf7, 0x2a, 0xe4, 0xf4, 0x72, 0x76, 0xad, ++ 0xc2, 0xdd, 0x64, 0x5d, 0x79, 0xb6, 0xf5, 0x7a, ++ 0x77, 0x20, 0x05, 0x3d, 0x30, 0x06, 0xd4, 0x4c, ++ 0x0a, 0x2c, 0x98, 0x5a, 0xb9, 0xd4, 0x98, 0xa9, ++ 0x3f, 0xc6, 0x12, 0xea, 0x3b, 0x4b, 0xc5, 0x79, ++ 0x64, 0x63, 0x6b, 0x09, 0x54, 0x3b, 0x14, 0x27, ++ 0xba, 0x99, 0x80, 0xc8, 0x72, 0xa8, 0x12, 0x90, ++ 0x29, 0xba, 0x40, 0x54, 0x97, 0x2b, 0x7b, 0xfe, ++ 0xeb, 0xcd, 0x01, 0x05, 0x44, 0x72, 0xdb, 0x99, ++ 0xe4, 0x61, 0xc9, 0x69, 0xd6, 0xb9, 0x28, 0xd1, ++ 0x05, 0x3e, 0xf9, 0x0b, 0x49, 0x0a, 0x49, 0xe9, ++ 0x8d, 0x0e, 0xa7, 0x4a, 0x0f, 0xaf, 0x32, 0xd0, ++ 0xe0, 0xb2, 0x3a, 0x55, 0x58, 0xfe, 0x5c, 0x28, ++ 0x70, 0x51, 0x23, 0xb0, 0x7b, 0x6a, 0x5f, 0x1e, ++ 0xb8, 0x17, 0xd7, 0x94, 0x15, 0x8f, 0xee, 0x20, ++ 0xc7, 0x42, 0x25, 0x3e, 0x9a, 0x14, 0xd7, 0x60, ++ 0x72, 0x39, 0x47, 0x48, 0xa9, 0xfe, 0xdd, 0x47, ++ 0x0a, 0xb1, 0xe6, 0x60, 0x28, 0x8c, 0x11, 0x68, ++ 0xe1, 0xff, 0xd7, 0xce, 0xc8, 0xbe, 0xb3, 0xfe, ++ 0x27, 0x30, 0x09, 0x70, 0xd7, 0xfa, 0x02, 0x33, ++ 0x3a, 0x61, 0x2e, 0xc7, 0xff, 0xa4, 0x2a, 0xa8, ++ 0x6e, 0xb4, 0x79, 0x35, 0x6d, 0x4c, 0x1e, 0x38, ++ 0xf8, 0xee, 0xd4, 0x84, 0x4e, 0x6e, 0x28, 0xa7, ++ 0xce, 0xc8, 0xc1, 0xcf, 0x80, 0x05, 0xf3, 0x04, ++ 0xef, 0xc8, 0x18, 0x28, 0x2e, 0x8d, 0x5e, 0x0c, ++ 0xdf, 0xb8, 0x5f, 0x96, 0xe8, 0xc6, 0x9c, 0x2f, ++ 0xe5, 0xa6, 0x44, 0xd7, 0xe7, 0x99, 0x44, 0x0c, ++ 0xec, 0xd7, 0x05, 0x60, 0x97, 0xbb, 0x74, 0x77, ++ 0x58, 0xd5, 0xbb, 0x48, 0xde, 0x5a, 0xb2, 0x54, ++ 0x7f, 0x0e, 0x46, 0x70, 0x6a, 0x6f, 0x78, 0xa5, ++ 0x08, 0x89, 0x05, 0x4e, 0x7e, 0xa0, 0x69, 0xb4, ++ 0x40, 0x60, 0x55, 0x77, 0x75, 0x9b, 0x19, 0xf2, ++ 0xd5, 0x13, 0x80, 0x77, 0xf9, 0x4b, 0x3f, 0x1e, ++ 0xee, 0xe6, 0x76, 0x84, 0x7b, 0x8c, 0xe5, 0x27, ++ 0xa8, 0x0a, 0x91, 0x01, 0x68, 0x71, 0x8a, 0x3f, ++ 0x06, 0xab, 0xf6, 0xa9, 0xa5, 0xe6, 0x72, 0x92, ++ 0xe4, 0x67, 0xe2, 0xa2, 0x46, 0x35, 0x84, 0x55, ++ 0x7d, 0xca, 0xa8, 0x85, 0xd0, 0xf1, 0x3f, 0xbe, ++ 0xd7, 0x34, 0x64, 0xfc, 0xae, 0xe3, 0xe4, 0x04, ++ 0x9f, 0x66, 0x02, 0xb9, 0x88, 0x10, 0xd9, 0xc4, ++ 0x4c, 0x31, 0x43, 0x7a, 0x93, 0xe2, 0x9b, 0x56, ++ 0x43, 0x84, 0xdc, 0xdc, 0xde, 0x1d, 0xa4, 0x02, ++ 0x0e, 0xc2, 0xef, 0xc3, 0xf8, 0x78, 0xd1, 0xb2, ++ 0x6b, 0x63, 0x18, 0xc9, 0xa9, 0xe5, 0x72, 0xd8, ++ 0xf3, 0xb9, 0xd1, 0x8a, 0xc7, 0x1a, 0x02, 0x27, ++ 0x20, 0x77, 0x10, 0xe5, 0xc8, 0xd4, 0x4a, 0x47, ++ 0xe5, 0xdf, 0x5f, 0x01, 0xaa, 0xb0, 0xd4, 0x10, ++ 0xbb, 0x69, 0xe3, 0x36, 0xc8, 0xe1, 0x3d, 0x43, ++ 0xfb, 0x86, 0xcd, 0xcc, 0xbf, 0xf4, 0x88, 0xe0, ++ 0x20, 0xca, 0xb7, 0x1b, 0xf1, 0x2f, 0x5c, 0xee, ++ 0xd4, 0xd3, 0xa3, 0xcc, 0xa4, 0x1e, 0x1c, 0x47, ++ 0xfb, 0xbf, 0xfc, 0xa2, 0x41, 0x55, 0x9d, 0xf6, ++ 0x5a, 0x5e, 0x65, 0x32, 0x34, 0x7b, 0x52, 0x8d, ++ 0xd5, 0xd0, 0x20, 0x60, 0x03, 0xab, 0x3f, 0x8c, ++ 0xd4, 0x21, 0xea, 0x2a, 0xd9, 0xc4, 0xd0, 0xd3, ++ 0x65, 0xd8, 0x7a, 0x13, 0x28, 0x62, 0x32, 0x4b, ++ 0x2c, 0x87, 0x93, 0xa8, 0xb4, 0x52, 0x45, 0x09, ++ 0x44, 0xec, 0xec, 0xc3, 0x17, 0xdb, 0x9a, 0x4d, ++ 0x5c, 0xa9, 0x11, 0xd4, 0x7d, 0xaf, 0x9e, 0xf1, ++ 0x2d, 0xb2, 0x66, 0xc5, 0x1d, 0xed, 0xb7, 0xcd, ++ 0x0b, 0x25, 0x5e, 0x30, 0x47, 0x3f, 0x40, 0xf4, ++ 0xa1, 0xa0, 0x00, 0x94, 0x10, 0xc5, 0x6a, 0x63, ++ 0x1a, 0xd5, 0x88, 0x92, 0x8e, 0x82, 0x39, 0x87, ++ 0x3c, 0x78, 0x65, 0x58, 0x42, 0x75, 0x5b, 0xdd, ++ 0x77, 0x3e, 0x09, 0x4e, 0x76, 0x5b, 0xe6, 0x0e, ++ 0x4d, 0x38, 0xb2, 0xc0, 0xb8, 0x95, 0x01, 0x7a, ++ 0x10, 0xe0, 0xfb, 0x07, 0xf2, 0xab, 0x2d, 0x8c, ++ 0x32, 0xed, 0x2b, 0xc0, 0x46, 0xc2, 0xf5, 0x38, ++ 0x83, 0xf0, 0x17, 0xec, 0xc1, 0x20, 0x6a, 0x9a, ++ 0x0b, 0x00, 0xa0, 0x98, 0x22, 0x50, 0x23, 0xd5, ++ 0x80, 0x6b, 0xf6, 0x1f, 0xc3, 0xcc, 0x97, 0xc9, ++ 0x24, 0x9f, 0xf3, 0xaf, 0x43, 0x14, 0xd5, 0xa0 ++}; ++static const u8 dec_output010[] __initconst = { ++ 0x42, 0x93, 0xe4, 0xeb, 0x97, 0xb0, 0x57, 0xbf, ++ 0x1a, 0x8b, 0x1f, 0xe4, 0x5f, 0x36, 0x20, 0x3c, ++ 0xef, 0x0a, 0xa9, 0x48, 0x5f, 0x5f, 0x37, 0x22, ++ 0x3a, 0xde, 0xe3, 0xae, 0xbe, 0xad, 0x07, 0xcc, ++ 0xb1, 0xf6, 0xf5, 0xf9, 0x56, 0xdd, 0xe7, 0x16, ++ 0x1e, 0x7f, 0xdf, 0x7a, 0x9e, 0x75, 0xb7, 0xc7, ++ 0xbe, 0xbe, 0x8a, 0x36, 0x04, 0xc0, 0x10, 0xf4, ++ 0x95, 0x20, 0x03, 0xec, 0xdc, 0x05, 0xa1, 0x7d, ++ 0xc4, 0xa9, 0x2c, 0x82, 0xd0, 0xbc, 0x8b, 0xc5, ++ 0xc7, 0x45, 0x50, 0xf6, 0xa2, 0x1a, 0xb5, 0x46, ++ 0x3b, 0x73, 0x02, 0xa6, 0x83, 0x4b, 0x73, 0x82, ++ 0x58, 0x5e, 0x3b, 0x65, 0x2f, 0x0e, 0xfd, 0x2b, ++ 0x59, 0x16, 0xce, 0xa1, 0x60, 0x9c, 0xe8, 0x3a, ++ 0x99, 0xed, 0x8d, 0x5a, 0xcf, 0xf6, 0x83, 0xaf, ++ 0xba, 0xd7, 0x73, 0x73, 0x40, 0x97, 0x3d, 0xca, ++ 0xef, 0x07, 0x57, 0xe6, 0xd9, 0x70, 0x0e, 0x95, ++ 0xae, 0xa6, 0x8d, 0x04, 0xcc, 0xee, 0xf7, 0x09, ++ 0x31, 0x77, 0x12, 0xa3, 0x23, 0x97, 0x62, 0xb3, ++ 0x7b, 0x32, 0xfb, 0x80, 0x14, 0x48, 0x81, 0xc3, ++ 0xe5, 0xea, 0x91, 0x39, 0x52, 0x81, 0xa2, 0x4f, ++ 0xe4, 0xb3, 0x09, 0xff, 0xde, 0x5e, 0xe9, 0x58, ++ 0x84, 0x6e, 0xf9, 0x3d, 0xdf, 0x25, 0xea, 0xad, ++ 0xae, 0xe6, 0x9a, 0xd1, 0x89, 0x55, 0xd3, 0xde, ++ 0x6c, 0x52, 0xdb, 0x70, 0xfe, 0x37, 0xce, 0x44, ++ 0x0a, 0xa8, 0x25, 0x5f, 0x92, 0xc1, 0x33, 0x4a, ++ 0x4f, 0x9b, 0x62, 0x35, 0xff, 0xce, 0xc0, 0xa9, ++ 0x60, 0xce, 0x52, 0x00, 0x97, 0x51, 0x35, 0x26, ++ 0x2e, 0xb9, 0x36, 0xa9, 0x87, 0x6e, 0x1e, 0xcc, ++ 0x91, 0x78, 0x53, 0x98, 0x86, 0x5b, 0x9c, 0x74, ++ 0x7d, 0x88, 0x33, 0xe1, 0xdf, 0x37, 0x69, 0x2b, ++ 0xbb, 0xf1, 0x4d, 0xf4, 0xd1, 0xf1, 0x39, 0x93, ++ 0x17, 0x51, 0x19, 0xe3, 0x19, 0x1e, 0x76, 0x37, ++ 0x25, 0xfb, 0x09, 0x27, 0x6a, 0xab, 0x67, 0x6f, ++ 0x14, 0x12, 0x64, 0xe7, 0xc4, 0x07, 0xdf, 0x4d, ++ 0x17, 0xbb, 0x6d, 0xe0, 0xe9, 0xb9, 0xab, 0xca, ++ 0x10, 0x68, 0xaf, 0x7e, 0xb7, 0x33, 0x54, 0x73, ++ 0x07, 0x6e, 0xf7, 0x81, 0x97, 0x9c, 0x05, 0x6f, ++ 0x84, 0x5f, 0xd2, 0x42, 0xfb, 0x38, 0xcf, 0xd1, ++ 0x2f, 0x14, 0x30, 0x88, 0x98, 0x4d, 0x5a, 0xa9, ++ 0x76, 0xd5, 0x4f, 0x3e, 0x70, 0x6c, 0x85, 0x76, ++ 0xd7, 0x01, 0xa0, 0x1a, 0xc8, 0x4e, 0xaa, 0xac, ++ 0x78, 0xfe, 0x46, 0xde, 0x6a, 0x05, 0x46, 0xa7, ++ 0x43, 0x0c, 0xb9, 0xde, 0xb9, 0x68, 0xfb, 0xce, ++ 0x42, 0x99, 0x07, 0x4d, 0x0b, 0x3b, 0x5a, 0x30, ++ 0x35, 0xa8, 0xf9, 0x3a, 0x73, 0xef, 0x0f, 0xdb, ++ 0x1e, 0x16, 0x42, 0xc4, 0xba, 0xae, 0x58, 0xaa, ++ 0xf8, 0xe5, 0x75, 0x2f, 0x1b, 0x15, 0x5c, 0xfd, ++ 0x0a, 0x97, 0xd0, 0xe4, 0x37, 0x83, 0x61, 0x5f, ++ 0x43, 0xa6, 0xc7, 0x3f, 0x38, 0x59, 0xe6, 0xeb, ++ 0xa3, 0x90, 0xc3, 0xaa, 0xaa, 0x5a, 0xd3, 0x34, ++ 0xd4, 0x17, 0xc8, 0x65, 0x3e, 0x57, 0xbc, 0x5e, ++ 0xdd, 0x9e, 0xb7, 0xf0, 0x2e, 0x5b, 0xb2, 0x1f, ++ 0x8a, 0x08, 0x0d, 0x45, 0x91, 0x0b, 0x29, 0x53, ++ 0x4f, 0x4c, 0x5a, 0x73, 0x56, 0xfe, 0xaf, 0x41, ++ 0x01, 0x39, 0x0a, 0x24, 0x3c, 0x7e, 0xbe, 0x4e, ++ 0x53, 0xf3, 0xeb, 0x06, 0x66, 0x51, 0x28, 0x1d, ++ 0xbd, 0x41, 0x0a, 0x01, 0xab, 0x16, 0x47, 0x27, ++ 0x47, 0x47, 0xf7, 0xcb, 0x46, 0x0a, 0x70, 0x9e, ++ 0x01, 0x9c, 0x09, 0xe1, 0x2a, 0x00, 0x1a, 0xd8, ++ 0xd4, 0x79, 0x9d, 0x80, 0x15, 0x8e, 0x53, 0x2a, ++ 0x65, 0x83, 0x78, 0x3e, 0x03, 0x00, 0x07, 0x12, ++ 0x1f, 0x33, 0x3e, 0x7b, 0x13, 0x37, 0xf1, 0xc3, ++ 0xef, 0xb7, 0xc1, 0x20, 0x3c, 0x3e, 0x67, 0x66, ++ 0x5d, 0x88, 0xa7, 0x7d, 0x33, 0x50, 0x77, 0xb0, ++ 0x28, 0x8e, 0xe7, 0x2c, 0x2e, 0x7a, 0xf4, 0x3c, ++ 0x8d, 0x74, 0x83, 0xaf, 0x8e, 0x87, 0x0f, 0xe4, ++ 0x50, 0xff, 0x84, 0x5c, 0x47, 0x0c, 0x6a, 0x49, ++ 0xbf, 0x42, 0x86, 0x77, 0x15, 0x48, 0xa5, 0x90, ++ 0x5d, 0x93, 0xd6, 0x2a, 0x11, 0xd5, 0xd5, 0x11, ++ 0xaa, 0xce, 0xe7, 0x6f, 0xa5, 0xb0, 0x09, 0x2c, ++ 0x8d, 0xd3, 0x92, 0xf0, 0x5a, 0x2a, 0xda, 0x5b, ++ 0x1e, 0xd5, 0x9a, 0xc4, 0xc4, 0xf3, 0x49, 0x74, ++ 0x41, 0xca, 0xe8, 0xc1, 0xf8, 0x44, 0xd6, 0x3c, ++ 0xae, 0x6c, 0x1d, 0x9a, 0x30, 0x04, 0x4d, 0x27, ++ 0x0e, 0xb1, 0x5f, 0x59, 0xa2, 0x24, 0xe8, 0xe1, ++ 0x98, 0xc5, 0x6a, 0x4c, 0xfe, 0x41, 0xd2, 0x27, ++ 0x42, 0x52, 0xe1, 0xe9, 0x7d, 0x62, 0xe4, 0x88, ++ 0x0f, 0xad, 0xb2, 0x70, 0xcb, 0x9d, 0x4c, 0x27, ++ 0x2e, 0x76, 0x1e, 0x1a, 0x63, 0x65, 0xf5, 0x3b, ++ 0xf8, 0x57, 0x69, 0xeb, 0x5b, 0x38, 0x26, 0x39, ++ 0x33, 0x25, 0x45, 0x3e, 0x91, 0xb8, 0xd8, 0xc7, ++ 0xd5, 0x42, 0xc0, 0x22, 0x31, 0x74, 0xf4, 0xbc, ++ 0x0c, 0x23, 0xf1, 0xca, 0xc1, 0x8d, 0xd7, 0xbe, ++ 0xc9, 0x62, 0xe4, 0x08, 0x1a, 0xcf, 0x36, 0xd5, ++ 0xfe, 0x55, 0x21, 0x59, 0x91, 0x87, 0x87, 0xdf, ++ 0x06, 0xdb, 0xdf, 0x96, 0x45, 0x58, 0xda, 0x05, ++ 0xcd, 0x50, 0x4d, 0xd2, 0x7d, 0x05, 0x18, 0x73, ++ 0x6a, 0x8d, 0x11, 0x85, 0xa6, 0x88, 0xe8, 0xda, ++ 0xe6, 0x30, 0x33, 0xa4, 0x89, 0x31, 0x75, 0xbe, ++ 0x69, 0x43, 0x84, 0x43, 0x50, 0x87, 0xdd, 0x71, ++ 0x36, 0x83, 0xc3, 0x78, 0x74, 0x24, 0x0a, 0xed, ++ 0x7b, 0xdb, 0xa4, 0x24, 0x0b, 0xb9, 0x7e, 0x5d, ++ 0xff, 0xde, 0xb1, 0xef, 0x61, 0x5a, 0x45, 0x33, ++ 0xf6, 0x17, 0x07, 0x08, 0x98, 0x83, 0x92, 0x0f, ++ 0x23, 0x6d, 0xe6, 0xaa, 0x17, 0x54, 0xad, 0x6a, ++ 0xc8, 0xdb, 0x26, 0xbe, 0xb8, 0xb6, 0x08, 0xfa, ++ 0x68, 0xf1, 0xd7, 0x79, 0x6f, 0x18, 0xb4, 0x9e, ++ 0x2d, 0x3f, 0x1b, 0x64, 0xaf, 0x8d, 0x06, 0x0e, ++ 0x49, 0x28, 0xe0, 0x5d, 0x45, 0x68, 0x13, 0x87, ++ 0xfa, 0xde, 0x40, 0x7b, 0xd2, 0xc3, 0x94, 0xd5, ++ 0xe1, 0xd9, 0xc2, 0xaf, 0x55, 0x89, 0xeb, 0xb4, ++ 0x12, 0x59, 0xa8, 0xd4, 0xc5, 0x29, 0x66, 0x38, ++ 0xe6, 0xac, 0x22, 0x22, 0xd9, 0x64, 0x9b, 0x34, ++ 0x0a, 0x32, 0x9f, 0xc2, 0xbf, 0x17, 0x6c, 0x3f, ++ 0x71, 0x7a, 0x38, 0x6b, 0x98, 0xfb, 0x49, 0x36, ++ 0x89, 0xc9, 0xe2, 0xd6, 0xc7, 0x5d, 0xd0, 0x69, ++ 0x5f, 0x23, 0x35, 0xc9, 0x30, 0xe2, 0xfd, 0x44, ++ 0x58, 0x39, 0xd7, 0x97, 0xfb, 0x5c, 0x00, 0xd5, ++ 0x4f, 0x7a, 0x1a, 0x95, 0x8b, 0x62, 0x4b, 0xce, ++ 0xe5, 0x91, 0x21, 0x7b, 0x30, 0x00, 0xd6, 0xdd, ++ 0x6d, 0x02, 0x86, 0x49, 0x0f, 0x3c, 0x1a, 0x27, ++ 0x3c, 0xd3, 0x0e, 0x71, 0xf2, 0xff, 0xf5, 0x2f, ++ 0x87, 0xac, 0x67, 0x59, 0x81, 0xa3, 0xf7, 0xf8, ++ 0xd6, 0x11, 0x0c, 0x84, 0xa9, 0x03, 0xee, 0x2a, ++ 0xc4, 0xf3, 0x22, 0xab, 0x7c, 0xe2, 0x25, 0xf5, ++ 0x67, 0xa3, 0xe4, 0x11, 0xe0, 0x59, 0xb3, 0xca, ++ 0x87, 0xa0, 0xae, 0xc9, 0xa6, 0x62, 0x1b, 0x6e, ++ 0x4d, 0x02, 0x6b, 0x07, 0x9d, 0xfd, 0xd0, 0x92, ++ 0x06, 0xe1, 0xb2, 0x9a, 0x4a, 0x1f, 0x1f, 0x13, ++ 0x49, 0x99, 0x97, 0x08, 0xde, 0x7f, 0x98, 0xaf, ++ 0x51, 0x98, 0xee, 0x2c, 0xcb, 0xf0, 0x0b, 0xc6, ++ 0xb6, 0xb7, 0x2d, 0x9a, 0xb1, 0xac, 0xa6, 0xe3, ++ 0x15, 0x77, 0x9d, 0x6b, 0x1a, 0xe4, 0xfc, 0x8b, ++ 0xf2, 0x17, 0x59, 0x08, 0x04, 0x58, 0x81, 0x9d, ++ 0x1b, 0x1b, 0x69, 0x55, 0xc2, 0xb4, 0x3c, 0x1f, ++ 0x50, 0xf1, 0x7f, 0x77, 0x90, 0x4c, 0x66, 0x40, ++ 0x5a, 0xc0, 0x33, 0x1f, 0xcb, 0x05, 0x6d, 0x5c, ++ 0x06, 0x87, 0x52, 0xa2, 0x8f, 0x26, 0xd5, 0x4f ++}; ++static const u8 dec_assoc010[] __initconst = { ++ 0xd2, 0xa1, 0x70, 0xdb, 0x7a, 0xf8, 0xfa, 0x27, ++ 0xba, 0x73, 0x0f, 0xbf, 0x3d, 0x1e, 0x82, 0xb2 ++}; ++static const u8 dec_nonce010[] __initconst = { ++ 0xdb, 0x92, 0x0f, 0x7f, 0x17, 0x54, 0x0c, 0x30 ++}; ++static const u8 dec_key010[] __initconst = { ++ 0x47, 0x11, 0xeb, 0x86, 0x2b, 0x2c, 0xab, 0x44, ++ 0x34, 0xda, 0x7f, 0x57, 0x03, 0x39, 0x0c, 0xaf, ++ 0x2c, 0x14, 0xfd, 0x65, 0x23, 0xe9, 0x8e, 0x74, ++ 0xd5, 0x08, 0x68, 0x08, 0xe7, 0xb4, 0x72, 0xd7 ++}; ++ ++static const u8 dec_input011[] __initconst = { ++ 0x6a, 0xfc, 0x4b, 0x25, 0xdf, 0xc0, 0xe4, 0xe8, ++ 0x17, 0x4d, 0x4c, 0xc9, 0x7e, 0xde, 0x3a, 0xcc, ++ 0x3c, 0xba, 0x6a, 0x77, 0x47, 0xdb, 0xe3, 0x74, ++ 0x7a, 0x4d, 0x5f, 0x8d, 0x37, 0x55, 0x80, 0x73, ++ 0x90, 0x66, 0x5d, 0x3a, 0x7d, 0x5d, 0x86, 0x5e, ++ 0x8d, 0xfd, 0x83, 0xff, 0x4e, 0x74, 0x6f, 0xf9, ++ 0xe6, 0x70, 0x17, 0x70, 0x3e, 0x96, 0xa7, 0x7e, ++ 0xcb, 0xab, 0x8f, 0x58, 0x24, 0x9b, 0x01, 0xfd, ++ 0xcb, 0xe6, 0x4d, 0x9b, 0xf0, 0x88, 0x94, 0x57, ++ 0x66, 0xef, 0x72, 0x4c, 0x42, 0x6e, 0x16, 0x19, ++ 0x15, 0xea, 0x70, 0x5b, 0xac, 0x13, 0xdb, 0x9f, ++ 0x18, 0xe2, 0x3c, 0x26, 0x97, 0xbc, 0xdc, 0x45, ++ 0x8c, 0x6c, 0x24, 0x69, 0x9c, 0xf7, 0x65, 0x1e, ++ 0x18, 0x59, 0x31, 0x7c, 0xe4, 0x73, 0xbc, 0x39, ++ 0x62, 0xc6, 0x5c, 0x9f, 0xbf, 0xfa, 0x90, 0x03, ++ 0xc9, 0x72, 0x26, 0xb6, 0x1b, 0xc2, 0xb7, 0x3f, ++ 0xf2, 0x13, 0x77, 0xf2, 0x8d, 0xb9, 0x47, 0xd0, ++ 0x53, 0xdd, 0xc8, 0x91, 0x83, 0x8b, 0xb1, 0xce, ++ 0xa3, 0xfe, 0xcd, 0xd9, 0xdd, 0x92, 0x7b, 0xdb, ++ 0xb8, 0xfb, 0xc9, 0x2d, 0x01, 0x59, 0x39, 0x52, ++ 0xad, 0x1b, 0xec, 0xcf, 0xd7, 0x70, 0x13, 0x21, ++ 0xf5, 0x47, 0xaa, 0x18, 0x21, 0x5c, 0xc9, 0x9a, ++ 0xd2, 0x6b, 0x05, 0x9c, 0x01, 0xa1, 0xda, 0x35, ++ 0x5d, 0xb3, 0x70, 0xe6, 0xa9, 0x80, 0x8b, 0x91, ++ 0xb7, 0xb3, 0x5f, 0x24, 0x9a, 0xb7, 0xd1, 0x6b, ++ 0xa1, 0x1c, 0x50, 0xba, 0x49, 0xe0, 0xee, 0x2e, ++ 0x75, 0xac, 0x69, 0xc0, 0xeb, 0x03, 0xdd, 0x19, ++ 0xe5, 0xf6, 0x06, 0xdd, 0xc3, 0xd7, 0x2b, 0x07, ++ 0x07, 0x30, 0xa7, 0x19, 0x0c, 0xbf, 0xe6, 0x18, ++ 0xcc, 0xb1, 0x01, 0x11, 0x85, 0x77, 0x1d, 0x96, ++ 0xa7, 0xa3, 0x00, 0x84, 0x02, 0xa2, 0x83, 0x68, ++ 0xda, 0x17, 0x27, 0xc8, 0x7f, 0x23, 0xb7, 0xf4, ++ 0x13, 0x85, 0xcf, 0xdd, 0x7a, 0x7d, 0x24, 0x57, ++ 0xfe, 0x05, 0x93, 0xf5, 0x74, 0xce, 0xed, 0x0c, ++ 0x20, 0x98, 0x8d, 0x92, 0x30, 0xa1, 0x29, 0x23, ++ 0x1a, 0xa0, 0x4f, 0x69, 0x56, 0x4c, 0xe1, 0xc8, ++ 0xce, 0xf6, 0x9a, 0x0c, 0xa4, 0xfa, 0x04, 0xf6, ++ 0x62, 0x95, 0xf2, 0xfa, 0xc7, 0x40, 0x68, 0x40, ++ 0x8f, 0x41, 0xda, 0xb4, 0x26, 0x6f, 0x70, 0xab, ++ 0x40, 0x61, 0xa4, 0x0e, 0x75, 0xfb, 0x86, 0xeb, ++ 0x9d, 0x9a, 0x1f, 0xec, 0x76, 0x99, 0xe7, 0xea, ++ 0xaa, 0x1e, 0x2d, 0xb5, 0xd4, 0xa6, 0x1a, 0xb8, ++ 0x61, 0x0a, 0x1d, 0x16, 0x5b, 0x98, 0xc2, 0x31, ++ 0x40, 0xe7, 0x23, 0x1d, 0x66, 0x99, 0xc8, 0xc0, ++ 0xd7, 0xce, 0xf3, 0x57, 0x40, 0x04, 0x3f, 0xfc, ++ 0xea, 0xb3, 0xfc, 0xd2, 0xd3, 0x99, 0xa4, 0x94, ++ 0x69, 0xa0, 0xef, 0xd1, 0x85, 0xb3, 0xa6, 0xb1, ++ 0x28, 0xbf, 0x94, 0x67, 0x22, 0xc3, 0x36, 0x46, ++ 0xf8, 0xd2, 0x0f, 0x5f, 0xf4, 0x59, 0x80, 0xe6, ++ 0x2d, 0x43, 0x08, 0x7d, 0x19, 0x09, 0x97, 0xa7, ++ 0x4c, 0x3d, 0x8d, 0xba, 0x65, 0x62, 0xa3, 0x71, ++ 0x33, 0x29, 0x62, 0xdb, 0xc1, 0x33, 0x34, 0x1a, ++ 0x63, 0x33, 0x16, 0xb6, 0x64, 0x7e, 0xab, 0x33, ++ 0xf0, 0xe6, 0x26, 0x68, 0xba, 0x1d, 0x2e, 0x38, ++ 0x08, 0xe6, 0x02, 0xd3, 0x25, 0x2c, 0x47, 0x23, ++ 0x58, 0x34, 0x0f, 0x9d, 0x63, 0x4f, 0x63, 0xbb, ++ 0x7f, 0x3b, 0x34, 0x38, 0xa7, 0xb5, 0x8d, 0x65, ++ 0xd9, 0x9f, 0x79, 0x55, 0x3e, 0x4d, 0xe7, 0x73, ++ 0xd8, 0xf6, 0x98, 0x97, 0x84, 0x60, 0x9c, 0xc8, ++ 0xa9, 0x3c, 0xf6, 0xdc, 0x12, 0x5c, 0xe1, 0xbb, ++ 0x0b, 0x8b, 0x98, 0x9c, 0x9d, 0x26, 0x7c, 0x4a, ++ 0xe6, 0x46, 0x36, 0x58, 0x21, 0x4a, 0xee, 0xca, ++ 0xd7, 0x3b, 0xc2, 0x6c, 0x49, 0x2f, 0xe5, 0xd5, ++ 0x03, 0x59, 0x84, 0x53, 0xcb, 0xfe, 0x92, 0x71, ++ 0x2e, 0x7c, 0x21, 0xcc, 0x99, 0x85, 0x7f, 0xb8, ++ 0x74, 0x90, 0x13, 0x42, 0x3f, 0xe0, 0x6b, 0x1d, ++ 0xf2, 0x4d, 0x54, 0xd4, 0xfc, 0x3a, 0x05, 0xe6, ++ 0x74, 0xaf, 0xa6, 0xa0, 0x2a, 0x20, 0x23, 0x5d, ++ 0x34, 0x5c, 0xd9, 0x3e, 0x4e, 0xfa, 0x93, 0xe7, ++ 0xaa, 0xe9, 0x6f, 0x08, 0x43, 0x67, 0x41, 0xc5, ++ 0xad, 0xfb, 0x31, 0x95, 0x82, 0x73, 0x32, 0xd8, ++ 0xa6, 0xa3, 0xed, 0x0e, 0x2d, 0xf6, 0x5f, 0xfd, ++ 0x80, 0xa6, 0x7a, 0xe0, 0xdf, 0x78, 0x15, 0x29, ++ 0x74, 0x33, 0xd0, 0x9e, 0x83, 0x86, 0x72, 0x22, ++ 0x57, 0x29, 0xb9, 0x9e, 0x5d, 0xd3, 0x1a, 0xb5, ++ 0x96, 0x72, 0x41, 0x3d, 0xf1, 0x64, 0x43, 0x67, ++ 0xee, 0xaa, 0x5c, 0xd3, 0x9a, 0x96, 0x13, 0x11, ++ 0x5d, 0xf3, 0x0c, 0x87, 0x82, 0x1e, 0x41, 0x9e, ++ 0xd0, 0x27, 0xd7, 0x54, 0x3b, 0x67, 0x73, 0x09, ++ 0x91, 0xe9, 0xd5, 0x36, 0xa7, 0xb5, 0x55, 0xe4, ++ 0xf3, 0x21, 0x51, 0x49, 0x22, 0x07, 0x55, 0x4f, ++ 0x44, 0x4b, 0xd2, 0x15, 0x93, 0x17, 0x2a, 0xfa, ++ 0x4d, 0x4a, 0x57, 0xdb, 0x4c, 0xa6, 0xeb, 0xec, ++ 0x53, 0x25, 0x6c, 0x21, 0xed, 0x00, 0x4c, 0x3b, ++ 0xca, 0x14, 0x57, 0xa9, 0xd6, 0x6a, 0xcd, 0x8d, ++ 0x5e, 0x74, 0xac, 0x72, 0xc1, 0x97, 0xe5, 0x1b, ++ 0x45, 0x4e, 0xda, 0xfc, 0xcc, 0x40, 0xe8, 0x48, ++ 0x88, 0x0b, 0xa3, 0xe3, 0x8d, 0x83, 0x42, 0xc3, ++ 0x23, 0xfd, 0x68, 0xb5, 0x8e, 0xf1, 0x9d, 0x63, ++ 0x77, 0xe9, 0xa3, 0x8e, 0x8c, 0x26, 0x6b, 0xbd, ++ 0x72, 0x73, 0x35, 0x0c, 0x03, 0xf8, 0x43, 0x78, ++ 0x52, 0x71, 0x15, 0x1f, 0x71, 0x5d, 0x6e, 0xed, ++ 0xb9, 0xcc, 0x86, 0x30, 0xdb, 0x2b, 0xd3, 0x82, ++ 0x88, 0x23, 0x71, 0x90, 0x53, 0x5c, 0xa9, 0x2f, ++ 0x76, 0x01, 0xb7, 0x9a, 0xfe, 0x43, 0x55, 0xa3, ++ 0x04, 0x9b, 0x0e, 0xe4, 0x59, 0xdf, 0xc9, 0xe9, ++ 0xb1, 0xea, 0x29, 0x28, 0x3c, 0x5c, 0xae, 0x72, ++ 0x84, 0xb6, 0xc6, 0xeb, 0x0c, 0x27, 0x07, 0x74, ++ 0x90, 0x0d, 0x31, 0xb0, 0x00, 0x77, 0xe9, 0x40, ++ 0x70, 0x6f, 0x68, 0xa7, 0xfd, 0x06, 0xec, 0x4b, ++ 0xc0, 0xb7, 0xac, 0xbc, 0x33, 0xb7, 0x6d, 0x0a, ++ 0xbd, 0x12, 0x1b, 0x59, 0xcb, 0xdd, 0x32, 0xf5, ++ 0x1d, 0x94, 0x57, 0x76, 0x9e, 0x0c, 0x18, 0x98, ++ 0x71, 0xd7, 0x2a, 0xdb, 0x0b, 0x7b, 0xa7, 0x71, ++ 0xb7, 0x67, 0x81, 0x23, 0x96, 0xae, 0xb9, 0x7e, ++ 0x32, 0x43, 0x92, 0x8a, 0x19, 0xa0, 0xc4, 0xd4, ++ 0x3b, 0x57, 0xf9, 0x4a, 0x2c, 0xfb, 0x51, 0x46, ++ 0xbb, 0xcb, 0x5d, 0xb3, 0xef, 0x13, 0x93, 0x6e, ++ 0x68, 0x42, 0x54, 0x57, 0xd3, 0x6a, 0x3a, 0x8f, ++ 0x9d, 0x66, 0xbf, 0xbd, 0x36, 0x23, 0xf5, 0x93, ++ 0x83, 0x7b, 0x9c, 0xc0, 0xdd, 0xc5, 0x49, 0xc0, ++ 0x64, 0xed, 0x07, 0x12, 0xb3, 0xe6, 0xe4, 0xe5, ++ 0x38, 0x95, 0x23, 0xb1, 0xa0, 0x3b, 0x1a, 0x61, ++ 0xda, 0x17, 0xac, 0xc3, 0x58, 0xdd, 0x74, 0x64, ++ 0x22, 0x11, 0xe8, 0x32, 0x1d, 0x16, 0x93, 0x85, ++ 0x99, 0xa5, 0x9c, 0x34, 0x55, 0xb1, 0xe9, 0x20, ++ 0x72, 0xc9, 0x28, 0x7b, 0x79, 0x00, 0xa1, 0xa6, ++ 0xa3, 0x27, 0x40, 0x18, 0x8a, 0x54, 0xe0, 0xcc, ++ 0xe8, 0x4e, 0x8e, 0x43, 0x96, 0xe7, 0x3f, 0xc8, ++ 0xe9, 0xb2, 0xf9, 0xc9, 0xda, 0x04, 0x71, 0x50, ++ 0x47, 0xe4, 0xaa, 0xce, 0xa2, 0x30, 0xc8, 0xe4, ++ 0xac, 0xc7, 0x0d, 0x06, 0x2e, 0xe6, 0xe8, 0x80, ++ 0x36, 0x29, 0x9e, 0x01, 0xb8, 0xc3, 0xf0, 0xa0, ++ 0x5d, 0x7a, 0xca, 0x4d, 0xa0, 0x57, 0xbd, 0x2a, ++ 0x45, 0xa7, 0x7f, 0x9c, 0x93, 0x07, 0x8f, 0x35, ++ 0x67, 0x92, 0xe3, 0xe9, 0x7f, 0xa8, 0x61, 0x43, ++ 0x9e, 0x25, 0x4f, 0x33, 0x76, 0x13, 0x6e, 0x12, ++ 0xb9, 0xdd, 0xa4, 0x7c, 0x08, 0x9f, 0x7c, 0xe7, ++ 0x0a, 0x8d, 0x84, 0x06, 0xa4, 0x33, 0x17, 0x34, ++ 0x5e, 0x10, 0x7c, 0xc0, 0xa8, 0x3d, 0x1f, 0x42, ++ 0x20, 0x51, 0x65, 0x5d, 0x09, 0xc3, 0xaa, 0xc0, ++ 0xc8, 0x0d, 0xf0, 0x79, 0xbc, 0x20, 0x1b, 0x95, ++ 0xe7, 0x06, 0x7d, 0x47, 0x20, 0x03, 0x1a, 0x74, ++ 0xdd, 0xe2, 0xd4, 0xae, 0x38, 0x71, 0x9b, 0xf5, ++ 0x80, 0xec, 0x08, 0x4e, 0x56, 0xba, 0x76, 0x12, ++ 0x1a, 0xdf, 0x48, 0xf3, 0xae, 0xb3, 0xe6, 0xe6, ++ 0xbe, 0xc0, 0x91, 0x2e, 0x01, 0xb3, 0x01, 0x86, ++ 0xa2, 0xb9, 0x52, 0xd1, 0x21, 0xae, 0xd4, 0x97, ++ 0x1d, 0xef, 0x41, 0x12, 0x95, 0x3d, 0x48, 0x45, ++ 0x1c, 0x56, 0x32, 0x8f, 0xb8, 0x43, 0xbb, 0x19, ++ 0xf3, 0xca, 0xe9, 0xeb, 0x6d, 0x84, 0xbe, 0x86, ++ 0x06, 0xe2, 0x36, 0xb2, 0x62, 0x9d, 0xd3, 0x4c, ++ 0x48, 0x18, 0x54, 0x13, 0x4e, 0xcf, 0xfd, 0xba, ++ 0x84, 0xb9, 0x30, 0x53, 0xcf, 0xfb, 0xb9, 0x29, ++ 0x8f, 0xdc, 0x9f, 0xef, 0x60, 0x0b, 0x64, 0xf6, ++ 0x8b, 0xee, 0xa6, 0x91, 0xc2, 0x41, 0x6c, 0xf6, ++ 0xfa, 0x79, 0x67, 0x4b, 0xc1, 0x3f, 0xaf, 0x09, ++ 0x81, 0xd4, 0x5d, 0xcb, 0x09, 0xdf, 0x36, 0x31, ++ 0xc0, 0x14, 0x3c, 0x7c, 0x0e, 0x65, 0x95, 0x99, ++ 0x6d, 0xa3, 0xf4, 0xd7, 0x38, 0xee, 0x1a, 0x2b, ++ 0x37, 0xe2, 0xa4, 0x3b, 0x4b, 0xd0, 0x65, 0xca, ++ 0xf8, 0xc3, 0xe8, 0x15, 0x20, 0xef, 0xf2, 0x00, ++ 0xfd, 0x01, 0x09, 0xc5, 0xc8, 0x17, 0x04, 0x93, ++ 0xd0, 0x93, 0x03, 0x55, 0xc5, 0xfe, 0x32, 0xa3, ++ 0x3e, 0x28, 0x2d, 0x3b, 0x93, 0x8a, 0xcc, 0x07, ++ 0x72, 0x80, 0x8b, 0x74, 0x16, 0x24, 0xbb, 0xda, ++ 0x94, 0x39, 0x30, 0x8f, 0xb1, 0xcd, 0x4a, 0x90, ++ 0x92, 0x7c, 0x14, 0x8f, 0x95, 0x4e, 0xac, 0x9b, ++ 0xd8, 0x8f, 0x1a, 0x87, 0xa4, 0x32, 0x27, 0x8a, ++ 0xba, 0xf7, 0x41, 0xcf, 0x84, 0x37, 0x19, 0xe6, ++ 0x06, 0xf5, 0x0e, 0xcf, 0x36, 0xf5, 0x9e, 0x6c, ++ 0xde, 0xbc, 0xff, 0x64, 0x7e, 0x4e, 0x59, 0x57, ++ 0x48, 0xfe, 0x14, 0xf7, 0x9c, 0x93, 0x5d, 0x15, ++ 0xad, 0xcc, 0x11, 0xb1, 0x17, 0x18, 0xb2, 0x7e, ++ 0xcc, 0xab, 0xe9, 0xce, 0x7d, 0x77, 0x5b, 0x51, ++ 0x1b, 0x1e, 0x20, 0xa8, 0x32, 0x06, 0x0e, 0x75, ++ 0x93, 0xac, 0xdb, 0x35, 0x37, 0x1f, 0xe9, 0x19, ++ 0x1d, 0xb4, 0x71, 0x97, 0xd6, 0x4e, 0x2c, 0x08, ++ 0xa5, 0x13, 0xf9, 0x0e, 0x7e, 0x78, 0x6e, 0x14, ++ 0xe0, 0xa9, 0xb9, 0x96, 0x4c, 0x80, 0x82, 0xba, ++ 0x17, 0xb3, 0x9d, 0x69, 0xb0, 0x84, 0x46, 0xff, ++ 0xf9, 0x52, 0x79, 0x94, 0x58, 0x3a, 0x62, 0x90, ++ 0x15, 0x35, 0x71, 0x10, 0x37, 0xed, 0xa1, 0x8e, ++ 0x53, 0x6e, 0xf4, 0x26, 0x57, 0x93, 0x15, 0x93, ++ 0xf6, 0x81, 0x2c, 0x5a, 0x10, 0xda, 0x92, 0xad, ++ 0x2f, 0xdb, 0x28, 0x31, 0x2d, 0x55, 0x04, 0xd2, ++ 0x06, 0x28, 0x8c, 0x1e, 0xdc, 0xea, 0x54, 0xac, ++ 0xff, 0xb7, 0x6c, 0x30, 0x15, 0xd4, 0xb4, 0x0d, ++ 0x00, 0x93, 0x57, 0xdd, 0xd2, 0x07, 0x07, 0x06, ++ 0xd9, 0x43, 0x9b, 0xcd, 0x3a, 0xf4, 0x7d, 0x4c, ++ 0x36, 0x5d, 0x23, 0xa2, 0xcc, 0x57, 0x40, 0x91, ++ 0xe9, 0x2c, 0x2f, 0x2c, 0xd5, 0x30, 0x9b, 0x17, ++ 0xb0, 0xc9, 0xf7, 0xa7, 0x2f, 0xd1, 0x93, 0x20, ++ 0x6b, 0xc6, 0xc1, 0xe4, 0x6f, 0xcb, 0xd1, 0xe7, ++ 0x09, 0x0f, 0x9e, 0xdc, 0xaa, 0x9f, 0x2f, 0xdf, ++ 0x56, 0x9f, 0xd4, 0x33, 0x04, 0xaf, 0xd3, 0x6c, ++ 0x58, 0x61, 0xf0, 0x30, 0xec, 0xf2, 0x7f, 0xf2, ++ 0x9c, 0xdf, 0x39, 0xbb, 0x6f, 0xa2, 0x8c, 0x7e, ++ 0xc4, 0x22, 0x51, 0x71, 0xc0, 0x4d, 0x14, 0x1a, ++ 0xc4, 0xcd, 0x04, 0xd9, 0x87, 0x08, 0x50, 0x05, ++ 0xcc, 0xaf, 0xf6, 0xf0, 0x8f, 0x92, 0x54, 0x58, ++ 0xc2, 0xc7, 0x09, 0x7a, 0x59, 0x02, 0x05, 0xe8, ++ 0xb0, 0x86, 0xd9, 0xbf, 0x7b, 0x35, 0x51, 0x4d, ++ 0xaf, 0x08, 0x97, 0x2c, 0x65, 0xda, 0x2a, 0x71, ++ 0x3a, 0xa8, 0x51, 0xcc, 0xf2, 0x73, 0x27, 0xc3, ++ 0xfd, 0x62, 0xcf, 0xe3, 0xb2, 0xca, 0xcb, 0xbe, ++ 0x1a, 0x0a, 0xa1, 0x34, 0x7b, 0x77, 0xc4, 0x62, ++ 0x68, 0x78, 0x5f, 0x94, 0x07, 0x04, 0x65, 0x16, ++ 0x4b, 0x61, 0xcb, 0xff, 0x75, 0x26, 0x50, 0x66, ++ 0x1f, 0x6e, 0x93, 0xf8, 0xc5, 0x51, 0xeb, 0xa4, ++ 0x4a, 0x48, 0x68, 0x6b, 0xe2, 0x5e, 0x44, 0xb2, ++ 0x50, 0x2c, 0x6c, 0xae, 0x79, 0x4e, 0x66, 0x35, ++ 0x81, 0x50, 0xac, 0xbc, 0x3f, 0xb1, 0x0c, 0xf3, ++ 0x05, 0x3c, 0x4a, 0xa3, 0x6c, 0x2a, 0x79, 0xb4, ++ 0xb7, 0xab, 0xca, 0xc7, 0x9b, 0x8e, 0xcd, 0x5f, ++ 0x11, 0x03, 0xcb, 0x30, 0xa3, 0xab, 0xda, 0xfe, ++ 0x64, 0xb9, 0xbb, 0xd8, 0x5e, 0x3a, 0x1a, 0x56, ++ 0xe5, 0x05, 0x48, 0x90, 0x1e, 0x61, 0x69, 0x1b, ++ 0x22, 0xe6, 0x1a, 0x3c, 0x75, 0xad, 0x1f, 0x37, ++ 0x28, 0xdc, 0xe4, 0x6d, 0xbd, 0x42, 0xdc, 0xd3, ++ 0xc8, 0xb6, 0x1c, 0x48, 0xfe, 0x94, 0x77, 0x7f, ++ 0xbd, 0x62, 0xac, 0xa3, 0x47, 0x27, 0xcf, 0x5f, ++ 0xd9, 0xdb, 0xaf, 0xec, 0xf7, 0x5e, 0xc1, 0xb0, ++ 0x9d, 0x01, 0x26, 0x99, 0x7e, 0x8f, 0x03, 0x70, ++ 0xb5, 0x42, 0xbe, 0x67, 0x28, 0x1b, 0x7c, 0xbd, ++ 0x61, 0x21, 0x97, 0xcc, 0x5c, 0xe1, 0x97, 0x8f, ++ 0x8d, 0xde, 0x2b, 0xaa, 0xa7, 0x71, 0x1d, 0x1e, ++ 0x02, 0x73, 0x70, 0x58, 0x32, 0x5b, 0x1d, 0x67, ++ 0x3d, 0xe0, 0x74, 0x4f, 0x03, 0xf2, 0x70, 0x51, ++ 0x79, 0xf1, 0x61, 0x70, 0x15, 0x74, 0x9d, 0x23, ++ 0x89, 0xde, 0xac, 0xfd, 0xde, 0xd0, 0x1f, 0xc3, ++ 0x87, 0x44, 0x35, 0x4b, 0xe5, 0xb0, 0x60, 0xc5, ++ 0x22, 0xe4, 0x9e, 0xca, 0xeb, 0xd5, 0x3a, 0x09, ++ 0x45, 0xa4, 0xdb, 0xfa, 0x3f, 0xeb, 0x1b, 0xc7, ++ 0xc8, 0x14, 0x99, 0x51, 0x92, 0x10, 0xed, 0xed, ++ 0x28, 0xe0, 0xa1, 0xf8, 0x26, 0xcf, 0xcd, 0xcb, ++ 0x63, 0xa1, 0x3b, 0xe3, 0xdf, 0x7e, 0xfe, 0xa6, ++ 0xf0, 0x81, 0x9a, 0xbf, 0x55, 0xde, 0x54, 0xd5, ++ 0x56, 0x60, 0x98, 0x10, 0x68, 0xf4, 0x38, 0x96, ++ 0x8e, 0x6f, 0x1d, 0x44, 0x7f, 0xd6, 0x2f, 0xfe, ++ 0x55, 0xfb, 0x0c, 0x7e, 0x67, 0xe2, 0x61, 0x44, ++ 0xed, 0xf2, 0x35, 0x30, 0x5d, 0xe9, 0xc7, 0xd6, ++ 0x6d, 0xe0, 0xa0, 0xed, 0xf3, 0xfc, 0xd8, 0x3e, ++ 0x0a, 0x7b, 0xcd, 0xaf, 0x65, 0x68, 0x18, 0xc0, ++ 0xec, 0x04, 0x1c, 0x74, 0x6d, 0xe2, 0x6e, 0x79, ++ 0xd4, 0x11, 0x2b, 0x62, 0xd5, 0x27, 0xad, 0x4f, ++ 0x01, 0x59, 0x73, 0xcc, 0x6a, 0x53, 0xfb, 0x2d, ++ 0xd5, 0x4e, 0x99, 0x21, 0x65, 0x4d, 0xf5, 0x82, ++ 0xf7, 0xd8, 0x42, 0xce, 0x6f, 0x3d, 0x36, 0x47, ++ 0xf1, 0x05, 0x16, 0xe8, 0x1b, 0x6a, 0x8f, 0x93, ++ 0xf2, 0x8f, 0x37, 0x40, 0x12, 0x28, 0xa3, 0xe6, ++ 0xb9, 0x17, 0x4a, 0x1f, 0xb1, 0xd1, 0x66, 0x69, ++ 0x86, 0xc4, 0xfc, 0x97, 0xae, 0x3f, 0x8f, 0x1e, ++ 0x2b, 0xdf, 0xcd, 0xf9, 0x3c ++}; ++static const u8 dec_output011[] __initconst = { ++ 0x7a, 0x57, 0xf2, 0xc7, 0x06, 0x3f, 0x50, 0x7b, ++ 0x36, 0x1a, 0x66, 0x5c, 0xb9, 0x0e, 0x5e, 0x3b, ++ 0x45, 0x60, 0xbe, 0x9a, 0x31, 0x9f, 0xff, 0x5d, ++ 0x66, 0x34, 0xb4, 0xdc, 0xfb, 0x9d, 0x8e, 0xee, ++ 0x6a, 0x33, 0xa4, 0x07, 0x3c, 0xf9, 0x4c, 0x30, ++ 0xa1, 0x24, 0x52, 0xf9, 0x50, 0x46, 0x88, 0x20, ++ 0x02, 0x32, 0x3a, 0x0e, 0x99, 0x63, 0xaf, 0x1f, ++ 0x15, 0x28, 0x2a, 0x05, 0xff, 0x57, 0x59, 0x5e, ++ 0x18, 0xa1, 0x1f, 0xd0, 0x92, 0x5c, 0x88, 0x66, ++ 0x1b, 0x00, 0x64, 0xa5, 0x93, 0x8d, 0x06, 0x46, ++ 0xb0, 0x64, 0x8b, 0x8b, 0xef, 0x99, 0x05, 0x35, ++ 0x85, 0xb3, 0xf3, 0x33, 0xbb, 0xec, 0x66, 0xb6, ++ 0x3d, 0x57, 0x42, 0xe3, 0xb4, 0xc6, 0xaa, 0xb0, ++ 0x41, 0x2a, 0xb9, 0x59, 0xa9, 0xf6, 0x3e, 0x15, ++ 0x26, 0x12, 0x03, 0x21, 0x4c, 0x74, 0x43, 0x13, ++ 0x2a, 0x03, 0x27, 0x09, 0xb4, 0xfb, 0xe7, 0xb7, ++ 0x40, 0xff, 0x5e, 0xce, 0x48, 0x9a, 0x60, 0xe3, ++ 0x8b, 0x80, 0x8c, 0x38, 0x2d, 0xcb, 0x93, 0x37, ++ 0x74, 0x05, 0x52, 0x6f, 0x73, 0x3e, 0xc3, 0xbc, ++ 0xca, 0x72, 0x0a, 0xeb, 0xf1, 0x3b, 0xa0, 0x95, ++ 0xdc, 0x8a, 0xc4, 0xa9, 0xdc, 0xca, 0x44, 0xd8, ++ 0x08, 0x63, 0x6a, 0x36, 0xd3, 0x3c, 0xb8, 0xac, ++ 0x46, 0x7d, 0xfd, 0xaa, 0xeb, 0x3e, 0x0f, 0x45, ++ 0x8f, 0x49, 0xda, 0x2b, 0xf2, 0x12, 0xbd, 0xaf, ++ 0x67, 0x8a, 0x63, 0x48, 0x4b, 0x55, 0x5f, 0x6d, ++ 0x8c, 0xb9, 0x76, 0x34, 0x84, 0xae, 0xc2, 0xfc, ++ 0x52, 0x64, 0x82, 0xf7, 0xb0, 0x06, 0xf0, 0x45, ++ 0x73, 0x12, 0x50, 0x30, 0x72, 0xea, 0x78, 0x9a, ++ 0xa8, 0xaf, 0xb5, 0xe3, 0xbb, 0x77, 0x52, 0xec, ++ 0x59, 0x84, 0xbf, 0x6b, 0x8f, 0xce, 0x86, 0x5e, ++ 0x1f, 0x23, 0xe9, 0xfb, 0x08, 0x86, 0xf7, 0x10, ++ 0xb9, 0xf2, 0x44, 0x96, 0x44, 0x63, 0xa9, 0xa8, ++ 0x78, 0x00, 0x23, 0xd6, 0xc7, 0xe7, 0x6e, 0x66, ++ 0x4f, 0xcc, 0xee, 0x15, 0xb3, 0xbd, 0x1d, 0xa0, ++ 0xe5, 0x9c, 0x1b, 0x24, 0x2c, 0x4d, 0x3c, 0x62, ++ 0x35, 0x9c, 0x88, 0x59, 0x09, 0xdd, 0x82, 0x1b, ++ 0xcf, 0x0a, 0x83, 0x6b, 0x3f, 0xae, 0x03, 0xc4, ++ 0xb4, 0xdd, 0x7e, 0x5b, 0x28, 0x76, 0x25, 0x96, ++ 0xd9, 0xc9, 0x9d, 0x5f, 0x86, 0xfa, 0xf6, 0xd7, ++ 0xd2, 0xe6, 0x76, 0x1d, 0x0f, 0xa1, 0xdc, 0x74, ++ 0x05, 0x1b, 0x1d, 0xe0, 0xcd, 0x16, 0xb0, 0xa8, ++ 0x8a, 0x34, 0x7b, 0x15, 0x11, 0x77, 0xe5, 0x7b, ++ 0x7e, 0x20, 0xf7, 0xda, 0x38, 0xda, 0xce, 0x70, ++ 0xe9, 0xf5, 0x6c, 0xd9, 0xbe, 0x0c, 0x4c, 0x95, ++ 0x4c, 0xc2, 0x9b, 0x34, 0x55, 0x55, 0xe1, 0xf3, ++ 0x46, 0x8e, 0x48, 0x74, 0x14, 0x4f, 0x9d, 0xc9, ++ 0xf5, 0xe8, 0x1a, 0xf0, 0x11, 0x4a, 0xc1, 0x8d, ++ 0xe0, 0x93, 0xa0, 0xbe, 0x09, 0x1c, 0x2b, 0x4e, ++ 0x0f, 0xb2, 0x87, 0x8b, 0x84, 0xfe, 0x92, 0x32, ++ 0x14, 0xd7, 0x93, 0xdf, 0xe7, 0x44, 0xbc, 0xc5, ++ 0xae, 0x53, 0x69, 0xd8, 0xb3, 0x79, 0x37, 0x80, ++ 0xe3, 0x17, 0x5c, 0xec, 0x53, 0x00, 0x9a, 0xe3, ++ 0x8e, 0xdc, 0x38, 0xb8, 0x66, 0xf0, 0xd3, 0xad, ++ 0x1d, 0x02, 0x96, 0x86, 0x3e, 0x9d, 0x3b, 0x5d, ++ 0xa5, 0x7f, 0x21, 0x10, 0xf1, 0x1f, 0x13, 0x20, ++ 0xf9, 0x57, 0x87, 0x20, 0xf5, 0x5f, 0xf1, 0x17, ++ 0x48, 0x0a, 0x51, 0x5a, 0xcd, 0x19, 0x03, 0xa6, ++ 0x5a, 0xd1, 0x12, 0x97, 0xe9, 0x48, 0xe2, 0x1d, ++ 0x83, 0x75, 0x50, 0xd9, 0x75, 0x7d, 0x6a, 0x82, ++ 0xa1, 0xf9, 0x4e, 0x54, 0x87, 0x89, 0xc9, 0x0c, ++ 0xb7, 0x5b, 0x6a, 0x91, 0xc1, 0x9c, 0xb2, 0xa9, ++ 0xdc, 0x9a, 0xa4, 0x49, 0x0a, 0x6d, 0x0d, 0xbb, ++ 0xde, 0x86, 0x44, 0xdd, 0x5d, 0x89, 0x2b, 0x96, ++ 0x0f, 0x23, 0x95, 0xad, 0xcc, 0xa2, 0xb3, 0xb9, ++ 0x7e, 0x74, 0x38, 0xba, 0x9f, 0x73, 0xae, 0x5f, ++ 0xf8, 0x68, 0xa2, 0xe0, 0xa9, 0xce, 0xbd, 0x40, ++ 0xd4, 0x4c, 0x6b, 0xd2, 0x56, 0x62, 0xb0, 0xcc, ++ 0x63, 0x7e, 0x5b, 0xd3, 0xae, 0xd1, 0x75, 0xce, ++ 0xbb, 0xb4, 0x5b, 0xa8, 0xf8, 0xb4, 0xac, 0x71, ++ 0x75, 0xaa, 0xc9, 0x9f, 0xbb, 0x6c, 0xad, 0x0f, ++ 0x55, 0x5d, 0xe8, 0x85, 0x7d, 0xf9, 0x21, 0x35, ++ 0xea, 0x92, 0x85, 0x2b, 0x00, 0xec, 0x84, 0x90, ++ 0x0a, 0x63, 0x96, 0xe4, 0x6b, 0xa9, 0x77, 0xb8, ++ 0x91, 0xf8, 0x46, 0x15, 0x72, 0x63, 0x70, 0x01, ++ 0x40, 0xa3, 0xa5, 0x76, 0x62, 0x2b, 0xbf, 0xf1, ++ 0xe5, 0x8d, 0x9f, 0xa3, 0xfa, 0x9b, 0x03, 0xbe, ++ 0xfe, 0x65, 0x6f, 0xa2, 0x29, 0x0d, 0x54, 0xb4, ++ 0x71, 0xce, 0xa9, 0xd6, 0x3d, 0x88, 0xf9, 0xaf, ++ 0x6b, 0xa8, 0x9e, 0xf4, 0x16, 0x96, 0x36, 0xb9, ++ 0x00, 0xdc, 0x10, 0xab, 0xb5, 0x08, 0x31, 0x1f, ++ 0x00, 0xb1, 0x3c, 0xd9, 0x38, 0x3e, 0xc6, 0x04, ++ 0xa7, 0x4e, 0xe8, 0xae, 0xed, 0x98, 0xc2, 0xf7, ++ 0xb9, 0x00, 0x5f, 0x8c, 0x60, 0xd1, 0xe5, 0x15, ++ 0xf7, 0xae, 0x1e, 0x84, 0x88, 0xd1, 0xf6, 0xbc, ++ 0x3a, 0x89, 0x35, 0x22, 0x83, 0x7c, 0xca, 0xf0, ++ 0x33, 0x82, 0x4c, 0x79, 0x3c, 0xfd, 0xb1, 0xae, ++ 0x52, 0x62, 0x55, 0xd2, 0x41, 0x60, 0xc6, 0xbb, ++ 0xfa, 0x0e, 0x59, 0xd6, 0xa8, 0xfe, 0x5d, 0xed, ++ 0x47, 0x3d, 0xe0, 0xea, 0x1f, 0x6e, 0x43, 0x51, ++ 0xec, 0x10, 0x52, 0x56, 0x77, 0x42, 0x6b, 0x52, ++ 0x87, 0xd8, 0xec, 0xe0, 0xaa, 0x76, 0xa5, 0x84, ++ 0x2a, 0x22, 0x24, 0xfd, 0x92, 0x40, 0x88, 0xd5, ++ 0x85, 0x1c, 0x1f, 0x6b, 0x47, 0xa0, 0xc4, 0xe4, ++ 0xef, 0xf4, 0xea, 0xd7, 0x59, 0xac, 0x2a, 0x9e, ++ 0x8c, 0xfa, 0x1f, 0x42, 0x08, 0xfe, 0x4f, 0x74, ++ 0xa0, 0x26, 0xf5, 0xb3, 0x84, 0xf6, 0x58, 0x5f, ++ 0x26, 0x66, 0x3e, 0xd7, 0xe4, 0x22, 0x91, 0x13, ++ 0xc8, 0xac, 0x25, 0x96, 0x23, 0xd8, 0x09, 0xea, ++ 0x45, 0x75, 0x23, 0xb8, 0x5f, 0xc2, 0x90, 0x8b, ++ 0x09, 0xc4, 0xfc, 0x47, 0x6c, 0x6d, 0x0a, 0xef, ++ 0x69, 0xa4, 0x38, 0x19, 0xcf, 0x7d, 0xf9, 0x09, ++ 0x73, 0x9b, 0x60, 0x5a, 0xf7, 0x37, 0xb5, 0xfe, ++ 0x9f, 0xe3, 0x2b, 0x4c, 0x0d, 0x6e, 0x19, 0xf1, ++ 0xd6, 0xc0, 0x70, 0xf3, 0x9d, 0x22, 0x3c, 0xf9, ++ 0x49, 0xce, 0x30, 0x8e, 0x44, 0xb5, 0x76, 0x15, ++ 0x8f, 0x52, 0xfd, 0xa5, 0x04, 0xb8, 0x55, 0x6a, ++ 0x36, 0x59, 0x7c, 0xc4, 0x48, 0xb8, 0xd7, 0xab, ++ 0x05, 0x66, 0xe9, 0x5e, 0x21, 0x6f, 0x6b, 0x36, ++ 0x29, 0xbb, 0xe9, 0xe3, 0xa2, 0x9a, 0xa8, 0xcd, ++ 0x55, 0x25, 0x11, 0xba, 0x5a, 0x58, 0xa0, 0xde, ++ 0xae, 0x19, 0x2a, 0x48, 0x5a, 0xff, 0x36, 0xcd, ++ 0x6d, 0x16, 0x7a, 0x73, 0x38, 0x46, 0xe5, 0x47, ++ 0x59, 0xc8, 0xa2, 0xf6, 0xe2, 0x6c, 0x83, 0xc5, ++ 0x36, 0x2c, 0x83, 0x7d, 0xb4, 0x01, 0x05, 0x69, ++ 0xe7, 0xaf, 0x5c, 0xc4, 0x64, 0x82, 0x12, 0x21, ++ 0xef, 0xf7, 0xd1, 0x7d, 0xb8, 0x8d, 0x8c, 0x98, ++ 0x7c, 0x5f, 0x7d, 0x92, 0x88, 0xb9, 0x94, 0x07, ++ 0x9c, 0xd8, 0xe9, 0x9c, 0x17, 0x38, 0xe3, 0x57, ++ 0x6c, 0xe0, 0xdc, 0xa5, 0x92, 0x42, 0xb3, 0xbd, ++ 0x50, 0xa2, 0x7e, 0xb5, 0xb1, 0x52, 0x72, 0x03, ++ 0x97, 0xd8, 0xaa, 0x9a, 0x1e, 0x75, 0x41, 0x11, ++ 0xa3, 0x4f, 0xcc, 0xd4, 0xe3, 0x73, 0xad, 0x96, ++ 0xdc, 0x47, 0x41, 0x9f, 0xb0, 0xbe, 0x79, 0x91, ++ 0xf5, 0xb6, 0x18, 0xfe, 0xc2, 0x83, 0x18, 0x7d, ++ 0x73, 0xd9, 0x4f, 0x83, 0x84, 0x03, 0xb3, 0xf0, ++ 0x77, 0x66, 0x3d, 0x83, 0x63, 0x2e, 0x2c, 0xf9, ++ 0xdd, 0xa6, 0x1f, 0x89, 0x82, 0xb8, 0x23, 0x42, ++ 0xeb, 0xe2, 0xca, 0x70, 0x82, 0x61, 0x41, 0x0a, ++ 0x6d, 0x5f, 0x75, 0xc5, 0xe2, 0xc4, 0x91, 0x18, ++ 0x44, 0x22, 0xfa, 0x34, 0x10, 0xf5, 0x20, 0xdc, ++ 0xb7, 0xdd, 0x2a, 0x20, 0x77, 0xf5, 0xf9, 0xce, ++ 0xdb, 0xa0, 0x0a, 0x52, 0x2a, 0x4e, 0xdd, 0xcc, ++ 0x97, 0xdf, 0x05, 0xe4, 0x5e, 0xb7, 0xaa, 0xf0, ++ 0xe2, 0x80, 0xff, 0xba, 0x1a, 0x0f, 0xac, 0xdf, ++ 0x02, 0x32, 0xe6, 0xf7, 0xc7, 0x17, 0x13, 0xb7, ++ 0xfc, 0x98, 0x48, 0x8c, 0x0d, 0x82, 0xc9, 0x80, ++ 0x7a, 0xe2, 0x0a, 0xc5, 0xb4, 0xde, 0x7c, 0x3c, ++ 0x79, 0x81, 0x0e, 0x28, 0x65, 0x79, 0x67, 0x82, ++ 0x69, 0x44, 0x66, 0x09, 0xf7, 0x16, 0x1a, 0xf9, ++ 0x7d, 0x80, 0xa1, 0x79, 0x14, 0xa9, 0xc8, 0x20, ++ 0xfb, 0xa2, 0x46, 0xbe, 0x08, 0x35, 0x17, 0x58, ++ 0xc1, 0x1a, 0xda, 0x2a, 0x6b, 0x2e, 0x1e, 0xe6, ++ 0x27, 0x55, 0x7b, 0x19, 0xe2, 0xfb, 0x64, 0xfc, ++ 0x5e, 0x15, 0x54, 0x3c, 0xe7, 0xc2, 0x11, 0x50, ++ 0x30, 0xb8, 0x72, 0x03, 0x0b, 0x1a, 0x9f, 0x86, ++ 0x27, 0x11, 0x5c, 0x06, 0x2b, 0xbd, 0x75, 0x1a, ++ 0x0a, 0xda, 0x01, 0xfa, 0x5c, 0x4a, 0xc1, 0x80, ++ 0x3a, 0x6e, 0x30, 0xc8, 0x2c, 0xeb, 0x56, 0xec, ++ 0x89, 0xfa, 0x35, 0x7b, 0xb2, 0xf0, 0x97, 0x08, ++ 0x86, 0x53, 0xbe, 0xbd, 0x40, 0x41, 0x38, 0x1c, ++ 0xb4, 0x8b, 0x79, 0x2e, 0x18, 0x96, 0x94, 0xde, ++ 0xe8, 0xca, 0xe5, 0x9f, 0x92, 0x9f, 0x15, 0x5d, ++ 0x56, 0x60, 0x5c, 0x09, 0xf9, 0x16, 0xf4, 0x17, ++ 0x0f, 0xf6, 0x4c, 0xda, 0xe6, 0x67, 0x89, 0x9f, ++ 0xca, 0x6c, 0xe7, 0x9b, 0x04, 0x62, 0x0e, 0x26, ++ 0xa6, 0x52, 0xbd, 0x29, 0xff, 0xc7, 0xa4, 0x96, ++ 0xe6, 0x6a, 0x02, 0xa5, 0x2e, 0x7b, 0xfe, 0x97, ++ 0x68, 0x3e, 0x2e, 0x5f, 0x3b, 0x0f, 0x36, 0xd6, ++ 0x98, 0x19, 0x59, 0x48, 0xd2, 0xc6, 0xe1, 0x55, ++ 0x1a, 0x6e, 0xd6, 0xed, 0x2c, 0xba, 0xc3, 0x9e, ++ 0x64, 0xc9, 0x95, 0x86, 0x35, 0x5e, 0x3e, 0x88, ++ 0x69, 0x99, 0x4b, 0xee, 0xbe, 0x9a, 0x99, 0xb5, ++ 0x6e, 0x58, 0xae, 0xdd, 0x22, 0xdb, 0xdd, 0x6b, ++ 0xfc, 0xaf, 0x90, 0xa3, 0x3d, 0xa4, 0xc1, 0x15, ++ 0x92, 0x18, 0x8d, 0xd2, 0x4b, 0x7b, 0x06, 0xd1, ++ 0x37, 0xb5, 0xe2, 0x7c, 0x2c, 0xf0, 0x25, 0xe4, ++ 0x94, 0x2a, 0xbd, 0xe3, 0x82, 0x70, 0x78, 0xa3, ++ 0x82, 0x10, 0x5a, 0x90, 0xd7, 0xa4, 0xfa, 0xaf, ++ 0x1a, 0x88, 0x59, 0xdc, 0x74, 0x12, 0xb4, 0x8e, ++ 0xd7, 0x19, 0x46, 0xf4, 0x84, 0x69, 0x9f, 0xbb, ++ 0x70, 0xa8, 0x4c, 0x52, 0x81, 0xa9, 0xff, 0x76, ++ 0x1c, 0xae, 0xd8, 0x11, 0x3d, 0x7f, 0x7d, 0xc5, ++ 0x12, 0x59, 0x28, 0x18, 0xc2, 0xa2, 0xb7, 0x1c, ++ 0x88, 0xf8, 0xd6, 0x1b, 0xa6, 0x7d, 0x9e, 0xde, ++ 0x29, 0xf8, 0xed, 0xff, 0xeb, 0x92, 0x24, 0x4f, ++ 0x05, 0xaa, 0xd9, 0x49, 0xba, 0x87, 0x59, 0x51, ++ 0xc9, 0x20, 0x5c, 0x9b, 0x74, 0xcf, 0x03, 0xd9, ++ 0x2d, 0x34, 0xc7, 0x5b, 0xa5, 0x40, 0xb2, 0x99, ++ 0xf5, 0xcb, 0xb4, 0xf6, 0xb7, 0x72, 0x4a, 0xd6, ++ 0xbd, 0xb0, 0xf3, 0x93, 0xe0, 0x1b, 0xa8, 0x04, ++ 0x1e, 0x35, 0xd4, 0x80, 0x20, 0xf4, 0x9c, 0x31, ++ 0x6b, 0x45, 0xb9, 0x15, 0xb0, 0x5e, 0xdd, 0x0a, ++ 0x33, 0x9c, 0x83, 0xcd, 0x58, 0x89, 0x50, 0x56, ++ 0xbb, 0x81, 0x00, 0x91, 0x32, 0xf3, 0x1b, 0x3e, ++ 0xcf, 0x45, 0xe1, 0xf9, 0xe1, 0x2c, 0x26, 0x78, ++ 0x93, 0x9a, 0x60, 0x46, 0xc9, 0xb5, 0x5e, 0x6a, ++ 0x28, 0x92, 0x87, 0x3f, 0x63, 0x7b, 0xdb, 0xf7, ++ 0xd0, 0x13, 0x9d, 0x32, 0x40, 0x5e, 0xcf, 0xfb, ++ 0x79, 0x68, 0x47, 0x4c, 0xfd, 0x01, 0x17, 0xe6, ++ 0x97, 0x93, 0x78, 0xbb, 0xa6, 0x27, 0xa3, 0xe8, ++ 0x1a, 0xe8, 0x94, 0x55, 0x7d, 0x08, 0xe5, 0xdc, ++ 0x66, 0xa3, 0x69, 0xc8, 0xca, 0xc5, 0xa1, 0x84, ++ 0x55, 0xde, 0x08, 0x91, 0x16, 0x3a, 0x0c, 0x86, ++ 0xab, 0x27, 0x2b, 0x64, 0x34, 0x02, 0x6c, 0x76, ++ 0x8b, 0xc6, 0xaf, 0xcc, 0xe1, 0xd6, 0x8c, 0x2a, ++ 0x18, 0x3d, 0xa6, 0x1b, 0x37, 0x75, 0x45, 0x73, ++ 0xc2, 0x75, 0xd7, 0x53, 0x78, 0x3a, 0xd6, 0xe8, ++ 0x29, 0xd2, 0x4a, 0xa8, 0x1e, 0x82, 0xf6, 0xb6, ++ 0x81, 0xde, 0x21, 0xed, 0x2b, 0x56, 0xbb, 0xf2, ++ 0xd0, 0x57, 0xc1, 0x7c, 0xd2, 0x6a, 0xd2, 0x56, ++ 0xf5, 0x13, 0x5f, 0x1c, 0x6a, 0x0b, 0x74, 0xfb, ++ 0xe9, 0xfe, 0x9e, 0xea, 0x95, 0xb2, 0x46, 0xab, ++ 0x0a, 0xfc, 0xfd, 0xf3, 0xbb, 0x04, 0x2b, 0x76, ++ 0x1b, 0xa4, 0x74, 0xb0, 0xc1, 0x78, 0xc3, 0x69, ++ 0xe2, 0xb0, 0x01, 0xe1, 0xde, 0x32, 0x4c, 0x8d, ++ 0x1a, 0xb3, 0x38, 0x08, 0xd5, 0xfc, 0x1f, 0xdc, ++ 0x0e, 0x2c, 0x9c, 0xb1, 0xa1, 0x63, 0x17, 0x22, ++ 0xf5, 0x6c, 0x93, 0x70, 0x74, 0x00, 0xf8, 0x39, ++ 0x01, 0x94, 0xd1, 0x32, 0x23, 0x56, 0x5d, 0xa6, ++ 0x02, 0x76, 0x76, 0x93, 0xce, 0x2f, 0x19, 0xe9, ++ 0x17, 0x52, 0xae, 0x6e, 0x2c, 0x6d, 0x61, 0x7f, ++ 0x3b, 0xaa, 0xe0, 0x52, 0x85, 0xc5, 0x65, 0xc1, ++ 0xbb, 0x8e, 0x5b, 0x21, 0xd5, 0xc9, 0x78, 0x83, ++ 0x07, 0x97, 0x4c, 0x62, 0x61, 0x41, 0xd4, 0xfc, ++ 0xc9, 0x39, 0xe3, 0x9b, 0xd0, 0xcc, 0x75, 0xc4, ++ 0x97, 0xe6, 0xdd, 0x2a, 0x5f, 0xa6, 0xe8, 0x59, ++ 0x6c, 0x98, 0xb9, 0x02, 0xe2, 0xa2, 0xd6, 0x68, ++ 0xee, 0x3b, 0x1d, 0xe3, 0x4d, 0x5b, 0x30, 0xef, ++ 0x03, 0xf2, 0xeb, 0x18, 0x57, 0x36, 0xe8, 0xa1, ++ 0xf4, 0x47, 0xfb, 0xcb, 0x8f, 0xcb, 0xc8, 0xf3, ++ 0x4f, 0x74, 0x9d, 0x9d, 0xb1, 0x8d, 0x14, 0x44, ++ 0xd9, 0x19, 0xb4, 0x54, 0x4f, 0x75, 0x19, 0x09, ++ 0xa0, 0x75, 0xbc, 0x3b, 0x82, 0xc6, 0x3f, 0xb8, ++ 0x83, 0x19, 0x6e, 0xd6, 0x37, 0xfe, 0x6e, 0x8a, ++ 0x4e, 0xe0, 0x4a, 0xab, 0x7b, 0xc8, 0xb4, 0x1d, ++ 0xf4, 0xed, 0x27, 0x03, 0x65, 0xa2, 0xa1, 0xae, ++ 0x11, 0xe7, 0x98, 0x78, 0x48, 0x91, 0xd2, 0xd2, ++ 0xd4, 0x23, 0x78, 0x50, 0xb1, 0x5b, 0x85, 0x10, ++ 0x8d, 0xca, 0x5f, 0x0f, 0x71, 0xae, 0x72, 0x9a, ++ 0xf6, 0x25, 0x19, 0x60, 0x06, 0xf7, 0x10, 0x34, ++ 0x18, 0x0d, 0xc9, 0x9f, 0x7b, 0x0c, 0x9b, 0x8f, ++ 0x91, 0x1b, 0x9f, 0xcd, 0x10, 0xee, 0x75, 0xf9, ++ 0x97, 0x66, 0xfc, 0x4d, 0x33, 0x6e, 0x28, 0x2b, ++ 0x92, 0x85, 0x4f, 0xab, 0x43, 0x8d, 0x8f, 0x7d, ++ 0x86, 0xa7, 0xc7, 0xd8, 0xd3, 0x0b, 0x8b, 0x57, ++ 0xb6, 0x1d, 0x95, 0x0d, 0xe9, 0xbc, 0xd9, 0x03, ++ 0xd9, 0x10, 0x19, 0xc3, 0x46, 0x63, 0x55, 0x87, ++ 0x61, 0x79, 0x6c, 0x95, 0x0e, 0x9c, 0xdd, 0xca, ++ 0xc3, 0xf3, 0x64, 0xf0, 0x7d, 0x76, 0xb7, 0x53, ++ 0x67, 0x2b, 0x1e, 0x44, 0x56, 0x81, 0xea, 0x8f, ++ 0x5c, 0x42, 0x16, 0xb8, 0x28, 0xeb, 0x1b, 0x61, ++ 0x10, 0x1e, 0xbf, 0xec, 0xa8 ++}; ++static const u8 dec_assoc011[] __initconst = { ++ 0xd6, 0x31, 0xda, 0x5d, 0x42, 0x5e, 0xd7 ++}; ++static const u8 dec_nonce011[] __initconst = { ++ 0xfd, 0x87, 0xd4, 0xd8, 0x62, 0xfd, 0xec, 0xaa ++}; ++static const u8 dec_key011[] __initconst = { ++ 0x35, 0x4e, 0xb5, 0x70, 0x50, 0x42, 0x8a, 0x85, ++ 0xf2, 0xfb, 0xed, 0x7b, 0xd0, 0x9e, 0x97, 0xca, ++ 0xfa, 0x98, 0x66, 0x63, 0xee, 0x37, 0xcc, 0x52, ++ 0xfe, 0xd1, 0xdf, 0x95, 0x15, 0x34, 0x29, 0x38 ++}; ++ ++static const u8 dec_input012[] __initconst = { ++ 0x52, 0x34, 0xb3, 0x65, 0x3b, 0xb7, 0xe5, 0xd3, ++ 0xab, 0x49, 0x17, 0x60, 0xd2, 0x52, 0x56, 0xdf, ++ 0xdf, 0x34, 0x56, 0x82, 0xe2, 0xbe, 0xe5, 0xe1, ++ 0x28, 0xd1, 0x4e, 0x5f, 0x4f, 0x01, 0x7d, 0x3f, ++ 0x99, 0x6b, 0x30, 0x6e, 0x1a, 0x7c, 0x4c, 0x8e, ++ 0x62, 0x81, 0xae, 0x86, 0x3f, 0x6b, 0xd0, 0xb5, ++ 0xa9, 0xcf, 0x50, 0xf1, 0x02, 0x12, 0xa0, 0x0b, ++ 0x24, 0xe9, 0xe6, 0x72, 0x89, 0x2c, 0x52, 0x1b, ++ 0x34, 0x38, 0xf8, 0x75, 0x5f, 0xa0, 0x74, 0xe2, ++ 0x99, 0xdd, 0xa6, 0x4b, 0x14, 0x50, 0x4e, 0xf1, ++ 0xbe, 0xd6, 0x9e, 0xdb, 0xb2, 0x24, 0x27, 0x74, ++ 0x12, 0x4a, 0x78, 0x78, 0x17, 0xa5, 0x58, 0x8e, ++ 0x2f, 0xf9, 0xf4, 0x8d, 0xee, 0x03, 0x88, 0xae, ++ 0xb8, 0x29, 0xa1, 0x2f, 0x4b, 0xee, 0x92, 0xbd, ++ 0x87, 0xb3, 0xce, 0x34, 0x21, 0x57, 0x46, 0x04, ++ 0x49, 0x0c, 0x80, 0xf2, 0x01, 0x13, 0xa1, 0x55, ++ 0xb3, 0xff, 0x44, 0x30, 0x3c, 0x1c, 0xd0, 0xef, ++ 0xbc, 0x18, 0x74, 0x26, 0xad, 0x41, 0x5b, 0x5b, ++ 0x3e, 0x9a, 0x7a, 0x46, 0x4f, 0x16, 0xd6, 0x74, ++ 0x5a, 0xb7, 0x3a, 0x28, 0x31, 0xd8, 0xae, 0x26, ++ 0xac, 0x50, 0x53, 0x86, 0xf2, 0x56, 0xd7, 0x3f, ++ 0x29, 0xbc, 0x45, 0x68, 0x8e, 0xcb, 0x98, 0x64, ++ 0xdd, 0xc9, 0xba, 0xb8, 0x4b, 0x7b, 0x82, 0xdd, ++ 0x14, 0xa7, 0xcb, 0x71, 0x72, 0x00, 0x5c, 0xad, ++ 0x7b, 0x6a, 0x89, 0xa4, 0x3d, 0xbf, 0xb5, 0x4b, ++ 0x3e, 0x7c, 0x5a, 0xcf, 0xb8, 0xa1, 0xc5, 0x6e, ++ 0xc8, 0xb6, 0x31, 0x57, 0x7b, 0xdf, 0xa5, 0x7e, ++ 0xb1, 0xd6, 0x42, 0x2a, 0x31, 0x36, 0xd1, 0xd0, ++ 0x3f, 0x7a, 0xe5, 0x94, 0xd6, 0x36, 0xa0, 0x6f, ++ 0xb7, 0x40, 0x7d, 0x37, 0xc6, 0x55, 0x7c, 0x50, ++ 0x40, 0x6d, 0x29, 0x89, 0xe3, 0x5a, 0xae, 0x97, ++ 0xe7, 0x44, 0x49, 0x6e, 0xbd, 0x81, 0x3d, 0x03, ++ 0x93, 0x06, 0x12, 0x06, 0xe2, 0x41, 0x12, 0x4a, ++ 0xf1, 0x6a, 0xa4, 0x58, 0xa2, 0xfb, 0xd2, 0x15, ++ 0xba, 0xc9, 0x79, 0xc9, 0xce, 0x5e, 0x13, 0xbb, ++ 0xf1, 0x09, 0x04, 0xcc, 0xfd, 0xe8, 0x51, 0x34, ++ 0x6a, 0xe8, 0x61, 0x88, 0xda, 0xed, 0x01, 0x47, ++ 0x84, 0xf5, 0x73, 0x25, 0xf9, 0x1c, 0x42, 0x86, ++ 0x07, 0xf3, 0x5b, 0x1a, 0x01, 0xb3, 0xeb, 0x24, ++ 0x32, 0x8d, 0xf6, 0xed, 0x7c, 0x4b, 0xeb, 0x3c, ++ 0x36, 0x42, 0x28, 0xdf, 0xdf, 0xb6, 0xbe, 0xd9, ++ 0x8c, 0x52, 0xd3, 0x2b, 0x08, 0x90, 0x8c, 0xe7, ++ 0x98, 0x31, 0xe2, 0x32, 0x8e, 0xfc, 0x11, 0x48, ++ 0x00, 0xa8, 0x6a, 0x42, 0x4a, 0x02, 0xc6, 0x4b, ++ 0x09, 0xf1, 0xe3, 0x49, 0xf3, 0x45, 0x1f, 0x0e, ++ 0xbc, 0x56, 0xe2, 0xe4, 0xdf, 0xfb, 0xeb, 0x61, ++ 0xfa, 0x24, 0xc1, 0x63, 0x75, 0xbb, 0x47, 0x75, ++ 0xaf, 0xe1, 0x53, 0x16, 0x96, 0x21, 0x85, 0x26, ++ 0x11, 0xb3, 0x76, 0xe3, 0x23, 0xa1, 0x6b, 0x74, ++ 0x37, 0xd0, 0xde, 0x06, 0x90, 0x71, 0x5d, 0x43, ++ 0x88, 0x9b, 0x00, 0x54, 0xa6, 0x75, 0x2f, 0xa1, ++ 0xc2, 0x0b, 0x73, 0x20, 0x1d, 0xb6, 0x21, 0x79, ++ 0x57, 0x3f, 0xfa, 0x09, 0xbe, 0x8a, 0x33, 0xc3, ++ 0x52, 0xf0, 0x1d, 0x82, 0x31, 0xd1, 0x55, 0xb5, ++ 0x6c, 0x99, 0x25, 0xcf, 0x5c, 0x32, 0xce, 0xe9, ++ 0x0d, 0xfa, 0x69, 0x2c, 0xd5, 0x0d, 0xc5, 0x6d, ++ 0x86, 0xd0, 0x0c, 0x3b, 0x06, 0x50, 0x79, 0xe8, ++ 0xc3, 0xae, 0x04, 0xe6, 0xcd, 0x51, 0xe4, 0x26, ++ 0x9b, 0x4f, 0x7e, 0xa6, 0x0f, 0xab, 0xd8, 0xe5, ++ 0xde, 0xa9, 0x00, 0x95, 0xbe, 0xa3, 0x9d, 0x5d, ++ 0xb2, 0x09, 0x70, 0x18, 0x1c, 0xf0, 0xac, 0x29, ++ 0x23, 0x02, 0x29, 0x28, 0xd2, 0x74, 0x35, 0x57, ++ 0x62, 0x0f, 0x24, 0xea, 0x5e, 0x33, 0xc2, 0x92, ++ 0xf3, 0x78, 0x4d, 0x30, 0x1e, 0xa1, 0x99, 0xa9, ++ 0x82, 0xb0, 0x42, 0x31, 0x8d, 0xad, 0x8a, 0xbc, ++ 0xfc, 0xd4, 0x57, 0x47, 0x3e, 0xb4, 0x50, 0xdd, ++ 0x6e, 0x2c, 0x80, 0x4d, 0x22, 0xf1, 0xfb, 0x57, ++ 0xc4, 0xdd, 0x17, 0xe1, 0x8a, 0x36, 0x4a, 0xb3, ++ 0x37, 0xca, 0xc9, 0x4e, 0xab, 0xd5, 0x69, 0xc4, ++ 0xf4, 0xbc, 0x0b, 0x3b, 0x44, 0x4b, 0x29, 0x9c, ++ 0xee, 0xd4, 0x35, 0x22, 0x21, 0xb0, 0x1f, 0x27, ++ 0x64, 0xa8, 0x51, 0x1b, 0xf0, 0x9f, 0x19, 0x5c, ++ 0xfb, 0x5a, 0x64, 0x74, 0x70, 0x45, 0x09, 0xf5, ++ 0x64, 0xfe, 0x1a, 0x2d, 0xc9, 0x14, 0x04, 0x14, ++ 0xcf, 0xd5, 0x7d, 0x60, 0xaf, 0x94, 0x39, 0x94, ++ 0xe2, 0x7d, 0x79, 0x82, 0xd0, 0x65, 0x3b, 0x6b, ++ 0x9c, 0x19, 0x84, 0xb4, 0x6d, 0xb3, 0x0c, 0x99, ++ 0xc0, 0x56, 0xa8, 0xbd, 0x73, 0xce, 0x05, 0x84, ++ 0x3e, 0x30, 0xaa, 0xc4, 0x9b, 0x1b, 0x04, 0x2a, ++ 0x9f, 0xd7, 0x43, 0x2b, 0x23, 0xdf, 0xbf, 0xaa, ++ 0xd5, 0xc2, 0x43, 0x2d, 0x70, 0xab, 0xdc, 0x75, ++ 0xad, 0xac, 0xf7, 0xc0, 0xbe, 0x67, 0xb2, 0x74, ++ 0xed, 0x67, 0x10, 0x4a, 0x92, 0x60, 0xc1, 0x40, ++ 0x50, 0x19, 0x8a, 0x8a, 0x8c, 0x09, 0x0e, 0x72, ++ 0xe1, 0x73, 0x5e, 0xe8, 0x41, 0x85, 0x63, 0x9f, ++ 0x3f, 0xd7, 0x7d, 0xc4, 0xfb, 0x22, 0x5d, 0x92, ++ 0x6c, 0xb3, 0x1e, 0xe2, 0x50, 0x2f, 0x82, 0xa8, ++ 0x28, 0xc0, 0xb5, 0xd7, 0x5f, 0x68, 0x0d, 0x2c, ++ 0x2d, 0xaf, 0x7e, 0xfa, 0x2e, 0x08, 0x0f, 0x1f, ++ 0x70, 0x9f, 0xe9, 0x19, 0x72, 0x55, 0xf8, 0xfb, ++ 0x51, 0xd2, 0x33, 0x5d, 0xa0, 0xd3, 0x2b, 0x0a, ++ 0x6c, 0xbc, 0x4e, 0xcf, 0x36, 0x4d, 0xdc, 0x3b, ++ 0xe9, 0x3e, 0x81, 0x7c, 0x61, 0xdb, 0x20, 0x2d, ++ 0x3a, 0xc3, 0xb3, 0x0c, 0x1e, 0x00, 0xb9, 0x7c, ++ 0xf5, 0xca, 0x10, 0x5f, 0x3a, 0x71, 0xb3, 0xe4, ++ 0x20, 0xdb, 0x0c, 0x2a, 0x98, 0x63, 0x45, 0x00, ++ 0x58, 0xf6, 0x68, 0xe4, 0x0b, 0xda, 0x13, 0x3b, ++ 0x60, 0x5c, 0x76, 0xdb, 0xb9, 0x97, 0x71, 0xe4, ++ 0xd9, 0xb7, 0xdb, 0xbd, 0x68, 0xc7, 0x84, 0x84, ++ 0xaa, 0x7c, 0x68, 0x62, 0x5e, 0x16, 0xfc, 0xba, ++ 0x72, 0xaa, 0x9a, 0xa9, 0xeb, 0x7c, 0x75, 0x47, ++ 0x97, 0x7e, 0xad, 0xe2, 0xd9, 0x91, 0xe8, 0xe4, ++ 0xa5, 0x31, 0xd7, 0x01, 0x8e, 0xa2, 0x11, 0x88, ++ 0x95, 0xb9, 0xf2, 0x9b, 0xd3, 0x7f, 0x1b, 0x81, ++ 0x22, 0xf7, 0x98, 0x60, 0x0a, 0x64, 0xa6, 0xc1, ++ 0xf6, 0x49, 0xc7, 0xe3, 0x07, 0x4d, 0x94, 0x7a, ++ 0xcf, 0x6e, 0x68, 0x0c, 0x1b, 0x3f, 0x6e, 0x2e, ++ 0xee, 0x92, 0xfa, 0x52, 0xb3, 0x59, 0xf8, 0xf1, ++ 0x8f, 0x6a, 0x66, 0xa3, 0x82, 0x76, 0x4a, 0x07, ++ 0x1a, 0xc7, 0xdd, 0xf5, 0xda, 0x9c, 0x3c, 0x24, ++ 0xbf, 0xfd, 0x42, 0xa1, 0x10, 0x64, 0x6a, 0x0f, ++ 0x89, 0xee, 0x36, 0xa5, 0xce, 0x99, 0x48, 0x6a, ++ 0xf0, 0x9f, 0x9e, 0x69, 0xa4, 0x40, 0x20, 0xe9, ++ 0x16, 0x15, 0xf7, 0xdb, 0x75, 0x02, 0xcb, 0xe9, ++ 0x73, 0x8b, 0x3b, 0x49, 0x2f, 0xf0, 0xaf, 0x51, ++ 0x06, 0x5c, 0xdf, 0x27, 0x27, 0x49, 0x6a, 0xd1, ++ 0xcc, 0xc7, 0xb5, 0x63, 0xb5, 0xfc, 0xb8, 0x5c, ++ 0x87, 0x7f, 0x84, 0xb4, 0xcc, 0x14, 0xa9, 0x53, ++ 0xda, 0xa4, 0x56, 0xf8, 0xb6, 0x1b, 0xcc, 0x40, ++ 0x27, 0x52, 0x06, 0x5a, 0x13, 0x81, 0xd7, 0x3a, ++ 0xd4, 0x3b, 0xfb, 0x49, 0x65, 0x31, 0x33, 0xb2, ++ 0xfa, 0xcd, 0xad, 0x58, 0x4e, 0x2b, 0xae, 0xd2, ++ 0x20, 0xfb, 0x1a, 0x48, 0xb4, 0x3f, 0x9a, 0xd8, ++ 0x7a, 0x35, 0x4a, 0xc8, 0xee, 0x88, 0x5e, 0x07, ++ 0x66, 0x54, 0xb9, 0xec, 0x9f, 0xa3, 0xe3, 0xb9, ++ 0x37, 0xaa, 0x49, 0x76, 0x31, 0xda, 0x74, 0x2d, ++ 0x3c, 0xa4, 0x65, 0x10, 0x32, 0x38, 0xf0, 0xde, ++ 0xd3, 0x99, 0x17, 0xaa, 0x71, 0xaa, 0x8f, 0x0f, ++ 0x8c, 0xaf, 0xa2, 0xf8, 0x5d, 0x64, 0xba, 0x1d, ++ 0xa3, 0xef, 0x96, 0x73, 0xe8, 0xa1, 0x02, 0x8d, ++ 0x0c, 0x6d, 0xb8, 0x06, 0x90, 0xb8, 0x08, 0x56, ++ 0x2c, 0xa7, 0x06, 0xc9, 0xc2, 0x38, 0xdb, 0x7c, ++ 0x63, 0xb1, 0x57, 0x8e, 0xea, 0x7c, 0x79, 0xf3, ++ 0x49, 0x1d, 0xfe, 0x9f, 0xf3, 0x6e, 0xb1, 0x1d, ++ 0xba, 0x19, 0x80, 0x1a, 0x0a, 0xd3, 0xb0, 0x26, ++ 0x21, 0x40, 0xb1, 0x7c, 0xf9, 0x4d, 0x8d, 0x10, ++ 0xc1, 0x7e, 0xf4, 0xf6, 0x3c, 0xa8, 0xfd, 0x7c, ++ 0xa3, 0x92, 0xb2, 0x0f, 0xaa, 0xcc, 0xa6, 0x11, ++ 0xfe, 0x04, 0xe3, 0xd1, 0x7a, 0x32, 0x89, 0xdf, ++ 0x0d, 0xc4, 0x8f, 0x79, 0x6b, 0xca, 0x16, 0x7c, ++ 0x6e, 0xf9, 0xad, 0x0f, 0xf6, 0xfe, 0x27, 0xdb, ++ 0xc4, 0x13, 0x70, 0xf1, 0x62, 0x1a, 0x4f, 0x79, ++ 0x40, 0xc9, 0x9b, 0x8b, 0x21, 0xea, 0x84, 0xfa, ++ 0xf5, 0xf1, 0x89, 0xce, 0xb7, 0x55, 0x0a, 0x80, ++ 0x39, 0x2f, 0x55, 0x36, 0x16, 0x9c, 0x7b, 0x08, ++ 0xbd, 0x87, 0x0d, 0xa5, 0x32, 0xf1, 0x52, 0x7c, ++ 0xe8, 0x55, 0x60, 0x5b, 0xd7, 0x69, 0xe4, 0xfc, ++ 0xfa, 0x12, 0x85, 0x96, 0xea, 0x50, 0x28, 0xab, ++ 0x8a, 0xf7, 0xbb, 0x0e, 0x53, 0x74, 0xca, 0xa6, ++ 0x27, 0x09, 0xc2, 0xb5, 0xde, 0x18, 0x14, 0xd9, ++ 0xea, 0xe5, 0x29, 0x1c, 0x40, 0x56, 0xcf, 0xd7, ++ 0xae, 0x05, 0x3f, 0x65, 0xaf, 0x05, 0x73, 0xe2, ++ 0x35, 0x96, 0x27, 0x07, 0x14, 0xc0, 0xad, 0x33, ++ 0xf1, 0xdc, 0x44, 0x7a, 0x89, 0x17, 0x77, 0xd2, ++ 0x9c, 0x58, 0x60, 0xf0, 0x3f, 0x7b, 0x2d, 0x2e, ++ 0x57, 0x95, 0x54, 0x87, 0xed, 0xf2, 0xc7, 0x4c, ++ 0xf0, 0xae, 0x56, 0x29, 0x19, 0x7d, 0x66, 0x4b, ++ 0x9b, 0x83, 0x84, 0x42, 0x3b, 0x01, 0x25, 0x66, ++ 0x8e, 0x02, 0xde, 0xb9, 0x83, 0x54, 0x19, 0xf6, ++ 0x9f, 0x79, 0x0d, 0x67, 0xc5, 0x1d, 0x7a, 0x44, ++ 0x02, 0x98, 0xa7, 0x16, 0x1c, 0x29, 0x0d, 0x74, ++ 0xff, 0x85, 0x40, 0x06, 0xef, 0x2c, 0xa9, 0xc6, ++ 0xf5, 0x53, 0x07, 0x06, 0xae, 0xe4, 0xfa, 0x5f, ++ 0xd8, 0x39, 0x4d, 0xf1, 0x9b, 0x6b, 0xd9, 0x24, ++ 0x84, 0xfe, 0x03, 0x4c, 0xb2, 0x3f, 0xdf, 0xa1, ++ 0x05, 0x9e, 0x50, 0x14, 0x5a, 0xd9, 0x1a, 0xa2, ++ 0xa7, 0xfa, 0xfa, 0x17, 0xf7, 0x78, 0xd6, 0xb5, ++ 0x92, 0x61, 0x91, 0xac, 0x36, 0xfa, 0x56, 0x0d, ++ 0x38, 0x32, 0x18, 0x85, 0x08, 0x58, 0x37, 0xf0, ++ 0x4b, 0xdb, 0x59, 0xe7, 0xa4, 0x34, 0xc0, 0x1b, ++ 0x01, 0xaf, 0x2d, 0xde, 0xa1, 0xaa, 0x5d, 0xd3, ++ 0xec, 0xe1, 0xd4, 0xf7, 0xe6, 0x54, 0x68, 0xf0, ++ 0x51, 0x97, 0xa7, 0x89, 0xea, 0x24, 0xad, 0xd3, ++ 0x6e, 0x47, 0x93, 0x8b, 0x4b, 0xb4, 0xf7, 0x1c, ++ 0x42, 0x06, 0x67, 0xe8, 0x99, 0xf6, 0xf5, 0x7b, ++ 0x85, 0xb5, 0x65, 0xb5, 0xb5, 0xd2, 0x37, 0xf5, ++ 0xf3, 0x02, 0xa6, 0x4d, 0x11, 0xa7, 0xdc, 0x51, ++ 0x09, 0x7f, 0xa0, 0xd8, 0x88, 0x1c, 0x13, 0x71, ++ 0xae, 0x9c, 0xb7, 0x7b, 0x34, 0xd6, 0x4e, 0x68, ++ 0x26, 0x83, 0x51, 0xaf, 0x1d, 0xee, 0x8b, 0xbb, ++ 0x69, 0x43, 0x2b, 0x9e, 0x8a, 0xbc, 0x02, 0x0e, ++ 0xa0, 0x1b, 0xe0, 0xa8, 0x5f, 0x6f, 0xaf, 0x1b, ++ 0x8f, 0xe7, 0x64, 0x71, 0x74, 0x11, 0x7e, 0xa8, ++ 0xd8, 0xf9, 0x97, 0x06, 0xc3, 0xb6, 0xfb, 0xfb, ++ 0xb7, 0x3d, 0x35, 0x9d, 0x3b, 0x52, 0xed, 0x54, ++ 0xca, 0xf4, 0x81, 0x01, 0x2d, 0x1b, 0xc3, 0xa7, ++ 0x00, 0x3d, 0x1a, 0x39, 0x54, 0xe1, 0xf6, 0xff, ++ 0xed, 0x6f, 0x0b, 0x5a, 0x68, 0xda, 0x58, 0xdd, ++ 0xa9, 0xcf, 0x5c, 0x4a, 0xe5, 0x09, 0x4e, 0xde, ++ 0x9d, 0xbc, 0x3e, 0xee, 0x5a, 0x00, 0x3b, 0x2c, ++ 0x87, 0x10, 0x65, 0x60, 0xdd, 0xd7, 0x56, 0xd1, ++ 0x4c, 0x64, 0x45, 0xe4, 0x21, 0xec, 0x78, 0xf8, ++ 0x25, 0x7a, 0x3e, 0x16, 0x5d, 0x09, 0x53, 0x14, ++ 0xbe, 0x4f, 0xae, 0x87, 0xd8, 0xd1, 0xaa, 0x3c, ++ 0xf6, 0x3e, 0xa4, 0x70, 0x8c, 0x5e, 0x70, 0xa4, ++ 0xb3, 0x6b, 0x66, 0x73, 0xd3, 0xbf, 0x31, 0x06, ++ 0x19, 0x62, 0x93, 0x15, 0xf2, 0x86, 0xe4, 0x52, ++ 0x7e, 0x53, 0x4c, 0x12, 0x38, 0xcc, 0x34, 0x7d, ++ 0x57, 0xf6, 0x42, 0x93, 0x8a, 0xc4, 0xee, 0x5c, ++ 0x8a, 0xe1, 0x52, 0x8f, 0x56, 0x64, 0xf6, 0xa6, ++ 0xd1, 0x91, 0x57, 0x70, 0xcd, 0x11, 0x76, 0xf5, ++ 0x59, 0x60, 0x60, 0x3c, 0xc1, 0xc3, 0x0b, 0x7f, ++ 0x58, 0x1a, 0x50, 0x91, 0xf1, 0x68, 0x8f, 0x6e, ++ 0x74, 0x74, 0xa8, 0x51, 0x0b, 0xf7, 0x7a, 0x98, ++ 0x37, 0xf2, 0x0a, 0x0e, 0xa4, 0x97, 0x04, 0xb8, ++ 0x9b, 0xfd, 0xa0, 0xea, 0xf7, 0x0d, 0xe1, 0xdb, ++ 0x03, 0xf0, 0x31, 0x29, 0xf8, 0xdd, 0x6b, 0x8b, ++ 0x5d, 0xd8, 0x59, 0xa9, 0x29, 0xcf, 0x9a, 0x79, ++ 0x89, 0x19, 0x63, 0x46, 0x09, 0x79, 0x6a, 0x11, ++ 0xda, 0x63, 0x68, 0x48, 0x77, 0x23, 0xfb, 0x7d, ++ 0x3a, 0x43, 0xcb, 0x02, 0x3b, 0x7a, 0x6d, 0x10, ++ 0x2a, 0x9e, 0xac, 0xf1, 0xd4, 0x19, 0xf8, 0x23, ++ 0x64, 0x1d, 0x2c, 0x5f, 0xf2, 0xb0, 0x5c, 0x23, ++ 0x27, 0xf7, 0x27, 0x30, 0x16, 0x37, 0xb1, 0x90, ++ 0xab, 0x38, 0xfb, 0x55, 0xcd, 0x78, 0x58, 0xd4, ++ 0x7d, 0x43, 0xf6, 0x45, 0x5e, 0x55, 0x8d, 0xb1, ++ 0x02, 0x65, 0x58, 0xb4, 0x13, 0x4b, 0x36, 0xf7, ++ 0xcc, 0xfe, 0x3d, 0x0b, 0x82, 0xe2, 0x12, 0x11, ++ 0xbb, 0xe6, 0xb8, 0x3a, 0x48, 0x71, 0xc7, 0x50, ++ 0x06, 0x16, 0x3a, 0xe6, 0x7c, 0x05, 0xc7, 0xc8, ++ 0x4d, 0x2f, 0x08, 0x6a, 0x17, 0x9a, 0x95, 0x97, ++ 0x50, 0x68, 0xdc, 0x28, 0x18, 0xc4, 0x61, 0x38, ++ 0xb9, 0xe0, 0x3e, 0x78, 0xdb, 0x29, 0xe0, 0x9f, ++ 0x52, 0xdd, 0xf8, 0x4f, 0x91, 0xc1, 0xd0, 0x33, ++ 0xa1, 0x7a, 0x8e, 0x30, 0x13, 0x82, 0x07, 0x9f, ++ 0xd3, 0x31, 0x0f, 0x23, 0xbe, 0x32, 0x5a, 0x75, ++ 0xcf, 0x96, 0xb2, 0xec, 0xb5, 0x32, 0xac, 0x21, ++ 0xd1, 0x82, 0x33, 0xd3, 0x15, 0x74, 0xbd, 0x90, ++ 0xf1, 0x2c, 0xe6, 0x5f, 0x8d, 0xe3, 0x02, 0xe8, ++ 0xe9, 0xc4, 0xca, 0x96, 0xeb, 0x0e, 0xbc, 0x91, ++ 0xf4, 0xb9, 0xea, 0xd9, 0x1b, 0x75, 0xbd, 0xe1, ++ 0xac, 0x2a, 0x05, 0x37, 0x52, 0x9b, 0x1b, 0x3f, ++ 0x5a, 0xdc, 0x21, 0xc3, 0x98, 0xbb, 0xaf, 0xa3, ++ 0xf2, 0x00, 0xbf, 0x0d, 0x30, 0x89, 0x05, 0xcc, ++ 0xa5, 0x76, 0xf5, 0x06, 0xf0, 0xc6, 0x54, 0x8a, ++ 0x5d, 0xd4, 0x1e, 0xc1, 0xf2, 0xce, 0xb0, 0x62, ++ 0xc8, 0xfc, 0x59, 0x42, 0x9a, 0x90, 0x60, 0x55, ++ 0xfe, 0x88, 0xa5, 0x8b, 0xb8, 0x33, 0x0c, 0x23, ++ 0x24, 0x0d, 0x15, 0x70, 0x37, 0x1e, 0x3d, 0xf6, ++ 0xd2, 0xea, 0x92, 0x10, 0xb2, 0xc4, 0x51, 0xac, ++ 0xf2, 0xac, 0xf3, 0x6b, 0x6c, 0xaa, 0xcf, 0x12, ++ 0xc5, 0x6c, 0x90, 0x50, 0xb5, 0x0c, 0xfc, 0x1a, ++ 0x15, 0x52, 0xe9, 0x26, 0xc6, 0x52, 0xa4, 0xe7, ++ 0x81, 0x69, 0xe1, 0xe7, 0x9e, 0x30, 0x01, 0xec, ++ 0x84, 0x89, 0xb2, 0x0d, 0x66, 0xdd, 0xce, 0x28, ++ 0x5c, 0xec, 0x98, 0x46, 0x68, 0x21, 0x9f, 0x88, ++ 0x3f, 0x1f, 0x42, 0x77, 0xce, 0xd0, 0x61, 0xd4, ++ 0x20, 0xa7, 0xff, 0x53, 0xad, 0x37, 0xd0, 0x17, ++ 0x35, 0xc9, 0xfc, 0xba, 0x0a, 0x78, 0x3f, 0xf2, ++ 0xcc, 0x86, 0x89, 0xe8, 0x4b, 0x3c, 0x48, 0x33, ++ 0x09, 0x7f, 0xc6, 0xc0, 0xdd, 0xb8, 0xfd, 0x7a, ++ 0x66, 0x66, 0x65, 0xeb, 0x47, 0xa7, 0x04, 0x28, ++ 0xa3, 0x19, 0x8e, 0xa9, 0xb1, 0x13, 0x67, 0x62, ++ 0x70, 0xcf, 0xd6 ++}; ++static const u8 dec_output012[] __initconst = { ++ 0x74, 0xa6, 0x3e, 0xe4, 0xb1, 0xcb, 0xaf, 0xb0, ++ 0x40, 0xe5, 0x0f, 0x9e, 0xf1, 0xf2, 0x89, 0xb5, ++ 0x42, 0x34, 0x8a, 0xa1, 0x03, 0xb7, 0xe9, 0x57, ++ 0x46, 0xbe, 0x20, 0xe4, 0x6e, 0xb0, 0xeb, 0xff, ++ 0xea, 0x07, 0x7e, 0xef, 0xe2, 0x55, 0x9f, 0xe5, ++ 0x78, 0x3a, 0xb7, 0x83, 0xc2, 0x18, 0x40, 0x7b, ++ 0xeb, 0xcd, 0x81, 0xfb, 0x90, 0x12, 0x9e, 0x46, ++ 0xa9, 0xd6, 0x4a, 0xba, 0xb0, 0x62, 0xdb, 0x6b, ++ 0x99, 0xc4, 0xdb, 0x54, 0x4b, 0xb8, 0xa5, 0x71, ++ 0xcb, 0xcd, 0x63, 0x32, 0x55, 0xfb, 0x31, 0xf0, ++ 0x38, 0xf5, 0xbe, 0x78, 0xe4, 0x45, 0xce, 0x1b, ++ 0x6a, 0x5b, 0x0e, 0xf4, 0x16, 0xe4, 0xb1, 0x3d, ++ 0xf6, 0x63, 0x7b, 0xa7, 0x0c, 0xde, 0x6f, 0x8f, ++ 0x74, 0xdf, 0xe0, 0x1e, 0x9d, 0xce, 0x8f, 0x24, ++ 0xef, 0x23, 0x35, 0x33, 0x7b, 0x83, 0x34, 0x23, ++ 0x58, 0x74, 0x14, 0x77, 0x1f, 0xc2, 0x4f, 0x4e, ++ 0xc6, 0x89, 0xf9, 0x52, 0x09, 0x37, 0x64, 0x14, ++ 0xc4, 0x01, 0x6b, 0x9d, 0x77, 0xe8, 0x90, 0x5d, ++ 0xa8, 0x4a, 0x2a, 0xef, 0x5c, 0x7f, 0xeb, 0xbb, ++ 0xb2, 0xc6, 0x93, 0x99, 0x66, 0xdc, 0x7f, 0xd4, ++ 0x9e, 0x2a, 0xca, 0x8d, 0xdb, 0xe7, 0x20, 0xcf, ++ 0xe4, 0x73, 0xae, 0x49, 0x7d, 0x64, 0x0f, 0x0e, ++ 0x28, 0x46, 0xa9, 0xa8, 0x32, 0xe4, 0x0e, 0xf6, ++ 0x51, 0x53, 0xb8, 0x3c, 0xb1, 0xff, 0xa3, 0x33, ++ 0x41, 0x75, 0xff, 0xf1, 0x6f, 0xf1, 0xfb, 0xbb, ++ 0x83, 0x7f, 0x06, 0x9b, 0xe7, 0x1b, 0x0a, 0xe0, ++ 0x5c, 0x33, 0x60, 0x5b, 0xdb, 0x5b, 0xed, 0xfe, ++ 0xa5, 0x16, 0x19, 0x72, 0xa3, 0x64, 0x23, 0x00, ++ 0x02, 0xc7, 0xf3, 0x6a, 0x81, 0x3e, 0x44, 0x1d, ++ 0x79, 0x15, 0x5f, 0x9a, 0xde, 0xe2, 0xfd, 0x1b, ++ 0x73, 0xc1, 0xbc, 0x23, 0xba, 0x31, 0xd2, 0x50, ++ 0xd5, 0xad, 0x7f, 0x74, 0xa7, 0xc9, 0xf8, 0x3e, ++ 0x2b, 0x26, 0x10, 0xf6, 0x03, 0x36, 0x74, 0xe4, ++ 0x0e, 0x6a, 0x72, 0xb7, 0x73, 0x0a, 0x42, 0x28, ++ 0xc2, 0xad, 0x5e, 0x03, 0xbe, 0xb8, 0x0b, 0xa8, ++ 0x5b, 0xd4, 0xb8, 0xba, 0x52, 0x89, 0xb1, 0x9b, ++ 0xc1, 0xc3, 0x65, 0x87, 0xed, 0xa5, 0xf4, 0x86, ++ 0xfd, 0x41, 0x80, 0x91, 0x27, 0x59, 0x53, 0x67, ++ 0x15, 0x78, 0x54, 0x8b, 0x2d, 0x3d, 0xc7, 0xff, ++ 0x02, 0x92, 0x07, 0x5f, 0x7a, 0x4b, 0x60, 0x59, ++ 0x3c, 0x6f, 0x5c, 0xd8, 0xec, 0x95, 0xd2, 0xfe, ++ 0xa0, 0x3b, 0xd8, 0x3f, 0xd1, 0x69, 0xa6, 0xd6, ++ 0x41, 0xb2, 0xf4, 0x4d, 0x12, 0xf4, 0x58, 0x3e, ++ 0x66, 0x64, 0x80, 0x31, 0x9b, 0xa8, 0x4c, 0x8b, ++ 0x07, 0xb2, 0xec, 0x66, 0x94, 0x66, 0x47, 0x50, ++ 0x50, 0x5f, 0x18, 0x0b, 0x0e, 0xd6, 0xc0, 0x39, ++ 0x21, 0x13, 0x9e, 0x33, 0xbc, 0x79, 0x36, 0x02, ++ 0x96, 0x70, 0xf0, 0x48, 0x67, 0x2f, 0x26, 0xe9, ++ 0x6d, 0x10, 0xbb, 0xd6, 0x3f, 0xd1, 0x64, 0x7a, ++ 0x2e, 0xbe, 0x0c, 0x61, 0xf0, 0x75, 0x42, 0x38, ++ 0x23, 0xb1, 0x9e, 0x9f, 0x7c, 0x67, 0x66, 0xd9, ++ 0x58, 0x9a, 0xf1, 0xbb, 0x41, 0x2a, 0x8d, 0x65, ++ 0x84, 0x94, 0xfc, 0xdc, 0x6a, 0x50, 0x64, 0xdb, ++ 0x56, 0x33, 0x76, 0x00, 0x10, 0xed, 0xbe, 0xd2, ++ 0x12, 0xf6, 0xf6, 0x1b, 0xa2, 0x16, 0xde, 0xae, ++ 0x31, 0x95, 0xdd, 0xb1, 0x08, 0x7e, 0x4e, 0xee, ++ 0xe7, 0xf9, 0xa5, 0xfb, 0x5b, 0x61, 0x43, 0x00, ++ 0x40, 0xf6, 0x7e, 0x02, 0x04, 0x32, 0x4e, 0x0c, ++ 0xe2, 0x66, 0x0d, 0xd7, 0x07, 0x98, 0x0e, 0xf8, ++ 0x72, 0x34, 0x6d, 0x95, 0x86, 0xd7, 0xcb, 0x31, ++ 0x54, 0x47, 0xd0, 0x38, 0x29, 0x9c, 0x5a, 0x68, ++ 0xd4, 0x87, 0x76, 0xc9, 0xe7, 0x7e, 0xe3, 0xf4, ++ 0x81, 0x6d, 0x18, 0xcb, 0xc9, 0x05, 0xaf, 0xa0, ++ 0xfb, 0x66, 0xf7, 0xf1, 0x1c, 0xc6, 0x14, 0x11, ++ 0x4f, 0x2b, 0x79, 0x42, 0x8b, 0xbc, 0xac, 0xe7, ++ 0x6c, 0xfe, 0x0f, 0x58, 0xe7, 0x7c, 0x78, 0x39, ++ 0x30, 0xb0, 0x66, 0x2c, 0x9b, 0x6d, 0x3a, 0xe1, ++ 0xcf, 0xc9, 0xa4, 0x0e, 0x6d, 0x6d, 0x8a, 0xa1, ++ 0x3a, 0xe7, 0x28, 0xd4, 0x78, 0x4c, 0xa6, 0xa2, ++ 0x2a, 0xa6, 0x03, 0x30, 0xd7, 0xa8, 0x25, 0x66, ++ 0x87, 0x2f, 0x69, 0x5c, 0x4e, 0xdd, 0xa5, 0x49, ++ 0x5d, 0x37, 0x4a, 0x59, 0xc4, 0xaf, 0x1f, 0xa2, ++ 0xe4, 0xf8, 0xa6, 0x12, 0x97, 0xd5, 0x79, 0xf5, ++ 0xe2, 0x4a, 0x2b, 0x5f, 0x61, 0xe4, 0x9e, 0xe3, ++ 0xee, 0xb8, 0xa7, 0x5b, 0x2f, 0xf4, 0x9e, 0x6c, ++ 0xfb, 0xd1, 0xc6, 0x56, 0x77, 0xba, 0x75, 0xaa, ++ 0x3d, 0x1a, 0xa8, 0x0b, 0xb3, 0x68, 0x24, 0x00, ++ 0x10, 0x7f, 0xfd, 0xd7, 0xa1, 0x8d, 0x83, 0x54, ++ 0x4f, 0x1f, 0xd8, 0x2a, 0xbe, 0x8a, 0x0c, 0x87, ++ 0xab, 0xa2, 0xde, 0xc3, 0x39, 0xbf, 0x09, 0x03, ++ 0xa5, 0xf3, 0x05, 0x28, 0xe1, 0xe1, 0xee, 0x39, ++ 0x70, 0x9c, 0xd8, 0x81, 0x12, 0x1e, 0x02, 0x40, ++ 0xd2, 0x6e, 0xf0, 0xeb, 0x1b, 0x3d, 0x22, 0xc6, ++ 0xe5, 0xe3, 0xb4, 0x5a, 0x98, 0xbb, 0xf0, 0x22, ++ 0x28, 0x8d, 0xe5, 0xd3, 0x16, 0x48, 0x24, 0xa5, ++ 0xe6, 0x66, 0x0c, 0xf9, 0x08, 0xf9, 0x7e, 0x1e, ++ 0xe1, 0x28, 0x26, 0x22, 0xc7, 0xc7, 0x0a, 0x32, ++ 0x47, 0xfa, 0xa3, 0xbe, 0x3c, 0xc4, 0xc5, 0x53, ++ 0x0a, 0xd5, 0x94, 0x4a, 0xd7, 0x93, 0xd8, 0x42, ++ 0x99, 0xb9, 0x0a, 0xdb, 0x56, 0xf7, 0xb9, 0x1c, ++ 0x53, 0x4f, 0xfa, 0xd3, 0x74, 0xad, 0xd9, 0x68, ++ 0xf1, 0x1b, 0xdf, 0x61, 0xc6, 0x5e, 0xa8, 0x48, ++ 0xfc, 0xd4, 0x4a, 0x4c, 0x3c, 0x32, 0xf7, 0x1c, ++ 0x96, 0x21, 0x9b, 0xf9, 0xa3, 0xcc, 0x5a, 0xce, ++ 0xd5, 0xd7, 0x08, 0x24, 0xf6, 0x1c, 0xfd, 0xdd, ++ 0x38, 0xc2, 0x32, 0xe9, 0xb8, 0xe7, 0xb6, 0xfa, ++ 0x9d, 0x45, 0x13, 0x2c, 0x83, 0xfd, 0x4a, 0x69, ++ 0x82, 0xcd, 0xdc, 0xb3, 0x76, 0x0c, 0x9e, 0xd8, ++ 0xf4, 0x1b, 0x45, 0x15, 0xb4, 0x97, 0xe7, 0x58, ++ 0x34, 0xe2, 0x03, 0x29, 0x5a, 0xbf, 0xb6, 0xe0, ++ 0x5d, 0x13, 0xd9, 0x2b, 0xb4, 0x80, 0xb2, 0x45, ++ 0x81, 0x6a, 0x2e, 0x6c, 0x89, 0x7d, 0xee, 0xbb, ++ 0x52, 0xdd, 0x1f, 0x18, 0xe7, 0x13, 0x6b, 0x33, ++ 0x0e, 0xea, 0x36, 0x92, 0x77, 0x7b, 0x6d, 0x9c, ++ 0x5a, 0x5f, 0x45, 0x7b, 0x7b, 0x35, 0x62, 0x23, ++ 0xd1, 0xbf, 0x0f, 0xd0, 0x08, 0x1b, 0x2b, 0x80, ++ 0x6b, 0x7e, 0xf1, 0x21, 0x47, 0xb0, 0x57, 0xd1, ++ 0x98, 0x72, 0x90, 0x34, 0x1c, 0x20, 0x04, 0xff, ++ 0x3d, 0x5c, 0xee, 0x0e, 0x57, 0x5f, 0x6f, 0x24, ++ 0x4e, 0x3c, 0xea, 0xfc, 0xa5, 0xa9, 0x83, 0xc9, ++ 0x61, 0xb4, 0x51, 0x24, 0xf8, 0x27, 0x5e, 0x46, ++ 0x8c, 0xb1, 0x53, 0x02, 0x96, 0x35, 0xba, 0xb8, ++ 0x4c, 0x71, 0xd3, 0x15, 0x59, 0x35, 0x22, 0x20, ++ 0xad, 0x03, 0x9f, 0x66, 0x44, 0x3b, 0x9c, 0x35, ++ 0x37, 0x1f, 0x9b, 0xbb, 0xf3, 0xdb, 0x35, 0x63, ++ 0x30, 0x64, 0xaa, 0xa2, 0x06, 0xa8, 0x5d, 0xbb, ++ 0xe1, 0x9f, 0x70, 0xec, 0x82, 0x11, 0x06, 0x36, ++ 0xec, 0x8b, 0x69, 0x66, 0x24, 0x44, 0xc9, 0x4a, ++ 0x57, 0xbb, 0x9b, 0x78, 0x13, 0xce, 0x9c, 0x0c, ++ 0xba, 0x92, 0x93, 0x63, 0xb8, 0xe2, 0x95, 0x0f, ++ 0x0f, 0x16, 0x39, 0x52, 0xfd, 0x3a, 0x6d, 0x02, ++ 0x4b, 0xdf, 0x13, 0xd3, 0x2a, 0x22, 0xb4, 0x03, ++ 0x7c, 0x54, 0x49, 0x96, 0x68, 0x54, 0x10, 0xfa, ++ 0xef, 0xaa, 0x6c, 0xe8, 0x22, 0xdc, 0x71, 0x16, ++ 0x13, 0x1a, 0xf6, 0x28, 0xe5, 0x6d, 0x77, 0x3d, ++ 0xcd, 0x30, 0x63, 0xb1, 0x70, 0x52, 0xa1, 0xc5, ++ 0x94, 0x5f, 0xcf, 0xe8, 0xb8, 0x26, 0x98, 0xf7, ++ 0x06, 0xa0, 0x0a, 0x70, 0xfa, 0x03, 0x80, 0xac, ++ 0xc1, 0xec, 0xd6, 0x4c, 0x54, 0xd7, 0xfe, 0x47, ++ 0xb6, 0x88, 0x4a, 0xf7, 0x71, 0x24, 0xee, 0xf3, ++ 0xd2, 0xc2, 0x4a, 0x7f, 0xfe, 0x61, 0xc7, 0x35, ++ 0xc9, 0x37, 0x67, 0xcb, 0x24, 0x35, 0xda, 0x7e, ++ 0xca, 0x5f, 0xf3, 0x8d, 0xd4, 0x13, 0x8e, 0xd6, ++ 0xcb, 0x4d, 0x53, 0x8f, 0x53, 0x1f, 0xc0, 0x74, ++ 0xf7, 0x53, 0xb9, 0x5e, 0x23, 0x37, 0xba, 0x6e, ++ 0xe3, 0x9d, 0x07, 0x55, 0x25, 0x7b, 0xe6, 0x2a, ++ 0x64, 0xd1, 0x32, 0xdd, 0x54, 0x1b, 0x4b, 0xc0, ++ 0xe1, 0xd7, 0x69, 0x58, 0xf8, 0x93, 0x29, 0xc4, ++ 0xdd, 0x23, 0x2f, 0xa5, 0xfc, 0x9d, 0x7e, 0xf8, ++ 0xd4, 0x90, 0xcd, 0x82, 0x55, 0xdc, 0x16, 0x16, ++ 0x9f, 0x07, 0x52, 0x9b, 0x9d, 0x25, 0xed, 0x32, ++ 0xc5, 0x7b, 0xdf, 0xf6, 0x83, 0x46, 0x3d, 0x65, ++ 0xb7, 0xef, 0x87, 0x7a, 0x12, 0x69, 0x8f, 0x06, ++ 0x7c, 0x51, 0x15, 0x4a, 0x08, 0xe8, 0xac, 0x9a, ++ 0x0c, 0x24, 0xa7, 0x27, 0xd8, 0x46, 0x2f, 0xe7, ++ 0x01, 0x0e, 0x1c, 0xc6, 0x91, 0xb0, 0x6e, 0x85, ++ 0x65, 0xf0, 0x29, 0x0d, 0x2e, 0x6b, 0x3b, 0xfb, ++ 0x4b, 0xdf, 0xe4, 0x80, 0x93, 0x03, 0x66, 0x46, ++ 0x3e, 0x8a, 0x6e, 0xf3, 0x5e, 0x4d, 0x62, 0x0e, ++ 0x49, 0x05, 0xaf, 0xd4, 0xf8, 0x21, 0x20, 0x61, ++ 0x1d, 0x39, 0x17, 0xf4, 0x61, 0x47, 0x95, 0xfb, ++ 0x15, 0x2e, 0xb3, 0x4f, 0xd0, 0x5d, 0xf5, 0x7d, ++ 0x40, 0xda, 0x90, 0x3c, 0x6b, 0xcb, 0x17, 0x00, ++ 0x13, 0x3b, 0x64, 0x34, 0x1b, 0xf0, 0xf2, 0xe5, ++ 0x3b, 0xb2, 0xc7, 0xd3, 0x5f, 0x3a, 0x44, 0xa6, ++ 0x9b, 0xb7, 0x78, 0x0e, 0x42, 0x5d, 0x4c, 0xc1, ++ 0xe9, 0xd2, 0xcb, 0xb7, 0x78, 0xd1, 0xfe, 0x9a, ++ 0xb5, 0x07, 0xe9, 0xe0, 0xbe, 0xe2, 0x8a, 0xa7, ++ 0x01, 0x83, 0x00, 0x8c, 0x5c, 0x08, 0xe6, 0x63, ++ 0x12, 0x92, 0xb7, 0xb7, 0xa6, 0x19, 0x7d, 0x38, ++ 0x13, 0x38, 0x92, 0x87, 0x24, 0xf9, 0x48, 0xb3, ++ 0x5e, 0x87, 0x6a, 0x40, 0x39, 0x5c, 0x3f, 0xed, ++ 0x8f, 0xee, 0xdb, 0x15, 0x82, 0x06, 0xda, 0x49, ++ 0x21, 0x2b, 0xb5, 0xbf, 0x32, 0x7c, 0x9f, 0x42, ++ 0x28, 0x63, 0xcf, 0xaf, 0x1e, 0xf8, 0xc6, 0xa0, ++ 0xd1, 0x02, 0x43, 0x57, 0x62, 0xec, 0x9b, 0x0f, ++ 0x01, 0x9e, 0x71, 0xd8, 0x87, 0x9d, 0x01, 0xc1, ++ 0x58, 0x77, 0xd9, 0xaf, 0xb1, 0x10, 0x7e, 0xdd, ++ 0xa6, 0x50, 0x96, 0xe5, 0xf0, 0x72, 0x00, 0x6d, ++ 0x4b, 0xf8, 0x2a, 0x8f, 0x19, 0xf3, 0x22, 0x88, ++ 0x11, 0x4a, 0x8b, 0x7c, 0xfd, 0xb7, 0xed, 0xe1, ++ 0xf6, 0x40, 0x39, 0xe0, 0xe9, 0xf6, 0x3d, 0x25, ++ 0xe6, 0x74, 0x3c, 0x58, 0x57, 0x7f, 0xe1, 0x22, ++ 0x96, 0x47, 0x31, 0x91, 0xba, 0x70, 0x85, 0x28, ++ 0x6b, 0x9f, 0x6e, 0x25, 0xac, 0x23, 0x66, 0x2f, ++ 0x29, 0x88, 0x28, 0xce, 0x8c, 0x5c, 0x88, 0x53, ++ 0xd1, 0x3b, 0xcc, 0x6a, 0x51, 0xb2, 0xe1, 0x28, ++ 0x3f, 0x91, 0xb4, 0x0d, 0x00, 0x3a, 0xe3, 0xf8, ++ 0xc3, 0x8f, 0xd7, 0x96, 0x62, 0x0e, 0x2e, 0xfc, ++ 0xc8, 0x6c, 0x77, 0xa6, 0x1d, 0x22, 0xc1, 0xb8, ++ 0xe6, 0x61, 0xd7, 0x67, 0x36, 0x13, 0x7b, 0xbb, ++ 0x9b, 0x59, 0x09, 0xa6, 0xdf, 0xf7, 0x6b, 0xa3, ++ 0x40, 0x1a, 0xf5, 0x4f, 0xb4, 0xda, 0xd3, 0xf3, ++ 0x81, 0x93, 0xc6, 0x18, 0xd9, 0x26, 0xee, 0xac, ++ 0xf0, 0xaa, 0xdf, 0xc5, 0x9c, 0xca, 0xc2, 0xa2, ++ 0xcc, 0x7b, 0x5c, 0x24, 0xb0, 0xbc, 0xd0, 0x6a, ++ 0x4d, 0x89, 0x09, 0xb8, 0x07, 0xfe, 0x87, 0xad, ++ 0x0a, 0xea, 0xb8, 0x42, 0xf9, 0x5e, 0xb3, 0x3e, ++ 0x36, 0x4c, 0xaf, 0x75, 0x9e, 0x1c, 0xeb, 0xbd, ++ 0xbc, 0xbb, 0x80, 0x40, 0xa7, 0x3a, 0x30, 0xbf, ++ 0xa8, 0x44, 0xf4, 0xeb, 0x38, 0xad, 0x29, 0xba, ++ 0x23, 0xed, 0x41, 0x0c, 0xea, 0xd2, 0xbb, 0x41, ++ 0x18, 0xd6, 0xb9, 0xba, 0x65, 0x2b, 0xa3, 0x91, ++ 0x6d, 0x1f, 0xa9, 0xf4, 0xd1, 0x25, 0x8d, 0x4d, ++ 0x38, 0xff, 0x64, 0xa0, 0xec, 0xde, 0xa6, 0xb6, ++ 0x79, 0xab, 0x8e, 0x33, 0x6c, 0x47, 0xde, 0xaf, ++ 0x94, 0xa4, 0xa5, 0x86, 0x77, 0x55, 0x09, 0x92, ++ 0x81, 0x31, 0x76, 0xc7, 0x34, 0x22, 0x89, 0x8e, ++ 0x3d, 0x26, 0x26, 0xd7, 0xfc, 0x1e, 0x16, 0x72, ++ 0x13, 0x33, 0x63, 0xd5, 0x22, 0xbe, 0xb8, 0x04, ++ 0x34, 0x84, 0x41, 0xbb, 0x80, 0xd0, 0x9f, 0x46, ++ 0x48, 0x07, 0xa7, 0xfc, 0x2b, 0x3a, 0x75, 0x55, ++ 0x8c, 0xc7, 0x6a, 0xbd, 0x7e, 0x46, 0x08, 0x84, ++ 0x0f, 0xd5, 0x74, 0xc0, 0x82, 0x8e, 0xaa, 0x61, ++ 0x05, 0x01, 0xb2, 0x47, 0x6e, 0x20, 0x6a, 0x2d, ++ 0x58, 0x70, 0x48, 0x32, 0xa7, 0x37, 0xd2, 0xb8, ++ 0x82, 0x1a, 0x51, 0xb9, 0x61, 0xdd, 0xfd, 0x9d, ++ 0x6b, 0x0e, 0x18, 0x97, 0xf8, 0x45, 0x5f, 0x87, ++ 0x10, 0xcf, 0x34, 0x72, 0x45, 0x26, 0x49, 0x70, ++ 0xe7, 0xa3, 0x78, 0xe0, 0x52, 0x89, 0x84, 0x94, ++ 0x83, 0x82, 0xc2, 0x69, 0x8f, 0xe3, 0xe1, 0x3f, ++ 0x60, 0x74, 0x88, 0xc4, 0xf7, 0x75, 0x2c, 0xfb, ++ 0xbd, 0xb6, 0xc4, 0x7e, 0x10, 0x0a, 0x6c, 0x90, ++ 0x04, 0x9e, 0xc3, 0x3f, 0x59, 0x7c, 0xce, 0x31, ++ 0x18, 0x60, 0x57, 0x73, 0x46, 0x94, 0x7d, 0x06, ++ 0xa0, 0x6d, 0x44, 0xec, 0xa2, 0x0a, 0x9e, 0x05, ++ 0x15, 0xef, 0xca, 0x5c, 0xbf, 0x00, 0xeb, 0xf7, ++ 0x3d, 0x32, 0xd4, 0xa5, 0xef, 0x49, 0x89, 0x5e, ++ 0x46, 0xb0, 0xa6, 0x63, 0x5b, 0x8a, 0x73, 0xae, ++ 0x6f, 0xd5, 0x9d, 0xf8, 0x4f, 0x40, 0xb5, 0xb2, ++ 0x6e, 0xd3, 0xb6, 0x01, 0xa9, 0x26, 0xa2, 0x21, ++ 0xcf, 0x33, 0x7a, 0x3a, 0xa4, 0x23, 0x13, 0xb0, ++ 0x69, 0x6a, 0xee, 0xce, 0xd8, 0x9d, 0x01, 0x1d, ++ 0x50, 0xc1, 0x30, 0x6c, 0xb1, 0xcd, 0xa0, 0xf0, ++ 0xf0, 0xa2, 0x64, 0x6f, 0xbb, 0xbf, 0x5e, 0xe6, ++ 0xab, 0x87, 0xb4, 0x0f, 0x4f, 0x15, 0xaf, 0xb5, ++ 0x25, 0xa1, 0xb2, 0xd0, 0x80, 0x2c, 0xfb, 0xf9, ++ 0xfe, 0xd2, 0x33, 0xbb, 0x76, 0xfe, 0x7c, 0xa8, ++ 0x66, 0xf7, 0xe7, 0x85, 0x9f, 0x1f, 0x85, 0x57, ++ 0x88, 0xe1, 0xe9, 0x63, 0xe4, 0xd8, 0x1c, 0xa1, ++ 0xfb, 0xda, 0x44, 0x05, 0x2e, 0x1d, 0x3a, 0x1c, ++ 0xff, 0xc8, 0x3b, 0xc0, 0xfe, 0xda, 0x22, 0x0b, ++ 0x43, 0xd6, 0x88, 0x39, 0x4c, 0x4a, 0xa6, 0x69, ++ 0x18, 0x93, 0x42, 0x4e, 0xb5, 0xcc, 0x66, 0x0d, ++ 0x09, 0xf8, 0x1e, 0x7c, 0xd3, 0x3c, 0x99, 0x0d, ++ 0x50, 0x1d, 0x62, 0xe9, 0x57, 0x06, 0xbf, 0x19, ++ 0x88, 0xdd, 0xad, 0x7b, 0x4f, 0xf9, 0xc7, 0x82, ++ 0x6d, 0x8d, 0xc8, 0xc4, 0xc5, 0x78, 0x17, 0x20, ++ 0x15, 0xc5, 0x52, 0x41, 0xcf, 0x5b, 0xd6, 0x7f, ++ 0x94, 0x02, 0x41, 0xe0, 0x40, 0x22, 0x03, 0x5e, ++ 0xd1, 0x53, 0xd4, 0x86, 0xd3, 0x2c, 0x9f, 0x0f, ++ 0x96, 0xe3, 0x6b, 0x9a, 0x76, 0x32, 0x06, 0x47, ++ 0x4b, 0x11, 0xb3, 0xdd, 0x03, 0x65, 0xbd, 0x9b, ++ 0x01, 0xda, 0x9c, 0xb9, 0x7e, 0x3f, 0x6a, 0xc4, ++ 0x7b, 0xea, 0xd4, 0x3c, 0xb9, 0xfb, 0x5c, 0x6b, ++ 0x64, 0x33, 0x52, 0xba, 0x64, 0x78, 0x8f, 0xa4, ++ 0xaf, 0x7a, 0x61, 0x8d, 0xbc, 0xc5, 0x73, 0xe9, ++ 0x6b, 0x58, 0x97, 0x4b, 0xbf, 0x63, 0x22, 0xd3, ++ 0x37, 0x02, 0x54, 0xc5, 0xb9, 0x16, 0x4a, 0xf0, ++ 0x19, 0xd8, 0x94, 0x57, 0xb8, 0x8a, 0xb3, 0x16, ++ 0x3b, 0xd0, 0x84, 0x8e, 0x67, 0xa6, 0xa3, 0x7d, ++ 0x78, 0xec, 0x00 ++}; ++static const u8 dec_assoc012[] __initconst = { ++ 0xb1, 0x69, 0x83, 0x87, 0x30, 0xaa, 0x5d, 0xb8, ++ 0x77, 0xe8, 0x21, 0xff, 0x06, 0x59, 0x35, 0xce, ++ 0x75, 0xfe, 0x38, 0xef, 0xb8, 0x91, 0x43, 0x8c, ++ 0xcf, 0x70, 0xdd, 0x0a, 0x68, 0xbf, 0xd4, 0xbc, ++ 0x16, 0x76, 0x99, 0x36, 0x1e, 0x58, 0x79, 0x5e, ++ 0xd4, 0x29, 0xf7, 0x33, 0x93, 0x48, 0xdb, 0x5f, ++ 0x01, 0xae, 0x9c, 0xb6, 0xe4, 0x88, 0x6d, 0x2b, ++ 0x76, 0x75, 0xe0, 0xf3, 0x74, 0xe2, 0xc9 ++}; ++static const u8 dec_nonce012[] __initconst = { ++ 0x05, 0xa3, 0x93, 0xed, 0x30, 0xc5, 0xa2, 0x06 ++}; ++static const u8 dec_key012[] __initconst = { ++ 0xb3, 0x35, 0x50, 0x03, 0x54, 0x2e, 0x40, 0x5e, ++ 0x8f, 0x59, 0x8e, 0xc5, 0x90, 0xd5, 0x27, 0x2d, ++ 0xba, 0x29, 0x2e, 0xcb, 0x1b, 0x70, 0x44, 0x1e, ++ 0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64 ++}; ++ ++static const u8 dec_input013[] __initconst = { ++ 0x52, 0x34, 0xb3, 0x65, 0x3b, 0xb7, 0xe5, 0xd3, ++ 0xab, 0x49, 0x17, 0x60, 0xd2, 0x52, 0x56, 0xdf, ++ 0xdf, 0x34, 0x56, 0x82, 0xe2, 0xbe, 0xe5, 0xe1, ++ 0x28, 0xd1, 0x4e, 0x5f, 0x4f, 0x01, 0x7d, 0x3f, ++ 0x99, 0x6b, 0x30, 0x6e, 0x1a, 0x7c, 0x4c, 0x8e, ++ 0x62, 0x81, 0xae, 0x86, 0x3f, 0x6b, 0xd0, 0xb5, ++ 0xa9, 0xcf, 0x50, 0xf1, 0x02, 0x12, 0xa0, 0x0b, ++ 0x24, 0xe9, 0xe6, 0x72, 0x89, 0x2c, 0x52, 0x1b, ++ 0x34, 0x38, 0xf8, 0x75, 0x5f, 0xa0, 0x74, 0xe2, ++ 0x99, 0xdd, 0xa6, 0x4b, 0x14, 0x50, 0x4e, 0xf1, ++ 0xbe, 0xd6, 0x9e, 0xdb, 0xb2, 0x24, 0x27, 0x74, ++ 0x12, 0x4a, 0x78, 0x78, 0x17, 0xa5, 0x58, 0x8e, ++ 0x2f, 0xf9, 0xf4, 0x8d, 0xee, 0x03, 0x88, 0xae, ++ 0xb8, 0x29, 0xa1, 0x2f, 0x4b, 0xee, 0x92, 0xbd, ++ 0x87, 0xb3, 0xce, 0x34, 0x21, 0x57, 0x46, 0x04, ++ 0x49, 0x0c, 0x80, 0xf2, 0x01, 0x13, 0xa1, 0x55, ++ 0xb3, 0xff, 0x44, 0x30, 0x3c, 0x1c, 0xd0, 0xef, ++ 0xbc, 0x18, 0x74, 0x26, 0xad, 0x41, 0x5b, 0x5b, ++ 0x3e, 0x9a, 0x7a, 0x46, 0x4f, 0x16, 0xd6, 0x74, ++ 0x5a, 0xb7, 0x3a, 0x28, 0x31, 0xd8, 0xae, 0x26, ++ 0xac, 0x50, 0x53, 0x86, 0xf2, 0x56, 0xd7, 0x3f, ++ 0x29, 0xbc, 0x45, 0x68, 0x8e, 0xcb, 0x98, 0x64, ++ 0xdd, 0xc9, 0xba, 0xb8, 0x4b, 0x7b, 0x82, 0xdd, ++ 0x14, 0xa7, 0xcb, 0x71, 0x72, 0x00, 0x5c, 0xad, ++ 0x7b, 0x6a, 0x89, 0xa4, 0x3d, 0xbf, 0xb5, 0x4b, ++ 0x3e, 0x7c, 0x5a, 0xcf, 0xb8, 0xa1, 0xc5, 0x6e, ++ 0xc8, 0xb6, 0x31, 0x57, 0x7b, 0xdf, 0xa5, 0x7e, ++ 0xb1, 0xd6, 0x42, 0x2a, 0x31, 0x36, 0xd1, 0xd0, ++ 0x3f, 0x7a, 0xe5, 0x94, 0xd6, 0x36, 0xa0, 0x6f, ++ 0xb7, 0x40, 0x7d, 0x37, 0xc6, 0x55, 0x7c, 0x50, ++ 0x40, 0x6d, 0x29, 0x89, 0xe3, 0x5a, 0xae, 0x97, ++ 0xe7, 0x44, 0x49, 0x6e, 0xbd, 0x81, 0x3d, 0x03, ++ 0x93, 0x06, 0x12, 0x06, 0xe2, 0x41, 0x12, 0x4a, ++ 0xf1, 0x6a, 0xa4, 0x58, 0xa2, 0xfb, 0xd2, 0x15, ++ 0xba, 0xc9, 0x79, 0xc9, 0xce, 0x5e, 0x13, 0xbb, ++ 0xf1, 0x09, 0x04, 0xcc, 0xfd, 0xe8, 0x51, 0x34, ++ 0x6a, 0xe8, 0x61, 0x88, 0xda, 0xed, 0x01, 0x47, ++ 0x84, 0xf5, 0x73, 0x25, 0xf9, 0x1c, 0x42, 0x86, ++ 0x07, 0xf3, 0x5b, 0x1a, 0x01, 0xb3, 0xeb, 0x24, ++ 0x32, 0x8d, 0xf6, 0xed, 0x7c, 0x4b, 0xeb, 0x3c, ++ 0x36, 0x42, 0x28, 0xdf, 0xdf, 0xb6, 0xbe, 0xd9, ++ 0x8c, 0x52, 0xd3, 0x2b, 0x08, 0x90, 0x8c, 0xe7, ++ 0x98, 0x31, 0xe2, 0x32, 0x8e, 0xfc, 0x11, 0x48, ++ 0x00, 0xa8, 0x6a, 0x42, 0x4a, 0x02, 0xc6, 0x4b, ++ 0x09, 0xf1, 0xe3, 0x49, 0xf3, 0x45, 0x1f, 0x0e, ++ 0xbc, 0x56, 0xe2, 0xe4, 0xdf, 0xfb, 0xeb, 0x61, ++ 0xfa, 0x24, 0xc1, 0x63, 0x75, 0xbb, 0x47, 0x75, ++ 0xaf, 0xe1, 0x53, 0x16, 0x96, 0x21, 0x85, 0x26, ++ 0x11, 0xb3, 0x76, 0xe3, 0x23, 0xa1, 0x6b, 0x74, ++ 0x37, 0xd0, 0xde, 0x06, 0x90, 0x71, 0x5d, 0x43, ++ 0x88, 0x9b, 0x00, 0x54, 0xa6, 0x75, 0x2f, 0xa1, ++ 0xc2, 0x0b, 0x73, 0x20, 0x1d, 0xb6, 0x21, 0x79, ++ 0x57, 0x3f, 0xfa, 0x09, 0xbe, 0x8a, 0x33, 0xc3, ++ 0x52, 0xf0, 0x1d, 0x82, 0x31, 0xd1, 0x55, 0xb5, ++ 0x6c, 0x99, 0x25, 0xcf, 0x5c, 0x32, 0xce, 0xe9, ++ 0x0d, 0xfa, 0x69, 0x2c, 0xd5, 0x0d, 0xc5, 0x6d, ++ 0x86, 0xd0, 0x0c, 0x3b, 0x06, 0x50, 0x79, 0xe8, ++ 0xc3, 0xae, 0x04, 0xe6, 0xcd, 0x51, 0xe4, 0x26, ++ 0x9b, 0x4f, 0x7e, 0xa6, 0x0f, 0xab, 0xd8, 0xe5, ++ 0xde, 0xa9, 0x00, 0x95, 0xbe, 0xa3, 0x9d, 0x5d, ++ 0xb2, 0x09, 0x70, 0x18, 0x1c, 0xf0, 0xac, 0x29, ++ 0x23, 0x02, 0x29, 0x28, 0xd2, 0x74, 0x35, 0x57, ++ 0x62, 0x0f, 0x24, 0xea, 0x5e, 0x33, 0xc2, 0x92, ++ 0xf3, 0x78, 0x4d, 0x30, 0x1e, 0xa1, 0x99, 0xa9, ++ 0x82, 0xb0, 0x42, 0x31, 0x8d, 0xad, 0x8a, 0xbc, ++ 0xfc, 0xd4, 0x57, 0x47, 0x3e, 0xb4, 0x50, 0xdd, ++ 0x6e, 0x2c, 0x80, 0x4d, 0x22, 0xf1, 0xfb, 0x57, ++ 0xc4, 0xdd, 0x17, 0xe1, 0x8a, 0x36, 0x4a, 0xb3, ++ 0x37, 0xca, 0xc9, 0x4e, 0xab, 0xd5, 0x69, 0xc4, ++ 0xf4, 0xbc, 0x0b, 0x3b, 0x44, 0x4b, 0x29, 0x9c, ++ 0xee, 0xd4, 0x35, 0x22, 0x21, 0xb0, 0x1f, 0x27, ++ 0x64, 0xa8, 0x51, 0x1b, 0xf0, 0x9f, 0x19, 0x5c, ++ 0xfb, 0x5a, 0x64, 0x74, 0x70, 0x45, 0x09, 0xf5, ++ 0x64, 0xfe, 0x1a, 0x2d, 0xc9, 0x14, 0x04, 0x14, ++ 0xcf, 0xd5, 0x7d, 0x60, 0xaf, 0x94, 0x39, 0x94, ++ 0xe2, 0x7d, 0x79, 0x82, 0xd0, 0x65, 0x3b, 0x6b, ++ 0x9c, 0x19, 0x84, 0xb4, 0x6d, 0xb3, 0x0c, 0x99, ++ 0xc0, 0x56, 0xa8, 0xbd, 0x73, 0xce, 0x05, 0x84, ++ 0x3e, 0x30, 0xaa, 0xc4, 0x9b, 0x1b, 0x04, 0x2a, ++ 0x9f, 0xd7, 0x43, 0x2b, 0x23, 0xdf, 0xbf, 0xaa, ++ 0xd5, 0xc2, 0x43, 0x2d, 0x70, 0xab, 0xdc, 0x75, ++ 0xad, 0xac, 0xf7, 0xc0, 0xbe, 0x67, 0xb2, 0x74, ++ 0xed, 0x67, 0x10, 0x4a, 0x92, 0x60, 0xc1, 0x40, ++ 0x50, 0x19, 0x8a, 0x8a, 0x8c, 0x09, 0x0e, 0x72, ++ 0xe1, 0x73, 0x5e, 0xe8, 0x41, 0x85, 0x63, 0x9f, ++ 0x3f, 0xd7, 0x7d, 0xc4, 0xfb, 0x22, 0x5d, 0x92, ++ 0x6c, 0xb3, 0x1e, 0xe2, 0x50, 0x2f, 0x82, 0xa8, ++ 0x28, 0xc0, 0xb5, 0xd7, 0x5f, 0x68, 0x0d, 0x2c, ++ 0x2d, 0xaf, 0x7e, 0xfa, 0x2e, 0x08, 0x0f, 0x1f, ++ 0x70, 0x9f, 0xe9, 0x19, 0x72, 0x55, 0xf8, 0xfb, ++ 0x51, 0xd2, 0x33, 0x5d, 0xa0, 0xd3, 0x2b, 0x0a, ++ 0x6c, 0xbc, 0x4e, 0xcf, 0x36, 0x4d, 0xdc, 0x3b, ++ 0xe9, 0x3e, 0x81, 0x7c, 0x61, 0xdb, 0x20, 0x2d, ++ 0x3a, 0xc3, 0xb3, 0x0c, 0x1e, 0x00, 0xb9, 0x7c, ++ 0xf5, 0xca, 0x10, 0x5f, 0x3a, 0x71, 0xb3, 0xe4, ++ 0x20, 0xdb, 0x0c, 0x2a, 0x98, 0x63, 0x45, 0x00, ++ 0x58, 0xf6, 0x68, 0xe4, 0x0b, 0xda, 0x13, 0x3b, ++ 0x60, 0x5c, 0x76, 0xdb, 0xb9, 0x97, 0x71, 0xe4, ++ 0xd9, 0xb7, 0xdb, 0xbd, 0x68, 0xc7, 0x84, 0x84, ++ 0xaa, 0x7c, 0x68, 0x62, 0x5e, 0x16, 0xfc, 0xba, ++ 0x72, 0xaa, 0x9a, 0xa9, 0xeb, 0x7c, 0x75, 0x47, ++ 0x97, 0x7e, 0xad, 0xe2, 0xd9, 0x91, 0xe8, 0xe4, ++ 0xa5, 0x31, 0xd7, 0x01, 0x8e, 0xa2, 0x11, 0x88, ++ 0x95, 0xb9, 0xf2, 0x9b, 0xd3, 0x7f, 0x1b, 0x81, ++ 0x22, 0xf7, 0x98, 0x60, 0x0a, 0x64, 0xa6, 0xc1, ++ 0xf6, 0x49, 0xc7, 0xe3, 0x07, 0x4d, 0x94, 0x7a, ++ 0xcf, 0x6e, 0x68, 0x0c, 0x1b, 0x3f, 0x6e, 0x2e, ++ 0xee, 0x92, 0xfa, 0x52, 0xb3, 0x59, 0xf8, 0xf1, ++ 0x8f, 0x6a, 0x66, 0xa3, 0x82, 0x76, 0x4a, 0x07, ++ 0x1a, 0xc7, 0xdd, 0xf5, 0xda, 0x9c, 0x3c, 0x24, ++ 0xbf, 0xfd, 0x42, 0xa1, 0x10, 0x64, 0x6a, 0x0f, ++ 0x89, 0xee, 0x36, 0xa5, 0xce, 0x99, 0x48, 0x6a, ++ 0xf0, 0x9f, 0x9e, 0x69, 0xa4, 0x40, 0x20, 0xe9, ++ 0x16, 0x15, 0xf7, 0xdb, 0x75, 0x02, 0xcb, 0xe9, ++ 0x73, 0x8b, 0x3b, 0x49, 0x2f, 0xf0, 0xaf, 0x51, ++ 0x06, 0x5c, 0xdf, 0x27, 0x27, 0x49, 0x6a, 0xd1, ++ 0xcc, 0xc7, 0xb5, 0x63, 0xb5, 0xfc, 0xb8, 0x5c, ++ 0x87, 0x7f, 0x84, 0xb4, 0xcc, 0x14, 0xa9, 0x53, ++ 0xda, 0xa4, 0x56, 0xf8, 0xb6, 0x1b, 0xcc, 0x40, ++ 0x27, 0x52, 0x06, 0x5a, 0x13, 0x81, 0xd7, 0x3a, ++ 0xd4, 0x3b, 0xfb, 0x49, 0x65, 0x31, 0x33, 0xb2, ++ 0xfa, 0xcd, 0xad, 0x58, 0x4e, 0x2b, 0xae, 0xd2, ++ 0x20, 0xfb, 0x1a, 0x48, 0xb4, 0x3f, 0x9a, 0xd8, ++ 0x7a, 0x35, 0x4a, 0xc8, 0xee, 0x88, 0x5e, 0x07, ++ 0x66, 0x54, 0xb9, 0xec, 0x9f, 0xa3, 0xe3, 0xb9, ++ 0x37, 0xaa, 0x49, 0x76, 0x31, 0xda, 0x74, 0x2d, ++ 0x3c, 0xa4, 0x65, 0x10, 0x32, 0x38, 0xf0, 0xde, ++ 0xd3, 0x99, 0x17, 0xaa, 0x71, 0xaa, 0x8f, 0x0f, ++ 0x8c, 0xaf, 0xa2, 0xf8, 0x5d, 0x64, 0xba, 0x1d, ++ 0xa3, 0xef, 0x96, 0x73, 0xe8, 0xa1, 0x02, 0x8d, ++ 0x0c, 0x6d, 0xb8, 0x06, 0x90, 0xb8, 0x08, 0x56, ++ 0x2c, 0xa7, 0x06, 0xc9, 0xc2, 0x38, 0xdb, 0x7c, ++ 0x63, 0xb1, 0x57, 0x8e, 0xea, 0x7c, 0x79, 0xf3, ++ 0x49, 0x1d, 0xfe, 0x9f, 0xf3, 0x6e, 0xb1, 0x1d, ++ 0xba, 0x19, 0x80, 0x1a, 0x0a, 0xd3, 0xb0, 0x26, ++ 0x21, 0x40, 0xb1, 0x7c, 0xf9, 0x4d, 0x8d, 0x10, ++ 0xc1, 0x7e, 0xf4, 0xf6, 0x3c, 0xa8, 0xfd, 0x7c, ++ 0xa3, 0x92, 0xb2, 0x0f, 0xaa, 0xcc, 0xa6, 0x11, ++ 0xfe, 0x04, 0xe3, 0xd1, 0x7a, 0x32, 0x89, 0xdf, ++ 0x0d, 0xc4, 0x8f, 0x79, 0x6b, 0xca, 0x16, 0x7c, ++ 0x6e, 0xf9, 0xad, 0x0f, 0xf6, 0xfe, 0x27, 0xdb, ++ 0xc4, 0x13, 0x70, 0xf1, 0x62, 0x1a, 0x4f, 0x79, ++ 0x40, 0xc9, 0x9b, 0x8b, 0x21, 0xea, 0x84, 0xfa, ++ 0xf5, 0xf1, 0x89, 0xce, 0xb7, 0x55, 0x0a, 0x80, ++ 0x39, 0x2f, 0x55, 0x36, 0x16, 0x9c, 0x7b, 0x08, ++ 0xbd, 0x87, 0x0d, 0xa5, 0x32, 0xf1, 0x52, 0x7c, ++ 0xe8, 0x55, 0x60, 0x5b, 0xd7, 0x69, 0xe4, 0xfc, ++ 0xfa, 0x12, 0x85, 0x96, 0xea, 0x50, 0x28, 0xab, ++ 0x8a, 0xf7, 0xbb, 0x0e, 0x53, 0x74, 0xca, 0xa6, ++ 0x27, 0x09, 0xc2, 0xb5, 0xde, 0x18, 0x14, 0xd9, ++ 0xea, 0xe5, 0x29, 0x1c, 0x40, 0x56, 0xcf, 0xd7, ++ 0xae, 0x05, 0x3f, 0x65, 0xaf, 0x05, 0x73, 0xe2, ++ 0x35, 0x96, 0x27, 0x07, 0x14, 0xc0, 0xad, 0x33, ++ 0xf1, 0xdc, 0x44, 0x7a, 0x89, 0x17, 0x77, 0xd2, ++ 0x9c, 0x58, 0x60, 0xf0, 0x3f, 0x7b, 0x2d, 0x2e, ++ 0x57, 0x95, 0x54, 0x87, 0xed, 0xf2, 0xc7, 0x4c, ++ 0xf0, 0xae, 0x56, 0x29, 0x19, 0x7d, 0x66, 0x4b, ++ 0x9b, 0x83, 0x84, 0x42, 0x3b, 0x01, 0x25, 0x66, ++ 0x8e, 0x02, 0xde, 0xb9, 0x83, 0x54, 0x19, 0xf6, ++ 0x9f, 0x79, 0x0d, 0x67, 0xc5, 0x1d, 0x7a, 0x44, ++ 0x02, 0x98, 0xa7, 0x16, 0x1c, 0x29, 0x0d, 0x74, ++ 0xff, 0x85, 0x40, 0x06, 0xef, 0x2c, 0xa9, 0xc6, ++ 0xf5, 0x53, 0x07, 0x06, 0xae, 0xe4, 0xfa, 0x5f, ++ 0xd8, 0x39, 0x4d, 0xf1, 0x9b, 0x6b, 0xd9, 0x24, ++ 0x84, 0xfe, 0x03, 0x4c, 0xb2, 0x3f, 0xdf, 0xa1, ++ 0x05, 0x9e, 0x50, 0x14, 0x5a, 0xd9, 0x1a, 0xa2, ++ 0xa7, 0xfa, 0xfa, 0x17, 0xf7, 0x78, 0xd6, 0xb5, ++ 0x92, 0x61, 0x91, 0xac, 0x36, 0xfa, 0x56, 0x0d, ++ 0x38, 0x32, 0x18, 0x85, 0x08, 0x58, 0x37, 0xf0, ++ 0x4b, 0xdb, 0x59, 0xe7, 0xa4, 0x34, 0xc0, 0x1b, ++ 0x01, 0xaf, 0x2d, 0xde, 0xa1, 0xaa, 0x5d, 0xd3, ++ 0xec, 0xe1, 0xd4, 0xf7, 0xe6, 0x54, 0x68, 0xf0, ++ 0x51, 0x97, 0xa7, 0x89, 0xea, 0x24, 0xad, 0xd3, ++ 0x6e, 0x47, 0x93, 0x8b, 0x4b, 0xb4, 0xf7, 0x1c, ++ 0x42, 0x06, 0x67, 0xe8, 0x99, 0xf6, 0xf5, 0x7b, ++ 0x85, 0xb5, 0x65, 0xb5, 0xb5, 0xd2, 0x37, 0xf5, ++ 0xf3, 0x02, 0xa6, 0x4d, 0x11, 0xa7, 0xdc, 0x51, ++ 0x09, 0x7f, 0xa0, 0xd8, 0x88, 0x1c, 0x13, 0x71, ++ 0xae, 0x9c, 0xb7, 0x7b, 0x34, 0xd6, 0x4e, 0x68, ++ 0x26, 0x83, 0x51, 0xaf, 0x1d, 0xee, 0x8b, 0xbb, ++ 0x69, 0x43, 0x2b, 0x9e, 0x8a, 0xbc, 0x02, 0x0e, ++ 0xa0, 0x1b, 0xe0, 0xa8, 0x5f, 0x6f, 0xaf, 0x1b, ++ 0x8f, 0xe7, 0x64, 0x71, 0x74, 0x11, 0x7e, 0xa8, ++ 0xd8, 0xf9, 0x97, 0x06, 0xc3, 0xb6, 0xfb, 0xfb, ++ 0xb7, 0x3d, 0x35, 0x9d, 0x3b, 0x52, 0xed, 0x54, ++ 0xca, 0xf4, 0x81, 0x01, 0x2d, 0x1b, 0xc3, 0xa7, ++ 0x00, 0x3d, 0x1a, 0x39, 0x54, 0xe1, 0xf6, 0xff, ++ 0xed, 0x6f, 0x0b, 0x5a, 0x68, 0xda, 0x58, 0xdd, ++ 0xa9, 0xcf, 0x5c, 0x4a, 0xe5, 0x09, 0x4e, 0xde, ++ 0x9d, 0xbc, 0x3e, 0xee, 0x5a, 0x00, 0x3b, 0x2c, ++ 0x87, 0x10, 0x65, 0x60, 0xdd, 0xd7, 0x56, 0xd1, ++ 0x4c, 0x64, 0x45, 0xe4, 0x21, 0xec, 0x78, 0xf8, ++ 0x25, 0x7a, 0x3e, 0x16, 0x5d, 0x09, 0x53, 0x14, ++ 0xbe, 0x4f, 0xae, 0x87, 0xd8, 0xd1, 0xaa, 0x3c, ++ 0xf6, 0x3e, 0xa4, 0x70, 0x8c, 0x5e, 0x70, 0xa4, ++ 0xb3, 0x6b, 0x66, 0x73, 0xd3, 0xbf, 0x31, 0x06, ++ 0x19, 0x62, 0x93, 0x15, 0xf2, 0x86, 0xe4, 0x52, ++ 0x7e, 0x53, 0x4c, 0x12, 0x38, 0xcc, 0x34, 0x7d, ++ 0x57, 0xf6, 0x42, 0x93, 0x8a, 0xc4, 0xee, 0x5c, ++ 0x8a, 0xe1, 0x52, 0x8f, 0x56, 0x64, 0xf6, 0xa6, ++ 0xd1, 0x91, 0x57, 0x70, 0xcd, 0x11, 0x76, 0xf5, ++ 0x59, 0x60, 0x60, 0x3c, 0xc1, 0xc3, 0x0b, 0x7f, ++ 0x58, 0x1a, 0x50, 0x91, 0xf1, 0x68, 0x8f, 0x6e, ++ 0x74, 0x74, 0xa8, 0x51, 0x0b, 0xf7, 0x7a, 0x98, ++ 0x37, 0xf2, 0x0a, 0x0e, 0xa4, 0x97, 0x04, 0xb8, ++ 0x9b, 0xfd, 0xa0, 0xea, 0xf7, 0x0d, 0xe1, 0xdb, ++ 0x03, 0xf0, 0x31, 0x29, 0xf8, 0xdd, 0x6b, 0x8b, ++ 0x5d, 0xd8, 0x59, 0xa9, 0x29, 0xcf, 0x9a, 0x79, ++ 0x89, 0x19, 0x63, 0x46, 0x09, 0x79, 0x6a, 0x11, ++ 0xda, 0x63, 0x68, 0x48, 0x77, 0x23, 0xfb, 0x7d, ++ 0x3a, 0x43, 0xcb, 0x02, 0x3b, 0x7a, 0x6d, 0x10, ++ 0x2a, 0x9e, 0xac, 0xf1, 0xd4, 0x19, 0xf8, 0x23, ++ 0x64, 0x1d, 0x2c, 0x5f, 0xf2, 0xb0, 0x5c, 0x23, ++ 0x27, 0xf7, 0x27, 0x30, 0x16, 0x37, 0xb1, 0x90, ++ 0xab, 0x38, 0xfb, 0x55, 0xcd, 0x78, 0x58, 0xd4, ++ 0x7d, 0x43, 0xf6, 0x45, 0x5e, 0x55, 0x8d, 0xb1, ++ 0x02, 0x65, 0x58, 0xb4, 0x13, 0x4b, 0x36, 0xf7, ++ 0xcc, 0xfe, 0x3d, 0x0b, 0x82, 0xe2, 0x12, 0x11, ++ 0xbb, 0xe6, 0xb8, 0x3a, 0x48, 0x71, 0xc7, 0x50, ++ 0x06, 0x16, 0x3a, 0xe6, 0x7c, 0x05, 0xc7, 0xc8, ++ 0x4d, 0x2f, 0x08, 0x6a, 0x17, 0x9a, 0x95, 0x97, ++ 0x50, 0x68, 0xdc, 0x28, 0x18, 0xc4, 0x61, 0x38, ++ 0xb9, 0xe0, 0x3e, 0x78, 0xdb, 0x29, 0xe0, 0x9f, ++ 0x52, 0xdd, 0xf8, 0x4f, 0x91, 0xc1, 0xd0, 0x33, ++ 0xa1, 0x7a, 0x8e, 0x30, 0x13, 0x82, 0x07, 0x9f, ++ 0xd3, 0x31, 0x0f, 0x23, 0xbe, 0x32, 0x5a, 0x75, ++ 0xcf, 0x96, 0xb2, 0xec, 0xb5, 0x32, 0xac, 0x21, ++ 0xd1, 0x82, 0x33, 0xd3, 0x15, 0x74, 0xbd, 0x90, ++ 0xf1, 0x2c, 0xe6, 0x5f, 0x8d, 0xe3, 0x02, 0xe8, ++ 0xe9, 0xc4, 0xca, 0x96, 0xeb, 0x0e, 0xbc, 0x91, ++ 0xf4, 0xb9, 0xea, 0xd9, 0x1b, 0x75, 0xbd, 0xe1, ++ 0xac, 0x2a, 0x05, 0x37, 0x52, 0x9b, 0x1b, 0x3f, ++ 0x5a, 0xdc, 0x21, 0xc3, 0x98, 0xbb, 0xaf, 0xa3, ++ 0xf2, 0x00, 0xbf, 0x0d, 0x30, 0x89, 0x05, 0xcc, ++ 0xa5, 0x76, 0xf5, 0x06, 0xf0, 0xc6, 0x54, 0x8a, ++ 0x5d, 0xd4, 0x1e, 0xc1, 0xf2, 0xce, 0xb0, 0x62, ++ 0xc8, 0xfc, 0x59, 0x42, 0x9a, 0x90, 0x60, 0x55, ++ 0xfe, 0x88, 0xa5, 0x8b, 0xb8, 0x33, 0x0c, 0x23, ++ 0x24, 0x0d, 0x15, 0x70, 0x37, 0x1e, 0x3d, 0xf6, ++ 0xd2, 0xea, 0x92, 0x10, 0xb2, 0xc4, 0x51, 0xac, ++ 0xf2, 0xac, 0xf3, 0x6b, 0x6c, 0xaa, 0xcf, 0x12, ++ 0xc5, 0x6c, 0x90, 0x50, 0xb5, 0x0c, 0xfc, 0x1a, ++ 0x15, 0x52, 0xe9, 0x26, 0xc6, 0x52, 0xa4, 0xe7, ++ 0x81, 0x69, 0xe1, 0xe7, 0x9e, 0x30, 0x01, 0xec, ++ 0x84, 0x89, 0xb2, 0x0d, 0x66, 0xdd, 0xce, 0x28, ++ 0x5c, 0xec, 0x98, 0x46, 0x68, 0x21, 0x9f, 0x88, ++ 0x3f, 0x1f, 0x42, 0x77, 0xce, 0xd0, 0x61, 0xd4, ++ 0x20, 0xa7, 0xff, 0x53, 0xad, 0x37, 0xd0, 0x17, ++ 0x35, 0xc9, 0xfc, 0xba, 0x0a, 0x78, 0x3f, 0xf2, ++ 0xcc, 0x86, 0x89, 0xe8, 0x4b, 0x3c, 0x48, 0x33, ++ 0x09, 0x7f, 0xc6, 0xc0, 0xdd, 0xb8, 0xfd, 0x7a, ++ 0x66, 0x66, 0x65, 0xeb, 0x47, 0xa7, 0x04, 0x28, ++ 0xa3, 0x19, 0x8e, 0xa9, 0xb1, 0x13, 0x67, 0x62, ++ 0x70, 0xcf, 0xd7 ++}; ++static const u8 dec_output013[] __initconst = { ++ 0x74, 0xa6, 0x3e, 0xe4, 0xb1, 0xcb, 0xaf, 0xb0, ++ 0x40, 0xe5, 0x0f, 0x9e, 0xf1, 0xf2, 0x89, 0xb5, ++ 0x42, 0x34, 0x8a, 0xa1, 0x03, 0xb7, 0xe9, 0x57, ++ 0x46, 0xbe, 0x20, 0xe4, 0x6e, 0xb0, 0xeb, 0xff, ++ 0xea, 0x07, 0x7e, 0xef, 0xe2, 0x55, 0x9f, 0xe5, ++ 0x78, 0x3a, 0xb7, 0x83, 0xc2, 0x18, 0x40, 0x7b, ++ 0xeb, 0xcd, 0x81, 0xfb, 0x90, 0x12, 0x9e, 0x46, ++ 0xa9, 0xd6, 0x4a, 0xba, 0xb0, 0x62, 0xdb, 0x6b, ++ 0x99, 0xc4, 0xdb, 0x54, 0x4b, 0xb8, 0xa5, 0x71, ++ 0xcb, 0xcd, 0x63, 0x32, 0x55, 0xfb, 0x31, 0xf0, ++ 0x38, 0xf5, 0xbe, 0x78, 0xe4, 0x45, 0xce, 0x1b, ++ 0x6a, 0x5b, 0x0e, 0xf4, 0x16, 0xe4, 0xb1, 0x3d, ++ 0xf6, 0x63, 0x7b, 0xa7, 0x0c, 0xde, 0x6f, 0x8f, ++ 0x74, 0xdf, 0xe0, 0x1e, 0x9d, 0xce, 0x8f, 0x24, ++ 0xef, 0x23, 0x35, 0x33, 0x7b, 0x83, 0x34, 0x23, ++ 0x58, 0x74, 0x14, 0x77, 0x1f, 0xc2, 0x4f, 0x4e, ++ 0xc6, 0x89, 0xf9, 0x52, 0x09, 0x37, 0x64, 0x14, ++ 0xc4, 0x01, 0x6b, 0x9d, 0x77, 0xe8, 0x90, 0x5d, ++ 0xa8, 0x4a, 0x2a, 0xef, 0x5c, 0x7f, 0xeb, 0xbb, ++ 0xb2, 0xc6, 0x93, 0x99, 0x66, 0xdc, 0x7f, 0xd4, ++ 0x9e, 0x2a, 0xca, 0x8d, 0xdb, 0xe7, 0x20, 0xcf, ++ 0xe4, 0x73, 0xae, 0x49, 0x7d, 0x64, 0x0f, 0x0e, ++ 0x28, 0x46, 0xa9, 0xa8, 0x32, 0xe4, 0x0e, 0xf6, ++ 0x51, 0x53, 0xb8, 0x3c, 0xb1, 0xff, 0xa3, 0x33, ++ 0x41, 0x75, 0xff, 0xf1, 0x6f, 0xf1, 0xfb, 0xbb, ++ 0x83, 0x7f, 0x06, 0x9b, 0xe7, 0x1b, 0x0a, 0xe0, ++ 0x5c, 0x33, 0x60, 0x5b, 0xdb, 0x5b, 0xed, 0xfe, ++ 0xa5, 0x16, 0x19, 0x72, 0xa3, 0x64, 0x23, 0x00, ++ 0x02, 0xc7, 0xf3, 0x6a, 0x81, 0x3e, 0x44, 0x1d, ++ 0x79, 0x15, 0x5f, 0x9a, 0xde, 0xe2, 0xfd, 0x1b, ++ 0x73, 0xc1, 0xbc, 0x23, 0xba, 0x31, 0xd2, 0x50, ++ 0xd5, 0xad, 0x7f, 0x74, 0xa7, 0xc9, 0xf8, 0x3e, ++ 0x2b, 0x26, 0x10, 0xf6, 0x03, 0x36, 0x74, 0xe4, ++ 0x0e, 0x6a, 0x72, 0xb7, 0x73, 0x0a, 0x42, 0x28, ++ 0xc2, 0xad, 0x5e, 0x03, 0xbe, 0xb8, 0x0b, 0xa8, ++ 0x5b, 0xd4, 0xb8, 0xba, 0x52, 0x89, 0xb1, 0x9b, ++ 0xc1, 0xc3, 0x65, 0x87, 0xed, 0xa5, 0xf4, 0x86, ++ 0xfd, 0x41, 0x80, 0x91, 0x27, 0x59, 0x53, 0x67, ++ 0x15, 0x78, 0x54, 0x8b, 0x2d, 0x3d, 0xc7, 0xff, ++ 0x02, 0x92, 0x07, 0x5f, 0x7a, 0x4b, 0x60, 0x59, ++ 0x3c, 0x6f, 0x5c, 0xd8, 0xec, 0x95, 0xd2, 0xfe, ++ 0xa0, 0x3b, 0xd8, 0x3f, 0xd1, 0x69, 0xa6, 0xd6, ++ 0x41, 0xb2, 0xf4, 0x4d, 0x12, 0xf4, 0x58, 0x3e, ++ 0x66, 0x64, 0x80, 0x31, 0x9b, 0xa8, 0x4c, 0x8b, ++ 0x07, 0xb2, 0xec, 0x66, 0x94, 0x66, 0x47, 0x50, ++ 0x50, 0x5f, 0x18, 0x0b, 0x0e, 0xd6, 0xc0, 0x39, ++ 0x21, 0x13, 0x9e, 0x33, 0xbc, 0x79, 0x36, 0x02, ++ 0x96, 0x70, 0xf0, 0x48, 0x67, 0x2f, 0x26, 0xe9, ++ 0x6d, 0x10, 0xbb, 0xd6, 0x3f, 0xd1, 0x64, 0x7a, ++ 0x2e, 0xbe, 0x0c, 0x61, 0xf0, 0x75, 0x42, 0x38, ++ 0x23, 0xb1, 0x9e, 0x9f, 0x7c, 0x67, 0x66, 0xd9, ++ 0x58, 0x9a, 0xf1, 0xbb, 0x41, 0x2a, 0x8d, 0x65, ++ 0x84, 0x94, 0xfc, 0xdc, 0x6a, 0x50, 0x64, 0xdb, ++ 0x56, 0x33, 0x76, 0x00, 0x10, 0xed, 0xbe, 0xd2, ++ 0x12, 0xf6, 0xf6, 0x1b, 0xa2, 0x16, 0xde, 0xae, ++ 0x31, 0x95, 0xdd, 0xb1, 0x08, 0x7e, 0x4e, 0xee, ++ 0xe7, 0xf9, 0xa5, 0xfb, 0x5b, 0x61, 0x43, 0x00, ++ 0x40, 0xf6, 0x7e, 0x02, 0x04, 0x32, 0x4e, 0x0c, ++ 0xe2, 0x66, 0x0d, 0xd7, 0x07, 0x98, 0x0e, 0xf8, ++ 0x72, 0x34, 0x6d, 0x95, 0x86, 0xd7, 0xcb, 0x31, ++ 0x54, 0x47, 0xd0, 0x38, 0x29, 0x9c, 0x5a, 0x68, ++ 0xd4, 0x87, 0x76, 0xc9, 0xe7, 0x7e, 0xe3, 0xf4, ++ 0x81, 0x6d, 0x18, 0xcb, 0xc9, 0x05, 0xaf, 0xa0, ++ 0xfb, 0x66, 0xf7, 0xf1, 0x1c, 0xc6, 0x14, 0x11, ++ 0x4f, 0x2b, 0x79, 0x42, 0x8b, 0xbc, 0xac, 0xe7, ++ 0x6c, 0xfe, 0x0f, 0x58, 0xe7, 0x7c, 0x78, 0x39, ++ 0x30, 0xb0, 0x66, 0x2c, 0x9b, 0x6d, 0x3a, 0xe1, ++ 0xcf, 0xc9, 0xa4, 0x0e, 0x6d, 0x6d, 0x8a, 0xa1, ++ 0x3a, 0xe7, 0x28, 0xd4, 0x78, 0x4c, 0xa6, 0xa2, ++ 0x2a, 0xa6, 0x03, 0x30, 0xd7, 0xa8, 0x25, 0x66, ++ 0x87, 0x2f, 0x69, 0x5c, 0x4e, 0xdd, 0xa5, 0x49, ++ 0x5d, 0x37, 0x4a, 0x59, 0xc4, 0xaf, 0x1f, 0xa2, ++ 0xe4, 0xf8, 0xa6, 0x12, 0x97, 0xd5, 0x79, 0xf5, ++ 0xe2, 0x4a, 0x2b, 0x5f, 0x61, 0xe4, 0x9e, 0xe3, ++ 0xee, 0xb8, 0xa7, 0x5b, 0x2f, 0xf4, 0x9e, 0x6c, ++ 0xfb, 0xd1, 0xc6, 0x56, 0x77, 0xba, 0x75, 0xaa, ++ 0x3d, 0x1a, 0xa8, 0x0b, 0xb3, 0x68, 0x24, 0x00, ++ 0x10, 0x7f, 0xfd, 0xd7, 0xa1, 0x8d, 0x83, 0x54, ++ 0x4f, 0x1f, 0xd8, 0x2a, 0xbe, 0x8a, 0x0c, 0x87, ++ 0xab, 0xa2, 0xde, 0xc3, 0x39, 0xbf, 0x09, 0x03, ++ 0xa5, 0xf3, 0x05, 0x28, 0xe1, 0xe1, 0xee, 0x39, ++ 0x70, 0x9c, 0xd8, 0x81, 0x12, 0x1e, 0x02, 0x40, ++ 0xd2, 0x6e, 0xf0, 0xeb, 0x1b, 0x3d, 0x22, 0xc6, ++ 0xe5, 0xe3, 0xb4, 0x5a, 0x98, 0xbb, 0xf0, 0x22, ++ 0x28, 0x8d, 0xe5, 0xd3, 0x16, 0x48, 0x24, 0xa5, ++ 0xe6, 0x66, 0x0c, 0xf9, 0x08, 0xf9, 0x7e, 0x1e, ++ 0xe1, 0x28, 0x26, 0x22, 0xc7, 0xc7, 0x0a, 0x32, ++ 0x47, 0xfa, 0xa3, 0xbe, 0x3c, 0xc4, 0xc5, 0x53, ++ 0x0a, 0xd5, 0x94, 0x4a, 0xd7, 0x93, 0xd8, 0x42, ++ 0x99, 0xb9, 0x0a, 0xdb, 0x56, 0xf7, 0xb9, 0x1c, ++ 0x53, 0x4f, 0xfa, 0xd3, 0x74, 0xad, 0xd9, 0x68, ++ 0xf1, 0x1b, 0xdf, 0x61, 0xc6, 0x5e, 0xa8, 0x48, ++ 0xfc, 0xd4, 0x4a, 0x4c, 0x3c, 0x32, 0xf7, 0x1c, ++ 0x96, 0x21, 0x9b, 0xf9, 0xa3, 0xcc, 0x5a, 0xce, ++ 0xd5, 0xd7, 0x08, 0x24, 0xf6, 0x1c, 0xfd, 0xdd, ++ 0x38, 0xc2, 0x32, 0xe9, 0xb8, 0xe7, 0xb6, 0xfa, ++ 0x9d, 0x45, 0x13, 0x2c, 0x83, 0xfd, 0x4a, 0x69, ++ 0x82, 0xcd, 0xdc, 0xb3, 0x76, 0x0c, 0x9e, 0xd8, ++ 0xf4, 0x1b, 0x45, 0x15, 0xb4, 0x97, 0xe7, 0x58, ++ 0x34, 0xe2, 0x03, 0x29, 0x5a, 0xbf, 0xb6, 0xe0, ++ 0x5d, 0x13, 0xd9, 0x2b, 0xb4, 0x80, 0xb2, 0x45, ++ 0x81, 0x6a, 0x2e, 0x6c, 0x89, 0x7d, 0xee, 0xbb, ++ 0x52, 0xdd, 0x1f, 0x18, 0xe7, 0x13, 0x6b, 0x33, ++ 0x0e, 0xea, 0x36, 0x92, 0x77, 0x7b, 0x6d, 0x9c, ++ 0x5a, 0x5f, 0x45, 0x7b, 0x7b, 0x35, 0x62, 0x23, ++ 0xd1, 0xbf, 0x0f, 0xd0, 0x08, 0x1b, 0x2b, 0x80, ++ 0x6b, 0x7e, 0xf1, 0x21, 0x47, 0xb0, 0x57, 0xd1, ++ 0x98, 0x72, 0x90, 0x34, 0x1c, 0x20, 0x04, 0xff, ++ 0x3d, 0x5c, 0xee, 0x0e, 0x57, 0x5f, 0x6f, 0x24, ++ 0x4e, 0x3c, 0xea, 0xfc, 0xa5, 0xa9, 0x83, 0xc9, ++ 0x61, 0xb4, 0x51, 0x24, 0xf8, 0x27, 0x5e, 0x46, ++ 0x8c, 0xb1, 0x53, 0x02, 0x96, 0x35, 0xba, 0xb8, ++ 0x4c, 0x71, 0xd3, 0x15, 0x59, 0x35, 0x22, 0x20, ++ 0xad, 0x03, 0x9f, 0x66, 0x44, 0x3b, 0x9c, 0x35, ++ 0x37, 0x1f, 0x9b, 0xbb, 0xf3, 0xdb, 0x35, 0x63, ++ 0x30, 0x64, 0xaa, 0xa2, 0x06, 0xa8, 0x5d, 0xbb, ++ 0xe1, 0x9f, 0x70, 0xec, 0x82, 0x11, 0x06, 0x36, ++ 0xec, 0x8b, 0x69, 0x66, 0x24, 0x44, 0xc9, 0x4a, ++ 0x57, 0xbb, 0x9b, 0x78, 0x13, 0xce, 0x9c, 0x0c, ++ 0xba, 0x92, 0x93, 0x63, 0xb8, 0xe2, 0x95, 0x0f, ++ 0x0f, 0x16, 0x39, 0x52, 0xfd, 0x3a, 0x6d, 0x02, ++ 0x4b, 0xdf, 0x13, 0xd3, 0x2a, 0x22, 0xb4, 0x03, ++ 0x7c, 0x54, 0x49, 0x96, 0x68, 0x54, 0x10, 0xfa, ++ 0xef, 0xaa, 0x6c, 0xe8, 0x22, 0xdc, 0x71, 0x16, ++ 0x13, 0x1a, 0xf6, 0x28, 0xe5, 0x6d, 0x77, 0x3d, ++ 0xcd, 0x30, 0x63, 0xb1, 0x70, 0x52, 0xa1, 0xc5, ++ 0x94, 0x5f, 0xcf, 0xe8, 0xb8, 0x26, 0x98, 0xf7, ++ 0x06, 0xa0, 0x0a, 0x70, 0xfa, 0x03, 0x80, 0xac, ++ 0xc1, 0xec, 0xd6, 0x4c, 0x54, 0xd7, 0xfe, 0x47, ++ 0xb6, 0x88, 0x4a, 0xf7, 0x71, 0x24, 0xee, 0xf3, ++ 0xd2, 0xc2, 0x4a, 0x7f, 0xfe, 0x61, 0xc7, 0x35, ++ 0xc9, 0x37, 0x67, 0xcb, 0x24, 0x35, 0xda, 0x7e, ++ 0xca, 0x5f, 0xf3, 0x8d, 0xd4, 0x13, 0x8e, 0xd6, ++ 0xcb, 0x4d, 0x53, 0x8f, 0x53, 0x1f, 0xc0, 0x74, ++ 0xf7, 0x53, 0xb9, 0x5e, 0x23, 0x37, 0xba, 0x6e, ++ 0xe3, 0x9d, 0x07, 0x55, 0x25, 0x7b, 0xe6, 0x2a, ++ 0x64, 0xd1, 0x32, 0xdd, 0x54, 0x1b, 0x4b, 0xc0, ++ 0xe1, 0xd7, 0x69, 0x58, 0xf8, 0x93, 0x29, 0xc4, ++ 0xdd, 0x23, 0x2f, 0xa5, 0xfc, 0x9d, 0x7e, 0xf8, ++ 0xd4, 0x90, 0xcd, 0x82, 0x55, 0xdc, 0x16, 0x16, ++ 0x9f, 0x07, 0x52, 0x9b, 0x9d, 0x25, 0xed, 0x32, ++ 0xc5, 0x7b, 0xdf, 0xf6, 0x83, 0x46, 0x3d, 0x65, ++ 0xb7, 0xef, 0x87, 0x7a, 0x12, 0x69, 0x8f, 0x06, ++ 0x7c, 0x51, 0x15, 0x4a, 0x08, 0xe8, 0xac, 0x9a, ++ 0x0c, 0x24, 0xa7, 0x27, 0xd8, 0x46, 0x2f, 0xe7, ++ 0x01, 0x0e, 0x1c, 0xc6, 0x91, 0xb0, 0x6e, 0x85, ++ 0x65, 0xf0, 0x29, 0x0d, 0x2e, 0x6b, 0x3b, 0xfb, ++ 0x4b, 0xdf, 0xe4, 0x80, 0x93, 0x03, 0x66, 0x46, ++ 0x3e, 0x8a, 0x6e, 0xf3, 0x5e, 0x4d, 0x62, 0x0e, ++ 0x49, 0x05, 0xaf, 0xd4, 0xf8, 0x21, 0x20, 0x61, ++ 0x1d, 0x39, 0x17, 0xf4, 0x61, 0x47, 0x95, 0xfb, ++ 0x15, 0x2e, 0xb3, 0x4f, 0xd0, 0x5d, 0xf5, 0x7d, ++ 0x40, 0xda, 0x90, 0x3c, 0x6b, 0xcb, 0x17, 0x00, ++ 0x13, 0x3b, 0x64, 0x34, 0x1b, 0xf0, 0xf2, 0xe5, ++ 0x3b, 0xb2, 0xc7, 0xd3, 0x5f, 0x3a, 0x44, 0xa6, ++ 0x9b, 0xb7, 0x78, 0x0e, 0x42, 0x5d, 0x4c, 0xc1, ++ 0xe9, 0xd2, 0xcb, 0xb7, 0x78, 0xd1, 0xfe, 0x9a, ++ 0xb5, 0x07, 0xe9, 0xe0, 0xbe, 0xe2, 0x8a, 0xa7, ++ 0x01, 0x83, 0x00, 0x8c, 0x5c, 0x08, 0xe6, 0x63, ++ 0x12, 0x92, 0xb7, 0xb7, 0xa6, 0x19, 0x7d, 0x38, ++ 0x13, 0x38, 0x92, 0x87, 0x24, 0xf9, 0x48, 0xb3, ++ 0x5e, 0x87, 0x6a, 0x40, 0x39, 0x5c, 0x3f, 0xed, ++ 0x8f, 0xee, 0xdb, 0x15, 0x82, 0x06, 0xda, 0x49, ++ 0x21, 0x2b, 0xb5, 0xbf, 0x32, 0x7c, 0x9f, 0x42, ++ 0x28, 0x63, 0xcf, 0xaf, 0x1e, 0xf8, 0xc6, 0xa0, ++ 0xd1, 0x02, 0x43, 0x57, 0x62, 0xec, 0x9b, 0x0f, ++ 0x01, 0x9e, 0x71, 0xd8, 0x87, 0x9d, 0x01, 0xc1, ++ 0x58, 0x77, 0xd9, 0xaf, 0xb1, 0x10, 0x7e, 0xdd, ++ 0xa6, 0x50, 0x96, 0xe5, 0xf0, 0x72, 0x00, 0x6d, ++ 0x4b, 0xf8, 0x2a, 0x8f, 0x19, 0xf3, 0x22, 0x88, ++ 0x11, 0x4a, 0x8b, 0x7c, 0xfd, 0xb7, 0xed, 0xe1, ++ 0xf6, 0x40, 0x39, 0xe0, 0xe9, 0xf6, 0x3d, 0x25, ++ 0xe6, 0x74, 0x3c, 0x58, 0x57, 0x7f, 0xe1, 0x22, ++ 0x96, 0x47, 0x31, 0x91, 0xba, 0x70, 0x85, 0x28, ++ 0x6b, 0x9f, 0x6e, 0x25, 0xac, 0x23, 0x66, 0x2f, ++ 0x29, 0x88, 0x28, 0xce, 0x8c, 0x5c, 0x88, 0x53, ++ 0xd1, 0x3b, 0xcc, 0x6a, 0x51, 0xb2, 0xe1, 0x28, ++ 0x3f, 0x91, 0xb4, 0x0d, 0x00, 0x3a, 0xe3, 0xf8, ++ 0xc3, 0x8f, 0xd7, 0x96, 0x62, 0x0e, 0x2e, 0xfc, ++ 0xc8, 0x6c, 0x77, 0xa6, 0x1d, 0x22, 0xc1, 0xb8, ++ 0xe6, 0x61, 0xd7, 0x67, 0x36, 0x13, 0x7b, 0xbb, ++ 0x9b, 0x59, 0x09, 0xa6, 0xdf, 0xf7, 0x6b, 0xa3, ++ 0x40, 0x1a, 0xf5, 0x4f, 0xb4, 0xda, 0xd3, 0xf3, ++ 0x81, 0x93, 0xc6, 0x18, 0xd9, 0x26, 0xee, 0xac, ++ 0xf0, 0xaa, 0xdf, 0xc5, 0x9c, 0xca, 0xc2, 0xa2, ++ 0xcc, 0x7b, 0x5c, 0x24, 0xb0, 0xbc, 0xd0, 0x6a, ++ 0x4d, 0x89, 0x09, 0xb8, 0x07, 0xfe, 0x87, 0xad, ++ 0x0a, 0xea, 0xb8, 0x42, 0xf9, 0x5e, 0xb3, 0x3e, ++ 0x36, 0x4c, 0xaf, 0x75, 0x9e, 0x1c, 0xeb, 0xbd, ++ 0xbc, 0xbb, 0x80, 0x40, 0xa7, 0x3a, 0x30, 0xbf, ++ 0xa8, 0x44, 0xf4, 0xeb, 0x38, 0xad, 0x29, 0xba, ++ 0x23, 0xed, 0x41, 0x0c, 0xea, 0xd2, 0xbb, 0x41, ++ 0x18, 0xd6, 0xb9, 0xba, 0x65, 0x2b, 0xa3, 0x91, ++ 0x6d, 0x1f, 0xa9, 0xf4, 0xd1, 0x25, 0x8d, 0x4d, ++ 0x38, 0xff, 0x64, 0xa0, 0xec, 0xde, 0xa6, 0xb6, ++ 0x79, 0xab, 0x8e, 0x33, 0x6c, 0x47, 0xde, 0xaf, ++ 0x94, 0xa4, 0xa5, 0x86, 0x77, 0x55, 0x09, 0x92, ++ 0x81, 0x31, 0x76, 0xc7, 0x34, 0x22, 0x89, 0x8e, ++ 0x3d, 0x26, 0x26, 0xd7, 0xfc, 0x1e, 0x16, 0x72, ++ 0x13, 0x33, 0x63, 0xd5, 0x22, 0xbe, 0xb8, 0x04, ++ 0x34, 0x84, 0x41, 0xbb, 0x80, 0xd0, 0x9f, 0x46, ++ 0x48, 0x07, 0xa7, 0xfc, 0x2b, 0x3a, 0x75, 0x55, ++ 0x8c, 0xc7, 0x6a, 0xbd, 0x7e, 0x46, 0x08, 0x84, ++ 0x0f, 0xd5, 0x74, 0xc0, 0x82, 0x8e, 0xaa, 0x61, ++ 0x05, 0x01, 0xb2, 0x47, 0x6e, 0x20, 0x6a, 0x2d, ++ 0x58, 0x70, 0x48, 0x32, 0xa7, 0x37, 0xd2, 0xb8, ++ 0x82, 0x1a, 0x51, 0xb9, 0x61, 0xdd, 0xfd, 0x9d, ++ 0x6b, 0x0e, 0x18, 0x97, 0xf8, 0x45, 0x5f, 0x87, ++ 0x10, 0xcf, 0x34, 0x72, 0x45, 0x26, 0x49, 0x70, ++ 0xe7, 0xa3, 0x78, 0xe0, 0x52, 0x89, 0x84, 0x94, ++ 0x83, 0x82, 0xc2, 0x69, 0x8f, 0xe3, 0xe1, 0x3f, ++ 0x60, 0x74, 0x88, 0xc4, 0xf7, 0x75, 0x2c, 0xfb, ++ 0xbd, 0xb6, 0xc4, 0x7e, 0x10, 0x0a, 0x6c, 0x90, ++ 0x04, 0x9e, 0xc3, 0x3f, 0x59, 0x7c, 0xce, 0x31, ++ 0x18, 0x60, 0x57, 0x73, 0x46, 0x94, 0x7d, 0x06, ++ 0xa0, 0x6d, 0x44, 0xec, 0xa2, 0x0a, 0x9e, 0x05, ++ 0x15, 0xef, 0xca, 0x5c, 0xbf, 0x00, 0xeb, 0xf7, ++ 0x3d, 0x32, 0xd4, 0xa5, 0xef, 0x49, 0x89, 0x5e, ++ 0x46, 0xb0, 0xa6, 0x63, 0x5b, 0x8a, 0x73, 0xae, ++ 0x6f, 0xd5, 0x9d, 0xf8, 0x4f, 0x40, 0xb5, 0xb2, ++ 0x6e, 0xd3, 0xb6, 0x01, 0xa9, 0x26, 0xa2, 0x21, ++ 0xcf, 0x33, 0x7a, 0x3a, 0xa4, 0x23, 0x13, 0xb0, ++ 0x69, 0x6a, 0xee, 0xce, 0xd8, 0x9d, 0x01, 0x1d, ++ 0x50, 0xc1, 0x30, 0x6c, 0xb1, 0xcd, 0xa0, 0xf0, ++ 0xf0, 0xa2, 0x64, 0x6f, 0xbb, 0xbf, 0x5e, 0xe6, ++ 0xab, 0x87, 0xb4, 0x0f, 0x4f, 0x15, 0xaf, 0xb5, ++ 0x25, 0xa1, 0xb2, 0xd0, 0x80, 0x2c, 0xfb, 0xf9, ++ 0xfe, 0xd2, 0x33, 0xbb, 0x76, 0xfe, 0x7c, 0xa8, ++ 0x66, 0xf7, 0xe7, 0x85, 0x9f, 0x1f, 0x85, 0x57, ++ 0x88, 0xe1, 0xe9, 0x63, 0xe4, 0xd8, 0x1c, 0xa1, ++ 0xfb, 0xda, 0x44, 0x05, 0x2e, 0x1d, 0x3a, 0x1c, ++ 0xff, 0xc8, 0x3b, 0xc0, 0xfe, 0xda, 0x22, 0x0b, ++ 0x43, 0xd6, 0x88, 0x39, 0x4c, 0x4a, 0xa6, 0x69, ++ 0x18, 0x93, 0x42, 0x4e, 0xb5, 0xcc, 0x66, 0x0d, ++ 0x09, 0xf8, 0x1e, 0x7c, 0xd3, 0x3c, 0x99, 0x0d, ++ 0x50, 0x1d, 0x62, 0xe9, 0x57, 0x06, 0xbf, 0x19, ++ 0x88, 0xdd, 0xad, 0x7b, 0x4f, 0xf9, 0xc7, 0x82, ++ 0x6d, 0x8d, 0xc8, 0xc4, 0xc5, 0x78, 0x17, 0x20, ++ 0x15, 0xc5, 0x52, 0x41, 0xcf, 0x5b, 0xd6, 0x7f, ++ 0x94, 0x02, 0x41, 0xe0, 0x40, 0x22, 0x03, 0x5e, ++ 0xd1, 0x53, 0xd4, 0x86, 0xd3, 0x2c, 0x9f, 0x0f, ++ 0x96, 0xe3, 0x6b, 0x9a, 0x76, 0x32, 0x06, 0x47, ++ 0x4b, 0x11, 0xb3, 0xdd, 0x03, 0x65, 0xbd, 0x9b, ++ 0x01, 0xda, 0x9c, 0xb9, 0x7e, 0x3f, 0x6a, 0xc4, ++ 0x7b, 0xea, 0xd4, 0x3c, 0xb9, 0xfb, 0x5c, 0x6b, ++ 0x64, 0x33, 0x52, 0xba, 0x64, 0x78, 0x8f, 0xa4, ++ 0xaf, 0x7a, 0x61, 0x8d, 0xbc, 0xc5, 0x73, 0xe9, ++ 0x6b, 0x58, 0x97, 0x4b, 0xbf, 0x63, 0x22, 0xd3, ++ 0x37, 0x02, 0x54, 0xc5, 0xb9, 0x16, 0x4a, 0xf0, ++ 0x19, 0xd8, 0x94, 0x57, 0xb8, 0x8a, 0xb3, 0x16, ++ 0x3b, 0xd0, 0x84, 0x8e, 0x67, 0xa6, 0xa3, 0x7d, ++ 0x78, 0xec, 0x00 ++}; ++static const u8 dec_assoc013[] __initconst = { ++ 0xb1, 0x69, 0x83, 0x87, 0x30, 0xaa, 0x5d, 0xb8, ++ 0x77, 0xe8, 0x21, 0xff, 0x06, 0x59, 0x35, 0xce, ++ 0x75, 0xfe, 0x38, 0xef, 0xb8, 0x91, 0x43, 0x8c, ++ 0xcf, 0x70, 0xdd, 0x0a, 0x68, 0xbf, 0xd4, 0xbc, ++ 0x16, 0x76, 0x99, 0x36, 0x1e, 0x58, 0x79, 0x5e, ++ 0xd4, 0x29, 0xf7, 0x33, 0x93, 0x48, 0xdb, 0x5f, ++ 0x01, 0xae, 0x9c, 0xb6, 0xe4, 0x88, 0x6d, 0x2b, ++ 0x76, 0x75, 0xe0, 0xf3, 0x74, 0xe2, 0xc9 ++}; ++static const u8 dec_nonce013[] __initconst = { ++ 0x05, 0xa3, 0x93, 0xed, 0x30, 0xc5, 0xa2, 0x06 ++}; ++static const u8 dec_key013[] __initconst = { ++ 0xb3, 0x35, 0x50, 0x03, 0x54, 0x2e, 0x40, 0x5e, ++ 0x8f, 0x59, 0x8e, 0xc5, 0x90, 0xd5, 0x27, 0x2d, ++ 0xba, 0x29, 0x2e, 0xcb, 0x1b, 0x70, 0x44, 0x1e, ++ 0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64 ++}; ++ ++static const struct chacha20poly1305_testvec ++chacha20poly1305_dec_vectors[] __initconst = { ++ { dec_input001, dec_output001, dec_assoc001, dec_nonce001, dec_key001, ++ sizeof(dec_input001), sizeof(dec_assoc001), sizeof(dec_nonce001) }, ++ { dec_input002, dec_output002, dec_assoc002, dec_nonce002, dec_key002, ++ sizeof(dec_input002), sizeof(dec_assoc002), sizeof(dec_nonce002) }, ++ { dec_input003, dec_output003, dec_assoc003, dec_nonce003, dec_key003, ++ sizeof(dec_input003), sizeof(dec_assoc003), sizeof(dec_nonce003) }, ++ { dec_input004, dec_output004, dec_assoc004, dec_nonce004, dec_key004, ++ sizeof(dec_input004), sizeof(dec_assoc004), sizeof(dec_nonce004) }, ++ { dec_input005, dec_output005, dec_assoc005, dec_nonce005, dec_key005, ++ sizeof(dec_input005), sizeof(dec_assoc005), sizeof(dec_nonce005) }, ++ { dec_input006, dec_output006, dec_assoc006, dec_nonce006, dec_key006, ++ sizeof(dec_input006), sizeof(dec_assoc006), sizeof(dec_nonce006) }, ++ { dec_input007, dec_output007, dec_assoc007, dec_nonce007, dec_key007, ++ sizeof(dec_input007), sizeof(dec_assoc007), sizeof(dec_nonce007) }, ++ { dec_input008, dec_output008, dec_assoc008, dec_nonce008, dec_key008, ++ sizeof(dec_input008), sizeof(dec_assoc008), sizeof(dec_nonce008) }, ++ { dec_input009, dec_output009, dec_assoc009, dec_nonce009, dec_key009, ++ sizeof(dec_input009), sizeof(dec_assoc009), sizeof(dec_nonce009) }, ++ { dec_input010, dec_output010, dec_assoc010, dec_nonce010, dec_key010, ++ sizeof(dec_input010), sizeof(dec_assoc010), sizeof(dec_nonce010) }, ++ { dec_input011, dec_output011, dec_assoc011, dec_nonce011, dec_key011, ++ sizeof(dec_input011), sizeof(dec_assoc011), sizeof(dec_nonce011) }, ++ { dec_input012, dec_output012, dec_assoc012, dec_nonce012, dec_key012, ++ sizeof(dec_input012), sizeof(dec_assoc012), sizeof(dec_nonce012) }, ++ { dec_input013, dec_output013, dec_assoc013, dec_nonce013, dec_key013, ++ sizeof(dec_input013), sizeof(dec_assoc013), sizeof(dec_nonce013), ++ true } ++}; ++ ++static const u8 xenc_input001[] __initconst = { ++ 0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74, ++ 0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20, ++ 0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66, ++ 0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69, ++ 0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20, ++ 0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20, ++ 0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d, ++ 0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e, ++ 0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65, ++ 0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64, ++ 0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63, ++ 0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f, ++ 0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64, ++ 0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65, ++ 0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61, ++ 0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e, ++ 0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69, ++ 0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72, ++ 0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20, ++ 0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65, ++ 0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61, ++ 0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72, ++ 0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65, ++ 0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61, ++ 0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20, ++ 0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65, ++ 0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20, ++ 0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20, ++ 0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b, ++ 0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67, ++ 0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80, ++ 0x9d ++}; ++static const u8 xenc_output001[] __initconst = { ++ 0x1a, 0x6e, 0x3a, 0xd9, 0xfd, 0x41, 0x3f, 0x77, ++ 0x54, 0x72, 0x0a, 0x70, 0x9a, 0xa0, 0x29, 0x92, ++ 0x2e, 0xed, 0x93, 0xcf, 0x0f, 0x71, 0x88, 0x18, ++ 0x7a, 0x9d, 0x2d, 0x24, 0xe0, 0xf5, 0xea, 0x3d, ++ 0x55, 0x64, 0xd7, 0xad, 0x2a, 0x1a, 0x1f, 0x7e, ++ 0x86, 0x6d, 0xb0, 0xce, 0x80, 0x41, 0x72, 0x86, ++ 0x26, 0xee, 0x84, 0xd7, 0xef, 0x82, 0x9e, 0xe2, ++ 0x60, 0x9d, 0x5a, 0xfc, 0xf0, 0xe4, 0x19, 0x85, ++ 0xea, 0x09, 0xc6, 0xfb, 0xb3, 0xa9, 0x50, 0x09, ++ 0xec, 0x5e, 0x11, 0x90, 0xa1, 0xc5, 0x4e, 0x49, ++ 0xef, 0x50, 0xd8, 0x8f, 0xe0, 0x78, 0xd7, 0xfd, ++ 0xb9, 0x3b, 0xc9, 0xf2, 0x91, 0xc8, 0x25, 0xc8, ++ 0xa7, 0x63, 0x60, 0xce, 0x10, 0xcd, 0xc6, 0x7f, ++ 0xf8, 0x16, 0xf8, 0xe1, 0x0a, 0xd9, 0xde, 0x79, ++ 0x50, 0x33, 0xf2, 0x16, 0x0f, 0x17, 0xba, 0xb8, ++ 0x5d, 0xd8, 0xdf, 0x4e, 0x51, 0xa8, 0x39, 0xd0, ++ 0x85, 0xca, 0x46, 0x6a, 0x10, 0xa7, 0xa3, 0x88, ++ 0xef, 0x79, 0xb9, 0xf8, 0x24, 0xf3, 0xe0, 0x71, ++ 0x7b, 0x76, 0x28, 0x46, 0x3a, 0x3a, 0x1b, 0x91, ++ 0xb6, 0xd4, 0x3e, 0x23, 0xe5, 0x44, 0x15, 0xbf, ++ 0x60, 0x43, 0x9d, 0xa4, 0xbb, 0xd5, 0x5f, 0x89, ++ 0xeb, 0xef, 0x8e, 0xfd, 0xdd, 0xb4, 0x0d, 0x46, ++ 0xf0, 0x69, 0x23, 0x63, 0xae, 0x94, 0xf5, 0x5e, ++ 0xa5, 0xad, 0x13, 0x1c, 0x41, 0x76, 0xe6, 0x90, ++ 0xd6, 0x6d, 0xa2, 0x8f, 0x97, 0x4c, 0xa8, 0x0b, ++ 0xcf, 0x8d, 0x43, 0x2b, 0x9c, 0x9b, 0xc5, 0x58, ++ 0xa5, 0xb6, 0x95, 0x9a, 0xbf, 0x81, 0xc6, 0x54, ++ 0xc9, 0x66, 0x0c, 0xe5, 0x4f, 0x6a, 0x53, 0xa1, ++ 0xe5, 0x0c, 0xba, 0x31, 0xde, 0x34, 0x64, 0x73, ++ 0x8a, 0x3b, 0xbd, 0x92, 0x01, 0xdb, 0x71, 0x69, ++ 0xf3, 0x58, 0x99, 0xbc, 0xd1, 0xcb, 0x4a, 0x05, ++ 0xe2, 0x58, 0x9c, 0x25, 0x17, 0xcd, 0xdc, 0x83, ++ 0xb7, 0xff, 0xfb, 0x09, 0x61, 0xad, 0xbf, 0x13, ++ 0x5b, 0x5e, 0xed, 0x46, 0x82, 0x6f, 0x22, 0xd8, ++ 0x93, 0xa6, 0x85, 0x5b, 0x40, 0x39, 0x5c, 0xc5, ++ 0x9c ++}; ++static const u8 xenc_assoc001[] __initconst = { ++ 0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x4e, 0x91 ++}; ++static const u8 xenc_nonce001[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, ++ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17 ++}; ++static const u8 xenc_key001[] __initconst = { ++ 0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a, ++ 0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0, ++ 0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09, ++ 0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0 ++}; ++ ++static const struct chacha20poly1305_testvec ++xchacha20poly1305_enc_vectors[] __initconst = { ++ { xenc_input001, xenc_output001, xenc_assoc001, xenc_nonce001, xenc_key001, ++ sizeof(xenc_input001), sizeof(xenc_assoc001), sizeof(xenc_nonce001) } ++}; ++ ++static const u8 xdec_input001[] __initconst = { ++ 0x1a, 0x6e, 0x3a, 0xd9, 0xfd, 0x41, 0x3f, 0x77, ++ 0x54, 0x72, 0x0a, 0x70, 0x9a, 0xa0, 0x29, 0x92, ++ 0x2e, 0xed, 0x93, 0xcf, 0x0f, 0x71, 0x88, 0x18, ++ 0x7a, 0x9d, 0x2d, 0x24, 0xe0, 0xf5, 0xea, 0x3d, ++ 0x55, 0x64, 0xd7, 0xad, 0x2a, 0x1a, 0x1f, 0x7e, ++ 0x86, 0x6d, 0xb0, 0xce, 0x80, 0x41, 0x72, 0x86, ++ 0x26, 0xee, 0x84, 0xd7, 0xef, 0x82, 0x9e, 0xe2, ++ 0x60, 0x9d, 0x5a, 0xfc, 0xf0, 0xe4, 0x19, 0x85, ++ 0xea, 0x09, 0xc6, 0xfb, 0xb3, 0xa9, 0x50, 0x09, ++ 0xec, 0x5e, 0x11, 0x90, 0xa1, 0xc5, 0x4e, 0x49, ++ 0xef, 0x50, 0xd8, 0x8f, 0xe0, 0x78, 0xd7, 0xfd, ++ 0xb9, 0x3b, 0xc9, 0xf2, 0x91, 0xc8, 0x25, 0xc8, ++ 0xa7, 0x63, 0x60, 0xce, 0x10, 0xcd, 0xc6, 0x7f, ++ 0xf8, 0x16, 0xf8, 0xe1, 0x0a, 0xd9, 0xde, 0x79, ++ 0x50, 0x33, 0xf2, 0x16, 0x0f, 0x17, 0xba, 0xb8, ++ 0x5d, 0xd8, 0xdf, 0x4e, 0x51, 0xa8, 0x39, 0xd0, ++ 0x85, 0xca, 0x46, 0x6a, 0x10, 0xa7, 0xa3, 0x88, ++ 0xef, 0x79, 0xb9, 0xf8, 0x24, 0xf3, 0xe0, 0x71, ++ 0x7b, 0x76, 0x28, 0x46, 0x3a, 0x3a, 0x1b, 0x91, ++ 0xb6, 0xd4, 0x3e, 0x23, 0xe5, 0x44, 0x15, 0xbf, ++ 0x60, 0x43, 0x9d, 0xa4, 0xbb, 0xd5, 0x5f, 0x89, ++ 0xeb, 0xef, 0x8e, 0xfd, 0xdd, 0xb4, 0x0d, 0x46, ++ 0xf0, 0x69, 0x23, 0x63, 0xae, 0x94, 0xf5, 0x5e, ++ 0xa5, 0xad, 0x13, 0x1c, 0x41, 0x76, 0xe6, 0x90, ++ 0xd6, 0x6d, 0xa2, 0x8f, 0x97, 0x4c, 0xa8, 0x0b, ++ 0xcf, 0x8d, 0x43, 0x2b, 0x9c, 0x9b, 0xc5, 0x58, ++ 0xa5, 0xb6, 0x95, 0x9a, 0xbf, 0x81, 0xc6, 0x54, ++ 0xc9, 0x66, 0x0c, 0xe5, 0x4f, 0x6a, 0x53, 0xa1, ++ 0xe5, 0x0c, 0xba, 0x31, 0xde, 0x34, 0x64, 0x73, ++ 0x8a, 0x3b, 0xbd, 0x92, 0x01, 0xdb, 0x71, 0x69, ++ 0xf3, 0x58, 0x99, 0xbc, 0xd1, 0xcb, 0x4a, 0x05, ++ 0xe2, 0x58, 0x9c, 0x25, 0x17, 0xcd, 0xdc, 0x83, ++ 0xb7, 0xff, 0xfb, 0x09, 0x61, 0xad, 0xbf, 0x13, ++ 0x5b, 0x5e, 0xed, 0x46, 0x82, 0x6f, 0x22, 0xd8, ++ 0x93, 0xa6, 0x85, 0x5b, 0x40, 0x39, 0x5c, 0xc5, ++ 0x9c ++}; ++static const u8 xdec_output001[] __initconst = { ++ 0x49, 0x6e, 0x74, 0x65, 0x72, 0x6e, 0x65, 0x74, ++ 0x2d, 0x44, 0x72, 0x61, 0x66, 0x74, 0x73, 0x20, ++ 0x61, 0x72, 0x65, 0x20, 0x64, 0x72, 0x61, 0x66, ++ 0x74, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x76, 0x61, 0x6c, 0x69, ++ 0x64, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x20, ++ 0x6d, 0x61, 0x78, 0x69, 0x6d, 0x75, 0x6d, 0x20, ++ 0x6f, 0x66, 0x20, 0x73, 0x69, 0x78, 0x20, 0x6d, ++ 0x6f, 0x6e, 0x74, 0x68, 0x73, 0x20, 0x61, 0x6e, ++ 0x64, 0x20, 0x6d, 0x61, 0x79, 0x20, 0x62, 0x65, ++ 0x20, 0x75, 0x70, 0x64, 0x61, 0x74, 0x65, 0x64, ++ 0x2c, 0x20, 0x72, 0x65, 0x70, 0x6c, 0x61, 0x63, ++ 0x65, 0x64, 0x2c, 0x20, 0x6f, 0x72, 0x20, 0x6f, ++ 0x62, 0x73, 0x6f, 0x6c, 0x65, 0x74, 0x65, 0x64, ++ 0x20, 0x62, 0x79, 0x20, 0x6f, 0x74, 0x68, 0x65, ++ 0x72, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, ++ 0x6e, 0x74, 0x73, 0x20, 0x61, 0x74, 0x20, 0x61, ++ 0x6e, 0x79, 0x20, 0x74, 0x69, 0x6d, 0x65, 0x2e, ++ 0x20, 0x49, 0x74, 0x20, 0x69, 0x73, 0x20, 0x69, ++ 0x6e, 0x61, 0x70, 0x70, 0x72, 0x6f, 0x70, 0x72, ++ 0x69, 0x61, 0x74, 0x65, 0x20, 0x74, 0x6f, 0x20, ++ 0x75, 0x73, 0x65, 0x20, 0x49, 0x6e, 0x74, 0x65, ++ 0x72, 0x6e, 0x65, 0x74, 0x2d, 0x44, 0x72, 0x61, ++ 0x66, 0x74, 0x73, 0x20, 0x61, 0x73, 0x20, 0x72, ++ 0x65, 0x66, 0x65, 0x72, 0x65, 0x6e, 0x63, 0x65, ++ 0x20, 0x6d, 0x61, 0x74, 0x65, 0x72, 0x69, 0x61, ++ 0x6c, 0x20, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20, ++ 0x63, 0x69, 0x74, 0x65, 0x20, 0x74, 0x68, 0x65, ++ 0x6d, 0x20, 0x6f, 0x74, 0x68, 0x65, 0x72, 0x20, ++ 0x74, 0x68, 0x61, 0x6e, 0x20, 0x61, 0x73, 0x20, ++ 0x2f, 0xe2, 0x80, 0x9c, 0x77, 0x6f, 0x72, 0x6b, ++ 0x20, 0x69, 0x6e, 0x20, 0x70, 0x72, 0x6f, 0x67, ++ 0x72, 0x65, 0x73, 0x73, 0x2e, 0x2f, 0xe2, 0x80, ++ 0x9d ++}; ++static const u8 xdec_assoc001[] __initconst = { ++ 0xf3, 0x33, 0x88, 0x86, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x4e, 0x91 ++}; ++static const u8 xdec_nonce001[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, ++ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17 ++}; ++static const u8 xdec_key001[] __initconst = { ++ 0x1c, 0x92, 0x40, 0xa5, 0xeb, 0x55, 0xd3, 0x8a, ++ 0xf3, 0x33, 0x88, 0x86, 0x04, 0xf6, 0xb5, 0xf0, ++ 0x47, 0x39, 0x17, 0xc1, 0x40, 0x2b, 0x80, 0x09, ++ 0x9d, 0xca, 0x5c, 0xbc, 0x20, 0x70, 0x75, 0xc0 ++}; ++ ++static const struct chacha20poly1305_testvec ++xchacha20poly1305_dec_vectors[] __initconst = { ++ { xdec_input001, xdec_output001, xdec_assoc001, xdec_nonce001, xdec_key001, ++ sizeof(xdec_input001), sizeof(xdec_assoc001), sizeof(xdec_nonce001) } ++}; ++ ++static void __init ++chacha20poly1305_selftest_encrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u8 *nonce, const size_t nonce_len, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ if (nonce_len == 8) ++ chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len, ++ get_unaligned_le64(nonce), key); ++ else ++ BUG(); ++} ++ ++static bool __init ++decryption_success(bool func_ret, bool expect_failure, int memcmp_result) ++{ ++ if (expect_failure) ++ return !func_ret; ++ return func_ret && !memcmp_result; ++} ++ ++bool __init chacha20poly1305_selftest(void) ++{ ++ enum { MAXIMUM_TEST_BUFFER_LEN = 1UL << 12 }; ++ size_t i; ++ u8 *computed_output = NULL, *heap_src = NULL; ++ bool success = true, ret; ++ ++ heap_src = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL); ++ computed_output = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL); ++ if (!heap_src || !computed_output) { ++ pr_err("chacha20poly1305 self-test malloc: FAIL\n"); ++ success = false; ++ goto out; ++ } ++ ++ for (i = 0; i < ARRAY_SIZE(chacha20poly1305_enc_vectors); ++i) { ++ memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); ++ chacha20poly1305_selftest_encrypt(computed_output, ++ chacha20poly1305_enc_vectors[i].input, ++ chacha20poly1305_enc_vectors[i].ilen, ++ chacha20poly1305_enc_vectors[i].assoc, ++ chacha20poly1305_enc_vectors[i].alen, ++ chacha20poly1305_enc_vectors[i].nonce, ++ chacha20poly1305_enc_vectors[i].nlen, ++ chacha20poly1305_enc_vectors[i].key); ++ if (memcmp(computed_output, ++ chacha20poly1305_enc_vectors[i].output, ++ chacha20poly1305_enc_vectors[i].ilen + ++ POLY1305_DIGEST_SIZE)) { ++ pr_err("chacha20poly1305 encryption self-test %zu: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } ++ ++ for (i = 0; i < ARRAY_SIZE(chacha20poly1305_dec_vectors); ++i) { ++ memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); ++ ret = chacha20poly1305_decrypt(computed_output, ++ chacha20poly1305_dec_vectors[i].input, ++ chacha20poly1305_dec_vectors[i].ilen, ++ chacha20poly1305_dec_vectors[i].assoc, ++ chacha20poly1305_dec_vectors[i].alen, ++ get_unaligned_le64(chacha20poly1305_dec_vectors[i].nonce), ++ chacha20poly1305_dec_vectors[i].key); ++ if (!decryption_success(ret, ++ chacha20poly1305_dec_vectors[i].failure, ++ memcmp(computed_output, ++ chacha20poly1305_dec_vectors[i].output, ++ chacha20poly1305_dec_vectors[i].ilen - ++ POLY1305_DIGEST_SIZE))) { ++ pr_err("chacha20poly1305 decryption self-test %zu: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } ++ ++ ++ for (i = 0; i < ARRAY_SIZE(xchacha20poly1305_enc_vectors); ++i) { ++ memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); ++ xchacha20poly1305_encrypt(computed_output, ++ xchacha20poly1305_enc_vectors[i].input, ++ xchacha20poly1305_enc_vectors[i].ilen, ++ xchacha20poly1305_enc_vectors[i].assoc, ++ xchacha20poly1305_enc_vectors[i].alen, ++ xchacha20poly1305_enc_vectors[i].nonce, ++ xchacha20poly1305_enc_vectors[i].key); ++ if (memcmp(computed_output, ++ xchacha20poly1305_enc_vectors[i].output, ++ xchacha20poly1305_enc_vectors[i].ilen + ++ POLY1305_DIGEST_SIZE)) { ++ pr_err("xchacha20poly1305 encryption self-test %zu: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } ++ for (i = 0; i < ARRAY_SIZE(xchacha20poly1305_dec_vectors); ++i) { ++ memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); ++ ret = xchacha20poly1305_decrypt(computed_output, ++ xchacha20poly1305_dec_vectors[i].input, ++ xchacha20poly1305_dec_vectors[i].ilen, ++ xchacha20poly1305_dec_vectors[i].assoc, ++ xchacha20poly1305_dec_vectors[i].alen, ++ xchacha20poly1305_dec_vectors[i].nonce, ++ xchacha20poly1305_dec_vectors[i].key); ++ if (!decryption_success(ret, ++ xchacha20poly1305_dec_vectors[i].failure, ++ memcmp(computed_output, ++ xchacha20poly1305_dec_vectors[i].output, ++ xchacha20poly1305_dec_vectors[i].ilen - ++ POLY1305_DIGEST_SIZE))) { ++ pr_err("xchacha20poly1305 decryption self-test %zu: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } ++ ++out: ++ kfree(heap_src); ++ kfree(computed_output); ++ return success; ++} +--- /dev/null ++++ b/lib/crypto/chacha20poly1305.c +@@ -0,0 +1,219 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is an implementation of the ChaCha20Poly1305 AEAD construction. ++ * ++ * Information: https://tools.ietf.org/html/rfc8439 ++ */ ++ ++#include ++#include ++#include ++#include ++ ++#include ++#include ++#include ++#include ++#include ++ ++#define CHACHA_KEY_WORDS (CHACHA_KEY_SIZE / sizeof(u32)) ++ ++bool __init chacha20poly1305_selftest(void); ++ ++static void chacha_load_key(u32 *k, const u8 *in) ++{ ++ k[0] = get_unaligned_le32(in); ++ k[1] = get_unaligned_le32(in + 4); ++ k[2] = get_unaligned_le32(in + 8); ++ k[3] = get_unaligned_le32(in + 12); ++ k[4] = get_unaligned_le32(in + 16); ++ k[5] = get_unaligned_le32(in + 20); ++ k[6] = get_unaligned_le32(in + 24); ++ k[7] = get_unaligned_le32(in + 28); ++} ++ ++static void xchacha_init(u32 *chacha_state, const u8 *key, const u8 *nonce) ++{ ++ u32 k[CHACHA_KEY_WORDS]; ++ u8 iv[CHACHA_IV_SIZE]; ++ ++ memset(iv, 0, 8); ++ memcpy(iv + 8, nonce + 16, 8); ++ ++ chacha_load_key(k, key); ++ ++ /* Compute the subkey given the original key and first 128 nonce bits */ ++ chacha_init(chacha_state, k, nonce); ++ hchacha_block(chacha_state, k, 20); ++ ++ chacha_init(chacha_state, k, iv); ++ ++ memzero_explicit(k, sizeof(k)); ++ memzero_explicit(iv, sizeof(iv)); ++} ++ ++static void ++__chacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, u32 *chacha_state) ++{ ++ const u8 *pad0 = page_address(ZERO_PAGE(0)); ++ struct poly1305_desc_ctx poly1305_state; ++ union { ++ u8 block0[POLY1305_KEY_SIZE]; ++ __le64 lens[2]; ++ } b; ++ ++ chacha_crypt(chacha_state, b.block0, pad0, sizeof(b.block0), 20); ++ poly1305_init(&poly1305_state, b.block0); ++ ++ poly1305_update(&poly1305_state, ad, ad_len); ++ if (ad_len & 0xf) ++ poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf)); ++ ++ chacha_crypt(chacha_state, dst, src, src_len, 20); ++ ++ poly1305_update(&poly1305_state, dst, src_len); ++ if (src_len & 0xf) ++ poly1305_update(&poly1305_state, pad0, 0x10 - (src_len & 0xf)); ++ ++ b.lens[0] = cpu_to_le64(ad_len); ++ b.lens[1] = cpu_to_le64(src_len); ++ poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens)); ++ ++ poly1305_final(&poly1305_state, dst + src_len); ++ ++ memzero_explicit(chacha_state, CHACHA_STATE_WORDS * sizeof(u32)); ++ memzero_explicit(&b, sizeof(b)); ++} ++ ++void chacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ u32 chacha_state[CHACHA_STATE_WORDS]; ++ u32 k[CHACHA_KEY_WORDS]; ++ __le64 iv[2]; ++ ++ chacha_load_key(k, key); ++ ++ iv[0] = 0; ++ iv[1] = cpu_to_le64(nonce); ++ ++ chacha_init(chacha_state, k, (u8 *)iv); ++ __chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len, chacha_state); ++ ++ memzero_explicit(iv, sizeof(iv)); ++ memzero_explicit(k, sizeof(k)); ++} ++EXPORT_SYMBOL(chacha20poly1305_encrypt); ++ ++void xchacha20poly1305_encrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE], ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ u32 chacha_state[CHACHA_STATE_WORDS]; ++ ++ xchacha_init(chacha_state, key, nonce); ++ __chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len, chacha_state); ++} ++EXPORT_SYMBOL(xchacha20poly1305_encrypt); ++ ++static bool ++__chacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, u32 *chacha_state) ++{ ++ const u8 *pad0 = page_address(ZERO_PAGE(0)); ++ struct poly1305_desc_ctx poly1305_state; ++ size_t dst_len; ++ int ret; ++ union { ++ u8 block0[POLY1305_KEY_SIZE]; ++ u8 mac[POLY1305_DIGEST_SIZE]; ++ __le64 lens[2]; ++ } b; ++ ++ if (unlikely(src_len < POLY1305_DIGEST_SIZE)) ++ return false; ++ ++ chacha_crypt(chacha_state, b.block0, pad0, sizeof(b.block0), 20); ++ poly1305_init(&poly1305_state, b.block0); ++ ++ poly1305_update(&poly1305_state, ad, ad_len); ++ if (ad_len & 0xf) ++ poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf)); ++ ++ dst_len = src_len - POLY1305_DIGEST_SIZE; ++ poly1305_update(&poly1305_state, src, dst_len); ++ if (dst_len & 0xf) ++ poly1305_update(&poly1305_state, pad0, 0x10 - (dst_len & 0xf)); ++ ++ b.lens[0] = cpu_to_le64(ad_len); ++ b.lens[1] = cpu_to_le64(dst_len); ++ poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens)); ++ ++ poly1305_final(&poly1305_state, b.mac); ++ ++ ret = crypto_memneq(b.mac, src + dst_len, POLY1305_DIGEST_SIZE); ++ if (likely(!ret)) ++ chacha_crypt(chacha_state, dst, src, dst_len, 20); ++ ++ memzero_explicit(&b, sizeof(b)); ++ ++ return !ret; ++} ++ ++bool chacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ u32 chacha_state[CHACHA_STATE_WORDS]; ++ u32 k[CHACHA_KEY_WORDS]; ++ __le64 iv[2]; ++ bool ret; ++ ++ chacha_load_key(k, key); ++ ++ iv[0] = 0; ++ iv[1] = cpu_to_le64(nonce); ++ ++ chacha_init(chacha_state, k, (u8 *)iv); ++ ret = __chacha20poly1305_decrypt(dst, src, src_len, ad, ad_len, ++ chacha_state); ++ ++ memzero_explicit(chacha_state, sizeof(chacha_state)); ++ memzero_explicit(iv, sizeof(iv)); ++ memzero_explicit(k, sizeof(k)); ++ return ret; ++} ++EXPORT_SYMBOL(chacha20poly1305_decrypt); ++ ++bool xchacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE], ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ u32 chacha_state[CHACHA_STATE_WORDS]; ++ ++ xchacha_init(chacha_state, key, nonce); ++ return __chacha20poly1305_decrypt(dst, src, src_len, ad, ad_len, ++ chacha_state); ++} ++EXPORT_SYMBOL(xchacha20poly1305_decrypt); ++ ++static int __init mod_init(void) ++{ ++ if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && ++ WARN_ON(!chacha20poly1305_selftest())) ++ return -ENODEV; ++ return 0; ++} ++ ++module_init(mod_init); ++MODULE_LICENSE("GPL v2"); ++MODULE_DESCRIPTION("ChaCha20Poly1305 AEAD construction"); ++MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0033-crypto-lib-chacha20poly1305-reimplement-crypt_from_s.patch b/target/linux/generic/backport-5.4/080-wireguard-0033-crypto-lib-chacha20poly1305-reimplement-crypt_from_s.patch new file mode 100644 index 0000000000..a7811eb26a --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0033-crypto-lib-chacha20poly1305-reimplement-crypt_from_s.patch @@ -0,0 +1,295 @@ +From b7af0c213ba3afe27da21845419756aec63b43b4 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 8 Nov 2019 13:22:40 +0100 +Subject: [PATCH 033/124] crypto: lib/chacha20poly1305 - reimplement + crypt_from_sg() routine + +commit d95312a3ccc0cd544d374be2fc45aeaa803e5fd9 upstream. + +Reimplement the library routines to perform chacha20poly1305 en/decryption +on scatterlists, without [ab]using the [deprecated] blkcipher interface, +which is rather heavyweight and does things we don't really need. + +Instead, we use the sg_miter API in a novel and clever way, to iterate +over the scatterlist in-place (i.e., source == destination, which is the +only way this library is expected to be used). That way, we don't have to +iterate over two scatterlists in parallel. + +Another optimization is that, instead of relying on the blkcipher walker +to present the input in suitable chunks, we recognize that ChaCha is a +streamcipher, and so we can simply deal with partial blocks by keeping a +block of cipherstream on the stack and use crypto_xor() to mix it with +the in/output. + +Finally, we omit the scatterwalk_and_copy() call if the last element of +the scatterlist covers the MAC as well (which is the common case), +avoiding the need to walk the scatterlist and kmap() the page twice. + +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + include/crypto/chacha20poly1305.h | 11 ++ + lib/crypto/chacha20poly1305-selftest.c | 45 ++++++++ + lib/crypto/chacha20poly1305.c | 150 +++++++++++++++++++++++++ + 3 files changed, 206 insertions(+) + +--- a/include/crypto/chacha20poly1305.h ++++ b/include/crypto/chacha20poly1305.h +@@ -7,6 +7,7 @@ + #define __CHACHA20POLY1305_H + + #include ++#include + + enum chacha20poly1305_lengths { + XCHACHA20POLY1305_NONCE_SIZE = 24, +@@ -34,4 +35,14 @@ bool __must_check xchacha20poly1305_decr + const size_t ad_len, const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE], + const u8 key[CHACHA20POLY1305_KEY_SIZE]); + ++bool chacha20poly1305_encrypt_sg_inplace(struct scatterlist *src, size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]); ++ ++bool chacha20poly1305_decrypt_sg_inplace(struct scatterlist *src, size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]); ++ + #endif /* __CHACHA20POLY1305_H */ +--- a/lib/crypto/chacha20poly1305-selftest.c ++++ b/lib/crypto/chacha20poly1305-selftest.c +@@ -7250,6 +7250,7 @@ bool __init chacha20poly1305_selftest(vo + enum { MAXIMUM_TEST_BUFFER_LEN = 1UL << 12 }; + size_t i; + u8 *computed_output = NULL, *heap_src = NULL; ++ struct scatterlist sg_src; + bool success = true, ret; + + heap_src = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL); +@@ -7280,6 +7281,29 @@ bool __init chacha20poly1305_selftest(vo + } + } + ++ for (i = 0; i < ARRAY_SIZE(chacha20poly1305_enc_vectors); ++i) { ++ if (chacha20poly1305_enc_vectors[i].nlen != 8) ++ continue; ++ memcpy(heap_src, chacha20poly1305_enc_vectors[i].input, ++ chacha20poly1305_enc_vectors[i].ilen); ++ sg_init_one(&sg_src, heap_src, ++ chacha20poly1305_enc_vectors[i].ilen + POLY1305_DIGEST_SIZE); ++ chacha20poly1305_encrypt_sg_inplace(&sg_src, ++ chacha20poly1305_enc_vectors[i].ilen, ++ chacha20poly1305_enc_vectors[i].assoc, ++ chacha20poly1305_enc_vectors[i].alen, ++ get_unaligned_le64(chacha20poly1305_enc_vectors[i].nonce), ++ chacha20poly1305_enc_vectors[i].key); ++ if (memcmp(heap_src, ++ chacha20poly1305_enc_vectors[i].output, ++ chacha20poly1305_enc_vectors[i].ilen + ++ POLY1305_DIGEST_SIZE)) { ++ pr_err("chacha20poly1305 sg encryption self-test %zu: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } ++ + for (i = 0; i < ARRAY_SIZE(chacha20poly1305_dec_vectors); ++i) { + memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); + ret = chacha20poly1305_decrypt(computed_output, +@@ -7301,6 +7325,27 @@ bool __init chacha20poly1305_selftest(vo + } + } + ++ for (i = 0; i < ARRAY_SIZE(chacha20poly1305_dec_vectors); ++i) { ++ memcpy(heap_src, chacha20poly1305_dec_vectors[i].input, ++ chacha20poly1305_dec_vectors[i].ilen); ++ sg_init_one(&sg_src, heap_src, ++ chacha20poly1305_dec_vectors[i].ilen); ++ ret = chacha20poly1305_decrypt_sg_inplace(&sg_src, ++ chacha20poly1305_dec_vectors[i].ilen, ++ chacha20poly1305_dec_vectors[i].assoc, ++ chacha20poly1305_dec_vectors[i].alen, ++ get_unaligned_le64(chacha20poly1305_dec_vectors[i].nonce), ++ chacha20poly1305_dec_vectors[i].key); ++ if (!decryption_success(ret, ++ chacha20poly1305_dec_vectors[i].failure, ++ memcmp(heap_src, chacha20poly1305_dec_vectors[i].output, ++ chacha20poly1305_dec_vectors[i].ilen - ++ POLY1305_DIGEST_SIZE))) { ++ pr_err("chacha20poly1305 sg decryption self-test %zu: FAIL\n", ++ i + 1); ++ success = false; ++ } ++ } + + for (i = 0; i < ARRAY_SIZE(xchacha20poly1305_enc_vectors); ++i) { + memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); +--- a/lib/crypto/chacha20poly1305.c ++++ b/lib/crypto/chacha20poly1305.c +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -205,6 +206,155 @@ bool xchacha20poly1305_decrypt(u8 *dst, + } + EXPORT_SYMBOL(xchacha20poly1305_decrypt); + ++static ++bool chacha20poly1305_crypt_sg_inplace(struct scatterlist *src, ++ const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE], ++ int encrypt) ++{ ++ const u8 *pad0 = page_address(ZERO_PAGE(0)); ++ struct poly1305_desc_ctx poly1305_state; ++ u32 chacha_state[CHACHA_STATE_WORDS]; ++ struct sg_mapping_iter miter; ++ size_t partial = 0; ++ unsigned int flags; ++ bool ret = true; ++ int sl; ++ union { ++ struct { ++ u32 k[CHACHA_KEY_WORDS]; ++ __le64 iv[2]; ++ }; ++ u8 block0[POLY1305_KEY_SIZE]; ++ u8 chacha_stream[CHACHA_BLOCK_SIZE]; ++ struct { ++ u8 mac[2][POLY1305_DIGEST_SIZE]; ++ }; ++ __le64 lens[2]; ++ } b __aligned(16); ++ ++ chacha_load_key(b.k, key); ++ ++ b.iv[0] = 0; ++ b.iv[1] = cpu_to_le64(nonce); ++ ++ chacha_init(chacha_state, b.k, (u8 *)b.iv); ++ chacha_crypt(chacha_state, b.block0, pad0, sizeof(b.block0), 20); ++ poly1305_init(&poly1305_state, b.block0); ++ ++ if (unlikely(ad_len)) { ++ poly1305_update(&poly1305_state, ad, ad_len); ++ if (ad_len & 0xf) ++ poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf)); ++ } ++ ++ flags = SG_MITER_TO_SG; ++ if (!preemptible()) ++ flags |= SG_MITER_ATOMIC; ++ ++ sg_miter_start(&miter, src, sg_nents(src), flags); ++ ++ for (sl = src_len; sl > 0 && sg_miter_next(&miter); sl -= miter.length) { ++ u8 *addr = miter.addr; ++ size_t length = min_t(size_t, sl, miter.length); ++ ++ if (!encrypt) ++ poly1305_update(&poly1305_state, addr, length); ++ ++ if (unlikely(partial)) { ++ size_t l = min(length, CHACHA_BLOCK_SIZE - partial); ++ ++ crypto_xor(addr, b.chacha_stream + partial, l); ++ partial = (partial + l) & (CHACHA_BLOCK_SIZE - 1); ++ ++ addr += l; ++ length -= l; ++ } ++ ++ if (likely(length >= CHACHA_BLOCK_SIZE || length == sl)) { ++ size_t l = length; ++ ++ if (unlikely(length < sl)) ++ l &= ~(CHACHA_BLOCK_SIZE - 1); ++ chacha_crypt(chacha_state, addr, addr, l, 20); ++ addr += l; ++ length -= l; ++ } ++ ++ if (unlikely(length > 0)) { ++ chacha_crypt(chacha_state, b.chacha_stream, pad0, ++ CHACHA_BLOCK_SIZE, 20); ++ crypto_xor(addr, b.chacha_stream, length); ++ partial = length; ++ } ++ ++ if (encrypt) ++ poly1305_update(&poly1305_state, miter.addr, ++ min_t(size_t, sl, miter.length)); ++ } ++ ++ if (src_len & 0xf) ++ poly1305_update(&poly1305_state, pad0, 0x10 - (src_len & 0xf)); ++ ++ b.lens[0] = cpu_to_le64(ad_len); ++ b.lens[1] = cpu_to_le64(src_len); ++ poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens)); ++ ++ if (likely(sl <= -POLY1305_DIGEST_SIZE)) { ++ if (encrypt) { ++ poly1305_final(&poly1305_state, ++ miter.addr + miter.length + sl); ++ ret = true; ++ } else { ++ poly1305_final(&poly1305_state, b.mac[0]); ++ ret = !crypto_memneq(b.mac[0], ++ miter.addr + miter.length + sl, ++ POLY1305_DIGEST_SIZE); ++ } ++ } ++ ++ sg_miter_stop(&miter); ++ ++ if (unlikely(sl > -POLY1305_DIGEST_SIZE)) { ++ poly1305_final(&poly1305_state, b.mac[1]); ++ scatterwalk_map_and_copy(b.mac[encrypt], src, src_len, ++ sizeof(b.mac[1]), encrypt); ++ ret = encrypt || ++ !crypto_memneq(b.mac[0], b.mac[1], POLY1305_DIGEST_SIZE); ++ } ++ ++ memzero_explicit(chacha_state, sizeof(chacha_state)); ++ memzero_explicit(&b, sizeof(b)); ++ ++ return ret; ++} ++ ++bool chacha20poly1305_encrypt_sg_inplace(struct scatterlist *src, size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ return chacha20poly1305_crypt_sg_inplace(src, src_len, ad, ad_len, ++ nonce, key, 1); ++} ++EXPORT_SYMBOL(chacha20poly1305_encrypt_sg_inplace); ++ ++bool chacha20poly1305_decrypt_sg_inplace(struct scatterlist *src, size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u64 nonce, ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ if (unlikely(src_len < POLY1305_DIGEST_SIZE)) ++ return false; ++ ++ return chacha20poly1305_crypt_sg_inplace(src, ++ src_len - POLY1305_DIGEST_SIZE, ++ ad, ad_len, nonce, key, 0); ++} ++EXPORT_SYMBOL(chacha20poly1305_decrypt_sg_inplace); ++ + static int __init mod_init(void) + { + if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && diff --git a/target/linux/generic/backport-5.4/080-wireguard-0034-crypto-chacha_generic-remove-unnecessary-setkey-func.patch b/target/linux/generic/backport-5.4/080-wireguard-0034-crypto-chacha_generic-remove-unnecessary-setkey-func.patch new file mode 100644 index 0000000000..493da3a097 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0034-crypto-chacha_generic-remove-unnecessary-setkey-func.patch @@ -0,0 +1,68 @@ +From d59a7ffb8aa6735586929c5a2d90e142c6d6952d Mon Sep 17 00:00:00 2001 +From: Eric Biggers +Date: Sun, 17 Nov 2019 23:21:29 -0800 +Subject: [PATCH 034/124] crypto: chacha_generic - remove unnecessary setkey() + functions + +commit 2043323a799a660bc84bbee404cf7a2617ec6157 upstream. + +Use chacha20_setkey() and chacha12_setkey() from + instead of defining them again in +chacha_generic.c. + +Signed-off-by: Eric Biggers +Acked-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/chacha_generic.c | 18 +++--------------- + 1 file changed, 3 insertions(+), 15 deletions(-) + +--- a/crypto/chacha_generic.c ++++ b/crypto/chacha_generic.c +@@ -37,18 +37,6 @@ static int chacha_stream_xor(struct skci + return err; + } + +-static int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize) +-{ +- return chacha_setkey(tfm, key, keysize, 20); +-} +- +-static int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, +- unsigned int keysize) +-{ +- return chacha_setkey(tfm, key, keysize, 12); +-} +- + static int crypto_chacha_crypt(struct skcipher_request *req) + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); +@@ -91,7 +79,7 @@ static struct skcipher_alg algs[] = { + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha20_setkey, ++ .setkey = chacha20_setkey, + .encrypt = crypto_chacha_crypt, + .decrypt = crypto_chacha_crypt, + }, { +@@ -106,7 +94,7 @@ static struct skcipher_alg algs[] = { + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha20_setkey, ++ .setkey = chacha20_setkey, + .encrypt = crypto_xchacha_crypt, + .decrypt = crypto_xchacha_crypt, + }, { +@@ -121,7 +109,7 @@ static struct skcipher_alg algs[] = { + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, +- .setkey = crypto_chacha12_setkey, ++ .setkey = chacha12_setkey, + .encrypt = crypto_xchacha_crypt, + .decrypt = crypto_xchacha_crypt, + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0035-crypto-x86-chacha-only-unregister-algorithms-if-regi.patch b/target/linux/generic/backport-5.4/080-wireguard-0035-crypto-x86-chacha-only-unregister-algorithms-if-regi.patch new file mode 100644 index 0000000000..f423acb90b --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0035-crypto-x86-chacha-only-unregister-algorithms-if-regi.patch @@ -0,0 +1,32 @@ +From 4fa6b436d97e44deef404676d150ed4c13d63bba Mon Sep 17 00:00:00 2001 +From: Eric Biggers +Date: Sun, 17 Nov 2019 23:21:58 -0800 +Subject: [PATCH 035/124] crypto: x86/chacha - only unregister algorithms if + registered + +commit b62755aed3a3f5ca9edd2718339ccea3b6bbbe57 upstream. + +It's not valid to call crypto_unregister_skciphers() without a prior +call to crypto_register_skciphers(). + +Fixes: 84e03fa39fbe ("crypto: x86/chacha - expose SIMD ChaCha routine as library function") +Signed-off-by: Eric Biggers +Acked-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/chacha_glue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -304,7 +304,8 @@ static int __init chacha_simd_mod_init(v + + static void __exit chacha_simd_mod_fini(void) + { +- crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); ++ if (boot_cpu_has(X86_FEATURE_SSSE3)) ++ crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + } + + module_init(chacha_simd_mod_init); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0036-crypto-lib-chacha20poly1305-use-chacha20_crypt.patch b/target/linux/generic/backport-5.4/080-wireguard-0036-crypto-lib-chacha20poly1305-use-chacha20_crypt.patch new file mode 100644 index 0000000000..1f6d22ee35 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0036-crypto-lib-chacha20poly1305-use-chacha20_crypt.patch @@ -0,0 +1,83 @@ +From 41d7b5227dcad70f5bd6471e9620fe3c8b3db300 Mon Sep 17 00:00:00 2001 +From: Eric Biggers +Date: Sun, 17 Nov 2019 23:22:16 -0800 +Subject: [PATCH 036/124] crypto: lib/chacha20poly1305 - use chacha20_crypt() + +commit 413808b71e6204b0cc1eeaa77960f7c3cd381d33 upstream. + +Use chacha20_crypt() instead of chacha_crypt(), since it's not really +appropriate for users of the ChaCha library API to be passing the number +of rounds as an argument. + +Signed-off-by: Eric Biggers +Acked-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/chacha20poly1305.c | 16 ++++++++-------- + 1 file changed, 8 insertions(+), 8 deletions(-) + +--- a/lib/crypto/chacha20poly1305.c ++++ b/lib/crypto/chacha20poly1305.c +@@ -66,14 +66,14 @@ __chacha20poly1305_encrypt(u8 *dst, cons + __le64 lens[2]; + } b; + +- chacha_crypt(chacha_state, b.block0, pad0, sizeof(b.block0), 20); ++ chacha20_crypt(chacha_state, b.block0, pad0, sizeof(b.block0)); + poly1305_init(&poly1305_state, b.block0); + + poly1305_update(&poly1305_state, ad, ad_len); + if (ad_len & 0xf) + poly1305_update(&poly1305_state, pad0, 0x10 - (ad_len & 0xf)); + +- chacha_crypt(chacha_state, dst, src, src_len, 20); ++ chacha20_crypt(chacha_state, dst, src, src_len); + + poly1305_update(&poly1305_state, dst, src_len); + if (src_len & 0xf) +@@ -140,7 +140,7 @@ __chacha20poly1305_decrypt(u8 *dst, cons + if (unlikely(src_len < POLY1305_DIGEST_SIZE)) + return false; + +- chacha_crypt(chacha_state, b.block0, pad0, sizeof(b.block0), 20); ++ chacha20_crypt(chacha_state, b.block0, pad0, sizeof(b.block0)); + poly1305_init(&poly1305_state, b.block0); + + poly1305_update(&poly1305_state, ad, ad_len); +@@ -160,7 +160,7 @@ __chacha20poly1305_decrypt(u8 *dst, cons + + ret = crypto_memneq(b.mac, src + dst_len, POLY1305_DIGEST_SIZE); + if (likely(!ret)) +- chacha_crypt(chacha_state, dst, src, dst_len, 20); ++ chacha20_crypt(chacha_state, dst, src, dst_len); + + memzero_explicit(&b, sizeof(b)); + +@@ -241,7 +241,7 @@ bool chacha20poly1305_crypt_sg_inplace(s + b.iv[1] = cpu_to_le64(nonce); + + chacha_init(chacha_state, b.k, (u8 *)b.iv); +- chacha_crypt(chacha_state, b.block0, pad0, sizeof(b.block0), 20); ++ chacha20_crypt(chacha_state, b.block0, pad0, sizeof(b.block0)); + poly1305_init(&poly1305_state, b.block0); + + if (unlikely(ad_len)) { +@@ -278,14 +278,14 @@ bool chacha20poly1305_crypt_sg_inplace(s + + if (unlikely(length < sl)) + l &= ~(CHACHA_BLOCK_SIZE - 1); +- chacha_crypt(chacha_state, addr, addr, l, 20); ++ chacha20_crypt(chacha_state, addr, addr, l); + addr += l; + length -= l; + } + + if (unlikely(length > 0)) { +- chacha_crypt(chacha_state, b.chacha_stream, pad0, +- CHACHA_BLOCK_SIZE, 20); ++ chacha20_crypt(chacha_state, b.chacha_stream, pad0, ++ CHACHA_BLOCK_SIZE); + crypto_xor(addr, b.chacha_stream, length); + partial = length; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0037-crypto-arch-conditionalize-crypto-api-in-arch-glue-f.patch b/target/linux/generic/backport-5.4/080-wireguard-0037-crypto-arch-conditionalize-crypto-api-in-arch-glue-f.patch new file mode 100644 index 0000000000..ab04cecf05 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0037-crypto-arch-conditionalize-crypto-api-in-arch-glue-f.patch @@ -0,0 +1,275 @@ +From f23fdc58a0a08afada84fe4910279ec3d8d085e7 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 25 Nov 2019 11:31:12 +0100 +Subject: [PATCH 037/124] crypto: arch - conditionalize crypto api in arch glue + for lib code + +commit 8394bfec51e0e565556101bcc4e2fe7551104cd8 upstream. + +For glue code that's used by Zinc, the actual Crypto API functions might +not necessarily exist, and don't need to exist either. Before this +patch, there are valid build configurations that lead to a unbuildable +kernel. This fixes it to conditionalize those symbols on the existence +of the proper config entry. + +Signed-off-by: Jason A. Donenfeld +Acked-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/chacha-glue.c | 26 ++++++++++++++++---------- + arch/arm/crypto/curve25519-glue.c | 5 +++-- + arch/arm/crypto/poly1305-glue.c | 9 ++++++--- + arch/arm64/crypto/chacha-neon-glue.c | 5 +++-- + arch/arm64/crypto/poly1305-glue.c | 5 +++-- + arch/mips/crypto/chacha-glue.c | 6 ++++-- + arch/mips/crypto/poly1305-glue.c | 6 ++++-- + arch/x86/crypto/blake2s-glue.c | 6 ++++-- + arch/x86/crypto/chacha_glue.c | 5 +++-- + arch/x86/crypto/curve25519-x86_64.c | 7 ++++--- + arch/x86/crypto/poly1305_glue.c | 5 +++-- + 11 files changed, 53 insertions(+), 32 deletions(-) + +--- a/arch/arm/crypto/chacha-glue.c ++++ b/arch/arm/crypto/chacha-glue.c +@@ -286,11 +286,13 @@ static struct skcipher_alg neon_algs[] = + + static int __init chacha_simd_mod_init(void) + { +- int err; ++ int err = 0; + +- err = crypto_register_skciphers(arm_algs, ARRAY_SIZE(arm_algs)); +- if (err) +- return err; ++ if (IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER)) { ++ 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; +@@ -310,18 +312,22 @@ static int __init chacha_simd_mod_init(v + static_branch_enable(&use_neon); + } + +- err = crypto_register_skciphers(neon_algs, ARRAY_SIZE(neon_algs)); +- if (err) +- crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs)); ++ if (IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER)) { ++ 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) + { +- 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)); ++ if (IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER)) { ++ 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); +--- a/arch/arm/crypto/curve25519-glue.c ++++ b/arch/arm/crypto/curve25519-glue.c +@@ -108,14 +108,15 @@ static int __init mod_init(void) + { + if (elf_hwcap & HWCAP_NEON) { + static_branch_enable(&have_neon); +- return crypto_register_kpp(&curve25519_alg); ++ return IS_REACHABLE(CONFIG_CRYPTO_KPP) ? ++ crypto_register_kpp(&curve25519_alg) : 0; + } + return 0; + } + + static void __exit mod_exit(void) + { +- if (elf_hwcap & HWCAP_NEON) ++ if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && elf_hwcap & HWCAP_NEON) + crypto_unregister_kpp(&curve25519_alg); + } + +--- a/arch/arm/crypto/poly1305-glue.c ++++ b/arch/arm/crypto/poly1305-glue.c +@@ -249,16 +249,19 @@ static int __init arm_poly1305_mod_init( + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && + (elf_hwcap & HWCAP_NEON)) + static_branch_enable(&have_neon); +- else ++ else if (IS_REACHABLE(CONFIG_CRYPTO_HASH)) + /* register only the first entry */ + return crypto_register_shash(&arm_poly1305_algs[0]); + +- return crypto_register_shashes(arm_poly1305_algs, +- ARRAY_SIZE(arm_poly1305_algs)); ++ 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; +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -211,12 +211,13 @@ static int __init chacha_simd_mod_init(v + + static_branch_enable(&have_neon); + +- return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); ++ return IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER) ? ++ crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0; + } + + static void __exit chacha_simd_mod_fini(void) + { +- if (cpu_have_named_feature(ASIMD)) ++ if (IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER) && cpu_have_named_feature(ASIMD)) + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + } + +--- a/arch/arm64/crypto/poly1305-glue.c ++++ b/arch/arm64/crypto/poly1305-glue.c +@@ -220,12 +220,13 @@ static int __init neon_poly1305_mod_init + + static_branch_enable(&have_neon); + +- return crypto_register_shash(&neon_poly1305_alg); ++ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? ++ crypto_register_shash(&neon_poly1305_alg) : 0; + } + + static void __exit neon_poly1305_mod_exit(void) + { +- if (cpu_have_named_feature(ASIMD)) ++ if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && cpu_have_named_feature(ASIMD)) + crypto_unregister_shash(&neon_poly1305_alg); + } + +--- a/arch/mips/crypto/chacha-glue.c ++++ b/arch/mips/crypto/chacha-glue.c +@@ -128,12 +128,14 @@ static struct skcipher_alg algs[] = { + + static int __init chacha_simd_mod_init(void) + { +- return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); ++ return IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER) ? ++ crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0; + } + + static void __exit chacha_simd_mod_fini(void) + { +- crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); ++ if (IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER)) ++ crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + } + + module_init(chacha_simd_mod_init); +--- a/arch/mips/crypto/poly1305-glue.c ++++ b/arch/mips/crypto/poly1305-glue.c +@@ -187,12 +187,14 @@ static struct shash_alg mips_poly1305_al + + static int __init mips_poly1305_mod_init(void) + { +- return crypto_register_shash(&mips_poly1305_alg); ++ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? ++ crypto_register_shash(&mips_poly1305_alg) : 0; + } + + static void __exit mips_poly1305_mod_exit(void) + { +- crypto_unregister_shash(&mips_poly1305_alg); ++ if (IS_REACHABLE(CONFIG_CRYPTO_HASH)) ++ crypto_unregister_shash(&mips_poly1305_alg); + } + + module_init(mips_poly1305_mod_init); +--- a/arch/x86/crypto/blake2s-glue.c ++++ b/arch/x86/crypto/blake2s-glue.c +@@ -210,12 +210,14 @@ static int __init blake2s_mod_init(void) + XFEATURE_MASK_AVX512, NULL)) + static_branch_enable(&blake2s_use_avx512); + +- return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); ++ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? ++ crypto_register_shashes(blake2s_algs, ++ ARRAY_SIZE(blake2s_algs)) : 0; + } + + static void __exit blake2s_mod_exit(void) + { +- if (boot_cpu_has(X86_FEATURE_SSSE3)) ++ if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs)); + } + +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -299,12 +299,13 @@ static int __init chacha_simd_mod_init(v + boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */ + static_branch_enable(&chacha_use_avx512vl); + } +- return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); ++ return IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER) ? ++ crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0; + } + + static void __exit chacha_simd_mod_fini(void) + { +- if (boot_cpu_has(X86_FEATURE_SSSE3)) ++ if (IS_REACHABLE(CONFIG_CRYPTO_BLKCIPHER) && boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); + } + +--- a/arch/x86/crypto/curve25519-x86_64.c ++++ b/arch/x86/crypto/curve25519-x86_64.c +@@ -2457,13 +2457,14 @@ static int __init curve25519_mod_init(vo + static_branch_enable(&curve25519_use_adx); + else + return 0; +- return crypto_register_kpp(&curve25519_alg); ++ return IS_REACHABLE(CONFIG_CRYPTO_KPP) ? ++ crypto_register_kpp(&curve25519_alg) : 0; + } + + static void __exit curve25519_mod_exit(void) + { +- if (boot_cpu_has(X86_FEATURE_BMI2) || +- boot_cpu_has(X86_FEATURE_ADX)) ++ if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && ++ (boot_cpu_has(X86_FEATURE_BMI2) || boot_cpu_has(X86_FEATURE_ADX))) + crypto_unregister_kpp(&curve25519_alg); + } + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -224,12 +224,13 @@ static int __init poly1305_simd_mod_init + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) + static_branch_enable(&poly1305_use_avx2); + +- return crypto_register_shash(&alg); ++ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0; + } + + static void __exit poly1305_simd_mod_exit(void) + { +- crypto_unregister_shash(&alg); ++ if (IS_REACHABLE(CONFIG_CRYPTO_HASH)) ++ crypto_unregister_shash(&alg); + } + + module_init(poly1305_simd_mod_init); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0038-crypto-chacha-fix-warning-message-in-header-file.patch b/target/linux/generic/backport-5.4/080-wireguard-0038-crypto-chacha-fix-warning-message-in-header-file.patch new file mode 100644 index 0000000000..6170e7b76e --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0038-crypto-chacha-fix-warning-message-in-header-file.patch @@ -0,0 +1,35 @@ +From 61ad3d7b564718b9810b8112a6d2e9ad6405b167 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Valdis=20Kl=C4=93tnieks?= +Date: Thu, 5 Dec 2019 20:58:36 -0500 +Subject: [PATCH 038/124] crypto: chacha - fix warning message in header file + +commit 579d705cd64e44f3fcda1a6cfd5f37468a5ddf63 upstream. + +Building with W=1 causes a warning: + + CC [M] arch/x86/crypto/chacha_glue.o +In file included from arch/x86/crypto/chacha_glue.c:10: +./include/crypto/internal/chacha.h:37:1: warning: 'inline' is not at beginning of declaration [-Wold-style-declaration] + 37 | static int inline chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, + | ^~~~~~ + +Straighten out the order to match the rest of the header file. + +Signed-off-by: Valdis Kletnieks +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + include/crypto/internal/chacha.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/include/crypto/internal/chacha.h ++++ b/include/crypto/internal/chacha.h +@@ -34,7 +34,7 @@ static inline int chacha20_setkey(struct + return chacha_setkey(tfm, key, keysize, 20); + } + +-static int inline chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, ++static inline int chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize) + { + return chacha_setkey(tfm, key, keysize, 12); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0039-crypto-arm-curve25519-add-arch-specific-key-generati.patch b/target/linux/generic/backport-5.4/080-wireguard-0039-crypto-arm-curve25519-add-arch-specific-key-generati.patch new file mode 100644 index 0000000000..19d1338594 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0039-crypto-arm-curve25519-add-arch-specific-key-generati.patch @@ -0,0 +1,38 @@ +From 610442255536492764547dddde0289d46a9566db Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 11 Dec 2019 10:26:39 +0100 +Subject: [PATCH 039/124] crypto: arm/curve25519 - add arch-specific key + generation function + +commit 84faa307249b341f6ad8de3e1869d77a65e26669 upstream. + +Somehow this was forgotten when Zinc was being split into oddly shaped +pieces, resulting in linker errors. The x86_64 glue has a specific key +generation implementation, but the Arm one does not. However, it can +still receive the NEON speedups by calling the ordinary DH function +using the base point. + +Signed-off-by: Jason A. Donenfeld +Acked-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/curve25519-glue.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/arch/arm/crypto/curve25519-glue.c ++++ b/arch/arm/crypto/curve25519-glue.c +@@ -38,6 +38,13 @@ void curve25519_arch(u8 out[CURVE25519_K + } + 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) + { diff --git a/target/linux/generic/backport-5.4/080-wireguard-0040-crypto-lib-curve25519-re-add-selftests.patch b/target/linux/generic/backport-5.4/080-wireguard-0040-crypto-lib-curve25519-re-add-selftests.patch new file mode 100644 index 0000000000..e4de170a56 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0040-crypto-lib-curve25519-re-add-selftests.patch @@ -0,0 +1,1387 @@ +From 63b5e3c85a71705225aa3eab04127b3449a4ab5a Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 16 Dec 2019 19:53:26 +0100 +Subject: [PATCH 040/124] crypto: lib/curve25519 - re-add selftests + +commit aa127963f1cab2b93c74c9b128a84610203fb674 upstream. + +Somehow these were dropped when Zinc was being integrated, which is +problematic, because testing the library interface for Curve25519 is +important.. This commit simply adds them back and wires them in in the +same way that the blake2s selftests are wired in. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/Makefile | 1 + + lib/crypto/curve25519-selftest.c | 1321 ++++++++++++++++++++++++++++++ + lib/crypto/curve25519.c | 17 + + 3 files changed, 1339 insertions(+) + create mode 100644 lib/crypto/curve25519-selftest.c + +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -36,4 +36,5 @@ libsha256-y := sha256.o + ifneq ($(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS),y) + libblake2s-y += blake2s-selftest.o + libchacha20poly1305-y += chacha20poly1305-selftest.o ++libcurve25519-y += curve25519-selftest.o + endif +--- /dev/null ++++ b/lib/crypto/curve25519-selftest.c +@@ -0,0 +1,1321 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include ++ ++struct curve25519_test_vector { ++ u8 private[CURVE25519_KEY_SIZE]; ++ u8 public[CURVE25519_KEY_SIZE]; ++ u8 result[CURVE25519_KEY_SIZE]; ++ bool valid; ++}; ++static const struct curve25519_test_vector curve25519_test_vectors[] __initconst = { ++ { ++ .private = { 0x77, 0x07, 0x6d, 0x0a, 0x73, 0x18, 0xa5, 0x7d, ++ 0x3c, 0x16, 0xc1, 0x72, 0x51, 0xb2, 0x66, 0x45, ++ 0xdf, 0x4c, 0x2f, 0x87, 0xeb, 0xc0, 0x99, 0x2a, ++ 0xb1, 0x77, 0xfb, 0xa5, 0x1d, 0xb9, 0x2c, 0x2a }, ++ .public = { 0xde, 0x9e, 0xdb, 0x7d, 0x7b, 0x7d, 0xc1, 0xb4, ++ 0xd3, 0x5b, 0x61, 0xc2, 0xec, 0xe4, 0x35, 0x37, ++ 0x3f, 0x83, 0x43, 0xc8, 0x5b, 0x78, 0x67, 0x4d, ++ 0xad, 0xfc, 0x7e, 0x14, 0x6f, 0x88, 0x2b, 0x4f }, ++ .result = { 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1, ++ 0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25, ++ 0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33, ++ 0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 }, ++ .valid = true ++ }, ++ { ++ .private = { 0x5d, 0xab, 0x08, 0x7e, 0x62, 0x4a, 0x8a, 0x4b, ++ 0x79, 0xe1, 0x7f, 0x8b, 0x83, 0x80, 0x0e, 0xe6, ++ 0x6f, 0x3b, 0xb1, 0x29, 0x26, 0x18, 0xb6, 0xfd, ++ 0x1c, 0x2f, 0x8b, 0x27, 0xff, 0x88, 0xe0, 0xeb }, ++ .public = { 0x85, 0x20, 0xf0, 0x09, 0x89, 0x30, 0xa7, 0x54, ++ 0x74, 0x8b, 0x7d, 0xdc, 0xb4, 0x3e, 0xf7, 0x5a, ++ 0x0d, 0xbf, 0x3a, 0x0d, 0x26, 0x38, 0x1a, 0xf4, ++ 0xeb, 0xa4, 0xa9, 0x8e, 0xaa, 0x9b, 0x4e, 0x6a }, ++ .result = { 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1, ++ 0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25, ++ 0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33, ++ 0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 }, ++ .valid = true ++ }, ++ { ++ .private = { 1 }, ++ .public = { 0x25, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x3c, 0x77, 0x77, 0xca, 0xf9, 0x97, 0xb2, 0x64, ++ 0x41, 0x60, 0x77, 0x66, 0x5b, 0x4e, 0x22, 0x9d, ++ 0x0b, 0x95, 0x48, 0xdc, 0x0c, 0xd8, 0x19, 0x98, ++ 0xdd, 0xcd, 0xc5, 0xc8, 0x53, 0x3c, 0x79, 0x7f }, ++ .valid = true ++ }, ++ { ++ .private = { 1 }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0xb3, 0x2d, 0x13, 0x62, 0xc2, 0x48, 0xd6, 0x2f, ++ 0xe6, 0x26, 0x19, 0xcf, 0xf0, 0x4d, 0xd4, 0x3d, ++ 0xb7, 0x3f, 0xfc, 0x1b, 0x63, 0x08, 0xed, 0xe3, ++ 0x0b, 0x78, 0xd8, 0x73, 0x80, 0xf1, 0xe8, 0x34 }, ++ .valid = true ++ }, ++ { ++ .private = { 0xa5, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d, ++ 0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd, ++ 0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18, ++ 0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0xc4 }, ++ .public = { 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb, ++ 0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c, ++ 0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b, ++ 0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c }, ++ .result = { 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90, ++ 0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f, ++ 0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7, ++ 0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 }, ++ .valid = true ++ }, ++ { ++ .private = { 1, 2, 3, 4 }, ++ .public = { 0 }, ++ .result = { 0 }, ++ .valid = false ++ }, ++ { ++ .private = { 2, 4, 6, 8 }, ++ .public = { 0xe0, 0xeb, 0x7a, 0x7c, 0x3b, 0x41, 0xb8, 0xae, ++ 0x16, 0x56, 0xe3, 0xfa, 0xf1, 0x9f, 0xc4, 0x6a, ++ 0xda, 0x09, 0x8d, 0xeb, 0x9c, 0x32, 0xb1, 0xfd, ++ 0x86, 0x62, 0x05, 0x16, 0x5f, 0x49, 0xb8 }, ++ .result = { 0 }, ++ .valid = false ++ }, ++ { ++ .private = { 0xff, 0xff, 0xff, 0xff, 0x0a, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0x0a, 0x00, 0xfb, 0x9f }, ++ .result = { 0x77, 0x52, 0xb6, 0x18, 0xc1, 0x2d, 0x48, 0xd2, ++ 0xc6, 0x93, 0x46, 0x83, 0x81, 0x7c, 0xc6, 0x57, ++ 0xf3, 0x31, 0x03, 0x19, 0x49, 0x48, 0x20, 0x05, ++ 0x42, 0x2b, 0x4e, 0xae, 0x8d, 0x1d, 0x43, 0x23 }, ++ .valid = true ++ }, ++ { ++ .private = { 0x8e, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .public = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8e, 0x06 }, ++ .result = { 0x5a, 0xdf, 0xaa, 0x25, 0x86, 0x8e, 0x32, 0x3d, ++ 0xae, 0x49, 0x62, 0xc1, 0x01, 0x5c, 0xb3, 0x12, ++ 0xe1, 0xc5, 0xc7, 0x9e, 0x95, 0x3f, 0x03, 0x99, ++ 0xb0, 0xba, 0x16, 0x22, 0xf3, 0xb6, 0xf7, 0x0c }, ++ .valid = true ++ }, ++ /* wycheproof - normal case */ ++ { ++ .private = { 0x48, 0x52, 0x83, 0x4d, 0x9d, 0x6b, 0x77, 0xda, ++ 0xde, 0xab, 0xaa, 0xf2, 0xe1, 0x1d, 0xca, 0x66, ++ 0xd1, 0x9f, 0xe7, 0x49, 0x93, 0xa7, 0xbe, 0xc3, ++ 0x6c, 0x6e, 0x16, 0xa0, 0x98, 0x3f, 0xea, 0xba }, ++ .public = { 0x9c, 0x64, 0x7d, 0x9a, 0xe5, 0x89, 0xb9, 0xf5, ++ 0x8f, 0xdc, 0x3c, 0xa4, 0x94, 0x7e, 0xfb, 0xc9, ++ 0x15, 0xc4, 0xb2, 0xe0, 0x8e, 0x74, 0x4a, 0x0e, ++ 0xdf, 0x46, 0x9d, 0xac, 0x59, 0xc8, 0xf8, 0x5a }, ++ .result = { 0x87, 0xb7, 0xf2, 0x12, 0xb6, 0x27, 0xf7, 0xa5, ++ 0x4c, 0xa5, 0xe0, 0xbc, 0xda, 0xdd, 0xd5, 0x38, ++ 0x9d, 0x9d, 0xe6, 0x15, 0x6c, 0xdb, 0xcf, 0x8e, ++ 0xbe, 0x14, 0xff, 0xbc, 0xfb, 0x43, 0x65, 0x51 }, ++ .valid = true ++ }, ++ /* wycheproof - public key on twist */ ++ { ++ .private = { 0x58, 0x8c, 0x06, 0x1a, 0x50, 0x80, 0x4a, 0xc4, ++ 0x88, 0xad, 0x77, 0x4a, 0xc7, 0x16, 0xc3, 0xf5, ++ 0xba, 0x71, 0x4b, 0x27, 0x12, 0xe0, 0x48, 0x49, ++ 0x13, 0x79, 0xa5, 0x00, 0x21, 0x19, 0x98, 0xa8 }, ++ .public = { 0x63, 0xaa, 0x40, 0xc6, 0xe3, 0x83, 0x46, 0xc5, ++ 0xca, 0xf2, 0x3a, 0x6d, 0xf0, 0xa5, 0xe6, 0xc8, ++ 0x08, 0x89, 0xa0, 0x86, 0x47, 0xe5, 0x51, 0xb3, ++ 0x56, 0x34, 0x49, 0xbe, 0xfc, 0xfc, 0x97, 0x33 }, ++ .result = { 0xb1, 0xa7, 0x07, 0x51, 0x94, 0x95, 0xff, 0xff, ++ 0xb2, 0x98, 0xff, 0x94, 0x17, 0x16, 0xb0, 0x6d, ++ 0xfa, 0xb8, 0x7c, 0xf8, 0xd9, 0x11, 0x23, 0xfe, ++ 0x2b, 0xe9, 0xa2, 0x33, 0xdd, 0xa2, 0x22, 0x12 }, ++ .valid = true ++ }, ++ /* wycheproof - public key on twist */ ++ { ++ .private = { 0xb0, 0x5b, 0xfd, 0x32, 0xe5, 0x53, 0x25, 0xd9, ++ 0xfd, 0x64, 0x8c, 0xb3, 0x02, 0x84, 0x80, 0x39, ++ 0x00, 0x0b, 0x39, 0x0e, 0x44, 0xd5, 0x21, 0xe5, ++ 0x8a, 0xab, 0x3b, 0x29, 0xa6, 0x96, 0x0b, 0xa8 }, ++ .public = { 0x0f, 0x83, 0xc3, 0x6f, 0xde, 0xd9, 0xd3, 0x2f, ++ 0xad, 0xf4, 0xef, 0xa3, 0xae, 0x93, 0xa9, 0x0b, ++ 0xb5, 0xcf, 0xa6, 0x68, 0x93, 0xbc, 0x41, 0x2c, ++ 0x43, 0xfa, 0x72, 0x87, 0xdb, 0xb9, 0x97, 0x79 }, ++ .result = { 0x67, 0xdd, 0x4a, 0x6e, 0x16, 0x55, 0x33, 0x53, ++ 0x4c, 0x0e, 0x3f, 0x17, 0x2e, 0x4a, 0xb8, 0x57, ++ 0x6b, 0xca, 0x92, 0x3a, 0x5f, 0x07, 0xb2, 0xc0, ++ 0x69, 0xb4, 0xc3, 0x10, 0xff, 0x2e, 0x93, 0x5b }, ++ .valid = true ++ }, ++ /* wycheproof - public key on twist */ ++ { ++ .private = { 0x70, 0xe3, 0x4b, 0xcb, 0xe1, 0xf4, 0x7f, 0xbc, ++ 0x0f, 0xdd, 0xfd, 0x7c, 0x1e, 0x1a, 0xa5, 0x3d, ++ 0x57, 0xbf, 0xe0, 0xf6, 0x6d, 0x24, 0x30, 0x67, ++ 0xb4, 0x24, 0xbb, 0x62, 0x10, 0xbe, 0xd1, 0x9c }, ++ .public = { 0x0b, 0x82, 0x11, 0xa2, 0xb6, 0x04, 0x90, 0x97, ++ 0xf6, 0x87, 0x1c, 0x6c, 0x05, 0x2d, 0x3c, 0x5f, ++ 0xc1, 0xba, 0x17, 0xda, 0x9e, 0x32, 0xae, 0x45, ++ 0x84, 0x03, 0xb0, 0x5b, 0xb2, 0x83, 0x09, 0x2a }, ++ .result = { 0x4a, 0x06, 0x38, 0xcf, 0xaa, 0x9e, 0xf1, 0x93, ++ 0x3b, 0x47, 0xf8, 0x93, 0x92, 0x96, 0xa6, 0xb2, ++ 0x5b, 0xe5, 0x41, 0xef, 0x7f, 0x70, 0xe8, 0x44, ++ 0xc0, 0xbc, 0xc0, 0x0b, 0x13, 0x4d, 0xe6, 0x4a }, ++ .valid = true ++ }, ++ /* wycheproof - public key on twist */ ++ { ++ .private = { 0x68, 0xc1, 0xf3, 0xa6, 0x53, 0xa4, 0xcd, 0xb1, ++ 0xd3, 0x7b, 0xba, 0x94, 0x73, 0x8f, 0x8b, 0x95, ++ 0x7a, 0x57, 0xbe, 0xb2, 0x4d, 0x64, 0x6e, 0x99, ++ 0x4d, 0xc2, 0x9a, 0x27, 0x6a, 0xad, 0x45, 0x8d }, ++ .public = { 0x34, 0x3a, 0xc2, 0x0a, 0x3b, 0x9c, 0x6a, 0x27, ++ 0xb1, 0x00, 0x81, 0x76, 0x50, 0x9a, 0xd3, 0x07, ++ 0x35, 0x85, 0x6e, 0xc1, 0xc8, 0xd8, 0xfc, 0xae, ++ 0x13, 0x91, 0x2d, 0x08, 0xd1, 0x52, 0xf4, 0x6c }, ++ .result = { 0x39, 0x94, 0x91, 0xfc, 0xe8, 0xdf, 0xab, 0x73, ++ 0xb4, 0xf9, 0xf6, 0x11, 0xde, 0x8e, 0xa0, 0xb2, ++ 0x7b, 0x28, 0xf8, 0x59, 0x94, 0x25, 0x0b, 0x0f, ++ 0x47, 0x5d, 0x58, 0x5d, 0x04, 0x2a, 0xc2, 0x07 }, ++ .valid = true ++ }, ++ /* wycheproof - public key on twist */ ++ { ++ .private = { 0xd8, 0x77, 0xb2, 0x6d, 0x06, 0xdf, 0xf9, 0xd9, ++ 0xf7, 0xfd, 0x4c, 0x5b, 0x37, 0x69, 0xf8, 0xcd, ++ 0xd5, 0xb3, 0x05, 0x16, 0xa5, 0xab, 0x80, 0x6b, ++ 0xe3, 0x24, 0xff, 0x3e, 0xb6, 0x9e, 0xa0, 0xb2 }, ++ .public = { 0xfa, 0x69, 0x5f, 0xc7, 0xbe, 0x8d, 0x1b, 0xe5, ++ 0xbf, 0x70, 0x48, 0x98, 0xf3, 0x88, 0xc4, 0x52, ++ 0xba, 0xfd, 0xd3, 0xb8, 0xea, 0xe8, 0x05, 0xf8, ++ 0x68, 0x1a, 0x8d, 0x15, 0xc2, 0xd4, 0xe1, 0x42 }, ++ .result = { 0x2c, 0x4f, 0xe1, 0x1d, 0x49, 0x0a, 0x53, 0x86, ++ 0x17, 0x76, 0xb1, 0x3b, 0x43, 0x54, 0xab, 0xd4, ++ 0xcf, 0x5a, 0x97, 0x69, 0x9d, 0xb6, 0xe6, 0xc6, ++ 0x8c, 0x16, 0x26, 0xd0, 0x76, 0x62, 0xf7, 0x58 }, ++ .valid = true ++ }, ++ /* wycheproof - public key = 0 */ ++ { ++ .private = { 0x20, 0x74, 0x94, 0x03, 0x8f, 0x2b, 0xb8, 0x11, ++ 0xd4, 0x78, 0x05, 0xbc, 0xdf, 0x04, 0xa2, 0xac, ++ 0x58, 0x5a, 0xda, 0x7f, 0x2f, 0x23, 0x38, 0x9b, ++ 0xfd, 0x46, 0x58, 0xf9, 0xdd, 0xd4, 0xde, 0xbc }, ++ .public = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key = 1 */ ++ { ++ .private = { 0x20, 0x2e, 0x89, 0x72, 0xb6, 0x1c, 0x7e, 0x61, ++ 0x93, 0x0e, 0xb9, 0x45, 0x0b, 0x50, 0x70, 0xea, ++ 0xe1, 0xc6, 0x70, 0x47, 0x56, 0x85, 0x54, 0x1f, ++ 0x04, 0x76, 0x21, 0x7e, 0x48, 0x18, 0xcf, 0xab }, ++ .public = { 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - edge case on twist */ ++ { ++ .private = { 0x38, 0xdd, 0xe9, 0xf3, 0xe7, 0xb7, 0x99, 0x04, ++ 0x5f, 0x9a, 0xc3, 0x79, 0x3d, 0x4a, 0x92, 0x77, ++ 0xda, 0xde, 0xad, 0xc4, 0x1b, 0xec, 0x02, 0x90, ++ 0xf8, 0x1f, 0x74, 0x4f, 0x73, 0x77, 0x5f, 0x84 }, ++ .public = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x9a, 0x2c, 0xfe, 0x84, 0xff, 0x9c, 0x4a, 0x97, ++ 0x39, 0x62, 0x5c, 0xae, 0x4a, 0x3b, 0x82, 0xa9, ++ 0x06, 0x87, 0x7a, 0x44, 0x19, 0x46, 0xf8, 0xd7, ++ 0xb3, 0xd7, 0x95, 0xfe, 0x8f, 0x5d, 0x16, 0x39 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case on twist */ ++ { ++ .private = { 0x98, 0x57, 0xa9, 0x14, 0xe3, 0xc2, 0x90, 0x36, ++ 0xfd, 0x9a, 0x44, 0x2b, 0xa5, 0x26, 0xb5, 0xcd, ++ 0xcd, 0xf2, 0x82, 0x16, 0x15, 0x3e, 0x63, 0x6c, ++ 0x10, 0x67, 0x7a, 0xca, 0xb6, 0xbd, 0x6a, 0xa5 }, ++ .public = { 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x4d, 0xa4, 0xe0, 0xaa, 0x07, 0x2c, 0x23, 0x2e, ++ 0xe2, 0xf0, 0xfa, 0x4e, 0x51, 0x9a, 0xe5, 0x0b, ++ 0x52, 0xc1, 0xed, 0xd0, 0x8a, 0x53, 0x4d, 0x4e, ++ 0xf3, 0x46, 0xc2, 0xe1, 0x06, 0xd2, 0x1d, 0x60 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case on twist */ ++ { ++ .private = { 0x48, 0xe2, 0x13, 0x0d, 0x72, 0x33, 0x05, 0xed, ++ 0x05, 0xe6, 0xe5, 0x89, 0x4d, 0x39, 0x8a, 0x5e, ++ 0x33, 0x36, 0x7a, 0x8c, 0x6a, 0xac, 0x8f, 0xcd, ++ 0xf0, 0xa8, 0x8e, 0x4b, 0x42, 0x82, 0x0d, 0xb7 }, ++ .public = { 0xff, 0xff, 0xff, 0x03, 0x00, 0x00, 0xf8, 0xff, ++ 0xff, 0x1f, 0x00, 0x00, 0xc0, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0xfe, 0xff, 0xff, 0x07, 0x00, ++ 0x00, 0xf0, 0xff, 0xff, 0x3f, 0x00, 0x00, 0x00 }, ++ .result = { 0x9e, 0xd1, 0x0c, 0x53, 0x74, 0x7f, 0x64, 0x7f, ++ 0x82, 0xf4, 0x51, 0x25, 0xd3, 0xde, 0x15, 0xa1, ++ 0xe6, 0xb8, 0x24, 0x49, 0x6a, 0xb4, 0x04, 0x10, ++ 0xff, 0xcc, 0x3c, 0xfe, 0x95, 0x76, 0x0f, 0x3b }, ++ .valid = true ++ }, ++ /* wycheproof - edge case on twist */ ++ { ++ .private = { 0x28, 0xf4, 0x10, 0x11, 0x69, 0x18, 0x51, 0xb3, ++ 0xa6, 0x2b, 0x64, 0x15, 0x53, 0xb3, 0x0d, 0x0d, ++ 0xfd, 0xdc, 0xb8, 0xff, 0xfc, 0xf5, 0x37, 0x00, ++ 0xa7, 0xbe, 0x2f, 0x6a, 0x87, 0x2e, 0x9f, 0xb0 }, ++ .public = { 0x00, 0x00, 0x00, 0xfc, 0xff, 0xff, 0x07, 0x00, ++ 0x00, 0xe0, 0xff, 0xff, 0x3f, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0x01, 0x00, 0x00, 0xf8, 0xff, ++ 0xff, 0x0f, 0x00, 0x00, 0xc0, 0xff, 0xff, 0x7f }, ++ .result = { 0xcf, 0x72, 0xb4, 0xaa, 0x6a, 0xa1, 0xc9, 0xf8, ++ 0x94, 0xf4, 0x16, 0x5b, 0x86, 0x10, 0x9a, 0xa4, ++ 0x68, 0x51, 0x76, 0x48, 0xe1, 0xf0, 0xcc, 0x70, ++ 0xe1, 0xab, 0x08, 0x46, 0x01, 0x76, 0x50, 0x6b }, ++ .valid = true ++ }, ++ /* wycheproof - edge case on twist */ ++ { ++ .private = { 0x18, 0xa9, 0x3b, 0x64, 0x99, 0xb9, 0xf6, 0xb3, ++ 0x22, 0x5c, 0xa0, 0x2f, 0xef, 0x41, 0x0e, 0x0a, ++ 0xde, 0xc2, 0x35, 0x32, 0x32, 0x1d, 0x2d, 0x8e, ++ 0xf1, 0xa6, 0xd6, 0x02, 0xa8, 0xc6, 0x5b, 0x83 }, ++ .public = { 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x5d, 0x50, 0xb6, 0x28, 0x36, 0xbb, 0x69, 0x57, ++ 0x94, 0x10, 0x38, 0x6c, 0xf7, 0xbb, 0x81, 0x1c, ++ 0x14, 0xbf, 0x85, 0xb1, 0xc7, 0xb1, 0x7e, 0x59, ++ 0x24, 0xc7, 0xff, 0xea, 0x91, 0xef, 0x9e, 0x12 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case on twist */ ++ { ++ .private = { 0xc0, 0x1d, 0x13, 0x05, 0xa1, 0x33, 0x8a, 0x1f, ++ 0xca, 0xc2, 0xba, 0x7e, 0x2e, 0x03, 0x2b, 0x42, ++ 0x7e, 0x0b, 0x04, 0x90, 0x31, 0x65, 0xac, 0xa9, ++ 0x57, 0xd8, 0xd0, 0x55, 0x3d, 0x87, 0x17, 0xb0 }, ++ .public = { 0xea, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x19, 0x23, 0x0e, 0xb1, 0x48, 0xd5, 0xd6, 0x7c, ++ 0x3c, 0x22, 0xab, 0x1d, 0xae, 0xff, 0x80, 0xa5, ++ 0x7e, 0xae, 0x42, 0x65, 0xce, 0x28, 0x72, 0x65, ++ 0x7b, 0x2c, 0x80, 0x99, 0xfc, 0x69, 0x8e, 0x50 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0x38, 0x6f, 0x7f, 0x16, 0xc5, 0x07, 0x31, 0xd6, ++ 0x4f, 0x82, 0xe6, 0xa1, 0x70, 0xb1, 0x42, 0xa4, ++ 0xe3, 0x4f, 0x31, 0xfd, 0x77, 0x68, 0xfc, 0xb8, ++ 0x90, 0x29, 0x25, 0xe7, 0xd1, 0xe2, 0x1a, 0xbe }, ++ .public = { 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x0f, 0xca, 0xb5, 0xd8, 0x42, 0xa0, 0x78, 0xd7, ++ 0xa7, 0x1f, 0xc5, 0x9b, 0x57, 0xbf, 0xb4, 0xca, ++ 0x0b, 0xe6, 0x87, 0x3b, 0x49, 0xdc, 0xdb, 0x9f, ++ 0x44, 0xe1, 0x4a, 0xe8, 0xfb, 0xdf, 0xa5, 0x42 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0xe0, 0x23, 0xa2, 0x89, 0xbd, 0x5e, 0x90, 0xfa, ++ 0x28, 0x04, 0xdd, 0xc0, 0x19, 0xa0, 0x5e, 0xf3, ++ 0xe7, 0x9d, 0x43, 0x4b, 0xb6, 0xea, 0x2f, 0x52, ++ 0x2e, 0xcb, 0x64, 0x3a, 0x75, 0x29, 0x6e, 0x95 }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }, ++ .result = { 0x54, 0xce, 0x8f, 0x22, 0x75, 0xc0, 0x77, 0xe3, ++ 0xb1, 0x30, 0x6a, 0x39, 0x39, 0xc5, 0xe0, 0x3e, ++ 0xef, 0x6b, 0xbb, 0x88, 0x06, 0x05, 0x44, 0x75, ++ 0x8d, 0x9f, 0xef, 0x59, 0xb0, 0xbc, 0x3e, 0x4f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0x68, 0xf0, 0x10, 0xd6, 0x2e, 0xe8, 0xd9, 0x26, ++ 0x05, 0x3a, 0x36, 0x1c, 0x3a, 0x75, 0xc6, 0xea, ++ 0x4e, 0xbd, 0xc8, 0x60, 0x6a, 0xb2, 0x85, 0x00, ++ 0x3a, 0x6f, 0x8f, 0x40, 0x76, 0xb0, 0x1e, 0x83 }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x03 }, ++ .result = { 0xf1, 0x36, 0x77, 0x5c, 0x5b, 0xeb, 0x0a, 0xf8, ++ 0x11, 0x0a, 0xf1, 0x0b, 0x20, 0x37, 0x23, 0x32, ++ 0x04, 0x3c, 0xab, 0x75, 0x24, 0x19, 0x67, 0x87, ++ 0x75, 0xa2, 0x23, 0xdf, 0x57, 0xc9, 0xd3, 0x0d }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0x58, 0xeb, 0xcb, 0x35, 0xb0, 0xf8, 0x84, 0x5c, ++ 0xaf, 0x1e, 0xc6, 0x30, 0xf9, 0x65, 0x76, 0xb6, ++ 0x2c, 0x4b, 0x7b, 0x6c, 0x36, 0xb2, 0x9d, 0xeb, ++ 0x2c, 0xb0, 0x08, 0x46, 0x51, 0x75, 0x5c, 0x96 }, ++ .public = { 0xff, 0xff, 0xff, 0xfb, 0xff, 0xff, 0xfb, 0xff, ++ 0xff, 0xdf, 0xff, 0xff, 0xdf, 0xff, 0xff, 0xff, ++ 0xfe, 0xff, 0xff, 0xfe, 0xff, 0xff, 0xf7, 0xff, ++ 0xff, 0xf7, 0xff, 0xff, 0xbf, 0xff, 0xff, 0x3f }, ++ .result = { 0xbf, 0x9a, 0xff, 0xd0, 0x6b, 0x84, 0x40, 0x85, ++ 0x58, 0x64, 0x60, 0x96, 0x2e, 0xf2, 0x14, 0x6f, ++ 0xf3, 0xd4, 0x53, 0x3d, 0x94, 0x44, 0xaa, 0xb0, ++ 0x06, 0xeb, 0x88, 0xcc, 0x30, 0x54, 0x40, 0x7d }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0x18, 0x8c, 0x4b, 0xc5, 0xb9, 0xc4, 0x4b, 0x38, ++ 0xbb, 0x65, 0x8b, 0x9b, 0x2a, 0xe8, 0x2d, 0x5b, ++ 0x01, 0x01, 0x5e, 0x09, 0x31, 0x84, 0xb1, 0x7c, ++ 0xb7, 0x86, 0x35, 0x03, 0xa7, 0x83, 0xe1, 0xbb }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .result = { 0xd4, 0x80, 0xde, 0x04, 0xf6, 0x99, 0xcb, 0x3b, ++ 0xe0, 0x68, 0x4a, 0x9c, 0xc2, 0xe3, 0x12, 0x81, ++ 0xea, 0x0b, 0xc5, 0xa9, 0xdc, 0xc1, 0x57, 0xd3, ++ 0xd2, 0x01, 0x58, 0xd4, 0x6c, 0xa5, 0x24, 0x6d }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0xe0, 0x6c, 0x11, 0xbb, 0x2e, 0x13, 0xce, 0x3d, ++ 0xc7, 0x67, 0x3f, 0x67, 0xf5, 0x48, 0x22, 0x42, ++ 0x90, 0x94, 0x23, 0xa9, 0xae, 0x95, 0xee, 0x98, ++ 0x6a, 0x98, 0x8d, 0x98, 0xfa, 0xee, 0x23, 0xa2 }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0xff, 0xfe, 0xff, 0xff, 0x7f }, ++ .result = { 0x4c, 0x44, 0x01, 0xcc, 0xe6, 0xb5, 0x1e, 0x4c, ++ 0xb1, 0x8f, 0x27, 0x90, 0x24, 0x6c, 0x9b, 0xf9, ++ 0x14, 0xdb, 0x66, 0x77, 0x50, 0xa1, 0xcb, 0x89, ++ 0x06, 0x90, 0x92, 0xaf, 0x07, 0x29, 0x22, 0x76 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for public key */ ++ { ++ .private = { 0xc0, 0x65, 0x8c, 0x46, 0xdd, 0xe1, 0x81, 0x29, ++ 0x29, 0x38, 0x77, 0x53, 0x5b, 0x11, 0x62, 0xb6, ++ 0xf9, 0xf5, 0x41, 0x4a, 0x23, 0xcf, 0x4d, 0x2c, ++ 0xbc, 0x14, 0x0a, 0x4d, 0x99, 0xda, 0x2b, 0x8f }, ++ .public = { 0xeb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x57, 0x8b, 0xa8, 0xcc, 0x2d, 0xbd, 0xc5, 0x75, ++ 0xaf, 0xcf, 0x9d, 0xf2, 0xb3, 0xee, 0x61, 0x89, ++ 0xf5, 0x33, 0x7d, 0x68, 0x54, 0xc7, 0x9b, 0x4c, ++ 0xe1, 0x65, 0xea, 0x12, 0x29, 0x3b, 0x3a, 0x0f }, ++ .valid = true ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x10, 0x25, 0x5c, 0x92, 0x30, 0xa9, 0x7a, 0x30, ++ 0xa4, 0x58, 0xca, 0x28, 0x4a, 0x62, 0x96, 0x69, ++ 0x29, 0x3a, 0x31, 0x89, 0x0c, 0xda, 0x9d, 0x14, ++ 0x7f, 0xeb, 0xc7, 0xd1, 0xe2, 0x2d, 0x6b, 0xb1 }, ++ .public = { 0xe0, 0xeb, 0x7a, 0x7c, 0x3b, 0x41, 0xb8, 0xae, ++ 0x16, 0x56, 0xe3, 0xfa, 0xf1, 0x9f, 0xc4, 0x6a, ++ 0xda, 0x09, 0x8d, 0xeb, 0x9c, 0x32, 0xb1, 0xfd, ++ 0x86, 0x62, 0x05, 0x16, 0x5f, 0x49, 0xb8, 0x00 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x78, 0xf1, 0xe8, 0xed, 0xf1, 0x44, 0x81, 0xb3, ++ 0x89, 0x44, 0x8d, 0xac, 0x8f, 0x59, 0xc7, 0x0b, ++ 0x03, 0x8e, 0x7c, 0xf9, 0x2e, 0xf2, 0xc7, 0xef, ++ 0xf5, 0x7a, 0x72, 0x46, 0x6e, 0x11, 0x52, 0x96 }, ++ .public = { 0x5f, 0x9c, 0x95, 0xbc, 0xa3, 0x50, 0x8c, 0x24, ++ 0xb1, 0xd0, 0xb1, 0x55, 0x9c, 0x83, 0xef, 0x5b, ++ 0x04, 0x44, 0x5c, 0xc4, 0x58, 0x1c, 0x8e, 0x86, ++ 0xd8, 0x22, 0x4e, 0xdd, 0xd0, 0x9f, 0x11, 0x57 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0xa0, 0xa0, 0x5a, 0x3e, 0x8f, 0x9f, 0x44, 0x20, ++ 0x4d, 0x5f, 0x80, 0x59, 0xa9, 0x4a, 0xc7, 0xdf, ++ 0xc3, 0x9a, 0x49, 0xac, 0x01, 0x6d, 0xd7, 0x43, ++ 0xdb, 0xfa, 0x43, 0xc5, 0xd6, 0x71, 0xfd, 0x88 }, ++ .public = { 0xec, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0xd0, 0xdb, 0xb3, 0xed, 0x19, 0x06, 0x66, 0x3f, ++ 0x15, 0x42, 0x0a, 0xf3, 0x1f, 0x4e, 0xaf, 0x65, ++ 0x09, 0xd9, 0xa9, 0x94, 0x97, 0x23, 0x50, 0x06, ++ 0x05, 0xad, 0x7c, 0x1c, 0x6e, 0x74, 0x50, 0xa9 }, ++ .public = { 0xed, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0xc0, 0xb1, 0xd0, 0xeb, 0x22, 0xb2, 0x44, 0xfe, ++ 0x32, 0x91, 0x14, 0x00, 0x72, 0xcd, 0xd9, 0xd9, ++ 0x89, 0xb5, 0xf0, 0xec, 0xd9, 0x6c, 0x10, 0x0f, ++ 0xeb, 0x5b, 0xca, 0x24, 0x1c, 0x1d, 0x9f, 0x8f }, ++ .public = { 0xee, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x48, 0x0b, 0xf4, 0x5f, 0x59, 0x49, 0x42, 0xa8, ++ 0xbc, 0x0f, 0x33, 0x53, 0xc6, 0xe8, 0xb8, 0x85, ++ 0x3d, 0x77, 0xf3, 0x51, 0xf1, 0xc2, 0xca, 0x6c, ++ 0x2d, 0x1a, 0xbf, 0x8a, 0x00, 0xb4, 0x22, 0x9c }, ++ .public = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x30, 0xf9, 0x93, 0xfc, 0xf8, 0x51, 0x4f, 0xc8, ++ 0x9b, 0xd8, 0xdb, 0x14, 0xcd, 0x43, 0xba, 0x0d, ++ 0x4b, 0x25, 0x30, 0xe7, 0x3c, 0x42, 0x76, 0xa0, ++ 0x5e, 0x1b, 0x14, 0x5d, 0x42, 0x0c, 0xed, 0xb4 }, ++ .public = { 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0xc0, 0x49, 0x74, 0xb7, 0x58, 0x38, 0x0e, 0x2a, ++ 0x5b, 0x5d, 0xf6, 0xeb, 0x09, 0xbb, 0x2f, 0x6b, ++ 0x34, 0x34, 0xf9, 0x82, 0x72, 0x2a, 0x8e, 0x67, ++ 0x6d, 0x3d, 0xa2, 0x51, 0xd1, 0xb3, 0xde, 0x83 }, ++ .public = { 0xe0, 0xeb, 0x7a, 0x7c, 0x3b, 0x41, 0xb8, 0xae, ++ 0x16, 0x56, 0xe3, 0xfa, 0xf1, 0x9f, 0xc4, 0x6a, ++ 0xda, 0x09, 0x8d, 0xeb, 0x9c, 0x32, 0xb1, 0xfd, ++ 0x86, 0x62, 0x05, 0x16, 0x5f, 0x49, 0xb8, 0x80 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x50, 0x2a, 0x31, 0x37, 0x3d, 0xb3, 0x24, 0x46, ++ 0x84, 0x2f, 0xe5, 0xad, 0xd3, 0xe0, 0x24, 0x02, ++ 0x2e, 0xa5, 0x4f, 0x27, 0x41, 0x82, 0xaf, 0xc3, ++ 0xd9, 0xf1, 0xbb, 0x3d, 0x39, 0x53, 0x4e, 0xb5 }, ++ .public = { 0x5f, 0x9c, 0x95, 0xbc, 0xa3, 0x50, 0x8c, 0x24, ++ 0xb1, 0xd0, 0xb1, 0x55, 0x9c, 0x83, 0xef, 0x5b, ++ 0x04, 0x44, 0x5c, 0xc4, 0x58, 0x1c, 0x8e, 0x86, ++ 0xd8, 0x22, 0x4e, 0xdd, 0xd0, 0x9f, 0x11, 0xd7 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x90, 0xfa, 0x64, 0x17, 0xb0, 0xe3, 0x70, 0x30, ++ 0xfd, 0x6e, 0x43, 0xef, 0xf2, 0xab, 0xae, 0xf1, ++ 0x4c, 0x67, 0x93, 0x11, 0x7a, 0x03, 0x9c, 0xf6, ++ 0x21, 0x31, 0x8b, 0xa9, 0x0f, 0x4e, 0x98, 0xbe }, ++ .public = { 0xec, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x78, 0xad, 0x3f, 0x26, 0x02, 0x7f, 0x1c, 0x9f, ++ 0xdd, 0x97, 0x5a, 0x16, 0x13, 0xb9, 0x47, 0x77, ++ 0x9b, 0xad, 0x2c, 0xf2, 0xb7, 0x41, 0xad, 0xe0, ++ 0x18, 0x40, 0x88, 0x5a, 0x30, 0xbb, 0x97, 0x9c }, ++ .public = { 0xed, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key with low order */ ++ { ++ .private = { 0x98, 0xe2, 0x3d, 0xe7, 0xb1, 0xe0, 0x92, 0x6e, ++ 0xd9, 0xc8, 0x7e, 0x7b, 0x14, 0xba, 0xf5, 0x5f, ++ 0x49, 0x7a, 0x1d, 0x70, 0x96, 0xf9, 0x39, 0x77, ++ 0x68, 0x0e, 0x44, 0xdc, 0x1c, 0x7b, 0x7b, 0x8b }, ++ .public = { 0xee, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = false ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0xf0, 0x1e, 0x48, 0xda, 0xfa, 0xc9, 0xd7, 0xbc, ++ 0xf5, 0x89, 0xcb, 0xc3, 0x82, 0xc8, 0x78, 0xd1, ++ 0x8b, 0xda, 0x35, 0x50, 0x58, 0x9f, 0xfb, 0x5d, ++ 0x50, 0xb5, 0x23, 0xbe, 0xbe, 0x32, 0x9d, 0xae }, ++ .public = { 0xef, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0xbd, 0x36, 0xa0, 0x79, 0x0e, 0xb8, 0x83, 0x09, ++ 0x8c, 0x98, 0x8b, 0x21, 0x78, 0x67, 0x73, 0xde, ++ 0x0b, 0x3a, 0x4d, 0xf1, 0x62, 0x28, 0x2c, 0xf1, ++ 0x10, 0xde, 0x18, 0xdd, 0x48, 0x4c, 0xe7, 0x4b }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x28, 0x87, 0x96, 0xbc, 0x5a, 0xff, 0x4b, 0x81, ++ 0xa3, 0x75, 0x01, 0x75, 0x7b, 0xc0, 0x75, 0x3a, ++ 0x3c, 0x21, 0x96, 0x47, 0x90, 0xd3, 0x86, 0x99, ++ 0x30, 0x8d, 0xeb, 0xc1, 0x7a, 0x6e, 0xaf, 0x8d }, ++ .public = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0xb4, 0xe0, 0xdd, 0x76, 0xda, 0x7b, 0x07, 0x17, ++ 0x28, 0xb6, 0x1f, 0x85, 0x67, 0x71, 0xaa, 0x35, ++ 0x6e, 0x57, 0xed, 0xa7, 0x8a, 0x5b, 0x16, 0x55, ++ 0xcc, 0x38, 0x20, 0xfb, 0x5f, 0x85, 0x4c, 0x5c }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x98, 0xdf, 0x84, 0x5f, 0x66, 0x51, 0xbf, 0x11, ++ 0x38, 0x22, 0x1f, 0x11, 0x90, 0x41, 0xf7, 0x2b, ++ 0x6d, 0xbc, 0x3c, 0x4a, 0xce, 0x71, 0x43, 0xd9, ++ 0x9f, 0xd5, 0x5a, 0xd8, 0x67, 0x48, 0x0d, 0xa8 }, ++ .public = { 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x6f, 0xdf, 0x6c, 0x37, 0x61, 0x1d, 0xbd, 0x53, ++ 0x04, 0xdc, 0x0f, 0x2e, 0xb7, 0xc9, 0x51, 0x7e, ++ 0xb3, 0xc5, 0x0e, 0x12, 0xfd, 0x05, 0x0a, 0xc6, ++ 0xde, 0xc2, 0x70, 0x71, 0xd4, 0xbf, 0xc0, 0x34 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0xf0, 0x94, 0x98, 0xe4, 0x6f, 0x02, 0xf8, 0x78, ++ 0x82, 0x9e, 0x78, 0xb8, 0x03, 0xd3, 0x16, 0xa2, ++ 0xed, 0x69, 0x5d, 0x04, 0x98, 0xa0, 0x8a, 0xbd, ++ 0xf8, 0x27, 0x69, 0x30, 0xe2, 0x4e, 0xdc, 0xb0 }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .result = { 0x4c, 0x8f, 0xc4, 0xb1, 0xc6, 0xab, 0x88, 0xfb, ++ 0x21, 0xf1, 0x8f, 0x6d, 0x4c, 0x81, 0x02, 0x40, ++ 0xd4, 0xe9, 0x46, 0x51, 0xba, 0x44, 0xf7, 0xa2, ++ 0xc8, 0x63, 0xce, 0xc7, 0xdc, 0x56, 0x60, 0x2d }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x18, 0x13, 0xc1, 0x0a, 0x5c, 0x7f, 0x21, 0xf9, ++ 0x6e, 0x17, 0xf2, 0x88, 0xc0, 0xcc, 0x37, 0x60, ++ 0x7c, 0x04, 0xc5, 0xf5, 0xae, 0xa2, 0xdb, 0x13, ++ 0x4f, 0x9e, 0x2f, 0xfc, 0x66, 0xbd, 0x9d, 0xb8 }, ++ .public = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .result = { 0x1c, 0xd0, 0xb2, 0x82, 0x67, 0xdc, 0x54, 0x1c, ++ 0x64, 0x2d, 0x6d, 0x7d, 0xca, 0x44, 0xa8, 0xb3, ++ 0x8a, 0x63, 0x73, 0x6e, 0xef, 0x5c, 0x4e, 0x65, ++ 0x01, 0xff, 0xbb, 0xb1, 0x78, 0x0c, 0x03, 0x3c }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x78, 0x57, 0xfb, 0x80, 0x86, 0x53, 0x64, 0x5a, ++ 0x0b, 0xeb, 0x13, 0x8a, 0x64, 0xf5, 0xf4, 0xd7, ++ 0x33, 0xa4, 0x5e, 0xa8, 0x4c, 0x3c, 0xda, 0x11, ++ 0xa9, 0xc0, 0x6f, 0x7e, 0x71, 0x39, 0x14, 0x9e }, ++ .public = { 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .result = { 0x87, 0x55, 0xbe, 0x01, 0xc6, 0x0a, 0x7e, 0x82, ++ 0x5c, 0xff, 0x3e, 0x0e, 0x78, 0xcb, 0x3a, 0xa4, ++ 0x33, 0x38, 0x61, 0x51, 0x6a, 0xa5, 0x9b, 0x1c, ++ 0x51, 0xa8, 0xb2, 0xa5, 0x43, 0xdf, 0xa8, 0x22 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0xe0, 0x3a, 0xa8, 0x42, 0xe2, 0xab, 0xc5, 0x6e, ++ 0x81, 0xe8, 0x7b, 0x8b, 0x9f, 0x41, 0x7b, 0x2a, ++ 0x1e, 0x59, 0x13, 0xc7, 0x23, 0xee, 0xd2, 0x8d, ++ 0x75, 0x2f, 0x8d, 0x47, 0xa5, 0x9f, 0x49, 0x8f }, ++ .public = { 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80 }, ++ .result = { 0x54, 0xc9, 0xa1, 0xed, 0x95, 0xe5, 0x46, 0xd2, ++ 0x78, 0x22, 0xa3, 0x60, 0x93, 0x1d, 0xda, 0x60, ++ 0xa1, 0xdf, 0x04, 0x9d, 0xa6, 0xf9, 0x04, 0x25, ++ 0x3c, 0x06, 0x12, 0xbb, 0xdc, 0x08, 0x74, 0x76 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0xf8, 0xf7, 0x07, 0xb7, 0x99, 0x9b, 0x18, 0xcb, ++ 0x0d, 0x6b, 0x96, 0x12, 0x4f, 0x20, 0x45, 0x97, ++ 0x2c, 0xa2, 0x74, 0xbf, 0xc1, 0x54, 0xad, 0x0c, ++ 0x87, 0x03, 0x8c, 0x24, 0xc6, 0xd0, 0xd4, 0xb2 }, ++ .public = { 0xda, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0xcc, 0x1f, 0x40, 0xd7, 0x43, 0xcd, 0xc2, 0x23, ++ 0x0e, 0x10, 0x43, 0xda, 0xba, 0x8b, 0x75, 0xe8, ++ 0x10, 0xf1, 0xfb, 0xab, 0x7f, 0x25, 0x52, 0x69, ++ 0xbd, 0x9e, 0xbb, 0x29, 0xe6, 0xbf, 0x49, 0x4f }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0xa0, 0x34, 0xf6, 0x84, 0xfa, 0x63, 0x1e, 0x1a, ++ 0x34, 0x81, 0x18, 0xc1, 0xce, 0x4c, 0x98, 0x23, ++ 0x1f, 0x2d, 0x9e, 0xec, 0x9b, 0xa5, 0x36, 0x5b, ++ 0x4a, 0x05, 0xd6, 0x9a, 0x78, 0x5b, 0x07, 0x96 }, ++ .public = { 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x54, 0x99, 0x8e, 0xe4, 0x3a, 0x5b, 0x00, 0x7b, ++ 0xf4, 0x99, 0xf0, 0x78, 0xe7, 0x36, 0x52, 0x44, ++ 0x00, 0xa8, 0xb5, 0xc7, 0xe9, 0xb9, 0xb4, 0x37, ++ 0x71, 0x74, 0x8c, 0x7c, 0xdf, 0x88, 0x04, 0x12 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x30, 0xb6, 0xc6, 0xa0, 0xf2, 0xff, 0xa6, 0x80, ++ 0x76, 0x8f, 0x99, 0x2b, 0xa8, 0x9e, 0x15, 0x2d, ++ 0x5b, 0xc9, 0x89, 0x3d, 0x38, 0xc9, 0x11, 0x9b, ++ 0xe4, 0xf7, 0x67, 0xbf, 0xab, 0x6e, 0x0c, 0xa5 }, ++ .public = { 0xdc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0xea, 0xd9, 0xb3, 0x8e, 0xfd, 0xd7, 0x23, 0x63, ++ 0x79, 0x34, 0xe5, 0x5a, 0xb7, 0x17, 0xa7, 0xae, ++ 0x09, 0xeb, 0x86, 0xa2, 0x1d, 0xc3, 0x6a, 0x3f, ++ 0xee, 0xb8, 0x8b, 0x75, 0x9e, 0x39, 0x1e, 0x09 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x90, 0x1b, 0x9d, 0xcf, 0x88, 0x1e, 0x01, 0xe0, ++ 0x27, 0x57, 0x50, 0x35, 0xd4, 0x0b, 0x43, 0xbd, ++ 0xc1, 0xc5, 0x24, 0x2e, 0x03, 0x08, 0x47, 0x49, ++ 0x5b, 0x0c, 0x72, 0x86, 0x46, 0x9b, 0x65, 0x91 }, ++ .public = { 0xea, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x60, 0x2f, 0xf4, 0x07, 0x89, 0xb5, 0x4b, 0x41, ++ 0x80, 0x59, 0x15, 0xfe, 0x2a, 0x62, 0x21, 0xf0, ++ 0x7a, 0x50, 0xff, 0xc2, 0xc3, 0xfc, 0x94, 0xcf, ++ 0x61, 0xf1, 0x3d, 0x79, 0x04, 0xe8, 0x8e, 0x0e }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x80, 0x46, 0x67, 0x7c, 0x28, 0xfd, 0x82, 0xc9, ++ 0xa1, 0xbd, 0xb7, 0x1a, 0x1a, 0x1a, 0x34, 0xfa, ++ 0xba, 0x12, 0x25, 0xe2, 0x50, 0x7f, 0xe3, 0xf5, ++ 0x4d, 0x10, 0xbd, 0x5b, 0x0d, 0x86, 0x5f, 0x8e }, ++ .public = { 0xeb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0xe0, 0x0a, 0xe8, 0xb1, 0x43, 0x47, 0x12, 0x47, ++ 0xba, 0x24, 0xf1, 0x2c, 0x88, 0x55, 0x36, 0xc3, ++ 0xcb, 0x98, 0x1b, 0x58, 0xe1, 0xe5, 0x6b, 0x2b, ++ 0xaf, 0x35, 0xc1, 0x2a, 0xe1, 0xf7, 0x9c, 0x26 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x60, 0x2f, 0x7e, 0x2f, 0x68, 0xa8, 0x46, 0xb8, ++ 0x2c, 0xc2, 0x69, 0xb1, 0xd4, 0x8e, 0x93, 0x98, ++ 0x86, 0xae, 0x54, 0xfd, 0x63, 0x6c, 0x1f, 0xe0, ++ 0x74, 0xd7, 0x10, 0x12, 0x7d, 0x47, 0x24, 0x91 }, ++ .public = { 0xef, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x98, 0xcb, 0x9b, 0x50, 0xdd, 0x3f, 0xc2, 0xb0, ++ 0xd4, 0xf2, 0xd2, 0xbf, 0x7c, 0x5c, 0xfd, 0xd1, ++ 0x0c, 0x8f, 0xcd, 0x31, 0xfc, 0x40, 0xaf, 0x1a, ++ 0xd4, 0x4f, 0x47, 0xc1, 0x31, 0x37, 0x63, 0x62 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x60, 0x88, 0x7b, 0x3d, 0xc7, 0x24, 0x43, 0x02, ++ 0x6e, 0xbe, 0xdb, 0xbb, 0xb7, 0x06, 0x65, 0xf4, ++ 0x2b, 0x87, 0xad, 0xd1, 0x44, 0x0e, 0x77, 0x68, ++ 0xfb, 0xd7, 0xe8, 0xe2, 0xce, 0x5f, 0x63, 0x9d }, ++ .public = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x38, 0xd6, 0x30, 0x4c, 0x4a, 0x7e, 0x6d, 0x9f, ++ 0x79, 0x59, 0x33, 0x4f, 0xb5, 0x24, 0x5b, 0xd2, ++ 0xc7, 0x54, 0x52, 0x5d, 0x4c, 0x91, 0xdb, 0x95, ++ 0x02, 0x06, 0x92, 0x62, 0x34, 0xc1, 0xf6, 0x33 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0x78, 0xd3, 0x1d, 0xfa, 0x85, 0x44, 0x97, 0xd7, ++ 0x2d, 0x8d, 0xef, 0x8a, 0x1b, 0x7f, 0xb0, 0x06, ++ 0xce, 0xc2, 0xd8, 0xc4, 0x92, 0x46, 0x47, 0xc9, ++ 0x38, 0x14, 0xae, 0x56, 0xfa, 0xed, 0xa4, 0x95 }, ++ .public = { 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x78, 0x6c, 0xd5, 0x49, 0x96, 0xf0, 0x14, 0xa5, ++ 0xa0, 0x31, 0xec, 0x14, 0xdb, 0x81, 0x2e, 0xd0, ++ 0x83, 0x55, 0x06, 0x1f, 0xdb, 0x5d, 0xe6, 0x80, ++ 0xa8, 0x00, 0xac, 0x52, 0x1f, 0x31, 0x8e, 0x23 }, ++ .valid = true ++ }, ++ /* wycheproof - public key >= p */ ++ { ++ .private = { 0xc0, 0x4c, 0x5b, 0xae, 0xfa, 0x83, 0x02, 0xdd, ++ 0xde, 0xd6, 0xa4, 0xbb, 0x95, 0x77, 0x61, 0xb4, ++ 0xeb, 0x97, 0xae, 0xfa, 0x4f, 0xc3, 0xb8, 0x04, ++ 0x30, 0x85, 0xf9, 0x6a, 0x56, 0x59, 0xb3, 0xa5 }, ++ .public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }, ++ .result = { 0x29, 0xae, 0x8b, 0xc7, 0x3e, 0x9b, 0x10, 0xa0, ++ 0x8b, 0x4f, 0x68, 0x1c, 0x43, 0xc3, 0xe0, 0xac, ++ 0x1a, 0x17, 0x1d, 0x31, 0xb3, 0x8f, 0x1a, 0x48, ++ 0xef, 0xba, 0x29, 0xae, 0x63, 0x9e, 0xa1, 0x34 }, ++ .valid = true ++ }, ++ /* wycheproof - RFC 7748 */ ++ { ++ .private = { 0xa0, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d, ++ 0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd, ++ 0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18, ++ 0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0x44 }, ++ .public = { 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb, ++ 0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c, ++ 0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b, ++ 0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c }, ++ .result = { 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90, ++ 0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f, ++ 0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7, ++ 0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 }, ++ .valid = true ++ }, ++ /* wycheproof - RFC 7748 */ ++ { ++ .private = { 0x48, 0x66, 0xe9, 0xd4, 0xd1, 0xb4, 0x67, 0x3c, ++ 0x5a, 0xd2, 0x26, 0x91, 0x95, 0x7d, 0x6a, 0xf5, ++ 0xc1, 0x1b, 0x64, 0x21, 0xe0, 0xea, 0x01, 0xd4, ++ 0x2c, 0xa4, 0x16, 0x9e, 0x79, 0x18, 0xba, 0x4d }, ++ .public = { 0xe5, 0x21, 0x0f, 0x12, 0x78, 0x68, 0x11, 0xd3, ++ 0xf4, 0xb7, 0x95, 0x9d, 0x05, 0x38, 0xae, 0x2c, ++ 0x31, 0xdb, 0xe7, 0x10, 0x6f, 0xc0, 0x3c, 0x3e, ++ 0xfc, 0x4c, 0xd5, 0x49, 0xc7, 0x15, 0xa4, 0x13 }, ++ .result = { 0x95, 0xcb, 0xde, 0x94, 0x76, 0xe8, 0x90, 0x7d, ++ 0x7a, 0xad, 0xe4, 0x5c, 0xb4, 0xb8, 0x73, 0xf8, ++ 0x8b, 0x59, 0x5a, 0x68, 0x79, 0x9f, 0xa1, 0x52, ++ 0xe6, 0xf8, 0xf7, 0x64, 0x7a, 0xac, 0x79, 0x57 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x0a, 0xb4, 0xe7, 0x63, 0x80, 0xd8, 0x4d, 0xde, ++ 0x4f, 0x68, 0x33, 0xc5, 0x8f, 0x2a, 0x9f, 0xb8, ++ 0xf8, 0x3b, 0xb0, 0x16, 0x9b, 0x17, 0x2b, 0xe4, ++ 0xb6, 0xe0, 0x59, 0x28, 0x87, 0x74, 0x1a, 0x36 }, ++ .result = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x89, 0xe1, 0x0d, 0x57, 0x01, 0xb4, 0x33, 0x7d, ++ 0x2d, 0x03, 0x21, 0x81, 0x53, 0x8b, 0x10, 0x64, ++ 0xbd, 0x40, 0x84, 0x40, 0x1c, 0xec, 0xa1, 0xfd, ++ 0x12, 0x66, 0x3a, 0x19, 0x59, 0x38, 0x80, 0x00 }, ++ .result = { 0x09, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x2b, 0x55, 0xd3, 0xaa, 0x4a, 0x8f, 0x80, 0xc8, ++ 0xc0, 0xb2, 0xae, 0x5f, 0x93, 0x3e, 0x85, 0xaf, ++ 0x49, 0xbe, 0xac, 0x36, 0xc2, 0xfa, 0x73, 0x94, ++ 0xba, 0xb7, 0x6c, 0x89, 0x33, 0xf8, 0xf8, 0x1d }, ++ .result = { 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x63, 0xe5, 0xb1, 0xfe, 0x96, 0x01, 0xfe, 0x84, ++ 0x38, 0x5d, 0x88, 0x66, 0xb0, 0x42, 0x12, 0x62, ++ 0xf7, 0x8f, 0xbf, 0xa5, 0xaf, 0xf9, 0x58, 0x5e, ++ 0x62, 0x66, 0x79, 0xb1, 0x85, 0x47, 0xd9, 0x59 }, ++ .result = { 0xfe, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0xe4, 0x28, 0xf3, 0xda, 0xc1, 0x78, 0x09, 0xf8, ++ 0x27, 0xa5, 0x22, 0xce, 0x32, 0x35, 0x50, 0x58, ++ 0xd0, 0x73, 0x69, 0x36, 0x4a, 0xa7, 0x89, 0x02, ++ 0xee, 0x10, 0x13, 0x9b, 0x9f, 0x9d, 0xd6, 0x53 }, ++ .result = { 0xfc, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0xb3, 0xb5, 0x0e, 0x3e, 0xd3, 0xa4, 0x07, 0xb9, ++ 0x5d, 0xe9, 0x42, 0xef, 0x74, 0x57, 0x5b, 0x5a, ++ 0xb8, 0xa1, 0x0c, 0x09, 0xee, 0x10, 0x35, 0x44, ++ 0xd6, 0x0b, 0xdf, 0xed, 0x81, 0x38, 0xab, 0x2b }, ++ .result = { 0xf9, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x21, 0x3f, 0xff, 0xe9, 0x3d, 0x5e, 0xa8, 0xcd, ++ 0x24, 0x2e, 0x46, 0x28, 0x44, 0x02, 0x99, 0x22, ++ 0xc4, 0x3c, 0x77, 0xc9, 0xe3, 0xe4, 0x2f, 0x56, ++ 0x2f, 0x48, 0x5d, 0x24, 0xc5, 0x01, 0xa2, 0x0b }, ++ .result = { 0xf3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x91, 0xb2, 0x32, 0xa1, 0x78, 0xb3, 0xcd, 0x53, ++ 0x09, 0x32, 0x44, 0x1e, 0x61, 0x39, 0x41, 0x8f, ++ 0x72, 0x17, 0x22, 0x92, 0xf1, 0xda, 0x4c, 0x18, ++ 0x34, 0xfc, 0x5e, 0xbf, 0xef, 0xb5, 0x1e, 0x3f }, ++ .result = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x03 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x04, 0x5c, 0x6e, 0x11, 0xc5, 0xd3, 0x32, 0x55, ++ 0x6c, 0x78, 0x22, 0xfe, 0x94, 0xeb, 0xf8, 0x9b, ++ 0x56, 0xa3, 0x87, 0x8d, 0xc2, 0x7c, 0xa0, 0x79, ++ 0x10, 0x30, 0x58, 0x84, 0x9f, 0xab, 0xcb, 0x4f }, ++ .result = { 0xe5, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x1c, 0xa2, 0x19, 0x0b, 0x71, 0x16, 0x35, 0x39, ++ 0x06, 0x3c, 0x35, 0x77, 0x3b, 0xda, 0x0c, 0x9c, ++ 0x92, 0x8e, 0x91, 0x36, 0xf0, 0x62, 0x0a, 0xeb, ++ 0x09, 0x3f, 0x09, 0x91, 0x97, 0xb7, 0xf7, 0x4e }, ++ .result = { 0xe3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0xf7, 0x6e, 0x90, 0x10, 0xac, 0x33, 0xc5, 0x04, ++ 0x3b, 0x2d, 0x3b, 0x76, 0xa8, 0x42, 0x17, 0x10, ++ 0x00, 0xc4, 0x91, 0x62, 0x22, 0xe9, 0xe8, 0x58, ++ 0x97, 0xa0, 0xae, 0xc7, 0xf6, 0x35, 0x0b, 0x3c }, ++ .result = { 0xdd, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0xbb, 0x72, 0x68, 0x8d, 0x8f, 0x8a, 0xa7, 0xa3, ++ 0x9c, 0xd6, 0x06, 0x0c, 0xd5, 0xc8, 0x09, 0x3c, ++ 0xde, 0xc6, 0xfe, 0x34, 0x19, 0x37, 0xc3, 0x88, ++ 0x6a, 0x99, 0x34, 0x6c, 0xd0, 0x7f, 0xaa, 0x55 }, ++ .result = { 0xdb, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x88, 0xfd, 0xde, 0xa1, 0x93, 0x39, 0x1c, 0x6a, ++ 0x59, 0x33, 0xef, 0x9b, 0x71, 0x90, 0x15, 0x49, ++ 0x44, 0x72, 0x05, 0xaa, 0xe9, 0xda, 0x92, 0x8a, ++ 0x6b, 0x91, 0xa3, 0x52, 0xba, 0x10, 0xf4, 0x1f }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02 }, ++ .valid = true ++ }, ++ /* wycheproof - edge case for shared secret */ ++ { ++ .private = { 0xa0, 0xa4, 0xf1, 0x30, 0xb9, 0x8a, 0x5b, 0xe4, ++ 0xb1, 0xce, 0xdb, 0x7c, 0xb8, 0x55, 0x84, 0xa3, ++ 0x52, 0x0e, 0x14, 0x2d, 0x47, 0x4d, 0xc9, 0xcc, ++ 0xb9, 0x09, 0xa0, 0x73, 0xa9, 0x76, 0xbf, 0x63 }, ++ .public = { 0x30, 0x3b, 0x39, 0x2f, 0x15, 0x31, 0x16, 0xca, ++ 0xd9, 0xcc, 0x68, 0x2a, 0x00, 0xcc, 0xc4, 0x4c, ++ 0x95, 0xff, 0x0d, 0x3b, 0xbe, 0x56, 0x8b, 0xeb, ++ 0x6c, 0x4e, 0x73, 0x9b, 0xaf, 0xdc, 0x2c, 0x68 }, ++ .result = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 }, ++ .valid = true ++ }, ++ /* wycheproof - checking for overflow */ ++ { ++ .private = { 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .public = { 0xfd, 0x30, 0x0a, 0xeb, 0x40, 0xe1, 0xfa, 0x58, ++ 0x25, 0x18, 0x41, 0x2b, 0x49, 0xb2, 0x08, 0xa7, ++ 0x84, 0x2b, 0x1e, 0x1f, 0x05, 0x6a, 0x04, 0x01, ++ 0x78, 0xea, 0x41, 0x41, 0x53, 0x4f, 0x65, 0x2d }, ++ .result = { 0xb7, 0x34, 0x10, 0x5d, 0xc2, 0x57, 0x58, 0x5d, ++ 0x73, 0xb5, 0x66, 0xcc, 0xb7, 0x6f, 0x06, 0x27, ++ 0x95, 0xcc, 0xbe, 0xc8, 0x91, 0x28, 0xe5, 0x2b, ++ 0x02, 0xf3, 0xe5, 0x96, 0x39, 0xf1, 0x3c, 0x46 }, ++ .valid = true ++ }, ++ /* wycheproof - checking for overflow */ ++ { ++ .private = { 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .public = { 0xc8, 0xef, 0x79, 0xb5, 0x14, 0xd7, 0x68, 0x26, ++ 0x77, 0xbc, 0x79, 0x31, 0xe0, 0x6e, 0xe5, 0xc2, ++ 0x7c, 0x9b, 0x39, 0x2b, 0x4a, 0xe9, 0x48, 0x44, ++ 0x73, 0xf5, 0x54, 0xe6, 0x67, 0x8e, 0xcc, 0x2e }, ++ .result = { 0x64, 0x7a, 0x46, 0xb6, 0xfc, 0x3f, 0x40, 0xd6, ++ 0x21, 0x41, 0xee, 0x3c, 0xee, 0x70, 0x6b, 0x4d, ++ 0x7a, 0x92, 0x71, 0x59, 0x3a, 0x7b, 0x14, 0x3e, ++ 0x8e, 0x2e, 0x22, 0x79, 0x88, 0x3e, 0x45, 0x50 }, ++ .valid = true ++ }, ++ /* wycheproof - checking for overflow */ ++ { ++ .private = { 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .public = { 0x64, 0xae, 0xac, 0x25, 0x04, 0x14, 0x48, 0x61, ++ 0x53, 0x2b, 0x7b, 0xbc, 0xb6, 0xc8, 0x7d, 0x67, ++ 0xdd, 0x4c, 0x1f, 0x07, 0xeb, 0xc2, 0xe0, 0x6e, ++ 0xff, 0xb9, 0x5a, 0xec, 0xc6, 0x17, 0x0b, 0x2c }, ++ .result = { 0x4f, 0xf0, 0x3d, 0x5f, 0xb4, 0x3c, 0xd8, 0x65, ++ 0x7a, 0x3c, 0xf3, 0x7c, 0x13, 0x8c, 0xad, 0xce, ++ 0xcc, 0xe5, 0x09, 0xe4, 0xeb, 0xa0, 0x89, 0xd0, ++ 0xef, 0x40, 0xb4, 0xe4, 0xfb, 0x94, 0x61, 0x55 }, ++ .valid = true ++ }, ++ /* wycheproof - checking for overflow */ ++ { ++ .private = { 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .public = { 0xbf, 0x68, 0xe3, 0x5e, 0x9b, 0xdb, 0x7e, 0xee, ++ 0x1b, 0x50, 0x57, 0x02, 0x21, 0x86, 0x0f, 0x5d, ++ 0xcd, 0xad, 0x8a, 0xcb, 0xab, 0x03, 0x1b, 0x14, ++ 0x97, 0x4c, 0xc4, 0x90, 0x13, 0xc4, 0x98, 0x31 }, ++ .result = { 0x21, 0xce, 0xe5, 0x2e, 0xfd, 0xbc, 0x81, 0x2e, ++ 0x1d, 0x02, 0x1a, 0x4a, 0xf1, 0xe1, 0xd8, 0xbc, ++ 0x4d, 0xb3, 0xc4, 0x00, 0xe4, 0xd2, 0xa2, 0xc5, ++ 0x6a, 0x39, 0x26, 0xdb, 0x4d, 0x99, 0xc6, 0x5b }, ++ .valid = true ++ }, ++ /* wycheproof - checking for overflow */ ++ { ++ .private = { 0xc8, 0x17, 0x24, 0x70, 0x40, 0x00, 0xb2, 0x6d, ++ 0x31, 0x70, 0x3c, 0xc9, 0x7e, 0x3a, 0x37, 0x8d, ++ 0x56, 0xfa, 0xd8, 0x21, 0x93, 0x61, 0xc8, 0x8c, ++ 0xca, 0x8b, 0xd7, 0xc5, 0x71, 0x9b, 0x12, 0xb2 }, ++ .public = { 0x53, 0x47, 0xc4, 0x91, 0x33, 0x1a, 0x64, 0xb4, ++ 0x3d, 0xdc, 0x68, 0x30, 0x34, 0xe6, 0x77, 0xf5, ++ 0x3d, 0xc3, 0x2b, 0x52, 0xa5, 0x2a, 0x57, 0x7c, ++ 0x15, 0xa8, 0x3b, 0xf2, 0x98, 0xe9, 0x9f, 0x19 }, ++ .result = { 0x18, 0xcb, 0x89, 0xe4, 0xe2, 0x0c, 0x0c, 0x2b, ++ 0xd3, 0x24, 0x30, 0x52, 0x45, 0x26, 0x6c, 0x93, ++ 0x27, 0x69, 0x0b, 0xbe, 0x79, 0xac, 0xb8, 0x8f, ++ 0x5b, 0x8f, 0xb3, 0xf7, 0x4e, 0xca, 0x3e, 0x52 }, ++ .valid = true ++ }, ++ /* wycheproof - private key == -1 (mod order) */ ++ { ++ .private = { 0xa0, 0x23, 0xcd, 0xd0, 0x83, 0xef, 0x5b, 0xb8, ++ 0x2f, 0x10, 0xd6, 0x2e, 0x59, 0xe1, 0x5a, 0x68, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50 }, ++ .public = { 0x25, 0x8e, 0x04, 0x52, 0x3b, 0x8d, 0x25, 0x3e, ++ 0xe6, 0x57, 0x19, 0xfc, 0x69, 0x06, 0xc6, 0x57, ++ 0x19, 0x2d, 0x80, 0x71, 0x7e, 0xdc, 0x82, 0x8f, ++ 0xa0, 0xaf, 0x21, 0x68, 0x6e, 0x2f, 0xaa, 0x75 }, ++ .result = { 0x25, 0x8e, 0x04, 0x52, 0x3b, 0x8d, 0x25, 0x3e, ++ 0xe6, 0x57, 0x19, 0xfc, 0x69, 0x06, 0xc6, 0x57, ++ 0x19, 0x2d, 0x80, 0x71, 0x7e, 0xdc, 0x82, 0x8f, ++ 0xa0, 0xaf, 0x21, 0x68, 0x6e, 0x2f, 0xaa, 0x75 }, ++ .valid = true ++ }, ++ /* wycheproof - private key == 1 (mod order) on twist */ ++ { ++ .private = { 0x58, 0x08, 0x3d, 0xd2, 0x61, 0xad, 0x91, 0xef, ++ 0xf9, 0x52, 0x32, 0x2e, 0xc8, 0x24, 0xc6, 0x82, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x5f }, ++ .public = { 0x2e, 0xae, 0x5e, 0xc3, 0xdd, 0x49, 0x4e, 0x9f, ++ 0x2d, 0x37, 0xd2, 0x58, 0xf8, 0x73, 0xa8, 0xe6, ++ 0xe9, 0xd0, 0xdb, 0xd1, 0xe3, 0x83, 0xef, 0x64, ++ 0xd9, 0x8b, 0xb9, 0x1b, 0x3e, 0x0b, 0xe0, 0x35 }, ++ .result = { 0x2e, 0xae, 0x5e, 0xc3, 0xdd, 0x49, 0x4e, 0x9f, ++ 0x2d, 0x37, 0xd2, 0x58, 0xf8, 0x73, 0xa8, 0xe6, ++ 0xe9, 0xd0, 0xdb, 0xd1, 0xe3, 0x83, 0xef, 0x64, ++ 0xd9, 0x8b, 0xb9, 0x1b, 0x3e, 0x0b, 0xe0, 0x35 }, ++ .valid = true ++ } ++}; ++ ++bool __init curve25519_selftest(void) ++{ ++ bool success = true, ret, ret2; ++ size_t i = 0, j; ++ u8 in[CURVE25519_KEY_SIZE]; ++ u8 out[CURVE25519_KEY_SIZE], out2[CURVE25519_KEY_SIZE], ++ out3[CURVE25519_KEY_SIZE]; ++ ++ for (i = 0; i < ARRAY_SIZE(curve25519_test_vectors); ++i) { ++ memset(out, 0, CURVE25519_KEY_SIZE); ++ ret = curve25519(out, curve25519_test_vectors[i].private, ++ curve25519_test_vectors[i].public); ++ if (ret != curve25519_test_vectors[i].valid || ++ memcmp(out, curve25519_test_vectors[i].result, ++ CURVE25519_KEY_SIZE)) { ++ pr_err("curve25519 self-test %zu: FAIL\n", i + 1); ++ success = false; ++ } ++ } ++ ++ for (i = 0; i < 5; ++i) { ++ get_random_bytes(in, sizeof(in)); ++ ret = curve25519_generate_public(out, in); ++ ret2 = curve25519(out2, in, (u8[CURVE25519_KEY_SIZE]){ 9 }); ++ curve25519_generic(out3, in, (u8[CURVE25519_KEY_SIZE]){ 9 }); ++ if (ret != ret2 || ++ memcmp(out, out2, CURVE25519_KEY_SIZE) || ++ memcmp(out, out3, CURVE25519_KEY_SIZE)) { ++ pr_err("curve25519 basepoint self-test %zu: FAIL: input - 0x", ++ i + 1); ++ for (j = CURVE25519_KEY_SIZE; j-- > 0;) ++ printk(KERN_CONT "%02x", in[j]); ++ printk(KERN_CONT "\n"); ++ success = false; ++ } ++ } ++ ++ return success; ++} +--- a/lib/crypto/curve25519.c ++++ b/lib/crypto/curve25519.c +@@ -13,6 +13,8 @@ + #include + #include + ++bool curve25519_selftest(void); ++ + const u8 curve25519_null_point[CURVE25519_KEY_SIZE] __aligned(32) = { 0 }; + const u8 curve25519_base_point[CURVE25519_KEY_SIZE] __aligned(32) = { 9 }; + +@@ -20,6 +22,21 @@ EXPORT_SYMBOL(curve25519_null_point); + EXPORT_SYMBOL(curve25519_base_point); + EXPORT_SYMBOL(curve25519_generic); + ++static int __init mod_init(void) ++{ ++ if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && ++ WARN_ON(!curve25519_selftest())) ++ return -ENODEV; ++ return 0; ++} ++ ++static void __exit mod_exit(void) ++{ ++} ++ ++module_init(mod_init); ++module_exit(mod_exit); ++ + MODULE_LICENSE("GPL v2"); + MODULE_DESCRIPTION("Curve25519 scalar multiplication"); + MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0041-crypto-poly1305-add-new-32-and-64-bit-generic-versio.patch b/target/linux/generic/backport-5.4/080-wireguard-0041-crypto-poly1305-add-new-32-and-64-bit-generic-versio.patch new file mode 100644 index 0000000000..d843ea17ba --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0041-crypto-poly1305-add-new-32-and-64-bit-generic-versio.patch @@ -0,0 +1,1165 @@ +From a9f240ba1206fb080c1b3f727dfba1512035a82b Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 5 Jan 2020 22:40:46 -0500 +Subject: [PATCH 041/124] crypto: poly1305 - add new 32 and 64-bit generic + versions + +commit 1c08a104360f3e18f4ee6346c21cc3923efb952e upstream. + +These two C implementations from Zinc -- a 32x32 one and a 64x64 one, +depending on the platform -- come from Andrew Moon's public domain +poly1305-donna portable code, modified for usage in the kernel. The +precomputation in the 32-bit version and the use of 64x64 multiplies in +the 64-bit version make these perform better than the code it replaces. +Moon's code is also very widespread and has received many eyeballs of +scrutiny. + +There's a bit of interference between the x86 implementation, which +relies on internal details of the old scalar implementation. In the next +commit, the x86 implementation will be replaced with a faster one that +doesn't rely on this, so none of this matters much. But for now, to keep +this passing the tests, we inline the bits of the old implementation +that the x86 implementation relied on. Also, since we now support a +slightly larger key space, via the union, some offsets had to be fixed +up. + +Nonce calculation was folded in with the emit function, to take +advantage of 64x64 arithmetic. However, Adiantum appeared to rely on no +nonce handling in emit, so this path was conditionalized. We also +introduced a new struct, poly1305_core_key, to represent the precise +amount of space that particular implementation uses. + +Testing with kbench9000, depending on the CPU, the update function for +the 32x32 version has been improved by 4%-7%, and for the 64x64 by +19%-30%. The 32x32 gains are small, but I think there's great value in +having a parallel implementation to the 64x64 one so that the two can be +compared side-by-side as nice stand-alone units. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305-avx2-x86_64.S | 20 +-- + arch/x86/crypto/poly1305_glue.c | 215 +++++++++++++++++++++++-- + crypto/adiantum.c | 4 +- + crypto/nhpoly1305.c | 2 +- + crypto/poly1305_generic.c | 25 ++- + include/crypto/internal/poly1305.h | 45 ++---- + include/crypto/nhpoly1305.h | 4 +- + include/crypto/poly1305.h | 26 ++- + lib/crypto/Makefile | 4 +- + lib/crypto/poly1305-donna32.c | 204 +++++++++++++++++++++++ + lib/crypto/poly1305-donna64.c | 185 +++++++++++++++++++++ + lib/crypto/poly1305.c | 169 +------------------ + 12 files changed, 675 insertions(+), 228 deletions(-) + create mode 100644 lib/crypto/poly1305-donna32.c + create mode 100644 lib/crypto/poly1305-donna64.c + +--- a/arch/x86/crypto/poly1305-avx2-x86_64.S ++++ b/arch/x86/crypto/poly1305-avx2-x86_64.S +@@ -34,16 +34,16 @@ ORMASK: .octa 0x000000000100000000000000 + #define u2 0x08(%r8) + #define u3 0x0c(%r8) + #define u4 0x10(%r8) +-#define w0 0x14(%r8) +-#define w1 0x18(%r8) +-#define w2 0x1c(%r8) +-#define w3 0x20(%r8) +-#define w4 0x24(%r8) +-#define y0 0x28(%r8) +-#define y1 0x2c(%r8) +-#define y2 0x30(%r8) +-#define y3 0x34(%r8) +-#define y4 0x38(%r8) ++#define w0 0x18(%r8) ++#define w1 0x1c(%r8) ++#define w2 0x20(%r8) ++#define w3 0x24(%r8) ++#define w4 0x28(%r8) ++#define y0 0x30(%r8) ++#define y1 0x34(%r8) ++#define y2 0x38(%r8) ++#define y3 0x3c(%r8) ++#define y4 0x40(%r8) + #define m %rsi + #define hc0 %ymm0 + #define hc1 %ymm1 +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -25,6 +25,21 @@ asmlinkage void poly1305_4block_avx2(u32 + static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_simd); + static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2); + ++static inline u64 mlt(u64 a, u64 b) ++{ ++ return a * b; ++} ++ ++static inline u32 sr(u64 v, u_char n) ++{ ++ return v >> n; ++} ++ ++static inline u32 and(u32 v, u32 mask) ++{ ++ return v & mask; ++} ++ + static void poly1305_simd_mult(u32 *a, const u32 *b) + { + u8 m[POLY1305_BLOCK_SIZE]; +@@ -36,6 +51,168 @@ static void poly1305_simd_mult(u32 *a, c + poly1305_block_sse2(a, m, b, 1); + } + ++static void poly1305_integer_setkey(struct poly1305_key *key, const u8 *raw_key) ++{ ++ /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ ++ key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff; ++ key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03; ++ key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff; ++ key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff; ++ key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff; ++} ++ ++static void poly1305_integer_blocks(struct poly1305_state *state, ++ const struct poly1305_key *key, ++ const void *src, ++ unsigned int nblocks, u32 hibit) ++{ ++ u32 r0, r1, r2, r3, r4; ++ u32 s1, s2, s3, s4; ++ u32 h0, h1, h2, h3, h4; ++ u64 d0, d1, d2, d3, d4; ++ ++ if (!nblocks) ++ return; ++ ++ r0 = key->r[0]; ++ r1 = key->r[1]; ++ r2 = key->r[2]; ++ r3 = key->r[3]; ++ r4 = key->r[4]; ++ ++ s1 = r1 * 5; ++ s2 = r2 * 5; ++ s3 = r3 * 5; ++ s4 = r4 * 5; ++ ++ h0 = state->h[0]; ++ h1 = state->h[1]; ++ h2 = state->h[2]; ++ h3 = state->h[3]; ++ h4 = state->h[4]; ++ ++ do { ++ /* h += m[i] */ ++ h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff; ++ h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff; ++ h2 += (get_unaligned_le32(src + 6) >> 4) & 0x3ffffff; ++ h3 += (get_unaligned_le32(src + 9) >> 6) & 0x3ffffff; ++ h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24); ++ ++ /* h *= r */ ++ d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + ++ mlt(h3, s2) + mlt(h4, s1); ++ d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) + ++ mlt(h3, s3) + mlt(h4, s2); ++ d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) + ++ mlt(h3, s4) + mlt(h4, s3); ++ d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) + ++ mlt(h3, r0) + mlt(h4, s4); ++ d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) + ++ mlt(h3, r1) + mlt(h4, r0); ++ ++ /* (partial) h %= p */ ++ d1 += sr(d0, 26); h0 = and(d0, 0x3ffffff); ++ d2 += sr(d1, 26); h1 = and(d1, 0x3ffffff); ++ d3 += sr(d2, 26); h2 = and(d2, 0x3ffffff); ++ d4 += sr(d3, 26); h3 = and(d3, 0x3ffffff); ++ h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff); ++ h1 += h0 >> 26; h0 = h0 & 0x3ffffff; ++ ++ src += POLY1305_BLOCK_SIZE; ++ } while (--nblocks); ++ ++ state->h[0] = h0; ++ state->h[1] = h1; ++ state->h[2] = h2; ++ state->h[3] = h3; ++ state->h[4] = h4; ++} ++ ++static void poly1305_integer_emit(const struct poly1305_state *state, void *dst) ++{ ++ u32 h0, h1, h2, h3, h4; ++ u32 g0, g1, g2, g3, g4; ++ u32 mask; ++ ++ /* fully carry h */ ++ h0 = state->h[0]; ++ h1 = state->h[1]; ++ h2 = state->h[2]; ++ h3 = state->h[3]; ++ h4 = state->h[4]; ++ ++ h2 += (h1 >> 26); h1 = h1 & 0x3ffffff; ++ h3 += (h2 >> 26); h2 = h2 & 0x3ffffff; ++ h4 += (h3 >> 26); h3 = h3 & 0x3ffffff; ++ h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff; ++ h1 += (h0 >> 26); h0 = h0 & 0x3ffffff; ++ ++ /* compute h + -p */ ++ g0 = h0 + 5; ++ g1 = h1 + (g0 >> 26); g0 &= 0x3ffffff; ++ g2 = h2 + (g1 >> 26); g1 &= 0x3ffffff; ++ g3 = h3 + (g2 >> 26); g2 &= 0x3ffffff; ++ g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff; ++ ++ /* select h if h < p, or h + -p if h >= p */ ++ mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1; ++ g0 &= mask; ++ g1 &= mask; ++ g2 &= mask; ++ g3 &= mask; ++ g4 &= mask; ++ mask = ~mask; ++ h0 = (h0 & mask) | g0; ++ h1 = (h1 & mask) | g1; ++ h2 = (h2 & mask) | g2; ++ h3 = (h3 & mask) | g3; ++ h4 = (h4 & mask) | g4; ++ ++ /* h = h % (2^128) */ ++ put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0); ++ put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4); ++ put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8); ++ put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12); ++} ++ ++void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key) ++{ ++ poly1305_integer_setkey(desc->opaque_r, key); ++ desc->s[0] = get_unaligned_le32(key + 16); ++ desc->s[1] = get_unaligned_le32(key + 20); ++ desc->s[2] = get_unaligned_le32(key + 24); ++ desc->s[3] = get_unaligned_le32(key + 28); ++ poly1305_core_init(&desc->h); ++ desc->buflen = 0; ++ desc->sset = true; ++ desc->rset = 1; ++} ++EXPORT_SYMBOL_GPL(poly1305_init_arch); ++ ++static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, ++ const u8 *src, unsigned int srclen) ++{ ++ if (!dctx->sset) { ++ if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { ++ poly1305_integer_setkey(dctx->r, src); ++ src += POLY1305_BLOCK_SIZE; ++ srclen -= POLY1305_BLOCK_SIZE; ++ dctx->rset = 1; ++ } ++ if (srclen >= 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; ++ srclen -= POLY1305_BLOCK_SIZE; ++ dctx->sset = true; ++ } ++ } ++ return srclen; ++} ++ + static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx, + const u8 *src, unsigned int srclen) + { +@@ -47,8 +224,8 @@ static unsigned int poly1305_scalar_bloc + srclen = datalen; + } + if (srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_core_blocks(&dctx->h, dctx->r, src, +- srclen / POLY1305_BLOCK_SIZE, 1); ++ poly1305_integer_blocks(&dctx->h, dctx->opaque_r, src, ++ srclen / POLY1305_BLOCK_SIZE, 1); + srclen %= POLY1305_BLOCK_SIZE; + } + return srclen; +@@ -105,12 +282,6 @@ static unsigned int poly1305_simd_blocks + return srclen; + } + +-void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key) +-{ +- poly1305_init_generic(desc, key); +-} +-EXPORT_SYMBOL(poly1305_init_arch); +- + void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, + unsigned int srclen) + { +@@ -158,9 +329,31 @@ void poly1305_update_arch(struct poly130 + } + EXPORT_SYMBOL(poly1305_update_arch); + +-void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest) ++void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *dst) + { +- poly1305_final_generic(desc, digest); ++ __le32 digest[4]; ++ u64 f = 0; ++ ++ if (unlikely(desc->buflen)) { ++ desc->buf[desc->buflen++] = 1; ++ memset(desc->buf + desc->buflen, 0, ++ POLY1305_BLOCK_SIZE - desc->buflen); ++ poly1305_integer_blocks(&desc->h, desc->opaque_r, desc->buf, 1, 0); ++ } ++ ++ poly1305_integer_emit(&desc->h, digest); ++ ++ /* mac = (h + s) % (2^128) */ ++ f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0]; ++ put_unaligned_le32(f, dst + 0); ++ f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1]; ++ put_unaligned_le32(f, dst + 4); ++ f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2]; ++ put_unaligned_le32(f, dst + 8); ++ f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3]; ++ put_unaligned_le32(f, dst + 12); ++ ++ *desc = (struct poly1305_desc_ctx){}; + } + EXPORT_SYMBOL(poly1305_final_arch); + +@@ -183,7 +376,7 @@ static int crypto_poly1305_final(struct + if (unlikely(!dctx->sset)) + return -ENOKEY; + +- poly1305_final_generic(dctx, dst); ++ poly1305_final_arch(dctx, dst); + return 0; + } + +--- a/crypto/adiantum.c ++++ b/crypto/adiantum.c +@@ -72,7 +72,7 @@ struct adiantum_tfm_ctx { + struct crypto_skcipher *streamcipher; + struct crypto_cipher *blockcipher; + struct crypto_shash *hash; +- struct poly1305_key header_hash_key; ++ struct poly1305_core_key header_hash_key; + }; + + struct adiantum_request_ctx { +@@ -249,7 +249,7 @@ static void adiantum_hash_header(struct + poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv, + TWEAK_SIZE / POLY1305_BLOCK_SIZE, 1); + +- poly1305_core_emit(&state, &rctx->header_hash); ++ poly1305_core_emit(&state, NULL, &rctx->header_hash); + } + + /* Hash the left-hand part (the "bulk") of the message using NHPoly1305 */ +--- a/crypto/nhpoly1305.c ++++ b/crypto/nhpoly1305.c +@@ -210,7 +210,7 @@ int crypto_nhpoly1305_final_helper(struc + if (state->nh_remaining) + process_nh_hash_value(state, key); + +- poly1305_core_emit(&state->poly_state, dst); ++ poly1305_core_emit(&state->poly_state, NULL, dst); + return 0; + } + EXPORT_SYMBOL(crypto_nhpoly1305_final_helper); +--- a/crypto/poly1305_generic.c ++++ b/crypto/poly1305_generic.c +@@ -31,6 +31,29 @@ static int crypto_poly1305_init(struct s + return 0; + } + ++static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, ++ const u8 *src, unsigned int srclen) ++{ ++ if (!dctx->sset) { ++ if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { ++ poly1305_core_setkey(&dctx->core_r, src); ++ src += POLY1305_BLOCK_SIZE; ++ srclen -= POLY1305_BLOCK_SIZE; ++ dctx->rset = 2; ++ } ++ if (srclen >= 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; ++ srclen -= POLY1305_BLOCK_SIZE; ++ dctx->sset = true; ++ } ++ } ++ return srclen; ++} ++ + static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src, + unsigned int srclen) + { +@@ -42,7 +65,7 @@ static void poly1305_blocks(struct poly1 + srclen = datalen; + } + +- poly1305_core_blocks(&dctx->h, dctx->r, src, ++ poly1305_core_blocks(&dctx->h, &dctx->core_r, src, + srclen / POLY1305_BLOCK_SIZE, 1); + } + +--- a/include/crypto/internal/poly1305.h ++++ b/include/crypto/internal/poly1305.h +@@ -11,48 +11,23 @@ + #include + + /* +- * Poly1305 core functions. These implement the ε-almost-∆-universal hash +- * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce +- * ("s key") at the end. They also only support block-aligned inputs. ++ * Poly1305 core functions. These only accept whole blocks; the caller must ++ * handle any needed block buffering and padding. 'hibit' must be 1 for any ++ * full blocks, or 0 for the final block if it had to be padded. If 'nonce' is ++ * non-NULL, then it's added at the end to compute the Poly1305 MAC. Otherwise, ++ * only the ε-almost-∆-universal hash function (not the full MAC) is computed. + */ +-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key); ++ ++void poly1305_core_setkey(struct poly1305_core_key *key, const u8 *raw_key); + static inline void poly1305_core_init(struct poly1305_state *state) + { + *state = (struct poly1305_state){}; + } + + void poly1305_core_blocks(struct poly1305_state *state, +- const struct poly1305_key *key, const void *src, ++ const struct poly1305_core_key *key, const void *src, + unsigned int nblocks, u32 hibit); +-void poly1305_core_emit(const struct poly1305_state *state, void *dst); +- +-/* +- * Poly1305 requires a unique key for each tag, which implies that we can't set +- * it on the tfm that gets accessed by multiple users simultaneously. Instead we +- * expect the key as the first 32 bytes in the update() call. +- */ +-static inline +-unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen) +-{ +- if (!dctx->sset) { +- if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_core_setkey(dctx->r, src); +- src += POLY1305_BLOCK_SIZE; +- srclen -= POLY1305_BLOCK_SIZE; +- dctx->rset = 1; +- } +- if (srclen >= 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; +- srclen -= POLY1305_BLOCK_SIZE; +- dctx->sset = true; +- } +- } +- return srclen; +-} ++void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4], ++ void *dst); + + #endif +--- a/include/crypto/nhpoly1305.h ++++ b/include/crypto/nhpoly1305.h +@@ -7,7 +7,7 @@ + #define _NHPOLY1305_H + + #include +-#include ++#include + + /* NH parameterization: */ + +@@ -33,7 +33,7 @@ + #define NHPOLY1305_KEY_SIZE (POLY1305_BLOCK_SIZE + NH_KEY_BYTES) + + struct nhpoly1305_key { +- struct poly1305_key poly_key; ++ struct poly1305_core_key poly_key; + u32 nh_key[NH_KEY_WORDS]; + }; + +--- a/include/crypto/poly1305.h ++++ b/include/crypto/poly1305.h +@@ -13,12 +13,29 @@ + #define POLY1305_KEY_SIZE 32 + #define POLY1305_DIGEST_SIZE 16 + ++/* The poly1305_key and poly1305_state types are mostly opaque and ++ * implementation-defined. Limbs might be in base 2^64 or base 2^26, or ++ * different yet. The union type provided keeps these 64-bit aligned for the ++ * case in which this is implemented using 64x64 multiplies. ++ */ ++ + struct poly1305_key { +- u32 r[5]; /* key, base 2^26 */ ++ union { ++ u32 r[5]; ++ u64 r64[3]; ++ }; ++}; ++ ++struct poly1305_core_key { ++ struct poly1305_key key; ++ struct poly1305_key precomputed_s; + }; + + struct poly1305_state { +- u32 h[5]; /* accumulator, base 2^26 */ ++ union { ++ u32 h[5]; ++ u64 h64[3]; ++ }; + }; + + struct poly1305_desc_ctx { +@@ -35,7 +52,10 @@ struct poly1305_desc_ctx { + /* accumulator */ + struct poly1305_state h; + /* key */ +- struct poly1305_key r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE]; ++ union { ++ struct poly1305_key opaque_r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE]; ++ struct poly1305_core_key core_r; ++ }; + }; + + void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key); +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -28,7 +28,9 @@ obj-$(CONFIG_CRYPTO_LIB_DES) += libdes + libdes-y := des.o + + obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC) += libpoly1305.o +-libpoly1305-y := poly1305.o ++libpoly1305-y := poly1305-donna32.o ++libpoly1305-$(CONFIG_ARCH_SUPPORTS_INT128) := poly1305-donna64.o ++libpoly1305-y += poly1305.o + + obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o + libsha256-y := sha256.o +--- /dev/null ++++ b/lib/crypto/poly1305-donna32.c +@@ -0,0 +1,204 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is based in part on Andrew Moon's poly1305-donna, which is in the ++ * public domain. ++ */ ++ ++#include ++#include ++#include ++ ++void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) ++{ ++ /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ ++ key->key.r[0] = (get_unaligned_le32(&raw_key[0])) & 0x3ffffff; ++ key->key.r[1] = (get_unaligned_le32(&raw_key[3]) >> 2) & 0x3ffff03; ++ key->key.r[2] = (get_unaligned_le32(&raw_key[6]) >> 4) & 0x3ffc0ff; ++ key->key.r[3] = (get_unaligned_le32(&raw_key[9]) >> 6) & 0x3f03fff; ++ key->key.r[4] = (get_unaligned_le32(&raw_key[12]) >> 8) & 0x00fffff; ++ ++ /* s = 5*r */ ++ key->precomputed_s.r[0] = key->key.r[1] * 5; ++ key->precomputed_s.r[1] = key->key.r[2] * 5; ++ key->precomputed_s.r[2] = key->key.r[3] * 5; ++ key->precomputed_s.r[3] = key->key.r[4] * 5; ++} ++EXPORT_SYMBOL(poly1305_core_setkey); ++ ++void poly1305_core_blocks(struct poly1305_state *state, ++ const struct poly1305_core_key *key, const void *src, ++ unsigned int nblocks, u32 hibit) ++{ ++ const u8 *input = src; ++ u32 r0, r1, r2, r3, r4; ++ u32 s1, s2, s3, s4; ++ u32 h0, h1, h2, h3, h4; ++ u64 d0, d1, d2, d3, d4; ++ u32 c; ++ ++ if (!nblocks) ++ return; ++ ++ hibit <<= 24; ++ ++ r0 = key->key.r[0]; ++ r1 = key->key.r[1]; ++ r2 = key->key.r[2]; ++ r3 = key->key.r[3]; ++ r4 = key->key.r[4]; ++ ++ s1 = key->precomputed_s.r[0]; ++ s2 = key->precomputed_s.r[1]; ++ s3 = key->precomputed_s.r[2]; ++ s4 = key->precomputed_s.r[3]; ++ ++ h0 = state->h[0]; ++ h1 = state->h[1]; ++ h2 = state->h[2]; ++ h3 = state->h[3]; ++ h4 = state->h[4]; ++ ++ do { ++ /* h += m[i] */ ++ h0 += (get_unaligned_le32(&input[0])) & 0x3ffffff; ++ h1 += (get_unaligned_le32(&input[3]) >> 2) & 0x3ffffff; ++ h2 += (get_unaligned_le32(&input[6]) >> 4) & 0x3ffffff; ++ h3 += (get_unaligned_le32(&input[9]) >> 6) & 0x3ffffff; ++ h4 += (get_unaligned_le32(&input[12]) >> 8) | hibit; ++ ++ /* h *= r */ ++ d0 = ((u64)h0 * r0) + ((u64)h1 * s4) + ++ ((u64)h2 * s3) + ((u64)h3 * s2) + ++ ((u64)h4 * s1); ++ d1 = ((u64)h0 * r1) + ((u64)h1 * r0) + ++ ((u64)h2 * s4) + ((u64)h3 * s3) + ++ ((u64)h4 * s2); ++ d2 = ((u64)h0 * r2) + ((u64)h1 * r1) + ++ ((u64)h2 * r0) + ((u64)h3 * s4) + ++ ((u64)h4 * s3); ++ d3 = ((u64)h0 * r3) + ((u64)h1 * r2) + ++ ((u64)h2 * r1) + ((u64)h3 * r0) + ++ ((u64)h4 * s4); ++ d4 = ((u64)h0 * r4) + ((u64)h1 * r3) + ++ ((u64)h2 * r2) + ((u64)h3 * r1) + ++ ((u64)h4 * r0); ++ ++ /* (partial) h %= p */ ++ c = (u32)(d0 >> 26); ++ h0 = (u32)d0 & 0x3ffffff; ++ d1 += c; ++ c = (u32)(d1 >> 26); ++ h1 = (u32)d1 & 0x3ffffff; ++ d2 += c; ++ c = (u32)(d2 >> 26); ++ h2 = (u32)d2 & 0x3ffffff; ++ d3 += c; ++ c = (u32)(d3 >> 26); ++ h3 = (u32)d3 & 0x3ffffff; ++ d4 += c; ++ c = (u32)(d4 >> 26); ++ h4 = (u32)d4 & 0x3ffffff; ++ h0 += c * 5; ++ c = (h0 >> 26); ++ h0 = h0 & 0x3ffffff; ++ h1 += c; ++ ++ input += POLY1305_BLOCK_SIZE; ++ } while (--nblocks); ++ ++ state->h[0] = h0; ++ state->h[1] = h1; ++ state->h[2] = h2; ++ state->h[3] = h3; ++ state->h[4] = h4; ++} ++EXPORT_SYMBOL(poly1305_core_blocks); ++ ++void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4], ++ void *dst) ++{ ++ u8 *mac = dst; ++ u32 h0, h1, h2, h3, h4, c; ++ u32 g0, g1, g2, g3, g4; ++ u64 f; ++ u32 mask; ++ ++ /* fully carry h */ ++ h0 = state->h[0]; ++ h1 = state->h[1]; ++ h2 = state->h[2]; ++ h3 = state->h[3]; ++ h4 = state->h[4]; ++ ++ c = h1 >> 26; ++ h1 = h1 & 0x3ffffff; ++ h2 += c; ++ c = h2 >> 26; ++ h2 = h2 & 0x3ffffff; ++ h3 += c; ++ c = h3 >> 26; ++ h3 = h3 & 0x3ffffff; ++ h4 += c; ++ c = h4 >> 26; ++ h4 = h4 & 0x3ffffff; ++ h0 += c * 5; ++ c = h0 >> 26; ++ h0 = h0 & 0x3ffffff; ++ h1 += c; ++ ++ /* compute h + -p */ ++ g0 = h0 + 5; ++ c = g0 >> 26; ++ g0 &= 0x3ffffff; ++ g1 = h1 + c; ++ c = g1 >> 26; ++ g1 &= 0x3ffffff; ++ g2 = h2 + c; ++ c = g2 >> 26; ++ g2 &= 0x3ffffff; ++ g3 = h3 + c; ++ c = g3 >> 26; ++ g3 &= 0x3ffffff; ++ g4 = h4 + c - (1UL << 26); ++ ++ /* select h if h < p, or h + -p if h >= p */ ++ mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1; ++ g0 &= mask; ++ g1 &= mask; ++ g2 &= mask; ++ g3 &= mask; ++ g4 &= mask; ++ mask = ~mask; ++ ++ h0 = (h0 & mask) | g0; ++ h1 = (h1 & mask) | g1; ++ h2 = (h2 & mask) | g2; ++ h3 = (h3 & mask) | g3; ++ h4 = (h4 & mask) | g4; ++ ++ /* h = h % (2^128) */ ++ h0 = ((h0) | (h1 << 26)) & 0xffffffff; ++ h1 = ((h1 >> 6) | (h2 << 20)) & 0xffffffff; ++ h2 = ((h2 >> 12) | (h3 << 14)) & 0xffffffff; ++ h3 = ((h3 >> 18) | (h4 << 8)) & 0xffffffff; ++ ++ if (likely(nonce)) { ++ /* mac = (h + nonce) % (2^128) */ ++ f = (u64)h0 + nonce[0]; ++ h0 = (u32)f; ++ f = (u64)h1 + nonce[1] + (f >> 32); ++ h1 = (u32)f; ++ f = (u64)h2 + nonce[2] + (f >> 32); ++ h2 = (u32)f; ++ f = (u64)h3 + nonce[3] + (f >> 32); ++ h3 = (u32)f; ++ } ++ ++ put_unaligned_le32(h0, &mac[0]); ++ put_unaligned_le32(h1, &mac[4]); ++ put_unaligned_le32(h2, &mac[8]); ++ put_unaligned_le32(h3, &mac[12]); ++} ++EXPORT_SYMBOL(poly1305_core_emit); +--- /dev/null ++++ b/lib/crypto/poly1305-donna64.c +@@ -0,0 +1,185 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is based in part on Andrew Moon's poly1305-donna, which is in the ++ * public domain. ++ */ ++ ++#include ++#include ++#include ++ ++typedef __uint128_t u128; ++ ++void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) ++{ ++ u64 t0, t1; ++ ++ /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ ++ t0 = get_unaligned_le64(&raw_key[0]); ++ t1 = get_unaligned_le64(&raw_key[8]); ++ ++ key->key.r64[0] = t0 & 0xffc0fffffffULL; ++ key->key.r64[1] = ((t0 >> 44) | (t1 << 20)) & 0xfffffc0ffffULL; ++ key->key.r64[2] = ((t1 >> 24)) & 0x00ffffffc0fULL; ++ ++ /* s = 20*r */ ++ key->precomputed_s.r64[0] = key->key.r64[1] * 20; ++ key->precomputed_s.r64[1] = key->key.r64[2] * 20; ++} ++EXPORT_SYMBOL(poly1305_core_setkey); ++ ++void poly1305_core_blocks(struct poly1305_state *state, ++ const struct poly1305_core_key *key, const void *src, ++ unsigned int nblocks, u32 hibit) ++{ ++ const u8 *input = src; ++ u64 hibit64; ++ u64 r0, r1, r2; ++ u64 s1, s2; ++ u64 h0, h1, h2; ++ u64 c; ++ u128 d0, d1, d2, d; ++ ++ if (!nblocks) ++ return; ++ ++ hibit64 = ((u64)hibit) << 40; ++ ++ r0 = key->key.r64[0]; ++ r1 = key->key.r64[1]; ++ r2 = key->key.r64[2]; ++ ++ h0 = state->h64[0]; ++ h1 = state->h64[1]; ++ h2 = state->h64[2]; ++ ++ s1 = key->precomputed_s.r64[0]; ++ s2 = key->precomputed_s.r64[1]; ++ ++ do { ++ u64 t0, t1; ++ ++ /* h += m[i] */ ++ t0 = get_unaligned_le64(&input[0]); ++ t1 = get_unaligned_le64(&input[8]); ++ ++ h0 += t0 & 0xfffffffffffULL; ++ h1 += ((t0 >> 44) | (t1 << 20)) & 0xfffffffffffULL; ++ h2 += (((t1 >> 24)) & 0x3ffffffffffULL) | hibit64; ++ ++ /* h *= r */ ++ d0 = (u128)h0 * r0; ++ d = (u128)h1 * s2; ++ d0 += d; ++ d = (u128)h2 * s1; ++ d0 += d; ++ d1 = (u128)h0 * r1; ++ d = (u128)h1 * r0; ++ d1 += d; ++ d = (u128)h2 * s2; ++ d1 += d; ++ d2 = (u128)h0 * r2; ++ d = (u128)h1 * r1; ++ d2 += d; ++ d = (u128)h2 * r0; ++ d2 += d; ++ ++ /* (partial) h %= p */ ++ c = (u64)(d0 >> 44); ++ h0 = (u64)d0 & 0xfffffffffffULL; ++ d1 += c; ++ c = (u64)(d1 >> 44); ++ h1 = (u64)d1 & 0xfffffffffffULL; ++ d2 += c; ++ c = (u64)(d2 >> 42); ++ h2 = (u64)d2 & 0x3ffffffffffULL; ++ h0 += c * 5; ++ c = h0 >> 44; ++ h0 = h0 & 0xfffffffffffULL; ++ h1 += c; ++ ++ input += POLY1305_BLOCK_SIZE; ++ } while (--nblocks); ++ ++ state->h64[0] = h0; ++ state->h64[1] = h1; ++ state->h64[2] = h2; ++} ++EXPORT_SYMBOL(poly1305_core_blocks); ++ ++void poly1305_core_emit(const struct poly1305_state *state, const u32 nonce[4], ++ void *dst) ++{ ++ u8 *mac = dst; ++ u64 h0, h1, h2, c; ++ u64 g0, g1, g2; ++ u64 t0, t1; ++ ++ /* fully carry h */ ++ h0 = state->h64[0]; ++ h1 = state->h64[1]; ++ h2 = state->h64[2]; ++ ++ c = h1 >> 44; ++ h1 &= 0xfffffffffffULL; ++ h2 += c; ++ c = h2 >> 42; ++ h2 &= 0x3ffffffffffULL; ++ h0 += c * 5; ++ c = h0 >> 44; ++ h0 &= 0xfffffffffffULL; ++ h1 += c; ++ c = h1 >> 44; ++ h1 &= 0xfffffffffffULL; ++ h2 += c; ++ c = h2 >> 42; ++ h2 &= 0x3ffffffffffULL; ++ h0 += c * 5; ++ c = h0 >> 44; ++ h0 &= 0xfffffffffffULL; ++ h1 += c; ++ ++ /* compute h + -p */ ++ g0 = h0 + 5; ++ c = g0 >> 44; ++ g0 &= 0xfffffffffffULL; ++ g1 = h1 + c; ++ c = g1 >> 44; ++ g1 &= 0xfffffffffffULL; ++ g2 = h2 + c - (1ULL << 42); ++ ++ /* select h if h < p, or h + -p if h >= p */ ++ c = (g2 >> ((sizeof(u64) * 8) - 1)) - 1; ++ g0 &= c; ++ g1 &= c; ++ g2 &= c; ++ c = ~c; ++ h0 = (h0 & c) | g0; ++ h1 = (h1 & c) | g1; ++ h2 = (h2 & c) | g2; ++ ++ if (likely(nonce)) { ++ /* h = (h + nonce) */ ++ t0 = ((u64)nonce[1] << 32) | nonce[0]; ++ t1 = ((u64)nonce[3] << 32) | nonce[2]; ++ ++ h0 += t0 & 0xfffffffffffULL; ++ c = h0 >> 44; ++ h0 &= 0xfffffffffffULL; ++ h1 += (((t0 >> 44) | (t1 << 20)) & 0xfffffffffffULL) + c; ++ c = h1 >> 44; ++ h1 &= 0xfffffffffffULL; ++ h2 += (((t1 >> 24)) & 0x3ffffffffffULL) + c; ++ h2 &= 0x3ffffffffffULL; ++ } ++ ++ /* mac = h % (2^128) */ ++ h0 = h0 | (h1 << 44); ++ h1 = (h1 >> 20) | (h2 << 24); ++ ++ put_unaligned_le64(h0, &mac[0]); ++ put_unaligned_le64(h1, &mac[8]); ++} ++EXPORT_SYMBOL(poly1305_core_emit); +--- a/lib/crypto/poly1305.c ++++ b/lib/crypto/poly1305.c +@@ -12,151 +12,9 @@ + #include + #include + +-static inline u64 mlt(u64 a, u64 b) +-{ +- return a * b; +-} +- +-static inline u32 sr(u64 v, u_char n) +-{ +- return v >> n; +-} +- +-static inline u32 and(u32 v, u32 mask) +-{ +- return v & mask; +-} +- +-void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key) +-{ +- /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ +- key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff; +- key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03; +- key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff; +- key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff; +- key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff; +-} +-EXPORT_SYMBOL_GPL(poly1305_core_setkey); +- +-void poly1305_core_blocks(struct poly1305_state *state, +- const struct poly1305_key *key, const void *src, +- unsigned int nblocks, u32 hibit) +-{ +- u32 r0, r1, r2, r3, r4; +- u32 s1, s2, s3, s4; +- u32 h0, h1, h2, h3, h4; +- u64 d0, d1, d2, d3, d4; +- +- if (!nblocks) +- return; +- +- r0 = key->r[0]; +- r1 = key->r[1]; +- r2 = key->r[2]; +- r3 = key->r[3]; +- r4 = key->r[4]; +- +- s1 = r1 * 5; +- s2 = r2 * 5; +- s3 = r3 * 5; +- s4 = r4 * 5; +- +- h0 = state->h[0]; +- h1 = state->h[1]; +- h2 = state->h[2]; +- h3 = state->h[3]; +- h4 = state->h[4]; +- +- do { +- /* h += m[i] */ +- h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff; +- h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff; +- h2 += (get_unaligned_le32(src + 6) >> 4) & 0x3ffffff; +- h3 += (get_unaligned_le32(src + 9) >> 6) & 0x3ffffff; +- h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24); +- +- /* h *= r */ +- d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + +- mlt(h3, s2) + mlt(h4, s1); +- d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) + +- mlt(h3, s3) + mlt(h4, s2); +- d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) + +- mlt(h3, s4) + mlt(h4, s3); +- d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) + +- mlt(h3, r0) + mlt(h4, s4); +- d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) + +- mlt(h3, r1) + mlt(h4, r0); +- +- /* (partial) h %= p */ +- d1 += sr(d0, 26); h0 = and(d0, 0x3ffffff); +- d2 += sr(d1, 26); h1 = and(d1, 0x3ffffff); +- d3 += sr(d2, 26); h2 = and(d2, 0x3ffffff); +- d4 += sr(d3, 26); h3 = and(d3, 0x3ffffff); +- h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff); +- h1 += h0 >> 26; h0 = h0 & 0x3ffffff; +- +- src += POLY1305_BLOCK_SIZE; +- } while (--nblocks); +- +- state->h[0] = h0; +- state->h[1] = h1; +- state->h[2] = h2; +- state->h[3] = h3; +- state->h[4] = h4; +-} +-EXPORT_SYMBOL_GPL(poly1305_core_blocks); +- +-void poly1305_core_emit(const struct poly1305_state *state, void *dst) +-{ +- u32 h0, h1, h2, h3, h4; +- u32 g0, g1, g2, g3, g4; +- u32 mask; +- +- /* fully carry h */ +- h0 = state->h[0]; +- h1 = state->h[1]; +- h2 = state->h[2]; +- h3 = state->h[3]; +- h4 = state->h[4]; +- +- h2 += (h1 >> 26); h1 = h1 & 0x3ffffff; +- h3 += (h2 >> 26); h2 = h2 & 0x3ffffff; +- h4 += (h3 >> 26); h3 = h3 & 0x3ffffff; +- h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff; +- h1 += (h0 >> 26); h0 = h0 & 0x3ffffff; +- +- /* compute h + -p */ +- g0 = h0 + 5; +- g1 = h1 + (g0 >> 26); g0 &= 0x3ffffff; +- g2 = h2 + (g1 >> 26); g1 &= 0x3ffffff; +- g3 = h3 + (g2 >> 26); g2 &= 0x3ffffff; +- g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff; +- +- /* select h if h < p, or h + -p if h >= p */ +- mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1; +- g0 &= mask; +- g1 &= mask; +- g2 &= mask; +- g3 &= mask; +- g4 &= mask; +- mask = ~mask; +- h0 = (h0 & mask) | g0; +- h1 = (h1 & mask) | g1; +- h2 = (h2 & mask) | g2; +- h3 = (h3 & mask) | g3; +- h4 = (h4 & mask) | g4; +- +- /* h = h % (2^128) */ +- put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0); +- put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4); +- put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8); +- put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12); +-} +-EXPORT_SYMBOL_GPL(poly1305_core_emit); +- + void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key) + { +- poly1305_core_setkey(desc->r, key); ++ poly1305_core_setkey(&desc->core_r, key); + desc->s[0] = get_unaligned_le32(key + 16); + desc->s[1] = get_unaligned_le32(key + 20); + desc->s[2] = get_unaligned_le32(key + 24); +@@ -164,7 +22,7 @@ void poly1305_init_generic(struct poly13 + poly1305_core_init(&desc->h); + desc->buflen = 0; + desc->sset = true; +- desc->rset = 1; ++ desc->rset = 2; + } + EXPORT_SYMBOL_GPL(poly1305_init_generic); + +@@ -181,13 +39,14 @@ void poly1305_update_generic(struct poly + desc->buflen += bytes; + + if (desc->buflen == POLY1305_BLOCK_SIZE) { +- poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 1); ++ poly1305_core_blocks(&desc->h, &desc->core_r, desc->buf, ++ 1, 1); + desc->buflen = 0; + } + } + + if (likely(nbytes >= POLY1305_BLOCK_SIZE)) { +- poly1305_core_blocks(&desc->h, desc->r, src, ++ poly1305_core_blocks(&desc->h, &desc->core_r, src, + nbytes / POLY1305_BLOCK_SIZE, 1); + src += nbytes - (nbytes % POLY1305_BLOCK_SIZE); + nbytes %= POLY1305_BLOCK_SIZE; +@@ -202,28 +61,14 @@ EXPORT_SYMBOL_GPL(poly1305_update_generi + + void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *dst) + { +- __le32 digest[4]; +- u64 f = 0; +- + if (unlikely(desc->buflen)) { + desc->buf[desc->buflen++] = 1; + memset(desc->buf + desc->buflen, 0, + POLY1305_BLOCK_SIZE - desc->buflen); +- poly1305_core_blocks(&desc->h, desc->r, desc->buf, 1, 0); ++ poly1305_core_blocks(&desc->h, &desc->core_r, desc->buf, 1, 0); + } + +- poly1305_core_emit(&desc->h, digest); +- +- /* mac = (h + s) % (2^128) */ +- f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0]; +- put_unaligned_le32(f, dst + 0); +- f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1]; +- put_unaligned_le32(f, dst + 4); +- f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2]; +- put_unaligned_le32(f, dst + 8); +- f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3]; +- put_unaligned_le32(f, dst + 12); +- ++ poly1305_core_emit(&desc->h, desc->s, dst); + *desc = (struct poly1305_desc_ctx){}; + } + EXPORT_SYMBOL_GPL(poly1305_final_generic); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0042-crypto-x86-poly1305-import-unmodified-cryptogams-imp.patch b/target/linux/generic/backport-5.4/080-wireguard-0042-crypto-x86-poly1305-import-unmodified-cryptogams-imp.patch new file mode 100644 index 0000000000..7c80309d2a --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0042-crypto-x86-poly1305-import-unmodified-cryptogams-imp.patch @@ -0,0 +1,4183 @@ +From 6dbd1094c7b9897a3264418cd6543fae1a0bcade Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 5 Jan 2020 22:40:47 -0500 +Subject: [PATCH 042/124] crypto: x86/poly1305 - import unmodified cryptogams + implementation + +commit 0896ca2a0cb6127e8a129f1f2a680d49b6b0f65c upstream. + +These x86_64 vectorized implementations come from Andy Polyakov's +CRYPTOGAMS implementation, and are included here in raw form without +modification, so that subsequent commits that fix these up for the +kernel can see how it has changed. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 4159 +++++++++++++++++ + 1 file changed, 4159 insertions(+) + create mode 100644 arch/x86/crypto/poly1305-x86_64-cryptogams.pl + +--- /dev/null ++++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +@@ -0,0 +1,4159 @@ ++#! /usr/bin/env perl ++# Copyright 2016-2018 The OpenSSL Project Authors. All Rights Reserved. ++# ++# Licensed under the OpenSSL license (the "License"). You may not use ++# this file except in compliance with the License. You can obtain a copy ++# in the file LICENSE in the source distribution or at ++# https://www.openssl.org/source/license.html ++ ++# ++# ==================================================================== ++# Written by Andy Polyakov 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 http://www.openssl.org/~appro/cryptogams/. ++# ==================================================================== ++# ++# This module implements Poly1305 hash for x86_64. ++# ++# March 2015 ++# ++# Initial release. ++# ++# December 2016 ++# ++# Add AVX512F+VL+BW code path. ++# ++# November 2017 ++# ++# Convert AVX512F+VL+BW code path to pure AVX512F, so that it can be ++# executed even on Knights Landing. Trigger for modification was ++# observation that AVX512 code paths can negatively affect overall ++# Skylake-X system performance. Since we are likely to suppress ++# AVX512F capability flag [at least on Skylake-X], conversion serves ++# as kind of "investment protection". Note that next *lake processor, ++# Cannolake, has AVX512IFMA code path to execute... ++# ++# Numbers are cycles per processed byte with poly1305_blocks alone, ++# measured with rdtsc at fixed clock frequency. ++# ++# IALU/gcc-4.8(*) AVX(**) AVX2 AVX-512 ++# P4 4.46/+120% - ++# Core 2 2.41/+90% - ++# Westmere 1.88/+120% - ++# Sandy Bridge 1.39/+140% 1.10 ++# Haswell 1.14/+175% 1.11 0.65 ++# Skylake[-X] 1.13/+120% 0.96 0.51 [0.35] ++# Silvermont 2.83/+95% - ++# Knights L 3.60/? 1.65 1.10 0.41(***) ++# Goldmont 1.70/+180% - ++# VIA Nano 1.82/+150% - ++# Sledgehammer 1.38/+160% - ++# Bulldozer 2.30/+130% 0.97 ++# Ryzen 1.15/+200% 1.08 1.18 ++# ++# (*) improvement coefficients relative to clang are more modest and ++# are ~50% on most processors, in both cases we are comparing to ++# __int128 code; ++# (**) SSE2 implementation was attempted, but among non-AVX processors ++# it was faster than integer-only code only on older Intel P4 and ++# Core processors, 50-30%, less newer processor is, but slower on ++# contemporary ones, for example almost 2x slower on Atom, and as ++# former are naturally disappearing, SSE2 is deemed unnecessary; ++# (***) strangely enough performance seems to vary from core to core, ++# listed result is best case; ++ ++$flavour = shift; ++$output = shift; ++if ($flavour =~ /\./) { $output = $flavour; undef $flavour; } ++ ++$win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/); ++ ++$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; ++( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or ++( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or ++die "can't locate x86_64-xlate.pl"; ++ ++if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1` ++ =~ /GNU assembler version ([2-9]\.[0-9]+)/) { ++ $avx = ($1>=2.19) + ($1>=2.22) + ($1>=2.25) + ($1>=2.26); ++} ++ ++if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) && ++ `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)(?:\.([0-9]+))?/) { ++ $avx = ($1>=2.09) + ($1>=2.10) + 2 * ($1>=2.12); ++ $avx += 2 if ($1==2.11 && $2>=8); ++} ++ ++if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) && ++ `ml64 2>&1` =~ /Version ([0-9]+)\./) { ++ $avx = ($1>=10) + ($1>=12); ++} ++ ++if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) { ++ $avx = ($2>=3.0) + ($2>3.0); ++} ++ ++open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\""; ++*STDOUT=*OUT; ++ ++my ($ctx,$inp,$len,$padbit)=("%rdi","%rsi","%rdx","%rcx"); ++my ($mac,$nonce)=($inp,$len); # *_emit arguments ++my ($d1,$d2,$d3, $r0,$r1,$s1)=map("%r$_",(8..13)); ++my ($h0,$h1,$h2)=("%r14","%rbx","%rbp"); ++ ++sub poly1305_iteration { ++# input: copy of $r1 in %rax, $h0-$h2, $r0-$r1 ++# output: $h0-$h2 *= $r0-$r1 ++$code.=<<___; ++ mulq $h0 # h0*r1 ++ mov %rax,$d2 ++ mov $r0,%rax ++ mov %rdx,$d3 ++ ++ mulq $h0 # h0*r0 ++ mov %rax,$h0 # future $h0 ++ mov $r0,%rax ++ mov %rdx,$d1 ++ ++ mulq $h1 # h1*r0 ++ add %rax,$d2 ++ mov $s1,%rax ++ adc %rdx,$d3 ++ ++ mulq $h1 # h1*s1 ++ mov $h2,$h1 # borrow $h1 ++ add %rax,$h0 ++ adc %rdx,$d1 ++ ++ imulq $s1,$h1 # h2*s1 ++ add $h1,$d2 ++ mov $d1,$h1 ++ adc \$0,$d3 ++ ++ imulq $r0,$h2 # h2*r0 ++ add $d2,$h1 ++ mov \$-4,%rax # mask value ++ adc $h2,$d3 ++ ++ and $d3,%rax # last reduction step ++ mov $d3,$h2 ++ shr \$2,$d3 ++ and \$3,$h2 ++ add $d3,%rax ++ add %rax,$h0 ++ adc \$0,$h1 ++ adc \$0,$h2 ++___ ++} ++ ++######################################################################## ++# Layout of opaque area is following. ++# ++# unsigned __int64 h[3]; # current hash value base 2^64 ++# unsigned __int64 r[2]; # key value base 2^64 ++ ++$code.=<<___; ++.text ++ ++.extern OPENSSL_ia32cap_P ++ ++.globl poly1305_init ++.hidden poly1305_init ++.globl poly1305_blocks ++.hidden poly1305_blocks ++.globl poly1305_emit ++.hidden poly1305_emit ++ ++.type poly1305_init,\@function,3 ++.align 32 ++poly1305_init: ++ xor %rax,%rax ++ mov %rax,0($ctx) # initialize hash value ++ mov %rax,8($ctx) ++ mov %rax,16($ctx) ++ ++ cmp \$0,$inp ++ je .Lno_key ++ ++ lea poly1305_blocks(%rip),%r10 ++ lea poly1305_emit(%rip),%r11 ++___ ++$code.=<<___ if ($avx); ++ mov OPENSSL_ia32cap_P+4(%rip),%r9 ++ lea poly1305_blocks_avx(%rip),%rax ++ lea poly1305_emit_avx(%rip),%rcx ++ bt \$`60-32`,%r9 # AVX? ++ cmovc %rax,%r10 ++ cmovc %rcx,%r11 ++___ ++$code.=<<___ if ($avx>1); ++ lea poly1305_blocks_avx2(%rip),%rax ++ bt \$`5+32`,%r9 # AVX2? ++ cmovc %rax,%r10 ++___ ++$code.=<<___ if ($avx>3); ++ mov \$`(1<<31|1<<21|1<<16)`,%rax ++ shr \$32,%r9 ++ and %rax,%r9 ++ cmp %rax,%r9 ++ je .Linit_base2_44 ++___ ++$code.=<<___; ++ mov \$0x0ffffffc0fffffff,%rax ++ mov \$0x0ffffffc0ffffffc,%rcx ++ and 0($inp),%rax ++ and 8($inp),%rcx ++ mov %rax,24($ctx) ++ mov %rcx,32($ctx) ++___ ++$code.=<<___ if ($flavour !~ /elf32/); ++ mov %r10,0(%rdx) ++ mov %r11,8(%rdx) ++___ ++$code.=<<___ if ($flavour =~ /elf32/); ++ mov %r10d,0(%rdx) ++ mov %r11d,4(%rdx) ++___ ++$code.=<<___; ++ mov \$1,%eax ++.Lno_key: ++ ret ++.size poly1305_init,.-poly1305_init ++ ++.type poly1305_blocks,\@function,4 ++.align 32 ++poly1305_blocks: ++.cfi_startproc ++.Lblocks: ++ shr \$4,$len ++ jz .Lno_data # too short ++ ++ push %rbx ++.cfi_push %rbx ++ push %rbp ++.cfi_push %rbp ++ push %r12 ++.cfi_push %r12 ++ push %r13 ++.cfi_push %r13 ++ push %r14 ++.cfi_push %r14 ++ push %r15 ++.cfi_push %r15 ++.Lblocks_body: ++ ++ mov $len,%r15 # reassign $len ++ ++ mov 24($ctx),$r0 # load r ++ mov 32($ctx),$s1 ++ ++ mov 0($ctx),$h0 # load hash value ++ mov 8($ctx),$h1 ++ mov 16($ctx),$h2 ++ ++ mov $s1,$r1 ++ shr \$2,$s1 ++ mov $r1,%rax ++ add $r1,$s1 # s1 = r1 + (r1 >> 2) ++ jmp .Loop ++ ++.align 32 ++.Loop: ++ add 0($inp),$h0 # accumulate input ++ adc 8($inp),$h1 ++ lea 16($inp),$inp ++ adc $padbit,$h2 ++___ ++ &poly1305_iteration(); ++$code.=<<___; ++ mov $r1,%rax ++ dec %r15 # len-=16 ++ jnz .Loop ++ ++ mov $h0,0($ctx) # store hash value ++ mov $h1,8($ctx) ++ mov $h2,16($ctx) ++ ++ mov 0(%rsp),%r15 ++.cfi_restore %r15 ++ mov 8(%rsp),%r14 ++.cfi_restore %r14 ++ mov 16(%rsp),%r13 ++.cfi_restore %r13 ++ mov 24(%rsp),%r12 ++.cfi_restore %r12 ++ mov 32(%rsp),%rbp ++.cfi_restore %rbp ++ mov 40(%rsp),%rbx ++.cfi_restore %rbx ++ lea 48(%rsp),%rsp ++.cfi_adjust_cfa_offset -48 ++.Lno_data: ++.Lblocks_epilogue: ++ ret ++.cfi_endproc ++.size poly1305_blocks,.-poly1305_blocks ++ ++.type poly1305_emit,\@function,3 ++.align 32 ++poly1305_emit: ++.Lemit: ++ mov 0($ctx),%r8 # load hash value ++ mov 8($ctx),%r9 ++ mov 16($ctx),%r10 ++ ++ mov %r8,%rax ++ add \$5,%r8 # compare to modulus ++ mov %r9,%rcx ++ adc \$0,%r9 ++ adc \$0,%r10 ++ shr \$2,%r10 # did 130-bit value overflow? ++ cmovnz %r8,%rax ++ cmovnz %r9,%rcx ++ ++ add 0($nonce),%rax # accumulate nonce ++ adc 8($nonce),%rcx ++ mov %rax,0($mac) # write result ++ mov %rcx,8($mac) ++ ++ ret ++.size poly1305_emit,.-poly1305_emit ++___ ++if ($avx) { ++ ++######################################################################## ++# Layout of opaque area is following. ++# ++# unsigned __int32 h[5]; # current hash value base 2^26 ++# unsigned __int32 is_base2_26; ++# unsigned __int64 r[2]; # key value base 2^64 ++# unsigned __int64 pad; ++# struct { unsigned __int32 r^2, r^1, r^4, r^3; } r[9]; ++# ++# where r^n are base 2^26 digits of degrees of multiplier key. There are ++# 5 digits, but last four are interleaved with multiples of 5, totalling ++# in 9 elements: r0, r1, 5*r1, r2, 5*r2, r3, 5*r3, r4, 5*r4. ++ ++my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) = ++ map("%xmm$_",(0..15)); ++ ++$code.=<<___; ++.type __poly1305_block,\@abi-omnipotent ++.align 32 ++__poly1305_block: ++___ ++ &poly1305_iteration(); ++$code.=<<___; ++ ret ++.size __poly1305_block,.-__poly1305_block ++ ++.type __poly1305_init_avx,\@abi-omnipotent ++.align 32 ++__poly1305_init_avx: ++ mov $r0,$h0 ++ mov $r1,$h1 ++ xor $h2,$h2 ++ ++ lea 48+64($ctx),$ctx # size optimization ++ ++ mov $r1,%rax ++ call __poly1305_block # r^2 ++ ++ mov \$0x3ffffff,%eax # save interleaved r^2 and r base 2^26 ++ mov \$0x3ffffff,%edx ++ mov $h0,$d1 ++ and $h0#d,%eax ++ mov $r0,$d2 ++ and $r0#d,%edx ++ mov %eax,`16*0+0-64`($ctx) ++ shr \$26,$d1 ++ mov %edx,`16*0+4-64`($ctx) ++ shr \$26,$d2 ++ ++ mov \$0x3ffffff,%eax ++ mov \$0x3ffffff,%edx ++ and $d1#d,%eax ++ and $d2#d,%edx ++ mov %eax,`16*1+0-64`($ctx) ++ lea (%rax,%rax,4),%eax # *5 ++ mov %edx,`16*1+4-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ mov %eax,`16*2+0-64`($ctx) ++ shr \$26,$d1 ++ mov %edx,`16*2+4-64`($ctx) ++ shr \$26,$d2 ++ ++ mov $h1,%rax ++ mov $r1,%rdx ++ shl \$12,%rax ++ shl \$12,%rdx ++ or $d1,%rax ++ or $d2,%rdx ++ and \$0x3ffffff,%eax ++ and \$0x3ffffff,%edx ++ mov %eax,`16*3+0-64`($ctx) ++ lea (%rax,%rax,4),%eax # *5 ++ mov %edx,`16*3+4-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ mov %eax,`16*4+0-64`($ctx) ++ mov $h1,$d1 ++ mov %edx,`16*4+4-64`($ctx) ++ mov $r1,$d2 ++ ++ mov \$0x3ffffff,%eax ++ mov \$0x3ffffff,%edx ++ shr \$14,$d1 ++ shr \$14,$d2 ++ and $d1#d,%eax ++ and $d2#d,%edx ++ mov %eax,`16*5+0-64`($ctx) ++ lea (%rax,%rax,4),%eax # *5 ++ mov %edx,`16*5+4-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ mov %eax,`16*6+0-64`($ctx) ++ shr \$26,$d1 ++ mov %edx,`16*6+4-64`($ctx) ++ shr \$26,$d2 ++ ++ mov $h2,%rax ++ shl \$24,%rax ++ or %rax,$d1 ++ mov $d1#d,`16*7+0-64`($ctx) ++ lea ($d1,$d1,4),$d1 # *5 ++ mov $d2#d,`16*7+4-64`($ctx) ++ lea ($d2,$d2,4),$d2 # *5 ++ mov $d1#d,`16*8+0-64`($ctx) ++ mov $d2#d,`16*8+4-64`($ctx) ++ ++ mov $r1,%rax ++ call __poly1305_block # r^3 ++ ++ mov \$0x3ffffff,%eax # save r^3 base 2^26 ++ mov $h0,$d1 ++ and $h0#d,%eax ++ shr \$26,$d1 ++ mov %eax,`16*0+12-64`($ctx) ++ ++ mov \$0x3ffffff,%edx ++ and $d1#d,%edx ++ mov %edx,`16*1+12-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ shr \$26,$d1 ++ mov %edx,`16*2+12-64`($ctx) ++ ++ mov $h1,%rax ++ shl \$12,%rax ++ or $d1,%rax ++ and \$0x3ffffff,%eax ++ mov %eax,`16*3+12-64`($ctx) ++ lea (%rax,%rax,4),%eax # *5 ++ mov $h1,$d1 ++ mov %eax,`16*4+12-64`($ctx) ++ ++ mov \$0x3ffffff,%edx ++ shr \$14,$d1 ++ and $d1#d,%edx ++ mov %edx,`16*5+12-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ shr \$26,$d1 ++ mov %edx,`16*6+12-64`($ctx) ++ ++ mov $h2,%rax ++ shl \$24,%rax ++ or %rax,$d1 ++ mov $d1#d,`16*7+12-64`($ctx) ++ lea ($d1,$d1,4),$d1 # *5 ++ mov $d1#d,`16*8+12-64`($ctx) ++ ++ mov $r1,%rax ++ call __poly1305_block # r^4 ++ ++ mov \$0x3ffffff,%eax # save r^4 base 2^26 ++ mov $h0,$d1 ++ and $h0#d,%eax ++ shr \$26,$d1 ++ mov %eax,`16*0+8-64`($ctx) ++ ++ mov \$0x3ffffff,%edx ++ and $d1#d,%edx ++ mov %edx,`16*1+8-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ shr \$26,$d1 ++ mov %edx,`16*2+8-64`($ctx) ++ ++ mov $h1,%rax ++ shl \$12,%rax ++ or $d1,%rax ++ and \$0x3ffffff,%eax ++ mov %eax,`16*3+8-64`($ctx) ++ lea (%rax,%rax,4),%eax # *5 ++ mov $h1,$d1 ++ mov %eax,`16*4+8-64`($ctx) ++ ++ mov \$0x3ffffff,%edx ++ shr \$14,$d1 ++ and $d1#d,%edx ++ mov %edx,`16*5+8-64`($ctx) ++ lea (%rdx,%rdx,4),%edx # *5 ++ shr \$26,$d1 ++ mov %edx,`16*6+8-64`($ctx) ++ ++ mov $h2,%rax ++ shl \$24,%rax ++ or %rax,$d1 ++ mov $d1#d,`16*7+8-64`($ctx) ++ lea ($d1,$d1,4),$d1 # *5 ++ mov $d1#d,`16*8+8-64`($ctx) ++ ++ lea -48-64($ctx),$ctx # size [de-]optimization ++ ret ++.size __poly1305_init_avx,.-__poly1305_init_avx ++ ++.type poly1305_blocks_avx,\@function,4 ++.align 32 ++poly1305_blocks_avx: ++.cfi_startproc ++ mov 20($ctx),%r8d # is_base2_26 ++ cmp \$128,$len ++ jae .Lblocks_avx ++ test %r8d,%r8d ++ jz .Lblocks ++ ++.Lblocks_avx: ++ and \$-16,$len ++ jz .Lno_data_avx ++ ++ vzeroupper ++ ++ test %r8d,%r8d ++ jz .Lbase2_64_avx ++ ++ test \$31,$len ++ jz .Leven_avx ++ ++ push %rbx ++.cfi_push %rbx ++ push %rbp ++.cfi_push %rbp ++ push %r12 ++.cfi_push %r12 ++ push %r13 ++.cfi_push %r13 ++ push %r14 ++.cfi_push %r14 ++ push %r15 ++.cfi_push %r15 ++.Lblocks_avx_body: ++ ++ mov $len,%r15 # reassign $len ++ ++ mov 0($ctx),$d1 # load hash value ++ mov 8($ctx),$d2 ++ mov 16($ctx),$h2#d ++ ++ mov 24($ctx),$r0 # load r ++ mov 32($ctx),$s1 ++ ++ ################################# base 2^26 -> base 2^64 ++ mov $d1#d,$h0#d ++ and \$`-1*(1<<31)`,$d1 ++ mov $d2,$r1 # borrow $r1 ++ mov $d2#d,$h1#d ++ and \$`-1*(1<<31)`,$d2 ++ ++ shr \$6,$d1 ++ shl \$52,$r1 ++ add $d1,$h0 ++ shr \$12,$h1 ++ shr \$18,$d2 ++ add $r1,$h0 ++ adc $d2,$h1 ++ ++ mov $h2,$d1 ++ shl \$40,$d1 ++ shr \$24,$h2 ++ add $d1,$h1 ++ adc \$0,$h2 # can be partially reduced... ++ ++ mov \$-4,$d2 # ... so reduce ++ mov $h2,$d1 ++ and $h2,$d2 ++ shr \$2,$d1 ++ and \$3,$h2 ++ add $d2,$d1 # =*5 ++ add $d1,$h0 ++ adc \$0,$h1 ++ adc \$0,$h2 ++ ++ mov $s1,$r1 ++ mov $s1,%rax ++ shr \$2,$s1 ++ add $r1,$s1 # s1 = r1 + (r1 >> 2) ++ ++ add 0($inp),$h0 # accumulate input ++ adc 8($inp),$h1 ++ lea 16($inp),$inp ++ adc $padbit,$h2 ++ ++ call __poly1305_block ++ ++ test $padbit,$padbit # if $padbit is zero, ++ jz .Lstore_base2_64_avx # store hash in base 2^64 format ++ ++ ################################# base 2^64 -> base 2^26 ++ mov $h0,%rax ++ mov $h0,%rdx ++ shr \$52,$h0 ++ mov $h1,$r0 ++ mov $h1,$r1 ++ shr \$26,%rdx ++ and \$0x3ffffff,%rax # h[0] ++ shl \$12,$r0 ++ and \$0x3ffffff,%rdx # h[1] ++ shr \$14,$h1 ++ or $r0,$h0 ++ shl \$24,$h2 ++ and \$0x3ffffff,$h0 # h[2] ++ shr \$40,$r1 ++ and \$0x3ffffff,$h1 # h[3] ++ or $r1,$h2 # h[4] ++ ++ sub \$16,%r15 ++ jz .Lstore_base2_26_avx ++ ++ vmovd %rax#d,$H0 ++ vmovd %rdx#d,$H1 ++ vmovd $h0#d,$H2 ++ vmovd $h1#d,$H3 ++ vmovd $h2#d,$H4 ++ jmp .Lproceed_avx ++ ++.align 32 ++.Lstore_base2_64_avx: ++ mov $h0,0($ctx) ++ mov $h1,8($ctx) ++ mov $h2,16($ctx) # note that is_base2_26 is zeroed ++ jmp .Ldone_avx ++ ++.align 16 ++.Lstore_base2_26_avx: ++ mov %rax#d,0($ctx) # store hash value base 2^26 ++ mov %rdx#d,4($ctx) ++ mov $h0#d,8($ctx) ++ mov $h1#d,12($ctx) ++ mov $h2#d,16($ctx) ++.align 16 ++.Ldone_avx: ++ mov 0(%rsp),%r15 ++.cfi_restore %r15 ++ mov 8(%rsp),%r14 ++.cfi_restore %r14 ++ mov 16(%rsp),%r13 ++.cfi_restore %r13 ++ mov 24(%rsp),%r12 ++.cfi_restore %r12 ++ mov 32(%rsp),%rbp ++.cfi_restore %rbp ++ mov 40(%rsp),%rbx ++.cfi_restore %rbx ++ lea 48(%rsp),%rsp ++.cfi_adjust_cfa_offset -48 ++.Lno_data_avx: ++.Lblocks_avx_epilogue: ++ ret ++.cfi_endproc ++ ++.align 32 ++.Lbase2_64_avx: ++.cfi_startproc ++ push %rbx ++.cfi_push %rbx ++ push %rbp ++.cfi_push %rbp ++ push %r12 ++.cfi_push %r12 ++ push %r13 ++.cfi_push %r13 ++ push %r14 ++.cfi_push %r14 ++ push %r15 ++.cfi_push %r15 ++.Lbase2_64_avx_body: ++ ++ mov $len,%r15 # reassign $len ++ ++ mov 24($ctx),$r0 # load r ++ mov 32($ctx),$s1 ++ ++ mov 0($ctx),$h0 # load hash value ++ mov 8($ctx),$h1 ++ mov 16($ctx),$h2#d ++ ++ mov $s1,$r1 ++ mov $s1,%rax ++ shr \$2,$s1 ++ add $r1,$s1 # s1 = r1 + (r1 >> 2) ++ ++ test \$31,$len ++ jz .Linit_avx ++ ++ add 0($inp),$h0 # accumulate input ++ adc 8($inp),$h1 ++ lea 16($inp),$inp ++ adc $padbit,$h2 ++ sub \$16,%r15 ++ ++ call __poly1305_block ++ ++.Linit_avx: ++ ################################# base 2^64 -> base 2^26 ++ mov $h0,%rax ++ mov $h0,%rdx ++ shr \$52,$h0 ++ mov $h1,$d1 ++ mov $h1,$d2 ++ shr \$26,%rdx ++ and \$0x3ffffff,%rax # h[0] ++ shl \$12,$d1 ++ and \$0x3ffffff,%rdx # h[1] ++ shr \$14,$h1 ++ or $d1,$h0 ++ shl \$24,$h2 ++ and \$0x3ffffff,$h0 # h[2] ++ shr \$40,$d2 ++ and \$0x3ffffff,$h1 # h[3] ++ or $d2,$h2 # h[4] ++ ++ vmovd %rax#d,$H0 ++ vmovd %rdx#d,$H1 ++ vmovd $h0#d,$H2 ++ vmovd $h1#d,$H3 ++ vmovd $h2#d,$H4 ++ movl \$1,20($ctx) # set is_base2_26 ++ ++ call __poly1305_init_avx ++ ++.Lproceed_avx: ++ mov %r15,$len ++ ++ mov 0(%rsp),%r15 ++.cfi_restore %r15 ++ mov 8(%rsp),%r14 ++.cfi_restore %r14 ++ mov 16(%rsp),%r13 ++.cfi_restore %r13 ++ mov 24(%rsp),%r12 ++.cfi_restore %r12 ++ mov 32(%rsp),%rbp ++.cfi_restore %rbp ++ mov 40(%rsp),%rbx ++.cfi_restore %rbx ++ lea 48(%rsp),%rax ++ lea 48(%rsp),%rsp ++.cfi_adjust_cfa_offset -48 ++.Lbase2_64_avx_epilogue: ++ jmp .Ldo_avx ++.cfi_endproc ++ ++.align 32 ++.Leven_avx: ++.cfi_startproc ++ vmovd 4*0($ctx),$H0 # load hash value ++ vmovd 4*1($ctx),$H1 ++ vmovd 4*2($ctx),$H2 ++ vmovd 4*3($ctx),$H3 ++ vmovd 4*4($ctx),$H4 ++ ++.Ldo_avx: ++___ ++$code.=<<___ if (!$win64); ++ lea -0x58(%rsp),%r11 ++.cfi_def_cfa %r11,0x60 ++ sub \$0x178,%rsp ++___ ++$code.=<<___ if ($win64); ++ lea -0xf8(%rsp),%r11 ++ sub \$0x218,%rsp ++ vmovdqa %xmm6,0x50(%r11) ++ vmovdqa %xmm7,0x60(%r11) ++ vmovdqa %xmm8,0x70(%r11) ++ vmovdqa %xmm9,0x80(%r11) ++ vmovdqa %xmm10,0x90(%r11) ++ vmovdqa %xmm11,0xa0(%r11) ++ vmovdqa %xmm12,0xb0(%r11) ++ vmovdqa %xmm13,0xc0(%r11) ++ vmovdqa %xmm14,0xd0(%r11) ++ vmovdqa %xmm15,0xe0(%r11) ++.Ldo_avx_body: ++___ ++$code.=<<___; ++ sub \$64,$len ++ lea -32($inp),%rax ++ cmovc %rax,$inp ++ ++ vmovdqu `16*3`($ctx),$D4 # preload r0^2 ++ lea `16*3+64`($ctx),$ctx # size optimization ++ lea .Lconst(%rip),%rcx ++ ++ ################################################################ ++ # load input ++ vmovdqu 16*2($inp),$T0 ++ vmovdqu 16*3($inp),$T1 ++ vmovdqa 64(%rcx),$MASK # .Lmask26 ++ ++ vpsrldq \$6,$T0,$T2 # splat input ++ vpsrldq \$6,$T1,$T3 ++ vpunpckhqdq $T1,$T0,$T4 # 4 ++ vpunpcklqdq $T1,$T0,$T0 # 0:1 ++ vpunpcklqdq $T3,$T2,$T3 # 2:3 ++ ++ vpsrlq \$40,$T4,$T4 # 4 ++ vpsrlq \$26,$T0,$T1 ++ vpand $MASK,$T0,$T0 # 0 ++ vpsrlq \$4,$T3,$T2 ++ vpand $MASK,$T1,$T1 # 1 ++ vpsrlq \$30,$T3,$T3 ++ vpand $MASK,$T2,$T2 # 2 ++ vpand $MASK,$T3,$T3 # 3 ++ vpor 32(%rcx),$T4,$T4 # padbit, yes, always ++ ++ jbe .Lskip_loop_avx ++ ++ # expand and copy pre-calculated table to stack ++ vmovdqu `16*1-64`($ctx),$D1 ++ vmovdqu `16*2-64`($ctx),$D2 ++ vpshufd \$0xEE,$D4,$D3 # 34xx -> 3434 ++ vpshufd \$0x44,$D4,$D0 # xx12 -> 1212 ++ vmovdqa $D3,-0x90(%r11) ++ vmovdqa $D0,0x00(%rsp) ++ vpshufd \$0xEE,$D1,$D4 ++ vmovdqu `16*3-64`($ctx),$D0 ++ vpshufd \$0x44,$D1,$D1 ++ vmovdqa $D4,-0x80(%r11) ++ vmovdqa $D1,0x10(%rsp) ++ vpshufd \$0xEE,$D2,$D3 ++ vmovdqu `16*4-64`($ctx),$D1 ++ vpshufd \$0x44,$D2,$D2 ++ vmovdqa $D3,-0x70(%r11) ++ vmovdqa $D2,0x20(%rsp) ++ vpshufd \$0xEE,$D0,$D4 ++ vmovdqu `16*5-64`($ctx),$D2 ++ vpshufd \$0x44,$D0,$D0 ++ vmovdqa $D4,-0x60(%r11) ++ vmovdqa $D0,0x30(%rsp) ++ vpshufd \$0xEE,$D1,$D3 ++ vmovdqu `16*6-64`($ctx),$D0 ++ vpshufd \$0x44,$D1,$D1 ++ vmovdqa $D3,-0x50(%r11) ++ vmovdqa $D1,0x40(%rsp) ++ vpshufd \$0xEE,$D2,$D4 ++ vmovdqu `16*7-64`($ctx),$D1 ++ vpshufd \$0x44,$D2,$D2 ++ vmovdqa $D4,-0x40(%r11) ++ vmovdqa $D2,0x50(%rsp) ++ vpshufd \$0xEE,$D0,$D3 ++ vmovdqu `16*8-64`($ctx),$D2 ++ vpshufd \$0x44,$D0,$D0 ++ vmovdqa $D3,-0x30(%r11) ++ vmovdqa $D0,0x60(%rsp) ++ vpshufd \$0xEE,$D1,$D4 ++ vpshufd \$0x44,$D1,$D1 ++ vmovdqa $D4,-0x20(%r11) ++ vmovdqa $D1,0x70(%rsp) ++ vpshufd \$0xEE,$D2,$D3 ++ vmovdqa 0x00(%rsp),$D4 # preload r0^2 ++ vpshufd \$0x44,$D2,$D2 ++ vmovdqa $D3,-0x10(%r11) ++ vmovdqa $D2,0x80(%rsp) ++ ++ jmp .Loop_avx ++ ++.align 32 ++.Loop_avx: ++ ################################################################ ++ # ((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 ++ # ++ # though note that $Tx and $Hx are "reversed" in this section, ++ # and $D4 is preloaded with r0^2... ++ ++ vpmuludq $T0,$D4,$D0 # d0 = h0*r0 ++ vpmuludq $T1,$D4,$D1 # d1 = h1*r0 ++ vmovdqa $H2,0x20(%r11) # offload hash ++ vpmuludq $T2,$D4,$D2 # d3 = h2*r0 ++ vmovdqa 0x10(%rsp),$H2 # r1^2 ++ vpmuludq $T3,$D4,$D3 # d3 = h3*r0 ++ vpmuludq $T4,$D4,$D4 # d4 = h4*r0 ++ ++ vmovdqa $H0,0x00(%r11) # ++ vpmuludq 0x20(%rsp),$T4,$H0 # h4*s1 ++ vmovdqa $H1,0x10(%r11) # ++ vpmuludq $T3,$H2,$H1 # h3*r1 ++ vpaddq $H0,$D0,$D0 # d0 += h4*s1 ++ vpaddq $H1,$D4,$D4 # d4 += h3*r1 ++ vmovdqa $H3,0x30(%r11) # ++ vpmuludq $T2,$H2,$H0 # h2*r1 ++ vpmuludq $T1,$H2,$H1 # h1*r1 ++ vpaddq $H0,$D3,$D3 # d3 += h2*r1 ++ vmovdqa 0x30(%rsp),$H3 # r2^2 ++ vpaddq $H1,$D2,$D2 # d2 += h1*r1 ++ vmovdqa $H4,0x40(%r11) # ++ vpmuludq $T0,$H2,$H2 # h0*r1 ++ vpmuludq $T2,$H3,$H0 # h2*r2 ++ vpaddq $H2,$D1,$D1 # d1 += h0*r1 ++ ++ vmovdqa 0x40(%rsp),$H4 # s2^2 ++ vpaddq $H0,$D4,$D4 # d4 += h2*r2 ++ vpmuludq $T1,$H3,$H1 # h1*r2 ++ vpmuludq $T0,$H3,$H3 # h0*r2 ++ vpaddq $H1,$D3,$D3 # d3 += h1*r2 ++ vmovdqa 0x50(%rsp),$H2 # r3^2 ++ vpaddq $H3,$D2,$D2 # d2 += h0*r2 ++ vpmuludq $T4,$H4,$H0 # h4*s2 ++ vpmuludq $T3,$H4,$H4 # h3*s2 ++ vpaddq $H0,$D1,$D1 # d1 += h4*s2 ++ vmovdqa 0x60(%rsp),$H3 # s3^2 ++ vpaddq $H4,$D0,$D0 # d0 += h3*s2 ++ ++ vmovdqa 0x80(%rsp),$H4 # s4^2 ++ vpmuludq $T1,$H2,$H1 # h1*r3 ++ vpmuludq $T0,$H2,$H2 # h0*r3 ++ vpaddq $H1,$D4,$D4 # d4 += h1*r3 ++ vpaddq $H2,$D3,$D3 # d3 += h0*r3 ++ vpmuludq $T4,$H3,$H0 # h4*s3 ++ vpmuludq $T3,$H3,$H1 # h3*s3 ++ vpaddq $H0,$D2,$D2 # d2 += h4*s3 ++ vmovdqu 16*0($inp),$H0 # load input ++ vpaddq $H1,$D1,$D1 # d1 += h3*s3 ++ vpmuludq $T2,$H3,$H3 # h2*s3 ++ vpmuludq $T2,$H4,$T2 # h2*s4 ++ vpaddq $H3,$D0,$D0 # d0 += h2*s3 ++ ++ vmovdqu 16*1($inp),$H1 # ++ vpaddq $T2,$D1,$D1 # d1 += h2*s4 ++ vpmuludq $T3,$H4,$T3 # h3*s4 ++ vpmuludq $T4,$H4,$T4 # h4*s4 ++ vpsrldq \$6,$H0,$H2 # splat input ++ vpaddq $T3,$D2,$D2 # d2 += h3*s4 ++ vpaddq $T4,$D3,$D3 # d3 += h4*s4 ++ vpsrldq \$6,$H1,$H3 # ++ vpmuludq 0x70(%rsp),$T0,$T4 # h0*r4 ++ vpmuludq $T1,$H4,$T0 # h1*s4 ++ vpunpckhqdq $H1,$H0,$H4 # 4 ++ vpaddq $T4,$D4,$D4 # d4 += h0*r4 ++ vmovdqa -0x90(%r11),$T4 # r0^4 ++ vpaddq $T0,$D0,$D0 # d0 += h1*s4 ++ ++ vpunpcklqdq $H1,$H0,$H0 # 0:1 ++ vpunpcklqdq $H3,$H2,$H3 # 2:3 ++ ++ #vpsrlq \$40,$H4,$H4 # 4 ++ vpsrldq \$`40/8`,$H4,$H4 # 4 ++ vpsrlq \$26,$H0,$H1 ++ vpand $MASK,$H0,$H0 # 0 ++ vpsrlq \$4,$H3,$H2 ++ vpand $MASK,$H1,$H1 # 1 ++ vpand 0(%rcx),$H4,$H4 # .Lmask24 ++ vpsrlq \$30,$H3,$H3 ++ vpand $MASK,$H2,$H2 # 2 ++ vpand $MASK,$H3,$H3 # 3 ++ vpor 32(%rcx),$H4,$H4 # padbit, yes, always ++ ++ vpaddq 0x00(%r11),$H0,$H0 # add hash value ++ vpaddq 0x10(%r11),$H1,$H1 ++ vpaddq 0x20(%r11),$H2,$H2 ++ vpaddq 0x30(%r11),$H3,$H3 ++ vpaddq 0x40(%r11),$H4,$H4 ++ ++ lea 16*2($inp),%rax ++ lea 16*4($inp),$inp ++ sub \$64,$len ++ cmovc %rax,$inp ++ ++ ################################################################ ++ # Now we accumulate (inp[0:1]+hash)*r^4 ++ ################################################################ ++ # 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 ++ ++ vpmuludq $H0,$T4,$T0 # h0*r0 ++ vpmuludq $H1,$T4,$T1 # h1*r0 ++ vpaddq $T0,$D0,$D0 ++ vpaddq $T1,$D1,$D1 ++ vmovdqa -0x80(%r11),$T2 # r1^4 ++ vpmuludq $H2,$T4,$T0 # h2*r0 ++ vpmuludq $H3,$T4,$T1 # h3*r0 ++ vpaddq $T0,$D2,$D2 ++ vpaddq $T1,$D3,$D3 ++ vpmuludq $H4,$T4,$T4 # h4*r0 ++ vpmuludq -0x70(%r11),$H4,$T0 # h4*s1 ++ vpaddq $T4,$D4,$D4 ++ ++ vpaddq $T0,$D0,$D0 # d0 += h4*s1 ++ vpmuludq $H2,$T2,$T1 # h2*r1 ++ vpmuludq $H3,$T2,$T0 # h3*r1 ++ vpaddq $T1,$D3,$D3 # d3 += h2*r1 ++ vmovdqa -0x60(%r11),$T3 # r2^4 ++ vpaddq $T0,$D4,$D4 # d4 += h3*r1 ++ vpmuludq $H1,$T2,$T1 # h1*r1 ++ vpmuludq $H0,$T2,$T2 # h0*r1 ++ vpaddq $T1,$D2,$D2 # d2 += h1*r1 ++ vpaddq $T2,$D1,$D1 # d1 += h0*r1 ++ ++ vmovdqa -0x50(%r11),$T4 # s2^4 ++ vpmuludq $H2,$T3,$T0 # h2*r2 ++ vpmuludq $H1,$T3,$T1 # h1*r2 ++ vpaddq $T0,$D4,$D4 # d4 += h2*r2 ++ vpaddq $T1,$D3,$D3 # d3 += h1*r2 ++ vmovdqa -0x40(%r11),$T2 # r3^4 ++ vpmuludq $H0,$T3,$T3 # h0*r2 ++ vpmuludq $H4,$T4,$T0 # h4*s2 ++ vpaddq $T3,$D2,$D2 # d2 += h0*r2 ++ vpaddq $T0,$D1,$D1 # d1 += h4*s2 ++ vmovdqa -0x30(%r11),$T3 # s3^4 ++ vpmuludq $H3,$T4,$T4 # h3*s2 ++ vpmuludq $H1,$T2,$T1 # h1*r3 ++ vpaddq $T4,$D0,$D0 # d0 += h3*s2 ++ ++ vmovdqa -0x10(%r11),$T4 # s4^4 ++ vpaddq $T1,$D4,$D4 # d4 += h1*r3 ++ vpmuludq $H0,$T2,$T2 # h0*r3 ++ vpmuludq $H4,$T3,$T0 # h4*s3 ++ vpaddq $T2,$D3,$D3 # d3 += h0*r3 ++ vpaddq $T0,$D2,$D2 # d2 += h4*s3 ++ vmovdqu 16*2($inp),$T0 # load input ++ vpmuludq $H3,$T3,$T2 # h3*s3 ++ vpmuludq $H2,$T3,$T3 # h2*s3 ++ vpaddq $T2,$D1,$D1 # d1 += h3*s3 ++ vmovdqu 16*3($inp),$T1 # ++ vpaddq $T3,$D0,$D0 # d0 += h2*s3 ++ ++ vpmuludq $H2,$T4,$H2 # h2*s4 ++ vpmuludq $H3,$T4,$H3 # h3*s4 ++ vpsrldq \$6,$T0,$T2 # splat input ++ vpaddq $H2,$D1,$D1 # d1 += h2*s4 ++ vpmuludq $H4,$T4,$H4 # h4*s4 ++ vpsrldq \$6,$T1,$T3 # ++ vpaddq $H3,$D2,$H2 # h2 = d2 + h3*s4 ++ vpaddq $H4,$D3,$H3 # h3 = d3 + h4*s4 ++ vpmuludq -0x20(%r11),$H0,$H4 # h0*r4 ++ vpmuludq $H1,$T4,$H0 ++ vpunpckhqdq $T1,$T0,$T4 # 4 ++ vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4 ++ vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4 ++ ++ vpunpcklqdq $T1,$T0,$T0 # 0:1 ++ vpunpcklqdq $T3,$T2,$T3 # 2:3 ++ ++ #vpsrlq \$40,$T4,$T4 # 4 ++ vpsrldq \$`40/8`,$T4,$T4 # 4 ++ vpsrlq \$26,$T0,$T1 ++ vmovdqa 0x00(%rsp),$D4 # preload r0^2 ++ vpand $MASK,$T0,$T0 # 0 ++ vpsrlq \$4,$T3,$T2 ++ vpand $MASK,$T1,$T1 # 1 ++ vpand 0(%rcx),$T4,$T4 # .Lmask24 ++ vpsrlq \$30,$T3,$T3 ++ vpand $MASK,$T2,$T2 # 2 ++ vpand $MASK,$T3,$T3 # 3 ++ vpor 32(%rcx),$T4,$T4 # padbit, yes, always ++ ++ ################################################################ ++ # lazy reduction as discussed in "NEON crypto" by D.J. Bernstein ++ # and P. Schwabe ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $D0,$D1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H4,$D0 ++ vpand $MASK,$H4,$H4 ++ ++ vpsrlq \$26,$H1,$D1 ++ vpand $MASK,$H1,$H1 ++ vpaddq $D1,$H2,$H2 # h1 -> h2 ++ ++ vpaddq $D0,$H0,$H0 ++ vpsllq \$2,$D0,$D0 ++ vpaddq $D0,$H0,$H0 # h4 -> h0 ++ ++ vpsrlq \$26,$H2,$D2 ++ vpand $MASK,$H2,$H2 ++ vpaddq $D2,$H3,$H3 # h2 -> h3 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ ja .Loop_avx ++ ++.Lskip_loop_avx: ++ ################################################################ ++ # multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1 ++ ++ vpshufd \$0x10,$D4,$D4 # r0^n, xx12 -> x1x2 ++ add \$32,$len ++ jnz .Long_tail_avx ++ ++ vpaddq $H2,$T2,$T2 ++ vpaddq $H0,$T0,$T0 ++ vpaddq $H1,$T1,$T1 ++ vpaddq $H3,$T3,$T3 ++ vpaddq $H4,$T4,$T4 ++ ++.Long_tail_avx: ++ vmovdqa $H2,0x20(%r11) ++ vmovdqa $H0,0x00(%r11) ++ vmovdqa $H1,0x10(%r11) ++ vmovdqa $H3,0x30(%r11) ++ vmovdqa $H4,0x40(%r11) ++ ++ # 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 ++ ++ vpmuludq $T2,$D4,$D2 # d2 = h2*r0 ++ vpmuludq $T0,$D4,$D0 # d0 = h0*r0 ++ vpshufd \$0x10,`16*1-64`($ctx),$H2 # r1^n ++ vpmuludq $T1,$D4,$D1 # d1 = h1*r0 ++ vpmuludq $T3,$D4,$D3 # d3 = h3*r0 ++ vpmuludq $T4,$D4,$D4 # d4 = h4*r0 ++ ++ vpmuludq $T3,$H2,$H0 # h3*r1 ++ vpaddq $H0,$D4,$D4 # d4 += h3*r1 ++ vpshufd \$0x10,`16*2-64`($ctx),$H3 # s1^n ++ vpmuludq $T2,$H2,$H1 # h2*r1 ++ vpaddq $H1,$D3,$D3 # d3 += h2*r1 ++ vpshufd \$0x10,`16*3-64`($ctx),$H4 # r2^n ++ vpmuludq $T1,$H2,$H0 # h1*r1 ++ vpaddq $H0,$D2,$D2 # d2 += h1*r1 ++ vpmuludq $T0,$H2,$H2 # h0*r1 ++ vpaddq $H2,$D1,$D1 # d1 += h0*r1 ++ vpmuludq $T4,$H3,$H3 # h4*s1 ++ vpaddq $H3,$D0,$D0 # d0 += h4*s1 ++ ++ vpshufd \$0x10,`16*4-64`($ctx),$H2 # s2^n ++ vpmuludq $T2,$H4,$H1 # h2*r2 ++ vpaddq $H1,$D4,$D4 # d4 += h2*r2 ++ vpmuludq $T1,$H4,$H0 # h1*r2 ++ vpaddq $H0,$D3,$D3 # d3 += h1*r2 ++ vpshufd \$0x10,`16*5-64`($ctx),$H3 # r3^n ++ vpmuludq $T0,$H4,$H4 # h0*r2 ++ vpaddq $H4,$D2,$D2 # d2 += h0*r2 ++ vpmuludq $T4,$H2,$H1 # h4*s2 ++ vpaddq $H1,$D1,$D1 # d1 += h4*s2 ++ vpshufd \$0x10,`16*6-64`($ctx),$H4 # s3^n ++ vpmuludq $T3,$H2,$H2 # h3*s2 ++ vpaddq $H2,$D0,$D0 # d0 += h3*s2 ++ ++ vpmuludq $T1,$H3,$H0 # h1*r3 ++ vpaddq $H0,$D4,$D4 # d4 += h1*r3 ++ vpmuludq $T0,$H3,$H3 # h0*r3 ++ vpaddq $H3,$D3,$D3 # d3 += h0*r3 ++ vpshufd \$0x10,`16*7-64`($ctx),$H2 # r4^n ++ vpmuludq $T4,$H4,$H1 # h4*s3 ++ vpaddq $H1,$D2,$D2 # d2 += h4*s3 ++ vpshufd \$0x10,`16*8-64`($ctx),$H3 # s4^n ++ vpmuludq $T3,$H4,$H0 # h3*s3 ++ vpaddq $H0,$D1,$D1 # d1 += h3*s3 ++ vpmuludq $T2,$H4,$H4 # h2*s3 ++ vpaddq $H4,$D0,$D0 # d0 += h2*s3 ++ ++ vpmuludq $T0,$H2,$H2 # h0*r4 ++ vpaddq $H2,$D4,$D4 # h4 = d4 + h0*r4 ++ vpmuludq $T4,$H3,$H1 # h4*s4 ++ vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4 ++ vpmuludq $T3,$H3,$H0 # h3*s4 ++ vpaddq $H0,$D2,$D2 # h2 = d2 + h3*s4 ++ vpmuludq $T2,$H3,$H1 # h2*s4 ++ vpaddq $H1,$D1,$D1 # h1 = d1 + h2*s4 ++ vpmuludq $T1,$H3,$H3 # h1*s4 ++ vpaddq $H3,$D0,$D0 # h0 = d0 + h1*s4 ++ ++ jz .Lshort_tail_avx ++ ++ vmovdqu 16*0($inp),$H0 # load input ++ vmovdqu 16*1($inp),$H1 ++ ++ vpsrldq \$6,$H0,$H2 # splat input ++ vpsrldq \$6,$H1,$H3 ++ vpunpckhqdq $H1,$H0,$H4 # 4 ++ vpunpcklqdq $H1,$H0,$H0 # 0:1 ++ vpunpcklqdq $H3,$H2,$H3 # 2:3 ++ ++ vpsrlq \$40,$H4,$H4 # 4 ++ vpsrlq \$26,$H0,$H1 ++ vpand $MASK,$H0,$H0 # 0 ++ vpsrlq \$4,$H3,$H2 ++ vpand $MASK,$H1,$H1 # 1 ++ vpsrlq \$30,$H3,$H3 ++ vpand $MASK,$H2,$H2 # 2 ++ vpand $MASK,$H3,$H3 # 3 ++ vpor 32(%rcx),$H4,$H4 # padbit, yes, always ++ ++ vpshufd \$0x32,`16*0-64`($ctx),$T4 # r0^n, 34xx -> x3x4 ++ vpaddq 0x00(%r11),$H0,$H0 ++ vpaddq 0x10(%r11),$H1,$H1 ++ vpaddq 0x20(%r11),$H2,$H2 ++ vpaddq 0x30(%r11),$H3,$H3 ++ vpaddq 0x40(%r11),$H4,$H4 ++ ++ ################################################################ ++ # multiply (inp[0:1]+hash) by r^4:r^3 and accumulate ++ ++ vpmuludq $H0,$T4,$T0 # h0*r0 ++ vpaddq $T0,$D0,$D0 # d0 += h0*r0 ++ vpmuludq $H1,$T4,$T1 # h1*r0 ++ vpaddq $T1,$D1,$D1 # d1 += h1*r0 ++ vpmuludq $H2,$T4,$T0 # h2*r0 ++ vpaddq $T0,$D2,$D2 # d2 += h2*r0 ++ vpshufd \$0x32,`16*1-64`($ctx),$T2 # r1^n ++ vpmuludq $H3,$T4,$T1 # h3*r0 ++ vpaddq $T1,$D3,$D3 # d3 += h3*r0 ++ vpmuludq $H4,$T4,$T4 # h4*r0 ++ vpaddq $T4,$D4,$D4 # d4 += h4*r0 ++ ++ vpmuludq $H3,$T2,$T0 # h3*r1 ++ vpaddq $T0,$D4,$D4 # d4 += h3*r1 ++ vpshufd \$0x32,`16*2-64`($ctx),$T3 # s1 ++ vpmuludq $H2,$T2,$T1 # h2*r1 ++ vpaddq $T1,$D3,$D3 # d3 += h2*r1 ++ vpshufd \$0x32,`16*3-64`($ctx),$T4 # r2 ++ vpmuludq $H1,$T2,$T0 # h1*r1 ++ vpaddq $T0,$D2,$D2 # d2 += h1*r1 ++ vpmuludq $H0,$T2,$T2 # h0*r1 ++ vpaddq $T2,$D1,$D1 # d1 += h0*r1 ++ vpmuludq $H4,$T3,$T3 # h4*s1 ++ vpaddq $T3,$D0,$D0 # d0 += h4*s1 ++ ++ vpshufd \$0x32,`16*4-64`($ctx),$T2 # s2 ++ vpmuludq $H2,$T4,$T1 # h2*r2 ++ vpaddq $T1,$D4,$D4 # d4 += h2*r2 ++ vpmuludq $H1,$T4,$T0 # h1*r2 ++ vpaddq $T0,$D3,$D3 # d3 += h1*r2 ++ vpshufd \$0x32,`16*5-64`($ctx),$T3 # r3 ++ vpmuludq $H0,$T4,$T4 # h0*r2 ++ vpaddq $T4,$D2,$D2 # d2 += h0*r2 ++ vpmuludq $H4,$T2,$T1 # h4*s2 ++ vpaddq $T1,$D1,$D1 # d1 += h4*s2 ++ vpshufd \$0x32,`16*6-64`($ctx),$T4 # s3 ++ vpmuludq $H3,$T2,$T2 # h3*s2 ++ vpaddq $T2,$D0,$D0 # d0 += h3*s2 ++ ++ vpmuludq $H1,$T3,$T0 # h1*r3 ++ vpaddq $T0,$D4,$D4 # d4 += h1*r3 ++ vpmuludq $H0,$T3,$T3 # h0*r3 ++ vpaddq $T3,$D3,$D3 # d3 += h0*r3 ++ vpshufd \$0x32,`16*7-64`($ctx),$T2 # r4 ++ vpmuludq $H4,$T4,$T1 # h4*s3 ++ vpaddq $T1,$D2,$D2 # d2 += h4*s3 ++ vpshufd \$0x32,`16*8-64`($ctx),$T3 # s4 ++ vpmuludq $H3,$T4,$T0 # h3*s3 ++ vpaddq $T0,$D1,$D1 # d1 += h3*s3 ++ vpmuludq $H2,$T4,$T4 # h2*s3 ++ vpaddq $T4,$D0,$D0 # d0 += h2*s3 ++ ++ vpmuludq $H0,$T2,$T2 # h0*r4 ++ vpaddq $T2,$D4,$D4 # d4 += h0*r4 ++ vpmuludq $H4,$T3,$T1 # h4*s4 ++ vpaddq $T1,$D3,$D3 # d3 += h4*s4 ++ vpmuludq $H3,$T3,$T0 # h3*s4 ++ vpaddq $T0,$D2,$D2 # d2 += h3*s4 ++ vpmuludq $H2,$T3,$T1 # h2*s4 ++ vpaddq $T1,$D1,$D1 # d1 += h2*s4 ++ vpmuludq $H1,$T3,$T3 # h1*s4 ++ vpaddq $T3,$D0,$D0 # d0 += h1*s4 ++ ++.Lshort_tail_avx: ++ ################################################################ ++ # horizontal addition ++ ++ vpsrldq \$8,$D4,$T4 ++ vpsrldq \$8,$D3,$T3 ++ vpsrldq \$8,$D1,$T1 ++ vpsrldq \$8,$D0,$T0 ++ vpsrldq \$8,$D2,$T2 ++ vpaddq $T3,$D3,$D3 ++ vpaddq $T4,$D4,$D4 ++ vpaddq $T0,$D0,$D0 ++ vpaddq $T1,$D1,$D1 ++ vpaddq $T2,$D2,$D2 ++ ++ ################################################################ ++ # lazy reduction ++ ++ vpsrlq \$26,$D3,$H3 ++ vpand $MASK,$D3,$D3 ++ vpaddq $H3,$D4,$D4 # h3 -> h4 ++ ++ vpsrlq \$26,$D0,$H0 ++ vpand $MASK,$D0,$D0 ++ vpaddq $H0,$D1,$D1 # h0 -> h1 ++ ++ vpsrlq \$26,$D4,$H4 ++ vpand $MASK,$D4,$D4 ++ ++ vpsrlq \$26,$D1,$H1 ++ vpand $MASK,$D1,$D1 ++ vpaddq $H1,$D2,$D2 # h1 -> h2 ++ ++ vpaddq $H4,$D0,$D0 ++ vpsllq \$2,$H4,$H4 ++ vpaddq $H4,$D0,$D0 # h4 -> h0 ++ ++ vpsrlq \$26,$D2,$H2 ++ vpand $MASK,$D2,$D2 ++ vpaddq $H2,$D3,$D3 # h2 -> h3 ++ ++ vpsrlq \$26,$D0,$H0 ++ vpand $MASK,$D0,$D0 ++ vpaddq $H0,$D1,$D1 # h0 -> h1 ++ ++ vpsrlq \$26,$D3,$H3 ++ vpand $MASK,$D3,$D3 ++ vpaddq $H3,$D4,$D4 # h3 -> h4 ++ ++ vmovd $D0,`4*0-48-64`($ctx) # save partially reduced ++ vmovd $D1,`4*1-48-64`($ctx) ++ vmovd $D2,`4*2-48-64`($ctx) ++ vmovd $D3,`4*3-48-64`($ctx) ++ vmovd $D4,`4*4-48-64`($ctx) ++___ ++$code.=<<___ if ($win64); ++ vmovdqa 0x50(%r11),%xmm6 ++ vmovdqa 0x60(%r11),%xmm7 ++ vmovdqa 0x70(%r11),%xmm8 ++ vmovdqa 0x80(%r11),%xmm9 ++ vmovdqa 0x90(%r11),%xmm10 ++ vmovdqa 0xa0(%r11),%xmm11 ++ vmovdqa 0xb0(%r11),%xmm12 ++ vmovdqa 0xc0(%r11),%xmm13 ++ vmovdqa 0xd0(%r11),%xmm14 ++ vmovdqa 0xe0(%r11),%xmm15 ++ lea 0xf8(%r11),%rsp ++.Ldo_avx_epilogue: ++___ ++$code.=<<___ if (!$win64); ++ lea 0x58(%r11),%rsp ++.cfi_def_cfa %rsp,8 ++___ ++$code.=<<___; ++ vzeroupper ++ ret ++.cfi_endproc ++.size poly1305_blocks_avx,.-poly1305_blocks_avx ++ ++.type poly1305_emit_avx,\@function,3 ++.align 32 ++poly1305_emit_avx: ++ cmpl \$0,20($ctx) # is_base2_26? ++ je .Lemit ++ ++ mov 0($ctx),%eax # load hash value base 2^26 ++ mov 4($ctx),%ecx ++ mov 8($ctx),%r8d ++ mov 12($ctx),%r11d ++ mov 16($ctx),%r10d ++ ++ shl \$26,%rcx # base 2^26 -> base 2^64 ++ mov %r8,%r9 ++ shl \$52,%r8 ++ add %rcx,%rax ++ shr \$12,%r9 ++ add %rax,%r8 # h0 ++ adc \$0,%r9 ++ ++ shl \$14,%r11 ++ mov %r10,%rax ++ shr \$24,%r10 ++ add %r11,%r9 ++ shl \$40,%rax ++ add %rax,%r9 # h1 ++ adc \$0,%r10 # h2 ++ ++ mov %r10,%rax # could be partially reduced, so reduce ++ mov %r10,%rcx ++ and \$3,%r10 ++ shr \$2,%rax ++ and \$-4,%rcx ++ add %rcx,%rax ++ add %rax,%r8 ++ adc \$0,%r9 ++ adc \$0,%r10 ++ ++ mov %r8,%rax ++ add \$5,%r8 # compare to modulus ++ mov %r9,%rcx ++ adc \$0,%r9 ++ adc \$0,%r10 ++ shr \$2,%r10 # did 130-bit value overflow? ++ cmovnz %r8,%rax ++ cmovnz %r9,%rcx ++ ++ add 0($nonce),%rax # accumulate nonce ++ adc 8($nonce),%rcx ++ mov %rax,0($mac) # write result ++ mov %rcx,8($mac) ++ ++ ret ++.size poly1305_emit_avx,.-poly1305_emit_avx ++___ ++ ++if ($avx>1) { ++my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) = ++ map("%ymm$_",(0..15)); ++my $S4=$MASK; ++ ++$code.=<<___; ++.type poly1305_blocks_avx2,\@function,4 ++.align 32 ++poly1305_blocks_avx2: ++.cfi_startproc ++ mov 20($ctx),%r8d # is_base2_26 ++ cmp \$128,$len ++ jae .Lblocks_avx2 ++ test %r8d,%r8d ++ jz .Lblocks ++ ++.Lblocks_avx2: ++ and \$-16,$len ++ jz .Lno_data_avx2 ++ ++ vzeroupper ++ ++ test %r8d,%r8d ++ jz .Lbase2_64_avx2 ++ ++ test \$63,$len ++ jz .Leven_avx2 ++ ++ push %rbx ++.cfi_push %rbx ++ push %rbp ++.cfi_push %rbp ++ push %r12 ++.cfi_push %r12 ++ push %r13 ++.cfi_push %r13 ++ push %r14 ++.cfi_push %r14 ++ push %r15 ++.cfi_push %r15 ++.Lblocks_avx2_body: ++ ++ mov $len,%r15 # reassign $len ++ ++ mov 0($ctx),$d1 # load hash value ++ mov 8($ctx),$d2 ++ mov 16($ctx),$h2#d ++ ++ mov 24($ctx),$r0 # load r ++ mov 32($ctx),$s1 ++ ++ ################################# base 2^26 -> base 2^64 ++ mov $d1#d,$h0#d ++ and \$`-1*(1<<31)`,$d1 ++ mov $d2,$r1 # borrow $r1 ++ mov $d2#d,$h1#d ++ and \$`-1*(1<<31)`,$d2 ++ ++ shr \$6,$d1 ++ shl \$52,$r1 ++ add $d1,$h0 ++ shr \$12,$h1 ++ shr \$18,$d2 ++ add $r1,$h0 ++ adc $d2,$h1 ++ ++ mov $h2,$d1 ++ shl \$40,$d1 ++ shr \$24,$h2 ++ add $d1,$h1 ++ adc \$0,$h2 # can be partially reduced... ++ ++ mov \$-4,$d2 # ... so reduce ++ mov $h2,$d1 ++ and $h2,$d2 ++ shr \$2,$d1 ++ and \$3,$h2 ++ add $d2,$d1 # =*5 ++ add $d1,$h0 ++ adc \$0,$h1 ++ adc \$0,$h2 ++ ++ mov $s1,$r1 ++ mov $s1,%rax ++ shr \$2,$s1 ++ add $r1,$s1 # s1 = r1 + (r1 >> 2) ++ ++.Lbase2_26_pre_avx2: ++ add 0($inp),$h0 # accumulate input ++ adc 8($inp),$h1 ++ lea 16($inp),$inp ++ adc $padbit,$h2 ++ sub \$16,%r15 ++ ++ call __poly1305_block ++ mov $r1,%rax ++ ++ test \$63,%r15 ++ jnz .Lbase2_26_pre_avx2 ++ ++ test $padbit,$padbit # if $padbit is zero, ++ jz .Lstore_base2_64_avx2 # store hash in base 2^64 format ++ ++ ################################# base 2^64 -> base 2^26 ++ mov $h0,%rax ++ mov $h0,%rdx ++ shr \$52,$h0 ++ mov $h1,$r0 ++ mov $h1,$r1 ++ shr \$26,%rdx ++ and \$0x3ffffff,%rax # h[0] ++ shl \$12,$r0 ++ and \$0x3ffffff,%rdx # h[1] ++ shr \$14,$h1 ++ or $r0,$h0 ++ shl \$24,$h2 ++ and \$0x3ffffff,$h0 # h[2] ++ shr \$40,$r1 ++ and \$0x3ffffff,$h1 # h[3] ++ or $r1,$h2 # h[4] ++ ++ test %r15,%r15 ++ jz .Lstore_base2_26_avx2 ++ ++ vmovd %rax#d,%x#$H0 ++ vmovd %rdx#d,%x#$H1 ++ vmovd $h0#d,%x#$H2 ++ vmovd $h1#d,%x#$H3 ++ vmovd $h2#d,%x#$H4 ++ jmp .Lproceed_avx2 ++ ++.align 32 ++.Lstore_base2_64_avx2: ++ mov $h0,0($ctx) ++ mov $h1,8($ctx) ++ mov $h2,16($ctx) # note that is_base2_26 is zeroed ++ jmp .Ldone_avx2 ++ ++.align 16 ++.Lstore_base2_26_avx2: ++ mov %rax#d,0($ctx) # store hash value base 2^26 ++ mov %rdx#d,4($ctx) ++ mov $h0#d,8($ctx) ++ mov $h1#d,12($ctx) ++ mov $h2#d,16($ctx) ++.align 16 ++.Ldone_avx2: ++ mov 0(%rsp),%r15 ++.cfi_restore %r15 ++ mov 8(%rsp),%r14 ++.cfi_restore %r14 ++ mov 16(%rsp),%r13 ++.cfi_restore %r13 ++ mov 24(%rsp),%r12 ++.cfi_restore %r12 ++ mov 32(%rsp),%rbp ++.cfi_restore %rbp ++ mov 40(%rsp),%rbx ++.cfi_restore %rbx ++ lea 48(%rsp),%rsp ++.cfi_adjust_cfa_offset -48 ++.Lno_data_avx2: ++.Lblocks_avx2_epilogue: ++ ret ++.cfi_endproc ++ ++.align 32 ++.Lbase2_64_avx2: ++.cfi_startproc ++ push %rbx ++.cfi_push %rbx ++ push %rbp ++.cfi_push %rbp ++ push %r12 ++.cfi_push %r12 ++ push %r13 ++.cfi_push %r13 ++ push %r14 ++.cfi_push %r14 ++ push %r15 ++.cfi_push %r15 ++.Lbase2_64_avx2_body: ++ ++ mov $len,%r15 # reassign $len ++ ++ mov 24($ctx),$r0 # load r ++ mov 32($ctx),$s1 ++ ++ mov 0($ctx),$h0 # load hash value ++ mov 8($ctx),$h1 ++ mov 16($ctx),$h2#d ++ ++ mov $s1,$r1 ++ mov $s1,%rax ++ shr \$2,$s1 ++ add $r1,$s1 # s1 = r1 + (r1 >> 2) ++ ++ test \$63,$len ++ jz .Linit_avx2 ++ ++.Lbase2_64_pre_avx2: ++ add 0($inp),$h0 # accumulate input ++ adc 8($inp),$h1 ++ lea 16($inp),$inp ++ adc $padbit,$h2 ++ sub \$16,%r15 ++ ++ call __poly1305_block ++ mov $r1,%rax ++ ++ test \$63,%r15 ++ jnz .Lbase2_64_pre_avx2 ++ ++.Linit_avx2: ++ ################################# base 2^64 -> base 2^26 ++ mov $h0,%rax ++ mov $h0,%rdx ++ shr \$52,$h0 ++ mov $h1,$d1 ++ mov $h1,$d2 ++ shr \$26,%rdx ++ and \$0x3ffffff,%rax # h[0] ++ shl \$12,$d1 ++ and \$0x3ffffff,%rdx # h[1] ++ shr \$14,$h1 ++ or $d1,$h0 ++ shl \$24,$h2 ++ and \$0x3ffffff,$h0 # h[2] ++ shr \$40,$d2 ++ and \$0x3ffffff,$h1 # h[3] ++ or $d2,$h2 # h[4] ++ ++ vmovd %rax#d,%x#$H0 ++ vmovd %rdx#d,%x#$H1 ++ vmovd $h0#d,%x#$H2 ++ vmovd $h1#d,%x#$H3 ++ vmovd $h2#d,%x#$H4 ++ movl \$1,20($ctx) # set is_base2_26 ++ ++ call __poly1305_init_avx ++ ++.Lproceed_avx2: ++ mov %r15,$len # restore $len ++ mov OPENSSL_ia32cap_P+8(%rip),%r10d ++ mov \$`(1<<31|1<<30|1<<16)`,%r11d ++ ++ mov 0(%rsp),%r15 ++.cfi_restore %r15 ++ mov 8(%rsp),%r14 ++.cfi_restore %r14 ++ mov 16(%rsp),%r13 ++.cfi_restore %r13 ++ mov 24(%rsp),%r12 ++.cfi_restore %r12 ++ mov 32(%rsp),%rbp ++.cfi_restore %rbp ++ mov 40(%rsp),%rbx ++.cfi_restore %rbx ++ lea 48(%rsp),%rax ++ lea 48(%rsp),%rsp ++.cfi_adjust_cfa_offset -48 ++.Lbase2_64_avx2_epilogue: ++ jmp .Ldo_avx2 ++.cfi_endproc ++ ++.align 32 ++.Leven_avx2: ++.cfi_startproc ++ mov OPENSSL_ia32cap_P+8(%rip),%r10d ++ vmovd 4*0($ctx),%x#$H0 # load hash value base 2^26 ++ vmovd 4*1($ctx),%x#$H1 ++ vmovd 4*2($ctx),%x#$H2 ++ vmovd 4*3($ctx),%x#$H3 ++ vmovd 4*4($ctx),%x#$H4 ++ ++.Ldo_avx2: ++___ ++$code.=<<___ if ($avx>2); ++ cmp \$512,$len ++ jb .Lskip_avx512 ++ and %r11d,%r10d ++ test \$`1<<16`,%r10d # check for AVX512F ++ jnz .Lblocks_avx512 ++.Lskip_avx512: ++___ ++$code.=<<___ if (!$win64); ++ lea -8(%rsp),%r11 ++.cfi_def_cfa %r11,16 ++ sub \$0x128,%rsp ++___ ++$code.=<<___ if ($win64); ++ lea -0xf8(%rsp),%r11 ++ sub \$0x1c8,%rsp ++ vmovdqa %xmm6,0x50(%r11) ++ vmovdqa %xmm7,0x60(%r11) ++ vmovdqa %xmm8,0x70(%r11) ++ vmovdqa %xmm9,0x80(%r11) ++ vmovdqa %xmm10,0x90(%r11) ++ vmovdqa %xmm11,0xa0(%r11) ++ vmovdqa %xmm12,0xb0(%r11) ++ vmovdqa %xmm13,0xc0(%r11) ++ vmovdqa %xmm14,0xd0(%r11) ++ vmovdqa %xmm15,0xe0(%r11) ++.Ldo_avx2_body: ++___ ++$code.=<<___; ++ lea .Lconst(%rip),%rcx ++ lea 48+64($ctx),$ctx # size optimization ++ vmovdqa 96(%rcx),$T0 # .Lpermd_avx2 ++ ++ # expand and copy pre-calculated table to stack ++ vmovdqu `16*0-64`($ctx),%x#$T2 ++ and \$-512,%rsp ++ vmovdqu `16*1-64`($ctx),%x#$T3 ++ vmovdqu `16*2-64`($ctx),%x#$T4 ++ vmovdqu `16*3-64`($ctx),%x#$D0 ++ vmovdqu `16*4-64`($ctx),%x#$D1 ++ vmovdqu `16*5-64`($ctx),%x#$D2 ++ lea 0x90(%rsp),%rax # size optimization ++ vmovdqu `16*6-64`($ctx),%x#$D3 ++ vpermd $T2,$T0,$T2 # 00003412 -> 14243444 ++ vmovdqu `16*7-64`($ctx),%x#$D4 ++ vpermd $T3,$T0,$T3 ++ vmovdqu `16*8-64`($ctx),%x#$MASK ++ vpermd $T4,$T0,$T4 ++ vmovdqa $T2,0x00(%rsp) ++ vpermd $D0,$T0,$D0 ++ vmovdqa $T3,0x20-0x90(%rax) ++ vpermd $D1,$T0,$D1 ++ vmovdqa $T4,0x40-0x90(%rax) ++ vpermd $D2,$T0,$D2 ++ vmovdqa $D0,0x60-0x90(%rax) ++ vpermd $D3,$T0,$D3 ++ vmovdqa $D1,0x80-0x90(%rax) ++ vpermd $D4,$T0,$D4 ++ vmovdqa $D2,0xa0-0x90(%rax) ++ vpermd $MASK,$T0,$MASK ++ vmovdqa $D3,0xc0-0x90(%rax) ++ vmovdqa $D4,0xe0-0x90(%rax) ++ vmovdqa $MASK,0x100-0x90(%rax) ++ vmovdqa 64(%rcx),$MASK # .Lmask26 ++ ++ ################################################################ ++ # load input ++ vmovdqu 16*0($inp),%x#$T0 ++ vmovdqu 16*1($inp),%x#$T1 ++ vinserti128 \$1,16*2($inp),$T0,$T0 ++ vinserti128 \$1,16*3($inp),$T1,$T1 ++ lea 16*4($inp),$inp ++ ++ vpsrldq \$6,$T0,$T2 # splat input ++ vpsrldq \$6,$T1,$T3 ++ vpunpckhqdq $T1,$T0,$T4 # 4 ++ vpunpcklqdq $T3,$T2,$T2 # 2:3 ++ vpunpcklqdq $T1,$T0,$T0 # 0:1 ++ ++ vpsrlq \$30,$T2,$T3 ++ vpsrlq \$4,$T2,$T2 ++ vpsrlq \$26,$T0,$T1 ++ vpsrlq \$40,$T4,$T4 # 4 ++ vpand $MASK,$T2,$T2 # 2 ++ vpand $MASK,$T0,$T0 # 0 ++ vpand $MASK,$T1,$T1 # 1 ++ vpand $MASK,$T3,$T3 # 3 ++ vpor 32(%rcx),$T4,$T4 # padbit, yes, always ++ ++ vpaddq $H2,$T2,$H2 # accumulate input ++ sub \$64,$len ++ jz .Ltail_avx2 ++ jmp .Loop_avx2 ++ ++.align 32 ++.Loop_avx2: ++ ################################################################ ++ # ((inp[0]*r^4+inp[4])*r^4+inp[ 8])*r^4 ++ # ((inp[1]*r^4+inp[5])*r^4+inp[ 9])*r^3 ++ # ((inp[2]*r^4+inp[6])*r^4+inp[10])*r^2 ++ # ((inp[3]*r^4+inp[7])*r^4+inp[11])*r^1 ++ # \________/\__________/ ++ ################################################################ ++ #vpaddq $H2,$T2,$H2 # accumulate input ++ vpaddq $H0,$T0,$H0 ++ vmovdqa `32*0`(%rsp),$T0 # r0^4 ++ vpaddq $H1,$T1,$H1 ++ vmovdqa `32*1`(%rsp),$T1 # r1^4 ++ vpaddq $H3,$T3,$H3 ++ vmovdqa `32*3`(%rsp),$T2 # r2^4 ++ vpaddq $H4,$T4,$H4 ++ vmovdqa `32*6-0x90`(%rax),$T3 # s3^4 ++ vmovdqa `32*8-0x90`(%rax),$S4 # s4^4 ++ ++ # 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 ++ # ++ # however, as h2 is "chronologically" first one available pull ++ # corresponding operations up, so it's ++ # ++ # d4 = h2*r2 + h4*r0 + h3*r1 + h1*r3 + h0*r4 ++ # d3 = h2*r1 + h3*r0 + h1*r2 + h0*r3 + h4*5*r4 ++ # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4 ++ # d1 = h2*5*r4 + h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 ++ # d0 = h2*5*r3 + h0*r0 + h4*5*r1 + h3*5*r2 + h1*5*r4 ++ ++ vpmuludq $H2,$T0,$D2 # d2 = h2*r0 ++ vpmuludq $H2,$T1,$D3 # d3 = h2*r1 ++ vpmuludq $H2,$T2,$D4 # d4 = h2*r2 ++ vpmuludq $H2,$T3,$D0 # d0 = h2*s3 ++ vpmuludq $H2,$S4,$D1 # d1 = h2*s4 ++ ++ vpmuludq $H0,$T1,$T4 # h0*r1 ++ vpmuludq $H1,$T1,$H2 # h1*r1, borrow $H2 as temp ++ vpaddq $T4,$D1,$D1 # d1 += h0*r1 ++ vpaddq $H2,$D2,$D2 # d2 += h1*r1 ++ vpmuludq $H3,$T1,$T4 # h3*r1 ++ vpmuludq `32*2`(%rsp),$H4,$H2 # h4*s1 ++ vpaddq $T4,$D4,$D4 # d4 += h3*r1 ++ vpaddq $H2,$D0,$D0 # d0 += h4*s1 ++ vmovdqa `32*4-0x90`(%rax),$T1 # s2 ++ ++ vpmuludq $H0,$T0,$T4 # h0*r0 ++ vpmuludq $H1,$T0,$H2 # h1*r0 ++ vpaddq $T4,$D0,$D0 # d0 += h0*r0 ++ vpaddq $H2,$D1,$D1 # d1 += h1*r0 ++ vpmuludq $H3,$T0,$T4 # h3*r0 ++ vpmuludq $H4,$T0,$H2 # h4*r0 ++ vmovdqu 16*0($inp),%x#$T0 # load input ++ vpaddq $T4,$D3,$D3 # d3 += h3*r0 ++ vpaddq $H2,$D4,$D4 # d4 += h4*r0 ++ vinserti128 \$1,16*2($inp),$T0,$T0 ++ ++ vpmuludq $H3,$T1,$T4 # h3*s2 ++ vpmuludq $H4,$T1,$H2 # h4*s2 ++ vmovdqu 16*1($inp),%x#$T1 ++ vpaddq $T4,$D0,$D0 # d0 += h3*s2 ++ vpaddq $H2,$D1,$D1 # d1 += h4*s2 ++ vmovdqa `32*5-0x90`(%rax),$H2 # r3 ++ vpmuludq $H1,$T2,$T4 # h1*r2 ++ vpmuludq $H0,$T2,$T2 # h0*r2 ++ vpaddq $T4,$D3,$D3 # d3 += h1*r2 ++ vpaddq $T2,$D2,$D2 # d2 += h0*r2 ++ vinserti128 \$1,16*3($inp),$T1,$T1 ++ lea 16*4($inp),$inp ++ ++ vpmuludq $H1,$H2,$T4 # h1*r3 ++ vpmuludq $H0,$H2,$H2 # h0*r3 ++ vpsrldq \$6,$T0,$T2 # splat input ++ vpaddq $T4,$D4,$D4 # d4 += h1*r3 ++ vpaddq $H2,$D3,$D3 # d3 += h0*r3 ++ vpmuludq $H3,$T3,$T4 # h3*s3 ++ vpmuludq $H4,$T3,$H2 # h4*s3 ++ vpsrldq \$6,$T1,$T3 ++ vpaddq $T4,$D1,$D1 # d1 += h3*s3 ++ vpaddq $H2,$D2,$D2 # d2 += h4*s3 ++ vpunpckhqdq $T1,$T0,$T4 # 4 ++ ++ vpmuludq $H3,$S4,$H3 # h3*s4 ++ vpmuludq $H4,$S4,$H4 # h4*s4 ++ vpunpcklqdq $T1,$T0,$T0 # 0:1 ++ vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4 ++ vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4 ++ vpunpcklqdq $T3,$T2,$T3 # 2:3 ++ vpmuludq `32*7-0x90`(%rax),$H0,$H4 # h0*r4 ++ vpmuludq $H1,$S4,$H0 # h1*s4 ++ vmovdqa 64(%rcx),$MASK # .Lmask26 ++ vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4 ++ vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4 ++ ++ ################################################################ ++ # lazy reduction (interleaved with tail of input splat) ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $D0,$D1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H4,$D4 ++ vpand $MASK,$H4,$H4 ++ ++ vpsrlq \$4,$T3,$T2 ++ ++ vpsrlq \$26,$H1,$D1 ++ vpand $MASK,$H1,$H1 ++ vpaddq $D1,$H2,$H2 # h1 -> h2 ++ ++ vpaddq $D4,$H0,$H0 ++ vpsllq \$2,$D4,$D4 ++ vpaddq $D4,$H0,$H0 # h4 -> h0 ++ ++ vpand $MASK,$T2,$T2 # 2 ++ vpsrlq \$26,$T0,$T1 ++ ++ vpsrlq \$26,$H2,$D2 ++ vpand $MASK,$H2,$H2 ++ vpaddq $D2,$H3,$H3 # h2 -> h3 ++ ++ vpaddq $T2,$H2,$H2 # modulo-scheduled ++ vpsrlq \$30,$T3,$T3 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpsrlq \$40,$T4,$T4 # 4 ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vpand $MASK,$T0,$T0 # 0 ++ vpand $MASK,$T1,$T1 # 1 ++ vpand $MASK,$T3,$T3 # 3 ++ vpor 32(%rcx),$T4,$T4 # padbit, yes, always ++ ++ sub \$64,$len ++ jnz .Loop_avx2 ++ ++ .byte 0x66,0x90 ++.Ltail_avx2: ++ ################################################################ ++ # while above multiplications were by r^4 in all lanes, in last ++ # iteration we multiply least significant lane by r^4 and most ++ # significant one by r, so copy of above except that references ++ # to the precomputed table are displaced by 4... ++ ++ #vpaddq $H2,$T2,$H2 # accumulate input ++ vpaddq $H0,$T0,$H0 ++ vmovdqu `32*0+4`(%rsp),$T0 # r0^4 ++ vpaddq $H1,$T1,$H1 ++ vmovdqu `32*1+4`(%rsp),$T1 # r1^4 ++ vpaddq $H3,$T3,$H3 ++ vmovdqu `32*3+4`(%rsp),$T2 # r2^4 ++ vpaddq $H4,$T4,$H4 ++ vmovdqu `32*6+4-0x90`(%rax),$T3 # s3^4 ++ vmovdqu `32*8+4-0x90`(%rax),$S4 # s4^4 ++ ++ vpmuludq $H2,$T0,$D2 # d2 = h2*r0 ++ vpmuludq $H2,$T1,$D3 # d3 = h2*r1 ++ vpmuludq $H2,$T2,$D4 # d4 = h2*r2 ++ vpmuludq $H2,$T3,$D0 # d0 = h2*s3 ++ vpmuludq $H2,$S4,$D1 # d1 = h2*s4 ++ ++ vpmuludq $H0,$T1,$T4 # h0*r1 ++ vpmuludq $H1,$T1,$H2 # h1*r1 ++ vpaddq $T4,$D1,$D1 # d1 += h0*r1 ++ vpaddq $H2,$D2,$D2 # d2 += h1*r1 ++ vpmuludq $H3,$T1,$T4 # h3*r1 ++ vpmuludq `32*2+4`(%rsp),$H4,$H2 # h4*s1 ++ vpaddq $T4,$D4,$D4 # d4 += h3*r1 ++ vpaddq $H2,$D0,$D0 # d0 += h4*s1 ++ ++ vpmuludq $H0,$T0,$T4 # h0*r0 ++ vpmuludq $H1,$T0,$H2 # h1*r0 ++ vpaddq $T4,$D0,$D0 # d0 += h0*r0 ++ vmovdqu `32*4+4-0x90`(%rax),$T1 # s2 ++ vpaddq $H2,$D1,$D1 # d1 += h1*r0 ++ vpmuludq $H3,$T0,$T4 # h3*r0 ++ vpmuludq $H4,$T0,$H2 # h4*r0 ++ vpaddq $T4,$D3,$D3 # d3 += h3*r0 ++ vpaddq $H2,$D4,$D4 # d4 += h4*r0 ++ ++ vpmuludq $H3,$T1,$T4 # h3*s2 ++ vpmuludq $H4,$T1,$H2 # h4*s2 ++ vpaddq $T4,$D0,$D0 # d0 += h3*s2 ++ vpaddq $H2,$D1,$D1 # d1 += h4*s2 ++ vmovdqu `32*5+4-0x90`(%rax),$H2 # r3 ++ vpmuludq $H1,$T2,$T4 # h1*r2 ++ vpmuludq $H0,$T2,$T2 # h0*r2 ++ vpaddq $T4,$D3,$D3 # d3 += h1*r2 ++ vpaddq $T2,$D2,$D2 # d2 += h0*r2 ++ ++ vpmuludq $H1,$H2,$T4 # h1*r3 ++ vpmuludq $H0,$H2,$H2 # h0*r3 ++ vpaddq $T4,$D4,$D4 # d4 += h1*r3 ++ vpaddq $H2,$D3,$D3 # d3 += h0*r3 ++ vpmuludq $H3,$T3,$T4 # h3*s3 ++ vpmuludq $H4,$T3,$H2 # h4*s3 ++ vpaddq $T4,$D1,$D1 # d1 += h3*s3 ++ vpaddq $H2,$D2,$D2 # d2 += h4*s3 ++ ++ vpmuludq $H3,$S4,$H3 # h3*s4 ++ vpmuludq $H4,$S4,$H4 # h4*s4 ++ vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4 ++ vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4 ++ vpmuludq `32*7+4-0x90`(%rax),$H0,$H4 # h0*r4 ++ vpmuludq $H1,$S4,$H0 # h1*s4 ++ vmovdqa 64(%rcx),$MASK # .Lmask26 ++ vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4 ++ vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4 ++ ++ ################################################################ ++ # horizontal addition ++ ++ vpsrldq \$8,$D1,$T1 ++ vpsrldq \$8,$H2,$T2 ++ vpsrldq \$8,$H3,$T3 ++ vpsrldq \$8,$H4,$T4 ++ vpsrldq \$8,$H0,$T0 ++ vpaddq $T1,$D1,$D1 ++ vpaddq $T2,$H2,$H2 ++ vpaddq $T3,$H3,$H3 ++ vpaddq $T4,$H4,$H4 ++ vpaddq $T0,$H0,$H0 ++ ++ vpermq \$0x2,$H3,$T3 ++ vpermq \$0x2,$H4,$T4 ++ vpermq \$0x2,$H0,$T0 ++ vpermq \$0x2,$D1,$T1 ++ vpermq \$0x2,$H2,$T2 ++ vpaddq $T3,$H3,$H3 ++ vpaddq $T4,$H4,$H4 ++ vpaddq $T0,$H0,$H0 ++ vpaddq $T1,$D1,$D1 ++ vpaddq $T2,$H2,$H2 ++ ++ ################################################################ ++ # lazy reduction ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $D0,$D1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H4,$D4 ++ vpand $MASK,$H4,$H4 ++ ++ vpsrlq \$26,$H1,$D1 ++ vpand $MASK,$H1,$H1 ++ vpaddq $D1,$H2,$H2 # h1 -> h2 ++ ++ vpaddq $D4,$H0,$H0 ++ vpsllq \$2,$D4,$D4 ++ vpaddq $D4,$H0,$H0 # h4 -> h0 ++ ++ vpsrlq \$26,$H2,$D2 ++ vpand $MASK,$H2,$H2 ++ vpaddq $D2,$H3,$H3 # h2 -> h3 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced ++ vmovd %x#$H1,`4*1-48-64`($ctx) ++ vmovd %x#$H2,`4*2-48-64`($ctx) ++ vmovd %x#$H3,`4*3-48-64`($ctx) ++ vmovd %x#$H4,`4*4-48-64`($ctx) ++___ ++$code.=<<___ if ($win64); ++ vmovdqa 0x50(%r11),%xmm6 ++ vmovdqa 0x60(%r11),%xmm7 ++ vmovdqa 0x70(%r11),%xmm8 ++ vmovdqa 0x80(%r11),%xmm9 ++ vmovdqa 0x90(%r11),%xmm10 ++ vmovdqa 0xa0(%r11),%xmm11 ++ vmovdqa 0xb0(%r11),%xmm12 ++ vmovdqa 0xc0(%r11),%xmm13 ++ vmovdqa 0xd0(%r11),%xmm14 ++ vmovdqa 0xe0(%r11),%xmm15 ++ lea 0xf8(%r11),%rsp ++.Ldo_avx2_epilogue: ++___ ++$code.=<<___ if (!$win64); ++ lea 8(%r11),%rsp ++.cfi_def_cfa %rsp,8 ++___ ++$code.=<<___; ++ vzeroupper ++ ret ++.cfi_endproc ++.size poly1305_blocks_avx2,.-poly1305_blocks_avx2 ++___ ++####################################################################### ++if ($avx>2) { ++# On entry we have input length divisible by 64. But since inner loop ++# processes 128 bytes per iteration, cases when length is not divisible ++# by 128 are handled by passing tail 64 bytes to .Ltail_avx2. For this ++# reason stack layout is kept identical to poly1305_blocks_avx2. If not ++# for this tail, we wouldn't have to even allocate stack frame... ++ ++my ($R0,$R1,$R2,$R3,$R4, $S1,$S2,$S3,$S4) = map("%zmm$_",(16..24)); ++my ($M0,$M1,$M2,$M3,$M4) = map("%zmm$_",(25..29)); ++my $PADBIT="%zmm30"; ++ ++map(s/%y/%z/,($T4,$T0,$T1,$T2,$T3)); # switch to %zmm domain ++map(s/%y/%z/,($D0,$D1,$D2,$D3,$D4)); ++map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4)); ++map(s/%y/%z/,($MASK)); ++ ++$code.=<<___; ++.type poly1305_blocks_avx512,\@function,4 ++.align 32 ++poly1305_blocks_avx512: ++.cfi_startproc ++.Lblocks_avx512: ++ mov \$15,%eax ++ kmovw %eax,%k2 ++___ ++$code.=<<___ if (!$win64); ++ lea -8(%rsp),%r11 ++.cfi_def_cfa %r11,16 ++ sub \$0x128,%rsp ++___ ++$code.=<<___ if ($win64); ++ lea -0xf8(%rsp),%r11 ++ sub \$0x1c8,%rsp ++ vmovdqa %xmm6,0x50(%r11) ++ vmovdqa %xmm7,0x60(%r11) ++ vmovdqa %xmm8,0x70(%r11) ++ vmovdqa %xmm9,0x80(%r11) ++ vmovdqa %xmm10,0x90(%r11) ++ vmovdqa %xmm11,0xa0(%r11) ++ vmovdqa %xmm12,0xb0(%r11) ++ vmovdqa %xmm13,0xc0(%r11) ++ vmovdqa %xmm14,0xd0(%r11) ++ vmovdqa %xmm15,0xe0(%r11) ++.Ldo_avx512_body: ++___ ++$code.=<<___; ++ lea .Lconst(%rip),%rcx ++ lea 48+64($ctx),$ctx # size optimization ++ vmovdqa 96(%rcx),%y#$T2 # .Lpermd_avx2 ++ ++ # expand pre-calculated table ++ vmovdqu `16*0-64`($ctx),%x#$D0 # will become expanded ${R0} ++ and \$-512,%rsp ++ vmovdqu `16*1-64`($ctx),%x#$D1 # will become ... ${R1} ++ mov \$0x20,%rax ++ vmovdqu `16*2-64`($ctx),%x#$T0 # ... ${S1} ++ vmovdqu `16*3-64`($ctx),%x#$D2 # ... ${R2} ++ vmovdqu `16*4-64`($ctx),%x#$T1 # ... ${S2} ++ vmovdqu `16*5-64`($ctx),%x#$D3 # ... ${R3} ++ vmovdqu `16*6-64`($ctx),%x#$T3 # ... ${S3} ++ vmovdqu `16*7-64`($ctx),%x#$D4 # ... ${R4} ++ vmovdqu `16*8-64`($ctx),%x#$T4 # ... ${S4} ++ vpermd $D0,$T2,$R0 # 00003412 -> 14243444 ++ vpbroadcastq 64(%rcx),$MASK # .Lmask26 ++ vpermd $D1,$T2,$R1 ++ vpermd $T0,$T2,$S1 ++ vpermd $D2,$T2,$R2 ++ vmovdqa64 $R0,0x00(%rsp){%k2} # save in case $len%128 != 0 ++ vpsrlq \$32,$R0,$T0 # 14243444 -> 01020304 ++ vpermd $T1,$T2,$S2 ++ vmovdqu64 $R1,0x00(%rsp,%rax){%k2} ++ vpsrlq \$32,$R1,$T1 ++ vpermd $D3,$T2,$R3 ++ vmovdqa64 $S1,0x40(%rsp){%k2} ++ vpermd $T3,$T2,$S3 ++ vpermd $D4,$T2,$R4 ++ vmovdqu64 $R2,0x40(%rsp,%rax){%k2} ++ vpermd $T4,$T2,$S4 ++ vmovdqa64 $S2,0x80(%rsp){%k2} ++ vmovdqu64 $R3,0x80(%rsp,%rax){%k2} ++ vmovdqa64 $S3,0xc0(%rsp){%k2} ++ vmovdqu64 $R4,0xc0(%rsp,%rax){%k2} ++ vmovdqa64 $S4,0x100(%rsp){%k2} ++ ++ ################################################################ ++ # calculate 5th through 8th powers of the key ++ # ++ # d0 = r0'*r0 + r1'*5*r4 + r2'*5*r3 + r3'*5*r2 + r4'*5*r1 ++ # d1 = r0'*r1 + r1'*r0 + r2'*5*r4 + r3'*5*r3 + r4'*5*r2 ++ # d2 = r0'*r2 + r1'*r1 + r2'*r0 + r3'*5*r4 + r4'*5*r3 ++ # d3 = r0'*r3 + r1'*r2 + r2'*r1 + r3'*r0 + r4'*5*r4 ++ # d4 = r0'*r4 + r1'*r3 + r2'*r2 + r3'*r1 + r4'*r0 ++ ++ vpmuludq $T0,$R0,$D0 # d0 = r0'*r0 ++ vpmuludq $T0,$R1,$D1 # d1 = r0'*r1 ++ vpmuludq $T0,$R2,$D2 # d2 = r0'*r2 ++ vpmuludq $T0,$R3,$D3 # d3 = r0'*r3 ++ vpmuludq $T0,$R4,$D4 # d4 = r0'*r4 ++ vpsrlq \$32,$R2,$T2 ++ ++ vpmuludq $T1,$S4,$M0 ++ vpmuludq $T1,$R0,$M1 ++ vpmuludq $T1,$R1,$M2 ++ vpmuludq $T1,$R2,$M3 ++ vpmuludq $T1,$R3,$M4 ++ vpsrlq \$32,$R3,$T3 ++ vpaddq $M0,$D0,$D0 # d0 += r1'*5*r4 ++ vpaddq $M1,$D1,$D1 # d1 += r1'*r0 ++ vpaddq $M2,$D2,$D2 # d2 += r1'*r1 ++ vpaddq $M3,$D3,$D3 # d3 += r1'*r2 ++ vpaddq $M4,$D4,$D4 # d4 += r1'*r3 ++ ++ vpmuludq $T2,$S3,$M0 ++ vpmuludq $T2,$S4,$M1 ++ vpmuludq $T2,$R1,$M3 ++ vpmuludq $T2,$R2,$M4 ++ vpmuludq $T2,$R0,$M2 ++ vpsrlq \$32,$R4,$T4 ++ vpaddq $M0,$D0,$D0 # d0 += r2'*5*r3 ++ vpaddq $M1,$D1,$D1 # d1 += r2'*5*r4 ++ vpaddq $M3,$D3,$D3 # d3 += r2'*r1 ++ vpaddq $M4,$D4,$D4 # d4 += r2'*r2 ++ vpaddq $M2,$D2,$D2 # d2 += r2'*r0 ++ ++ vpmuludq $T3,$S2,$M0 ++ vpmuludq $T3,$R0,$M3 ++ vpmuludq $T3,$R1,$M4 ++ vpmuludq $T3,$S3,$M1 ++ vpmuludq $T3,$S4,$M2 ++ vpaddq $M0,$D0,$D0 # d0 += r3'*5*r2 ++ vpaddq $M3,$D3,$D3 # d3 += r3'*r0 ++ vpaddq $M4,$D4,$D4 # d4 += r3'*r1 ++ vpaddq $M1,$D1,$D1 # d1 += r3'*5*r3 ++ vpaddq $M2,$D2,$D2 # d2 += r3'*5*r4 ++ ++ vpmuludq $T4,$S4,$M3 ++ vpmuludq $T4,$R0,$M4 ++ vpmuludq $T4,$S1,$M0 ++ vpmuludq $T4,$S2,$M1 ++ vpmuludq $T4,$S3,$M2 ++ vpaddq $M3,$D3,$D3 # d3 += r2'*5*r4 ++ vpaddq $M4,$D4,$D4 # d4 += r2'*r0 ++ vpaddq $M0,$D0,$D0 # d0 += r2'*5*r1 ++ vpaddq $M1,$D1,$D1 # d1 += r2'*5*r2 ++ vpaddq $M2,$D2,$D2 # d2 += r2'*5*r3 ++ ++ ################################################################ ++ # load input ++ vmovdqu64 16*0($inp),%z#$T3 ++ vmovdqu64 16*4($inp),%z#$T4 ++ lea 16*8($inp),$inp ++ ++ ################################################################ ++ # lazy reduction ++ ++ vpsrlq \$26,$D3,$M3 ++ vpandq $MASK,$D3,$D3 ++ vpaddq $M3,$D4,$D4 # d3 -> d4 ++ ++ vpsrlq \$26,$D0,$M0 ++ vpandq $MASK,$D0,$D0 ++ vpaddq $M0,$D1,$D1 # d0 -> d1 ++ ++ vpsrlq \$26,$D4,$M4 ++ vpandq $MASK,$D4,$D4 ++ ++ vpsrlq \$26,$D1,$M1 ++ vpandq $MASK,$D1,$D1 ++ vpaddq $M1,$D2,$D2 # d1 -> d2 ++ ++ vpaddq $M4,$D0,$D0 ++ vpsllq \$2,$M4,$M4 ++ vpaddq $M4,$D0,$D0 # d4 -> d0 ++ ++ vpsrlq \$26,$D2,$M2 ++ vpandq $MASK,$D2,$D2 ++ vpaddq $M2,$D3,$D3 # d2 -> d3 ++ ++ vpsrlq \$26,$D0,$M0 ++ vpandq $MASK,$D0,$D0 ++ vpaddq $M0,$D1,$D1 # d0 -> d1 ++ ++ vpsrlq \$26,$D3,$M3 ++ vpandq $MASK,$D3,$D3 ++ vpaddq $M3,$D4,$D4 # d3 -> d4 ++ ++ ################################################################ ++ # at this point we have 14243444 in $R0-$S4 and 05060708 in ++ # $D0-$D4, ... ++ ++ vpunpcklqdq $T4,$T3,$T0 # transpose input ++ vpunpckhqdq $T4,$T3,$T4 ++ ++ # ... since input 64-bit lanes are ordered as 73625140, we could ++ # "vperm" it to 76543210 (here and in each loop iteration), *or* ++ # we could just flow along, hence the goal for $R0-$S4 is ++ # 1858286838784888 ... ++ ++ vmovdqa32 128(%rcx),$M0 # .Lpermd_avx512: ++ mov \$0x7777,%eax ++ kmovw %eax,%k1 ++ ++ vpermd $R0,$M0,$R0 # 14243444 -> 1---2---3---4--- ++ vpermd $R1,$M0,$R1 ++ vpermd $R2,$M0,$R2 ++ vpermd $R3,$M0,$R3 ++ vpermd $R4,$M0,$R4 ++ ++ vpermd $D0,$M0,${R0}{%k1} # 05060708 -> 1858286838784888 ++ vpermd $D1,$M0,${R1}{%k1} ++ vpermd $D2,$M0,${R2}{%k1} ++ vpermd $D3,$M0,${R3}{%k1} ++ vpermd $D4,$M0,${R4}{%k1} ++ ++ vpslld \$2,$R1,$S1 # *5 ++ vpslld \$2,$R2,$S2 ++ vpslld \$2,$R3,$S3 ++ vpslld \$2,$R4,$S4 ++ vpaddd $R1,$S1,$S1 ++ vpaddd $R2,$S2,$S2 ++ vpaddd $R3,$S3,$S3 ++ vpaddd $R4,$S4,$S4 ++ ++ vpbroadcastq 32(%rcx),$PADBIT # .L129 ++ ++ vpsrlq \$52,$T0,$T2 # splat input ++ vpsllq \$12,$T4,$T3 ++ vporq $T3,$T2,$T2 ++ vpsrlq \$26,$T0,$T1 ++ vpsrlq \$14,$T4,$T3 ++ vpsrlq \$40,$T4,$T4 # 4 ++ vpandq $MASK,$T2,$T2 # 2 ++ vpandq $MASK,$T0,$T0 # 0 ++ #vpandq $MASK,$T1,$T1 # 1 ++ #vpandq $MASK,$T3,$T3 # 3 ++ #vporq $PADBIT,$T4,$T4 # padbit, yes, always ++ ++ vpaddq $H2,$T2,$H2 # accumulate input ++ sub \$192,$len ++ jbe .Ltail_avx512 ++ jmp .Loop_avx512 ++ ++.align 32 ++.Loop_avx512: ++ ################################################################ ++ # ((inp[0]*r^8+inp[ 8])*r^8+inp[16])*r^8 ++ # ((inp[1]*r^8+inp[ 9])*r^8+inp[17])*r^7 ++ # ((inp[2]*r^8+inp[10])*r^8+inp[18])*r^6 ++ # ((inp[3]*r^8+inp[11])*r^8+inp[19])*r^5 ++ # ((inp[4]*r^8+inp[12])*r^8+inp[20])*r^4 ++ # ((inp[5]*r^8+inp[13])*r^8+inp[21])*r^3 ++ # ((inp[6]*r^8+inp[14])*r^8+inp[22])*r^2 ++ # ((inp[7]*r^8+inp[15])*r^8+inp[23])*r^1 ++ # \________/\___________/ ++ ################################################################ ++ #vpaddq $H2,$T2,$H2 # accumulate input ++ ++ # 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 ++ # ++ # however, as h2 is "chronologically" first one available pull ++ # corresponding operations up, so it's ++ # ++ # d3 = h2*r1 + h0*r3 + h1*r2 + h3*r0 + h4*5*r4 ++ # d4 = h2*r2 + h0*r4 + h1*r3 + h3*r1 + h4*r0 ++ # d0 = h2*5*r3 + h0*r0 + h1*5*r4 + h3*5*r2 + h4*5*r1 ++ # d1 = h2*5*r4 + h0*r1 + h1*r0 + h3*5*r3 + h4*5*r2 ++ # d2 = h2*r0 + h0*r2 + h1*r1 + h3*5*r4 + h4*5*r3 ++ ++ vpmuludq $H2,$R1,$D3 # d3 = h2*r1 ++ vpaddq $H0,$T0,$H0 ++ vpmuludq $H2,$R2,$D4 # d4 = h2*r2 ++ vpandq $MASK,$T1,$T1 # 1 ++ vpmuludq $H2,$S3,$D0 # d0 = h2*s3 ++ vpandq $MASK,$T3,$T3 # 3 ++ vpmuludq $H2,$S4,$D1 # d1 = h2*s4 ++ vporq $PADBIT,$T4,$T4 # padbit, yes, always ++ vpmuludq $H2,$R0,$D2 # d2 = h2*r0 ++ vpaddq $H1,$T1,$H1 # accumulate input ++ vpaddq $H3,$T3,$H3 ++ vpaddq $H4,$T4,$H4 ++ ++ vmovdqu64 16*0($inp),$T3 # load input ++ vmovdqu64 16*4($inp),$T4 ++ lea 16*8($inp),$inp ++ vpmuludq $H0,$R3,$M3 ++ vpmuludq $H0,$R4,$M4 ++ vpmuludq $H0,$R0,$M0 ++ vpmuludq $H0,$R1,$M1 ++ vpaddq $M3,$D3,$D3 # d3 += h0*r3 ++ vpaddq $M4,$D4,$D4 # d4 += h0*r4 ++ vpaddq $M0,$D0,$D0 # d0 += h0*r0 ++ vpaddq $M1,$D1,$D1 # d1 += h0*r1 ++ ++ vpmuludq $H1,$R2,$M3 ++ vpmuludq $H1,$R3,$M4 ++ vpmuludq $H1,$S4,$M0 ++ vpmuludq $H0,$R2,$M2 ++ vpaddq $M3,$D3,$D3 # d3 += h1*r2 ++ vpaddq $M4,$D4,$D4 # d4 += h1*r3 ++ vpaddq $M0,$D0,$D0 # d0 += h1*s4 ++ vpaddq $M2,$D2,$D2 # d2 += h0*r2 ++ ++ vpunpcklqdq $T4,$T3,$T0 # transpose input ++ vpunpckhqdq $T4,$T3,$T4 ++ ++ vpmuludq $H3,$R0,$M3 ++ vpmuludq $H3,$R1,$M4 ++ vpmuludq $H1,$R0,$M1 ++ vpmuludq $H1,$R1,$M2 ++ vpaddq $M3,$D3,$D3 # d3 += h3*r0 ++ vpaddq $M4,$D4,$D4 # d4 += h3*r1 ++ vpaddq $M1,$D1,$D1 # d1 += h1*r0 ++ vpaddq $M2,$D2,$D2 # d2 += h1*r1 ++ ++ vpmuludq $H4,$S4,$M3 ++ vpmuludq $H4,$R0,$M4 ++ vpmuludq $H3,$S2,$M0 ++ vpmuludq $H3,$S3,$M1 ++ vpaddq $M3,$D3,$D3 # d3 += h4*s4 ++ vpmuludq $H3,$S4,$M2 ++ vpaddq $M4,$D4,$D4 # d4 += h4*r0 ++ vpaddq $M0,$D0,$D0 # d0 += h3*s2 ++ vpaddq $M1,$D1,$D1 # d1 += h3*s3 ++ vpaddq $M2,$D2,$D2 # d2 += h3*s4 ++ ++ vpmuludq $H4,$S1,$M0 ++ vpmuludq $H4,$S2,$M1 ++ vpmuludq $H4,$S3,$M2 ++ vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1 ++ vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2 ++ vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3 ++ ++ ################################################################ ++ # lazy reduction (interleaved with input splat) ++ ++ vpsrlq \$52,$T0,$T2 # splat input ++ vpsllq \$12,$T4,$T3 ++ ++ vpsrlq \$26,$D3,$H3 ++ vpandq $MASK,$D3,$D3 ++ vpaddq $H3,$D4,$H4 # h3 -> h4 ++ ++ vporq $T3,$T2,$T2 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpandq $MASK,$H0,$H0 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpandq $MASK,$T2,$T2 # 2 ++ ++ vpsrlq \$26,$H4,$D4 ++ vpandq $MASK,$H4,$H4 ++ ++ vpsrlq \$26,$H1,$D1 ++ vpandq $MASK,$H1,$H1 ++ vpaddq $D1,$H2,$H2 # h1 -> h2 ++ ++ vpaddq $D4,$H0,$H0 ++ vpsllq \$2,$D4,$D4 ++ vpaddq $D4,$H0,$H0 # h4 -> h0 ++ ++ vpaddq $T2,$H2,$H2 # modulo-scheduled ++ vpsrlq \$26,$T0,$T1 ++ ++ vpsrlq \$26,$H2,$D2 ++ vpandq $MASK,$H2,$H2 ++ vpaddq $D2,$D3,$H3 # h2 -> h3 ++ ++ vpsrlq \$14,$T4,$T3 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpandq $MASK,$H0,$H0 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpsrlq \$40,$T4,$T4 # 4 ++ ++ vpsrlq \$26,$H3,$D3 ++ vpandq $MASK,$H3,$H3 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vpandq $MASK,$T0,$T0 # 0 ++ #vpandq $MASK,$T1,$T1 # 1 ++ #vpandq $MASK,$T3,$T3 # 3 ++ #vporq $PADBIT,$T4,$T4 # padbit, yes, always ++ ++ sub \$128,$len ++ ja .Loop_avx512 ++ ++.Ltail_avx512: ++ ################################################################ ++ # while above multiplications were by r^8 in all lanes, in last ++ # iteration we multiply least significant lane by r^8 and most ++ # significant one by r, that's why table gets shifted... ++ ++ vpsrlq \$32,$R0,$R0 # 0105020603070408 ++ vpsrlq \$32,$R1,$R1 ++ vpsrlq \$32,$R2,$R2 ++ vpsrlq \$32,$S3,$S3 ++ vpsrlq \$32,$S4,$S4 ++ vpsrlq \$32,$R3,$R3 ++ vpsrlq \$32,$R4,$R4 ++ vpsrlq \$32,$S1,$S1 ++ vpsrlq \$32,$S2,$S2 ++ ++ ################################################################ ++ # load either next or last 64 byte of input ++ lea ($inp,$len),$inp ++ ++ #vpaddq $H2,$T2,$H2 # accumulate input ++ vpaddq $H0,$T0,$H0 ++ ++ vpmuludq $H2,$R1,$D3 # d3 = h2*r1 ++ vpmuludq $H2,$R2,$D4 # d4 = h2*r2 ++ vpmuludq $H2,$S3,$D0 # d0 = h2*s3 ++ vpandq $MASK,$T1,$T1 # 1 ++ vpmuludq $H2,$S4,$D1 # d1 = h2*s4 ++ vpandq $MASK,$T3,$T3 # 3 ++ vpmuludq $H2,$R0,$D2 # d2 = h2*r0 ++ vporq $PADBIT,$T4,$T4 # padbit, yes, always ++ vpaddq $H1,$T1,$H1 # accumulate input ++ vpaddq $H3,$T3,$H3 ++ vpaddq $H4,$T4,$H4 ++ ++ vmovdqu 16*0($inp),%x#$T0 ++ vpmuludq $H0,$R3,$M3 ++ vpmuludq $H0,$R4,$M4 ++ vpmuludq $H0,$R0,$M0 ++ vpmuludq $H0,$R1,$M1 ++ vpaddq $M3,$D3,$D3 # d3 += h0*r3 ++ vpaddq $M4,$D4,$D4 # d4 += h0*r4 ++ vpaddq $M0,$D0,$D0 # d0 += h0*r0 ++ vpaddq $M1,$D1,$D1 # d1 += h0*r1 ++ ++ vmovdqu 16*1($inp),%x#$T1 ++ vpmuludq $H1,$R2,$M3 ++ vpmuludq $H1,$R3,$M4 ++ vpmuludq $H1,$S4,$M0 ++ vpmuludq $H0,$R2,$M2 ++ vpaddq $M3,$D3,$D3 # d3 += h1*r2 ++ vpaddq $M4,$D4,$D4 # d4 += h1*r3 ++ vpaddq $M0,$D0,$D0 # d0 += h1*s4 ++ vpaddq $M2,$D2,$D2 # d2 += h0*r2 ++ ++ vinserti128 \$1,16*2($inp),%y#$T0,%y#$T0 ++ vpmuludq $H3,$R0,$M3 ++ vpmuludq $H3,$R1,$M4 ++ vpmuludq $H1,$R0,$M1 ++ vpmuludq $H1,$R1,$M2 ++ vpaddq $M3,$D3,$D3 # d3 += h3*r0 ++ vpaddq $M4,$D4,$D4 # d4 += h3*r1 ++ vpaddq $M1,$D1,$D1 # d1 += h1*r0 ++ vpaddq $M2,$D2,$D2 # d2 += h1*r1 ++ ++ vinserti128 \$1,16*3($inp),%y#$T1,%y#$T1 ++ vpmuludq $H4,$S4,$M3 ++ vpmuludq $H4,$R0,$M4 ++ vpmuludq $H3,$S2,$M0 ++ vpmuludq $H3,$S3,$M1 ++ vpmuludq $H3,$S4,$M2 ++ vpaddq $M3,$D3,$H3 # h3 = d3 + h4*s4 ++ vpaddq $M4,$D4,$D4 # d4 += h4*r0 ++ vpaddq $M0,$D0,$D0 # d0 += h3*s2 ++ vpaddq $M1,$D1,$D1 # d1 += h3*s3 ++ vpaddq $M2,$D2,$D2 # d2 += h3*s4 ++ ++ vpmuludq $H4,$S1,$M0 ++ vpmuludq $H4,$S2,$M1 ++ vpmuludq $H4,$S3,$M2 ++ vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1 ++ vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2 ++ vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3 ++ ++ ################################################################ ++ # horizontal addition ++ ++ mov \$1,%eax ++ vpermq \$0xb1,$H3,$D3 ++ vpermq \$0xb1,$D4,$H4 ++ vpermq \$0xb1,$H0,$D0 ++ vpermq \$0xb1,$H1,$D1 ++ vpermq \$0xb1,$H2,$D2 ++ vpaddq $D3,$H3,$H3 ++ vpaddq $D4,$H4,$H4 ++ vpaddq $D0,$H0,$H0 ++ vpaddq $D1,$H1,$H1 ++ vpaddq $D2,$H2,$H2 ++ ++ kmovw %eax,%k3 ++ vpermq \$0x2,$H3,$D3 ++ vpermq \$0x2,$H4,$D4 ++ vpermq \$0x2,$H0,$D0 ++ vpermq \$0x2,$H1,$D1 ++ vpermq \$0x2,$H2,$D2 ++ vpaddq $D3,$H3,$H3 ++ vpaddq $D4,$H4,$H4 ++ vpaddq $D0,$H0,$H0 ++ vpaddq $D1,$H1,$H1 ++ vpaddq $D2,$H2,$H2 ++ ++ vextracti64x4 \$0x1,$H3,%y#$D3 ++ vextracti64x4 \$0x1,$H4,%y#$D4 ++ vextracti64x4 \$0x1,$H0,%y#$D0 ++ vextracti64x4 \$0x1,$H1,%y#$D1 ++ vextracti64x4 \$0x1,$H2,%y#$D2 ++ vpaddq $D3,$H3,${H3}{%k3}{z} # keep single qword in case ++ vpaddq $D4,$H4,${H4}{%k3}{z} # it's passed to .Ltail_avx2 ++ vpaddq $D0,$H0,${H0}{%k3}{z} ++ vpaddq $D1,$H1,${H1}{%k3}{z} ++ vpaddq $D2,$H2,${H2}{%k3}{z} ++___ ++map(s/%z/%y/,($T0,$T1,$T2,$T3,$T4, $PADBIT)); ++map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK)); ++$code.=<<___; ++ ################################################################ ++ # lazy reduction (interleaved with input splat) ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpsrldq \$6,$T0,$T2 # splat input ++ vpsrldq \$6,$T1,$T3 ++ vpunpckhqdq $T1,$T0,$T4 # 4 ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpunpcklqdq $T3,$T2,$T2 # 2:3 ++ vpunpcklqdq $T1,$T0,$T0 # 0:1 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H4,$D4 ++ vpand $MASK,$H4,$H4 ++ ++ vpsrlq \$26,$H1,$D1 ++ vpand $MASK,$H1,$H1 ++ vpsrlq \$30,$T2,$T3 ++ vpsrlq \$4,$T2,$T2 ++ vpaddq $D1,$H2,$H2 # h1 -> h2 ++ ++ vpaddq $D4,$H0,$H0 ++ vpsllq \$2,$D4,$D4 ++ vpsrlq \$26,$T0,$T1 ++ vpsrlq \$40,$T4,$T4 # 4 ++ vpaddq $D4,$H0,$H0 # h4 -> h0 ++ ++ vpsrlq \$26,$H2,$D2 ++ vpand $MASK,$H2,$H2 ++ vpand $MASK,$T2,$T2 # 2 ++ vpand $MASK,$T0,$T0 # 0 ++ vpaddq $D2,$H3,$H3 # h2 -> h3 ++ ++ vpsrlq \$26,$H0,$D0 ++ vpand $MASK,$H0,$H0 ++ vpaddq $H2,$T2,$H2 # accumulate input for .Ltail_avx2 ++ vpand $MASK,$T1,$T1 # 1 ++ vpaddq $D0,$H1,$H1 # h0 -> h1 ++ ++ vpsrlq \$26,$H3,$D3 ++ vpand $MASK,$H3,$H3 ++ vpand $MASK,$T3,$T3 # 3 ++ vpor 32(%rcx),$T4,$T4 # padbit, yes, always ++ vpaddq $D3,$H4,$H4 # h3 -> h4 ++ ++ lea 0x90(%rsp),%rax # size optimization for .Ltail_avx2 ++ add \$64,$len ++ jnz .Ltail_avx2 ++ ++ vpsubq $T2,$H2,$H2 # undo input accumulation ++ vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced ++ vmovd %x#$H1,`4*1-48-64`($ctx) ++ vmovd %x#$H2,`4*2-48-64`($ctx) ++ vmovd %x#$H3,`4*3-48-64`($ctx) ++ vmovd %x#$H4,`4*4-48-64`($ctx) ++ vzeroall ++___ ++$code.=<<___ if ($win64); ++ movdqa 0x50(%r11),%xmm6 ++ movdqa 0x60(%r11),%xmm7 ++ movdqa 0x70(%r11),%xmm8 ++ movdqa 0x80(%r11),%xmm9 ++ movdqa 0x90(%r11),%xmm10 ++ movdqa 0xa0(%r11),%xmm11 ++ movdqa 0xb0(%r11),%xmm12 ++ movdqa 0xc0(%r11),%xmm13 ++ movdqa 0xd0(%r11),%xmm14 ++ movdqa 0xe0(%r11),%xmm15 ++ lea 0xf8(%r11),%rsp ++.Ldo_avx512_epilogue: ++___ ++$code.=<<___ if (!$win64); ++ lea 8(%r11),%rsp ++.cfi_def_cfa %rsp,8 ++___ ++$code.=<<___; ++ ret ++.cfi_endproc ++.size poly1305_blocks_avx512,.-poly1305_blocks_avx512 ++___ ++if ($avx>3) { ++######################################################################## ++# VPMADD52 version using 2^44 radix. ++# ++# One can argue that base 2^52 would be more natural. Well, even though ++# some operations would be more natural, one has to recognize couple of ++# things. Base 2^52 doesn't provide advantage over base 2^44 if you look ++# at amount of multiply-n-accumulate operations. Secondly, it makes it ++# impossible to pre-compute multiples of 5 [referred to as s[]/sN in ++# reference implementations], which means that more such operations ++# would have to be performed in inner loop, which in turn makes critical ++# path longer. In other words, even though base 2^44 reduction might ++# look less elegant, overall critical path is actually shorter... ++ ++######################################################################## ++# Layout of opaque area is following. ++# ++# unsigned __int64 h[3]; # current hash value base 2^44 ++# unsigned __int64 s[2]; # key value*20 base 2^44 ++# unsigned __int64 r[3]; # key value base 2^44 ++# struct { unsigned __int64 r^1, r^3, r^2, r^4; } R[4]; ++# # r^n positions reflect ++# # placement in register, not ++# # memory, R[3] is R[1]*20 ++ ++$code.=<<___; ++.type poly1305_init_base2_44,\@function,3 ++.align 32 ++poly1305_init_base2_44: ++ xor %rax,%rax ++ mov %rax,0($ctx) # initialize hash value ++ mov %rax,8($ctx) ++ mov %rax,16($ctx) ++ ++.Linit_base2_44: ++ lea poly1305_blocks_vpmadd52(%rip),%r10 ++ lea poly1305_emit_base2_44(%rip),%r11 ++ ++ mov \$0x0ffffffc0fffffff,%rax ++ mov \$0x0ffffffc0ffffffc,%rcx ++ and 0($inp),%rax ++ mov \$0x00000fffffffffff,%r8 ++ and 8($inp),%rcx ++ mov \$0x00000fffffffffff,%r9 ++ and %rax,%r8 ++ shrd \$44,%rcx,%rax ++ mov %r8,40($ctx) # r0 ++ and %r9,%rax ++ shr \$24,%rcx ++ mov %rax,48($ctx) # r1 ++ lea (%rax,%rax,4),%rax # *5 ++ mov %rcx,56($ctx) # r2 ++ shl \$2,%rax # magic <<2 ++ lea (%rcx,%rcx,4),%rcx # *5 ++ shl \$2,%rcx # magic <<2 ++ mov %rax,24($ctx) # s1 ++ mov %rcx,32($ctx) # s2 ++ movq \$-1,64($ctx) # write impossible value ++___ ++$code.=<<___ if ($flavour !~ /elf32/); ++ mov %r10,0(%rdx) ++ mov %r11,8(%rdx) ++___ ++$code.=<<___ if ($flavour =~ /elf32/); ++ mov %r10d,0(%rdx) ++ mov %r11d,4(%rdx) ++___ ++$code.=<<___; ++ mov \$1,%eax ++ ret ++.size poly1305_init_base2_44,.-poly1305_init_base2_44 ++___ ++{ ++my ($H0,$H1,$H2,$r2r1r0,$r1r0s2,$r0s2s1,$Dlo,$Dhi) = map("%ymm$_",(0..5,16,17)); ++my ($T0,$inp_permd,$inp_shift,$PAD) = map("%ymm$_",(18..21)); ++my ($reduc_mask,$reduc_rght,$reduc_left) = map("%ymm$_",(22..25)); ++ ++$code.=<<___; ++.type poly1305_blocks_vpmadd52,\@function,4 ++.align 32 ++poly1305_blocks_vpmadd52: ++ shr \$4,$len ++ jz .Lno_data_vpmadd52 # too short ++ ++ shl \$40,$padbit ++ mov 64($ctx),%r8 # peek on power of the key ++ ++ # if powers of the key are not calculated yet, process up to 3 ++ # blocks with this single-block subroutine, otherwise ensure that ++ # length is divisible by 2 blocks and pass the rest down to next ++ # subroutine... ++ ++ mov \$3,%rax ++ mov \$1,%r10 ++ cmp \$4,$len # is input long ++ cmovae %r10,%rax ++ test %r8,%r8 # is power value impossible? ++ cmovns %r10,%rax ++ ++ and $len,%rax # is input of favourable length? ++ jz .Lblocks_vpmadd52_4x ++ ++ sub %rax,$len ++ mov \$7,%r10d ++ mov \$1,%r11d ++ kmovw %r10d,%k7 ++ lea .L2_44_inp_permd(%rip),%r10 ++ kmovw %r11d,%k1 ++ ++ vmovq $padbit,%x#$PAD ++ vmovdqa64 0(%r10),$inp_permd # .L2_44_inp_permd ++ vmovdqa64 32(%r10),$inp_shift # .L2_44_inp_shift ++ vpermq \$0xcf,$PAD,$PAD ++ vmovdqa64 64(%r10),$reduc_mask # .L2_44_mask ++ ++ vmovdqu64 0($ctx),${Dlo}{%k7}{z} # load hash value ++ vmovdqu64 40($ctx),${r2r1r0}{%k7}{z} # load keys ++ vmovdqu64 32($ctx),${r1r0s2}{%k7}{z} ++ vmovdqu64 24($ctx),${r0s2s1}{%k7}{z} ++ ++ vmovdqa64 96(%r10),$reduc_rght # .L2_44_shift_rgt ++ vmovdqa64 128(%r10),$reduc_left # .L2_44_shift_lft ++ ++ jmp .Loop_vpmadd52 ++ ++.align 32 ++.Loop_vpmadd52: ++ vmovdqu32 0($inp),%x#$T0 # load input as ----3210 ++ lea 16($inp),$inp ++ ++ vpermd $T0,$inp_permd,$T0 # ----3210 -> --322110 ++ vpsrlvq $inp_shift,$T0,$T0 ++ vpandq $reduc_mask,$T0,$T0 ++ vporq $PAD,$T0,$T0 ++ ++ vpaddq $T0,$Dlo,$Dlo # accumulate input ++ ++ vpermq \$0,$Dlo,${H0}{%k7}{z} # smash hash value ++ vpermq \$0b01010101,$Dlo,${H1}{%k7}{z} ++ vpermq \$0b10101010,$Dlo,${H2}{%k7}{z} ++ ++ vpxord $Dlo,$Dlo,$Dlo ++ vpxord $Dhi,$Dhi,$Dhi ++ ++ vpmadd52luq $r2r1r0,$H0,$Dlo ++ vpmadd52huq $r2r1r0,$H0,$Dhi ++ ++ vpmadd52luq $r1r0s2,$H1,$Dlo ++ vpmadd52huq $r1r0s2,$H1,$Dhi ++ ++ vpmadd52luq $r0s2s1,$H2,$Dlo ++ vpmadd52huq $r0s2s1,$H2,$Dhi ++ ++ vpsrlvq $reduc_rght,$Dlo,$T0 # 0 in topmost qword ++ vpsllvq $reduc_left,$Dhi,$Dhi # 0 in topmost qword ++ vpandq $reduc_mask,$Dlo,$Dlo ++ ++ vpaddq $T0,$Dhi,$Dhi ++ ++ vpermq \$0b10010011,$Dhi,$Dhi # 0 in lowest qword ++ ++ vpaddq $Dhi,$Dlo,$Dlo # note topmost qword :-) ++ ++ vpsrlvq $reduc_rght,$Dlo,$T0 # 0 in topmost word ++ vpandq $reduc_mask,$Dlo,$Dlo ++ ++ vpermq \$0b10010011,$T0,$T0 ++ ++ vpaddq $T0,$Dlo,$Dlo ++ ++ vpermq \$0b10010011,$Dlo,${T0}{%k1}{z} ++ ++ vpaddq $T0,$Dlo,$Dlo ++ vpsllq \$2,$T0,$T0 ++ ++ vpaddq $T0,$Dlo,$Dlo ++ ++ dec %rax # len-=16 ++ jnz .Loop_vpmadd52 ++ ++ vmovdqu64 $Dlo,0($ctx){%k7} # store hash value ++ ++ test $len,$len ++ jnz .Lblocks_vpmadd52_4x ++ ++.Lno_data_vpmadd52: ++ ret ++.size poly1305_blocks_vpmadd52,.-poly1305_blocks_vpmadd52 ++___ ++} ++{ ++######################################################################## ++# As implied by its name 4x subroutine processes 4 blocks in parallel ++# (but handles even 4*n+2 blocks lengths). It takes up to 4th key power ++# and is handled in 256-bit %ymm registers. ++ ++my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17)); ++my ($D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi) = map("%ymm$_",(18..23)); ++my ($T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD) = map("%ymm$_",(24..31)); ++ ++$code.=<<___; ++.type poly1305_blocks_vpmadd52_4x,\@function,4 ++.align 32 ++poly1305_blocks_vpmadd52_4x: ++ shr \$4,$len ++ jz .Lno_data_vpmadd52_4x # too short ++ ++ shl \$40,$padbit ++ mov 64($ctx),%r8 # peek on power of the key ++ ++.Lblocks_vpmadd52_4x: ++ vpbroadcastq $padbit,$PAD ++ ++ vmovdqa64 .Lx_mask44(%rip),$mask44 ++ mov \$5,%eax ++ vmovdqa64 .Lx_mask42(%rip),$mask42 ++ kmovw %eax,%k1 # used in 2x path ++ ++ test %r8,%r8 # is power value impossible? ++ js .Linit_vpmadd52 # if it is, then init R[4] ++ ++ vmovq 0($ctx),%x#$H0 # load current hash value ++ vmovq 8($ctx),%x#$H1 ++ vmovq 16($ctx),%x#$H2 ++ ++ test \$3,$len # is length 4*n+2? ++ jnz .Lblocks_vpmadd52_2x_do ++ ++.Lblocks_vpmadd52_4x_do: ++ vpbroadcastq 64($ctx),$R0 # load 4th power of the key ++ vpbroadcastq 96($ctx),$R1 ++ vpbroadcastq 128($ctx),$R2 ++ vpbroadcastq 160($ctx),$S1 ++ ++.Lblocks_vpmadd52_4x_key_loaded: ++ vpsllq \$2,$R2,$S2 # S2 = R2*5*4 ++ vpaddq $R2,$S2,$S2 ++ vpsllq \$2,$S2,$S2 ++ ++ test \$7,$len # is len 8*n? ++ jz .Lblocks_vpmadd52_8x ++ ++ vmovdqu64 16*0($inp),$T2 # load data ++ vmovdqu64 16*2($inp),$T3 ++ lea 16*4($inp),$inp ++ ++ vpunpcklqdq $T3,$T2,$T1 # transpose data ++ vpunpckhqdq $T3,$T2,$T3 ++ ++ # at this point 64-bit lanes are ordered as 3-1-2-0 ++ ++ vpsrlq \$24,$T3,$T2 # splat the data ++ vporq $PAD,$T2,$T2 ++ vpaddq $T2,$H2,$H2 # accumulate input ++ vpandq $mask44,$T1,$T0 ++ vpsrlq \$44,$T1,$T1 ++ vpsllq \$20,$T3,$T3 ++ vporq $T3,$T1,$T1 ++ vpandq $mask44,$T1,$T1 ++ ++ sub \$4,$len ++ jz .Ltail_vpmadd52_4x ++ jmp .Loop_vpmadd52_4x ++ ud2 ++ ++.align 32 ++.Linit_vpmadd52: ++ vmovq 24($ctx),%x#$S1 # load key ++ vmovq 56($ctx),%x#$H2 ++ vmovq 32($ctx),%x#$S2 ++ vmovq 40($ctx),%x#$R0 ++ vmovq 48($ctx),%x#$R1 ++ ++ vmovdqa $R0,$H0 ++ vmovdqa $R1,$H1 ++ vmovdqa $H2,$R2 ++ ++ mov \$2,%eax ++ ++.Lmul_init_vpmadd52: ++ vpxorq $D0lo,$D0lo,$D0lo ++ vpmadd52luq $H2,$S1,$D0lo ++ vpxorq $D0hi,$D0hi,$D0hi ++ vpmadd52huq $H2,$S1,$D0hi ++ vpxorq $D1lo,$D1lo,$D1lo ++ vpmadd52luq $H2,$S2,$D1lo ++ vpxorq $D1hi,$D1hi,$D1hi ++ vpmadd52huq $H2,$S2,$D1hi ++ vpxorq $D2lo,$D2lo,$D2lo ++ vpmadd52luq $H2,$R0,$D2lo ++ vpxorq $D2hi,$D2hi,$D2hi ++ vpmadd52huq $H2,$R0,$D2hi ++ ++ vpmadd52luq $H0,$R0,$D0lo ++ vpmadd52huq $H0,$R0,$D0hi ++ vpmadd52luq $H0,$R1,$D1lo ++ vpmadd52huq $H0,$R1,$D1hi ++ vpmadd52luq $H0,$R2,$D2lo ++ vpmadd52huq $H0,$R2,$D2hi ++ ++ vpmadd52luq $H1,$S2,$D0lo ++ vpmadd52huq $H1,$S2,$D0hi ++ vpmadd52luq $H1,$R0,$D1lo ++ vpmadd52huq $H1,$R0,$D1hi ++ vpmadd52luq $H1,$R1,$D2lo ++ vpmadd52huq $H1,$R1,$D2hi ++ ++ ################################################################ ++ # partial reduction ++ vpsrlq \$44,$D0lo,$tmp ++ vpsllq \$8,$D0hi,$D0hi ++ vpandq $mask44,$D0lo,$H0 ++ vpaddq $tmp,$D0hi,$D0hi ++ ++ vpaddq $D0hi,$D1lo,$D1lo ++ ++ vpsrlq \$44,$D1lo,$tmp ++ vpsllq \$8,$D1hi,$D1hi ++ vpandq $mask44,$D1lo,$H1 ++ vpaddq $tmp,$D1hi,$D1hi ++ ++ vpaddq $D1hi,$D2lo,$D2lo ++ ++ vpsrlq \$42,$D2lo,$tmp ++ vpsllq \$10,$D2hi,$D2hi ++ vpandq $mask42,$D2lo,$H2 ++ vpaddq $tmp,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ vpsllq \$2,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ ++ vpsrlq \$44,$H0,$tmp # additional step ++ vpandq $mask44,$H0,$H0 ++ ++ vpaddq $tmp,$H1,$H1 ++ ++ dec %eax ++ jz .Ldone_init_vpmadd52 ++ ++ vpunpcklqdq $R1,$H1,$R1 # 1,2 ++ vpbroadcastq %x#$H1,%x#$H1 # 2,2 ++ vpunpcklqdq $R2,$H2,$R2 ++ vpbroadcastq %x#$H2,%x#$H2 ++ vpunpcklqdq $R0,$H0,$R0 ++ vpbroadcastq %x#$H0,%x#$H0 ++ ++ vpsllq \$2,$R1,$S1 # S1 = R1*5*4 ++ vpsllq \$2,$R2,$S2 # S2 = R2*5*4 ++ vpaddq $R1,$S1,$S1 ++ vpaddq $R2,$S2,$S2 ++ vpsllq \$2,$S1,$S1 ++ vpsllq \$2,$S2,$S2 ++ ++ jmp .Lmul_init_vpmadd52 ++ ud2 ++ ++.align 32 ++.Ldone_init_vpmadd52: ++ vinserti128 \$1,%x#$R1,$H1,$R1 # 1,2,3,4 ++ vinserti128 \$1,%x#$R2,$H2,$R2 ++ vinserti128 \$1,%x#$R0,$H0,$R0 ++ ++ vpermq \$0b11011000,$R1,$R1 # 1,3,2,4 ++ vpermq \$0b11011000,$R2,$R2 ++ vpermq \$0b11011000,$R0,$R0 ++ ++ vpsllq \$2,$R1,$S1 # S1 = R1*5*4 ++ vpaddq $R1,$S1,$S1 ++ vpsllq \$2,$S1,$S1 ++ ++ vmovq 0($ctx),%x#$H0 # load current hash value ++ vmovq 8($ctx),%x#$H1 ++ vmovq 16($ctx),%x#$H2 ++ ++ test \$3,$len # is length 4*n+2? ++ jnz .Ldone_init_vpmadd52_2x ++ ++ vmovdqu64 $R0,64($ctx) # save key powers ++ vpbroadcastq %x#$R0,$R0 # broadcast 4th power ++ vmovdqu64 $R1,96($ctx) ++ vpbroadcastq %x#$R1,$R1 ++ vmovdqu64 $R2,128($ctx) ++ vpbroadcastq %x#$R2,$R2 ++ vmovdqu64 $S1,160($ctx) ++ vpbroadcastq %x#$S1,$S1 ++ ++ jmp .Lblocks_vpmadd52_4x_key_loaded ++ ud2 ++ ++.align 32 ++.Ldone_init_vpmadd52_2x: ++ vmovdqu64 $R0,64($ctx) # save key powers ++ vpsrldq \$8,$R0,$R0 # 0-1-0-2 ++ vmovdqu64 $R1,96($ctx) ++ vpsrldq \$8,$R1,$R1 ++ vmovdqu64 $R2,128($ctx) ++ vpsrldq \$8,$R2,$R2 ++ vmovdqu64 $S1,160($ctx) ++ vpsrldq \$8,$S1,$S1 ++ jmp .Lblocks_vpmadd52_2x_key_loaded ++ ud2 ++ ++.align 32 ++.Lblocks_vpmadd52_2x_do: ++ vmovdqu64 128+8($ctx),${R2}{%k1}{z}# load 2nd and 1st key powers ++ vmovdqu64 160+8($ctx),${S1}{%k1}{z} ++ vmovdqu64 64+8($ctx),${R0}{%k1}{z} ++ vmovdqu64 96+8($ctx),${R1}{%k1}{z} ++ ++.Lblocks_vpmadd52_2x_key_loaded: ++ vmovdqu64 16*0($inp),$T2 # load data ++ vpxorq $T3,$T3,$T3 ++ lea 16*2($inp),$inp ++ ++ vpunpcklqdq $T3,$T2,$T1 # transpose data ++ vpunpckhqdq $T3,$T2,$T3 ++ ++ # at this point 64-bit lanes are ordered as x-1-x-0 ++ ++ vpsrlq \$24,$T3,$T2 # splat the data ++ vporq $PAD,$T2,$T2 ++ vpaddq $T2,$H2,$H2 # accumulate input ++ vpandq $mask44,$T1,$T0 ++ vpsrlq \$44,$T1,$T1 ++ vpsllq \$20,$T3,$T3 ++ vporq $T3,$T1,$T1 ++ vpandq $mask44,$T1,$T1 ++ ++ jmp .Ltail_vpmadd52_2x ++ ud2 ++ ++.align 32 ++.Loop_vpmadd52_4x: ++ #vpaddq $T2,$H2,$H2 # accumulate input ++ vpaddq $T0,$H0,$H0 ++ vpaddq $T1,$H1,$H1 ++ ++ vpxorq $D0lo,$D0lo,$D0lo ++ vpmadd52luq $H2,$S1,$D0lo ++ vpxorq $D0hi,$D0hi,$D0hi ++ vpmadd52huq $H2,$S1,$D0hi ++ vpxorq $D1lo,$D1lo,$D1lo ++ vpmadd52luq $H2,$S2,$D1lo ++ vpxorq $D1hi,$D1hi,$D1hi ++ vpmadd52huq $H2,$S2,$D1hi ++ vpxorq $D2lo,$D2lo,$D2lo ++ vpmadd52luq $H2,$R0,$D2lo ++ vpxorq $D2hi,$D2hi,$D2hi ++ vpmadd52huq $H2,$R0,$D2hi ++ ++ vmovdqu64 16*0($inp),$T2 # load data ++ vmovdqu64 16*2($inp),$T3 ++ lea 16*4($inp),$inp ++ vpmadd52luq $H0,$R0,$D0lo ++ vpmadd52huq $H0,$R0,$D0hi ++ vpmadd52luq $H0,$R1,$D1lo ++ vpmadd52huq $H0,$R1,$D1hi ++ vpmadd52luq $H0,$R2,$D2lo ++ vpmadd52huq $H0,$R2,$D2hi ++ ++ vpunpcklqdq $T3,$T2,$T1 # transpose data ++ vpunpckhqdq $T3,$T2,$T3 ++ vpmadd52luq $H1,$S2,$D0lo ++ vpmadd52huq $H1,$S2,$D0hi ++ vpmadd52luq $H1,$R0,$D1lo ++ vpmadd52huq $H1,$R0,$D1hi ++ vpmadd52luq $H1,$R1,$D2lo ++ vpmadd52huq $H1,$R1,$D2hi ++ ++ ################################################################ ++ # partial reduction (interleaved with data splat) ++ vpsrlq \$44,$D0lo,$tmp ++ vpsllq \$8,$D0hi,$D0hi ++ vpandq $mask44,$D0lo,$H0 ++ vpaddq $tmp,$D0hi,$D0hi ++ ++ vpsrlq \$24,$T3,$T2 ++ vporq $PAD,$T2,$T2 ++ vpaddq $D0hi,$D1lo,$D1lo ++ ++ vpsrlq \$44,$D1lo,$tmp ++ vpsllq \$8,$D1hi,$D1hi ++ vpandq $mask44,$D1lo,$H1 ++ vpaddq $tmp,$D1hi,$D1hi ++ ++ vpandq $mask44,$T1,$T0 ++ vpsrlq \$44,$T1,$T1 ++ vpsllq \$20,$T3,$T3 ++ vpaddq $D1hi,$D2lo,$D2lo ++ ++ vpsrlq \$42,$D2lo,$tmp ++ vpsllq \$10,$D2hi,$D2hi ++ vpandq $mask42,$D2lo,$H2 ++ vpaddq $tmp,$D2hi,$D2hi ++ ++ vpaddq $T2,$H2,$H2 # accumulate input ++ vpaddq $D2hi,$H0,$H0 ++ vpsllq \$2,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ vporq $T3,$T1,$T1 ++ vpandq $mask44,$T1,$T1 ++ ++ vpsrlq \$44,$H0,$tmp # additional step ++ vpandq $mask44,$H0,$H0 ++ ++ vpaddq $tmp,$H1,$H1 ++ ++ sub \$4,$len # len-=64 ++ jnz .Loop_vpmadd52_4x ++ ++.Ltail_vpmadd52_4x: ++ vmovdqu64 128($ctx),$R2 # load all key powers ++ vmovdqu64 160($ctx),$S1 ++ vmovdqu64 64($ctx),$R0 ++ vmovdqu64 96($ctx),$R1 ++ ++.Ltail_vpmadd52_2x: ++ vpsllq \$2,$R2,$S2 # S2 = R2*5*4 ++ vpaddq $R2,$S2,$S2 ++ vpsllq \$2,$S2,$S2 ++ ++ #vpaddq $T2,$H2,$H2 # accumulate input ++ vpaddq $T0,$H0,$H0 ++ vpaddq $T1,$H1,$H1 ++ ++ vpxorq $D0lo,$D0lo,$D0lo ++ vpmadd52luq $H2,$S1,$D0lo ++ vpxorq $D0hi,$D0hi,$D0hi ++ vpmadd52huq $H2,$S1,$D0hi ++ vpxorq $D1lo,$D1lo,$D1lo ++ vpmadd52luq $H2,$S2,$D1lo ++ vpxorq $D1hi,$D1hi,$D1hi ++ vpmadd52huq $H2,$S2,$D1hi ++ vpxorq $D2lo,$D2lo,$D2lo ++ vpmadd52luq $H2,$R0,$D2lo ++ vpxorq $D2hi,$D2hi,$D2hi ++ vpmadd52huq $H2,$R0,$D2hi ++ ++ vpmadd52luq $H0,$R0,$D0lo ++ vpmadd52huq $H0,$R0,$D0hi ++ vpmadd52luq $H0,$R1,$D1lo ++ vpmadd52huq $H0,$R1,$D1hi ++ vpmadd52luq $H0,$R2,$D2lo ++ vpmadd52huq $H0,$R2,$D2hi ++ ++ vpmadd52luq $H1,$S2,$D0lo ++ vpmadd52huq $H1,$S2,$D0hi ++ vpmadd52luq $H1,$R0,$D1lo ++ vpmadd52huq $H1,$R0,$D1hi ++ vpmadd52luq $H1,$R1,$D2lo ++ vpmadd52huq $H1,$R1,$D2hi ++ ++ ################################################################ ++ # horizontal addition ++ ++ mov \$1,%eax ++ kmovw %eax,%k1 ++ vpsrldq \$8,$D0lo,$T0 ++ vpsrldq \$8,$D0hi,$H0 ++ vpsrldq \$8,$D1lo,$T1 ++ vpsrldq \$8,$D1hi,$H1 ++ vpaddq $T0,$D0lo,$D0lo ++ vpaddq $H0,$D0hi,$D0hi ++ vpsrldq \$8,$D2lo,$T2 ++ vpsrldq \$8,$D2hi,$H2 ++ vpaddq $T1,$D1lo,$D1lo ++ vpaddq $H1,$D1hi,$D1hi ++ vpermq \$0x2,$D0lo,$T0 ++ vpermq \$0x2,$D0hi,$H0 ++ vpaddq $T2,$D2lo,$D2lo ++ vpaddq $H2,$D2hi,$D2hi ++ ++ vpermq \$0x2,$D1lo,$T1 ++ vpermq \$0x2,$D1hi,$H1 ++ vpaddq $T0,$D0lo,${D0lo}{%k1}{z} ++ vpaddq $H0,$D0hi,${D0hi}{%k1}{z} ++ vpermq \$0x2,$D2lo,$T2 ++ vpermq \$0x2,$D2hi,$H2 ++ vpaddq $T1,$D1lo,${D1lo}{%k1}{z} ++ vpaddq $H1,$D1hi,${D1hi}{%k1}{z} ++ vpaddq $T2,$D2lo,${D2lo}{%k1}{z} ++ vpaddq $H2,$D2hi,${D2hi}{%k1}{z} ++ ++ ################################################################ ++ # partial reduction ++ vpsrlq \$44,$D0lo,$tmp ++ vpsllq \$8,$D0hi,$D0hi ++ vpandq $mask44,$D0lo,$H0 ++ vpaddq $tmp,$D0hi,$D0hi ++ ++ vpaddq $D0hi,$D1lo,$D1lo ++ ++ vpsrlq \$44,$D1lo,$tmp ++ vpsllq \$8,$D1hi,$D1hi ++ vpandq $mask44,$D1lo,$H1 ++ vpaddq $tmp,$D1hi,$D1hi ++ ++ vpaddq $D1hi,$D2lo,$D2lo ++ ++ vpsrlq \$42,$D2lo,$tmp ++ vpsllq \$10,$D2hi,$D2hi ++ vpandq $mask42,$D2lo,$H2 ++ vpaddq $tmp,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ vpsllq \$2,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ ++ vpsrlq \$44,$H0,$tmp # additional step ++ vpandq $mask44,$H0,$H0 ++ ++ vpaddq $tmp,$H1,$H1 ++ # at this point $len is ++ # either 4*n+2 or 0... ++ sub \$2,$len # len-=32 ++ ja .Lblocks_vpmadd52_4x_do ++ ++ vmovq %x#$H0,0($ctx) ++ vmovq %x#$H1,8($ctx) ++ vmovq %x#$H2,16($ctx) ++ vzeroall ++ ++.Lno_data_vpmadd52_4x: ++ ret ++.size poly1305_blocks_vpmadd52_4x,.-poly1305_blocks_vpmadd52_4x ++___ ++} ++{ ++######################################################################## ++# As implied by its name 8x subroutine processes 8 blocks in parallel... ++# This is intermediate version, as it's used only in cases when input ++# length is either 8*n, 8*n+1 or 8*n+2... ++ ++my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17)); ++my ($D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi) = map("%ymm$_",(18..23)); ++my ($T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD) = map("%ymm$_",(24..31)); ++my ($RR0,$RR1,$RR2,$SS1,$SS2) = map("%ymm$_",(6..10)); ++ ++$code.=<<___; ++.type poly1305_blocks_vpmadd52_8x,\@function,4 ++.align 32 ++poly1305_blocks_vpmadd52_8x: ++ shr \$4,$len ++ jz .Lno_data_vpmadd52_8x # too short ++ ++ shl \$40,$padbit ++ mov 64($ctx),%r8 # peek on power of the key ++ ++ vmovdqa64 .Lx_mask44(%rip),$mask44 ++ vmovdqa64 .Lx_mask42(%rip),$mask42 ++ ++ test %r8,%r8 # is power value impossible? ++ js .Linit_vpmadd52 # if it is, then init R[4] ++ ++ vmovq 0($ctx),%x#$H0 # load current hash value ++ vmovq 8($ctx),%x#$H1 ++ vmovq 16($ctx),%x#$H2 ++ ++.Lblocks_vpmadd52_8x: ++ ################################################################ ++ # fist we calculate more key powers ++ ++ vmovdqu64 128($ctx),$R2 # load 1-3-2-4 powers ++ vmovdqu64 160($ctx),$S1 ++ vmovdqu64 64($ctx),$R0 ++ vmovdqu64 96($ctx),$R1 ++ ++ vpsllq \$2,$R2,$S2 # S2 = R2*5*4 ++ vpaddq $R2,$S2,$S2 ++ vpsllq \$2,$S2,$S2 ++ ++ vpbroadcastq %x#$R2,$RR2 # broadcast 4th power ++ vpbroadcastq %x#$R0,$RR0 ++ vpbroadcastq %x#$R1,$RR1 ++ ++ vpxorq $D0lo,$D0lo,$D0lo ++ vpmadd52luq $RR2,$S1,$D0lo ++ vpxorq $D0hi,$D0hi,$D0hi ++ vpmadd52huq $RR2,$S1,$D0hi ++ vpxorq $D1lo,$D1lo,$D1lo ++ vpmadd52luq $RR2,$S2,$D1lo ++ vpxorq $D1hi,$D1hi,$D1hi ++ vpmadd52huq $RR2,$S2,$D1hi ++ vpxorq $D2lo,$D2lo,$D2lo ++ vpmadd52luq $RR2,$R0,$D2lo ++ vpxorq $D2hi,$D2hi,$D2hi ++ vpmadd52huq $RR2,$R0,$D2hi ++ ++ vpmadd52luq $RR0,$R0,$D0lo ++ vpmadd52huq $RR0,$R0,$D0hi ++ vpmadd52luq $RR0,$R1,$D1lo ++ vpmadd52huq $RR0,$R1,$D1hi ++ vpmadd52luq $RR0,$R2,$D2lo ++ vpmadd52huq $RR0,$R2,$D2hi ++ ++ vpmadd52luq $RR1,$S2,$D0lo ++ vpmadd52huq $RR1,$S2,$D0hi ++ vpmadd52luq $RR1,$R0,$D1lo ++ vpmadd52huq $RR1,$R0,$D1hi ++ vpmadd52luq $RR1,$R1,$D2lo ++ vpmadd52huq $RR1,$R1,$D2hi ++ ++ ################################################################ ++ # partial reduction ++ vpsrlq \$44,$D0lo,$tmp ++ vpsllq \$8,$D0hi,$D0hi ++ vpandq $mask44,$D0lo,$RR0 ++ vpaddq $tmp,$D0hi,$D0hi ++ ++ vpaddq $D0hi,$D1lo,$D1lo ++ ++ vpsrlq \$44,$D1lo,$tmp ++ vpsllq \$8,$D1hi,$D1hi ++ vpandq $mask44,$D1lo,$RR1 ++ vpaddq $tmp,$D1hi,$D1hi ++ ++ vpaddq $D1hi,$D2lo,$D2lo ++ ++ vpsrlq \$42,$D2lo,$tmp ++ vpsllq \$10,$D2hi,$D2hi ++ vpandq $mask42,$D2lo,$RR2 ++ vpaddq $tmp,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$RR0,$RR0 ++ vpsllq \$2,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$RR0,$RR0 ++ ++ vpsrlq \$44,$RR0,$tmp # additional step ++ vpandq $mask44,$RR0,$RR0 ++ ++ vpaddq $tmp,$RR1,$RR1 ++ ++ ################################################################ ++ # At this point Rx holds 1324 powers, RRx - 5768, and the goal ++ # is 15263748, which reflects how data is loaded... ++ ++ vpunpcklqdq $R2,$RR2,$T2 # 3748 ++ vpunpckhqdq $R2,$RR2,$R2 # 1526 ++ vpunpcklqdq $R0,$RR0,$T0 ++ vpunpckhqdq $R0,$RR0,$R0 ++ vpunpcklqdq $R1,$RR1,$T1 ++ vpunpckhqdq $R1,$RR1,$R1 ++___ ++######## switch to %zmm ++map(s/%y/%z/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2); ++map(s/%y/%z/, $D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi); ++map(s/%y/%z/, $T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD); ++map(s/%y/%z/, $RR0,$RR1,$RR2,$SS1,$SS2); ++ ++$code.=<<___; ++ vshufi64x2 \$0x44,$R2,$T2,$RR2 # 15263748 ++ vshufi64x2 \$0x44,$R0,$T0,$RR0 ++ vshufi64x2 \$0x44,$R1,$T1,$RR1 ++ ++ vmovdqu64 16*0($inp),$T2 # load data ++ vmovdqu64 16*4($inp),$T3 ++ lea 16*8($inp),$inp ++ ++ vpsllq \$2,$RR2,$SS2 # S2 = R2*5*4 ++ vpsllq \$2,$RR1,$SS1 # S1 = R1*5*4 ++ vpaddq $RR2,$SS2,$SS2 ++ vpaddq $RR1,$SS1,$SS1 ++ vpsllq \$2,$SS2,$SS2 ++ vpsllq \$2,$SS1,$SS1 ++ ++ vpbroadcastq $padbit,$PAD ++ vpbroadcastq %x#$mask44,$mask44 ++ vpbroadcastq %x#$mask42,$mask42 ++ ++ vpbroadcastq %x#$SS1,$S1 # broadcast 8th power ++ vpbroadcastq %x#$SS2,$S2 ++ vpbroadcastq %x#$RR0,$R0 ++ vpbroadcastq %x#$RR1,$R1 ++ vpbroadcastq %x#$RR2,$R2 ++ ++ vpunpcklqdq $T3,$T2,$T1 # transpose data ++ vpunpckhqdq $T3,$T2,$T3 ++ ++ # at this point 64-bit lanes are ordered as 73625140 ++ ++ vpsrlq \$24,$T3,$T2 # splat the data ++ vporq $PAD,$T2,$T2 ++ vpaddq $T2,$H2,$H2 # accumulate input ++ vpandq $mask44,$T1,$T0 ++ vpsrlq \$44,$T1,$T1 ++ vpsllq \$20,$T3,$T3 ++ vporq $T3,$T1,$T1 ++ vpandq $mask44,$T1,$T1 ++ ++ sub \$8,$len ++ jz .Ltail_vpmadd52_8x ++ jmp .Loop_vpmadd52_8x ++ ++.align 32 ++.Loop_vpmadd52_8x: ++ #vpaddq $T2,$H2,$H2 # accumulate input ++ vpaddq $T0,$H0,$H0 ++ vpaddq $T1,$H1,$H1 ++ ++ vpxorq $D0lo,$D0lo,$D0lo ++ vpmadd52luq $H2,$S1,$D0lo ++ vpxorq $D0hi,$D0hi,$D0hi ++ vpmadd52huq $H2,$S1,$D0hi ++ vpxorq $D1lo,$D1lo,$D1lo ++ vpmadd52luq $H2,$S2,$D1lo ++ vpxorq $D1hi,$D1hi,$D1hi ++ vpmadd52huq $H2,$S2,$D1hi ++ vpxorq $D2lo,$D2lo,$D2lo ++ vpmadd52luq $H2,$R0,$D2lo ++ vpxorq $D2hi,$D2hi,$D2hi ++ vpmadd52huq $H2,$R0,$D2hi ++ ++ vmovdqu64 16*0($inp),$T2 # load data ++ vmovdqu64 16*4($inp),$T3 ++ lea 16*8($inp),$inp ++ vpmadd52luq $H0,$R0,$D0lo ++ vpmadd52huq $H0,$R0,$D0hi ++ vpmadd52luq $H0,$R1,$D1lo ++ vpmadd52huq $H0,$R1,$D1hi ++ vpmadd52luq $H0,$R2,$D2lo ++ vpmadd52huq $H0,$R2,$D2hi ++ ++ vpunpcklqdq $T3,$T2,$T1 # transpose data ++ vpunpckhqdq $T3,$T2,$T3 ++ vpmadd52luq $H1,$S2,$D0lo ++ vpmadd52huq $H1,$S2,$D0hi ++ vpmadd52luq $H1,$R0,$D1lo ++ vpmadd52huq $H1,$R0,$D1hi ++ vpmadd52luq $H1,$R1,$D2lo ++ vpmadd52huq $H1,$R1,$D2hi ++ ++ ################################################################ ++ # partial reduction (interleaved with data splat) ++ vpsrlq \$44,$D0lo,$tmp ++ vpsllq \$8,$D0hi,$D0hi ++ vpandq $mask44,$D0lo,$H0 ++ vpaddq $tmp,$D0hi,$D0hi ++ ++ vpsrlq \$24,$T3,$T2 ++ vporq $PAD,$T2,$T2 ++ vpaddq $D0hi,$D1lo,$D1lo ++ ++ vpsrlq \$44,$D1lo,$tmp ++ vpsllq \$8,$D1hi,$D1hi ++ vpandq $mask44,$D1lo,$H1 ++ vpaddq $tmp,$D1hi,$D1hi ++ ++ vpandq $mask44,$T1,$T0 ++ vpsrlq \$44,$T1,$T1 ++ vpsllq \$20,$T3,$T3 ++ vpaddq $D1hi,$D2lo,$D2lo ++ ++ vpsrlq \$42,$D2lo,$tmp ++ vpsllq \$10,$D2hi,$D2hi ++ vpandq $mask42,$D2lo,$H2 ++ vpaddq $tmp,$D2hi,$D2hi ++ ++ vpaddq $T2,$H2,$H2 # accumulate input ++ vpaddq $D2hi,$H0,$H0 ++ vpsllq \$2,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ vporq $T3,$T1,$T1 ++ vpandq $mask44,$T1,$T1 ++ ++ vpsrlq \$44,$H0,$tmp # additional step ++ vpandq $mask44,$H0,$H0 ++ ++ vpaddq $tmp,$H1,$H1 ++ ++ sub \$8,$len # len-=128 ++ jnz .Loop_vpmadd52_8x ++ ++.Ltail_vpmadd52_8x: ++ #vpaddq $T2,$H2,$H2 # accumulate input ++ vpaddq $T0,$H0,$H0 ++ vpaddq $T1,$H1,$H1 ++ ++ vpxorq $D0lo,$D0lo,$D0lo ++ vpmadd52luq $H2,$SS1,$D0lo ++ vpxorq $D0hi,$D0hi,$D0hi ++ vpmadd52huq $H2,$SS1,$D0hi ++ vpxorq $D1lo,$D1lo,$D1lo ++ vpmadd52luq $H2,$SS2,$D1lo ++ vpxorq $D1hi,$D1hi,$D1hi ++ vpmadd52huq $H2,$SS2,$D1hi ++ vpxorq $D2lo,$D2lo,$D2lo ++ vpmadd52luq $H2,$RR0,$D2lo ++ vpxorq $D2hi,$D2hi,$D2hi ++ vpmadd52huq $H2,$RR0,$D2hi ++ ++ vpmadd52luq $H0,$RR0,$D0lo ++ vpmadd52huq $H0,$RR0,$D0hi ++ vpmadd52luq $H0,$RR1,$D1lo ++ vpmadd52huq $H0,$RR1,$D1hi ++ vpmadd52luq $H0,$RR2,$D2lo ++ vpmadd52huq $H0,$RR2,$D2hi ++ ++ vpmadd52luq $H1,$SS2,$D0lo ++ vpmadd52huq $H1,$SS2,$D0hi ++ vpmadd52luq $H1,$RR0,$D1lo ++ vpmadd52huq $H1,$RR0,$D1hi ++ vpmadd52luq $H1,$RR1,$D2lo ++ vpmadd52huq $H1,$RR1,$D2hi ++ ++ ################################################################ ++ # horizontal addition ++ ++ mov \$1,%eax ++ kmovw %eax,%k1 ++ vpsrldq \$8,$D0lo,$T0 ++ vpsrldq \$8,$D0hi,$H0 ++ vpsrldq \$8,$D1lo,$T1 ++ vpsrldq \$8,$D1hi,$H1 ++ vpaddq $T0,$D0lo,$D0lo ++ vpaddq $H0,$D0hi,$D0hi ++ vpsrldq \$8,$D2lo,$T2 ++ vpsrldq \$8,$D2hi,$H2 ++ vpaddq $T1,$D1lo,$D1lo ++ vpaddq $H1,$D1hi,$D1hi ++ vpermq \$0x2,$D0lo,$T0 ++ vpermq \$0x2,$D0hi,$H0 ++ vpaddq $T2,$D2lo,$D2lo ++ vpaddq $H2,$D2hi,$D2hi ++ ++ vpermq \$0x2,$D1lo,$T1 ++ vpermq \$0x2,$D1hi,$H1 ++ vpaddq $T0,$D0lo,$D0lo ++ vpaddq $H0,$D0hi,$D0hi ++ vpermq \$0x2,$D2lo,$T2 ++ vpermq \$0x2,$D2hi,$H2 ++ vpaddq $T1,$D1lo,$D1lo ++ vpaddq $H1,$D1hi,$D1hi ++ vextracti64x4 \$1,$D0lo,%y#$T0 ++ vextracti64x4 \$1,$D0hi,%y#$H0 ++ vpaddq $T2,$D2lo,$D2lo ++ vpaddq $H2,$D2hi,$D2hi ++ ++ vextracti64x4 \$1,$D1lo,%y#$T1 ++ vextracti64x4 \$1,$D1hi,%y#$H1 ++ vextracti64x4 \$1,$D2lo,%y#$T2 ++ vextracti64x4 \$1,$D2hi,%y#$H2 ++___ ++######## switch back to %ymm ++map(s/%z/%y/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2); ++map(s/%z/%y/, $D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi); ++map(s/%z/%y/, $T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD); ++ ++$code.=<<___; ++ vpaddq $T0,$D0lo,${D0lo}{%k1}{z} ++ vpaddq $H0,$D0hi,${D0hi}{%k1}{z} ++ vpaddq $T1,$D1lo,${D1lo}{%k1}{z} ++ vpaddq $H1,$D1hi,${D1hi}{%k1}{z} ++ vpaddq $T2,$D2lo,${D2lo}{%k1}{z} ++ vpaddq $H2,$D2hi,${D2hi}{%k1}{z} ++ ++ ################################################################ ++ # partial reduction ++ vpsrlq \$44,$D0lo,$tmp ++ vpsllq \$8,$D0hi,$D0hi ++ vpandq $mask44,$D0lo,$H0 ++ vpaddq $tmp,$D0hi,$D0hi ++ ++ vpaddq $D0hi,$D1lo,$D1lo ++ ++ vpsrlq \$44,$D1lo,$tmp ++ vpsllq \$8,$D1hi,$D1hi ++ vpandq $mask44,$D1lo,$H1 ++ vpaddq $tmp,$D1hi,$D1hi ++ ++ vpaddq $D1hi,$D2lo,$D2lo ++ ++ vpsrlq \$42,$D2lo,$tmp ++ vpsllq \$10,$D2hi,$D2hi ++ vpandq $mask42,$D2lo,$H2 ++ vpaddq $tmp,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ vpsllq \$2,$D2hi,$D2hi ++ ++ vpaddq $D2hi,$H0,$H0 ++ ++ vpsrlq \$44,$H0,$tmp # additional step ++ vpandq $mask44,$H0,$H0 ++ ++ vpaddq $tmp,$H1,$H1 ++ ++ ################################################################ ++ ++ vmovq %x#$H0,0($ctx) ++ vmovq %x#$H1,8($ctx) ++ vmovq %x#$H2,16($ctx) ++ vzeroall ++ ++.Lno_data_vpmadd52_8x: ++ ret ++.size poly1305_blocks_vpmadd52_8x,.-poly1305_blocks_vpmadd52_8x ++___ ++} ++$code.=<<___; ++.type poly1305_emit_base2_44,\@function,3 ++.align 32 ++poly1305_emit_base2_44: ++ mov 0($ctx),%r8 # load hash value ++ mov 8($ctx),%r9 ++ mov 16($ctx),%r10 ++ ++ mov %r9,%rax ++ shr \$20,%r9 ++ shl \$44,%rax ++ mov %r10,%rcx ++ shr \$40,%r10 ++ shl \$24,%rcx ++ ++ add %rax,%r8 ++ adc %rcx,%r9 ++ adc \$0,%r10 ++ ++ mov %r8,%rax ++ add \$5,%r8 # compare to modulus ++ mov %r9,%rcx ++ adc \$0,%r9 ++ adc \$0,%r10 ++ shr \$2,%r10 # did 130-bit value overflow? ++ cmovnz %r8,%rax ++ cmovnz %r9,%rcx ++ ++ add 0($nonce),%rax # accumulate nonce ++ adc 8($nonce),%rcx ++ mov %rax,0($mac) # write result ++ mov %rcx,8($mac) ++ ++ ret ++.size poly1305_emit_base2_44,.-poly1305_emit_base2_44 ++___ ++} } } ++$code.=<<___; ++.align 64 ++.Lconst: ++.Lmask24: ++.long 0x0ffffff,0,0x0ffffff,0,0x0ffffff,0,0x0ffffff,0 ++.L129: ++.long `1<<24`,0,`1<<24`,0,`1<<24`,0,`1<<24`,0 ++.Lmask26: ++.long 0x3ffffff,0,0x3ffffff,0,0x3ffffff,0,0x3ffffff,0 ++.Lpermd_avx2: ++.long 2,2,2,3,2,0,2,1 ++.Lpermd_avx512: ++.long 0,0,0,1, 0,2,0,3, 0,4,0,5, 0,6,0,7 ++ ++.L2_44_inp_permd: ++.long 0,1,1,2,2,3,7,7 ++.L2_44_inp_shift: ++.quad 0,12,24,64 ++.L2_44_mask: ++.quad 0xfffffffffff,0xfffffffffff,0x3ffffffffff,0xffffffffffffffff ++.L2_44_shift_rgt: ++.quad 44,44,42,64 ++.L2_44_shift_lft: ++.quad 8,8,10,64 ++ ++.align 64 ++.Lx_mask44: ++.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff ++.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff ++.Lx_mask42: ++.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff ++.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff ++___ ++} ++$code.=<<___; ++.asciz "Poly1305 for x86_64, CRYPTOGAMS by " ++.align 16 ++___ ++ ++{ # chacha20-poly1305 helpers ++my ($out,$inp,$otp,$len)=$win64 ? ("%rcx","%rdx","%r8", "%r9") : # Win64 order ++ ("%rdi","%rsi","%rdx","%rcx"); # Unix order ++$code.=<<___; ++.globl xor128_encrypt_n_pad ++.type xor128_encrypt_n_pad,\@abi-omnipotent ++.align 16 ++xor128_encrypt_n_pad: ++ sub $otp,$inp ++ sub $otp,$out ++ mov $len,%r10 # put len aside ++ shr \$4,$len # len / 16 ++ jz .Ltail_enc ++ nop ++.Loop_enc_xmm: ++ movdqu ($inp,$otp),%xmm0 ++ pxor ($otp),%xmm0 ++ movdqu %xmm0,($out,$otp) ++ movdqa %xmm0,($otp) ++ lea 16($otp),$otp ++ dec $len ++ jnz .Loop_enc_xmm ++ ++ and \$15,%r10 # len % 16 ++ jz .Ldone_enc ++ ++.Ltail_enc: ++ mov \$16,$len ++ sub %r10,$len ++ xor %eax,%eax ++.Loop_enc_byte: ++ mov ($inp,$otp),%al ++ xor ($otp),%al ++ mov %al,($out,$otp) ++ mov %al,($otp) ++ lea 1($otp),$otp ++ dec %r10 ++ jnz .Loop_enc_byte ++ ++ xor %eax,%eax ++.Loop_enc_pad: ++ mov %al,($otp) ++ lea 1($otp),$otp ++ dec $len ++ jnz .Loop_enc_pad ++ ++.Ldone_enc: ++ mov $otp,%rax ++ ret ++.size xor128_encrypt_n_pad,.-xor128_encrypt_n_pad ++ ++.globl xor128_decrypt_n_pad ++.type xor128_decrypt_n_pad,\@abi-omnipotent ++.align 16 ++xor128_decrypt_n_pad: ++ sub $otp,$inp ++ sub $otp,$out ++ mov $len,%r10 # put len aside ++ shr \$4,$len # len / 16 ++ jz .Ltail_dec ++ nop ++.Loop_dec_xmm: ++ movdqu ($inp,$otp),%xmm0 ++ movdqa ($otp),%xmm1 ++ pxor %xmm0,%xmm1 ++ movdqu %xmm1,($out,$otp) ++ movdqa %xmm0,($otp) ++ lea 16($otp),$otp ++ dec $len ++ jnz .Loop_dec_xmm ++ ++ pxor %xmm1,%xmm1 ++ and \$15,%r10 # len % 16 ++ jz .Ldone_dec ++ ++.Ltail_dec: ++ mov \$16,$len ++ sub %r10,$len ++ xor %eax,%eax ++ xor %r11,%r11 ++.Loop_dec_byte: ++ mov ($inp,$otp),%r11b ++ mov ($otp),%al ++ xor %r11b,%al ++ mov %al,($out,$otp) ++ mov %r11b,($otp) ++ lea 1($otp),$otp ++ dec %r10 ++ jnz .Loop_dec_byte ++ ++ xor %eax,%eax ++.Loop_dec_pad: ++ mov %al,($otp) ++ lea 1($otp),$otp ++ dec $len ++ jnz .Loop_dec_pad ++ ++.Ldone_dec: ++ mov $otp,%rax ++ ret ++.size xor128_decrypt_n_pad,.-xor128_decrypt_n_pad ++___ ++} ++ ++# EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame, ++# CONTEXT *context,DISPATCHER_CONTEXT *disp) ++if ($win64) { ++$rec="%rcx"; ++$frame="%rdx"; ++$context="%r8"; ++$disp="%r9"; ++ ++$code.=<<___; ++.extern __imp_RtlVirtualUnwind ++.type se_handler,\@abi-omnipotent ++.align 16 ++se_handler: ++ push %rsi ++ push %rdi ++ push %rbx ++ push %rbp ++ push %r12 ++ push %r13 ++ push %r14 ++ push %r15 ++ pushfq ++ sub \$64,%rsp ++ ++ mov 120($context),%rax # pull context->Rax ++ mov 248($context),%rbx # pull context->Rip ++ ++ mov 8($disp),%rsi # disp->ImageBase ++ mov 56($disp),%r11 # disp->HandlerData ++ ++ mov 0(%r11),%r10d # HandlerData[0] ++ lea (%rsi,%r10),%r10 # prologue label ++ cmp %r10,%rbx # context->Rip<.Lprologue ++ jb .Lcommon_seh_tail ++ ++ mov 152($context),%rax # pull context->Rsp ++ ++ mov 4(%r11),%r10d # HandlerData[1] ++ lea (%rsi,%r10),%r10 # epilogue label ++ cmp %r10,%rbx # context->Rip>=.Lepilogue ++ jae .Lcommon_seh_tail ++ ++ lea 48(%rax),%rax ++ ++ mov -8(%rax),%rbx ++ mov -16(%rax),%rbp ++ mov -24(%rax),%r12 ++ mov -32(%rax),%r13 ++ mov -40(%rax),%r14 ++ mov -48(%rax),%r15 ++ mov %rbx,144($context) # restore context->Rbx ++ mov %rbp,160($context) # restore context->Rbp ++ mov %r12,216($context) # restore context->R12 ++ mov %r13,224($context) # restore context->R13 ++ mov %r14,232($context) # restore context->R14 ++ mov %r15,240($context) # restore context->R14 ++ ++ jmp .Lcommon_seh_tail ++.size se_handler,.-se_handler ++ ++.type avx_handler,\@abi-omnipotent ++.align 16 ++avx_handler: ++ push %rsi ++ push %rdi ++ push %rbx ++ push %rbp ++ push %r12 ++ push %r13 ++ push %r14 ++ push %r15 ++ pushfq ++ sub \$64,%rsp ++ ++ mov 120($context),%rax # pull context->Rax ++ mov 248($context),%rbx # pull context->Rip ++ ++ mov 8($disp),%rsi # disp->ImageBase ++ mov 56($disp),%r11 # disp->HandlerData ++ ++ mov 0(%r11),%r10d # HandlerData[0] ++ lea (%rsi,%r10),%r10 # prologue label ++ cmp %r10,%rbx # context->RipRsp ++ ++ mov 4(%r11),%r10d # HandlerData[1] ++ lea (%rsi,%r10),%r10 # epilogue label ++ cmp %r10,%rbx # context->Rip>=epilogue label ++ jae .Lcommon_seh_tail ++ ++ mov 208($context),%rax # pull context->R11 ++ ++ lea 0x50(%rax),%rsi ++ lea 0xf8(%rax),%rax ++ lea 512($context),%rdi # &context.Xmm6 ++ mov \$20,%ecx ++ .long 0xa548f3fc # cld; rep movsq ++ ++.Lcommon_seh_tail: ++ mov 8(%rax),%rdi ++ mov 16(%rax),%rsi ++ mov %rax,152($context) # restore context->Rsp ++ mov %rsi,168($context) # restore context->Rsi ++ mov %rdi,176($context) # restore context->Rdi ++ ++ mov 40($disp),%rdi # disp->ContextRecord ++ mov $context,%rsi # context ++ mov \$154,%ecx # sizeof(CONTEXT) ++ .long 0xa548f3fc # cld; rep movsq ++ ++ mov $disp,%rsi ++ xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER ++ mov 8(%rsi),%rdx # arg2, disp->ImageBase ++ mov 0(%rsi),%r8 # arg3, disp->ControlPc ++ mov 16(%rsi),%r9 # arg4, disp->FunctionEntry ++ mov 40(%rsi),%r10 # disp->ContextRecord ++ lea 56(%rsi),%r11 # &disp->HandlerData ++ lea 24(%rsi),%r12 # &disp->EstablisherFrame ++ mov %r10,32(%rsp) # arg5 ++ mov %r11,40(%rsp) # arg6 ++ mov %r12,48(%rsp) # arg7 ++ mov %rcx,56(%rsp) # arg8, (NULL) ++ call *__imp_RtlVirtualUnwind(%rip) ++ ++ mov \$1,%eax # ExceptionContinueSearch ++ add \$64,%rsp ++ popfq ++ pop %r15 ++ pop %r14 ++ pop %r13 ++ pop %r12 ++ pop %rbp ++ pop %rbx ++ pop %rdi ++ pop %rsi ++ ret ++.size avx_handler,.-avx_handler ++ ++.section .pdata ++.align 4 ++ .rva .LSEH_begin_poly1305_init ++ .rva .LSEH_end_poly1305_init ++ .rva .LSEH_info_poly1305_init ++ ++ .rva .LSEH_begin_poly1305_blocks ++ .rva .LSEH_end_poly1305_blocks ++ .rva .LSEH_info_poly1305_blocks ++ ++ .rva .LSEH_begin_poly1305_emit ++ .rva .LSEH_end_poly1305_emit ++ .rva .LSEH_info_poly1305_emit ++___ ++$code.=<<___ if ($avx); ++ .rva .LSEH_begin_poly1305_blocks_avx ++ .rva .Lbase2_64_avx ++ .rva .LSEH_info_poly1305_blocks_avx_1 ++ ++ .rva .Lbase2_64_avx ++ .rva .Leven_avx ++ .rva .LSEH_info_poly1305_blocks_avx_2 ++ ++ .rva .Leven_avx ++ .rva .LSEH_end_poly1305_blocks_avx ++ .rva .LSEH_info_poly1305_blocks_avx_3 ++ ++ .rva .LSEH_begin_poly1305_emit_avx ++ .rva .LSEH_end_poly1305_emit_avx ++ .rva .LSEH_info_poly1305_emit_avx ++___ ++$code.=<<___ if ($avx>1); ++ .rva .LSEH_begin_poly1305_blocks_avx2 ++ .rva .Lbase2_64_avx2 ++ .rva .LSEH_info_poly1305_blocks_avx2_1 ++ ++ .rva .Lbase2_64_avx2 ++ .rva .Leven_avx2 ++ .rva .LSEH_info_poly1305_blocks_avx2_2 ++ ++ .rva .Leven_avx2 ++ .rva .LSEH_end_poly1305_blocks_avx2 ++ .rva .LSEH_info_poly1305_blocks_avx2_3 ++___ ++$code.=<<___ if ($avx>2); ++ .rva .LSEH_begin_poly1305_blocks_avx512 ++ .rva .LSEH_end_poly1305_blocks_avx512 ++ .rva .LSEH_info_poly1305_blocks_avx512 ++___ ++$code.=<<___; ++.section .xdata ++.align 8 ++.LSEH_info_poly1305_init: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .LSEH_begin_poly1305_init,.LSEH_begin_poly1305_init ++ ++.LSEH_info_poly1305_blocks: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .Lblocks_body,.Lblocks_epilogue ++ ++.LSEH_info_poly1305_emit: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .LSEH_begin_poly1305_emit,.LSEH_begin_poly1305_emit ++___ ++$code.=<<___ if ($avx); ++.LSEH_info_poly1305_blocks_avx_1: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .Lblocks_avx_body,.Lblocks_avx_epilogue # HandlerData[] ++ ++.LSEH_info_poly1305_blocks_avx_2: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .Lbase2_64_avx_body,.Lbase2_64_avx_epilogue # HandlerData[] ++ ++.LSEH_info_poly1305_blocks_avx_3: ++ .byte 9,0,0,0 ++ .rva avx_handler ++ .rva .Ldo_avx_body,.Ldo_avx_epilogue # HandlerData[] ++ ++.LSEH_info_poly1305_emit_avx: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .LSEH_begin_poly1305_emit_avx,.LSEH_begin_poly1305_emit_avx ++___ ++$code.=<<___ if ($avx>1); ++.LSEH_info_poly1305_blocks_avx2_1: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .Lblocks_avx2_body,.Lblocks_avx2_epilogue # HandlerData[] ++ ++.LSEH_info_poly1305_blocks_avx2_2: ++ .byte 9,0,0,0 ++ .rva se_handler ++ .rva .Lbase2_64_avx2_body,.Lbase2_64_avx2_epilogue # HandlerData[] ++ ++.LSEH_info_poly1305_blocks_avx2_3: ++ .byte 9,0,0,0 ++ .rva avx_handler ++ .rva .Ldo_avx2_body,.Ldo_avx2_epilogue # HandlerData[] ++___ ++$code.=<<___ if ($avx>2); ++.LSEH_info_poly1305_blocks_avx512: ++ .byte 9,0,0,0 ++ .rva avx_handler ++ .rva .Ldo_avx512_body,.Ldo_avx512_epilogue # HandlerData[] ++___ ++} ++ ++foreach (split('\n',$code)) { ++ s/\`([^\`]*)\`/eval($1)/ge; ++ s/%r([a-z]+)#d/%e$1/g; ++ s/%r([0-9]+)#d/%r$1d/g; ++ s/%x#%[yz]/%x/g or s/%y#%z/%y/g or s/%z#%[yz]/%z/g; ++ ++ print $_,"\n"; ++} ++close STDOUT; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0043-crypto-x86-poly1305-wire-up-faster-implementations-f.patch b/target/linux/generic/backport-5.4/080-wireguard-0043-crypto-x86-poly1305-wire-up-faster-implementations-f.patch new file mode 100644 index 0000000000..307c9b6ef3 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0043-crypto-x86-poly1305-wire-up-faster-implementations-f.patch @@ -0,0 +1,2927 @@ +From a81b2f8bd42fe51705d7102e9d9a2a40c2a9d624 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 5 Jan 2020 22:40:48 -0500 +Subject: [PATCH 043/124] crypto: x86/poly1305 - wire up faster implementations + for kernel + +commit d7d7b853566254648df59f7ea27ea05952a6cfa8 upstream. + +These x86_64 vectorized implementations support AVX, AVX-2, and AVX512F. +The AVX-512F implementation is disabled on Skylake, due to throttling, +but it is quite fast on >= Cannonlake. + +On the left is cycle counts on a Core i7 6700HQ using the AVX-2 +codepath, comparing this implementation ("new") to the implementation in +the current crypto api ("old"). On the right are benchmarks on a Xeon +Gold 5120 using the AVX-512 codepath. The new implementation is faster +on all benchmarks. + + AVX-2 AVX-512 + --------- ----------- + + size old new size old new + ---- ---- ---- ---- ---- ---- + 0 70 68 0 74 70 + 16 92 90 16 96 92 + 32 134 104 32 136 106 + 48 172 120 48 184 124 + 64 218 136 64 218 138 + 80 254 158 80 260 160 + 96 298 174 96 300 176 + 112 342 192 112 342 194 + 128 388 212 128 384 212 + 144 428 228 144 420 226 + 160 466 246 160 464 248 + 176 510 264 176 504 264 + 192 550 282 192 544 282 + 208 594 302 208 582 300 + 224 628 316 224 624 318 + 240 676 334 240 662 338 + 256 716 354 256 708 358 + 272 764 374 272 748 372 + 288 802 352 288 788 358 + 304 420 366 304 422 370 + 320 428 360 320 432 364 + 336 484 378 336 486 380 + 352 426 384 352 434 390 + 368 478 400 368 480 408 + 384 488 394 384 490 398 + 400 542 408 400 542 412 + 416 486 416 416 492 426 + 432 534 430 432 538 436 + 448 544 422 448 546 432 + 464 600 438 464 600 448 + 480 540 448 480 548 456 + 496 594 464 496 594 476 + 512 602 456 512 606 470 + 528 656 476 528 656 480 + 544 600 480 544 606 498 + 560 650 494 560 652 512 + 576 664 490 576 662 508 + 592 714 508 592 716 522 + 608 656 514 608 664 538 + 624 708 532 624 710 552 + 640 716 524 640 720 516 + 656 770 536 656 772 526 + 672 716 548 672 722 544 + 688 770 562 688 768 556 + 704 774 552 704 778 556 + 720 826 568 720 832 568 + 736 768 574 736 780 584 + 752 822 592 752 826 600 + 768 830 584 768 836 560 + 784 884 602 784 888 572 + 800 828 610 800 838 588 + 816 884 628 816 884 604 + 832 888 618 832 894 598 + 848 942 632 848 946 612 + 864 884 644 864 896 628 + 880 936 660 880 942 644 + 896 948 652 896 952 608 + 912 1000 664 912 1004 616 + 928 942 676 928 954 634 + 944 994 690 944 1000 646 + 960 1002 680 960 1008 646 + 976 1054 694 976 1062 658 + 992 1002 706 992 1012 674 + 1008 1052 720 1008 1058 690 + +This commit wires in the prior implementation from Andy, and makes the +following changes to be suitable for kernel land. + + - Some cosmetic and structural changes, like renaming labels to + .Lname, constants, and other Linux conventions, as well as making + the code easy for us to maintain moving forward. + + - CPU feature checking is done in C by the glue code. + + - We avoid jumping into the middle of functions, to appease objtool, + and instead parameterize shared code. + + - We maintain frame pointers so that stack traces make sense. + + - We remove the dependency on the perl xlate code, which transforms + the output into things that assemblers we don't care about use. + +Importantly, none of our changes affect the arithmetic or core code, but +just involve the differing environment of kernel space. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Samuel Neves +Co-developed-by: Samuel Neves +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/.gitignore | 1 + + arch/x86/crypto/Makefile | 11 +- + arch/x86/crypto/poly1305-avx2-x86_64.S | 390 ---------- + arch/x86/crypto/poly1305-sse2-x86_64.S | 590 --------------- + arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 682 ++++++++++-------- + arch/x86/crypto/poly1305_glue.c | 473 +++++------- + lib/crypto/Kconfig | 2 +- + 7 files changed, 572 insertions(+), 1577 deletions(-) + create mode 100644 arch/x86/crypto/.gitignore + delete mode 100644 arch/x86/crypto/poly1305-avx2-x86_64.S + delete mode 100644 arch/x86/crypto/poly1305-sse2-x86_64.S + +--- /dev/null ++++ b/arch/x86/crypto/.gitignore +@@ -0,0 +1 @@ ++poly1305-x86_64.S +--- a/arch/x86/crypto/Makefile ++++ b/arch/x86/crypto/Makefile +@@ -73,6 +73,10 @@ aegis128-aesni-y := aegis128-aesni-asm.o + + nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o + blake2s-x86_64-y := blake2s-core.o blake2s-glue.o ++poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o ++ifneq ($(CONFIG_CRYPTO_POLY1305_X86_64),) ++targets += poly1305-x86_64-cryptogams.S ++endif + + ifeq ($(avx_supported),yes) + camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \ +@@ -101,10 +105,8 @@ aesni-intel-y := aesni-intel_asm.o aesni + aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o + ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o + sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o +-poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o + ifeq ($(avx2_supported),yes) + sha1-ssse3-y += sha1_avx2_x86_64_asm.o +-poly1305-x86_64-y += poly1305-avx2-x86_64.o + endif + ifeq ($(sha1_ni_supported),yes) + sha1-ssse3-y += sha1_ni_asm.o +@@ -118,3 +120,8 @@ sha256-ssse3-y += sha256_ni_asm.o + endif + sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o + crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o ++ ++quiet_cmd_perlasm = PERLASM $@ ++ cmd_perlasm = $(PERL) $< > $@ ++$(obj)/%.S: $(src)/%.pl FORCE ++ $(call if_changed,perlasm) +--- a/arch/x86/crypto/poly1305-avx2-x86_64.S ++++ /dev/null +@@ -1,390 +0,0 @@ +-/* SPDX-License-Identifier: GPL-2.0-or-later */ +-/* +- * Poly1305 authenticator algorithm, RFC7539, x64 AVX2 functions +- * +- * Copyright (C) 2015 Martin Willi +- */ +- +-#include +- +-.section .rodata.cst32.ANMASK, "aM", @progbits, 32 +-.align 32 +-ANMASK: .octa 0x0000000003ffffff0000000003ffffff +- .octa 0x0000000003ffffff0000000003ffffff +- +-.section .rodata.cst32.ORMASK, "aM", @progbits, 32 +-.align 32 +-ORMASK: .octa 0x00000000010000000000000001000000 +- .octa 0x00000000010000000000000001000000 +- +-.text +- +-#define h0 0x00(%rdi) +-#define h1 0x04(%rdi) +-#define h2 0x08(%rdi) +-#define h3 0x0c(%rdi) +-#define h4 0x10(%rdi) +-#define r0 0x00(%rdx) +-#define r1 0x04(%rdx) +-#define r2 0x08(%rdx) +-#define r3 0x0c(%rdx) +-#define r4 0x10(%rdx) +-#define u0 0x00(%r8) +-#define u1 0x04(%r8) +-#define u2 0x08(%r8) +-#define u3 0x0c(%r8) +-#define u4 0x10(%r8) +-#define w0 0x18(%r8) +-#define w1 0x1c(%r8) +-#define w2 0x20(%r8) +-#define w3 0x24(%r8) +-#define w4 0x28(%r8) +-#define y0 0x30(%r8) +-#define y1 0x34(%r8) +-#define y2 0x38(%r8) +-#define y3 0x3c(%r8) +-#define y4 0x40(%r8) +-#define m %rsi +-#define hc0 %ymm0 +-#define hc1 %ymm1 +-#define hc2 %ymm2 +-#define hc3 %ymm3 +-#define hc4 %ymm4 +-#define hc0x %xmm0 +-#define hc1x %xmm1 +-#define hc2x %xmm2 +-#define hc3x %xmm3 +-#define hc4x %xmm4 +-#define t1 %ymm5 +-#define t2 %ymm6 +-#define t1x %xmm5 +-#define t2x %xmm6 +-#define ruwy0 %ymm7 +-#define ruwy1 %ymm8 +-#define ruwy2 %ymm9 +-#define ruwy3 %ymm10 +-#define ruwy4 %ymm11 +-#define ruwy0x %xmm7 +-#define ruwy1x %xmm8 +-#define ruwy2x %xmm9 +-#define ruwy3x %xmm10 +-#define ruwy4x %xmm11 +-#define svxz1 %ymm12 +-#define svxz2 %ymm13 +-#define svxz3 %ymm14 +-#define svxz4 %ymm15 +-#define d0 %r9 +-#define d1 %r10 +-#define d2 %r11 +-#define d3 %r12 +-#define d4 %r13 +- +-ENTRY(poly1305_4block_avx2) +- # %rdi: Accumulator h[5] +- # %rsi: 64 byte input block m +- # %rdx: Poly1305 key r[5] +- # %rcx: Quadblock count +- # %r8: Poly1305 derived key r^2 u[5], r^3 w[5], r^4 y[5], +- +- # This four-block variant uses loop unrolled block processing. It +- # requires 4 Poly1305 keys: r, r^2, r^3 and r^4: +- # h = (h + m) * r => h = (h + m1) * r^4 + m2 * r^3 + m3 * r^2 + m4 * r +- +- vzeroupper +- push %rbx +- push %r12 +- push %r13 +- +- # combine r0,u0,w0,y0 +- vmovd y0,ruwy0x +- vmovd w0,t1x +- vpunpcklqdq t1,ruwy0,ruwy0 +- vmovd u0,t1x +- vmovd r0,t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,ruwy0,ruwy0 +- +- # combine r1,u1,w1,y1 and s1=r1*5,v1=u1*5,x1=w1*5,z1=y1*5 +- vmovd y1,ruwy1x +- vmovd w1,t1x +- vpunpcklqdq t1,ruwy1,ruwy1 +- vmovd u1,t1x +- vmovd r1,t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,ruwy1,ruwy1 +- vpslld $2,ruwy1,svxz1 +- vpaddd ruwy1,svxz1,svxz1 +- +- # combine r2,u2,w2,y2 and s2=r2*5,v2=u2*5,x2=w2*5,z2=y2*5 +- vmovd y2,ruwy2x +- vmovd w2,t1x +- vpunpcklqdq t1,ruwy2,ruwy2 +- vmovd u2,t1x +- vmovd r2,t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,ruwy2,ruwy2 +- vpslld $2,ruwy2,svxz2 +- vpaddd ruwy2,svxz2,svxz2 +- +- # combine r3,u3,w3,y3 and s3=r3*5,v3=u3*5,x3=w3*5,z3=y3*5 +- vmovd y3,ruwy3x +- vmovd w3,t1x +- vpunpcklqdq t1,ruwy3,ruwy3 +- vmovd u3,t1x +- vmovd r3,t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,ruwy3,ruwy3 +- vpslld $2,ruwy3,svxz3 +- vpaddd ruwy3,svxz3,svxz3 +- +- # combine r4,u4,w4,y4 and s4=r4*5,v4=u4*5,x4=w4*5,z4=y4*5 +- vmovd y4,ruwy4x +- vmovd w4,t1x +- vpunpcklqdq t1,ruwy4,ruwy4 +- vmovd u4,t1x +- vmovd r4,t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,ruwy4,ruwy4 +- vpslld $2,ruwy4,svxz4 +- vpaddd ruwy4,svxz4,svxz4 +- +-.Ldoblock4: +- # hc0 = [m[48-51] & 0x3ffffff, m[32-35] & 0x3ffffff, +- # m[16-19] & 0x3ffffff, m[ 0- 3] & 0x3ffffff + h0] +- vmovd 0x00(m),hc0x +- vmovd 0x10(m),t1x +- vpunpcklqdq t1,hc0,hc0 +- vmovd 0x20(m),t1x +- vmovd 0x30(m),t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,hc0,hc0 +- vpand ANMASK(%rip),hc0,hc0 +- vmovd h0,t1x +- vpaddd t1,hc0,hc0 +- # hc1 = [(m[51-54] >> 2) & 0x3ffffff, (m[35-38] >> 2) & 0x3ffffff, +- # (m[19-22] >> 2) & 0x3ffffff, (m[ 3- 6] >> 2) & 0x3ffffff + h1] +- vmovd 0x03(m),hc1x +- vmovd 0x13(m),t1x +- vpunpcklqdq t1,hc1,hc1 +- vmovd 0x23(m),t1x +- vmovd 0x33(m),t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,hc1,hc1 +- vpsrld $2,hc1,hc1 +- vpand ANMASK(%rip),hc1,hc1 +- vmovd h1,t1x +- vpaddd t1,hc1,hc1 +- # hc2 = [(m[54-57] >> 4) & 0x3ffffff, (m[38-41] >> 4) & 0x3ffffff, +- # (m[22-25] >> 4) & 0x3ffffff, (m[ 6- 9] >> 4) & 0x3ffffff + h2] +- vmovd 0x06(m),hc2x +- vmovd 0x16(m),t1x +- vpunpcklqdq t1,hc2,hc2 +- vmovd 0x26(m),t1x +- vmovd 0x36(m),t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,hc2,hc2 +- vpsrld $4,hc2,hc2 +- vpand ANMASK(%rip),hc2,hc2 +- vmovd h2,t1x +- vpaddd t1,hc2,hc2 +- # hc3 = [(m[57-60] >> 6) & 0x3ffffff, (m[41-44] >> 6) & 0x3ffffff, +- # (m[25-28] >> 6) & 0x3ffffff, (m[ 9-12] >> 6) & 0x3ffffff + h3] +- vmovd 0x09(m),hc3x +- vmovd 0x19(m),t1x +- vpunpcklqdq t1,hc3,hc3 +- vmovd 0x29(m),t1x +- vmovd 0x39(m),t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,hc3,hc3 +- vpsrld $6,hc3,hc3 +- vpand ANMASK(%rip),hc3,hc3 +- vmovd h3,t1x +- vpaddd t1,hc3,hc3 +- # hc4 = [(m[60-63] >> 8) | (1<<24), (m[44-47] >> 8) | (1<<24), +- # (m[28-31] >> 8) | (1<<24), (m[12-15] >> 8) | (1<<24) + h4] +- vmovd 0x0c(m),hc4x +- vmovd 0x1c(m),t1x +- vpunpcklqdq t1,hc4,hc4 +- vmovd 0x2c(m),t1x +- vmovd 0x3c(m),t2x +- vpunpcklqdq t2,t1,t1 +- vperm2i128 $0x20,t1,hc4,hc4 +- vpsrld $8,hc4,hc4 +- vpor ORMASK(%rip),hc4,hc4 +- vmovd h4,t1x +- vpaddd t1,hc4,hc4 +- +- # t1 = [ hc0[3] * r0, hc0[2] * u0, hc0[1] * w0, hc0[0] * y0 ] +- vpmuludq hc0,ruwy0,t1 +- # t1 += [ hc1[3] * s4, hc1[2] * v4, hc1[1] * x4, hc1[0] * z4 ] +- vpmuludq hc1,svxz4,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc2[3] * s3, hc2[2] * v3, hc2[1] * x3, hc2[0] * z3 ] +- vpmuludq hc2,svxz3,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc3[3] * s2, hc3[2] * v2, hc3[1] * x2, hc3[0] * z2 ] +- vpmuludq hc3,svxz2,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc4[3] * s1, hc4[2] * v1, hc4[1] * x1, hc4[0] * z1 ] +- vpmuludq hc4,svxz1,t2 +- vpaddq t2,t1,t1 +- # d0 = t1[0] + t1[1] + t[2] + t[3] +- vpermq $0xee,t1,t2 +- vpaddq t2,t1,t1 +- vpsrldq $8,t1,t2 +- vpaddq t2,t1,t1 +- vmovq t1x,d0 +- +- # t1 = [ hc0[3] * r1, hc0[2] * u1,hc0[1] * w1, hc0[0] * y1 ] +- vpmuludq hc0,ruwy1,t1 +- # t1 += [ hc1[3] * r0, hc1[2] * u0, hc1[1] * w0, hc1[0] * y0 ] +- vpmuludq hc1,ruwy0,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc2[3] * s4, hc2[2] * v4, hc2[1] * x4, hc2[0] * z4 ] +- vpmuludq hc2,svxz4,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc3[3] * s3, hc3[2] * v3, hc3[1] * x3, hc3[0] * z3 ] +- vpmuludq hc3,svxz3,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc4[3] * s2, hc4[2] * v2, hc4[1] * x2, hc4[0] * z2 ] +- vpmuludq hc4,svxz2,t2 +- vpaddq t2,t1,t1 +- # d1 = t1[0] + t1[1] + t1[3] + t1[4] +- vpermq $0xee,t1,t2 +- vpaddq t2,t1,t1 +- vpsrldq $8,t1,t2 +- vpaddq t2,t1,t1 +- vmovq t1x,d1 +- +- # t1 = [ hc0[3] * r2, hc0[2] * u2, hc0[1] * w2, hc0[0] * y2 ] +- vpmuludq hc0,ruwy2,t1 +- # t1 += [ hc1[3] * r1, hc1[2] * u1, hc1[1] * w1, hc1[0] * y1 ] +- vpmuludq hc1,ruwy1,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc2[3] * r0, hc2[2] * u0, hc2[1] * w0, hc2[0] * y0 ] +- vpmuludq hc2,ruwy0,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc3[3] * s4, hc3[2] * v4, hc3[1] * x4, hc3[0] * z4 ] +- vpmuludq hc3,svxz4,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc4[3] * s3, hc4[2] * v3, hc4[1] * x3, hc4[0] * z3 ] +- vpmuludq hc4,svxz3,t2 +- vpaddq t2,t1,t1 +- # d2 = t1[0] + t1[1] + t1[2] + t1[3] +- vpermq $0xee,t1,t2 +- vpaddq t2,t1,t1 +- vpsrldq $8,t1,t2 +- vpaddq t2,t1,t1 +- vmovq t1x,d2 +- +- # t1 = [ hc0[3] * r3, hc0[2] * u3, hc0[1] * w3, hc0[0] * y3 ] +- vpmuludq hc0,ruwy3,t1 +- # t1 += [ hc1[3] * r2, hc1[2] * u2, hc1[1] * w2, hc1[0] * y2 ] +- vpmuludq hc1,ruwy2,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc2[3] * r1, hc2[2] * u1, hc2[1] * w1, hc2[0] * y1 ] +- vpmuludq hc2,ruwy1,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc3[3] * r0, hc3[2] * u0, hc3[1] * w0, hc3[0] * y0 ] +- vpmuludq hc3,ruwy0,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc4[3] * s4, hc4[2] * v4, hc4[1] * x4, hc4[0] * z4 ] +- vpmuludq hc4,svxz4,t2 +- vpaddq t2,t1,t1 +- # d3 = t1[0] + t1[1] + t1[2] + t1[3] +- vpermq $0xee,t1,t2 +- vpaddq t2,t1,t1 +- vpsrldq $8,t1,t2 +- vpaddq t2,t1,t1 +- vmovq t1x,d3 +- +- # t1 = [ hc0[3] * r4, hc0[2] * u4, hc0[1] * w4, hc0[0] * y4 ] +- vpmuludq hc0,ruwy4,t1 +- # t1 += [ hc1[3] * r3, hc1[2] * u3, hc1[1] * w3, hc1[0] * y3 ] +- vpmuludq hc1,ruwy3,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc2[3] * r2, hc2[2] * u2, hc2[1] * w2, hc2[0] * y2 ] +- vpmuludq hc2,ruwy2,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc3[3] * r1, hc3[2] * u1, hc3[1] * w1, hc3[0] * y1 ] +- vpmuludq hc3,ruwy1,t2 +- vpaddq t2,t1,t1 +- # t1 += [ hc4[3] * r0, hc4[2] * u0, hc4[1] * w0, hc4[0] * y0 ] +- vpmuludq hc4,ruwy0,t2 +- vpaddq t2,t1,t1 +- # d4 = t1[0] + t1[1] + t1[2] + t1[3] +- vpermq $0xee,t1,t2 +- vpaddq t2,t1,t1 +- vpsrldq $8,t1,t2 +- vpaddq t2,t1,t1 +- vmovq t1x,d4 +- +- # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> +- # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small +- # amount. Careful: we must not assume the carry bits 'd0 >> 26', +- # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit +- # integers. It's true in a single-block implementation, but not here. +- +- # d1 += d0 >> 26 +- mov d0,%rax +- shr $26,%rax +- add %rax,d1 +- # h0 = d0 & 0x3ffffff +- mov d0,%rbx +- and $0x3ffffff,%ebx +- +- # d2 += d1 >> 26 +- mov d1,%rax +- shr $26,%rax +- add %rax,d2 +- # h1 = d1 & 0x3ffffff +- mov d1,%rax +- and $0x3ffffff,%eax +- mov %eax,h1 +- +- # d3 += d2 >> 26 +- mov d2,%rax +- shr $26,%rax +- add %rax,d3 +- # h2 = d2 & 0x3ffffff +- mov d2,%rax +- and $0x3ffffff,%eax +- mov %eax,h2 +- +- # d4 += d3 >> 26 +- mov d3,%rax +- shr $26,%rax +- add %rax,d4 +- # h3 = d3 & 0x3ffffff +- mov d3,%rax +- and $0x3ffffff,%eax +- mov %eax,h3 +- +- # h0 += (d4 >> 26) * 5 +- mov d4,%rax +- shr $26,%rax +- lea (%rax,%rax,4),%rax +- add %rax,%rbx +- # h4 = d4 & 0x3ffffff +- mov d4,%rax +- and $0x3ffffff,%eax +- mov %eax,h4 +- +- # h1 += h0 >> 26 +- mov %rbx,%rax +- shr $26,%rax +- add %eax,h1 +- # h0 = h0 & 0x3ffffff +- andl $0x3ffffff,%ebx +- mov %ebx,h0 +- +- add $0x40,m +- dec %rcx +- jnz .Ldoblock4 +- +- vzeroupper +- pop %r13 +- pop %r12 +- pop %rbx +- ret +-ENDPROC(poly1305_4block_avx2) +--- a/arch/x86/crypto/poly1305-sse2-x86_64.S ++++ /dev/null +@@ -1,590 +0,0 @@ +-/* SPDX-License-Identifier: GPL-2.0-or-later */ +-/* +- * Poly1305 authenticator algorithm, RFC7539, x64 SSE2 functions +- * +- * Copyright (C) 2015 Martin Willi +- */ +- +-#include +- +-.section .rodata.cst16.ANMASK, "aM", @progbits, 16 +-.align 16 +-ANMASK: .octa 0x0000000003ffffff0000000003ffffff +- +-.section .rodata.cst16.ORMASK, "aM", @progbits, 16 +-.align 16 +-ORMASK: .octa 0x00000000010000000000000001000000 +- +-.text +- +-#define h0 0x00(%rdi) +-#define h1 0x04(%rdi) +-#define h2 0x08(%rdi) +-#define h3 0x0c(%rdi) +-#define h4 0x10(%rdi) +-#define r0 0x00(%rdx) +-#define r1 0x04(%rdx) +-#define r2 0x08(%rdx) +-#define r3 0x0c(%rdx) +-#define r4 0x10(%rdx) +-#define s1 0x00(%rsp) +-#define s2 0x04(%rsp) +-#define s3 0x08(%rsp) +-#define s4 0x0c(%rsp) +-#define m %rsi +-#define h01 %xmm0 +-#define h23 %xmm1 +-#define h44 %xmm2 +-#define t1 %xmm3 +-#define t2 %xmm4 +-#define t3 %xmm5 +-#define t4 %xmm6 +-#define mask %xmm7 +-#define d0 %r8 +-#define d1 %r9 +-#define d2 %r10 +-#define d3 %r11 +-#define d4 %r12 +- +-ENTRY(poly1305_block_sse2) +- # %rdi: Accumulator h[5] +- # %rsi: 16 byte input block m +- # %rdx: Poly1305 key r[5] +- # %rcx: Block count +- +- # This single block variant tries to improve performance by doing two +- # multiplications in parallel using SSE instructions. There is quite +- # some quardword packing involved, hence the speedup is marginal. +- +- push %rbx +- push %r12 +- sub $0x10,%rsp +- +- # s1..s4 = r1..r4 * 5 +- mov r1,%eax +- lea (%eax,%eax,4),%eax +- mov %eax,s1 +- mov r2,%eax +- lea (%eax,%eax,4),%eax +- mov %eax,s2 +- mov r3,%eax +- lea (%eax,%eax,4),%eax +- mov %eax,s3 +- mov r4,%eax +- lea (%eax,%eax,4),%eax +- mov %eax,s4 +- +- movdqa ANMASK(%rip),mask +- +-.Ldoblock: +- # h01 = [0, h1, 0, h0] +- # h23 = [0, h3, 0, h2] +- # h44 = [0, h4, 0, h4] +- movd h0,h01 +- movd h1,t1 +- movd h2,h23 +- movd h3,t2 +- movd h4,h44 +- punpcklqdq t1,h01 +- punpcklqdq t2,h23 +- punpcklqdq h44,h44 +- +- # h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ] +- movd 0x00(m),t1 +- movd 0x03(m),t2 +- psrld $2,t2 +- punpcklqdq t2,t1 +- pand mask,t1 +- paddd t1,h01 +- # h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ] +- movd 0x06(m),t1 +- movd 0x09(m),t2 +- psrld $4,t1 +- psrld $6,t2 +- punpcklqdq t2,t1 +- pand mask,t1 +- paddd t1,h23 +- # h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ] +- mov 0x0c(m),%eax +- shr $8,%eax +- or $0x01000000,%eax +- movd %eax,t1 +- pshufd $0xc4,t1,t1 +- paddd t1,h44 +- +- # t1[0] = h0 * r0 + h2 * s3 +- # t1[1] = h1 * s4 + h3 * s2 +- movd r0,t1 +- movd s4,t2 +- punpcklqdq t2,t1 +- pmuludq h01,t1 +- movd s3,t2 +- movd s2,t3 +- punpcklqdq t3,t2 +- pmuludq h23,t2 +- paddq t2,t1 +- # t2[0] = h0 * r1 + h2 * s4 +- # t2[1] = h1 * r0 + h3 * s3 +- movd r1,t2 +- movd r0,t3 +- punpcklqdq t3,t2 +- pmuludq h01,t2 +- movd s4,t3 +- movd s3,t4 +- punpcklqdq t4,t3 +- pmuludq h23,t3 +- paddq t3,t2 +- # t3[0] = h4 * s1 +- # t3[1] = h4 * s2 +- movd s1,t3 +- movd s2,t4 +- punpcklqdq t4,t3 +- pmuludq h44,t3 +- # d0 = t1[0] + t1[1] + t3[0] +- # d1 = t2[0] + t2[1] + t3[1] +- movdqa t1,t4 +- punpcklqdq t2,t4 +- punpckhqdq t2,t1 +- paddq t4,t1 +- paddq t3,t1 +- movq t1,d0 +- psrldq $8,t1 +- movq t1,d1 +- +- # t1[0] = h0 * r2 + h2 * r0 +- # t1[1] = h1 * r1 + h3 * s4 +- movd r2,t1 +- movd r1,t2 +- punpcklqdq t2,t1 +- pmuludq h01,t1 +- movd r0,t2 +- movd s4,t3 +- punpcklqdq t3,t2 +- pmuludq h23,t2 +- paddq t2,t1 +- # t2[0] = h0 * r3 + h2 * r1 +- # t2[1] = h1 * r2 + h3 * r0 +- movd r3,t2 +- movd r2,t3 +- punpcklqdq t3,t2 +- pmuludq h01,t2 +- movd r1,t3 +- movd r0,t4 +- punpcklqdq t4,t3 +- pmuludq h23,t3 +- paddq t3,t2 +- # t3[0] = h4 * s3 +- # t3[1] = h4 * s4 +- movd s3,t3 +- movd s4,t4 +- punpcklqdq t4,t3 +- pmuludq h44,t3 +- # d2 = t1[0] + t1[1] + t3[0] +- # d3 = t2[0] + t2[1] + t3[1] +- movdqa t1,t4 +- punpcklqdq t2,t4 +- punpckhqdq t2,t1 +- paddq t4,t1 +- paddq t3,t1 +- movq t1,d2 +- psrldq $8,t1 +- movq t1,d3 +- +- # t1[0] = h0 * r4 + h2 * r2 +- # t1[1] = h1 * r3 + h3 * r1 +- movd r4,t1 +- movd r3,t2 +- punpcklqdq t2,t1 +- pmuludq h01,t1 +- movd r2,t2 +- movd r1,t3 +- punpcklqdq t3,t2 +- pmuludq h23,t2 +- paddq t2,t1 +- # t3[0] = h4 * r0 +- movd r0,t3 +- pmuludq h44,t3 +- # d4 = t1[0] + t1[1] + t3[0] +- movdqa t1,t4 +- psrldq $8,t4 +- paddq t4,t1 +- paddq t3,t1 +- movq t1,d4 +- +- # d1 += d0 >> 26 +- mov d0,%rax +- shr $26,%rax +- add %rax,d1 +- # h0 = d0 & 0x3ffffff +- mov d0,%rbx +- and $0x3ffffff,%ebx +- +- # d2 += d1 >> 26 +- mov d1,%rax +- shr $26,%rax +- add %rax,d2 +- # h1 = d1 & 0x3ffffff +- mov d1,%rax +- and $0x3ffffff,%eax +- mov %eax,h1 +- +- # d3 += d2 >> 26 +- mov d2,%rax +- shr $26,%rax +- add %rax,d3 +- # h2 = d2 & 0x3ffffff +- mov d2,%rax +- and $0x3ffffff,%eax +- mov %eax,h2 +- +- # d4 += d3 >> 26 +- mov d3,%rax +- shr $26,%rax +- add %rax,d4 +- # h3 = d3 & 0x3ffffff +- mov d3,%rax +- and $0x3ffffff,%eax +- mov %eax,h3 +- +- # h0 += (d4 >> 26) * 5 +- mov d4,%rax +- shr $26,%rax +- lea (%rax,%rax,4),%rax +- add %rax,%rbx +- # h4 = d4 & 0x3ffffff +- mov d4,%rax +- and $0x3ffffff,%eax +- mov %eax,h4 +- +- # h1 += h0 >> 26 +- mov %rbx,%rax +- shr $26,%rax +- add %eax,h1 +- # h0 = h0 & 0x3ffffff +- andl $0x3ffffff,%ebx +- mov %ebx,h0 +- +- add $0x10,m +- dec %rcx +- jnz .Ldoblock +- +- # Zeroing of key material +- mov %rcx,0x00(%rsp) +- mov %rcx,0x08(%rsp) +- +- add $0x10,%rsp +- pop %r12 +- pop %rbx +- ret +-ENDPROC(poly1305_block_sse2) +- +- +-#define u0 0x00(%r8) +-#define u1 0x04(%r8) +-#define u2 0x08(%r8) +-#define u3 0x0c(%r8) +-#define u4 0x10(%r8) +-#define hc0 %xmm0 +-#define hc1 %xmm1 +-#define hc2 %xmm2 +-#define hc3 %xmm5 +-#define hc4 %xmm6 +-#define ru0 %xmm7 +-#define ru1 %xmm8 +-#define ru2 %xmm9 +-#define ru3 %xmm10 +-#define ru4 %xmm11 +-#define sv1 %xmm12 +-#define sv2 %xmm13 +-#define sv3 %xmm14 +-#define sv4 %xmm15 +-#undef d0 +-#define d0 %r13 +- +-ENTRY(poly1305_2block_sse2) +- # %rdi: Accumulator h[5] +- # %rsi: 16 byte input block m +- # %rdx: Poly1305 key r[5] +- # %rcx: Doubleblock count +- # %r8: Poly1305 derived key r^2 u[5] +- +- # This two-block variant further improves performance by using loop +- # unrolled block processing. This is more straight forward and does +- # less byte shuffling, but requires a second Poly1305 key r^2: +- # h = (h + m) * r => h = (h + m1) * r^2 + m2 * r +- +- push %rbx +- push %r12 +- push %r13 +- +- # combine r0,u0 +- movd u0,ru0 +- movd r0,t1 +- punpcklqdq t1,ru0 +- +- # combine r1,u1 and s1=r1*5,v1=u1*5 +- movd u1,ru1 +- movd r1,t1 +- punpcklqdq t1,ru1 +- movdqa ru1,sv1 +- pslld $2,sv1 +- paddd ru1,sv1 +- +- # combine r2,u2 and s2=r2*5,v2=u2*5 +- movd u2,ru2 +- movd r2,t1 +- punpcklqdq t1,ru2 +- movdqa ru2,sv2 +- pslld $2,sv2 +- paddd ru2,sv2 +- +- # combine r3,u3 and s3=r3*5,v3=u3*5 +- movd u3,ru3 +- movd r3,t1 +- punpcklqdq t1,ru3 +- movdqa ru3,sv3 +- pslld $2,sv3 +- paddd ru3,sv3 +- +- # combine r4,u4 and s4=r4*5,v4=u4*5 +- movd u4,ru4 +- movd r4,t1 +- punpcklqdq t1,ru4 +- movdqa ru4,sv4 +- pslld $2,sv4 +- paddd ru4,sv4 +- +-.Ldoblock2: +- # hc0 = [ m[16-19] & 0x3ffffff, h0 + m[0-3] & 0x3ffffff ] +- movd 0x00(m),hc0 +- movd 0x10(m),t1 +- punpcklqdq t1,hc0 +- pand ANMASK(%rip),hc0 +- movd h0,t1 +- paddd t1,hc0 +- # hc1 = [ (m[19-22] >> 2) & 0x3ffffff, h1 + (m[3-6] >> 2) & 0x3ffffff ] +- movd 0x03(m),hc1 +- movd 0x13(m),t1 +- punpcklqdq t1,hc1 +- psrld $2,hc1 +- pand ANMASK(%rip),hc1 +- movd h1,t1 +- paddd t1,hc1 +- # hc2 = [ (m[22-25] >> 4) & 0x3ffffff, h2 + (m[6-9] >> 4) & 0x3ffffff ] +- movd 0x06(m),hc2 +- movd 0x16(m),t1 +- punpcklqdq t1,hc2 +- psrld $4,hc2 +- pand ANMASK(%rip),hc2 +- movd h2,t1 +- paddd t1,hc2 +- # hc3 = [ (m[25-28] >> 6) & 0x3ffffff, h3 + (m[9-12] >> 6) & 0x3ffffff ] +- movd 0x09(m),hc3 +- movd 0x19(m),t1 +- punpcklqdq t1,hc3 +- psrld $6,hc3 +- pand ANMASK(%rip),hc3 +- movd h3,t1 +- paddd t1,hc3 +- # hc4 = [ (m[28-31] >> 8) | (1<<24), h4 + (m[12-15] >> 8) | (1<<24) ] +- movd 0x0c(m),hc4 +- movd 0x1c(m),t1 +- punpcklqdq t1,hc4 +- psrld $8,hc4 +- por ORMASK(%rip),hc4 +- movd h4,t1 +- paddd t1,hc4 +- +- # t1 = [ hc0[1] * r0, hc0[0] * u0 ] +- movdqa ru0,t1 +- pmuludq hc0,t1 +- # t1 += [ hc1[1] * s4, hc1[0] * v4 ] +- movdqa sv4,t2 +- pmuludq hc1,t2 +- paddq t2,t1 +- # t1 += [ hc2[1] * s3, hc2[0] * v3 ] +- movdqa sv3,t2 +- pmuludq hc2,t2 +- paddq t2,t1 +- # t1 += [ hc3[1] * s2, hc3[0] * v2 ] +- movdqa sv2,t2 +- pmuludq hc3,t2 +- paddq t2,t1 +- # t1 += [ hc4[1] * s1, hc4[0] * v1 ] +- movdqa sv1,t2 +- pmuludq hc4,t2 +- paddq t2,t1 +- # d0 = t1[0] + t1[1] +- movdqa t1,t2 +- psrldq $8,t2 +- paddq t2,t1 +- movq t1,d0 +- +- # t1 = [ hc0[1] * r1, hc0[0] * u1 ] +- movdqa ru1,t1 +- pmuludq hc0,t1 +- # t1 += [ hc1[1] * r0, hc1[0] * u0 ] +- movdqa ru0,t2 +- pmuludq hc1,t2 +- paddq t2,t1 +- # t1 += [ hc2[1] * s4, hc2[0] * v4 ] +- movdqa sv4,t2 +- pmuludq hc2,t2 +- paddq t2,t1 +- # t1 += [ hc3[1] * s3, hc3[0] * v3 ] +- movdqa sv3,t2 +- pmuludq hc3,t2 +- paddq t2,t1 +- # t1 += [ hc4[1] * s2, hc4[0] * v2 ] +- movdqa sv2,t2 +- pmuludq hc4,t2 +- paddq t2,t1 +- # d1 = t1[0] + t1[1] +- movdqa t1,t2 +- psrldq $8,t2 +- paddq t2,t1 +- movq t1,d1 +- +- # t1 = [ hc0[1] * r2, hc0[0] * u2 ] +- movdqa ru2,t1 +- pmuludq hc0,t1 +- # t1 += [ hc1[1] * r1, hc1[0] * u1 ] +- movdqa ru1,t2 +- pmuludq hc1,t2 +- paddq t2,t1 +- # t1 += [ hc2[1] * r0, hc2[0] * u0 ] +- movdqa ru0,t2 +- pmuludq hc2,t2 +- paddq t2,t1 +- # t1 += [ hc3[1] * s4, hc3[0] * v4 ] +- movdqa sv4,t2 +- pmuludq hc3,t2 +- paddq t2,t1 +- # t1 += [ hc4[1] * s3, hc4[0] * v3 ] +- movdqa sv3,t2 +- pmuludq hc4,t2 +- paddq t2,t1 +- # d2 = t1[0] + t1[1] +- movdqa t1,t2 +- psrldq $8,t2 +- paddq t2,t1 +- movq t1,d2 +- +- # t1 = [ hc0[1] * r3, hc0[0] * u3 ] +- movdqa ru3,t1 +- pmuludq hc0,t1 +- # t1 += [ hc1[1] * r2, hc1[0] * u2 ] +- movdqa ru2,t2 +- pmuludq hc1,t2 +- paddq t2,t1 +- # t1 += [ hc2[1] * r1, hc2[0] * u1 ] +- movdqa ru1,t2 +- pmuludq hc2,t2 +- paddq t2,t1 +- # t1 += [ hc3[1] * r0, hc3[0] * u0 ] +- movdqa ru0,t2 +- pmuludq hc3,t2 +- paddq t2,t1 +- # t1 += [ hc4[1] * s4, hc4[0] * v4 ] +- movdqa sv4,t2 +- pmuludq hc4,t2 +- paddq t2,t1 +- # d3 = t1[0] + t1[1] +- movdqa t1,t2 +- psrldq $8,t2 +- paddq t2,t1 +- movq t1,d3 +- +- # t1 = [ hc0[1] * r4, hc0[0] * u4 ] +- movdqa ru4,t1 +- pmuludq hc0,t1 +- # t1 += [ hc1[1] * r3, hc1[0] * u3 ] +- movdqa ru3,t2 +- pmuludq hc1,t2 +- paddq t2,t1 +- # t1 += [ hc2[1] * r2, hc2[0] * u2 ] +- movdqa ru2,t2 +- pmuludq hc2,t2 +- paddq t2,t1 +- # t1 += [ hc3[1] * r1, hc3[0] * u1 ] +- movdqa ru1,t2 +- pmuludq hc3,t2 +- paddq t2,t1 +- # t1 += [ hc4[1] * r0, hc4[0] * u0 ] +- movdqa ru0,t2 +- pmuludq hc4,t2 +- paddq t2,t1 +- # d4 = t1[0] + t1[1] +- movdqa t1,t2 +- psrldq $8,t2 +- paddq t2,t1 +- movq t1,d4 +- +- # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> +- # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small +- # amount. Careful: we must not assume the carry bits 'd0 >> 26', +- # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit +- # integers. It's true in a single-block implementation, but not here. +- +- # d1 += d0 >> 26 +- mov d0,%rax +- shr $26,%rax +- add %rax,d1 +- # h0 = d0 & 0x3ffffff +- mov d0,%rbx +- and $0x3ffffff,%ebx +- +- # d2 += d1 >> 26 +- mov d1,%rax +- shr $26,%rax +- add %rax,d2 +- # h1 = d1 & 0x3ffffff +- mov d1,%rax +- and $0x3ffffff,%eax +- mov %eax,h1 +- +- # d3 += d2 >> 26 +- mov d2,%rax +- shr $26,%rax +- add %rax,d3 +- # h2 = d2 & 0x3ffffff +- mov d2,%rax +- and $0x3ffffff,%eax +- mov %eax,h2 +- +- # d4 += d3 >> 26 +- mov d3,%rax +- shr $26,%rax +- add %rax,d4 +- # h3 = d3 & 0x3ffffff +- mov d3,%rax +- and $0x3ffffff,%eax +- mov %eax,h3 +- +- # h0 += (d4 >> 26) * 5 +- mov d4,%rax +- shr $26,%rax +- lea (%rax,%rax,4),%rax +- add %rax,%rbx +- # h4 = d4 & 0x3ffffff +- mov d4,%rax +- and $0x3ffffff,%eax +- mov %eax,h4 +- +- # h1 += h0 >> 26 +- mov %rbx,%rax +- shr $26,%rax +- add %eax,h1 +- # h0 = h0 & 0x3ffffff +- andl $0x3ffffff,%ebx +- mov %ebx,h0 +- +- add $0x20,m +- dec %rcx +- jnz .Ldoblock2 +- +- pop %r13 +- pop %r12 +- pop %rbx +- ret +-ENDPROC(poly1305_2block_sse2) +--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl ++++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +@@ -1,11 +1,14 @@ +-#! /usr/bin/env perl +-# Copyright 2016-2018 The OpenSSL Project Authors. All Rights Reserved. ++#!/usr/bin/env perl ++# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + # +-# Licensed under the OpenSSL license (the "License"). You may not use +-# this file except in compliance with the License. You can obtain a copy +-# in the file LICENSE in the source distribution or at +-# https://www.openssl.org/source/license.html +- ++# Copyright (C) 2017-2018 Samuel Neves . All Rights Reserved. ++# Copyright (C) 2017-2019 Jason A. Donenfeld . All Rights Reserved. ++# Copyright (C) 2006-2017 CRYPTOGAMS by . All Rights Reserved. ++# ++# This code is taken from the OpenSSL project but the author, Andy Polyakov, ++# has relicensed it under the licenses specified in the SPDX header above. ++# The original headers, including the original license headers, are ++# included below for completeness. + # + # ==================================================================== + # Written by Andy Polyakov for the OpenSSL +@@ -32,7 +35,7 @@ + # Skylake-X system performance. Since we are likely to suppress + # AVX512F capability flag [at least on Skylake-X], conversion serves + # as kind of "investment protection". Note that next *lake processor, +-# Cannolake, has AVX512IFMA code path to execute... ++# Cannonlake, has AVX512IFMA code path to execute... + # + # Numbers are cycles per processed byte with poly1305_blocks alone, + # measured with rdtsc at fixed clock frequency. +@@ -68,39 +71,114 @@ $output = shift; + if ($flavour =~ /\./) { $output = $flavour; undef $flavour; } + + $win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/); ++$kernel=0; $kernel=1 if (!$flavour && !$output); + +-$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; +-( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or +-( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or +-die "can't locate x86_64-xlate.pl"; +- +-if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1` +- =~ /GNU assembler version ([2-9]\.[0-9]+)/) { +- $avx = ($1>=2.19) + ($1>=2.22) + ($1>=2.25) + ($1>=2.26); ++if (!$kernel) { ++ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1; ++ ( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or ++ ( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or ++ die "can't locate x86_64-xlate.pl"; ++ ++ open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\""; ++ *STDOUT=*OUT; ++ ++ if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1` ++ =~ /GNU assembler version ([2-9]\.[0-9]+)/) { ++ $avx = ($1>=2.19) + ($1>=2.22) + ($1>=2.25); ++ } ++ ++ if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) && ++ `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)(?:\.([0-9]+))?/) { ++ $avx = ($1>=2.09) + ($1>=2.10) + ($1>=2.12); ++ $avx += 1 if ($1==2.11 && $2>=8); ++ } ++ ++ if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) && ++ `ml64 2>&1` =~ /Version ([0-9]+)\./) { ++ $avx = ($1>=10) + ($1>=11); ++ } ++ ++ if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) { ++ $avx = ($2>=3.0) + ($2>3.0); ++ } ++} else { ++ $avx = 4; # The kernel uses ifdefs for this. + } + +-if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) && +- `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)(?:\.([0-9]+))?/) { +- $avx = ($1>=2.09) + ($1>=2.10) + 2 * ($1>=2.12); +- $avx += 2 if ($1==2.11 && $2>=8); ++sub declare_function() { ++ my ($name, $align, $nargs) = @_; ++ if($kernel) { ++ $code .= ".align $align\n"; ++ $code .= "ENTRY($name)\n"; ++ $code .= ".L$name:\n"; ++ } else { ++ $code .= ".globl $name\n"; ++ $code .= ".type $name,\@function,$nargs\n"; ++ $code .= ".align $align\n"; ++ $code .= "$name:\n"; ++ } + } + +-if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) && +- `ml64 2>&1` =~ /Version ([0-9]+)\./) { +- $avx = ($1>=10) + ($1>=12); ++sub end_function() { ++ my ($name) = @_; ++ if($kernel) { ++ $code .= "ENDPROC($name)\n"; ++ } else { ++ $code .= ".size $name,.-$name\n"; ++ } + } + +-if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) { +- $avx = ($2>=3.0) + ($2>3.0); +-} ++$code.=<<___ if $kernel; ++#include ++___ + +-open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\""; +-*STDOUT=*OUT; ++if ($avx) { ++$code.=<<___ if $kernel; ++.section .rodata ++___ ++$code.=<<___; ++.align 64 ++.Lconst: ++.Lmask24: ++.long 0x0ffffff,0,0x0ffffff,0,0x0ffffff,0,0x0ffffff,0 ++.L129: ++.long `1<<24`,0,`1<<24`,0,`1<<24`,0,`1<<24`,0 ++.Lmask26: ++.long 0x3ffffff,0,0x3ffffff,0,0x3ffffff,0,0x3ffffff,0 ++.Lpermd_avx2: ++.long 2,2,2,3,2,0,2,1 ++.Lpermd_avx512: ++.long 0,0,0,1, 0,2,0,3, 0,4,0,5, 0,6,0,7 ++ ++.L2_44_inp_permd: ++.long 0,1,1,2,2,3,7,7 ++.L2_44_inp_shift: ++.quad 0,12,24,64 ++.L2_44_mask: ++.quad 0xfffffffffff,0xfffffffffff,0x3ffffffffff,0xffffffffffffffff ++.L2_44_shift_rgt: ++.quad 44,44,42,64 ++.L2_44_shift_lft: ++.quad 8,8,10,64 ++ ++.align 64 ++.Lx_mask44: ++.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff ++.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff ++.Lx_mask42: ++.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff ++.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff ++___ ++} ++$code.=<<___ if (!$kernel); ++.asciz "Poly1305 for x86_64, CRYPTOGAMS by " ++.align 16 ++___ + + my ($ctx,$inp,$len,$padbit)=("%rdi","%rsi","%rdx","%rcx"); + my ($mac,$nonce)=($inp,$len); # *_emit arguments +-my ($d1,$d2,$d3, $r0,$r1,$s1)=map("%r$_",(8..13)); +-my ($h0,$h1,$h2)=("%r14","%rbx","%rbp"); ++my ($d1,$d2,$d3, $r0,$r1,$s1)=("%r8","%r9","%rdi","%r11","%r12","%r13"); ++my ($h0,$h1,$h2)=("%r14","%rbx","%r10"); + + sub poly1305_iteration { + # input: copy of $r1 in %rax, $h0-$h2, $r0-$r1 +@@ -155,19 +233,19 @@ ___ + + $code.=<<___; + .text +- ++___ ++$code.=<<___ if (!$kernel); + .extern OPENSSL_ia32cap_P + +-.globl poly1305_init +-.hidden poly1305_init +-.globl poly1305_blocks +-.hidden poly1305_blocks +-.globl poly1305_emit +-.hidden poly1305_emit +- +-.type poly1305_init,\@function,3 +-.align 32 +-poly1305_init: ++.globl poly1305_init_x86_64 ++.hidden poly1305_init_x86_64 ++.globl poly1305_blocks_x86_64 ++.hidden poly1305_blocks_x86_64 ++.globl poly1305_emit_x86_64 ++.hidden poly1305_emit_x86_64 ++___ ++&declare_function("poly1305_init_x86_64", 32, 3); ++$code.=<<___; + xor %rax,%rax + mov %rax,0($ctx) # initialize hash value + mov %rax,8($ctx) +@@ -175,11 +253,12 @@ poly1305_init: + + cmp \$0,$inp + je .Lno_key +- +- lea poly1305_blocks(%rip),%r10 +- lea poly1305_emit(%rip),%r11 + ___ +-$code.=<<___ if ($avx); ++$code.=<<___ if (!$kernel); ++ lea poly1305_blocks_x86_64(%rip),%r10 ++ lea poly1305_emit_x86_64(%rip),%r11 ++___ ++$code.=<<___ if (!$kernel && $avx); + mov OPENSSL_ia32cap_P+4(%rip),%r9 + lea poly1305_blocks_avx(%rip),%rax + lea poly1305_emit_avx(%rip),%rcx +@@ -187,12 +266,12 @@ $code.=<<___ if ($avx); + cmovc %rax,%r10 + cmovc %rcx,%r11 + ___ +-$code.=<<___ if ($avx>1); ++$code.=<<___ if (!$kernel && $avx>1); + lea poly1305_blocks_avx2(%rip),%rax + bt \$`5+32`,%r9 # AVX2? + cmovc %rax,%r10 + ___ +-$code.=<<___ if ($avx>3); ++$code.=<<___ if (!$kernel && $avx>3); + mov \$`(1<<31|1<<21|1<<16)`,%rax + shr \$32,%r9 + and %rax,%r9 +@@ -207,11 +286,11 @@ $code.=<<___; + mov %rax,24($ctx) + mov %rcx,32($ctx) + ___ +-$code.=<<___ if ($flavour !~ /elf32/); ++$code.=<<___ if (!$kernel && $flavour !~ /elf32/); + mov %r10,0(%rdx) + mov %r11,8(%rdx) + ___ +-$code.=<<___ if ($flavour =~ /elf32/); ++$code.=<<___ if (!$kernel && $flavour =~ /elf32/); + mov %r10d,0(%rdx) + mov %r11d,4(%rdx) + ___ +@@ -219,11 +298,11 @@ $code.=<<___; + mov \$1,%eax + .Lno_key: + ret +-.size poly1305_init,.-poly1305_init ++___ ++&end_function("poly1305_init_x86_64"); + +-.type poly1305_blocks,\@function,4 +-.align 32 +-poly1305_blocks: ++&declare_function("poly1305_blocks_x86_64", 32, 4); ++$code.=<<___; + .cfi_startproc + .Lblocks: + shr \$4,$len +@@ -231,8 +310,6 @@ poly1305_blocks: + + push %rbx + .cfi_push %rbx +- push %rbp +-.cfi_push %rbp + push %r12 + .cfi_push %r12 + push %r13 +@@ -241,6 +318,8 @@ poly1305_blocks: + .cfi_push %r14 + push %r15 + .cfi_push %r15 ++ push $ctx ++.cfi_push $ctx + .Lblocks_body: + + mov $len,%r15 # reassign $len +@@ -265,26 +344,29 @@ poly1305_blocks: + lea 16($inp),$inp + adc $padbit,$h2 + ___ ++ + &poly1305_iteration(); ++ + $code.=<<___; + mov $r1,%rax + dec %r15 # len-=16 + jnz .Loop + ++ mov 0(%rsp),$ctx ++.cfi_restore $ctx ++ + mov $h0,0($ctx) # store hash value + mov $h1,8($ctx) + mov $h2,16($ctx) + +- mov 0(%rsp),%r15 ++ mov 8(%rsp),%r15 + .cfi_restore %r15 +- mov 8(%rsp),%r14 ++ mov 16(%rsp),%r14 + .cfi_restore %r14 +- mov 16(%rsp),%r13 ++ mov 24(%rsp),%r13 + .cfi_restore %r13 +- mov 24(%rsp),%r12 ++ mov 32(%rsp),%r12 + .cfi_restore %r12 +- mov 32(%rsp),%rbp +-.cfi_restore %rbp + mov 40(%rsp),%rbx + .cfi_restore %rbx + lea 48(%rsp),%rsp +@@ -293,11 +375,11 @@ $code.=<<___; + .Lblocks_epilogue: + ret + .cfi_endproc +-.size poly1305_blocks,.-poly1305_blocks ++___ ++&end_function("poly1305_blocks_x86_64"); + +-.type poly1305_emit,\@function,3 +-.align 32 +-poly1305_emit: ++&declare_function("poly1305_emit_x86_64", 32, 3); ++$code.=<<___; + .Lemit: + mov 0($ctx),%r8 # load hash value + mov 8($ctx),%r9 +@@ -318,10 +400,14 @@ poly1305_emit: + mov %rcx,8($mac) + + ret +-.size poly1305_emit,.-poly1305_emit + ___ ++&end_function("poly1305_emit_x86_64"); + if ($avx) { + ++if($kernel) { ++ $code .= "#ifdef CONFIG_AS_AVX\n"; ++} ++ + ######################################################################## + # Layout of opaque area is following. + # +@@ -342,15 +428,19 @@ $code.=<<___; + .type __poly1305_block,\@abi-omnipotent + .align 32 + __poly1305_block: ++ push $ctx + ___ + &poly1305_iteration(); + $code.=<<___; ++ pop $ctx + ret + .size __poly1305_block,.-__poly1305_block + + .type __poly1305_init_avx,\@abi-omnipotent + .align 32 + __poly1305_init_avx: ++ push %rbp ++ mov %rsp,%rbp + mov $r0,$h0 + mov $r1,$h1 + xor $h2,$h2 +@@ -507,12 +597,13 @@ __poly1305_init_avx: + mov $d1#d,`16*8+8-64`($ctx) + + lea -48-64($ctx),$ctx # size [de-]optimization ++ pop %rbp + ret + .size __poly1305_init_avx,.-__poly1305_init_avx ++___ + +-.type poly1305_blocks_avx,\@function,4 +-.align 32 +-poly1305_blocks_avx: ++&declare_function("poly1305_blocks_avx", 32, 4); ++$code.=<<___; + .cfi_startproc + mov 20($ctx),%r8d # is_base2_26 + cmp \$128,$len +@@ -532,10 +623,11 @@ poly1305_blocks_avx: + test \$31,$len + jz .Leven_avx + +- push %rbx +-.cfi_push %rbx + push %rbp + .cfi_push %rbp ++ mov %rsp,%rbp ++ push %rbx ++.cfi_push %rbx + push %r12 + .cfi_push %r12 + push %r13 +@@ -645,20 +737,18 @@ poly1305_blocks_avx: + mov $h2#d,16($ctx) + .align 16 + .Ldone_avx: +- mov 0(%rsp),%r15 ++ pop %r15 + .cfi_restore %r15 +- mov 8(%rsp),%r14 ++ pop %r14 + .cfi_restore %r14 +- mov 16(%rsp),%r13 ++ pop %r13 + .cfi_restore %r13 +- mov 24(%rsp),%r12 ++ pop %r12 + .cfi_restore %r12 +- mov 32(%rsp),%rbp +-.cfi_restore %rbp +- mov 40(%rsp),%rbx ++ pop %rbx + .cfi_restore %rbx +- lea 48(%rsp),%rsp +-.cfi_adjust_cfa_offset -48 ++ pop %rbp ++.cfi_restore %rbp + .Lno_data_avx: + .Lblocks_avx_epilogue: + ret +@@ -667,10 +757,11 @@ poly1305_blocks_avx: + .align 32 + .Lbase2_64_avx: + .cfi_startproc +- push %rbx +-.cfi_push %rbx + push %rbp + .cfi_push %rbp ++ mov %rsp,%rbp ++ push %rbx ++.cfi_push %rbx + push %r12 + .cfi_push %r12 + push %r13 +@@ -736,22 +827,18 @@ poly1305_blocks_avx: + + .Lproceed_avx: + mov %r15,$len +- +- mov 0(%rsp),%r15 ++ pop %r15 + .cfi_restore %r15 +- mov 8(%rsp),%r14 ++ pop %r14 + .cfi_restore %r14 +- mov 16(%rsp),%r13 ++ pop %r13 + .cfi_restore %r13 +- mov 24(%rsp),%r12 ++ pop %r12 + .cfi_restore %r12 +- mov 32(%rsp),%rbp +-.cfi_restore %rbp +- mov 40(%rsp),%rbx ++ pop %rbx + .cfi_restore %rbx +- lea 48(%rsp),%rax +- lea 48(%rsp),%rsp +-.cfi_adjust_cfa_offset -48 ++ pop %rbp ++.cfi_restore %rbp + .Lbase2_64_avx_epilogue: + jmp .Ldo_avx + .cfi_endproc +@@ -768,8 +855,11 @@ poly1305_blocks_avx: + .Ldo_avx: + ___ + $code.=<<___ if (!$win64); ++ lea 8(%rsp),%r10 ++.cfi_def_cfa_register %r10 ++ and \$-32,%rsp ++ sub \$-8,%rsp + lea -0x58(%rsp),%r11 +-.cfi_def_cfa %r11,0x60 + sub \$0x178,%rsp + ___ + $code.=<<___ if ($win64); +@@ -1361,18 +1451,18 @@ $code.=<<___ if ($win64); + .Ldo_avx_epilogue: + ___ + $code.=<<___ if (!$win64); +- lea 0x58(%r11),%rsp +-.cfi_def_cfa %rsp,8 ++ lea -8(%r10),%rsp ++.cfi_def_cfa_register %rsp + ___ + $code.=<<___; + vzeroupper + ret + .cfi_endproc +-.size poly1305_blocks_avx,.-poly1305_blocks_avx ++___ ++&end_function("poly1305_blocks_avx"); + +-.type poly1305_emit_avx,\@function,3 +-.align 32 +-poly1305_emit_avx: ++&declare_function("poly1305_emit_avx", 32, 3); ++$code.=<<___; + cmpl \$0,20($ctx) # is_base2_26? + je .Lemit + +@@ -1423,41 +1513,51 @@ poly1305_emit_avx: + mov %rcx,8($mac) + + ret +-.size poly1305_emit_avx,.-poly1305_emit_avx + ___ ++&end_function("poly1305_emit_avx"); ++ ++if ($kernel) { ++ $code .= "#endif\n"; ++} + + if ($avx>1) { ++ ++if ($kernel) { ++ $code .= "#ifdef CONFIG_AS_AVX2\n"; ++} ++ + my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) = + map("%ymm$_",(0..15)); + my $S4=$MASK; + ++sub poly1305_blocks_avxN { ++ my ($avx512) = @_; ++ my $suffix = $avx512 ? "_avx512" : ""; + $code.=<<___; +-.type poly1305_blocks_avx2,\@function,4 +-.align 32 +-poly1305_blocks_avx2: + .cfi_startproc + mov 20($ctx),%r8d # is_base2_26 + cmp \$128,$len +- jae .Lblocks_avx2 ++ jae .Lblocks_avx2$suffix + test %r8d,%r8d + jz .Lblocks + +-.Lblocks_avx2: ++.Lblocks_avx2$suffix: + and \$-16,$len +- jz .Lno_data_avx2 ++ jz .Lno_data_avx2$suffix + + vzeroupper + + test %r8d,%r8d +- jz .Lbase2_64_avx2 ++ jz .Lbase2_64_avx2$suffix + + test \$63,$len +- jz .Leven_avx2 ++ jz .Leven_avx2$suffix + +- push %rbx +-.cfi_push %rbx + push %rbp + .cfi_push %rbp ++ mov %rsp,%rbp ++ push %rbx ++.cfi_push %rbx + push %r12 + .cfi_push %r12 + push %r13 +@@ -1466,7 +1566,7 @@ poly1305_blocks_avx2: + .cfi_push %r14 + push %r15 + .cfi_push %r15 +-.Lblocks_avx2_body: ++.Lblocks_avx2_body$suffix: + + mov $len,%r15 # reassign $len + +@@ -1513,7 +1613,7 @@ poly1305_blocks_avx2: + shr \$2,$s1 + add $r1,$s1 # s1 = r1 + (r1 >> 2) + +-.Lbase2_26_pre_avx2: ++.Lbase2_26_pre_avx2$suffix: + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp +@@ -1524,10 +1624,10 @@ poly1305_blocks_avx2: + mov $r1,%rax + + test \$63,%r15 +- jnz .Lbase2_26_pre_avx2 ++ jnz .Lbase2_26_pre_avx2$suffix + + test $padbit,$padbit # if $padbit is zero, +- jz .Lstore_base2_64_avx2 # store hash in base 2^64 format ++ jz .Lstore_base2_64_avx2$suffix # store hash in base 2^64 format + + ################################# base 2^64 -> base 2^26 + mov $h0,%rax +@@ -1548,57 +1648,56 @@ poly1305_blocks_avx2: + or $r1,$h2 # h[4] + + test %r15,%r15 +- jz .Lstore_base2_26_avx2 ++ jz .Lstore_base2_26_avx2$suffix + + vmovd %rax#d,%x#$H0 + vmovd %rdx#d,%x#$H1 + vmovd $h0#d,%x#$H2 + vmovd $h1#d,%x#$H3 + vmovd $h2#d,%x#$H4 +- jmp .Lproceed_avx2 ++ jmp .Lproceed_avx2$suffix + + .align 32 +-.Lstore_base2_64_avx2: ++.Lstore_base2_64_avx2$suffix: + mov $h0,0($ctx) + mov $h1,8($ctx) + mov $h2,16($ctx) # note that is_base2_26 is zeroed +- jmp .Ldone_avx2 ++ jmp .Ldone_avx2$suffix + + .align 16 +-.Lstore_base2_26_avx2: ++.Lstore_base2_26_avx2$suffix: + mov %rax#d,0($ctx) # store hash value base 2^26 + mov %rdx#d,4($ctx) + mov $h0#d,8($ctx) + mov $h1#d,12($ctx) + mov $h2#d,16($ctx) + .align 16 +-.Ldone_avx2: +- mov 0(%rsp),%r15 ++.Ldone_avx2$suffix: ++ pop %r15 + .cfi_restore %r15 +- mov 8(%rsp),%r14 ++ pop %r14 + .cfi_restore %r14 +- mov 16(%rsp),%r13 ++ pop %r13 + .cfi_restore %r13 +- mov 24(%rsp),%r12 ++ pop %r12 + .cfi_restore %r12 +- mov 32(%rsp),%rbp +-.cfi_restore %rbp +- mov 40(%rsp),%rbx ++ pop %rbx + .cfi_restore %rbx +- lea 48(%rsp),%rsp +-.cfi_adjust_cfa_offset -48 +-.Lno_data_avx2: +-.Lblocks_avx2_epilogue: ++ pop %rbp ++.cfi_restore %rbp ++.Lno_data_avx2$suffix: ++.Lblocks_avx2_epilogue$suffix: + ret + .cfi_endproc + + .align 32 +-.Lbase2_64_avx2: ++.Lbase2_64_avx2$suffix: + .cfi_startproc +- push %rbx +-.cfi_push %rbx + push %rbp + .cfi_push %rbp ++ mov %rsp,%rbp ++ push %rbx ++.cfi_push %rbx + push %r12 + .cfi_push %r12 + push %r13 +@@ -1607,7 +1706,7 @@ poly1305_blocks_avx2: + .cfi_push %r14 + push %r15 + .cfi_push %r15 +-.Lbase2_64_avx2_body: ++.Lbase2_64_avx2_body$suffix: + + mov $len,%r15 # reassign $len + +@@ -1624,9 +1723,9 @@ poly1305_blocks_avx2: + add $r1,$s1 # s1 = r1 + (r1 >> 2) + + test \$63,$len +- jz .Linit_avx2 ++ jz .Linit_avx2$suffix + +-.Lbase2_64_pre_avx2: ++.Lbase2_64_pre_avx2$suffix: + add 0($inp),$h0 # accumulate input + adc 8($inp),$h1 + lea 16($inp),$inp +@@ -1637,9 +1736,9 @@ poly1305_blocks_avx2: + mov $r1,%rax + + test \$63,%r15 +- jnz .Lbase2_64_pre_avx2 ++ jnz .Lbase2_64_pre_avx2$suffix + +-.Linit_avx2: ++.Linit_avx2$suffix: + ################################# base 2^64 -> base 2^26 + mov $h0,%rax + mov $h0,%rdx +@@ -1667,69 +1766,77 @@ poly1305_blocks_avx2: + + call __poly1305_init_avx + +-.Lproceed_avx2: ++.Lproceed_avx2$suffix: + mov %r15,$len # restore $len +- mov OPENSSL_ia32cap_P+8(%rip),%r10d ++___ ++$code.=<<___ if (!$kernel); ++ mov OPENSSL_ia32cap_P+8(%rip),%r9d + mov \$`(1<<31|1<<30|1<<16)`,%r11d +- +- mov 0(%rsp),%r15 ++___ ++$code.=<<___; ++ pop %r15 + .cfi_restore %r15 +- mov 8(%rsp),%r14 ++ pop %r14 + .cfi_restore %r14 +- mov 16(%rsp),%r13 ++ pop %r13 + .cfi_restore %r13 +- mov 24(%rsp),%r12 ++ pop %r12 + .cfi_restore %r12 +- mov 32(%rsp),%rbp +-.cfi_restore %rbp +- mov 40(%rsp),%rbx ++ pop %rbx + .cfi_restore %rbx +- lea 48(%rsp),%rax +- lea 48(%rsp),%rsp +-.cfi_adjust_cfa_offset -48 +-.Lbase2_64_avx2_epilogue: +- jmp .Ldo_avx2 ++ pop %rbp ++.cfi_restore %rbp ++.Lbase2_64_avx2_epilogue$suffix: ++ jmp .Ldo_avx2$suffix + .cfi_endproc + + .align 32 +-.Leven_avx2: ++.Leven_avx2$suffix: + .cfi_startproc +- mov OPENSSL_ia32cap_P+8(%rip),%r10d ++___ ++$code.=<<___ if (!$kernel); ++ mov OPENSSL_ia32cap_P+8(%rip),%r9d ++___ ++$code.=<<___; + vmovd 4*0($ctx),%x#$H0 # load hash value base 2^26 + vmovd 4*1($ctx),%x#$H1 + vmovd 4*2($ctx),%x#$H2 + vmovd 4*3($ctx),%x#$H3 + vmovd 4*4($ctx),%x#$H4 + +-.Ldo_avx2: ++.Ldo_avx2$suffix: + ___ +-$code.=<<___ if ($avx>2); ++$code.=<<___ if (!$kernel && $avx>2); + cmp \$512,$len + jb .Lskip_avx512 +- and %r11d,%r10d +- test \$`1<<16`,%r10d # check for AVX512F ++ and %r11d,%r9d ++ test \$`1<<16`,%r9d # check for AVX512F + jnz .Lblocks_avx512 +-.Lskip_avx512: ++.Lskip_avx512$suffix: ++___ ++$code.=<<___ if ($avx > 2 && $avx512 && $kernel); ++ cmp \$512,$len ++ jae .Lblocks_avx512 + ___ + $code.=<<___ if (!$win64); +- lea -8(%rsp),%r11 +-.cfi_def_cfa %r11,16 ++ lea 8(%rsp),%r10 ++.cfi_def_cfa_register %r10 + sub \$0x128,%rsp + ___ + $code.=<<___ if ($win64); +- lea -0xf8(%rsp),%r11 ++ lea 8(%rsp),%r10 + sub \$0x1c8,%rsp +- vmovdqa %xmm6,0x50(%r11) +- vmovdqa %xmm7,0x60(%r11) +- vmovdqa %xmm8,0x70(%r11) +- vmovdqa %xmm9,0x80(%r11) +- vmovdqa %xmm10,0x90(%r11) +- vmovdqa %xmm11,0xa0(%r11) +- vmovdqa %xmm12,0xb0(%r11) +- vmovdqa %xmm13,0xc0(%r11) +- vmovdqa %xmm14,0xd0(%r11) +- vmovdqa %xmm15,0xe0(%r11) +-.Ldo_avx2_body: ++ vmovdqa %xmm6,-0xb0(%r10) ++ vmovdqa %xmm7,-0xa0(%r10) ++ vmovdqa %xmm8,-0x90(%r10) ++ vmovdqa %xmm9,-0x80(%r10) ++ vmovdqa %xmm10,-0x70(%r10) ++ vmovdqa %xmm11,-0x60(%r10) ++ vmovdqa %xmm12,-0x50(%r10) ++ vmovdqa %xmm13,-0x40(%r10) ++ vmovdqa %xmm14,-0x30(%r10) ++ vmovdqa %xmm15,-0x20(%r10) ++.Ldo_avx2_body$suffix: + ___ + $code.=<<___; + lea .Lconst(%rip),%rcx +@@ -1794,11 +1901,11 @@ $code.=<<___; + + vpaddq $H2,$T2,$H2 # accumulate input + sub \$64,$len +- jz .Ltail_avx2 +- jmp .Loop_avx2 ++ jz .Ltail_avx2$suffix ++ jmp .Loop_avx2$suffix + + .align 32 +-.Loop_avx2: ++.Loop_avx2$suffix: + ################################################################ + # ((inp[0]*r^4+inp[4])*r^4+inp[ 8])*r^4 + # ((inp[1]*r^4+inp[5])*r^4+inp[ 9])*r^3 +@@ -1946,10 +2053,10 @@ $code.=<<___; + vpor 32(%rcx),$T4,$T4 # padbit, yes, always + + sub \$64,$len +- jnz .Loop_avx2 ++ jnz .Loop_avx2$suffix + + .byte 0x66,0x90 +-.Ltail_avx2: ++.Ltail_avx2$suffix: + ################################################################ + # while above multiplications were by r^4 in all lanes, in last + # iteration we multiply least significant lane by r^4 and most +@@ -2087,37 +2194,29 @@ $code.=<<___; + vmovd %x#$H4,`4*4-48-64`($ctx) + ___ + $code.=<<___ if ($win64); +- vmovdqa 0x50(%r11),%xmm6 +- vmovdqa 0x60(%r11),%xmm7 +- vmovdqa 0x70(%r11),%xmm8 +- vmovdqa 0x80(%r11),%xmm9 +- vmovdqa 0x90(%r11),%xmm10 +- vmovdqa 0xa0(%r11),%xmm11 +- vmovdqa 0xb0(%r11),%xmm12 +- vmovdqa 0xc0(%r11),%xmm13 +- vmovdqa 0xd0(%r11),%xmm14 +- vmovdqa 0xe0(%r11),%xmm15 +- lea 0xf8(%r11),%rsp +-.Ldo_avx2_epilogue: ++ vmovdqa -0xb0(%r10),%xmm6 ++ vmovdqa -0xa0(%r10),%xmm7 ++ vmovdqa -0x90(%r10),%xmm8 ++ vmovdqa -0x80(%r10),%xmm9 ++ vmovdqa -0x70(%r10),%xmm10 ++ vmovdqa -0x60(%r10),%xmm11 ++ vmovdqa -0x50(%r10),%xmm12 ++ vmovdqa -0x40(%r10),%xmm13 ++ vmovdqa -0x30(%r10),%xmm14 ++ vmovdqa -0x20(%r10),%xmm15 ++ lea -8(%r10),%rsp ++.Ldo_avx2_epilogue$suffix: + ___ + $code.=<<___ if (!$win64); +- lea 8(%r11),%rsp +-.cfi_def_cfa %rsp,8 ++ lea -8(%r10),%rsp ++.cfi_def_cfa_register %rsp + ___ + $code.=<<___; + vzeroupper + ret + .cfi_endproc +-.size poly1305_blocks_avx2,.-poly1305_blocks_avx2 + ___ +-####################################################################### +-if ($avx>2) { +-# On entry we have input length divisible by 64. But since inner loop +-# processes 128 bytes per iteration, cases when length is not divisible +-# by 128 are handled by passing tail 64 bytes to .Ltail_avx2. For this +-# reason stack layout is kept identical to poly1305_blocks_avx2. If not +-# for this tail, we wouldn't have to even allocate stack frame... +- ++if($avx > 2 && $avx512) { + my ($R0,$R1,$R2,$R3,$R4, $S1,$S2,$S3,$S4) = map("%zmm$_",(16..24)); + my ($M0,$M1,$M2,$M3,$M4) = map("%zmm$_",(25..29)); + my $PADBIT="%zmm30"; +@@ -2128,32 +2227,29 @@ map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4)); + map(s/%y/%z/,($MASK)); + + $code.=<<___; +-.type poly1305_blocks_avx512,\@function,4 +-.align 32 +-poly1305_blocks_avx512: + .cfi_startproc + .Lblocks_avx512: + mov \$15,%eax + kmovw %eax,%k2 + ___ + $code.=<<___ if (!$win64); +- lea -8(%rsp),%r11 +-.cfi_def_cfa %r11,16 ++ lea 8(%rsp),%r10 ++.cfi_def_cfa_register %r10 + sub \$0x128,%rsp + ___ + $code.=<<___ if ($win64); +- lea -0xf8(%rsp),%r11 ++ lea 8(%rsp),%r10 + sub \$0x1c8,%rsp +- vmovdqa %xmm6,0x50(%r11) +- vmovdqa %xmm7,0x60(%r11) +- vmovdqa %xmm8,0x70(%r11) +- vmovdqa %xmm9,0x80(%r11) +- vmovdqa %xmm10,0x90(%r11) +- vmovdqa %xmm11,0xa0(%r11) +- vmovdqa %xmm12,0xb0(%r11) +- vmovdqa %xmm13,0xc0(%r11) +- vmovdqa %xmm14,0xd0(%r11) +- vmovdqa %xmm15,0xe0(%r11) ++ vmovdqa %xmm6,-0xb0(%r10) ++ vmovdqa %xmm7,-0xa0(%r10) ++ vmovdqa %xmm8,-0x90(%r10) ++ vmovdqa %xmm9,-0x80(%r10) ++ vmovdqa %xmm10,-0x70(%r10) ++ vmovdqa %xmm11,-0x60(%r10) ++ vmovdqa %xmm12,-0x50(%r10) ++ vmovdqa %xmm13,-0x40(%r10) ++ vmovdqa %xmm14,-0x30(%r10) ++ vmovdqa %xmm15,-0x20(%r10) + .Ldo_avx512_body: + ___ + $code.=<<___; +@@ -2679,7 +2775,7 @@ $code.=<<___; + + lea 0x90(%rsp),%rax # size optimization for .Ltail_avx2 + add \$64,$len +- jnz .Ltail_avx2 ++ jnz .Ltail_avx2$suffix + + vpsubq $T2,$H2,$H2 # undo input accumulation + vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced +@@ -2690,29 +2786,61 @@ $code.=<<___; + vzeroall + ___ + $code.=<<___ if ($win64); +- movdqa 0x50(%r11),%xmm6 +- movdqa 0x60(%r11),%xmm7 +- movdqa 0x70(%r11),%xmm8 +- movdqa 0x80(%r11),%xmm9 +- movdqa 0x90(%r11),%xmm10 +- movdqa 0xa0(%r11),%xmm11 +- movdqa 0xb0(%r11),%xmm12 +- movdqa 0xc0(%r11),%xmm13 +- movdqa 0xd0(%r11),%xmm14 +- movdqa 0xe0(%r11),%xmm15 +- lea 0xf8(%r11),%rsp ++ movdqa -0xb0(%r10),%xmm6 ++ movdqa -0xa0(%r10),%xmm7 ++ movdqa -0x90(%r10),%xmm8 ++ movdqa -0x80(%r10),%xmm9 ++ movdqa -0x70(%r10),%xmm10 ++ movdqa -0x60(%r10),%xmm11 ++ movdqa -0x50(%r10),%xmm12 ++ movdqa -0x40(%r10),%xmm13 ++ movdqa -0x30(%r10),%xmm14 ++ movdqa -0x20(%r10),%xmm15 ++ lea -8(%r10),%rsp + .Ldo_avx512_epilogue: + ___ + $code.=<<___ if (!$win64); +- lea 8(%r11),%rsp +-.cfi_def_cfa %rsp,8 ++ lea -8(%r10),%rsp ++.cfi_def_cfa_register %rsp + ___ + $code.=<<___; + ret + .cfi_endproc +-.size poly1305_blocks_avx512,.-poly1305_blocks_avx512 + ___ +-if ($avx>3) { ++ ++} ++ ++} ++ ++&declare_function("poly1305_blocks_avx2", 32, 4); ++poly1305_blocks_avxN(0); ++&end_function("poly1305_blocks_avx2"); ++ ++if($kernel) { ++ $code .= "#endif\n"; ++} ++ ++####################################################################### ++if ($avx>2) { ++# On entry we have input length divisible by 64. But since inner loop ++# processes 128 bytes per iteration, cases when length is not divisible ++# by 128 are handled by passing tail 64 bytes to .Ltail_avx2. For this ++# reason stack layout is kept identical to poly1305_blocks_avx2. If not ++# for this tail, we wouldn't have to even allocate stack frame... ++ ++if($kernel) { ++ $code .= "#ifdef CONFIG_AS_AVX512\n"; ++} ++ ++&declare_function("poly1305_blocks_avx512", 32, 4); ++poly1305_blocks_avxN(1); ++&end_function("poly1305_blocks_avx512"); ++ ++if ($kernel) { ++ $code .= "#endif\n"; ++} ++ ++if (!$kernel && $avx>3) { + ######################################################################## + # VPMADD52 version using 2^44 radix. + # +@@ -3753,45 +3881,9 @@ poly1305_emit_base2_44: + .size poly1305_emit_base2_44,.-poly1305_emit_base2_44 + ___ + } } } +-$code.=<<___; +-.align 64 +-.Lconst: +-.Lmask24: +-.long 0x0ffffff,0,0x0ffffff,0,0x0ffffff,0,0x0ffffff,0 +-.L129: +-.long `1<<24`,0,`1<<24`,0,`1<<24`,0,`1<<24`,0 +-.Lmask26: +-.long 0x3ffffff,0,0x3ffffff,0,0x3ffffff,0,0x3ffffff,0 +-.Lpermd_avx2: +-.long 2,2,2,3,2,0,2,1 +-.Lpermd_avx512: +-.long 0,0,0,1, 0,2,0,3, 0,4,0,5, 0,6,0,7 +- +-.L2_44_inp_permd: +-.long 0,1,1,2,2,3,7,7 +-.L2_44_inp_shift: +-.quad 0,12,24,64 +-.L2_44_mask: +-.quad 0xfffffffffff,0xfffffffffff,0x3ffffffffff,0xffffffffffffffff +-.L2_44_shift_rgt: +-.quad 44,44,42,64 +-.L2_44_shift_lft: +-.quad 8,8,10,64 +- +-.align 64 +-.Lx_mask44: +-.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff +-.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff +-.Lx_mask42: +-.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff +-.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff +-___ + } +-$code.=<<___; +-.asciz "Poly1305 for x86_64, CRYPTOGAMS by " +-.align 16 +-___ + ++if (!$kernel) + { # chacha20-poly1305 helpers + my ($out,$inp,$otp,$len)=$win64 ? ("%rcx","%rdx","%r8", "%r9") : # Win64 order + ("%rdi","%rsi","%rdx","%rcx"); # Unix order +@@ -4038,17 +4130,17 @@ avx_handler: + + .section .pdata + .align 4 +- .rva .LSEH_begin_poly1305_init +- .rva .LSEH_end_poly1305_init +- .rva .LSEH_info_poly1305_init +- +- .rva .LSEH_begin_poly1305_blocks +- .rva .LSEH_end_poly1305_blocks +- .rva .LSEH_info_poly1305_blocks +- +- .rva .LSEH_begin_poly1305_emit +- .rva .LSEH_end_poly1305_emit +- .rva .LSEH_info_poly1305_emit ++ .rva .LSEH_begin_poly1305_init_x86_64 ++ .rva .LSEH_end_poly1305_init_x86_64 ++ .rva .LSEH_info_poly1305_init_x86_64 ++ ++ .rva .LSEH_begin_poly1305_blocks_x86_64 ++ .rva .LSEH_end_poly1305_blocks_x86_64 ++ .rva .LSEH_info_poly1305_blocks_x86_64 ++ ++ .rva .LSEH_begin_poly1305_emit_x86_64 ++ .rva .LSEH_end_poly1305_emit_x86_64 ++ .rva .LSEH_info_poly1305_emit_x86_64 + ___ + $code.=<<___ if ($avx); + .rva .LSEH_begin_poly1305_blocks_avx +@@ -4088,20 +4180,20 @@ ___ + $code.=<<___; + .section .xdata + .align 8 +-.LSEH_info_poly1305_init: ++.LSEH_info_poly1305_init_x86_64: + .byte 9,0,0,0 + .rva se_handler +- .rva .LSEH_begin_poly1305_init,.LSEH_begin_poly1305_init ++ .rva .LSEH_begin_poly1305_init_x86_64,.LSEH_begin_poly1305_init_x86_64 + +-.LSEH_info_poly1305_blocks: ++.LSEH_info_poly1305_blocks_x86_64: + .byte 9,0,0,0 + .rva se_handler + .rva .Lblocks_body,.Lblocks_epilogue + +-.LSEH_info_poly1305_emit: ++.LSEH_info_poly1305_emit_x86_64: + .byte 9,0,0,0 + .rva se_handler +- .rva .LSEH_begin_poly1305_emit,.LSEH_begin_poly1305_emit ++ .rva .LSEH_begin_poly1305_emit_x86_64,.LSEH_begin_poly1305_emit_x86_64 + ___ + $code.=<<___ if ($avx); + .LSEH_info_poly1305_blocks_avx_1: +@@ -4148,12 +4240,26 @@ $code.=<<___ if ($avx>2); + ___ + } + ++open SELF,$0; ++while() { ++ next if (/^#!/); ++ last if (!s/^#/\/\// and !/^$/); ++ print; ++} ++close SELF; ++ + foreach (split('\n',$code)) { + s/\`([^\`]*)\`/eval($1)/ge; + s/%r([a-z]+)#d/%e$1/g; + s/%r([0-9]+)#d/%r$1d/g; + s/%x#%[yz]/%x/g or s/%y#%z/%y/g or s/%z#%[yz]/%z/g; + ++ if ($kernel) { ++ s/(^\.type.*),[0-9]+$/\1/; ++ s/(^\.type.*),\@abi-omnipotent+$/\1,\@function/; ++ next if /^\.cfi.*/; ++ } ++ + print $_,"\n"; + } + close STDOUT; +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -1,8 +1,6 @@ +-// SPDX-License-Identifier: GPL-2.0-or-later ++// SPDX-License-Identifier: GPL-2.0 OR MIT + /* +- * Poly1305 authenticator algorithm, RFC7539, SIMD glue code +- * +- * Copyright (C) 2015 Martin Willi ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. + */ + + #include +@@ -13,279 +11,170 @@ + #include + #include + #include ++#include + #include + +-asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src, +- const u32 *r, unsigned int blocks); +-asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r, +- unsigned int blocks, const u32 *u); +-asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r, +- unsigned int blocks, const u32 *u); ++asmlinkage void poly1305_init_x86_64(void *ctx, ++ const u8 key[POLY1305_KEY_SIZE]); ++asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp, ++ const size_t len, const u32 padbit); ++asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], ++ const u32 nonce[4]); ++asmlinkage void poly1305_emit_avx(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], ++ const u32 nonce[4]); ++asmlinkage void poly1305_blocks_avx(void *ctx, const u8 *inp, const size_t len, ++ const u32 padbit); ++asmlinkage void poly1305_blocks_avx2(void *ctx, const u8 *inp, const size_t len, ++ const u32 padbit); ++asmlinkage void poly1305_blocks_avx512(void *ctx, const u8 *inp, ++ const size_t len, const u32 padbit); + +-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_simd); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx); + static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2); ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx512); + +-static inline u64 mlt(u64 a, u64 b) +-{ +- return a * b; +-} +- +-static inline u32 sr(u64 v, u_char n) +-{ +- return v >> n; +-} +- +-static inline u32 and(u32 v, u32 mask) +-{ +- return v & mask; +-} +- +-static void poly1305_simd_mult(u32 *a, const u32 *b) +-{ +- u8 m[POLY1305_BLOCK_SIZE]; +- +- memset(m, 0, sizeof(m)); +- /* The poly1305 block function adds a hi-bit to the accumulator which +- * we don't need for key multiplication; compensate for it. */ +- a[4] -= 1 << 24; +- poly1305_block_sse2(a, m, b, 1); +-} +- +-static void poly1305_integer_setkey(struct poly1305_key *key, const u8 *raw_key) +-{ +- /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ +- key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff; +- key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03; +- key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff; +- key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff; +- key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff; +-} ++struct poly1305_arch_internal { ++ union { ++ struct { ++ u32 h[5]; ++ u32 is_base2_26; ++ }; ++ u64 hs[3]; ++ }; ++ u64 r[2]; ++ u64 pad; ++ struct { u32 r2, r1, r4, r3; } rn[9]; ++}; + +-static void poly1305_integer_blocks(struct poly1305_state *state, +- const struct poly1305_key *key, +- const void *src, +- unsigned int nblocks, u32 hibit) ++/* The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit ++ * the unfortunate situation of using AVX and then having to go back to scalar ++ * -- because the user is silly and has called the update function from two ++ * separate contexts -- then we need to convert back to the original base before ++ * proceeding. It is possible to reason that the initial reduction below is ++ * sufficient given the implementation invariants. However, for an avoidance of ++ * doubt and because this is not performance critical, we do the full reduction ++ * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py ++ */ ++static void convert_to_base2_64(void *ctx) + { +- u32 r0, r1, r2, r3, r4; +- u32 s1, s2, s3, s4; +- u32 h0, h1, h2, h3, h4; +- u64 d0, d1, d2, d3, d4; ++ struct poly1305_arch_internal *state = ctx; ++ u32 cy; + +- if (!nblocks) ++ if (!state->is_base2_26) + return; + +- r0 = key->r[0]; +- r1 = key->r[1]; +- r2 = key->r[2]; +- r3 = key->r[3]; +- r4 = key->r[4]; +- +- s1 = r1 * 5; +- s2 = r2 * 5; +- s3 = r3 * 5; +- s4 = r4 * 5; +- +- h0 = state->h[0]; +- h1 = state->h[1]; +- h2 = state->h[2]; +- h3 = state->h[3]; +- h4 = state->h[4]; +- +- do { +- /* h += m[i] */ +- h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff; +- h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff; +- h2 += (get_unaligned_le32(src + 6) >> 4) & 0x3ffffff; +- h3 += (get_unaligned_le32(src + 9) >> 6) & 0x3ffffff; +- h4 += (get_unaligned_le32(src + 12) >> 8) | (hibit << 24); +- +- /* h *= r */ +- d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) + +- mlt(h3, s2) + mlt(h4, s1); +- d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) + +- mlt(h3, s3) + mlt(h4, s2); +- d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) + +- mlt(h3, s4) + mlt(h4, s3); +- d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) + +- mlt(h3, r0) + mlt(h4, s4); +- d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) + +- mlt(h3, r1) + mlt(h4, r0); +- +- /* (partial) h %= p */ +- d1 += sr(d0, 26); h0 = and(d0, 0x3ffffff); +- d2 += sr(d1, 26); h1 = and(d1, 0x3ffffff); +- d3 += sr(d2, 26); h2 = and(d2, 0x3ffffff); +- d4 += sr(d3, 26); h3 = and(d3, 0x3ffffff); +- h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff); +- h1 += h0 >> 26; h0 = h0 & 0x3ffffff; +- +- src += POLY1305_BLOCK_SIZE; +- } while (--nblocks); +- +- state->h[0] = h0; +- state->h[1] = h1; +- state->h[2] = h2; +- state->h[3] = h3; +- state->h[4] = h4; +-} +- +-static void poly1305_integer_emit(const struct poly1305_state *state, void *dst) +-{ +- u32 h0, h1, h2, h3, h4; +- u32 g0, g1, g2, g3, g4; +- u32 mask; +- +- /* fully carry h */ +- h0 = state->h[0]; +- h1 = state->h[1]; +- h2 = state->h[2]; +- h3 = state->h[3]; +- h4 = state->h[4]; +- +- h2 += (h1 >> 26); h1 = h1 & 0x3ffffff; +- h3 += (h2 >> 26); h2 = h2 & 0x3ffffff; +- h4 += (h3 >> 26); h3 = h3 & 0x3ffffff; +- h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff; +- h1 += (h0 >> 26); h0 = h0 & 0x3ffffff; +- +- /* compute h + -p */ +- g0 = h0 + 5; +- g1 = h1 + (g0 >> 26); g0 &= 0x3ffffff; +- g2 = h2 + (g1 >> 26); g1 &= 0x3ffffff; +- g3 = h3 + (g2 >> 26); g2 &= 0x3ffffff; +- g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff; +- +- /* select h if h < p, or h + -p if h >= p */ +- mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1; +- g0 &= mask; +- g1 &= mask; +- g2 &= mask; +- g3 &= mask; +- g4 &= mask; +- mask = ~mask; +- h0 = (h0 & mask) | g0; +- h1 = (h1 & mask) | g1; +- h2 = (h2 & mask) | g2; +- h3 = (h3 & mask) | g3; +- h4 = (h4 & mask) | g4; +- +- /* h = h % (2^128) */ +- put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0); +- put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4); +- put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8); +- put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12); +-} +- +-void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key) +-{ +- poly1305_integer_setkey(desc->opaque_r, key); +- desc->s[0] = get_unaligned_le32(key + 16); +- desc->s[1] = get_unaligned_le32(key + 20); +- desc->s[2] = get_unaligned_le32(key + 24); +- desc->s[3] = get_unaligned_le32(key + 28); +- poly1305_core_init(&desc->h); +- desc->buflen = 0; +- desc->sset = true; +- desc->rset = 1; +-} +-EXPORT_SYMBOL_GPL(poly1305_init_arch); +- +-static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen) +-{ +- if (!dctx->sset) { +- if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_integer_setkey(dctx->r, src); +- src += POLY1305_BLOCK_SIZE; +- srclen -= POLY1305_BLOCK_SIZE; +- dctx->rset = 1; +- } +- if (srclen >= 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; +- srclen -= POLY1305_BLOCK_SIZE; +- dctx->sset = true; +- } ++ cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy; ++ cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy; ++ cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy; ++ cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy; ++ state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0]; ++ state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12); ++ state->hs[2] = state->h[4] >> 24; ++#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1)) ++ cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL); ++ state->hs[2] &= 3; ++ state->hs[0] += cy; ++ state->hs[1] += (cy = ULT(state->hs[0], cy)); ++ state->hs[2] += ULT(state->hs[1], cy); ++#undef ULT ++ state->is_base2_26 = 0; ++} ++ ++static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_KEY_SIZE]) ++{ ++ poly1305_init_x86_64(ctx, key); ++} ++ ++static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, ++ const u32 padbit) ++{ ++ struct poly1305_arch_internal *state = ctx; ++ ++ /* SIMD disables preemption, so relax after processing each page. */ ++ BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || ++ PAGE_SIZE % POLY1305_BLOCK_SIZE); ++ ++ if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || ++ (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || ++ !crypto_simd_usable()) { ++ convert_to_base2_64(ctx); ++ poly1305_blocks_x86_64(ctx, inp, len, padbit); ++ return; + } +- return srclen; +-} + +-static unsigned int poly1305_scalar_blocks(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen) +-{ +- unsigned int datalen; ++ for (;;) { ++ const size_t bytes = min_t(size_t, len, PAGE_SIZE); + +- if (unlikely(!dctx->sset)) { +- datalen = crypto_poly1305_setdesckey(dctx, src, srclen); +- src += srclen - datalen; +- srclen = datalen; +- } +- if (srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_integer_blocks(&dctx->h, dctx->opaque_r, src, +- srclen / POLY1305_BLOCK_SIZE, 1); +- srclen %= POLY1305_BLOCK_SIZE; ++ kernel_fpu_begin(); ++ if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) ++ poly1305_blocks_avx512(ctx, inp, bytes, padbit); ++ else if (IS_ENABLED(CONFIG_AS_AVX2) && static_branch_likely(&poly1305_use_avx2)) ++ poly1305_blocks_avx2(ctx, inp, bytes, padbit); ++ else ++ poly1305_blocks_avx(ctx, inp, bytes, padbit); ++ kernel_fpu_end(); ++ len -= bytes; ++ if (!len) ++ break; ++ inp += bytes; + } +- return srclen; + } + +-static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, +- const u8 *src, unsigned int srclen) +-{ +- unsigned int blocks, datalen; ++static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], ++ const u32 nonce[4]) ++{ ++ struct poly1305_arch_internal *state = ctx; ++ ++ if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || ++ !state->is_base2_26 || !crypto_simd_usable()) { ++ convert_to_base2_64(ctx); ++ poly1305_emit_x86_64(ctx, mac, nonce); ++ } else ++ poly1305_emit_avx(ctx, mac, nonce); ++} ++ ++void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) ++{ ++ poly1305_simd_init(&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; ++ dctx->sset = true; ++} ++EXPORT_SYMBOL(poly1305_init_arch); + ++static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx, ++ const u8 *inp, unsigned int len) ++{ ++ unsigned int acc = 0; + if (unlikely(!dctx->sset)) { +- datalen = crypto_poly1305_setdesckey(dctx, src, srclen); +- src += srclen - datalen; +- srclen = datalen; +- } +- +- if (IS_ENABLED(CONFIG_AS_AVX2) && +- static_branch_likely(&poly1305_use_avx2) && +- srclen >= POLY1305_BLOCK_SIZE * 4) { +- if (unlikely(dctx->rset < 4)) { +- if (dctx->rset < 2) { +- dctx->r[1] = dctx->r[0]; +- poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r); +- } +- dctx->r[2] = dctx->r[1]; +- poly1305_simd_mult(dctx->r[2].r, dctx->r[0].r); +- dctx->r[3] = dctx->r[2]; +- poly1305_simd_mult(dctx->r[3].r, dctx->r[0].r); +- dctx->rset = 4; ++ if (!dctx->rset && len >= POLY1305_BLOCK_SIZE) { ++ poly1305_simd_init(&dctx->h, inp); ++ inp += POLY1305_BLOCK_SIZE; ++ len -= POLY1305_BLOCK_SIZE; ++ acc += POLY1305_BLOCK_SIZE; ++ dctx->rset = 1; + } +- blocks = srclen / (POLY1305_BLOCK_SIZE * 4); +- poly1305_4block_avx2(dctx->h.h, src, dctx->r[0].r, blocks, +- dctx->r[1].r); +- src += POLY1305_BLOCK_SIZE * 4 * blocks; +- srclen -= POLY1305_BLOCK_SIZE * 4 * blocks; +- } +- +- if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) { +- if (unlikely(dctx->rset < 2)) { +- dctx->r[1] = dctx->r[0]; +- poly1305_simd_mult(dctx->r[1].r, dctx->r[0].r); +- dctx->rset = 2; ++ if (len >= POLY1305_BLOCK_SIZE) { ++ dctx->s[0] = get_unaligned_le32(&inp[0]); ++ dctx->s[1] = get_unaligned_le32(&inp[4]); ++ dctx->s[2] = get_unaligned_le32(&inp[8]); ++ dctx->s[3] = get_unaligned_le32(&inp[12]); ++ inp += POLY1305_BLOCK_SIZE; ++ len -= POLY1305_BLOCK_SIZE; ++ acc += POLY1305_BLOCK_SIZE; ++ dctx->sset = true; + } +- blocks = srclen / (POLY1305_BLOCK_SIZE * 2); +- poly1305_2block_sse2(dctx->h.h, src, dctx->r[0].r, +- blocks, dctx->r[1].r); +- src += POLY1305_BLOCK_SIZE * 2 * blocks; +- srclen -= POLY1305_BLOCK_SIZE * 2 * blocks; +- } +- if (srclen >= POLY1305_BLOCK_SIZE) { +- poly1305_block_sse2(dctx->h.h, src, dctx->r[0].r, 1); +- srclen -= POLY1305_BLOCK_SIZE; + } +- return srclen; ++ return acc; + } + + void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, + unsigned int srclen) + { +- unsigned int bytes; ++ unsigned int bytes, used; + + if (unlikely(dctx->buflen)) { + bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen); +@@ -295,31 +184,19 @@ void poly1305_update_arch(struct poly130 + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { +- if (static_branch_likely(&poly1305_use_simd) && +- likely(crypto_simd_usable())) { +- kernel_fpu_begin(); +- poly1305_simd_blocks(dctx, dctx->buf, +- POLY1305_BLOCK_SIZE); +- kernel_fpu_end(); +- } else { +- poly1305_scalar_blocks(dctx, dctx->buf, +- POLY1305_BLOCK_SIZE); +- } ++ if (likely(!crypto_poly1305_setdctxkey(dctx, dctx->buf, POLY1305_BLOCK_SIZE))) ++ poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1); + dctx->buflen = 0; + } + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { +- if (static_branch_likely(&poly1305_use_simd) && +- likely(crypto_simd_usable())) { +- kernel_fpu_begin(); +- bytes = poly1305_simd_blocks(dctx, src, srclen); +- kernel_fpu_end(); +- } else { +- bytes = poly1305_scalar_blocks(dctx, src, srclen); +- } +- src += srclen - bytes; +- srclen = bytes; ++ bytes = round_down(srclen, POLY1305_BLOCK_SIZE); ++ srclen -= bytes; ++ used = crypto_poly1305_setdctxkey(dctx, src, bytes); ++ if (likely(bytes - used)) ++ poly1305_simd_blocks(&dctx->h, src + used, bytes - used, 1); ++ src += bytes; + } + + if (unlikely(srclen)) { +@@ -329,31 +206,17 @@ void poly1305_update_arch(struct poly130 + } + EXPORT_SYMBOL(poly1305_update_arch); + +-void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *dst) ++void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst) + { +- __le32 digest[4]; +- u64 f = 0; +- +- if (unlikely(desc->buflen)) { +- desc->buf[desc->buflen++] = 1; +- memset(desc->buf + desc->buflen, 0, +- POLY1305_BLOCK_SIZE - desc->buflen); +- poly1305_integer_blocks(&desc->h, desc->opaque_r, desc->buf, 1, 0); ++ if (unlikely(dctx->buflen)) { ++ dctx->buf[dctx->buflen++] = 1; ++ memset(dctx->buf + dctx->buflen, 0, ++ POLY1305_BLOCK_SIZE - dctx->buflen); ++ poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + +- poly1305_integer_emit(&desc->h, digest); +- +- /* mac = (h + s) % (2^128) */ +- f = (f >> 32) + le32_to_cpu(digest[0]) + desc->s[0]; +- put_unaligned_le32(f, dst + 0); +- f = (f >> 32) + le32_to_cpu(digest[1]) + desc->s[1]; +- put_unaligned_le32(f, dst + 4); +- f = (f >> 32) + le32_to_cpu(digest[2]) + desc->s[2]; +- put_unaligned_le32(f, dst + 8); +- f = (f >> 32) + le32_to_cpu(digest[3]) + desc->s[3]; +- put_unaligned_le32(f, dst + 12); +- +- *desc = (struct poly1305_desc_ctx){}; ++ poly1305_simd_emit(&dctx->h, dst, dctx->s); ++ *dctx = (struct poly1305_desc_ctx){}; + } + EXPORT_SYMBOL(poly1305_final_arch); + +@@ -361,38 +224,34 @@ static int crypto_poly1305_init(struct s + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + +- poly1305_core_init(&dctx->h); +- dctx->buflen = 0; +- dctx->rset = 0; +- dctx->sset = false; +- ++ *dctx = (struct poly1305_desc_ctx){}; + return 0; + } + +-static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) ++static int crypto_poly1305_update(struct shash_desc *desc, ++ const u8 *src, unsigned int srclen) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + +- if (unlikely(!dctx->sset)) +- return -ENOKEY; +- +- poly1305_final_arch(dctx, dst); ++ poly1305_update_arch(dctx, src, srclen); + return 0; + } + +-static int poly1305_simd_update(struct shash_desc *desc, +- const u8 *src, unsigned int srclen) ++static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) + { + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + +- poly1305_update_arch(dctx, src, srclen); ++ if (unlikely(!dctx->sset)) ++ return -ENOKEY; ++ ++ poly1305_final_arch(dctx, dst); + return 0; + } + + static struct shash_alg alg = { + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_poly1305_init, +- .update = poly1305_simd_update, ++ .update = crypto_poly1305_update, + .final = crypto_poly1305_final, + .descsize = sizeof(struct poly1305_desc_ctx), + .base = { +@@ -406,17 +265,19 @@ static struct shash_alg alg = { + + static int __init poly1305_simd_mod_init(void) + { +- if (!boot_cpu_has(X86_FEATURE_XMM2)) +- return 0; +- +- static_branch_enable(&poly1305_use_simd); +- +- if (IS_ENABLED(CONFIG_AS_AVX2) && +- boot_cpu_has(X86_FEATURE_AVX) && ++ if (IS_ENABLED(CONFIG_AS_AVX) && boot_cpu_has(X86_FEATURE_AVX) && ++ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) ++ static_branch_enable(&poly1305_use_avx); ++ if (IS_ENABLED(CONFIG_AS_AVX2) && boot_cpu_has(X86_FEATURE_AVX) && + boot_cpu_has(X86_FEATURE_AVX2) && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) + static_branch_enable(&poly1305_use_avx2); +- ++ if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && ++ boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) && ++ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) && ++ /* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */ ++ boot_cpu_data.x86_model != INTEL_FAM6_SKYLAKE_X) ++ static_branch_enable(&poly1305_use_avx512); + return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0; + } + +@@ -430,7 +291,7 @@ module_init(poly1305_simd_mod_init); + module_exit(poly1305_simd_mod_exit); + + MODULE_LICENSE("GPL"); +-MODULE_AUTHOR("Martin Willi "); ++MODULE_AUTHOR("Jason A. Donenfeld "); + MODULE_DESCRIPTION("Poly1305 authenticator"); + MODULE_ALIAS_CRYPTO("poly1305"); + MODULE_ALIAS_CRYPTO("poly1305-simd"); +--- a/lib/crypto/Kconfig ++++ b/lib/crypto/Kconfig +@@ -90,7 +90,7 @@ config CRYPTO_LIB_DES + config CRYPTO_LIB_POLY1305_RSIZE + int + default 2 if MIPS +- default 4 if X86_64 ++ default 11 if X86_64 + default 9 if ARM || ARM64 + default 1 + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0044-crypto-arm-arm64-mips-poly1305-remove-redundant-non-.patch b/target/linux/generic/backport-5.4/080-wireguard-0044-crypto-arm-arm64-mips-poly1305-remove-redundant-non-.patch new file mode 100644 index 0000000000..e1c719fc01 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0044-crypto-arm-arm64-mips-poly1305-remove-redundant-non-.patch @@ -0,0 +1,171 @@ +From 3b1cffd5e47b394b8c0a92583e26acf599022364 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 5 Jan 2020 22:40:49 -0500 +Subject: [PATCH 044/124] crypto: {arm,arm64,mips}/poly1305 - remove redundant + non-reduction from emit +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit 31899908a0d248b030b4464425b86c717e0007d4 upstream. + +This appears to be some kind of copy and paste error, and is actually +dead code. + +Pre: f = 0 ⇒ (f >> 32) = 0 + f = (f >> 32) + le32_to_cpu(digest[0]); +Post: 0 ≤ f < 2³² + put_unaligned_le32(f, dst); + +Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0 + f = (f >> 32) + le32_to_cpu(digest[1]); +Post: 0 ≤ f < 2³² + put_unaligned_le32(f, dst + 4); + +Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0 + f = (f >> 32) + le32_to_cpu(digest[2]); +Post: 0 ≤ f < 2³² + put_unaligned_le32(f, dst + 8); + +Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0 + f = (f >> 32) + le32_to_cpu(digest[3]); +Post: 0 ≤ f < 2³² + put_unaligned_le32(f, dst + 12); + +Therefore this sequence is redundant. And Andy's code appears to handle +misalignment acceptably. + +Signed-off-by: Jason A. Donenfeld +Tested-by: Ard Biesheuvel +Reviewed-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/poly1305-glue.c | 18 ++---------------- + arch/arm64/crypto/poly1305-glue.c | 18 ++---------------- + arch/mips/crypto/poly1305-glue.c | 18 ++---------------- + 3 files changed, 6 insertions(+), 48 deletions(-) + +--- a/arch/arm/crypto/poly1305-glue.c ++++ b/arch/arm/crypto/poly1305-glue.c +@@ -20,7 +20,7 @@ + + void poly1305_init_arm(void *state, const u8 *key); + void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit); +-void poly1305_emit_arm(void *state, __le32 *digest, const u32 *nonce); ++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) + { +@@ -179,9 +179,6 @@ EXPORT_SYMBOL(poly1305_update_arch); + + void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst) + { +- __le32 digest[4]; +- u64 f = 0; +- + if (unlikely(dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, +@@ -189,18 +186,7 @@ void poly1305_final_arch(struct poly1305 + poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + +- poly1305_emit_arm(&dctx->h, digest, dctx->s); +- +- /* mac = (h + s) % (2^128) */ +- f = (f >> 32) + le32_to_cpu(digest[0]); +- put_unaligned_le32(f, dst); +- f = (f >> 32) + le32_to_cpu(digest[1]); +- put_unaligned_le32(f, dst + 4); +- f = (f >> 32) + le32_to_cpu(digest[2]); +- put_unaligned_le32(f, dst + 8); +- f = (f >> 32) + le32_to_cpu(digest[3]); +- put_unaligned_le32(f, dst + 12); +- ++ poly1305_emit_arm(&dctx->h, dst, dctx->s); + *dctx = (struct poly1305_desc_ctx){}; + } + EXPORT_SYMBOL(poly1305_final_arch); +--- a/arch/arm64/crypto/poly1305-glue.c ++++ b/arch/arm64/crypto/poly1305-glue.c +@@ -21,7 +21,7 @@ + asmlinkage void poly1305_init_arm64(void *state, const u8 *key); + asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit); + asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit); +-asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce); ++asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce); + + static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); + +@@ -162,9 +162,6 @@ EXPORT_SYMBOL(poly1305_update_arch); + + void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst) + { +- __le32 digest[4]; +- u64 f = 0; +- + if (unlikely(dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, +@@ -172,18 +169,7 @@ void poly1305_final_arch(struct poly1305 + poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + +- poly1305_emit(&dctx->h, digest, dctx->s); +- +- /* mac = (h + s) % (2^128) */ +- f = (f >> 32) + le32_to_cpu(digest[0]); +- put_unaligned_le32(f, dst); +- f = (f >> 32) + le32_to_cpu(digest[1]); +- put_unaligned_le32(f, dst + 4); +- f = (f >> 32) + le32_to_cpu(digest[2]); +- put_unaligned_le32(f, dst + 8); +- f = (f >> 32) + le32_to_cpu(digest[3]); +- put_unaligned_le32(f, dst + 12); +- ++ poly1305_emit(&dctx->h, dst, dctx->s); + *dctx = (struct poly1305_desc_ctx){}; + } + EXPORT_SYMBOL(poly1305_final_arch); +--- a/arch/mips/crypto/poly1305-glue.c ++++ b/arch/mips/crypto/poly1305-glue.c +@@ -15,7 +15,7 @@ + + asmlinkage void poly1305_init_mips(void *state, const u8 *key); + asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit); +-asmlinkage void poly1305_emit_mips(void *state, __le32 *digest, const u32 *nonce); ++asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce); + + void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) + { +@@ -134,9 +134,6 @@ EXPORT_SYMBOL(poly1305_update_arch); + + void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst) + { +- __le32 digest[4]; +- u64 f = 0; +- + if (unlikely(dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, +@@ -144,18 +141,7 @@ void poly1305_final_arch(struct poly1305 + poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + +- poly1305_emit_mips(&dctx->h, digest, dctx->s); +- +- /* mac = (h + s) % (2^128) */ +- f = (f >> 32) + le32_to_cpu(digest[0]); +- put_unaligned_le32(f, dst); +- f = (f >> 32) + le32_to_cpu(digest[1]); +- put_unaligned_le32(f, dst + 4); +- f = (f >> 32) + le32_to_cpu(digest[2]); +- put_unaligned_le32(f, dst + 8); +- f = (f >> 32) + le32_to_cpu(digest[3]); +- put_unaligned_le32(f, dst + 12); +- ++ poly1305_emit_mips(&dctx->h, dst, dctx->s); + *dctx = (struct poly1305_desc_ctx){}; + } + EXPORT_SYMBOL(poly1305_final_arch); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0045-crypto-curve25519-Fix-selftest-build-error.patch b/target/linux/generic/backport-5.4/080-wireguard-0045-crypto-curve25519-Fix-selftest-build-error.patch new file mode 100644 index 0000000000..6247d99fea --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0045-crypto-curve25519-Fix-selftest-build-error.patch @@ -0,0 +1,102 @@ +From a7e800af9c95490f8b42934eccc88d02d0af6d2a Mon Sep 17 00:00:00 2001 +From: Herbert Xu +Date: Wed, 8 Jan 2020 12:37:35 +0800 +Subject: [PATCH 045/124] crypto: curve25519 - Fix selftest build error + +commit a8bdf2c42ee4d1ee42af1f3601f85de94e70a421 upstream. + +If CRYPTO_CURVE25519 is y, CRYPTO_LIB_CURVE25519_GENERIC will be +y, but CRYPTO_LIB_CURVE25519 may be set to m, this causes build +errors: + +lib/crypto/curve25519-selftest.o: In function `curve25519': +curve25519-selftest.c:(.text.unlikely+0xc): undefined reference to `curve25519_arch' +lib/crypto/curve25519-selftest.o: In function `curve25519_selftest': +curve25519-selftest.c:(.init.text+0x17e): undefined reference to `curve25519_base_arch' + +This is because the curve25519 self-test code is being controlled +by the GENERIC option rather than the overall CURVE25519 option, +as is the case with blake2s. To recap, the GENERIC and ARCH options +for CURVE25519 are internal only and selected by users such as +the Crypto API, or the externally visible CURVE25519 option which +in turn is selected by wireguard. The self-test is specific to the +the external CURVE25519 option and should not be enabled by the +Crypto API. + +This patch fixes this by splitting the GENERIC module from the +CURVE25519 module with the latter now containing just the self-test. + +Reported-by: Hulk Robot +Fixes: aa127963f1ca ("crypto: lib/curve25519 - re-add selftests") +Signed-off-by: Herbert Xu +Reviewed-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/Makefile | 9 ++++++--- + lib/crypto/curve25519-generic.c | 24 ++++++++++++++++++++++++ + lib/crypto/curve25519.c | 7 ------- + 3 files changed, 30 insertions(+), 10 deletions(-) + create mode 100644 lib/crypto/curve25519-generic.c + +--- a/lib/crypto/Makefile ++++ b/lib/crypto/Makefile +@@ -19,9 +19,12 @@ libblake2s-y += blake2s.o + obj-$(CONFIG_CRYPTO_LIB_CHACHA20POLY1305) += libchacha20poly1305.o + libchacha20poly1305-y += chacha20poly1305.o + +-obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC) += libcurve25519.o +-libcurve25519-y := curve25519-fiat32.o +-libcurve25519-$(CONFIG_ARCH_SUPPORTS_INT128) := curve25519-hacl64.o ++obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC) += libcurve25519-generic.o ++libcurve25519-generic-y := curve25519-fiat32.o ++libcurve25519-generic-$(CONFIG_ARCH_SUPPORTS_INT128) := curve25519-hacl64.o ++libcurve25519-generic-y += curve25519-generic.o ++ ++obj-$(CONFIG_CRYPTO_LIB_CURVE25519) += libcurve25519.o + libcurve25519-y += curve25519.o + + obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o +--- /dev/null ++++ b/lib/crypto/curve25519-generic.c +@@ -0,0 +1,24 @@ ++// SPDX-License-Identifier: GPL-2.0 OR MIT ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This is an implementation of the Curve25519 ECDH algorithm, using either ++ * a 32-bit implementation or a 64-bit implementation with 128-bit integers, ++ * depending on what is supported by the target compiler. ++ * ++ * Information: https://cr.yp.to/ecdh.html ++ */ ++ ++#include ++#include ++ ++const u8 curve25519_null_point[CURVE25519_KEY_SIZE] __aligned(32) = { 0 }; ++const u8 curve25519_base_point[CURVE25519_KEY_SIZE] __aligned(32) = { 9 }; ++ ++EXPORT_SYMBOL(curve25519_null_point); ++EXPORT_SYMBOL(curve25519_base_point); ++EXPORT_SYMBOL(curve25519_generic); ++ ++MODULE_LICENSE("GPL v2"); ++MODULE_DESCRIPTION("Curve25519 scalar multiplication"); ++MODULE_AUTHOR("Jason A. Donenfeld "); +--- a/lib/crypto/curve25519.c ++++ b/lib/crypto/curve25519.c +@@ -15,13 +15,6 @@ + + bool curve25519_selftest(void); + +-const u8 curve25519_null_point[CURVE25519_KEY_SIZE] __aligned(32) = { 0 }; +-const u8 curve25519_base_point[CURVE25519_KEY_SIZE] __aligned(32) = { 9 }; +- +-EXPORT_SYMBOL(curve25519_null_point); +-EXPORT_SYMBOL(curve25519_base_point); +-EXPORT_SYMBOL(curve25519_generic); +- + static int __init mod_init(void) + { + if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && diff --git a/target/linux/generic/backport-5.4/080-wireguard-0046-crypto-x86-poly1305-fix-.gitignore-typo.patch b/target/linux/generic/backport-5.4/080-wireguard-0046-crypto-x86-poly1305-fix-.gitignore-typo.patch new file mode 100644 index 0000000000..f5a7c21e07 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0046-crypto-x86-poly1305-fix-.gitignore-typo.patch @@ -0,0 +1,23 @@ +From cd86f0664c2e42b6406cb56ac8d5182a65764e93 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 16 Jan 2020 18:23:55 +0100 +Subject: [PATCH 046/124] crypto: x86/poly1305 - fix .gitignore typo + +commit 1f6868995326cc82102049e349d8dbd116bdb656 upstream. + +Admist the kbuild robot induced changes, the .gitignore file for the +generated file wasn't updated with the non-clashing filename. This +commit adjusts that. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/.gitignore | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/x86/crypto/.gitignore ++++ b/arch/x86/crypto/.gitignore +@@ -1 +1 @@ +-poly1305-x86_64.S ++poly1305-x86_64-cryptogams.S diff --git a/target/linux/generic/backport-5.4/080-wireguard-0047-crypto-chacha20poly1305-add-back-missing-test-vector.patch b/target/linux/generic/backport-5.4/080-wireguard-0047-crypto-chacha20poly1305-add-back-missing-test-vector.patch new file mode 100644 index 0000000000..9e10334873 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0047-crypto-chacha20poly1305-add-back-missing-test-vector.patch @@ -0,0 +1,1858 @@ +From 956c2d9a4e69f7458c9b7cb81db98ec1be75ea49 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 16 Jan 2020 21:26:34 +0100 +Subject: [PATCH 047/124] crypto: chacha20poly1305 - add back missing test + vectors and test chunking + +commit 72c7943792c9e7788ddd182337bcf8f650cf56f5 upstream. + +When this was originally ported, the 12-byte nonce vectors were left out +to keep things simple. I agree that we don't need nor want a library +interface for 12-byte nonces. But these test vectors were specially +crafted to look at issues in the underlying primitives and related +interactions. Therefore, we actually want to keep around all of the +test vectors, and simply have a helper function to test them with. + +Secondly, the sglist-based chunking code in the library interface is +rather complicated, so this adds a developer-only test for ensuring that +all the book keeping is correct, across a wide array of possibilities. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/chacha20poly1305-selftest.c | 1712 +++++++++++++++++++++++- + 1 file changed, 1698 insertions(+), 14 deletions(-) + +--- a/lib/crypto/chacha20poly1305-selftest.c ++++ b/lib/crypto/chacha20poly1305-selftest.c +@@ -4,6 +4,7 @@ + */ + + #include ++#include + #include + + #include +@@ -1926,6 +1927,1104 @@ static const u8 enc_key012[] __initconst + 0x65, 0x91, 0x6e, 0x2a, 0x79, 0x22, 0xda, 0x64 + }; + ++/* wycheproof - rfc7539 */ ++static const u8 enc_input013[] __initconst = { ++ 0x4c, 0x61, 0x64, 0x69, 0x65, 0x73, 0x20, 0x61, ++ 0x6e, 0x64, 0x20, 0x47, 0x65, 0x6e, 0x74, 0x6c, ++ 0x65, 0x6d, 0x65, 0x6e, 0x20, 0x6f, 0x66, 0x20, ++ 0x74, 0x68, 0x65, 0x20, 0x63, 0x6c, 0x61, 0x73, ++ 0x73, 0x20, 0x6f, 0x66, 0x20, 0x27, 0x39, 0x39, ++ 0x3a, 0x20, 0x49, 0x66, 0x20, 0x49, 0x20, 0x63, ++ 0x6f, 0x75, 0x6c, 0x64, 0x20, 0x6f, 0x66, 0x66, ++ 0x65, 0x72, 0x20, 0x79, 0x6f, 0x75, 0x20, 0x6f, ++ 0x6e, 0x6c, 0x79, 0x20, 0x6f, 0x6e, 0x65, 0x20, ++ 0x74, 0x69, 0x70, 0x20, 0x66, 0x6f, 0x72, 0x20, ++ 0x74, 0x68, 0x65, 0x20, 0x66, 0x75, 0x74, 0x75, ++ 0x72, 0x65, 0x2c, 0x20, 0x73, 0x75, 0x6e, 0x73, ++ 0x63, 0x72, 0x65, 0x65, 0x6e, 0x20, 0x77, 0x6f, ++ 0x75, 0x6c, 0x64, 0x20, 0x62, 0x65, 0x20, 0x69, ++ 0x74, 0x2e ++}; ++static const u8 enc_output013[] __initconst = { ++ 0xd3, 0x1a, 0x8d, 0x34, 0x64, 0x8e, 0x60, 0xdb, ++ 0x7b, 0x86, 0xaf, 0xbc, 0x53, 0xef, 0x7e, 0xc2, ++ 0xa4, 0xad, 0xed, 0x51, 0x29, 0x6e, 0x08, 0xfe, ++ 0xa9, 0xe2, 0xb5, 0xa7, 0x36, 0xee, 0x62, 0xd6, ++ 0x3d, 0xbe, 0xa4, 0x5e, 0x8c, 0xa9, 0x67, 0x12, ++ 0x82, 0xfa, 0xfb, 0x69, 0xda, 0x92, 0x72, 0x8b, ++ 0x1a, 0x71, 0xde, 0x0a, 0x9e, 0x06, 0x0b, 0x29, ++ 0x05, 0xd6, 0xa5, 0xb6, 0x7e, 0xcd, 0x3b, 0x36, ++ 0x92, 0xdd, 0xbd, 0x7f, 0x2d, 0x77, 0x8b, 0x8c, ++ 0x98, 0x03, 0xae, 0xe3, 0x28, 0x09, 0x1b, 0x58, ++ 0xfa, 0xb3, 0x24, 0xe4, 0xfa, 0xd6, 0x75, 0x94, ++ 0x55, 0x85, 0x80, 0x8b, 0x48, 0x31, 0xd7, 0xbc, ++ 0x3f, 0xf4, 0xde, 0xf0, 0x8e, 0x4b, 0x7a, 0x9d, ++ 0xe5, 0x76, 0xd2, 0x65, 0x86, 0xce, 0xc6, 0x4b, ++ 0x61, 0x16, 0x1a, 0xe1, 0x0b, 0x59, 0x4f, 0x09, ++ 0xe2, 0x6a, 0x7e, 0x90, 0x2e, 0xcb, 0xd0, 0x60, ++ 0x06, 0x91 ++}; ++static const u8 enc_assoc013[] __initconst = { ++ 0x50, 0x51, 0x52, 0x53, 0xc0, 0xc1, 0xc2, 0xc3, ++ 0xc4, 0xc5, 0xc6, 0xc7 ++}; ++static const u8 enc_nonce013[] __initconst = { ++ 0x07, 0x00, 0x00, 0x00, 0x40, 0x41, 0x42, 0x43, ++ 0x44, 0x45, 0x46, 0x47 ++}; ++static const u8 enc_key013[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input014[] __initconst = { }; ++static const u8 enc_output014[] __initconst = { ++ 0x76, 0xac, 0xb3, 0x42, 0xcf, 0x31, 0x66, 0xa5, ++ 0xb6, 0x3c, 0x0c, 0x0e, 0xa1, 0x38, 0x3c, 0x8d ++}; ++static const u8 enc_assoc014[] __initconst = { }; ++static const u8 enc_nonce014[] __initconst = { ++ 0x4d, 0xa5, 0xbf, 0x8d, 0xfd, 0x58, 0x52, 0xc1, ++ 0xea, 0x12, 0x37, 0x9d ++}; ++static const u8 enc_key014[] __initconst = { ++ 0x80, 0xba, 0x31, 0x92, 0xc8, 0x03, 0xce, 0x96, ++ 0x5e, 0xa3, 0x71, 0xd5, 0xff, 0x07, 0x3c, 0xf0, ++ 0xf4, 0x3b, 0x6a, 0x2a, 0xb5, 0x76, 0xb2, 0x08, ++ 0x42, 0x6e, 0x11, 0x40, 0x9c, 0x09, 0xb9, 0xb0 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input015[] __initconst = { }; ++static const u8 enc_output015[] __initconst = { ++ 0x90, 0x6f, 0xa6, 0x28, 0x4b, 0x52, 0xf8, 0x7b, ++ 0x73, 0x59, 0xcb, 0xaa, 0x75, 0x63, 0xc7, 0x09 ++}; ++static const u8 enc_assoc015[] __initconst = { ++ 0xbd, 0x50, 0x67, 0x64, 0xf2, 0xd2, 0xc4, 0x10 ++}; ++static const u8 enc_nonce015[] __initconst = { ++ 0xa9, 0x2e, 0xf0, 0xac, 0x99, 0x1d, 0xd5, 0x16, ++ 0xa3, 0xc6, 0xf6, 0x89 ++}; ++static const u8 enc_key015[] __initconst = { ++ 0x7a, 0x4c, 0xd7, 0x59, 0x17, 0x2e, 0x02, 0xeb, ++ 0x20, 0x4d, 0xb2, 0xc3, 0xf5, 0xc7, 0x46, 0x22, ++ 0x7d, 0xf5, 0x84, 0xfc, 0x13, 0x45, 0x19, 0x63, ++ 0x91, 0xdb, 0xb9, 0x57, 0x7a, 0x25, 0x07, 0x42 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input016[] __initconst = { ++ 0x2a ++}; ++static const u8 enc_output016[] __initconst = { ++ 0x3a, 0xca, 0xc2, 0x7d, 0xec, 0x09, 0x68, 0x80, ++ 0x1e, 0x9f, 0x6e, 0xde, 0xd6, 0x9d, 0x80, 0x75, ++ 0x22 ++}; ++static const u8 enc_assoc016[] __initconst = { }; ++static const u8 enc_nonce016[] __initconst = { ++ 0x99, 0xe2, 0x3e, 0xc4, 0x89, 0x85, 0xbc, 0xcd, ++ 0xee, 0xab, 0x60, 0xf1 ++}; ++static const u8 enc_key016[] __initconst = { ++ 0xcc, 0x56, 0xb6, 0x80, 0x55, 0x2e, 0xb7, 0x50, ++ 0x08, 0xf5, 0x48, 0x4b, 0x4c, 0xb8, 0x03, 0xfa, ++ 0x50, 0x63, 0xeb, 0xd6, 0xea, 0xb9, 0x1f, 0x6a, ++ 0xb6, 0xae, 0xf4, 0x91, 0x6a, 0x76, 0x62, 0x73 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input017[] __initconst = { ++ 0x51 ++}; ++static const u8 enc_output017[] __initconst = { ++ 0xc4, 0x16, 0x83, 0x10, 0xca, 0x45, 0xb1, 0xf7, ++ 0xc6, 0x6c, 0xad, 0x4e, 0x99, 0xe4, 0x3f, 0x72, ++ 0xb9 ++}; ++static const u8 enc_assoc017[] __initconst = { ++ 0x91, 0xca, 0x6c, 0x59, 0x2c, 0xbc, 0xca, 0x53 ++}; ++static const u8 enc_nonce017[] __initconst = { ++ 0xab, 0x0d, 0xca, 0x71, 0x6e, 0xe0, 0x51, 0xd2, ++ 0x78, 0x2f, 0x44, 0x03 ++}; ++static const u8 enc_key017[] __initconst = { ++ 0x46, 0xf0, 0x25, 0x49, 0x65, 0xf7, 0x69, 0xd5, ++ 0x2b, 0xdb, 0x4a, 0x70, 0xb4, 0x43, 0x19, 0x9f, ++ 0x8e, 0xf2, 0x07, 0x52, 0x0d, 0x12, 0x20, 0xc5, ++ 0x5e, 0x4b, 0x70, 0xf0, 0xfd, 0xa6, 0x20, 0xee ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input018[] __initconst = { ++ 0x5c, 0x60 ++}; ++static const u8 enc_output018[] __initconst = { ++ 0x4d, 0x13, 0x91, 0xe8, 0xb6, 0x1e, 0xfb, 0x39, ++ 0xc1, 0x22, 0x19, 0x54, 0x53, 0x07, 0x7b, 0x22, ++ 0xe5, 0xe2 ++}; ++static const u8 enc_assoc018[] __initconst = { }; ++static const u8 enc_nonce018[] __initconst = { ++ 0x46, 0x1a, 0xf1, 0x22, 0xe9, 0xf2, 0xe0, 0x34, ++ 0x7e, 0x03, 0xf2, 0xdb ++}; ++static const u8 enc_key018[] __initconst = { ++ 0x2f, 0x7f, 0x7e, 0x4f, 0x59, 0x2b, 0xb3, 0x89, ++ 0x19, 0x49, 0x89, 0x74, 0x35, 0x07, 0xbf, 0x3e, ++ 0xe9, 0xcb, 0xde, 0x17, 0x86, 0xb6, 0x69, 0x5f, ++ 0xe6, 0xc0, 0x25, 0xfd, 0x9b, 0xa4, 0xc1, 0x00 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input019[] __initconst = { ++ 0xdd, 0xf2 ++}; ++static const u8 enc_output019[] __initconst = { ++ 0xb6, 0x0d, 0xea, 0xd0, 0xfd, 0x46, 0x97, 0xec, ++ 0x2e, 0x55, 0x58, 0x23, 0x77, 0x19, 0xd0, 0x24, ++ 0x37, 0xa2 ++}; ++static const u8 enc_assoc019[] __initconst = { ++ 0x88, 0x36, 0x4f, 0xc8, 0x06, 0x05, 0x18, 0xbf ++}; ++static const u8 enc_nonce019[] __initconst = { ++ 0x61, 0x54, 0x6b, 0xa5, 0xf1, 0x72, 0x05, 0x90, ++ 0xb6, 0x04, 0x0a, 0xc6 ++}; ++static const u8 enc_key019[] __initconst = { ++ 0xc8, 0x83, 0x3d, 0xce, 0x5e, 0xa9, 0xf2, 0x48, ++ 0xaa, 0x20, 0x30, 0xea, 0xcf, 0xe7, 0x2b, 0xff, ++ 0xe6, 0x9a, 0x62, 0x0c, 0xaf, 0x79, 0x33, 0x44, ++ 0xe5, 0x71, 0x8f, 0xe0, 0xd7, 0xab, 0x1a, 0x58 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input020[] __initconst = { ++ 0xab, 0x85, 0xe9, 0xc1, 0x57, 0x17, 0x31 ++}; ++static const u8 enc_output020[] __initconst = { ++ 0x5d, 0xfe, 0x34, 0x40, 0xdb, 0xb3, 0xc3, 0xed, ++ 0x7a, 0x43, 0x4e, 0x26, 0x02, 0xd3, 0x94, 0x28, ++ 0x1e, 0x0a, 0xfa, 0x9f, 0xb7, 0xaa, 0x42 ++}; ++static const u8 enc_assoc020[] __initconst = { }; ++static const u8 enc_nonce020[] __initconst = { ++ 0x3c, 0x4e, 0x65, 0x4d, 0x66, 0x3f, 0xa4, 0x59, ++ 0x6d, 0xc5, 0x5b, 0xb7 ++}; ++static const u8 enc_key020[] __initconst = { ++ 0x55, 0x56, 0x81, 0x58, 0xd3, 0xa6, 0x48, 0x3f, ++ 0x1f, 0x70, 0x21, 0xea, 0xb6, 0x9b, 0x70, 0x3f, ++ 0x61, 0x42, 0x51, 0xca, 0xdc, 0x1a, 0xf5, 0xd3, ++ 0x4a, 0x37, 0x4f, 0xdb, 0xfc, 0x5a, 0xda, 0xc7 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input021[] __initconst = { ++ 0x4e, 0xe5, 0xcd, 0xa2, 0x0d, 0x42, 0x90 ++}; ++static const u8 enc_output021[] __initconst = { ++ 0x4b, 0xd4, 0x72, 0x12, 0x94, 0x1c, 0xe3, 0x18, ++ 0x5f, 0x14, 0x08, 0xee, 0x7f, 0xbf, 0x18, 0xf5, ++ 0xab, 0xad, 0x6e, 0x22, 0x53, 0xa1, 0xba ++}; ++static const u8 enc_assoc021[] __initconst = { ++ 0x84, 0xe4, 0x6b, 0xe8, 0xc0, 0x91, 0x90, 0x53 ++}; ++static const u8 enc_nonce021[] __initconst = { ++ 0x58, 0x38, 0x93, 0x75, 0xc6, 0x9e, 0xe3, 0x98, ++ 0xde, 0x94, 0x83, 0x96 ++}; ++static const u8 enc_key021[] __initconst = { ++ 0xe3, 0xc0, 0x9e, 0x7f, 0xab, 0x1a, 0xef, 0xb5, ++ 0x16, 0xda, 0x6a, 0x33, 0x02, 0x2a, 0x1d, 0xd4, ++ 0xeb, 0x27, 0x2c, 0x80, 0xd5, 0x40, 0xc5, 0xda, ++ 0x52, 0xa7, 0x30, 0xf3, 0x4d, 0x84, 0x0d, 0x7f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input022[] __initconst = { ++ 0xbe, 0x33, 0x08, 0xf7, 0x2a, 0x2c, 0x6a, 0xed ++}; ++static const u8 enc_output022[] __initconst = { ++ 0x8e, 0x94, 0x39, 0xa5, 0x6e, 0xee, 0xc8, 0x17, ++ 0xfb, 0xe8, 0xa6, 0xed, 0x8f, 0xab, 0xb1, 0x93, ++ 0x75, 0x39, 0xdd, 0x6c, 0x00, 0xe9, 0x00, 0x21 ++}; ++static const u8 enc_assoc022[] __initconst = { }; ++static const u8 enc_nonce022[] __initconst = { ++ 0x4f, 0x07, 0xaf, 0xed, 0xfd, 0xc3, 0xb6, 0xc2, ++ 0x36, 0x18, 0x23, 0xd3 ++}; ++static const u8 enc_key022[] __initconst = { ++ 0x51, 0xe4, 0xbf, 0x2b, 0xad, 0x92, 0xb7, 0xaf, ++ 0xf1, 0xa4, 0xbc, 0x05, 0x55, 0x0b, 0xa8, 0x1d, ++ 0xf4, 0xb9, 0x6f, 0xab, 0xf4, 0x1c, 0x12, 0xc7, ++ 0xb0, 0x0e, 0x60, 0xe4, 0x8d, 0xb7, 0xe1, 0x52 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input023[] __initconst = { ++ 0xa4, 0xc9, 0xc2, 0x80, 0x1b, 0x71, 0xf7, 0xdf ++}; ++static const u8 enc_output023[] __initconst = { ++ 0xb9, 0xb9, 0x10, 0x43, 0x3a, 0xf0, 0x52, 0xb0, ++ 0x45, 0x30, 0xf5, 0x1a, 0xee, 0xe0, 0x24, 0xe0, ++ 0xa4, 0x45, 0xa6, 0x32, 0x8f, 0xa6, 0x7a, 0x18 ++}; ++static const u8 enc_assoc023[] __initconst = { ++ 0x66, 0xc0, 0xae, 0x70, 0x07, 0x6c, 0xb1, 0x4d ++}; ++static const u8 enc_nonce023[] __initconst = { ++ 0xb4, 0xea, 0x66, 0x6e, 0xe1, 0x19, 0x56, 0x33, ++ 0x66, 0x48, 0x4a, 0x78 ++}; ++static const u8 enc_key023[] __initconst = { ++ 0x11, 0x31, 0xc1, 0x41, 0x85, 0x77, 0xa0, 0x54, ++ 0xde, 0x7a, 0x4a, 0xc5, 0x51, 0x95, 0x0f, 0x1a, ++ 0x05, 0x3f, 0x9a, 0xe4, 0x6e, 0x5b, 0x75, 0xfe, ++ 0x4a, 0xbd, 0x56, 0x08, 0xd7, 0xcd, 0xda, 0xdd ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input024[] __initconst = { ++ 0x42, 0xba, 0xae, 0x59, 0x78, 0xfe, 0xaf, 0x5c, ++ 0x36, 0x8d, 0x14, 0xe0 ++}; ++static const u8 enc_output024[] __initconst = { ++ 0xff, 0x7d, 0xc2, 0x03, 0xb2, 0x6c, 0x46, 0x7a, ++ 0x6b, 0x50, 0xdb, 0x33, 0x57, 0x8c, 0x0f, 0x27, ++ 0x58, 0xc2, 0xe1, 0x4e, 0x36, 0xd4, 0xfc, 0x10, ++ 0x6d, 0xcb, 0x29, 0xb4 ++}; ++static const u8 enc_assoc024[] __initconst = { }; ++static const u8 enc_nonce024[] __initconst = { ++ 0x9a, 0x59, 0xfc, 0xe2, 0x6d, 0xf0, 0x00, 0x5e, ++ 0x07, 0x53, 0x86, 0x56 ++}; ++static const u8 enc_key024[] __initconst = { ++ 0x99, 0xb6, 0x2b, 0xd5, 0xaf, 0xbe, 0x3f, 0xb0, ++ 0x15, 0xbd, 0xe9, 0x3f, 0x0a, 0xbf, 0x48, 0x39, ++ 0x57, 0xa1, 0xc3, 0xeb, 0x3c, 0xa5, 0x9c, 0xb5, ++ 0x0b, 0x39, 0xf7, 0xf8, 0xa9, 0xcc, 0x51, 0xbe ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input025[] __initconst = { ++ 0xfd, 0xc8, 0x5b, 0x94, 0xa4, 0xb2, 0xa6, 0xb7, ++ 0x59, 0xb1, 0xa0, 0xda ++}; ++static const u8 enc_output025[] __initconst = { ++ 0x9f, 0x88, 0x16, 0xde, 0x09, 0x94, 0xe9, 0x38, ++ 0xd9, 0xe5, 0x3f, 0x95, 0xd0, 0x86, 0xfc, 0x6c, ++ 0x9d, 0x8f, 0xa9, 0x15, 0xfd, 0x84, 0x23, 0xa7, ++ 0xcf, 0x05, 0x07, 0x2f ++}; ++static const u8 enc_assoc025[] __initconst = { ++ 0xa5, 0x06, 0xe1, 0xa5, 0xc6, 0x90, 0x93, 0xf9 ++}; ++static const u8 enc_nonce025[] __initconst = { ++ 0x58, 0xdb, 0xd4, 0xad, 0x2c, 0x4a, 0xd3, 0x5d, ++ 0xd9, 0x06, 0xe9, 0xce ++}; ++static const u8 enc_key025[] __initconst = { ++ 0x85, 0xf3, 0x5b, 0x62, 0x82, 0xcf, 0xf4, 0x40, ++ 0xbc, 0x10, 0x20, 0xc8, 0x13, 0x6f, 0xf2, 0x70, ++ 0x31, 0x11, 0x0f, 0xa6, 0x3e, 0xc1, 0x6f, 0x1e, ++ 0x82, 0x51, 0x18, 0xb0, 0x06, 0xb9, 0x12, 0x57 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input026[] __initconst = { ++ 0x51, 0xf8, 0xc1, 0xf7, 0x31, 0xea, 0x14, 0xac, ++ 0xdb, 0x21, 0x0a, 0x6d, 0x97, 0x3e, 0x07 ++}; ++static const u8 enc_output026[] __initconst = { ++ 0x0b, 0x29, 0x63, 0x8e, 0x1f, 0xbd, 0xd6, 0xdf, ++ 0x53, 0x97, 0x0b, 0xe2, 0x21, 0x00, 0x42, 0x2a, ++ 0x91, 0x34, 0x08, 0x7d, 0x67, 0xa4, 0x6e, 0x79, ++ 0x17, 0x8d, 0x0a, 0x93, 0xf5, 0xe1, 0xd2 ++}; ++static const u8 enc_assoc026[] __initconst = { }; ++static const u8 enc_nonce026[] __initconst = { ++ 0x68, 0xab, 0x7f, 0xdb, 0xf6, 0x19, 0x01, 0xda, ++ 0xd4, 0x61, 0xd2, 0x3c ++}; ++static const u8 enc_key026[] __initconst = { ++ 0x67, 0x11, 0x96, 0x27, 0xbd, 0x98, 0x8e, 0xda, ++ 0x90, 0x62, 0x19, 0xe0, 0x8c, 0x0d, 0x0d, 0x77, ++ 0x9a, 0x07, 0xd2, 0x08, 0xce, 0x8a, 0x4f, 0xe0, ++ 0x70, 0x9a, 0xf7, 0x55, 0xee, 0xec, 0x6d, 0xcb ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input027[] __initconst = { ++ 0x97, 0x46, 0x9d, 0xa6, 0x67, 0xd6, 0x11, 0x0f, ++ 0x9c, 0xbd, 0xa1, 0xd1, 0xa2, 0x06, 0x73 ++}; ++static const u8 enc_output027[] __initconst = { ++ 0x32, 0xdb, 0x66, 0xc4, 0xa3, 0x81, 0x9d, 0x81, ++ 0x55, 0x74, 0x55, 0xe5, 0x98, 0x0f, 0xed, 0xfe, ++ 0xae, 0x30, 0xde, 0xc9, 0x4e, 0x6a, 0xd3, 0xa9, ++ 0xee, 0xa0, 0x6a, 0x0d, 0x70, 0x39, 0x17 ++}; ++static const u8 enc_assoc027[] __initconst = { ++ 0x64, 0x53, 0xa5, 0x33, 0x84, 0x63, 0x22, 0x12 ++}; ++static const u8 enc_nonce027[] __initconst = { ++ 0xd9, 0x5b, 0x32, 0x43, 0xaf, 0xae, 0xf7, 0x14, ++ 0xc5, 0x03, 0x5b, 0x6a ++}; ++static const u8 enc_key027[] __initconst = { ++ 0xe6, 0xf1, 0x11, 0x8d, 0x41, 0xe4, 0xb4, 0x3f, ++ 0xb5, 0x82, 0x21, 0xb7, 0xed, 0x79, 0x67, 0x38, ++ 0x34, 0xe0, 0xd8, 0xac, 0x5c, 0x4f, 0xa6, 0x0b, ++ 0xbc, 0x8b, 0xc4, 0x89, 0x3a, 0x58, 0x89, 0x4d ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input028[] __initconst = { ++ 0x54, 0x9b, 0x36, 0x5a, 0xf9, 0x13, 0xf3, 0xb0, ++ 0x81, 0x13, 0x1c, 0xcb, 0x6b, 0x82, 0x55, 0x88 ++}; ++static const u8 enc_output028[] __initconst = { ++ 0xe9, 0x11, 0x0e, 0x9f, 0x56, 0xab, 0x3c, 0xa4, ++ 0x83, 0x50, 0x0c, 0xea, 0xba, 0xb6, 0x7a, 0x13, ++ 0x83, 0x6c, 0xca, 0xbf, 0x15, 0xa6, 0xa2, 0x2a, ++ 0x51, 0xc1, 0x07, 0x1c, 0xfa, 0x68, 0xfa, 0x0c ++}; ++static const u8 enc_assoc028[] __initconst = { }; ++static const u8 enc_nonce028[] __initconst = { ++ 0x2f, 0xcb, 0x1b, 0x38, 0xa9, 0x9e, 0x71, 0xb8, ++ 0x47, 0x40, 0xad, 0x9b ++}; ++static const u8 enc_key028[] __initconst = { ++ 0x59, 0xd4, 0xea, 0xfb, 0x4d, 0xe0, 0xcf, 0xc7, ++ 0xd3, 0xdb, 0x99, 0xa8, 0xf5, 0x4b, 0x15, 0xd7, ++ 0xb3, 0x9f, 0x0a, 0xcc, 0x8d, 0xa6, 0x97, 0x63, ++ 0xb0, 0x19, 0xc1, 0x69, 0x9f, 0x87, 0x67, 0x4a ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input029[] __initconst = { ++ 0x55, 0xa4, 0x65, 0x64, 0x4f, 0x5b, 0x65, 0x09, ++ 0x28, 0xcb, 0xee, 0x7c, 0x06, 0x32, 0x14, 0xd6 ++}; ++static const u8 enc_output029[] __initconst = { ++ 0xe4, 0xb1, 0x13, 0xcb, 0x77, 0x59, 0x45, 0xf3, ++ 0xd3, 0xa8, 0xae, 0x9e, 0xc1, 0x41, 0xc0, 0x0c, ++ 0x7c, 0x43, 0xf1, 0x6c, 0xe0, 0x96, 0xd0, 0xdc, ++ 0x27, 0xc9, 0x58, 0x49, 0xdc, 0x38, 0x3b, 0x7d ++}; ++static const u8 enc_assoc029[] __initconst = { ++ 0x03, 0x45, 0x85, 0x62, 0x1a, 0xf8, 0xd7, 0xff ++}; ++static const u8 enc_nonce029[] __initconst = { ++ 0x11, 0x8a, 0x69, 0x64, 0xc2, 0xd3, 0xe3, 0x80, ++ 0x07, 0x1f, 0x52, 0x66 ++}; ++static const u8 enc_key029[] __initconst = { ++ 0xb9, 0x07, 0xa4, 0x50, 0x75, 0x51, 0x3f, 0xe8, ++ 0xa8, 0x01, 0x9e, 0xde, 0xe3, 0xf2, 0x59, 0x14, ++ 0x87, 0xb2, 0xa0, 0x30, 0xb0, 0x3c, 0x6e, 0x1d, ++ 0x77, 0x1c, 0x86, 0x25, 0x71, 0xd2, 0xea, 0x1e ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input030[] __initconst = { ++ 0x3f, 0xf1, 0x51, 0x4b, 0x1c, 0x50, 0x39, 0x15, ++ 0x91, 0x8f, 0x0c, 0x0c, 0x31, 0x09, 0x4a, 0x6e, ++ 0x1f ++}; ++static const u8 enc_output030[] __initconst = { ++ 0x02, 0xcc, 0x3a, 0xcb, 0x5e, 0xe1, 0xfc, 0xdd, ++ 0x12, 0xa0, 0x3b, 0xb8, 0x57, 0x97, 0x64, 0x74, ++ 0xd3, 0xd8, 0x3b, 0x74, 0x63, 0xa2, 0xc3, 0x80, ++ 0x0f, 0xe9, 0x58, 0xc2, 0x8e, 0xaa, 0x29, 0x08, ++ 0x13 ++}; ++static const u8 enc_assoc030[] __initconst = { }; ++static const u8 enc_nonce030[] __initconst = { ++ 0x45, 0xaa, 0xa3, 0xe5, 0xd1, 0x6d, 0x2d, 0x42, ++ 0xdc, 0x03, 0x44, 0x5d ++}; ++static const u8 enc_key030[] __initconst = { ++ 0x3b, 0x24, 0x58, 0xd8, 0x17, 0x6e, 0x16, 0x21, ++ 0xc0, 0xcc, 0x24, 0xc0, 0xc0, 0xe2, 0x4c, 0x1e, ++ 0x80, 0xd7, 0x2f, 0x7e, 0xe9, 0x14, 0x9a, 0x4b, ++ 0x16, 0x61, 0x76, 0x62, 0x96, 0x16, 0xd0, 0x11 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input031[] __initconst = { ++ 0x63, 0x85, 0x8c, 0xa3, 0xe2, 0xce, 0x69, 0x88, ++ 0x7b, 0x57, 0x8a, 0x3c, 0x16, 0x7b, 0x42, 0x1c, ++ 0x9c ++}; ++static const u8 enc_output031[] __initconst = { ++ 0x35, 0x76, 0x64, 0x88, 0xd2, 0xbc, 0x7c, 0x2b, ++ 0x8d, 0x17, 0xcb, 0xbb, 0x9a, 0xbf, 0xad, 0x9e, ++ 0x6d, 0x1f, 0x39, 0x1e, 0x65, 0x7b, 0x27, 0x38, ++ 0xdd, 0xa0, 0x84, 0x48, 0xcb, 0xa2, 0x81, 0x1c, ++ 0xeb ++}; ++static const u8 enc_assoc031[] __initconst = { ++ 0x9a, 0xaf, 0x29, 0x9e, 0xee, 0xa7, 0x8f, 0x79 ++}; ++static const u8 enc_nonce031[] __initconst = { ++ 0xf0, 0x38, 0x4f, 0xb8, 0x76, 0x12, 0x14, 0x10, ++ 0x63, 0x3d, 0x99, 0x3d ++}; ++static const u8 enc_key031[] __initconst = { ++ 0xf6, 0x0c, 0x6a, 0x1b, 0x62, 0x57, 0x25, 0xf7, ++ 0x6c, 0x70, 0x37, 0xb4, 0x8f, 0xe3, 0x57, 0x7f, ++ 0xa7, 0xf7, 0xb8, 0x7b, 0x1b, 0xd5, 0xa9, 0x82, ++ 0x17, 0x6d, 0x18, 0x23, 0x06, 0xff, 0xb8, 0x70 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input032[] __initconst = { ++ 0x10, 0xf1, 0xec, 0xf9, 0xc6, 0x05, 0x84, 0x66, ++ 0x5d, 0x9a, 0xe5, 0xef, 0xe2, 0x79, 0xe7, 0xf7, ++ 0x37, 0x7e, 0xea, 0x69, 0x16, 0xd2, 0xb1, 0x11 ++}; ++static const u8 enc_output032[] __initconst = { ++ 0x42, 0xf2, 0x6c, 0x56, 0xcb, 0x4b, 0xe2, 0x1d, ++ 0x9d, 0x8d, 0x0c, 0x80, 0xfc, 0x99, 0xdd, 0xe0, ++ 0x0d, 0x75, 0xf3, 0x80, 0x74, 0xbf, 0xe7, 0x64, ++ 0x54, 0xaa, 0x7e, 0x13, 0xd4, 0x8f, 0xff, 0x7d, ++ 0x75, 0x57, 0x03, 0x94, 0x57, 0x04, 0x0a, 0x3a ++}; ++static const u8 enc_assoc032[] __initconst = { }; ++static const u8 enc_nonce032[] __initconst = { ++ 0xe6, 0xb1, 0xad, 0xf2, 0xfd, 0x58, 0xa8, 0x76, ++ 0x2c, 0x65, 0xf3, 0x1b ++}; ++static const u8 enc_key032[] __initconst = { ++ 0x02, 0x12, 0xa8, 0xde, 0x50, 0x07, 0xed, 0x87, ++ 0xb3, 0x3f, 0x1a, 0x70, 0x90, 0xb6, 0x11, 0x4f, ++ 0x9e, 0x08, 0xce, 0xfd, 0x96, 0x07, 0xf2, 0xc2, ++ 0x76, 0xbd, 0xcf, 0xdb, 0xc5, 0xce, 0x9c, 0xd7 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input033[] __initconst = { ++ 0x92, 0x22, 0xf9, 0x01, 0x8e, 0x54, 0xfd, 0x6d, ++ 0xe1, 0x20, 0x08, 0x06, 0xa9, 0xee, 0x8e, 0x4c, ++ 0xc9, 0x04, 0xd2, 0x9f, 0x25, 0xcb, 0xa1, 0x93 ++}; ++static const u8 enc_output033[] __initconst = { ++ 0x12, 0x30, 0x32, 0x43, 0x7b, 0x4b, 0xfd, 0x69, ++ 0x20, 0xe8, 0xf7, 0xe7, 0xe0, 0x08, 0x7a, 0xe4, ++ 0x88, 0x9e, 0xbe, 0x7a, 0x0a, 0xd0, 0xe9, 0x00, ++ 0x3c, 0xf6, 0x8f, 0x17, 0x95, 0x50, 0xda, 0x63, ++ 0xd3, 0xb9, 0x6c, 0x2d, 0x55, 0x41, 0x18, 0x65 ++}; ++static const u8 enc_assoc033[] __initconst = { ++ 0x3e, 0x8b, 0xc5, 0xad, 0xe1, 0x82, 0xff, 0x08 ++}; ++static const u8 enc_nonce033[] __initconst = { ++ 0x6b, 0x28, 0x2e, 0xbe, 0xcc, 0x54, 0x1b, 0xcd, ++ 0x78, 0x34, 0xed, 0x55 ++}; ++static const u8 enc_key033[] __initconst = { ++ 0xc5, 0xbc, 0x09, 0x56, 0x56, 0x46, 0xe7, 0xed, ++ 0xda, 0x95, 0x4f, 0x1f, 0x73, 0x92, 0x23, 0xda, ++ 0xda, 0x20, 0xb9, 0x5c, 0x44, 0xab, 0x03, 0x3d, ++ 0x0f, 0xae, 0x4b, 0x02, 0x83, 0xd1, 0x8b, 0xe3 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input034[] __initconst = { ++ 0xb0, 0x53, 0x99, 0x92, 0x86, 0xa2, 0x82, 0x4f, ++ 0x42, 0xcc, 0x8c, 0x20, 0x3a, 0xb2, 0x4e, 0x2c, ++ 0x97, 0xa6, 0x85, 0xad, 0xcc, 0x2a, 0xd3, 0x26, ++ 0x62, 0x55, 0x8e, 0x55, 0xa5, 0xc7, 0x29 ++}; ++static const u8 enc_output034[] __initconst = { ++ 0x45, 0xc7, 0xd6, 0xb5, 0x3a, 0xca, 0xd4, 0xab, ++ 0xb6, 0x88, 0x76, 0xa6, 0xe9, 0x6a, 0x48, 0xfb, ++ 0x59, 0x52, 0x4d, 0x2c, 0x92, 0xc9, 0xd8, 0xa1, ++ 0x89, 0xc9, 0xfd, 0x2d, 0xb9, 0x17, 0x46, 0x56, ++ 0x6d, 0x3c, 0xa1, 0x0e, 0x31, 0x1b, 0x69, 0x5f, ++ 0x3e, 0xae, 0x15, 0x51, 0x65, 0x24, 0x93 ++}; ++static const u8 enc_assoc034[] __initconst = { }; ++static const u8 enc_nonce034[] __initconst = { ++ 0x04, 0xa9, 0xbe, 0x03, 0x50, 0x8a, 0x5f, 0x31, ++ 0x37, 0x1a, 0x6f, 0xd2 ++}; ++static const u8 enc_key034[] __initconst = { ++ 0x2e, 0xb5, 0x1c, 0x46, 0x9a, 0xa8, 0xeb, 0x9e, ++ 0x6c, 0x54, 0xa8, 0x34, 0x9b, 0xae, 0x50, 0xa2, ++ 0x0f, 0x0e, 0x38, 0x27, 0x11, 0xbb, 0xa1, 0x15, ++ 0x2c, 0x42, 0x4f, 0x03, 0xb6, 0x67, 0x1d, 0x71 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input035[] __initconst = { ++ 0xf4, 0x52, 0x06, 0xab, 0xc2, 0x55, 0x52, 0xb2, ++ 0xab, 0xc9, 0xab, 0x7f, 0xa2, 0x43, 0x03, 0x5f, ++ 0xed, 0xaa, 0xdd, 0xc3, 0xb2, 0x29, 0x39, 0x56, ++ 0xf1, 0xea, 0x6e, 0x71, 0x56, 0xe7, 0xeb ++}; ++static const u8 enc_output035[] __initconst = { ++ 0x46, 0xa8, 0x0c, 0x41, 0x87, 0x02, 0x47, 0x20, ++ 0x08, 0x46, 0x27, 0x58, 0x00, 0x80, 0xdd, 0xe5, ++ 0xa3, 0xf4, 0xa1, 0x10, 0x93, 0xa7, 0x07, 0x6e, ++ 0xd6, 0xf3, 0xd3, 0x26, 0xbc, 0x7b, 0x70, 0x53, ++ 0x4d, 0x4a, 0xa2, 0x83, 0x5a, 0x52, 0xe7, 0x2d, ++ 0x14, 0xdf, 0x0e, 0x4f, 0x47, 0xf2, 0x5f ++}; ++static const u8 enc_assoc035[] __initconst = { ++ 0x37, 0x46, 0x18, 0xa0, 0x6e, 0xa9, 0x8a, 0x48 ++}; ++static const u8 enc_nonce035[] __initconst = { ++ 0x47, 0x0a, 0x33, 0x9e, 0xcb, 0x32, 0x19, 0xb8, ++ 0xb8, 0x1a, 0x1f, 0x8b ++}; ++static const u8 enc_key035[] __initconst = { ++ 0x7f, 0x5b, 0x74, 0xc0, 0x7e, 0xd1, 0xb4, 0x0f, ++ 0xd1, 0x43, 0x58, 0xfe, 0x2f, 0xf2, 0xa7, 0x40, ++ 0xc1, 0x16, 0xc7, 0x70, 0x65, 0x10, 0xe6, 0xa4, ++ 0x37, 0xf1, 0x9e, 0xa4, 0x99, 0x11, 0xce, 0xc4 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input036[] __initconst = { ++ 0xb9, 0xc5, 0x54, 0xcb, 0xc3, 0x6a, 0xc1, 0x8a, ++ 0xe8, 0x97, 0xdf, 0x7b, 0xee, 0xca, 0xc1, 0xdb, ++ 0xeb, 0x4e, 0xaf, 0xa1, 0x56, 0xbb, 0x60, 0xce, ++ 0x2e, 0x5d, 0x48, 0xf0, 0x57, 0x15, 0xe6, 0x78 ++}; ++static const u8 enc_output036[] __initconst = { ++ 0xea, 0x29, 0xaf, 0xa4, 0x9d, 0x36, 0xe8, 0x76, ++ 0x0f, 0x5f, 0xe1, 0x97, 0x23, 0xb9, 0x81, 0x1e, ++ 0xd5, 0xd5, 0x19, 0x93, 0x4a, 0x44, 0x0f, 0x50, ++ 0x81, 0xac, 0x43, 0x0b, 0x95, 0x3b, 0x0e, 0x21, ++ 0x22, 0x25, 0x41, 0xaf, 0x46, 0xb8, 0x65, 0x33, ++ 0xc6, 0xb6, 0x8d, 0x2f, 0xf1, 0x08, 0xa7, 0xea ++}; ++static const u8 enc_assoc036[] __initconst = { }; ++static const u8 enc_nonce036[] __initconst = { ++ 0x72, 0xcf, 0xd9, 0x0e, 0xf3, 0x02, 0x6c, 0xa2, ++ 0x2b, 0x7e, 0x6e, 0x6a ++}; ++static const u8 enc_key036[] __initconst = { ++ 0xe1, 0x73, 0x1d, 0x58, 0x54, 0xe1, 0xb7, 0x0c, ++ 0xb3, 0xff, 0xe8, 0xb7, 0x86, 0xa2, 0xb3, 0xeb, ++ 0xf0, 0x99, 0x43, 0x70, 0x95, 0x47, 0x57, 0xb9, ++ 0xdc, 0x8c, 0x7b, 0xc5, 0x35, 0x46, 0x34, 0xa3 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input037[] __initconst = { ++ 0x6b, 0x26, 0x04, 0x99, 0x6c, 0xd3, 0x0c, 0x14, ++ 0xa1, 0x3a, 0x52, 0x57, 0xed, 0x6c, 0xff, 0xd3, ++ 0xbc, 0x5e, 0x29, 0xd6, 0xb9, 0x7e, 0xb1, 0x79, ++ 0x9e, 0xb3, 0x35, 0xe2, 0x81, 0xea, 0x45, 0x1e ++}; ++static const u8 enc_output037[] __initconst = { ++ 0x6d, 0xad, 0x63, 0x78, 0x97, 0x54, 0x4d, 0x8b, ++ 0xf6, 0xbe, 0x95, 0x07, 0xed, 0x4d, 0x1b, 0xb2, ++ 0xe9, 0x54, 0xbc, 0x42, 0x7e, 0x5d, 0xe7, 0x29, ++ 0xda, 0xf5, 0x07, 0x62, 0x84, 0x6f, 0xf2, 0xf4, ++ 0x7b, 0x99, 0x7d, 0x93, 0xc9, 0x82, 0x18, 0x9d, ++ 0x70, 0x95, 0xdc, 0x79, 0x4c, 0x74, 0x62, 0x32 ++}; ++static const u8 enc_assoc037[] __initconst = { ++ 0x23, 0x33, 0xe5, 0xce, 0x0f, 0x93, 0xb0, 0x59 ++}; ++static const u8 enc_nonce037[] __initconst = { ++ 0x26, 0x28, 0x80, 0xd4, 0x75, 0xf3, 0xda, 0xc5, ++ 0x34, 0x0d, 0xd1, 0xb8 ++}; ++static const u8 enc_key037[] __initconst = { ++ 0x27, 0xd8, 0x60, 0x63, 0x1b, 0x04, 0x85, 0xa4, ++ 0x10, 0x70, 0x2f, 0xea, 0x61, 0xbc, 0x87, 0x3f, ++ 0x34, 0x42, 0x26, 0x0c, 0xad, 0xed, 0x4a, 0xbd, ++ 0xe2, 0x5b, 0x78, 0x6a, 0x2d, 0x97, 0xf1, 0x45 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input038[] __initconst = { ++ 0x97, 0x3d, 0x0c, 0x75, 0x38, 0x26, 0xba, 0xe4, ++ 0x66, 0xcf, 0x9a, 0xbb, 0x34, 0x93, 0x15, 0x2e, ++ 0x9d, 0xe7, 0x81, 0x9e, 0x2b, 0xd0, 0xc7, 0x11, ++ 0x71, 0x34, 0x6b, 0x4d, 0x2c, 0xeb, 0xf8, 0x04, ++ 0x1a, 0xa3, 0xce, 0xdc, 0x0d, 0xfd, 0x7b, 0x46, ++ 0x7e, 0x26, 0x22, 0x8b, 0xc8, 0x6c, 0x9a ++}; ++static const u8 enc_output038[] __initconst = { ++ 0xfb, 0xa7, 0x8a, 0xe4, 0xf9, 0xd8, 0x08, 0xa6, ++ 0x2e, 0x3d, 0xa4, 0x0b, 0xe2, 0xcb, 0x77, 0x00, ++ 0xc3, 0x61, 0x3d, 0x9e, 0xb2, 0xc5, 0x29, 0xc6, ++ 0x52, 0xe7, 0x6a, 0x43, 0x2c, 0x65, 0x8d, 0x27, ++ 0x09, 0x5f, 0x0e, 0xb8, 0xf9, 0x40, 0xc3, 0x24, ++ 0x98, 0x1e, 0xa9, 0x35, 0xe5, 0x07, 0xf9, 0x8f, ++ 0x04, 0x69, 0x56, 0xdb, 0x3a, 0x51, 0x29, 0x08, ++ 0xbd, 0x7a, 0xfc, 0x8f, 0x2a, 0xb0, 0xa9 ++}; ++static const u8 enc_assoc038[] __initconst = { }; ++static const u8 enc_nonce038[] __initconst = { ++ 0xe7, 0x4a, 0x51, 0x5e, 0x7e, 0x21, 0x02, 0xb9, ++ 0x0b, 0xef, 0x55, 0xd2 ++}; ++static const u8 enc_key038[] __initconst = { ++ 0xcf, 0x0d, 0x40, 0xa4, 0x64, 0x4e, 0x5f, 0x51, ++ 0x81, 0x51, 0x65, 0xd5, 0x30, 0x1b, 0x22, 0x63, ++ 0x1f, 0x45, 0x44, 0xc4, 0x9a, 0x18, 0x78, 0xe3, ++ 0xa0, 0xa5, 0xe8, 0xe1, 0xaa, 0xe0, 0xf2, 0x64 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input039[] __initconst = { ++ 0xa9, 0x89, 0x95, 0x50, 0x4d, 0xf1, 0x6f, 0x74, ++ 0x8b, 0xfb, 0x77, 0x85, 0xff, 0x91, 0xee, 0xb3, ++ 0xb6, 0x60, 0xea, 0x9e, 0xd3, 0x45, 0x0c, 0x3d, ++ 0x5e, 0x7b, 0x0e, 0x79, 0xef, 0x65, 0x36, 0x59, ++ 0xa9, 0x97, 0x8d, 0x75, 0x54, 0x2e, 0xf9, 0x1c, ++ 0x45, 0x67, 0x62, 0x21, 0x56, 0x40, 0xb9 ++}; ++static const u8 enc_output039[] __initconst = { ++ 0xa1, 0xff, 0xed, 0x80, 0x76, 0x18, 0x29, 0xec, ++ 0xce, 0x24, 0x2e, 0x0e, 0x88, 0xb1, 0x38, 0x04, ++ 0x90, 0x16, 0xbc, 0xa0, 0x18, 0xda, 0x2b, 0x6e, ++ 0x19, 0x98, 0x6b, 0x3e, 0x31, 0x8c, 0xae, 0x8d, ++ 0x80, 0x61, 0x98, 0xfb, 0x4c, 0x52, 0x7c, 0xc3, ++ 0x93, 0x50, 0xeb, 0xdd, 0xea, 0xc5, 0x73, 0xc4, ++ 0xcb, 0xf0, 0xbe, 0xfd, 0xa0, 0xb7, 0x02, 0x42, ++ 0xc6, 0x40, 0xd7, 0xcd, 0x02, 0xd7, 0xa3 ++}; ++static const u8 enc_assoc039[] __initconst = { ++ 0xb3, 0xe4, 0x06, 0x46, 0x83, 0xb0, 0x2d, 0x84 ++}; ++static const u8 enc_nonce039[] __initconst = { ++ 0xd4, 0xd8, 0x07, 0x34, 0x16, 0x83, 0x82, 0x5b, ++ 0x31, 0xcd, 0x4d, 0x95 ++}; ++static const u8 enc_key039[] __initconst = { ++ 0x6c, 0xbf, 0xd7, 0x1c, 0x64, 0x5d, 0x18, 0x4c, ++ 0xf5, 0xd2, 0x3c, 0x40, 0x2b, 0xdb, 0x0d, 0x25, ++ 0xec, 0x54, 0x89, 0x8c, 0x8a, 0x02, 0x73, 0xd4, ++ 0x2e, 0xb5, 0xbe, 0x10, 0x9f, 0xdc, 0xb2, 0xac ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input040[] __initconst = { ++ 0xd0, 0x96, 0x80, 0x31, 0x81, 0xbe, 0xef, 0x9e, ++ 0x00, 0x8f, 0xf8, 0x5d, 0x5d, 0xdc, 0x38, 0xdd, ++ 0xac, 0xf0, 0xf0, 0x9e, 0xe5, 0xf7, 0xe0, 0x7f, ++ 0x1e, 0x40, 0x79, 0xcb, 0x64, 0xd0, 0xdc, 0x8f, ++ 0x5e, 0x67, 0x11, 0xcd, 0x49, 0x21, 0xa7, 0x88, ++ 0x7d, 0xe7, 0x6e, 0x26, 0x78, 0xfd, 0xc6, 0x76, ++ 0x18, 0xf1, 0x18, 0x55, 0x86, 0xbf, 0xea, 0x9d, ++ 0x4c, 0x68, 0x5d, 0x50, 0xe4, 0xbb, 0x9a, 0x82 ++}; ++static const u8 enc_output040[] __initconst = { ++ 0x9a, 0x4e, 0xf2, 0x2b, 0x18, 0x16, 0x77, 0xb5, ++ 0x75, 0x5c, 0x08, 0xf7, 0x47, 0xc0, 0xf8, 0xd8, ++ 0xe8, 0xd4, 0xc1, 0x8a, 0x9c, 0xc2, 0x40, 0x5c, ++ 0x12, 0xbb, 0x51, 0xbb, 0x18, 0x72, 0xc8, 0xe8, ++ 0xb8, 0x77, 0x67, 0x8b, 0xec, 0x44, 0x2c, 0xfc, ++ 0xbb, 0x0f, 0xf4, 0x64, 0xa6, 0x4b, 0x74, 0x33, ++ 0x2c, 0xf0, 0x72, 0x89, 0x8c, 0x7e, 0x0e, 0xdd, ++ 0xf6, 0x23, 0x2e, 0xa6, 0xe2, 0x7e, 0xfe, 0x50, ++ 0x9f, 0xf3, 0x42, 0x7a, 0x0f, 0x32, 0xfa, 0x56, ++ 0x6d, 0x9c, 0xa0, 0xa7, 0x8a, 0xef, 0xc0, 0x13 ++}; ++static const u8 enc_assoc040[] __initconst = { }; ++static const u8 enc_nonce040[] __initconst = { ++ 0xd6, 0x10, 0x40, 0xa3, 0x13, 0xed, 0x49, 0x28, ++ 0x23, 0xcc, 0x06, 0x5b ++}; ++static const u8 enc_key040[] __initconst = { ++ 0x5b, 0x1d, 0x10, 0x35, 0xc0, 0xb1, 0x7e, 0xe0, ++ 0xb0, 0x44, 0x47, 0x67, 0xf8, 0x0a, 0x25, 0xb8, ++ 0xc1, 0xb7, 0x41, 0xf4, 0xb5, 0x0a, 0x4d, 0x30, ++ 0x52, 0x22, 0x6b, 0xaa, 0x1c, 0x6f, 0xb7, 0x01 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input041[] __initconst = { ++ 0x94, 0xee, 0x16, 0x6d, 0x6d, 0x6e, 0xcf, 0x88, ++ 0x32, 0x43, 0x71, 0x36, 0xb4, 0xae, 0x80, 0x5d, ++ 0x42, 0x88, 0x64, 0x35, 0x95, 0x86, 0xd9, 0x19, ++ 0x3a, 0x25, 0x01, 0x62, 0x93, 0xed, 0xba, 0x44, ++ 0x3c, 0x58, 0xe0, 0x7e, 0x7b, 0x71, 0x95, 0xec, ++ 0x5b, 0xd8, 0x45, 0x82, 0xa9, 0xd5, 0x6c, 0x8d, ++ 0x4a, 0x10, 0x8c, 0x7d, 0x7c, 0xe3, 0x4e, 0x6c, ++ 0x6f, 0x8e, 0xa1, 0xbe, 0xc0, 0x56, 0x73, 0x17 ++}; ++static const u8 enc_output041[] __initconst = { ++ 0x5f, 0xbb, 0xde, 0xcc, 0x34, 0xbe, 0x20, 0x16, ++ 0x14, 0xf6, 0x36, 0x03, 0x1e, 0xeb, 0x42, 0xf1, ++ 0xca, 0xce, 0x3c, 0x79, 0xa1, 0x2c, 0xff, 0xd8, ++ 0x71, 0xee, 0x8e, 0x73, 0x82, 0x0c, 0x82, 0x97, ++ 0x49, 0xf1, 0xab, 0xb4, 0x29, 0x43, 0x67, 0x84, ++ 0x9f, 0xb6, 0xc2, 0xaa, 0x56, 0xbd, 0xa8, 0xa3, ++ 0x07, 0x8f, 0x72, 0x3d, 0x7c, 0x1c, 0x85, 0x20, ++ 0x24, 0xb0, 0x17, 0xb5, 0x89, 0x73, 0xfb, 0x1e, ++ 0x09, 0x26, 0x3d, 0xa7, 0xb4, 0xcb, 0x92, 0x14, ++ 0x52, 0xf9, 0x7d, 0xca, 0x40, 0xf5, 0x80, 0xec ++}; ++static const u8 enc_assoc041[] __initconst = { ++ 0x71, 0x93, 0xf6, 0x23, 0x66, 0x33, 0x21, 0xa2 ++}; ++static const u8 enc_nonce041[] __initconst = { ++ 0xd3, 0x1c, 0x21, 0xab, 0xa1, 0x75, 0xb7, 0x0d, ++ 0xe4, 0xeb, 0xb1, 0x9c ++}; ++static const u8 enc_key041[] __initconst = { ++ 0x97, 0xd6, 0x35, 0xc4, 0xf4, 0x75, 0x74, 0xd9, ++ 0x99, 0x8a, 0x90, 0x87, 0x5d, 0xa1, 0xd3, 0xa2, ++ 0x84, 0xb7, 0x55, 0xb2, 0xd3, 0x92, 0x97, 0xa5, ++ 0x72, 0x52, 0x35, 0x19, 0x0e, 0x10, 0xa9, 0x7e ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input042[] __initconst = { ++ 0xb4, 0x29, 0xeb, 0x80, 0xfb, 0x8f, 0xe8, 0xba, ++ 0xed, 0xa0, 0xc8, 0x5b, 0x9c, 0x33, 0x34, 0x58, ++ 0xe7, 0xc2, 0x99, 0x2e, 0x55, 0x84, 0x75, 0x06, ++ 0x9d, 0x12, 0xd4, 0x5c, 0x22, 0x21, 0x75, 0x64, ++ 0x12, 0x15, 0x88, 0x03, 0x22, 0x97, 0xef, 0xf5, ++ 0x67, 0x83, 0x74, 0x2a, 0x5f, 0xc2, 0x2d, 0x74, ++ 0x10, 0xff, 0xb2, 0x9d, 0x66, 0x09, 0x86, 0x61, ++ 0xd7, 0x6f, 0x12, 0x6c, 0x3c, 0x27, 0x68, 0x9e, ++ 0x43, 0xb3, 0x72, 0x67, 0xca, 0xc5, 0xa3, 0xa6, ++ 0xd3, 0xab, 0x49, 0xe3, 0x91, 0xda, 0x29, 0xcd, ++ 0x30, 0x54, 0xa5, 0x69, 0x2e, 0x28, 0x07, 0xe4, ++ 0xc3, 0xea, 0x46, 0xc8, 0x76, 0x1d, 0x50, 0xf5, ++ 0x92 ++}; ++static const u8 enc_output042[] __initconst = { ++ 0xd0, 0x10, 0x2f, 0x6c, 0x25, 0x8b, 0xf4, 0x97, ++ 0x42, 0xce, 0xc3, 0x4c, 0xf2, 0xd0, 0xfe, 0xdf, ++ 0x23, 0xd1, 0x05, 0xfb, 0x4c, 0x84, 0xcf, 0x98, ++ 0x51, 0x5e, 0x1b, 0xc9, 0xa6, 0x4f, 0x8a, 0xd5, ++ 0xbe, 0x8f, 0x07, 0x21, 0xbd, 0xe5, 0x06, 0x45, ++ 0xd0, 0x00, 0x83, 0xc3, 0xa2, 0x63, 0xa3, 0x10, ++ 0x53, 0xb7, 0x60, 0x24, 0x5f, 0x52, 0xae, 0x28, ++ 0x66, 0xa5, 0xec, 0x83, 0xb1, 0x9f, 0x61, 0xbe, ++ 0x1d, 0x30, 0xd5, 0xc5, 0xd9, 0xfe, 0xcc, 0x4c, ++ 0xbb, 0xe0, 0x8f, 0xd3, 0x85, 0x81, 0x3a, 0x2a, ++ 0xa3, 0x9a, 0x00, 0xff, 0x9c, 0x10, 0xf7, 0xf2, ++ 0x37, 0x02, 0xad, 0xd1, 0xe4, 0xb2, 0xff, 0xa3, ++ 0x1c, 0x41, 0x86, 0x5f, 0xc7, 0x1d, 0xe1, 0x2b, ++ 0x19, 0x61, 0x21, 0x27, 0xce, 0x49, 0x99, 0x3b, ++ 0xb0 ++}; ++static const u8 enc_assoc042[] __initconst = { }; ++static const u8 enc_nonce042[] __initconst = { ++ 0x17, 0xc8, 0x6a, 0x8a, 0xbb, 0xb7, 0xe0, 0x03, ++ 0xac, 0xde, 0x27, 0x99 ++}; ++static const u8 enc_key042[] __initconst = { ++ 0xfe, 0x6e, 0x55, 0xbd, 0xae, 0xd1, 0xf7, 0x28, ++ 0x4c, 0xa5, 0xfc, 0x0f, 0x8c, 0x5f, 0x2b, 0x8d, ++ 0xf5, 0x6d, 0xc0, 0xf4, 0x9e, 0x8c, 0xa6, 0x6a, ++ 0x41, 0x99, 0x5e, 0x78, 0x33, 0x51, 0xf9, 0x01 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input043[] __initconst = { ++ 0xce, 0xb5, 0x34, 0xce, 0x50, 0xdc, 0x23, 0xff, ++ 0x63, 0x8a, 0xce, 0x3e, 0xf6, 0x3a, 0xb2, 0xcc, ++ 0x29, 0x73, 0xee, 0xad, 0xa8, 0x07, 0x85, 0xfc, ++ 0x16, 0x5d, 0x06, 0xc2, 0xf5, 0x10, 0x0f, 0xf5, ++ 0xe8, 0xab, 0x28, 0x82, 0xc4, 0x75, 0xaf, 0xcd, ++ 0x05, 0xcc, 0xd4, 0x9f, 0x2e, 0x7d, 0x8f, 0x55, ++ 0xef, 0x3a, 0x72, 0xe3, 0xdc, 0x51, 0xd6, 0x85, ++ 0x2b, 0x8e, 0x6b, 0x9e, 0x7a, 0xec, 0xe5, 0x7b, ++ 0xe6, 0x55, 0x6b, 0x0b, 0x6d, 0x94, 0x13, 0xe3, ++ 0x3f, 0xc5, 0xfc, 0x24, 0xa9, 0xa2, 0x05, 0xad, ++ 0x59, 0x57, 0x4b, 0xb3, 0x9d, 0x94, 0x4a, 0x92, ++ 0xdc, 0x47, 0x97, 0x0d, 0x84, 0xa6, 0xad, 0x31, ++ 0x76 ++}; ++static const u8 enc_output043[] __initconst = { ++ 0x75, 0x45, 0x39, 0x1b, 0x51, 0xde, 0x01, 0xd5, ++ 0xc5, 0x3d, 0xfa, 0xca, 0x77, 0x79, 0x09, 0x06, ++ 0x3e, 0x58, 0xed, 0xee, 0x4b, 0xb1, 0x22, 0x7e, ++ 0x71, 0x10, 0xac, 0x4d, 0x26, 0x20, 0xc2, 0xae, ++ 0xc2, 0xf8, 0x48, 0xf5, 0x6d, 0xee, 0xb0, 0x37, ++ 0xa8, 0xdc, 0xed, 0x75, 0xaf, 0xa8, 0xa6, 0xc8, ++ 0x90, 0xe2, 0xde, 0xe4, 0x2f, 0x95, 0x0b, 0xb3, ++ 0x3d, 0x9e, 0x24, 0x24, 0xd0, 0x8a, 0x50, 0x5d, ++ 0x89, 0x95, 0x63, 0x97, 0x3e, 0xd3, 0x88, 0x70, ++ 0xf3, 0xde, 0x6e, 0xe2, 0xad, 0xc7, 0xfe, 0x07, ++ 0x2c, 0x36, 0x6c, 0x14, 0xe2, 0xcf, 0x7c, 0xa6, ++ 0x2f, 0xb3, 0xd3, 0x6b, 0xee, 0x11, 0x68, 0x54, ++ 0x61, 0xb7, 0x0d, 0x44, 0xef, 0x8c, 0x66, 0xc5, ++ 0xc7, 0xbb, 0xf1, 0x0d, 0xca, 0xdd, 0x7f, 0xac, ++ 0xf6 ++}; ++static const u8 enc_assoc043[] __initconst = { ++ 0xa1, 0x1c, 0x40, 0xb6, 0x03, 0x76, 0x73, 0x30 ++}; ++static const u8 enc_nonce043[] __initconst = { ++ 0x46, 0x36, 0x2f, 0x45, 0xd6, 0x37, 0x9e, 0x63, ++ 0xe5, 0x22, 0x94, 0x60 ++}; ++static const u8 enc_key043[] __initconst = { ++ 0xaa, 0xbc, 0x06, 0x34, 0x74, 0xe6, 0x5c, 0x4c, ++ 0x3e, 0x9b, 0xdc, 0x48, 0x0d, 0xea, 0x97, 0xb4, ++ 0x51, 0x10, 0xc8, 0x61, 0x88, 0x46, 0xff, 0x6b, ++ 0x15, 0xbd, 0xd2, 0xa4, 0xa5, 0x68, 0x2c, 0x4e ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input044[] __initconst = { ++ 0xe5, 0xcc, 0xaa, 0x44, 0x1b, 0xc8, 0x14, 0x68, ++ 0x8f, 0x8f, 0x6e, 0x8f, 0x28, 0xb5, 0x00, 0xb2 ++}; ++static const u8 enc_output044[] __initconst = { ++ 0x7e, 0x72, 0xf5, 0xa1, 0x85, 0xaf, 0x16, 0xa6, ++ 0x11, 0x92, 0x1b, 0x43, 0x8f, 0x74, 0x9f, 0x0b, ++ 0x12, 0x42, 0xc6, 0x70, 0x73, 0x23, 0x34, 0x02, ++ 0x9a, 0xdf, 0xe1, 0xc5, 0x00, 0x16, 0x51, 0xe4 ++}; ++static const u8 enc_assoc044[] __initconst = { ++ 0x02 ++}; ++static const u8 enc_nonce044[] __initconst = { ++ 0x87, 0x34, 0x5f, 0x10, 0x55, 0xfd, 0x9e, 0x21, ++ 0x02, 0xd5, 0x06, 0x56 ++}; ++static const u8 enc_key044[] __initconst = { ++ 0x7d, 0x00, 0xb4, 0x80, 0x95, 0xad, 0xfa, 0x32, ++ 0x72, 0x05, 0x06, 0x07, 0xb2, 0x64, 0x18, 0x50, ++ 0x02, 0xba, 0x99, 0x95, 0x7c, 0x49, 0x8b, 0xe0, ++ 0x22, 0x77, 0x0f, 0x2c, 0xe2, 0xf3, 0x14, 0x3c ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input045[] __initconst = { ++ 0x02, 0xcd, 0xe1, 0x68, 0xfb, 0xa3, 0xf5, 0x44, ++ 0xbb, 0xd0, 0x33, 0x2f, 0x7a, 0xde, 0xad, 0xa8 ++}; ++static const u8 enc_output045[] __initconst = { ++ 0x85, 0xf2, 0x9a, 0x71, 0x95, 0x57, 0xcd, 0xd1, ++ 0x4d, 0x1f, 0x8f, 0xff, 0xab, 0x6d, 0x9e, 0x60, ++ 0x73, 0x2c, 0xa3, 0x2b, 0xec, 0xd5, 0x15, 0xa1, ++ 0xed, 0x35, 0x3f, 0x54, 0x2e, 0x99, 0x98, 0x58 ++}; ++static const u8 enc_assoc045[] __initconst = { ++ 0xb6, 0x48 ++}; ++static const u8 enc_nonce045[] __initconst = { ++ 0x87, 0xa3, 0x16, 0x3e, 0xc0, 0x59, 0x8a, 0xd9, ++ 0x5b, 0x3a, 0xa7, 0x13 ++}; ++static const u8 enc_key045[] __initconst = { ++ 0x64, 0x32, 0x71, 0x7f, 0x1d, 0xb8, 0x5e, 0x41, ++ 0xac, 0x78, 0x36, 0xbc, 0xe2, 0x51, 0x85, 0xa0, ++ 0x80, 0xd5, 0x76, 0x2b, 0x9e, 0x2b, 0x18, 0x44, ++ 0x4b, 0x6e, 0xc7, 0x2c, 0x3b, 0xd8, 0xe4, 0xdc ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input046[] __initconst = { ++ 0x16, 0xdd, 0xd2, 0x3f, 0xf5, 0x3f, 0x3d, 0x23, ++ 0xc0, 0x63, 0x34, 0x48, 0x70, 0x40, 0xeb, 0x47 ++}; ++static const u8 enc_output046[] __initconst = { ++ 0xc1, 0xb2, 0x95, 0x93, 0x6d, 0x56, 0xfa, 0xda, ++ 0xc0, 0x3e, 0x5f, 0x74, 0x2b, 0xff, 0x73, 0xa1, ++ 0x39, 0xc4, 0x57, 0xdb, 0xab, 0x66, 0x38, 0x2b, ++ 0xab, 0xb3, 0xb5, 0x58, 0x00, 0xcd, 0xa5, 0xb8 ++}; ++static const u8 enc_assoc046[] __initconst = { ++ 0xbd, 0x4c, 0xd0, 0x2f, 0xc7, 0x50, 0x2b, 0xbd, ++ 0xbd, 0xf6, 0xc9, 0xa3, 0xcb, 0xe8, 0xf0 ++}; ++static const u8 enc_nonce046[] __initconst = { ++ 0x6f, 0x57, 0x3a, 0xa8, 0x6b, 0xaa, 0x49, 0x2b, ++ 0xa4, 0x65, 0x96, 0xdf ++}; ++static const u8 enc_key046[] __initconst = { ++ 0x8e, 0x34, 0xcf, 0x73, 0xd2, 0x45, 0xa1, 0x08, ++ 0x2a, 0x92, 0x0b, 0x86, 0x36, 0x4e, 0xb8, 0x96, ++ 0xc4, 0x94, 0x64, 0x67, 0xbc, 0xb3, 0xd5, 0x89, ++ 0x29, 0xfc, 0xb3, 0x66, 0x90, 0xe6, 0x39, 0x4f ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input047[] __initconst = { ++ 0x62, 0x3b, 0x78, 0x50, 0xc3, 0x21, 0xe2, 0xcf, ++ 0x0c, 0x6f, 0xbc, 0xc8, 0xdf, 0xd1, 0xaf, 0xf2 ++}; ++static const u8 enc_output047[] __initconst = { ++ 0xc8, 0x4c, 0x9b, 0xb7, 0xc6, 0x1c, 0x1b, 0xcb, ++ 0x17, 0x77, 0x2a, 0x1c, 0x50, 0x0c, 0x50, 0x95, ++ 0xdb, 0xad, 0xf7, 0xa5, 0x13, 0x8c, 0xa0, 0x34, ++ 0x59, 0xa2, 0xcd, 0x65, 0x83, 0x1e, 0x09, 0x2f ++}; ++static const u8 enc_assoc047[] __initconst = { ++ 0x89, 0xcc, 0xe9, 0xfb, 0x47, 0x44, 0x1d, 0x07, ++ 0xe0, 0x24, 0x5a, 0x66, 0xfe, 0x8b, 0x77, 0x8b ++}; ++static const u8 enc_nonce047[] __initconst = { ++ 0x1a, 0x65, 0x18, 0xf0, 0x2e, 0xde, 0x1d, 0xa6, ++ 0x80, 0x92, 0x66, 0xd9 ++}; ++static const u8 enc_key047[] __initconst = { ++ 0xcb, 0x55, 0x75, 0xf5, 0xc7, 0xc4, 0x5c, 0x91, ++ 0xcf, 0x32, 0x0b, 0x13, 0x9f, 0xb5, 0x94, 0x23, ++ 0x75, 0x60, 0xd0, 0xa3, 0xe6, 0xf8, 0x65, 0xa6, ++ 0x7d, 0x4f, 0x63, 0x3f, 0x2c, 0x08, 0xf0, 0x16 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input048[] __initconst = { ++ 0x87, 0xb3, 0xa4, 0xd7, 0xb2, 0x6d, 0x8d, 0x32, ++ 0x03, 0xa0, 0xde, 0x1d, 0x64, 0xef, 0x82, 0xe3 ++}; ++static const u8 enc_output048[] __initconst = { ++ 0x94, 0xbc, 0x80, 0x62, 0x1e, 0xd1, 0xe7, 0x1b, ++ 0x1f, 0xd2, 0xb5, 0xc3, 0xa1, 0x5e, 0x35, 0x68, ++ 0x33, 0x35, 0x11, 0x86, 0x17, 0x96, 0x97, 0x84, ++ 0x01, 0x59, 0x8b, 0x96, 0x37, 0x22, 0xf5, 0xb3 ++}; ++static const u8 enc_assoc048[] __initconst = { ++ 0xd1, 0x9f, 0x2d, 0x98, 0x90, 0x95, 0xf7, 0xab, ++ 0x03, 0xa5, 0xfd, 0xe8, 0x44, 0x16, 0xe0, 0x0c, ++ 0x0e ++}; ++static const u8 enc_nonce048[] __initconst = { ++ 0x56, 0x4d, 0xee, 0x49, 0xab, 0x00, 0xd2, 0x40, ++ 0xfc, 0x10, 0x68, 0xc3 ++}; ++static const u8 enc_key048[] __initconst = { ++ 0xa5, 0x56, 0x9e, 0x72, 0x9a, 0x69, 0xb2, 0x4b, ++ 0xa6, 0xe0, 0xff, 0x15, 0xc4, 0x62, 0x78, 0x97, ++ 0x43, 0x68, 0x24, 0xc9, 0x41, 0xe9, 0xd0, 0x0b, ++ 0x2e, 0x93, 0xfd, 0xdc, 0x4b, 0xa7, 0x76, 0x57 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input049[] __initconst = { ++ 0xe6, 0x01, 0xb3, 0x85, 0x57, 0x79, 0x7d, 0xa2, ++ 0xf8, 0xa4, 0x10, 0x6a, 0x08, 0x9d, 0x1d, 0xa6 ++}; ++static const u8 enc_output049[] __initconst = { ++ 0x29, 0x9b, 0x5d, 0x3f, 0x3d, 0x03, 0xc0, 0x87, ++ 0x20, 0x9a, 0x16, 0xe2, 0x85, 0x14, 0x31, 0x11, ++ 0x4b, 0x45, 0x4e, 0xd1, 0x98, 0xde, 0x11, 0x7e, ++ 0x83, 0xec, 0x49, 0xfa, 0x8d, 0x85, 0x08, 0xd6 ++}; ++static const u8 enc_assoc049[] __initconst = { ++ 0x5e, 0x64, 0x70, 0xfa, 0xcd, 0x99, 0xc1, 0xd8, ++ 0x1e, 0x37, 0xcd, 0x44, 0x01, 0x5f, 0xe1, 0x94, ++ 0x80, 0xa2, 0xa4, 0xd3, 0x35, 0x2a, 0x4f, 0xf5, ++ 0x60, 0xc0, 0x64, 0x0f, 0xdb, 0xda ++}; ++static const u8 enc_nonce049[] __initconst = { ++ 0xdf, 0x87, 0x13, 0xe8, 0x7e, 0xc3, 0xdb, 0xcf, ++ 0xad, 0x14, 0xd5, 0x3e ++}; ++static const u8 enc_key049[] __initconst = { ++ 0x56, 0x20, 0x74, 0x65, 0xb4, 0xe4, 0x8e, 0x6d, ++ 0x04, 0x63, 0x0f, 0x4a, 0x42, 0xf3, 0x5c, 0xfc, ++ 0x16, 0x3a, 0xb2, 0x89, 0xc2, 0x2a, 0x2b, 0x47, ++ 0x84, 0xf6, 0xf9, 0x29, 0x03, 0x30, 0xbe, 0xe0 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input050[] __initconst = { ++ 0xdc, 0x9e, 0x9e, 0xaf, 0x11, 0xe3, 0x14, 0x18, ++ 0x2d, 0xf6, 0xa4, 0xeb, 0xa1, 0x7a, 0xec, 0x9c ++}; ++static const u8 enc_output050[] __initconst = { ++ 0x60, 0x5b, 0xbf, 0x90, 0xae, 0xb9, 0x74, 0xf6, ++ 0x60, 0x2b, 0xc7, 0x78, 0x05, 0x6f, 0x0d, 0xca, ++ 0x38, 0xea, 0x23, 0xd9, 0x90, 0x54, 0xb4, 0x6b, ++ 0x42, 0xff, 0xe0, 0x04, 0x12, 0x9d, 0x22, 0x04 ++}; ++static const u8 enc_assoc050[] __initconst = { ++ 0xba, 0x44, 0x6f, 0x6f, 0x9a, 0x0c, 0xed, 0x22, ++ 0x45, 0x0f, 0xeb, 0x10, 0x73, 0x7d, 0x90, 0x07, ++ 0xfd, 0x69, 0xab, 0xc1, 0x9b, 0x1d, 0x4d, 0x90, ++ 0x49, 0xa5, 0x55, 0x1e, 0x86, 0xec, 0x2b, 0x37 ++}; ++static const u8 enc_nonce050[] __initconst = { ++ 0x8d, 0xf4, 0xb1, 0x5a, 0x88, 0x8c, 0x33, 0x28, ++ 0x6a, 0x7b, 0x76, 0x51 ++}; ++static const u8 enc_key050[] __initconst = { ++ 0x39, 0x37, 0x98, 0x6a, 0xf8, 0x6d, 0xaf, 0xc1, ++ 0xba, 0x0c, 0x46, 0x72, 0xd8, 0xab, 0xc4, 0x6c, ++ 0x20, 0x70, 0x62, 0x68, 0x2d, 0x9c, 0x26, 0x4a, ++ 0xb0, 0x6d, 0x6c, 0x58, 0x07, 0x20, 0x51, 0x30 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input051[] __initconst = { ++ 0x81, 0xce, 0x84, 0xed, 0xe9, 0xb3, 0x58, 0x59, ++ 0xcc, 0x8c, 0x49, 0xa8, 0xf6, 0xbe, 0x7d, 0xc6 ++}; ++static const u8 enc_output051[] __initconst = { ++ 0x7b, 0x7c, 0xe0, 0xd8, 0x24, 0x80, 0x9a, 0x70, ++ 0xde, 0x32, 0x56, 0x2c, 0xcf, 0x2c, 0x2b, 0xbd, ++ 0x15, 0xd4, 0x4a, 0x00, 0xce, 0x0d, 0x19, 0xb4, ++ 0x23, 0x1f, 0x92, 0x1e, 0x22, 0xbc, 0x0a, 0x43 ++}; ++static const u8 enc_assoc051[] __initconst = { ++ 0xd4, 0x1a, 0x82, 0x8d, 0x5e, 0x71, 0x82, 0x92, ++ 0x47, 0x02, 0x19, 0x05, 0x40, 0x2e, 0xa2, 0x57, ++ 0xdc, 0xcb, 0xc3, 0xb8, 0x0f, 0xcd, 0x56, 0x75, ++ 0x05, 0x6b, 0x68, 0xbb, 0x59, 0xe6, 0x2e, 0x88, ++ 0x73 ++}; ++static const u8 enc_nonce051[] __initconst = { ++ 0xbe, 0x40, 0xe5, 0xf1, 0xa1, 0x18, 0x17, 0xa0, ++ 0xa8, 0xfa, 0x89, 0x49 ++}; ++static const u8 enc_key051[] __initconst = { ++ 0x36, 0x37, 0x2a, 0xbc, 0xdb, 0x78, 0xe0, 0x27, ++ 0x96, 0x46, 0xac, 0x3d, 0x17, 0x6b, 0x96, 0x74, ++ 0xe9, 0x15, 0x4e, 0xec, 0xf0, 0xd5, 0x46, 0x9c, ++ 0x65, 0x1e, 0xc7, 0xe1, 0x6b, 0x4c, 0x11, 0x99 ++}; ++ ++/* wycheproof - misc */ ++static const u8 enc_input052[] __initconst = { ++ 0xa6, 0x67, 0x47, 0xc8, 0x9e, 0x85, 0x7a, 0xf3, ++ 0xa1, 0x8e, 0x2c, 0x79, 0x50, 0x00, 0x87, 0xed ++}; ++static const u8 enc_output052[] __initconst = { ++ 0xca, 0x82, 0xbf, 0xf3, 0xe2, 0xf3, 0x10, 0xcc, ++ 0xc9, 0x76, 0x67, 0x2c, 0x44, 0x15, 0xe6, 0x9b, ++ 0x57, 0x63, 0x8c, 0x62, 0xa5, 0xd8, 0x5d, 0xed, ++ 0x77, 0x4f, 0x91, 0x3c, 0x81, 0x3e, 0xa0, 0x32 ++}; ++static const u8 enc_assoc052[] __initconst = { ++ 0x3f, 0x2d, 0xd4, 0x9b, 0xbf, 0x09, 0xd6, 0x9a, ++ 0x78, 0xa3, 0xd8, 0x0e, 0xa2, 0x56, 0x66, 0x14, ++ 0xfc, 0x37, 0x94, 0x74, 0x19, 0x6c, 0x1a, 0xae, ++ 0x84, 0x58, 0x3d, 0xa7, 0x3d, 0x7f, 0xf8, 0x5c, ++ 0x6f, 0x42, 0xca, 0x42, 0x05, 0x6a, 0x97, 0x92, ++ 0xcc, 0x1b, 0x9f, 0xb3, 0xc7, 0xd2, 0x61 ++}; ++static const u8 enc_nonce052[] __initconst = { ++ 0x84, 0xc8, 0x7d, 0xae, 0x4e, 0xee, 0x27, 0x73, ++ 0x0e, 0xc3, 0x5d, 0x12 ++}; ++static const u8 enc_key052[] __initconst = { ++ 0x9f, 0x14, 0x79, 0xed, 0x09, 0x7d, 0x7f, 0xe5, ++ 0x29, 0xc1, 0x1f, 0x2f, 0x5a, 0xdd, 0x9a, 0xaf, ++ 0xf4, 0xa1, 0xca, 0x0b, 0x68, 0x99, 0x7a, 0x2c, ++ 0xb7, 0xf7, 0x97, 0x49, 0xbd, 0x90, 0xaa, 0xf4 ++}; ++ + /* wycheproof - misc */ + static const u8 enc_input053[] __initconst = { + 0x25, 0x6d, 0x40, 0x88, 0x80, 0x94, 0x17, 0x83, +@@ -2760,6 +3859,126 @@ static const u8 enc_key073[] __initconst + }; + + /* wycheproof - checking for int overflows */ ++static const u8 enc_input074[] __initconst = { ++ 0xd4, 0x50, 0x0b, 0xf0, 0x09, 0x49, 0x35, 0x51, ++ 0xc3, 0x80, 0xad, 0xf5, 0x2c, 0x57, 0x3a, 0x69, ++ 0xdf, 0x7e, 0x8b, 0x76, 0x24, 0x63, 0x33, 0x0f, ++ 0xac, 0xc1, 0x6a, 0x57, 0x26, 0xbe, 0x71, 0x90, ++ 0xc6, 0x3c, 0x5a, 0x1c, 0x92, 0x65, 0x84, 0xa0, ++ 0x96, 0x75, 0x68, 0x28, 0xdc, 0xdc, 0x64, 0xac, ++ 0xdf, 0x96, 0x3d, 0x93, 0x1b, 0xf1, 0xda, 0xe2, ++ 0x38, 0xf3, 0xf1, 0x57, 0x22, 0x4a, 0xc4, 0xb5, ++ 0x42, 0xd7, 0x85, 0xb0, 0xdd, 0x84, 0xdb, 0x6b, ++ 0xe3, 0xbc, 0x5a, 0x36, 0x63, 0xe8, 0x41, 0x49, ++ 0xff, 0xbe, 0xd0, 0x9e, 0x54, 0xf7, 0x8f, 0x16, ++ 0xa8, 0x22, 0x3b, 0x24, 0xcb, 0x01, 0x9f, 0x58, ++ 0xb2, 0x1b, 0x0e, 0x55, 0x1e, 0x7a, 0xa0, 0x73, ++ 0x27, 0x62, 0x95, 0x51, 0x37, 0x6c, 0xcb, 0xc3, ++ 0x93, 0x76, 0x71, 0xa0, 0x62, 0x9b, 0xd9, 0x5c, ++ 0x99, 0x15, 0xc7, 0x85, 0x55, 0x77, 0x1e, 0x7a ++}; ++static const u8 enc_output074[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x0b, 0x30, 0x0d, 0x8d, 0xa5, 0x6c, 0x21, 0x85, ++ 0x75, 0x52, 0x79, 0x55, 0x3c, 0x4c, 0x82, 0xca ++}; ++static const u8 enc_assoc074[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce074[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x00, 0x02, 0x50, 0x6e ++}; ++static const u8 enc_key074[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ ++static const u8 enc_input075[] __initconst = { ++ 0x7d, 0xe8, 0x7f, 0x67, 0x29, 0x94, 0x52, 0x75, ++ 0xd0, 0x65, 0x5d, 0xa4, 0xc7, 0xfd, 0xe4, 0x56, ++ 0x9e, 0x16, 0xf1, 0x11, 0xb5, 0xeb, 0x26, 0xc2, ++ 0x2d, 0x85, 0x9e, 0x3f, 0xf8, 0x22, 0xec, 0xed, ++ 0x3a, 0x6d, 0xd9, 0xa6, 0x0f, 0x22, 0x95, 0x7f, ++ 0x7b, 0x7c, 0x85, 0x7e, 0x88, 0x22, 0xeb, 0x9f, ++ 0xe0, 0xb8, 0xd7, 0x02, 0x21, 0x41, 0xf2, 0xd0, ++ 0xb4, 0x8f, 0x4b, 0x56, 0x12, 0xd3, 0x22, 0xa8, ++ 0x8d, 0xd0, 0xfe, 0x0b, 0x4d, 0x91, 0x79, 0x32, ++ 0x4f, 0x7c, 0x6c, 0x9e, 0x99, 0x0e, 0xfb, 0xd8, ++ 0x0e, 0x5e, 0xd6, 0x77, 0x58, 0x26, 0x49, 0x8b, ++ 0x1e, 0xfe, 0x0f, 0x71, 0xa0, 0xf3, 0xec, 0x5b, ++ 0x29, 0xcb, 0x28, 0xc2, 0x54, 0x0a, 0x7d, 0xcd, ++ 0x51, 0xb7, 0xda, 0xae, 0xe0, 0xff, 0x4a, 0x7f, ++ 0x3a, 0xc1, 0xee, 0x54, 0xc2, 0x9e, 0xe4, 0xc1, ++ 0x70, 0xde, 0x40, 0x8f, 0x66, 0x69, 0x21, 0x94 ++}; ++static const u8 enc_output075[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xc5, 0x78, 0xe2, 0xaa, 0x44, 0xd3, 0x09, 0xb7, ++ 0xb6, 0xa5, 0x19, 0x3b, 0xdc, 0x61, 0x18, 0xf5 ++}; ++static const u8 enc_assoc075[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_nonce075[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x00, 0x03, 0x18, 0xa5 ++}; ++static const u8 enc_key075[] __initconst = { ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, ++ 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30 ++}; ++ ++/* wycheproof - checking for int overflows */ + static const u8 enc_input076[] __initconst = { + 0x1b, 0x99, 0x6f, 0x9a, 0x3c, 0xcc, 0x67, 0x85, + 0xde, 0x22, 0xff, 0x5b, 0x8a, 0xdd, 0x95, 0x02, +@@ -3349,6 +4568,286 @@ static const u8 enc_key085[] __initconst + 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f + }; + ++/* wycheproof - special case tag */ ++static const u8 enc_input086[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output086[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f ++}; ++static const u8 enc_assoc086[] __initconst = { ++ 0x85, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xa6, 0x90, 0x2f, 0xcb, 0xc8, 0x83, 0xbb, 0xc1, ++ 0x80, 0xb2, 0x56, 0xae, 0x34, 0xad, 0x7f, 0x00 ++}; ++static const u8 enc_nonce086[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key086[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - special case tag */ ++static const u8 enc_input087[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output087[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_assoc087[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x24, 0x7e, 0x50, 0x64, 0x2a, 0x1c, 0x0a, 0x2f, ++ 0x8f, 0x77, 0x21, 0x96, 0x09, 0xdb, 0xa9, 0x58 ++}; ++static const u8 enc_nonce087[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key087[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - special case tag */ ++static const u8 enc_input088[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output088[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff ++}; ++static const u8 enc_assoc088[] __initconst = { ++ 0x7c, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xd9, 0xe7, 0x2c, 0x06, 0x4a, 0xc8, 0x96, 0x1f, ++ 0x3f, 0xa5, 0x85, 0xe0, 0xe2, 0xab, 0xd6, 0x00 ++}; ++static const u8 enc_nonce088[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key088[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - special case tag */ ++static const u8 enc_input089[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output089[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80, ++ 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, 0x80 ++}; ++static const u8 enc_assoc089[] __initconst = { ++ 0x65, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x95, 0xaf, 0x0f, 0x4d, 0x0b, 0x68, 0x6e, 0xae, ++ 0xcc, 0xca, 0x43, 0x07, 0xd5, 0x96, 0xf5, 0x02 ++}; ++static const u8 enc_nonce089[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key089[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - special case tag */ ++static const u8 enc_input090[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output090[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f, ++ 0xff, 0xff, 0xff, 0x7f, 0xff, 0xff, 0xff, 0x7f ++}; ++static const u8 enc_assoc090[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x85, 0x40, 0xb4, 0x64, 0x35, 0x77, 0x07, 0xbe, ++ 0x3a, 0x39, 0xd5, 0x5c, 0x34, 0xf8, 0xbc, 0xb3 ++}; ++static const u8 enc_nonce090[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key090[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - special case tag */ ++static const u8 enc_input091[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output091[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x01, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, ++ 0x01, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_assoc091[] __initconst = { ++ 0x4f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x66, 0x23, 0xd9, 0x90, 0xb8, 0x98, 0xd8, 0x30, ++ 0xd2, 0x12, 0xaf, 0x23, 0x83, 0x33, 0x07, 0x01 ++}; ++static const u8 enc_nonce091[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key091[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ ++/* wycheproof - special case tag */ ++static const u8 enc_input092[] __initconst = { ++ 0x9a, 0x49, 0xc4, 0x0f, 0x8b, 0x48, 0xd7, 0xc6, ++ 0x6d, 0x1d, 0xb4, 0xe5, 0x3f, 0x20, 0xf2, 0xdd, ++ 0x4a, 0xaa, 0x24, 0x1d, 0xda, 0xb2, 0x6b, 0x5b, ++ 0xc0, 0xe2, 0x18, 0xb7, 0x2c, 0x33, 0x90, 0xf2, ++ 0xdf, 0x3e, 0xbd, 0x01, 0x76, 0x70, 0x44, 0x19, ++ 0x97, 0x2b, 0xcd, 0xbc, 0x6b, 0xbc, 0xb3, 0xe4, ++ 0xe7, 0x4a, 0x71, 0x52, 0x8e, 0xf5, 0x12, 0x63, ++ 0xce, 0x24, 0xe0, 0xd5, 0x75, 0xe0, 0xe4, 0x4d ++}; ++static const u8 enc_output092[] __initconst = { ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, ++ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 ++}; ++static const u8 enc_assoc092[] __initconst = { ++ 0x83, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, ++ 0x5f, 0x16, 0xd0, 0x9f, 0x17, 0x78, 0x72, 0x11, ++ 0xb7, 0xd4, 0x84, 0xe0, 0x24, 0xf8, 0x97, 0x01 ++}; ++static const u8 enc_nonce092[] __initconst = { ++ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, ++ 0x08, 0x09, 0x0a, 0x0b ++}; ++static const u8 enc_key092[] __initconst = { ++ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, ++ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, ++ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, ++ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f ++}; ++ + /* wycheproof - edge case intermediate sums in poly1305 */ + static const u8 enc_input093[] __initconst = { + 0x00, 0x52, 0x35, 0xd2, 0xa9, 0x19, 0xf2, 0x8d, +@@ -4455,6 +5954,86 @@ chacha20poly1305_enc_vectors[] __initcon + sizeof(enc_input011), sizeof(enc_assoc011), sizeof(enc_nonce011) }, + { enc_input012, enc_output012, enc_assoc012, enc_nonce012, enc_key012, + sizeof(enc_input012), sizeof(enc_assoc012), sizeof(enc_nonce012) }, ++ { enc_input013, enc_output013, enc_assoc013, enc_nonce013, enc_key013, ++ sizeof(enc_input013), sizeof(enc_assoc013), sizeof(enc_nonce013) }, ++ { enc_input014, enc_output014, enc_assoc014, enc_nonce014, enc_key014, ++ sizeof(enc_input014), sizeof(enc_assoc014), sizeof(enc_nonce014) }, ++ { enc_input015, enc_output015, enc_assoc015, enc_nonce015, enc_key015, ++ sizeof(enc_input015), sizeof(enc_assoc015), sizeof(enc_nonce015) }, ++ { enc_input016, enc_output016, enc_assoc016, enc_nonce016, enc_key016, ++ sizeof(enc_input016), sizeof(enc_assoc016), sizeof(enc_nonce016) }, ++ { enc_input017, enc_output017, enc_assoc017, enc_nonce017, enc_key017, ++ sizeof(enc_input017), sizeof(enc_assoc017), sizeof(enc_nonce017) }, ++ { enc_input018, enc_output018, enc_assoc018, enc_nonce018, enc_key018, ++ sizeof(enc_input018), sizeof(enc_assoc018), sizeof(enc_nonce018) }, ++ { enc_input019, enc_output019, enc_assoc019, enc_nonce019, enc_key019, ++ sizeof(enc_input019), sizeof(enc_assoc019), sizeof(enc_nonce019) }, ++ { enc_input020, enc_output020, enc_assoc020, enc_nonce020, enc_key020, ++ sizeof(enc_input020), sizeof(enc_assoc020), sizeof(enc_nonce020) }, ++ { enc_input021, enc_output021, enc_assoc021, enc_nonce021, enc_key021, ++ sizeof(enc_input021), sizeof(enc_assoc021), sizeof(enc_nonce021) }, ++ { enc_input022, enc_output022, enc_assoc022, enc_nonce022, enc_key022, ++ sizeof(enc_input022), sizeof(enc_assoc022), sizeof(enc_nonce022) }, ++ { enc_input023, enc_output023, enc_assoc023, enc_nonce023, enc_key023, ++ sizeof(enc_input023), sizeof(enc_assoc023), sizeof(enc_nonce023) }, ++ { enc_input024, enc_output024, enc_assoc024, enc_nonce024, enc_key024, ++ sizeof(enc_input024), sizeof(enc_assoc024), sizeof(enc_nonce024) }, ++ { enc_input025, enc_output025, enc_assoc025, enc_nonce025, enc_key025, ++ sizeof(enc_input025), sizeof(enc_assoc025), sizeof(enc_nonce025) }, ++ { enc_input026, enc_output026, enc_assoc026, enc_nonce026, enc_key026, ++ sizeof(enc_input026), sizeof(enc_assoc026), sizeof(enc_nonce026) }, ++ { enc_input027, enc_output027, enc_assoc027, enc_nonce027, enc_key027, ++ sizeof(enc_input027), sizeof(enc_assoc027), sizeof(enc_nonce027) }, ++ { enc_input028, enc_output028, enc_assoc028, enc_nonce028, enc_key028, ++ sizeof(enc_input028), sizeof(enc_assoc028), sizeof(enc_nonce028) }, ++ { enc_input029, enc_output029, enc_assoc029, enc_nonce029, enc_key029, ++ sizeof(enc_input029), sizeof(enc_assoc029), sizeof(enc_nonce029) }, ++ { enc_input030, enc_output030, enc_assoc030, enc_nonce030, enc_key030, ++ sizeof(enc_input030), sizeof(enc_assoc030), sizeof(enc_nonce030) }, ++ { enc_input031, enc_output031, enc_assoc031, enc_nonce031, enc_key031, ++ sizeof(enc_input031), sizeof(enc_assoc031), sizeof(enc_nonce031) }, ++ { enc_input032, enc_output032, enc_assoc032, enc_nonce032, enc_key032, ++ sizeof(enc_input032), sizeof(enc_assoc032), sizeof(enc_nonce032) }, ++ { enc_input033, enc_output033, enc_assoc033, enc_nonce033, enc_key033, ++ sizeof(enc_input033), sizeof(enc_assoc033), sizeof(enc_nonce033) }, ++ { enc_input034, enc_output034, enc_assoc034, enc_nonce034, enc_key034, ++ sizeof(enc_input034), sizeof(enc_assoc034), sizeof(enc_nonce034) }, ++ { enc_input035, enc_output035, enc_assoc035, enc_nonce035, enc_key035, ++ sizeof(enc_input035), sizeof(enc_assoc035), sizeof(enc_nonce035) }, ++ { enc_input036, enc_output036, enc_assoc036, enc_nonce036, enc_key036, ++ sizeof(enc_input036), sizeof(enc_assoc036), sizeof(enc_nonce036) }, ++ { enc_input037, enc_output037, enc_assoc037, enc_nonce037, enc_key037, ++ sizeof(enc_input037), sizeof(enc_assoc037), sizeof(enc_nonce037) }, ++ { enc_input038, enc_output038, enc_assoc038, enc_nonce038, enc_key038, ++ sizeof(enc_input038), sizeof(enc_assoc038), sizeof(enc_nonce038) }, ++ { enc_input039, enc_output039, enc_assoc039, enc_nonce039, enc_key039, ++ sizeof(enc_input039), sizeof(enc_assoc039), sizeof(enc_nonce039) }, ++ { enc_input040, enc_output040, enc_assoc040, enc_nonce040, enc_key040, ++ sizeof(enc_input040), sizeof(enc_assoc040), sizeof(enc_nonce040) }, ++ { enc_input041, enc_output041, enc_assoc041, enc_nonce041, enc_key041, ++ sizeof(enc_input041), sizeof(enc_assoc041), sizeof(enc_nonce041) }, ++ { enc_input042, enc_output042, enc_assoc042, enc_nonce042, enc_key042, ++ sizeof(enc_input042), sizeof(enc_assoc042), sizeof(enc_nonce042) }, ++ { enc_input043, enc_output043, enc_assoc043, enc_nonce043, enc_key043, ++ sizeof(enc_input043), sizeof(enc_assoc043), sizeof(enc_nonce043) }, ++ { enc_input044, enc_output044, enc_assoc044, enc_nonce044, enc_key044, ++ sizeof(enc_input044), sizeof(enc_assoc044), sizeof(enc_nonce044) }, ++ { enc_input045, enc_output045, enc_assoc045, enc_nonce045, enc_key045, ++ sizeof(enc_input045), sizeof(enc_assoc045), sizeof(enc_nonce045) }, ++ { enc_input046, enc_output046, enc_assoc046, enc_nonce046, enc_key046, ++ sizeof(enc_input046), sizeof(enc_assoc046), sizeof(enc_nonce046) }, ++ { enc_input047, enc_output047, enc_assoc047, enc_nonce047, enc_key047, ++ sizeof(enc_input047), sizeof(enc_assoc047), sizeof(enc_nonce047) }, ++ { enc_input048, enc_output048, enc_assoc048, enc_nonce048, enc_key048, ++ sizeof(enc_input048), sizeof(enc_assoc048), sizeof(enc_nonce048) }, ++ { enc_input049, enc_output049, enc_assoc049, enc_nonce049, enc_key049, ++ sizeof(enc_input049), sizeof(enc_assoc049), sizeof(enc_nonce049) }, ++ { enc_input050, enc_output050, enc_assoc050, enc_nonce050, enc_key050, ++ sizeof(enc_input050), sizeof(enc_assoc050), sizeof(enc_nonce050) }, ++ { enc_input051, enc_output051, enc_assoc051, enc_nonce051, enc_key051, ++ sizeof(enc_input051), sizeof(enc_assoc051), sizeof(enc_nonce051) }, ++ { enc_input052, enc_output052, enc_assoc052, enc_nonce052, enc_key052, ++ sizeof(enc_input052), sizeof(enc_assoc052), sizeof(enc_nonce052) }, + { enc_input053, enc_output053, enc_assoc053, enc_nonce053, enc_key053, + sizeof(enc_input053), sizeof(enc_assoc053), sizeof(enc_nonce053) }, + { enc_input054, enc_output054, enc_assoc054, enc_nonce054, enc_key054, +@@ -4497,6 +6076,10 @@ chacha20poly1305_enc_vectors[] __initcon + sizeof(enc_input072), sizeof(enc_assoc072), sizeof(enc_nonce072) }, + { enc_input073, enc_output073, enc_assoc073, enc_nonce073, enc_key073, + sizeof(enc_input073), sizeof(enc_assoc073), sizeof(enc_nonce073) }, ++ { enc_input074, enc_output074, enc_assoc074, enc_nonce074, enc_key074, ++ sizeof(enc_input074), sizeof(enc_assoc074), sizeof(enc_nonce074) }, ++ { enc_input075, enc_output075, enc_assoc075, enc_nonce075, enc_key075, ++ sizeof(enc_input075), sizeof(enc_assoc075), sizeof(enc_nonce075) }, + { enc_input076, enc_output076, enc_assoc076, enc_nonce076, enc_key076, + sizeof(enc_input076), sizeof(enc_assoc076), sizeof(enc_nonce076) }, + { enc_input077, enc_output077, enc_assoc077, enc_nonce077, enc_key077, +@@ -4517,6 +6100,20 @@ chacha20poly1305_enc_vectors[] __initcon + sizeof(enc_input084), sizeof(enc_assoc084), sizeof(enc_nonce084) }, + { enc_input085, enc_output085, enc_assoc085, enc_nonce085, enc_key085, + sizeof(enc_input085), sizeof(enc_assoc085), sizeof(enc_nonce085) }, ++ { enc_input086, enc_output086, enc_assoc086, enc_nonce086, enc_key086, ++ sizeof(enc_input086), sizeof(enc_assoc086), sizeof(enc_nonce086) }, ++ { enc_input087, enc_output087, enc_assoc087, enc_nonce087, enc_key087, ++ sizeof(enc_input087), sizeof(enc_assoc087), sizeof(enc_nonce087) }, ++ { enc_input088, enc_output088, enc_assoc088, enc_nonce088, enc_key088, ++ sizeof(enc_input088), sizeof(enc_assoc088), sizeof(enc_nonce088) }, ++ { enc_input089, enc_output089, enc_assoc089, enc_nonce089, enc_key089, ++ sizeof(enc_input089), sizeof(enc_assoc089), sizeof(enc_nonce089) }, ++ { enc_input090, enc_output090, enc_assoc090, enc_nonce090, enc_key090, ++ sizeof(enc_input090), sizeof(enc_assoc090), sizeof(enc_nonce090) }, ++ { enc_input091, enc_output091, enc_assoc091, enc_nonce091, enc_key091, ++ sizeof(enc_input091), sizeof(enc_assoc091), sizeof(enc_nonce091) }, ++ { enc_input092, enc_output092, enc_assoc092, enc_nonce092, enc_key092, ++ sizeof(enc_input092), sizeof(enc_assoc092), sizeof(enc_nonce092) }, + { enc_input093, enc_output093, enc_assoc093, enc_nonce093, enc_key093, + sizeof(enc_input093), sizeof(enc_assoc093), sizeof(enc_nonce093) }, + { enc_input094, enc_output094, enc_assoc094, enc_nonce094, enc_key094, +@@ -7224,6 +8821,43 @@ xchacha20poly1305_dec_vectors[] __initco + sizeof(xdec_input001), sizeof(xdec_assoc001), sizeof(xdec_nonce001) } + }; + ++/* This is for the selftests-only, since it is only useful for the purpose of ++ * testing the underlying primitives and interactions. ++ */ ++static void __init ++chacha20poly1305_encrypt_bignonce(u8 *dst, const u8 *src, const size_t src_len, ++ const u8 *ad, const size_t ad_len, ++ const u8 nonce[12], ++ const u8 key[CHACHA20POLY1305_KEY_SIZE]) ++{ ++ const u8 *pad0 = page_address(ZERO_PAGE(0)); ++ struct poly1305_desc_ctx poly1305_state; ++ u32 chacha20_state[CHACHA_STATE_WORDS]; ++ union { ++ u8 block0[POLY1305_KEY_SIZE]; ++ __le64 lens[2]; ++ } b = {{ 0 }}; ++ u8 bottom_row[16] = { 0 }; ++ u32 le_key[8]; ++ int i; ++ ++ memcpy(&bottom_row[4], nonce, 12); ++ for (i = 0; i < 8; ++i) ++ le_key[i] = get_unaligned_le32(key + sizeof(le_key[i]) * i); ++ chacha_init(chacha20_state, le_key, bottom_row); ++ chacha20_crypt(chacha20_state, b.block0, b.block0, sizeof(b.block0)); ++ poly1305_init(&poly1305_state, b.block0); ++ poly1305_update(&poly1305_state, ad, ad_len); ++ poly1305_update(&poly1305_state, pad0, (0x10 - ad_len) & 0xf); ++ chacha20_crypt(chacha20_state, dst, src, src_len); ++ poly1305_update(&poly1305_state, dst, src_len); ++ poly1305_update(&poly1305_state, pad0, (0x10 - src_len) & 0xf); ++ b.lens[0] = cpu_to_le64(ad_len); ++ b.lens[1] = cpu_to_le64(src_len); ++ poly1305_update(&poly1305_state, (u8 *)b.lens, sizeof(b.lens)); ++ poly1305_final(&poly1305_state, dst + src_len); ++} ++ + static void __init + chacha20poly1305_selftest_encrypt(u8 *dst, const u8 *src, const size_t src_len, + const u8 *ad, const size_t ad_len, +@@ -7233,6 +8867,9 @@ chacha20poly1305_selftest_encrypt(u8 *ds + if (nonce_len == 8) + chacha20poly1305_encrypt(dst, src, src_len, ad, ad_len, + get_unaligned_le64(nonce), key); ++ else if (nonce_len == 12) ++ chacha20poly1305_encrypt_bignonce(dst, src, src_len, ad, ++ ad_len, nonce, key); + else + BUG(); + } +@@ -7248,14 +8885,14 @@ decryption_success(bool func_ret, bool e + bool __init chacha20poly1305_selftest(void) + { + enum { MAXIMUM_TEST_BUFFER_LEN = 1UL << 12 }; +- size_t i; +- u8 *computed_output = NULL, *heap_src = NULL; +- struct scatterlist sg_src; ++ size_t i, j, k, total_len; ++ u8 *computed_output = NULL, *input = NULL; + bool success = true, ret; ++ struct scatterlist sg_src[3]; + +- heap_src = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL); + computed_output = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL); +- if (!heap_src || !computed_output) { ++ input = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL); ++ if (!computed_output || !input) { + pr_err("chacha20poly1305 self-test malloc: FAIL\n"); + success = false; + goto out; +@@ -7284,17 +8921,17 @@ bool __init chacha20poly1305_selftest(vo + for (i = 0; i < ARRAY_SIZE(chacha20poly1305_enc_vectors); ++i) { + if (chacha20poly1305_enc_vectors[i].nlen != 8) + continue; +- memcpy(heap_src, chacha20poly1305_enc_vectors[i].input, ++ memcpy(computed_output, chacha20poly1305_enc_vectors[i].input, + chacha20poly1305_enc_vectors[i].ilen); +- sg_init_one(&sg_src, heap_src, ++ sg_init_one(sg_src, computed_output, + chacha20poly1305_enc_vectors[i].ilen + POLY1305_DIGEST_SIZE); +- chacha20poly1305_encrypt_sg_inplace(&sg_src, ++ ret = chacha20poly1305_encrypt_sg_inplace(sg_src, + chacha20poly1305_enc_vectors[i].ilen, + chacha20poly1305_enc_vectors[i].assoc, + chacha20poly1305_enc_vectors[i].alen, + get_unaligned_le64(chacha20poly1305_enc_vectors[i].nonce), + chacha20poly1305_enc_vectors[i].key); +- if (memcmp(heap_src, ++ if (!ret || memcmp(computed_output, + chacha20poly1305_enc_vectors[i].output, + chacha20poly1305_enc_vectors[i].ilen + + POLY1305_DIGEST_SIZE)) { +@@ -7326,11 +8963,11 @@ bool __init chacha20poly1305_selftest(vo + } + + for (i = 0; i < ARRAY_SIZE(chacha20poly1305_dec_vectors); ++i) { +- memcpy(heap_src, chacha20poly1305_dec_vectors[i].input, ++ memcpy(computed_output, chacha20poly1305_dec_vectors[i].input, + chacha20poly1305_dec_vectors[i].ilen); +- sg_init_one(&sg_src, heap_src, ++ sg_init_one(sg_src, computed_output, + chacha20poly1305_dec_vectors[i].ilen); +- ret = chacha20poly1305_decrypt_sg_inplace(&sg_src, ++ ret = chacha20poly1305_decrypt_sg_inplace(sg_src, + chacha20poly1305_dec_vectors[i].ilen, + chacha20poly1305_dec_vectors[i].assoc, + chacha20poly1305_dec_vectors[i].alen, +@@ -7338,7 +8975,7 @@ bool __init chacha20poly1305_selftest(vo + chacha20poly1305_dec_vectors[i].key); + if (!decryption_success(ret, + chacha20poly1305_dec_vectors[i].failure, +- memcmp(heap_src, chacha20poly1305_dec_vectors[i].output, ++ memcmp(computed_output, chacha20poly1305_dec_vectors[i].output, + chacha20poly1305_dec_vectors[i].ilen - + POLY1305_DIGEST_SIZE))) { + pr_err("chacha20poly1305 sg decryption self-test %zu: FAIL\n", +@@ -7365,6 +9002,7 @@ bool __init chacha20poly1305_selftest(vo + success = false; + } + } ++ + for (i = 0; i < ARRAY_SIZE(xchacha20poly1305_dec_vectors); ++i) { + memset(computed_output, 0, MAXIMUM_TEST_BUFFER_LEN); + ret = xchacha20poly1305_decrypt(computed_output, +@@ -7386,8 +9024,54 @@ bool __init chacha20poly1305_selftest(vo + } + } + ++ for (total_len = POLY1305_DIGEST_SIZE; IS_ENABLED(DEBUG_CHACHA20POLY1305_SLOW_CHUNK_TEST) ++ && total_len <= 1 << 10; ++total_len) { ++ for (i = 0; i <= total_len; ++i) { ++ for (j = i; j <= total_len; ++j) { ++ sg_init_table(sg_src, 3); ++ sg_set_buf(&sg_src[0], input, i); ++ sg_set_buf(&sg_src[1], input + i, j - i); ++ sg_set_buf(&sg_src[2], input + j, total_len - j); ++ memset(computed_output, 0, total_len); ++ memset(input, 0, total_len); ++ ++ if (!chacha20poly1305_encrypt_sg_inplace(sg_src, ++ total_len - POLY1305_DIGEST_SIZE, NULL, 0, ++ 0, enc_key001)) ++ goto chunkfail; ++ chacha20poly1305_encrypt(computed_output, ++ computed_output, ++ total_len - POLY1305_DIGEST_SIZE, NULL, 0, 0, ++ enc_key001); ++ if (memcmp(computed_output, input, total_len)) ++ goto chunkfail; ++ if (!chacha20poly1305_decrypt(computed_output, ++ input, total_len, NULL, 0, 0, enc_key001)) ++ goto chunkfail; ++ for (k = 0; k < total_len - POLY1305_DIGEST_SIZE; ++k) { ++ if (computed_output[k]) ++ goto chunkfail; ++ } ++ if (!chacha20poly1305_decrypt_sg_inplace(sg_src, ++ total_len, NULL, 0, 0, enc_key001)) ++ goto chunkfail; ++ for (k = 0; k < total_len - POLY1305_DIGEST_SIZE; ++k) { ++ if (input[k]) ++ goto chunkfail; ++ } ++ continue; ++ ++ chunkfail: ++ pr_err("chacha20poly1305 chunked self-test %zu/%zu/%zu: FAIL\n", ++ total_len, i, j); ++ success = false; ++ } ++ ++ } ++ } ++ + out: +- kfree(heap_src); + kfree(computed_output); ++ kfree(input); + return success; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0048-crypto-x86-poly1305-emit-does-base-conversion-itself.patch b/target/linux/generic/backport-5.4/080-wireguard-0048-crypto-x86-poly1305-emit-does-base-conversion-itself.patch new file mode 100644 index 0000000000..68af53f52c --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0048-crypto-x86-poly1305-emit-does-base-conversion-itself.patch @@ -0,0 +1,37 @@ +From 722ccb5da4bab4e142e4dc1eea10406a08547c7b Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 17 Jan 2020 11:42:22 +0100 +Subject: [PATCH 048/124] crypto: x86/poly1305 - emit does base conversion + itself + +commit f9e7fe32a792726186301423ff63a465d63386e1 upstream. + +The emit code does optional base conversion itself in assembly, so we +don't need to do that here. Also, neither one of these functions uses +simd instructions, so checking for that doesn't make sense either. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 8 ++------ + 1 file changed, 2 insertions(+), 6 deletions(-) + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -123,13 +123,9 @@ static void poly1305_simd_blocks(void *c + static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], + const u32 nonce[4]) + { +- struct poly1305_arch_internal *state = ctx; +- +- if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || +- !state->is_base2_26 || !crypto_simd_usable()) { +- convert_to_base2_64(ctx); ++ if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx)) + poly1305_emit_x86_64(ctx, mac, nonce); +- } else ++ else + poly1305_emit_avx(ctx, mac, nonce); + } + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0049-crypto-arm-chacha-fix-build-failured-when-kernel-mod.patch b/target/linux/generic/backport-5.4/080-wireguard-0049-crypto-arm-chacha-fix-build-failured-when-kernel-mod.patch new file mode 100644 index 0000000000..392d52f205 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0049-crypto-arm-chacha-fix-build-failured-when-kernel-mod.patch @@ -0,0 +1,58 @@ +From 627e2c8313065e627fe5c8c9f82cebd765f5a65e Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 17 Jan 2020 17:43:18 +0100 +Subject: [PATCH 049/124] crypto: arm/chacha - fix build failured when kernel + mode NEON is disabled + +commit 0bc81767c5bd9d005fae1099fb39eb3688370cb1 upstream. + +When the ARM accelerated ChaCha driver is built as part of a configuration +that has kernel mode NEON disabled, we expect the compiler to propagate +the build time constant expression IS_ENABLED(CONFIG_KERNEL_MODE_NEON) in +a way that eliminates all the cross-object references to the actual NEON +routines, which allows the chacha-neon-core.o object to be omitted from +the build entirely. + +Unfortunately, this fails to work as expected in some cases, and we may +end up with a build error such as + + chacha-glue.c:(.text+0xc0): undefined reference to `chacha_4block_xor_neon' + +caused by the fact that chacha_doneon() has not been eliminated from the +object code, even though it will never be called in practice. + +Let's fix this by adding some IS_ENABLED(CONFIG_KERNEL_MODE_NEON) tests +that are not strictly needed from a logical point of view, but should +help the compiler infer that the NEON code paths are unreachable in +those cases. + +Fixes: b36d8c09e710c71f ("crypto: arm/chacha - remove dependency on generic ...") +Reported-by: Russell King +Cc: Arnd Bergmann +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/chacha-glue.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/arch/arm/crypto/chacha-glue.c ++++ b/arch/arm/crypto/chacha-glue.c +@@ -115,7 +115,7 @@ static int chacha_stream_xor(struct skci + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); + +- if (!neon) { ++ 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); +@@ -159,7 +159,7 @@ static int do_xchacha(struct skcipher_re + + chacha_init_generic(state, ctx->key, req->iv); + +- if (!neon) { ++ if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon) { + hchacha_block_arm(state, subctx.key, ctx->nrounds); + } else { + kernel_neon_begin(); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0050-crypto-Kconfig-allow-tests-to-be-disabled-when-manag.patch b/target/linux/generic/backport-5.4/080-wireguard-0050-crypto-Kconfig-allow-tests-to-be-disabled-when-manag.patch new file mode 100644 index 0000000000..88ce1849c6 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0050-crypto-Kconfig-allow-tests-to-be-disabled-when-manag.patch @@ -0,0 +1,40 @@ +From 5e8381a3dc454813605aef01de31985f0f6bf130 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 17 Jan 2020 12:01:36 +0100 +Subject: [PATCH 050/124] crypto: Kconfig - allow tests to be disabled when + manager is disabled + +commit 2343d1529aff8b552589f622c23932035ed7a05d upstream. + +The library code uses CRYPTO_MANAGER_DISABLE_TESTS to conditionalize its +tests, but the library code can also exist without CRYPTO_MANAGER. That +means on minimal configs, the test code winds up being built with no way +to disable it. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/Kconfig | 4 ---- + 1 file changed, 4 deletions(-) + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -136,8 +136,6 @@ config CRYPTO_USER + Userspace configuration for cryptographic instantiations such as + cbc(aes). + +-if CRYPTO_MANAGER2 +- + config CRYPTO_MANAGER_DISABLE_TESTS + bool "Disable run-time self tests" + default y +@@ -155,8 +153,6 @@ config CRYPTO_MANAGER_EXTRA_TESTS + This is intended for developer use only, as these tests take much + longer to run than the normal self tests. + +-endif # if CRYPTO_MANAGER2 +- + config CRYPTO_GF128MUL + tristate + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0051-crypto-chacha20poly1305-prevent-integer-overflow-on-.patch b/target/linux/generic/backport-5.4/080-wireguard-0051-crypto-chacha20poly1305-prevent-integer-overflow-on-.patch new file mode 100644 index 0000000000..300420f6fe --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0051-crypto-chacha20poly1305-prevent-integer-overflow-on-.patch @@ -0,0 +1,40 @@ +From dceaaf068879fc228e85c482f65ebb707587f696 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 6 Feb 2020 12:42:01 +0100 +Subject: [PATCH 051/124] crypto: chacha20poly1305 - prevent integer overflow + on large input + +commit c9cc0517bba9f0213f1e55172feceb99e5512daf upstream. + +This code assigns src_len (size_t) to sl (int), which causes problems +when src_len is very large. Probably nobody in the kernel should be +passing this much data to chacha20poly1305 all in one go anyway, so I +don't think we need to change the algorithm or introduce larger types +or anything. But we should at least error out early in this case and +print a warning so that we get reports if this does happen and can look +into why anybody is possibly passing it that much data or if they're +accidently passing -1 or similar. + +Fixes: d95312a3ccc0 ("crypto: lib/chacha20poly1305 - reimplement crypt_from_sg() routine") +Cc: Ard Biesheuvel +Cc: stable@vger.kernel.org # 5.5+ +Signed-off-by: Jason A. Donenfeld +Acked-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/chacha20poly1305.c | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/lib/crypto/chacha20poly1305.c ++++ b/lib/crypto/chacha20poly1305.c +@@ -235,6 +235,9 @@ bool chacha20poly1305_crypt_sg_inplace(s + __le64 lens[2]; + } b __aligned(16); + ++ if (WARN_ON(src_len > INT_MAX)) ++ return false; ++ + chacha_load_key(b.k, key); + + b.iv[0] = 0; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0052-crypto-x86-curve25519-support-assemblers-with-no-adx.patch b/target/linux/generic/backport-5.4/080-wireguard-0052-crypto-x86-curve25519-support-assemblers-with-no-adx.patch new file mode 100644 index 0000000000..9a380d377c --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0052-crypto-x86-curve25519-support-assemblers-with-no-adx.patch @@ -0,0 +1,84 @@ +From 50af997532492b0f55bd9928743ac1f99dc1cd41 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 1 Mar 2020 22:52:35 +0800 +Subject: [PATCH 052/124] crypto: x86/curve25519 - support assemblers with no + adx support + +commit 1579f1bc3b753d17a44de3457d5c6f4a5b14c752 upstream. + +Some older version of GAS do not support the ADX instructions, similarly +to how they also don't support AVX and such. This commit adds the same +build-time detection mechanisms we use for AVX and others for ADX, and +then makes sure that the curve25519 library dispatcher calls the right +functions. + +Reported-by: Willy Tarreau +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/Makefile | 5 +++-- + arch/x86/crypto/Makefile | 7 ++++++- + include/crypto/curve25519.h | 6 ++++-- + 3 files changed, 13 insertions(+), 5 deletions(-) + +--- a/arch/x86/Makefile ++++ b/arch/x86/Makefile +@@ -197,9 +197,10 @@ avx2_instr :=$(call as-instr,vpbroadcast + avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) + sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) + sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) ++adx_instr := $(call as-instr,adox %r10$(comma)%r10,-DCONFIG_AS_ADX=1) + +-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) +-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) ++KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) ++KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) + + KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) + +--- a/arch/x86/crypto/Makefile ++++ b/arch/x86/crypto/Makefile +@@ -11,6 +11,7 @@ avx2_supported := $(call as-instr,vpgath + avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) + sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) + sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) ++adx_supported := $(call as-instr,adox %r10$(comma)%r10,yes,no) + + obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o + +@@ -39,7 +40,11 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) + + obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o + obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o +-obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o ++ ++# These modules require the assembler to support ADX. ++ifeq ($(adx_supported),yes) ++ obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o ++endif + + # These modules require assembler to support AVX. + ifeq ($(avx_supported),yes) +--- a/include/crypto/curve25519.h ++++ b/include/crypto/curve25519.h +@@ -33,7 +33,8 @@ bool __must_check curve25519(u8 mypublic + const u8 secret[CURVE25519_KEY_SIZE], + const u8 basepoint[CURVE25519_KEY_SIZE]) + { +- if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && ++ (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) + curve25519_arch(mypublic, secret, basepoint); + else + curve25519_generic(mypublic, secret, basepoint); +@@ -49,7 +50,8 @@ __must_check curve25519_generate_public( + CURVE25519_KEY_SIZE))) + return false; + +- if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) ++ if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && ++ (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) + curve25519_base_arch(pub, secret); + else + curve25519_generic(pub, secret, curve25519_base_point); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0053-crypto-arm64-chacha-correctly-walk-through-blocks.patch b/target/linux/generic/backport-5.4/080-wireguard-0053-crypto-arm64-chacha-correctly-walk-through-blocks.patch new file mode 100644 index 0000000000..1c8d2df2e5 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0053-crypto-arm64-chacha-correctly-walk-through-blocks.patch @@ -0,0 +1,68 @@ +From ed61666f3b3fae43e872dc36a2c01794d7119165 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 18 Mar 2020 20:27:32 -0600 +Subject: [PATCH 053/124] crypto: arm64/chacha - correctly walk through blocks + +commit c8cfcb78c65877313cda7bcbace624d3dbd1f3b3 upstream. + +Prior, passing in chunks of 2, 3, or 4, followed by any additional +chunks would result in the chacha state counter getting out of sync, +resulting in incorrect encryption/decryption, which is a pretty nasty +crypto vuln: "why do images look weird on webpages?" WireGuard users +never experienced this prior, because we have always, out of tree, used +a different crypto library, until the recent Frankenzinc addition. This +commit fixes the issue by advancing the pointers and state counter by +the actual size processed. It also fixes up a bug in the (optional, +costly) stride test that prevented it from running on arm64. + +Fixes: b3aad5bad26a ("crypto: arm64/chacha - expose arm64 ChaCha routine as library function") +Reported-and-tested-by: Emil Renner Berthing +Cc: Ard Biesheuvel +Cc: stable@vger.kernel.org # v5.5+ +Signed-off-by: Jason A. Donenfeld +Reviewed-by: Eric Biggers +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm64/crypto/chacha-neon-glue.c | 8 ++++---- + lib/crypto/chacha20poly1305-selftest.c | 11 ++++++++--- + 2 files changed, 12 insertions(+), 7 deletions(-) + +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -55,10 +55,10 @@ static void chacha_doneon(u32 *state, u8 + break; + } + chacha_4block_xor_neon(state, dst, src, nrounds, l); +- bytes -= CHACHA_BLOCK_SIZE * 5; +- src += CHACHA_BLOCK_SIZE * 5; +- dst += CHACHA_BLOCK_SIZE * 5; +- state[12] += 5; ++ bytes -= l; ++ src += l; ++ dst += l; ++ state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE); + } + } + +--- a/lib/crypto/chacha20poly1305-selftest.c ++++ b/lib/crypto/chacha20poly1305-selftest.c +@@ -9028,10 +9028,15 @@ bool __init chacha20poly1305_selftest(vo + && total_len <= 1 << 10; ++total_len) { + for (i = 0; i <= total_len; ++i) { + for (j = i; j <= total_len; ++j) { ++ k = 0; + sg_init_table(sg_src, 3); +- sg_set_buf(&sg_src[0], input, i); +- sg_set_buf(&sg_src[1], input + i, j - i); +- sg_set_buf(&sg_src[2], input + j, total_len - j); ++ if (i) ++ sg_set_buf(&sg_src[k++], input, i); ++ if (j - i) ++ sg_set_buf(&sg_src[k++], input + i, j - i); ++ if (total_len - j) ++ sg_set_buf(&sg_src[k++], input + j, total_len - j); ++ sg_init_marker(sg_src, k); + memset(computed_output, 0, total_len); + memset(input, 0, total_len); + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0054-crypto-x86-curve25519-replace-with-formally-verified.patch b/target/linux/generic/backport-5.4/080-wireguard-0054-crypto-x86-curve25519-replace-with-formally-verified.patch new file mode 100644 index 0000000000..46ee2573dd --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0054-crypto-x86-curve25519-replace-with-formally-verified.patch @@ -0,0 +1,3765 @@ +From a35b4c8928691ab2aa671aa2ca38a02d4e3cc58d Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 20 Jan 2020 18:18:15 +0100 +Subject: [PATCH 054/124] crypto: x86/curve25519 - replace with formally + verified implementation + +commit 07b586fe06625b0b610dc3d3a969c51913d143d4 upstream. + +This comes from INRIA's HACL*/Vale. It implements the same algorithm and +implementation strategy as the code it replaces, only this code has been +formally verified, sans the base point multiplication, which uses code +similar to prior, only it uses the formally verified field arithmetic +alongside reproducable ladder generation steps. This doesn't have a +pure-bmi2 version, which means haswell no longer benefits, but the +increased (doubled) code complexity is not worth it for a single +generation of chips that's already old. + +Performance-wise, this is around 1% slower on older microarchitectures, +and slightly faster on newer microarchitectures, mainly 10nm ones or +backports of 10nm to 14nm. This implementation is "everest" below: + +Xeon E5-2680 v4 (Broadwell) + + armfazh: 133340 cycles per call + everest: 133436 cycles per call + +Xeon Gold 5120 (Sky Lake Server) + + armfazh: 112636 cycles per call + everest: 113906 cycles per call + +Core i5-6300U (Sky Lake Client) + + armfazh: 116810 cycles per call + everest: 117916 cycles per call + +Core i7-7600U (Kaby Lake) + + armfazh: 119523 cycles per call + everest: 119040 cycles per call + +Core i7-8750H (Coffee Lake) + + armfazh: 113914 cycles per call + everest: 113650 cycles per call + +Core i9-9880H (Coffee Lake Refresh) + + armfazh: 112616 cycles per call + everest: 114082 cycles per call + +Core i3-8121U (Cannon Lake) + + armfazh: 113202 cycles per call + everest: 111382 cycles per call + +Core i7-8265U (Whiskey Lake) + + armfazh: 127307 cycles per call + everest: 127697 cycles per call + +Core i7-8550U (Kaby Lake Refresh) + + armfazh: 127522 cycles per call + everest: 127083 cycles per call + +Xeon Platinum 8275CL (Cascade Lake) + + armfazh: 114380 cycles per call + everest: 114656 cycles per call + +Achieving these kind of results with formally verified code is quite +remarkable, especialy considering that performance is favorable for +newer chips. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/curve25519-x86_64.c | 3546 ++++++++++----------------- + 1 file changed, 1292 insertions(+), 2254 deletions(-) + +--- a/arch/x86/crypto/curve25519-x86_64.c ++++ b/arch/x86/crypto/curve25519-x86_64.c +@@ -1,8 +1,7 @@ +-// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause ++// SPDX-License-Identifier: GPL-2.0 OR MIT + /* +- * Copyright (c) 2017 Armando Faz . All Rights Reserved. +- * Copyright (C) 2018-2019 Jason A. Donenfeld . All Rights Reserved. +- * Copyright (C) 2018 Samuel Neves . All Rights Reserved. ++ * Copyright (C) 2020 Jason A. Donenfeld . All Rights Reserved. ++ * Copyright (c) 2016-2020 INRIA, CMU and Microsoft Corporation + */ + + #include +@@ -16,2337 +15,1378 @@ + #include + #include + +-static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2); +-static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_adx); +- +-enum { NUM_WORDS_ELTFP25519 = 4 }; +-typedef __aligned(32) u64 eltfp25519_1w[NUM_WORDS_ELTFP25519]; +-typedef __aligned(32) u64 eltfp25519_1w_buffer[2 * NUM_WORDS_ELTFP25519]; +- +-#define mul_eltfp25519_1w_adx(c, a, b) do { \ +- mul_256x256_integer_adx(m.buffer, a, b); \ +- red_eltfp25519_1w_adx(c, m.buffer); \ +-} while (0) +- +-#define mul_eltfp25519_1w_bmi2(c, a, b) do { \ +- mul_256x256_integer_bmi2(m.buffer, a, b); \ +- red_eltfp25519_1w_bmi2(c, m.buffer); \ +-} while (0) +- +-#define sqr_eltfp25519_1w_adx(a) do { \ +- sqr_256x256_integer_adx(m.buffer, a); \ +- red_eltfp25519_1w_adx(a, m.buffer); \ +-} while (0) +- +-#define sqr_eltfp25519_1w_bmi2(a) do { \ +- sqr_256x256_integer_bmi2(m.buffer, a); \ +- red_eltfp25519_1w_bmi2(a, m.buffer); \ +-} while (0) +- +-#define mul_eltfp25519_2w_adx(c, a, b) do { \ +- mul2_256x256_integer_adx(m.buffer, a, b); \ +- red_eltfp25519_2w_adx(c, m.buffer); \ +-} while (0) +- +-#define mul_eltfp25519_2w_bmi2(c, a, b) do { \ +- mul2_256x256_integer_bmi2(m.buffer, a, b); \ +- red_eltfp25519_2w_bmi2(c, m.buffer); \ +-} while (0) +- +-#define sqr_eltfp25519_2w_adx(a) do { \ +- sqr2_256x256_integer_adx(m.buffer, a); \ +- red_eltfp25519_2w_adx(a, m.buffer); \ +-} while (0) +- +-#define sqr_eltfp25519_2w_bmi2(a) do { \ +- sqr2_256x256_integer_bmi2(m.buffer, a); \ +- red_eltfp25519_2w_bmi2(a, m.buffer); \ +-} while (0) +- +-#define sqrn_eltfp25519_1w_adx(a, times) do { \ +- int ____counter = (times); \ +- while (____counter-- > 0) \ +- sqr_eltfp25519_1w_adx(a); \ +-} while (0) +- +-#define sqrn_eltfp25519_1w_bmi2(a, times) do { \ +- int ____counter = (times); \ +- while (____counter-- > 0) \ +- sqr_eltfp25519_1w_bmi2(a); \ +-} while (0) +- +-#define copy_eltfp25519_1w(C, A) do { \ +- (C)[0] = (A)[0]; \ +- (C)[1] = (A)[1]; \ +- (C)[2] = (A)[2]; \ +- (C)[3] = (A)[3]; \ +-} while (0) +- +-#define setzero_eltfp25519_1w(C) do { \ +- (C)[0] = 0; \ +- (C)[1] = 0; \ +- (C)[2] = 0; \ +- (C)[3] = 0; \ +-} while (0) +- +-__aligned(32) static const u64 table_ladder_8k[252 * NUM_WORDS_ELTFP25519] = { +- /* 1 */ 0xfffffffffffffff3UL, 0xffffffffffffffffUL, +- 0xffffffffffffffffUL, 0x5fffffffffffffffUL, +- /* 2 */ 0x6b8220f416aafe96UL, 0x82ebeb2b4f566a34UL, +- 0xd5a9a5b075a5950fUL, 0x5142b2cf4b2488f4UL, +- /* 3 */ 0x6aaebc750069680cUL, 0x89cf7820a0f99c41UL, +- 0x2a58d9183b56d0f4UL, 0x4b5aca80e36011a4UL, +- /* 4 */ 0x329132348c29745dUL, 0xf4a2e616e1642fd7UL, +- 0x1e45bb03ff67bc34UL, 0x306912d0f42a9b4aUL, +- /* 5 */ 0xff886507e6af7154UL, 0x04f50e13dfeec82fUL, +- 0xaa512fe82abab5ceUL, 0x174e251a68d5f222UL, +- /* 6 */ 0xcf96700d82028898UL, 0x1743e3370a2c02c5UL, +- 0x379eec98b4e86eaaUL, 0x0c59888a51e0482eUL, +- /* 7 */ 0xfbcbf1d699b5d189UL, 0xacaef0d58e9fdc84UL, +- 0xc1c20d06231f7614UL, 0x2938218da274f972UL, +- /* 8 */ 0xf6af49beff1d7f18UL, 0xcc541c22387ac9c2UL, +- 0x96fcc9ef4015c56bUL, 0x69c1627c690913a9UL, +- /* 9 */ 0x7a86fd2f4733db0eUL, 0xfdb8c4f29e087de9UL, +- 0x095e4b1a8ea2a229UL, 0x1ad7a7c829b37a79UL, +- /* 10 */ 0x342d89cad17ea0c0UL, 0x67bedda6cced2051UL, +- 0x19ca31bf2bb42f74UL, 0x3df7b4c84980acbbUL, +- /* 11 */ 0xa8c6444dc80ad883UL, 0xb91e440366e3ab85UL, +- 0xc215cda00164f6d8UL, 0x3d867c6ef247e668UL, +- /* 12 */ 0xc7dd582bcc3e658cUL, 0xfd2c4748ee0e5528UL, +- 0xa0fd9b95cc9f4f71UL, 0x7529d871b0675ddfUL, +- /* 13 */ 0xb8f568b42d3cbd78UL, 0x1233011b91f3da82UL, +- 0x2dce6ccd4a7c3b62UL, 0x75e7fc8e9e498603UL, +- /* 14 */ 0x2f4f13f1fcd0b6ecUL, 0xf1a8ca1f29ff7a45UL, +- 0xc249c1a72981e29bUL, 0x6ebe0dbb8c83b56aUL, +- /* 15 */ 0x7114fa8d170bb222UL, 0x65a2dcd5bf93935fUL, +- 0xbdc41f68b59c979aUL, 0x2f0eef79a2ce9289UL, +- /* 16 */ 0x42ecbf0c083c37ceUL, 0x2930bc09ec496322UL, +- 0xf294b0c19cfeac0dUL, 0x3780aa4bedfabb80UL, +- /* 17 */ 0x56c17d3e7cead929UL, 0xe7cb4beb2e5722c5UL, +- 0x0ce931732dbfe15aUL, 0x41b883c7621052f8UL, +- /* 18 */ 0xdbf75ca0c3d25350UL, 0x2936be086eb1e351UL, +- 0xc936e03cb4a9b212UL, 0x1d45bf82322225aaUL, +- /* 19 */ 0xe81ab1036a024cc5UL, 0xe212201c304c9a72UL, +- 0xc5d73fba6832b1fcUL, 0x20ffdb5a4d839581UL, +- /* 20 */ 0xa283d367be5d0fadUL, 0x6c2b25ca8b164475UL, +- 0x9d4935467caaf22eUL, 0x5166408eee85ff49UL, +- /* 21 */ 0x3c67baa2fab4e361UL, 0xb3e433c67ef35cefUL, +- 0x5259729241159b1cUL, 0x6a621892d5b0ab33UL, +- /* 22 */ 0x20b74a387555cdcbUL, 0x532aa10e1208923fUL, +- 0xeaa17b7762281dd1UL, 0x61ab3443f05c44bfUL, +- /* 23 */ 0x257a6c422324def8UL, 0x131c6c1017e3cf7fUL, +- 0x23758739f630a257UL, 0x295a407a01a78580UL, +- /* 24 */ 0xf8c443246d5da8d9UL, 0x19d775450c52fa5dUL, +- 0x2afcfc92731bf83dUL, 0x7d10c8e81b2b4700UL, +- /* 25 */ 0xc8e0271f70baa20bUL, 0x993748867ca63957UL, +- 0x5412efb3cb7ed4bbUL, 0x3196d36173e62975UL, +- /* 26 */ 0xde5bcad141c7dffcUL, 0x47cc8cd2b395c848UL, +- 0xa34cd942e11af3cbUL, 0x0256dbf2d04ecec2UL, +- /* 27 */ 0x875ab7e94b0e667fUL, 0xcad4dd83c0850d10UL, +- 0x47f12e8f4e72c79fUL, 0x5f1a87bb8c85b19bUL, +- /* 28 */ 0x7ae9d0b6437f51b8UL, 0x12c7ce5518879065UL, +- 0x2ade09fe5cf77aeeUL, 0x23a05a2f7d2c5627UL, +- /* 29 */ 0x5908e128f17c169aUL, 0xf77498dd8ad0852dUL, +- 0x74b4c4ceab102f64UL, 0x183abadd10139845UL, +- /* 30 */ 0xb165ba8daa92aaacUL, 0xd5c5ef9599386705UL, +- 0xbe2f8f0cf8fc40d1UL, 0x2701e635ee204514UL, +- /* 31 */ 0x629fa80020156514UL, 0xf223868764a8c1ceUL, +- 0x5b894fff0b3f060eUL, 0x60d9944cf708a3faUL, +- /* 32 */ 0xaeea001a1c7a201fUL, 0xebf16a633ee2ce63UL, +- 0x6f7709594c7a07e1UL, 0x79b958150d0208cbUL, +- /* 33 */ 0x24b55e5301d410e7UL, 0xe3a34edff3fdc84dUL, +- 0xd88768e4904032d8UL, 0x131384427b3aaeecUL, +- /* 34 */ 0x8405e51286234f14UL, 0x14dc4739adb4c529UL, +- 0xb8a2b5b250634ffdUL, 0x2fe2a94ad8a7ff93UL, +- /* 35 */ 0xec5c57efe843faddUL, 0x2843ce40f0bb9918UL, +- 0xa4b561d6cf3d6305UL, 0x743629bde8fb777eUL, +- /* 36 */ 0x343edd46bbaf738fUL, 0xed981828b101a651UL, +- 0xa401760b882c797aUL, 0x1fc223e28dc88730UL, +- /* 37 */ 0x48604e91fc0fba0eUL, 0xb637f78f052c6fa4UL, +- 0x91ccac3d09e9239cUL, 0x23f7eed4437a687cUL, +- /* 38 */ 0x5173b1118d9bd800UL, 0x29d641b63189d4a7UL, +- 0xfdbf177988bbc586UL, 0x2959894fcad81df5UL, +- /* 39 */ 0xaebc8ef3b4bbc899UL, 0x4148995ab26992b9UL, +- 0x24e20b0134f92cfbUL, 0x40d158894a05dee8UL, +- /* 40 */ 0x46b00b1185af76f6UL, 0x26bac77873187a79UL, +- 0x3dc0bf95ab8fff5fUL, 0x2a608bd8945524d7UL, +- /* 41 */ 0x26449588bd446302UL, 0x7c4bc21c0388439cUL, +- 0x8e98a4f383bd11b2UL, 0x26218d7bc9d876b9UL, +- /* 42 */ 0xe3081542997c178aUL, 0x3c2d29a86fb6606fUL, +- 0x5c217736fa279374UL, 0x7dde05734afeb1faUL, +- /* 43 */ 0x3bf10e3906d42babUL, 0xe4f7803e1980649cUL, +- 0xe6053bf89595bf7aUL, 0x394faf38da245530UL, +- /* 44 */ 0x7a8efb58896928f4UL, 0xfbc778e9cc6a113cUL, +- 0x72670ce330af596fUL, 0x48f222a81d3d6cf7UL, +- /* 45 */ 0xf01fce410d72caa7UL, 0x5a20ecc7213b5595UL, +- 0x7bc21165c1fa1483UL, 0x07f89ae31da8a741UL, +- /* 46 */ 0x05d2c2b4c6830ff9UL, 0xd43e330fc6316293UL, +- 0xa5a5590a96d3a904UL, 0x705edb91a65333b6UL, +- /* 47 */ 0x048ee15e0bb9a5f7UL, 0x3240cfca9e0aaf5dUL, +- 0x8f4b71ceedc4a40bUL, 0x621c0da3de544a6dUL, +- /* 48 */ 0x92872836a08c4091UL, 0xce8375b010c91445UL, +- 0x8a72eb524f276394UL, 0x2667fcfa7ec83635UL, +- /* 49 */ 0x7f4c173345e8752aUL, 0x061b47feee7079a5UL, +- 0x25dd9afa9f86ff34UL, 0x3780cef5425dc89cUL, +- /* 50 */ 0x1a46035a513bb4e9UL, 0x3e1ef379ac575adaUL, +- 0xc78c5f1c5fa24b50UL, 0x321a967634fd9f22UL, +- /* 51 */ 0x946707b8826e27faUL, 0x3dca84d64c506fd0UL, +- 0xc189218075e91436UL, 0x6d9284169b3b8484UL, +- /* 52 */ 0x3a67e840383f2ddfUL, 0x33eec9a30c4f9b75UL, +- 0x3ec7c86fa783ef47UL, 0x26ec449fbac9fbc4UL, +- /* 53 */ 0x5c0f38cba09b9e7dUL, 0x81168cc762a3478cUL, +- 0x3e23b0d306fc121cUL, 0x5a238aa0a5efdcddUL, +- /* 54 */ 0x1ba26121c4ea43ffUL, 0x36f8c77f7c8832b5UL, +- 0x88fbea0b0adcf99aUL, 0x5ca9938ec25bebf9UL, +- /* 55 */ 0xd5436a5e51fccda0UL, 0x1dbc4797c2cd893bUL, +- 0x19346a65d3224a08UL, 0x0f5034e49b9af466UL, +- /* 56 */ 0xf23c3967a1e0b96eUL, 0xe58b08fa867a4d88UL, +- 0xfb2fabc6a7341679UL, 0x2a75381eb6026946UL, +- /* 57 */ 0xc80a3be4c19420acUL, 0x66b1f6c681f2b6dcUL, +- 0x7cf7036761e93388UL, 0x25abbbd8a660a4c4UL, +- /* 58 */ 0x91ea12ba14fd5198UL, 0x684950fc4a3cffa9UL, +- 0xf826842130f5ad28UL, 0x3ea988f75301a441UL, +- /* 59 */ 0xc978109a695f8c6fUL, 0x1746eb4a0530c3f3UL, +- 0x444d6d77b4459995UL, 0x75952b8c054e5cc7UL, +- /* 60 */ 0xa3703f7915f4d6aaUL, 0x66c346202f2647d8UL, +- 0xd01469df811d644bUL, 0x77fea47d81a5d71fUL, +- /* 61 */ 0xc5e9529ef57ca381UL, 0x6eeeb4b9ce2f881aUL, +- 0xb6e91a28e8009bd6UL, 0x4b80be3e9afc3fecUL, +- /* 62 */ 0x7e3773c526aed2c5UL, 0x1b4afcb453c9a49dUL, +- 0xa920bdd7baffb24dUL, 0x7c54699f122d400eUL, +- /* 63 */ 0xef46c8e14fa94bc8UL, 0xe0b074ce2952ed5eUL, +- 0xbea450e1dbd885d5UL, 0x61b68649320f712cUL, +- /* 64 */ 0x8a485f7309ccbdd1UL, 0xbd06320d7d4d1a2dUL, +- 0x25232973322dbef4UL, 0x445dc4758c17f770UL, +- /* 65 */ 0xdb0434177cc8933cUL, 0xed6fe82175ea059fUL, +- 0x1efebefdc053db34UL, 0x4adbe867c65daf99UL, +- /* 66 */ 0x3acd71a2a90609dfUL, 0xe5e991856dd04050UL, +- 0x1ec69b688157c23cUL, 0x697427f6885cfe4dUL, +- /* 67 */ 0xd7be7b9b65e1a851UL, 0xa03d28d522c536ddUL, +- 0x28399d658fd2b645UL, 0x49e5b7e17c2641e1UL, +- /* 68 */ 0x6f8c3a98700457a4UL, 0x5078f0a25ebb6778UL, +- 0xd13c3ccbc382960fUL, 0x2e003258a7df84b1UL, +- /* 69 */ 0x8ad1f39be6296a1cUL, 0xc1eeaa652a5fbfb2UL, +- 0x33ee0673fd26f3cbUL, 0x59256173a69d2cccUL, +- /* 70 */ 0x41ea07aa4e18fc41UL, 0xd9fc19527c87a51eUL, +- 0xbdaacb805831ca6fUL, 0x445b652dc916694fUL, +- /* 71 */ 0xce92a3a7f2172315UL, 0x1edc282de11b9964UL, +- 0xa1823aafe04c314aUL, 0x790a2d94437cf586UL, +- /* 72 */ 0x71c447fb93f6e009UL, 0x8922a56722845276UL, +- 0xbf70903b204f5169UL, 0x2f7a89891ba319feUL, +- /* 73 */ 0x02a08eb577e2140cUL, 0xed9a4ed4427bdcf4UL, +- 0x5253ec44e4323cd1UL, 0x3e88363c14e9355bUL, +- /* 74 */ 0xaa66c14277110b8cUL, 0x1ae0391610a23390UL, +- 0x2030bd12c93fc2a2UL, 0x3ee141579555c7abUL, +- /* 75 */ 0x9214de3a6d6e7d41UL, 0x3ccdd88607f17efeUL, +- 0x674f1288f8e11217UL, 0x5682250f329f93d0UL, +- /* 76 */ 0x6cf00b136d2e396eUL, 0x6e4cf86f1014debfUL, +- 0x5930b1b5bfcc4e83UL, 0x047069b48aba16b6UL, +- /* 77 */ 0x0d4ce4ab69b20793UL, 0xb24db91a97d0fb9eUL, +- 0xcdfa50f54e00d01dUL, 0x221b1085368bddb5UL, +- /* 78 */ 0xe7e59468b1e3d8d2UL, 0x53c56563bd122f93UL, +- 0xeee8a903e0663f09UL, 0x61efa662cbbe3d42UL, +- /* 79 */ 0x2cf8ddddde6eab2aUL, 0x9bf80ad51435f231UL, +- 0x5deadacec9f04973UL, 0x29275b5d41d29b27UL, +- /* 80 */ 0xcfde0f0895ebf14fUL, 0xb9aab96b054905a7UL, +- 0xcae80dd9a1c420fdUL, 0x0a63bf2f1673bbc7UL, +- /* 81 */ 0x092f6e11958fbc8cUL, 0x672a81e804822fadUL, +- 0xcac8351560d52517UL, 0x6f3f7722c8f192f8UL, +- /* 82 */ 0xf8ba90ccc2e894b7UL, 0x2c7557a438ff9f0dUL, +- 0x894d1d855ae52359UL, 0x68e122157b743d69UL, +- /* 83 */ 0xd87e5570cfb919f3UL, 0x3f2cdecd95798db9UL, +- 0x2121154710c0a2ceUL, 0x3c66a115246dc5b2UL, +- /* 84 */ 0xcbedc562294ecb72UL, 0xba7143c36a280b16UL, +- 0x9610c2efd4078b67UL, 0x6144735d946a4b1eUL, +- /* 85 */ 0x536f111ed75b3350UL, 0x0211db8c2041d81bUL, +- 0xf93cb1000e10413cUL, 0x149dfd3c039e8876UL, +- /* 86 */ 0xd479dde46b63155bUL, 0xb66e15e93c837976UL, +- 0xdafde43b1f13e038UL, 0x5fafda1a2e4b0b35UL, +- /* 87 */ 0x3600bbdf17197581UL, 0x3972050bbe3cd2c2UL, +- 0x5938906dbdd5be86UL, 0x34fce5e43f9b860fUL, +- /* 88 */ 0x75a8a4cd42d14d02UL, 0x828dabc53441df65UL, +- 0x33dcabedd2e131d3UL, 0x3ebad76fb814d25fUL, +- /* 89 */ 0xd4906f566f70e10fUL, 0x5d12f7aa51690f5aUL, +- 0x45adb16e76cefcf2UL, 0x01f768aead232999UL, +- /* 90 */ 0x2b6cc77b6248febdUL, 0x3cd30628ec3aaffdUL, +- 0xce1c0b80d4ef486aUL, 0x4c3bff2ea6f66c23UL, +- /* 91 */ 0x3f2ec4094aeaeb5fUL, 0x61b19b286e372ca7UL, +- 0x5eefa966de2a701dUL, 0x23b20565de55e3efUL, +- /* 92 */ 0xe301ca5279d58557UL, 0x07b2d4ce27c2874fUL, +- 0xa532cd8a9dcf1d67UL, 0x2a52fee23f2bff56UL, +- /* 93 */ 0x8624efb37cd8663dUL, 0xbbc7ac20ffbd7594UL, +- 0x57b85e9c82d37445UL, 0x7b3052cb86a6ec66UL, +- /* 94 */ 0x3482f0ad2525e91eUL, 0x2cb68043d28edca0UL, +- 0xaf4f6d052e1b003aUL, 0x185f8c2529781b0aUL, +- /* 95 */ 0xaa41de5bd80ce0d6UL, 0x9407b2416853e9d6UL, +- 0x563ec36e357f4c3aUL, 0x4cc4b8dd0e297bceUL, +- /* 96 */ 0xa2fc1a52ffb8730eUL, 0x1811f16e67058e37UL, +- 0x10f9a366cddf4ee1UL, 0x72f4a0c4a0b9f099UL, +- /* 97 */ 0x8c16c06f663f4ea7UL, 0x693b3af74e970fbaUL, +- 0x2102e7f1d69ec345UL, 0x0ba53cbc968a8089UL, +- /* 98 */ 0xca3d9dc7fea15537UL, 0x4c6824bb51536493UL, +- 0xb9886314844006b1UL, 0x40d2a72ab454cc60UL, +- /* 99 */ 0x5936a1b712570975UL, 0x91b9d648debda657UL, +- 0x3344094bb64330eaUL, 0x006ba10d12ee51d0UL, +- /* 100 */ 0x19228468f5de5d58UL, 0x0eb12f4c38cc05b0UL, +- 0xa1039f9dd5601990UL, 0x4502d4ce4fff0e0bUL, +- /* 101 */ 0xeb2054106837c189UL, 0xd0f6544c6dd3b93cUL, +- 0x40727064c416d74fUL, 0x6e15c6114b502ef0UL, +- /* 102 */ 0x4df2a398cfb1a76bUL, 0x11256c7419f2f6b1UL, +- 0x4a497962066e6043UL, 0x705b3aab41355b44UL, +- /* 103 */ 0x365ef536d797b1d8UL, 0x00076bd622ddf0dbUL, +- 0x3bbf33b0e0575a88UL, 0x3777aa05c8e4ca4dUL, +- /* 104 */ 0x392745c85578db5fUL, 0x6fda4149dbae5ae2UL, +- 0xb1f0b00b8adc9867UL, 0x09963437d36f1da3UL, +- /* 105 */ 0x7e824e90a5dc3853UL, 0xccb5f6641f135cbdUL, +- 0x6736d86c87ce8fccUL, 0x625f3ce26604249fUL, +- /* 106 */ 0xaf8ac8059502f63fUL, 0x0c05e70a2e351469UL, +- 0x35292e9c764b6305UL, 0x1a394360c7e23ac3UL, +- /* 107 */ 0xd5c6d53251183264UL, 0x62065abd43c2b74fUL, +- 0xb5fbf5d03b973f9bUL, 0x13a3da3661206e5eUL, +- /* 108 */ 0xc6bd5837725d94e5UL, 0x18e30912205016c5UL, +- 0x2088ce1570033c68UL, 0x7fba1f495c837987UL, +- /* 109 */ 0x5a8c7423f2f9079dUL, 0x1735157b34023fc5UL, +- 0xe4f9b49ad2fab351UL, 0x6691ff72c878e33cUL, +- /* 110 */ 0x122c2adedc5eff3eUL, 0xf8dd4bf1d8956cf4UL, +- 0xeb86205d9e9e5bdaUL, 0x049b92b9d975c743UL, +- /* 111 */ 0xa5379730b0f6c05aUL, 0x72a0ffacc6f3a553UL, +- 0xb0032c34b20dcd6dUL, 0x470e9dbc88d5164aUL, +- /* 112 */ 0xb19cf10ca237c047UL, 0xb65466711f6c81a2UL, +- 0xb3321bd16dd80b43UL, 0x48c14f600c5fbe8eUL, +- /* 113 */ 0x66451c264aa6c803UL, 0xb66e3904a4fa7da6UL, +- 0xd45f19b0b3128395UL, 0x31602627c3c9bc10UL, +- /* 114 */ 0x3120dc4832e4e10dUL, 0xeb20c46756c717f7UL, +- 0x00f52e3f67280294UL, 0x566d4fc14730c509UL, +- /* 115 */ 0x7e3a5d40fd837206UL, 0xc1e926dc7159547aUL, +- 0x216730fba68d6095UL, 0x22e8c3843f69cea7UL, +- /* 116 */ 0x33d074e8930e4b2bUL, 0xb6e4350e84d15816UL, +- 0x5534c26ad6ba2365UL, 0x7773c12f89f1f3f3UL, +- /* 117 */ 0x8cba404da57962aaUL, 0x5b9897a81999ce56UL, +- 0x508e862f121692fcUL, 0x3a81907fa093c291UL, +- /* 118 */ 0x0dded0ff4725a510UL, 0x10d8cc10673fc503UL, +- 0x5b9d151c9f1f4e89UL, 0x32a5c1d5cb09a44cUL, +- /* 119 */ 0x1e0aa442b90541fbUL, 0x5f85eb7cc1b485dbUL, +- 0xbee595ce8a9df2e5UL, 0x25e496c722422236UL, +- /* 120 */ 0x5edf3c46cd0fe5b9UL, 0x34e75a7ed2a43388UL, +- 0xe488de11d761e352UL, 0x0e878a01a085545cUL, +- /* 121 */ 0xba493c77e021bb04UL, 0x2b4d1843c7df899aUL, +- 0x9ea37a487ae80d67UL, 0x67a9958011e41794UL, +- /* 122 */ 0x4b58051a6697b065UL, 0x47e33f7d8d6ba6d4UL, +- 0xbb4da8d483ca46c1UL, 0x68becaa181c2db0dUL, +- /* 123 */ 0x8d8980e90b989aa5UL, 0xf95eb14a2c93c99bUL, +- 0x51c6c7c4796e73a2UL, 0x6e228363b5efb569UL, +- /* 124 */ 0xc6bbc0b02dd624c8UL, 0x777eb47dec8170eeUL, +- 0x3cde15a004cfafa9UL, 0x1dc6bc087160bf9bUL, +- /* 125 */ 0x2e07e043eec34002UL, 0x18e9fc677a68dc7fUL, +- 0xd8da03188bd15b9aUL, 0x48fbc3bb00568253UL, +- /* 126 */ 0x57547d4cfb654ce1UL, 0xd3565b82a058e2adUL, +- 0xf63eaf0bbf154478UL, 0x47531ef114dfbb18UL, +- /* 127 */ 0xe1ec630a4278c587UL, 0x5507d546ca8e83f3UL, +- 0x85e135c63adc0c2bUL, 0x0aa7efa85682844eUL, +- /* 128 */ 0x72691ba8b3e1f615UL, 0x32b4e9701fbe3ffaUL, +- 0x97b6d92e39bb7868UL, 0x2cfe53dea02e39e8UL, +- /* 129 */ 0x687392cd85cd52b0UL, 0x27ff66c910e29831UL, +- 0x97134556a9832d06UL, 0x269bb0360a84f8a0UL, +- /* 130 */ 0x706e55457643f85cUL, 0x3734a48c9b597d1bUL, +- 0x7aee91e8c6efa472UL, 0x5cd6abc198a9d9e0UL, +- /* 131 */ 0x0e04de06cb3ce41aUL, 0xd8c6eb893402e138UL, +- 0x904659bb686e3772UL, 0x7215c371746ba8c8UL, +- /* 132 */ 0xfd12a97eeae4a2d9UL, 0x9514b7516394f2c5UL, +- 0x266fd5809208f294UL, 0x5c847085619a26b9UL, +- /* 133 */ 0x52985410fed694eaUL, 0x3c905b934a2ed254UL, +- 0x10bb47692d3be467UL, 0x063b3d2d69e5e9e1UL, +- /* 134 */ 0x472726eedda57debUL, 0xefb6c4ae10f41891UL, +- 0x2b1641917b307614UL, 0x117c554fc4f45b7cUL, +- /* 135 */ 0xc07cf3118f9d8812UL, 0x01dbd82050017939UL, +- 0xd7e803f4171b2827UL, 0x1015e87487d225eaUL, +- /* 136 */ 0xc58de3fed23acc4dUL, 0x50db91c294a7be2dUL, +- 0x0b94d43d1c9cf457UL, 0x6b1640fa6e37524aUL, +- /* 137 */ 0x692f346c5fda0d09UL, 0x200b1c59fa4d3151UL, +- 0xb8c46f760777a296UL, 0x4b38395f3ffdfbcfUL, +- /* 138 */ 0x18d25e00be54d671UL, 0x60d50582bec8aba6UL, +- 0x87ad8f263b78b982UL, 0x50fdf64e9cda0432UL, +- /* 139 */ 0x90f567aac578dcf0UL, 0xef1e9b0ef2a3133bUL, +- 0x0eebba9242d9de71UL, 0x15473c9bf03101c7UL, +- /* 140 */ 0x7c77e8ae56b78095UL, 0xb678e7666e6f078eUL, +- 0x2da0b9615348ba1fUL, 0x7cf931c1ff733f0bUL, +- /* 141 */ 0x26b357f50a0a366cUL, 0xe9708cf42b87d732UL, +- 0xc13aeea5f91cb2c0UL, 0x35d90c991143bb4cUL, +- /* 142 */ 0x47c1c404a9a0d9dcUL, 0x659e58451972d251UL, +- 0x3875a8c473b38c31UL, 0x1fbd9ed379561f24UL, +- /* 143 */ 0x11fabc6fd41ec28dUL, 0x7ef8dfe3cd2a2dcaUL, +- 0x72e73b5d8c404595UL, 0x6135fa4954b72f27UL, +- /* 144 */ 0xccfc32a2de24b69cUL, 0x3f55698c1f095d88UL, +- 0xbe3350ed5ac3f929UL, 0x5e9bf806ca477eebUL, +- /* 145 */ 0xe9ce8fb63c309f68UL, 0x5376f63565e1f9f4UL, +- 0xd1afcfb35a6393f1UL, 0x6632a1ede5623506UL, +- /* 146 */ 0x0b7d6c390c2ded4cUL, 0x56cb3281df04cb1fUL, +- 0x66305a1249ecc3c7UL, 0x5d588b60a38ca72aUL, +- /* 147 */ 0xa6ecbf78e8e5f42dUL, 0x86eeb44b3c8a3eecUL, +- 0xec219c48fbd21604UL, 0x1aaf1af517c36731UL, +- /* 148 */ 0xc306a2836769bde7UL, 0x208280622b1e2adbUL, +- 0x8027f51ffbff94a6UL, 0x76cfa1ce1124f26bUL, +- /* 149 */ 0x18eb00562422abb6UL, 0xf377c4d58f8c29c3UL, +- 0x4dbbc207f531561aUL, 0x0253b7f082128a27UL, +- /* 150 */ 0x3d1f091cb62c17e0UL, 0x4860e1abd64628a9UL, +- 0x52d17436309d4253UL, 0x356f97e13efae576UL, +- /* 151 */ 0xd351e11aa150535bUL, 0x3e6b45bb1dd878ccUL, +- 0x0c776128bed92c98UL, 0x1d34ae93032885b8UL, +- /* 152 */ 0x4ba0488ca85ba4c3UL, 0x985348c33c9ce6ceUL, +- 0x66124c6f97bda770UL, 0x0f81a0290654124aUL, +- /* 153 */ 0x9ed09ca6569b86fdUL, 0x811009fd18af9a2dUL, +- 0xff08d03f93d8c20aUL, 0x52a148199faef26bUL, +- /* 154 */ 0x3e03f9dc2d8d1b73UL, 0x4205801873961a70UL, +- 0xc0d987f041a35970UL, 0x07aa1f15a1c0d549UL, +- /* 155 */ 0xdfd46ce08cd27224UL, 0x6d0a024f934e4239UL, +- 0x808a7a6399897b59UL, 0x0a4556e9e13d95a2UL, +- /* 156 */ 0xd21a991fe9c13045UL, 0x9b0e8548fe7751b8UL, +- 0x5da643cb4bf30035UL, 0x77db28d63940f721UL, +- /* 157 */ 0xfc5eeb614adc9011UL, 0x5229419ae8c411ebUL, +- 0x9ec3e7787d1dcf74UL, 0x340d053e216e4cb5UL, +- /* 158 */ 0xcac7af39b48df2b4UL, 0xc0faec2871a10a94UL, +- 0x140a69245ca575edUL, 0x0cf1c37134273a4cUL, +- /* 159 */ 0xc8ee306ac224b8a5UL, 0x57eaee7ccb4930b0UL, +- 0xa1e806bdaacbe74fUL, 0x7d9a62742eeb657dUL, +- /* 160 */ 0x9eb6b6ef546c4830UL, 0x885cca1fddb36e2eUL, +- 0xe6b9f383ef0d7105UL, 0x58654fef9d2e0412UL, +- /* 161 */ 0xa905c4ffbe0e8e26UL, 0x942de5df9b31816eUL, +- 0x497d723f802e88e1UL, 0x30684dea602f408dUL, +- /* 162 */ 0x21e5a278a3e6cb34UL, 0xaefb6e6f5b151dc4UL, +- 0xb30b8e049d77ca15UL, 0x28c3c9cf53b98981UL, +- /* 163 */ 0x287fb721556cdd2aUL, 0x0d317ca897022274UL, +- 0x7468c7423a543258UL, 0x4a7f11464eb5642fUL, +- /* 164 */ 0xa237a4774d193aa6UL, 0xd865986ea92129a1UL, +- 0x24c515ecf87c1a88UL, 0x604003575f39f5ebUL, +- /* 165 */ 0x47b9f189570a9b27UL, 0x2b98cede465e4b78UL, +- 0x026df551dbb85c20UL, 0x74fcd91047e21901UL, +- /* 166 */ 0x13e2a90a23c1bfa3UL, 0x0cb0074e478519f6UL, +- 0x5ff1cbbe3af6cf44UL, 0x67fe5438be812dbeUL, +- /* 167 */ 0xd13cf64fa40f05b0UL, 0x054dfb2f32283787UL, +- 0x4173915b7f0d2aeaUL, 0x482f144f1f610d4eUL, +- /* 168 */ 0xf6210201b47f8234UL, 0x5d0ae1929e70b990UL, +- 0xdcd7f455b049567cUL, 0x7e93d0f1f0916f01UL, +- /* 169 */ 0xdd79cbf18a7db4faUL, 0xbe8391bf6f74c62fUL, +- 0x027145d14b8291bdUL, 0x585a73ea2cbf1705UL, +- /* 170 */ 0x485ca03e928a0db2UL, 0x10fc01a5742857e7UL, +- 0x2f482edbd6d551a7UL, 0x0f0433b5048fdb8aUL, +- /* 171 */ 0x60da2e8dd7dc6247UL, 0x88b4c9d38cd4819aUL, +- 0x13033ac001f66697UL, 0x273b24fe3b367d75UL, +- /* 172 */ 0xc6e8f66a31b3b9d4UL, 0x281514a494df49d5UL, +- 0xd1726fdfc8b23da7UL, 0x4b3ae7d103dee548UL, +- /* 173 */ 0xc6256e19ce4b9d7eUL, 0xff5c5cf186e3c61cUL, +- 0xacc63ca34b8ec145UL, 0x74621888fee66574UL, +- /* 174 */ 0x956f409645290a1eUL, 0xef0bf8e3263a962eUL, +- 0xed6a50eb5ec2647bUL, 0x0694283a9dca7502UL, +- /* 175 */ 0x769b963643a2dcd1UL, 0x42b7c8ea09fc5353UL, +- 0x4f002aee13397eabUL, 0x63005e2c19b7d63aUL, +- /* 176 */ 0xca6736da63023beaUL, 0x966c7f6db12a99b7UL, +- 0xace09390c537c5e1UL, 0x0b696063a1aa89eeUL, +- /* 177 */ 0xebb03e97288c56e5UL, 0x432a9f9f938c8be8UL, +- 0xa6a5a93d5b717f71UL, 0x1a5fb4c3e18f9d97UL, +- /* 178 */ 0x1c94e7ad1c60cdceUL, 0xee202a43fc02c4a0UL, +- 0x8dafe4d867c46a20UL, 0x0a10263c8ac27b58UL, +- /* 179 */ 0xd0dea9dfe4432a4aUL, 0x856af87bbe9277c5UL, +- 0xce8472acc212c71aUL, 0x6f151b6d9bbb1e91UL, +- /* 180 */ 0x26776c527ceed56aUL, 0x7d211cb7fbf8faecUL, +- 0x37ae66a6fd4609ccUL, 0x1f81b702d2770c42UL, +- /* 181 */ 0x2fb0b057eac58392UL, 0xe1dd89fe29744e9dUL, +- 0xc964f8eb17beb4f8UL, 0x29571073c9a2d41eUL, +- /* 182 */ 0xa948a18981c0e254UL, 0x2df6369b65b22830UL, +- 0xa33eb2d75fcfd3c6UL, 0x078cd6ec4199a01fUL, +- /* 183 */ 0x4a584a41ad900d2fUL, 0x32142b78e2c74c52UL, +- 0x68c4e8338431c978UL, 0x7f69ea9008689fc2UL, +- /* 184 */ 0x52f2c81e46a38265UL, 0xfd78072d04a832fdUL, +- 0x8cd7d5fa25359e94UL, 0x4de71b7454cc29d2UL, +- /* 185 */ 0x42eb60ad1eda6ac9UL, 0x0aad37dfdbc09c3aUL, +- 0x81004b71e33cc191UL, 0x44e6be345122803cUL, +- /* 186 */ 0x03fe8388ba1920dbUL, 0xf5d57c32150db008UL, +- 0x49c8c4281af60c29UL, 0x21edb518de701aeeUL, +- /* 187 */ 0x7fb63e418f06dc99UL, 0xa4460d99c166d7b8UL, +- 0x24dd5248ce520a83UL, 0x5ec3ad712b928358UL, +- /* 188 */ 0x15022a5fbd17930fUL, 0xa4f64a77d82570e3UL, +- 0x12bc8d6915783712UL, 0x498194c0fc620abbUL, +- /* 189 */ 0x38a2d9d255686c82UL, 0x785c6bd9193e21f0UL, +- 0xe4d5c81ab24a5484UL, 0x56307860b2e20989UL, +- /* 190 */ 0x429d55f78b4d74c4UL, 0x22f1834643350131UL, +- 0x1e60c24598c71fffUL, 0x59f2f014979983efUL, +- /* 191 */ 0x46a47d56eb494a44UL, 0x3e22a854d636a18eUL, +- 0xb346e15274491c3bUL, 0x2ceafd4e5390cde7UL, +- /* 192 */ 0xba8a8538be0d6675UL, 0x4b9074bb50818e23UL, +- 0xcbdab89085d304c3UL, 0x61a24fe0e56192c4UL, +- /* 193 */ 0xcb7615e6db525bcbUL, 0xdd7d8c35a567e4caUL, +- 0xe6b4153acafcdd69UL, 0x2d668e097f3c9766UL, +- /* 194 */ 0xa57e7e265ce55ef0UL, 0x5d9f4e527cd4b967UL, +- 0xfbc83606492fd1e5UL, 0x090d52beb7c3f7aeUL, +- /* 195 */ 0x09b9515a1e7b4d7cUL, 0x1f266a2599da44c0UL, +- 0xa1c49548e2c55504UL, 0x7ef04287126f15ccUL, +- /* 196 */ 0xfed1659dbd30ef15UL, 0x8b4ab9eec4e0277bUL, +- 0x884d6236a5df3291UL, 0x1fd96ea6bf5cf788UL, +- /* 197 */ 0x42a161981f190d9aUL, 0x61d849507e6052c1UL, +- 0x9fe113bf285a2cd5UL, 0x7c22d676dbad85d8UL, +- /* 198 */ 0x82e770ed2bfbd27dUL, 0x4c05b2ece996f5a5UL, +- 0xcd40a9c2b0900150UL, 0x5895319213d9bf64UL, +- /* 199 */ 0xe7cc5d703fea2e08UL, 0xb50c491258e2188cUL, +- 0xcce30baa48205bf0UL, 0x537c659ccfa32d62UL, +- /* 200 */ 0x37b6623a98cfc088UL, 0xfe9bed1fa4d6aca4UL, +- 0x04d29b8e56a8d1b0UL, 0x725f71c40b519575UL, +- /* 201 */ 0x28c7f89cd0339ce6UL, 0x8367b14469ddc18bUL, +- 0x883ada83a6a1652cUL, 0x585f1974034d6c17UL, +- /* 202 */ 0x89cfb266f1b19188UL, 0xe63b4863e7c35217UL, +- 0xd88c9da6b4c0526aUL, 0x3e035c9df0954635UL, +- /* 203 */ 0xdd9d5412fb45de9dUL, 0xdd684532e4cff40dUL, +- 0x4b5c999b151d671cUL, 0x2d8c2cc811e7f690UL, +- /* 204 */ 0x7f54be1d90055d40UL, 0xa464c5df464aaf40UL, +- 0x33979624f0e917beUL, 0x2c018dc527356b30UL, +- /* 205 */ 0xa5415024e330b3d4UL, 0x73ff3d96691652d3UL, +- 0x94ec42c4ef9b59f1UL, 0x0747201618d08e5aUL, +- /* 206 */ 0x4d6ca48aca411c53UL, 0x66415f2fcfa66119UL, +- 0x9c4dd40051e227ffUL, 0x59810bc09a02f7ebUL, +- /* 207 */ 0x2a7eb171b3dc101dUL, 0x441c5ab99ffef68eUL, +- 0x32025c9b93b359eaUL, 0x5e8ce0a71e9d112fUL, +- /* 208 */ 0xbfcccb92429503fdUL, 0xd271ba752f095d55UL, +- 0x345ead5e972d091eUL, 0x18c8df11a83103baUL, +- /* 209 */ 0x90cd949a9aed0f4cUL, 0xc5d1f4cb6660e37eUL, +- 0xb8cac52d56c52e0bUL, 0x6e42e400c5808e0dUL, +- /* 210 */ 0xa3b46966eeaefd23UL, 0x0c4f1f0be39ecdcaUL, +- 0x189dc8c9d683a51dUL, 0x51f27f054c09351bUL, +- /* 211 */ 0x4c487ccd2a320682UL, 0x587ea95bb3df1c96UL, +- 0xc8ccf79e555cb8e8UL, 0x547dc829a206d73dUL, +- /* 212 */ 0xb822a6cd80c39b06UL, 0xe96d54732000d4c6UL, +- 0x28535b6f91463b4dUL, 0x228f4660e2486e1dUL, +- /* 213 */ 0x98799538de8d3abfUL, 0x8cd8330045ebca6eUL, +- 0x79952a008221e738UL, 0x4322e1a7535cd2bbUL, +- /* 214 */ 0xb114c11819d1801cUL, 0x2016e4d84f3f5ec7UL, +- 0xdd0e2df409260f4cUL, 0x5ec362c0ae5f7266UL, +- /* 215 */ 0xc0462b18b8b2b4eeUL, 0x7cc8d950274d1afbUL, +- 0xf25f7105436b02d2UL, 0x43bbf8dcbff9ccd3UL, +- /* 216 */ 0xb6ad1767a039e9dfUL, 0xb0714da8f69d3583UL, +- 0x5e55fa18b42931f5UL, 0x4ed5558f33c60961UL, +- /* 217 */ 0x1fe37901c647a5ddUL, 0x593ddf1f8081d357UL, +- 0x0249a4fd813fd7a6UL, 0x69acca274e9caf61UL, +- /* 218 */ 0x047ba3ea330721c9UL, 0x83423fc20e7e1ea0UL, +- 0x1df4c0af01314a60UL, 0x09a62dab89289527UL, +- /* 219 */ 0xa5b325a49cc6cb00UL, 0xe94b5dc654b56cb6UL, +- 0x3be28779adc994a0UL, 0x4296e8f8ba3a4aadUL, +- /* 220 */ 0x328689761e451eabUL, 0x2e4d598bff59594aUL, +- 0x49b96853d7a7084aUL, 0x4980a319601420a8UL, +- /* 221 */ 0x9565b9e12f552c42UL, 0x8a5318db7100fe96UL, +- 0x05c90b4d43add0d7UL, 0x538b4cd66a5d4edaUL, +- /* 222 */ 0xf4e94fc3e89f039fUL, 0x592c9af26f618045UL, +- 0x08a36eb5fd4b9550UL, 0x25fffaf6c2ed1419UL, +- /* 223 */ 0x34434459cc79d354UL, 0xeeecbfb4b1d5476bUL, +- 0xddeb34a061615d99UL, 0x5129cecceb64b773UL, +- /* 224 */ 0xee43215894993520UL, 0x772f9c7cf14c0b3bUL, +- 0xd2e2fce306bedad5UL, 0x715f42b546f06a97UL, +- /* 225 */ 0x434ecdceda5b5f1aUL, 0x0da17115a49741a9UL, +- 0x680bd77c73edad2eUL, 0x487c02354edd9041UL, +- /* 226 */ 0xb8efeff3a70ed9c4UL, 0x56a32aa3e857e302UL, +- 0xdf3a68bd48a2a5a0UL, 0x07f650b73176c444UL, +- /* 227 */ 0xe38b9b1626e0ccb1UL, 0x79e053c18b09fb36UL, +- 0x56d90319c9f94964UL, 0x1ca941e7ac9ff5c4UL, +- /* 228 */ 0x49c4df29162fa0bbUL, 0x8488cf3282b33305UL, +- 0x95dfda14cabb437dUL, 0x3391f78264d5ad86UL, +- /* 229 */ 0x729ae06ae2b5095dUL, 0xd58a58d73259a946UL, +- 0xe9834262d13921edUL, 0x27fedafaa54bb592UL, +- /* 230 */ 0xa99dc5b829ad48bbUL, 0x5f025742499ee260UL, +- 0x802c8ecd5d7513fdUL, 0x78ceb3ef3f6dd938UL, +- /* 231 */ 0xc342f44f8a135d94UL, 0x7b9edb44828cdda3UL, +- 0x9436d11a0537cfe7UL, 0x5064b164ec1ab4c8UL, +- /* 232 */ 0x7020eccfd37eb2fcUL, 0x1f31ea3ed90d25fcUL, +- 0x1b930d7bdfa1bb34UL, 0x5344467a48113044UL, +- /* 233 */ 0x70073170f25e6dfbUL, 0xe385dc1a50114cc8UL, +- 0x2348698ac8fc4f00UL, 0x2a77a55284dd40d8UL, +- /* 234 */ 0xfe06afe0c98c6ce4UL, 0xc235df96dddfd6e4UL, +- 0x1428d01e33bf1ed3UL, 0x785768ec9300bdafUL, +- /* 235 */ 0x9702e57a91deb63bUL, 0x61bdb8bfe5ce8b80UL, +- 0x645b426f3d1d58acUL, 0x4804a82227a557bcUL, +- /* 236 */ 0x8e57048ab44d2601UL, 0x68d6501a4b3a6935UL, +- 0xc39c9ec3f9e1c293UL, 0x4172f257d4de63e2UL, +- /* 237 */ 0xd368b450330c6401UL, 0x040d3017418f2391UL, +- 0x2c34bb6090b7d90dUL, 0x16f649228fdfd51fUL, +- /* 238 */ 0xbea6818e2b928ef5UL, 0xe28ccf91cdc11e72UL, +- 0x594aaa68e77a36cdUL, 0x313034806c7ffd0fUL, +- /* 239 */ 0x8a9d27ac2249bd65UL, 0x19a3b464018e9512UL, +- 0xc26ccff352b37ec7UL, 0x056f68341d797b21UL, +- /* 240 */ 0x5e79d6757efd2327UL, 0xfabdbcb6553afe15UL, +- 0xd3e7222c6eaf5a60UL, 0x7046c76d4dae743bUL, +- /* 241 */ 0x660be872b18d4a55UL, 0x19992518574e1496UL, +- 0xc103053a302bdcbbUL, 0x3ed8e9800b218e8eUL, +- /* 242 */ 0x7b0b9239fa75e03eUL, 0xefe9fb684633c083UL, +- 0x98a35fbe391a7793UL, 0x6065510fe2d0fe34UL, +- /* 243 */ 0x55cb668548abad0cUL, 0xb4584548da87e527UL, +- 0x2c43ecea0107c1ddUL, 0x526028809372de35UL, +- /* 244 */ 0x3415c56af9213b1fUL, 0x5bee1a4d017e98dbUL, +- 0x13f6b105b5cf709bUL, 0x5ff20e3482b29ab6UL, +- /* 245 */ 0x0aa29c75cc2e6c90UL, 0xfc7d73ca3a70e206UL, +- 0x899fc38fc4b5c515UL, 0x250386b124ffc207UL, +- /* 246 */ 0x54ea28d5ae3d2b56UL, 0x9913149dd6de60ceUL, +- 0x16694fc58f06d6c1UL, 0x46b23975eb018fc7UL, +- /* 247 */ 0x470a6a0fb4b7b4e2UL, 0x5d92475a8f7253deUL, +- 0xabeee5b52fbd3adbUL, 0x7fa20801a0806968UL, +- /* 248 */ 0x76f3faf19f7714d2UL, 0xb3e840c12f4660c3UL, +- 0x0fb4cd8df212744eUL, 0x4b065a251d3a2dd2UL, +- /* 249 */ 0x5cebde383d77cd4aUL, 0x6adf39df882c9cb1UL, +- 0xa2dd242eb09af759UL, 0x3147c0e50e5f6422UL, +- /* 250 */ 0x164ca5101d1350dbUL, 0xf8d13479c33fc962UL, +- 0xe640ce4d13e5da08UL, 0x4bdee0c45061f8baUL, +- /* 251 */ 0xd7c46dc1a4edb1c9UL, 0x5514d7b6437fd98aUL, +- 0x58942f6bb2a1c00bUL, 0x2dffb2ab1d70710eUL, +- /* 252 */ 0xccdfcf2fc18b6d68UL, 0xa8ebcba8b7806167UL, +- 0x980697f95e2937e3UL, 0x02fbba1cd0126e8cUL +-}; +- +-/* c is two 512-bit products: c0[0:7]=a0[0:3]*b0[0:3] and c1[8:15]=a1[4:7]*b1[4:7] +- * a is two 256-bit integers: a0[0:3] and a1[4:7] +- * b is two 256-bit integers: b0[0:3] and b1[4:7] +- */ +-static void mul2_256x256_integer_adx(u64 *const c, const u64 *const a, +- const u64 *const b) +-{ +- asm volatile( +- "xorl %%r14d, %%r14d ;" +- "movq (%1), %%rdx; " /* A[0] */ +- "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ +- "xorl %%r10d, %%r10d ;" +- "movq %%r8, (%0) ;" +- "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ +- "adox %%r10, %%r15 ;" +- "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ +- "adox %%r8, %%rax ;" +- "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ +- "adox %%r10, %%rbx ;" +- /******************************************/ +- "adox %%r14, %%rcx ;" +- +- "movq 8(%1), %%rdx; " /* A[1] */ +- "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ +- "adox %%r15, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ +- "adox %%r10, %%r9 ;" +- "adcx %%r9, %%rax ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ +- "adox %%r8, %%r11 ;" +- "adcx %%r11, %%rbx ;" +- "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ +- "adox %%r10, %%r13 ;" +- "adcx %%r13, %%rcx ;" +- /******************************************/ +- "adox %%r14, %%r15 ;" +- "adcx %%r14, %%r15 ;" +- +- "movq 16(%1), %%rdx; " /* A[2] */ +- "xorl %%r10d, %%r10d ;" +- "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ +- "adox %%rax, %%r8 ;" +- "movq %%r8, 16(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ +- "adox %%r10, %%r9 ;" +- "adcx %%r9, %%rbx ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ +- "adox %%r8, %%r11 ;" +- "adcx %%r11, %%rcx ;" +- "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ +- "adox %%r10, %%r13 ;" +- "adcx %%r13, %%r15 ;" +- /******************************************/ +- "adox %%r14, %%rax ;" +- "adcx %%r14, %%rax ;" +- +- "movq 24(%1), %%rdx; " /* A[3] */ +- "xorl %%r10d, %%r10d ;" +- "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ +- "adox %%rbx, %%r8 ;" +- "movq %%r8, 24(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ +- "adox %%r10, %%r9 ;" +- "adcx %%r9, %%rcx ;" +- "movq %%rcx, 32(%0) ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ +- "adox %%r8, %%r11 ;" +- "adcx %%r11, %%r15 ;" +- "movq %%r15, 40(%0) ;" +- "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ +- "adox %%r10, %%r13 ;" +- "adcx %%r13, %%rax ;" +- "movq %%rax, 48(%0) ;" +- /******************************************/ +- "adox %%r14, %%rbx ;" +- "adcx %%r14, %%rbx ;" +- "movq %%rbx, 56(%0) ;" +- +- "movq 32(%1), %%rdx; " /* C[0] */ +- "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ +- "xorl %%r10d, %%r10d ;" +- "movq %%r8, 64(%0);" +- "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ +- "adox %%r10, %%r15 ;" +- "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ +- "adox %%r8, %%rax ;" +- "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ +- "adox %%r10, %%rbx ;" +- /******************************************/ +- "adox %%r14, %%rcx ;" +- +- "movq 40(%1), %%rdx; " /* C[1] */ +- "xorl %%r10d, %%r10d ;" +- "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ +- "adox %%r15, %%r8 ;" +- "movq %%r8, 72(%0);" +- "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ +- "adox %%r10, %%r9 ;" +- "adcx %%r9, %%rax ;" +- "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ +- "adox %%r8, %%r11 ;" +- "adcx %%r11, %%rbx ;" +- "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ +- "adox %%r10, %%r13 ;" +- "adcx %%r13, %%rcx ;" +- /******************************************/ +- "adox %%r14, %%r15 ;" +- "adcx %%r14, %%r15 ;" +- +- "movq 48(%1), %%rdx; " /* C[2] */ +- "xorl %%r10d, %%r10d ;" +- "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ +- "adox %%rax, %%r8 ;" +- "movq %%r8, 80(%0);" +- "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ +- "adox %%r10, %%r9 ;" +- "adcx %%r9, %%rbx ;" +- "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ +- "adox %%r8, %%r11 ;" +- "adcx %%r11, %%rcx ;" +- "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ +- "adox %%r10, %%r13 ;" +- "adcx %%r13, %%r15 ;" +- /******************************************/ +- "adox %%r14, %%rax ;" +- "adcx %%r14, %%rax ;" +- +- "movq 56(%1), %%rdx; " /* C[3] */ +- "xorl %%r10d, %%r10d ;" +- "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ +- "adox %%rbx, %%r8 ;" +- "movq %%r8, 88(%0);" +- "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ +- "adox %%r10, %%r9 ;" +- "adcx %%r9, %%rcx ;" +- "movq %%rcx, 96(%0) ;" +- "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ +- "adox %%r8, %%r11 ;" +- "adcx %%r11, %%r15 ;" +- "movq %%r15, 104(%0) ;" +- "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ +- "adox %%r10, %%r13 ;" +- "adcx %%r13, %%rax ;" +- "movq %%rax, 112(%0) ;" +- /******************************************/ +- "adox %%r14, %%rbx ;" +- "adcx %%r14, %%rbx ;" +- "movq %%rbx, 120(%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11", "%r13", "%r14", "%r15"); +-} +- +-static void mul2_256x256_integer_bmi2(u64 *const c, const u64 *const a, +- const u64 *const b) ++static __always_inline u64 eq_mask(u64 a, u64 b) + { +- asm volatile( +- "movq (%1), %%rdx; " /* A[0] */ +- "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ +- "movq %%r8, (%0) ;" +- "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ +- "addq %%r10, %%r15 ;" +- "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ +- "adcq %%r8, %%rax ;" +- "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ +- "adcq %%r10, %%rbx ;" +- /******************************************/ +- "adcq $0, %%rcx ;" +- +- "movq 8(%1), %%rdx; " /* A[1] */ +- "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ +- "addq %%r15, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%r15 ;" +- +- "addq %%r9, %%rax ;" +- "adcq %%r11, %%rbx ;" +- "adcq %%r13, %%rcx ;" +- "adcq $0, %%r15 ;" +- +- "movq 16(%1), %%rdx; " /* A[2] */ +- "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ +- "addq %%rax, %%r8 ;" +- "movq %%r8, 16(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%rax ;" +- +- "addq %%r9, %%rbx ;" +- "adcq %%r11, %%rcx ;" +- "adcq %%r13, %%r15 ;" +- "adcq $0, %%rax ;" +- +- "movq 24(%1), %%rdx; " /* A[3] */ +- "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ +- "addq %%rbx, %%r8 ;" +- "movq %%r8, 24(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%rbx ;" +- +- "addq %%r9, %%rcx ;" +- "movq %%rcx, 32(%0) ;" +- "adcq %%r11, %%r15 ;" +- "movq %%r15, 40(%0) ;" +- "adcq %%r13, %%rax ;" +- "movq %%rax, 48(%0) ;" +- "adcq $0, %%rbx ;" +- "movq %%rbx, 56(%0) ;" +- +- "movq 32(%1), %%rdx; " /* C[0] */ +- "mulx 32(%2), %%r8, %%r15; " /* C[0]*D[0] */ +- "movq %%r8, 64(%0) ;" +- "mulx 40(%2), %%r10, %%rax; " /* C[0]*D[1] */ +- "addq %%r10, %%r15 ;" +- "mulx 48(%2), %%r8, %%rbx; " /* C[0]*D[2] */ +- "adcq %%r8, %%rax ;" +- "mulx 56(%2), %%r10, %%rcx; " /* C[0]*D[3] */ +- "adcq %%r10, %%rbx ;" +- /******************************************/ +- "adcq $0, %%rcx ;" +- +- "movq 40(%1), %%rdx; " /* C[1] */ +- "mulx 32(%2), %%r8, %%r9; " /* C[1]*D[0] */ +- "addq %%r15, %%r8 ;" +- "movq %%r8, 72(%0) ;" +- "mulx 40(%2), %%r10, %%r11; " /* C[1]*D[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 48(%2), %%r8, %%r13; " /* C[1]*D[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 56(%2), %%r10, %%r15; " /* C[1]*D[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%r15 ;" +- +- "addq %%r9, %%rax ;" +- "adcq %%r11, %%rbx ;" +- "adcq %%r13, %%rcx ;" +- "adcq $0, %%r15 ;" +- +- "movq 48(%1), %%rdx; " /* C[2] */ +- "mulx 32(%2), %%r8, %%r9; " /* C[2]*D[0] */ +- "addq %%rax, %%r8 ;" +- "movq %%r8, 80(%0) ;" +- "mulx 40(%2), %%r10, %%r11; " /* C[2]*D[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 48(%2), %%r8, %%r13; " /* C[2]*D[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 56(%2), %%r10, %%rax; " /* C[2]*D[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%rax ;" +- +- "addq %%r9, %%rbx ;" +- "adcq %%r11, %%rcx ;" +- "adcq %%r13, %%r15 ;" +- "adcq $0, %%rax ;" +- +- "movq 56(%1), %%rdx; " /* C[3] */ +- "mulx 32(%2), %%r8, %%r9; " /* C[3]*D[0] */ +- "addq %%rbx, %%r8 ;" +- "movq %%r8, 88(%0) ;" +- "mulx 40(%2), %%r10, %%r11; " /* C[3]*D[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 48(%2), %%r8, %%r13; " /* C[3]*D[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 56(%2), %%r10, %%rbx; " /* C[3]*D[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%rbx ;" +- +- "addq %%r9, %%rcx ;" +- "movq %%rcx, 96(%0) ;" +- "adcq %%r11, %%r15 ;" +- "movq %%r15, 104(%0) ;" +- "adcq %%r13, %%rax ;" +- "movq %%rax, 112(%0) ;" +- "adcq $0, %%rbx ;" +- "movq %%rbx, 120(%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11", "%r13", "%r15"); ++ u64 x = a ^ b; ++ u64 minus_x = ~x + (u64)1U; ++ u64 x_or_minus_x = x | minus_x; ++ u64 xnx = x_or_minus_x >> (u32)63U; ++ return xnx - (u64)1U; + } + +-static void sqr2_256x256_integer_adx(u64 *const c, const u64 *const a) ++static __always_inline u64 gte_mask(u64 a, u64 b) + { +- asm volatile( +- "movq (%1), %%rdx ;" /* A[0] */ +- "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ +- "xorl %%r15d, %%r15d;" +- "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ +- "adcx %%r14, %%r9 ;" +- "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ +- "adcx %%rax, %%r10 ;" +- "movq 24(%1), %%rdx ;" /* A[3] */ +- "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ +- "adcx %%rcx, %%r11 ;" +- "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ +- "adcx %%rax, %%rbx ;" +- "movq 8(%1), %%rdx ;" /* A[1] */ +- "adcx %%r15, %%r13 ;" +- "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ +- "movq $0, %%r14 ;" +- /******************************************/ +- "adcx %%r15, %%r14 ;" +- +- "xorl %%r15d, %%r15d;" +- "adox %%rax, %%r10 ;" +- "adcx %%r8, %%r8 ;" +- "adox %%rcx, %%r11 ;" +- "adcx %%r9, %%r9 ;" +- "adox %%r15, %%rbx ;" +- "adcx %%r10, %%r10 ;" +- "adox %%r15, %%r13 ;" +- "adcx %%r11, %%r11 ;" +- "adox %%r15, %%r14 ;" +- "adcx %%rbx, %%rbx ;" +- "adcx %%r13, %%r13 ;" +- "adcx %%r14, %%r14 ;" +- +- "movq (%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ +- /*******************/ +- "movq %%rax, 0(%0) ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "movq 8(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ +- "adcq %%rax, %%r9 ;" +- "movq %%r9, 16(%0) ;" +- "adcq %%rcx, %%r10 ;" +- "movq %%r10, 24(%0) ;" +- "movq 16(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ +- "adcq %%rax, %%r11 ;" +- "movq %%r11, 32(%0) ;" +- "adcq %%rcx, %%rbx ;" +- "movq %%rbx, 40(%0) ;" +- "movq 24(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ +- "adcq %%rax, %%r13 ;" +- "movq %%r13, 48(%0) ;" +- "adcq %%rcx, %%r14 ;" +- "movq %%r14, 56(%0) ;" +- +- +- "movq 32(%1), %%rdx ;" /* B[0] */ +- "mulx 40(%1), %%r8, %%r14 ;" /* B[1]*B[0] */ +- "xorl %%r15d, %%r15d;" +- "mulx 48(%1), %%r9, %%r10 ;" /* B[2]*B[0] */ +- "adcx %%r14, %%r9 ;" +- "mulx 56(%1), %%rax, %%rcx ;" /* B[3]*B[0] */ +- "adcx %%rax, %%r10 ;" +- "movq 56(%1), %%rdx ;" /* B[3] */ +- "mulx 40(%1), %%r11, %%rbx ;" /* B[1]*B[3] */ +- "adcx %%rcx, %%r11 ;" +- "mulx 48(%1), %%rax, %%r13 ;" /* B[2]*B[3] */ +- "adcx %%rax, %%rbx ;" +- "movq 40(%1), %%rdx ;" /* B[1] */ +- "adcx %%r15, %%r13 ;" +- "mulx 48(%1), %%rax, %%rcx ;" /* B[2]*B[1] */ +- "movq $0, %%r14 ;" +- /******************************************/ +- "adcx %%r15, %%r14 ;" +- +- "xorl %%r15d, %%r15d;" +- "adox %%rax, %%r10 ;" +- "adcx %%r8, %%r8 ;" +- "adox %%rcx, %%r11 ;" +- "adcx %%r9, %%r9 ;" +- "adox %%r15, %%rbx ;" +- "adcx %%r10, %%r10 ;" +- "adox %%r15, %%r13 ;" +- "adcx %%r11, %%r11 ;" +- "adox %%r15, %%r14 ;" +- "adcx %%rbx, %%rbx ;" +- "adcx %%r13, %%r13 ;" +- "adcx %%r14, %%r14 ;" +- +- "movq 32(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* B[0]^2 */ +- /*******************/ +- "movq %%rax, 64(%0) ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 72(%0) ;" +- "movq 40(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* B[1]^2 */ +- "adcq %%rax, %%r9 ;" +- "movq %%r9, 80(%0) ;" +- "adcq %%rcx, %%r10 ;" +- "movq %%r10, 88(%0) ;" +- "movq 48(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* B[2]^2 */ +- "adcq %%rax, %%r11 ;" +- "movq %%r11, 96(%0) ;" +- "adcq %%rcx, %%rbx ;" +- "movq %%rbx, 104(%0) ;" +- "movq 56(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* B[3]^2 */ +- "adcq %%rax, %%r13 ;" +- "movq %%r13, 112(%0) ;" +- "adcq %%rcx, %%r14 ;" +- "movq %%r14, 120(%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11", "%r13", "%r14", "%r15"); ++ u64 x = a; ++ u64 y = b; ++ u64 x_xor_y = x ^ y; ++ u64 x_sub_y = x - y; ++ u64 x_sub_y_xor_y = x_sub_y ^ y; ++ u64 q = x_xor_y | x_sub_y_xor_y; ++ u64 x_xor_q = x ^ q; ++ u64 x_xor_q_ = x_xor_q >> (u32)63U; ++ return x_xor_q_ - (u64)1U; + } + +-static void sqr2_256x256_integer_bmi2(u64 *const c, const u64 *const a) ++/* Computes the addition of four-element f1 with value in f2 ++ * and returns the carry (if any) */ ++static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2) + { +- asm volatile( +- "movq 8(%1), %%rdx ;" /* A[1] */ +- "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ +- "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ +- "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ +- +- "movq 16(%1), %%rdx ;" /* A[2] */ +- "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ +- "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ +- +- "addq %%rax, %%r9 ;" +- "adcq %%rdx, %%r10 ;" +- "adcq %%rcx, %%r11 ;" +- "adcq %%r14, %%r15 ;" +- "adcq $0, %%r13 ;" +- "movq $0, %%r14 ;" +- "adcq $0, %%r14 ;" +- +- "movq (%1), %%rdx ;" /* A[0] */ +- "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ +- +- "addq %%rax, %%r10 ;" +- "adcq %%rcx, %%r11 ;" +- "adcq $0, %%r15 ;" +- "adcq $0, %%r13 ;" +- "adcq $0, %%r14 ;" +- +- "shldq $1, %%r13, %%r14 ;" +- "shldq $1, %%r15, %%r13 ;" +- "shldq $1, %%r11, %%r15 ;" +- "shldq $1, %%r10, %%r11 ;" +- "shldq $1, %%r9, %%r10 ;" +- "shldq $1, %%r8, %%r9 ;" +- "shlq $1, %%r8 ;" +- +- /*******************/ +- "mulx %%rdx, %%rax, %%rcx ; " /* A[0]^2 */ +- /*******************/ +- "movq %%rax, 0(%0) ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "movq 8(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ; " /* A[1]^2 */ +- "adcq %%rax, %%r9 ;" +- "movq %%r9, 16(%0) ;" +- "adcq %%rcx, %%r10 ;" +- "movq %%r10, 24(%0) ;" +- "movq 16(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ; " /* A[2]^2 */ +- "adcq %%rax, %%r11 ;" +- "movq %%r11, 32(%0) ;" +- "adcq %%rcx, %%r15 ;" +- "movq %%r15, 40(%0) ;" +- "movq 24(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ; " /* A[3]^2 */ +- "adcq %%rax, %%r13 ;" +- "movq %%r13, 48(%0) ;" +- "adcq %%rcx, %%r14 ;" +- "movq %%r14, 56(%0) ;" +- +- "movq 40(%1), %%rdx ;" /* B[1] */ +- "mulx 32(%1), %%r8, %%r9 ;" /* B[0]*B[1] */ +- "mulx 48(%1), %%r10, %%r11 ;" /* B[2]*B[1] */ +- "mulx 56(%1), %%rcx, %%r14 ;" /* B[3]*B[1] */ +- +- "movq 48(%1), %%rdx ;" /* B[2] */ +- "mulx 56(%1), %%r15, %%r13 ;" /* B[3]*B[2] */ +- "mulx 32(%1), %%rax, %%rdx ;" /* B[0]*B[2] */ +- +- "addq %%rax, %%r9 ;" +- "adcq %%rdx, %%r10 ;" +- "adcq %%rcx, %%r11 ;" +- "adcq %%r14, %%r15 ;" +- "adcq $0, %%r13 ;" +- "movq $0, %%r14 ;" +- "adcq $0, %%r14 ;" +- +- "movq 32(%1), %%rdx ;" /* B[0] */ +- "mulx 56(%1), %%rax, %%rcx ;" /* B[0]*B[3] */ +- +- "addq %%rax, %%r10 ;" +- "adcq %%rcx, %%r11 ;" +- "adcq $0, %%r15 ;" +- "adcq $0, %%r13 ;" +- "adcq $0, %%r14 ;" +- +- "shldq $1, %%r13, %%r14 ;" +- "shldq $1, %%r15, %%r13 ;" +- "shldq $1, %%r11, %%r15 ;" +- "shldq $1, %%r10, %%r11 ;" +- "shldq $1, %%r9, %%r10 ;" +- "shldq $1, %%r8, %%r9 ;" +- "shlq $1, %%r8 ;" +- +- /*******************/ +- "mulx %%rdx, %%rax, %%rcx ; " /* B[0]^2 */ +- /*******************/ +- "movq %%rax, 64(%0) ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 72(%0) ;" +- "movq 40(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ; " /* B[1]^2 */ +- "adcq %%rax, %%r9 ;" +- "movq %%r9, 80(%0) ;" +- "adcq %%rcx, %%r10 ;" +- "movq %%r10, 88(%0) ;" +- "movq 48(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ; " /* B[2]^2 */ +- "adcq %%rax, %%r11 ;" +- "movq %%r11, 96(%0) ;" +- "adcq %%rcx, %%r15 ;" +- "movq %%r15, 104(%0) ;" +- "movq 56(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ; " /* B[3]^2 */ +- "adcq %%rax, %%r13 ;" +- "movq %%r13, 112(%0) ;" +- "adcq %%rcx, %%r14 ;" +- "movq %%r14, 120(%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", +- "%r11", "%r13", "%r14", "%r15"); +-} ++ u64 carry_r; + +-static void red_eltfp25519_2w_adx(u64 *const c, const u64 *const a) +-{ + asm volatile( +- "movl $38, %%edx; " /* 2*c = 38 = 2^256 */ +- "mulx 32(%1), %%r8, %%r10; " /* c*C[4] */ +- "xorl %%ebx, %%ebx ;" +- "adox (%1), %%r8 ;" +- "mulx 40(%1), %%r9, %%r11; " /* c*C[5] */ +- "adcx %%r10, %%r9 ;" +- "adox 8(%1), %%r9 ;" +- "mulx 48(%1), %%r10, %%rax; " /* c*C[6] */ +- "adcx %%r11, %%r10 ;" +- "adox 16(%1), %%r10 ;" +- "mulx 56(%1), %%r11, %%rcx; " /* c*C[7] */ +- "adcx %%rax, %%r11 ;" +- "adox 24(%1), %%r11 ;" +- /***************************************/ +- "adcx %%rbx, %%rcx ;" +- "adox %%rbx, %%rcx ;" +- "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ +- "adcx %%rcx, %%r8 ;" +- "adcx %%rbx, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcx %%rbx, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcx %%rbx, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- +- "mulx 96(%1), %%r8, %%r10; " /* c*C[4] */ +- "xorl %%ebx, %%ebx ;" +- "adox 64(%1), %%r8 ;" +- "mulx 104(%1), %%r9, %%r11; " /* c*C[5] */ +- "adcx %%r10, %%r9 ;" +- "adox 72(%1), %%r9 ;" +- "mulx 112(%1), %%r10, %%rax; " /* c*C[6] */ +- "adcx %%r11, %%r10 ;" +- "adox 80(%1), %%r10 ;" +- "mulx 120(%1), %%r11, %%rcx; " /* c*C[7] */ +- "adcx %%rax, %%r11 ;" +- "adox 88(%1), %%r11 ;" +- /****************************************/ +- "adcx %%rbx, %%rcx ;" +- "adox %%rbx, %%rcx ;" +- "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ +- "adcx %%rcx, %%r8 ;" +- "adcx %%rbx, %%r9 ;" +- "movq %%r9, 40(%0) ;" +- "adcx %%rbx, %%r10 ;" +- "movq %%r10, 48(%0) ;" +- "adcx %%rbx, %%r11 ;" +- "movq %%r11, 56(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 32(%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11"); +-} ++ /* Clear registers to propagate the carry bit */ ++ " xor %%r8, %%r8;" ++ " xor %%r9, %%r9;" ++ " xor %%r10, %%r10;" ++ " xor %%r11, %%r11;" ++ " xor %1, %1;" ++ ++ /* Begin addition chain */ ++ " addq 0(%3), %0;" ++ " movq %0, 0(%2);" ++ " adcxq 8(%3), %%r8;" ++ " movq %%r8, 8(%2);" ++ " adcxq 16(%3), %%r9;" ++ " movq %%r9, 16(%2);" ++ " adcxq 24(%3), %%r10;" ++ " movq %%r10, 24(%2);" ++ ++ /* Return the carry bit in a register */ ++ " adcx %%r11, %1;" ++ : "+&r" (f2), "=&r" (carry_r) ++ : "r" (out), "r" (f1) ++ : "%r8", "%r9", "%r10", "%r11", "memory", "cc" ++ ); + +-static void red_eltfp25519_2w_bmi2(u64 *const c, const u64 *const a) +-{ +- asm volatile( +- "movl $38, %%edx ; " /* 2*c = 38 = 2^256 */ +- "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ +- "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ +- "addq %%r10, %%r9 ;" +- "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ +- "adcq %%r11, %%r10 ;" +- "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ +- "adcq %%rax, %%r11 ;" +- /***************************************/ +- "adcq $0, %%rcx ;" +- "addq (%1), %%r8 ;" +- "adcq 8(%1), %%r9 ;" +- "adcq 16(%1), %%r10 ;" +- "adcq 24(%1), %%r11 ;" +- "adcq $0, %%rcx ;" +- "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ +- "addq %%rcx, %%r8 ;" +- "adcq $0, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcq $0, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcq $0, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- +- "mulx 96(%1), %%r8, %%r10 ;" /* c*C[4] */ +- "mulx 104(%1), %%r9, %%r11 ;" /* c*C[5] */ +- "addq %%r10, %%r9 ;" +- "mulx 112(%1), %%r10, %%rax ;" /* c*C[6] */ +- "adcq %%r11, %%r10 ;" +- "mulx 120(%1), %%r11, %%rcx ;" /* c*C[7] */ +- "adcq %%rax, %%r11 ;" +- /****************************************/ +- "adcq $0, %%rcx ;" +- "addq 64(%1), %%r8 ;" +- "adcq 72(%1), %%r9 ;" +- "adcq 80(%1), %%r10 ;" +- "adcq 88(%1), %%r11 ;" +- "adcq $0, %%rcx ;" +- "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ +- "addq %%rcx, %%r8 ;" +- "adcq $0, %%r9 ;" +- "movq %%r9, 40(%0) ;" +- "adcq $0, %%r10 ;" +- "movq %%r10, 48(%0) ;" +- "adcq $0, %%r11 ;" +- "movq %%r11, 56(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 32(%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", +- "%r11"); ++ return carry_r; + } + +-static void mul_256x256_integer_adx(u64 *const c, const u64 *const a, +- const u64 *const b) ++/* Computes the field addition of two field elements */ ++static inline void fadd(u64 *out, const u64 *f1, const u64 *f2) + { + asm volatile( +- "movq (%1), %%rdx; " /* A[0] */ +- "mulx (%2), %%r8, %%r9; " /* A[0]*B[0] */ +- "xorl %%r10d, %%r10d ;" +- "movq %%r8, (%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[0]*B[1] */ +- "adox %%r9, %%r10 ;" +- "movq %%r10, 8(%0) ;" +- "mulx 16(%2), %%r15, %%r13; " /* A[0]*B[2] */ +- "adox %%r11, %%r15 ;" +- "mulx 24(%2), %%r14, %%rdx; " /* A[0]*B[3] */ +- "adox %%r13, %%r14 ;" +- "movq $0, %%rax ;" +- /******************************************/ +- "adox %%rdx, %%rax ;" +- +- "movq 8(%1), %%rdx; " /* A[1] */ +- "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ +- "xorl %%r10d, %%r10d ;" +- "adcx 8(%0), %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ +- "adox %%r9, %%r10 ;" +- "adcx %%r15, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "mulx 16(%2), %%r15, %%r13; " /* A[1]*B[2] */ +- "adox %%r11, %%r15 ;" +- "adcx %%r14, %%r15 ;" +- "movq $0, %%r8 ;" +- "mulx 24(%2), %%r14, %%rdx; " /* A[1]*B[3] */ +- "adox %%r13, %%r14 ;" +- "adcx %%rax, %%r14 ;" +- "movq $0, %%rax ;" +- /******************************************/ +- "adox %%rdx, %%rax ;" +- "adcx %%r8, %%rax ;" +- +- "movq 16(%1), %%rdx; " /* A[2] */ +- "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ +- "xorl %%r10d, %%r10d ;" +- "adcx 16(%0), %%r8 ;" +- "movq %%r8, 16(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ +- "adox %%r9, %%r10 ;" +- "adcx %%r15, %%r10 ;" +- "movq %%r10, 24(%0) ;" +- "mulx 16(%2), %%r15, %%r13; " /* A[2]*B[2] */ +- "adox %%r11, %%r15 ;" +- "adcx %%r14, %%r15 ;" +- "movq $0, %%r8 ;" +- "mulx 24(%2), %%r14, %%rdx; " /* A[2]*B[3] */ +- "adox %%r13, %%r14 ;" +- "adcx %%rax, %%r14 ;" +- "movq $0, %%rax ;" +- /******************************************/ +- "adox %%rdx, %%rax ;" +- "adcx %%r8, %%rax ;" +- +- "movq 24(%1), %%rdx; " /* A[3] */ +- "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ +- "xorl %%r10d, %%r10d ;" +- "adcx 24(%0), %%r8 ;" +- "movq %%r8, 24(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ +- "adox %%r9, %%r10 ;" +- "adcx %%r15, %%r10 ;" +- "movq %%r10, 32(%0) ;" +- "mulx 16(%2), %%r15, %%r13; " /* A[3]*B[2] */ +- "adox %%r11, %%r15 ;" +- "adcx %%r14, %%r15 ;" +- "movq %%r15, 40(%0) ;" +- "movq $0, %%r8 ;" +- "mulx 24(%2), %%r14, %%rdx; " /* A[3]*B[3] */ +- "adox %%r13, %%r14 ;" +- "adcx %%rax, %%r14 ;" +- "movq %%r14, 48(%0) ;" +- "movq $0, %%rax ;" +- /******************************************/ +- "adox %%rdx, %%rax ;" +- "adcx %%r8, %%rax ;" +- "movq %%rax, 56(%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", +- "%r13", "%r14", "%r15"); ++ /* Compute the raw addition of f1 + f2 */ ++ " movq 0(%0), %%r8;" ++ " addq 0(%2), %%r8;" ++ " movq 8(%0), %%r9;" ++ " adcxq 8(%2), %%r9;" ++ " movq 16(%0), %%r10;" ++ " adcxq 16(%2), %%r10;" ++ " movq 24(%0), %%r11;" ++ " adcxq 24(%2), %%r11;" ++ ++ /* Wrap the result back into the field */ ++ ++ /* Step 1: Compute carry*38 */ ++ " mov $0, %%rax;" ++ " mov $38, %0;" ++ " cmovc %0, %%rax;" ++ ++ /* Step 2: Add carry*38 to the original sum */ ++ " xor %%rcx, %%rcx;" ++ " add %%rax, %%r8;" ++ " adcx %%rcx, %%r9;" ++ " movq %%r9, 8(%1);" ++ " adcx %%rcx, %%r10;" ++ " movq %%r10, 16(%1);" ++ " adcx %%rcx, %%r11;" ++ " movq %%r11, 24(%1);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %0, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 0(%1);" ++ : "+&r" (f2) ++ : "r" (out), "r" (f1) ++ : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc" ++ ); + } + +-static void mul_256x256_integer_bmi2(u64 *const c, const u64 *const a, +- const u64 *const b) ++/* Computes the field substraction of two field elements */ ++static inline void fsub(u64 *out, const u64 *f1, const u64 *f2) + { + asm volatile( +- "movq (%1), %%rdx; " /* A[0] */ +- "mulx (%2), %%r8, %%r15; " /* A[0]*B[0] */ +- "movq %%r8, (%0) ;" +- "mulx 8(%2), %%r10, %%rax; " /* A[0]*B[1] */ +- "addq %%r10, %%r15 ;" +- "mulx 16(%2), %%r8, %%rbx; " /* A[0]*B[2] */ +- "adcq %%r8, %%rax ;" +- "mulx 24(%2), %%r10, %%rcx; " /* A[0]*B[3] */ +- "adcq %%r10, %%rbx ;" +- /******************************************/ +- "adcq $0, %%rcx ;" +- +- "movq 8(%1), %%rdx; " /* A[1] */ +- "mulx (%2), %%r8, %%r9; " /* A[1]*B[0] */ +- "addq %%r15, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[1]*B[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[1]*B[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 24(%2), %%r10, %%r15; " /* A[1]*B[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%r15 ;" +- +- "addq %%r9, %%rax ;" +- "adcq %%r11, %%rbx ;" +- "adcq %%r13, %%rcx ;" +- "adcq $0, %%r15 ;" +- +- "movq 16(%1), %%rdx; " /* A[2] */ +- "mulx (%2), %%r8, %%r9; " /* A[2]*B[0] */ +- "addq %%rax, %%r8 ;" +- "movq %%r8, 16(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[2]*B[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[2]*B[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 24(%2), %%r10, %%rax; " /* A[2]*B[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%rax ;" +- +- "addq %%r9, %%rbx ;" +- "adcq %%r11, %%rcx ;" +- "adcq %%r13, %%r15 ;" +- "adcq $0, %%rax ;" +- +- "movq 24(%1), %%rdx; " /* A[3] */ +- "mulx (%2), %%r8, %%r9; " /* A[3]*B[0] */ +- "addq %%rbx, %%r8 ;" +- "movq %%r8, 24(%0) ;" +- "mulx 8(%2), %%r10, %%r11; " /* A[3]*B[1] */ +- "adcq %%r10, %%r9 ;" +- "mulx 16(%2), %%r8, %%r13; " /* A[3]*B[2] */ +- "adcq %%r8, %%r11 ;" +- "mulx 24(%2), %%r10, %%rbx; " /* A[3]*B[3] */ +- "adcq %%r10, %%r13 ;" +- /******************************************/ +- "adcq $0, %%rbx ;" +- +- "addq %%r9, %%rcx ;" +- "movq %%rcx, 32(%0) ;" +- "adcq %%r11, %%r15 ;" +- "movq %%r15, 40(%0) ;" +- "adcq %%r13, %%rax ;" +- "movq %%rax, 48(%0) ;" +- "adcq $0, %%rbx ;" +- "movq %%rbx, 56(%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11", "%r13", "%r15"); ++ /* Compute the raw substraction of f1-f2 */ ++ " movq 0(%1), %%r8;" ++ " subq 0(%2), %%r8;" ++ " movq 8(%1), %%r9;" ++ " sbbq 8(%2), %%r9;" ++ " movq 16(%1), %%r10;" ++ " sbbq 16(%2), %%r10;" ++ " movq 24(%1), %%r11;" ++ " sbbq 24(%2), %%r11;" ++ ++ /* Wrap the result back into the field */ ++ ++ /* Step 1: Compute carry*38 */ ++ " mov $0, %%rax;" ++ " mov $38, %%rcx;" ++ " cmovc %%rcx, %%rax;" ++ ++ /* Step 2: Substract carry*38 from the original difference */ ++ " sub %%rax, %%r8;" ++ " sbb $0, %%r9;" ++ " sbb $0, %%r10;" ++ " sbb $0, %%r11;" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rcx, %%rax;" ++ " sub %%rax, %%r8;" ++ ++ /* Store the result */ ++ " movq %%r8, 0(%0);" ++ " movq %%r9, 8(%0);" ++ " movq %%r10, 16(%0);" ++ " movq %%r11, 24(%0);" ++ : ++ : "r" (out), "r" (f1), "r" (f2) ++ : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc" ++ ); + } + +-static void sqr_256x256_integer_adx(u64 *const c, const u64 *const a) ++/* Computes a field multiplication: out <- f1 * f2 ++ * Uses the 8-element buffer tmp for intermediate results */ ++static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) + { + asm volatile( +- "movq (%1), %%rdx ;" /* A[0] */ +- "mulx 8(%1), %%r8, %%r14 ;" /* A[1]*A[0] */ +- "xorl %%r15d, %%r15d;" +- "mulx 16(%1), %%r9, %%r10 ;" /* A[2]*A[0] */ +- "adcx %%r14, %%r9 ;" +- "mulx 24(%1), %%rax, %%rcx ;" /* A[3]*A[0] */ +- "adcx %%rax, %%r10 ;" +- "movq 24(%1), %%rdx ;" /* A[3] */ +- "mulx 8(%1), %%r11, %%rbx ;" /* A[1]*A[3] */ +- "adcx %%rcx, %%r11 ;" +- "mulx 16(%1), %%rax, %%r13 ;" /* A[2]*A[3] */ +- "adcx %%rax, %%rbx ;" +- "movq 8(%1), %%rdx ;" /* A[1] */ +- "adcx %%r15, %%r13 ;" +- "mulx 16(%1), %%rax, %%rcx ;" /* A[2]*A[1] */ +- "movq $0, %%r14 ;" +- /******************************************/ +- "adcx %%r15, %%r14 ;" +- +- "xorl %%r15d, %%r15d;" +- "adox %%rax, %%r10 ;" +- "adcx %%r8, %%r8 ;" +- "adox %%rcx, %%r11 ;" +- "adcx %%r9, %%r9 ;" +- "adox %%r15, %%rbx ;" +- "adcx %%r10, %%r10 ;" +- "adox %%r15, %%r13 ;" +- "adcx %%r11, %%r11 ;" +- "adox %%r15, %%r14 ;" +- "adcx %%rbx, %%rbx ;" +- "adcx %%r13, %%r13 ;" +- "adcx %%r14, %%r14 ;" +- +- "movq (%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ +- /*******************/ +- "movq %%rax, 0(%0) ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "movq 8(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ +- "adcq %%rax, %%r9 ;" +- "movq %%r9, 16(%0) ;" +- "adcq %%rcx, %%r10 ;" +- "movq %%r10, 24(%0) ;" +- "movq 16(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ +- "adcq %%rax, %%r11 ;" +- "movq %%r11, 32(%0) ;" +- "adcq %%rcx, %%rbx ;" +- "movq %%rbx, 40(%0) ;" +- "movq 24(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ +- "adcq %%rax, %%r13 ;" +- "movq %%r13, 48(%0) ;" +- "adcq %%rcx, %%r14 ;" +- "movq %%r14, 56(%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11", "%r13", "%r14", "%r15"); +-} ++ /* Compute the raw multiplication: tmp <- src1 * src2 */ + +-static void sqr_256x256_integer_bmi2(u64 *const c, const u64 *const a) +-{ +- asm volatile( +- "movq 8(%1), %%rdx ;" /* A[1] */ +- "mulx (%1), %%r8, %%r9 ;" /* A[0]*A[1] */ +- "mulx 16(%1), %%r10, %%r11 ;" /* A[2]*A[1] */ +- "mulx 24(%1), %%rcx, %%r14 ;" /* A[3]*A[1] */ +- +- "movq 16(%1), %%rdx ;" /* A[2] */ +- "mulx 24(%1), %%r15, %%r13 ;" /* A[3]*A[2] */ +- "mulx (%1), %%rax, %%rdx ;" /* A[0]*A[2] */ +- +- "addq %%rax, %%r9 ;" +- "adcq %%rdx, %%r10 ;" +- "adcq %%rcx, %%r11 ;" +- "adcq %%r14, %%r15 ;" +- "adcq $0, %%r13 ;" +- "movq $0, %%r14 ;" +- "adcq $0, %%r14 ;" +- +- "movq (%1), %%rdx ;" /* A[0] */ +- "mulx 24(%1), %%rax, %%rcx ;" /* A[0]*A[3] */ +- +- "addq %%rax, %%r10 ;" +- "adcq %%rcx, %%r11 ;" +- "adcq $0, %%r15 ;" +- "adcq $0, %%r13 ;" +- "adcq $0, %%r14 ;" +- +- "shldq $1, %%r13, %%r14 ;" +- "shldq $1, %%r15, %%r13 ;" +- "shldq $1, %%r11, %%r15 ;" +- "shldq $1, %%r10, %%r11 ;" +- "shldq $1, %%r9, %%r10 ;" +- "shldq $1, %%r8, %%r9 ;" +- "shlq $1, %%r8 ;" +- +- /*******************/ +- "mulx %%rdx, %%rax, %%rcx ;" /* A[0]^2 */ +- /*******************/ +- "movq %%rax, 0(%0) ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, 8(%0) ;" +- "movq 8(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[1]^2 */ +- "adcq %%rax, %%r9 ;" +- "movq %%r9, 16(%0) ;" +- "adcq %%rcx, %%r10 ;" +- "movq %%r10, 24(%0) ;" +- "movq 16(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[2]^2 */ +- "adcq %%rax, %%r11 ;" +- "movq %%r11, 32(%0) ;" +- "adcq %%rcx, %%r15 ;" +- "movq %%r15, 40(%0) ;" +- "movq 24(%1), %%rdx ;" +- "mulx %%rdx, %%rax, %%rcx ;" /* A[3]^2 */ +- "adcq %%rax, %%r13 ;" +- "movq %%r13, 48(%0) ;" +- "adcq %%rcx, %%r14 ;" +- "movq %%r14, 56(%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", +- "%r11", "%r13", "%r14", "%r15"); ++ /* Compute src1[0] * src2 */ ++ " movq 0(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" ++ /* Compute src1[1] * src2 */ ++ " movq 8(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 16(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" ++ /* Compute src1[2] * src2 */ ++ " movq 16(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 24(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" ++ /* Compute src1[3] * src2 */ ++ " movq 24(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 32(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " movq %%r12, 40(%0);" " mov $0, %%r8;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%0);" ++ /* Line up pointers */ ++ " mov %0, %1;" ++ " mov %2, %0;" ++ ++ /* Wrap the result back into the field */ ++ ++ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ ++ " mov $38, %%rdx;" ++ " mulxq 32(%1), %%r8, %%r13;" ++ " xor %3, %3;" ++ " adoxq 0(%1), %%r8;" ++ " mulxq 40(%1), %%r9, %%r12;" ++ " adcx %%r13, %%r9;" ++ " adoxq 8(%1), %%r9;" ++ " mulxq 48(%1), %%r10, %%r13;" ++ " adcx %%r12, %%r10;" ++ " adoxq 16(%1), %%r10;" ++ " mulxq 56(%1), %%r11, %%rax;" ++ " adcx %%r13, %%r11;" ++ " adoxq 24(%1), %%r11;" ++ " adcx %3, %%rax;" ++ " adox %3, %%rax;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %3, %%r9;" ++ " movq %%r9, 8(%0);" ++ " adcx %3, %%r10;" ++ " movq %%r10, 16(%0);" ++ " adcx %3, %%r11;" ++ " movq %%r11, 24(%0);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 0(%0);" ++ : "+&r" (tmp), "+&r" (f1), "+&r" (out), "+&r" (f2) ++ : ++ : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "memory", "cc" ++ ); + } + +-static void red_eltfp25519_1w_adx(u64 *const c, const u64 *const a) ++/* Computes two field multiplications: ++ * out[0] <- f1[0] * f2[0] ++ * out[1] <- f1[1] * f2[1] ++ * Uses the 16-element buffer tmp for intermediate results. */ ++static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) + { + asm volatile( +- "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ +- "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ +- "xorl %%ebx, %%ebx ;" +- "adox (%1), %%r8 ;" +- "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ +- "adcx %%r10, %%r9 ;" +- "adox 8(%1), %%r9 ;" +- "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ +- "adcx %%r11, %%r10 ;" +- "adox 16(%1), %%r10 ;" +- "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ +- "adcx %%rax, %%r11 ;" +- "adox 24(%1), %%r11 ;" +- /***************************************/ +- "adcx %%rbx, %%rcx ;" +- "adox %%rbx, %%rcx ;" +- "imul %%rdx, %%rcx ;" /* c*C[4], cf=0, of=0 */ +- "adcx %%rcx, %%r8 ;" +- "adcx %%rbx, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcx %%rbx, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcx %%rbx, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", +- "%r10", "%r11"); +-} ++ /* Compute the raw multiplication tmp[0] <- f1[0] * f2[0] */ + +-static void red_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) +-{ +- asm volatile( +- "movl $38, %%edx ;" /* 2*c = 38 = 2^256 */ +- "mulx 32(%1), %%r8, %%r10 ;" /* c*C[4] */ +- "mulx 40(%1), %%r9, %%r11 ;" /* c*C[5] */ +- "addq %%r10, %%r9 ;" +- "mulx 48(%1), %%r10, %%rax ;" /* c*C[6] */ +- "adcq %%r11, %%r10 ;" +- "mulx 56(%1), %%r11, %%rcx ;" /* c*C[7] */ +- "adcq %%rax, %%r11 ;" +- /***************************************/ +- "adcq $0, %%rcx ;" +- "addq (%1), %%r8 ;" +- "adcq 8(%1), %%r9 ;" +- "adcq 16(%1), %%r10 ;" +- "adcq 24(%1), %%r11 ;" +- "adcq $0, %%rcx ;" +- "imul %%rdx, %%rcx ;" /* c*C[4], cf=0 */ +- "addq %%rcx, %%r8 ;" +- "adcq $0, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcq $0, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcq $0, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- : +- : "r"(c), "r"(a) +- : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", +- "%r11"); ++ /* Compute src1[0] * src2 */ ++ " movq 0(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" ++ /* Compute src1[1] * src2 */ ++ " movq 8(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 16(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" ++ /* Compute src1[2] * src2 */ ++ " movq 16(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 24(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" ++ /* Compute src1[3] * src2 */ ++ " movq 24(%1), %%rdx;" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 32(%0);" ++ " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " movq %%r12, 40(%0);" " mov $0, %%r8;" ++ " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%0);" ++ ++ /* Compute the raw multiplication tmp[1] <- f1[1] * f2[1] */ ++ ++ /* Compute src1[0] * src2 */ ++ " movq 32(%1), %%rdx;" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 64(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" ++ " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" ++ " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" ++ /* Compute src1[1] * src2 */ ++ " movq 40(%1), %%rdx;" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 80(%0);" ++ " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" ++ /* Compute src1[2] * src2 */ ++ " movq 48(%1), %%rdx;" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 88(%0);" ++ " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" ++ /* Compute src1[3] * src2 */ ++ " movq 56(%1), %%rdx;" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 96(%0);" ++ " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " movq %%r12, 104(%0);" " mov $0, %%r8;" ++ " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%0);" " mov $0, %%rax;" ++ " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%0);" ++ /* Line up pointers */ ++ " mov %0, %1;" ++ " mov %2, %0;" ++ ++ /* Wrap the results back into the field */ ++ ++ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ ++ " mov $38, %%rdx;" ++ " mulxq 32(%1), %%r8, %%r13;" ++ " xor %3, %3;" ++ " adoxq 0(%1), %%r8;" ++ " mulxq 40(%1), %%r9, %%r12;" ++ " adcx %%r13, %%r9;" ++ " adoxq 8(%1), %%r9;" ++ " mulxq 48(%1), %%r10, %%r13;" ++ " adcx %%r12, %%r10;" ++ " adoxq 16(%1), %%r10;" ++ " mulxq 56(%1), %%r11, %%rax;" ++ " adcx %%r13, %%r11;" ++ " adoxq 24(%1), %%r11;" ++ " adcx %3, %%rax;" ++ " adox %3, %%rax;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %3, %%r9;" ++ " movq %%r9, 8(%0);" ++ " adcx %3, %%r10;" ++ " movq %%r10, 16(%0);" ++ " adcx %3, %%r11;" ++ " movq %%r11, 24(%0);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 0(%0);" ++ ++ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ ++ " mov $38, %%rdx;" ++ " mulxq 96(%1), %%r8, %%r13;" ++ " xor %3, %3;" ++ " adoxq 64(%1), %%r8;" ++ " mulxq 104(%1), %%r9, %%r12;" ++ " adcx %%r13, %%r9;" ++ " adoxq 72(%1), %%r9;" ++ " mulxq 112(%1), %%r10, %%r13;" ++ " adcx %%r12, %%r10;" ++ " adoxq 80(%1), %%r10;" ++ " mulxq 120(%1), %%r11, %%rax;" ++ " adcx %%r13, %%r11;" ++ " adoxq 88(%1), %%r11;" ++ " adcx %3, %%rax;" ++ " adox %3, %%rax;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %3, %%r9;" ++ " movq %%r9, 40(%0);" ++ " adcx %3, %%r10;" ++ " movq %%r10, 48(%0);" ++ " adcx %3, %%r11;" ++ " movq %%r11, 56(%0);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 32(%0);" ++ : "+&r" (tmp), "+&r" (f1), "+&r" (out), "+&r" (f2) ++ : ++ : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "memory", "cc" ++ ); + } + +-static __always_inline void +-add_eltfp25519_1w_adx(u64 *const c, const u64 *const a, const u64 *const b) ++/* Computes the field multiplication of four-element f1 with value in f2 */ ++static inline void fmul_scalar(u64 *out, const u64 *f1, u64 f2) + { +- asm volatile( +- "mov $38, %%eax ;" +- "xorl %%ecx, %%ecx ;" +- "movq (%2), %%r8 ;" +- "adcx (%1), %%r8 ;" +- "movq 8(%2), %%r9 ;" +- "adcx 8(%1), %%r9 ;" +- "movq 16(%2), %%r10 ;" +- "adcx 16(%1), %%r10 ;" +- "movq 24(%2), %%r11 ;" +- "adcx 24(%1), %%r11 ;" +- "cmovc %%eax, %%ecx ;" +- "xorl %%eax, %%eax ;" +- "adcx %%rcx, %%r8 ;" +- "adcx %%rax, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcx %%rax, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcx %%rax, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $38, %%ecx ;" +- "cmovc %%ecx, %%eax ;" +- "addq %%rax, %%r8 ;" +- "movq %%r8, (%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); +-} ++ register u64 f2_r asm("rdx") = f2; + +-static __always_inline void +-add_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a, const u64 *const b) +-{ + asm volatile( +- "mov $38, %%eax ;" +- "movq (%2), %%r8 ;" +- "addq (%1), %%r8 ;" +- "movq 8(%2), %%r9 ;" +- "adcq 8(%1), %%r9 ;" +- "movq 16(%2), %%r10 ;" +- "adcq 16(%1), %%r10 ;" +- "movq 24(%2), %%r11 ;" +- "adcq 24(%1), %%r11 ;" +- "mov $0, %%ecx ;" +- "cmovc %%eax, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "adcq $0, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcq $0, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcq $0, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%eax, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); ++ /* Compute the raw multiplication of f1*f2 */ ++ " mulxq 0(%2), %%r8, %%rcx;" /* f1[0]*f2 */ ++ " mulxq 8(%2), %%r9, %%r12;" /* f1[1]*f2 */ ++ " add %%rcx, %%r9;" ++ " mov $0, %%rcx;" ++ " mulxq 16(%2), %%r10, %%r13;" /* f1[2]*f2 */ ++ " adcx %%r12, %%r10;" ++ " mulxq 24(%2), %%r11, %%rax;" /* f1[3]*f2 */ ++ " adcx %%r13, %%r11;" ++ " adcx %%rcx, %%rax;" ++ ++ /* Wrap the result back into the field */ ++ ++ /* Step 1: Compute carry*38 */ ++ " mov $38, %%rdx;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %%rcx, %%r9;" ++ " movq %%r9, 8(%1);" ++ " adcx %%rcx, %%r10;" ++ " movq %%r10, 16(%1);" ++ " adcx %%rcx, %%r11;" ++ " movq %%r11, 24(%1);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 0(%1);" ++ : "+&r" (f2_r) ++ : "r" (out), "r" (f1) ++ : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "memory", "cc" ++ ); + } + +-static __always_inline void +-sub_eltfp25519_1w(u64 *const c, const u64 *const a, const u64 *const b) +-{ +- asm volatile( +- "mov $38, %%eax ;" +- "movq (%1), %%r8 ;" +- "subq (%2), %%r8 ;" +- "movq 8(%1), %%r9 ;" +- "sbbq 8(%2), %%r9 ;" +- "movq 16(%1), %%r10 ;" +- "sbbq 16(%2), %%r10 ;" +- "movq 24(%1), %%r11 ;" +- "sbbq 24(%2), %%r11 ;" +- "mov $0, %%ecx ;" +- "cmovc %%eax, %%ecx ;" +- "subq %%rcx, %%r8 ;" +- "sbbq $0, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "sbbq $0, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "sbbq $0, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%eax, %%ecx ;" +- "subq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- : +- : "r"(c), "r"(a), "r"(b) +- : "memory", "cc", "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11"); +-} +- +-/* Multiplication by a24 = (A+2)/4 = (486662+2)/4 = 121666 */ +-static __always_inline void +-mul_a24_eltfp25519_1w(u64 *const c, const u64 *const a) ++/* Computes p1 <- bit ? p2 : p1 in constant time */ ++static inline void cswap2(u64 bit, const u64 *p1, const u64 *p2) + { +- const u64 a24 = 121666; + asm volatile( +- "movq %2, %%rdx ;" +- "mulx (%1), %%r8, %%r10 ;" +- "mulx 8(%1), %%r9, %%r11 ;" +- "addq %%r10, %%r9 ;" +- "mulx 16(%1), %%r10, %%rax ;" +- "adcq %%r11, %%r10 ;" +- "mulx 24(%1), %%r11, %%rcx ;" +- "adcq %%rax, %%r11 ;" +- /**************************/ +- "adcq $0, %%rcx ;" +- "movl $38, %%edx ;" /* 2*c = 38 = 2^256 mod 2^255-19*/ +- "imul %%rdx, %%rcx ;" +- "addq %%rcx, %%r8 ;" +- "adcq $0, %%r9 ;" +- "movq %%r9, 8(%0) ;" +- "adcq $0, %%r10 ;" +- "movq %%r10, 16(%0) ;" +- "adcq $0, %%r11 ;" +- "movq %%r11, 24(%0) ;" +- "mov $0, %%ecx ;" +- "cmovc %%edx, %%ecx ;" +- "addq %%rcx, %%r8 ;" +- "movq %%r8, (%0) ;" +- : +- : "r"(c), "r"(a), "r"(a24) +- : "memory", "cc", "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", +- "%r11"); +-} +- +-static void inv_eltfp25519_1w_adx(u64 *const c, const u64 *const a) +-{ +- struct { +- eltfp25519_1w_buffer buffer; +- eltfp25519_1w x0, x1, x2; +- } __aligned(32) m; +- u64 *T[4]; +- +- T[0] = m.x0; +- T[1] = c; /* x^(-1) */ +- T[2] = m.x1; +- T[3] = m.x2; +- +- copy_eltfp25519_1w(T[1], a); +- sqrn_eltfp25519_1w_adx(T[1], 1); +- copy_eltfp25519_1w(T[2], T[1]); +- sqrn_eltfp25519_1w_adx(T[2], 2); +- mul_eltfp25519_1w_adx(T[0], a, T[2]); +- mul_eltfp25519_1w_adx(T[1], T[1], T[0]); +- copy_eltfp25519_1w(T[2], T[1]); +- sqrn_eltfp25519_1w_adx(T[2], 1); +- mul_eltfp25519_1w_adx(T[0], T[0], T[2]); +- copy_eltfp25519_1w(T[2], T[0]); +- sqrn_eltfp25519_1w_adx(T[2], 5); +- mul_eltfp25519_1w_adx(T[0], T[0], T[2]); +- copy_eltfp25519_1w(T[2], T[0]); +- sqrn_eltfp25519_1w_adx(T[2], 10); +- mul_eltfp25519_1w_adx(T[2], T[2], T[0]); +- copy_eltfp25519_1w(T[3], T[2]); +- sqrn_eltfp25519_1w_adx(T[3], 20); +- mul_eltfp25519_1w_adx(T[3], T[3], T[2]); +- sqrn_eltfp25519_1w_adx(T[3], 10); +- mul_eltfp25519_1w_adx(T[3], T[3], T[0]); +- copy_eltfp25519_1w(T[0], T[3]); +- sqrn_eltfp25519_1w_adx(T[0], 50); +- mul_eltfp25519_1w_adx(T[0], T[0], T[3]); +- copy_eltfp25519_1w(T[2], T[0]); +- sqrn_eltfp25519_1w_adx(T[2], 100); +- mul_eltfp25519_1w_adx(T[2], T[2], T[0]); +- sqrn_eltfp25519_1w_adx(T[2], 50); +- mul_eltfp25519_1w_adx(T[2], T[2], T[3]); +- sqrn_eltfp25519_1w_adx(T[2], 5); +- mul_eltfp25519_1w_adx(T[1], T[1], T[2]); +- +- memzero_explicit(&m, sizeof(m)); +-} +- +-static void inv_eltfp25519_1w_bmi2(u64 *const c, const u64 *const a) +-{ +- struct { +- eltfp25519_1w_buffer buffer; +- eltfp25519_1w x0, x1, x2; +- } __aligned(32) m; +- u64 *T[5]; +- +- T[0] = m.x0; +- T[1] = c; /* x^(-1) */ +- T[2] = m.x1; +- T[3] = m.x2; +- +- copy_eltfp25519_1w(T[1], a); +- sqrn_eltfp25519_1w_bmi2(T[1], 1); +- copy_eltfp25519_1w(T[2], T[1]); +- sqrn_eltfp25519_1w_bmi2(T[2], 2); +- mul_eltfp25519_1w_bmi2(T[0], a, T[2]); +- mul_eltfp25519_1w_bmi2(T[1], T[1], T[0]); +- copy_eltfp25519_1w(T[2], T[1]); +- sqrn_eltfp25519_1w_bmi2(T[2], 1); +- mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); +- copy_eltfp25519_1w(T[2], T[0]); +- sqrn_eltfp25519_1w_bmi2(T[2], 5); +- mul_eltfp25519_1w_bmi2(T[0], T[0], T[2]); +- copy_eltfp25519_1w(T[2], T[0]); +- sqrn_eltfp25519_1w_bmi2(T[2], 10); +- mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); +- copy_eltfp25519_1w(T[3], T[2]); +- sqrn_eltfp25519_1w_bmi2(T[3], 20); +- mul_eltfp25519_1w_bmi2(T[3], T[3], T[2]); +- sqrn_eltfp25519_1w_bmi2(T[3], 10); +- mul_eltfp25519_1w_bmi2(T[3], T[3], T[0]); +- copy_eltfp25519_1w(T[0], T[3]); +- sqrn_eltfp25519_1w_bmi2(T[0], 50); +- mul_eltfp25519_1w_bmi2(T[0], T[0], T[3]); +- copy_eltfp25519_1w(T[2], T[0]); +- sqrn_eltfp25519_1w_bmi2(T[2], 100); +- mul_eltfp25519_1w_bmi2(T[2], T[2], T[0]); +- sqrn_eltfp25519_1w_bmi2(T[2], 50); +- mul_eltfp25519_1w_bmi2(T[2], T[2], T[3]); +- sqrn_eltfp25519_1w_bmi2(T[2], 5); +- mul_eltfp25519_1w_bmi2(T[1], T[1], T[2]); ++ /* Invert the polarity of bit to match cmov expectations */ ++ " add $18446744073709551615, %0;" + +- memzero_explicit(&m, sizeof(m)); ++ /* cswap p1[0], p2[0] */ ++ " movq 0(%1), %%r8;" ++ " movq 0(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 0(%1);" ++ " movq %%r9, 0(%2);" ++ ++ /* cswap p1[1], p2[1] */ ++ " movq 8(%1), %%r8;" ++ " movq 8(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 8(%1);" ++ " movq %%r9, 8(%2);" ++ ++ /* cswap p1[2], p2[2] */ ++ " movq 16(%1), %%r8;" ++ " movq 16(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 16(%1);" ++ " movq %%r9, 16(%2);" ++ ++ /* cswap p1[3], p2[3] */ ++ " movq 24(%1), %%r8;" ++ " movq 24(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 24(%1);" ++ " movq %%r9, 24(%2);" ++ ++ /* cswap p1[4], p2[4] */ ++ " movq 32(%1), %%r8;" ++ " movq 32(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 32(%1);" ++ " movq %%r9, 32(%2);" ++ ++ /* cswap p1[5], p2[5] */ ++ " movq 40(%1), %%r8;" ++ " movq 40(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 40(%1);" ++ " movq %%r9, 40(%2);" ++ ++ /* cswap p1[6], p2[6] */ ++ " movq 48(%1), %%r8;" ++ " movq 48(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 48(%1);" ++ " movq %%r9, 48(%2);" ++ ++ /* cswap p1[7], p2[7] */ ++ " movq 56(%1), %%r8;" ++ " movq 56(%2), %%r9;" ++ " mov %%r8, %%r10;" ++ " cmovc %%r9, %%r8;" ++ " cmovc %%r10, %%r9;" ++ " movq %%r8, 56(%1);" ++ " movq %%r9, 56(%2);" ++ : "+&r" (bit) ++ : "r" (p1), "r" (p2) ++ : "%r8", "%r9", "%r10", "memory", "cc" ++ ); + } + +-/* Given c, a 256-bit number, fred_eltfp25519_1w updates c +- * with a number such that 0 <= C < 2**255-19. +- */ +-static __always_inline void fred_eltfp25519_1w(u64 *const c) ++/* Computes the square of a field element: out <- f * f ++ * Uses the 8-element buffer tmp for intermediate results */ ++static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) + { +- u64 tmp0 = 38, tmp1 = 19; + asm volatile( +- "btrq $63, %3 ;" /* Put bit 255 in carry flag and clear */ +- "cmovncl %k5, %k4 ;" /* c[255] ? 38 : 19 */ +- +- /* Add either 19 or 38 to c */ +- "addq %4, %0 ;" +- "adcq $0, %1 ;" +- "adcq $0, %2 ;" +- "adcq $0, %3 ;" +- +- /* Test for bit 255 again; only triggered on overflow modulo 2^255-19 */ +- "movl $0, %k4 ;" +- "cmovnsl %k5, %k4 ;" /* c[255] ? 0 : 19 */ +- "btrq $63, %3 ;" /* Clear bit 255 */ +- +- /* Subtract 19 if necessary */ +- "subq %4, %0 ;" +- "sbbq $0, %1 ;" +- "sbbq $0, %2 ;" +- "sbbq $0, %3 ;" +- +- : "+r"(c[0]), "+r"(c[1]), "+r"(c[2]), "+r"(c[3]), "+r"(tmp0), +- "+r"(tmp1) +- : +- : "memory", "cc"); +-} ++ /* Compute the raw multiplication: tmp <- f * f */ + +-static __always_inline void cswap(u8 bit, u64 *const px, u64 *const py) +-{ +- u64 temp; +- asm volatile( +- "test %9, %9 ;" +- "movq %0, %8 ;" +- "cmovnzq %4, %0 ;" +- "cmovnzq %8, %4 ;" +- "movq %1, %8 ;" +- "cmovnzq %5, %1 ;" +- "cmovnzq %8, %5 ;" +- "movq %2, %8 ;" +- "cmovnzq %6, %2 ;" +- "cmovnzq %8, %6 ;" +- "movq %3, %8 ;" +- "cmovnzq %7, %3 ;" +- "cmovnzq %8, %7 ;" +- : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]), +- "+r"(py[0]), "+r"(py[1]), "+r"(py[2]), "+r"(py[3]), +- "=r"(temp) +- : "r"(bit) +- : "cc" ++ /* Step 1: Compute all partial products */ ++ " movq 0(%1), %%rdx;" /* f[0] */ ++ " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ ++ " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ ++ " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ ++ " movq 24(%1), %%rdx;" /* f[3] */ ++ " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ ++ " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */ ++ " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ ++ " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ ++ ++ /* Step 2: Compute two parallel carry chains */ ++ " xor %%r15, %%r15;" ++ " adox %%rax, %%r10;" ++ " adcx %%r8, %%r8;" ++ " adox %%rcx, %%r11;" ++ " adcx %%r9, %%r9;" ++ " adox %%r15, %%r12;" ++ " adcx %%r10, %%r10;" ++ " adox %%r15, %%r13;" ++ " adcx %%r11, %%r11;" ++ " adox %%r15, %%r14;" ++ " adcx %%r12, %%r12;" ++ " adcx %%r13, %%r13;" ++ " adcx %%r14, %%r14;" ++ ++ /* Step 3: Compute intermediate squares */ ++ " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ ++ " movq %%rax, 0(%0);" ++ " add %%rcx, %%r8;" " movq %%r8, 8(%0);" ++ " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ ++ " adcx %%rax, %%r9;" " movq %%r9, 16(%0);" ++ " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);" ++ " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ ++ " adcx %%rax, %%r11;" " movq %%r11, 32(%0);" ++ " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);" ++ " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ ++ " adcx %%rax, %%r13;" " movq %%r13, 48(%0);" ++ " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);" ++ ++ /* Line up pointers */ ++ " mov %0, %1;" ++ " mov %2, %0;" ++ ++ /* Wrap the result back into the field */ ++ ++ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ ++ " mov $38, %%rdx;" ++ " mulxq 32(%1), %%r8, %%r13;" ++ " xor %%rcx, %%rcx;" ++ " adoxq 0(%1), %%r8;" ++ " mulxq 40(%1), %%r9, %%r12;" ++ " adcx %%r13, %%r9;" ++ " adoxq 8(%1), %%r9;" ++ " mulxq 48(%1), %%r10, %%r13;" ++ " adcx %%r12, %%r10;" ++ " adoxq 16(%1), %%r10;" ++ " mulxq 56(%1), %%r11, %%rax;" ++ " adcx %%r13, %%r11;" ++ " adoxq 24(%1), %%r11;" ++ " adcx %%rcx, %%rax;" ++ " adox %%rcx, %%rax;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %%rcx, %%r9;" ++ " movq %%r9, 8(%0);" ++ " adcx %%rcx, %%r10;" ++ " movq %%r10, 16(%0);" ++ " adcx %%rcx, %%r11;" ++ " movq %%r11, 24(%0);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 0(%0);" ++ : "+&r" (tmp), "+&r" (f), "+&r" (out) ++ : ++ : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc" + ); + } + +-static __always_inline void cselect(u8 bit, u64 *const px, const u64 *const py) ++/* Computes two field squarings: ++ * out[0] <- f[0] * f[0] ++ * out[1] <- f[1] * f[1] ++ * Uses the 16-element buffer tmp for intermediate results */ ++static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) + { + asm volatile( +- "test %4, %4 ;" +- "cmovnzq %5, %0 ;" +- "cmovnzq %6, %1 ;" +- "cmovnzq %7, %2 ;" +- "cmovnzq %8, %3 ;" +- : "+r"(px[0]), "+r"(px[1]), "+r"(px[2]), "+r"(px[3]) +- : "r"(bit), "rm"(py[0]), "rm"(py[1]), "rm"(py[2]), "rm"(py[3]) +- : "cc" ++ /* Step 1: Compute all partial products */ ++ " movq 0(%1), %%rdx;" /* f[0] */ ++ " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ ++ " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ ++ " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ ++ " movq 24(%1), %%rdx;" /* f[3] */ ++ " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ ++ " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */ ++ " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ ++ " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ ++ ++ /* Step 2: Compute two parallel carry chains */ ++ " xor %%r15, %%r15;" ++ " adox %%rax, %%r10;" ++ " adcx %%r8, %%r8;" ++ " adox %%rcx, %%r11;" ++ " adcx %%r9, %%r9;" ++ " adox %%r15, %%r12;" ++ " adcx %%r10, %%r10;" ++ " adox %%r15, %%r13;" ++ " adcx %%r11, %%r11;" ++ " adox %%r15, %%r14;" ++ " adcx %%r12, %%r12;" ++ " adcx %%r13, %%r13;" ++ " adcx %%r14, %%r14;" ++ ++ /* Step 3: Compute intermediate squares */ ++ " movq 0(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ ++ " movq %%rax, 0(%0);" ++ " add %%rcx, %%r8;" " movq %%r8, 8(%0);" ++ " movq 8(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ ++ " adcx %%rax, %%r9;" " movq %%r9, 16(%0);" ++ " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);" ++ " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ ++ " adcx %%rax, %%r11;" " movq %%r11, 32(%0);" ++ " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);" ++ " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ ++ " adcx %%rax, %%r13;" " movq %%r13, 48(%0);" ++ " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);" ++ ++ /* Step 1: Compute all partial products */ ++ " movq 32(%1), %%rdx;" /* f[0] */ ++ " mulxq 40(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ ++ " mulxq 48(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ ++ " mulxq 56(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ ++ " movq 56(%1), %%rdx;" /* f[3] */ ++ " mulxq 40(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ ++ " mulxq 48(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */ ++ " movq 40(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ ++ " mulxq 48(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ ++ ++ /* Step 2: Compute two parallel carry chains */ ++ " xor %%r15, %%r15;" ++ " adox %%rax, %%r10;" ++ " adcx %%r8, %%r8;" ++ " adox %%rcx, %%r11;" ++ " adcx %%r9, %%r9;" ++ " adox %%r15, %%r12;" ++ " adcx %%r10, %%r10;" ++ " adox %%r15, %%r13;" ++ " adcx %%r11, %%r11;" ++ " adox %%r15, %%r14;" ++ " adcx %%r12, %%r12;" ++ " adcx %%r13, %%r13;" ++ " adcx %%r14, %%r14;" ++ ++ /* Step 3: Compute intermediate squares */ ++ " movq 32(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ ++ " movq %%rax, 64(%0);" ++ " add %%rcx, %%r8;" " movq %%r8, 72(%0);" ++ " movq 40(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ ++ " adcx %%rax, %%r9;" " movq %%r9, 80(%0);" ++ " adcx %%rcx, %%r10;" " movq %%r10, 88(%0);" ++ " movq 48(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ ++ " adcx %%rax, %%r11;" " movq %%r11, 96(%0);" ++ " adcx %%rcx, %%r12;" " movq %%r12, 104(%0);" ++ " movq 56(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ ++ " adcx %%rax, %%r13;" " movq %%r13, 112(%0);" ++ " adcx %%rcx, %%r14;" " movq %%r14, 120(%0);" ++ ++ /* Line up pointers */ ++ " mov %0, %1;" ++ " mov %2, %0;" ++ ++ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ ++ " mov $38, %%rdx;" ++ " mulxq 32(%1), %%r8, %%r13;" ++ " xor %%rcx, %%rcx;" ++ " adoxq 0(%1), %%r8;" ++ " mulxq 40(%1), %%r9, %%r12;" ++ " adcx %%r13, %%r9;" ++ " adoxq 8(%1), %%r9;" ++ " mulxq 48(%1), %%r10, %%r13;" ++ " adcx %%r12, %%r10;" ++ " adoxq 16(%1), %%r10;" ++ " mulxq 56(%1), %%r11, %%rax;" ++ " adcx %%r13, %%r11;" ++ " adoxq 24(%1), %%r11;" ++ " adcx %%rcx, %%rax;" ++ " adox %%rcx, %%rax;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %%rcx, %%r9;" ++ " movq %%r9, 8(%0);" ++ " adcx %%rcx, %%r10;" ++ " movq %%r10, 16(%0);" ++ " adcx %%rcx, %%r11;" ++ " movq %%r11, 24(%0);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 0(%0);" ++ ++ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ ++ " mov $38, %%rdx;" ++ " mulxq 96(%1), %%r8, %%r13;" ++ " xor %%rcx, %%rcx;" ++ " adoxq 64(%1), %%r8;" ++ " mulxq 104(%1), %%r9, %%r12;" ++ " adcx %%r13, %%r9;" ++ " adoxq 72(%1), %%r9;" ++ " mulxq 112(%1), %%r10, %%r13;" ++ " adcx %%r12, %%r10;" ++ " adoxq 80(%1), %%r10;" ++ " mulxq 120(%1), %%r11, %%rax;" ++ " adcx %%r13, %%r11;" ++ " adoxq 88(%1), %%r11;" ++ " adcx %%rcx, %%rax;" ++ " adox %%rcx, %%rax;" ++ " imul %%rdx, %%rax;" ++ ++ /* Step 2: Fold the carry back into dst */ ++ " add %%rax, %%r8;" ++ " adcx %%rcx, %%r9;" ++ " movq %%r9, 40(%0);" ++ " adcx %%rcx, %%r10;" ++ " movq %%r10, 48(%0);" ++ " adcx %%rcx, %%r11;" ++ " movq %%r11, 56(%0);" ++ ++ /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ ++ " mov $0, %%rax;" ++ " cmovc %%rdx, %%rax;" ++ " add %%rax, %%r8;" ++ " movq %%r8, 32(%0);" ++ : "+&r" (tmp), "+&r" (f), "+&r" (out) ++ : ++ : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc" + ); + } + +-static void curve25519_adx(u8 shared[CURVE25519_KEY_SIZE], +- const u8 private_key[CURVE25519_KEY_SIZE], +- const u8 session_key[CURVE25519_KEY_SIZE]) +-{ +- struct { +- u64 buffer[4 * NUM_WORDS_ELTFP25519]; +- u64 coordinates[4 * NUM_WORDS_ELTFP25519]; +- u64 workspace[6 * NUM_WORDS_ELTFP25519]; +- u8 session[CURVE25519_KEY_SIZE]; +- u8 private[CURVE25519_KEY_SIZE]; +- } __aligned(32) m; +- +- int i = 0, j = 0; +- u64 prev = 0; +- u64 *const X1 = (u64 *)m.session; +- u64 *const key = (u64 *)m.private; +- u64 *const Px = m.coordinates + 0; +- u64 *const Pz = m.coordinates + 4; +- u64 *const Qx = m.coordinates + 8; +- u64 *const Qz = m.coordinates + 12; +- u64 *const X2 = Qx; +- u64 *const Z2 = Qz; +- u64 *const X3 = Px; +- u64 *const Z3 = Pz; +- u64 *const X2Z2 = Qx; +- u64 *const X3Z3 = Px; +- +- u64 *const A = m.workspace + 0; +- u64 *const B = m.workspace + 4; +- u64 *const D = m.workspace + 8; +- u64 *const C = m.workspace + 12; +- u64 *const DA = m.workspace + 16; +- u64 *const CB = m.workspace + 20; +- u64 *const AB = A; +- u64 *const DC = D; +- u64 *const DACB = DA; +- +- memcpy(m.private, private_key, sizeof(m.private)); +- memcpy(m.session, session_key, sizeof(m.session)); +- +- curve25519_clamp_secret(m.private); +- +- /* As in the draft: +- * When receiving such an array, implementations of curve25519 +- * MUST mask the most-significant bit in the final byte. This +- * is done to preserve compatibility with point formats which +- * reserve the sign bit for use in other protocols and to +- * increase resistance to implementation fingerprinting +- */ +- m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; +- +- copy_eltfp25519_1w(Px, X1); +- setzero_eltfp25519_1w(Pz); +- setzero_eltfp25519_1w(Qx); +- setzero_eltfp25519_1w(Qz); +- +- Pz[0] = 1; +- Qx[0] = 1; +- +- /* main-loop */ +- prev = 0; +- j = 62; +- for (i = 3; i >= 0; --i) { +- while (j >= 0) { +- u64 bit = (key[i] >> j) & 0x1; +- u64 swap = bit ^ prev; +- prev = bit; +- +- add_eltfp25519_1w_adx(A, X2, Z2); /* A = (X2+Z2) */ +- sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ +- add_eltfp25519_1w_adx(C, X3, Z3); /* C = (X3+Z3) */ +- sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ +- mul_eltfp25519_2w_adx(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ +- +- cselect(swap, A, C); +- cselect(swap, B, D); +- +- sqr_eltfp25519_2w_adx(AB); /* [AA|BB] = [A^2|B^2] */ +- add_eltfp25519_1w_adx(X3, DA, CB); /* X3 = (DA+CB) */ +- sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ +- sqr_eltfp25519_2w_adx(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ +- +- copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ +- sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ +- +- mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ +- add_eltfp25519_1w_adx(B, B, X2); /* B = a24*E+B */ +- mul_eltfp25519_2w_adx(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ +- mul_eltfp25519_1w_adx(Z3, Z3, X1); /* Z3 = Z3*X1 */ +- --j; +- } +- j = 63; +- } +- +- inv_eltfp25519_1w_adx(A, Qz); +- mul_eltfp25519_1w_adx((u64 *)shared, Qx, A); +- fred_eltfp25519_1w((u64 *)shared); +- +- memzero_explicit(&m, sizeof(m)); +-} +- +-static void curve25519_adx_base(u8 session_key[CURVE25519_KEY_SIZE], +- const u8 private_key[CURVE25519_KEY_SIZE]) ++static void point_add_and_double(u64 *q, u64 *p01_tmp1, u64 *tmp2) + { +- struct { +- u64 buffer[4 * NUM_WORDS_ELTFP25519]; +- u64 coordinates[4 * NUM_WORDS_ELTFP25519]; +- u64 workspace[4 * NUM_WORDS_ELTFP25519]; +- u8 private[CURVE25519_KEY_SIZE]; +- } __aligned(32) m; +- +- const int ite[4] = { 64, 64, 64, 63 }; +- const int q = 3; +- u64 swap = 1; +- +- int i = 0, j = 0, k = 0; +- u64 *const key = (u64 *)m.private; +- u64 *const Ur1 = m.coordinates + 0; +- u64 *const Zr1 = m.coordinates + 4; +- u64 *const Ur2 = m.coordinates + 8; +- u64 *const Zr2 = m.coordinates + 12; +- +- u64 *const UZr1 = m.coordinates + 0; +- u64 *const ZUr2 = m.coordinates + 8; +- +- u64 *const A = m.workspace + 0; +- u64 *const B = m.workspace + 4; +- u64 *const C = m.workspace + 8; +- u64 *const D = m.workspace + 12; +- +- u64 *const AB = m.workspace + 0; +- u64 *const CD = m.workspace + 8; +- +- const u64 *const P = table_ladder_8k; +- +- memcpy(m.private, private_key, sizeof(m.private)); +- +- curve25519_clamp_secret(m.private); +- +- setzero_eltfp25519_1w(Ur1); +- setzero_eltfp25519_1w(Zr1); +- setzero_eltfp25519_1w(Zr2); +- Ur1[0] = 1; +- Zr1[0] = 1; +- Zr2[0] = 1; +- +- /* G-S */ +- Ur2[3] = 0x1eaecdeee27cab34UL; +- Ur2[2] = 0xadc7a0b9235d48e2UL; +- Ur2[1] = 0xbbf095ae14b2edf8UL; +- Ur2[0] = 0x7e94e1fec82faabdUL; +- +- /* main-loop */ +- j = q; +- for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { +- while (j < ite[i]) { +- u64 bit = (key[i] >> j) & 0x1; +- k = (64 * i + j - q); +- swap = swap ^ bit; +- cswap(swap, Ur1, Ur2); +- cswap(swap, Zr1, Zr2); +- swap = bit; +- /* Addition */ +- sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ +- add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ +- mul_eltfp25519_1w_adx(C, &P[4 * k], B); /* C = M0-B */ +- sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ +- add_eltfp25519_1w_adx(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ +- sqr_eltfp25519_2w_adx(AB); /* A = A^2 | B = B^2 */ +- mul_eltfp25519_2w_adx(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ +- ++j; ++ u64 *nq = p01_tmp1; ++ u64 *nq_p1 = p01_tmp1 + (u32)8U; ++ u64 *tmp1 = p01_tmp1 + (u32)16U; ++ u64 *x1 = q; ++ u64 *x2 = nq; ++ u64 *z2 = nq + (u32)4U; ++ u64 *z3 = nq_p1 + (u32)4U; ++ u64 *a = tmp1; ++ u64 *b = tmp1 + (u32)4U; ++ u64 *ab = tmp1; ++ u64 *dc = tmp1 + (u32)8U; ++ u64 *x3; ++ u64 *z31; ++ u64 *d0; ++ u64 *c0; ++ u64 *a1; ++ u64 *b1; ++ u64 *d; ++ u64 *c; ++ u64 *ab1; ++ u64 *dc1; ++ fadd(a, x2, z2); ++ fsub(b, x2, z2); ++ x3 = nq_p1; ++ z31 = nq_p1 + (u32)4U; ++ d0 = dc; ++ c0 = dc + (u32)4U; ++ fadd(c0, x3, z31); ++ fsub(d0, x3, z31); ++ fmul2(dc, dc, ab, tmp2); ++ fadd(x3, d0, c0); ++ fsub(z31, d0, c0); ++ a1 = tmp1; ++ b1 = tmp1 + (u32)4U; ++ d = tmp1 + (u32)8U; ++ c = tmp1 + (u32)12U; ++ ab1 = tmp1; ++ dc1 = tmp1 + (u32)8U; ++ fsqr2(dc1, ab1, tmp2); ++ fsqr2(nq_p1, nq_p1, tmp2); ++ a1[0U] = c[0U]; ++ a1[1U] = c[1U]; ++ a1[2U] = c[2U]; ++ a1[3U] = c[3U]; ++ fsub(c, d, c); ++ fmul_scalar(b1, c, (u64)121665U); ++ fadd(b1, b1, d); ++ fmul2(nq, dc1, ab1, tmp2); ++ fmul(z3, z3, x1, tmp2); ++} ++ ++static void point_double(u64 *nq, u64 *tmp1, u64 *tmp2) ++{ ++ u64 *x2 = nq; ++ u64 *z2 = nq + (u32)4U; ++ u64 *a = tmp1; ++ u64 *b = tmp1 + (u32)4U; ++ u64 *d = tmp1 + (u32)8U; ++ u64 *c = tmp1 + (u32)12U; ++ u64 *ab = tmp1; ++ u64 *dc = tmp1 + (u32)8U; ++ fadd(a, x2, z2); ++ fsub(b, x2, z2); ++ fsqr2(dc, ab, tmp2); ++ a[0U] = c[0U]; ++ a[1U] = c[1U]; ++ a[2U] = c[2U]; ++ a[3U] = c[3U]; ++ fsub(c, d, c); ++ fmul_scalar(b, c, (u64)121665U); ++ fadd(b, b, d); ++ fmul2(nq, dc, ab, tmp2); ++} ++ ++static void montgomery_ladder(u64 *out, const u8 *key, u64 *init1) ++{ ++ u64 tmp2[16U] = { 0U }; ++ u64 p01_tmp1_swap[33U] = { 0U }; ++ u64 *p0 = p01_tmp1_swap; ++ u64 *p01 = p01_tmp1_swap; ++ u64 *p03 = p01; ++ u64 *p11 = p01 + (u32)8U; ++ u64 *x0; ++ u64 *z0; ++ u64 *p01_tmp1; ++ u64 *p01_tmp11; ++ u64 *nq10; ++ u64 *nq_p11; ++ u64 *swap1; ++ u64 sw0; ++ u64 *nq1; ++ u64 *tmp1; ++ memcpy(p11, init1, (u32)8U * sizeof(init1[0U])); ++ x0 = p03; ++ z0 = p03 + (u32)4U; ++ x0[0U] = (u64)1U; ++ x0[1U] = (u64)0U; ++ x0[2U] = (u64)0U; ++ x0[3U] = (u64)0U; ++ z0[0U] = (u64)0U; ++ z0[1U] = (u64)0U; ++ z0[2U] = (u64)0U; ++ z0[3U] = (u64)0U; ++ p01_tmp1 = p01_tmp1_swap; ++ p01_tmp11 = p01_tmp1_swap; ++ nq10 = p01_tmp1_swap; ++ nq_p11 = p01_tmp1_swap + (u32)8U; ++ swap1 = p01_tmp1_swap + (u32)32U; ++ cswap2((u64)1U, nq10, nq_p11); ++ point_add_and_double(init1, p01_tmp11, tmp2); ++ swap1[0U] = (u64)1U; ++ { ++ u32 i; ++ for (i = (u32)0U; i < (u32)251U; i = i + (u32)1U) { ++ u64 *p01_tmp12 = p01_tmp1_swap; ++ u64 *swap2 = p01_tmp1_swap + (u32)32U; ++ u64 *nq2 = p01_tmp12; ++ u64 *nq_p12 = p01_tmp12 + (u32)8U; ++ u64 bit = (u64)(key[((u32)253U - i) / (u32)8U] >> ((u32)253U - i) % (u32)8U & (u8)1U); ++ u64 sw = swap2[0U] ^ bit; ++ cswap2(sw, nq2, nq_p12); ++ point_add_and_double(init1, p01_tmp12, tmp2); ++ swap2[0U] = bit; + } +- j = 0; + } +- +- /* Doubling */ +- for (i = 0; i < q; ++i) { +- add_eltfp25519_1w_adx(A, Ur1, Zr1); /* A = Ur1+Zr1 */ +- sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ +- sqr_eltfp25519_2w_adx(AB); /* A = A**2 B = B**2 */ +- copy_eltfp25519_1w(C, B); /* C = B */ +- sub_eltfp25519_1w(B, A, B); /* B = A-B */ +- mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ +- add_eltfp25519_1w_adx(D, D, C); /* D = D+C */ +- mul_eltfp25519_2w_adx(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ +- } +- +- /* Convert to affine coordinates */ +- inv_eltfp25519_1w_adx(A, Zr1); +- mul_eltfp25519_1w_adx((u64 *)session_key, Ur1, A); +- fred_eltfp25519_1w((u64 *)session_key); +- +- memzero_explicit(&m, sizeof(m)); +-} +- +-static void curve25519_bmi2(u8 shared[CURVE25519_KEY_SIZE], +- const u8 private_key[CURVE25519_KEY_SIZE], +- const u8 session_key[CURVE25519_KEY_SIZE]) +-{ +- struct { +- u64 buffer[4 * NUM_WORDS_ELTFP25519]; +- u64 coordinates[4 * NUM_WORDS_ELTFP25519]; +- u64 workspace[6 * NUM_WORDS_ELTFP25519]; +- u8 session[CURVE25519_KEY_SIZE]; +- u8 private[CURVE25519_KEY_SIZE]; +- } __aligned(32) m; +- +- int i = 0, j = 0; +- u64 prev = 0; +- u64 *const X1 = (u64 *)m.session; +- u64 *const key = (u64 *)m.private; +- u64 *const Px = m.coordinates + 0; +- u64 *const Pz = m.coordinates + 4; +- u64 *const Qx = m.coordinates + 8; +- u64 *const Qz = m.coordinates + 12; +- u64 *const X2 = Qx; +- u64 *const Z2 = Qz; +- u64 *const X3 = Px; +- u64 *const Z3 = Pz; +- u64 *const X2Z2 = Qx; +- u64 *const X3Z3 = Px; +- +- u64 *const A = m.workspace + 0; +- u64 *const B = m.workspace + 4; +- u64 *const D = m.workspace + 8; +- u64 *const C = m.workspace + 12; +- u64 *const DA = m.workspace + 16; +- u64 *const CB = m.workspace + 20; +- u64 *const AB = A; +- u64 *const DC = D; +- u64 *const DACB = DA; +- +- memcpy(m.private, private_key, sizeof(m.private)); +- memcpy(m.session, session_key, sizeof(m.session)); +- +- curve25519_clamp_secret(m.private); +- +- /* As in the draft: +- * When receiving such an array, implementations of curve25519 +- * MUST mask the most-significant bit in the final byte. This +- * is done to preserve compatibility with point formats which +- * reserve the sign bit for use in other protocols and to +- * increase resistance to implementation fingerprinting +- */ +- m.session[CURVE25519_KEY_SIZE - 1] &= (1 << (255 % 8)) - 1; +- +- copy_eltfp25519_1w(Px, X1); +- setzero_eltfp25519_1w(Pz); +- setzero_eltfp25519_1w(Qx); +- setzero_eltfp25519_1w(Qz); +- +- Pz[0] = 1; +- Qx[0] = 1; +- +- /* main-loop */ +- prev = 0; +- j = 62; +- for (i = 3; i >= 0; --i) { +- while (j >= 0) { +- u64 bit = (key[i] >> j) & 0x1; +- u64 swap = bit ^ prev; +- prev = bit; +- +- add_eltfp25519_1w_bmi2(A, X2, Z2); /* A = (X2+Z2) */ +- sub_eltfp25519_1w(B, X2, Z2); /* B = (X2-Z2) */ +- add_eltfp25519_1w_bmi2(C, X3, Z3); /* C = (X3+Z3) */ +- sub_eltfp25519_1w(D, X3, Z3); /* D = (X3-Z3) */ +- mul_eltfp25519_2w_bmi2(DACB, AB, DC); /* [DA|CB] = [A|B]*[D|C] */ +- +- cselect(swap, A, C); +- cselect(swap, B, D); +- +- sqr_eltfp25519_2w_bmi2(AB); /* [AA|BB] = [A^2|B^2] */ +- add_eltfp25519_1w_bmi2(X3, DA, CB); /* X3 = (DA+CB) */ +- sub_eltfp25519_1w(Z3, DA, CB); /* Z3 = (DA-CB) */ +- sqr_eltfp25519_2w_bmi2(X3Z3); /* [X3|Z3] = [(DA+CB)|(DA+CB)]^2 */ +- +- copy_eltfp25519_1w(X2, B); /* X2 = B^2 */ +- sub_eltfp25519_1w(Z2, A, B); /* Z2 = E = AA-BB */ +- +- mul_a24_eltfp25519_1w(B, Z2); /* B = a24*E */ +- add_eltfp25519_1w_bmi2(B, B, X2); /* B = a24*E+B */ +- mul_eltfp25519_2w_bmi2(X2Z2, X2Z2, AB); /* [X2|Z2] = [B|E]*[A|a24*E+B] */ +- mul_eltfp25519_1w_bmi2(Z3, Z3, X1); /* Z3 = Z3*X1 */ +- --j; ++ sw0 = swap1[0U]; ++ cswap2(sw0, nq10, nq_p11); ++ nq1 = p01_tmp1; ++ tmp1 = p01_tmp1 + (u32)16U; ++ point_double(nq1, tmp1, tmp2); ++ point_double(nq1, tmp1, tmp2); ++ point_double(nq1, tmp1, tmp2); ++ memcpy(out, p0, (u32)8U * sizeof(p0[0U])); ++ ++ memzero_explicit(tmp2, sizeof(tmp2)); ++ memzero_explicit(p01_tmp1_swap, sizeof(p01_tmp1_swap)); ++} ++ ++static void fsquare_times(u64 *o, const u64 *inp, u64 *tmp, u32 n1) ++{ ++ u32 i; ++ fsqr(o, inp, tmp); ++ for (i = (u32)0U; i < n1 - (u32)1U; i = i + (u32)1U) ++ fsqr(o, o, tmp); ++} ++ ++static void finv(u64 *o, const u64 *i, u64 *tmp) ++{ ++ u64 t1[16U] = { 0U }; ++ u64 *a0 = t1; ++ u64 *b = t1 + (u32)4U; ++ u64 *c = t1 + (u32)8U; ++ u64 *t00 = t1 + (u32)12U; ++ u64 *tmp1 = tmp; ++ u64 *a; ++ u64 *t0; ++ fsquare_times(a0, i, tmp1, (u32)1U); ++ fsquare_times(t00, a0, tmp1, (u32)2U); ++ fmul(b, t00, i, tmp); ++ fmul(a0, b, a0, tmp); ++ fsquare_times(t00, a0, tmp1, (u32)1U); ++ fmul(b, t00, b, tmp); ++ fsquare_times(t00, b, tmp1, (u32)5U); ++ fmul(b, t00, b, tmp); ++ fsquare_times(t00, b, tmp1, (u32)10U); ++ fmul(c, t00, b, tmp); ++ fsquare_times(t00, c, tmp1, (u32)20U); ++ fmul(t00, t00, c, tmp); ++ fsquare_times(t00, t00, tmp1, (u32)10U); ++ fmul(b, t00, b, tmp); ++ fsquare_times(t00, b, tmp1, (u32)50U); ++ fmul(c, t00, b, tmp); ++ fsquare_times(t00, c, tmp1, (u32)100U); ++ fmul(t00, t00, c, tmp); ++ fsquare_times(t00, t00, tmp1, (u32)50U); ++ fmul(t00, t00, b, tmp); ++ fsquare_times(t00, t00, tmp1, (u32)5U); ++ a = t1; ++ t0 = t1 + (u32)12U; ++ fmul(o, t0, a, tmp); ++} ++ ++static void store_felem(u64 *b, u64 *f) ++{ ++ u64 f30 = f[3U]; ++ u64 top_bit0 = f30 >> (u32)63U; ++ u64 carry0; ++ u64 f31; ++ u64 top_bit; ++ u64 carry; ++ u64 f0; ++ u64 f1; ++ u64 f2; ++ u64 f3; ++ u64 m0; ++ u64 m1; ++ u64 m2; ++ u64 m3; ++ u64 mask; ++ u64 f0_; ++ u64 f1_; ++ u64 f2_; ++ u64 f3_; ++ u64 o0; ++ u64 o1; ++ u64 o2; ++ u64 o3; ++ f[3U] = f30 & (u64)0x7fffffffffffffffU; ++ carry0 = add_scalar(f, f, (u64)19U * top_bit0); ++ f31 = f[3U]; ++ top_bit = f31 >> (u32)63U; ++ f[3U] = f31 & (u64)0x7fffffffffffffffU; ++ carry = add_scalar(f, f, (u64)19U * top_bit); ++ f0 = f[0U]; ++ f1 = f[1U]; ++ f2 = f[2U]; ++ f3 = f[3U]; ++ m0 = gte_mask(f0, (u64)0xffffffffffffffedU); ++ m1 = eq_mask(f1, (u64)0xffffffffffffffffU); ++ m2 = eq_mask(f2, (u64)0xffffffffffffffffU); ++ m3 = eq_mask(f3, (u64)0x7fffffffffffffffU); ++ mask = ((m0 & m1) & m2) & m3; ++ f0_ = f0 - (mask & (u64)0xffffffffffffffedU); ++ f1_ = f1 - (mask & (u64)0xffffffffffffffffU); ++ f2_ = f2 - (mask & (u64)0xffffffffffffffffU); ++ f3_ = f3 - (mask & (u64)0x7fffffffffffffffU); ++ o0 = f0_; ++ o1 = f1_; ++ o2 = f2_; ++ o3 = f3_; ++ b[0U] = o0; ++ b[1U] = o1; ++ b[2U] = o2; ++ b[3U] = o3; ++} ++ ++static void encode_point(u8 *o, const u64 *i) ++{ ++ const u64 *x = i; ++ const u64 *z = i + (u32)4U; ++ u64 tmp[4U] = { 0U }; ++ u64 tmp_w[16U] = { 0U }; ++ finv(tmp, z, tmp_w); ++ fmul(tmp, tmp, x, tmp_w); ++ store_felem((u64 *)o, tmp); ++} ++ ++static void curve25519_ever64(u8 *out, const u8 *priv, const u8 *pub) ++{ ++ u64 init1[8U] = { 0U }; ++ u64 tmp[4U] = { 0U }; ++ u64 tmp3; ++ u64 *x; ++ u64 *z; ++ { ++ u32 i; ++ for (i = (u32)0U; i < (u32)4U; i = i + (u32)1U) { ++ u64 *os = tmp; ++ const u8 *bj = pub + i * (u32)8U; ++ u64 u = *(u64 *)bj; ++ u64 r = u; ++ u64 x0 = r; ++ os[i] = x0; + } +- j = 63; + } ++ tmp3 = tmp[3U]; ++ tmp[3U] = tmp3 & (u64)0x7fffffffffffffffU; ++ x = init1; ++ z = init1 + (u32)4U; ++ z[0U] = (u64)1U; ++ z[1U] = (u64)0U; ++ z[2U] = (u64)0U; ++ z[3U] = (u64)0U; ++ x[0U] = tmp[0U]; ++ x[1U] = tmp[1U]; ++ x[2U] = tmp[2U]; ++ x[3U] = tmp[3U]; ++ montgomery_ladder(init1, priv, init1); ++ encode_point(out, init1); ++} ++ ++/* The below constants were generated using this sage script: ++ * ++ * #!/usr/bin/env sage ++ * import sys ++ * from sage.all import * ++ * def limbs(n): ++ * n = int(n) ++ * l = ((n >> 0) % 2^64, (n >> 64) % 2^64, (n >> 128) % 2^64, (n >> 192) % 2^64) ++ * return "0x%016xULL, 0x%016xULL, 0x%016xULL, 0x%016xULL" % l ++ * ec = EllipticCurve(GF(2^255 - 19), [0, 486662, 0, 1, 0]) ++ * p_minus_s = (ec.lift_x(9) - ec.lift_x(1))[0] ++ * print("static const u64 p_minus_s[] = { %s };\n" % limbs(p_minus_s)) ++ * print("static const u64 table_ladder[] = {") ++ * p = ec.lift_x(9) ++ * for i in range(252): ++ * l = (p[0] + p[2]) / (p[0] - p[2]) ++ * print(("\t%s" + ("," if i != 251 else "")) % limbs(l)) ++ * p = p * 2 ++ * print("};") ++ * ++ */ + +- inv_eltfp25519_1w_bmi2(A, Qz); +- mul_eltfp25519_1w_bmi2((u64 *)shared, Qx, A); +- fred_eltfp25519_1w((u64 *)shared); ++static const u64 p_minus_s[] = { 0x816b1e0137d48290ULL, 0x440f6a51eb4d1207ULL, 0x52385f46dca2b71dULL, 0x215132111d8354cbULL }; + +- memzero_explicit(&m, sizeof(m)); +-} ++static const u64 table_ladder[] = { ++ 0xfffffffffffffff3ULL, 0xffffffffffffffffULL, 0xffffffffffffffffULL, 0x5fffffffffffffffULL, ++ 0x6b8220f416aafe96ULL, 0x82ebeb2b4f566a34ULL, 0xd5a9a5b075a5950fULL, 0x5142b2cf4b2488f4ULL, ++ 0x6aaebc750069680cULL, 0x89cf7820a0f99c41ULL, 0x2a58d9183b56d0f4ULL, 0x4b5aca80e36011a4ULL, ++ 0x329132348c29745dULL, 0xf4a2e616e1642fd7ULL, 0x1e45bb03ff67bc34ULL, 0x306912d0f42a9b4aULL, ++ 0xff886507e6af7154ULL, 0x04f50e13dfeec82fULL, 0xaa512fe82abab5ceULL, 0x174e251a68d5f222ULL, ++ 0xcf96700d82028898ULL, 0x1743e3370a2c02c5ULL, 0x379eec98b4e86eaaULL, 0x0c59888a51e0482eULL, ++ 0xfbcbf1d699b5d189ULL, 0xacaef0d58e9fdc84ULL, 0xc1c20d06231f7614ULL, 0x2938218da274f972ULL, ++ 0xf6af49beff1d7f18ULL, 0xcc541c22387ac9c2ULL, 0x96fcc9ef4015c56bULL, 0x69c1627c690913a9ULL, ++ 0x7a86fd2f4733db0eULL, 0xfdb8c4f29e087de9ULL, 0x095e4b1a8ea2a229ULL, 0x1ad7a7c829b37a79ULL, ++ 0x342d89cad17ea0c0ULL, 0x67bedda6cced2051ULL, 0x19ca31bf2bb42f74ULL, 0x3df7b4c84980acbbULL, ++ 0xa8c6444dc80ad883ULL, 0xb91e440366e3ab85ULL, 0xc215cda00164f6d8ULL, 0x3d867c6ef247e668ULL, ++ 0xc7dd582bcc3e658cULL, 0xfd2c4748ee0e5528ULL, 0xa0fd9b95cc9f4f71ULL, 0x7529d871b0675ddfULL, ++ 0xb8f568b42d3cbd78ULL, 0x1233011b91f3da82ULL, 0x2dce6ccd4a7c3b62ULL, 0x75e7fc8e9e498603ULL, ++ 0x2f4f13f1fcd0b6ecULL, 0xf1a8ca1f29ff7a45ULL, 0xc249c1a72981e29bULL, 0x6ebe0dbb8c83b56aULL, ++ 0x7114fa8d170bb222ULL, 0x65a2dcd5bf93935fULL, 0xbdc41f68b59c979aULL, 0x2f0eef79a2ce9289ULL, ++ 0x42ecbf0c083c37ceULL, 0x2930bc09ec496322ULL, 0xf294b0c19cfeac0dULL, 0x3780aa4bedfabb80ULL, ++ 0x56c17d3e7cead929ULL, 0xe7cb4beb2e5722c5ULL, 0x0ce931732dbfe15aULL, 0x41b883c7621052f8ULL, ++ 0xdbf75ca0c3d25350ULL, 0x2936be086eb1e351ULL, 0xc936e03cb4a9b212ULL, 0x1d45bf82322225aaULL, ++ 0xe81ab1036a024cc5ULL, 0xe212201c304c9a72ULL, 0xc5d73fba6832b1fcULL, 0x20ffdb5a4d839581ULL, ++ 0xa283d367be5d0fadULL, 0x6c2b25ca8b164475ULL, 0x9d4935467caaf22eULL, 0x5166408eee85ff49ULL, ++ 0x3c67baa2fab4e361ULL, 0xb3e433c67ef35cefULL, 0x5259729241159b1cULL, 0x6a621892d5b0ab33ULL, ++ 0x20b74a387555cdcbULL, 0x532aa10e1208923fULL, 0xeaa17b7762281dd1ULL, 0x61ab3443f05c44bfULL, ++ 0x257a6c422324def8ULL, 0x131c6c1017e3cf7fULL, 0x23758739f630a257ULL, 0x295a407a01a78580ULL, ++ 0xf8c443246d5da8d9ULL, 0x19d775450c52fa5dULL, 0x2afcfc92731bf83dULL, 0x7d10c8e81b2b4700ULL, ++ 0xc8e0271f70baa20bULL, 0x993748867ca63957ULL, 0x5412efb3cb7ed4bbULL, 0x3196d36173e62975ULL, ++ 0xde5bcad141c7dffcULL, 0x47cc8cd2b395c848ULL, 0xa34cd942e11af3cbULL, 0x0256dbf2d04ecec2ULL, ++ 0x875ab7e94b0e667fULL, 0xcad4dd83c0850d10ULL, 0x47f12e8f4e72c79fULL, 0x5f1a87bb8c85b19bULL, ++ 0x7ae9d0b6437f51b8ULL, 0x12c7ce5518879065ULL, 0x2ade09fe5cf77aeeULL, 0x23a05a2f7d2c5627ULL, ++ 0x5908e128f17c169aULL, 0xf77498dd8ad0852dULL, 0x74b4c4ceab102f64ULL, 0x183abadd10139845ULL, ++ 0xb165ba8daa92aaacULL, 0xd5c5ef9599386705ULL, 0xbe2f8f0cf8fc40d1ULL, 0x2701e635ee204514ULL, ++ 0x629fa80020156514ULL, 0xf223868764a8c1ceULL, 0x5b894fff0b3f060eULL, 0x60d9944cf708a3faULL, ++ 0xaeea001a1c7a201fULL, 0xebf16a633ee2ce63ULL, 0x6f7709594c7a07e1ULL, 0x79b958150d0208cbULL, ++ 0x24b55e5301d410e7ULL, 0xe3a34edff3fdc84dULL, 0xd88768e4904032d8ULL, 0x131384427b3aaeecULL, ++ 0x8405e51286234f14ULL, 0x14dc4739adb4c529ULL, 0xb8a2b5b250634ffdULL, 0x2fe2a94ad8a7ff93ULL, ++ 0xec5c57efe843faddULL, 0x2843ce40f0bb9918ULL, 0xa4b561d6cf3d6305ULL, 0x743629bde8fb777eULL, ++ 0x343edd46bbaf738fULL, 0xed981828b101a651ULL, 0xa401760b882c797aULL, 0x1fc223e28dc88730ULL, ++ 0x48604e91fc0fba0eULL, 0xb637f78f052c6fa4ULL, 0x91ccac3d09e9239cULL, 0x23f7eed4437a687cULL, ++ 0x5173b1118d9bd800ULL, 0x29d641b63189d4a7ULL, 0xfdbf177988bbc586ULL, 0x2959894fcad81df5ULL, ++ 0xaebc8ef3b4bbc899ULL, 0x4148995ab26992b9ULL, 0x24e20b0134f92cfbULL, 0x40d158894a05dee8ULL, ++ 0x46b00b1185af76f6ULL, 0x26bac77873187a79ULL, 0x3dc0bf95ab8fff5fULL, 0x2a608bd8945524d7ULL, ++ 0x26449588bd446302ULL, 0x7c4bc21c0388439cULL, 0x8e98a4f383bd11b2ULL, 0x26218d7bc9d876b9ULL, ++ 0xe3081542997c178aULL, 0x3c2d29a86fb6606fULL, 0x5c217736fa279374ULL, 0x7dde05734afeb1faULL, ++ 0x3bf10e3906d42babULL, 0xe4f7803e1980649cULL, 0xe6053bf89595bf7aULL, 0x394faf38da245530ULL, ++ 0x7a8efb58896928f4ULL, 0xfbc778e9cc6a113cULL, 0x72670ce330af596fULL, 0x48f222a81d3d6cf7ULL, ++ 0xf01fce410d72caa7ULL, 0x5a20ecc7213b5595ULL, 0x7bc21165c1fa1483ULL, 0x07f89ae31da8a741ULL, ++ 0x05d2c2b4c6830ff9ULL, 0xd43e330fc6316293ULL, 0xa5a5590a96d3a904ULL, 0x705edb91a65333b6ULL, ++ 0x048ee15e0bb9a5f7ULL, 0x3240cfca9e0aaf5dULL, 0x8f4b71ceedc4a40bULL, 0x621c0da3de544a6dULL, ++ 0x92872836a08c4091ULL, 0xce8375b010c91445ULL, 0x8a72eb524f276394ULL, 0x2667fcfa7ec83635ULL, ++ 0x7f4c173345e8752aULL, 0x061b47feee7079a5ULL, 0x25dd9afa9f86ff34ULL, 0x3780cef5425dc89cULL, ++ 0x1a46035a513bb4e9ULL, 0x3e1ef379ac575adaULL, 0xc78c5f1c5fa24b50ULL, 0x321a967634fd9f22ULL, ++ 0x946707b8826e27faULL, 0x3dca84d64c506fd0ULL, 0xc189218075e91436ULL, 0x6d9284169b3b8484ULL, ++ 0x3a67e840383f2ddfULL, 0x33eec9a30c4f9b75ULL, 0x3ec7c86fa783ef47ULL, 0x26ec449fbac9fbc4ULL, ++ 0x5c0f38cba09b9e7dULL, 0x81168cc762a3478cULL, 0x3e23b0d306fc121cULL, 0x5a238aa0a5efdcddULL, ++ 0x1ba26121c4ea43ffULL, 0x36f8c77f7c8832b5ULL, 0x88fbea0b0adcf99aULL, 0x5ca9938ec25bebf9ULL, ++ 0xd5436a5e51fccda0ULL, 0x1dbc4797c2cd893bULL, 0x19346a65d3224a08ULL, 0x0f5034e49b9af466ULL, ++ 0xf23c3967a1e0b96eULL, 0xe58b08fa867a4d88ULL, 0xfb2fabc6a7341679ULL, 0x2a75381eb6026946ULL, ++ 0xc80a3be4c19420acULL, 0x66b1f6c681f2b6dcULL, 0x7cf7036761e93388ULL, 0x25abbbd8a660a4c4ULL, ++ 0x91ea12ba14fd5198ULL, 0x684950fc4a3cffa9ULL, 0xf826842130f5ad28ULL, 0x3ea988f75301a441ULL, ++ 0xc978109a695f8c6fULL, 0x1746eb4a0530c3f3ULL, 0x444d6d77b4459995ULL, 0x75952b8c054e5cc7ULL, ++ 0xa3703f7915f4d6aaULL, 0x66c346202f2647d8ULL, 0xd01469df811d644bULL, 0x77fea47d81a5d71fULL, ++ 0xc5e9529ef57ca381ULL, 0x6eeeb4b9ce2f881aULL, 0xb6e91a28e8009bd6ULL, 0x4b80be3e9afc3fecULL, ++ 0x7e3773c526aed2c5ULL, 0x1b4afcb453c9a49dULL, 0xa920bdd7baffb24dULL, 0x7c54699f122d400eULL, ++ 0xef46c8e14fa94bc8ULL, 0xe0b074ce2952ed5eULL, 0xbea450e1dbd885d5ULL, 0x61b68649320f712cULL, ++ 0x8a485f7309ccbdd1ULL, 0xbd06320d7d4d1a2dULL, 0x25232973322dbef4ULL, 0x445dc4758c17f770ULL, ++ 0xdb0434177cc8933cULL, 0xed6fe82175ea059fULL, 0x1efebefdc053db34ULL, 0x4adbe867c65daf99ULL, ++ 0x3acd71a2a90609dfULL, 0xe5e991856dd04050ULL, 0x1ec69b688157c23cULL, 0x697427f6885cfe4dULL, ++ 0xd7be7b9b65e1a851ULL, 0xa03d28d522c536ddULL, 0x28399d658fd2b645ULL, 0x49e5b7e17c2641e1ULL, ++ 0x6f8c3a98700457a4ULL, 0x5078f0a25ebb6778ULL, 0xd13c3ccbc382960fULL, 0x2e003258a7df84b1ULL, ++ 0x8ad1f39be6296a1cULL, 0xc1eeaa652a5fbfb2ULL, 0x33ee0673fd26f3cbULL, 0x59256173a69d2cccULL, ++ 0x41ea07aa4e18fc41ULL, 0xd9fc19527c87a51eULL, 0xbdaacb805831ca6fULL, 0x445b652dc916694fULL, ++ 0xce92a3a7f2172315ULL, 0x1edc282de11b9964ULL, 0xa1823aafe04c314aULL, 0x790a2d94437cf586ULL, ++ 0x71c447fb93f6e009ULL, 0x8922a56722845276ULL, 0xbf70903b204f5169ULL, 0x2f7a89891ba319feULL, ++ 0x02a08eb577e2140cULL, 0xed9a4ed4427bdcf4ULL, 0x5253ec44e4323cd1ULL, 0x3e88363c14e9355bULL, ++ 0xaa66c14277110b8cULL, 0x1ae0391610a23390ULL, 0x2030bd12c93fc2a2ULL, 0x3ee141579555c7abULL, ++ 0x9214de3a6d6e7d41ULL, 0x3ccdd88607f17efeULL, 0x674f1288f8e11217ULL, 0x5682250f329f93d0ULL, ++ 0x6cf00b136d2e396eULL, 0x6e4cf86f1014debfULL, 0x5930b1b5bfcc4e83ULL, 0x047069b48aba16b6ULL, ++ 0x0d4ce4ab69b20793ULL, 0xb24db91a97d0fb9eULL, 0xcdfa50f54e00d01dULL, 0x221b1085368bddb5ULL, ++ 0xe7e59468b1e3d8d2ULL, 0x53c56563bd122f93ULL, 0xeee8a903e0663f09ULL, 0x61efa662cbbe3d42ULL, ++ 0x2cf8ddddde6eab2aULL, 0x9bf80ad51435f231ULL, 0x5deadacec9f04973ULL, 0x29275b5d41d29b27ULL, ++ 0xcfde0f0895ebf14fULL, 0xb9aab96b054905a7ULL, 0xcae80dd9a1c420fdULL, 0x0a63bf2f1673bbc7ULL, ++ 0x092f6e11958fbc8cULL, 0x672a81e804822fadULL, 0xcac8351560d52517ULL, 0x6f3f7722c8f192f8ULL, ++ 0xf8ba90ccc2e894b7ULL, 0x2c7557a438ff9f0dULL, 0x894d1d855ae52359ULL, 0x68e122157b743d69ULL, ++ 0xd87e5570cfb919f3ULL, 0x3f2cdecd95798db9ULL, 0x2121154710c0a2ceULL, 0x3c66a115246dc5b2ULL, ++ 0xcbedc562294ecb72ULL, 0xba7143c36a280b16ULL, 0x9610c2efd4078b67ULL, 0x6144735d946a4b1eULL, ++ 0x536f111ed75b3350ULL, 0x0211db8c2041d81bULL, 0xf93cb1000e10413cULL, 0x149dfd3c039e8876ULL, ++ 0xd479dde46b63155bULL, 0xb66e15e93c837976ULL, 0xdafde43b1f13e038ULL, 0x5fafda1a2e4b0b35ULL, ++ 0x3600bbdf17197581ULL, 0x3972050bbe3cd2c2ULL, 0x5938906dbdd5be86ULL, 0x34fce5e43f9b860fULL, ++ 0x75a8a4cd42d14d02ULL, 0x828dabc53441df65ULL, 0x33dcabedd2e131d3ULL, 0x3ebad76fb814d25fULL, ++ 0xd4906f566f70e10fULL, 0x5d12f7aa51690f5aULL, 0x45adb16e76cefcf2ULL, 0x01f768aead232999ULL, ++ 0x2b6cc77b6248febdULL, 0x3cd30628ec3aaffdULL, 0xce1c0b80d4ef486aULL, 0x4c3bff2ea6f66c23ULL, ++ 0x3f2ec4094aeaeb5fULL, 0x61b19b286e372ca7ULL, 0x5eefa966de2a701dULL, 0x23b20565de55e3efULL, ++ 0xe301ca5279d58557ULL, 0x07b2d4ce27c2874fULL, 0xa532cd8a9dcf1d67ULL, 0x2a52fee23f2bff56ULL, ++ 0x8624efb37cd8663dULL, 0xbbc7ac20ffbd7594ULL, 0x57b85e9c82d37445ULL, 0x7b3052cb86a6ec66ULL, ++ 0x3482f0ad2525e91eULL, 0x2cb68043d28edca0ULL, 0xaf4f6d052e1b003aULL, 0x185f8c2529781b0aULL, ++ 0xaa41de5bd80ce0d6ULL, 0x9407b2416853e9d6ULL, 0x563ec36e357f4c3aULL, 0x4cc4b8dd0e297bceULL, ++ 0xa2fc1a52ffb8730eULL, 0x1811f16e67058e37ULL, 0x10f9a366cddf4ee1ULL, 0x72f4a0c4a0b9f099ULL, ++ 0x8c16c06f663f4ea7ULL, 0x693b3af74e970fbaULL, 0x2102e7f1d69ec345ULL, 0x0ba53cbc968a8089ULL, ++ 0xca3d9dc7fea15537ULL, 0x4c6824bb51536493ULL, 0xb9886314844006b1ULL, 0x40d2a72ab454cc60ULL, ++ 0x5936a1b712570975ULL, 0x91b9d648debda657ULL, 0x3344094bb64330eaULL, 0x006ba10d12ee51d0ULL, ++ 0x19228468f5de5d58ULL, 0x0eb12f4c38cc05b0ULL, 0xa1039f9dd5601990ULL, 0x4502d4ce4fff0e0bULL, ++ 0xeb2054106837c189ULL, 0xd0f6544c6dd3b93cULL, 0x40727064c416d74fULL, 0x6e15c6114b502ef0ULL, ++ 0x4df2a398cfb1a76bULL, 0x11256c7419f2f6b1ULL, 0x4a497962066e6043ULL, 0x705b3aab41355b44ULL, ++ 0x365ef536d797b1d8ULL, 0x00076bd622ddf0dbULL, 0x3bbf33b0e0575a88ULL, 0x3777aa05c8e4ca4dULL, ++ 0x392745c85578db5fULL, 0x6fda4149dbae5ae2ULL, 0xb1f0b00b8adc9867ULL, 0x09963437d36f1da3ULL, ++ 0x7e824e90a5dc3853ULL, 0xccb5f6641f135cbdULL, 0x6736d86c87ce8fccULL, 0x625f3ce26604249fULL, ++ 0xaf8ac8059502f63fULL, 0x0c05e70a2e351469ULL, 0x35292e9c764b6305ULL, 0x1a394360c7e23ac3ULL, ++ 0xd5c6d53251183264ULL, 0x62065abd43c2b74fULL, 0xb5fbf5d03b973f9bULL, 0x13a3da3661206e5eULL, ++ 0xc6bd5837725d94e5ULL, 0x18e30912205016c5ULL, 0x2088ce1570033c68ULL, 0x7fba1f495c837987ULL, ++ 0x5a8c7423f2f9079dULL, 0x1735157b34023fc5ULL, 0xe4f9b49ad2fab351ULL, 0x6691ff72c878e33cULL, ++ 0x122c2adedc5eff3eULL, 0xf8dd4bf1d8956cf4ULL, 0xeb86205d9e9e5bdaULL, 0x049b92b9d975c743ULL, ++ 0xa5379730b0f6c05aULL, 0x72a0ffacc6f3a553ULL, 0xb0032c34b20dcd6dULL, 0x470e9dbc88d5164aULL, ++ 0xb19cf10ca237c047ULL, 0xb65466711f6c81a2ULL, 0xb3321bd16dd80b43ULL, 0x48c14f600c5fbe8eULL, ++ 0x66451c264aa6c803ULL, 0xb66e3904a4fa7da6ULL, 0xd45f19b0b3128395ULL, 0x31602627c3c9bc10ULL, ++ 0x3120dc4832e4e10dULL, 0xeb20c46756c717f7ULL, 0x00f52e3f67280294ULL, 0x566d4fc14730c509ULL, ++ 0x7e3a5d40fd837206ULL, 0xc1e926dc7159547aULL, 0x216730fba68d6095ULL, 0x22e8c3843f69cea7ULL, ++ 0x33d074e8930e4b2bULL, 0xb6e4350e84d15816ULL, 0x5534c26ad6ba2365ULL, 0x7773c12f89f1f3f3ULL, ++ 0x8cba404da57962aaULL, 0x5b9897a81999ce56ULL, 0x508e862f121692fcULL, 0x3a81907fa093c291ULL, ++ 0x0dded0ff4725a510ULL, 0x10d8cc10673fc503ULL, 0x5b9d151c9f1f4e89ULL, 0x32a5c1d5cb09a44cULL, ++ 0x1e0aa442b90541fbULL, 0x5f85eb7cc1b485dbULL, 0xbee595ce8a9df2e5ULL, 0x25e496c722422236ULL, ++ 0x5edf3c46cd0fe5b9ULL, 0x34e75a7ed2a43388ULL, 0xe488de11d761e352ULL, 0x0e878a01a085545cULL, ++ 0xba493c77e021bb04ULL, 0x2b4d1843c7df899aULL, 0x9ea37a487ae80d67ULL, 0x67a9958011e41794ULL, ++ 0x4b58051a6697b065ULL, 0x47e33f7d8d6ba6d4ULL, 0xbb4da8d483ca46c1ULL, 0x68becaa181c2db0dULL, ++ 0x8d8980e90b989aa5ULL, 0xf95eb14a2c93c99bULL, 0x51c6c7c4796e73a2ULL, 0x6e228363b5efb569ULL, ++ 0xc6bbc0b02dd624c8ULL, 0x777eb47dec8170eeULL, 0x3cde15a004cfafa9ULL, 0x1dc6bc087160bf9bULL, ++ 0x2e07e043eec34002ULL, 0x18e9fc677a68dc7fULL, 0xd8da03188bd15b9aULL, 0x48fbc3bb00568253ULL, ++ 0x57547d4cfb654ce1ULL, 0xd3565b82a058e2adULL, 0xf63eaf0bbf154478ULL, 0x47531ef114dfbb18ULL, ++ 0xe1ec630a4278c587ULL, 0x5507d546ca8e83f3ULL, 0x85e135c63adc0c2bULL, 0x0aa7efa85682844eULL, ++ 0x72691ba8b3e1f615ULL, 0x32b4e9701fbe3ffaULL, 0x97b6d92e39bb7868ULL, 0x2cfe53dea02e39e8ULL, ++ 0x687392cd85cd52b0ULL, 0x27ff66c910e29831ULL, 0x97134556a9832d06ULL, 0x269bb0360a84f8a0ULL, ++ 0x706e55457643f85cULL, 0x3734a48c9b597d1bULL, 0x7aee91e8c6efa472ULL, 0x5cd6abc198a9d9e0ULL, ++ 0x0e04de06cb3ce41aULL, 0xd8c6eb893402e138ULL, 0x904659bb686e3772ULL, 0x7215c371746ba8c8ULL, ++ 0xfd12a97eeae4a2d9ULL, 0x9514b7516394f2c5ULL, 0x266fd5809208f294ULL, 0x5c847085619a26b9ULL, ++ 0x52985410fed694eaULL, 0x3c905b934a2ed254ULL, 0x10bb47692d3be467ULL, 0x063b3d2d69e5e9e1ULL, ++ 0x472726eedda57debULL, 0xefb6c4ae10f41891ULL, 0x2b1641917b307614ULL, 0x117c554fc4f45b7cULL, ++ 0xc07cf3118f9d8812ULL, 0x01dbd82050017939ULL, 0xd7e803f4171b2827ULL, 0x1015e87487d225eaULL, ++ 0xc58de3fed23acc4dULL, 0x50db91c294a7be2dULL, 0x0b94d43d1c9cf457ULL, 0x6b1640fa6e37524aULL, ++ 0x692f346c5fda0d09ULL, 0x200b1c59fa4d3151ULL, 0xb8c46f760777a296ULL, 0x4b38395f3ffdfbcfULL, ++ 0x18d25e00be54d671ULL, 0x60d50582bec8aba6ULL, 0x87ad8f263b78b982ULL, 0x50fdf64e9cda0432ULL, ++ 0x90f567aac578dcf0ULL, 0xef1e9b0ef2a3133bULL, 0x0eebba9242d9de71ULL, 0x15473c9bf03101c7ULL, ++ 0x7c77e8ae56b78095ULL, 0xb678e7666e6f078eULL, 0x2da0b9615348ba1fULL, 0x7cf931c1ff733f0bULL, ++ 0x26b357f50a0a366cULL, 0xe9708cf42b87d732ULL, 0xc13aeea5f91cb2c0ULL, 0x35d90c991143bb4cULL, ++ 0x47c1c404a9a0d9dcULL, 0x659e58451972d251ULL, 0x3875a8c473b38c31ULL, 0x1fbd9ed379561f24ULL, ++ 0x11fabc6fd41ec28dULL, 0x7ef8dfe3cd2a2dcaULL, 0x72e73b5d8c404595ULL, 0x6135fa4954b72f27ULL, ++ 0xccfc32a2de24b69cULL, 0x3f55698c1f095d88ULL, 0xbe3350ed5ac3f929ULL, 0x5e9bf806ca477eebULL, ++ 0xe9ce8fb63c309f68ULL, 0x5376f63565e1f9f4ULL, 0xd1afcfb35a6393f1ULL, 0x6632a1ede5623506ULL, ++ 0x0b7d6c390c2ded4cULL, 0x56cb3281df04cb1fULL, 0x66305a1249ecc3c7ULL, 0x5d588b60a38ca72aULL, ++ 0xa6ecbf78e8e5f42dULL, 0x86eeb44b3c8a3eecULL, 0xec219c48fbd21604ULL, 0x1aaf1af517c36731ULL, ++ 0xc306a2836769bde7ULL, 0x208280622b1e2adbULL, 0x8027f51ffbff94a6ULL, 0x76cfa1ce1124f26bULL, ++ 0x18eb00562422abb6ULL, 0xf377c4d58f8c29c3ULL, 0x4dbbc207f531561aULL, 0x0253b7f082128a27ULL, ++ 0x3d1f091cb62c17e0ULL, 0x4860e1abd64628a9ULL, 0x52d17436309d4253ULL, 0x356f97e13efae576ULL, ++ 0xd351e11aa150535bULL, 0x3e6b45bb1dd878ccULL, 0x0c776128bed92c98ULL, 0x1d34ae93032885b8ULL, ++ 0x4ba0488ca85ba4c3ULL, 0x985348c33c9ce6ceULL, 0x66124c6f97bda770ULL, 0x0f81a0290654124aULL, ++ 0x9ed09ca6569b86fdULL, 0x811009fd18af9a2dULL, 0xff08d03f93d8c20aULL, 0x52a148199faef26bULL, ++ 0x3e03f9dc2d8d1b73ULL, 0x4205801873961a70ULL, 0xc0d987f041a35970ULL, 0x07aa1f15a1c0d549ULL, ++ 0xdfd46ce08cd27224ULL, 0x6d0a024f934e4239ULL, 0x808a7a6399897b59ULL, 0x0a4556e9e13d95a2ULL, ++ 0xd21a991fe9c13045ULL, 0x9b0e8548fe7751b8ULL, 0x5da643cb4bf30035ULL, 0x77db28d63940f721ULL, ++ 0xfc5eeb614adc9011ULL, 0x5229419ae8c411ebULL, 0x9ec3e7787d1dcf74ULL, 0x340d053e216e4cb5ULL, ++ 0xcac7af39b48df2b4ULL, 0xc0faec2871a10a94ULL, 0x140a69245ca575edULL, 0x0cf1c37134273a4cULL, ++ 0xc8ee306ac224b8a5ULL, 0x57eaee7ccb4930b0ULL, 0xa1e806bdaacbe74fULL, 0x7d9a62742eeb657dULL, ++ 0x9eb6b6ef546c4830ULL, 0x885cca1fddb36e2eULL, 0xe6b9f383ef0d7105ULL, 0x58654fef9d2e0412ULL, ++ 0xa905c4ffbe0e8e26ULL, 0x942de5df9b31816eULL, 0x497d723f802e88e1ULL, 0x30684dea602f408dULL, ++ 0x21e5a278a3e6cb34ULL, 0xaefb6e6f5b151dc4ULL, 0xb30b8e049d77ca15ULL, 0x28c3c9cf53b98981ULL, ++ 0x287fb721556cdd2aULL, 0x0d317ca897022274ULL, 0x7468c7423a543258ULL, 0x4a7f11464eb5642fULL, ++ 0xa237a4774d193aa6ULL, 0xd865986ea92129a1ULL, 0x24c515ecf87c1a88ULL, 0x604003575f39f5ebULL, ++ 0x47b9f189570a9b27ULL, 0x2b98cede465e4b78ULL, 0x026df551dbb85c20ULL, 0x74fcd91047e21901ULL, ++ 0x13e2a90a23c1bfa3ULL, 0x0cb0074e478519f6ULL, 0x5ff1cbbe3af6cf44ULL, 0x67fe5438be812dbeULL, ++ 0xd13cf64fa40f05b0ULL, 0x054dfb2f32283787ULL, 0x4173915b7f0d2aeaULL, 0x482f144f1f610d4eULL, ++ 0xf6210201b47f8234ULL, 0x5d0ae1929e70b990ULL, 0xdcd7f455b049567cULL, 0x7e93d0f1f0916f01ULL, ++ 0xdd79cbf18a7db4faULL, 0xbe8391bf6f74c62fULL, 0x027145d14b8291bdULL, 0x585a73ea2cbf1705ULL, ++ 0x485ca03e928a0db2ULL, 0x10fc01a5742857e7ULL, 0x2f482edbd6d551a7ULL, 0x0f0433b5048fdb8aULL, ++ 0x60da2e8dd7dc6247ULL, 0x88b4c9d38cd4819aULL, 0x13033ac001f66697ULL, 0x273b24fe3b367d75ULL, ++ 0xc6e8f66a31b3b9d4ULL, 0x281514a494df49d5ULL, 0xd1726fdfc8b23da7ULL, 0x4b3ae7d103dee548ULL, ++ 0xc6256e19ce4b9d7eULL, 0xff5c5cf186e3c61cULL, 0xacc63ca34b8ec145ULL, 0x74621888fee66574ULL, ++ 0x956f409645290a1eULL, 0xef0bf8e3263a962eULL, 0xed6a50eb5ec2647bULL, 0x0694283a9dca7502ULL, ++ 0x769b963643a2dcd1ULL, 0x42b7c8ea09fc5353ULL, 0x4f002aee13397eabULL, 0x63005e2c19b7d63aULL, ++ 0xca6736da63023beaULL, 0x966c7f6db12a99b7ULL, 0xace09390c537c5e1ULL, 0x0b696063a1aa89eeULL, ++ 0xebb03e97288c56e5ULL, 0x432a9f9f938c8be8ULL, 0xa6a5a93d5b717f71ULL, 0x1a5fb4c3e18f9d97ULL, ++ 0x1c94e7ad1c60cdceULL, 0xee202a43fc02c4a0ULL, 0x8dafe4d867c46a20ULL, 0x0a10263c8ac27b58ULL, ++ 0xd0dea9dfe4432a4aULL, 0x856af87bbe9277c5ULL, 0xce8472acc212c71aULL, 0x6f151b6d9bbb1e91ULL, ++ 0x26776c527ceed56aULL, 0x7d211cb7fbf8faecULL, 0x37ae66a6fd4609ccULL, 0x1f81b702d2770c42ULL, ++ 0x2fb0b057eac58392ULL, 0xe1dd89fe29744e9dULL, 0xc964f8eb17beb4f8ULL, 0x29571073c9a2d41eULL, ++ 0xa948a18981c0e254ULL, 0x2df6369b65b22830ULL, 0xa33eb2d75fcfd3c6ULL, 0x078cd6ec4199a01fULL, ++ 0x4a584a41ad900d2fULL, 0x32142b78e2c74c52ULL, 0x68c4e8338431c978ULL, 0x7f69ea9008689fc2ULL, ++ 0x52f2c81e46a38265ULL, 0xfd78072d04a832fdULL, 0x8cd7d5fa25359e94ULL, 0x4de71b7454cc29d2ULL, ++ 0x42eb60ad1eda6ac9ULL, 0x0aad37dfdbc09c3aULL, 0x81004b71e33cc191ULL, 0x44e6be345122803cULL, ++ 0x03fe8388ba1920dbULL, 0xf5d57c32150db008ULL, 0x49c8c4281af60c29ULL, 0x21edb518de701aeeULL, ++ 0x7fb63e418f06dc99ULL, 0xa4460d99c166d7b8ULL, 0x24dd5248ce520a83ULL, 0x5ec3ad712b928358ULL, ++ 0x15022a5fbd17930fULL, 0xa4f64a77d82570e3ULL, 0x12bc8d6915783712ULL, 0x498194c0fc620abbULL, ++ 0x38a2d9d255686c82ULL, 0x785c6bd9193e21f0ULL, 0xe4d5c81ab24a5484ULL, 0x56307860b2e20989ULL, ++ 0x429d55f78b4d74c4ULL, 0x22f1834643350131ULL, 0x1e60c24598c71fffULL, 0x59f2f014979983efULL, ++ 0x46a47d56eb494a44ULL, 0x3e22a854d636a18eULL, 0xb346e15274491c3bULL, 0x2ceafd4e5390cde7ULL, ++ 0xba8a8538be0d6675ULL, 0x4b9074bb50818e23ULL, 0xcbdab89085d304c3ULL, 0x61a24fe0e56192c4ULL, ++ 0xcb7615e6db525bcbULL, 0xdd7d8c35a567e4caULL, 0xe6b4153acafcdd69ULL, 0x2d668e097f3c9766ULL, ++ 0xa57e7e265ce55ef0ULL, 0x5d9f4e527cd4b967ULL, 0xfbc83606492fd1e5ULL, 0x090d52beb7c3f7aeULL, ++ 0x09b9515a1e7b4d7cULL, 0x1f266a2599da44c0ULL, 0xa1c49548e2c55504ULL, 0x7ef04287126f15ccULL, ++ 0xfed1659dbd30ef15ULL, 0x8b4ab9eec4e0277bULL, 0x884d6236a5df3291ULL, 0x1fd96ea6bf5cf788ULL, ++ 0x42a161981f190d9aULL, 0x61d849507e6052c1ULL, 0x9fe113bf285a2cd5ULL, 0x7c22d676dbad85d8ULL, ++ 0x82e770ed2bfbd27dULL, 0x4c05b2ece996f5a5ULL, 0xcd40a9c2b0900150ULL, 0x5895319213d9bf64ULL, ++ 0xe7cc5d703fea2e08ULL, 0xb50c491258e2188cULL, 0xcce30baa48205bf0ULL, 0x537c659ccfa32d62ULL, ++ 0x37b6623a98cfc088ULL, 0xfe9bed1fa4d6aca4ULL, 0x04d29b8e56a8d1b0ULL, 0x725f71c40b519575ULL, ++ 0x28c7f89cd0339ce6ULL, 0x8367b14469ddc18bULL, 0x883ada83a6a1652cULL, 0x585f1974034d6c17ULL, ++ 0x89cfb266f1b19188ULL, 0xe63b4863e7c35217ULL, 0xd88c9da6b4c0526aULL, 0x3e035c9df0954635ULL, ++ 0xdd9d5412fb45de9dULL, 0xdd684532e4cff40dULL, 0x4b5c999b151d671cULL, 0x2d8c2cc811e7f690ULL, ++ 0x7f54be1d90055d40ULL, 0xa464c5df464aaf40ULL, 0x33979624f0e917beULL, 0x2c018dc527356b30ULL, ++ 0xa5415024e330b3d4ULL, 0x73ff3d96691652d3ULL, 0x94ec42c4ef9b59f1ULL, 0x0747201618d08e5aULL, ++ 0x4d6ca48aca411c53ULL, 0x66415f2fcfa66119ULL, 0x9c4dd40051e227ffULL, 0x59810bc09a02f7ebULL, ++ 0x2a7eb171b3dc101dULL, 0x441c5ab99ffef68eULL, 0x32025c9b93b359eaULL, 0x5e8ce0a71e9d112fULL, ++ 0xbfcccb92429503fdULL, 0xd271ba752f095d55ULL, 0x345ead5e972d091eULL, 0x18c8df11a83103baULL, ++ 0x90cd949a9aed0f4cULL, 0xc5d1f4cb6660e37eULL, 0xb8cac52d56c52e0bULL, 0x6e42e400c5808e0dULL, ++ 0xa3b46966eeaefd23ULL, 0x0c4f1f0be39ecdcaULL, 0x189dc8c9d683a51dULL, 0x51f27f054c09351bULL, ++ 0x4c487ccd2a320682ULL, 0x587ea95bb3df1c96ULL, 0xc8ccf79e555cb8e8ULL, 0x547dc829a206d73dULL, ++ 0xb822a6cd80c39b06ULL, 0xe96d54732000d4c6ULL, 0x28535b6f91463b4dULL, 0x228f4660e2486e1dULL, ++ 0x98799538de8d3abfULL, 0x8cd8330045ebca6eULL, 0x79952a008221e738ULL, 0x4322e1a7535cd2bbULL, ++ 0xb114c11819d1801cULL, 0x2016e4d84f3f5ec7ULL, 0xdd0e2df409260f4cULL, 0x5ec362c0ae5f7266ULL, ++ 0xc0462b18b8b2b4eeULL, 0x7cc8d950274d1afbULL, 0xf25f7105436b02d2ULL, 0x43bbf8dcbff9ccd3ULL, ++ 0xb6ad1767a039e9dfULL, 0xb0714da8f69d3583ULL, 0x5e55fa18b42931f5ULL, 0x4ed5558f33c60961ULL, ++ 0x1fe37901c647a5ddULL, 0x593ddf1f8081d357ULL, 0x0249a4fd813fd7a6ULL, 0x69acca274e9caf61ULL, ++ 0x047ba3ea330721c9ULL, 0x83423fc20e7e1ea0ULL, 0x1df4c0af01314a60ULL, 0x09a62dab89289527ULL, ++ 0xa5b325a49cc6cb00ULL, 0xe94b5dc654b56cb6ULL, 0x3be28779adc994a0ULL, 0x4296e8f8ba3a4aadULL, ++ 0x328689761e451eabULL, 0x2e4d598bff59594aULL, 0x49b96853d7a7084aULL, 0x4980a319601420a8ULL, ++ 0x9565b9e12f552c42ULL, 0x8a5318db7100fe96ULL, 0x05c90b4d43add0d7ULL, 0x538b4cd66a5d4edaULL, ++ 0xf4e94fc3e89f039fULL, 0x592c9af26f618045ULL, 0x08a36eb5fd4b9550ULL, 0x25fffaf6c2ed1419ULL, ++ 0x34434459cc79d354ULL, 0xeeecbfb4b1d5476bULL, 0xddeb34a061615d99ULL, 0x5129cecceb64b773ULL, ++ 0xee43215894993520ULL, 0x772f9c7cf14c0b3bULL, 0xd2e2fce306bedad5ULL, 0x715f42b546f06a97ULL, ++ 0x434ecdceda5b5f1aULL, 0x0da17115a49741a9ULL, 0x680bd77c73edad2eULL, 0x487c02354edd9041ULL, ++ 0xb8efeff3a70ed9c4ULL, 0x56a32aa3e857e302ULL, 0xdf3a68bd48a2a5a0ULL, 0x07f650b73176c444ULL, ++ 0xe38b9b1626e0ccb1ULL, 0x79e053c18b09fb36ULL, 0x56d90319c9f94964ULL, 0x1ca941e7ac9ff5c4ULL, ++ 0x49c4df29162fa0bbULL, 0x8488cf3282b33305ULL, 0x95dfda14cabb437dULL, 0x3391f78264d5ad86ULL, ++ 0x729ae06ae2b5095dULL, 0xd58a58d73259a946ULL, 0xe9834262d13921edULL, 0x27fedafaa54bb592ULL, ++ 0xa99dc5b829ad48bbULL, 0x5f025742499ee260ULL, 0x802c8ecd5d7513fdULL, 0x78ceb3ef3f6dd938ULL, ++ 0xc342f44f8a135d94ULL, 0x7b9edb44828cdda3ULL, 0x9436d11a0537cfe7ULL, 0x5064b164ec1ab4c8ULL, ++ 0x7020eccfd37eb2fcULL, 0x1f31ea3ed90d25fcULL, 0x1b930d7bdfa1bb34ULL, 0x5344467a48113044ULL, ++ 0x70073170f25e6dfbULL, 0xe385dc1a50114cc8ULL, 0x2348698ac8fc4f00ULL, 0x2a77a55284dd40d8ULL, ++ 0xfe06afe0c98c6ce4ULL, 0xc235df96dddfd6e4ULL, 0x1428d01e33bf1ed3ULL, 0x785768ec9300bdafULL, ++ 0x9702e57a91deb63bULL, 0x61bdb8bfe5ce8b80ULL, 0x645b426f3d1d58acULL, 0x4804a82227a557bcULL, ++ 0x8e57048ab44d2601ULL, 0x68d6501a4b3a6935ULL, 0xc39c9ec3f9e1c293ULL, 0x4172f257d4de63e2ULL, ++ 0xd368b450330c6401ULL, 0x040d3017418f2391ULL, 0x2c34bb6090b7d90dULL, 0x16f649228fdfd51fULL, ++ 0xbea6818e2b928ef5ULL, 0xe28ccf91cdc11e72ULL, 0x594aaa68e77a36cdULL, 0x313034806c7ffd0fULL, ++ 0x8a9d27ac2249bd65ULL, 0x19a3b464018e9512ULL, 0xc26ccff352b37ec7ULL, 0x056f68341d797b21ULL, ++ 0x5e79d6757efd2327ULL, 0xfabdbcb6553afe15ULL, 0xd3e7222c6eaf5a60ULL, 0x7046c76d4dae743bULL, ++ 0x660be872b18d4a55ULL, 0x19992518574e1496ULL, 0xc103053a302bdcbbULL, 0x3ed8e9800b218e8eULL, ++ 0x7b0b9239fa75e03eULL, 0xefe9fb684633c083ULL, 0x98a35fbe391a7793ULL, 0x6065510fe2d0fe34ULL, ++ 0x55cb668548abad0cULL, 0xb4584548da87e527ULL, 0x2c43ecea0107c1ddULL, 0x526028809372de35ULL, ++ 0x3415c56af9213b1fULL, 0x5bee1a4d017e98dbULL, 0x13f6b105b5cf709bULL, 0x5ff20e3482b29ab6ULL, ++ 0x0aa29c75cc2e6c90ULL, 0xfc7d73ca3a70e206ULL, 0x899fc38fc4b5c515ULL, 0x250386b124ffc207ULL, ++ 0x54ea28d5ae3d2b56ULL, 0x9913149dd6de60ceULL, 0x16694fc58f06d6c1ULL, 0x46b23975eb018fc7ULL, ++ 0x470a6a0fb4b7b4e2ULL, 0x5d92475a8f7253deULL, 0xabeee5b52fbd3adbULL, 0x7fa20801a0806968ULL, ++ 0x76f3faf19f7714d2ULL, 0xb3e840c12f4660c3ULL, 0x0fb4cd8df212744eULL, 0x4b065a251d3a2dd2ULL, ++ 0x5cebde383d77cd4aULL, 0x6adf39df882c9cb1ULL, 0xa2dd242eb09af759ULL, 0x3147c0e50e5f6422ULL, ++ 0x164ca5101d1350dbULL, 0xf8d13479c33fc962ULL, 0xe640ce4d13e5da08ULL, 0x4bdee0c45061f8baULL, ++ 0xd7c46dc1a4edb1c9ULL, 0x5514d7b6437fd98aULL, 0x58942f6bb2a1c00bULL, 0x2dffb2ab1d70710eULL, ++ 0xccdfcf2fc18b6d68ULL, 0xa8ebcba8b7806167ULL, 0x980697f95e2937e3ULL, 0x02fbba1cd0126e8cULL ++}; + +-static void curve25519_bmi2_base(u8 session_key[CURVE25519_KEY_SIZE], +- const u8 private_key[CURVE25519_KEY_SIZE]) ++static void curve25519_ever64_base(u8 *out, const u8 *priv) + { +- struct { +- u64 buffer[4 * NUM_WORDS_ELTFP25519]; +- u64 coordinates[4 * NUM_WORDS_ELTFP25519]; +- u64 workspace[4 * NUM_WORDS_ELTFP25519]; +- u8 private[CURVE25519_KEY_SIZE]; +- } __aligned(32) m; +- +- const int ite[4] = { 64, 64, 64, 63 }; +- const int q = 3; + u64 swap = 1; +- +- int i = 0, j = 0, k = 0; +- u64 *const key = (u64 *)m.private; +- u64 *const Ur1 = m.coordinates + 0; +- u64 *const Zr1 = m.coordinates + 4; +- u64 *const Ur2 = m.coordinates + 8; +- u64 *const Zr2 = m.coordinates + 12; +- +- u64 *const UZr1 = m.coordinates + 0; +- u64 *const ZUr2 = m.coordinates + 8; +- +- u64 *const A = m.workspace + 0; +- u64 *const B = m.workspace + 4; +- u64 *const C = m.workspace + 8; +- u64 *const D = m.workspace + 12; +- +- u64 *const AB = m.workspace + 0; +- u64 *const CD = m.workspace + 8; +- +- const u64 *const P = table_ladder_8k; +- +- memcpy(m.private, private_key, sizeof(m.private)); +- +- curve25519_clamp_secret(m.private); +- +- setzero_eltfp25519_1w(Ur1); +- setzero_eltfp25519_1w(Zr1); +- setzero_eltfp25519_1w(Zr2); +- Ur1[0] = 1; +- Zr1[0] = 1; +- Zr2[0] = 1; +- +- /* G-S */ +- Ur2[3] = 0x1eaecdeee27cab34UL; +- Ur2[2] = 0xadc7a0b9235d48e2UL; +- Ur2[1] = 0xbbf095ae14b2edf8UL; +- Ur2[0] = 0x7e94e1fec82faabdUL; +- +- /* main-loop */ +- j = q; +- for (i = 0; i < NUM_WORDS_ELTFP25519; ++i) { +- while (j < ite[i]) { +- u64 bit = (key[i] >> j) & 0x1; +- k = (64 * i + j - q); ++ int i, j, k; ++ u64 tmp[16 + 32 + 4]; ++ u64 *x1 = &tmp[0]; ++ u64 *z1 = &tmp[4]; ++ u64 *x2 = &tmp[8]; ++ u64 *z2 = &tmp[12]; ++ u64 *xz1 = &tmp[0]; ++ u64 *xz2 = &tmp[8]; ++ u64 *a = &tmp[0 + 16]; ++ u64 *b = &tmp[4 + 16]; ++ u64 *c = &tmp[8 + 16]; ++ u64 *ab = &tmp[0 + 16]; ++ u64 *abcd = &tmp[0 + 16]; ++ u64 *ef = &tmp[16 + 16]; ++ u64 *efgh = &tmp[16 + 16]; ++ u64 *key = &tmp[0 + 16 + 32]; ++ ++ memcpy(key, priv, 32); ++ ((u8 *)key)[0] &= 248; ++ ((u8 *)key)[31] = (((u8 *)key)[31] & 127) | 64; ++ ++ x1[0] = 1, x1[1] = x1[2] = x1[3] = 0; ++ z1[0] = 1, z1[1] = z1[2] = z1[3] = 0; ++ z2[0] = 1, z2[1] = z2[2] = z2[3] = 0; ++ memcpy(x2, p_minus_s, sizeof(p_minus_s)); ++ ++ j = 3; ++ for (i = 0; i < 4; ++i) { ++ while (j < (const int[]){ 64, 64, 64, 63 }[i]) { ++ u64 bit = (key[i] >> j) & 1; ++ k = (64 * i + j - 3); + swap = swap ^ bit; +- cswap(swap, Ur1, Ur2); +- cswap(swap, Zr1, Zr2); ++ cswap2(swap, xz1, xz2); + swap = bit; +- /* Addition */ +- sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ +- add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ +- mul_eltfp25519_1w_bmi2(C, &P[4 * k], B);/* C = M0-B */ +- sub_eltfp25519_1w(B, A, C); /* B = (Ur1+Zr1) - M*(Ur1-Zr1) */ +- add_eltfp25519_1w_bmi2(A, A, C); /* A = (Ur1+Zr1) + M*(Ur1-Zr1) */ +- sqr_eltfp25519_2w_bmi2(AB); /* A = A^2 | B = B^2 */ +- mul_eltfp25519_2w_bmi2(UZr1, ZUr2, AB); /* Ur1 = Zr2*A | Zr1 = Ur2*B */ ++ fsub(b, x1, z1); ++ fadd(a, x1, z1); ++ fmul(c, &table_ladder[4 * k], b, ef); ++ fsub(b, a, c); ++ fadd(a, a, c); ++ fsqr2(ab, ab, efgh); ++ fmul2(xz1, xz2, ab, efgh); + ++j; + } + j = 0; + } + +- /* Doubling */ +- for (i = 0; i < q; ++i) { +- add_eltfp25519_1w_bmi2(A, Ur1, Zr1); /* A = Ur1+Zr1 */ +- sub_eltfp25519_1w(B, Ur1, Zr1); /* B = Ur1-Zr1 */ +- sqr_eltfp25519_2w_bmi2(AB); /* A = A**2 B = B**2 */ +- copy_eltfp25519_1w(C, B); /* C = B */ +- sub_eltfp25519_1w(B, A, B); /* B = A-B */ +- mul_a24_eltfp25519_1w(D, B); /* D = my_a24*B */ +- add_eltfp25519_1w_bmi2(D, D, C); /* D = D+C */ +- mul_eltfp25519_2w_bmi2(UZr1, AB, CD); /* Ur1 = A*B Zr1 = Zr1*A */ +- } +- +- /* Convert to affine coordinates */ +- inv_eltfp25519_1w_bmi2(A, Zr1); +- mul_eltfp25519_1w_bmi2((u64 *)session_key, Ur1, A); +- fred_eltfp25519_1w((u64 *)session_key); ++ point_double(xz1, abcd, efgh); ++ point_double(xz1, abcd, efgh); ++ point_double(xz1, abcd, efgh); ++ encode_point(out, xz1); + +- memzero_explicit(&m, sizeof(m)); ++ memzero_explicit(tmp, sizeof(tmp)); + } + ++static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2_adx); ++ + void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE], + const u8 secret[CURVE25519_KEY_SIZE], + const u8 basepoint[CURVE25519_KEY_SIZE]) + { +- if (static_branch_likely(&curve25519_use_adx)) +- curve25519_adx(mypublic, secret, basepoint); +- else if (static_branch_likely(&curve25519_use_bmi2)) +- curve25519_bmi2(mypublic, secret, basepoint); ++ if (static_branch_likely(&curve25519_use_bmi2_adx)) ++ curve25519_ever64(mypublic, secret, basepoint); + else + curve25519_generic(mypublic, secret, basepoint); + } +@@ -2355,10 +1395,8 @@ EXPORT_SYMBOL(curve25519_arch); + void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], + const u8 secret[CURVE25519_KEY_SIZE]) + { +- if (static_branch_likely(&curve25519_use_adx)) +- curve25519_adx_base(pub, secret); +- else if (static_branch_likely(&curve25519_use_bmi2)) +- curve25519_bmi2_base(pub, secret); ++ if (static_branch_likely(&curve25519_use_bmi2_adx)) ++ curve25519_ever64_base(pub, secret); + else + curve25519_generic(pub, secret, curve25519_base_point); + } +@@ -2449,12 +1487,11 @@ static struct kpp_alg curve25519_alg = { + .max_size = curve25519_max_size, + }; + ++ + static int __init curve25519_mod_init(void) + { +- if (boot_cpu_has(X86_FEATURE_BMI2)) +- static_branch_enable(&curve25519_use_bmi2); +- else if (boot_cpu_has(X86_FEATURE_ADX)) +- static_branch_enable(&curve25519_use_adx); ++ if (boot_cpu_has(X86_FEATURE_BMI2) && boot_cpu_has(X86_FEATURE_ADX)) ++ static_branch_enable(&curve25519_use_bmi2_adx); + else + return 0; + return IS_REACHABLE(CONFIG_CRYPTO_KPP) ? +@@ -2474,3 +1511,4 @@ module_exit(curve25519_mod_exit); + MODULE_ALIAS_CRYPTO("curve25519"); + MODULE_ALIAS_CRYPTO("curve25519-x86"); + MODULE_LICENSE("GPL v2"); ++MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0055-crypto-x86-curve25519-leave-r12-as-spare-register.patch b/target/linux/generic/backport-5.4/080-wireguard-0055-crypto-x86-curve25519-leave-r12-as-spare-register.patch new file mode 100644 index 0000000000..74a6ef648b --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0055-crypto-x86-curve25519-leave-r12-as-spare-register.patch @@ -0,0 +1,376 @@ +From 481c5ed9ac2acec32d93847636707bda02208ec8 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 1 Mar 2020 16:06:56 +0800 +Subject: [PATCH 055/124] crypto: x86/curve25519 - leave r12 as spare register + +commit dc7fc3a53ae158263196b1892b672aedf67796c5 upstream. + +This updates to the newer register selection proved by HACL*, which +leads to a more compact instruction encoding, and saves around 100 +cycles. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/curve25519-x86_64.c | 110 ++++++++++++++-------------- + 1 file changed, 55 insertions(+), 55 deletions(-) + +--- a/arch/x86/crypto/curve25519-x86_64.c ++++ b/arch/x86/crypto/curve25519-x86_64.c +@@ -167,28 +167,28 @@ static inline void fmul(u64 *out, const + " movq 0(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 8(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" +- " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 16(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 16(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" +- " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 24(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 24(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" +- " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 32(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " movq %%r12, 40(%0);" " mov $0, %%r8;" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%0);" + /* Line up pointers */ +@@ -202,11 +202,11 @@ static inline void fmul(u64 *out, const + " mulxq 32(%1), %%r8, %%r13;" + " xor %3, %3;" + " adoxq 0(%1), %%r8;" +- " mulxq 40(%1), %%r9, %%r12;" ++ " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" +@@ -231,7 +231,7 @@ static inline void fmul(u64 *out, const + " movq %%r8, 0(%0);" + : "+&r" (tmp), "+&r" (f1), "+&r" (out), "+&r" (f2) + : +- : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "memory", "cc" ++ : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "memory", "cc" + ); + } + +@@ -248,28 +248,28 @@ static inline void fmul2(u64 *out, const + " movq 0(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 8(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" +- " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 16(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 16(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" +- " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 24(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 24(%1), %%rdx;" + " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" +- " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 32(%0);" +- " mulxq 16(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " movq %%r12, 40(%0);" " mov $0, %%r8;" ++ " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" ++ " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%0);" + +@@ -279,28 +279,28 @@ static inline void fmul2(u64 *out, const + " movq 32(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 64(%0);" + " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" +- " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" ++ " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 40(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 80(%0);" +- " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%0);" ++ " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 48(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 88(%0);" +- " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " mov $0, %%r8;" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%0);" ++ " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 56(%1), %%rdx;" + " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%r12, %%r10;" " movq %%r10, 96(%0);" +- " mulxq 48(%3), %%r12, %%r13;" " adox %%r11, %%r12;" " adcx %%r14, %%r12;" " movq %%r12, 104(%0);" " mov $0, %%r8;" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%0);" ++ " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 104(%0);" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%0);" + /* Line up pointers */ +@@ -314,11 +314,11 @@ static inline void fmul2(u64 *out, const + " mulxq 32(%1), %%r8, %%r13;" + " xor %3, %3;" + " adoxq 0(%1), %%r8;" +- " mulxq 40(%1), %%r9, %%r12;" ++ " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" +@@ -347,11 +347,11 @@ static inline void fmul2(u64 *out, const + " mulxq 96(%1), %%r8, %%r13;" + " xor %3, %3;" + " adoxq 64(%1), %%r8;" +- " mulxq 104(%1), %%r9, %%r12;" ++ " mulxq 104(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 72(%1), %%r9;" + " mulxq 112(%1), %%r10, %%r13;" +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " adoxq 80(%1), %%r10;" + " mulxq 120(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" +@@ -376,7 +376,7 @@ static inline void fmul2(u64 *out, const + " movq %%r8, 32(%0);" + : "+&r" (tmp), "+&r" (f1), "+&r" (out), "+&r" (f2) + : +- : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "memory", "cc" ++ : "%rax", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "memory", "cc" + ); + } + +@@ -388,11 +388,11 @@ static inline void fmul_scalar(u64 *out, + asm volatile( + /* Compute the raw multiplication of f1*f2 */ + " mulxq 0(%2), %%r8, %%rcx;" /* f1[0]*f2 */ +- " mulxq 8(%2), %%r9, %%r12;" /* f1[1]*f2 */ ++ " mulxq 8(%2), %%r9, %%rbx;" /* f1[1]*f2 */ + " add %%rcx, %%r9;" + " mov $0, %%rcx;" + " mulxq 16(%2), %%r10, %%r13;" /* f1[2]*f2 */ +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " mulxq 24(%2), %%r11, %%rax;" /* f1[3]*f2 */ + " adcx %%r13, %%r11;" + " adcx %%rcx, %%rax;" +@@ -419,7 +419,7 @@ static inline void fmul_scalar(u64 *out, + " movq %%r8, 0(%1);" + : "+&r" (f2_r) + : "r" (out), "r" (f1) +- : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "memory", "cc" ++ : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "memory", "cc" + ); + } + +@@ -520,8 +520,8 @@ static inline void fsqr(u64 *out, const + " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 24(%1), %%rdx;" /* f[3] */ +- " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ +- " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */ ++ " mulxq 8(%1), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ ++ " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ + " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ + " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + +@@ -531,12 +531,12 @@ static inline void fsqr(u64 *out, const + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" + " adcx %%r9, %%r9;" +- " adox %%r15, %%r12;" ++ " adox %%r15, %%rbx;" + " adcx %%r10, %%r10;" + " adox %%r15, %%r13;" + " adcx %%r11, %%r11;" + " adox %%r15, %%r14;" +- " adcx %%r12, %%r12;" ++ " adcx %%rbx, %%rbx;" + " adcx %%r13, %%r13;" + " adcx %%r14, %%r14;" + +@@ -549,7 +549,7 @@ static inline void fsqr(u64 *out, const + " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);" + " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ + " adcx %%rax, %%r11;" " movq %%r11, 32(%0);" +- " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);" ++ " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%0);" + " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ + " adcx %%rax, %%r13;" " movq %%r13, 48(%0);" + " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);" +@@ -565,11 +565,11 @@ static inline void fsqr(u64 *out, const + " mulxq 32(%1), %%r8, %%r13;" + " xor %%rcx, %%rcx;" + " adoxq 0(%1), %%r8;" +- " mulxq 40(%1), %%r9, %%r12;" ++ " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" +@@ -594,7 +594,7 @@ static inline void fsqr(u64 *out, const + " movq %%r8, 0(%0);" + : "+&r" (tmp), "+&r" (f), "+&r" (out) + : +- : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc" ++ : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "%r15", "memory", "cc" + ); + } + +@@ -611,8 +611,8 @@ static inline void fsqr2(u64 *out, const + " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 24(%1), %%rdx;" /* f[3] */ +- " mulxq 8(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ +- " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */ ++ " mulxq 8(%1), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ ++ " mulxq 16(%1), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ + " movq 8(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ + " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + +@@ -622,12 +622,12 @@ static inline void fsqr2(u64 *out, const + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" + " adcx %%r9, %%r9;" +- " adox %%r15, %%r12;" ++ " adox %%r15, %%rbx;" + " adcx %%r10, %%r10;" + " adox %%r15, %%r13;" + " adcx %%r11, %%r11;" + " adox %%r15, %%r14;" +- " adcx %%r12, %%r12;" ++ " adcx %%rbx, %%rbx;" + " adcx %%r13, %%r13;" + " adcx %%r14, %%r14;" + +@@ -640,7 +640,7 @@ static inline void fsqr2(u64 *out, const + " adcx %%rcx, %%r10;" " movq %%r10, 24(%0);" + " movq 16(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ + " adcx %%rax, %%r11;" " movq %%r11, 32(%0);" +- " adcx %%rcx, %%r12;" " movq %%r12, 40(%0);" ++ " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%0);" + " movq 24(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ + " adcx %%rax, %%r13;" " movq %%r13, 48(%0);" + " adcx %%rcx, %%r14;" " movq %%r14, 56(%0);" +@@ -651,8 +651,8 @@ static inline void fsqr2(u64 *out, const + " mulxq 48(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 56(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 56(%1), %%rdx;" /* f[3] */ +- " mulxq 40(%1), %%r11, %%r12;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ +- " mulxq 48(%1), %%rax, %%r13;" " adcx %%rax, %%r12;" /* f[2]*f[3] */ ++ " mulxq 40(%1), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ ++ " mulxq 48(%1), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ + " movq 40(%1), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ + " mulxq 48(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + +@@ -662,12 +662,12 @@ static inline void fsqr2(u64 *out, const + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" + " adcx %%r9, %%r9;" +- " adox %%r15, %%r12;" ++ " adox %%r15, %%rbx;" + " adcx %%r10, %%r10;" + " adox %%r15, %%r13;" + " adcx %%r11, %%r11;" + " adox %%r15, %%r14;" +- " adcx %%r12, %%r12;" ++ " adcx %%rbx, %%rbx;" + " adcx %%r13, %%r13;" + " adcx %%r14, %%r14;" + +@@ -680,7 +680,7 @@ static inline void fsqr2(u64 *out, const + " adcx %%rcx, %%r10;" " movq %%r10, 88(%0);" + " movq 48(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ + " adcx %%rax, %%r11;" " movq %%r11, 96(%0);" +- " adcx %%rcx, %%r12;" " movq %%r12, 104(%0);" ++ " adcx %%rcx, %%rbx;" " movq %%rbx, 104(%0);" + " movq 56(%1), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ + " adcx %%rax, %%r13;" " movq %%r13, 112(%0);" + " adcx %%rcx, %%r14;" " movq %%r14, 120(%0);" +@@ -694,11 +694,11 @@ static inline void fsqr2(u64 *out, const + " mulxq 32(%1), %%r8, %%r13;" + " xor %%rcx, %%rcx;" + " adoxq 0(%1), %%r8;" +- " mulxq 40(%1), %%r9, %%r12;" ++ " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 8(%1), %%r9;" + " mulxq 48(%1), %%r10, %%r13;" +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " adoxq 16(%1), %%r10;" + " mulxq 56(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" +@@ -727,11 +727,11 @@ static inline void fsqr2(u64 *out, const + " mulxq 96(%1), %%r8, %%r13;" + " xor %%rcx, %%rcx;" + " adoxq 64(%1), %%r8;" +- " mulxq 104(%1), %%r9, %%r12;" ++ " mulxq 104(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" + " adoxq 72(%1), %%r9;" + " mulxq 112(%1), %%r10, %%r13;" +- " adcx %%r12, %%r10;" ++ " adcx %%rbx, %%r10;" + " adoxq 80(%1), %%r10;" + " mulxq 120(%1), %%r11, %%rax;" + " adcx %%r13, %%r11;" +@@ -756,7 +756,7 @@ static inline void fsqr2(u64 *out, const + " movq %%r8, 32(%0);" + : "+&r" (tmp), "+&r" (f), "+&r" (out) + : +- : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", "memory", "cc" ++ : "%rax", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%rbx", "%r13", "%r14", "%r15", "memory", "cc" + ); + } + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0056-crypto-arm-64-poly1305-add-artifact-to-.gitignore-fi.patch b/target/linux/generic/backport-5.4/080-wireguard-0056-crypto-arm-64-poly1305-add-artifact-to-.gitignore-fi.patch new file mode 100644 index 0000000000..528de4335e --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0056-crypto-arm-64-poly1305-add-artifact-to-.gitignore-fi.patch @@ -0,0 +1,36 @@ +From 216f24cb4aba8385025c38da0f79c4aa8e637484 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 19 Mar 2020 11:56:17 -0600 +Subject: [PATCH 056/124] crypto: arm[64]/poly1305 - add artifact to .gitignore + files + +commit 6e4e00d8b68ca7eb30d08afb740033e0d36abe55 upstream. + +The .S_shipped yields a .S, and the pattern in these directories is to +add that to .gitignore so that git-status doesn't raise a fuss. + +Fixes: a6b803b3ddc7 ("crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") +Fixes: f569ca164751 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") +Reported-by: Emil Renner Berthing +Cc: Ard Biesheuvel +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/.gitignore | 1 + + arch/arm64/crypto/.gitignore | 1 + + 2 files changed, 2 insertions(+) + +--- a/arch/arm/crypto/.gitignore ++++ b/arch/arm/crypto/.gitignore +@@ -1,3 +1,4 @@ + aesbs-core.S + sha256-core.S + sha512-core.S ++poly1305-core.S +--- a/arch/arm64/crypto/.gitignore ++++ b/arch/arm64/crypto/.gitignore +@@ -1,2 +1,3 @@ + sha256-core.S + sha512-core.S ++poly1305-core.S diff --git a/target/linux/generic/backport-5.4/080-wireguard-0057-crypto-arch-lib-limit-simd-usage-to-4k-chunks.patch b/target/linux/generic/backport-5.4/080-wireguard-0057-crypto-arch-lib-limit-simd-usage-to-4k-chunks.patch new file mode 100644 index 0000000000..bb0f5802a9 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0057-crypto-arch-lib-limit-simd-usage-to-4k-chunks.patch @@ -0,0 +1,243 @@ +From af386d2b1f9207290a12aa97ecec8b428f3bebb2 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 23 Apr 2020 15:54:04 -0600 +Subject: [PATCH 057/124] crypto: arch/lib - limit simd usage to 4k chunks + +commit 706024a52c614b478b63f7728d202532ce6591a9 upstream. + +The initial Zinc patchset, after some mailing list discussion, contained +code to ensure that kernel_fpu_enable would not be kept on for more than +a 4k chunk, since it disables preemption. The choice of 4k isn't totally +scientific, but it's not a bad guess either, and it's what's used in +both the x86 poly1305, blake2s, and nhpoly1305 code already (in the form +of PAGE_SIZE, which this commit corrects to be explicitly 4k for the +former two). + +Ard did some back of the envelope calculations and found that +at 5 cycles/byte (overestimate) on a 1ghz processor (pretty slow), 4k +means we have a maximum preemption disabling of 20us, which Sebastian +confirmed was probably a good limit. + +Unfortunately the chunking appears to have been left out of the final +patchset that added the glue code. So, this commit adds it back in. + +Fixes: 84e03fa39fbe ("crypto: x86/chacha - expose SIMD ChaCha routine as library function") +Fixes: b3aad5bad26a ("crypto: arm64/chacha - expose arm64 ChaCha routine as library function") +Fixes: a44a3430d71b ("crypto: arm/chacha - expose ARM ChaCha routine as library function") +Fixes: d7d7b8535662 ("crypto: x86/poly1305 - wire up faster implementations for kernel") +Fixes: f569ca164751 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") +Fixes: a6b803b3ddc7 ("crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") +Fixes: ed0356eda153 ("crypto: blake2s - x86_64 SIMD implementation") +Cc: Eric Biggers +Cc: Ard Biesheuvel +Cc: Sebastian Andrzej Siewior +Cc: stable@vger.kernel.org +Signed-off-by: Jason A. Donenfeld +Reviewed-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/chacha-glue.c | 14 +++++++++++--- + arch/arm/crypto/poly1305-glue.c | 15 +++++++++++---- + arch/arm64/crypto/chacha-neon-glue.c | 14 +++++++++++--- + arch/arm64/crypto/poly1305-glue.c | 15 +++++++++++---- + arch/x86/crypto/blake2s-glue.c | 10 ++++------ + arch/x86/crypto/chacha_glue.c | 14 +++++++++++--- + arch/x86/crypto/poly1305_glue.c | 13 ++++++------- + 7 files changed, 65 insertions(+), 30 deletions(-) + +--- a/arch/arm/crypto/chacha-glue.c ++++ b/arch/arm/crypto/chacha-glue.c +@@ -91,9 +91,17 @@ void chacha_crypt_arch(u32 *state, u8 *d + return; + } + +- kernel_neon_begin(); +- chacha_doneon(state, dst, src, bytes, nrounds); +- kernel_neon_end(); ++ 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); + +--- a/arch/arm/crypto/poly1305-glue.c ++++ b/arch/arm/crypto/poly1305-glue.c +@@ -160,13 +160,20 @@ void poly1305_update_arch(struct poly130 + unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); + + if (static_branch_likely(&have_neon) && do_neon) { +- kernel_neon_begin(); +- poly1305_blocks_neon(&dctx->h, src, len, 1); +- kernel_neon_end(); ++ 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; + } +- src += len; + nbytes %= POLY1305_BLOCK_SIZE; + } + +--- a/arch/arm64/crypto/chacha-neon-glue.c ++++ b/arch/arm64/crypto/chacha-neon-glue.c +@@ -87,9 +87,17 @@ void chacha_crypt_arch(u32 *state, u8 *d + !crypto_simd_usable()) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + +- kernel_neon_begin(); +- chacha_doneon(state, dst, src, bytes, nrounds); +- kernel_neon_end(); ++ 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); + +--- a/arch/arm64/crypto/poly1305-glue.c ++++ b/arch/arm64/crypto/poly1305-glue.c +@@ -143,13 +143,20 @@ void poly1305_update_arch(struct poly130 + unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); + + if (static_branch_likely(&have_neon) && crypto_simd_usable()) { +- kernel_neon_begin(); +- poly1305_blocks_neon(&dctx->h, src, len, 1); +- kernel_neon_end(); ++ 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(&dctx->h, src, len, 1); ++ src += len; + } +- src += len; + nbytes %= POLY1305_BLOCK_SIZE; + } + +--- a/arch/x86/crypto/blake2s-glue.c ++++ b/arch/x86/crypto/blake2s-glue.c +@@ -32,16 +32,16 @@ void blake2s_compress_arch(struct blake2 + const u32 inc) + { + /* SIMD disables preemption, so relax after processing each page. */ +- BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); ++ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); + + if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { + blake2s_compress_generic(state, block, nblocks, inc); + return; + } + +- for (;;) { ++ do { + const size_t blocks = min_t(size_t, nblocks, +- PAGE_SIZE / BLAKE2S_BLOCK_SIZE); ++ SZ_4K / BLAKE2S_BLOCK_SIZE); + + kernel_fpu_begin(); + if (IS_ENABLED(CONFIG_AS_AVX512) && +@@ -52,10 +52,8 @@ void blake2s_compress_arch(struct blake2 + kernel_fpu_end(); + + nblocks -= blocks; +- if (!nblocks) +- break; + block += blocks * BLAKE2S_BLOCK_SIZE; +- } ++ } while (nblocks); + } + EXPORT_SYMBOL(blake2s_compress_arch); + +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -154,9 +154,17 @@ void chacha_crypt_arch(u32 *state, u8 *d + bytes <= CHACHA_BLOCK_SIZE) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + +- kernel_fpu_begin(); +- chacha_dosimd(state, dst, src, bytes, nrounds); +- kernel_fpu_end(); ++ do { ++ unsigned int todo = min_t(unsigned int, bytes, SZ_4K); ++ ++ kernel_fpu_begin(); ++ chacha_dosimd(state, dst, src, todo, nrounds); ++ kernel_fpu_end(); ++ ++ bytes -= todo; ++ src += todo; ++ dst += todo; ++ } while (bytes); + } + EXPORT_SYMBOL(chacha_crypt_arch); + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -91,8 +91,8 @@ static void poly1305_simd_blocks(void *c + struct poly1305_arch_internal *state = ctx; + + /* SIMD disables preemption, so relax after processing each page. */ +- BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || +- PAGE_SIZE % POLY1305_BLOCK_SIZE); ++ BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || ++ SZ_4K % POLY1305_BLOCK_SIZE); + + if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || + (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || +@@ -102,8 +102,8 @@ static void poly1305_simd_blocks(void *c + return; + } + +- for (;;) { +- const size_t bytes = min_t(size_t, len, PAGE_SIZE); ++ do { ++ const size_t bytes = min_t(size_t, len, SZ_4K); + + kernel_fpu_begin(); + if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) +@@ -113,11 +113,10 @@ static void poly1305_simd_blocks(void *c + else + poly1305_blocks_avx(ctx, inp, bytes, padbit); + kernel_fpu_end(); ++ + len -= bytes; +- if (!len) +- break; + inp += bytes; +- } ++ } while (len); + } + + static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], diff --git a/target/linux/generic/backport-5.4/080-wireguard-0058-crypto-lib-chacha20poly1305-Add-missing-function-dec.patch b/target/linux/generic/backport-5.4/080-wireguard-0058-crypto-lib-chacha20poly1305-Add-missing-function-dec.patch new file mode 100644 index 0000000000..0653e3a8ba --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0058-crypto-lib-chacha20poly1305-Add-missing-function-dec.patch @@ -0,0 +1,38 @@ +From 58c2229461f888087fc3175650bc2e6aa70fd862 Mon Sep 17 00:00:00 2001 +From: Herbert Xu +Date: Wed, 8 Jul 2020 12:41:13 +1000 +Subject: [PATCH 058/124] crypto: lib/chacha20poly1305 - Add missing function + declaration + +commit 06cc2afbbdf9a9e8df3e2f8db724997dd6e1b4ac upstream. + +This patch adds a declaration for chacha20poly1305_selftest to +silence a sparse warning. + +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + include/crypto/chacha20poly1305.h | 2 ++ + lib/crypto/chacha20poly1305.c | 2 -- + 2 files changed, 2 insertions(+), 2 deletions(-) + +--- a/include/crypto/chacha20poly1305.h ++++ b/include/crypto/chacha20poly1305.h +@@ -45,4 +45,6 @@ bool chacha20poly1305_decrypt_sg_inplace + const u64 nonce, + const u8 key[CHACHA20POLY1305_KEY_SIZE]); + ++bool chacha20poly1305_selftest(void); ++ + #endif /* __CHACHA20POLY1305_H */ +--- a/lib/crypto/chacha20poly1305.c ++++ b/lib/crypto/chacha20poly1305.c +@@ -21,8 +21,6 @@ + + #define CHACHA_KEY_WORDS (CHACHA_KEY_SIZE / sizeof(u32)) + +-bool __init chacha20poly1305_selftest(void); +- + static void chacha_load_key(u32 *k, const u8 *in) + { + k[0] = get_unaligned_le32(in); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0059-crypto-x86-chacha-sse3-use-unaligned-loads-for-state.patch b/target/linux/generic/backport-5.4/080-wireguard-0059-crypto-x86-chacha-sse3-use-unaligned-loads-for-state.patch new file mode 100644 index 0000000000..652439393b --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0059-crypto-x86-chacha-sse3-use-unaligned-loads-for-state.patch @@ -0,0 +1,148 @@ +From 833ca409e17c10f4affb5879e22a03fdf1933439 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Wed, 8 Jul 2020 12:11:18 +0300 +Subject: [PATCH 059/124] crypto: x86/chacha-sse3 - use unaligned loads for + state array + +commit e79a31715193686e92dadb4caedfbb1f5de3659c upstream. + +Due to the fact that the x86 port does not support allocating objects +on the stack with an alignment that exceeds 8 bytes, we have a rather +ugly hack in the x86 code for ChaCha to ensure that the state array is +aligned to 16 bytes, allowing the SSE3 implementation of the algorithm +to use aligned loads. + +Given that the performance benefit of using of aligned loads appears to +be limited (~0.25% for 1k blocks using tcrypt on a Corei7-8650U), and +the fact that this hack has leaked into generic ChaCha code, let's just +remove it. + +Cc: Martin Willi +Cc: Herbert Xu +Cc: Eric Biggers +Signed-off-by: Ard Biesheuvel +Reviewed-by: Martin Willi +Reviewed-by: Eric Biggers +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/chacha-ssse3-x86_64.S | 16 ++++++++-------- + arch/x86/crypto/chacha_glue.c | 17 ++--------------- + include/crypto/chacha.h | 4 ---- + 3 files changed, 10 insertions(+), 27 deletions(-) + +--- a/arch/x86/crypto/chacha-ssse3-x86_64.S ++++ b/arch/x86/crypto/chacha-ssse3-x86_64.S +@@ -120,10 +120,10 @@ ENTRY(chacha_block_xor_ssse3) + FRAME_BEGIN + + # x0..3 = s0..3 +- movdqa 0x00(%rdi),%xmm0 +- movdqa 0x10(%rdi),%xmm1 +- movdqa 0x20(%rdi),%xmm2 +- movdqa 0x30(%rdi),%xmm3 ++ movdqu 0x00(%rdi),%xmm0 ++ movdqu 0x10(%rdi),%xmm1 ++ movdqu 0x20(%rdi),%xmm2 ++ movdqu 0x30(%rdi),%xmm3 + movdqa %xmm0,%xmm8 + movdqa %xmm1,%xmm9 + movdqa %xmm2,%xmm10 +@@ -205,10 +205,10 @@ ENTRY(hchacha_block_ssse3) + # %edx: nrounds + FRAME_BEGIN + +- movdqa 0x00(%rdi),%xmm0 +- movdqa 0x10(%rdi),%xmm1 +- movdqa 0x20(%rdi),%xmm2 +- movdqa 0x30(%rdi),%xmm3 ++ movdqu 0x00(%rdi),%xmm0 ++ movdqu 0x10(%rdi),%xmm1 ++ movdqu 0x20(%rdi),%xmm2 ++ movdqu 0x30(%rdi),%xmm3 + + mov %edx,%r8d + call chacha_permute +--- a/arch/x86/crypto/chacha_glue.c ++++ b/arch/x86/crypto/chacha_glue.c +@@ -14,8 +14,6 @@ + #include + #include + +-#define CHACHA_STATE_ALIGN 16 +- + asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src, + unsigned int len, int nrounds); + asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src, +@@ -125,8 +123,6 @@ static void chacha_dosimd(u32 *state, u8 + + void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds) + { +- state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); +- + if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) { + hchacha_block_generic(state, stream, nrounds); + } else { +@@ -139,8 +135,6 @@ EXPORT_SYMBOL(hchacha_block_arch); + + void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv) + { +- state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); +- + chacha_init_generic(state, key, iv); + } + EXPORT_SYMBOL(chacha_init_arch); +@@ -148,8 +142,6 @@ EXPORT_SYMBOL(chacha_init_arch); + void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, + int nrounds) + { +- state = PTR_ALIGN(state, CHACHA_STATE_ALIGN); +- + if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() || + bytes <= CHACHA_BLOCK_SIZE) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); +@@ -171,15 +163,12 @@ EXPORT_SYMBOL(chacha_crypt_arch); + static int chacha_simd_stream_xor(struct skcipher_request *req, + const struct chacha_ctx *ctx, const u8 *iv) + { +- u32 *state, state_buf[16 + 2] __aligned(8); ++ u32 state[CHACHA_STATE_WORDS] __aligned(8); + struct skcipher_walk walk; + int err; + + err = skcipher_walk_virt(&walk, req, false); + +- BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16); +- state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN); +- + chacha_init_generic(state, ctx->key, iv); + + while (walk.nbytes > 0) { +@@ -218,12 +207,10 @@ static int xchacha_simd(struct skcipher_ + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); +- u32 *state, state_buf[16 + 2] __aligned(8); ++ u32 state[CHACHA_STATE_WORDS] __aligned(8); + struct chacha_ctx subctx; + u8 real_iv[16]; + +- BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16); +- state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN); + chacha_init_generic(state, ctx->key, req->iv); + + if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) { +--- a/include/crypto/chacha.h ++++ b/include/crypto/chacha.h +@@ -25,11 +25,7 @@ + #define CHACHA_BLOCK_SIZE 64 + #define CHACHAPOLY_IV_SIZE 12 + +-#ifdef CONFIG_X86_64 +-#define CHACHA_STATE_WORDS ((CHACHA_BLOCK_SIZE + 12) / sizeof(u32)) +-#else + #define CHACHA_STATE_WORDS (CHACHA_BLOCK_SIZE / sizeof(u32)) +-#endif + + /* 192-bit nonce, then 64-bit stream position */ + #define XCHACHA_IV_SIZE 32 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0060-crypto-x86-curve25519-Remove-unused-carry-variables.patch b/target/linux/generic/backport-5.4/080-wireguard-0060-crypto-x86-curve25519-Remove-unused-carry-variables.patch new file mode 100644 index 0000000000..9c7c3c7bcc --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0060-crypto-x86-curve25519-Remove-unused-carry-variables.patch @@ -0,0 +1,47 @@ +From 9cfd2787b0b37940c656c6ea5fede6b3c360f0e5 Mon Sep 17 00:00:00 2001 +From: Herbert Xu +Date: Thu, 23 Jul 2020 17:50:48 +1000 +Subject: [PATCH 060/124] crypto: x86/curve25519 - Remove unused carry + variables + +commit 054a5540fb8f7268e2c79e9deab4242db15c8cba upstream. + +The carry variables are assigned but never used, which upsets +the compiler. This patch removes them. + +Signed-off-by: Herbert Xu +Reviewed-by: Karthikeyan Bhargavan +Acked-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/curve25519-x86_64.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +--- a/arch/x86/crypto/curve25519-x86_64.c ++++ b/arch/x86/crypto/curve25519-x86_64.c +@@ -948,10 +948,8 @@ static void store_felem(u64 *b, u64 *f) + { + u64 f30 = f[3U]; + u64 top_bit0 = f30 >> (u32)63U; +- u64 carry0; + u64 f31; + u64 top_bit; +- u64 carry; + u64 f0; + u64 f1; + u64 f2; +@@ -970,11 +968,11 @@ static void store_felem(u64 *b, u64 *f) + u64 o2; + u64 o3; + f[3U] = f30 & (u64)0x7fffffffffffffffU; +- carry0 = add_scalar(f, f, (u64)19U * top_bit0); ++ add_scalar(f, f, (u64)19U * top_bit0); + f31 = f[3U]; + top_bit = f31 >> (u32)63U; + f[3U] = f31 & (u64)0x7fffffffffffffffU; +- carry = add_scalar(f, f, (u64)19U * top_bit); ++ add_scalar(f, f, (u64)19U * top_bit); + f0 = f[0U]; + f1 = f[1U]; + f2 = f[2U]; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0061-crypto-arm-curve25519-include-linux-scatterlist.h.patch b/target/linux/generic/backport-5.4/080-wireguard-0061-crypto-arm-curve25519-include-linux-scatterlist.h.patch new file mode 100644 index 0000000000..e1857f82b9 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0061-crypto-arm-curve25519-include-linux-scatterlist.h.patch @@ -0,0 +1,37 @@ +From 6ae9f0d421af5145d457c51abe2b704ebb297a17 Mon Sep 17 00:00:00 2001 +From: Fabio Estevam +Date: Mon, 24 Aug 2020 11:09:53 -0300 +Subject: [PATCH 061/124] crypto: arm/curve25519 - include + + +commit 6779d0e6b0fe193ab3010ea201782ca6f75a3862 upstream. + +Building ARM allmodconfig leads to the following warnings: + +arch/arm/crypto/curve25519-glue.c:73:12: error: implicit declaration of function 'sg_copy_to_buffer' [-Werror=implicit-function-declaration] +arch/arm/crypto/curve25519-glue.c:74:9: error: implicit declaration of function 'sg_nents_for_len' [-Werror=implicit-function-declaration] +arch/arm/crypto/curve25519-glue.c:88:11: error: implicit declaration of function 'sg_copy_from_buffer' [-Werror=implicit-function-declaration] + +Include to fix such warnings + +Reported-by: Olof's autobuilder +Fixes: 0c3dc787a62a ("crypto: algapi - Remove skbuff.h inclusion") +Signed-off-by: Fabio Estevam +Acked-by: Ard Biesheuvel +Acked-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/curve25519-glue.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/arch/arm/crypto/curve25519-glue.c ++++ b/arch/arm/crypto/curve25519-glue.c +@@ -16,6 +16,7 @@ + #include + #include + #include ++#include + #include + + asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE], diff --git a/target/linux/generic/backport-5.4/080-wireguard-0062-crypto-arm-poly1305-Add-prototype-for-poly1305_block.patch b/target/linux/generic/backport-5.4/080-wireguard-0062-crypto-arm-poly1305-Add-prototype-for-poly1305_block.patch new file mode 100644 index 0000000000..7cdf0dbdaf --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0062-crypto-arm-poly1305-Add-prototype-for-poly1305_block.patch @@ -0,0 +1,34 @@ +From 55a3d2044f411ecf291777f31053b8d8ee81c051 Mon Sep 17 00:00:00 2001 +From: Herbert Xu +Date: Tue, 25 Aug 2020 11:23:00 +1000 +Subject: [PATCH 062/124] crypto: arm/poly1305 - Add prototype for + poly1305_blocks_neon + +commit 51982ea02aef972132eb35c583d3e4c5b83166e5 upstream. + +This patch adds a prototype for poly1305_blocks_neon to slience +a compiler warning: + + CC [M] arch/arm/crypto/poly1305-glue.o +../arch/arm/crypto/poly1305-glue.c:25:13: warning: no previous prototype for `poly1305_blocks_neon' [-Wmissing-prototypes] + void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit) + ^~~~~~~~~~~~~~~~~~~~ + +Signed-off-by: Herbert Xu +Acked-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/poly1305-glue.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/arch/arm/crypto/poly1305-glue.c ++++ b/arch/arm/crypto/poly1305-glue.c +@@ -20,6 +20,7 @@ + + 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) diff --git a/target/linux/generic/backport-5.4/080-wireguard-0063-crypto-curve25519-x86_64-Use-XORL-r32-32.patch b/target/linux/generic/backport-5.4/080-wireguard-0063-crypto-curve25519-x86_64-Use-XORL-r32-32.patch new file mode 100644 index 0000000000..9c2d666d01 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0063-crypto-curve25519-x86_64-Use-XORL-r32-32.patch @@ -0,0 +1,261 @@ +From 4c4ab112443b42603d57b698111b55bfec278001 Mon Sep 17 00:00:00 2001 +From: Uros Bizjak +Date: Thu, 27 Aug 2020 19:30:58 +0200 +Subject: [PATCH 063/124] crypto: curve25519-x86_64 - Use XORL r32,32 + +commit db719539fd3889836900bf912755aa30a5985e9a upstream. + +x86_64 zero extends 32bit operations, so for 64bit operands, +XORL r32,r32 is functionally equal to XORL r64,r64, but avoids +a REX prefix byte when legacy registers are used. + +Signed-off-by: Uros Bizjak +Cc: Herbert Xu +Cc: "David S. Miller" +Acked-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/curve25519-x86_64.c | 68 ++++++++++++++--------------- + 1 file changed, 34 insertions(+), 34 deletions(-) + +--- a/arch/x86/crypto/curve25519-x86_64.c ++++ b/arch/x86/crypto/curve25519-x86_64.c +@@ -45,11 +45,11 @@ static inline u64 add_scalar(u64 *out, c + + asm volatile( + /* Clear registers to propagate the carry bit */ +- " xor %%r8, %%r8;" +- " xor %%r9, %%r9;" +- " xor %%r10, %%r10;" +- " xor %%r11, %%r11;" +- " xor %1, %1;" ++ " xor %%r8d, %%r8d;" ++ " xor %%r9d, %%r9d;" ++ " xor %%r10d, %%r10d;" ++ " xor %%r11d, %%r11d;" ++ " xor %k1, %k1;" + + /* Begin addition chain */ + " addq 0(%3), %0;" +@@ -93,7 +93,7 @@ static inline void fadd(u64 *out, const + " cmovc %0, %%rax;" + + /* Step 2: Add carry*38 to the original sum */ +- " xor %%rcx, %%rcx;" ++ " xor %%ecx, %%ecx;" + " add %%rax, %%r8;" + " adcx %%rcx, %%r9;" + " movq %%r9, 8(%1);" +@@ -165,28 +165,28 @@ static inline void fmul(u64 *out, const + + /* Compute src1[0] * src2 */ + " movq 0(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 8(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 16(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 24(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" +@@ -200,7 +200,7 @@ static inline void fmul(u64 *out, const + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" +- " xor %3, %3;" ++ " xor %k3, %k3;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" +@@ -246,28 +246,28 @@ static inline void fmul2(u64 *out, const + + /* Compute src1[0] * src2 */ + " movq 0(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 0(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 8(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%0), %%r8;" " movq %%r8, 8(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 16(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%0), %%r8;" " movq %%r8, 16(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 24(%1), %%rdx;" +- " mulxq 0(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" ++ " mulxq 0(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%0), %%r8;" " movq %%r8, 24(%0);" + " mulxq 8(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%0);" + " mulxq 16(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%0);" " mov $0, %%r8;" + " mulxq 24(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%0);" " mov $0, %%rax;" +@@ -277,29 +277,29 @@ static inline void fmul2(u64 *out, const + + /* Compute src1[0] * src2 */ + " movq 32(%1), %%rdx;" +- " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " movq %%r8, 64(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 64(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" + /* Compute src1[1] * src2 */ + " movq 40(%1), %%rdx;" +- " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%0);" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 72(%0), %%r8;" " movq %%r8, 72(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[2] * src2 */ + " movq 48(%1), %%rdx;" +- " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%0);" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 80(%0), %%r8;" " movq %%r8, 80(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" + /* Compute src1[3] * src2 */ + " movq 56(%1), %%rdx;" +- " mulxq 32(%3), %%r8, %%r9;" " xor %%r10, %%r10;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" +- " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%0);" ++ " mulxq 32(%3), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 88(%0), %%r8;" " movq %%r8, 88(%0);" ++ " mulxq 40(%3), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%0);" + " mulxq 48(%3), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 104(%0);" " mov $0, %%r8;" + " mulxq 56(%3), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%0);" " mov $0, %%rax;" + " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%0);" +@@ -312,7 +312,7 @@ static inline void fmul2(u64 *out, const + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" +- " xor %3, %3;" ++ " xor %k3, %k3;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" +@@ -345,7 +345,7 @@ static inline void fmul2(u64 *out, const + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 96(%1), %%r8, %%r13;" +- " xor %3, %3;" ++ " xor %k3, %k3;" + " adoxq 64(%1), %%r8;" + " mulxq 104(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" +@@ -516,7 +516,7 @@ static inline void fsqr(u64 *out, const + + /* Step 1: Compute all partial products */ + " movq 0(%1), %%rdx;" /* f[0] */ +- " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ ++ " mulxq 8(%1), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ + " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 24(%1), %%rdx;" /* f[3] */ +@@ -526,7 +526,7 @@ static inline void fsqr(u64 *out, const + " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + + /* Step 2: Compute two parallel carry chains */ +- " xor %%r15, %%r15;" ++ " xor %%r15d, %%r15d;" + " adox %%rax, %%r10;" + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" +@@ -563,7 +563,7 @@ static inline void fsqr(u64 *out, const + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" +- " xor %%rcx, %%rcx;" ++ " xor %%ecx, %%ecx;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" +@@ -607,7 +607,7 @@ static inline void fsqr2(u64 *out, const + asm volatile( + /* Step 1: Compute all partial products */ + " movq 0(%1), %%rdx;" /* f[0] */ +- " mulxq 8(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ ++ " mulxq 8(%1), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ + " mulxq 16(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 24(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 24(%1), %%rdx;" /* f[3] */ +@@ -617,7 +617,7 @@ static inline void fsqr2(u64 *out, const + " mulxq 16(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + + /* Step 2: Compute two parallel carry chains */ +- " xor %%r15, %%r15;" ++ " xor %%r15d, %%r15d;" + " adox %%rax, %%r10;" + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" +@@ -647,7 +647,7 @@ static inline void fsqr2(u64 *out, const + + /* Step 1: Compute all partial products */ + " movq 32(%1), %%rdx;" /* f[0] */ +- " mulxq 40(%1), %%r8, %%r14;" " xor %%r15, %%r15;" /* f[1]*f[0] */ ++ " mulxq 40(%1), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ + " mulxq 48(%1), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ + " mulxq 56(%1), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ + " movq 56(%1), %%rdx;" /* f[3] */ +@@ -657,7 +657,7 @@ static inline void fsqr2(u64 *out, const + " mulxq 48(%1), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ + + /* Step 2: Compute two parallel carry chains */ +- " xor %%r15, %%r15;" ++ " xor %%r15d, %%r15d;" + " adox %%rax, %%r10;" + " adcx %%r8, %%r8;" + " adox %%rcx, %%r11;" +@@ -692,7 +692,7 @@ static inline void fsqr2(u64 *out, const + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 32(%1), %%r8, %%r13;" +- " xor %%rcx, %%rcx;" ++ " xor %%ecx, %%ecx;" + " adoxq 0(%1), %%r8;" + " mulxq 40(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" +@@ -725,7 +725,7 @@ static inline void fsqr2(u64 *out, const + /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ + " mov $38, %%rdx;" + " mulxq 96(%1), %%r8, %%r13;" +- " xor %%rcx, %%rcx;" ++ " xor %%ecx, %%ecx;" + " adoxq 64(%1), %%r8;" + " mulxq 104(%1), %%r9, %%rbx;" + " adcx %%r13, %%r9;" diff --git a/target/linux/generic/backport-5.4/080-wireguard-0064-crypto-poly1305-x86_64-Use-XORL-r32-32.patch b/target/linux/generic/backport-5.4/080-wireguard-0064-crypto-poly1305-x86_64-Use-XORL-r32-32.patch new file mode 100644 index 0000000000..fa5c1882da --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0064-crypto-poly1305-x86_64-Use-XORL-r32-32.patch @@ -0,0 +1,59 @@ +From a2c7d387da3b3cdb8b7c16ef91cce45f92ebcf61 Mon Sep 17 00:00:00 2001 +From: Uros Bizjak +Date: Thu, 27 Aug 2020 19:38:31 +0200 +Subject: [PATCH 064/124] crypto: poly1305-x86_64 - Use XORL r32,32 + +commit 7dfd1e01b3dfc13431b1b25720cf2692a7e111ef upstream. + +x86_64 zero extends 32bit operations, so for 64bit operands, +XORL r32,r32 is functionally equal to XORQ r64,r64, but avoids +a REX prefix byte when legacy registers are used. + +Signed-off-by: Uros Bizjak +Cc: Herbert Xu +Cc: "David S. Miller" +Acked-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl ++++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +@@ -246,7 +246,7 @@ $code.=<<___ if (!$kernel); + ___ + &declare_function("poly1305_init_x86_64", 32, 3); + $code.=<<___; +- xor %rax,%rax ++ xor %eax,%eax + mov %rax,0($ctx) # initialize hash value + mov %rax,8($ctx) + mov %rax,16($ctx) +@@ -2869,7 +2869,7 @@ $code.=<<___; + .type poly1305_init_base2_44,\@function,3 + .align 32 + poly1305_init_base2_44: +- xor %rax,%rax ++ xor %eax,%eax + mov %rax,0($ctx) # initialize hash value + mov %rax,8($ctx) + mov %rax,16($ctx) +@@ -3963,7 +3963,7 @@ xor128_decrypt_n_pad: + mov \$16,$len + sub %r10,$len + xor %eax,%eax +- xor %r11,%r11 ++ xor %r11d,%r11d + .Loop_dec_byte: + mov ($inp,$otp),%r11b + mov ($otp),%al +@@ -4101,7 +4101,7 @@ avx_handler: + .long 0xa548f3fc # cld; rep movsq + + mov $disp,%rsi +- xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER ++ xor %ecx,%ecx # arg1, UNW_FLAG_NHANDLER + mov 8(%rsi),%rdx # arg2, disp->ImageBase + mov 0(%rsi),%r8 # arg3, disp->ControlPc + mov 16(%rsi),%r9 # arg4, disp->FunctionEntry diff --git a/target/linux/generic/backport-5.4/080-wireguard-0065-crypto-x86-poly1305-Remove-assignments-with-no-effec.patch b/target/linux/generic/backport-5.4/080-wireguard-0065-crypto-x86-poly1305-Remove-assignments-with-no-effec.patch new file mode 100644 index 0000000000..0f8c836da9 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0065-crypto-x86-poly1305-Remove-assignments-with-no-effec.patch @@ -0,0 +1,30 @@ +From 5502c4d51b8c27631ed1026ef172bd9ce58303d2 Mon Sep 17 00:00:00 2001 +From: Herbert Xu +Date: Thu, 24 Sep 2020 13:29:04 +1000 +Subject: [PATCH 065/124] crypto: x86/poly1305 - Remove assignments with no + effect + +commit 4a0c1de64bf9d9027a6f19adfba89fc27893db23 upstream. + +This patch removes a few ineffectual assignments from the function +crypto_poly1305_setdctxkey. + +Reported-by: kernel test robot +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 3 --- + 1 file changed, 3 deletions(-) + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -157,9 +157,6 @@ static unsigned int crypto_poly1305_setd + dctx->s[1] = get_unaligned_le32(&inp[4]); + dctx->s[2] = get_unaligned_le32(&inp[8]); + dctx->s[3] = get_unaligned_le32(&inp[12]); +- inp += POLY1305_BLOCK_SIZE; +- len -= POLY1305_BLOCK_SIZE; +- acc += POLY1305_BLOCK_SIZE; + dctx->sset = true; + } + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0066-crypto-x86-poly1305-add-back-a-needed-assignment.patch b/target/linux/generic/backport-5.4/080-wireguard-0066-crypto-x86-poly1305-add-back-a-needed-assignment.patch new file mode 100644 index 0000000000..aebedb0282 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0066-crypto-x86-poly1305-add-back-a-needed-assignment.patch @@ -0,0 +1,33 @@ +From 4849474f7e021d0d2e33a008abf93cacebf812f4 Mon Sep 17 00:00:00 2001 +From: Eric Biggers +Date: Fri, 23 Oct 2020 15:27:48 -0700 +Subject: [PATCH 066/124] crypto: x86/poly1305 - add back a needed assignment + +commit c3a98c3ad5c0dc60a1ac66bf91147a3f39cac96b upstream. + +One of the assignments that was removed by commit 4a0c1de64bf9 ("crypto: +x86/poly1305 - Remove assignments with no effect") is actually needed, +since it affects the return value. + +This fixes the following crypto self-test failure: + + alg: shash: poly1305-simd test failed (wrong result) on test vector 2, cfg="init+update+final aligned buffer" + +Fixes: 4a0c1de64bf9 ("crypto: x86/poly1305 - Remove assignments with no effect") +Signed-off-by: Eric Biggers +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/x86/crypto/poly1305_glue.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/arch/x86/crypto/poly1305_glue.c ++++ b/arch/x86/crypto/poly1305_glue.c +@@ -157,6 +157,7 @@ static unsigned int crypto_poly1305_setd + dctx->s[1] = get_unaligned_le32(&inp[4]); + dctx->s[2] = get_unaligned_le32(&inp[8]); + dctx->s[3] = get_unaligned_le32(&inp[12]); ++ acc += POLY1305_BLOCK_SIZE; + dctx->sset = true; + } + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0067-crypto-Kconfig-CRYPTO_MANAGER_EXTRA_TESTS-requires-t.patch b/target/linux/generic/backport-5.4/080-wireguard-0067-crypto-Kconfig-CRYPTO_MANAGER_EXTRA_TESTS-requires-t.patch new file mode 100644 index 0000000000..430737e0c0 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0067-crypto-Kconfig-CRYPTO_MANAGER_EXTRA_TESTS-requires-t.patch @@ -0,0 +1,33 @@ +From 4517445d7df86d35d348f884a228e6979113d485 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 2 Nov 2020 14:48:15 +0100 +Subject: [PATCH 067/124] crypto: Kconfig - CRYPTO_MANAGER_EXTRA_TESTS requires + the manager + +commit 6569e3097f1c4a490bdf2b23d326855e04942dfd upstream. + +The extra tests in the manager actually require the manager to be +selected too. Otherwise the linker gives errors like: + +ld: arch/x86/crypto/chacha_glue.o: in function `chacha_simd_stream_xor': +chacha_glue.c:(.text+0x422): undefined reference to `crypto_simd_disabled_for_test' + +Fixes: 2343d1529aff ("crypto: Kconfig - allow tests to be disabled when manager is disabled") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + crypto/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/crypto/Kconfig ++++ b/crypto/Kconfig +@@ -145,7 +145,7 @@ config CRYPTO_MANAGER_DISABLE_TESTS + + config CRYPTO_MANAGER_EXTRA_TESTS + bool "Enable extra run-time crypto self tests" +- depends on DEBUG_KERNEL && !CRYPTO_MANAGER_DISABLE_TESTS ++ depends on DEBUG_KERNEL && !CRYPTO_MANAGER_DISABLE_TESTS && CRYPTO_MANAGER + help + Enable extra run-time self tests of registered crypto algorithms, + including randomized fuzz tests. diff --git a/target/linux/generic/backport-5.4/080-wireguard-0068-crypto-arm-chacha-neon-optimize-for-non-block-size-m.patch b/target/linux/generic/backport-5.4/080-wireguard-0068-crypto-arm-chacha-neon-optimize-for-non-block-size-m.patch new file mode 100644 index 0000000000..2ecdbec380 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0068-crypto-arm-chacha-neon-optimize-for-non-block-size-m.patch @@ -0,0 +1,272 @@ +From de69c3a866f93a10d86d25d04af54a722bebc420 Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Tue, 3 Nov 2020 17:28:09 +0100 +Subject: [PATCH 068/124] crypto: arm/chacha-neon - optimize for non-block size + multiples + +commit 86cd97ec4b943af35562a74688bc4e909b32c3d1 upstream. + +The current NEON based ChaCha implementation for ARM is optimized for +multiples of 4x the ChaCha block size (64 bytes). This makes sense for +block encryption, but given that ChaCha is also often used in the +context of networking, it makes sense to consider arbitrary length +inputs as well. + +For example, WireGuard typically uses 1420 byte packets, and performing +ChaCha encryption involves 5 invocations of chacha_4block_xor_neon() +and 3 invocations of chacha_block_xor_neon(), where the last one also +involves a memcpy() using a buffer on the stack to process the final +chunk of 1420 % 64 == 12 bytes. + +Let's optimize for this case as well, by letting chacha_4block_xor_neon() +deal with any input size between 64 and 256 bytes, using NEON permutation +instructions and overlapping loads and stores. This way, the 140 byte +tail of a 1420 byte input buffer can simply be processed in one go. + +This results in the following performance improvements for 1420 byte +blocks, without significant impact on power-of-2 input sizes. (Note +that Raspberry Pi is widely used in combination with a 32-bit kernel, +even though the core is 64-bit capable) + + Cortex-A8 (BeagleBone) : 7% + Cortex-A15 (Calxeda Midway) : 21% + Cortex-A53 (Raspberry Pi 3) : 3% + Cortex-A72 (Raspberry Pi 4) : 19% + +Cc: Eric Biggers +Cc: "Jason A . Donenfeld" +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm/crypto/chacha-glue.c | 34 +++++------ + arch/arm/crypto/chacha-neon-core.S | 97 +++++++++++++++++++++++++++--- + 2 files changed, 107 insertions(+), 24 deletions(-) + +--- a/arch/arm/crypto/chacha-glue.c ++++ b/arch/arm/crypto/chacha-glue.c +@@ -23,7 +23,7 @@ + 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); ++ 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); + +@@ -42,24 +42,24 @@ static void chacha_doneon(u32 *state, u8 + { + u8 buf[CHACHA_BLOCK_SIZE]; + +- while (bytes >= CHACHA_BLOCK_SIZE * 4) { +- chacha_4block_xor_neon(state, dst, src, nrounds); +- bytes -= CHACHA_BLOCK_SIZE * 4; +- src += CHACHA_BLOCK_SIZE * 4; +- dst += CHACHA_BLOCK_SIZE * 4; +- state[12] += 4; +- } +- while (bytes >= CHACHA_BLOCK_SIZE) { +- chacha_block_xor_neon(state, dst, src, nrounds); +- bytes -= CHACHA_BLOCK_SIZE; +- src += CHACHA_BLOCK_SIZE; +- dst += CHACHA_BLOCK_SIZE; +- state[12]++; ++ 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) { +- memcpy(buf, src, bytes); +- chacha_block_xor_neon(state, buf, buf, nrounds); +- memcpy(dst, buf, 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); + } + } + +--- a/arch/arm/crypto/chacha-neon-core.S ++++ b/arch/arm/crypto/chacha-neon-core.S +@@ -47,6 +47,7 @@ + */ + + #include ++#include + + .text + .fpu neon +@@ -205,7 +206,7 @@ ENDPROC(hchacha_block_neon) + + .align 5 + ENTRY(chacha_4block_xor_neon) +- push {r4-r5} ++ 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 +@@ -229,10 +230,10 @@ ENTRY(chacha_4block_xor_neon) + vld1.32 {q0-q1}, [r0] + vld1.32 {q2-q3}, [ip] + +- adr r5, .Lctrinc ++ adr lr, .Lctrinc + vdup.32 q15, d7[1] + vdup.32 q14, d7[0] +- vld1.32 {q4}, [r5, :128] ++ vld1.32 {q4}, [lr, :128] + vdup.32 q13, d6[1] + vdup.32 q12, d6[0] + vdup.32 q11, d5[1] +@@ -455,7 +456,7 @@ ENTRY(chacha_4block_xor_neon) + + // 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}, [r5, :128] // load counter values 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) +@@ -493,6 +494,8 @@ ENTRY(chacha_4block_xor_neon) + + // 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) +@@ -520,41 +523,121 @@ ENTRY(chacha_4block_xor_neon) + // 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] +- mov sp, r4 // restore original stack pointer + veor q0, q0, q11 + veor q1, q1, q15 + vst1.8 {q0-q1}, [r1] + +- pop {r4-r5} +- bx lr ++ 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/target/linux/generic/backport-5.4/080-wireguard-0069-crypto-arm64-chacha-simplify-tail-block-handling.patch b/target/linux/generic/backport-5.4/080-wireguard-0069-crypto-arm64-chacha-simplify-tail-block-handling.patch new file mode 100644 index 0000000000..55e16247d9 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0069-crypto-arm64-chacha-simplify-tail-block-handling.patch @@ -0,0 +1,324 @@ +From af8c75e27b20e01464aa6ad43ca3095534c81a8b Mon Sep 17 00:00:00 2001 +From: Ard Biesheuvel +Date: Fri, 6 Nov 2020 17:39:38 +0100 +Subject: [PATCH 069/124] crypto: arm64/chacha - simplify tail block handling + +commit c4fc6328d6c67690a7e6e03f43a5a976a13120ef upstream. + +Based on lessons learnt from optimizing the 32-bit version of this driver, +we can simplify the arm64 version considerably, by reordering the final +two stores when the last block is not a multiple of 64 bytes. This removes +the need to use permutation instructions to calculate the elements that are +clobbered by the final overlapping store, given that the store of the +penultimate block now follows it, and that one carries the correct values +for those elements already. + +While at it, simplify the overlapping loads as well, by calculating the +address of the final overlapping load upfront, and switching to this +address for every load that would otherwise extend past the end of the +source buffer. + +There is no impact on performance, but the resulting code is substantially +smaller and easier to follow. + +Cc: Eric Biggers +Cc: "Jason A . Donenfeld" +Signed-off-by: Ard Biesheuvel +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + arch/arm64/crypto/chacha-neon-core.S | 193 ++++++++++----------------- + 1 file changed, 69 insertions(+), 124 deletions(-) + +--- a/arch/arm64/crypto/chacha-neon-core.S ++++ b/arch/arm64/crypto/chacha-neon-core.S +@@ -195,7 +195,6 @@ ENTRY(chacha_4block_xor_neon) + adr_l x10, .Lpermute + and x5, x4, #63 + add x10, x10, x5 +- add x11, x10, #64 + + // + // This function encrypts four consecutive ChaCha blocks by loading +@@ -645,11 +644,11 @@ CPU_BE( rev a15, a15 ) + zip2 v31.4s, v14.4s, v15.4s + eor a15, a15, w9 + +- mov x3, #64 ++ add x3, x2, x4 ++ sub x3, x3, #128 // start of last block ++ + subs x5, x4, #128 +- add x6, x5, x2 +- csel x3, x3, xzr, ge +- csel x2, x2, x6, ge ++ csel x2, x2, x3, ge + + // interleave 64-bit words in state n, n+2 + zip1 v0.2d, v16.2d, v18.2d +@@ -658,13 +657,10 @@ CPU_BE( rev a15, a15 ) + zip1 v8.2d, v17.2d, v19.2d + zip2 v12.2d, v17.2d, v19.2d + stp a2, a3, [x1, #-56] +- ld1 {v16.16b-v19.16b}, [x2], x3 + + subs x6, x4, #192 +- ccmp x3, xzr, #4, lt +- add x7, x6, x2 +- csel x3, x3, xzr, eq +- csel x2, x2, x7, eq ++ ld1 {v16.16b-v19.16b}, [x2], #64 ++ csel x2, x2, x3, ge + + zip1 v1.2d, v20.2d, v22.2d + zip2 v5.2d, v20.2d, v22.2d +@@ -672,13 +668,10 @@ CPU_BE( rev a15, a15 ) + zip1 v9.2d, v21.2d, v23.2d + zip2 v13.2d, v21.2d, v23.2d + stp a6, a7, [x1, #-40] +- ld1 {v20.16b-v23.16b}, [x2], x3 + + subs x7, x4, #256 +- ccmp x3, xzr, #4, lt +- add x8, x7, x2 +- csel x3, x3, xzr, eq +- csel x2, x2, x8, eq ++ ld1 {v20.16b-v23.16b}, [x2], #64 ++ csel x2, x2, x3, ge + + zip1 v2.2d, v24.2d, v26.2d + zip2 v6.2d, v24.2d, v26.2d +@@ -686,12 +679,10 @@ CPU_BE( rev a15, a15 ) + zip1 v10.2d, v25.2d, v27.2d + zip2 v14.2d, v25.2d, v27.2d + stp a10, a11, [x1, #-24] +- ld1 {v24.16b-v27.16b}, [x2], x3 + + subs x8, x4, #320 +- ccmp x3, xzr, #4, lt +- add x9, x8, x2 +- csel x2, x2, x9, eq ++ ld1 {v24.16b-v27.16b}, [x2], #64 ++ csel x2, x2, x3, ge + + zip1 v3.2d, v28.2d, v30.2d + zip2 v7.2d, v28.2d, v30.2d +@@ -699,151 +690,105 @@ CPU_BE( rev a15, a15 ) + zip1 v11.2d, v29.2d, v31.2d + zip2 v15.2d, v29.2d, v31.2d + stp a14, a15, [x1, #-8] ++ ++ tbnz x5, #63, .Lt128 + ld1 {v28.16b-v31.16b}, [x2] + + // xor with corresponding input, write to output +- tbnz x5, #63, 0f + eor v16.16b, v16.16b, v0.16b + eor v17.16b, v17.16b, v1.16b + eor v18.16b, v18.16b, v2.16b + eor v19.16b, v19.16b, v3.16b +- st1 {v16.16b-v19.16b}, [x1], #64 +- cbz x5, .Lout + +- tbnz x6, #63, 1f ++ tbnz x6, #63, .Lt192 ++ + eor v20.16b, v20.16b, v4.16b + eor v21.16b, v21.16b, v5.16b + eor v22.16b, v22.16b, v6.16b + eor v23.16b, v23.16b, v7.16b +- st1 {v20.16b-v23.16b}, [x1], #64 +- cbz x6, .Lout + +- tbnz x7, #63, 2f ++ st1 {v16.16b-v19.16b}, [x1], #64 ++ tbnz x7, #63, .Lt256 ++ + eor v24.16b, v24.16b, v8.16b + eor v25.16b, v25.16b, v9.16b + eor v26.16b, v26.16b, v10.16b + eor v27.16b, v27.16b, v11.16b +- st1 {v24.16b-v27.16b}, [x1], #64 +- cbz x7, .Lout + +- tbnz x8, #63, 3f ++ st1 {v20.16b-v23.16b}, [x1], #64 ++ tbnz x8, #63, .Lt320 ++ + eor v28.16b, v28.16b, v12.16b + eor v29.16b, v29.16b, v13.16b + eor v30.16b, v30.16b, v14.16b + eor v31.16b, v31.16b, v15.16b ++ ++ st1 {v24.16b-v27.16b}, [x1], #64 + st1 {v28.16b-v31.16b}, [x1] + + .Lout: frame_pop + ret + +- // fewer than 128 bytes of in/output +-0: ld1 {v8.16b}, [x10] +- ld1 {v9.16b}, [x11] +- movi v10.16b, #16 +- sub x2, x1, #64 +- add x1, x1, x5 +- ld1 {v16.16b-v19.16b}, [x2] +- tbl v4.16b, {v0.16b-v3.16b}, v8.16b +- tbx v20.16b, {v16.16b-v19.16b}, v9.16b +- add v8.16b, v8.16b, v10.16b +- add v9.16b, v9.16b, v10.16b +- tbl v5.16b, {v0.16b-v3.16b}, v8.16b +- tbx v21.16b, {v16.16b-v19.16b}, v9.16b +- add v8.16b, v8.16b, v10.16b +- add v9.16b, v9.16b, v10.16b +- tbl v6.16b, {v0.16b-v3.16b}, v8.16b +- tbx v22.16b, {v16.16b-v19.16b}, v9.16b +- add v8.16b, v8.16b, v10.16b +- add v9.16b, v9.16b, v10.16b +- tbl v7.16b, {v0.16b-v3.16b}, v8.16b +- tbx v23.16b, {v16.16b-v19.16b}, v9.16b +- +- eor v20.16b, v20.16b, v4.16b +- eor v21.16b, v21.16b, v5.16b +- eor v22.16b, v22.16b, v6.16b +- eor v23.16b, v23.16b, v7.16b +- st1 {v20.16b-v23.16b}, [x1] +- b .Lout +- + // fewer than 192 bytes of in/output +-1: ld1 {v8.16b}, [x10] +- ld1 {v9.16b}, [x11] +- movi v10.16b, #16 +- add x1, x1, x6 +- tbl v0.16b, {v4.16b-v7.16b}, v8.16b +- tbx v20.16b, {v16.16b-v19.16b}, v9.16b +- add v8.16b, v8.16b, v10.16b +- add v9.16b, v9.16b, v10.16b +- tbl v1.16b, {v4.16b-v7.16b}, v8.16b +- tbx v21.16b, {v16.16b-v19.16b}, v9.16b +- add v8.16b, v8.16b, v10.16b +- add v9.16b, v9.16b, v10.16b +- tbl v2.16b, {v4.16b-v7.16b}, v8.16b +- tbx v22.16b, {v16.16b-v19.16b}, v9.16b +- add v8.16b, v8.16b, v10.16b +- add v9.16b, v9.16b, v10.16b +- tbl v3.16b, {v4.16b-v7.16b}, v8.16b +- tbx v23.16b, {v16.16b-v19.16b}, v9.16b +- +- eor v20.16b, v20.16b, v0.16b +- eor v21.16b, v21.16b, v1.16b +- eor v22.16b, v22.16b, v2.16b +- eor v23.16b, v23.16b, v3.16b +- st1 {v20.16b-v23.16b}, [x1] ++.Lt192: cbz x5, 1f // exactly 128 bytes? ++ ld1 {v28.16b-v31.16b}, [x10] ++ add x5, x5, x1 ++ tbl v28.16b, {v4.16b-v7.16b}, v28.16b ++ tbl v29.16b, {v4.16b-v7.16b}, v29.16b ++ tbl v30.16b, {v4.16b-v7.16b}, v30.16b ++ tbl v31.16b, {v4.16b-v7.16b}, v31.16b ++ ++0: eor v20.16b, v20.16b, v28.16b ++ eor v21.16b, v21.16b, v29.16b ++ eor v22.16b, v22.16b, v30.16b ++ eor v23.16b, v23.16b, v31.16b ++ st1 {v20.16b-v23.16b}, [x5] // overlapping stores ++1: st1 {v16.16b-v19.16b}, [x1] + b .Lout + ++ // fewer than 128 bytes of in/output ++.Lt128: ld1 {v28.16b-v31.16b}, [x10] ++ add x5, x5, x1 ++ sub x1, x1, #64 ++ tbl v28.16b, {v0.16b-v3.16b}, v28.16b ++ tbl v29.16b, {v0.16b-v3.16b}, v29.16b ++ tbl v30.16b, {v0.16b-v3.16b}, v30.16b ++ tbl v31.16b, {v0.16b-v3.16b}, v31.16b ++ ld1 {v16.16b-v19.16b}, [x1] // reload first output block ++ b 0b ++ + // fewer than 256 bytes of in/output +-2: ld1 {v4.16b}, [x10] +- ld1 {v5.16b}, [x11] +- movi v6.16b, #16 +- add x1, x1, x7 ++.Lt256: cbz x6, 2f // exactly 192 bytes? ++ ld1 {v4.16b-v7.16b}, [x10] ++ add x6, x6, x1 + tbl v0.16b, {v8.16b-v11.16b}, v4.16b +- tbx v24.16b, {v20.16b-v23.16b}, v5.16b +- add v4.16b, v4.16b, v6.16b +- add v5.16b, v5.16b, v6.16b +- tbl v1.16b, {v8.16b-v11.16b}, v4.16b +- tbx v25.16b, {v20.16b-v23.16b}, v5.16b +- add v4.16b, v4.16b, v6.16b +- add v5.16b, v5.16b, v6.16b +- tbl v2.16b, {v8.16b-v11.16b}, v4.16b +- tbx v26.16b, {v20.16b-v23.16b}, v5.16b +- add v4.16b, v4.16b, v6.16b +- add v5.16b, v5.16b, v6.16b +- tbl v3.16b, {v8.16b-v11.16b}, v4.16b +- tbx v27.16b, {v20.16b-v23.16b}, v5.16b +- +- eor v24.16b, v24.16b, v0.16b +- eor v25.16b, v25.16b, v1.16b +- eor v26.16b, v26.16b, v2.16b +- eor v27.16b, v27.16b, v3.16b +- st1 {v24.16b-v27.16b}, [x1] ++ tbl v1.16b, {v8.16b-v11.16b}, v5.16b ++ tbl v2.16b, {v8.16b-v11.16b}, v6.16b ++ tbl v3.16b, {v8.16b-v11.16b}, v7.16b ++ ++ eor v28.16b, v28.16b, v0.16b ++ eor v29.16b, v29.16b, v1.16b ++ eor v30.16b, v30.16b, v2.16b ++ eor v31.16b, v31.16b, v3.16b ++ st1 {v28.16b-v31.16b}, [x6] // overlapping stores ++2: st1 {v20.16b-v23.16b}, [x1] + b .Lout + + // fewer than 320 bytes of in/output +-3: ld1 {v4.16b}, [x10] +- ld1 {v5.16b}, [x11] +- movi v6.16b, #16 +- add x1, x1, x8 ++.Lt320: cbz x7, 3f // exactly 256 bytes? ++ ld1 {v4.16b-v7.16b}, [x10] ++ add x7, x7, x1 + tbl v0.16b, {v12.16b-v15.16b}, v4.16b +- tbx v28.16b, {v24.16b-v27.16b}, v5.16b +- add v4.16b, v4.16b, v6.16b +- add v5.16b, v5.16b, v6.16b +- tbl v1.16b, {v12.16b-v15.16b}, v4.16b +- tbx v29.16b, {v24.16b-v27.16b}, v5.16b +- add v4.16b, v4.16b, v6.16b +- add v5.16b, v5.16b, v6.16b +- tbl v2.16b, {v12.16b-v15.16b}, v4.16b +- tbx v30.16b, {v24.16b-v27.16b}, v5.16b +- add v4.16b, v4.16b, v6.16b +- add v5.16b, v5.16b, v6.16b +- tbl v3.16b, {v12.16b-v15.16b}, v4.16b +- tbx v31.16b, {v24.16b-v27.16b}, v5.16b ++ tbl v1.16b, {v12.16b-v15.16b}, v5.16b ++ tbl v2.16b, {v12.16b-v15.16b}, v6.16b ++ tbl v3.16b, {v12.16b-v15.16b}, v7.16b + + eor v28.16b, v28.16b, v0.16b + eor v29.16b, v29.16b, v1.16b + eor v30.16b, v30.16b, v2.16b + eor v31.16b, v31.16b, v3.16b +- st1 {v28.16b-v31.16b}, [x1] ++ st1 {v28.16b-v31.16b}, [x7] // overlapping stores ++3: st1 {v24.16b-v27.16b}, [x1] + b .Lout + ENDPROC(chacha_4block_xor_neon) + +@@ -851,7 +796,7 @@ ENDPROC(chacha_4block_xor_neon) + .align L1_CACHE_SHIFT + .Lpermute: + .set .Li, 0 +- .rept 192 ++ .rept 128 + .byte (.Li - 64) + .set .Li, .Li + 1 + .endr diff --git a/target/linux/generic/backport-5.4/080-wireguard-0070-crypto-lib-chacha20poly1305-define-empty-module-exit.patch b/target/linux/generic/backport-5.4/080-wireguard-0070-crypto-lib-chacha20poly1305-define-empty-module-exit.patch new file mode 100644 index 0000000000..e4ca8892ca --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0070-crypto-lib-chacha20poly1305-define-empty-module-exit.patch @@ -0,0 +1,37 @@ +From 06c613a67ec604201f424e8e763f3361264d995e Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 15 Jan 2021 20:30:12 +0100 +Subject: [PATCH 070/124] crypto: lib/chacha20poly1305 - define empty module + exit function + +commit ac88c322d0f2917d41d13553c69e9d7f043c8b6f upstream. + +With no mod_exit function, users are unable to unload the module after +use. I'm not aware of any reason why module unloading should be +prohibited for this one, so this commit simply adds an empty exit +function. + +Reported-and-tested-by: John Donnelly +Acked-by: Ard Biesheuvel +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Herbert Xu +Signed-off-by: Jason A. Donenfeld +--- + lib/crypto/chacha20poly1305.c | 5 +++++ + 1 file changed, 5 insertions(+) + +--- a/lib/crypto/chacha20poly1305.c ++++ b/lib/crypto/chacha20poly1305.c +@@ -364,7 +364,12 @@ static int __init mod_init(void) + return 0; + } + ++static void __exit mod_exit(void) ++{ ++} ++ + module_init(mod_init); ++module_exit(mod_exit); + MODULE_LICENSE("GPL v2"); + MODULE_DESCRIPTION("ChaCha20Poly1305 AEAD construction"); + MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0071-icmp-introduce-helper-for-nat-d-source-address-in-ne.patch b/target/linux/generic/backport-5.4/080-wireguard-0071-icmp-introduce-helper-for-nat-d-source-address-in-ne.patch new file mode 100644 index 0000000000..f5ad6fe0fc --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0071-icmp-introduce-helper-for-nat-d-source-address-in-ne.patch @@ -0,0 +1,148 @@ +From 9793cc7357e8d70fed9cb350d2d39346328cc73b Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 11 Feb 2020 20:47:05 +0100 +Subject: [PATCH 071/124] icmp: introduce helper for nat'd source address in + network device context + +commit 0b41713b606694257b90d61ba7e2712d8457648b upstream. + +This introduces a helper function to be called only by network drivers +that wraps calls to icmp[v6]_send in a conntrack transformation, in case +NAT has been used. We don't want to pollute the non-driver path, though, +so we introduce this as a helper to be called by places that actually +make use of this, as suggested by Florian. + +Signed-off-by: Jason A. Donenfeld +Cc: Florian Westphal +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + include/linux/icmpv6.h | 10 ++++++++++ + include/net/icmp.h | 6 ++++++ + net/ipv4/icmp.c | 33 +++++++++++++++++++++++++++++++++ + net/ipv6/ip6_icmp.c | 34 ++++++++++++++++++++++++++++++++++ + 4 files changed, 83 insertions(+) + +--- a/include/linux/icmpv6.h ++++ b/include/linux/icmpv6.h +@@ -22,12 +22,22 @@ extern int inet6_unregister_icmp_sender( + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, + unsigned int data_len); + ++#if IS_ENABLED(CONFIG_NF_NAT) ++void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); ++#else ++#define icmpv6_ndo_send icmpv6_send ++#endif ++ + #else + + static inline void icmpv6_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) + { ++} + ++static inline void icmpv6_ndo_send(struct sk_buff *skb, ++ u8 type, u8 code, __u32 info) ++{ + } + #endif + +--- a/include/net/icmp.h ++++ b/include/net/icmp.h +@@ -43,6 +43,12 @@ static inline void icmp_send(struct sk_b + __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt); + } + ++#if IS_ENABLED(CONFIG_NF_NAT) ++void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); ++#else ++#define icmp_ndo_send icmp_send ++#endif ++ + int icmp_rcv(struct sk_buff *skb); + int icmp_err(struct sk_buff *skb, u32 info); + int icmp_init(void); +--- a/net/ipv4/icmp.c ++++ b/net/ipv4/icmp.c +@@ -750,6 +750,39 @@ out:; + } + EXPORT_SYMBOL(__icmp_send); + ++#if IS_ENABLED(CONFIG_NF_NAT) ++#include ++void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) ++{ ++ struct sk_buff *cloned_skb = NULL; ++ enum ip_conntrack_info ctinfo; ++ struct nf_conn *ct; ++ __be32 orig_ip; ++ ++ ct = nf_ct_get(skb_in, &ctinfo); ++ if (!ct || !(ct->status & IPS_SRC_NAT)) { ++ icmp_send(skb_in, type, code, info); ++ return; ++ } ++ ++ if (skb_shared(skb_in)) ++ skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); ++ ++ if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || ++ (skb_network_header(skb_in) + sizeof(struct iphdr)) > ++ skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, ++ skb_network_offset(skb_in) + sizeof(struct iphdr)))) ++ goto out; ++ ++ orig_ip = ip_hdr(skb_in)->saddr; ++ ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; ++ icmp_send(skb_in, type, code, info); ++ ip_hdr(skb_in)->saddr = orig_ip; ++out: ++ consume_skb(cloned_skb); ++} ++EXPORT_SYMBOL(icmp_ndo_send); ++#endif + + static void icmp_socket_deliver(struct sk_buff *skb, u32 info) + { +--- a/net/ipv6/ip6_icmp.c ++++ b/net/ipv6/ip6_icmp.c +@@ -45,4 +45,38 @@ out: + rcu_read_unlock(); + } + EXPORT_SYMBOL(icmpv6_send); ++ ++#if IS_ENABLED(CONFIG_NF_NAT) ++#include ++void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ++{ ++ struct sk_buff *cloned_skb = NULL; ++ enum ip_conntrack_info ctinfo; ++ struct in6_addr orig_ip; ++ struct nf_conn *ct; ++ ++ ct = nf_ct_get(skb_in, &ctinfo); ++ if (!ct || !(ct->status & IPS_SRC_NAT)) { ++ icmpv6_send(skb_in, type, code, info); ++ return; ++ } ++ ++ if (skb_shared(skb_in)) ++ skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); ++ ++ if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || ++ (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) > ++ skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, ++ skb_network_offset(skb_in) + sizeof(struct ipv6hdr)))) ++ goto out; ++ ++ orig_ip = ipv6_hdr(skb_in)->saddr; ++ ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; ++ icmpv6_send(skb_in, type, code, info); ++ ipv6_hdr(skb_in)->saddr = orig_ip; ++out: ++ consume_skb(cloned_skb); ++} ++EXPORT_SYMBOL(icmpv6_ndo_send); ++#endif + #endif diff --git a/target/linux/generic/backport-5.4/080-wireguard-0072-net-icmp-pass-zeroed-opts-from-icmp-v6-_ndo_send-bef.patch b/target/linux/generic/backport-5.4/080-wireguard-0072-net-icmp-pass-zeroed-opts-from-icmp-v6-_ndo_send-bef.patch new file mode 100644 index 0000000000..fcca169d2d --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0072-net-icmp-pass-zeroed-opts-from-icmp-v6-_ndo_send-bef.patch @@ -0,0 +1,299 @@ +From 4a25324891a32d080589a6e3a4dec2be2d9e3d60 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 23 Feb 2021 14:18:58 +0100 +Subject: [PATCH 072/124] net: icmp: pass zeroed opts from icmp{,v6}_ndo_send + before sending + +commit ee576c47db60432c37e54b1e2b43a8ca6d3a8dca upstream. + +The icmp{,v6}_send functions make all sorts of use of skb->cb, casting +it with IPCB or IP6CB, assuming the skb to have come directly from the +inet layer. But when the packet comes from the ndo layer, especially +when forwarded, there's no telling what might be in skb->cb at that +point. As a result, the icmp sending code risks reading bogus memory +contents, which can result in nasty stack overflows such as this one +reported by a user: + + panic+0x108/0x2ea + __stack_chk_fail+0x14/0x20 + __icmp_send+0x5bd/0x5c0 + icmp_ndo_send+0x148/0x160 + +In icmp_send, skb->cb is cast with IPCB and an ip_options struct is read +from it. The optlen parameter there is of particular note, as it can +induce writes beyond bounds. There are quite a few ways that can happen +in __ip_options_echo. For example: + + // sptr/skb are attacker-controlled skb bytes + sptr = skb_network_header(skb); + // dptr/dopt points to stack memory allocated by __icmp_send + dptr = dopt->__data; + // sopt is the corrupt skb->cb in question + if (sopt->rr) { + optlen = sptr[sopt->rr+1]; // corrupt skb->cb + skb->data + soffset = sptr[sopt->rr+2]; // corrupt skb->cb + skb->data + // this now writes potentially attacker-controlled data, over + // flowing the stack: + memcpy(dptr, sptr+sopt->rr, optlen); + } + +In the icmpv6_send case, the story is similar, but not as dire, as only +IP6CB(skb)->iif and IP6CB(skb)->dsthao are used. The dsthao case is +worse than the iif case, but it is passed to ipv6_find_tlv, which does +a bit of bounds checking on the value. + +This is easy to simulate by doing a `memset(skb->cb, 0x41, +sizeof(skb->cb));` before calling icmp{,v6}_ndo_send, and it's only by +good fortune and the rarity of icmp sending from that context that we've +avoided reports like this until now. For example, in KASAN: + + BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0xa0e/0x12b0 + Write of size 38 at addr ffff888006f1f80e by task ping/89 + CPU: 2 PID: 89 Comm: ping Not tainted 5.10.0-rc7-debug+ #5 + Call Trace: + dump_stack+0x9a/0xcc + print_address_description.constprop.0+0x1a/0x160 + __kasan_report.cold+0x20/0x38 + kasan_report+0x32/0x40 + check_memory_region+0x145/0x1a0 + memcpy+0x39/0x60 + __ip_options_echo+0xa0e/0x12b0 + __icmp_send+0x744/0x1700 + +Actually, out of the 4 drivers that do this, only gtp zeroed the cb for +the v4 case, while the rest did not. So this commit actually removes the +gtp-specific zeroing, while putting the code where it belongs in the +shared infrastructure of icmp{,v6}_ndo_send. + +This commit fixes the issue by passing an empty IPCB or IP6CB along to +the functions that actually do the work. For the icmp_send, this was +already trivial, thanks to __icmp_send providing the plumbing function. +For icmpv6_send, this required a tiny bit of refactoring to make it +behave like the v4 case, after which it was straight forward. + +Fixes: a2b78e9b2cac ("sunvnet: generate ICMP PTMUD messages for smaller port MTUs") +Reported-by: SinYu +Reviewed-by: Willem de Bruijn +Link: https://lore.kernel.org/netdev/CAF=yD-LOF116aHub6RMe8vB8ZpnrrnoTdqhobEx+bvoA8AsP0w@mail.gmail.com/T/ +Signed-off-by: Jason A. Donenfeld +Link: https://lore.kernel.org/r/20210223131858.72082-1-Jason@zx2c4.com +Signed-off-by: Jakub Kicinski +[Jason: the gtp part didn't apply because it doesn't use icmp_ndo_send on 5.4] +Signed-off-by: Jason A. Donenfeld +--- + include/linux/icmpv6.h | 17 ++++++++++++++--- + include/linux/ipv6.h | 1 - + include/net/icmp.h | 6 +++++- + net/ipv4/icmp.c | 5 +++-- + net/ipv6/icmp.c | 16 ++++++++-------- + net/ipv6/ip6_icmp.c | 12 +++++++----- + 6 files changed, 37 insertions(+), 20 deletions(-) + +--- a/include/linux/icmpv6.h ++++ b/include/linux/icmpv6.h +@@ -3,6 +3,7 @@ + #define _LINUX_ICMPV6_H + + #include ++#include + #include + + static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) +@@ -13,10 +14,16 @@ static inline struct icmp6hdr *icmp6_hdr + #include + + #if IS_ENABLED(CONFIG_IPV6) +-extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); ++extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, ++ const struct inet6_skb_parm *parm); + ++static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) ++{ ++ __icmpv6_send(skb, type, code, info, IP6CB(skb)); ++} + typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, +- const struct in6_addr *force_saddr); ++ const struct in6_addr *force_saddr, ++ const struct inet6_skb_parm *parm); + extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); + extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, +@@ -25,7 +32,11 @@ int ip6_err_gen_icmpv6_unreach(struct sk + #if IS_ENABLED(CONFIG_NF_NAT) + void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); + #else +-#define icmpv6_ndo_send icmpv6_send ++static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ++{ ++ struct inet6_skb_parm parm = { 0 }; ++ __icmpv6_send(skb_in, type, code, info, &parm); ++} + #endif + + #else +--- a/include/linux/ipv6.h ++++ b/include/linux/ipv6.h +@@ -83,7 +83,6 @@ struct ipv6_params { + __s32 autoconf; + }; + extern struct ipv6_params ipv6_defaults; +-#include + #include + #include + +--- a/include/net/icmp.h ++++ b/include/net/icmp.h +@@ -46,7 +46,11 @@ static inline void icmp_send(struct sk_b + #if IS_ENABLED(CONFIG_NF_NAT) + void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info); + #else +-#define icmp_ndo_send icmp_send ++static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) ++{ ++ struct ip_options opts = { 0 }; ++ __icmp_send(skb_in, type, code, info, &opts); ++} + #endif + + int icmp_rcv(struct sk_buff *skb); +--- a/net/ipv4/icmp.c ++++ b/net/ipv4/icmp.c +@@ -755,13 +755,14 @@ EXPORT_SYMBOL(__icmp_send); + void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) + { + struct sk_buff *cloned_skb = NULL; ++ struct ip_options opts = { 0 }; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + __be32 orig_ip; + + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { +- icmp_send(skb_in, type, code, info); ++ __icmp_send(skb_in, type, code, info, &opts); + return; + } + +@@ -776,7 +777,7 @@ void icmp_ndo_send(struct sk_buff *skb_i + + orig_ip = ip_hdr(skb_in)->saddr; + ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; +- icmp_send(skb_in, type, code, info); ++ __icmp_send(skb_in, type, code, info, &opts); + ip_hdr(skb_in)->saddr = orig_ip; + out: + consume_skb(cloned_skb); +--- a/net/ipv6/icmp.c ++++ b/net/ipv6/icmp.c +@@ -312,10 +312,9 @@ static int icmpv6_getfrag(void *from, ch + } + + #if IS_ENABLED(CONFIG_IPV6_MIP6) +-static void mip6_addr_swap(struct sk_buff *skb) ++static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) + { + struct ipv6hdr *iph = ipv6_hdr(skb); +- struct inet6_skb_parm *opt = IP6CB(skb); + struct ipv6_destopt_hao *hao; + struct in6_addr tmp; + int off; +@@ -332,7 +331,7 @@ static void mip6_addr_swap(struct sk_buf + } + } + #else +-static inline void mip6_addr_swap(struct sk_buff *skb) {} ++static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} + #endif + + static struct dst_entry *icmpv6_route_lookup(struct net *net, +@@ -427,7 +426,8 @@ static int icmp6_iif(const struct sk_buf + * Send an ICMP message in response to a packet in error + */ + static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, +- const struct in6_addr *force_saddr) ++ const struct in6_addr *force_saddr, ++ const struct inet6_skb_parm *parm) + { + struct inet6_dev *idev = NULL; + struct ipv6hdr *hdr = ipv6_hdr(skb); +@@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *s + if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) + goto out_bh_enable; + +- mip6_addr_swap(skb); ++ mip6_addr_swap(skb, parm); + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_ICMPV6; +@@ -605,7 +605,7 @@ out_bh_enable: + */ + void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) + { +- icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); ++ icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); + kfree_skb(skb); + } + +@@ -662,10 +662,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk + } + if (type == ICMP_TIME_EXCEEDED) + icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, +- info, &temp_saddr); ++ info, &temp_saddr, IP6CB(skb2)); + else + icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, +- info, &temp_saddr); ++ info, &temp_saddr, IP6CB(skb2)); + if (rt) + ip6_rt_put(rt); + +--- a/net/ipv6/ip6_icmp.c ++++ b/net/ipv6/ip6_icmp.c +@@ -31,7 +31,8 @@ int inet6_unregister_icmp_sender(ip6_icm + } + EXPORT_SYMBOL(inet6_unregister_icmp_sender); + +-void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) ++void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, ++ const struct inet6_skb_parm *parm) + { + ip6_icmp_send_t *send; + +@@ -40,16 +41,17 @@ void icmpv6_send(struct sk_buff *skb, u8 + + if (!send) + goto out; +- send(skb, type, code, info, NULL); ++ send(skb, type, code, info, NULL, parm); + out: + rcu_read_unlock(); + } +-EXPORT_SYMBOL(icmpv6_send); ++EXPORT_SYMBOL(__icmpv6_send); + + #if IS_ENABLED(CONFIG_NF_NAT) + #include + void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) + { ++ struct inet6_skb_parm parm = { 0 }; + struct sk_buff *cloned_skb = NULL; + enum ip_conntrack_info ctinfo; + struct in6_addr orig_ip; +@@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb + + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { +- icmpv6_send(skb_in, type, code, info); ++ __icmpv6_send(skb_in, type, code, info, &parm); + return; + } + +@@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb + + orig_ip = ipv6_hdr(skb_in)->saddr; + ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; +- icmpv6_send(skb_in, type, code, info); ++ __icmpv6_send(skb_in, type, code, info, &parm); + ipv6_hdr(skb_in)->saddr = orig_ip; + out: + consume_skb(cloned_skb); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0073-net-WireGuard-secure-network-tunnel.patch b/target/linux/generic/backport-5.4/080-wireguard-0073-net-WireGuard-secure-network-tunnel.patch new file mode 100644 index 0000000000..8651c73a5d --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0073-net-WireGuard-secure-network-tunnel.patch @@ -0,0 +1,8071 @@ +From 3e5c0a5efec6e13aa22c59b7170837972e23df49 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 9 Dec 2019 00:27:34 +0100 +Subject: [PATCH 073/124] net: WireGuard secure network tunnel + +commit e7096c131e5161fa3b8e52a650d7719d2857adfd upstream. + +WireGuard is a layer 3 secure networking tunnel made specifically for +the kernel, that aims to be much simpler and easier to audit than IPsec. +Extensive documentation and description of the protocol and +considerations, along with formal proofs of the cryptography, are +available at: + + * https://www.wireguard.com/ + * https://www.wireguard.com/papers/wireguard.pdf + +This commit implements WireGuard as a simple network device driver, +accessible in the usual RTNL way used by virtual network drivers. It +makes use of the udp_tunnel APIs, GRO, GSO, NAPI, and the usual set of +networking subsystem APIs. It has a somewhat novel multicore queueing +system designed for maximum throughput and minimal latency of encryption +operations, but it is implemented modestly using workqueues and NAPI. +Configuration is done via generic Netlink, and following a review from +the Netlink maintainer a year ago, several high profile userspace tools +have already implemented the API. + +This commit also comes with several different tests, both in-kernel +tests and out-of-kernel tests based on network namespaces, taking profit +of the fact that sockets used by WireGuard intentionally stay in the +namespace the WireGuard interface was originally created, exactly like +the semantics of userspace tun devices. See wireguard.com/netns/ for +pictures and examples. + +The source code is fairly short, but rather than combining everything +into a single file, WireGuard is developed as cleanly separable files, +making auditing and comprehension easier. Things are laid out as +follows: + + * noise.[ch], cookie.[ch], messages.h: These implement the bulk of the + cryptographic aspects of the protocol, and are mostly data-only in + nature, taking in buffers of bytes and spitting out buffers of + bytes. They also handle reference counting for their various shared + pieces of data, like keys and key lists. + + * ratelimiter.[ch]: Used as an integral part of cookie.[ch] for + ratelimiting certain types of cryptographic operations in accordance + with particular WireGuard semantics. + + * allowedips.[ch], peerlookup.[ch]: The main lookup structures of + WireGuard, the former being trie-like with particular semantics, an + integral part of the design of the protocol, and the latter just + being nice helper functions around the various hashtables we use. + + * device.[ch]: Implementation of functions for the netdevice and for + rtnl, responsible for maintaining the life of a given interface and + wiring it up to the rest of WireGuard. + + * peer.[ch]: Each interface has a list of peers, with helper functions + available here for creation, destruction, and reference counting. + + * socket.[ch]: Implementation of functions related to udp_socket and + the general set of kernel socket APIs, for sending and receiving + ciphertext UDP packets, and taking care of WireGuard-specific sticky + socket routing semantics for the automatic roaming. + + * netlink.[ch]: Userspace API entry point for configuring WireGuard + peers and devices. The API has been implemented by several userspace + tools and network management utility, and the WireGuard project + distributes the basic wg(8) tool. + + * queueing.[ch]: Shared function on the rx and tx path for handling + the various queues used in the multicore algorithms. + + * send.c: Handles encrypting outgoing packets in parallel on + multiple cores, before sending them in order on a single core, via + workqueues and ring buffers. Also handles sending handshake and cookie + messages as part of the protocol, in parallel. + + * receive.c: Handles decrypting incoming packets in parallel on + multiple cores, before passing them off in order to be ingested via + the rest of the networking subsystem with GRO via the typical NAPI + poll function. Also handles receiving handshake and cookie messages + as part of the protocol, in parallel. + + * timers.[ch]: Uses the timer wheel to implement protocol particular + event timeouts, and gives a set of very simple event-driven entry + point functions for callers. + + * main.c, version.h: Initialization and deinitialization of the module. + + * selftest/*.h: Runtime unit tests for some of the most security + sensitive functions. + + * tools/testing/selftests/wireguard/netns.sh: Aforementioned testing + script using network namespaces. + +This commit aims to be as self-contained as possible, implementing +WireGuard as a standalone module not needing much special handling or +coordination from the network subsystem. I expect for future +optimizations to the network stack to positively improve WireGuard, and +vice-versa, but for the time being, this exists as intentionally +standalone. + +We introduce a menu option for CONFIG_WIREGUARD, as well as providing a +verbose debug log and self-tests via CONFIG_WIREGUARD_DEBUG. + +Signed-off-by: Jason A. Donenfeld +Cc: David Miller +Cc: Greg KH +Cc: Linus Torvalds +Cc: Herbert Xu +Cc: linux-crypto@vger.kernel.org +Cc: linux-kernel@vger.kernel.org +Cc: netdev@vger.kernel.org +Signed-off-by: David S. Miller +[Jason: ported to 5.4 by doing the following: + - wg_get_device_start uses genl_family_attrbuf + - trival skb_redirect_reset change from 2c64605b590e is folded in + - skb_list_walk_safe was already backported prior] +Signed-off-by: Jason A. Donenfeld +--- + MAINTAINERS | 8 + + drivers/net/Kconfig | 41 + + drivers/net/Makefile | 1 + + drivers/net/wireguard/Makefile | 18 + + drivers/net/wireguard/allowedips.c | 381 +++++++++ + drivers/net/wireguard/allowedips.h | 59 ++ + drivers/net/wireguard/cookie.c | 236 ++++++ + drivers/net/wireguard/cookie.h | 59 ++ + drivers/net/wireguard/device.c | 458 ++++++++++ + drivers/net/wireguard/device.h | 65 ++ + drivers/net/wireguard/main.c | 64 ++ + drivers/net/wireguard/messages.h | 128 +++ + drivers/net/wireguard/netlink.c | 648 +++++++++++++++ + drivers/net/wireguard/netlink.h | 12 + + drivers/net/wireguard/noise.c | 828 +++++++++++++++++++ + drivers/net/wireguard/noise.h | 137 +++ + drivers/net/wireguard/peer.c | 240 ++++++ + drivers/net/wireguard/peer.h | 83 ++ + drivers/net/wireguard/peerlookup.c | 221 +++++ + drivers/net/wireguard/peerlookup.h | 64 ++ + drivers/net/wireguard/queueing.c | 53 ++ + drivers/net/wireguard/queueing.h | 197 +++++ + drivers/net/wireguard/ratelimiter.c | 223 +++++ + drivers/net/wireguard/ratelimiter.h | 19 + + drivers/net/wireguard/receive.c | 595 +++++++++++++ + drivers/net/wireguard/selftest/allowedips.c | 683 +++++++++++++++ + drivers/net/wireguard/selftest/counter.c | 104 +++ + drivers/net/wireguard/selftest/ratelimiter.c | 226 +++++ + drivers/net/wireguard/send.c | 413 +++++++++ + drivers/net/wireguard/socket.c | 437 ++++++++++ + drivers/net/wireguard/socket.h | 44 + + drivers/net/wireguard/timers.c | 243 ++++++ + drivers/net/wireguard/timers.h | 31 + + drivers/net/wireguard/version.h | 1 + + include/uapi/linux/wireguard.h | 196 +++++ + tools/testing/selftests/wireguard/netns.sh | 537 ++++++++++++ + 36 files changed, 7753 insertions(+) + create mode 100644 drivers/net/wireguard/Makefile + create mode 100644 drivers/net/wireguard/allowedips.c + create mode 100644 drivers/net/wireguard/allowedips.h + create mode 100644 drivers/net/wireguard/cookie.c + create mode 100644 drivers/net/wireguard/cookie.h + create mode 100644 drivers/net/wireguard/device.c + create mode 100644 drivers/net/wireguard/device.h + create mode 100644 drivers/net/wireguard/main.c + create mode 100644 drivers/net/wireguard/messages.h + create mode 100644 drivers/net/wireguard/netlink.c + create mode 100644 drivers/net/wireguard/netlink.h + create mode 100644 drivers/net/wireguard/noise.c + create mode 100644 drivers/net/wireguard/noise.h + create mode 100644 drivers/net/wireguard/peer.c + create mode 100644 drivers/net/wireguard/peer.h + create mode 100644 drivers/net/wireguard/peerlookup.c + create mode 100644 drivers/net/wireguard/peerlookup.h + create mode 100644 drivers/net/wireguard/queueing.c + create mode 100644 drivers/net/wireguard/queueing.h + create mode 100644 drivers/net/wireguard/ratelimiter.c + create mode 100644 drivers/net/wireguard/ratelimiter.h + create mode 100644 drivers/net/wireguard/receive.c + create mode 100644 drivers/net/wireguard/selftest/allowedips.c + create mode 100644 drivers/net/wireguard/selftest/counter.c + create mode 100644 drivers/net/wireguard/selftest/ratelimiter.c + create mode 100644 drivers/net/wireguard/send.c + create mode 100644 drivers/net/wireguard/socket.c + create mode 100644 drivers/net/wireguard/socket.h + create mode 100644 drivers/net/wireguard/timers.c + create mode 100644 drivers/net/wireguard/timers.h + create mode 100644 drivers/net/wireguard/version.h + create mode 100644 include/uapi/linux/wireguard.h + create mode 100755 tools/testing/selftests/wireguard/netns.sh + +--- a/MAINTAINERS ++++ b/MAINTAINERS +@@ -17584,6 +17584,14 @@ L: linux-gpio@vger.kernel.org + S: Maintained + F: drivers/gpio/gpio-ws16c48.c + ++WIREGUARD SECURE NETWORK TUNNEL ++M: Jason A. Donenfeld ++S: Maintained ++F: drivers/net/wireguard/ ++F: tools/testing/selftests/wireguard/ ++L: wireguard@lists.zx2c4.com ++L: netdev@vger.kernel.org ++ + WISTRON LAPTOP BUTTON DRIVER + M: Miloslav Trmac + S: Maintained +--- a/drivers/net/Kconfig ++++ b/drivers/net/Kconfig +@@ -71,6 +71,47 @@ config DUMMY + To compile this driver as a module, choose M here: the module + will be called dummy. + ++config WIREGUARD ++ tristate "WireGuard secure network tunnel" ++ depends on NET && INET ++ depends on IPV6 || !IPV6 ++ select NET_UDP_TUNNEL ++ select DST_CACHE ++ select CRYPTO ++ select CRYPTO_LIB_CURVE25519 ++ select CRYPTO_LIB_CHACHA20POLY1305 ++ select CRYPTO_LIB_BLAKE2S ++ select CRYPTO_CHACHA20_X86_64 if X86 && 64BIT ++ select CRYPTO_POLY1305_X86_64 if X86 && 64BIT ++ select CRYPTO_BLAKE2S_X86 if X86 && 64BIT ++ select CRYPTO_CURVE25519_X86 if X86 && 64BIT ++ select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON ++ select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON ++ select CRYPTO_POLY1305_ARM if ARM ++ select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON ++ select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2 ++ select CRYPTO_POLY1305_MIPS if CPU_MIPS32 || (CPU_MIPS64 && 64BIT) ++ help ++ WireGuard is a secure, fast, and easy to use replacement for IPSec ++ that uses modern cryptography and clever networking tricks. It's ++ designed to be fairly general purpose and abstract enough to fit most ++ use cases, while at the same time remaining extremely simple to ++ configure. See www.wireguard.com for more info. ++ ++ It's safe to say Y or M here, as the driver is very lightweight and ++ is only in use when an administrator chooses to add an interface. ++ ++config WIREGUARD_DEBUG ++ bool "Debugging checks and verbose messages" ++ depends on WIREGUARD ++ help ++ This will write log messages for handshake and other events ++ that occur for a WireGuard interface. It will also perform some ++ extra validation checks and unit tests at various points. This is ++ only useful for debugging. ++ ++ Say N here unless you know what you're doing. ++ + config EQUALIZER + tristate "EQL (serial line load balancing) support" + ---help--- +--- a/drivers/net/Makefile ++++ b/drivers/net/Makefile +@@ -10,6 +10,7 @@ obj-$(CONFIG_BONDING) += bonding/ + obj-$(CONFIG_IPVLAN) += ipvlan/ + obj-$(CONFIG_IPVTAP) += ipvlan/ + obj-$(CONFIG_DUMMY) += dummy.o ++obj-$(CONFIG_WIREGUARD) += wireguard/ + obj-$(CONFIG_EQUALIZER) += eql.o + obj-$(CONFIG_IFB) += ifb.o + obj-$(CONFIG_MACSEC) += macsec.o +--- /dev/null ++++ b/drivers/net/wireguard/Makefile +@@ -0,0 +1,18 @@ ++ccflags-y := -O3 ++ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt' ++ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG ++wireguard-y := main.o ++wireguard-y += noise.o ++wireguard-y += device.o ++wireguard-y += peer.o ++wireguard-y += timers.o ++wireguard-y += queueing.o ++wireguard-y += send.o ++wireguard-y += receive.o ++wireguard-y += socket.o ++wireguard-y += peerlookup.o ++wireguard-y += allowedips.o ++wireguard-y += ratelimiter.o ++wireguard-y += cookie.o ++wireguard-y += netlink.o ++obj-$(CONFIG_WIREGUARD) := wireguard.o +--- /dev/null ++++ b/drivers/net/wireguard/allowedips.c +@@ -0,0 +1,381 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "allowedips.h" ++#include "peer.h" ++ ++static void swap_endian(u8 *dst, const u8 *src, u8 bits) ++{ ++ if (bits == 32) { ++ *(u32 *)dst = be32_to_cpu(*(const __be32 *)src); ++ } else if (bits == 128) { ++ ((u64 *)dst)[0] = be64_to_cpu(((const __be64 *)src)[0]); ++ ((u64 *)dst)[1] = be64_to_cpu(((const __be64 *)src)[1]); ++ } ++} ++ ++static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src, ++ u8 cidr, u8 bits) ++{ ++ node->cidr = cidr; ++ node->bit_at_a = cidr / 8U; ++#ifdef __LITTLE_ENDIAN ++ node->bit_at_a ^= (bits / 8U - 1U) % 8U; ++#endif ++ node->bit_at_b = 7U - (cidr % 8U); ++ node->bitlen = bits; ++ memcpy(node->bits, src, bits / 8U); ++} ++#define CHOOSE_NODE(parent, key) \ ++ parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1] ++ ++static void node_free_rcu(struct rcu_head *rcu) ++{ ++ kfree(container_of(rcu, struct allowedips_node, rcu)); ++} ++ ++static void push_rcu(struct allowedips_node **stack, ++ struct allowedips_node __rcu *p, unsigned int *len) ++{ ++ if (rcu_access_pointer(p)) { ++ WARN_ON(IS_ENABLED(DEBUG) && *len >= 128); ++ stack[(*len)++] = rcu_dereference_raw(p); ++ } ++} ++ ++static void root_free_rcu(struct rcu_head *rcu) ++{ ++ struct allowedips_node *node, *stack[128] = { ++ container_of(rcu, struct allowedips_node, rcu) }; ++ unsigned int len = 1; ++ ++ while (len > 0 && (node = stack[--len])) { ++ push_rcu(stack, node->bit[0], &len); ++ push_rcu(stack, node->bit[1], &len); ++ kfree(node); ++ } ++} ++ ++static void root_remove_peer_lists(struct allowedips_node *root) ++{ ++ struct allowedips_node *node, *stack[128] = { root }; ++ unsigned int len = 1; ++ ++ while (len > 0 && (node = stack[--len])) { ++ push_rcu(stack, node->bit[0], &len); ++ push_rcu(stack, node->bit[1], &len); ++ if (rcu_access_pointer(node->peer)) ++ list_del(&node->peer_list); ++ } ++} ++ ++static void walk_remove_by_peer(struct allowedips_node __rcu **top, ++ struct wg_peer *peer, struct mutex *lock) ++{ ++#define REF(p) rcu_access_pointer(p) ++#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock)) ++#define PUSH(p) ({ \ ++ WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \ ++ stack[len++] = p; \ ++ }) ++ ++ struct allowedips_node __rcu **stack[128], **nptr; ++ struct allowedips_node *node, *prev; ++ unsigned int len; ++ ++ if (unlikely(!peer || !REF(*top))) ++ return; ++ ++ for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) { ++ nptr = stack[len - 1]; ++ node = DEREF(nptr); ++ if (!node) { ++ --len; ++ continue; ++ } ++ if (!prev || REF(prev->bit[0]) == node || ++ REF(prev->bit[1]) == node) { ++ if (REF(node->bit[0])) ++ PUSH(&node->bit[0]); ++ else if (REF(node->bit[1])) ++ PUSH(&node->bit[1]); ++ } else if (REF(node->bit[0]) == prev) { ++ if (REF(node->bit[1])) ++ PUSH(&node->bit[1]); ++ } else { ++ if (rcu_dereference_protected(node->peer, ++ lockdep_is_held(lock)) == peer) { ++ RCU_INIT_POINTER(node->peer, NULL); ++ list_del_init(&node->peer_list); ++ if (!node->bit[0] || !node->bit[1]) { ++ rcu_assign_pointer(*nptr, DEREF( ++ &node->bit[!REF(node->bit[0])])); ++ call_rcu(&node->rcu, node_free_rcu); ++ node = DEREF(nptr); ++ } ++ } ++ --len; ++ } ++ } ++ ++#undef REF ++#undef DEREF ++#undef PUSH ++} ++ ++static unsigned int fls128(u64 a, u64 b) ++{ ++ return a ? fls64(a) + 64U : fls64(b); ++} ++ ++static u8 common_bits(const struct allowedips_node *node, const u8 *key, ++ u8 bits) ++{ ++ if (bits == 32) ++ return 32U - fls(*(const u32 *)node->bits ^ *(const u32 *)key); ++ else if (bits == 128) ++ return 128U - fls128( ++ *(const u64 *)&node->bits[0] ^ *(const u64 *)&key[0], ++ *(const u64 *)&node->bits[8] ^ *(const u64 *)&key[8]); ++ return 0; ++} ++ ++static bool prefix_matches(const struct allowedips_node *node, const u8 *key, ++ u8 bits) ++{ ++ /* This could be much faster if it actually just compared the common ++ * bits properly, by precomputing a mask bswap(~0 << (32 - cidr)), and ++ * the rest, but it turns out that common_bits is already super fast on ++ * modern processors, even taking into account the unfortunate bswap. ++ * So, we just inline it like this instead. ++ */ ++ return common_bits(node, key, bits) >= node->cidr; ++} ++ ++static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits, ++ const u8 *key) ++{ ++ struct allowedips_node *node = trie, *found = NULL; ++ ++ while (node && prefix_matches(node, key, bits)) { ++ if (rcu_access_pointer(node->peer)) ++ found = node; ++ if (node->cidr == bits) ++ break; ++ node = rcu_dereference_bh(CHOOSE_NODE(node, key)); ++ } ++ return found; ++} ++ ++/* Returns a strong reference to a peer */ ++static struct wg_peer *lookup(struct allowedips_node __rcu *root, u8 bits, ++ const void *be_ip) ++{ ++ /* Aligned so it can be passed to fls/fls64 */ ++ u8 ip[16] __aligned(__alignof(u64)); ++ struct allowedips_node *node; ++ struct wg_peer *peer = NULL; ++ ++ swap_endian(ip, be_ip, bits); ++ ++ rcu_read_lock_bh(); ++retry: ++ node = find_node(rcu_dereference_bh(root), bits, ip); ++ if (node) { ++ peer = wg_peer_get_maybe_zero(rcu_dereference_bh(node->peer)); ++ if (!peer) ++ goto retry; ++ } ++ rcu_read_unlock_bh(); ++ return peer; ++} ++ ++static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key, ++ u8 cidr, u8 bits, struct allowedips_node **rnode, ++ struct mutex *lock) ++{ ++ struct allowedips_node *node = rcu_dereference_protected(trie, ++ lockdep_is_held(lock)); ++ struct allowedips_node *parent = NULL; ++ bool exact = false; ++ ++ while (node && node->cidr <= cidr && prefix_matches(node, key, bits)) { ++ parent = node; ++ if (parent->cidr == cidr) { ++ exact = true; ++ break; ++ } ++ node = rcu_dereference_protected(CHOOSE_NODE(parent, key), ++ lockdep_is_held(lock)); ++ } ++ *rnode = parent; ++ return exact; ++} ++ ++static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, ++ u8 cidr, struct wg_peer *peer, struct mutex *lock) ++{ ++ struct allowedips_node *node, *parent, *down, *newnode; ++ ++ if (unlikely(cidr > bits || !peer)) ++ return -EINVAL; ++ ++ if (!rcu_access_pointer(*trie)) { ++ node = kzalloc(sizeof(*node), GFP_KERNEL); ++ if (unlikely(!node)) ++ return -ENOMEM; ++ RCU_INIT_POINTER(node->peer, peer); ++ list_add_tail(&node->peer_list, &peer->allowedips_list); ++ copy_and_assign_cidr(node, key, cidr, bits); ++ rcu_assign_pointer(*trie, node); ++ return 0; ++ } ++ if (node_placement(*trie, key, cidr, bits, &node, lock)) { ++ rcu_assign_pointer(node->peer, peer); ++ list_move_tail(&node->peer_list, &peer->allowedips_list); ++ return 0; ++ } ++ ++ newnode = kzalloc(sizeof(*newnode), GFP_KERNEL); ++ if (unlikely(!newnode)) ++ return -ENOMEM; ++ RCU_INIT_POINTER(newnode->peer, peer); ++ list_add_tail(&newnode->peer_list, &peer->allowedips_list); ++ copy_and_assign_cidr(newnode, key, cidr, bits); ++ ++ if (!node) { ++ down = rcu_dereference_protected(*trie, lockdep_is_held(lock)); ++ } else { ++ down = rcu_dereference_protected(CHOOSE_NODE(node, key), ++ lockdep_is_held(lock)); ++ if (!down) { ++ rcu_assign_pointer(CHOOSE_NODE(node, key), newnode); ++ return 0; ++ } ++ } ++ cidr = min(cidr, common_bits(down, key, bits)); ++ parent = node; ++ ++ if (newnode->cidr == cidr) { ++ rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down); ++ if (!parent) ++ rcu_assign_pointer(*trie, newnode); ++ else ++ rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits), ++ newnode); ++ } else { ++ node = kzalloc(sizeof(*node), GFP_KERNEL); ++ if (unlikely(!node)) { ++ kfree(newnode); ++ return -ENOMEM; ++ } ++ INIT_LIST_HEAD(&node->peer_list); ++ copy_and_assign_cidr(node, newnode->bits, cidr, bits); ++ ++ rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down); ++ rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode); ++ if (!parent) ++ rcu_assign_pointer(*trie, node); ++ else ++ rcu_assign_pointer(CHOOSE_NODE(parent, node->bits), ++ node); ++ } ++ return 0; ++} ++ ++void wg_allowedips_init(struct allowedips *table) ++{ ++ table->root4 = table->root6 = NULL; ++ table->seq = 1; ++} ++ ++void wg_allowedips_free(struct allowedips *table, struct mutex *lock) ++{ ++ struct allowedips_node __rcu *old4 = table->root4, *old6 = table->root6; ++ ++ ++table->seq; ++ RCU_INIT_POINTER(table->root4, NULL); ++ RCU_INIT_POINTER(table->root6, NULL); ++ if (rcu_access_pointer(old4)) { ++ struct allowedips_node *node = rcu_dereference_protected(old4, ++ lockdep_is_held(lock)); ++ ++ root_remove_peer_lists(node); ++ call_rcu(&node->rcu, root_free_rcu); ++ } ++ if (rcu_access_pointer(old6)) { ++ struct allowedips_node *node = rcu_dereference_protected(old6, ++ lockdep_is_held(lock)); ++ ++ root_remove_peer_lists(node); ++ call_rcu(&node->rcu, root_free_rcu); ++ } ++} ++ ++int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip, ++ u8 cidr, struct wg_peer *peer, struct mutex *lock) ++{ ++ /* Aligned so it can be passed to fls */ ++ u8 key[4] __aligned(__alignof(u32)); ++ ++ ++table->seq; ++ swap_endian(key, (const u8 *)ip, 32); ++ return add(&table->root4, 32, key, cidr, peer, lock); ++} ++ ++int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, ++ u8 cidr, struct wg_peer *peer, struct mutex *lock) ++{ ++ /* Aligned so it can be passed to fls64 */ ++ u8 key[16] __aligned(__alignof(u64)); ++ ++ ++table->seq; ++ swap_endian(key, (const u8 *)ip, 128); ++ return add(&table->root6, 128, key, cidr, peer, lock); ++} ++ ++void wg_allowedips_remove_by_peer(struct allowedips *table, ++ struct wg_peer *peer, struct mutex *lock) ++{ ++ ++table->seq; ++ walk_remove_by_peer(&table->root4, peer, lock); ++ walk_remove_by_peer(&table->root6, peer, lock); ++} ++ ++int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr) ++{ ++ const unsigned int cidr_bytes = DIV_ROUND_UP(node->cidr, 8U); ++ swap_endian(ip, node->bits, node->bitlen); ++ memset(ip + cidr_bytes, 0, node->bitlen / 8U - cidr_bytes); ++ if (node->cidr) ++ ip[cidr_bytes - 1U] &= ~0U << (-node->cidr % 8U); ++ ++ *cidr = node->cidr; ++ return node->bitlen == 32 ? AF_INET : AF_INET6; ++} ++ ++/* Returns a strong reference to a peer */ ++struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table, ++ struct sk_buff *skb) ++{ ++ if (skb->protocol == htons(ETH_P_IP)) ++ return lookup(table->root4, 32, &ip_hdr(skb)->daddr); ++ else if (skb->protocol == htons(ETH_P_IPV6)) ++ return lookup(table->root6, 128, &ipv6_hdr(skb)->daddr); ++ return NULL; ++} ++ ++/* Returns a strong reference to a peer */ ++struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table, ++ struct sk_buff *skb) ++{ ++ if (skb->protocol == htons(ETH_P_IP)) ++ return lookup(table->root4, 32, &ip_hdr(skb)->saddr); ++ else if (skb->protocol == htons(ETH_P_IPV6)) ++ return lookup(table->root6, 128, &ipv6_hdr(skb)->saddr); ++ return NULL; ++} ++ ++#include "selftest/allowedips.c" +--- /dev/null ++++ b/drivers/net/wireguard/allowedips.h +@@ -0,0 +1,59 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_ALLOWEDIPS_H ++#define _WG_ALLOWEDIPS_H ++ ++#include ++#include ++#include ++ ++struct wg_peer; ++ ++struct allowedips_node { ++ struct wg_peer __rcu *peer; ++ struct allowedips_node __rcu *bit[2]; ++ /* While it may seem scandalous that we waste space for v4, ++ * we're alloc'ing to the nearest power of 2 anyway, so this ++ * doesn't actually make a difference. ++ */ ++ u8 bits[16] __aligned(__alignof(u64)); ++ u8 cidr, bit_at_a, bit_at_b, bitlen; ++ ++ /* Keep rarely used list at bottom to be beyond cache line. */ ++ union { ++ struct list_head peer_list; ++ struct rcu_head rcu; ++ }; ++}; ++ ++struct allowedips { ++ struct allowedips_node __rcu *root4; ++ struct allowedips_node __rcu *root6; ++ u64 seq; ++}; ++ ++void wg_allowedips_init(struct allowedips *table); ++void wg_allowedips_free(struct allowedips *table, struct mutex *mutex); ++int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip, ++ u8 cidr, struct wg_peer *peer, struct mutex *lock); ++int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, ++ u8 cidr, struct wg_peer *peer, struct mutex *lock); ++void wg_allowedips_remove_by_peer(struct allowedips *table, ++ struct wg_peer *peer, struct mutex *lock); ++/* The ip input pointer should be __aligned(__alignof(u64))) */ ++int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr); ++ ++/* These return a strong reference to a peer: */ ++struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table, ++ struct sk_buff *skb); ++struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table, ++ struct sk_buff *skb); ++ ++#ifdef DEBUG ++bool wg_allowedips_selftest(void); ++#endif ++ ++#endif /* _WG_ALLOWEDIPS_H */ +--- /dev/null ++++ b/drivers/net/wireguard/cookie.c +@@ -0,0 +1,236 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "cookie.h" ++#include "peer.h" ++#include "device.h" ++#include "messages.h" ++#include "ratelimiter.h" ++#include "timers.h" ++ ++#include ++#include ++ ++#include ++#include ++ ++void wg_cookie_checker_init(struct cookie_checker *checker, ++ struct wg_device *wg) ++{ ++ init_rwsem(&checker->secret_lock); ++ checker->secret_birthdate = ktime_get_coarse_boottime_ns(); ++ get_random_bytes(checker->secret, NOISE_HASH_LEN); ++ checker->device = wg; ++} ++ ++enum { COOKIE_KEY_LABEL_LEN = 8 }; ++static const u8 mac1_key_label[COOKIE_KEY_LABEL_LEN] = "mac1----"; ++static const u8 cookie_key_label[COOKIE_KEY_LABEL_LEN] = "cookie--"; ++ ++static void precompute_key(u8 key[NOISE_SYMMETRIC_KEY_LEN], ++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN], ++ const u8 label[COOKIE_KEY_LABEL_LEN]) ++{ ++ struct blake2s_state blake; ++ ++ blake2s_init(&blake, NOISE_SYMMETRIC_KEY_LEN); ++ blake2s_update(&blake, label, COOKIE_KEY_LABEL_LEN); ++ blake2s_update(&blake, pubkey, NOISE_PUBLIC_KEY_LEN); ++ blake2s_final(&blake, key); ++} ++ ++/* Must hold peer->handshake.static_identity->lock */ ++void wg_cookie_checker_precompute_device_keys(struct cookie_checker *checker) ++{ ++ if (likely(checker->device->static_identity.has_identity)) { ++ precompute_key(checker->cookie_encryption_key, ++ checker->device->static_identity.static_public, ++ cookie_key_label); ++ precompute_key(checker->message_mac1_key, ++ checker->device->static_identity.static_public, ++ mac1_key_label); ++ } else { ++ memset(checker->cookie_encryption_key, 0, ++ NOISE_SYMMETRIC_KEY_LEN); ++ memset(checker->message_mac1_key, 0, NOISE_SYMMETRIC_KEY_LEN); ++ } ++} ++ ++void wg_cookie_checker_precompute_peer_keys(struct wg_peer *peer) ++{ ++ precompute_key(peer->latest_cookie.cookie_decryption_key, ++ peer->handshake.remote_static, cookie_key_label); ++ precompute_key(peer->latest_cookie.message_mac1_key, ++ peer->handshake.remote_static, mac1_key_label); ++} ++ ++void wg_cookie_init(struct cookie *cookie) ++{ ++ memset(cookie, 0, sizeof(*cookie)); ++ init_rwsem(&cookie->lock); ++} ++ ++static void compute_mac1(u8 mac1[COOKIE_LEN], const void *message, size_t len, ++ const u8 key[NOISE_SYMMETRIC_KEY_LEN]) ++{ ++ len = len - sizeof(struct message_macs) + ++ offsetof(struct message_macs, mac1); ++ blake2s(mac1, message, key, COOKIE_LEN, len, NOISE_SYMMETRIC_KEY_LEN); ++} ++ ++static void compute_mac2(u8 mac2[COOKIE_LEN], const void *message, size_t len, ++ const u8 cookie[COOKIE_LEN]) ++{ ++ len = len - sizeof(struct message_macs) + ++ offsetof(struct message_macs, mac2); ++ blake2s(mac2, message, cookie, COOKIE_LEN, len, COOKIE_LEN); ++} ++ ++static void make_cookie(u8 cookie[COOKIE_LEN], struct sk_buff *skb, ++ struct cookie_checker *checker) ++{ ++ struct blake2s_state state; ++ ++ if (wg_birthdate_has_expired(checker->secret_birthdate, ++ COOKIE_SECRET_MAX_AGE)) { ++ down_write(&checker->secret_lock); ++ checker->secret_birthdate = ktime_get_coarse_boottime_ns(); ++ get_random_bytes(checker->secret, NOISE_HASH_LEN); ++ up_write(&checker->secret_lock); ++ } ++ ++ down_read(&checker->secret_lock); ++ ++ blake2s_init_key(&state, COOKIE_LEN, checker->secret, NOISE_HASH_LEN); ++ if (skb->protocol == htons(ETH_P_IP)) ++ blake2s_update(&state, (u8 *)&ip_hdr(skb)->saddr, ++ sizeof(struct in_addr)); ++ else if (skb->protocol == htons(ETH_P_IPV6)) ++ blake2s_update(&state, (u8 *)&ipv6_hdr(skb)->saddr, ++ sizeof(struct in6_addr)); ++ blake2s_update(&state, (u8 *)&udp_hdr(skb)->source, sizeof(__be16)); ++ blake2s_final(&state, cookie); ++ ++ up_read(&checker->secret_lock); ++} ++ ++enum cookie_mac_state wg_cookie_validate_packet(struct cookie_checker *checker, ++ struct sk_buff *skb, ++ bool check_cookie) ++{ ++ struct message_macs *macs = (struct message_macs *) ++ (skb->data + skb->len - sizeof(*macs)); ++ enum cookie_mac_state ret; ++ u8 computed_mac[COOKIE_LEN]; ++ u8 cookie[COOKIE_LEN]; ++ ++ ret = INVALID_MAC; ++ compute_mac1(computed_mac, skb->data, skb->len, ++ checker->message_mac1_key); ++ if (crypto_memneq(computed_mac, macs->mac1, COOKIE_LEN)) ++ goto out; ++ ++ ret = VALID_MAC_BUT_NO_COOKIE; ++ ++ if (!check_cookie) ++ goto out; ++ ++ make_cookie(cookie, skb, checker); ++ ++ compute_mac2(computed_mac, skb->data, skb->len, cookie); ++ if (crypto_memneq(computed_mac, macs->mac2, COOKIE_LEN)) ++ goto out; ++ ++ ret = VALID_MAC_WITH_COOKIE_BUT_RATELIMITED; ++ if (!wg_ratelimiter_allow(skb, dev_net(checker->device->dev))) ++ goto out; ++ ++ ret = VALID_MAC_WITH_COOKIE; ++ ++out: ++ return ret; ++} ++ ++void wg_cookie_add_mac_to_packet(void *message, size_t len, ++ struct wg_peer *peer) ++{ ++ struct message_macs *macs = (struct message_macs *) ++ ((u8 *)message + len - sizeof(*macs)); ++ ++ down_write(&peer->latest_cookie.lock); ++ compute_mac1(macs->mac1, message, len, ++ peer->latest_cookie.message_mac1_key); ++ memcpy(peer->latest_cookie.last_mac1_sent, macs->mac1, COOKIE_LEN); ++ peer->latest_cookie.have_sent_mac1 = true; ++ up_write(&peer->latest_cookie.lock); ++ ++ down_read(&peer->latest_cookie.lock); ++ if (peer->latest_cookie.is_valid && ++ !wg_birthdate_has_expired(peer->latest_cookie.birthdate, ++ COOKIE_SECRET_MAX_AGE - COOKIE_SECRET_LATENCY)) ++ compute_mac2(macs->mac2, message, len, ++ peer->latest_cookie.cookie); ++ else ++ memset(macs->mac2, 0, COOKIE_LEN); ++ up_read(&peer->latest_cookie.lock); ++} ++ ++void wg_cookie_message_create(struct message_handshake_cookie *dst, ++ struct sk_buff *skb, __le32 index, ++ struct cookie_checker *checker) ++{ ++ struct message_macs *macs = (struct message_macs *) ++ ((u8 *)skb->data + skb->len - sizeof(*macs)); ++ u8 cookie[COOKIE_LEN]; ++ ++ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE); ++ dst->receiver_index = index; ++ get_random_bytes_wait(dst->nonce, COOKIE_NONCE_LEN); ++ ++ make_cookie(cookie, skb, checker); ++ xchacha20poly1305_encrypt(dst->encrypted_cookie, cookie, COOKIE_LEN, ++ macs->mac1, COOKIE_LEN, dst->nonce, ++ checker->cookie_encryption_key); ++} ++ ++void wg_cookie_message_consume(struct message_handshake_cookie *src, ++ struct wg_device *wg) ++{ ++ struct wg_peer *peer = NULL; ++ u8 cookie[COOKIE_LEN]; ++ bool ret; ++ ++ if (unlikely(!wg_index_hashtable_lookup(wg->index_hashtable, ++ INDEX_HASHTABLE_HANDSHAKE | ++ INDEX_HASHTABLE_KEYPAIR, ++ src->receiver_index, &peer))) ++ return; ++ ++ down_read(&peer->latest_cookie.lock); ++ if (unlikely(!peer->latest_cookie.have_sent_mac1)) { ++ up_read(&peer->latest_cookie.lock); ++ goto out; ++ } ++ ret = xchacha20poly1305_decrypt( ++ cookie, src->encrypted_cookie, sizeof(src->encrypted_cookie), ++ peer->latest_cookie.last_mac1_sent, COOKIE_LEN, src->nonce, ++ peer->latest_cookie.cookie_decryption_key); ++ up_read(&peer->latest_cookie.lock); ++ ++ if (ret) { ++ down_write(&peer->latest_cookie.lock); ++ memcpy(peer->latest_cookie.cookie, cookie, COOKIE_LEN); ++ peer->latest_cookie.birthdate = ktime_get_coarse_boottime_ns(); ++ peer->latest_cookie.is_valid = true; ++ peer->latest_cookie.have_sent_mac1 = false; ++ up_write(&peer->latest_cookie.lock); ++ } else { ++ net_dbg_ratelimited("%s: Could not decrypt invalid cookie response\n", ++ wg->dev->name); ++ } ++ ++out: ++ wg_peer_put(peer); ++} +--- /dev/null ++++ b/drivers/net/wireguard/cookie.h +@@ -0,0 +1,59 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_COOKIE_H ++#define _WG_COOKIE_H ++ ++#include "messages.h" ++#include ++ ++struct wg_peer; ++ ++struct cookie_checker { ++ u8 secret[NOISE_HASH_LEN]; ++ u8 cookie_encryption_key[NOISE_SYMMETRIC_KEY_LEN]; ++ u8 message_mac1_key[NOISE_SYMMETRIC_KEY_LEN]; ++ u64 secret_birthdate; ++ struct rw_semaphore secret_lock; ++ struct wg_device *device; ++}; ++ ++struct cookie { ++ u64 birthdate; ++ bool is_valid; ++ u8 cookie[COOKIE_LEN]; ++ bool have_sent_mac1; ++ u8 last_mac1_sent[COOKIE_LEN]; ++ u8 cookie_decryption_key[NOISE_SYMMETRIC_KEY_LEN]; ++ u8 message_mac1_key[NOISE_SYMMETRIC_KEY_LEN]; ++ struct rw_semaphore lock; ++}; ++ ++enum cookie_mac_state { ++ INVALID_MAC, ++ VALID_MAC_BUT_NO_COOKIE, ++ VALID_MAC_WITH_COOKIE_BUT_RATELIMITED, ++ VALID_MAC_WITH_COOKIE ++}; ++ ++void wg_cookie_checker_init(struct cookie_checker *checker, ++ struct wg_device *wg); ++void wg_cookie_checker_precompute_device_keys(struct cookie_checker *checker); ++void wg_cookie_checker_precompute_peer_keys(struct wg_peer *peer); ++void wg_cookie_init(struct cookie *cookie); ++ ++enum cookie_mac_state wg_cookie_validate_packet(struct cookie_checker *checker, ++ struct sk_buff *skb, ++ bool check_cookie); ++void wg_cookie_add_mac_to_packet(void *message, size_t len, ++ struct wg_peer *peer); ++ ++void wg_cookie_message_create(struct message_handshake_cookie *src, ++ struct sk_buff *skb, __le32 index, ++ struct cookie_checker *checker); ++void wg_cookie_message_consume(struct message_handshake_cookie *src, ++ struct wg_device *wg); ++ ++#endif /* _WG_COOKIE_H */ +--- /dev/null ++++ b/drivers/net/wireguard/device.c +@@ -0,0 +1,458 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "queueing.h" ++#include "socket.h" ++#include "timers.h" ++#include "device.h" ++#include "ratelimiter.h" ++#include "peer.h" ++#include "messages.h" ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++static LIST_HEAD(device_list); ++ ++static int wg_open(struct net_device *dev) ++{ ++ struct in_device *dev_v4 = __in_dev_get_rtnl(dev); ++ struct inet6_dev *dev_v6 = __in6_dev_get(dev); ++ struct wg_device *wg = netdev_priv(dev); ++ struct wg_peer *peer; ++ int ret; ++ ++ if (dev_v4) { ++ /* At some point we might put this check near the ip_rt_send_ ++ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar ++ * to the current secpath check. ++ */ ++ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); ++ IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; ++ } ++ if (dev_v6) ++ dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; ++ ++ ret = wg_socket_init(wg, wg->incoming_port); ++ if (ret < 0) ++ return ret; ++ mutex_lock(&wg->device_update_lock); ++ list_for_each_entry(peer, &wg->peer_list, peer_list) { ++ wg_packet_send_staged_packets(peer); ++ if (peer->persistent_keepalive_interval) ++ wg_packet_send_keepalive(peer); ++ } ++ mutex_unlock(&wg->device_update_lock); ++ return 0; ++} ++ ++#ifdef CONFIG_PM_SLEEP ++static int wg_pm_notification(struct notifier_block *nb, unsigned long action, ++ void *data) ++{ ++ struct wg_device *wg; ++ struct wg_peer *peer; ++ ++ /* If the machine is constantly suspending and resuming, as part of ++ * its normal operation rather than as a somewhat rare event, then we ++ * don't actually want to clear keys. ++ */ ++ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_ANDROID)) ++ return 0; ++ ++ if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE) ++ return 0; ++ ++ rtnl_lock(); ++ list_for_each_entry(wg, &device_list, device_list) { ++ mutex_lock(&wg->device_update_lock); ++ list_for_each_entry(peer, &wg->peer_list, peer_list) { ++ del_timer(&peer->timer_zero_key_material); ++ wg_noise_handshake_clear(&peer->handshake); ++ wg_noise_keypairs_clear(&peer->keypairs); ++ } ++ mutex_unlock(&wg->device_update_lock); ++ } ++ rtnl_unlock(); ++ rcu_barrier(); ++ return 0; ++} ++ ++static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification }; ++#endif ++ ++static int wg_stop(struct net_device *dev) ++{ ++ struct wg_device *wg = netdev_priv(dev); ++ struct wg_peer *peer; ++ ++ mutex_lock(&wg->device_update_lock); ++ list_for_each_entry(peer, &wg->peer_list, peer_list) { ++ wg_packet_purge_staged_packets(peer); ++ wg_timers_stop(peer); ++ wg_noise_handshake_clear(&peer->handshake); ++ wg_noise_keypairs_clear(&peer->keypairs); ++ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); ++ } ++ mutex_unlock(&wg->device_update_lock); ++ skb_queue_purge(&wg->incoming_handshakes); ++ wg_socket_reinit(wg, NULL, NULL); ++ return 0; ++} ++ ++static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) ++{ ++ struct wg_device *wg = netdev_priv(dev); ++ struct sk_buff_head packets; ++ struct wg_peer *peer; ++ struct sk_buff *next; ++ sa_family_t family; ++ u32 mtu; ++ int ret; ++ ++ if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) { ++ ret = -EPROTONOSUPPORT; ++ net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); ++ goto err; ++ } ++ ++ peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb); ++ if (unlikely(!peer)) { ++ ret = -ENOKEY; ++ if (skb->protocol == htons(ETH_P_IP)) ++ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n", ++ dev->name, &ip_hdr(skb)->daddr); ++ else if (skb->protocol == htons(ETH_P_IPV6)) ++ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", ++ dev->name, &ipv6_hdr(skb)->daddr); ++ goto err; ++ } ++ ++ family = READ_ONCE(peer->endpoint.addr.sa_family); ++ if (unlikely(family != AF_INET && family != AF_INET6)) { ++ ret = -EDESTADDRREQ; ++ net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n", ++ dev->name, peer->internal_id); ++ goto err_peer; ++ } ++ ++ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; ++ ++ __skb_queue_head_init(&packets); ++ if (!skb_is_gso(skb)) { ++ skb_mark_not_on_list(skb); ++ } else { ++ struct sk_buff *segs = skb_gso_segment(skb, 0); ++ ++ if (unlikely(IS_ERR(segs))) { ++ ret = PTR_ERR(segs); ++ goto err_peer; ++ } ++ dev_kfree_skb(skb); ++ skb = segs; ++ } ++ ++ skb_list_walk_safe(skb, skb, next) { ++ skb_mark_not_on_list(skb); ++ ++ skb = skb_share_check(skb, GFP_ATOMIC); ++ if (unlikely(!skb)) ++ continue; ++ ++ /* We only need to keep the original dst around for icmp, ++ * so at this point we're in a position to drop it. ++ */ ++ skb_dst_drop(skb); ++ ++ PACKET_CB(skb)->mtu = mtu; ++ ++ __skb_queue_tail(&packets, skb); ++ } ++ ++ spin_lock_bh(&peer->staged_packet_queue.lock); ++ /* If the queue is getting too big, we start removing the oldest packets ++ * until it's small again. We do this before adding the new packet, so ++ * we don't remove GSO segments that are in excess. ++ */ ++ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { ++ dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); ++ ++dev->stats.tx_dropped; ++ } ++ skb_queue_splice_tail(&packets, &peer->staged_packet_queue); ++ spin_unlock_bh(&peer->staged_packet_queue.lock); ++ ++ wg_packet_send_staged_packets(peer); ++ ++ wg_peer_put(peer); ++ return NETDEV_TX_OK; ++ ++err_peer: ++ wg_peer_put(peer); ++err: ++ ++dev->stats.tx_errors; ++ if (skb->protocol == htons(ETH_P_IP)) ++ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); ++ else if (skb->protocol == htons(ETH_P_IPV6)) ++ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); ++ kfree_skb(skb); ++ return ret; ++} ++ ++static const struct net_device_ops netdev_ops = { ++ .ndo_open = wg_open, ++ .ndo_stop = wg_stop, ++ .ndo_start_xmit = wg_xmit, ++ .ndo_get_stats64 = ip_tunnel_get_stats64 ++}; ++ ++static void wg_destruct(struct net_device *dev) ++{ ++ struct wg_device *wg = netdev_priv(dev); ++ ++ rtnl_lock(); ++ list_del(&wg->device_list); ++ rtnl_unlock(); ++ mutex_lock(&wg->device_update_lock); ++ wg->incoming_port = 0; ++ wg_socket_reinit(wg, NULL, NULL); ++ /* The final references are cleared in the below calls to destroy_workqueue. */ ++ wg_peer_remove_all(wg); ++ destroy_workqueue(wg->handshake_receive_wq); ++ destroy_workqueue(wg->handshake_send_wq); ++ destroy_workqueue(wg->packet_crypt_wq); ++ wg_packet_queue_free(&wg->decrypt_queue, true); ++ wg_packet_queue_free(&wg->encrypt_queue, true); ++ rcu_barrier(); /* Wait for all the peers to be actually freed. */ ++ wg_ratelimiter_uninit(); ++ memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); ++ skb_queue_purge(&wg->incoming_handshakes); ++ free_percpu(dev->tstats); ++ free_percpu(wg->incoming_handshakes_worker); ++ if (wg->have_creating_net_ref) ++ put_net(wg->creating_net); ++ kvfree(wg->index_hashtable); ++ kvfree(wg->peer_hashtable); ++ mutex_unlock(&wg->device_update_lock); ++ ++ pr_debug("%s: Interface deleted\n", dev->name); ++ free_netdev(dev); ++} ++ ++static const struct device_type device_type = { .name = KBUILD_MODNAME }; ++ ++static void wg_setup(struct net_device *dev) ++{ ++ struct wg_device *wg = netdev_priv(dev); ++ enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | ++ NETIF_F_SG | NETIF_F_GSO | ++ NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; ++ ++ dev->netdev_ops = &netdev_ops; ++ dev->hard_header_len = 0; ++ dev->addr_len = 0; ++ dev->needed_headroom = DATA_PACKET_HEAD_ROOM; ++ dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE); ++ dev->type = ARPHRD_NONE; ++ dev->flags = IFF_POINTOPOINT | IFF_NOARP; ++ dev->priv_flags |= IFF_NO_QUEUE; ++ dev->features |= NETIF_F_LLTX; ++ dev->features |= WG_NETDEV_FEATURES; ++ dev->hw_features |= WG_NETDEV_FEATURES; ++ dev->hw_enc_features |= WG_NETDEV_FEATURES; ++ dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH - ++ sizeof(struct udphdr) - ++ max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); ++ ++ SET_NETDEV_DEVTYPE(dev, &device_type); ++ ++ /* We need to keep the dst around in case of icmp replies. */ ++ netif_keep_dst(dev); ++ ++ memset(wg, 0, sizeof(*wg)); ++ wg->dev = dev; ++} ++ ++static int wg_newlink(struct net *src_net, struct net_device *dev, ++ struct nlattr *tb[], struct nlattr *data[], ++ struct netlink_ext_ack *extack) ++{ ++ struct wg_device *wg = netdev_priv(dev); ++ int ret = -ENOMEM; ++ ++ wg->creating_net = src_net; ++ init_rwsem(&wg->static_identity.lock); ++ mutex_init(&wg->socket_update_lock); ++ mutex_init(&wg->device_update_lock); ++ skb_queue_head_init(&wg->incoming_handshakes); ++ wg_allowedips_init(&wg->peer_allowedips); ++ wg_cookie_checker_init(&wg->cookie_checker, wg); ++ INIT_LIST_HEAD(&wg->peer_list); ++ wg->device_update_gen = 1; ++ ++ wg->peer_hashtable = wg_pubkey_hashtable_alloc(); ++ if (!wg->peer_hashtable) ++ return ret; ++ ++ wg->index_hashtable = wg_index_hashtable_alloc(); ++ if (!wg->index_hashtable) ++ goto err_free_peer_hashtable; ++ ++ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); ++ if (!dev->tstats) ++ goto err_free_index_hashtable; ++ ++ wg->incoming_handshakes_worker = ++ wg_packet_percpu_multicore_worker_alloc( ++ wg_packet_handshake_receive_worker, wg); ++ if (!wg->incoming_handshakes_worker) ++ goto err_free_tstats; ++ ++ wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", ++ WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); ++ if (!wg->handshake_receive_wq) ++ goto err_free_incoming_handshakes; ++ ++ wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", ++ WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); ++ if (!wg->handshake_send_wq) ++ goto err_destroy_handshake_receive; ++ ++ wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s", ++ WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name); ++ if (!wg->packet_crypt_wq) ++ goto err_destroy_handshake_send; ++ ++ ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, ++ true, MAX_QUEUED_PACKETS); ++ if (ret < 0) ++ goto err_destroy_packet_crypt; ++ ++ ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, ++ true, MAX_QUEUED_PACKETS); ++ if (ret < 0) ++ goto err_free_encrypt_queue; ++ ++ ret = wg_ratelimiter_init(); ++ if (ret < 0) ++ goto err_free_decrypt_queue; ++ ++ ret = register_netdevice(dev); ++ if (ret < 0) ++ goto err_uninit_ratelimiter; ++ ++ list_add(&wg->device_list, &device_list); ++ ++ /* We wait until the end to assign priv_destructor, so that ++ * register_netdevice doesn't call it for us if it fails. ++ */ ++ dev->priv_destructor = wg_destruct; ++ ++ pr_debug("%s: Interface created\n", dev->name); ++ return ret; ++ ++err_uninit_ratelimiter: ++ wg_ratelimiter_uninit(); ++err_free_decrypt_queue: ++ wg_packet_queue_free(&wg->decrypt_queue, true); ++err_free_encrypt_queue: ++ wg_packet_queue_free(&wg->encrypt_queue, true); ++err_destroy_packet_crypt: ++ destroy_workqueue(wg->packet_crypt_wq); ++err_destroy_handshake_send: ++ destroy_workqueue(wg->handshake_send_wq); ++err_destroy_handshake_receive: ++ destroy_workqueue(wg->handshake_receive_wq); ++err_free_incoming_handshakes: ++ free_percpu(wg->incoming_handshakes_worker); ++err_free_tstats: ++ free_percpu(dev->tstats); ++err_free_index_hashtable: ++ kvfree(wg->index_hashtable); ++err_free_peer_hashtable: ++ kvfree(wg->peer_hashtable); ++ return ret; ++} ++ ++static struct rtnl_link_ops link_ops __read_mostly = { ++ .kind = KBUILD_MODNAME, ++ .priv_size = sizeof(struct wg_device), ++ .setup = wg_setup, ++ .newlink = wg_newlink, ++}; ++ ++static int wg_netdevice_notification(struct notifier_block *nb, ++ unsigned long action, void *data) ++{ ++ struct net_device *dev = ((struct netdev_notifier_info *)data)->dev; ++ struct wg_device *wg = netdev_priv(dev); ++ ++ ASSERT_RTNL(); ++ ++ if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops) ++ return 0; ++ ++ if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) { ++ put_net(wg->creating_net); ++ wg->have_creating_net_ref = false; ++ } else if (dev_net(dev) != wg->creating_net && ++ !wg->have_creating_net_ref) { ++ wg->have_creating_net_ref = true; ++ get_net(wg->creating_net); ++ } ++ return 0; ++} ++ ++static struct notifier_block netdevice_notifier = { ++ .notifier_call = wg_netdevice_notification ++}; ++ ++int __init wg_device_init(void) ++{ ++ int ret; ++ ++#ifdef CONFIG_PM_SLEEP ++ ret = register_pm_notifier(&pm_notifier); ++ if (ret) ++ return ret; ++#endif ++ ++ ret = register_netdevice_notifier(&netdevice_notifier); ++ if (ret) ++ goto error_pm; ++ ++ ret = rtnl_link_register(&link_ops); ++ if (ret) ++ goto error_netdevice; ++ ++ return 0; ++ ++error_netdevice: ++ unregister_netdevice_notifier(&netdevice_notifier); ++error_pm: ++#ifdef CONFIG_PM_SLEEP ++ unregister_pm_notifier(&pm_notifier); ++#endif ++ return ret; ++} ++ ++void wg_device_uninit(void) ++{ ++ rtnl_link_unregister(&link_ops); ++ unregister_netdevice_notifier(&netdevice_notifier); ++#ifdef CONFIG_PM_SLEEP ++ unregister_pm_notifier(&pm_notifier); ++#endif ++ rcu_barrier(); ++} +--- /dev/null ++++ b/drivers/net/wireguard/device.h +@@ -0,0 +1,65 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_DEVICE_H ++#define _WG_DEVICE_H ++ ++#include "noise.h" ++#include "allowedips.h" ++#include "peerlookup.h" ++#include "cookie.h" ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++struct wg_device; ++ ++struct multicore_worker { ++ void *ptr; ++ struct work_struct work; ++}; ++ ++struct crypt_queue { ++ struct ptr_ring ring; ++ union { ++ struct { ++ struct multicore_worker __percpu *worker; ++ int last_cpu; ++ }; ++ struct work_struct work; ++ }; ++}; ++ ++struct wg_device { ++ struct net_device *dev; ++ struct crypt_queue encrypt_queue, decrypt_queue; ++ struct sock __rcu *sock4, *sock6; ++ struct net *creating_net; ++ struct noise_static_identity static_identity; ++ struct workqueue_struct *handshake_receive_wq, *handshake_send_wq; ++ struct workqueue_struct *packet_crypt_wq; ++ struct sk_buff_head incoming_handshakes; ++ int incoming_handshake_cpu; ++ struct multicore_worker __percpu *incoming_handshakes_worker; ++ struct cookie_checker cookie_checker; ++ struct pubkey_hashtable *peer_hashtable; ++ struct index_hashtable *index_hashtable; ++ struct allowedips peer_allowedips; ++ struct mutex device_update_lock, socket_update_lock; ++ struct list_head device_list, peer_list; ++ unsigned int num_peers, device_update_gen; ++ u32 fwmark; ++ u16 incoming_port; ++ bool have_creating_net_ref; ++}; ++ ++int wg_device_init(void); ++void wg_device_uninit(void); ++ ++#endif /* _WG_DEVICE_H */ +--- /dev/null ++++ b/drivers/net/wireguard/main.c +@@ -0,0 +1,64 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "version.h" ++#include "device.h" ++#include "noise.h" ++#include "queueing.h" ++#include "ratelimiter.h" ++#include "netlink.h" ++ ++#include ++ ++#include ++#include ++#include ++#include ++#include ++ ++static int __init mod_init(void) ++{ ++ int ret; ++ ++#ifdef DEBUG ++ if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() || ++ !wg_ratelimiter_selftest()) ++ return -ENOTRECOVERABLE; ++#endif ++ wg_noise_init(); ++ ++ ret = wg_device_init(); ++ if (ret < 0) ++ goto err_device; ++ ++ ret = wg_genetlink_init(); ++ if (ret < 0) ++ goto err_netlink; ++ ++ pr_info("WireGuard " WIREGUARD_VERSION " loaded. See www.wireguard.com for information.\n"); ++ pr_info("Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved.\n"); ++ ++ return 0; ++ ++err_netlink: ++ wg_device_uninit(); ++err_device: ++ return ret; ++} ++ ++static void __exit mod_exit(void) ++{ ++ wg_genetlink_uninit(); ++ wg_device_uninit(); ++} ++ ++module_init(mod_init); ++module_exit(mod_exit); ++MODULE_LICENSE("GPL v2"); ++MODULE_DESCRIPTION("WireGuard secure network tunnel"); ++MODULE_AUTHOR("Jason A. Donenfeld "); ++MODULE_VERSION(WIREGUARD_VERSION); ++MODULE_ALIAS_RTNL_LINK(KBUILD_MODNAME); ++MODULE_ALIAS_GENL_FAMILY(WG_GENL_NAME); +--- /dev/null ++++ b/drivers/net/wireguard/messages.h +@@ -0,0 +1,128 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_MESSAGES_H ++#define _WG_MESSAGES_H ++ ++#include ++#include ++#include ++ ++#include ++#include ++#include ++ ++enum noise_lengths { ++ NOISE_PUBLIC_KEY_LEN = CURVE25519_KEY_SIZE, ++ NOISE_SYMMETRIC_KEY_LEN = CHACHA20POLY1305_KEY_SIZE, ++ NOISE_TIMESTAMP_LEN = sizeof(u64) + sizeof(u32), ++ NOISE_AUTHTAG_LEN = CHACHA20POLY1305_AUTHTAG_SIZE, ++ NOISE_HASH_LEN = BLAKE2S_HASH_SIZE ++}; ++ ++#define noise_encrypted_len(plain_len) ((plain_len) + NOISE_AUTHTAG_LEN) ++ ++enum cookie_values { ++ COOKIE_SECRET_MAX_AGE = 2 * 60, ++ COOKIE_SECRET_LATENCY = 5, ++ COOKIE_NONCE_LEN = XCHACHA20POLY1305_NONCE_SIZE, ++ COOKIE_LEN = 16 ++}; ++ ++enum counter_values { ++ COUNTER_BITS_TOTAL = 2048, ++ COUNTER_REDUNDANT_BITS = BITS_PER_LONG, ++ COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS ++}; ++ ++enum limits { ++ REKEY_AFTER_MESSAGES = 1ULL << 60, ++ REJECT_AFTER_MESSAGES = U64_MAX - COUNTER_WINDOW_SIZE - 1, ++ REKEY_TIMEOUT = 5, ++ REKEY_TIMEOUT_JITTER_MAX_JIFFIES = HZ / 3, ++ REKEY_AFTER_TIME = 120, ++ REJECT_AFTER_TIME = 180, ++ INITIATIONS_PER_SECOND = 50, ++ MAX_PEERS_PER_DEVICE = 1U << 20, ++ KEEPALIVE_TIMEOUT = 10, ++ MAX_TIMER_HANDSHAKES = 90 / REKEY_TIMEOUT, ++ MAX_QUEUED_INCOMING_HANDSHAKES = 4096, /* TODO: replace this with DQL */ ++ MAX_STAGED_PACKETS = 128, ++ MAX_QUEUED_PACKETS = 1024 /* TODO: replace this with DQL */ ++}; ++ ++enum message_type { ++ MESSAGE_INVALID = 0, ++ MESSAGE_HANDSHAKE_INITIATION = 1, ++ MESSAGE_HANDSHAKE_RESPONSE = 2, ++ MESSAGE_HANDSHAKE_COOKIE = 3, ++ MESSAGE_DATA = 4 ++}; ++ ++struct message_header { ++ /* The actual layout of this that we want is: ++ * u8 type ++ * u8 reserved_zero[3] ++ * ++ * But it turns out that by encoding this as little endian, ++ * we achieve the same thing, and it makes checking faster. ++ */ ++ __le32 type; ++}; ++ ++struct message_macs { ++ u8 mac1[COOKIE_LEN]; ++ u8 mac2[COOKIE_LEN]; ++}; ++ ++struct message_handshake_initiation { ++ struct message_header header; ++ __le32 sender_index; ++ u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN]; ++ u8 encrypted_static[noise_encrypted_len(NOISE_PUBLIC_KEY_LEN)]; ++ u8 encrypted_timestamp[noise_encrypted_len(NOISE_TIMESTAMP_LEN)]; ++ struct message_macs macs; ++}; ++ ++struct message_handshake_response { ++ struct message_header header; ++ __le32 sender_index; ++ __le32 receiver_index; ++ u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN]; ++ u8 encrypted_nothing[noise_encrypted_len(0)]; ++ struct message_macs macs; ++}; ++ ++struct message_handshake_cookie { ++ struct message_header header; ++ __le32 receiver_index; ++ u8 nonce[COOKIE_NONCE_LEN]; ++ u8 encrypted_cookie[noise_encrypted_len(COOKIE_LEN)]; ++}; ++ ++struct message_data { ++ struct message_header header; ++ __le32 key_idx; ++ __le64 counter; ++ u8 encrypted_data[]; ++}; ++ ++#define message_data_len(plain_len) \ ++ (noise_encrypted_len(plain_len) + sizeof(struct message_data)) ++ ++enum message_alignments { ++ MESSAGE_PADDING_MULTIPLE = 16, ++ MESSAGE_MINIMUM_LENGTH = message_data_len(0) ++}; ++ ++#define SKB_HEADER_LEN \ ++ (max(sizeof(struct iphdr), sizeof(struct ipv6hdr)) + \ ++ sizeof(struct udphdr) + NET_SKB_PAD) ++#define DATA_PACKET_HEAD_ROOM \ ++ ALIGN(sizeof(struct message_data) + SKB_HEADER_LEN, 4) ++ ++enum { HANDSHAKE_DSCP = 0x88 /* AF41, plus 00 ECN */ }; ++ ++#endif /* _WG_MESSAGES_H */ +--- /dev/null ++++ b/drivers/net/wireguard/netlink.c +@@ -0,0 +1,648 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "netlink.h" ++#include "device.h" ++#include "peer.h" ++#include "socket.h" ++#include "queueing.h" ++#include "messages.h" ++ ++#include ++ ++#include ++#include ++#include ++#include ++ ++static struct genl_family genl_family; ++ ++static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = { ++ [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 }, ++ [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, ++ [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, ++ [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, ++ [WGDEVICE_A_FLAGS] = { .type = NLA_U32 }, ++ [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 }, ++ [WGDEVICE_A_FWMARK] = { .type = NLA_U32 }, ++ [WGDEVICE_A_PEERS] = { .type = NLA_NESTED } ++}; ++ ++static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = { ++ [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, ++ [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN }, ++ [WGPEER_A_FLAGS] = { .type = NLA_U32 }, ++ [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) }, ++ [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 }, ++ [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) }, ++ [WGPEER_A_RX_BYTES] = { .type = NLA_U64 }, ++ [WGPEER_A_TX_BYTES] = { .type = NLA_U64 }, ++ [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED }, ++ [WGPEER_A_PROTOCOL_VERSION] = { .type = NLA_U32 } ++}; ++ ++static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = { ++ [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 }, ++ [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) }, ++ [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 } ++}; ++ ++static struct wg_device *lookup_interface(struct nlattr **attrs, ++ struct sk_buff *skb) ++{ ++ struct net_device *dev = NULL; ++ ++ if (!attrs[WGDEVICE_A_IFINDEX] == !attrs[WGDEVICE_A_IFNAME]) ++ return ERR_PTR(-EBADR); ++ if (attrs[WGDEVICE_A_IFINDEX]) ++ dev = dev_get_by_index(sock_net(skb->sk), ++ nla_get_u32(attrs[WGDEVICE_A_IFINDEX])); ++ else if (attrs[WGDEVICE_A_IFNAME]) ++ dev = dev_get_by_name(sock_net(skb->sk), ++ nla_data(attrs[WGDEVICE_A_IFNAME])); ++ if (!dev) ++ return ERR_PTR(-ENODEV); ++ if (!dev->rtnl_link_ops || !dev->rtnl_link_ops->kind || ++ strcmp(dev->rtnl_link_ops->kind, KBUILD_MODNAME)) { ++ dev_put(dev); ++ return ERR_PTR(-EOPNOTSUPP); ++ } ++ return netdev_priv(dev); ++} ++ ++static int get_allowedips(struct sk_buff *skb, const u8 *ip, u8 cidr, ++ int family) ++{ ++ struct nlattr *allowedip_nest; ++ ++ allowedip_nest = nla_nest_start(skb, 0); ++ if (!allowedip_nest) ++ return -EMSGSIZE; ++ ++ if (nla_put_u8(skb, WGALLOWEDIP_A_CIDR_MASK, cidr) || ++ nla_put_u16(skb, WGALLOWEDIP_A_FAMILY, family) || ++ nla_put(skb, WGALLOWEDIP_A_IPADDR, family == AF_INET6 ? ++ sizeof(struct in6_addr) : sizeof(struct in_addr), ip)) { ++ nla_nest_cancel(skb, allowedip_nest); ++ return -EMSGSIZE; ++ } ++ ++ nla_nest_end(skb, allowedip_nest); ++ return 0; ++} ++ ++struct dump_ctx { ++ struct wg_device *wg; ++ struct wg_peer *next_peer; ++ u64 allowedips_seq; ++ struct allowedips_node *next_allowedip; ++}; ++ ++#define DUMP_CTX(cb) ((struct dump_ctx *)(cb)->args) ++ ++static int ++get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx) ++{ ++ ++ struct nlattr *allowedips_nest, *peer_nest = nla_nest_start(skb, 0); ++ struct allowedips_node *allowedips_node = ctx->next_allowedip; ++ bool fail; ++ ++ if (!peer_nest) ++ return -EMSGSIZE; ++ ++ down_read(&peer->handshake.lock); ++ fail = nla_put(skb, WGPEER_A_PUBLIC_KEY, NOISE_PUBLIC_KEY_LEN, ++ peer->handshake.remote_static); ++ up_read(&peer->handshake.lock); ++ if (fail) ++ goto err; ++ ++ if (!allowedips_node) { ++ const struct __kernel_timespec last_handshake = { ++ .tv_sec = peer->walltime_last_handshake.tv_sec, ++ .tv_nsec = peer->walltime_last_handshake.tv_nsec ++ }; ++ ++ down_read(&peer->handshake.lock); ++ fail = nla_put(skb, WGPEER_A_PRESHARED_KEY, ++ NOISE_SYMMETRIC_KEY_LEN, ++ peer->handshake.preshared_key); ++ up_read(&peer->handshake.lock); ++ if (fail) ++ goto err; ++ ++ if (nla_put(skb, WGPEER_A_LAST_HANDSHAKE_TIME, ++ sizeof(last_handshake), &last_handshake) || ++ nla_put_u16(skb, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, ++ peer->persistent_keepalive_interval) || ++ nla_put_u64_64bit(skb, WGPEER_A_TX_BYTES, peer->tx_bytes, ++ WGPEER_A_UNSPEC) || ++ nla_put_u64_64bit(skb, WGPEER_A_RX_BYTES, peer->rx_bytes, ++ WGPEER_A_UNSPEC) || ++ nla_put_u32(skb, WGPEER_A_PROTOCOL_VERSION, 1)) ++ goto err; ++ ++ read_lock_bh(&peer->endpoint_lock); ++ if (peer->endpoint.addr.sa_family == AF_INET) ++ fail = nla_put(skb, WGPEER_A_ENDPOINT, ++ sizeof(peer->endpoint.addr4), ++ &peer->endpoint.addr4); ++ else if (peer->endpoint.addr.sa_family == AF_INET6) ++ fail = nla_put(skb, WGPEER_A_ENDPOINT, ++ sizeof(peer->endpoint.addr6), ++ &peer->endpoint.addr6); ++ read_unlock_bh(&peer->endpoint_lock); ++ if (fail) ++ goto err; ++ allowedips_node = ++ list_first_entry_or_null(&peer->allowedips_list, ++ struct allowedips_node, peer_list); ++ } ++ if (!allowedips_node) ++ goto no_allowedips; ++ if (!ctx->allowedips_seq) ++ ctx->allowedips_seq = peer->device->peer_allowedips.seq; ++ else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq) ++ goto no_allowedips; ++ ++ allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS); ++ if (!allowedips_nest) ++ goto err; ++ ++ list_for_each_entry_from(allowedips_node, &peer->allowedips_list, ++ peer_list) { ++ u8 cidr, ip[16] __aligned(__alignof(u64)); ++ int family; ++ ++ family = wg_allowedips_read_node(allowedips_node, ip, &cidr); ++ if (get_allowedips(skb, ip, cidr, family)) { ++ nla_nest_end(skb, allowedips_nest); ++ nla_nest_end(skb, peer_nest); ++ ctx->next_allowedip = allowedips_node; ++ return -EMSGSIZE; ++ } ++ } ++ nla_nest_end(skb, allowedips_nest); ++no_allowedips: ++ nla_nest_end(skb, peer_nest); ++ ctx->next_allowedip = NULL; ++ ctx->allowedips_seq = 0; ++ return 0; ++err: ++ nla_nest_cancel(skb, peer_nest); ++ return -EMSGSIZE; ++} ++ ++static int wg_get_device_start(struct netlink_callback *cb) ++{ ++ struct nlattr **attrs = genl_family_attrbuf(&genl_family); ++ struct wg_device *wg; ++ int ret; ++ ++ ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + genl_family.hdrsize, attrs, ++ genl_family.maxattr, device_policy, NULL); ++ if (ret < 0) ++ return ret; ++ wg = lookup_interface(attrs, cb->skb); ++ if (IS_ERR(wg)) ++ return PTR_ERR(wg); ++ DUMP_CTX(cb)->wg = wg; ++ return 0; ++} ++ ++static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb) ++{ ++ struct wg_peer *peer, *next_peer_cursor; ++ struct dump_ctx *ctx = DUMP_CTX(cb); ++ struct wg_device *wg = ctx->wg; ++ struct nlattr *peers_nest; ++ int ret = -EMSGSIZE; ++ bool done = true; ++ void *hdr; ++ ++ rtnl_lock(); ++ mutex_lock(&wg->device_update_lock); ++ cb->seq = wg->device_update_gen; ++ next_peer_cursor = ctx->next_peer; ++ ++ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, ++ &genl_family, NLM_F_MULTI, WG_CMD_GET_DEVICE); ++ if (!hdr) ++ goto out; ++ genl_dump_check_consistent(cb, hdr); ++ ++ if (!ctx->next_peer) { ++ if (nla_put_u16(skb, WGDEVICE_A_LISTEN_PORT, ++ wg->incoming_port) || ++ nla_put_u32(skb, WGDEVICE_A_FWMARK, wg->fwmark) || ++ nla_put_u32(skb, WGDEVICE_A_IFINDEX, wg->dev->ifindex) || ++ nla_put_string(skb, WGDEVICE_A_IFNAME, wg->dev->name)) ++ goto out; ++ ++ down_read(&wg->static_identity.lock); ++ if (wg->static_identity.has_identity) { ++ if (nla_put(skb, WGDEVICE_A_PRIVATE_KEY, ++ NOISE_PUBLIC_KEY_LEN, ++ wg->static_identity.static_private) || ++ nla_put(skb, WGDEVICE_A_PUBLIC_KEY, ++ NOISE_PUBLIC_KEY_LEN, ++ wg->static_identity.static_public)) { ++ up_read(&wg->static_identity.lock); ++ goto out; ++ } ++ } ++ up_read(&wg->static_identity.lock); ++ } ++ ++ peers_nest = nla_nest_start(skb, WGDEVICE_A_PEERS); ++ if (!peers_nest) ++ goto out; ++ ret = 0; ++ /* If the last cursor was removed via list_del_init in peer_remove, then ++ * we just treat this the same as there being no more peers left. The ++ * reason is that seq_nr should indicate to userspace that this isn't a ++ * coherent dump anyway, so they'll try again. ++ */ ++ if (list_empty(&wg->peer_list) || ++ (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) { ++ nla_nest_cancel(skb, peers_nest); ++ goto out; ++ } ++ lockdep_assert_held(&wg->device_update_lock); ++ peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list); ++ list_for_each_entry_continue(peer, &wg->peer_list, peer_list) { ++ if (get_peer(peer, skb, ctx)) { ++ done = false; ++ break; ++ } ++ next_peer_cursor = peer; ++ } ++ nla_nest_end(skb, peers_nest); ++ ++out: ++ if (!ret && !done && next_peer_cursor) ++ wg_peer_get(next_peer_cursor); ++ wg_peer_put(ctx->next_peer); ++ mutex_unlock(&wg->device_update_lock); ++ rtnl_unlock(); ++ ++ if (ret) { ++ genlmsg_cancel(skb, hdr); ++ return ret; ++ } ++ genlmsg_end(skb, hdr); ++ if (done) { ++ ctx->next_peer = NULL; ++ return 0; ++ } ++ ctx->next_peer = next_peer_cursor; ++ return skb->len; ++ ++ /* At this point, we can't really deal ourselves with safely zeroing out ++ * the private key material after usage. This will need an additional API ++ * in the kernel for marking skbs as zero_on_free. ++ */ ++} ++ ++static int wg_get_device_done(struct netlink_callback *cb) ++{ ++ struct dump_ctx *ctx = DUMP_CTX(cb); ++ ++ if (ctx->wg) ++ dev_put(ctx->wg->dev); ++ wg_peer_put(ctx->next_peer); ++ return 0; ++} ++ ++static int set_port(struct wg_device *wg, u16 port) ++{ ++ struct wg_peer *peer; ++ ++ if (wg->incoming_port == port) ++ return 0; ++ list_for_each_entry(peer, &wg->peer_list, peer_list) ++ wg_socket_clear_peer_endpoint_src(peer); ++ if (!netif_running(wg->dev)) { ++ wg->incoming_port = port; ++ return 0; ++ } ++ return wg_socket_init(wg, port); ++} ++ ++static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs) ++{ ++ int ret = -EINVAL; ++ u16 family; ++ u8 cidr; ++ ++ if (!attrs[WGALLOWEDIP_A_FAMILY] || !attrs[WGALLOWEDIP_A_IPADDR] || ++ !attrs[WGALLOWEDIP_A_CIDR_MASK]) ++ return ret; ++ family = nla_get_u16(attrs[WGALLOWEDIP_A_FAMILY]); ++ cidr = nla_get_u8(attrs[WGALLOWEDIP_A_CIDR_MASK]); ++ ++ if (family == AF_INET && cidr <= 32 && ++ nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr)) ++ ret = wg_allowedips_insert_v4( ++ &peer->device->peer_allowedips, ++ nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer, ++ &peer->device->device_update_lock); ++ else if (family == AF_INET6 && cidr <= 128 && ++ nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr)) ++ ret = wg_allowedips_insert_v6( ++ &peer->device->peer_allowedips, ++ nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer, ++ &peer->device->device_update_lock); ++ ++ return ret; ++} ++ ++static int set_peer(struct wg_device *wg, struct nlattr **attrs) ++{ ++ u8 *public_key = NULL, *preshared_key = NULL; ++ struct wg_peer *peer = NULL; ++ u32 flags = 0; ++ int ret; ++ ++ ret = -EINVAL; ++ if (attrs[WGPEER_A_PUBLIC_KEY] && ++ nla_len(attrs[WGPEER_A_PUBLIC_KEY]) == NOISE_PUBLIC_KEY_LEN) ++ public_key = nla_data(attrs[WGPEER_A_PUBLIC_KEY]); ++ else ++ goto out; ++ if (attrs[WGPEER_A_PRESHARED_KEY] && ++ nla_len(attrs[WGPEER_A_PRESHARED_KEY]) == NOISE_SYMMETRIC_KEY_LEN) ++ preshared_key = nla_data(attrs[WGPEER_A_PRESHARED_KEY]); ++ ++ if (attrs[WGPEER_A_FLAGS]) ++ flags = nla_get_u32(attrs[WGPEER_A_FLAGS]); ++ ret = -EOPNOTSUPP; ++ if (flags & ~__WGPEER_F_ALL) ++ goto out; ++ ++ ret = -EPFNOSUPPORT; ++ if (attrs[WGPEER_A_PROTOCOL_VERSION]) { ++ if (nla_get_u32(attrs[WGPEER_A_PROTOCOL_VERSION]) != 1) ++ goto out; ++ } ++ ++ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, ++ nla_data(attrs[WGPEER_A_PUBLIC_KEY])); ++ ret = 0; ++ if (!peer) { /* Peer doesn't exist yet. Add a new one. */ ++ if (flags & (WGPEER_F_REMOVE_ME | WGPEER_F_UPDATE_ONLY)) ++ goto out; ++ ++ /* The peer is new, so there aren't allowed IPs to remove. */ ++ flags &= ~WGPEER_F_REPLACE_ALLOWEDIPS; ++ ++ down_read(&wg->static_identity.lock); ++ if (wg->static_identity.has_identity && ++ !memcmp(nla_data(attrs[WGPEER_A_PUBLIC_KEY]), ++ wg->static_identity.static_public, ++ NOISE_PUBLIC_KEY_LEN)) { ++ /* We silently ignore peers that have the same public ++ * key as the device. The reason we do it silently is ++ * that we'd like for people to be able to reuse the ++ * same set of API calls across peers. ++ */ ++ up_read(&wg->static_identity.lock); ++ ret = 0; ++ goto out; ++ } ++ up_read(&wg->static_identity.lock); ++ ++ peer = wg_peer_create(wg, public_key, preshared_key); ++ if (IS_ERR(peer)) { ++ /* Similar to the above, if the key is invalid, we skip ++ * it without fanfare, so that services don't need to ++ * worry about doing key validation themselves. ++ */ ++ ret = PTR_ERR(peer) == -EKEYREJECTED ? 0 : PTR_ERR(peer); ++ peer = NULL; ++ goto out; ++ } ++ /* Take additional reference, as though we've just been ++ * looked up. ++ */ ++ wg_peer_get(peer); ++ } ++ ++ if (flags & WGPEER_F_REMOVE_ME) { ++ wg_peer_remove(peer); ++ goto out; ++ } ++ ++ if (preshared_key) { ++ down_write(&peer->handshake.lock); ++ memcpy(&peer->handshake.preshared_key, preshared_key, ++ NOISE_SYMMETRIC_KEY_LEN); ++ up_write(&peer->handshake.lock); ++ } ++ ++ if (attrs[WGPEER_A_ENDPOINT]) { ++ struct sockaddr *addr = nla_data(attrs[WGPEER_A_ENDPOINT]); ++ size_t len = nla_len(attrs[WGPEER_A_ENDPOINT]); ++ ++ if ((len == sizeof(struct sockaddr_in) && ++ addr->sa_family == AF_INET) || ++ (len == sizeof(struct sockaddr_in6) && ++ addr->sa_family == AF_INET6)) { ++ struct endpoint endpoint = { { { 0 } } }; ++ ++ memcpy(&endpoint.addr, addr, len); ++ wg_socket_set_peer_endpoint(peer, &endpoint); ++ } ++ } ++ ++ if (flags & WGPEER_F_REPLACE_ALLOWEDIPS) ++ wg_allowedips_remove_by_peer(&wg->peer_allowedips, peer, ++ &wg->device_update_lock); ++ ++ if (attrs[WGPEER_A_ALLOWEDIPS]) { ++ struct nlattr *attr, *allowedip[WGALLOWEDIP_A_MAX + 1]; ++ int rem; ++ ++ nla_for_each_nested(attr, attrs[WGPEER_A_ALLOWEDIPS], rem) { ++ ret = nla_parse_nested(allowedip, WGALLOWEDIP_A_MAX, ++ attr, allowedip_policy, NULL); ++ if (ret < 0) ++ goto out; ++ ret = set_allowedip(peer, allowedip); ++ if (ret < 0) ++ goto out; ++ } ++ } ++ ++ if (attrs[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL]) { ++ const u16 persistent_keepalive_interval = nla_get_u16( ++ attrs[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL]); ++ const bool send_keepalive = ++ !peer->persistent_keepalive_interval && ++ persistent_keepalive_interval && ++ netif_running(wg->dev); ++ ++ peer->persistent_keepalive_interval = persistent_keepalive_interval; ++ if (send_keepalive) ++ wg_packet_send_keepalive(peer); ++ } ++ ++ if (netif_running(wg->dev)) ++ wg_packet_send_staged_packets(peer); ++ ++out: ++ wg_peer_put(peer); ++ if (attrs[WGPEER_A_PRESHARED_KEY]) ++ memzero_explicit(nla_data(attrs[WGPEER_A_PRESHARED_KEY]), ++ nla_len(attrs[WGPEER_A_PRESHARED_KEY])); ++ return ret; ++} ++ ++static int wg_set_device(struct sk_buff *skb, struct genl_info *info) ++{ ++ struct wg_device *wg = lookup_interface(info->attrs, skb); ++ u32 flags = 0; ++ int ret; ++ ++ if (IS_ERR(wg)) { ++ ret = PTR_ERR(wg); ++ goto out_nodev; ++ } ++ ++ rtnl_lock(); ++ mutex_lock(&wg->device_update_lock); ++ ++ if (info->attrs[WGDEVICE_A_FLAGS]) ++ flags = nla_get_u32(info->attrs[WGDEVICE_A_FLAGS]); ++ ret = -EOPNOTSUPP; ++ if (flags & ~__WGDEVICE_F_ALL) ++ goto out; ++ ++ ret = -EPERM; ++ if ((info->attrs[WGDEVICE_A_LISTEN_PORT] || ++ info->attrs[WGDEVICE_A_FWMARK]) && ++ !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN)) ++ goto out; ++ ++ ++wg->device_update_gen; ++ ++ if (info->attrs[WGDEVICE_A_FWMARK]) { ++ struct wg_peer *peer; ++ ++ wg->fwmark = nla_get_u32(info->attrs[WGDEVICE_A_FWMARK]); ++ list_for_each_entry(peer, &wg->peer_list, peer_list) ++ wg_socket_clear_peer_endpoint_src(peer); ++ } ++ ++ if (info->attrs[WGDEVICE_A_LISTEN_PORT]) { ++ ret = set_port(wg, ++ nla_get_u16(info->attrs[WGDEVICE_A_LISTEN_PORT])); ++ if (ret) ++ goto out; ++ } ++ ++ if (flags & WGDEVICE_F_REPLACE_PEERS) ++ wg_peer_remove_all(wg); ++ ++ if (info->attrs[WGDEVICE_A_PRIVATE_KEY] && ++ nla_len(info->attrs[WGDEVICE_A_PRIVATE_KEY]) == ++ NOISE_PUBLIC_KEY_LEN) { ++ u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]); ++ u8 public_key[NOISE_PUBLIC_KEY_LEN]; ++ struct wg_peer *peer, *temp; ++ ++ if (!crypto_memneq(wg->static_identity.static_private, ++ private_key, NOISE_PUBLIC_KEY_LEN)) ++ goto skip_set_private_key; ++ ++ /* We remove before setting, to prevent race, which means doing ++ * two 25519-genpub ops. ++ */ ++ if (curve25519_generate_public(public_key, private_key)) { ++ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, ++ public_key); ++ if (peer) { ++ wg_peer_put(peer); ++ wg_peer_remove(peer); ++ } ++ } ++ ++ down_write(&wg->static_identity.lock); ++ wg_noise_set_static_identity_private_key(&wg->static_identity, ++ private_key); ++ list_for_each_entry_safe(peer, temp, &wg->peer_list, ++ peer_list) { ++ if (wg_noise_precompute_static_static(peer)) ++ wg_noise_expire_current_peer_keypairs(peer); ++ else ++ wg_peer_remove(peer); ++ } ++ wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); ++ up_write(&wg->static_identity.lock); ++ } ++skip_set_private_key: ++ ++ if (info->attrs[WGDEVICE_A_PEERS]) { ++ struct nlattr *attr, *peer[WGPEER_A_MAX + 1]; ++ int rem; ++ ++ nla_for_each_nested(attr, info->attrs[WGDEVICE_A_PEERS], rem) { ++ ret = nla_parse_nested(peer, WGPEER_A_MAX, attr, ++ peer_policy, NULL); ++ if (ret < 0) ++ goto out; ++ ret = set_peer(wg, peer); ++ if (ret < 0) ++ goto out; ++ } ++ } ++ ret = 0; ++ ++out: ++ mutex_unlock(&wg->device_update_lock); ++ rtnl_unlock(); ++ dev_put(wg->dev); ++out_nodev: ++ if (info->attrs[WGDEVICE_A_PRIVATE_KEY]) ++ memzero_explicit(nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]), ++ nla_len(info->attrs[WGDEVICE_A_PRIVATE_KEY])); ++ return ret; ++} ++ ++static const struct genl_ops genl_ops[] = { ++ { ++ .cmd = WG_CMD_GET_DEVICE, ++ .start = wg_get_device_start, ++ .dumpit = wg_get_device_dump, ++ .done = wg_get_device_done, ++ .flags = GENL_UNS_ADMIN_PERM ++ }, { ++ .cmd = WG_CMD_SET_DEVICE, ++ .doit = wg_set_device, ++ .flags = GENL_UNS_ADMIN_PERM ++ } ++}; ++ ++static struct genl_family genl_family __ro_after_init = { ++ .ops = genl_ops, ++ .n_ops = ARRAY_SIZE(genl_ops), ++ .name = WG_GENL_NAME, ++ .version = WG_GENL_VERSION, ++ .maxattr = WGDEVICE_A_MAX, ++ .module = THIS_MODULE, ++ .policy = device_policy, ++ .netnsok = true ++}; ++ ++int __init wg_genetlink_init(void) ++{ ++ return genl_register_family(&genl_family); ++} ++ ++void __exit wg_genetlink_uninit(void) ++{ ++ genl_unregister_family(&genl_family); ++} +--- /dev/null ++++ b/drivers/net/wireguard/netlink.h +@@ -0,0 +1,12 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_NETLINK_H ++#define _WG_NETLINK_H ++ ++int wg_genetlink_init(void); ++void wg_genetlink_uninit(void); ++ ++#endif /* _WG_NETLINK_H */ +--- /dev/null ++++ b/drivers/net/wireguard/noise.c +@@ -0,0 +1,828 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "noise.h" ++#include "device.h" ++#include "peer.h" ++#include "messages.h" ++#include "queueing.h" ++#include "peerlookup.h" ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++/* This implements Noise_IKpsk2: ++ * ++ * <- s ++ * ****** ++ * -> e, es, s, ss, {t} ++ * <- e, ee, se, psk, {} ++ */ ++ ++static const u8 handshake_name[37] = "Noise_IKpsk2_25519_ChaChaPoly_BLAKE2s"; ++static const u8 identifier_name[34] = "WireGuard v1 zx2c4 Jason@zx2c4.com"; ++static u8 handshake_init_hash[NOISE_HASH_LEN] __ro_after_init; ++static u8 handshake_init_chaining_key[NOISE_HASH_LEN] __ro_after_init; ++static atomic64_t keypair_counter = ATOMIC64_INIT(0); ++ ++void __init wg_noise_init(void) ++{ ++ struct blake2s_state blake; ++ ++ blake2s(handshake_init_chaining_key, handshake_name, NULL, ++ NOISE_HASH_LEN, sizeof(handshake_name), 0); ++ blake2s_init(&blake, NOISE_HASH_LEN); ++ blake2s_update(&blake, handshake_init_chaining_key, NOISE_HASH_LEN); ++ blake2s_update(&blake, identifier_name, sizeof(identifier_name)); ++ blake2s_final(&blake, handshake_init_hash); ++} ++ ++/* Must hold peer->handshake.static_identity->lock */ ++bool wg_noise_precompute_static_static(struct wg_peer *peer) ++{ ++ bool ret = true; ++ ++ down_write(&peer->handshake.lock); ++ if (peer->handshake.static_identity->has_identity) ++ ret = curve25519( ++ peer->handshake.precomputed_static_static, ++ peer->handshake.static_identity->static_private, ++ peer->handshake.remote_static); ++ else ++ memset(peer->handshake.precomputed_static_static, 0, ++ NOISE_PUBLIC_KEY_LEN); ++ up_write(&peer->handshake.lock); ++ return ret; ++} ++ ++bool wg_noise_handshake_init(struct noise_handshake *handshake, ++ struct noise_static_identity *static_identity, ++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], ++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], ++ struct wg_peer *peer) ++{ ++ memset(handshake, 0, sizeof(*handshake)); ++ init_rwsem(&handshake->lock); ++ handshake->entry.type = INDEX_HASHTABLE_HANDSHAKE; ++ handshake->entry.peer = peer; ++ memcpy(handshake->remote_static, peer_public_key, NOISE_PUBLIC_KEY_LEN); ++ if (peer_preshared_key) ++ memcpy(handshake->preshared_key, peer_preshared_key, ++ NOISE_SYMMETRIC_KEY_LEN); ++ handshake->static_identity = static_identity; ++ handshake->state = HANDSHAKE_ZEROED; ++ return wg_noise_precompute_static_static(peer); ++} ++ ++static void handshake_zero(struct noise_handshake *handshake) ++{ ++ memset(&handshake->ephemeral_private, 0, NOISE_PUBLIC_KEY_LEN); ++ memset(&handshake->remote_ephemeral, 0, NOISE_PUBLIC_KEY_LEN); ++ memset(&handshake->hash, 0, NOISE_HASH_LEN); ++ memset(&handshake->chaining_key, 0, NOISE_HASH_LEN); ++ handshake->remote_index = 0; ++ handshake->state = HANDSHAKE_ZEROED; ++} ++ ++void wg_noise_handshake_clear(struct noise_handshake *handshake) ++{ ++ wg_index_hashtable_remove( ++ handshake->entry.peer->device->index_hashtable, ++ &handshake->entry); ++ down_write(&handshake->lock); ++ handshake_zero(handshake); ++ up_write(&handshake->lock); ++ wg_index_hashtable_remove( ++ handshake->entry.peer->device->index_hashtable, ++ &handshake->entry); ++} ++ ++static struct noise_keypair *keypair_create(struct wg_peer *peer) ++{ ++ struct noise_keypair *keypair = kzalloc(sizeof(*keypair), GFP_KERNEL); ++ ++ if (unlikely(!keypair)) ++ return NULL; ++ keypair->internal_id = atomic64_inc_return(&keypair_counter); ++ keypair->entry.type = INDEX_HASHTABLE_KEYPAIR; ++ keypair->entry.peer = peer; ++ kref_init(&keypair->refcount); ++ return keypair; ++} ++ ++static void keypair_free_rcu(struct rcu_head *rcu) ++{ ++ kzfree(container_of(rcu, struct noise_keypair, rcu)); ++} ++ ++static void keypair_free_kref(struct kref *kref) ++{ ++ struct noise_keypair *keypair = ++ container_of(kref, struct noise_keypair, refcount); ++ ++ net_dbg_ratelimited("%s: Keypair %llu destroyed for peer %llu\n", ++ keypair->entry.peer->device->dev->name, ++ keypair->internal_id, ++ keypair->entry.peer->internal_id); ++ wg_index_hashtable_remove(keypair->entry.peer->device->index_hashtable, ++ &keypair->entry); ++ call_rcu(&keypair->rcu, keypair_free_rcu); ++} ++ ++void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now) ++{ ++ if (unlikely(!keypair)) ++ return; ++ if (unlikely(unreference_now)) ++ wg_index_hashtable_remove( ++ keypair->entry.peer->device->index_hashtable, ++ &keypair->entry); ++ kref_put(&keypair->refcount, keypair_free_kref); ++} ++ ++struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair) ++{ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(), ++ "Taking noise keypair reference without holding the RCU BH read lock"); ++ if (unlikely(!keypair || !kref_get_unless_zero(&keypair->refcount))) ++ return NULL; ++ return keypair; ++} ++ ++void wg_noise_keypairs_clear(struct noise_keypairs *keypairs) ++{ ++ struct noise_keypair *old; ++ ++ spin_lock_bh(&keypairs->keypair_update_lock); ++ ++ /* We zero the next_keypair before zeroing the others, so that ++ * wg_noise_received_with_keypair returns early before subsequent ones ++ * are zeroed. ++ */ ++ old = rcu_dereference_protected(keypairs->next_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ RCU_INIT_POINTER(keypairs->next_keypair, NULL); ++ wg_noise_keypair_put(old, true); ++ ++ old = rcu_dereference_protected(keypairs->previous_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ RCU_INIT_POINTER(keypairs->previous_keypair, NULL); ++ wg_noise_keypair_put(old, true); ++ ++ old = rcu_dereference_protected(keypairs->current_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ RCU_INIT_POINTER(keypairs->current_keypair, NULL); ++ wg_noise_keypair_put(old, true); ++ ++ spin_unlock_bh(&keypairs->keypair_update_lock); ++} ++ ++void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer) ++{ ++ struct noise_keypair *keypair; ++ ++ wg_noise_handshake_clear(&peer->handshake); ++ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); ++ ++ spin_lock_bh(&peer->keypairs.keypair_update_lock); ++ keypair = rcu_dereference_protected(peer->keypairs.next_keypair, ++ lockdep_is_held(&peer->keypairs.keypair_update_lock)); ++ if (keypair) ++ keypair->sending.is_valid = false; ++ keypair = rcu_dereference_protected(peer->keypairs.current_keypair, ++ lockdep_is_held(&peer->keypairs.keypair_update_lock)); ++ if (keypair) ++ keypair->sending.is_valid = false; ++ spin_unlock_bh(&peer->keypairs.keypair_update_lock); ++} ++ ++static void add_new_keypair(struct noise_keypairs *keypairs, ++ struct noise_keypair *new_keypair) ++{ ++ struct noise_keypair *previous_keypair, *next_keypair, *current_keypair; ++ ++ spin_lock_bh(&keypairs->keypair_update_lock); ++ previous_keypair = rcu_dereference_protected(keypairs->previous_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ next_keypair = rcu_dereference_protected(keypairs->next_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ current_keypair = rcu_dereference_protected(keypairs->current_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ if (new_keypair->i_am_the_initiator) { ++ /* If we're the initiator, it means we've sent a handshake, and ++ * received a confirmation response, which means this new ++ * keypair can now be used. ++ */ ++ if (next_keypair) { ++ /* If there already was a next keypair pending, we ++ * demote it to be the previous keypair, and free the ++ * existing current. Note that this means KCI can result ++ * in this transition. It would perhaps be more sound to ++ * always just get rid of the unused next keypair ++ * instead of putting it in the previous slot, but this ++ * might be a bit less robust. Something to think about ++ * for the future. ++ */ ++ RCU_INIT_POINTER(keypairs->next_keypair, NULL); ++ rcu_assign_pointer(keypairs->previous_keypair, ++ next_keypair); ++ wg_noise_keypair_put(current_keypair, true); ++ } else /* If there wasn't an existing next keypair, we replace ++ * the previous with the current one. ++ */ ++ rcu_assign_pointer(keypairs->previous_keypair, ++ current_keypair); ++ /* At this point we can get rid of the old previous keypair, and ++ * set up the new keypair. ++ */ ++ wg_noise_keypair_put(previous_keypair, true); ++ rcu_assign_pointer(keypairs->current_keypair, new_keypair); ++ } else { ++ /* If we're the responder, it means we can't use the new keypair ++ * until we receive confirmation via the first data packet, so ++ * we get rid of the existing previous one, the possibly ++ * existing next one, and slide in the new next one. ++ */ ++ rcu_assign_pointer(keypairs->next_keypair, new_keypair); ++ wg_noise_keypair_put(next_keypair, true); ++ RCU_INIT_POINTER(keypairs->previous_keypair, NULL); ++ wg_noise_keypair_put(previous_keypair, true); ++ } ++ spin_unlock_bh(&keypairs->keypair_update_lock); ++} ++ ++bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs, ++ struct noise_keypair *received_keypair) ++{ ++ struct noise_keypair *old_keypair; ++ bool key_is_new; ++ ++ /* We first check without taking the spinlock. */ ++ key_is_new = received_keypair == ++ rcu_access_pointer(keypairs->next_keypair); ++ if (likely(!key_is_new)) ++ return false; ++ ++ spin_lock_bh(&keypairs->keypair_update_lock); ++ /* After locking, we double check that things didn't change from ++ * beneath us. ++ */ ++ if (unlikely(received_keypair != ++ rcu_dereference_protected(keypairs->next_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)))) { ++ spin_unlock_bh(&keypairs->keypair_update_lock); ++ return false; ++ } ++ ++ /* When we've finally received the confirmation, we slide the next ++ * into the current, the current into the previous, and get rid of ++ * the old previous. ++ */ ++ old_keypair = rcu_dereference_protected(keypairs->previous_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock)); ++ rcu_assign_pointer(keypairs->previous_keypair, ++ rcu_dereference_protected(keypairs->current_keypair, ++ lockdep_is_held(&keypairs->keypair_update_lock))); ++ wg_noise_keypair_put(old_keypair, true); ++ rcu_assign_pointer(keypairs->current_keypair, received_keypair); ++ RCU_INIT_POINTER(keypairs->next_keypair, NULL); ++ ++ spin_unlock_bh(&keypairs->keypair_update_lock); ++ return true; ++} ++ ++/* Must hold static_identity->lock */ ++void wg_noise_set_static_identity_private_key( ++ struct noise_static_identity *static_identity, ++ const u8 private_key[NOISE_PUBLIC_KEY_LEN]) ++{ ++ memcpy(static_identity->static_private, private_key, ++ NOISE_PUBLIC_KEY_LEN); ++ curve25519_clamp_secret(static_identity->static_private); ++ static_identity->has_identity = curve25519_generate_public( ++ static_identity->static_public, private_key); ++} ++ ++/* This is Hugo Krawczyk's HKDF: ++ * - https://eprint.iacr.org/2010/264.pdf ++ * - https://tools.ietf.org/html/rfc5869 ++ */ ++static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data, ++ size_t first_len, size_t second_len, size_t third_len, ++ size_t data_len, const u8 chaining_key[NOISE_HASH_LEN]) ++{ ++ u8 output[BLAKE2S_HASH_SIZE + 1]; ++ u8 secret[BLAKE2S_HASH_SIZE]; ++ ++ WARN_ON(IS_ENABLED(DEBUG) && ++ (first_len > BLAKE2S_HASH_SIZE || ++ second_len > BLAKE2S_HASH_SIZE || ++ third_len > BLAKE2S_HASH_SIZE || ++ ((second_len || second_dst || third_len || third_dst) && ++ (!first_len || !first_dst)) || ++ ((third_len || third_dst) && (!second_len || !second_dst)))); ++ ++ /* Extract entropy from data into secret */ ++ blake2s256_hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN); ++ ++ if (!first_dst || !first_len) ++ goto out; ++ ++ /* Expand first key: key = secret, data = 0x1 */ ++ output[0] = 1; ++ blake2s256_hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE); ++ memcpy(first_dst, output, first_len); ++ ++ if (!second_dst || !second_len) ++ goto out; ++ ++ /* Expand second key: key = secret, data = first-key || 0x2 */ ++ output[BLAKE2S_HASH_SIZE] = 2; ++ blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, ++ BLAKE2S_HASH_SIZE); ++ memcpy(second_dst, output, second_len); ++ ++ if (!third_dst || !third_len) ++ goto out; ++ ++ /* Expand third key: key = secret, data = second-key || 0x3 */ ++ output[BLAKE2S_HASH_SIZE] = 3; ++ blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, ++ BLAKE2S_HASH_SIZE); ++ memcpy(third_dst, output, third_len); ++ ++out: ++ /* Clear sensitive data from stack */ ++ memzero_explicit(secret, BLAKE2S_HASH_SIZE); ++ memzero_explicit(output, BLAKE2S_HASH_SIZE + 1); ++} ++ ++static void symmetric_key_init(struct noise_symmetric_key *key) ++{ ++ spin_lock_init(&key->counter.receive.lock); ++ atomic64_set(&key->counter.counter, 0); ++ memset(key->counter.receive.backtrack, 0, ++ sizeof(key->counter.receive.backtrack)); ++ key->birthdate = ktime_get_coarse_boottime_ns(); ++ key->is_valid = true; ++} ++ ++static void derive_keys(struct noise_symmetric_key *first_dst, ++ struct noise_symmetric_key *second_dst, ++ const u8 chaining_key[NOISE_HASH_LEN]) ++{ ++ kdf(first_dst->key, second_dst->key, NULL, NULL, ++ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0, ++ chaining_key); ++ symmetric_key_init(first_dst); ++ symmetric_key_init(second_dst); ++} ++ ++static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN], ++ u8 key[NOISE_SYMMETRIC_KEY_LEN], ++ const u8 private[NOISE_PUBLIC_KEY_LEN], ++ const u8 public[NOISE_PUBLIC_KEY_LEN]) ++{ ++ u8 dh_calculation[NOISE_PUBLIC_KEY_LEN]; ++ ++ if (unlikely(!curve25519(dh_calculation, private, public))) ++ return false; ++ kdf(chaining_key, key, NULL, dh_calculation, NOISE_HASH_LEN, ++ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, chaining_key); ++ memzero_explicit(dh_calculation, NOISE_PUBLIC_KEY_LEN); ++ return true; ++} ++ ++static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len) ++{ ++ struct blake2s_state blake; ++ ++ blake2s_init(&blake, NOISE_HASH_LEN); ++ blake2s_update(&blake, hash, NOISE_HASH_LEN); ++ blake2s_update(&blake, src, src_len); ++ blake2s_final(&blake, hash); ++} ++ ++static void mix_psk(u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN], ++ u8 key[NOISE_SYMMETRIC_KEY_LEN], ++ const u8 psk[NOISE_SYMMETRIC_KEY_LEN]) ++{ ++ u8 temp_hash[NOISE_HASH_LEN]; ++ ++ kdf(chaining_key, temp_hash, key, psk, NOISE_HASH_LEN, NOISE_HASH_LEN, ++ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, chaining_key); ++ mix_hash(hash, temp_hash, NOISE_HASH_LEN); ++ memzero_explicit(temp_hash, NOISE_HASH_LEN); ++} ++ ++static void handshake_init(u8 chaining_key[NOISE_HASH_LEN], ++ u8 hash[NOISE_HASH_LEN], ++ const u8 remote_static[NOISE_PUBLIC_KEY_LEN]) ++{ ++ memcpy(hash, handshake_init_hash, NOISE_HASH_LEN); ++ memcpy(chaining_key, handshake_init_chaining_key, NOISE_HASH_LEN); ++ mix_hash(hash, remote_static, NOISE_PUBLIC_KEY_LEN); ++} ++ ++static void message_encrypt(u8 *dst_ciphertext, const u8 *src_plaintext, ++ size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN], ++ u8 hash[NOISE_HASH_LEN]) ++{ ++ chacha20poly1305_encrypt(dst_ciphertext, src_plaintext, src_len, hash, ++ NOISE_HASH_LEN, ++ 0 /* Always zero for Noise_IK */, key); ++ mix_hash(hash, dst_ciphertext, noise_encrypted_len(src_len)); ++} ++ ++static bool message_decrypt(u8 *dst_plaintext, const u8 *src_ciphertext, ++ size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN], ++ u8 hash[NOISE_HASH_LEN]) ++{ ++ if (!chacha20poly1305_decrypt(dst_plaintext, src_ciphertext, src_len, ++ hash, NOISE_HASH_LEN, ++ 0 /* Always zero for Noise_IK */, key)) ++ return false; ++ mix_hash(hash, src_ciphertext, src_len); ++ return true; ++} ++ ++static void message_ephemeral(u8 ephemeral_dst[NOISE_PUBLIC_KEY_LEN], ++ const u8 ephemeral_src[NOISE_PUBLIC_KEY_LEN], ++ u8 chaining_key[NOISE_HASH_LEN], ++ u8 hash[NOISE_HASH_LEN]) ++{ ++ if (ephemeral_dst != ephemeral_src) ++ memcpy(ephemeral_dst, ephemeral_src, NOISE_PUBLIC_KEY_LEN); ++ mix_hash(hash, ephemeral_src, NOISE_PUBLIC_KEY_LEN); ++ kdf(chaining_key, NULL, NULL, ephemeral_src, NOISE_HASH_LEN, 0, 0, ++ NOISE_PUBLIC_KEY_LEN, chaining_key); ++} ++ ++static void tai64n_now(u8 output[NOISE_TIMESTAMP_LEN]) ++{ ++ struct timespec64 now; ++ ++ ktime_get_real_ts64(&now); ++ ++ /* In order to prevent some sort of infoleak from precise timers, we ++ * round down the nanoseconds part to the closest rounded-down power of ++ * two to the maximum initiations per second allowed anyway by the ++ * implementation. ++ */ ++ now.tv_nsec = ALIGN_DOWN(now.tv_nsec, ++ rounddown_pow_of_two(NSEC_PER_SEC / INITIATIONS_PER_SECOND)); ++ ++ /* https://cr.yp.to/libtai/tai64.html */ ++ *(__be64 *)output = cpu_to_be64(0x400000000000000aULL + now.tv_sec); ++ *(__be32 *)(output + sizeof(__be64)) = cpu_to_be32(now.tv_nsec); ++} ++ ++bool ++wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst, ++ struct noise_handshake *handshake) ++{ ++ u8 timestamp[NOISE_TIMESTAMP_LEN]; ++ u8 key[NOISE_SYMMETRIC_KEY_LEN]; ++ bool ret = false; ++ ++ /* We need to wait for crng _before_ taking any locks, since ++ * curve25519_generate_secret uses get_random_bytes_wait. ++ */ ++ wait_for_random_bytes(); ++ ++ down_read(&handshake->static_identity->lock); ++ down_write(&handshake->lock); ++ ++ if (unlikely(!handshake->static_identity->has_identity)) ++ goto out; ++ ++ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION); ++ ++ handshake_init(handshake->chaining_key, handshake->hash, ++ handshake->remote_static); ++ ++ /* e */ ++ curve25519_generate_secret(handshake->ephemeral_private); ++ if (!curve25519_generate_public(dst->unencrypted_ephemeral, ++ handshake->ephemeral_private)) ++ goto out; ++ message_ephemeral(dst->unencrypted_ephemeral, ++ dst->unencrypted_ephemeral, handshake->chaining_key, ++ handshake->hash); ++ ++ /* es */ ++ if (!mix_dh(handshake->chaining_key, key, handshake->ephemeral_private, ++ handshake->remote_static)) ++ goto out; ++ ++ /* s */ ++ message_encrypt(dst->encrypted_static, ++ handshake->static_identity->static_public, ++ NOISE_PUBLIC_KEY_LEN, key, handshake->hash); ++ ++ /* ss */ ++ kdf(handshake->chaining_key, key, NULL, ++ handshake->precomputed_static_static, NOISE_HASH_LEN, ++ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, ++ handshake->chaining_key); ++ ++ /* {t} */ ++ tai64n_now(timestamp); ++ message_encrypt(dst->encrypted_timestamp, timestamp, ++ NOISE_TIMESTAMP_LEN, key, handshake->hash); ++ ++ dst->sender_index = wg_index_hashtable_insert( ++ handshake->entry.peer->device->index_hashtable, ++ &handshake->entry); ++ ++ handshake->state = HANDSHAKE_CREATED_INITIATION; ++ ret = true; ++ ++out: ++ up_write(&handshake->lock); ++ up_read(&handshake->static_identity->lock); ++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); ++ return ret; ++} ++ ++struct wg_peer * ++wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src, ++ struct wg_device *wg) ++{ ++ struct wg_peer *peer = NULL, *ret_peer = NULL; ++ struct noise_handshake *handshake; ++ bool replay_attack, flood_attack; ++ u8 key[NOISE_SYMMETRIC_KEY_LEN]; ++ u8 chaining_key[NOISE_HASH_LEN]; ++ u8 hash[NOISE_HASH_LEN]; ++ u8 s[NOISE_PUBLIC_KEY_LEN]; ++ u8 e[NOISE_PUBLIC_KEY_LEN]; ++ u8 t[NOISE_TIMESTAMP_LEN]; ++ u64 initiation_consumption; ++ ++ down_read(&wg->static_identity.lock); ++ if (unlikely(!wg->static_identity.has_identity)) ++ goto out; ++ ++ handshake_init(chaining_key, hash, wg->static_identity.static_public); ++ ++ /* e */ ++ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash); ++ ++ /* es */ ++ if (!mix_dh(chaining_key, key, wg->static_identity.static_private, e)) ++ goto out; ++ ++ /* s */ ++ if (!message_decrypt(s, src->encrypted_static, ++ sizeof(src->encrypted_static), key, hash)) ++ goto out; ++ ++ /* Lookup which peer we're actually talking to */ ++ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, s); ++ if (!peer) ++ goto out; ++ handshake = &peer->handshake; ++ ++ /* ss */ ++ kdf(chaining_key, key, NULL, handshake->precomputed_static_static, ++ NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, ++ chaining_key); ++ ++ /* {t} */ ++ if (!message_decrypt(t, src->encrypted_timestamp, ++ sizeof(src->encrypted_timestamp), key, hash)) ++ goto out; ++ ++ down_read(&handshake->lock); ++ replay_attack = memcmp(t, handshake->latest_timestamp, ++ NOISE_TIMESTAMP_LEN) <= 0; ++ flood_attack = (s64)handshake->last_initiation_consumption + ++ NSEC_PER_SEC / INITIATIONS_PER_SECOND > ++ (s64)ktime_get_coarse_boottime_ns(); ++ up_read(&handshake->lock); ++ if (replay_attack || flood_attack) ++ goto out; ++ ++ /* Success! Copy everything to peer */ ++ down_write(&handshake->lock); ++ memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN); ++ if (memcmp(t, handshake->latest_timestamp, NOISE_TIMESTAMP_LEN) > 0) ++ memcpy(handshake->latest_timestamp, t, NOISE_TIMESTAMP_LEN); ++ memcpy(handshake->hash, hash, NOISE_HASH_LEN); ++ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN); ++ handshake->remote_index = src->sender_index; ++ if ((s64)(handshake->last_initiation_consumption - ++ (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0) ++ handshake->last_initiation_consumption = initiation_consumption; ++ handshake->state = HANDSHAKE_CONSUMED_INITIATION; ++ up_write(&handshake->lock); ++ ret_peer = peer; ++ ++out: ++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); ++ memzero_explicit(hash, NOISE_HASH_LEN); ++ memzero_explicit(chaining_key, NOISE_HASH_LEN); ++ up_read(&wg->static_identity.lock); ++ if (!ret_peer) ++ wg_peer_put(peer); ++ return ret_peer; ++} ++ ++bool wg_noise_handshake_create_response(struct message_handshake_response *dst, ++ struct noise_handshake *handshake) ++{ ++ u8 key[NOISE_SYMMETRIC_KEY_LEN]; ++ bool ret = false; ++ ++ /* We need to wait for crng _before_ taking any locks, since ++ * curve25519_generate_secret uses get_random_bytes_wait. ++ */ ++ wait_for_random_bytes(); ++ ++ down_read(&handshake->static_identity->lock); ++ down_write(&handshake->lock); ++ ++ if (handshake->state != HANDSHAKE_CONSUMED_INITIATION) ++ goto out; ++ ++ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE); ++ dst->receiver_index = handshake->remote_index; ++ ++ /* e */ ++ curve25519_generate_secret(handshake->ephemeral_private); ++ if (!curve25519_generate_public(dst->unencrypted_ephemeral, ++ handshake->ephemeral_private)) ++ goto out; ++ message_ephemeral(dst->unencrypted_ephemeral, ++ dst->unencrypted_ephemeral, handshake->chaining_key, ++ handshake->hash); ++ ++ /* ee */ ++ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private, ++ handshake->remote_ephemeral)) ++ goto out; ++ ++ /* se */ ++ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private, ++ handshake->remote_static)) ++ goto out; ++ ++ /* psk */ ++ mix_psk(handshake->chaining_key, handshake->hash, key, ++ handshake->preshared_key); ++ ++ /* {} */ ++ message_encrypt(dst->encrypted_nothing, NULL, 0, key, handshake->hash); ++ ++ dst->sender_index = wg_index_hashtable_insert( ++ handshake->entry.peer->device->index_hashtable, ++ &handshake->entry); ++ ++ handshake->state = HANDSHAKE_CREATED_RESPONSE; ++ ret = true; ++ ++out: ++ up_write(&handshake->lock); ++ up_read(&handshake->static_identity->lock); ++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); ++ return ret; ++} ++ ++struct wg_peer * ++wg_noise_handshake_consume_response(struct message_handshake_response *src, ++ struct wg_device *wg) ++{ ++ enum noise_handshake_state state = HANDSHAKE_ZEROED; ++ struct wg_peer *peer = NULL, *ret_peer = NULL; ++ struct noise_handshake *handshake; ++ u8 key[NOISE_SYMMETRIC_KEY_LEN]; ++ u8 hash[NOISE_HASH_LEN]; ++ u8 chaining_key[NOISE_HASH_LEN]; ++ u8 e[NOISE_PUBLIC_KEY_LEN]; ++ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN]; ++ u8 static_private[NOISE_PUBLIC_KEY_LEN]; ++ ++ down_read(&wg->static_identity.lock); ++ ++ if (unlikely(!wg->static_identity.has_identity)) ++ goto out; ++ ++ handshake = (struct noise_handshake *)wg_index_hashtable_lookup( ++ wg->index_hashtable, INDEX_HASHTABLE_HANDSHAKE, ++ src->receiver_index, &peer); ++ if (unlikely(!handshake)) ++ goto out; ++ ++ down_read(&handshake->lock); ++ state = handshake->state; ++ memcpy(hash, handshake->hash, NOISE_HASH_LEN); ++ memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN); ++ memcpy(ephemeral_private, handshake->ephemeral_private, ++ NOISE_PUBLIC_KEY_LEN); ++ up_read(&handshake->lock); ++ ++ if (state != HANDSHAKE_CREATED_INITIATION) ++ goto fail; ++ ++ /* e */ ++ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash); ++ ++ /* ee */ ++ if (!mix_dh(chaining_key, NULL, ephemeral_private, e)) ++ goto fail; ++ ++ /* se */ ++ if (!mix_dh(chaining_key, NULL, wg->static_identity.static_private, e)) ++ goto fail; ++ ++ /* psk */ ++ mix_psk(chaining_key, hash, key, handshake->preshared_key); ++ ++ /* {} */ ++ if (!message_decrypt(NULL, src->encrypted_nothing, ++ sizeof(src->encrypted_nothing), key, hash)) ++ goto fail; ++ ++ /* Success! Copy everything to peer */ ++ down_write(&handshake->lock); ++ /* It's important to check that the state is still the same, while we ++ * have an exclusive lock. ++ */ ++ if (handshake->state != state) { ++ up_write(&handshake->lock); ++ goto fail; ++ } ++ memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN); ++ memcpy(handshake->hash, hash, NOISE_HASH_LEN); ++ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN); ++ handshake->remote_index = src->sender_index; ++ handshake->state = HANDSHAKE_CONSUMED_RESPONSE; ++ up_write(&handshake->lock); ++ ret_peer = peer; ++ goto out; ++ ++fail: ++ wg_peer_put(peer); ++out: ++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); ++ memzero_explicit(hash, NOISE_HASH_LEN); ++ memzero_explicit(chaining_key, NOISE_HASH_LEN); ++ memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN); ++ memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN); ++ up_read(&wg->static_identity.lock); ++ return ret_peer; ++} ++ ++bool wg_noise_handshake_begin_session(struct noise_handshake *handshake, ++ struct noise_keypairs *keypairs) ++{ ++ struct noise_keypair *new_keypair; ++ bool ret = false; ++ ++ down_write(&handshake->lock); ++ if (handshake->state != HANDSHAKE_CREATED_RESPONSE && ++ handshake->state != HANDSHAKE_CONSUMED_RESPONSE) ++ goto out; ++ ++ new_keypair = keypair_create(handshake->entry.peer); ++ if (!new_keypair) ++ goto out; ++ new_keypair->i_am_the_initiator = handshake->state == ++ HANDSHAKE_CONSUMED_RESPONSE; ++ new_keypair->remote_index = handshake->remote_index; ++ ++ if (new_keypair->i_am_the_initiator) ++ derive_keys(&new_keypair->sending, &new_keypair->receiving, ++ handshake->chaining_key); ++ else ++ derive_keys(&new_keypair->receiving, &new_keypair->sending, ++ handshake->chaining_key); ++ ++ handshake_zero(handshake); ++ rcu_read_lock_bh(); ++ if (likely(!READ_ONCE(container_of(handshake, struct wg_peer, ++ handshake)->is_dead))) { ++ add_new_keypair(keypairs, new_keypair); ++ net_dbg_ratelimited("%s: Keypair %llu created for peer %llu\n", ++ handshake->entry.peer->device->dev->name, ++ new_keypair->internal_id, ++ handshake->entry.peer->internal_id); ++ ret = wg_index_hashtable_replace( ++ handshake->entry.peer->device->index_hashtable, ++ &handshake->entry, &new_keypair->entry); ++ } else { ++ kzfree(new_keypair); ++ } ++ rcu_read_unlock_bh(); ++ ++out: ++ up_write(&handshake->lock); ++ return ret; ++} +--- /dev/null ++++ b/drivers/net/wireguard/noise.h +@@ -0,0 +1,137 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++#ifndef _WG_NOISE_H ++#define _WG_NOISE_H ++ ++#include "messages.h" ++#include "peerlookup.h" ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++union noise_counter { ++ struct { ++ u64 counter; ++ unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG]; ++ spinlock_t lock; ++ } receive; ++ atomic64_t counter; ++}; ++ ++struct noise_symmetric_key { ++ u8 key[NOISE_SYMMETRIC_KEY_LEN]; ++ union noise_counter counter; ++ u64 birthdate; ++ bool is_valid; ++}; ++ ++struct noise_keypair { ++ struct index_hashtable_entry entry; ++ struct noise_symmetric_key sending; ++ struct noise_symmetric_key receiving; ++ __le32 remote_index; ++ bool i_am_the_initiator; ++ struct kref refcount; ++ struct rcu_head rcu; ++ u64 internal_id; ++}; ++ ++struct noise_keypairs { ++ struct noise_keypair __rcu *current_keypair; ++ struct noise_keypair __rcu *previous_keypair; ++ struct noise_keypair __rcu *next_keypair; ++ spinlock_t keypair_update_lock; ++}; ++ ++struct noise_static_identity { ++ u8 static_public[NOISE_PUBLIC_KEY_LEN]; ++ u8 static_private[NOISE_PUBLIC_KEY_LEN]; ++ struct rw_semaphore lock; ++ bool has_identity; ++}; ++ ++enum noise_handshake_state { ++ HANDSHAKE_ZEROED, ++ HANDSHAKE_CREATED_INITIATION, ++ HANDSHAKE_CONSUMED_INITIATION, ++ HANDSHAKE_CREATED_RESPONSE, ++ HANDSHAKE_CONSUMED_RESPONSE ++}; ++ ++struct noise_handshake { ++ struct index_hashtable_entry entry; ++ ++ enum noise_handshake_state state; ++ u64 last_initiation_consumption; ++ ++ struct noise_static_identity *static_identity; ++ ++ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN]; ++ u8 remote_static[NOISE_PUBLIC_KEY_LEN]; ++ u8 remote_ephemeral[NOISE_PUBLIC_KEY_LEN]; ++ u8 precomputed_static_static[NOISE_PUBLIC_KEY_LEN]; ++ ++ u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]; ++ ++ u8 hash[NOISE_HASH_LEN]; ++ u8 chaining_key[NOISE_HASH_LEN]; ++ ++ u8 latest_timestamp[NOISE_TIMESTAMP_LEN]; ++ __le32 remote_index; ++ ++ /* Protects all members except the immutable (after noise_handshake_ ++ * init): remote_static, precomputed_static_static, static_identity. ++ */ ++ struct rw_semaphore lock; ++}; ++ ++struct wg_device; ++ ++void wg_noise_init(void); ++bool wg_noise_handshake_init(struct noise_handshake *handshake, ++ struct noise_static_identity *static_identity, ++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], ++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], ++ struct wg_peer *peer); ++void wg_noise_handshake_clear(struct noise_handshake *handshake); ++static inline void wg_noise_reset_last_sent_handshake(atomic64_t *handshake_ns) ++{ ++ atomic64_set(handshake_ns, ktime_get_coarse_boottime_ns() - ++ (u64)(REKEY_TIMEOUT + 1) * NSEC_PER_SEC); ++} ++ ++void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now); ++struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair); ++void wg_noise_keypairs_clear(struct noise_keypairs *keypairs); ++bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs, ++ struct noise_keypair *received_keypair); ++void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer); ++ ++void wg_noise_set_static_identity_private_key( ++ struct noise_static_identity *static_identity, ++ const u8 private_key[NOISE_PUBLIC_KEY_LEN]); ++bool wg_noise_precompute_static_static(struct wg_peer *peer); ++ ++bool ++wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst, ++ struct noise_handshake *handshake); ++struct wg_peer * ++wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src, ++ struct wg_device *wg); ++ ++bool wg_noise_handshake_create_response(struct message_handshake_response *dst, ++ struct noise_handshake *handshake); ++struct wg_peer * ++wg_noise_handshake_consume_response(struct message_handshake_response *src, ++ struct wg_device *wg); ++ ++bool wg_noise_handshake_begin_session(struct noise_handshake *handshake, ++ struct noise_keypairs *keypairs); ++ ++#endif /* _WG_NOISE_H */ +--- /dev/null ++++ b/drivers/net/wireguard/peer.c +@@ -0,0 +1,240 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "peer.h" ++#include "device.h" ++#include "queueing.h" ++#include "timers.h" ++#include "peerlookup.h" ++#include "noise.h" ++ ++#include ++#include ++#include ++#include ++ ++static atomic64_t peer_counter = ATOMIC64_INIT(0); ++ ++struct wg_peer *wg_peer_create(struct wg_device *wg, ++ const u8 public_key[NOISE_PUBLIC_KEY_LEN], ++ const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]) ++{ ++ struct wg_peer *peer; ++ int ret = -ENOMEM; ++ ++ lockdep_assert_held(&wg->device_update_lock); ++ ++ if (wg->num_peers >= MAX_PEERS_PER_DEVICE) ++ return ERR_PTR(ret); ++ ++ peer = kzalloc(sizeof(*peer), GFP_KERNEL); ++ if (unlikely(!peer)) ++ return ERR_PTR(ret); ++ peer->device = wg; ++ ++ if (!wg_noise_handshake_init(&peer->handshake, &wg->static_identity, ++ public_key, preshared_key, peer)) { ++ ret = -EKEYREJECTED; ++ goto err_1; ++ } ++ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) ++ goto err_1; ++ if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false, ++ MAX_QUEUED_PACKETS)) ++ goto err_2; ++ if (wg_packet_queue_init(&peer->rx_queue, NULL, false, ++ MAX_QUEUED_PACKETS)) ++ goto err_3; ++ ++ peer->internal_id = atomic64_inc_return(&peer_counter); ++ peer->serial_work_cpu = nr_cpumask_bits; ++ wg_cookie_init(&peer->latest_cookie); ++ wg_timers_init(peer); ++ wg_cookie_checker_precompute_peer_keys(peer); ++ spin_lock_init(&peer->keypairs.keypair_update_lock); ++ INIT_WORK(&peer->transmit_handshake_work, ++ wg_packet_handshake_send_worker); ++ rwlock_init(&peer->endpoint_lock); ++ kref_init(&peer->refcount); ++ skb_queue_head_init(&peer->staged_packet_queue); ++ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); ++ set_bit(NAPI_STATE_NO_BUSY_POLL, &peer->napi.state); ++ netif_napi_add(wg->dev, &peer->napi, wg_packet_rx_poll, ++ NAPI_POLL_WEIGHT); ++ napi_enable(&peer->napi); ++ list_add_tail(&peer->peer_list, &wg->peer_list); ++ INIT_LIST_HEAD(&peer->allowedips_list); ++ wg_pubkey_hashtable_add(wg->peer_hashtable, peer); ++ ++wg->num_peers; ++ pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id); ++ return peer; ++ ++err_3: ++ wg_packet_queue_free(&peer->tx_queue, false); ++err_2: ++ dst_cache_destroy(&peer->endpoint_cache); ++err_1: ++ kfree(peer); ++ return ERR_PTR(ret); ++} ++ ++struct wg_peer *wg_peer_get_maybe_zero(struct wg_peer *peer) ++{ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(), ++ "Taking peer reference without holding the RCU read lock"); ++ if (unlikely(!peer || !kref_get_unless_zero(&peer->refcount))) ++ return NULL; ++ return peer; ++} ++ ++static void peer_make_dead(struct wg_peer *peer) ++{ ++ /* Remove from configuration-time lookup structures. */ ++ list_del_init(&peer->peer_list); ++ wg_allowedips_remove_by_peer(&peer->device->peer_allowedips, peer, ++ &peer->device->device_update_lock); ++ wg_pubkey_hashtable_remove(peer->device->peer_hashtable, peer); ++ ++ /* Mark as dead, so that we don't allow jumping contexts after. */ ++ WRITE_ONCE(peer->is_dead, true); ++ ++ /* The caller must now synchronize_rcu() for this to take effect. */ ++} ++ ++static void peer_remove_after_dead(struct wg_peer *peer) ++{ ++ WARN_ON(!peer->is_dead); ++ ++ /* No more keypairs can be created for this peer, since is_dead protects ++ * add_new_keypair, so we can now destroy existing ones. ++ */ ++ wg_noise_keypairs_clear(&peer->keypairs); ++ ++ /* Destroy all ongoing timers that were in-flight at the beginning of ++ * this function. ++ */ ++ wg_timers_stop(peer); ++ ++ /* The transition between packet encryption/decryption queues isn't ++ * guarded by is_dead, but each reference's life is strictly bounded by ++ * two generations: once for parallel crypto and once for serial ++ * ingestion, so we can simply flush twice, and be sure that we no ++ * longer have references inside these queues. ++ */ ++ ++ /* a) For encrypt/decrypt. */ ++ flush_workqueue(peer->device->packet_crypt_wq); ++ /* b.1) For send (but not receive, since that's napi). */ ++ flush_workqueue(peer->device->packet_crypt_wq); ++ /* b.2.1) For receive (but not send, since that's wq). */ ++ napi_disable(&peer->napi); ++ /* b.2.1) It's now safe to remove the napi struct, which must be done ++ * here from process context. ++ */ ++ netif_napi_del(&peer->napi); ++ ++ /* Ensure any workstructs we own (like transmit_handshake_work or ++ * clear_peer_work) no longer are in use. ++ */ ++ flush_workqueue(peer->device->handshake_send_wq); ++ ++ /* After the above flushes, a peer might still be active in a few ++ * different contexts: 1) from xmit(), before hitting is_dead and ++ * returning, 2) from wg_packet_consume_data(), before hitting is_dead ++ * and returning, 3) from wg_receive_handshake_packet() after a point ++ * where it has processed an incoming handshake packet, but where ++ * all calls to pass it off to timers fails because of is_dead. We won't ++ * have new references in (1) eventually, because we're removed from ++ * allowedips; we won't have new references in (2) eventually, because ++ * wg_index_hashtable_lookup will always return NULL, since we removed ++ * all existing keypairs and no more can be created; we won't have new ++ * references in (3) eventually, because we're removed from the pubkey ++ * hash table, which allows for a maximum of one handshake response, ++ * via the still-uncleared index hashtable entry, but not more than one, ++ * and in wg_cookie_message_consume, the lookup eventually gets a peer ++ * with a refcount of zero, so no new reference is taken. ++ */ ++ ++ --peer->device->num_peers; ++ wg_peer_put(peer); ++} ++ ++/* We have a separate "remove" function make sure that all active places where ++ * a peer is currently operating will eventually come to an end and not pass ++ * their reference onto another context. ++ */ ++void wg_peer_remove(struct wg_peer *peer) ++{ ++ if (unlikely(!peer)) ++ return; ++ lockdep_assert_held(&peer->device->device_update_lock); ++ ++ peer_make_dead(peer); ++ synchronize_rcu(); ++ peer_remove_after_dead(peer); ++} ++ ++void wg_peer_remove_all(struct wg_device *wg) ++{ ++ struct wg_peer *peer, *temp; ++ LIST_HEAD(dead_peers); ++ ++ lockdep_assert_held(&wg->device_update_lock); ++ ++ /* Avoid having to traverse individually for each one. */ ++ wg_allowedips_free(&wg->peer_allowedips, &wg->device_update_lock); ++ ++ list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) { ++ peer_make_dead(peer); ++ list_add_tail(&peer->peer_list, &dead_peers); ++ } ++ synchronize_rcu(); ++ list_for_each_entry_safe(peer, temp, &dead_peers, peer_list) ++ peer_remove_after_dead(peer); ++} ++ ++static void rcu_release(struct rcu_head *rcu) ++{ ++ struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu); ++ ++ dst_cache_destroy(&peer->endpoint_cache); ++ wg_packet_queue_free(&peer->rx_queue, false); ++ wg_packet_queue_free(&peer->tx_queue, false); ++ ++ /* The final zeroing takes care of clearing any remaining handshake key ++ * material and other potentially sensitive information. ++ */ ++ kzfree(peer); ++} ++ ++static void kref_release(struct kref *refcount) ++{ ++ struct wg_peer *peer = container_of(refcount, struct wg_peer, refcount); ++ ++ pr_debug("%s: Peer %llu (%pISpfsc) destroyed\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ ++ /* Remove ourself from dynamic runtime lookup structures, now that the ++ * last reference is gone. ++ */ ++ wg_index_hashtable_remove(peer->device->index_hashtable, ++ &peer->handshake.entry); ++ ++ /* Remove any lingering packets that didn't have a chance to be ++ * transmitted. ++ */ ++ wg_packet_purge_staged_packets(peer); ++ ++ /* Free the memory used. */ ++ call_rcu(&peer->rcu, rcu_release); ++} ++ ++void wg_peer_put(struct wg_peer *peer) ++{ ++ if (unlikely(!peer)) ++ return; ++ kref_put(&peer->refcount, kref_release); ++} +--- /dev/null ++++ b/drivers/net/wireguard/peer.h +@@ -0,0 +1,83 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_PEER_H ++#define _WG_PEER_H ++ ++#include "device.h" ++#include "noise.h" ++#include "cookie.h" ++ ++#include ++#include ++#include ++#include ++#include ++ ++struct wg_device; ++ ++struct endpoint { ++ union { ++ struct sockaddr addr; ++ struct sockaddr_in addr4; ++ struct sockaddr_in6 addr6; ++ }; ++ union { ++ struct { ++ struct in_addr src4; ++ /* Essentially the same as addr6->scope_id */ ++ int src_if4; ++ }; ++ struct in6_addr src6; ++ }; ++}; ++ ++struct wg_peer { ++ struct wg_device *device; ++ struct crypt_queue tx_queue, rx_queue; ++ struct sk_buff_head staged_packet_queue; ++ int serial_work_cpu; ++ struct noise_keypairs keypairs; ++ struct endpoint endpoint; ++ struct dst_cache endpoint_cache; ++ rwlock_t endpoint_lock; ++ struct noise_handshake handshake; ++ atomic64_t last_sent_handshake; ++ struct work_struct transmit_handshake_work, clear_peer_work; ++ struct cookie latest_cookie; ++ struct hlist_node pubkey_hash; ++ u64 rx_bytes, tx_bytes; ++ struct timer_list timer_retransmit_handshake, timer_send_keepalive; ++ struct timer_list timer_new_handshake, timer_zero_key_material; ++ struct timer_list timer_persistent_keepalive; ++ unsigned int timer_handshake_attempts; ++ u16 persistent_keepalive_interval; ++ bool timer_need_another_keepalive; ++ bool sent_lastminute_handshake; ++ struct timespec64 walltime_last_handshake; ++ struct kref refcount; ++ struct rcu_head rcu; ++ struct list_head peer_list; ++ struct list_head allowedips_list; ++ u64 internal_id; ++ struct napi_struct napi; ++ bool is_dead; ++}; ++ ++struct wg_peer *wg_peer_create(struct wg_device *wg, ++ const u8 public_key[NOISE_PUBLIC_KEY_LEN], ++ const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]); ++ ++struct wg_peer *__must_check wg_peer_get_maybe_zero(struct wg_peer *peer); ++static inline struct wg_peer *wg_peer_get(struct wg_peer *peer) ++{ ++ kref_get(&peer->refcount); ++ return peer; ++} ++void wg_peer_put(struct wg_peer *peer); ++void wg_peer_remove(struct wg_peer *peer); ++void wg_peer_remove_all(struct wg_device *wg); ++ ++#endif /* _WG_PEER_H */ +--- /dev/null ++++ b/drivers/net/wireguard/peerlookup.c +@@ -0,0 +1,221 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "peerlookup.h" ++#include "peer.h" ++#include "noise.h" ++ ++static struct hlist_head *pubkey_bucket(struct pubkey_hashtable *table, ++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN]) ++{ ++ /* siphash gives us a secure 64bit number based on a random key. Since ++ * the bits are uniformly distributed, we can then mask off to get the ++ * bits we need. ++ */ ++ const u64 hash = siphash(pubkey, NOISE_PUBLIC_KEY_LEN, &table->key); ++ ++ return &table->hashtable[hash & (HASH_SIZE(table->hashtable) - 1)]; ++} ++ ++struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void) ++{ ++ struct pubkey_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL); ++ ++ if (!table) ++ return NULL; ++ ++ get_random_bytes(&table->key, sizeof(table->key)); ++ hash_init(table->hashtable); ++ mutex_init(&table->lock); ++ return table; ++} ++ ++void wg_pubkey_hashtable_add(struct pubkey_hashtable *table, ++ struct wg_peer *peer) ++{ ++ mutex_lock(&table->lock); ++ hlist_add_head_rcu(&peer->pubkey_hash, ++ pubkey_bucket(table, peer->handshake.remote_static)); ++ mutex_unlock(&table->lock); ++} ++ ++void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table, ++ struct wg_peer *peer) ++{ ++ mutex_lock(&table->lock); ++ hlist_del_init_rcu(&peer->pubkey_hash); ++ mutex_unlock(&table->lock); ++} ++ ++/* Returns a strong reference to a peer */ ++struct wg_peer * ++wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table, ++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN]) ++{ ++ struct wg_peer *iter_peer, *peer = NULL; ++ ++ rcu_read_lock_bh(); ++ hlist_for_each_entry_rcu_bh(iter_peer, pubkey_bucket(table, pubkey), ++ pubkey_hash) { ++ if (!memcmp(pubkey, iter_peer->handshake.remote_static, ++ NOISE_PUBLIC_KEY_LEN)) { ++ peer = iter_peer; ++ break; ++ } ++ } ++ peer = wg_peer_get_maybe_zero(peer); ++ rcu_read_unlock_bh(); ++ return peer; ++} ++ ++static struct hlist_head *index_bucket(struct index_hashtable *table, ++ const __le32 index) ++{ ++ /* Since the indices are random and thus all bits are uniformly ++ * distributed, we can find its bucket simply by masking. ++ */ ++ return &table->hashtable[(__force u32)index & ++ (HASH_SIZE(table->hashtable) - 1)]; ++} ++ ++struct index_hashtable *wg_index_hashtable_alloc(void) ++{ ++ struct index_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL); ++ ++ if (!table) ++ return NULL; ++ ++ hash_init(table->hashtable); ++ spin_lock_init(&table->lock); ++ return table; ++} ++ ++/* At the moment, we limit ourselves to 2^20 total peers, which generally might ++ * amount to 2^20*3 items in this hashtable. The algorithm below works by ++ * picking a random number and testing it. We can see that these limits mean we ++ * usually succeed pretty quickly: ++ * ++ * >>> def calculation(tries, size): ++ * ... return (size / 2**32)**(tries - 1) * (1 - (size / 2**32)) ++ * ... ++ * >>> calculation(1, 2**20 * 3) ++ * 0.999267578125 ++ * >>> calculation(2, 2**20 * 3) ++ * 0.0007318854331970215 ++ * >>> calculation(3, 2**20 * 3) ++ * 5.360489012673497e-07 ++ * >>> calculation(4, 2**20 * 3) ++ * 3.9261394135792216e-10 ++ * ++ * At the moment, we don't do any masking, so this algorithm isn't exactly ++ * constant time in either the random guessing or in the hash list lookup. We ++ * could require a minimum of 3 tries, which would successfully mask the ++ * guessing. this would not, however, help with the growing hash lengths, which ++ * is another thing to consider moving forward. ++ */ ++ ++__le32 wg_index_hashtable_insert(struct index_hashtable *table, ++ struct index_hashtable_entry *entry) ++{ ++ struct index_hashtable_entry *existing_entry; ++ ++ spin_lock_bh(&table->lock); ++ hlist_del_init_rcu(&entry->index_hash); ++ spin_unlock_bh(&table->lock); ++ ++ rcu_read_lock_bh(); ++ ++search_unused_slot: ++ /* First we try to find an unused slot, randomly, while unlocked. */ ++ entry->index = (__force __le32)get_random_u32(); ++ hlist_for_each_entry_rcu_bh(existing_entry, ++ index_bucket(table, entry->index), ++ index_hash) { ++ if (existing_entry->index == entry->index) ++ /* If it's already in use, we continue searching. */ ++ goto search_unused_slot; ++ } ++ ++ /* Once we've found an unused slot, we lock it, and then double-check ++ * that nobody else stole it from us. ++ */ ++ spin_lock_bh(&table->lock); ++ hlist_for_each_entry_rcu_bh(existing_entry, ++ index_bucket(table, entry->index), ++ index_hash) { ++ if (existing_entry->index == entry->index) { ++ spin_unlock_bh(&table->lock); ++ /* If it was stolen, we start over. */ ++ goto search_unused_slot; ++ } ++ } ++ /* Otherwise, we know we have it exclusively (since we're locked), ++ * so we insert. ++ */ ++ hlist_add_head_rcu(&entry->index_hash, ++ index_bucket(table, entry->index)); ++ spin_unlock_bh(&table->lock); ++ ++ rcu_read_unlock_bh(); ++ ++ return entry->index; ++} ++ ++bool wg_index_hashtable_replace(struct index_hashtable *table, ++ struct index_hashtable_entry *old, ++ struct index_hashtable_entry *new) ++{ ++ if (unlikely(hlist_unhashed(&old->index_hash))) ++ return false; ++ spin_lock_bh(&table->lock); ++ new->index = old->index; ++ hlist_replace_rcu(&old->index_hash, &new->index_hash); ++ ++ /* Calling init here NULLs out index_hash, and in fact after this ++ * function returns, it's theoretically possible for this to get ++ * reinserted elsewhere. That means the RCU lookup below might either ++ * terminate early or jump between buckets, in which case the packet ++ * simply gets dropped, which isn't terrible. ++ */ ++ INIT_HLIST_NODE(&old->index_hash); ++ spin_unlock_bh(&table->lock); ++ return true; ++} ++ ++void wg_index_hashtable_remove(struct index_hashtable *table, ++ struct index_hashtable_entry *entry) ++{ ++ spin_lock_bh(&table->lock); ++ hlist_del_init_rcu(&entry->index_hash); ++ spin_unlock_bh(&table->lock); ++} ++ ++/* Returns a strong reference to a entry->peer */ ++struct index_hashtable_entry * ++wg_index_hashtable_lookup(struct index_hashtable *table, ++ const enum index_hashtable_type type_mask, ++ const __le32 index, struct wg_peer **peer) ++{ ++ struct index_hashtable_entry *iter_entry, *entry = NULL; ++ ++ rcu_read_lock_bh(); ++ hlist_for_each_entry_rcu_bh(iter_entry, index_bucket(table, index), ++ index_hash) { ++ if (iter_entry->index == index) { ++ if (likely(iter_entry->type & type_mask)) ++ entry = iter_entry; ++ break; ++ } ++ } ++ if (likely(entry)) { ++ entry->peer = wg_peer_get_maybe_zero(entry->peer); ++ if (likely(entry->peer)) ++ *peer = entry->peer; ++ else ++ entry = NULL; ++ } ++ rcu_read_unlock_bh(); ++ return entry; ++} +--- /dev/null ++++ b/drivers/net/wireguard/peerlookup.h +@@ -0,0 +1,64 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_PEERLOOKUP_H ++#define _WG_PEERLOOKUP_H ++ ++#include "messages.h" ++ ++#include ++#include ++#include ++ ++struct wg_peer; ++ ++struct pubkey_hashtable { ++ /* TODO: move to rhashtable */ ++ DECLARE_HASHTABLE(hashtable, 11); ++ siphash_key_t key; ++ struct mutex lock; ++}; ++ ++struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void); ++void wg_pubkey_hashtable_add(struct pubkey_hashtable *table, ++ struct wg_peer *peer); ++void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table, ++ struct wg_peer *peer); ++struct wg_peer * ++wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table, ++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN]); ++ ++struct index_hashtable { ++ /* TODO: move to rhashtable */ ++ DECLARE_HASHTABLE(hashtable, 13); ++ spinlock_t lock; ++}; ++ ++enum index_hashtable_type { ++ INDEX_HASHTABLE_HANDSHAKE = 1U << 0, ++ INDEX_HASHTABLE_KEYPAIR = 1U << 1 ++}; ++ ++struct index_hashtable_entry { ++ struct wg_peer *peer; ++ struct hlist_node index_hash; ++ enum index_hashtable_type type; ++ __le32 index; ++}; ++ ++struct index_hashtable *wg_index_hashtable_alloc(void); ++__le32 wg_index_hashtable_insert(struct index_hashtable *table, ++ struct index_hashtable_entry *entry); ++bool wg_index_hashtable_replace(struct index_hashtable *table, ++ struct index_hashtable_entry *old, ++ struct index_hashtable_entry *new); ++void wg_index_hashtable_remove(struct index_hashtable *table, ++ struct index_hashtable_entry *entry); ++struct index_hashtable_entry * ++wg_index_hashtable_lookup(struct index_hashtable *table, ++ const enum index_hashtable_type type_mask, ++ const __le32 index, struct wg_peer **peer); ++ ++#endif /* _WG_PEERLOOKUP_H */ +--- /dev/null ++++ b/drivers/net/wireguard/queueing.c +@@ -0,0 +1,53 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "queueing.h" ++ ++struct multicore_worker __percpu * ++wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) ++{ ++ int cpu; ++ struct multicore_worker __percpu *worker = ++ alloc_percpu(struct multicore_worker); ++ ++ if (!worker) ++ return NULL; ++ ++ for_each_possible_cpu(cpu) { ++ per_cpu_ptr(worker, cpu)->ptr = ptr; ++ INIT_WORK(&per_cpu_ptr(worker, cpu)->work, function); ++ } ++ return worker; ++} ++ ++int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, ++ bool multicore, unsigned int len) ++{ ++ int ret; ++ ++ memset(queue, 0, sizeof(*queue)); ++ ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); ++ if (ret) ++ return ret; ++ if (function) { ++ if (multicore) { ++ queue->worker = wg_packet_percpu_multicore_worker_alloc( ++ function, queue); ++ if (!queue->worker) ++ return -ENOMEM; ++ } else { ++ INIT_WORK(&queue->work, function); ++ } ++ } ++ return 0; ++} ++ ++void wg_packet_queue_free(struct crypt_queue *queue, bool multicore) ++{ ++ if (multicore) ++ free_percpu(queue->worker); ++ WARN_ON(!__ptr_ring_empty(&queue->ring)); ++ ptr_ring_cleanup(&queue->ring, NULL); ++} +--- /dev/null ++++ b/drivers/net/wireguard/queueing.h +@@ -0,0 +1,197 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_QUEUEING_H ++#define _WG_QUEUEING_H ++ ++#include "peer.h" ++#include ++#include ++#include ++#include ++ ++struct wg_device; ++struct wg_peer; ++struct multicore_worker; ++struct crypt_queue; ++struct sk_buff; ++ ++/* queueing.c APIs: */ ++int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, ++ bool multicore, unsigned int len); ++void wg_packet_queue_free(struct crypt_queue *queue, bool multicore); ++struct multicore_worker __percpu * ++wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); ++ ++/* receive.c APIs: */ ++void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb); ++void wg_packet_handshake_receive_worker(struct work_struct *work); ++/* NAPI poll function: */ ++int wg_packet_rx_poll(struct napi_struct *napi, int budget); ++/* Workqueue worker: */ ++void wg_packet_decrypt_worker(struct work_struct *work); ++ ++/* send.c APIs: */ ++void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, ++ bool is_retry); ++void wg_packet_send_handshake_response(struct wg_peer *peer); ++void wg_packet_send_handshake_cookie(struct wg_device *wg, ++ struct sk_buff *initiating_skb, ++ __le32 sender_index); ++void wg_packet_send_keepalive(struct wg_peer *peer); ++void wg_packet_purge_staged_packets(struct wg_peer *peer); ++void wg_packet_send_staged_packets(struct wg_peer *peer); ++/* Workqueue workers: */ ++void wg_packet_handshake_send_worker(struct work_struct *work); ++void wg_packet_tx_worker(struct work_struct *work); ++void wg_packet_encrypt_worker(struct work_struct *work); ++ ++enum packet_state { ++ PACKET_STATE_UNCRYPTED, ++ PACKET_STATE_CRYPTED, ++ PACKET_STATE_DEAD ++}; ++ ++struct packet_cb { ++ u64 nonce; ++ struct noise_keypair *keypair; ++ atomic_t state; ++ u32 mtu; ++ u8 ds; ++}; ++ ++#define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) ++#define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) ++ ++/* Returns either the correct skb->protocol value, or 0 if invalid. */ ++static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb) ++{ ++ if (skb_network_header(skb) >= skb->head && ++ (skb_network_header(skb) + sizeof(struct iphdr)) <= ++ skb_tail_pointer(skb) && ++ ip_hdr(skb)->version == 4) ++ return htons(ETH_P_IP); ++ if (skb_network_header(skb) >= skb->head && ++ (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= ++ skb_tail_pointer(skb) && ++ ipv6_hdr(skb)->version == 6) ++ return htons(ETH_P_IPV6); ++ return 0; ++} ++ ++static inline void wg_reset_packet(struct sk_buff *skb) ++{ ++ const int pfmemalloc = skb->pfmemalloc; ++ ++ skb_scrub_packet(skb, true); ++ memset(&skb->headers_start, 0, ++ offsetof(struct sk_buff, headers_end) - ++ offsetof(struct sk_buff, headers_start)); ++ skb->pfmemalloc = pfmemalloc; ++ skb->queue_mapping = 0; ++ skb->nohdr = 0; ++ skb->peeked = 0; ++ skb->mac_len = 0; ++ skb->dev = NULL; ++#ifdef CONFIG_NET_SCHED ++ skb->tc_index = 0; ++#endif ++ skb_reset_redirect(skb); ++ skb->hdr_len = skb_headroom(skb); ++ skb_reset_mac_header(skb); ++ skb_reset_network_header(skb); ++ skb_reset_transport_header(skb); ++ skb_probe_transport_header(skb); ++ skb_reset_inner_headers(skb); ++} ++ ++static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) ++{ ++ unsigned int cpu = *stored_cpu, cpu_index, i; ++ ++ if (unlikely(cpu == nr_cpumask_bits || ++ !cpumask_test_cpu(cpu, cpu_online_mask))) { ++ cpu_index = id % cpumask_weight(cpu_online_mask); ++ cpu = cpumask_first(cpu_online_mask); ++ for (i = 0; i < cpu_index; ++i) ++ cpu = cpumask_next(cpu, cpu_online_mask); ++ *stored_cpu = cpu; ++ } ++ return cpu; ++} ++ ++/* This function is racy, in the sense that next is unlocked, so it could return ++ * the same CPU twice. A race-free version of this would be to instead store an ++ * atomic sequence number, do an increment-and-return, and then iterate through ++ * every possible CPU until we get to that index -- choose_cpu. However that's ++ * a bit slower, and it doesn't seem like this potential race actually ++ * introduces any performance loss, so we live with it. ++ */ ++static inline int wg_cpumask_next_online(int *next) ++{ ++ int cpu = *next; ++ ++ while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask))) ++ cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; ++ *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; ++ return cpu; ++} ++ ++static inline int wg_queue_enqueue_per_device_and_peer( ++ struct crypt_queue *device_queue, struct crypt_queue *peer_queue, ++ struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) ++{ ++ int cpu; ++ ++ atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED); ++ /* We first queue this up for the peer ingestion, but the consumer ++ * will wait for the state to change to CRYPTED or DEAD before. ++ */ ++ if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb))) ++ return -ENOSPC; ++ /* Then we queue it up in the device queue, which consumes the ++ * packet as soon as it can. ++ */ ++ cpu = wg_cpumask_next_online(next_cpu); ++ if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) ++ return -EPIPE; ++ queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); ++ return 0; ++} ++ ++static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue, ++ struct sk_buff *skb, ++ enum packet_state state) ++{ ++ /* We take a reference, because as soon as we call atomic_set, the ++ * peer can be freed from below us. ++ */ ++ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); ++ ++ atomic_set_release(&PACKET_CB(skb)->state, state); ++ queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, ++ peer->internal_id), ++ peer->device->packet_crypt_wq, &queue->work); ++ wg_peer_put(peer); ++} ++ ++static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb, ++ enum packet_state state) ++{ ++ /* We take a reference, because as soon as we call atomic_set, the ++ * peer can be freed from below us. ++ */ ++ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); ++ ++ atomic_set_release(&PACKET_CB(skb)->state, state); ++ napi_schedule(&peer->napi); ++ wg_peer_put(peer); ++} ++ ++#ifdef DEBUG ++bool wg_packet_counter_selftest(void); ++#endif ++ ++#endif /* _WG_QUEUEING_H */ +--- /dev/null ++++ b/drivers/net/wireguard/ratelimiter.c +@@ -0,0 +1,223 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "ratelimiter.h" ++#include ++#include ++#include ++#include ++ ++static struct kmem_cache *entry_cache; ++static hsiphash_key_t key; ++static spinlock_t table_lock = __SPIN_LOCK_UNLOCKED("ratelimiter_table_lock"); ++static DEFINE_MUTEX(init_lock); ++static u64 init_refcnt; /* Protected by init_lock, hence not atomic. */ ++static atomic_t total_entries = ATOMIC_INIT(0); ++static unsigned int max_entries, table_size; ++static void wg_ratelimiter_gc_entries(struct work_struct *); ++static DECLARE_DEFERRABLE_WORK(gc_work, wg_ratelimiter_gc_entries); ++static struct hlist_head *table_v4; ++#if IS_ENABLED(CONFIG_IPV6) ++static struct hlist_head *table_v6; ++#endif ++ ++struct ratelimiter_entry { ++ u64 last_time_ns, tokens, ip; ++ void *net; ++ spinlock_t lock; ++ struct hlist_node hash; ++ struct rcu_head rcu; ++}; ++ ++enum { ++ PACKETS_PER_SECOND = 20, ++ PACKETS_BURSTABLE = 5, ++ PACKET_COST = NSEC_PER_SEC / PACKETS_PER_SECOND, ++ TOKEN_MAX = PACKET_COST * PACKETS_BURSTABLE ++}; ++ ++static void entry_free(struct rcu_head *rcu) ++{ ++ kmem_cache_free(entry_cache, ++ container_of(rcu, struct ratelimiter_entry, rcu)); ++ atomic_dec(&total_entries); ++} ++ ++static void entry_uninit(struct ratelimiter_entry *entry) ++{ ++ hlist_del_rcu(&entry->hash); ++ call_rcu(&entry->rcu, entry_free); ++} ++ ++/* Calling this function with a NULL work uninits all entries. */ ++static void wg_ratelimiter_gc_entries(struct work_struct *work) ++{ ++ const u64 now = ktime_get_coarse_boottime_ns(); ++ struct ratelimiter_entry *entry; ++ struct hlist_node *temp; ++ unsigned int i; ++ ++ for (i = 0; i < table_size; ++i) { ++ spin_lock(&table_lock); ++ hlist_for_each_entry_safe(entry, temp, &table_v4[i], hash) { ++ if (unlikely(!work) || ++ now - entry->last_time_ns > NSEC_PER_SEC) ++ entry_uninit(entry); ++ } ++#if IS_ENABLED(CONFIG_IPV6) ++ hlist_for_each_entry_safe(entry, temp, &table_v6[i], hash) { ++ if (unlikely(!work) || ++ now - entry->last_time_ns > NSEC_PER_SEC) ++ entry_uninit(entry); ++ } ++#endif ++ spin_unlock(&table_lock); ++ if (likely(work)) ++ cond_resched(); ++ } ++ if (likely(work)) ++ queue_delayed_work(system_power_efficient_wq, &gc_work, HZ); ++} ++ ++bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net) ++{ ++ /* We only take the bottom half of the net pointer, so that we can hash ++ * 3 words in the end. This way, siphash's len param fits into the final ++ * u32, and we don't incur an extra round. ++ */ ++ const u32 net_word = (unsigned long)net; ++ struct ratelimiter_entry *entry; ++ struct hlist_head *bucket; ++ u64 ip; ++ ++ if (skb->protocol == htons(ETH_P_IP)) { ++ ip = (u64 __force)ip_hdr(skb)->saddr; ++ bucket = &table_v4[hsiphash_2u32(net_word, ip, &key) & ++ (table_size - 1)]; ++ } ++#if IS_ENABLED(CONFIG_IPV6) ++ else if (skb->protocol == htons(ETH_P_IPV6)) { ++ /* Only use 64 bits, so as to ratelimit the whole /64. */ ++ memcpy(&ip, &ipv6_hdr(skb)->saddr, sizeof(ip)); ++ bucket = &table_v6[hsiphash_3u32(net_word, ip >> 32, ip, &key) & ++ (table_size - 1)]; ++ } ++#endif ++ else ++ return false; ++ rcu_read_lock(); ++ hlist_for_each_entry_rcu(entry, bucket, hash) { ++ if (entry->net == net && entry->ip == ip) { ++ u64 now, tokens; ++ bool ret; ++ /* Quasi-inspired by nft_limit.c, but this is actually a ++ * slightly different algorithm. Namely, we incorporate ++ * the burst as part of the maximum tokens, rather than ++ * as part of the rate. ++ */ ++ spin_lock(&entry->lock); ++ now = ktime_get_coarse_boottime_ns(); ++ tokens = min_t(u64, TOKEN_MAX, ++ entry->tokens + now - ++ entry->last_time_ns); ++ entry->last_time_ns = now; ++ ret = tokens >= PACKET_COST; ++ entry->tokens = ret ? tokens - PACKET_COST : tokens; ++ spin_unlock(&entry->lock); ++ rcu_read_unlock(); ++ return ret; ++ } ++ } ++ rcu_read_unlock(); ++ ++ if (atomic_inc_return(&total_entries) > max_entries) ++ goto err_oom; ++ ++ entry = kmem_cache_alloc(entry_cache, GFP_KERNEL); ++ if (unlikely(!entry)) ++ goto err_oom; ++ ++ entry->net = net; ++ entry->ip = ip; ++ INIT_HLIST_NODE(&entry->hash); ++ spin_lock_init(&entry->lock); ++ entry->last_time_ns = ktime_get_coarse_boottime_ns(); ++ entry->tokens = TOKEN_MAX - PACKET_COST; ++ spin_lock(&table_lock); ++ hlist_add_head_rcu(&entry->hash, bucket); ++ spin_unlock(&table_lock); ++ return true; ++ ++err_oom: ++ atomic_dec(&total_entries); ++ return false; ++} ++ ++int wg_ratelimiter_init(void) ++{ ++ mutex_lock(&init_lock); ++ if (++init_refcnt != 1) ++ goto out; ++ ++ entry_cache = KMEM_CACHE(ratelimiter_entry, 0); ++ if (!entry_cache) ++ goto err; ++ ++ /* xt_hashlimit.c uses a slightly different algorithm for ratelimiting, ++ * but what it shares in common is that it uses a massive hashtable. So, ++ * we borrow their wisdom about good table sizes on different systems ++ * dependent on RAM. This calculation here comes from there. ++ */ ++ table_size = (totalram_pages() > (1U << 30) / PAGE_SIZE) ? 8192 : ++ max_t(unsigned long, 16, roundup_pow_of_two( ++ (totalram_pages() << PAGE_SHIFT) / ++ (1U << 14) / sizeof(struct hlist_head))); ++ max_entries = table_size * 8; ++ ++ table_v4 = kvzalloc(table_size * sizeof(*table_v4), GFP_KERNEL); ++ if (unlikely(!table_v4)) ++ goto err_kmemcache; ++ ++#if IS_ENABLED(CONFIG_IPV6) ++ table_v6 = kvzalloc(table_size * sizeof(*table_v6), GFP_KERNEL); ++ if (unlikely(!table_v6)) { ++ kvfree(table_v4); ++ goto err_kmemcache; ++ } ++#endif ++ ++ queue_delayed_work(system_power_efficient_wq, &gc_work, HZ); ++ get_random_bytes(&key, sizeof(key)); ++out: ++ mutex_unlock(&init_lock); ++ return 0; ++ ++err_kmemcache: ++ kmem_cache_destroy(entry_cache); ++err: ++ --init_refcnt; ++ mutex_unlock(&init_lock); ++ return -ENOMEM; ++} ++ ++void wg_ratelimiter_uninit(void) ++{ ++ mutex_lock(&init_lock); ++ if (!init_refcnt || --init_refcnt) ++ goto out; ++ ++ cancel_delayed_work_sync(&gc_work); ++ wg_ratelimiter_gc_entries(NULL); ++ rcu_barrier(); ++ kvfree(table_v4); ++#if IS_ENABLED(CONFIG_IPV6) ++ kvfree(table_v6); ++#endif ++ kmem_cache_destroy(entry_cache); ++out: ++ mutex_unlock(&init_lock); ++} ++ ++#include "selftest/ratelimiter.c" +--- /dev/null ++++ b/drivers/net/wireguard/ratelimiter.h +@@ -0,0 +1,19 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_RATELIMITER_H ++#define _WG_RATELIMITER_H ++ ++#include ++ ++int wg_ratelimiter_init(void); ++void wg_ratelimiter_uninit(void); ++bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net); ++ ++#ifdef DEBUG ++bool wg_ratelimiter_selftest(void); ++#endif ++ ++#endif /* _WG_RATELIMITER_H */ +--- /dev/null ++++ b/drivers/net/wireguard/receive.c +@@ -0,0 +1,595 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "queueing.h" ++#include "device.h" ++#include "peer.h" ++#include "timers.h" ++#include "messages.h" ++#include "cookie.h" ++#include "socket.h" ++ ++#include ++#include ++#include ++#include ++ ++/* Must be called with bh disabled. */ ++static void update_rx_stats(struct wg_peer *peer, size_t len) ++{ ++ struct pcpu_sw_netstats *tstats = ++ get_cpu_ptr(peer->device->dev->tstats); ++ ++ u64_stats_update_begin(&tstats->syncp); ++ ++tstats->rx_packets; ++ tstats->rx_bytes += len; ++ peer->rx_bytes += len; ++ u64_stats_update_end(&tstats->syncp); ++ put_cpu_ptr(tstats); ++} ++ ++#define SKB_TYPE_LE32(skb) (((struct message_header *)(skb)->data)->type) ++ ++static size_t validate_header_len(struct sk_buff *skb) ++{ ++ if (unlikely(skb->len < sizeof(struct message_header))) ++ return 0; ++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_DATA) && ++ skb->len >= MESSAGE_MINIMUM_LENGTH) ++ return sizeof(struct message_data); ++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION) && ++ skb->len == sizeof(struct message_handshake_initiation)) ++ return sizeof(struct message_handshake_initiation); ++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE) && ++ skb->len == sizeof(struct message_handshake_response)) ++ return sizeof(struct message_handshake_response); ++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE) && ++ skb->len == sizeof(struct message_handshake_cookie)) ++ return sizeof(struct message_handshake_cookie); ++ return 0; ++} ++ ++static int prepare_skb_header(struct sk_buff *skb, struct wg_device *wg) ++{ ++ size_t data_offset, data_len, header_len; ++ struct udphdr *udp; ++ ++ if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol || ++ skb_transport_header(skb) < skb->head || ++ (skb_transport_header(skb) + sizeof(struct udphdr)) > ++ skb_tail_pointer(skb))) ++ return -EINVAL; /* Bogus IP header */ ++ udp = udp_hdr(skb); ++ data_offset = (u8 *)udp - skb->data; ++ if (unlikely(data_offset > U16_MAX || ++ data_offset + sizeof(struct udphdr) > skb->len)) ++ /* Packet has offset at impossible location or isn't big enough ++ * to have UDP fields. ++ */ ++ return -EINVAL; ++ data_len = ntohs(udp->len); ++ if (unlikely(data_len < sizeof(struct udphdr) || ++ data_len > skb->len - data_offset)) ++ /* UDP packet is reporting too small of a size or lying about ++ * its size. ++ */ ++ return -EINVAL; ++ data_len -= sizeof(struct udphdr); ++ data_offset = (u8 *)udp + sizeof(struct udphdr) - skb->data; ++ if (unlikely(!pskb_may_pull(skb, ++ data_offset + sizeof(struct message_header)) || ++ pskb_trim(skb, data_len + data_offset) < 0)) ++ return -EINVAL; ++ skb_pull(skb, data_offset); ++ if (unlikely(skb->len != data_len)) ++ /* Final len does not agree with calculated len */ ++ return -EINVAL; ++ header_len = validate_header_len(skb); ++ if (unlikely(!header_len)) ++ return -EINVAL; ++ __skb_push(skb, data_offset); ++ if (unlikely(!pskb_may_pull(skb, data_offset + header_len))) ++ return -EINVAL; ++ __skb_pull(skb, data_offset); ++ return 0; ++} ++ ++static void wg_receive_handshake_packet(struct wg_device *wg, ++ struct sk_buff *skb) ++{ ++ enum cookie_mac_state mac_state; ++ struct wg_peer *peer = NULL; ++ /* This is global, so that our load calculation applies to the whole ++ * system. We don't care about races with it at all. ++ */ ++ static u64 last_under_load; ++ bool packet_needs_cookie; ++ bool under_load; ++ ++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE)) { ++ net_dbg_skb_ratelimited("%s: Receiving cookie response from %pISpfsc\n", ++ wg->dev->name, skb); ++ wg_cookie_message_consume( ++ (struct message_handshake_cookie *)skb->data, wg); ++ return; ++ } ++ ++ under_load = skb_queue_len(&wg->incoming_handshakes) >= ++ MAX_QUEUED_INCOMING_HANDSHAKES / 8; ++ if (under_load) ++ last_under_load = ktime_get_coarse_boottime_ns(); ++ else if (last_under_load) ++ under_load = !wg_birthdate_has_expired(last_under_load, 1); ++ mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb, ++ under_load); ++ if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) || ++ (!under_load && mac_state == VALID_MAC_BUT_NO_COOKIE)) { ++ packet_needs_cookie = false; ++ } else if (under_load && mac_state == VALID_MAC_BUT_NO_COOKIE) { ++ packet_needs_cookie = true; ++ } else { ++ net_dbg_skb_ratelimited("%s: Invalid MAC of handshake, dropping packet from %pISpfsc\n", ++ wg->dev->name, skb); ++ return; ++ } ++ ++ switch (SKB_TYPE_LE32(skb)) { ++ case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): { ++ struct message_handshake_initiation *message = ++ (struct message_handshake_initiation *)skb->data; ++ ++ if (packet_needs_cookie) { ++ wg_packet_send_handshake_cookie(wg, skb, ++ message->sender_index); ++ return; ++ } ++ peer = wg_noise_handshake_consume_initiation(message, wg); ++ if (unlikely(!peer)) { ++ net_dbg_skb_ratelimited("%s: Invalid handshake initiation from %pISpfsc\n", ++ wg->dev->name, skb); ++ return; ++ } ++ wg_socket_set_peer_endpoint_from_skb(peer, skb); ++ net_dbg_ratelimited("%s: Receiving handshake initiation from peer %llu (%pISpfsc)\n", ++ wg->dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ wg_packet_send_handshake_response(peer); ++ break; ++ } ++ case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): { ++ struct message_handshake_response *message = ++ (struct message_handshake_response *)skb->data; ++ ++ if (packet_needs_cookie) { ++ wg_packet_send_handshake_cookie(wg, skb, ++ message->sender_index); ++ return; ++ } ++ peer = wg_noise_handshake_consume_response(message, wg); ++ if (unlikely(!peer)) { ++ net_dbg_skb_ratelimited("%s: Invalid handshake response from %pISpfsc\n", ++ wg->dev->name, skb); ++ return; ++ } ++ wg_socket_set_peer_endpoint_from_skb(peer, skb); ++ net_dbg_ratelimited("%s: Receiving handshake response from peer %llu (%pISpfsc)\n", ++ wg->dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ if (wg_noise_handshake_begin_session(&peer->handshake, ++ &peer->keypairs)) { ++ wg_timers_session_derived(peer); ++ wg_timers_handshake_complete(peer); ++ /* Calling this function will either send any existing ++ * packets in the queue and not send a keepalive, which ++ * is the best case, Or, if there's nothing in the ++ * queue, it will send a keepalive, in order to give ++ * immediate confirmation of the session. ++ */ ++ wg_packet_send_keepalive(peer); ++ } ++ break; ++ } ++ } ++ ++ if (unlikely(!peer)) { ++ WARN(1, "Somehow a wrong type of packet wound up in the handshake queue!\n"); ++ return; ++ } ++ ++ local_bh_disable(); ++ update_rx_stats(peer, skb->len); ++ local_bh_enable(); ++ ++ wg_timers_any_authenticated_packet_received(peer); ++ wg_timers_any_authenticated_packet_traversal(peer); ++ wg_peer_put(peer); ++} ++ ++void wg_packet_handshake_receive_worker(struct work_struct *work) ++{ ++ struct wg_device *wg = container_of(work, struct multicore_worker, ++ work)->ptr; ++ struct sk_buff *skb; ++ ++ while ((skb = skb_dequeue(&wg->incoming_handshakes)) != NULL) { ++ wg_receive_handshake_packet(wg, skb); ++ dev_kfree_skb(skb); ++ cond_resched(); ++ } ++} ++ ++static void keep_key_fresh(struct wg_peer *peer) ++{ ++ struct noise_keypair *keypair; ++ bool send = false; ++ ++ if (peer->sent_lastminute_handshake) ++ return; ++ ++ rcu_read_lock_bh(); ++ keypair = rcu_dereference_bh(peer->keypairs.current_keypair); ++ if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && ++ keypair->i_am_the_initiator && ++ unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, ++ REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT))) ++ send = true; ++ rcu_read_unlock_bh(); ++ ++ if (send) { ++ peer->sent_lastminute_handshake = true; ++ wg_packet_send_queued_handshake_initiation(peer, false); ++ } ++} ++ ++static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key) ++{ ++ struct scatterlist sg[MAX_SKB_FRAGS + 8]; ++ struct sk_buff *trailer; ++ unsigned int offset; ++ int num_frags; ++ ++ if (unlikely(!key)) ++ return false; ++ ++ if (unlikely(!READ_ONCE(key->is_valid) || ++ wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) || ++ key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) { ++ WRITE_ONCE(key->is_valid, false); ++ return false; ++ } ++ ++ PACKET_CB(skb)->nonce = ++ le64_to_cpu(((struct message_data *)skb->data)->counter); ++ ++ /* We ensure that the network header is part of the packet before we ++ * call skb_cow_data, so that there's no chance that data is removed ++ * from the skb, so that later we can extract the original endpoint. ++ */ ++ offset = skb->data - skb_network_header(skb); ++ skb_push(skb, offset); ++ num_frags = skb_cow_data(skb, 0, &trailer); ++ offset += sizeof(struct message_data); ++ skb_pull(skb, offset); ++ if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) ++ return false; ++ ++ sg_init_table(sg, num_frags); ++ if (skb_to_sgvec(skb, sg, 0, skb->len) <= 0) ++ return false; ++ ++ if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0, ++ PACKET_CB(skb)->nonce, ++ key->key)) ++ return false; ++ ++ /* Another ugly situation of pushing and pulling the header so as to ++ * keep endpoint information intact. ++ */ ++ skb_push(skb, offset); ++ if (pskb_trim(skb, skb->len - noise_encrypted_len(0))) ++ return false; ++ skb_pull(skb, offset); ++ ++ return true; ++} ++ ++/* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */ ++static bool counter_validate(union noise_counter *counter, u64 their_counter) ++{ ++ unsigned long index, index_current, top, i; ++ bool ret = false; ++ ++ spin_lock_bh(&counter->receive.lock); ++ ++ if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 || ++ their_counter >= REJECT_AFTER_MESSAGES)) ++ goto out; ++ ++ ++their_counter; ++ ++ if (unlikely((COUNTER_WINDOW_SIZE + their_counter) < ++ counter->receive.counter)) ++ goto out; ++ ++ index = their_counter >> ilog2(BITS_PER_LONG); ++ ++ if (likely(their_counter > counter->receive.counter)) { ++ index_current = counter->receive.counter >> ilog2(BITS_PER_LONG); ++ top = min_t(unsigned long, index - index_current, ++ COUNTER_BITS_TOTAL / BITS_PER_LONG); ++ for (i = 1; i <= top; ++i) ++ counter->receive.backtrack[(i + index_current) & ++ ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; ++ counter->receive.counter = their_counter; ++ } ++ ++ index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; ++ ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1), ++ &counter->receive.backtrack[index]); ++ ++out: ++ spin_unlock_bh(&counter->receive.lock); ++ return ret; ++} ++ ++#include "selftest/counter.c" ++ ++static void wg_packet_consume_data_done(struct wg_peer *peer, ++ struct sk_buff *skb, ++ struct endpoint *endpoint) ++{ ++ struct net_device *dev = peer->device->dev; ++ unsigned int len, len_before_trim; ++ struct wg_peer *routed_peer; ++ ++ wg_socket_set_peer_endpoint(peer, endpoint); ++ ++ if (unlikely(wg_noise_received_with_keypair(&peer->keypairs, ++ PACKET_CB(skb)->keypair))) { ++ wg_timers_handshake_complete(peer); ++ wg_packet_send_staged_packets(peer); ++ } ++ ++ keep_key_fresh(peer); ++ ++ wg_timers_any_authenticated_packet_received(peer); ++ wg_timers_any_authenticated_packet_traversal(peer); ++ ++ /* A packet with length 0 is a keepalive packet */ ++ if (unlikely(!skb->len)) { ++ update_rx_stats(peer, message_data_len(0)); ++ net_dbg_ratelimited("%s: Receiving keepalive packet from peer %llu (%pISpfsc)\n", ++ dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ goto packet_processed; ++ } ++ ++ wg_timers_data_received(peer); ++ ++ if (unlikely(skb_network_header(skb) < skb->head)) ++ goto dishonest_packet_size; ++ if (unlikely(!(pskb_network_may_pull(skb, sizeof(struct iphdr)) && ++ (ip_hdr(skb)->version == 4 || ++ (ip_hdr(skb)->version == 6 && ++ pskb_network_may_pull(skb, sizeof(struct ipv6hdr))))))) ++ goto dishonest_packet_type; ++ ++ skb->dev = dev; ++ /* We've already verified the Poly1305 auth tag, which means this packet ++ * was not modified in transit. We can therefore tell the networking ++ * stack that all checksums of every layer of encapsulation have already ++ * been checked "by the hardware" and therefore is unneccessary to check ++ * again in software. ++ */ ++ skb->ip_summed = CHECKSUM_UNNECESSARY; ++ skb->csum_level = ~0; /* All levels */ ++ skb->protocol = wg_skb_examine_untrusted_ip_hdr(skb); ++ if (skb->protocol == htons(ETH_P_IP)) { ++ len = ntohs(ip_hdr(skb)->tot_len); ++ if (unlikely(len < sizeof(struct iphdr))) ++ goto dishonest_packet_size; ++ if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) ++ IP_ECN_set_ce(ip_hdr(skb)); ++ } else if (skb->protocol == htons(ETH_P_IPV6)) { ++ len = ntohs(ipv6_hdr(skb)->payload_len) + ++ sizeof(struct ipv6hdr); ++ if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) ++ IP6_ECN_set_ce(skb, ipv6_hdr(skb)); ++ } else { ++ goto dishonest_packet_type; ++ } ++ ++ if (unlikely(len > skb->len)) ++ goto dishonest_packet_size; ++ len_before_trim = skb->len; ++ if (unlikely(pskb_trim(skb, len))) ++ goto packet_processed; ++ ++ routed_peer = wg_allowedips_lookup_src(&peer->device->peer_allowedips, ++ skb); ++ wg_peer_put(routed_peer); /* We don't need the extra reference. */ ++ ++ if (unlikely(routed_peer != peer)) ++ goto dishonest_packet_peer; ++ ++ if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) { ++ ++dev->stats.rx_dropped; ++ net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n", ++ dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ } else { ++ update_rx_stats(peer, message_data_len(len_before_trim)); ++ } ++ return; ++ ++dishonest_packet_peer: ++ net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n", ++ dev->name, skb, peer->internal_id, ++ &peer->endpoint.addr); ++ ++dev->stats.rx_errors; ++ ++dev->stats.rx_frame_errors; ++ goto packet_processed; ++dishonest_packet_type: ++ net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n", ++ dev->name, peer->internal_id, &peer->endpoint.addr); ++ ++dev->stats.rx_errors; ++ ++dev->stats.rx_frame_errors; ++ goto packet_processed; ++dishonest_packet_size: ++ net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n", ++ dev->name, peer->internal_id, &peer->endpoint.addr); ++ ++dev->stats.rx_errors; ++ ++dev->stats.rx_length_errors; ++ goto packet_processed; ++packet_processed: ++ dev_kfree_skb(skb); ++} ++ ++int wg_packet_rx_poll(struct napi_struct *napi, int budget) ++{ ++ struct wg_peer *peer = container_of(napi, struct wg_peer, napi); ++ struct crypt_queue *queue = &peer->rx_queue; ++ struct noise_keypair *keypair; ++ struct endpoint endpoint; ++ enum packet_state state; ++ struct sk_buff *skb; ++ int work_done = 0; ++ bool free; ++ ++ if (unlikely(budget <= 0)) ++ return 0; ++ ++ while ((skb = __ptr_ring_peek(&queue->ring)) != NULL && ++ (state = atomic_read_acquire(&PACKET_CB(skb)->state)) != ++ PACKET_STATE_UNCRYPTED) { ++ __ptr_ring_discard_one(&queue->ring); ++ peer = PACKET_PEER(skb); ++ keypair = PACKET_CB(skb)->keypair; ++ free = true; ++ ++ if (unlikely(state != PACKET_STATE_CRYPTED)) ++ goto next; ++ ++ if (unlikely(!counter_validate(&keypair->receiving.counter, ++ PACKET_CB(skb)->nonce))) { ++ net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", ++ peer->device->dev->name, ++ PACKET_CB(skb)->nonce, ++ keypair->receiving.counter.receive.counter); ++ goto next; ++ } ++ ++ if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb))) ++ goto next; ++ ++ wg_reset_packet(skb); ++ wg_packet_consume_data_done(peer, skb, &endpoint); ++ free = false; ++ ++next: ++ wg_noise_keypair_put(keypair, false); ++ wg_peer_put(peer); ++ if (unlikely(free)) ++ dev_kfree_skb(skb); ++ ++ if (++work_done >= budget) ++ break; ++ } ++ ++ if (work_done < budget) ++ napi_complete_done(napi, work_done); ++ ++ return work_done; ++} ++ ++void wg_packet_decrypt_worker(struct work_struct *work) ++{ ++ struct crypt_queue *queue = container_of(work, struct multicore_worker, ++ work)->ptr; ++ struct sk_buff *skb; ++ ++ while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) { ++ enum packet_state state = likely(decrypt_packet(skb, ++ &PACKET_CB(skb)->keypair->receiving)) ? ++ PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; ++ wg_queue_enqueue_per_peer_napi(skb, state); ++ } ++} ++ ++static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) ++{ ++ __le32 idx = ((struct message_data *)skb->data)->key_idx; ++ struct wg_peer *peer = NULL; ++ int ret; ++ ++ rcu_read_lock_bh(); ++ PACKET_CB(skb)->keypair = ++ (struct noise_keypair *)wg_index_hashtable_lookup( ++ wg->index_hashtable, INDEX_HASHTABLE_KEYPAIR, idx, ++ &peer); ++ if (unlikely(!wg_noise_keypair_get(PACKET_CB(skb)->keypair))) ++ goto err_keypair; ++ ++ if (unlikely(READ_ONCE(peer->is_dead))) ++ goto err; ++ ++ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, ++ &peer->rx_queue, skb, ++ wg->packet_crypt_wq, ++ &wg->decrypt_queue.last_cpu); ++ if (unlikely(ret == -EPIPE)) ++ wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD); ++ if (likely(!ret || ret == -EPIPE)) { ++ rcu_read_unlock_bh(); ++ return; ++ } ++err: ++ wg_noise_keypair_put(PACKET_CB(skb)->keypair, false); ++err_keypair: ++ rcu_read_unlock_bh(); ++ wg_peer_put(peer); ++ dev_kfree_skb(skb); ++} ++ ++void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb) ++{ ++ if (unlikely(prepare_skb_header(skb, wg) < 0)) ++ goto err; ++ switch (SKB_TYPE_LE32(skb)) { ++ case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): ++ case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): ++ case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): { ++ int cpu; ++ ++ if (skb_queue_len(&wg->incoming_handshakes) > ++ MAX_QUEUED_INCOMING_HANDSHAKES || ++ unlikely(!rng_is_initialized())) { ++ net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n", ++ wg->dev->name, skb); ++ goto err; ++ } ++ skb_queue_tail(&wg->incoming_handshakes, skb); ++ /* Queues up a call to packet_process_queued_handshake_ ++ * packets(skb): ++ */ ++ cpu = wg_cpumask_next_online(&wg->incoming_handshake_cpu); ++ queue_work_on(cpu, wg->handshake_receive_wq, ++ &per_cpu_ptr(wg->incoming_handshakes_worker, cpu)->work); ++ break; ++ } ++ case cpu_to_le32(MESSAGE_DATA): ++ PACKET_CB(skb)->ds = ip_tunnel_get_dsfield(ip_hdr(skb), skb); ++ wg_packet_consume_data(wg, skb); ++ break; ++ default: ++ net_dbg_skb_ratelimited("%s: Invalid packet from %pISpfsc\n", ++ wg->dev->name, skb); ++ goto err; ++ } ++ return; ++ ++err: ++ dev_kfree_skb(skb); ++} +--- /dev/null ++++ b/drivers/net/wireguard/selftest/allowedips.c +@@ -0,0 +1,683 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * This contains some basic static unit tests for the allowedips data structure. ++ * It also has two additional modes that are disabled and meant to be used by ++ * folks directly playing with this file. If you define the macro ++ * DEBUG_PRINT_TRIE_GRAPHVIZ to be 1, then every time there's a full tree in ++ * memory, it will be printed out as KERN_DEBUG in a format that can be passed ++ * to graphviz (the dot command) to visualize it. If you define the macro ++ * DEBUG_RANDOM_TRIE to be 1, then there will be an extremely costly set of ++ * randomized tests done against a trivial implementation, which may take ++ * upwards of a half-hour to complete. There's no set of users who should be ++ * enabling these, and the only developers that should go anywhere near these ++ * nobs are the ones who are reading this comment. ++ */ ++ ++#ifdef DEBUG ++ ++#include ++ ++static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits, ++ u8 cidr) ++{ ++ swap_endian(dst, src, bits); ++ memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8); ++ if (cidr) ++ dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8); ++} ++ ++static __init void print_node(struct allowedips_node *node, u8 bits) ++{ ++ char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n"; ++ char *fmt_declaration = KERN_DEBUG ++ "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n"; ++ char *style = "dotted"; ++ u8 ip1[16], ip2[16]; ++ u32 color = 0; ++ ++ if (bits == 32) { ++ fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n"; ++ fmt_declaration = KERN_DEBUG ++ "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n"; ++ } else if (bits == 128) { ++ fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n"; ++ fmt_declaration = KERN_DEBUG ++ "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n"; ++ } ++ if (node->peer) { ++ hsiphash_key_t key = { { 0 } }; ++ ++ memcpy(&key, &node->peer, sizeof(node->peer)); ++ color = hsiphash_1u32(0xdeadbeef, &key) % 200 << 16 | ++ hsiphash_1u32(0xbabecafe, &key) % 200 << 8 | ++ hsiphash_1u32(0xabad1dea, &key) % 200; ++ style = "bold"; ++ } ++ swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr); ++ printk(fmt_declaration, ip1, node->cidr, style, color); ++ if (node->bit[0]) { ++ swap_endian_and_apply_cidr(ip2, ++ rcu_dereference_raw(node->bit[0])->bits, bits, ++ node->cidr); ++ printk(fmt_connection, ip1, node->cidr, ip2, ++ rcu_dereference_raw(node->bit[0])->cidr); ++ print_node(rcu_dereference_raw(node->bit[0]), bits); ++ } ++ if (node->bit[1]) { ++ swap_endian_and_apply_cidr(ip2, ++ rcu_dereference_raw(node->bit[1])->bits, ++ bits, node->cidr); ++ printk(fmt_connection, ip1, node->cidr, ip2, ++ rcu_dereference_raw(node->bit[1])->cidr); ++ print_node(rcu_dereference_raw(node->bit[1]), bits); ++ } ++} ++ ++static __init void print_tree(struct allowedips_node __rcu *top, u8 bits) ++{ ++ printk(KERN_DEBUG "digraph trie {\n"); ++ print_node(rcu_dereference_raw(top), bits); ++ printk(KERN_DEBUG "}\n"); ++} ++ ++enum { ++ NUM_PEERS = 2000, ++ NUM_RAND_ROUTES = 400, ++ NUM_MUTATED_ROUTES = 100, ++ NUM_QUERIES = NUM_RAND_ROUTES * NUM_MUTATED_ROUTES * 30 ++}; ++ ++struct horrible_allowedips { ++ struct hlist_head head; ++}; ++ ++struct horrible_allowedips_node { ++ struct hlist_node table; ++ union nf_inet_addr ip; ++ union nf_inet_addr mask; ++ u8 ip_version; ++ void *value; ++}; ++ ++static __init void horrible_allowedips_init(struct horrible_allowedips *table) ++{ ++ INIT_HLIST_HEAD(&table->head); ++} ++ ++static __init void horrible_allowedips_free(struct horrible_allowedips *table) ++{ ++ struct horrible_allowedips_node *node; ++ struct hlist_node *h; ++ ++ hlist_for_each_entry_safe(node, h, &table->head, table) { ++ hlist_del(&node->table); ++ kfree(node); ++ } ++} ++ ++static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr) ++{ ++ union nf_inet_addr mask; ++ ++ memset(&mask, 0x00, 128 / 8); ++ memset(&mask, 0xff, cidr / 8); ++ if (cidr % 32) ++ mask.all[cidr / 32] = (__force u32)htonl( ++ (0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL); ++ return mask; ++} ++ ++static __init inline u8 horrible_mask_to_cidr(union nf_inet_addr subnet) ++{ ++ return hweight32(subnet.all[0]) + hweight32(subnet.all[1]) + ++ hweight32(subnet.all[2]) + hweight32(subnet.all[3]); ++} ++ ++static __init inline void ++horrible_mask_self(struct horrible_allowedips_node *node) ++{ ++ if (node->ip_version == 4) { ++ node->ip.ip &= node->mask.ip; ++ } else if (node->ip_version == 6) { ++ node->ip.ip6[0] &= node->mask.ip6[0]; ++ node->ip.ip6[1] &= node->mask.ip6[1]; ++ node->ip.ip6[2] &= node->mask.ip6[2]; ++ node->ip.ip6[3] &= node->mask.ip6[3]; ++ } ++} ++ ++static __init inline bool ++horrible_match_v4(const struct horrible_allowedips_node *node, ++ struct in_addr *ip) ++{ ++ return (ip->s_addr & node->mask.ip) == node->ip.ip; ++} ++ ++static __init inline bool ++horrible_match_v6(const struct horrible_allowedips_node *node, ++ struct in6_addr *ip) ++{ ++ return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == ++ node->ip.ip6[0] && ++ (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == ++ node->ip.ip6[1] && ++ (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == ++ node->ip.ip6[2] && ++ (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3]; ++} ++ ++static __init void ++horrible_insert_ordered(struct horrible_allowedips *table, ++ struct horrible_allowedips_node *node) ++{ ++ struct horrible_allowedips_node *other = NULL, *where = NULL; ++ u8 my_cidr = horrible_mask_to_cidr(node->mask); ++ ++ hlist_for_each_entry(other, &table->head, table) { ++ if (!memcmp(&other->mask, &node->mask, ++ sizeof(union nf_inet_addr)) && ++ !memcmp(&other->ip, &node->ip, ++ sizeof(union nf_inet_addr)) && ++ other->ip_version == node->ip_version) { ++ other->value = node->value; ++ kfree(node); ++ return; ++ } ++ where = other; ++ if (horrible_mask_to_cidr(other->mask) <= my_cidr) ++ break; ++ } ++ if (!other && !where) ++ hlist_add_head(&node->table, &table->head); ++ else if (!other) ++ hlist_add_behind(&node->table, &where->table); ++ else ++ hlist_add_before(&node->table, &where->table); ++} ++ ++static __init int ++horrible_allowedips_insert_v4(struct horrible_allowedips *table, ++ struct in_addr *ip, u8 cidr, void *value) ++{ ++ struct horrible_allowedips_node *node = kzalloc(sizeof(*node), ++ GFP_KERNEL); ++ ++ if (unlikely(!node)) ++ return -ENOMEM; ++ node->ip.in = *ip; ++ node->mask = horrible_cidr_to_mask(cidr); ++ node->ip_version = 4; ++ node->value = value; ++ horrible_mask_self(node); ++ horrible_insert_ordered(table, node); ++ return 0; ++} ++ ++static __init int ++horrible_allowedips_insert_v6(struct horrible_allowedips *table, ++ struct in6_addr *ip, u8 cidr, void *value) ++{ ++ struct horrible_allowedips_node *node = kzalloc(sizeof(*node), ++ GFP_KERNEL); ++ ++ if (unlikely(!node)) ++ return -ENOMEM; ++ node->ip.in6 = *ip; ++ node->mask = horrible_cidr_to_mask(cidr); ++ node->ip_version = 6; ++ node->value = value; ++ horrible_mask_self(node); ++ horrible_insert_ordered(table, node); ++ return 0; ++} ++ ++static __init void * ++horrible_allowedips_lookup_v4(struct horrible_allowedips *table, ++ struct in_addr *ip) ++{ ++ struct horrible_allowedips_node *node; ++ void *ret = NULL; ++ ++ hlist_for_each_entry(node, &table->head, table) { ++ if (node->ip_version != 4) ++ continue; ++ if (horrible_match_v4(node, ip)) { ++ ret = node->value; ++ break; ++ } ++ } ++ return ret; ++} ++ ++static __init void * ++horrible_allowedips_lookup_v6(struct horrible_allowedips *table, ++ struct in6_addr *ip) ++{ ++ struct horrible_allowedips_node *node; ++ void *ret = NULL; ++ ++ hlist_for_each_entry(node, &table->head, table) { ++ if (node->ip_version != 6) ++ continue; ++ if (horrible_match_v6(node, ip)) { ++ ret = node->value; ++ break; ++ } ++ } ++ return ret; ++} ++ ++static __init bool randomized_test(void) ++{ ++ unsigned int i, j, k, mutate_amount, cidr; ++ u8 ip[16], mutate_mask[16], mutated[16]; ++ struct wg_peer **peers, *peer; ++ struct horrible_allowedips h; ++ DEFINE_MUTEX(mutex); ++ struct allowedips t; ++ bool ret = false; ++ ++ mutex_init(&mutex); ++ ++ wg_allowedips_init(&t); ++ horrible_allowedips_init(&h); ++ ++ peers = kcalloc(NUM_PEERS, sizeof(*peers), GFP_KERNEL); ++ if (unlikely(!peers)) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free; ++ } ++ for (i = 0; i < NUM_PEERS; ++i) { ++ peers[i] = kzalloc(sizeof(*peers[i]), GFP_KERNEL); ++ if (unlikely(!peers[i])) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free; ++ } ++ kref_init(&peers[i]->refcount); ++ } ++ ++ mutex_lock(&mutex); ++ ++ for (i = 0; i < NUM_RAND_ROUTES; ++i) { ++ prandom_bytes(ip, 4); ++ cidr = prandom_u32_max(32) + 1; ++ peer = peers[prandom_u32_max(NUM_PEERS)]; ++ if (wg_allowedips_insert_v4(&t, (struct in_addr *)ip, cidr, ++ peer, &mutex) < 0) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ if (horrible_allowedips_insert_v4(&h, (struct in_addr *)ip, ++ cidr, peer) < 0) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ for (j = 0; j < NUM_MUTATED_ROUTES; ++j) { ++ memcpy(mutated, ip, 4); ++ prandom_bytes(mutate_mask, 4); ++ mutate_amount = prandom_u32_max(32); ++ for (k = 0; k < mutate_amount / 8; ++k) ++ mutate_mask[k] = 0xff; ++ mutate_mask[k] = 0xff ++ << ((8 - (mutate_amount % 8)) % 8); ++ for (; k < 4; ++k) ++ mutate_mask[k] = 0; ++ for (k = 0; k < 4; ++k) ++ mutated[k] = (mutated[k] & mutate_mask[k]) | ++ (~mutate_mask[k] & ++ prandom_u32_max(256)); ++ cidr = prandom_u32_max(32) + 1; ++ peer = peers[prandom_u32_max(NUM_PEERS)]; ++ if (wg_allowedips_insert_v4(&t, ++ (struct in_addr *)mutated, ++ cidr, peer, &mutex) < 0) { ++ pr_err("allowedips random malloc: FAIL\n"); ++ goto free_locked; ++ } ++ if (horrible_allowedips_insert_v4(&h, ++ (struct in_addr *)mutated, cidr, peer)) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ } ++ } ++ ++ for (i = 0; i < NUM_RAND_ROUTES; ++i) { ++ prandom_bytes(ip, 16); ++ cidr = prandom_u32_max(128) + 1; ++ peer = peers[prandom_u32_max(NUM_PEERS)]; ++ if (wg_allowedips_insert_v6(&t, (struct in6_addr *)ip, cidr, ++ peer, &mutex) < 0) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ if (horrible_allowedips_insert_v6(&h, (struct in6_addr *)ip, ++ cidr, peer) < 0) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ for (j = 0; j < NUM_MUTATED_ROUTES; ++j) { ++ memcpy(mutated, ip, 16); ++ prandom_bytes(mutate_mask, 16); ++ mutate_amount = prandom_u32_max(128); ++ for (k = 0; k < mutate_amount / 8; ++k) ++ mutate_mask[k] = 0xff; ++ mutate_mask[k] = 0xff ++ << ((8 - (mutate_amount % 8)) % 8); ++ for (; k < 4; ++k) ++ mutate_mask[k] = 0; ++ for (k = 0; k < 4; ++k) ++ mutated[k] = (mutated[k] & mutate_mask[k]) | ++ (~mutate_mask[k] & ++ prandom_u32_max(256)); ++ cidr = prandom_u32_max(128) + 1; ++ peer = peers[prandom_u32_max(NUM_PEERS)]; ++ if (wg_allowedips_insert_v6(&t, ++ (struct in6_addr *)mutated, ++ cidr, peer, &mutex) < 0) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ if (horrible_allowedips_insert_v6( ++ &h, (struct in6_addr *)mutated, cidr, ++ peer)) { ++ pr_err("allowedips random self-test malloc: FAIL\n"); ++ goto free_locked; ++ } ++ } ++ } ++ ++ mutex_unlock(&mutex); ++ ++ if (IS_ENABLED(DEBUG_PRINT_TRIE_GRAPHVIZ)) { ++ print_tree(t.root4, 32); ++ print_tree(t.root6, 128); ++ } ++ ++ for (i = 0; i < NUM_QUERIES; ++i) { ++ prandom_bytes(ip, 4); ++ if (lookup(t.root4, 32, ip) != ++ horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { ++ pr_err("allowedips random self-test: FAIL\n"); ++ goto free; ++ } ++ } ++ ++ for (i = 0; i < NUM_QUERIES; ++i) { ++ prandom_bytes(ip, 16); ++ if (lookup(t.root6, 128, ip) != ++ horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { ++ pr_err("allowedips random self-test: FAIL\n"); ++ goto free; ++ } ++ } ++ ret = true; ++ ++free: ++ mutex_lock(&mutex); ++free_locked: ++ wg_allowedips_free(&t, &mutex); ++ mutex_unlock(&mutex); ++ horrible_allowedips_free(&h); ++ if (peers) { ++ for (i = 0; i < NUM_PEERS; ++i) ++ kfree(peers[i]); ++ } ++ kfree(peers); ++ return ret; ++} ++ ++static __init inline struct in_addr *ip4(u8 a, u8 b, u8 c, u8 d) ++{ ++ static struct in_addr ip; ++ u8 *split = (u8 *)&ip; ++ ++ split[0] = a; ++ split[1] = b; ++ split[2] = c; ++ split[3] = d; ++ return &ip; ++} ++ ++static __init inline struct in6_addr *ip6(u32 a, u32 b, u32 c, u32 d) ++{ ++ static struct in6_addr ip; ++ __be32 *split = (__be32 *)&ip; ++ ++ split[0] = cpu_to_be32(a); ++ split[1] = cpu_to_be32(b); ++ split[2] = cpu_to_be32(c); ++ split[3] = cpu_to_be32(d); ++ return &ip; ++} ++ ++static __init struct wg_peer *init_peer(void) ++{ ++ struct wg_peer *peer = kzalloc(sizeof(*peer), GFP_KERNEL); ++ ++ if (!peer) ++ return NULL; ++ kref_init(&peer->refcount); ++ INIT_LIST_HEAD(&peer->allowedips_list); ++ return peer; ++} ++ ++#define insert(version, mem, ipa, ipb, ipc, ipd, cidr) \ ++ wg_allowedips_insert_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \ ++ cidr, mem, &mutex) ++ ++#define maybe_fail() do { \ ++ ++i; \ ++ if (!_s) { \ ++ pr_info("allowedips self-test %zu: FAIL\n", i); \ ++ success = false; \ ++ } \ ++ } while (0) ++ ++#define test(version, mem, ipa, ipb, ipc, ipd) do { \ ++ bool _s = lookup(t.root##version, (version) == 4 ? 32 : 128, \ ++ ip##version(ipa, ipb, ipc, ipd)) == (mem); \ ++ maybe_fail(); \ ++ } while (0) ++ ++#define test_negative(version, mem, ipa, ipb, ipc, ipd) do { \ ++ bool _s = lookup(t.root##version, (version) == 4 ? 32 : 128, \ ++ ip##version(ipa, ipb, ipc, ipd)) != (mem); \ ++ maybe_fail(); \ ++ } while (0) ++ ++#define test_boolean(cond) do { \ ++ bool _s = (cond); \ ++ maybe_fail(); \ ++ } while (0) ++ ++bool __init wg_allowedips_selftest(void) ++{ ++ bool found_a = false, found_b = false, found_c = false, found_d = false, ++ found_e = false, found_other = false; ++ struct wg_peer *a = init_peer(), *b = init_peer(), *c = init_peer(), ++ *d = init_peer(), *e = init_peer(), *f = init_peer(), ++ *g = init_peer(), *h = init_peer(); ++ struct allowedips_node *iter_node; ++ bool success = false; ++ struct allowedips t; ++ DEFINE_MUTEX(mutex); ++ struct in6_addr ip; ++ size_t i = 0, count = 0; ++ __be64 part; ++ ++ mutex_init(&mutex); ++ mutex_lock(&mutex); ++ wg_allowedips_init(&t); ++ ++ if (!a || !b || !c || !d || !e || !f || !g || !h) { ++ pr_err("allowedips self-test malloc: FAIL\n"); ++ goto free; ++ } ++ ++ insert(4, a, 192, 168, 4, 0, 24); ++ insert(4, b, 192, 168, 4, 4, 32); ++ insert(4, c, 192, 168, 0, 0, 16); ++ insert(4, d, 192, 95, 5, 64, 27); ++ /* replaces previous entry, and maskself is required */ ++ insert(4, c, 192, 95, 5, 65, 27); ++ insert(6, d, 0x26075300, 0x60006b00, 0, 0xc05f0543, 128); ++ insert(6, c, 0x26075300, 0x60006b00, 0, 0, 64); ++ insert(4, e, 0, 0, 0, 0, 0); ++ insert(6, e, 0, 0, 0, 0, 0); ++ /* replaces previous entry */ ++ insert(6, f, 0, 0, 0, 0, 0); ++ insert(6, g, 0x24046800, 0, 0, 0, 32); ++ /* maskself is required */ ++ insert(6, h, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef, 64); ++ insert(6, a, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef, 128); ++ insert(6, c, 0x24446800, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128); ++ insert(6, b, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); ++ insert(4, g, 64, 15, 112, 0, 20); ++ /* maskself is required */ ++ insert(4, h, 64, 15, 123, 211, 25); ++ insert(4, a, 10, 0, 0, 0, 25); ++ insert(4, b, 10, 0, 0, 128, 25); ++ insert(4, a, 10, 1, 0, 0, 30); ++ insert(4, b, 10, 1, 0, 4, 30); ++ insert(4, c, 10, 1, 0, 8, 29); ++ insert(4, d, 10, 1, 0, 16, 29); ++ ++ if (IS_ENABLED(DEBUG_PRINT_TRIE_GRAPHVIZ)) { ++ print_tree(t.root4, 32); ++ print_tree(t.root6, 128); ++ } ++ ++ success = true; ++ ++ test(4, a, 192, 168, 4, 20); ++ test(4, a, 192, 168, 4, 0); ++ test(4, b, 192, 168, 4, 4); ++ test(4, c, 192, 168, 200, 182); ++ test(4, c, 192, 95, 5, 68); ++ test(4, e, 192, 95, 5, 96); ++ test(6, d, 0x26075300, 0x60006b00, 0, 0xc05f0543); ++ test(6, c, 0x26075300, 0x60006b00, 0, 0xc02e01ee); ++ test(6, f, 0x26075300, 0x60006b01, 0, 0); ++ test(6, g, 0x24046800, 0x40040806, 0, 0x1006); ++ test(6, g, 0x24046800, 0x40040806, 0x1234, 0x5678); ++ test(6, f, 0x240467ff, 0x40040806, 0x1234, 0x5678); ++ test(6, f, 0x24046801, 0x40040806, 0x1234, 0x5678); ++ test(6, h, 0x24046800, 0x40040800, 0x1234, 0x5678); ++ test(6, h, 0x24046800, 0x40040800, 0, 0); ++ test(6, h, 0x24046800, 0x40040800, 0x10101010, 0x10101010); ++ test(6, a, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef); ++ test(4, g, 64, 15, 116, 26); ++ test(4, g, 64, 15, 127, 3); ++ test(4, g, 64, 15, 123, 1); ++ test(4, h, 64, 15, 123, 128); ++ test(4, h, 64, 15, 123, 129); ++ test(4, a, 10, 0, 0, 52); ++ test(4, b, 10, 0, 0, 220); ++ test(4, a, 10, 1, 0, 2); ++ test(4, b, 10, 1, 0, 6); ++ test(4, c, 10, 1, 0, 10); ++ test(4, d, 10, 1, 0, 20); ++ ++ insert(4, a, 1, 0, 0, 0, 32); ++ insert(4, a, 64, 0, 0, 0, 32); ++ insert(4, a, 128, 0, 0, 0, 32); ++ insert(4, a, 192, 0, 0, 0, 32); ++ insert(4, a, 255, 0, 0, 0, 32); ++ wg_allowedips_remove_by_peer(&t, a, &mutex); ++ test_negative(4, a, 1, 0, 0, 0); ++ test_negative(4, a, 64, 0, 0, 0); ++ test_negative(4, a, 128, 0, 0, 0); ++ test_negative(4, a, 192, 0, 0, 0); ++ test_negative(4, a, 255, 0, 0, 0); ++ ++ wg_allowedips_free(&t, &mutex); ++ wg_allowedips_init(&t); ++ insert(4, a, 192, 168, 0, 0, 16); ++ insert(4, a, 192, 168, 0, 0, 24); ++ wg_allowedips_remove_by_peer(&t, a, &mutex); ++ test_negative(4, a, 192, 168, 0, 1); ++ ++ /* These will hit the WARN_ON(len >= 128) in free_node if something ++ * goes wrong. ++ */ ++ for (i = 0; i < 128; ++i) { ++ part = cpu_to_be64(~(1LLU << (i % 64))); ++ memset(&ip, 0xff, 16); ++ memcpy((u8 *)&ip + (i < 64) * 8, &part, 8); ++ wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); ++ } ++ ++ wg_allowedips_free(&t, &mutex); ++ ++ wg_allowedips_init(&t); ++ insert(4, a, 192, 95, 5, 93, 27); ++ insert(6, a, 0x26075300, 0x60006b00, 0, 0xc05f0543, 128); ++ insert(4, a, 10, 1, 0, 20, 29); ++ insert(6, a, 0x26075300, 0x6d8a6bf8, 0xdab1f1df, 0xc05f1523, 83); ++ insert(6, a, 0x26075300, 0x6d8a6bf8, 0xdab1f1df, 0xc05f1523, 21); ++ list_for_each_entry(iter_node, &a->allowedips_list, peer_list) { ++ u8 cidr, ip[16] __aligned(__alignof(u64)); ++ int family = wg_allowedips_read_node(iter_node, ip, &cidr); ++ ++ count++; ++ ++ if (cidr == 27 && family == AF_INET && ++ !memcmp(ip, ip4(192, 95, 5, 64), sizeof(struct in_addr))) ++ found_a = true; ++ else if (cidr == 128 && family == AF_INET6 && ++ !memcmp(ip, ip6(0x26075300, 0x60006b00, 0, 0xc05f0543), ++ sizeof(struct in6_addr))) ++ found_b = true; ++ else if (cidr == 29 && family == AF_INET && ++ !memcmp(ip, ip4(10, 1, 0, 16), sizeof(struct in_addr))) ++ found_c = true; ++ else if (cidr == 83 && family == AF_INET6 && ++ !memcmp(ip, ip6(0x26075300, 0x6d8a6bf8, 0xdab1e000, 0), ++ sizeof(struct in6_addr))) ++ found_d = true; ++ else if (cidr == 21 && family == AF_INET6 && ++ !memcmp(ip, ip6(0x26075000, 0, 0, 0), ++ sizeof(struct in6_addr))) ++ found_e = true; ++ else ++ found_other = true; ++ } ++ test_boolean(count == 5); ++ test_boolean(found_a); ++ test_boolean(found_b); ++ test_boolean(found_c); ++ test_boolean(found_d); ++ test_boolean(found_e); ++ test_boolean(!found_other); ++ ++ if (IS_ENABLED(DEBUG_RANDOM_TRIE) && success) ++ success = randomized_test(); ++ ++ if (success) ++ pr_info("allowedips self-tests: pass\n"); ++ ++free: ++ wg_allowedips_free(&t, &mutex); ++ kfree(a); ++ kfree(b); ++ kfree(c); ++ kfree(d); ++ kfree(e); ++ kfree(f); ++ kfree(g); ++ kfree(h); ++ mutex_unlock(&mutex); ++ ++ return success; ++} ++ ++#undef test_negative ++#undef test ++#undef remove ++#undef insert ++#undef init_peer ++ ++#endif +--- /dev/null ++++ b/drivers/net/wireguard/selftest/counter.c +@@ -0,0 +1,104 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifdef DEBUG ++bool __init wg_packet_counter_selftest(void) ++{ ++ unsigned int test_num = 0, i; ++ union noise_counter counter; ++ bool success = true; ++ ++#define T_INIT do { \ ++ memset(&counter, 0, sizeof(union noise_counter)); \ ++ spin_lock_init(&counter.receive.lock); \ ++ } while (0) ++#define T_LIM (COUNTER_WINDOW_SIZE + 1) ++#define T(n, v) do { \ ++ ++test_num; \ ++ if (counter_validate(&counter, n) != (v)) { \ ++ pr_err("nonce counter self-test %u: FAIL\n", \ ++ test_num); \ ++ success = false; \ ++ } \ ++ } while (0) ++ ++ T_INIT; ++ /* 1 */ T(0, true); ++ /* 2 */ T(1, true); ++ /* 3 */ T(1, false); ++ /* 4 */ T(9, true); ++ /* 5 */ T(8, true); ++ /* 6 */ T(7, true); ++ /* 7 */ T(7, false); ++ /* 8 */ T(T_LIM, true); ++ /* 9 */ T(T_LIM - 1, true); ++ /* 10 */ T(T_LIM - 1, false); ++ /* 11 */ T(T_LIM - 2, true); ++ /* 12 */ T(2, true); ++ /* 13 */ T(2, false); ++ /* 14 */ T(T_LIM + 16, true); ++ /* 15 */ T(3, false); ++ /* 16 */ T(T_LIM + 16, false); ++ /* 17 */ T(T_LIM * 4, true); ++ /* 18 */ T(T_LIM * 4 - (T_LIM - 1), true); ++ /* 19 */ T(10, false); ++ /* 20 */ T(T_LIM * 4 - T_LIM, false); ++ /* 21 */ T(T_LIM * 4 - (T_LIM + 1), false); ++ /* 22 */ T(T_LIM * 4 - (T_LIM - 2), true); ++ /* 23 */ T(T_LIM * 4 + 1 - T_LIM, false); ++ /* 24 */ T(0, false); ++ /* 25 */ T(REJECT_AFTER_MESSAGES, false); ++ /* 26 */ T(REJECT_AFTER_MESSAGES - 1, true); ++ /* 27 */ T(REJECT_AFTER_MESSAGES, false); ++ /* 28 */ T(REJECT_AFTER_MESSAGES - 1, false); ++ /* 29 */ T(REJECT_AFTER_MESSAGES - 2, true); ++ /* 30 */ T(REJECT_AFTER_MESSAGES + 1, false); ++ /* 31 */ T(REJECT_AFTER_MESSAGES + 2, false); ++ /* 32 */ T(REJECT_AFTER_MESSAGES - 2, false); ++ /* 33 */ T(REJECT_AFTER_MESSAGES - 3, true); ++ /* 34 */ T(0, false); ++ ++ T_INIT; ++ for (i = 1; i <= COUNTER_WINDOW_SIZE; ++i) ++ T(i, true); ++ T(0, true); ++ T(0, false); ++ ++ T_INIT; ++ for (i = 2; i <= COUNTER_WINDOW_SIZE + 1; ++i) ++ T(i, true); ++ T(1, true); ++ T(0, false); ++ ++ T_INIT; ++ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 0;) ++ T(i, true); ++ ++ T_INIT; ++ for (i = COUNTER_WINDOW_SIZE + 2; i-- > 1;) ++ T(i, true); ++ T(0, false); ++ ++ T_INIT; ++ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 1;) ++ T(i, true); ++ T(COUNTER_WINDOW_SIZE + 1, true); ++ T(0, false); ++ ++ T_INIT; ++ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 1;) ++ T(i, true); ++ T(0, true); ++ T(COUNTER_WINDOW_SIZE + 1, true); ++ ++#undef T ++#undef T_LIM ++#undef T_INIT ++ ++ if (success) ++ pr_info("nonce counter self-tests: pass\n"); ++ return success; ++} ++#endif +--- /dev/null ++++ b/drivers/net/wireguard/selftest/ratelimiter.c +@@ -0,0 +1,226 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifdef DEBUG ++ ++#include ++ ++static const struct { ++ bool result; ++ unsigned int msec_to_sleep_before; ++} expected_results[] __initconst = { ++ [0 ... PACKETS_BURSTABLE - 1] = { true, 0 }, ++ [PACKETS_BURSTABLE] = { false, 0 }, ++ [PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND }, ++ [PACKETS_BURSTABLE + 2] = { false, 0 }, ++ [PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 }, ++ [PACKETS_BURSTABLE + 4] = { true, 0 }, ++ [PACKETS_BURSTABLE + 5] = { false, 0 } ++}; ++ ++static __init unsigned int maximum_jiffies_at_index(int index) ++{ ++ unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3; ++ int i; ++ ++ for (i = 0; i <= index; ++i) ++ total_msecs += expected_results[i].msec_to_sleep_before; ++ return msecs_to_jiffies(total_msecs); ++} ++ ++static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4, ++ struct sk_buff *skb6, struct ipv6hdr *hdr6, ++ int *test) ++{ ++ unsigned long loop_start_time; ++ int i; ++ ++ wg_ratelimiter_gc_entries(NULL); ++ rcu_barrier(); ++ loop_start_time = jiffies; ++ ++ for (i = 0; i < ARRAY_SIZE(expected_results); ++i) { ++ if (expected_results[i].msec_to_sleep_before) ++ msleep(expected_results[i].msec_to_sleep_before); ++ ++ if (time_is_before_jiffies(loop_start_time + ++ maximum_jiffies_at_index(i))) ++ return -ETIMEDOUT; ++ if (wg_ratelimiter_allow(skb4, &init_net) != ++ expected_results[i].result) ++ return -EXFULL; ++ ++(*test); ++ ++ hdr4->saddr = htonl(ntohl(hdr4->saddr) + i + 1); ++ if (time_is_before_jiffies(loop_start_time + ++ maximum_jiffies_at_index(i))) ++ return -ETIMEDOUT; ++ if (!wg_ratelimiter_allow(skb4, &init_net)) ++ return -EXFULL; ++ ++(*test); ++ ++ hdr4->saddr = htonl(ntohl(hdr4->saddr) - i - 1); ++ ++#if IS_ENABLED(CONFIG_IPV6) ++ hdr6->saddr.in6_u.u6_addr32[2] = htonl(i); ++ hdr6->saddr.in6_u.u6_addr32[3] = htonl(i); ++ if (time_is_before_jiffies(loop_start_time + ++ maximum_jiffies_at_index(i))) ++ return -ETIMEDOUT; ++ if (wg_ratelimiter_allow(skb6, &init_net) != ++ expected_results[i].result) ++ return -EXFULL; ++ ++(*test); ++ ++ hdr6->saddr.in6_u.u6_addr32[0] = ++ htonl(ntohl(hdr6->saddr.in6_u.u6_addr32[0]) + i + 1); ++ if (time_is_before_jiffies(loop_start_time + ++ maximum_jiffies_at_index(i))) ++ return -ETIMEDOUT; ++ if (!wg_ratelimiter_allow(skb6, &init_net)) ++ return -EXFULL; ++ ++(*test); ++ ++ hdr6->saddr.in6_u.u6_addr32[0] = ++ htonl(ntohl(hdr6->saddr.in6_u.u6_addr32[0]) - i - 1); ++ ++ if (time_is_before_jiffies(loop_start_time + ++ maximum_jiffies_at_index(i))) ++ return -ETIMEDOUT; ++#endif ++ } ++ return 0; ++} ++ ++static __init int capacity_test(struct sk_buff *skb4, struct iphdr *hdr4, ++ int *test) ++{ ++ int i; ++ ++ wg_ratelimiter_gc_entries(NULL); ++ rcu_barrier(); ++ ++ if (atomic_read(&total_entries)) ++ return -EXFULL; ++ ++(*test); ++ ++ for (i = 0; i <= max_entries; ++i) { ++ hdr4->saddr = htonl(i); ++ if (wg_ratelimiter_allow(skb4, &init_net) != (i != max_entries)) ++ return -EXFULL; ++ ++(*test); ++ } ++ return 0; ++} ++ ++bool __init wg_ratelimiter_selftest(void) ++{ ++ enum { TRIALS_BEFORE_GIVING_UP = 5000 }; ++ bool success = false; ++ int test = 0, trials; ++ struct sk_buff *skb4, *skb6; ++ struct iphdr *hdr4; ++ struct ipv6hdr *hdr6; ++ ++ if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) ++ return true; ++ ++ BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0); ++ ++ if (wg_ratelimiter_init()) ++ goto out; ++ ++test; ++ if (wg_ratelimiter_init()) { ++ wg_ratelimiter_uninit(); ++ goto out; ++ } ++ ++test; ++ if (wg_ratelimiter_init()) { ++ wg_ratelimiter_uninit(); ++ wg_ratelimiter_uninit(); ++ goto out; ++ } ++ ++test; ++ ++ skb4 = alloc_skb(sizeof(struct iphdr), GFP_KERNEL); ++ if (unlikely(!skb4)) ++ goto err_nofree; ++ skb4->protocol = htons(ETH_P_IP); ++ hdr4 = (struct iphdr *)skb_put(skb4, sizeof(*hdr4)); ++ hdr4->saddr = htonl(8182); ++ skb_reset_network_header(skb4); ++ ++test; ++ ++#if IS_ENABLED(CONFIG_IPV6) ++ skb6 = alloc_skb(sizeof(struct ipv6hdr), GFP_KERNEL); ++ if (unlikely(!skb6)) { ++ kfree_skb(skb4); ++ goto err_nofree; ++ } ++ skb6->protocol = htons(ETH_P_IPV6); ++ hdr6 = (struct ipv6hdr *)skb_put(skb6, sizeof(*hdr6)); ++ hdr6->saddr.in6_u.u6_addr32[0] = htonl(1212); ++ hdr6->saddr.in6_u.u6_addr32[1] = htonl(289188); ++ skb_reset_network_header(skb6); ++ ++test; ++#endif ++ ++ for (trials = TRIALS_BEFORE_GIVING_UP;;) { ++ int test_count = 0, ret; ++ ++ ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count); ++ if (ret == -ETIMEDOUT) { ++ if (!trials--) { ++ test += test_count; ++ goto err; ++ } ++ msleep(500); ++ continue; ++ } else if (ret < 0) { ++ test += test_count; ++ goto err; ++ } else { ++ test += test_count; ++ break; ++ } ++ } ++ ++ for (trials = TRIALS_BEFORE_GIVING_UP;;) { ++ int test_count = 0; ++ ++ if (capacity_test(skb4, hdr4, &test_count) < 0) { ++ if (!trials--) { ++ test += test_count; ++ goto err; ++ } ++ msleep(50); ++ continue; ++ } ++ test += test_count; ++ break; ++ } ++ ++ success = true; ++ ++err: ++ kfree_skb(skb4); ++#if IS_ENABLED(CONFIG_IPV6) ++ kfree_skb(skb6); ++#endif ++err_nofree: ++ wg_ratelimiter_uninit(); ++ wg_ratelimiter_uninit(); ++ wg_ratelimiter_uninit(); ++ /* Uninit one extra time to check underflow detection. */ ++ wg_ratelimiter_uninit(); ++out: ++ if (success) ++ pr_info("ratelimiter self-tests: pass\n"); ++ else ++ pr_err("ratelimiter self-test %d: FAIL\n", test); ++ ++ return success; ++} ++#endif +--- /dev/null ++++ b/drivers/net/wireguard/send.c +@@ -0,0 +1,413 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "queueing.h" ++#include "timers.h" ++#include "device.h" ++#include "peer.h" ++#include "socket.h" ++#include "messages.h" ++#include "cookie.h" ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++static void wg_packet_send_handshake_initiation(struct wg_peer *peer) ++{ ++ struct message_handshake_initiation packet; ++ ++ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), ++ REKEY_TIMEOUT)) ++ return; /* This function is rate limited. */ ++ ++ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); ++ net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ ++ if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) { ++ wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); ++ wg_timers_any_authenticated_packet_traversal(peer); ++ wg_timers_any_authenticated_packet_sent(peer); ++ atomic64_set(&peer->last_sent_handshake, ++ ktime_get_coarse_boottime_ns()); ++ wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), ++ HANDSHAKE_DSCP); ++ wg_timers_handshake_initiated(peer); ++ } ++} ++ ++void wg_packet_handshake_send_worker(struct work_struct *work) ++{ ++ struct wg_peer *peer = container_of(work, struct wg_peer, ++ transmit_handshake_work); ++ ++ wg_packet_send_handshake_initiation(peer); ++ wg_peer_put(peer); ++} ++ ++void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, ++ bool is_retry) ++{ ++ if (!is_retry) ++ peer->timer_handshake_attempts = 0; ++ ++ rcu_read_lock_bh(); ++ /* We check last_sent_handshake here in addition to the actual function ++ * we're queueing up, so that we don't queue things if not strictly ++ * necessary: ++ */ ++ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), ++ REKEY_TIMEOUT) || ++ unlikely(READ_ONCE(peer->is_dead))) ++ goto out; ++ ++ wg_peer_get(peer); ++ /* Queues up calling packet_send_queued_handshakes(peer), where we do a ++ * peer_put(peer) after: ++ */ ++ if (!queue_work(peer->device->handshake_send_wq, ++ &peer->transmit_handshake_work)) ++ /* If the work was already queued, we want to drop the ++ * extra reference: ++ */ ++ wg_peer_put(peer); ++out: ++ rcu_read_unlock_bh(); ++} ++ ++void wg_packet_send_handshake_response(struct wg_peer *peer) ++{ ++ struct message_handshake_response packet; ++ ++ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); ++ net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ ++ if (wg_noise_handshake_create_response(&packet, &peer->handshake)) { ++ wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); ++ if (wg_noise_handshake_begin_session(&peer->handshake, ++ &peer->keypairs)) { ++ wg_timers_session_derived(peer); ++ wg_timers_any_authenticated_packet_traversal(peer); ++ wg_timers_any_authenticated_packet_sent(peer); ++ atomic64_set(&peer->last_sent_handshake, ++ ktime_get_coarse_boottime_ns()); ++ wg_socket_send_buffer_to_peer(peer, &packet, ++ sizeof(packet), ++ HANDSHAKE_DSCP); ++ } ++ } ++} ++ ++void wg_packet_send_handshake_cookie(struct wg_device *wg, ++ struct sk_buff *initiating_skb, ++ __le32 sender_index) ++{ ++ struct message_handshake_cookie packet; ++ ++ net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n", ++ wg->dev->name, initiating_skb); ++ wg_cookie_message_create(&packet, initiating_skb, sender_index, ++ &wg->cookie_checker); ++ wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet, ++ sizeof(packet)); ++} ++ ++static void keep_key_fresh(struct wg_peer *peer) ++{ ++ struct noise_keypair *keypair; ++ bool send = false; ++ ++ rcu_read_lock_bh(); ++ keypair = rcu_dereference_bh(peer->keypairs.current_keypair); ++ if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && ++ (unlikely(atomic64_read(&keypair->sending.counter.counter) > ++ REKEY_AFTER_MESSAGES) || ++ (keypair->i_am_the_initiator && ++ unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, ++ REKEY_AFTER_TIME))))) ++ send = true; ++ rcu_read_unlock_bh(); ++ ++ if (send) ++ wg_packet_send_queued_handshake_initiation(peer, false); ++} ++ ++static unsigned int calculate_skb_padding(struct sk_buff *skb) ++{ ++ /* We do this modulo business with the MTU, just in case the networking ++ * layer gives us a packet that's bigger than the MTU. In that case, we ++ * wouldn't want the final subtraction to overflow in the case of the ++ * padded_size being clamped. ++ */ ++ unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu; ++ unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE); ++ ++ if (padded_size > PACKET_CB(skb)->mtu) ++ padded_size = PACKET_CB(skb)->mtu; ++ return padded_size - last_unit; ++} ++ ++static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) ++{ ++ unsigned int padding_len, plaintext_len, trailer_len; ++ struct scatterlist sg[MAX_SKB_FRAGS + 8]; ++ struct message_data *header; ++ struct sk_buff *trailer; ++ int num_frags; ++ ++ /* Calculate lengths. */ ++ padding_len = calculate_skb_padding(skb); ++ trailer_len = padding_len + noise_encrypted_len(0); ++ plaintext_len = skb->len + padding_len; ++ ++ /* Expand data section to have room for padding and auth tag. */ ++ num_frags = skb_cow_data(skb, trailer_len, &trailer); ++ if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) ++ return false; ++ ++ /* Set the padding to zeros, and make sure it and the auth tag are part ++ * of the skb. ++ */ ++ memset(skb_tail_pointer(trailer), 0, padding_len); ++ ++ /* Expand head section to have room for our header and the network ++ * stack's headers. ++ */ ++ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0)) ++ return false; ++ ++ /* Finalize checksum calculation for the inner packet, if required. */ ++ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL && ++ skb_checksum_help(skb))) ++ return false; ++ ++ /* Only after checksumming can we safely add on the padding at the end ++ * and the header. ++ */ ++ skb_set_inner_network_header(skb, 0); ++ header = (struct message_data *)skb_push(skb, sizeof(*header)); ++ header->header.type = cpu_to_le32(MESSAGE_DATA); ++ header->key_idx = keypair->remote_index; ++ header->counter = cpu_to_le64(PACKET_CB(skb)->nonce); ++ pskb_put(skb, trailer, trailer_len); ++ ++ /* Now we can encrypt the scattergather segments */ ++ sg_init_table(sg, num_frags); ++ if (skb_to_sgvec(skb, sg, sizeof(struct message_data), ++ noise_encrypted_len(plaintext_len)) <= 0) ++ return false; ++ return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0, ++ PACKET_CB(skb)->nonce, ++ keypair->sending.key); ++} ++ ++void wg_packet_send_keepalive(struct wg_peer *peer) ++{ ++ struct sk_buff *skb; ++ ++ if (skb_queue_empty(&peer->staged_packet_queue)) { ++ skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, ++ GFP_ATOMIC); ++ if (unlikely(!skb)) ++ return; ++ skb_reserve(skb, DATA_PACKET_HEAD_ROOM); ++ skb->dev = peer->device->dev; ++ PACKET_CB(skb)->mtu = skb->dev->mtu; ++ skb_queue_tail(&peer->staged_packet_queue, skb); ++ net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr); ++ } ++ ++ wg_packet_send_staged_packets(peer); ++} ++ ++static void wg_packet_create_data_done(struct sk_buff *first, ++ struct wg_peer *peer) ++{ ++ struct sk_buff *skb, *next; ++ bool is_keepalive, data_sent = false; ++ ++ wg_timers_any_authenticated_packet_traversal(peer); ++ wg_timers_any_authenticated_packet_sent(peer); ++ skb_list_walk_safe(first, skb, next) { ++ is_keepalive = skb->len == message_data_len(0); ++ if (likely(!wg_socket_send_skb_to_peer(peer, skb, ++ PACKET_CB(skb)->ds) && !is_keepalive)) ++ data_sent = true; ++ } ++ ++ if (likely(data_sent)) ++ wg_timers_data_sent(peer); ++ ++ keep_key_fresh(peer); ++} ++ ++void wg_packet_tx_worker(struct work_struct *work) ++{ ++ struct crypt_queue *queue = container_of(work, struct crypt_queue, ++ work); ++ struct noise_keypair *keypair; ++ enum packet_state state; ++ struct sk_buff *first; ++ struct wg_peer *peer; ++ ++ while ((first = __ptr_ring_peek(&queue->ring)) != NULL && ++ (state = atomic_read_acquire(&PACKET_CB(first)->state)) != ++ PACKET_STATE_UNCRYPTED) { ++ __ptr_ring_discard_one(&queue->ring); ++ peer = PACKET_PEER(first); ++ keypair = PACKET_CB(first)->keypair; ++ ++ if (likely(state == PACKET_STATE_CRYPTED)) ++ wg_packet_create_data_done(first, peer); ++ else ++ kfree_skb_list(first); ++ ++ wg_noise_keypair_put(keypair, false); ++ wg_peer_put(peer); ++ } ++} ++ ++void wg_packet_encrypt_worker(struct work_struct *work) ++{ ++ struct crypt_queue *queue = container_of(work, struct multicore_worker, ++ work)->ptr; ++ struct sk_buff *first, *skb, *next; ++ ++ while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) { ++ enum packet_state state = PACKET_STATE_CRYPTED; ++ ++ skb_list_walk_safe(first, skb, next) { ++ if (likely(encrypt_packet(skb, ++ PACKET_CB(first)->keypair))) { ++ wg_reset_packet(skb); ++ } else { ++ state = PACKET_STATE_DEAD; ++ break; ++ } ++ } ++ wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, ++ state); ++ ++ } ++} ++ ++static void wg_packet_create_data(struct sk_buff *first) ++{ ++ struct wg_peer *peer = PACKET_PEER(first); ++ struct wg_device *wg = peer->device; ++ int ret = -EINVAL; ++ ++ rcu_read_lock_bh(); ++ if (unlikely(READ_ONCE(peer->is_dead))) ++ goto err; ++ ++ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, ++ &peer->tx_queue, first, ++ wg->packet_crypt_wq, ++ &wg->encrypt_queue.last_cpu); ++ if (unlikely(ret == -EPIPE)) ++ wg_queue_enqueue_per_peer(&peer->tx_queue, first, ++ PACKET_STATE_DEAD); ++err: ++ rcu_read_unlock_bh(); ++ if (likely(!ret || ret == -EPIPE)) ++ return; ++ wg_noise_keypair_put(PACKET_CB(first)->keypair, false); ++ wg_peer_put(peer); ++ kfree_skb_list(first); ++} ++ ++void wg_packet_purge_staged_packets(struct wg_peer *peer) ++{ ++ spin_lock_bh(&peer->staged_packet_queue.lock); ++ peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen; ++ __skb_queue_purge(&peer->staged_packet_queue); ++ spin_unlock_bh(&peer->staged_packet_queue.lock); ++} ++ ++void wg_packet_send_staged_packets(struct wg_peer *peer) ++{ ++ struct noise_symmetric_key *key; ++ struct noise_keypair *keypair; ++ struct sk_buff_head packets; ++ struct sk_buff *skb; ++ ++ /* Steal the current queue into our local one. */ ++ __skb_queue_head_init(&packets); ++ spin_lock_bh(&peer->staged_packet_queue.lock); ++ skb_queue_splice_init(&peer->staged_packet_queue, &packets); ++ spin_unlock_bh(&peer->staged_packet_queue.lock); ++ if (unlikely(skb_queue_empty(&packets))) ++ return; ++ ++ /* First we make sure we have a valid reference to a valid key. */ ++ rcu_read_lock_bh(); ++ keypair = wg_noise_keypair_get( ++ rcu_dereference_bh(peer->keypairs.current_keypair)); ++ rcu_read_unlock_bh(); ++ if (unlikely(!keypair)) ++ goto out_nokey; ++ key = &keypair->sending; ++ if (unlikely(!READ_ONCE(key->is_valid))) ++ goto out_nokey; ++ if (unlikely(wg_birthdate_has_expired(key->birthdate, ++ REJECT_AFTER_TIME))) ++ goto out_invalid; ++ ++ /* After we know we have a somewhat valid key, we now try to assign ++ * nonces to all of the packets in the queue. If we can't assign nonces ++ * for all of them, we just consider it a failure and wait for the next ++ * handshake. ++ */ ++ skb_queue_walk(&packets, skb) { ++ /* 0 for no outer TOS: no leak. TODO: at some later point, we ++ * might consider using flowi->tos as outer instead. ++ */ ++ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); ++ PACKET_CB(skb)->nonce = ++ atomic64_inc_return(&key->counter.counter) - 1; ++ if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) ++ goto out_invalid; ++ } ++ ++ packets.prev->next = NULL; ++ wg_peer_get(keypair->entry.peer); ++ PACKET_CB(packets.next)->keypair = keypair; ++ wg_packet_create_data(packets.next); ++ return; ++ ++out_invalid: ++ WRITE_ONCE(key->is_valid, false); ++out_nokey: ++ wg_noise_keypair_put(keypair, false); ++ ++ /* We orphan the packets if we're waiting on a handshake, so that they ++ * don't block a socket's pool. ++ */ ++ skb_queue_walk(&packets, skb) ++ skb_orphan(skb); ++ /* Then we put them back on the top of the queue. We're not too ++ * concerned about accidentally getting things a little out of order if ++ * packets are being added really fast, because this queue is for before ++ * packets can even be sent and it's small anyway. ++ */ ++ spin_lock_bh(&peer->staged_packet_queue.lock); ++ skb_queue_splice(&packets, &peer->staged_packet_queue); ++ spin_unlock_bh(&peer->staged_packet_queue.lock); ++ ++ /* If we're exiting because there's something wrong with the key, it ++ * means we should initiate a new handshake. ++ */ ++ wg_packet_send_queued_handshake_initiation(peer, false); ++} +--- /dev/null ++++ b/drivers/net/wireguard/socket.c +@@ -0,0 +1,437 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "device.h" ++#include "peer.h" ++#include "socket.h" ++#include "queueing.h" ++#include "messages.h" ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++static int send4(struct wg_device *wg, struct sk_buff *skb, ++ struct endpoint *endpoint, u8 ds, struct dst_cache *cache) ++{ ++ struct flowi4 fl = { ++ .saddr = endpoint->src4.s_addr, ++ .daddr = endpoint->addr4.sin_addr.s_addr, ++ .fl4_dport = endpoint->addr4.sin_port, ++ .flowi4_mark = wg->fwmark, ++ .flowi4_proto = IPPROTO_UDP ++ }; ++ struct rtable *rt = NULL; ++ struct sock *sock; ++ int ret = 0; ++ ++ skb_mark_not_on_list(skb); ++ skb->dev = wg->dev; ++ skb->mark = wg->fwmark; ++ ++ rcu_read_lock_bh(); ++ sock = rcu_dereference_bh(wg->sock4); ++ ++ if (unlikely(!sock)) { ++ ret = -ENONET; ++ goto err; ++ } ++ ++ fl.fl4_sport = inet_sk(sock)->inet_sport; ++ ++ if (cache) ++ rt = dst_cache_get_ip4(cache, &fl.saddr); ++ ++ if (!rt) { ++ security_sk_classify_flow(sock, flowi4_to_flowi(&fl)); ++ if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, ++ fl.saddr, RT_SCOPE_HOST))) { ++ endpoint->src4.s_addr = 0; ++ *(__force __be32 *)&endpoint->src_if4 = 0; ++ fl.saddr = 0; ++ if (cache) ++ dst_cache_reset(cache); ++ } ++ rt = ip_route_output_flow(sock_net(sock), &fl, sock); ++ if (unlikely(endpoint->src_if4 && ((IS_ERR(rt) && ++ PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && ++ rt->dst.dev->ifindex != endpoint->src_if4)))) { ++ endpoint->src4.s_addr = 0; ++ *(__force __be32 *)&endpoint->src_if4 = 0; ++ fl.saddr = 0; ++ if (cache) ++ dst_cache_reset(cache); ++ if (!IS_ERR(rt)) ++ ip_rt_put(rt); ++ rt = ip_route_output_flow(sock_net(sock), &fl, sock); ++ } ++ if (unlikely(IS_ERR(rt))) { ++ ret = PTR_ERR(rt); ++ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", ++ wg->dev->name, &endpoint->addr, ret); ++ goto err; ++ } else if (unlikely(rt->dst.dev == skb->dev)) { ++ ip_rt_put(rt); ++ ret = -ELOOP; ++ net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", ++ wg->dev->name, &endpoint->addr); ++ goto err; ++ } ++ if (cache) ++ dst_cache_set_ip4(cache, &rt->dst, fl.saddr); ++ } ++ ++ skb->ignore_df = 1; ++ udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds, ++ ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, ++ fl.fl4_dport, false, false); ++ goto out; ++ ++err: ++ kfree_skb(skb); ++out: ++ rcu_read_unlock_bh(); ++ return ret; ++} ++ ++static int send6(struct wg_device *wg, struct sk_buff *skb, ++ struct endpoint *endpoint, u8 ds, struct dst_cache *cache) ++{ ++#if IS_ENABLED(CONFIG_IPV6) ++ struct flowi6 fl = { ++ .saddr = endpoint->src6, ++ .daddr = endpoint->addr6.sin6_addr, ++ .fl6_dport = endpoint->addr6.sin6_port, ++ .flowi6_mark = wg->fwmark, ++ .flowi6_oif = endpoint->addr6.sin6_scope_id, ++ .flowi6_proto = IPPROTO_UDP ++ /* TODO: addr->sin6_flowinfo */ ++ }; ++ struct dst_entry *dst = NULL; ++ struct sock *sock; ++ int ret = 0; ++ ++ skb_mark_not_on_list(skb); ++ skb->dev = wg->dev; ++ skb->mark = wg->fwmark; ++ ++ rcu_read_lock_bh(); ++ sock = rcu_dereference_bh(wg->sock6); ++ ++ if (unlikely(!sock)) { ++ ret = -ENONET; ++ goto err; ++ } ++ ++ fl.fl6_sport = inet_sk(sock)->inet_sport; ++ ++ if (cache) ++ dst = dst_cache_get_ip6(cache, &fl.saddr); ++ ++ if (!dst) { ++ security_sk_classify_flow(sock, flowi6_to_flowi(&fl)); ++ if (unlikely(!ipv6_addr_any(&fl.saddr) && ++ !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) { ++ endpoint->src6 = fl.saddr = in6addr_any; ++ if (cache) ++ dst_cache_reset(cache); ++ } ++ dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl, ++ NULL); ++ if (unlikely(IS_ERR(dst))) { ++ ret = PTR_ERR(dst); ++ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", ++ wg->dev->name, &endpoint->addr, ret); ++ goto err; ++ } else if (unlikely(dst->dev == skb->dev)) { ++ dst_release(dst); ++ ret = -ELOOP; ++ net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", ++ wg->dev->name, &endpoint->addr); ++ goto err; ++ } ++ if (cache) ++ dst_cache_set_ip6(cache, dst, &fl.saddr); ++ } ++ ++ skb->ignore_df = 1; ++ udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds, ++ ip6_dst_hoplimit(dst), 0, fl.fl6_sport, ++ fl.fl6_dport, false); ++ goto out; ++ ++err: ++ kfree_skb(skb); ++out: ++ rcu_read_unlock_bh(); ++ return ret; ++#else ++ return -EAFNOSUPPORT; ++#endif ++} ++ ++int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb, u8 ds) ++{ ++ size_t skb_len = skb->len; ++ int ret = -EAFNOSUPPORT; ++ ++ read_lock_bh(&peer->endpoint_lock); ++ if (peer->endpoint.addr.sa_family == AF_INET) ++ ret = send4(peer->device, skb, &peer->endpoint, ds, ++ &peer->endpoint_cache); ++ else if (peer->endpoint.addr.sa_family == AF_INET6) ++ ret = send6(peer->device, skb, &peer->endpoint, ds, ++ &peer->endpoint_cache); ++ else ++ dev_kfree_skb(skb); ++ if (likely(!ret)) ++ peer->tx_bytes += skb_len; ++ read_unlock_bh(&peer->endpoint_lock); ++ ++ return ret; ++} ++ ++int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *buffer, ++ size_t len, u8 ds) ++{ ++ struct sk_buff *skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC); ++ ++ if (unlikely(!skb)) ++ return -ENOMEM; ++ ++ skb_reserve(skb, SKB_HEADER_LEN); ++ skb_set_inner_network_header(skb, 0); ++ skb_put_data(skb, buffer, len); ++ return wg_socket_send_skb_to_peer(peer, skb, ds); ++} ++ ++int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg, ++ struct sk_buff *in_skb, void *buffer, ++ size_t len) ++{ ++ int ret = 0; ++ struct sk_buff *skb; ++ struct endpoint endpoint; ++ ++ if (unlikely(!in_skb)) ++ return -EINVAL; ++ ret = wg_socket_endpoint_from_skb(&endpoint, in_skb); ++ if (unlikely(ret < 0)) ++ return ret; ++ ++ skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC); ++ if (unlikely(!skb)) ++ return -ENOMEM; ++ skb_reserve(skb, SKB_HEADER_LEN); ++ skb_set_inner_network_header(skb, 0); ++ skb_put_data(skb, buffer, len); ++ ++ if (endpoint.addr.sa_family == AF_INET) ++ ret = send4(wg, skb, &endpoint, 0, NULL); ++ else if (endpoint.addr.sa_family == AF_INET6) ++ ret = send6(wg, skb, &endpoint, 0, NULL); ++ /* No other possibilities if the endpoint is valid, which it is, ++ * as we checked above. ++ */ ++ ++ return ret; ++} ++ ++int wg_socket_endpoint_from_skb(struct endpoint *endpoint, ++ const struct sk_buff *skb) ++{ ++ memset(endpoint, 0, sizeof(*endpoint)); ++ if (skb->protocol == htons(ETH_P_IP)) { ++ endpoint->addr4.sin_family = AF_INET; ++ endpoint->addr4.sin_port = udp_hdr(skb)->source; ++ endpoint->addr4.sin_addr.s_addr = ip_hdr(skb)->saddr; ++ endpoint->src4.s_addr = ip_hdr(skb)->daddr; ++ endpoint->src_if4 = skb->skb_iif; ++ } else if (skb->protocol == htons(ETH_P_IPV6)) { ++ endpoint->addr6.sin6_family = AF_INET6; ++ endpoint->addr6.sin6_port = udp_hdr(skb)->source; ++ endpoint->addr6.sin6_addr = ipv6_hdr(skb)->saddr; ++ endpoint->addr6.sin6_scope_id = ipv6_iface_scope_id( ++ &ipv6_hdr(skb)->saddr, skb->skb_iif); ++ endpoint->src6 = ipv6_hdr(skb)->daddr; ++ } else { ++ return -EINVAL; ++ } ++ return 0; ++} ++ ++static bool endpoint_eq(const struct endpoint *a, const struct endpoint *b) ++{ ++ return (a->addr.sa_family == AF_INET && b->addr.sa_family == AF_INET && ++ a->addr4.sin_port == b->addr4.sin_port && ++ a->addr4.sin_addr.s_addr == b->addr4.sin_addr.s_addr && ++ a->src4.s_addr == b->src4.s_addr && a->src_if4 == b->src_if4) || ++ (a->addr.sa_family == AF_INET6 && ++ b->addr.sa_family == AF_INET6 && ++ a->addr6.sin6_port == b->addr6.sin6_port && ++ ipv6_addr_equal(&a->addr6.sin6_addr, &b->addr6.sin6_addr) && ++ a->addr6.sin6_scope_id == b->addr6.sin6_scope_id && ++ ipv6_addr_equal(&a->src6, &b->src6)) || ++ unlikely(!a->addr.sa_family && !b->addr.sa_family); ++} ++ ++void wg_socket_set_peer_endpoint(struct wg_peer *peer, ++ const struct endpoint *endpoint) ++{ ++ /* First we check unlocked, in order to optimize, since it's pretty rare ++ * that an endpoint will change. If we happen to be mid-write, and two ++ * CPUs wind up writing the same thing or something slightly different, ++ * it doesn't really matter much either. ++ */ ++ if (endpoint_eq(endpoint, &peer->endpoint)) ++ return; ++ write_lock_bh(&peer->endpoint_lock); ++ if (endpoint->addr.sa_family == AF_INET) { ++ peer->endpoint.addr4 = endpoint->addr4; ++ peer->endpoint.src4 = endpoint->src4; ++ peer->endpoint.src_if4 = endpoint->src_if4; ++ } else if (endpoint->addr.sa_family == AF_INET6) { ++ peer->endpoint.addr6 = endpoint->addr6; ++ peer->endpoint.src6 = endpoint->src6; ++ } else { ++ goto out; ++ } ++ dst_cache_reset(&peer->endpoint_cache); ++out: ++ write_unlock_bh(&peer->endpoint_lock); ++} ++ ++void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer, ++ const struct sk_buff *skb) ++{ ++ struct endpoint endpoint; ++ ++ if (!wg_socket_endpoint_from_skb(&endpoint, skb)) ++ wg_socket_set_peer_endpoint(peer, &endpoint); ++} ++ ++void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer) ++{ ++ write_lock_bh(&peer->endpoint_lock); ++ memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6)); ++ dst_cache_reset(&peer->endpoint_cache); ++ write_unlock_bh(&peer->endpoint_lock); ++} ++ ++static int wg_receive(struct sock *sk, struct sk_buff *skb) ++{ ++ struct wg_device *wg; ++ ++ if (unlikely(!sk)) ++ goto err; ++ wg = sk->sk_user_data; ++ if (unlikely(!wg)) ++ goto err; ++ wg_packet_receive(wg, skb); ++ return 0; ++ ++err: ++ kfree_skb(skb); ++ return 0; ++} ++ ++static void sock_free(struct sock *sock) ++{ ++ if (unlikely(!sock)) ++ return; ++ sk_clear_memalloc(sock); ++ udp_tunnel_sock_release(sock->sk_socket); ++} ++ ++static void set_sock_opts(struct socket *sock) ++{ ++ sock->sk->sk_allocation = GFP_ATOMIC; ++ sock->sk->sk_sndbuf = INT_MAX; ++ sk_set_memalloc(sock->sk); ++} ++ ++int wg_socket_init(struct wg_device *wg, u16 port) ++{ ++ int ret; ++ struct udp_tunnel_sock_cfg cfg = { ++ .sk_user_data = wg, ++ .encap_type = 1, ++ .encap_rcv = wg_receive ++ }; ++ struct socket *new4 = NULL, *new6 = NULL; ++ struct udp_port_cfg port4 = { ++ .family = AF_INET, ++ .local_ip.s_addr = htonl(INADDR_ANY), ++ .local_udp_port = htons(port), ++ .use_udp_checksums = true ++ }; ++#if IS_ENABLED(CONFIG_IPV6) ++ int retries = 0; ++ struct udp_port_cfg port6 = { ++ .family = AF_INET6, ++ .local_ip6 = IN6ADDR_ANY_INIT, ++ .use_udp6_tx_checksums = true, ++ .use_udp6_rx_checksums = true, ++ .ipv6_v6only = true ++ }; ++#endif ++ ++#if IS_ENABLED(CONFIG_IPV6) ++retry: ++#endif ++ ++ ret = udp_sock_create(wg->creating_net, &port4, &new4); ++ if (ret < 0) { ++ pr_err("%s: Could not create IPv4 socket\n", wg->dev->name); ++ return ret; ++ } ++ set_sock_opts(new4); ++ setup_udp_tunnel_sock(wg->creating_net, new4, &cfg); ++ ++#if IS_ENABLED(CONFIG_IPV6) ++ if (ipv6_mod_enabled()) { ++ port6.local_udp_port = inet_sk(new4->sk)->inet_sport; ++ ret = udp_sock_create(wg->creating_net, &port6, &new6); ++ if (ret < 0) { ++ udp_tunnel_sock_release(new4); ++ if (ret == -EADDRINUSE && !port && retries++ < 100) ++ goto retry; ++ pr_err("%s: Could not create IPv6 socket\n", ++ wg->dev->name); ++ return ret; ++ } ++ set_sock_opts(new6); ++ setup_udp_tunnel_sock(wg->creating_net, new6, &cfg); ++ } ++#endif ++ ++ wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL); ++ return 0; ++} ++ ++void wg_socket_reinit(struct wg_device *wg, struct sock *new4, ++ struct sock *new6) ++{ ++ struct sock *old4, *old6; ++ ++ mutex_lock(&wg->socket_update_lock); ++ old4 = rcu_dereference_protected(wg->sock4, ++ lockdep_is_held(&wg->socket_update_lock)); ++ old6 = rcu_dereference_protected(wg->sock6, ++ lockdep_is_held(&wg->socket_update_lock)); ++ rcu_assign_pointer(wg->sock4, new4); ++ rcu_assign_pointer(wg->sock6, new6); ++ if (new4) ++ wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); ++ mutex_unlock(&wg->socket_update_lock); ++ synchronize_rcu(); ++ synchronize_net(); ++ sock_free(old4); ++ sock_free(old6); ++} +--- /dev/null ++++ b/drivers/net/wireguard/socket.h +@@ -0,0 +1,44 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_SOCKET_H ++#define _WG_SOCKET_H ++ ++#include ++#include ++#include ++#include ++ ++int wg_socket_init(struct wg_device *wg, u16 port); ++void wg_socket_reinit(struct wg_device *wg, struct sock *new4, ++ struct sock *new6); ++int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *data, ++ size_t len, u8 ds); ++int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb, ++ u8 ds); ++int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg, ++ struct sk_buff *in_skb, ++ void *out_buffer, size_t len); ++ ++int wg_socket_endpoint_from_skb(struct endpoint *endpoint, ++ const struct sk_buff *skb); ++void wg_socket_set_peer_endpoint(struct wg_peer *peer, ++ const struct endpoint *endpoint); ++void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer, ++ const struct sk_buff *skb); ++void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer); ++ ++#if defined(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG) ++#define net_dbg_skb_ratelimited(fmt, dev, skb, ...) do { \ ++ struct endpoint __endpoint; \ ++ wg_socket_endpoint_from_skb(&__endpoint, skb); \ ++ net_dbg_ratelimited(fmt, dev, &__endpoint.addr, \ ++ ##__VA_ARGS__); \ ++ } while (0) ++#else ++#define net_dbg_skb_ratelimited(fmt, skb, ...) ++#endif ++ ++#endif /* _WG_SOCKET_H */ +--- /dev/null ++++ b/drivers/net/wireguard/timers.c +@@ -0,0 +1,243 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#include "timers.h" ++#include "device.h" ++#include "peer.h" ++#include "queueing.h" ++#include "socket.h" ++ ++/* ++ * - Timer for retransmitting the handshake if we don't hear back after ++ * `REKEY_TIMEOUT + jitter` ms. ++ * ++ * - Timer for sending empty packet if we have received a packet but after have ++ * not sent one for `KEEPALIVE_TIMEOUT` ms. ++ * ++ * - Timer for initiating new handshake if we have sent a packet but after have ++ * not received one (even empty) for `(KEEPALIVE_TIMEOUT + REKEY_TIMEOUT) + ++ * jitter` ms. ++ * ++ * - Timer for zeroing out all ephemeral keys after `(REJECT_AFTER_TIME * 3)` ms ++ * if no new keys have been received. ++ * ++ * - Timer for, if enabled, sending an empty authenticated packet every user- ++ * specified seconds. ++ */ ++ ++static inline void mod_peer_timer(struct wg_peer *peer, ++ struct timer_list *timer, ++ unsigned long expires) ++{ ++ rcu_read_lock_bh(); ++ if (likely(netif_running(peer->device->dev) && ++ !READ_ONCE(peer->is_dead))) ++ mod_timer(timer, expires); ++ rcu_read_unlock_bh(); ++} ++ ++static void wg_expired_retransmit_handshake(struct timer_list *timer) ++{ ++ struct wg_peer *peer = from_timer(peer, timer, ++ timer_retransmit_handshake); ++ ++ if (peer->timer_handshake_attempts > MAX_TIMER_HANDSHAKES) { ++ pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d attempts, giving up\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr, MAX_TIMER_HANDSHAKES + 2); ++ ++ del_timer(&peer->timer_send_keepalive); ++ /* We drop all packets without a keypair and don't try again, ++ * if we try unsuccessfully for too long to make a handshake. ++ */ ++ wg_packet_purge_staged_packets(peer); ++ ++ /* We set a timer for destroying any residue that might be left ++ * of a partial exchange. ++ */ ++ if (!timer_pending(&peer->timer_zero_key_material)) ++ mod_peer_timer(peer, &peer->timer_zero_key_material, ++ jiffies + REJECT_AFTER_TIME * 3 * HZ); ++ } else { ++ ++peer->timer_handshake_attempts; ++ pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d seconds, retrying (try %d)\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr, REKEY_TIMEOUT, ++ peer->timer_handshake_attempts + 1); ++ ++ /* We clear the endpoint address src address, in case this is ++ * the cause of trouble. ++ */ ++ wg_socket_clear_peer_endpoint_src(peer); ++ ++ wg_packet_send_queued_handshake_initiation(peer, true); ++ } ++} ++ ++static void wg_expired_send_keepalive(struct timer_list *timer) ++{ ++ struct wg_peer *peer = from_timer(peer, timer, timer_send_keepalive); ++ ++ wg_packet_send_keepalive(peer); ++ if (peer->timer_need_another_keepalive) { ++ peer->timer_need_another_keepalive = false; ++ mod_peer_timer(peer, &peer->timer_send_keepalive, ++ jiffies + KEEPALIVE_TIMEOUT * HZ); ++ } ++} ++ ++static void wg_expired_new_handshake(struct timer_list *timer) ++{ ++ struct wg_peer *peer = from_timer(peer, timer, timer_new_handshake); ++ ++ pr_debug("%s: Retrying handshake with peer %llu (%pISpfsc) because we stopped hearing back after %d seconds\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr, KEEPALIVE_TIMEOUT + REKEY_TIMEOUT); ++ /* We clear the endpoint address src address, in case this is the cause ++ * of trouble. ++ */ ++ wg_socket_clear_peer_endpoint_src(peer); ++ wg_packet_send_queued_handshake_initiation(peer, false); ++} ++ ++static void wg_expired_zero_key_material(struct timer_list *timer) ++{ ++ struct wg_peer *peer = from_timer(peer, timer, timer_zero_key_material); ++ ++ rcu_read_lock_bh(); ++ if (!READ_ONCE(peer->is_dead)) { ++ wg_peer_get(peer); ++ if (!queue_work(peer->device->handshake_send_wq, ++ &peer->clear_peer_work)) ++ /* If the work was already on the queue, we want to drop ++ * the extra reference. ++ */ ++ wg_peer_put(peer); ++ } ++ rcu_read_unlock_bh(); ++} ++ ++static void wg_queued_expired_zero_key_material(struct work_struct *work) ++{ ++ struct wg_peer *peer = container_of(work, struct wg_peer, ++ clear_peer_work); ++ ++ pr_debug("%s: Zeroing out all keys for peer %llu (%pISpfsc), since we haven't received a new one in %d seconds\n", ++ peer->device->dev->name, peer->internal_id, ++ &peer->endpoint.addr, REJECT_AFTER_TIME * 3); ++ wg_noise_handshake_clear(&peer->handshake); ++ wg_noise_keypairs_clear(&peer->keypairs); ++ wg_peer_put(peer); ++} ++ ++static void wg_expired_send_persistent_keepalive(struct timer_list *timer) ++{ ++ struct wg_peer *peer = from_timer(peer, timer, ++ timer_persistent_keepalive); ++ ++ if (likely(peer->persistent_keepalive_interval)) ++ wg_packet_send_keepalive(peer); ++} ++ ++/* Should be called after an authenticated data packet is sent. */ ++void wg_timers_data_sent(struct wg_peer *peer) ++{ ++ if (!timer_pending(&peer->timer_new_handshake)) ++ mod_peer_timer(peer, &peer->timer_new_handshake, ++ jiffies + (KEEPALIVE_TIMEOUT + REKEY_TIMEOUT) * HZ + ++ prandom_u32_max(REKEY_TIMEOUT_JITTER_MAX_JIFFIES)); ++} ++ ++/* Should be called after an authenticated data packet is received. */ ++void wg_timers_data_received(struct wg_peer *peer) ++{ ++ if (likely(netif_running(peer->device->dev))) { ++ if (!timer_pending(&peer->timer_send_keepalive)) ++ mod_peer_timer(peer, &peer->timer_send_keepalive, ++ jiffies + KEEPALIVE_TIMEOUT * HZ); ++ else ++ peer->timer_need_another_keepalive = true; ++ } ++} ++ ++/* Should be called after any type of authenticated packet is sent, whether ++ * keepalive, data, or handshake. ++ */ ++void wg_timers_any_authenticated_packet_sent(struct wg_peer *peer) ++{ ++ del_timer(&peer->timer_send_keepalive); ++} ++ ++/* Should be called after any type of authenticated packet is received, whether ++ * keepalive, data, or handshake. ++ */ ++void wg_timers_any_authenticated_packet_received(struct wg_peer *peer) ++{ ++ del_timer(&peer->timer_new_handshake); ++} ++ ++/* Should be called after a handshake initiation message is sent. */ ++void wg_timers_handshake_initiated(struct wg_peer *peer) ++{ ++ mod_peer_timer(peer, &peer->timer_retransmit_handshake, ++ jiffies + REKEY_TIMEOUT * HZ + ++ prandom_u32_max(REKEY_TIMEOUT_JITTER_MAX_JIFFIES)); ++} ++ ++/* Should be called after a handshake response message is received and processed ++ * or when getting key confirmation via the first data message. ++ */ ++void wg_timers_handshake_complete(struct wg_peer *peer) ++{ ++ del_timer(&peer->timer_retransmit_handshake); ++ peer->timer_handshake_attempts = 0; ++ peer->sent_lastminute_handshake = false; ++ ktime_get_real_ts64(&peer->walltime_last_handshake); ++} ++ ++/* Should be called after an ephemeral key is created, which is before sending a ++ * handshake response or after receiving a handshake response. ++ */ ++void wg_timers_session_derived(struct wg_peer *peer) ++{ ++ mod_peer_timer(peer, &peer->timer_zero_key_material, ++ jiffies + REJECT_AFTER_TIME * 3 * HZ); ++} ++ ++/* Should be called before a packet with authentication, whether ++ * keepalive, data, or handshakem is sent, or after one is received. ++ */ ++void wg_timers_any_authenticated_packet_traversal(struct wg_peer *peer) ++{ ++ if (peer->persistent_keepalive_interval) ++ mod_peer_timer(peer, &peer->timer_persistent_keepalive, ++ jiffies + peer->persistent_keepalive_interval * HZ); ++} ++ ++void wg_timers_init(struct wg_peer *peer) ++{ ++ timer_setup(&peer->timer_retransmit_handshake, ++ wg_expired_retransmit_handshake, 0); ++ timer_setup(&peer->timer_send_keepalive, wg_expired_send_keepalive, 0); ++ timer_setup(&peer->timer_new_handshake, wg_expired_new_handshake, 0); ++ timer_setup(&peer->timer_zero_key_material, ++ wg_expired_zero_key_material, 0); ++ timer_setup(&peer->timer_persistent_keepalive, ++ wg_expired_send_persistent_keepalive, 0); ++ INIT_WORK(&peer->clear_peer_work, wg_queued_expired_zero_key_material); ++ peer->timer_handshake_attempts = 0; ++ peer->sent_lastminute_handshake = false; ++ peer->timer_need_another_keepalive = false; ++} ++ ++void wg_timers_stop(struct wg_peer *peer) ++{ ++ del_timer_sync(&peer->timer_retransmit_handshake); ++ del_timer_sync(&peer->timer_send_keepalive); ++ del_timer_sync(&peer->timer_new_handshake); ++ del_timer_sync(&peer->timer_zero_key_material); ++ del_timer_sync(&peer->timer_persistent_keepalive); ++ flush_work(&peer->clear_peer_work); ++} +--- /dev/null ++++ b/drivers/net/wireguard/timers.h +@@ -0,0 +1,31 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#ifndef _WG_TIMERS_H ++#define _WG_TIMERS_H ++ ++#include ++ ++struct wg_peer; ++ ++void wg_timers_init(struct wg_peer *peer); ++void wg_timers_stop(struct wg_peer *peer); ++void wg_timers_data_sent(struct wg_peer *peer); ++void wg_timers_data_received(struct wg_peer *peer); ++void wg_timers_any_authenticated_packet_sent(struct wg_peer *peer); ++void wg_timers_any_authenticated_packet_received(struct wg_peer *peer); ++void wg_timers_handshake_initiated(struct wg_peer *peer); ++void wg_timers_handshake_complete(struct wg_peer *peer); ++void wg_timers_session_derived(struct wg_peer *peer); ++void wg_timers_any_authenticated_packet_traversal(struct wg_peer *peer); ++ ++static inline bool wg_birthdate_has_expired(u64 birthday_nanoseconds, ++ u64 expiration_seconds) ++{ ++ return (s64)(birthday_nanoseconds + expiration_seconds * NSEC_PER_SEC) ++ <= (s64)ktime_get_coarse_boottime_ns(); ++} ++ ++#endif /* _WG_TIMERS_H */ +--- /dev/null ++++ b/drivers/net/wireguard/version.h +@@ -0,0 +1 @@ ++#define WIREGUARD_VERSION "1.0.0" +--- /dev/null ++++ b/include/uapi/linux/wireguard.h +@@ -0,0 +1,196 @@ ++/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ * ++ * Documentation ++ * ============= ++ * ++ * The below enums and macros are for interfacing with WireGuard, using generic ++ * netlink, with family WG_GENL_NAME and version WG_GENL_VERSION. It defines two ++ * methods: get and set. Note that while they share many common attributes, ++ * these two functions actually accept a slightly different set of inputs and ++ * outputs. ++ * ++ * WG_CMD_GET_DEVICE ++ * ----------------- ++ * ++ * May only be called via NLM_F_REQUEST | NLM_F_DUMP. The command should contain ++ * one but not both of: ++ * ++ * WGDEVICE_A_IFINDEX: NLA_U32 ++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1 ++ * ++ * The kernel will then return several messages (NLM_F_MULTI) containing the ++ * following tree of nested items: ++ * ++ * WGDEVICE_A_IFINDEX: NLA_U32 ++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1 ++ * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN ++ * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN ++ * WGDEVICE_A_LISTEN_PORT: NLA_U16 ++ * WGDEVICE_A_FWMARK: NLA_U32 ++ * WGDEVICE_A_PEERS: NLA_NESTED ++ * 0: NLA_NESTED ++ * WGPEER_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN ++ * WGPEER_A_PRESHARED_KEY: NLA_EXACT_LEN, len WG_KEY_LEN ++ * WGPEER_A_ENDPOINT: NLA_MIN_LEN(struct sockaddr), struct sockaddr_in or struct sockaddr_in6 ++ * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16 ++ * WGPEER_A_LAST_HANDSHAKE_TIME: NLA_EXACT_LEN, struct __kernel_timespec ++ * WGPEER_A_RX_BYTES: NLA_U64 ++ * WGPEER_A_TX_BYTES: NLA_U64 ++ * WGPEER_A_ALLOWEDIPS: NLA_NESTED ++ * 0: NLA_NESTED ++ * WGALLOWEDIP_A_FAMILY: NLA_U16 ++ * WGALLOWEDIP_A_IPADDR: NLA_MIN_LEN(struct in_addr), struct in_addr or struct in6_addr ++ * WGALLOWEDIP_A_CIDR_MASK: NLA_U8 ++ * 0: NLA_NESTED ++ * ... ++ * 0: NLA_NESTED ++ * ... ++ * ... ++ * WGPEER_A_PROTOCOL_VERSION: NLA_U32 ++ * 0: NLA_NESTED ++ * ... ++ * ... ++ * ++ * It is possible that all of the allowed IPs of a single peer will not ++ * fit within a single netlink message. In that case, the same peer will ++ * be written in the following message, except it will only contain ++ * WGPEER_A_PUBLIC_KEY and WGPEER_A_ALLOWEDIPS. This may occur several ++ * times in a row for the same peer. It is then up to the receiver to ++ * coalesce adjacent peers. Likewise, it is possible that all peers will ++ * not fit within a single message. So, subsequent peers will be sent ++ * in following messages, except those will only contain WGDEVICE_A_IFNAME ++ * and WGDEVICE_A_PEERS. It is then up to the receiver to coalesce these ++ * messages to form the complete list of peers. ++ * ++ * Since this is an NLA_F_DUMP command, the final message will always be ++ * NLMSG_DONE, even if an error occurs. However, this NLMSG_DONE message ++ * contains an integer error code. It is either zero or a negative error ++ * code corresponding to the errno. ++ * ++ * WG_CMD_SET_DEVICE ++ * ----------------- ++ * ++ * May only be called via NLM_F_REQUEST. The command should contain the ++ * following tree of nested items, containing one but not both of ++ * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME: ++ * ++ * WGDEVICE_A_IFINDEX: NLA_U32 ++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1 ++ * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current ++ * peers should be removed prior to adding the list below. ++ * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove ++ * WGDEVICE_A_LISTEN_PORT: NLA_U16, 0 to choose randomly ++ * WGDEVICE_A_FWMARK: NLA_U32, 0 to disable ++ * WGDEVICE_A_PEERS: NLA_NESTED ++ * 0: NLA_NESTED ++ * WGPEER_A_PUBLIC_KEY: len WG_KEY_LEN ++ * WGPEER_A_FLAGS: NLA_U32, 0 and/or WGPEER_F_REMOVE_ME if the ++ * specified peer should not exist at the end of the ++ * operation, rather than added/updated and/or ++ * WGPEER_F_REPLACE_ALLOWEDIPS if all current allowed ++ * IPs of this peer should be removed prior to adding ++ * the list below and/or WGPEER_F_UPDATE_ONLY if the ++ * peer should only be set if it already exists. ++ * WGPEER_A_PRESHARED_KEY: len WG_KEY_LEN, all zeros to remove ++ * WGPEER_A_ENDPOINT: struct sockaddr_in or struct sockaddr_in6 ++ * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16, 0 to disable ++ * WGPEER_A_ALLOWEDIPS: NLA_NESTED ++ * 0: NLA_NESTED ++ * WGALLOWEDIP_A_FAMILY: NLA_U16 ++ * WGALLOWEDIP_A_IPADDR: struct in_addr or struct in6_addr ++ * WGALLOWEDIP_A_CIDR_MASK: NLA_U8 ++ * 0: NLA_NESTED ++ * ... ++ * 0: NLA_NESTED ++ * ... ++ * ... ++ * WGPEER_A_PROTOCOL_VERSION: NLA_U32, should not be set or used at ++ * all by most users of this API, as the ++ * most recent protocol will be used when ++ * this is unset. Otherwise, must be set ++ * to 1. ++ * 0: NLA_NESTED ++ * ... ++ * ... ++ * ++ * It is possible that the amount of configuration data exceeds that of ++ * the maximum message length accepted by the kernel. In that case, several ++ * messages should be sent one after another, with each successive one ++ * filling in information not contained in the prior. Note that if ++ * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably ++ * should not be specified in fragments that come after, so that the list ++ * of peers is only cleared the first time but appened after. Likewise for ++ * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message ++ * of a peer, it likely should not be specified in subsequent fragments. ++ * ++ * If an error occurs, NLMSG_ERROR will reply containing an errno. ++ */ ++ ++#ifndef _WG_UAPI_WIREGUARD_H ++#define _WG_UAPI_WIREGUARD_H ++ ++#define WG_GENL_NAME "wireguard" ++#define WG_GENL_VERSION 1 ++ ++#define WG_KEY_LEN 32 ++ ++enum wg_cmd { ++ WG_CMD_GET_DEVICE, ++ WG_CMD_SET_DEVICE, ++ __WG_CMD_MAX ++}; ++#define WG_CMD_MAX (__WG_CMD_MAX - 1) ++ ++enum wgdevice_flag { ++ WGDEVICE_F_REPLACE_PEERS = 1U << 0, ++ __WGDEVICE_F_ALL = WGDEVICE_F_REPLACE_PEERS ++}; ++enum wgdevice_attribute { ++ WGDEVICE_A_UNSPEC, ++ WGDEVICE_A_IFINDEX, ++ WGDEVICE_A_IFNAME, ++ WGDEVICE_A_PRIVATE_KEY, ++ WGDEVICE_A_PUBLIC_KEY, ++ WGDEVICE_A_FLAGS, ++ WGDEVICE_A_LISTEN_PORT, ++ WGDEVICE_A_FWMARK, ++ WGDEVICE_A_PEERS, ++ __WGDEVICE_A_LAST ++}; ++#define WGDEVICE_A_MAX (__WGDEVICE_A_LAST - 1) ++ ++enum wgpeer_flag { ++ WGPEER_F_REMOVE_ME = 1U << 0, ++ WGPEER_F_REPLACE_ALLOWEDIPS = 1U << 1, ++ WGPEER_F_UPDATE_ONLY = 1U << 2, ++ __WGPEER_F_ALL = WGPEER_F_REMOVE_ME | WGPEER_F_REPLACE_ALLOWEDIPS | ++ WGPEER_F_UPDATE_ONLY ++}; ++enum wgpeer_attribute { ++ WGPEER_A_UNSPEC, ++ WGPEER_A_PUBLIC_KEY, ++ WGPEER_A_PRESHARED_KEY, ++ WGPEER_A_FLAGS, ++ WGPEER_A_ENDPOINT, ++ WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, ++ WGPEER_A_LAST_HANDSHAKE_TIME, ++ WGPEER_A_RX_BYTES, ++ WGPEER_A_TX_BYTES, ++ WGPEER_A_ALLOWEDIPS, ++ WGPEER_A_PROTOCOL_VERSION, ++ __WGPEER_A_LAST ++}; ++#define WGPEER_A_MAX (__WGPEER_A_LAST - 1) ++ ++enum wgallowedip_attribute { ++ WGALLOWEDIP_A_UNSPEC, ++ WGALLOWEDIP_A_FAMILY, ++ WGALLOWEDIP_A_IPADDR, ++ WGALLOWEDIP_A_CIDR_MASK, ++ __WGALLOWEDIP_A_LAST ++}; ++#define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1) ++ ++#endif /* _WG_UAPI_WIREGUARD_H */ +--- /dev/null ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -0,0 +1,537 @@ ++#!/bin/bash ++# SPDX-License-Identifier: GPL-2.0 ++# ++# Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++# ++# This script tests the below topology: ++# ++# ┌─────────────────────┐ ┌──────────────────────────────────┐ ┌─────────────────────┐ ++# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ ++# │ │ │ │ │ │ ++# │┌────────┐ │ │ ┌────────┐ │ │ ┌────────┐│ ++# ││ wg0 │───────────┼───┼────────────│ lo │────────────┼───┼───────────│ wg0 ││ ++# │├────────┴──────────┐│ │ ┌───────┴────────┴────────┐ │ │┌──────────┴────────┤│ ++# ││192.168.241.1/24 ││ │ │(ns1) (ns2) │ │ ││192.168.241.2/24 ││ ++# ││fd00::1/24 ││ │ │127.0.0.1:1 127.0.0.1:2│ │ ││fd00::2/24 ││ ++# │└───────────────────┘│ │ │[::]:1 [::]:2 │ │ │└───────────────────┘│ ++# └─────────────────────┘ │ └─────────────────────────┘ │ └─────────────────────┘ ++# └──────────────────────────────────┘ ++# ++# After the topology is prepared we run a series of TCP/UDP iperf3 tests between the ++# wireguard peers in $ns1 and $ns2. Note that $ns0 is the endpoint for the wg0 ++# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further ++# details on how this is accomplished. ++set -e ++ ++exec 3>&1 ++export WG_HIDE_KEYS=never ++netns0="wg-test-$$-0" ++netns1="wg-test-$$-1" ++netns2="wg-test-$$-2" ++pretty() { echo -e "\x1b[32m\x1b[1m[+] ${1:+NS$1: }${2}\x1b[0m" >&3; } ++pp() { pretty "" "$*"; "$@"; } ++maybe_exec() { if [[ $BASHPID -eq $$ ]]; then "$@"; else exec "$@"; fi; } ++n0() { pretty 0 "$*"; maybe_exec ip netns exec $netns0 "$@"; } ++n1() { pretty 1 "$*"; maybe_exec ip netns exec $netns1 "$@"; } ++n2() { pretty 2 "$*"; maybe_exec ip netns exec $netns2 "$@"; } ++ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } ++ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } ++ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } ++sleep() { read -t "$1" -N 0 || true; } ++waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; } ++waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } ++waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } ++waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } ++ ++cleanup() { ++ set +e ++ exec 2>/dev/null ++ printf "$orig_message_cost" > /proc/sys/net/core/message_cost ++ ip0 link del dev wg0 ++ ip1 link del dev wg0 ++ ip2 link del dev wg0 ++ local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" ++ [[ -n $to_kill ]] && kill $to_kill ++ pp ip netns del $netns1 ++ pp ip netns del $netns2 ++ pp ip netns del $netns0 ++ exit ++} ++ ++orig_message_cost="$(< /proc/sys/net/core/message_cost)" ++trap cleanup EXIT ++printf 0 > /proc/sys/net/core/message_cost ++ ++ip netns del $netns0 2>/dev/null || true ++ip netns del $netns1 2>/dev/null || true ++ip netns del $netns2 2>/dev/null || true ++pp ip netns add $netns0 ++pp ip netns add $netns1 ++pp ip netns add $netns2 ++ip0 link set up dev lo ++ ++ip0 link add dev wg0 type wireguard ++ip0 link set wg0 netns $netns1 ++ip0 link add dev wg0 type wireguard ++ip0 link set wg0 netns $netns2 ++key1="$(pp wg genkey)" ++key2="$(pp wg genkey)" ++key3="$(pp wg genkey)" ++pub1="$(pp wg pubkey <<<"$key1")" ++pub2="$(pp wg pubkey <<<"$key2")" ++pub3="$(pp wg pubkey <<<"$key3")" ++psk="$(pp wg genpsk)" ++[[ -n $key1 && -n $key2 && -n $psk ]] ++ ++configure_peers() { ++ ip1 addr add 192.168.241.1/24 dev wg0 ++ ip1 addr add fd00::1/24 dev wg0 ++ ++ ip2 addr add 192.168.241.2/24 dev wg0 ++ ip2 addr add fd00::2/24 dev wg0 ++ ++ n1 wg set wg0 \ ++ private-key <(echo "$key1") \ ++ listen-port 1 \ ++ peer "$pub2" \ ++ preshared-key <(echo "$psk") \ ++ allowed-ips 192.168.241.2/32,fd00::2/128 ++ n2 wg set wg0 \ ++ private-key <(echo "$key2") \ ++ listen-port 2 \ ++ peer "$pub1" \ ++ preshared-key <(echo "$psk") \ ++ allowed-ips 192.168.241.1/32,fd00::1/128 ++ ++ ip1 link set up dev wg0 ++ ip2 link set up dev wg0 ++} ++configure_peers ++ ++tests() { ++ # Ping over IPv4 ++ n2 ping -c 10 -f -W 1 192.168.241.1 ++ n1 ping -c 10 -f -W 1 192.168.241.2 ++ ++ # Ping over IPv6 ++ n2 ping6 -c 10 -f -W 1 fd00::1 ++ n1 ping6 -c 10 -f -W 1 fd00::2 ++ ++ # TCP over IPv4 ++ n2 iperf3 -s -1 -B 192.168.241.2 & ++ waitiperf $netns2 ++ n1 iperf3 -Z -t 3 -c 192.168.241.2 ++ ++ # TCP over IPv6 ++ n1 iperf3 -s -1 -B fd00::1 & ++ waitiperf $netns1 ++ n2 iperf3 -Z -t 3 -c fd00::1 ++ ++ # UDP over IPv4 ++ n1 iperf3 -s -1 -B 192.168.241.1 & ++ waitiperf $netns1 ++ n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1 ++ ++ # UDP over IPv6 ++ n2 iperf3 -s -1 -B fd00::2 & ++ waitiperf $netns2 ++ n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 ++} ++ ++[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" ++big_mtu=$(( 34816 - 1500 + $orig_mtu )) ++ ++# Test using IPv4 as outer transport ++n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 ++n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 ++# Before calling tests, we first make sure that the stats counters and timestamper are working ++n2 ping -c 10 -f -W 1 192.168.241.1 ++{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip2 -stats link show dev wg0) ++(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) ++{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip1 -stats link show dev wg0) ++(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) ++read _ rx_bytes tx_bytes < <(n2 wg show wg0 transfer) ++(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) ++read _ rx_bytes tx_bytes < <(n1 wg show wg0 transfer) ++(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) ++read _ timestamp < <(n1 wg show wg0 latest-handshakes) ++(( timestamp != 0 )) ++ ++tests ++ip1 link set wg0 mtu $big_mtu ++ip2 link set wg0 mtu $big_mtu ++tests ++ ++ip1 link set wg0 mtu $orig_mtu ++ip2 link set wg0 mtu $orig_mtu ++ ++# Test using IPv6 as outer transport ++n1 wg set wg0 peer "$pub2" endpoint [::1]:2 ++n2 wg set wg0 peer "$pub1" endpoint [::1]:1 ++tests ++ip1 link set wg0 mtu $big_mtu ++ip2 link set wg0 mtu $big_mtu ++tests ++ ++# Test that route MTUs work with the padding ++ip1 link set wg0 mtu 1300 ++ip2 link set wg0 mtu 1300 ++n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 ++n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 ++n0 iptables -A INPUT -m length --length 1360 -j DROP ++n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 ++n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 ++n2 ping -c 1 -W 1 -s 1269 192.168.241.1 ++n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 ++n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 ++n0 iptables -F INPUT ++ ++ip1 link set wg0 mtu $orig_mtu ++ip2 link set wg0 mtu $orig_mtu ++ ++# Test using IPv4 that roaming works ++ip0 -4 addr del 127.0.0.1/8 dev lo ++ip0 -4 addr add 127.212.121.99/8 dev lo ++n1 wg set wg0 listen-port 9999 ++n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 ++n1 ping6 -W 1 -c 1 fd00::2 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 127.212.121.99:9999" ]] ++ ++# Test using IPv6 that roaming works ++n1 wg set wg0 listen-port 9998 ++n1 wg set wg0 peer "$pub2" endpoint [::1]:2 ++n1 ping -W 1 -c 1 192.168.241.2 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 [::1]:9998" ]] ++ ++# Test that crypto-RP filter works ++n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24 ++exec 4< <(n1 ncat -l -u -p 1111) ++ncat_pid=$! ++waitncatudp $netns1 ++n2 ncat -u 192.168.241.1 1111 <<<"X" ++read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]] ++kill $ncat_pid ++more_specific_key="$(pp wg genkey | pp wg pubkey)" ++n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32 ++n2 wg set wg0 listen-port 9997 ++exec 4< <(n1 ncat -l -u -p 1111) ++ncat_pid=$! ++waitncatudp $netns1 ++n2 ncat -u 192.168.241.1 1111 <<<"X" ++! read -r -N 1 -t 1 out <&4 || false ++kill $ncat_pid ++n1 wg set wg0 peer "$more_specific_key" remove ++[[ $(n1 wg show wg0 endpoints) == "$pub2 [::1]:9997" ]] ++ ++# Test that we can change private keys keys and immediately handshake ++n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips 192.168.241.2/32 endpoint 127.0.0.1:2 ++n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 ++n1 ping -W 1 -c 1 192.168.241.2 ++n1 wg set wg0 private-key <(echo "$key3") ++n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove ++n1 ping -W 1 -c 1 192.168.241.2 ++ ++ip1 link del wg0 ++ip2 link del wg0 ++ ++# Test using NAT. We now change the topology to this: ++# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ ++# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ ++# │ │ │ │ │ │ ++# │ ┌─────┐ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ ┌─────┐ │ ++# │ │ wg0 │─────────────│vethc│───────────┼────┼────│vethrc│ │vethrs│──────────────┼─────┼──│veths│────────────│ wg0 │ │ ++# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├──────┴─────────┐ ├──────┴────────────┐ │ │ ├─────┴──────────┐ ├─────┴──────────┐ │ ++# │ │192.168.241.1/24│ │192.168.1.100/24││ │ │192.168.1.1/24 │ │10.0.0.1/24 │ │ │ │10.0.0.100/24 │ │192.168.241.2/24│ │ ++# │ │fd00::1/24 │ │ ││ │ │ │ │SNAT:192.168.1.0/24│ │ │ │ │ │fd00::2/24 │ │ ++# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └───────────────────┘ │ │ └────────────────┘ └────────────────┘ │ ++# └────────────────────────────────────────┘ └────────────────────────────────────────────────┘ └────────────────────────────────────────┘ ++ ++ip1 link add dev wg0 type wireguard ++ip2 link add dev wg0 type wireguard ++configure_peers ++ ++ip0 link add vethrc type veth peer name vethc ++ip0 link add vethrs type veth peer name veths ++ip0 link set vethc netns $netns1 ++ip0 link set veths netns $netns2 ++ip0 link set vethrc up ++ip0 link set vethrs up ++ip0 addr add 192.168.1.1/24 dev vethrc ++ip0 addr add 10.0.0.1/24 dev vethrs ++ip1 addr add 192.168.1.100/24 dev vethc ++ip1 link set vethc up ++ip1 route add default via 192.168.1.1 ++ip2 addr add 10.0.0.100/24 dev veths ++ip2 link set veths up ++waitiface $netns0 vethrc ++waitiface $netns0 vethrs ++waitiface $netns1 vethc ++waitiface $netns2 veths ++ ++n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' ++n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' ++n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' ++n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 ++ ++n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 ++n1 ping -W 1 -c 1 192.168.241.2 ++n2 ping -W 1 -c 1 192.168.241.1 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] ++# Demonstrate n2 can still send packets to n1, since persistent-keepalive will prevent connection tracking entry from expiring (to see entries: `n0 conntrack -L`). ++pp sleep 3 ++n2 ping -W 1 -c 1 192.168.241.1 ++n1 wg set wg0 peer "$pub2" persistent-keepalive 0 ++ ++# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. ++ip1 -6 addr add fc00::9/96 dev vethc ++ip1 -6 route add default via fc00::1 ++ip2 -4 addr add 192.168.99.7/32 dev wg0 ++ip2 -6 addr add abab::1111/128 dev wg0 ++n1 wg set wg0 fwmark 51820 peer "$pub2" allowed-ips 192.168.99.7,abab::1111 ++ip1 -6 route add default dev wg0 table 51820 ++ip1 -6 rule add not fwmark 51820 table 51820 ++ip1 -6 rule add table main suppress_prefixlength 0 ++ip1 -4 route add default dev wg0 table 51820 ++ip1 -4 rule add not fwmark 51820 table 51820 ++ip1 -4 rule add table main suppress_prefixlength 0 ++# suppress_prefixlength only got added in 3.12, and we want to support 3.10+. ++if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then ++ # Flood the pings instead of sending just one, to trigger routing table reference counting bugs. ++ n1 ping -W 1 -c 100 -f 192.168.99.7 ++ n1 ping -W 1 -c 100 -f abab::1111 ++fi ++ ++n0 iptables -t nat -F ++ip0 link del vethrc ++ip0 link del vethrs ++ip1 link del wg0 ++ip2 link del wg0 ++ ++# Test that saddr routing is sticky but not too sticky, changing to this topology: ++# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────┐ ++# │ $ns1 namespace │ │ $ns2 namespace │ ++# │ │ │ │ ++# │ ┌─────┐ ┌─────┐ │ │ ┌─────┐ ┌─────┐ │ ++# │ │ wg0 │─────────────│veth1│───────────┼────┼──│veth2│────────────│ wg0 │ │ ++# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├─────┴──────────┐ ├─────┴──────────┐ │ ++# │ │192.168.241.1/24│ │10.0.0.1/24 ││ │ │10.0.0.2/24 │ │192.168.241.2/24│ │ ++# │ │fd00::1/24 │ │fd00:aa::1/96 ││ │ │fd00:aa::2/96 │ │fd00::2/24 │ │ ++# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └────────────────┘ │ ++# └────────────────────────────────────────┘ └────────────────────────────────────────┘ ++ ++ip1 link add dev wg0 type wireguard ++ip2 link add dev wg0 type wireguard ++configure_peers ++ip1 link add veth1 type veth peer name veth2 ++ip1 link set veth2 netns $netns2 ++n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' ++n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' ++n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth1/accept_dad' ++n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth2/accept_dad' ++n1 bash -c 'printf 1 > /proc/sys/net/ipv4/conf/veth1/promote_secondaries' ++ ++# First we check that we aren't overly sticky and can fall over to new IPs when old ones are removed ++ip1 addr add 10.0.0.1/24 dev veth1 ++ip1 addr add fd00:aa::1/96 dev veth1 ++ip2 addr add 10.0.0.2/24 dev veth2 ++ip2 addr add fd00:aa::2/96 dev veth2 ++ip1 link set veth1 up ++ip2 link set veth2 up ++waitiface $netns1 veth1 ++waitiface $netns2 veth2 ++n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 ++n1 ping -W 1 -c 1 192.168.241.2 ++ip1 addr add 10.0.0.10/24 dev veth1 ++ip1 addr del 10.0.0.1/24 dev veth1 ++n1 ping -W 1 -c 1 192.168.241.2 ++n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 ++n1 ping -W 1 -c 1 192.168.241.2 ++ip1 addr add fd00:aa::10/96 dev veth1 ++ip1 addr del fd00:aa::1/96 dev veth1 ++n1 ping -W 1 -c 1 192.168.241.2 ++ ++# Now we show that we can successfully do reply to sender routing ++ip1 link set veth1 down ++ip2 link set veth2 down ++ip1 addr flush dev veth1 ++ip2 addr flush dev veth2 ++ip1 addr add 10.0.0.1/24 dev veth1 ++ip1 addr add 10.0.0.2/24 dev veth1 ++ip1 addr add fd00:aa::1/96 dev veth1 ++ip1 addr add fd00:aa::2/96 dev veth1 ++ip2 addr add 10.0.0.3/24 dev veth2 ++ip2 addr add fd00:aa::3/96 dev veth2 ++ip1 link set veth1 up ++ip2 link set veth2 up ++waitiface $netns1 veth1 ++waitiface $netns2 veth2 ++n2 wg set wg0 peer "$pub1" endpoint 10.0.0.1:1 ++n2 ping -W 1 -c 1 192.168.241.1 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] ++n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 ++n2 ping -W 1 -c 1 192.168.241.1 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::1]:1" ]] ++n2 wg set wg0 peer "$pub1" endpoint 10.0.0.2:1 ++n2 ping -W 1 -c 1 192.168.241.1 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.2:1" ]] ++n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::2]:1 ++n2 ping -W 1 -c 1 192.168.241.1 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::2]:1" ]] ++ ++# What happens if the inbound destination address belongs to a different interface as the default route? ++ip1 link add dummy0 type dummy ++ip1 addr add 10.50.0.1/24 dev dummy0 ++ip1 link set dummy0 up ++ip2 route add 10.50.0.0/24 dev veth2 ++n2 wg set wg0 peer "$pub1" endpoint 10.50.0.1:1 ++n2 ping -W 1 -c 1 192.168.241.1 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.50.0.1:1" ]] ++ ++ip1 link del dummy0 ++ip1 addr flush dev veth1 ++ip2 addr flush dev veth2 ++ip1 route flush dev veth1 ++ip2 route flush dev veth2 ++ ++# Now we see what happens if another interface route takes precedence over an ongoing one ++ip1 link add veth3 type veth peer name veth4 ++ip1 link set veth4 netns $netns2 ++ip1 addr add 10.0.0.1/24 dev veth1 ++ip2 addr add 10.0.0.2/24 dev veth2 ++ip1 addr add 10.0.0.3/24 dev veth3 ++ip1 link set veth1 up ++ip2 link set veth2 up ++ip1 link set veth3 up ++ip2 link set veth4 up ++waitiface $netns1 veth1 ++waitiface $netns2 veth2 ++waitiface $netns1 veth3 ++waitiface $netns2 veth4 ++ip1 route flush dev veth1 ++ip1 route flush dev veth3 ++ip1 route add 10.0.0.0/24 dev veth1 src 10.0.0.1 metric 2 ++n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 ++n1 ping -W 1 -c 1 192.168.241.2 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] ++ip1 route add 10.0.0.0/24 dev veth3 src 10.0.0.3 metric 1 ++n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth1/rp_filter' ++n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth4/rp_filter' ++n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' ++n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' ++n1 ping -W 1 -c 1 192.168.241.2 ++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] ++ ++ip1 link del veth1 ++ip1 link del veth3 ++ip1 link del wg0 ++ip2 link del wg0 ++ ++# We test that Netlink/IPC is working properly by doing things that usually cause split responses ++ip0 link add dev wg0 type wireguard ++config=( "[Interface]" "PrivateKey=$(wg genkey)" "[Peer]" "PublicKey=$(wg genkey)" ) ++for a in {1..255}; do ++ for b in {0..255}; do ++ config+=( "AllowedIPs=$a.$b.0.0/16,$a::$b/128" ) ++ done ++done ++n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") ++i=0 ++for ip in $(n0 wg show wg0 allowed-ips); do ++ ((++i)) ++done ++((i == 255*256*2+1)) ++ip0 link del wg0 ++ip0 link add dev wg0 type wireguard ++config=( "[Interface]" "PrivateKey=$(wg genkey)" ) ++for a in {1..40}; do ++ config+=( "[Peer]" "PublicKey=$(wg genkey)" ) ++ for b in {1..52}; do ++ config+=( "AllowedIPs=$a.$b.0.0/16" ) ++ done ++done ++n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") ++i=0 ++while read -r line; do ++ j=0 ++ for ip in $line; do ++ ((++j)) ++ done ++ ((j == 53)) ++ ((++i)) ++done < <(n0 wg show wg0 allowed-ips) ++((i == 40)) ++ip0 link del wg0 ++ip0 link add wg0 type wireguard ++config=( ) ++for i in {1..29}; do ++ config+=( "[Peer]" "PublicKey=$(wg genkey)" ) ++done ++config+=( "[Peer]" "PublicKey=$(wg genkey)" "AllowedIPs=255.2.3.4/32,abcd::255/128" ) ++n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") ++n0 wg showconf wg0 > /dev/null ++ip0 link del wg0 ++ ++allowedips=( ) ++for i in {1..197}; do ++ allowedips+=( abcd::$i ) ++done ++saved_ifs="$IFS" ++IFS=, ++allowedips="${allowedips[*]}" ++IFS="$saved_ifs" ++ip0 link add wg0 type wireguard ++n0 wg set wg0 peer "$pub1" ++n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips" ++{ ++ read -r pub allowedips ++ [[ $pub == "$pub1" && $allowedips == "(none)" ]] ++ read -r pub allowedips ++ [[ $pub == "$pub2" ]] ++ i=0 ++ for _ in $allowedips; do ++ ((++i)) ++ done ++ ((i == 197)) ++} < <(n0 wg show wg0 allowed-ips) ++ip0 link del wg0 ++ ++! n0 wg show doesnotexist || false ++ ++ip0 link add wg0 type wireguard ++n0 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") ++[[ $(n0 wg show wg0 private-key) == "$key1" ]] ++[[ $(n0 wg show wg0 preshared-keys) == "$pub2 $psk" ]] ++n0 wg set wg0 private-key /dev/null peer "$pub2" preshared-key /dev/null ++[[ $(n0 wg show wg0 private-key) == "(none)" ]] ++[[ $(n0 wg show wg0 preshared-keys) == "$pub2 (none)" ]] ++n0 wg set wg0 peer "$pub2" ++n0 wg set wg0 private-key <(echo "$key2") ++[[ $(n0 wg show wg0 public-key) == "$pub2" ]] ++[[ -z $(n0 wg show wg0 peers) ]] ++n0 wg set wg0 peer "$pub2" ++[[ -z $(n0 wg show wg0 peers) ]] ++n0 wg set wg0 private-key <(echo "$key1") ++n0 wg set wg0 peer "$pub2" ++[[ $(n0 wg show wg0 peers) == "$pub2" ]] ++n0 wg set wg0 private-key <(echo "/${key1:1}") ++[[ $(n0 wg show wg0 private-key) == "+${key1:1}" ]] ++n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16.0.0/12,192.168.0.0/16 ++n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0 ++n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 ++n0 wg set wg0 peer "$pub2" allowed-ips ::/0 ++ip0 link del wg0 ++ ++declare -A objects ++while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do ++ [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue ++ objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}" ++done < /dev/kmsg ++alldeleted=1 ++for object in "${!objects[@]}"; do ++ if [[ ${objects["$object"]} != *createddestroyed ]]; then ++ echo "Error: $object: merely ${objects["$object"]}" >&3 ++ alldeleted=0 ++ fi ++done ++[[ $alldeleted -eq 1 ]] ++pretty "" "Objects that were created were also destroyed." diff --git a/target/linux/generic/backport-5.4/080-wireguard-0074-wireguard-selftests-import-harness-makefile-for-test.patch b/target/linux/generic/backport-5.4/080-wireguard-0074-wireguard-selftests-import-harness-makefile-for-test.patch new file mode 100644 index 0000000000..60ecebf50a --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0074-wireguard-selftests-import-harness-makefile-for-test.patch @@ -0,0 +1,1079 @@ +From e333013ee167444adefd8a292e401b70e97dd4b2 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 15 Dec 2019 22:08:00 +0100 +Subject: [PATCH 074/124] wireguard: selftests: import harness makefile for + test suite + +commit 65d88d04114bca7d85faebd5fed61069cb2b632c upstream. + +WireGuard has been using this on build.wireguard.com for the last +several years with considerable success. It allows for very quick and +iterative development cycles, and supports several platforms. + +To run the test suite on your current platform in QEMU: + + $ make -C tools/testing/selftests/wireguard/qemu -j$(nproc) + +To run it with KASAN and such turned on: + + $ DEBUG_KERNEL=yes make -C tools/testing/selftests/wireguard/qemu -j$(nproc) + +To run it emulated for another platform in QEMU: + + $ ARCH=arm make -C tools/testing/selftests/wireguard/qemu -j$(nproc) + +At the moment, we support aarch64_be, aarch64, arm, armeb, i686, m68k, +mips64, mips64el, mips, mipsel, powerpc64le, powerpc, and x86_64. + +The system supports incremental rebuilding, so it should be very fast to +change a single file and then test it out and have immediate feedback. + +This requires for the right toolchain and qemu to be installed prior. +I've had success with those from musl.cc. + +This is tailored for WireGuard at the moment, though later projects +might generalize it for other network testing. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + .../selftests/wireguard/qemu/.gitignore | 2 + + .../testing/selftests/wireguard/qemu/Makefile | 385 ++++++++++++++++++ + .../wireguard/qemu/arch/aarch64.config | 5 + + .../wireguard/qemu/arch/aarch64_be.config | 6 + + .../selftests/wireguard/qemu/arch/arm.config | 9 + + .../wireguard/qemu/arch/armeb.config | 10 + + .../selftests/wireguard/qemu/arch/i686.config | 5 + + .../selftests/wireguard/qemu/arch/m68k.config | 9 + + .../selftests/wireguard/qemu/arch/mips.config | 11 + + .../wireguard/qemu/arch/mips64.config | 14 + + .../wireguard/qemu/arch/mips64el.config | 15 + + .../wireguard/qemu/arch/mipsel.config | 12 + + .../wireguard/qemu/arch/powerpc.config | 10 + + .../wireguard/qemu/arch/powerpc64le.config | 12 + + .../wireguard/qemu/arch/x86_64.config | 5 + + .../selftests/wireguard/qemu/debug.config | 67 +++ + tools/testing/selftests/wireguard/qemu/init.c | 284 +++++++++++++ + .../selftests/wireguard/qemu/kernel.config | 86 ++++ + 18 files changed, 947 insertions(+) + create mode 100644 tools/testing/selftests/wireguard/qemu/.gitignore + create mode 100644 tools/testing/selftests/wireguard/qemu/Makefile + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/aarch64.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/arm.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/armeb.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/i686.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/m68k.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips64.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips64el.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mipsel.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config + create mode 100644 tools/testing/selftests/wireguard/qemu/arch/x86_64.config + create mode 100644 tools/testing/selftests/wireguard/qemu/debug.config + create mode 100644 tools/testing/selftests/wireguard/qemu/init.c + create mode 100644 tools/testing/selftests/wireguard/qemu/kernel.config + +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/.gitignore +@@ -0,0 +1,2 @@ ++build/ ++distfiles/ +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/Makefile +@@ -0,0 +1,385 @@ ++# SPDX-License-Identifier: GPL-2.0 ++# ++# Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ ++PWD := $(shell pwd) ++ ++CHOST := $(shell gcc -dumpmachine) ++ifneq (,$(ARCH)) ++CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) ++ifeq (,$(CBUILD)) ++$(error The toolchain for $(ARCH) is not installed) ++endif ++else ++CBUILD := $(CHOST) ++ARCH := $(firstword $(subst -, ,$(CBUILD))) ++endif ++ ++# Set these from the environment to override ++KERNEL_PATH ?= $(PWD)/../../../../.. ++BUILD_PATH ?= $(PWD)/build/$(ARCH) ++DISTFILES_PATH ?= $(PWD)/distfiles ++NR_CPUS ?= 4 ++ ++MIRROR := https://download.wireguard.com/qemu-test/distfiles/ ++ ++default: qemu ++ ++# variable name, tarball project name, version, tarball extension, default URI base ++define tar_download = ++$(1)_VERSION := $(3) ++$(1)_NAME := $(2)-$$($(1)_VERSION) ++$(1)_TAR := $(DISTFILES_PATH)/$$($(1)_NAME)$(4) ++$(1)_PATH := $(BUILD_PATH)/$$($(1)_NAME) ++$(call file_download,$$($(1)_NAME)$(4),$(5),$(6)) ++endef ++ ++define file_download = ++$(DISTFILES_PATH)/$(1): ++ mkdir -p $(DISTFILES_PATH) ++ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' ++ if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi ++endef ++ ++$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61)) ++$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) ++$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f)) ++$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) ++$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2)) ++$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5)) ++$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21)) ++$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a)) ++$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071)) ++ ++KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) ++rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) ++WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) ++ ++export CFLAGS ?= -O3 -pipe ++export LDFLAGS ?= ++export CPPFLAGS := -I$(BUILD_PATH)/include ++ ++ifeq ($(CHOST),$(CBUILD)) ++CROSS_COMPILE_FLAG := --host=$(CHOST) ++NOPIE_GCC := gcc -fno-PIE ++CFLAGS += -march=native ++STRIP := strip ++else ++$(info Cross compilation: building for $(CBUILD) using $(CHOST)) ++CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) ++export CROSS_COMPILE=$(CBUILD)- ++NOPIE_GCC := $(CBUILD)-gcc -fno-PIE ++STRIP := $(CBUILD)-strip ++endif ++ifeq ($(ARCH),aarch64) ++QEMU_ARCH := aarch64 ++KERNEL_ARCH := arm64 ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm ++else ++QEMU_MACHINE := -cpu cortex-a53 -machine virt ++CFLAGS += -march=armv8-a -mtune=cortex-a53 ++endif ++else ifeq ($(ARCH),aarch64_be) ++QEMU_ARCH := aarch64 ++KERNEL_ARCH := arm64 ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm ++else ++QEMU_MACHINE := -cpu cortex-a53 -machine virt ++CFLAGS += -march=armv8-a -mtune=cortex-a53 ++endif ++else ifeq ($(ARCH),arm) ++QEMU_ARCH := arm ++KERNEL_ARCH := arm ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm ++else ++QEMU_MACHINE := -cpu cortex-a15 -machine virt ++CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux ++endif ++else ifeq ($(ARCH),armeb) ++QEMU_ARCH := arm ++KERNEL_ARCH := arm ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm ++else ++QEMU_MACHINE := -cpu cortex-a15 -machine virt ++CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian. ++LDFLAGS += -Wl,--be8 ++endif ++else ifeq ($(ARCH),x86_64) ++QEMU_ARCH := x86_64 ++KERNEL_ARCH := x86_64 ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine q35,accel=kvm ++else ++QEMU_MACHINE := -cpu Skylake-Server -machine q35 ++CFLAGS += -march=skylake-avx512 ++endif ++else ifeq ($(ARCH),i686) ++QEMU_ARCH := i386 ++KERNEL_ARCH := x86 ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage ++ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST)) ++QEMU_MACHINE := -cpu host -machine q35,accel=kvm ++else ++QEMU_MACHINE := -cpu coreduo -machine q35 ++CFLAGS += -march=prescott ++endif ++else ifeq ($(ARCH),mips64) ++QEMU_ARCH := mips64 ++KERNEL_ARCH := mips ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine malta,accel=kvm ++CFLAGS += -EB ++else ++QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 ++CFLAGS += -march=mips64r2 -EB ++endif ++else ifeq ($(ARCH),mips64el) ++QEMU_ARCH := mips64el ++KERNEL_ARCH := mips ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine malta,accel=kvm ++CFLAGS += -EL ++else ++QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 ++CFLAGS += -march=mips64r2 -EL ++endif ++else ifeq ($(ARCH),mips) ++QEMU_ARCH := mips ++KERNEL_ARCH := mips ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine malta,accel=kvm ++CFLAGS += -EB ++else ++QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 ++CFLAGS += -march=mips32r2 -EB ++endif ++else ifeq ($(ARCH),mipsel) ++QEMU_ARCH := mipsel ++KERNEL_ARCH := mips ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host -machine malta,accel=kvm ++CFLAGS += -EL ++else ++QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 ++CFLAGS += -march=mips32r2 -EL ++endif ++else ifeq ($(ARCH),powerpc64le) ++QEMU_ARCH := ppc64 ++KERNEL_ARCH := powerpc ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host,accel=kvm -machine pseries ++else ++QEMU_MACHINE := -machine pseries ++endif ++CFLAGS += -mcpu=powerpc64le -mlong-double-64 ++else ifeq ($(ARCH),powerpc) ++QEMU_ARCH := ppc ++KERNEL_ARCH := powerpc ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 ++else ++QEMU_MACHINE := -machine ppce500 ++endif ++CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt ++else ifeq ($(ARCH),m68k) ++QEMU_ARCH := m68k ++KERNEL_ARCH := m68k ++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux ++ifeq ($(CHOST),$(CBUILD)) ++QEMU_MACHINE := -cpu host,accel=kvm -machine q800 ++else ++QEMU_MACHINE := -machine q800 ++endif ++else ++$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) ++endif ++ ++REAL_CC := $(CBUILD)-gcc ++MUSL_CC := $(BUILD_PATH)/musl-gcc ++export CC := $(MUSL_CC) ++USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed ++ ++build: $(KERNEL_BZIMAGE) ++qemu: $(KERNEL_BZIMAGE) ++ rm -f $(BUILD_PATH)/result ++ timeout --foreground 20m qemu-system-$(QEMU_ARCH) \ ++ -nodefaults \ ++ -nographic \ ++ -smp $(NR_CPUS) \ ++ $(QEMU_MACHINE) \ ++ -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \ ++ -serial stdio \ ++ -serial file:$(BUILD_PATH)/result \ ++ -no-reboot \ ++ -monitor none \ ++ -kernel $< ++ grep -Fq success $(BUILD_PATH)/result ++ ++$(BUILD_PATH)/init-cpio-spec.txt: ++ mkdir -p $(BUILD_PATH) ++ echo "file /init $(BUILD_PATH)/init 755 0 0" > $@ ++ echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@ ++ echo "dir /dev 755 0 0" >> $@ ++ echo "nod /dev/console 644 0 0 c 5 1" >> $@ ++ echo "dir /bin 755 0 0" >> $@ ++ echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@ ++ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@ ++ echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@ ++ echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@ ++ echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@ ++ echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@ ++ echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@ ++ echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@ ++ echo "slink /bin/iptables xtables-multi 777 0 0" >> $@ ++ echo "slink /bin/ping6 ping 777 0 0" >> $@ ++ echo "dir /lib 755 0 0" >> $@ ++ echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ ++ echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@ ++ ++$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config ++ mkdir -p $(KERNEL_BUILD_PATH) ++ cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config ++ printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config ++ cat arch/$(ARCH).config >> $(KERNEL_BUILD_PATH)/minimal.config ++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) allnoconfig ++ cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config ++ $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) ++ ++$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) ++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" ++ ++$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config ++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install ++ touch $@ ++ ++$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD) ++ $(MAKE) -C $(MUSL_PATH) ++ $(STRIP) -s $@ ++ ++$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so ++ $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers ++ touch $@ ++ ++$(MUSL_CC): $(MUSL_PATH)/lib/libc.so ++ sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs ++ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc ++ chmod +x $(BUILD_PATH)/musl-gcc ++ ++$(IPERF_PATH)/.installed: $(IPERF_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ sed -i '1s/^/#include /' $(IPERF_PATH)/src/cjson.h $(IPERF_PATH)/src/timer.h ++ sed -i -r 's/-p?g//g' $(IPERF_PATH)/src/Makefile* ++ touch $@ ++ ++$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) ++ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared ++ $(MAKE) -C $(IPERF_PATH) ++ $(STRIP) -s $@ ++ ++$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ touch $@ ++ ++$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) ++ cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared ++ $(MAKE) -C $(LIBMNL_PATH) ++ sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc ++ ++$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ touch $@ ++ ++$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) ++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg ++ $(STRIP) -s $@ ++ ++$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) ++ mkdir -p $(BUILD_PATH) ++ $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< ++ $(STRIP) -s $@ ++ ++$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ touch $@ ++ ++$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS) ++ $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping ++ $(STRIP) -s $@ ++ ++$(BASH_PATH)/.installed: $(BASH_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ touch $@ ++ ++$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) ++ cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble ++ $(MAKE) -C $(BASH_PATH) ++ $(STRIP) -s $@ ++ ++$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk ++ printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile ++ touch $@ ++ ++$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) ++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip ++ $(STRIP) -s $(IPROUTE2_PATH)/ip/ip ++ ++$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) ++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss ++ $(STRIP) -s $(IPROUTE2_PATH)/misc/ss ++ ++$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure ++ touch $@ ++ ++$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) ++ cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include ++ $(MAKE) -C $(IPTABLES_PATH) ++ $(STRIP) -s $@ ++ ++$(NMAP_PATH)/.installed: $(NMAP_TAR) ++ mkdir -p $(BUILD_PATH) ++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $< ++ touch $@ ++ ++$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS) ++ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux ++ $(MAKE) -C $(NMAP_PATH) build-ncat ++ $(STRIP) -s $@ ++ ++clean: ++ rm -rf $(BUILD_PATH) ++ ++distclean: clean ++ rm -rf $(DISTFILES_PATH) ++ ++menuconfig: $(KERNEL_BUILD_PATH)/.config ++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig ++ ++.PHONY: qemu build clean distclean menuconfig ++.DELETE_ON_ERROR: +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config +@@ -0,0 +1,5 @@ ++CONFIG_SERIAL_AMBA_PL011=y ++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" ++CONFIG_FRAME_WARN=1280 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config +@@ -0,0 +1,6 @@ ++CONFIG_CPU_BIG_ENDIAN=y ++CONFIG_SERIAL_AMBA_PL011=y ++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" ++CONFIG_FRAME_WARN=1280 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config +@@ -0,0 +1,9 @@ ++CONFIG_MMU=y ++CONFIG_ARCH_MULTI_V7=y ++CONFIG_ARCH_VIRT=y ++CONFIG_THUMB2_KERNEL=n ++CONFIG_SERIAL_AMBA_PL011=y ++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config +@@ -0,0 +1,10 @@ ++CONFIG_MMU=y ++CONFIG_ARCH_MULTI_V7=y ++CONFIG_ARCH_VIRT=y ++CONFIG_THUMB2_KERNEL=n ++CONFIG_SERIAL_AMBA_PL011=y ++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" ++CONFIG_CPU_BIG_ENDIAN=y ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config +@@ -0,0 +1,5 @@ ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config +@@ -0,0 +1,9 @@ ++CONFIG_MMU=y ++CONFIG_M68040=y ++CONFIG_MAC=y ++CONFIG_SERIAL_PMACZILOG=y ++CONFIG_SERIAL_PMACZILOG_TTYS=y ++CONFIG_SERIAL_PMACZILOG_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config +@@ -0,0 +1,11 @@ ++CONFIG_CPU_MIPS32_R2=y ++CONFIG_MIPS_MALTA=y ++CONFIG_MIPS_CPS=y ++CONFIG_MIPS_FP_SUPPORT=y ++CONFIG_POWER_RESET=y ++CONFIG_POWER_RESET_SYSCON=y ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config +@@ -0,0 +1,14 @@ ++CONFIG_64BIT=y ++CONFIG_CPU_MIPS64_R2=y ++CONFIG_MIPS32_N32=y ++CONFIG_CPU_HAS_MSA=y ++CONFIG_MIPS_MALTA=y ++CONFIG_MIPS_CPS=y ++CONFIG_MIPS_FP_SUPPORT=y ++CONFIG_POWER_RESET=y ++CONFIG_POWER_RESET_SYSCON=y ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1280 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config +@@ -0,0 +1,15 @@ ++CONFIG_64BIT=y ++CONFIG_CPU_MIPS64_R2=y ++CONFIG_MIPS32_N32=y ++CONFIG_CPU_HAS_MSA=y ++CONFIG_MIPS_MALTA=y ++CONFIG_CPU_LITTLE_ENDIAN=y ++CONFIG_MIPS_CPS=y ++CONFIG_MIPS_FP_SUPPORT=y ++CONFIG_POWER_RESET=y ++CONFIG_POWER_RESET_SYSCON=y ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1280 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config +@@ -0,0 +1,12 @@ ++CONFIG_CPU_MIPS32_R2=y ++CONFIG_MIPS_MALTA=y ++CONFIG_CPU_LITTLE_ENDIAN=y ++CONFIG_MIPS_CPS=y ++CONFIG_MIPS_FP_SUPPORT=y ++CONFIG_POWER_RESET=y ++CONFIG_POWER_RESET_SYSCON=y ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config +@@ -0,0 +1,10 @@ ++CONFIG_PPC_QEMU_E500=y ++CONFIG_FSL_SOC_BOOKE=y ++CONFIG_PPC_85xx=y ++CONFIG_PHYS_64BIT=y ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_MATH_EMULATION=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1024 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +@@ -0,0 +1,12 @@ ++CONFIG_PPC64=y ++CONFIG_PPC_PSERIES=y ++CONFIG_ALTIVEC=y ++CONFIG_VSX=y ++CONFIG_PPC_OF_BOOT_TRAMPOLINE=y ++CONFIG_PPC_RADIX_MMU=y ++CONFIG_HVC_CONSOLE=y ++CONFIG_CPU_LITTLE_ENDIAN=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" ++CONFIG_SECTION_MISMATCH_WARN_ONLY=y ++CONFIG_FRAME_WARN=1280 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config +@@ -0,0 +1,5 @@ ++CONFIG_SERIAL_8250=y ++CONFIG_SERIAL_8250_CONSOLE=y ++CONFIG_CMDLINE_BOOL=y ++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" ++CONFIG_FRAME_WARN=1280 +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/debug.config +@@ -0,0 +1,67 @@ ++CONFIG_LOCALVERSION="-debug" ++CONFIG_ENABLE_WARN_DEPRECATED=y ++CONFIG_ENABLE_MUST_CHECK=y ++CONFIG_FRAME_POINTER=y ++CONFIG_STACK_VALIDATION=y ++CONFIG_DEBUG_KERNEL=y ++CONFIG_DEBUG_INFO=y ++CONFIG_DEBUG_INFO_DWARF4=y ++CONFIG_PAGE_EXTENSION=y ++CONFIG_PAGE_POISONING=y ++CONFIG_DEBUG_OBJECTS=y ++CONFIG_DEBUG_OBJECTS_FREE=y ++CONFIG_DEBUG_OBJECTS_TIMERS=y ++CONFIG_DEBUG_OBJECTS_WORK=y ++CONFIG_DEBUG_OBJECTS_RCU_HEAD=y ++CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y ++CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 ++CONFIG_SLUB_DEBUG_ON=y ++CONFIG_DEBUG_VM=y ++CONFIG_DEBUG_MEMORY_INIT=y ++CONFIG_HAVE_DEBUG_STACKOVERFLOW=y ++CONFIG_DEBUG_STACKOVERFLOW=y ++CONFIG_HAVE_ARCH_KMEMCHECK=y ++CONFIG_HAVE_ARCH_KASAN=y ++CONFIG_KASAN=y ++CONFIG_KASAN_INLINE=y ++CONFIG_UBSAN=y ++CONFIG_UBSAN_SANITIZE_ALL=y ++CONFIG_UBSAN_NO_ALIGNMENT=y ++CONFIG_UBSAN_NULL=y ++CONFIG_DEBUG_KMEMLEAK=y ++CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 ++CONFIG_DEBUG_STACK_USAGE=y ++CONFIG_DEBUG_SHIRQ=y ++CONFIG_WQ_WATCHDOG=y ++CONFIG_SCHED_DEBUG=y ++CONFIG_SCHED_INFO=y ++CONFIG_SCHEDSTATS=y ++CONFIG_SCHED_STACK_END_CHECK=y ++CONFIG_DEBUG_TIMEKEEPING=y ++CONFIG_TIMER_STATS=y ++CONFIG_DEBUG_PREEMPT=y ++CONFIG_DEBUG_RT_MUTEXES=y ++CONFIG_DEBUG_SPINLOCK=y ++CONFIG_DEBUG_MUTEXES=y ++CONFIG_DEBUG_LOCK_ALLOC=y ++CONFIG_PROVE_LOCKING=y ++CONFIG_LOCKDEP=y ++CONFIG_DEBUG_ATOMIC_SLEEP=y ++CONFIG_TRACE_IRQFLAGS=y ++CONFIG_DEBUG_BUGVERBOSE=y ++CONFIG_DEBUG_LIST=y ++CONFIG_DEBUG_PI_LIST=y ++CONFIG_PROVE_RCU=y ++CONFIG_SPARSE_RCU_POINTER=y ++CONFIG_RCU_CPU_STALL_TIMEOUT=21 ++CONFIG_RCU_TRACE=y ++CONFIG_RCU_EQS_DEBUG=y ++CONFIG_USER_STACKTRACE_SUPPORT=y ++CONFIG_DEBUG_SG=y ++CONFIG_DEBUG_NOTIFIERS=y ++CONFIG_DOUBLEFAULT=y ++CONFIG_X86_DEBUG_FPU=y ++CONFIG_DEBUG_SECTION_MISMATCH=y ++CONFIG_DEBUG_PAGEALLOC=y ++CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT=y ++CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/init.c +@@ -0,0 +1,284 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. ++ */ ++ ++#define _GNU_SOURCE ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++__attribute__((noreturn)) static void poweroff(void) ++{ ++ fflush(stdout); ++ fflush(stderr); ++ reboot(RB_AUTOBOOT); ++ sleep(30); ++ fprintf(stderr, "\x1b[37m\x1b[41m\x1b[1mFailed to power off!!!\x1b[0m\n"); ++ exit(1); ++} ++ ++static void panic(const char *what) ++{ ++ fprintf(stderr, "\n\n\x1b[37m\x1b[41m\x1b[1mSOMETHING WENT HORRIBLY WRONG\x1b[0m\n\n \x1b[31m\x1b[1m%s: %s\x1b[0m\n\n\x1b[37m\x1b[44m\x1b[1mPower off...\x1b[0m\n\n", what, strerror(errno)); ++ poweroff(); ++} ++ ++#define pretty_message(msg) puts("\x1b[32m\x1b[1m" msg "\x1b[0m") ++ ++static void print_banner(void) ++{ ++ struct utsname utsname; ++ int len; ++ ++ if (uname(&utsname) < 0) ++ panic("uname"); ++ ++ len = strlen(" WireGuard Test Suite on ") + strlen(utsname.sysname) + strlen(utsname.release) + strlen(utsname.machine); ++ printf("\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\x1b[45m\x1b[33m\x1b[1m WireGuard Test Suite on %s %s %s \x1b[0m\n\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\n", len, "", utsname.sysname, utsname.release, utsname.machine, len, ""); ++} ++ ++static void seed_rng(void) ++{ ++ int fd; ++ struct { ++ int entropy_count; ++ int buffer_size; ++ unsigned char buffer[256]; ++ } entropy = { ++ .entropy_count = sizeof(entropy.buffer) * 8, ++ .buffer_size = sizeof(entropy.buffer), ++ .buffer = "Adding real entropy is not actually important for these tests. Don't try this at home, kids!" ++ }; ++ ++ if (mknod("/dev/urandom", S_IFCHR | 0644, makedev(1, 9))) ++ panic("mknod(/dev/urandom)"); ++ fd = open("/dev/urandom", O_WRONLY); ++ if (fd < 0) ++ panic("open(urandom)"); ++ for (int i = 0; i < 256; ++i) { ++ if (ioctl(fd, RNDADDENTROPY, &entropy) < 0) ++ panic("ioctl(urandom)"); ++ } ++ close(fd); ++} ++ ++static void mount_filesystems(void) ++{ ++ pretty_message("[+] Mounting filesystems..."); ++ mkdir("/dev", 0755); ++ mkdir("/proc", 0755); ++ mkdir("/sys", 0755); ++ mkdir("/tmp", 0755); ++ mkdir("/run", 0755); ++ mkdir("/var", 0755); ++ if (mount("none", "/dev", "devtmpfs", 0, NULL)) ++ panic("devtmpfs mount"); ++ if (mount("none", "/proc", "proc", 0, NULL)) ++ panic("procfs mount"); ++ if (mount("none", "/sys", "sysfs", 0, NULL)) ++ panic("sysfs mount"); ++ if (mount("none", "/tmp", "tmpfs", 0, NULL)) ++ panic("tmpfs mount"); ++ if (mount("none", "/run", "tmpfs", 0, NULL)) ++ panic("tmpfs mount"); ++ if (mount("none", "/sys/kernel/debug", "debugfs", 0, NULL)) ++ ; /* Not a problem if it fails.*/ ++ if (symlink("/run", "/var/run")) ++ panic("run symlink"); ++ if (symlink("/proc/self/fd", "/dev/fd")) ++ panic("fd symlink"); ++} ++ ++static void enable_logging(void) ++{ ++ int fd; ++ pretty_message("[+] Enabling logging..."); ++ fd = open("/proc/sys/kernel/printk", O_WRONLY); ++ if (fd >= 0) { ++ if (write(fd, "9\n", 2) != 2) ++ panic("write(printk)"); ++ close(fd); ++ } ++ fd = open("/proc/sys/debug/exception-trace", O_WRONLY); ++ if (fd >= 0) { ++ if (write(fd, "1\n", 2) != 2) ++ panic("write(exception-trace)"); ++ close(fd); ++ } ++ fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY); ++ if (fd >= 0) { ++ if (write(fd, "1\n", 2) != 2) ++ panic("write(panic_on_warn)"); ++ close(fd); ++ } ++} ++ ++static void kmod_selftests(void) ++{ ++ FILE *file; ++ char line[2048], *start, *pass; ++ bool success = true; ++ pretty_message("[+] Module self-tests:"); ++ file = fopen("/proc/kmsg", "r"); ++ if (!file) ++ panic("fopen(kmsg)"); ++ if (fcntl(fileno(file), F_SETFL, O_NONBLOCK) < 0) ++ panic("fcntl(kmsg, nonblock)"); ++ while (fgets(line, sizeof(line), file)) { ++ start = strstr(line, "wireguard: "); ++ if (!start) ++ continue; ++ start += 11; ++ *strchrnul(start, '\n') = '\0'; ++ if (strstr(start, "www.wireguard.com")) ++ break; ++ pass = strstr(start, ": pass"); ++ if (!pass || pass[6] != '\0') { ++ success = false; ++ printf(" \x1b[31m* %s\x1b[0m\n", start); ++ } else ++ printf(" \x1b[32m* %s\x1b[0m\n", start); ++ } ++ fclose(file); ++ if (!success) { ++ puts("\x1b[31m\x1b[1m[-] Tests failed! \u2639\x1b[0m"); ++ poweroff(); ++ } ++} ++ ++static void launch_tests(void) ++{ ++ char cmdline[4096], *success_dev; ++ int status, fd; ++ pid_t pid; ++ ++ pretty_message("[+] Launching tests..."); ++ pid = fork(); ++ if (pid == -1) ++ panic("fork"); ++ else if (pid == 0) { ++ execl("/init.sh", "init", NULL); ++ panic("exec"); ++ } ++ if (waitpid(pid, &status, 0) < 0) ++ panic("waitpid"); ++ if (WIFEXITED(status) && WEXITSTATUS(status) == 0) { ++ pretty_message("[+] Tests successful! :-)"); ++ fd = open("/proc/cmdline", O_RDONLY); ++ if (fd < 0) ++ panic("open(/proc/cmdline)"); ++ if (read(fd, cmdline, sizeof(cmdline) - 1) <= 0) ++ panic("read(/proc/cmdline)"); ++ cmdline[sizeof(cmdline) - 1] = '\0'; ++ for (success_dev = strtok(cmdline, " \n"); success_dev; success_dev = strtok(NULL, " \n")) { ++ if (strncmp(success_dev, "wg.success=", 11)) ++ continue; ++ memcpy(success_dev + 11 - 5, "/dev/", 5); ++ success_dev += 11 - 5; ++ break; ++ } ++ if (!success_dev || !strlen(success_dev)) ++ panic("Unable to find success device"); ++ ++ fd = open(success_dev, O_WRONLY); ++ if (fd < 0) ++ panic("open(success_dev)"); ++ if (write(fd, "success\n", 8) != 8) ++ panic("write(success_dev)"); ++ close(fd); ++ } else { ++ const char *why = "unknown cause"; ++ int what = -1; ++ ++ if (WIFEXITED(status)) { ++ why = "exit code"; ++ what = WEXITSTATUS(status); ++ } else if (WIFSIGNALED(status)) { ++ why = "signal"; ++ what = WTERMSIG(status); ++ } ++ printf("\x1b[31m\x1b[1m[-] Tests failed with %s %d! \u2639\x1b[0m\n", why, what); ++ } ++} ++ ++static void ensure_console(void) ++{ ++ for (unsigned int i = 0; i < 1000; ++i) { ++ int fd = open("/dev/console", O_RDWR); ++ if (fd < 0) { ++ usleep(50000); ++ continue; ++ } ++ dup2(fd, 0); ++ dup2(fd, 1); ++ dup2(fd, 2); ++ close(fd); ++ if (write(1, "\0\0\0\0\n", 5) == 5) ++ return; ++ } ++ panic("Unable to open console device"); ++} ++ ++static void clear_leaks(void) ++{ ++ int fd; ++ ++ fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); ++ if (fd < 0) ++ return; ++ pretty_message("[+] Starting memory leak detection..."); ++ write(fd, "clear\n", 5); ++ close(fd); ++} ++ ++static void check_leaks(void) ++{ ++ int fd; ++ ++ fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); ++ if (fd < 0) ++ return; ++ pretty_message("[+] Scanning for memory leaks..."); ++ sleep(2); /* Wait for any grace periods. */ ++ write(fd, "scan\n", 5); ++ close(fd); ++ ++ fd = open("/sys/kernel/debug/kmemleak", O_RDONLY); ++ if (fd < 0) ++ return; ++ if (sendfile(1, fd, NULL, 0x7ffff000) > 0) ++ panic("Memory leaks encountered"); ++ close(fd); ++} ++ ++int main(int argc, char *argv[]) ++{ ++ seed_rng(); ++ ensure_console(); ++ print_banner(); ++ mount_filesystems(); ++ kmod_selftests(); ++ enable_logging(); ++ clear_leaks(); ++ launch_tests(); ++ check_leaks(); ++ poweroff(); ++ return 1; ++} +--- /dev/null ++++ b/tools/testing/selftests/wireguard/qemu/kernel.config +@@ -0,0 +1,86 @@ ++CONFIG_LOCALVERSION="" ++CONFIG_NET=y ++CONFIG_NETDEVICES=y ++CONFIG_NET_CORE=y ++CONFIG_NET_IPIP=y ++CONFIG_DUMMY=y ++CONFIG_VETH=y ++CONFIG_MULTIUSER=y ++CONFIG_NAMESPACES=y ++CONFIG_NET_NS=y ++CONFIG_UNIX=y ++CONFIG_INET=y ++CONFIG_IPV6=y ++CONFIG_NETFILTER=y ++CONFIG_NETFILTER_ADVANCED=y ++CONFIG_NF_CONNTRACK=y ++CONFIG_NF_NAT=y ++CONFIG_NETFILTER_XTABLES=y ++CONFIG_NETFILTER_XT_NAT=y ++CONFIG_NETFILTER_XT_MATCH_LENGTH=y ++CONFIG_NF_CONNTRACK_IPV4=y ++CONFIG_NF_NAT_IPV4=y ++CONFIG_IP_NF_IPTABLES=y ++CONFIG_IP_NF_FILTER=y ++CONFIG_IP_NF_NAT=y ++CONFIG_IP_ADVANCED_ROUTER=y ++CONFIG_IP_MULTIPLE_TABLES=y ++CONFIG_IPV6_MULTIPLE_TABLES=y ++CONFIG_TTY=y ++CONFIG_BINFMT_ELF=y ++CONFIG_BINFMT_SCRIPT=y ++CONFIG_VDSO=y ++CONFIG_VIRTUALIZATION=y ++CONFIG_HYPERVISOR_GUEST=y ++CONFIG_PARAVIRT=y ++CONFIG_KVM_GUEST=y ++CONFIG_PARAVIRT_SPINLOCKS=y ++CONFIG_PRINTK=y ++CONFIG_KALLSYMS=y ++CONFIG_BUG=y ++CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y ++CONFIG_EMBEDDED=n ++CONFIG_BASE_FULL=y ++CONFIG_FUTEX=y ++CONFIG_SHMEM=y ++CONFIG_SLUB=y ++CONFIG_SPARSEMEM_VMEMMAP=y ++CONFIG_SMP=y ++CONFIG_SCHED_SMT=y ++CONFIG_SCHED_MC=y ++CONFIG_NUMA=y ++CONFIG_PREEMPT=y ++CONFIG_NO_HZ=y ++CONFIG_NO_HZ_IDLE=y ++CONFIG_NO_HZ_FULL=n ++CONFIG_HZ_PERIODIC=n ++CONFIG_HIGH_RES_TIMERS=y ++CONFIG_ARCH_RANDOM=y ++CONFIG_FILE_LOCKING=y ++CONFIG_POSIX_TIMERS=y ++CONFIG_DEVTMPFS=y ++CONFIG_PROC_FS=y ++CONFIG_PROC_SYSCTL=y ++CONFIG_SYSFS=y ++CONFIG_TMPFS=y ++CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 ++CONFIG_PRINTK_TIME=y ++CONFIG_BLK_DEV_INITRD=y ++CONFIG_LEGACY_VSYSCALL_NONE=y ++CONFIG_KERNEL_GZIP=y ++CONFIG_PANIC_ON_OOPS=y ++CONFIG_BUG_ON_DATA_CORRUPTION=y ++CONFIG_LOCKUP_DETECTOR=y ++CONFIG_SOFTLOCKUP_DETECTOR=y ++CONFIG_HARDLOCKUP_DETECTOR=y ++CONFIG_WQ_WATCHDOG=y ++CONFIG_DETECT_HUNG_TASK=y ++CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y ++CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y ++CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y ++CONFIG_PANIC_TIMEOUT=-1 ++CONFIG_STACKTRACE=y ++CONFIG_EARLY_PRINTK=y ++CONFIG_GDB_SCRIPTS=y ++CONFIG_WIREGUARD=y ++CONFIG_WIREGUARD_DEBUG=y diff --git a/target/linux/generic/backport-5.4/080-wireguard-0075-wireguard-Kconfig-select-parent-dependency-for-crypt.patch b/target/linux/generic/backport-5.4/080-wireguard-0075-wireguard-Kconfig-select-parent-dependency-for-crypt.patch new file mode 100644 index 0000000000..75c483a330 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0075-wireguard-Kconfig-select-parent-dependency-for-crypt.patch @@ -0,0 +1,31 @@ +From 87e4891e91a381de049a6c70690a295f44ae1f13 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Sun, 15 Dec 2019 22:08:01 +0100 +Subject: [PATCH 075/124] wireguard: Kconfig: select parent dependency for + crypto + +commit d7c68a38bb4f9b7c1a2e4a772872c752ee5c44a6 upstream. + +This fixes the crypto selection submenu depenencies. Otherwise, we'd +wind up issuing warnings in which certain dependencies we also select +couldn't be satisfied. This condition was triggered by the addition of +the test suite autobuilder in the previous commit. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/Kconfig | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/drivers/net/Kconfig ++++ b/drivers/net/Kconfig +@@ -85,6 +85,8 @@ config WIREGUARD + select CRYPTO_POLY1305_X86_64 if X86 && 64BIT + select CRYPTO_BLAKE2S_X86 if X86 && 64BIT + select CRYPTO_CURVE25519_X86 if X86 && 64BIT ++ select ARM_CRYPTO if ARM ++ select ARM64_CRYPTO if ARM64 + select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON + select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON + select CRYPTO_POLY1305_ARM if ARM diff --git a/target/linux/generic/backport-5.4/080-wireguard-0076-wireguard-global-fix-spelling-mistakes-in-comments.patch b/target/linux/generic/backport-5.4/080-wireguard-0076-wireguard-global-fix-spelling-mistakes-in-comments.patch new file mode 100644 index 0000000000..da9fd72bac --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0076-wireguard-global-fix-spelling-mistakes-in-comments.patch @@ -0,0 +1,66 @@ +From 163383e1867a8eb7026d436627bbcd39ecdbd509 Mon Sep 17 00:00:00 2001 +From: Josh Soref +Date: Sun, 15 Dec 2019 22:08:02 +0100 +Subject: [PATCH 076/124] wireguard: global: fix spelling mistakes in comments + +commit a2ec8b5706944d228181c8b91d815f41d6dd8e7b upstream. + +This fixes two spelling errors in source code comments. + +Signed-off-by: Josh Soref +[Jason: rewrote commit message] +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 2 +- + include/uapi/linux/wireguard.h | 8 ++++---- + 2 files changed, 5 insertions(+), 5 deletions(-) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -380,7 +380,7 @@ static void wg_packet_consume_data_done( + /* We've already verified the Poly1305 auth tag, which means this packet + * was not modified in transit. We can therefore tell the networking + * stack that all checksums of every layer of encapsulation have already +- * been checked "by the hardware" and therefore is unneccessary to check ++ * been checked "by the hardware" and therefore is unnecessary to check + * again in software. + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; +--- a/include/uapi/linux/wireguard.h ++++ b/include/uapi/linux/wireguard.h +@@ -18,13 +18,13 @@ + * one but not both of: + * + * WGDEVICE_A_IFINDEX: NLA_U32 +- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1 ++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1 + * + * The kernel will then return several messages (NLM_F_MULTI) containing the + * following tree of nested items: + * + * WGDEVICE_A_IFINDEX: NLA_U32 +- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1 ++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1 + * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN + * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN + * WGDEVICE_A_LISTEN_PORT: NLA_U16 +@@ -77,7 +77,7 @@ + * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME: + * + * WGDEVICE_A_IFINDEX: NLA_U32 +- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1 ++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1 + * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current + * peers should be removed prior to adding the list below. + * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove +@@ -121,7 +121,7 @@ + * filling in information not contained in the prior. Note that if + * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably + * should not be specified in fragments that come after, so that the list +- * of peers is only cleared the first time but appened after. Likewise for ++ * of peers is only cleared the first time but appended after. Likewise for + * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message + * of a peer, it likely should not be specified in subsequent fragments. + * diff --git a/target/linux/generic/backport-5.4/080-wireguard-0077-wireguard-main-remove-unused-include-linux-version.h.patch b/target/linux/generic/backport-5.4/080-wireguard-0077-wireguard-main-remove-unused-include-linux-version.h.patch new file mode 100644 index 0000000000..9f1070e542 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0077-wireguard-main-remove-unused-include-linux-version.h.patch @@ -0,0 +1,29 @@ +From 27686282c4b34ad6db44cb3dbf58763e5bb8e96b Mon Sep 17 00:00:00 2001 +From: YueHaibing +Date: Sun, 15 Dec 2019 22:08:03 +0100 +Subject: [PATCH 077/124] wireguard: main: remove unused include + + +commit 43967b6ff91e53bcce5ae08c16a0588a475b53a1 upstream. + +Remove from the includes for main.c, which is unused. + +Signed-off-by: YueHaibing +[Jason: reworded commit message] +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/main.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/drivers/net/wireguard/main.c ++++ b/drivers/net/wireguard/main.c +@@ -12,7 +12,6 @@ + + #include + +-#include + #include + #include + #include diff --git a/target/linux/generic/backport-5.4/080-wireguard-0078-wireguard-allowedips-use-kfree_rcu-instead-of-call_r.patch b/target/linux/generic/backport-5.4/080-wireguard-0078-wireguard-allowedips-use-kfree_rcu-instead-of-call_r.patch new file mode 100644 index 0000000000..82581e9205 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0078-wireguard-allowedips-use-kfree_rcu-instead-of-call_r.patch @@ -0,0 +1,42 @@ +From 17c33753f9b68288a2e8551b6161ca54f1809d37 Mon Sep 17 00:00:00 2001 +From: Wei Yongjun +Date: Sun, 15 Dec 2019 22:08:04 +0100 +Subject: [PATCH 078/124] wireguard: allowedips: use kfree_rcu() instead of + call_rcu() + +commit d89ee7d5c73af15c1c6f12b016cdf469742b5726 upstream. + +The callback function of call_rcu() just calls a kfree(), so we +can use kfree_rcu() instead of call_rcu() + callback function. + +Signed-off-by: Wei Yongjun +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/allowedips.c | 7 +------ + 1 file changed, 1 insertion(+), 6 deletions(-) + +--- a/drivers/net/wireguard/allowedips.c ++++ b/drivers/net/wireguard/allowedips.c +@@ -31,11 +31,6 @@ static void copy_and_assign_cidr(struct + #define CHOOSE_NODE(parent, key) \ + parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1] + +-static void node_free_rcu(struct rcu_head *rcu) +-{ +- kfree(container_of(rcu, struct allowedips_node, rcu)); +-} +- + static void push_rcu(struct allowedips_node **stack, + struct allowedips_node __rcu *p, unsigned int *len) + { +@@ -112,7 +107,7 @@ static void walk_remove_by_peer(struct a + if (!node->bit[0] || !node->bit[1]) { + rcu_assign_pointer(*nptr, DEREF( + &node->bit[!REF(node->bit[0])])); +- call_rcu(&node->rcu, node_free_rcu); ++ kfree_rcu(node, rcu); + node = DEREF(nptr); + } + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0079-wireguard-selftests-remove-ancient-kernel-compatibil.patch b/target/linux/generic/backport-5.4/080-wireguard-0079-wireguard-selftests-remove-ancient-kernel-compatibil.patch new file mode 100644 index 0000000000..efc5500290 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0079-wireguard-selftests-remove-ancient-kernel-compatibil.patch @@ -0,0 +1,373 @@ +From df3289cf81503ef299450a67f5bf11e526fdb2d0 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 2 Jan 2020 17:47:49 +0100 +Subject: [PATCH 079/124] wireguard: selftests: remove ancient kernel + compatibility code + +commit 9a69a4c8802adf642bc4a13d471b5a86b44ed434 upstream. + +Quite a bit of the test suite was designed to work with ancient kernels. +Thankfully we no longer have to deal with this. This commit updates +things that we can finally update and removes things that we can finally +remove, to avoid the build-up of the last several years as a result of +having to support ancient kernels. We can finally rely on suppress_ +prefixlength being available. On the build side of things, the no-PIE +hack is no longer required, and we can bump some of the tools, repair +our m68k and i686-kvm support, and get better coverage of the static +branches used in the crypto lib and in udp_tunnel. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/netns.sh | 11 +-- + .../testing/selftests/wireguard/qemu/Makefile | 82 ++++++++++--------- + .../selftests/wireguard/qemu/arch/m68k.config | 2 +- + tools/testing/selftests/wireguard/qemu/init.c | 1 + + .../selftests/wireguard/qemu/kernel.config | 2 + + 5 files changed, 50 insertions(+), 48 deletions(-) + +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -37,7 +37,7 @@ n2() { pretty 2 "$*"; maybe_exec ip netn + ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } + ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } + ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } +-sleep() { read -t "$1" -N 0 || true; } ++sleep() { read -t "$1" -N 1 || true; } + waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; } + waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } + waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +@@ -294,12 +294,9 @@ ip1 -6 rule add table main suppress_pref + ip1 -4 route add default dev wg0 table 51820 + ip1 -4 rule add not fwmark 51820 table 51820 + ip1 -4 rule add table main suppress_prefixlength 0 +-# suppress_prefixlength only got added in 3.12, and we want to support 3.10+. +-if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then +- # Flood the pings instead of sending just one, to trigger routing table reference counting bugs. +- n1 ping -W 1 -c 100 -f 192.168.99.7 +- n1 ping -W 1 -c 100 -f abab::1111 +-fi ++# Flood the pings instead of sending just one, to trigger routing table reference counting bugs. ++n1 ping -W 1 -c 100 -f 192.168.99.7 ++n1 ping -W 1 -c 100 -f abab::1111 + + n0 iptables -t nat -F + ip0 link del vethrc +--- a/tools/testing/selftests/wireguard/qemu/Makefile ++++ b/tools/testing/selftests/wireguard/qemu/Makefile +@@ -5,6 +5,7 @@ + PWD := $(shell pwd) + + CHOST := $(shell gcc -dumpmachine) ++HOST_ARCH := $(firstword $(subst -, ,$(CHOST))) + ifneq (,$(ARCH)) + CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) + ifeq (,$(CBUILD)) +@@ -37,19 +38,19 @@ endef + define file_download = + $(DISTFILES_PATH)/$(1): + mkdir -p $(DISTFILES_PATH) +- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' ++ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' + if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi + endef + +-$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61)) ++$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) + $(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) +-$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f)) ++$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) + $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) +-$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2)) +-$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5)) +-$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21)) +-$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a)) +-$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071)) ++$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) ++$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) ++$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) ++$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) ++$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) + + KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) + rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +@@ -59,23 +60,21 @@ export CFLAGS ?= -O3 -pipe + export LDFLAGS ?= + export CPPFLAGS := -I$(BUILD_PATH)/include + +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + CROSS_COMPILE_FLAG := --host=$(CHOST) +-NOPIE_GCC := gcc -fno-PIE + CFLAGS += -march=native + STRIP := strip + else + $(info Cross compilation: building for $(CBUILD) using $(CHOST)) + CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) + export CROSS_COMPILE=$(CBUILD)- +-NOPIE_GCC := $(CBUILD)-gcc -fno-PIE + STRIP := $(CBUILD)-strip + endif + ifeq ($(ARCH),aarch64) + QEMU_ARCH := aarch64 + KERNEL_ARCH := arm64 + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm + else + QEMU_MACHINE := -cpu cortex-a53 -machine virt +@@ -85,7 +84,7 @@ else ifeq ($(ARCH),aarch64_be) + QEMU_ARCH := aarch64 + KERNEL_ARCH := arm64 + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm + else + QEMU_MACHINE := -cpu cortex-a53 -machine virt +@@ -95,7 +94,7 @@ else ifeq ($(ARCH),arm) + QEMU_ARCH := arm + KERNEL_ARCH := arm + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm + else + QEMU_MACHINE := -cpu cortex-a15 -machine virt +@@ -105,7 +104,7 @@ else ifeq ($(ARCH),armeb) + QEMU_ARCH := arm + KERNEL_ARCH := arm + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm + else + QEMU_MACHINE := -cpu cortex-a15 -machine virt +@@ -116,7 +115,7 @@ else ifeq ($(ARCH),x86_64) + QEMU_ARCH := x86_64 + KERNEL_ARCH := x86_64 + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine q35,accel=kvm + else + QEMU_MACHINE := -cpu Skylake-Server -machine q35 +@@ -126,7 +125,7 @@ else ifeq ($(ARCH),i686) + QEMU_ARCH := i386 + KERNEL_ARCH := x86 + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +-ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST)) ++ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH)) + QEMU_MACHINE := -cpu host -machine q35,accel=kvm + else + QEMU_MACHINE := -cpu coreduo -machine q35 +@@ -136,7 +135,7 @@ else ifeq ($(ARCH),mips64) + QEMU_ARCH := mips64 + KERNEL_ARCH := mips + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine malta,accel=kvm + CFLAGS += -EB + else +@@ -147,7 +146,7 @@ else ifeq ($(ARCH),mips64el) + QEMU_ARCH := mips64el + KERNEL_ARCH := mips + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine malta,accel=kvm + CFLAGS += -EL + else +@@ -158,7 +157,7 @@ else ifeq ($(ARCH),mips) + QEMU_ARCH := mips + KERNEL_ARCH := mips + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine malta,accel=kvm + CFLAGS += -EB + else +@@ -169,7 +168,7 @@ else ifeq ($(ARCH),mipsel) + QEMU_ARCH := mipsel + KERNEL_ARCH := mips + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host -machine malta,accel=kvm + CFLAGS += -EL + else +@@ -180,7 +179,7 @@ else ifeq ($(ARCH),powerpc64le) + QEMU_ARCH := ppc64 + KERNEL_ARCH := powerpc + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host,accel=kvm -machine pseries + else + QEMU_MACHINE := -machine pseries +@@ -190,7 +189,7 @@ else ifeq ($(ARCH),powerpc) + QEMU_ARCH := ppc + KERNEL_ARCH := powerpc + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage +-ifeq ($(CHOST),$(CBUILD)) ++ifeq ($(HOST_ARCH),$(ARCH)) + QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 + else + QEMU_MACHINE := -machine ppce500 +@@ -200,10 +199,11 @@ else ifeq ($(ARCH),m68k) + QEMU_ARCH := m68k + KERNEL_ARCH := m68k + KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +-ifeq ($(CHOST),$(CBUILD)) +-QEMU_MACHINE := -cpu host,accel=kvm -machine q800 ++KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config) ++ifeq ($(HOST_ARCH),$(ARCH)) ++QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE) + else +-QEMU_MACHINE := -machine q800 ++QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE) + endif + else + $(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) +@@ -238,14 +238,14 @@ $(BUILD_PATH)/init-cpio-spec.txt: + echo "nod /dev/console 644 0 0 c 5 1" >> $@ + echo "dir /bin 755 0 0" >> $@ + echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@ +- echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@ ++ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@ + echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@ + echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@ + echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@ + echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@ + echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@ +- echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@ +- echo "slink /bin/iptables xtables-multi 777 0 0" >> $@ ++ echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@ ++ echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@ + echo "slink /bin/ping6 ping 777 0 0" >> $@ + echo "dir /lib 755 0 0" >> $@ + echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ +@@ -260,8 +260,8 @@ $(KERNEL_BUILD_PATH)/.config: kernel.con + cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config + $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) + +-$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) +- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" ++$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) ++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) + + $(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install +@@ -280,7 +280,7 @@ $(BUILD_PATH)/include/.installed: $(MUSL + + $(MUSL_CC): $(MUSL_PATH)/lib/libc.so + sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs +- printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc ++ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc + chmod +x $(BUILD_PATH)/musl-gcc + + $(IPERF_PATH)/.installed: $(IPERF_TAR) +@@ -291,7 +291,7 @@ $(IPERF_PATH)/.installed: $(IPERF_TAR) + touch $@ + + $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) +- cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared ++ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no + $(MAKE) -C $(IPERF_PATH) + $(STRIP) -s $@ + +@@ -308,8 +308,8 @@ $(WIREGUARD_TOOLS_PATH)/.installed: $(WI + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +-$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) +- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg ++$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) ++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg + $(STRIP) -s $@ + + $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) +@@ -323,7 +323,8 @@ $(IPUTILS_PATH)/.installed: $(IPUTILS_TA + touch $@ + + $(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS) +- $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping ++ sed -i /atexit/d $(IPUTILS_PATH)/ping.c ++ cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS) + $(STRIP) -s $@ + + $(BASH_PATH)/.installed: $(BASH_TAR) +@@ -357,7 +358,7 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_ + sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure + touch $@ + +-$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) ++$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include + $(MAKE) -C $(IPTABLES_PATH) + $(STRIP) -s $@ +@@ -368,8 +369,9 @@ $(NMAP_PATH)/.installed: $(NMAP_TAR) + touch $@ + + $(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS) +- cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux +- $(MAKE) -C $(NMAP_PATH) build-ncat ++ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh ++ $(MAKE) -C $(NMAP_PATH)/libpcap ++ $(MAKE) -C $(NMAP_PATH)/ncat + $(STRIP) -s $@ + + clean: +@@ -379,7 +381,7 @@ distclean: clean + rm -rf $(DISTFILES_PATH) + + menuconfig: $(KERNEL_BUILD_PATH)/.config +- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig ++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig + + .PHONY: qemu build clean distclean menuconfig + .DELETE_ON_ERROR: +--- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config ++++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config +@@ -1,9 +1,9 @@ + CONFIG_MMU=y ++CONFIG_M68KCLASSIC=y + CONFIG_M68040=y + CONFIG_MAC=y + CONFIG_SERIAL_PMACZILOG=y + CONFIG_SERIAL_PMACZILOG_TTYS=y + CONFIG_SERIAL_PMACZILOG_CONSOLE=y +-CONFIG_CMDLINE_BOOL=y + CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" + CONFIG_FRAME_WARN=1024 +--- a/tools/testing/selftests/wireguard/qemu/init.c ++++ b/tools/testing/selftests/wireguard/qemu/init.c +@@ -21,6 +21,7 @@ + #include + #include + #include ++#include + #include + #include + +--- a/tools/testing/selftests/wireguard/qemu/kernel.config ++++ b/tools/testing/selftests/wireguard/qemu/kernel.config +@@ -39,6 +39,7 @@ CONFIG_PRINTK=y + CONFIG_KALLSYMS=y + CONFIG_BUG=y + CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y ++CONFIG_JUMP_LABEL=y + CONFIG_EMBEDDED=n + CONFIG_BASE_FULL=y + CONFIG_FUTEX=y +@@ -55,6 +56,7 @@ CONFIG_NO_HZ_IDLE=y + CONFIG_NO_HZ_FULL=n + CONFIG_HZ_PERIODIC=n + CONFIG_HIGH_RES_TIMERS=y ++CONFIG_COMPAT_32BIT_TIME=y + CONFIG_ARCH_RANDOM=y + CONFIG_FILE_LOCKING=y + CONFIG_POSIX_TIMERS=y diff --git a/target/linux/generic/backport-5.4/080-wireguard-0080-wireguard-queueing-do-not-account-for-pfmemalloc-whe.patch b/target/linux/generic/backport-5.4/080-wireguard-0080-wireguard-queueing-do-not-account-for-pfmemalloc-whe.patch new file mode 100644 index 0000000000..edbca28d21 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0080-wireguard-queueing-do-not-account-for-pfmemalloc-whe.patch @@ -0,0 +1,39 @@ +From 2b7c5a4a57e1f5cc37877f838293173994e028c6 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 2 Jan 2020 17:47:50 +0100 +Subject: [PATCH 080/124] wireguard: queueing: do not account for pfmemalloc + when clearing skb header + +commit 04d2ea92a18417619182cbb79063f154892b0150 upstream. + +Before 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_ +header()"), the pfmemalloc flag used to be between headers_start and +headers_end, which is a region we clear when preparing the packet for +encryption/decryption. This is a parameter we certainly want to +preserve, which is why 8b7008620b84 moved it out of there. The code here +was written in a world before 8b7008620b84, though, where we had to +manually account for it. This commit brings things up to speed. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/queueing.h | 3 --- + 1 file changed, 3 deletions(-) + +--- a/drivers/net/wireguard/queueing.h ++++ b/drivers/net/wireguard/queueing.h +@@ -83,13 +83,10 @@ static inline __be16 wg_skb_examine_untr + + static inline void wg_reset_packet(struct sk_buff *skb) + { +- const int pfmemalloc = skb->pfmemalloc; +- + skb_scrub_packet(skb, true); + memset(&skb->headers_start, 0, + offsetof(struct sk_buff, headers_end) - + offsetof(struct sk_buff, headers_start)); +- skb->pfmemalloc = pfmemalloc; + skb->queue_mapping = 0; + skb->nohdr = 0; + skb->peeked = 0; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0081-wireguard-socket-mark-skbs-as-not-on-list-when-recei.patch b/target/linux/generic/backport-5.4/080-wireguard-0081-wireguard-socket-mark-skbs-as-not-on-list-when-recei.patch new file mode 100644 index 0000000000..a3472462ec --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0081-wireguard-socket-mark-skbs-as-not-on-list-when-recei.patch @@ -0,0 +1,34 @@ +From 6d8e17ad1b4b019c61403a88377e731491de409c Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 2 Jan 2020 17:47:51 +0100 +Subject: [PATCH 081/124] wireguard: socket: mark skbs as not on list when + receiving via gro + +commit 736775d06bac60d7a353e405398b48b2bd8b1e54 upstream. + +Certain drivers will pass gro skbs to udp, at which point the udp driver +simply iterates through them and passes them off to encap_rcv, which is +where we pick up. At the moment, we're not attempting to coalesce these +into bundles, but we also don't want to wind up having cascaded lists of +skbs treated separately. The right behavior here, then, is to just mark +each incoming one as not on a list. This can be seen in practice, for +example, with Qualcomm's rmnet_perf driver. + +Signed-off-by: Jason A. Donenfeld +Tested-by: Yaroslav Furman +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/socket.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/net/wireguard/socket.c ++++ b/drivers/net/wireguard/socket.c +@@ -333,6 +333,7 @@ static int wg_receive(struct sock *sk, s + wg = sk->sk_user_data; + if (unlikely(!wg)) + goto err; ++ skb_mark_not_on_list(skb); + wg_packet_receive(wg, skb); + return 0; + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0082-wireguard-allowedips-fix-use-after-free-in-root_remo.patch b/target/linux/generic/backport-5.4/080-wireguard-0082-wireguard-allowedips-fix-use-after-free-in-root_remo.patch new file mode 100644 index 0000000000..f0275396d5 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0082-wireguard-allowedips-fix-use-after-free-in-root_remo.patch @@ -0,0 +1,164 @@ +From 13696b0d3219c3ca9ff4ce6a580c53fab6284312 Mon Sep 17 00:00:00 2001 +From: Eric Dumazet +Date: Tue, 4 Feb 2020 22:17:25 +0100 +Subject: [PATCH 082/124] wireguard: allowedips: fix use-after-free in + root_remove_peer_lists + +commit 9981159fc3b677b357f84e069a11de5a5ec8a2a8 upstream. + +In the unlikely case a new node could not be allocated, we need to +remove @newnode from @peer->allowedips_list before freeing it. + +syzbot reported: + +BUG: KASAN: use-after-free in __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54 +Read of size 8 at addr ffff88809881a538 by task syz-executor.4/30133 + +CPU: 0 PID: 30133 Comm: syz-executor.4 Not tainted 5.5.0-syzkaller #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 +Call Trace: + __dump_stack lib/dump_stack.c:77 [inline] + dump_stack+0x197/0x210 lib/dump_stack.c:118 + print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 + __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506 + kasan_report+0x12/0x20 mm/kasan/common.c:639 + __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135 + __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54 + __list_del_entry include/linux/list.h:132 [inline] + list_del include/linux/list.h:146 [inline] + root_remove_peer_lists+0x24f/0x4b0 drivers/net/wireguard/allowedips.c:65 + wg_allowedips_free+0x232/0x390 drivers/net/wireguard/allowedips.c:300 + wg_peer_remove_all+0xd5/0x620 drivers/net/wireguard/peer.c:187 + wg_set_device+0xd01/0x1350 drivers/net/wireguard/netlink.c:542 + genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline] + genl_family_rcv_msg net/netlink/genetlink.c:717 [inline] + genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734 + netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 + genl_rcv+0x29/0x40 net/netlink/genetlink.c:745 + netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] + netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 + netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 + sock_sendmsg_nosec net/socket.c:652 [inline] + sock_sendmsg+0xd7/0x130 net/socket.c:672 + ____sys_sendmsg+0x753/0x880 net/socket.c:2343 + ___sys_sendmsg+0x100/0x170 net/socket.c:2397 + __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 + __do_sys_sendmsg net/socket.c:2439 [inline] + __se_sys_sendmsg net/socket.c:2437 [inline] + __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437 + do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 + entry_SYSCALL_64_after_hwframe+0x49/0xbe +RIP: 0033:0x45b399 +Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 +RSP: 002b:00007f99a9bcdc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e +RAX: ffffffffffffffda RBX: 00007f99a9bce6d4 RCX: 000000000045b399 +RDX: 0000000000000000 RSI: 0000000020001340 RDI: 0000000000000003 +RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000 +R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004 +R13: 00000000000009ba R14: 00000000004cb2b8 R15: 0000000000000009 + +Allocated by task 30103: + save_stack+0x23/0x90 mm/kasan/common.c:72 + set_track mm/kasan/common.c:80 [inline] + __kasan_kmalloc mm/kasan/common.c:513 [inline] + __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486 + kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527 + kmem_cache_alloc_trace+0x158/0x790 mm/slab.c:3551 + kmalloc include/linux/slab.h:556 [inline] + kzalloc include/linux/slab.h:670 [inline] + add+0x70a/0x1970 drivers/net/wireguard/allowedips.c:236 + wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320 + set_allowedip drivers/net/wireguard/netlink.c:343 [inline] + set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468 + wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591 + genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline] + genl_family_rcv_msg net/netlink/genetlink.c:717 [inline] + genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734 + netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 + genl_rcv+0x29/0x40 net/netlink/genetlink.c:745 + netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] + netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 + netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 + sock_sendmsg_nosec net/socket.c:652 [inline] + sock_sendmsg+0xd7/0x130 net/socket.c:672 + ____sys_sendmsg+0x753/0x880 net/socket.c:2343 + ___sys_sendmsg+0x100/0x170 net/socket.c:2397 + __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 + __do_sys_sendmsg net/socket.c:2439 [inline] + __se_sys_sendmsg net/socket.c:2437 [inline] + __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437 + do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 + entry_SYSCALL_64_after_hwframe+0x49/0xbe + +Freed by task 30103: + save_stack+0x23/0x90 mm/kasan/common.c:72 + set_track mm/kasan/common.c:80 [inline] + kasan_set_free_info mm/kasan/common.c:335 [inline] + __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474 + kasan_slab_free+0xe/0x10 mm/kasan/common.c:483 + __cache_free mm/slab.c:3426 [inline] + kfree+0x10a/0x2c0 mm/slab.c:3757 + add+0x12d2/0x1970 drivers/net/wireguard/allowedips.c:266 + wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320 + set_allowedip drivers/net/wireguard/netlink.c:343 [inline] + set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468 + wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591 + genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline] + genl_family_rcv_msg net/netlink/genetlink.c:717 [inline] + genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734 + netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 + genl_rcv+0x29/0x40 net/netlink/genetlink.c:745 + netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] + netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 + netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 + sock_sendmsg_nosec net/socket.c:652 [inline] + sock_sendmsg+0xd7/0x130 net/socket.c:672 + ____sys_sendmsg+0x753/0x880 net/socket.c:2343 + ___sys_sendmsg+0x100/0x170 net/socket.c:2397 + __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 + __do_sys_sendmsg net/socket.c:2439 [inline] + __se_sys_sendmsg net/socket.c:2437 [inline] + __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437 + do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 + entry_SYSCALL_64_after_hwframe+0x49/0xbe + +The buggy address belongs to the object at ffff88809881a500 + which belongs to the cache kmalloc-64 of size 64 +The buggy address is located 56 bytes inside of + 64-byte region [ffff88809881a500, ffff88809881a540) +The buggy address belongs to the page: +page:ffffea0002620680 refcount:1 mapcount:0 mapping:ffff8880aa400380 index:0x0 +raw: 00fffe0000000200 ffffea000250b748 ffffea000254bac8 ffff8880aa400380 +raw: 0000000000000000 ffff88809881a000 0000000100000020 0000000000000000 +page dumped because: kasan: bad access detected + +Memory state around the buggy address: + ffff88809881a400: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc + ffff88809881a480: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc +>ffff88809881a500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc + ^ + ffff88809881a580: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc + ffff88809881a600: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Eric Dumazet +Reported-by: syzbot +Cc: Jason A. Donenfeld +Cc: wireguard@lists.zx2c4.com +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/allowedips.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/net/wireguard/allowedips.c ++++ b/drivers/net/wireguard/allowedips.c +@@ -263,6 +263,7 @@ static int add(struct allowedips_node __ + } else { + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (unlikely(!node)) { ++ list_del(&newnode->peer_list); + kfree(newnode); + return -ENOMEM; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0083-wireguard-noise-reject-peers-with-low-order-public-k.patch b/target/linux/generic/backport-5.4/080-wireguard-0083-wireguard-noise-reject-peers-with-low-order-public-k.patch new file mode 100644 index 0000000000..113678d212 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0083-wireguard-noise-reject-peers-with-low-order-public-k.patch @@ -0,0 +1,234 @@ +From 1da05ad0bbc51cd226a2297e66b3cc8499803306 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 4 Feb 2020 22:17:26 +0100 +Subject: [PATCH 083/124] wireguard: noise: reject peers with low order public + keys + +commit ec31c2676a10e064878927b243fada8c2fb0c03c upstream. + +Our static-static calculation returns a failure if the public key is of +low order. We check for this when peers are added, and don't allow them +to be added if they're low order, except in the case where we haven't +yet been given a private key. In that case, we would defer the removal +of the peer until we're given a private key, since at that point we're +doing new static-static calculations which incur failures we can act on. +This meant, however, that we wound up removing peers rather late in the +configuration flow. + +Syzkaller points out that peer_remove calls flush_workqueue, which in +turn might then wait for sending a handshake initiation to complete. +Since handshake initiation needs the static identity lock, holding the +static identity lock while calling peer_remove can result in a rare +deadlock. We have precisely this case in this situation of late-stage +peer removal based on an invalid public key. We can't drop the lock when +removing, because then incoming handshakes might interact with a bogus +static-static calculation. + +While the band-aid patch for this would involve breaking up the peer +removal into two steps like wg_peer_remove_all does, in order to solve +the locking issue, there's actually a much more elegant way of fixing +this: + +If the static-static calculation succeeds with one private key, it +*must* succeed with all others, because all 32-byte strings map to valid +private keys, thanks to clamping. That means we can get rid of this +silly dance and locking headaches of removing peers late in the +configuration flow, and instead just reject them early on, regardless of +whether the device has yet been assigned a private key. For the case +where the device doesn't yet have a private key, we safely use zeros +just for the purposes of checking for low order points by way of +checking the output of the calculation. + +The following PoC will trigger the deadlock: + +ip link add wg0 type wireguard +ip addr add 10.0.0.1/24 dev wg0 +ip link set wg0 up +ping -f 10.0.0.2 & +while true; do + wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234 + wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=) +done + +[ 0.949105] ====================================================== +[ 0.949550] WARNING: possible circular locking dependency detected +[ 0.950143] 5.5.0-debug+ #18 Not tainted +[ 0.950431] ------------------------------------------------------ +[ 0.950959] wg/89 is trying to acquire lock: +[ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0 +[ 0.951865] +[ 0.951865] but task is already holding lock: +[ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 +[ 0.953011] +[ 0.953011] which lock already depends on the new lock. +[ 0.953011] +[ 0.953651] +[ 0.953651] the existing dependency chain (in reverse order) is: +[ 0.954292] +[ 0.954292] -> #2 (&wg->static_identity.lock){++++}: +[ 0.954804] lock_acquire+0x127/0x350 +[ 0.955133] down_read+0x83/0x410 +[ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700 +[ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280 +[ 0.956401] wg_packet_handshake_send_worker+0x10/0x20 +[ 0.956841] process_one_work+0x806/0x1500 +[ 0.957167] worker_thread+0x8c/0xcb0 +[ 0.957549] kthread+0x2ee/0x3b0 +[ 0.957792] ret_from_fork+0x24/0x30 +[ 0.958234] +[ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}: +[ 0.958808] lock_acquire+0x127/0x350 +[ 0.959075] process_one_work+0x7ab/0x1500 +[ 0.959369] worker_thread+0x8c/0xcb0 +[ 0.959639] kthread+0x2ee/0x3b0 +[ 0.959896] ret_from_fork+0x24/0x30 +[ 0.960346] +[ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}: +[ 0.960945] check_prev_add+0x167/0x1e20 +[ 0.961351] __lock_acquire+0x2012/0x3170 +[ 0.961725] lock_acquire+0x127/0x350 +[ 0.961990] flush_workqueue+0x106/0x12f0 +[ 0.962280] peer_remove_after_dead+0x160/0x220 +[ 0.962600] wg_set_device+0xa24/0xcc0 +[ 0.962994] genl_rcv_msg+0x52f/0xe90 +[ 0.963298] netlink_rcv_skb+0x111/0x320 +[ 0.963618] genl_rcv+0x1f/0x30 +[ 0.963853] netlink_unicast+0x3f6/0x610 +[ 0.964245] netlink_sendmsg+0x700/0xb80 +[ 0.964586] __sys_sendto+0x1dd/0x2c0 +[ 0.964854] __x64_sys_sendto+0xd8/0x1b0 +[ 0.965141] do_syscall_64+0x90/0xd9a +[ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe +[ 0.965769] +[ 0.965769] other info that might help us debug this: +[ 0.965769] +[ 0.966337] Chain exists of: +[ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock +[ 0.966337] +[ 0.967417] Possible unsafe locking scenario: +[ 0.967417] +[ 0.967836] CPU0 CPU1 +[ 0.968155] ---- ---- +[ 0.968497] lock(&wg->static_identity.lock); +[ 0.968779] lock((work_completion)(&peer->transmit_handshake_work)); +[ 0.969345] lock(&wg->static_identity.lock); +[ 0.969809] lock((wq_completion)wg-kex-wg0); +[ 0.970146] +[ 0.970146] *** DEADLOCK *** +[ 0.970146] +[ 0.970531] 5 locks held by wg/89: +[ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30 +[ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90 +[ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0 +[ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0 +[ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0 +[ 0.973653] +[ 0.973653] stack backtrace: +[ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18 +[ 0.974476] Call Trace: +[ 0.974638] dump_stack+0x97/0xe0 +[ 0.974869] check_noncircular+0x312/0x3e0 +[ 0.975132] ? print_circular_bug+0x1f0/0x1f0 +[ 0.975410] ? __kernel_text_address+0x9/0x30 +[ 0.975727] ? unwind_get_return_address+0x51/0x90 +[ 0.976024] check_prev_add+0x167/0x1e20 +[ 0.976367] ? graph_lock+0x70/0x160 +[ 0.976682] __lock_acquire+0x2012/0x3170 +[ 0.976998] ? register_lock_class+0x1140/0x1140 +[ 0.977323] lock_acquire+0x127/0x350 +[ 0.977627] ? flush_workqueue+0xe3/0x12f0 +[ 0.977890] flush_workqueue+0x106/0x12f0 +[ 0.978147] ? flush_workqueue+0xe3/0x12f0 +[ 0.978410] ? find_held_lock+0x2c/0x110 +[ 0.978662] ? lock_downgrade+0x6e0/0x6e0 +[ 0.978919] ? queue_rcu_work+0x60/0x60 +[ 0.979166] ? netif_napi_del+0x151/0x3b0 +[ 0.979501] ? peer_remove_after_dead+0x160/0x220 +[ 0.979871] peer_remove_after_dead+0x160/0x220 +[ 0.980232] wg_set_device+0xa24/0xcc0 +[ 0.980516] ? deref_stack_reg+0x8e/0xc0 +[ 0.980801] ? set_peer+0xe10/0xe10 +[ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150 +[ 0.981430] ? __nla_validate_parse+0x163/0x270 +[ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310 +[ 0.982078] genl_rcv_msg+0x52f/0xe90 +[ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 +[ 0.982690] ? register_lock_class+0x1140/0x1140 +[ 0.983049] netlink_rcv_skb+0x111/0x320 +[ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310 +[ 0.983645] ? netlink_ack+0x880/0x880 +[ 0.983888] genl_rcv+0x1f/0x30 +[ 0.984168] netlink_unicast+0x3f6/0x610 +[ 0.984443] ? netlink_detachskb+0x60/0x60 +[ 0.984729] ? find_held_lock+0x2c/0x110 +[ 0.984976] netlink_sendmsg+0x700/0xb80 +[ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60 +[ 0.985533] __sys_sendto+0x1dd/0x2c0 +[ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0 +[ 0.986039] ? sockfd_lookup_light+0x17/0x160 +[ 0.986397] ? __sys_recvmsg+0x8c/0xf0 +[ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0 +[ 0.987018] __x64_sys_sendto+0xd8/0x1b0 +[ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0 +[ 0.987666] do_syscall_64+0x90/0xd9a +[ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe +[ 0.988223] RIP: 0033:0x7fe77c12003e +[ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4 +[ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c +[ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e +[ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004 +[ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c +[ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c +[ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001 + +Signed-off-by: Jason A. Donenfeld +Reported-by: syzbot +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/netlink.c | 6 ++---- + drivers/net/wireguard/noise.c | 10 +++++++--- + 2 files changed, 9 insertions(+), 7 deletions(-) + +--- a/drivers/net/wireguard/netlink.c ++++ b/drivers/net/wireguard/netlink.c +@@ -575,10 +575,8 @@ static int wg_set_device(struct sk_buff + private_key); + list_for_each_entry_safe(peer, temp, &wg->peer_list, + peer_list) { +- if (wg_noise_precompute_static_static(peer)) +- wg_noise_expire_current_peer_keypairs(peer); +- else +- wg_peer_remove(peer); ++ BUG_ON(!wg_noise_precompute_static_static(peer)); ++ wg_noise_expire_current_peer_keypairs(peer); + } + wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); + up_write(&wg->static_identity.lock); +--- a/drivers/net/wireguard/noise.c ++++ b/drivers/net/wireguard/noise.c +@@ -46,17 +46,21 @@ void __init wg_noise_init(void) + /* Must hold peer->handshake.static_identity->lock */ + bool wg_noise_precompute_static_static(struct wg_peer *peer) + { +- bool ret = true; ++ bool ret; + + down_write(&peer->handshake.lock); +- if (peer->handshake.static_identity->has_identity) ++ if (peer->handshake.static_identity->has_identity) { + ret = curve25519( + peer->handshake.precomputed_static_static, + peer->handshake.static_identity->static_private, + peer->handshake.remote_static); +- else ++ } else { ++ u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 }; ++ ++ ret = curve25519(empty, empty, peer->handshake.remote_static); + memset(peer->handshake.precomputed_static_static, 0, + NOISE_PUBLIC_KEY_LEN); ++ } + up_write(&peer->handshake.lock); + return ret; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0084-wireguard-selftests-ensure-non-addition-of-peers-wit.patch b/target/linux/generic/backport-5.4/080-wireguard-0084-wireguard-selftests-ensure-non-addition-of-peers-wit.patch new file mode 100644 index 0000000000..d6ad3be309 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0084-wireguard-selftests-ensure-non-addition-of-peers-wit.patch @@ -0,0 +1,34 @@ +From eb6a11e6d69912d8bb0b951b08f6871785cfe0e9 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 4 Feb 2020 22:17:27 +0100 +Subject: [PATCH 084/124] wireguard: selftests: ensure non-addition of peers + with failed precomputation + +commit f9398acba6a4ae9cb98bfe4d56414d376eff8d57 upstream. + +Ensure that peers with low order points are ignored, both in the case +where we already have a device private key and in the case where we do +not. This adds points that naturally give a zero output. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/netns.sh | 6 ++++++ + 1 file changed, 6 insertions(+) + +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -516,6 +516,12 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0 + n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0 + n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 + n0 wg set wg0 peer "$pub2" allowed-ips ::/0 ++n0 wg set wg0 peer "$pub2" remove ++low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= ) ++n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer } ++[[ -z $(n0 wg show wg0 peers) ]] ++n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer } ++[[ -z $(n0 wg show wg0 peers) ]] + ip0 link del wg0 + + declare -A objects diff --git a/target/linux/generic/backport-5.4/080-wireguard-0085-wireguard-selftests-tie-socket-waiting-to-target-pid.patch b/target/linux/generic/backport-5.4/080-wireguard-0085-wireguard-selftests-tie-socket-waiting-to-target-pid.patch new file mode 100644 index 0000000000..c891f8f64f --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0085-wireguard-selftests-tie-socket-waiting-to-target-pid.patch @@ -0,0 +1,78 @@ +From d95179eade4bc805455dd5e6617db5e387004d13 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 4 Feb 2020 22:17:29 +0100 +Subject: [PATCH 085/124] wireguard: selftests: tie socket waiting to target + pid + +commit 88f404a9b1d75388225b1c67b6dd327cb2182777 upstream. + +Without this, we wind up proceeding too early sometimes when the +previous process has just used the same listening port. So, we tie the +listening socket query to the specific pid we're interested in. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/netns.sh | 17 ++++++++--------- + 1 file changed, 8 insertions(+), 9 deletions(-) + +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -38,9 +38,8 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0 + ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } + ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } + sleep() { read -t "$1" -N 1 || true; } +-waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; } +-waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +-waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } ++waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } ++waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } + waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } + + cleanup() { +@@ -119,22 +118,22 @@ tests() { + + # TCP over IPv4 + n2 iperf3 -s -1 -B 192.168.241.2 & +- waitiperf $netns2 ++ waitiperf $netns2 $! + n1 iperf3 -Z -t 3 -c 192.168.241.2 + + # TCP over IPv6 + n1 iperf3 -s -1 -B fd00::1 & +- waitiperf $netns1 ++ waitiperf $netns1 $! + n2 iperf3 -Z -t 3 -c fd00::1 + + # UDP over IPv4 + n1 iperf3 -s -1 -B 192.168.241.1 & +- waitiperf $netns1 ++ waitiperf $netns1 $! + n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1 + + # UDP over IPv6 + n2 iperf3 -s -1 -B fd00::2 & +- waitiperf $netns2 ++ waitiperf $netns2 $! + n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 + } + +@@ -207,7 +206,7 @@ n1 ping -W 1 -c 1 192.168.241.2 + n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24 + exec 4< <(n1 ncat -l -u -p 1111) + ncat_pid=$! +-waitncatudp $netns1 ++waitncatudp $netns1 $ncat_pid + n2 ncat -u 192.168.241.1 1111 <<<"X" + read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]] + kill $ncat_pid +@@ -216,7 +215,7 @@ n1 wg set wg0 peer "$more_specific_key" + n2 wg set wg0 listen-port 9997 + exec 4< <(n1 ncat -l -u -p 1111) + ncat_pid=$! +-waitncatudp $netns1 ++waitncatudp $netns1 $ncat_pid + n2 ncat -u 192.168.241.1 1111 <<<"X" + ! read -r -N 1 -t 1 out <&4 || false + kill $ncat_pid diff --git a/target/linux/generic/backport-5.4/080-wireguard-0086-wireguard-device-use-icmp_ndo_send-helper.patch b/target/linux/generic/backport-5.4/080-wireguard-0086-wireguard-device-use-icmp_ndo_send-helper.patch new file mode 100644 index 0000000000..32bb799594 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0086-wireguard-device-use-icmp_ndo_send-helper.patch @@ -0,0 +1,64 @@ +From a16efc93a9c12bbfbff6d50811332e687cc527a9 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 11 Feb 2020 20:47:08 +0100 +Subject: [PATCH 086/124] wireguard: device: use icmp_ndo_send helper + +commit a12d7f3cbdc72c7625881c8dc2660fc2c979fdf2 upstream. + +Because wireguard is calling icmp from network device context, it should +use the ndo helper so that the rate limiting applies correctly. This +commit adds a small test to the wireguard test suite to ensure that the +new functions continue doing the right thing in the context of +wireguard. It does this by setting up a condition that will definately +evoke an icmp error message from the driver, but along a nat'd path. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 4 ++-- + tools/testing/selftests/wireguard/netns.sh | 11 +++++++++++ + 2 files changed, 13 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -203,9 +203,9 @@ err_peer: + err: + ++dev->stats.tx_errors; + if (skb->protocol == htons(ETH_P_IP)) +- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); ++ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + else if (skb->protocol == htons(ETH_P_IPV6)) +- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); ++ icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); + kfree_skb(skb); + return ret; + } +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -24,6 +24,7 @@ + set -e + + exec 3>&1 ++export LANG=C + export WG_HIDE_KEYS=never + netns0="wg-test-$$-0" + netns1="wg-test-$$-1" +@@ -297,7 +298,17 @@ ip1 -4 rule add table main suppress_pref + n1 ping -W 1 -c 100 -f 192.168.99.7 + n1 ping -W 1 -c 100 -f abab::1111 + ++# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route. ++n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 ++n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. ++n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' ++ip0 -4 route add 192.168.241.1 via 10.0.0.100 ++n2 wg set wg0 peer "$pub1" remove ++[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]] ++ + n0 iptables -t nat -F ++n0 iptables -t filter -F ++n2 iptables -t nat -F + ip0 link del vethrc + ip0 link del vethrs + ip1 link del wg0 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0087-wireguard-selftests-reduce-complexity-and-fix-make-r.patch b/target/linux/generic/backport-5.4/080-wireguard-0087-wireguard-selftests-reduce-complexity-and-fix-make-r.patch new file mode 100644 index 0000000000..6ef752cf12 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0087-wireguard-selftests-reduce-complexity-and-fix-make-r.patch @@ -0,0 +1,105 @@ +From 871a6ff0cd8f9edad483b8f467c0abe6cff32390 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 14 Feb 2020 23:57:20 +0100 +Subject: [PATCH 087/124] wireguard: selftests: reduce complexity and fix make + races + +commit 04ddf1208f03e1dbc39a4619c40eba640051b950 upstream. + +This gives us fewer dependencies and shortens build time, fixes up some +hash checking race conditions, and also fixes missing directory creation +that caused issues on massively parallel builds. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + .../testing/selftests/wireguard/qemu/Makefile | 38 +++++++------------ + 1 file changed, 14 insertions(+), 24 deletions(-) + +--- a/tools/testing/selftests/wireguard/qemu/Makefile ++++ b/tools/testing/selftests/wireguard/qemu/Makefile +@@ -38,19 +38,17 @@ endef + define file_download = + $(DISTFILES_PATH)/$(1): + mkdir -p $(DISTFILES_PATH) +- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' +- if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi ++ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' + endef + + $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) +-$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) + $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) + $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) + $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) + $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) + $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) + $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) +-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) ++$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) + + KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) + rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +@@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH + $(MAKE) -C $(IPERF_PATH) + $(STRIP) -s $@ + +-$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) +- flock -s $<.lock tar -C $(BUILD_PATH) -xf $< +- touch $@ +- +-$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) +- cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared +- $(MAKE) -C $(LIBMNL_PATH) +- sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc +- + $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) ++ mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +-$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) +- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg ++$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS) ++ $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg + $(STRIP) -s $@ + + $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) +@@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.insta + $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< +- printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk ++ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk + printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile + touch $@ + +-$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) +- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip +- $(STRIP) -s $(IPROUTE2_PATH)/ip/ip +- +-$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) +- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss +- $(STRIP) -s $(IPROUTE2_PATH)/misc/ss ++$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) ++ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip ++ $(STRIP) -s $@ ++ ++$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) ++ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss ++ $(STRIP) -s $@ + + $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) + mkdir -p $(BUILD_PATH) +@@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_ + sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure + touch $@ + +-$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) +- cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include ++$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS) ++ cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include + $(MAKE) -C $(IPTABLES_PATH) + $(STRIP) -s $@ + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0088-wireguard-receive-reset-last_under_load-to-zero.patch b/target/linux/generic/backport-5.4/080-wireguard-0088-wireguard-receive-reset-last_under_load-to-zero.patch new file mode 100644 index 0000000000..2f3e6a3c9a --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0088-wireguard-receive-reset-last_under_load-to-zero.patch @@ -0,0 +1,38 @@ +From b3969f204f6f3e1b712d4892050abf35ad178ccc Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 14 Feb 2020 23:57:21 +0100 +Subject: [PATCH 088/124] wireguard: receive: reset last_under_load to zero + +commit 2a8a4df36462aa85b0db87b7c5ea145ba67e34a8 upstream. + +This is a small optimization that prevents more expensive comparisons +from happening when they are no longer necessary, by clearing the +last_under_load variable whenever we wind up in a state where we were +under load but we no longer are. + +Signed-off-by: Jason A. Donenfeld +Suggested-by: Matt Dunwoodie +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -118,10 +118,13 @@ static void wg_receive_handshake_packet( + + under_load = skb_queue_len(&wg->incoming_handshakes) >= + MAX_QUEUED_INCOMING_HANDSHAKES / 8; +- if (under_load) ++ if (under_load) { + last_under_load = ktime_get_coarse_boottime_ns(); +- else if (last_under_load) ++ } else if (last_under_load) { + under_load = !wg_birthdate_has_expired(last_under_load, 1); ++ if (!under_load) ++ last_under_load = 0; ++ } + mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb, + under_load); + if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) || diff --git a/target/linux/generic/backport-5.4/080-wireguard-0089-wireguard-send-account-for-mtu-0-devices.patch b/target/linux/generic/backport-5.4/080-wireguard-0089-wireguard-send-account-for-mtu-0-devices.patch new file mode 100644 index 0000000000..012a6a1d76 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0089-wireguard-send-account-for-mtu-0-devices.patch @@ -0,0 +1,95 @@ +From 6e82ecb98d019209c77c73d0460535f1fcb3d8cc Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 14 Feb 2020 23:57:22 +0100 +Subject: [PATCH 089/124] wireguard: send: account for mtu=0 devices + +commit 175f1ca9a9ed8689d2028da1a7c624bb4fb4ff7e upstream. + +It turns out there's an easy way to get packets queued up while still +having an MTU of zero, and that's via persistent keep alive. This commit +makes sure that in whatever condition, we don't wind up dividing by +zero. Note that an MTU of zero for a wireguard interface is something +quasi-valid, so I don't think the correct fix is to limit it via +min_mtu. This can be reproduced easily with: + +ip link add wg0 type wireguard +ip link add wg1 type wireguard +ip link set wg0 up mtu 0 +ip link set wg1 up +wg set wg0 private-key <(wg genkey) +wg set wg1 listen-port 1 private-key <(wg genkey) peer $(wg show wg0 public-key) +wg set wg0 peer $(wg show wg1 public-key) persistent-keepalive 1 endpoint 127.0.0.1:1 + +However, while min_mtu=0 seems fine, it makes sense to restrict the +max_mtu. This commit also restricts the maximum MTU to the greatest +number for which rounding up to the padding multiple won't overflow a +signed integer. Packets this large were always rejected anyway +eventually, due to checks deeper in, but it seems more sound not to even +let the administrator configure something that won't work anyway. + +We use this opportunity to clean up this function a bit so that it's +clear which paths we're expecting. + +Signed-off-by: Jason A. Donenfeld +Cc: Eric Dumazet +Reviewed-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 7 ++++--- + drivers/net/wireguard/send.c | 16 +++++++++++----- + 2 files changed, 15 insertions(+), 8 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -258,6 +258,8 @@ static void wg_setup(struct net_device * + enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | + NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; ++ const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + ++ max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); + + dev->netdev_ops = &netdev_ops; + dev->hard_header_len = 0; +@@ -271,9 +273,8 @@ static void wg_setup(struct net_device * + dev->features |= WG_NETDEV_FEATURES; + dev->hw_features |= WG_NETDEV_FEATURES; + dev->hw_enc_features |= WG_NETDEV_FEATURES; +- dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH - +- sizeof(struct udphdr) - +- max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); ++ dev->mtu = ETH_DATA_LEN - overhead; ++ dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; + + SET_NETDEV_DEVTYPE(dev, &device_type); + +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -143,16 +143,22 @@ static void keep_key_fresh(struct wg_pee + + static unsigned int calculate_skb_padding(struct sk_buff *skb) + { ++ unsigned int padded_size, last_unit = skb->len; ++ ++ if (unlikely(!PACKET_CB(skb)->mtu)) ++ return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; ++ + /* We do this modulo business with the MTU, just in case the networking + * layer gives us a packet that's bigger than the MTU. In that case, we + * wouldn't want the final subtraction to overflow in the case of the +- * padded_size being clamped. ++ * padded_size being clamped. Fortunately, that's very rarely the case, ++ * so we optimize for that not happening. + */ +- unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu; +- unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE); ++ if (unlikely(last_unit > PACKET_CB(skb)->mtu)) ++ last_unit %= PACKET_CB(skb)->mtu; + +- if (padded_size > PACKET_CB(skb)->mtu) +- padded_size = PACKET_CB(skb)->mtu; ++ padded_size = min(PACKET_CB(skb)->mtu, ++ ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); + return padded_size - last_unit; + } + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0090-wireguard-socket-remove-extra-call-to-synchronize_ne.patch b/target/linux/generic/backport-5.4/080-wireguard-0090-wireguard-socket-remove-extra-call-to-synchronize_ne.patch new file mode 100644 index 0000000000..542a9ca1fd --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0090-wireguard-socket-remove-extra-call-to-synchronize_ne.patch @@ -0,0 +1,33 @@ +From ce6c6fa0d2dd4ca9c500e6240e4f22c48018a0ae Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Fri, 14 Feb 2020 23:57:23 +0100 +Subject: [PATCH 090/124] wireguard: socket: remove extra call to + synchronize_net + +commit 1fbc33b0a7feb6ca72bf7dc8a05d81485ee8ee2e upstream. + +synchronize_net() is a wrapper around synchronize_rcu(), so there's no +point in having synchronize_net and synchronize_rcu back to back, +despite the documentation comment suggesting maybe it's somewhat useful, +"Wait for packets currently being received to be done." This commit +removes the extra call. + +Signed-off-by: Jason A. Donenfeld +Suggested-by: Eric Dumazet +Reviewed-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/socket.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/drivers/net/wireguard/socket.c ++++ b/drivers/net/wireguard/socket.c +@@ -432,7 +432,6 @@ void wg_socket_reinit(struct wg_device * + wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); + mutex_unlock(&wg->socket_update_lock); + synchronize_rcu(); +- synchronize_net(); + sock_free(old4); + sock_free(old6); + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0091-wireguard-selftests-remove-duplicated-include-sys-ty.patch b/target/linux/generic/backport-5.4/080-wireguard-0091-wireguard-selftests-remove-duplicated-include-sys-ty.patch new file mode 100644 index 0000000000..a7b2d70589 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0091-wireguard-selftests-remove-duplicated-include-sys-ty.patch @@ -0,0 +1,28 @@ +From 4c680d3ca400288018c9b9fff0c5df4dbed96e84 Mon Sep 17 00:00:00 2001 +From: YueHaibing +Date: Wed, 18 Mar 2020 18:30:43 -0600 +Subject: [PATCH 091/124] wireguard: selftests: remove duplicated include + + +commit 166391159c5deb84795d2ff46e95f276177fa5fb upstream. + +This commit removes a duplicated include. + +Signed-off-by: YueHaibing +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/qemu/init.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/tools/testing/selftests/wireguard/qemu/init.c ++++ b/tools/testing/selftests/wireguard/qemu/init.c +@@ -13,7 +13,6 @@ + #include + #include + #include +-#include + #include + #include + #include diff --git a/target/linux/generic/backport-5.4/080-wireguard-0092-wireguard-queueing-account-for-skb-protocol-0.patch b/target/linux/generic/backport-5.4/080-wireguard-0092-wireguard-queueing-account-for-skb-protocol-0.patch new file mode 100644 index 0000000000..7826e34759 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0092-wireguard-queueing-account-for-skb-protocol-0.patch @@ -0,0 +1,100 @@ +From db7e2e9ced3df1fb9286946914183f6a074a2b92 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 18 Mar 2020 18:30:45 -0600 +Subject: [PATCH 092/124] wireguard: queueing: account for skb->protocol==0 + +commit a5588604af448664e796daf3c1d5a4523c60667b upstream. + +We carry out checks to the effect of: + + if (skb->protocol != wg_examine_packet_protocol(skb)) + goto err; + +By having wg_skb_examine_untrusted_ip_hdr return 0 on failure, this +means that the check above still passes in the case where skb->protocol +is zero, which is possible to hit with AF_PACKET: + + struct sockaddr_pkt saddr = { .spkt_device = "wg0" }; + unsigned char buffer[5] = { 0 }; + sendto(socket(AF_PACKET, SOCK_PACKET, /* skb->protocol = */ 0), + buffer, sizeof(buffer), 0, (const struct sockaddr *)&saddr, sizeof(saddr)); + +Additional checks mean that this isn't actually a problem in the code +base, but I could imagine it becoming a problem later if the function is +used more liberally. + +I would prefer to fix this by having wg_examine_packet_protocol return a +32-bit ~0 value on failure, which will never match any value of +skb->protocol, which would simply change the generated code from a mov +to a movzx. However, sparse complains, and adding __force casts doesn't +seem like a good idea, so instead we just add a simple helper function +to check for the zero return value. Since wg_examine_packet_protocol +itself gets inlined, this winds up not adding an additional branch to +the generated code, since the 0 return value already happens in a +mergable branch. + +Reported-by: Fabian Freyer +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 2 +- + drivers/net/wireguard/queueing.h | 8 +++++++- + drivers/net/wireguard/receive.c | 4 ++-- + 3 files changed, 10 insertions(+), 4 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -122,7 +122,7 @@ static netdev_tx_t wg_xmit(struct sk_buf + u32 mtu; + int ret; + +- if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) { ++ if (unlikely(!wg_check_packet_protocol(skb))) { + ret = -EPROTONOSUPPORT; + net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); + goto err; +--- a/drivers/net/wireguard/queueing.h ++++ b/drivers/net/wireguard/queueing.h +@@ -66,7 +66,7 @@ struct packet_cb { + #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) + + /* Returns either the correct skb->protocol value, or 0 if invalid. */ +-static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb) ++static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb) + { + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct iphdr)) <= +@@ -81,6 +81,12 @@ static inline __be16 wg_skb_examine_untr + return 0; + } + ++static inline bool wg_check_packet_protocol(struct sk_buff *skb) ++{ ++ __be16 real_protocol = wg_examine_packet_protocol(skb); ++ return real_protocol && skb->protocol == real_protocol; ++} ++ + static inline void wg_reset_packet(struct sk_buff *skb) + { + skb_scrub_packet(skb, true); +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -56,7 +56,7 @@ static int prepare_skb_header(struct sk_ + size_t data_offset, data_len, header_len; + struct udphdr *udp; + +- if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol || ++ if (unlikely(!wg_check_packet_protocol(skb) || + skb_transport_header(skb) < skb->head || + (skb_transport_header(skb) + sizeof(struct udphdr)) > + skb_tail_pointer(skb))) +@@ -388,7 +388,7 @@ static void wg_packet_consume_data_done( + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = ~0; /* All levels */ +- skb->protocol = wg_skb_examine_untrusted_ip_hdr(skb); ++ skb->protocol = wg_examine_packet_protocol(skb); + if (skb->protocol == htons(ETH_P_IP)) { + len = ntohs(ip_hdr(skb)->tot_len); + if (unlikely(len < sizeof(struct iphdr))) diff --git a/target/linux/generic/backport-5.4/080-wireguard-0093-wireguard-receive-remove-dead-code-from-default-pack.patch b/target/linux/generic/backport-5.4/080-wireguard-0093-wireguard-receive-remove-dead-code-from-default-pack.patch new file mode 100644 index 0000000000..ed4c4a017e --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0093-wireguard-receive-remove-dead-code-from-default-pack.patch @@ -0,0 +1,35 @@ +From 827489b9186ac53ed1e162c7d9b0f7b19d1a5995 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 18 Mar 2020 18:30:46 -0600 +Subject: [PATCH 093/124] wireguard: receive: remove dead code from default + packet type case + +commit 2b8765c52db24c0fbcc81bac9b5e8390f2c7d3c8 upstream. + +The situation in which we wind up hitting the default case here +indicates a major bug in earlier parsing code. It is not a usual thing +that should ever happen, which means a "friendly" message for it doesn't +make sense. Rather, replace this with a WARN_ON, just like we do earlier +in the file for a similar situation, so that somebody sends us a bug +report and we can fix it. + +Reported-by: Fabian Freyer +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -587,8 +587,7 @@ void wg_packet_receive(struct wg_device + wg_packet_consume_data(wg, skb); + break; + default: +- net_dbg_skb_ratelimited("%s: Invalid packet from %pISpfsc\n", +- wg->dev->name, skb); ++ WARN(1, "Non-exhaustive parsing of packet header lead to unknown packet type!\n"); + goto err; + } + return; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0094-wireguard-noise-error-out-precomputed-DH-during-hand.patch b/target/linux/generic/backport-5.4/080-wireguard-0094-wireguard-noise-error-out-precomputed-DH-during-hand.patch new file mode 100644 index 0000000000..c014fc3a5f --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0094-wireguard-noise-error-out-precomputed-DH-during-hand.patch @@ -0,0 +1,224 @@ +From 3c5c9d96cea67a8dc381e6ca0f5a894f1ce099ea Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 18 Mar 2020 18:30:47 -0600 +Subject: [PATCH 094/124] wireguard: noise: error out precomputed DH during + handshake rather than config + +commit 11a7686aa99c7fe4b3f80f6dcccd54129817984d upstream. + +We precompute the static-static ECDH during configuration time, in order +to save an expensive computation later when receiving network packets. +However, not all ECDH computations yield a contributory result. Prior, +we were just not letting those peers be added to the interface. However, +this creates a strange inconsistency, since it was still possible to add +other weird points, like a valid public key plus a low-order point, and, +like points that result in zeros, a handshake would not complete. In +order to make the behavior more uniform and less surprising, simply +allow all peers to be added. Then, we'll error out later when doing the +crypto if there's an issue. This also adds more separation between the +crypto layer and the configuration layer. + +Discussed-with: Mathias Hall-Andersen +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/netlink.c | 8 +--- + drivers/net/wireguard/noise.c | 55 ++++++++++++---------- + drivers/net/wireguard/noise.h | 12 ++--- + drivers/net/wireguard/peer.c | 7 +-- + tools/testing/selftests/wireguard/netns.sh | 15 ++++-- + 5 files changed, 49 insertions(+), 48 deletions(-) + +--- a/drivers/net/wireguard/netlink.c ++++ b/drivers/net/wireguard/netlink.c +@@ -417,11 +417,7 @@ static int set_peer(struct wg_device *wg + + peer = wg_peer_create(wg, public_key, preshared_key); + if (IS_ERR(peer)) { +- /* Similar to the above, if the key is invalid, we skip +- * it without fanfare, so that services don't need to +- * worry about doing key validation themselves. +- */ +- ret = PTR_ERR(peer) == -EKEYREJECTED ? 0 : PTR_ERR(peer); ++ ret = PTR_ERR(peer); + peer = NULL; + goto out; + } +@@ -575,7 +571,7 @@ static int wg_set_device(struct sk_buff + private_key); + list_for_each_entry_safe(peer, temp, &wg->peer_list, + peer_list) { +- BUG_ON(!wg_noise_precompute_static_static(peer)); ++ wg_noise_precompute_static_static(peer); + wg_noise_expire_current_peer_keypairs(peer); + } + wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); +--- a/drivers/net/wireguard/noise.c ++++ b/drivers/net/wireguard/noise.c +@@ -44,32 +44,23 @@ void __init wg_noise_init(void) + } + + /* Must hold peer->handshake.static_identity->lock */ +-bool wg_noise_precompute_static_static(struct wg_peer *peer) ++void wg_noise_precompute_static_static(struct wg_peer *peer) + { +- bool ret; +- + down_write(&peer->handshake.lock); +- if (peer->handshake.static_identity->has_identity) { +- ret = curve25519( +- peer->handshake.precomputed_static_static, ++ if (!peer->handshake.static_identity->has_identity || ++ !curve25519(peer->handshake.precomputed_static_static, + peer->handshake.static_identity->static_private, +- peer->handshake.remote_static); +- } else { +- u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 }; +- +- ret = curve25519(empty, empty, peer->handshake.remote_static); ++ peer->handshake.remote_static)) + memset(peer->handshake.precomputed_static_static, 0, + NOISE_PUBLIC_KEY_LEN); +- } + up_write(&peer->handshake.lock); +- return ret; + } + +-bool wg_noise_handshake_init(struct noise_handshake *handshake, +- struct noise_static_identity *static_identity, +- const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], +- const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], +- struct wg_peer *peer) ++void wg_noise_handshake_init(struct noise_handshake *handshake, ++ struct noise_static_identity *static_identity, ++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], ++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], ++ struct wg_peer *peer) + { + memset(handshake, 0, sizeof(*handshake)); + init_rwsem(&handshake->lock); +@@ -81,7 +72,7 @@ bool wg_noise_handshake_init(struct nois + NOISE_SYMMETRIC_KEY_LEN); + handshake->static_identity = static_identity; + handshake->state = HANDSHAKE_ZEROED; +- return wg_noise_precompute_static_static(peer); ++ wg_noise_precompute_static_static(peer); + } + + static void handshake_zero(struct noise_handshake *handshake) +@@ -403,6 +394,19 @@ static bool __must_check mix_dh(u8 chain + return true; + } + ++static bool __must_check mix_precomputed_dh(u8 chaining_key[NOISE_HASH_LEN], ++ u8 key[NOISE_SYMMETRIC_KEY_LEN], ++ const u8 precomputed[NOISE_PUBLIC_KEY_LEN]) ++{ ++ static u8 zero_point[NOISE_PUBLIC_KEY_LEN]; ++ if (unlikely(!crypto_memneq(precomputed, zero_point, NOISE_PUBLIC_KEY_LEN))) ++ return false; ++ kdf(chaining_key, key, NULL, precomputed, NOISE_HASH_LEN, ++ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, ++ chaining_key); ++ return true; ++} ++ + static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len) + { + struct blake2s_state blake; +@@ -531,10 +535,9 @@ wg_noise_handshake_create_initiation(str + NOISE_PUBLIC_KEY_LEN, key, handshake->hash); + + /* ss */ +- kdf(handshake->chaining_key, key, NULL, +- handshake->precomputed_static_static, NOISE_HASH_LEN, +- NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, +- handshake->chaining_key); ++ if (!mix_precomputed_dh(handshake->chaining_key, key, ++ handshake->precomputed_static_static)) ++ goto out; + + /* {t} */ + tai64n_now(timestamp); +@@ -595,9 +598,9 @@ wg_noise_handshake_consume_initiation(st + handshake = &peer->handshake; + + /* ss */ +- kdf(chaining_key, key, NULL, handshake->precomputed_static_static, +- NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, +- chaining_key); ++ if (!mix_precomputed_dh(chaining_key, key, ++ handshake->precomputed_static_static)) ++ goto out; + + /* {t} */ + if (!message_decrypt(t, src->encrypted_timestamp, +--- a/drivers/net/wireguard/noise.h ++++ b/drivers/net/wireguard/noise.h +@@ -94,11 +94,11 @@ struct noise_handshake { + struct wg_device; + + void wg_noise_init(void); +-bool wg_noise_handshake_init(struct noise_handshake *handshake, +- struct noise_static_identity *static_identity, +- const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], +- const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], +- struct wg_peer *peer); ++void wg_noise_handshake_init(struct noise_handshake *handshake, ++ struct noise_static_identity *static_identity, ++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], ++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], ++ struct wg_peer *peer); + void wg_noise_handshake_clear(struct noise_handshake *handshake); + static inline void wg_noise_reset_last_sent_handshake(atomic64_t *handshake_ns) + { +@@ -116,7 +116,7 @@ void wg_noise_expire_current_peer_keypai + void wg_noise_set_static_identity_private_key( + struct noise_static_identity *static_identity, + const u8 private_key[NOISE_PUBLIC_KEY_LEN]); +-bool wg_noise_precompute_static_static(struct wg_peer *peer); ++void wg_noise_precompute_static_static(struct wg_peer *peer); + + bool + wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst, +--- a/drivers/net/wireguard/peer.c ++++ b/drivers/net/wireguard/peer.c +@@ -34,11 +34,8 @@ struct wg_peer *wg_peer_create(struct wg + return ERR_PTR(ret); + peer->device = wg; + +- if (!wg_noise_handshake_init(&peer->handshake, &wg->static_identity, +- public_key, preshared_key, peer)) { +- ret = -EKEYREJECTED; +- goto err_1; +- } ++ wg_noise_handshake_init(&peer->handshake, &wg->static_identity, ++ public_key, preshared_key, peer); + if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) + goto err_1; + if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false, +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -527,11 +527,16 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0 + n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 + n0 wg set wg0 peer "$pub2" allowed-ips ::/0 + n0 wg set wg0 peer "$pub2" remove +-low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= ) +-n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer } +-[[ -z $(n0 wg show wg0 peers) ]] +-n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer } +-[[ -z $(n0 wg show wg0 peers) ]] ++for low_order_point in AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38=; do ++ n0 wg set wg0 peer "$low_order_point" persistent-keepalive 1 endpoint 127.0.0.1:1111 ++done ++[[ -n $(n0 wg show wg0 peers) ]] ++exec 4< <(n0 ncat -l -u -p 1111) ++ncat_pid=$! ++waitncatudp $netns0 $ncat_pid ++ip0 link set wg0 up ++! read -r -n 1 -t 2 <&4 || false ++kill $ncat_pid + ip0 link del wg0 + + declare -A objects diff --git a/target/linux/generic/backport-5.4/080-wireguard-0095-wireguard-send-remove-errant-newline-from-packet_enc.patch b/target/linux/generic/backport-5.4/080-wireguard-0095-wireguard-send-remove-errant-newline-from-packet_enc.patch new file mode 100644 index 0000000000..d546cd6afc --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0095-wireguard-send-remove-errant-newline-from-packet_enc.patch @@ -0,0 +1,29 @@ +From 271fd6b0c4c81b844b81bbf4dd49d9e1de2827c2 Mon Sep 17 00:00:00 2001 +From: Sultan Alsawaf +Date: Wed, 29 Apr 2020 14:59:20 -0600 +Subject: [PATCH 095/124] wireguard: send: remove errant newline from + packet_encrypt_worker + +commit d6833e42786e050e7522d6a91a9361e54085897d upstream. + +This commit removes a useless newline at the end of a scope, which +doesn't add anything in the way of organization or readability. + +Signed-off-by: Sultan Alsawaf +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/send.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -304,7 +304,6 @@ void wg_packet_encrypt_worker(struct wor + } + wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, + state); +- + } + } + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0096-wireguard-queueing-cleanup-ptr_ring-in-error-path-of.patch b/target/linux/generic/backport-5.4/080-wireguard-0096-wireguard-queueing-cleanup-ptr_ring-in-error-path-of.patch new file mode 100644 index 0000000000..98ff785f39 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0096-wireguard-queueing-cleanup-ptr_ring-in-error-path-of.patch @@ -0,0 +1,35 @@ +From 08d5c8fc96361389fdd982477aaf6d7c9311f5e0 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 29 Apr 2020 14:59:21 -0600 +Subject: [PATCH 096/124] wireguard: queueing: cleanup ptr_ring in error path + of packet_queue_init + +commit 130c58606171326c81841a49cc913cd354113dd9 upstream. + +Prior, if the alloc_percpu of packet_percpu_multicore_worker_alloc +failed, the previously allocated ptr_ring wouldn't be freed. This commit +adds the missing call to ptr_ring_cleanup in the error case. + +Reported-by: Sultan Alsawaf +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/queueing.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/drivers/net/wireguard/queueing.c ++++ b/drivers/net/wireguard/queueing.c +@@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_qu + if (multicore) { + queue->worker = wg_packet_percpu_multicore_worker_alloc( + function, queue); +- if (!queue->worker) ++ if (!queue->worker) { ++ ptr_ring_cleanup(&queue->ring, NULL); + return -ENOMEM; ++ } + } else { + INIT_WORK(&queue->work, function); + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0097-wireguard-receive-use-tunnel-helpers-for-decapsulati.patch b/target/linux/generic/backport-5.4/080-wireguard-0097-wireguard-receive-use-tunnel-helpers-for-decapsulati.patch new file mode 100644 index 0000000000..300cc01cc3 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0097-wireguard-receive-use-tunnel-helpers-for-decapsulati.patch @@ -0,0 +1,50 @@ +From 274c356580ec1b077ad10212c59a05b6e0b90d97 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= +Date: Wed, 29 Apr 2020 14:59:22 -0600 +Subject: [PATCH 097/124] wireguard: receive: use tunnel helpers for + decapsulating ECN markings +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit eebabcb26ea1e3295704477c6cd4e772c96a9559 upstream. + +WireGuard currently only propagates ECN markings on tunnel decap according +to the old RFC3168 specification. However, the spec has since been updated +in RFC6040 to recommend slightly different decapsulation semantics. This +was implemented in the kernel as a set of common helpers for ECN +decapsulation, so let's just switch over WireGuard to using those, so it +can benefit from this enhancement and any future tweaks. We do not drop +packets with invalid ECN marking combinations, because WireGuard is +frequently used to work around broken ISPs, which could be doing that. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Reported-by: Olivier Tilmans +Cc: Dave Taht +Cc: Rodney W. Grimes +Signed-off-by: Toke Høiland-Jørgensen +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -393,13 +393,11 @@ static void wg_packet_consume_data_done( + len = ntohs(ip_hdr(skb)->tot_len); + if (unlikely(len < sizeof(struct iphdr))) + goto dishonest_packet_size; +- if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) +- IP_ECN_set_ce(ip_hdr(skb)); ++ INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos); + } else if (skb->protocol == htons(ETH_P_IPV6)) { + len = ntohs(ipv6_hdr(skb)->payload_len) + + sizeof(struct ipv6hdr); +- if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) +- IP6_ECN_set_ce(skb, ipv6_hdr(skb)); ++ INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb))); + } else { + goto dishonest_packet_type; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0098-wireguard-selftests-use-normal-kernel-stack-size-on-.patch b/target/linux/generic/backport-5.4/080-wireguard-0098-wireguard-selftests-use-normal-kernel-stack-size-on-.patch new file mode 100644 index 0000000000..6aa6c2ecc4 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0098-wireguard-selftests-use-normal-kernel-stack-size-on-.patch @@ -0,0 +1,29 @@ +From abf11efb5187c0aaa57c37f36db035c840c9c90d Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 6 May 2020 15:33:02 -0600 +Subject: [PATCH 098/124] wireguard: selftests: use normal kernel stack size on + ppc64 + +commit a0fd7cc87a018df1a17f9d3f0bd994c1f22c6b34 upstream. + +While at some point it might have made sense to be running these tests +on ppc64 with 4k stacks, the kernel hasn't actually used 4k stacks on +64-bit powerpc in a long time, and more interesting things that we test +don't really work when we deviate from the default (16k). So, we stop +pushing our luck in this commit, and return to the default instead of +the minimum. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config | 1 + + 1 file changed, 1 insertion(+) + +--- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config ++++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +@@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y + CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" + CONFIG_SECTION_MISMATCH_WARN_ONLY=y + CONFIG_FRAME_WARN=1280 ++CONFIG_THREAD_SHIFT=14 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0099-wireguard-socket-remove-errant-restriction-on-loopin.patch b/target/linux/generic/backport-5.4/080-wireguard-0099-wireguard-socket-remove-errant-restriction-on-loopin.patch new file mode 100644 index 0000000000..887cb5229e --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0099-wireguard-socket-remove-errant-restriction-on-loopin.patch @@ -0,0 +1,162 @@ +From 81676eb0adad9931279470559107f75741ba957c Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 6 May 2020 15:33:03 -0600 +Subject: [PATCH 099/124] wireguard: socket: remove errant restriction on + looping to self + +commit b673e24aad36981f327a6570412ffa7754de8911 upstream. + +It's already possible to create two different interfaces and loop +packets between them. This has always been possible with tunnels in the +kernel, and isn't specific to wireguard. Therefore, the networking stack +already needs to deal with that. At the very least, the packet winds up +exceeding the MTU and is discarded at that point. So, since this is +already something that happens, there's no need to forbid the not very +exceptional case of routing a packet back to the same interface; this +loop is no different than others, and we shouldn't special case it, but +rather rely on generic handling of loops in general. This also makes it +easier to do interesting things with wireguard such as onion routing. + +At the same time, we add a selftest for this, ensuring that both onion +routing works and infinite routing loops do not crash the kernel. We +also add a test case for wireguard interfaces nesting packets and +sending traffic between each other, as well as the loop in this case +too. We make sure to send some throughput-heavy traffic for this use +case, to stress out any possible recursion issues with the locks around +workqueues. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/socket.c | 12 ----- + tools/testing/selftests/wireguard/netns.sh | 54 ++++++++++++++++++++-- + 2 files changed, 51 insertions(+), 15 deletions(-) + +--- a/drivers/net/wireguard/socket.c ++++ b/drivers/net/wireguard/socket.c +@@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, s + net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", + wg->dev->name, &endpoint->addr, ret); + goto err; +- } else if (unlikely(rt->dst.dev == skb->dev)) { +- ip_rt_put(rt); +- ret = -ELOOP; +- net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", +- wg->dev->name, &endpoint->addr); +- goto err; + } + if (cache) + dst_cache_set_ip4(cache, &rt->dst, fl.saddr); +@@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, s + net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", + wg->dev->name, &endpoint->addr, ret); + goto err; +- } else if (unlikely(dst->dev == skb->dev)) { +- dst_release(dst); +- ret = -ELOOP; +- net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", +- wg->dev->name, &endpoint->addr); +- goto err; + } + if (cache) + dst_cache_set_ip6(cache, dst, &fl.saddr); +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -48,8 +48,11 @@ cleanup() { + exec 2>/dev/null + printf "$orig_message_cost" > /proc/sys/net/core/message_cost + ip0 link del dev wg0 ++ ip0 link del dev wg1 + ip1 link del dev wg0 ++ ip1 link del dev wg1 + ip2 link del dev wg0 ++ ip2 link del dev wg1 + local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" + [[ -n $to_kill ]] && kill $to_kill + pp ip netns del $netns1 +@@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2 + key1="$(pp wg genkey)" + key2="$(pp wg genkey)" + key3="$(pp wg genkey)" ++key4="$(pp wg genkey)" + pub1="$(pp wg pubkey <<<"$key1")" + pub2="$(pp wg pubkey <<<"$key2")" + pub3="$(pp wg pubkey <<<"$key3")" ++pub4="$(pp wg pubkey <<<"$key4")" + psk="$(pp wg genpsk)" + [[ -n $key1 && -n $key2 && -n $psk ]] + + configure_peers() { + ip1 addr add 192.168.241.1/24 dev wg0 +- ip1 addr add fd00::1/24 dev wg0 ++ ip1 addr add fd00::1/112 dev wg0 + + ip2 addr add 192.168.241.2/24 dev wg0 +- ip2 addr add fd00::2/24 dev wg0 ++ ip2 addr add fd00::2/112 dev wg0 + + n1 wg set wg0 \ + private-key <(echo "$key1") \ +@@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2 + n1 wg set wg0 private-key <(echo "$key3") + n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove + n1 ping -W 1 -c 1 192.168.241.2 ++n2 wg set wg0 peer "$pub3" remove + +-ip1 link del wg0 ++# Test that we can route wg through wg ++ip1 addr flush dev wg0 ++ip2 addr flush dev wg0 ++ip1 addr add fd00::5:1/112 dev wg0 ++ip2 addr add fd00::5:2/112 dev wg0 ++n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2 ++n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998 ++ip1 link add wg1 type wireguard ++ip2 link add wg1 type wireguard ++ip1 addr add 192.168.241.1/24 dev wg1 ++ip1 addr add fd00::1/112 dev wg1 ++ip2 addr add 192.168.241.2/24 dev wg1 ++ip2 addr add fd00::2/112 dev wg1 ++ip1 link set mtu 1340 up dev wg1 ++ip2 link set mtu 1340 up dev wg1 ++n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5 ++n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5 ++tests ++# Try to set up a routing loop between the two namespaces ++ip1 link set netns $netns0 dev wg1 ++ip0 addr add 192.168.241.1/24 dev wg1 ++ip0 link set up dev wg1 ++n0 ping -W 1 -c 1 192.168.241.2 ++n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 + ip2 link del wg0 ++ip2 link del wg1 ++! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel ++ ++ip0 link del wg1 ++ip1 link del wg0 + + # Test using NAT. We now change the topology to this: + # ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +@@ -282,6 +316,20 @@ pp sleep 3 + n2 ping -W 1 -c 1 192.168.241.1 + n1 wg set wg0 peer "$pub2" persistent-keepalive 0 + ++# Test that onion routing works, even when it loops ++n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 ++ip1 addr add 192.168.242.1/24 dev wg0 ++ip2 link add wg1 type wireguard ++ip2 addr add 192.168.242.2/24 dev wg1 ++n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32 ++ip2 link set wg1 up ++n1 ping -W 1 -c 1 192.168.242.2 ++ip2 link del wg1 ++n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5 ++! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel ++n1 wg set wg0 peer "$pub3" remove ++ip1 addr del 192.168.242.1/24 dev wg0 ++ + # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. + ip1 -6 addr add fc00::9/96 dev vethc + ip1 -6 route add default via fc00::1 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0100-wireguard-send-receive-cond_resched-when-processing-.patch b/target/linux/generic/backport-5.4/080-wireguard-0100-wireguard-send-receive-cond_resched-when-processing-.patch new file mode 100644 index 0000000000..a87a383981 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0100-wireguard-send-receive-cond_resched-when-processing-.patch @@ -0,0 +1,58 @@ +From 3943211e0997b04f1e2ca1a6624391cc72a176bc Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 6 May 2020 15:33:04 -0600 +Subject: [PATCH 100/124] wireguard: send/receive: cond_resched() when + processing worker ringbuffers + +commit 4005f5c3c9d006157ba716594e0d70c88a235c5e upstream. + +Users with pathological hardware reported CPU stalls on CONFIG_ +PREEMPT_VOLUNTARY=y, because the ringbuffers would stay full, meaning +these workers would never terminate. That turned out not to be okay on +systems without forced preemption, which Sultan observed. This commit +adds a cond_resched() to the bottom of each loop iteration, so that +these workers don't hog the core. Note that we don't need this on the +napi poll worker, since that terminates after its budget is expended. + +Suggested-by: Sultan Alsawaf +Reported-by: Wang Jian +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 2 ++ + drivers/net/wireguard/send.c | 4 ++++ + 2 files changed, 6 insertions(+) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -516,6 +516,8 @@ void wg_packet_decrypt_worker(struct wor + &PACKET_CB(skb)->keypair->receiving)) ? + PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; + wg_queue_enqueue_per_peer_napi(skb, state); ++ if (need_resched()) ++ cond_resched(); + } + } + +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -281,6 +281,8 @@ void wg_packet_tx_worker(struct work_str + + wg_noise_keypair_put(keypair, false); + wg_peer_put(peer); ++ if (need_resched()) ++ cond_resched(); + } + } + +@@ -304,6 +306,8 @@ void wg_packet_encrypt_worker(struct wor + } + wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, + state); ++ if (need_resched()) ++ cond_resched(); + } + } + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0101-wireguard-selftests-initalize-ipv6-members-to-NULL-t.patch b/target/linux/generic/backport-5.4/080-wireguard-0101-wireguard-selftests-initalize-ipv6-members-to-NULL-t.patch new file mode 100644 index 0000000000..3d57857ae4 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0101-wireguard-selftests-initalize-ipv6-members-to-NULL-t.patch @@ -0,0 +1,51 @@ +From 7b7da251149dd5fd070255dbf45f8e4f5c2110b8 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 6 May 2020 15:33:05 -0600 +Subject: [PATCH 101/124] wireguard: selftests: initalize ipv6 members to NULL + to squelch clang warning + +commit 4fed818ef54b08d4b29200e416cce65546ad5312 upstream. + +Without setting these to NULL, clang complains in certain +configurations that have CONFIG_IPV6=n: + +In file included from drivers/net/wireguard/ratelimiter.c:223: +drivers/net/wireguard/selftest/ratelimiter.c:173:34: error: variable 'skb6' is uninitialized when used here [-Werror,-Wuninitialized] + ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count); + ^~~~ +drivers/net/wireguard/selftest/ratelimiter.c:123:29: note: initialize the variable 'skb6' to silence this warning + struct sk_buff *skb4, *skb6; + ^ + = NULL +drivers/net/wireguard/selftest/ratelimiter.c:173:40: error: variable 'hdr6' is uninitialized when used here [-Werror,-Wuninitialized] + ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count); + ^~~~ +drivers/net/wireguard/selftest/ratelimiter.c:125:22: note: initialize the variable 'hdr6' to silence this warning + struct ipv6hdr *hdr6; + ^ + +We silence this warning by setting the variables to NULL as the warning +suggests. + +Reported-by: Arnd Bergmann +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/selftest/ratelimiter.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/selftest/ratelimiter.c ++++ b/drivers/net/wireguard/selftest/ratelimiter.c +@@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void + enum { TRIALS_BEFORE_GIVING_UP = 5000 }; + bool success = false; + int test = 0, trials; +- struct sk_buff *skb4, *skb6; ++ struct sk_buff *skb4, *skb6 = NULL; + struct iphdr *hdr4; +- struct ipv6hdr *hdr6; ++ struct ipv6hdr *hdr6 = NULL; + + if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) + return true; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0102-wireguard-send-receive-use-explicit-unlikely-branch-.patch b/target/linux/generic/backport-5.4/080-wireguard-0102-wireguard-send-receive-use-explicit-unlikely-branch-.patch new file mode 100644 index 0000000000..d8ea8908b9 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0102-wireguard-send-receive-use-explicit-unlikely-branch-.patch @@ -0,0 +1,88 @@ +From 8df862b663b026d61b4c463caece77f1f127771f Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 6 May 2020 15:33:06 -0600 +Subject: [PATCH 102/124] wireguard: send/receive: use explicit unlikely branch + instead of implicit coalescing + +commit 243f2148937adc72bcaaa590d482d599c936efde upstream. + +It's very unlikely that send will become true. It's nearly always false +between 0 and 120 seconds of a session, and in most cases becomes true +only between 120 and 121 seconds before becoming false again. So, +unlikely(send) is clearly the right option here. + +What happened before was that we had this complex boolean expression +with multiple likely and unlikely clauses nested. Since this is +evaluated left-to-right anyway, the whole thing got converted to +unlikely. So, we can clean this up to better represent what's going on. + +The generated code is the same. + +Suggested-by: Sultan Alsawaf +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 13 ++++++------- + drivers/net/wireguard/send.c | 15 ++++++--------- + 2 files changed, 12 insertions(+), 16 deletions(-) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -226,21 +226,20 @@ void wg_packet_handshake_receive_worker( + static void keep_key_fresh(struct wg_peer *peer) + { + struct noise_keypair *keypair; +- bool send = false; ++ bool send; + + if (peer->sent_lastminute_handshake) + return; + + rcu_read_lock_bh(); + keypair = rcu_dereference_bh(peer->keypairs.current_keypair); +- if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && +- keypair->i_am_the_initiator && +- unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, +- REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT))) +- send = true; ++ send = keypair && READ_ONCE(keypair->sending.is_valid) && ++ keypair->i_am_the_initiator && ++ wg_birthdate_has_expired(keypair->sending.birthdate, ++ REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT); + rcu_read_unlock_bh(); + +- if (send) { ++ if (unlikely(send)) { + peer->sent_lastminute_handshake = true; + wg_packet_send_queued_handshake_initiation(peer, false); + } +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(str + static void keep_key_fresh(struct wg_peer *peer) + { + struct noise_keypair *keypair; +- bool send = false; ++ bool send; + + rcu_read_lock_bh(); + keypair = rcu_dereference_bh(peer->keypairs.current_keypair); +- if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && +- (unlikely(atomic64_read(&keypair->sending.counter.counter) > +- REKEY_AFTER_MESSAGES) || +- (keypair->i_am_the_initiator && +- unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, +- REKEY_AFTER_TIME))))) +- send = true; ++ send = keypair && READ_ONCE(keypair->sending.is_valid) && ++ (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES || ++ (keypair->i_am_the_initiator && ++ wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); + rcu_read_unlock_bh(); + +- if (send) ++ if (unlikely(send)) + wg_packet_send_queued_handshake_initiation(peer, false); + } + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0103-wireguard-selftests-use-newer-iproute2-for-gcc-10.patch b/target/linux/generic/backport-5.4/080-wireguard-0103-wireguard-selftests-use-newer-iproute2-for-gcc-10.patch new file mode 100644 index 0000000000..4a4d8e8987 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0103-wireguard-selftests-use-newer-iproute2-for-gcc-10.patch @@ -0,0 +1,31 @@ +From 8c0f0162352081c875a7aa86d897e2bb50f6e46d Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 19 May 2020 22:49:27 -0600 +Subject: [PATCH 103/124] wireguard: selftests: use newer iproute2 for gcc-10 + +commit ee3c1aa3f34b7842c1557cfe5d8c3f7b8c692de8 upstream. + +gcc-10 switched to defaulting to -fno-common, which broke iproute2-5.4. +This was fixed in iproute-5.6, so switch to that. Because we're after a +stable testing surface, we generally don't like to bump these +unnecessarily, but in this case, being able to actually build is a basic +necessity. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/qemu/Makefile | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/tools/testing/selftests/wireguard/qemu/Makefile ++++ b/tools/testing/selftests/wireguard/qemu/Makefile +@@ -44,7 +44,7 @@ endef + $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) + $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) + $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) +-$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) ++$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692)) + $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) + $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) + $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) diff --git a/target/linux/generic/backport-5.4/080-wireguard-0104-wireguard-noise-read-preshared-key-while-taking-lock.patch b/target/linux/generic/backport-5.4/080-wireguard-0104-wireguard-noise-read-preshared-key-while-taking-lock.patch new file mode 100644 index 0000000000..33ad677c9e --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0104-wireguard-noise-read-preshared-key-while-taking-lock.patch @@ -0,0 +1,62 @@ +From 5e29ad069218c486737729f88d15e4fe0ca7eb45 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 19 May 2020 22:49:28 -0600 +Subject: [PATCH 104/124] wireguard: noise: read preshared key while taking + lock + +commit bc67d371256f5c47d824e2eec51e46c8d62d022e upstream. + +Prior we read the preshared key after dropping the handshake lock, which +isn't an actual crypto issue if it races, but it's still not quite +correct. So copy that part of the state into a temporary like we do with +the rest of the handshake state variables. Then we can release the lock, +operate on the temporary, and zero it out at the end of the function. In +performance tests, the impact of this was entirely unnoticable, probably +because those bytes are coming from the same cacheline as other things +that are being copied out in the same manner. + +Reported-by: Matt Dunwoodie +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/noise.c | 6 +++++- + 1 file changed, 5 insertions(+), 1 deletion(-) + +--- a/drivers/net/wireguard/noise.c ++++ b/drivers/net/wireguard/noise.c +@@ -715,6 +715,7 @@ wg_noise_handshake_consume_response(stru + u8 e[NOISE_PUBLIC_KEY_LEN]; + u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN]; + u8 static_private[NOISE_PUBLIC_KEY_LEN]; ++ u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]; + + down_read(&wg->static_identity.lock); + +@@ -733,6 +734,8 @@ wg_noise_handshake_consume_response(stru + memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN); + memcpy(ephemeral_private, handshake->ephemeral_private, + NOISE_PUBLIC_KEY_LEN); ++ memcpy(preshared_key, handshake->preshared_key, ++ NOISE_SYMMETRIC_KEY_LEN); + up_read(&handshake->lock); + + if (state != HANDSHAKE_CREATED_INITIATION) +@@ -750,7 +753,7 @@ wg_noise_handshake_consume_response(stru + goto fail; + + /* psk */ +- mix_psk(chaining_key, hash, key, handshake->preshared_key); ++ mix_psk(chaining_key, hash, key, preshared_key); + + /* {} */ + if (!message_decrypt(NULL, src->encrypted_nothing, +@@ -783,6 +786,7 @@ out: + memzero_explicit(chaining_key, NOISE_HASH_LEN); + memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN); + memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN); ++ memzero_explicit(preshared_key, NOISE_SYMMETRIC_KEY_LEN); + up_read(&wg->static_identity.lock); + return ret_peer; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0105-wireguard-queueing-preserve-flow-hash-across-packet-.patch b/target/linux/generic/backport-5.4/080-wireguard-0105-wireguard-queueing-preserve-flow-hash-across-packet-.patch new file mode 100644 index 0000000000..5834425d12 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0105-wireguard-queueing-preserve-flow-hash-across-packet-.patch @@ -0,0 +1,116 @@ +From a6fedb7ce9e487edae4c35b70e2d3a5bb2342fec Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 19 May 2020 22:49:29 -0600 +Subject: [PATCH 105/124] wireguard: queueing: preserve flow hash across packet + scrubbing +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit c78a0b4a78839d572d8a80f6a62221c0d7843135 upstream. + +It's important that we clear most header fields during encapsulation and +decapsulation, because the packet is substantially changed, and we don't +want any info leak or logic bug due to an accidental correlation. But, +for encapsulation, it's wrong to clear skb->hash, since it's used by +fq_codel and flow dissection in general. Without it, classification does +not proceed as usual. This change might make it easier to estimate the +number of innerflows by examining clustering of out of order packets, +but this shouldn't open up anything that can't already be inferred +otherwise (e.g. syn packet size inference), and fq_codel can be disabled +anyway. + +Furthermore, it might be the case that the hash isn't used or queried at +all until after wireguard transmits the encrypted UDP packet, which +means skb->hash might still be zero at this point, and thus no hash +taken over the inner packet data. In order to address this situation, we +force a calculation of skb->hash before encrypting packet data. + +Of course this means that fq_codel might transmit packets slightly more +out of order than usual. Toke did some testing on beefy machines with +high quantities of parallel flows and found that increasing the +reply-attack counter to 8192 takes care of the most pathological cases +pretty well. + +Reported-by: Dave Taht +Reviewed-and-tested-by: Toke Høiland-Jørgensen +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/messages.h | 2 +- + drivers/net/wireguard/queueing.h | 10 +++++++++- + drivers/net/wireguard/receive.c | 2 +- + drivers/net/wireguard/send.c | 7 ++++++- + 4 files changed, 17 insertions(+), 4 deletions(-) + +--- a/drivers/net/wireguard/messages.h ++++ b/drivers/net/wireguard/messages.h +@@ -32,7 +32,7 @@ enum cookie_values { + }; + + enum counter_values { +- COUNTER_BITS_TOTAL = 2048, ++ COUNTER_BITS_TOTAL = 8192, + COUNTER_REDUNDANT_BITS = BITS_PER_LONG, + COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS + }; +--- a/drivers/net/wireguard/queueing.h ++++ b/drivers/net/wireguard/queueing.h +@@ -87,12 +87,20 @@ static inline bool wg_check_packet_proto + return real_protocol && skb->protocol == real_protocol; + } + +-static inline void wg_reset_packet(struct sk_buff *skb) ++static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating) + { ++ u8 l4_hash = skb->l4_hash; ++ u8 sw_hash = skb->sw_hash; ++ u32 hash = skb->hash; + skb_scrub_packet(skb, true); + memset(&skb->headers_start, 0, + offsetof(struct sk_buff, headers_end) - + offsetof(struct sk_buff, headers_start)); ++ if (encapsulating) { ++ skb->l4_hash = l4_hash; ++ skb->sw_hash = sw_hash; ++ skb->hash = hash; ++ } + skb->queue_mapping = 0; + skb->nohdr = 0; + skb->peeked = 0; +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -484,7 +484,7 @@ int wg_packet_rx_poll(struct napi_struct + if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb))) + goto next; + +- wg_reset_packet(skb); ++ wg_reset_packet(skb, false); + wg_packet_consume_data_done(peer, skb, &endpoint); + free = false; + +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -167,6 +167,11 @@ static bool encrypt_packet(struct sk_buf + struct sk_buff *trailer; + int num_frags; + ++ /* Force hash calculation before encryption so that flow analysis is ++ * consistent over the inner packet. ++ */ ++ skb_get_hash(skb); ++ + /* Calculate lengths. */ + padding_len = calculate_skb_padding(skb); + trailer_len = padding_len + noise_encrypted_len(0); +@@ -295,7 +300,7 @@ void wg_packet_encrypt_worker(struct wor + skb_list_walk_safe(first, skb, next) { + if (likely(encrypt_packet(skb, + PACKET_CB(first)->keypair))) { +- wg_reset_packet(skb); ++ wg_reset_packet(skb, true); + } else { + state = PACKET_STATE_DEAD; + break; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0106-wireguard-noise-separate-receive-counter-from-send-c.patch b/target/linux/generic/backport-5.4/080-wireguard-0106-wireguard-noise-separate-receive-counter-from-send-c.patch new file mode 100644 index 0000000000..d72e9f8218 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0106-wireguard-noise-separate-receive-counter-from-send-c.patch @@ -0,0 +1,331 @@ +From 044b98abbb08fabca5c2cff426023f1f52448efc Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 19 May 2020 22:49:30 -0600 +Subject: [PATCH 106/124] wireguard: noise: separate receive counter from send + counter + +commit a9e90d9931f3a474f04bab782ccd9d77904941e9 upstream. + +In "wireguard: queueing: preserve flow hash across packet scrubbing", we +were required to slightly increase the size of the receive replay +counter to something still fairly small, but an increase nonetheless. +It turns out that we can recoup some of the additional memory overhead +by splitting up the prior union type into two distinct types. Before, we +used the same "noise_counter" union for both sending and receiving, with +sending just using a simple atomic64_t, while receiving used the full +replay counter checker. This meant that most of the memory being +allocated for the sending counter was being wasted. Since the old +"noise_counter" type increased in size in the prior commit, now is a +good time to split up that union type into a distinct "noise_replay_ +counter" for receiving and a boring atomic64_t for sending, each using +neither more nor less memory than required. + +Also, since sometimes the replay counter is accessed without +necessitating additional accesses to the bitmap, we can reduce cache +misses by hoisting the always-necessary lock above the bitmap in the +struct layout. We also change a "noise_replay_counter" stack allocation +to kmalloc in a -DDEBUG selftest so that KASAN doesn't trigger a stack +frame warning. + +All and all, removing a bit of abstraction in this commit makes the code +simpler and smaller, in addition to the motivating memory usage +recuperation. For example, passing around raw "noise_symmetric_key" +structs is something that really only makes sense within noise.c, in the +one place where the sending and receiving keys can safely be thought of +as the same type of object; subsequent to that, it's important that we +uniformly access these through keypair->{sending,receiving}, where their +distinct roles are always made explicit. So this patch allows us to draw +that distinction clearly as well. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/noise.c | 16 +++------ + drivers/net/wireguard/noise.h | 14 ++++---- + drivers/net/wireguard/receive.c | 42 ++++++++++++------------ + drivers/net/wireguard/selftest/counter.c | 17 +++++++--- + drivers/net/wireguard/send.c | 12 +++---- + 5 files changed, 48 insertions(+), 53 deletions(-) + +--- a/drivers/net/wireguard/noise.c ++++ b/drivers/net/wireguard/noise.c +@@ -104,6 +104,7 @@ static struct noise_keypair *keypair_cre + + if (unlikely(!keypair)) + return NULL; ++ spin_lock_init(&keypair->receiving_counter.lock); + keypair->internal_id = atomic64_inc_return(&keypair_counter); + keypair->entry.type = INDEX_HASHTABLE_KEYPAIR; + keypair->entry.peer = peer; +@@ -358,25 +359,16 @@ out: + memzero_explicit(output, BLAKE2S_HASH_SIZE + 1); + } + +-static void symmetric_key_init(struct noise_symmetric_key *key) +-{ +- spin_lock_init(&key->counter.receive.lock); +- atomic64_set(&key->counter.counter, 0); +- memset(key->counter.receive.backtrack, 0, +- sizeof(key->counter.receive.backtrack)); +- key->birthdate = ktime_get_coarse_boottime_ns(); +- key->is_valid = true; +-} +- + static void derive_keys(struct noise_symmetric_key *first_dst, + struct noise_symmetric_key *second_dst, + const u8 chaining_key[NOISE_HASH_LEN]) + { ++ u64 birthdate = ktime_get_coarse_boottime_ns(); + kdf(first_dst->key, second_dst->key, NULL, NULL, + NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0, + chaining_key); +- symmetric_key_init(first_dst); +- symmetric_key_init(second_dst); ++ first_dst->birthdate = second_dst->birthdate = birthdate; ++ first_dst->is_valid = second_dst->is_valid = true; + } + + static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN], +--- a/drivers/net/wireguard/noise.h ++++ b/drivers/net/wireguard/noise.h +@@ -15,18 +15,14 @@ + #include + #include + +-union noise_counter { +- struct { +- u64 counter; +- unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG]; +- spinlock_t lock; +- } receive; +- atomic64_t counter; ++struct noise_replay_counter { ++ u64 counter; ++ spinlock_t lock; ++ unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG]; + }; + + struct noise_symmetric_key { + u8 key[NOISE_SYMMETRIC_KEY_LEN]; +- union noise_counter counter; + u64 birthdate; + bool is_valid; + }; +@@ -34,7 +30,9 @@ struct noise_symmetric_key { + struct noise_keypair { + struct index_hashtable_entry entry; + struct noise_symmetric_key sending; ++ atomic64_t sending_counter; + struct noise_symmetric_key receiving; ++ struct noise_replay_counter receiving_counter; + __le32 remote_index; + bool i_am_the_initiator; + struct kref refcount; +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -245,20 +245,20 @@ static void keep_key_fresh(struct wg_pee + } + } + +-static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key) ++static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) + { + struct scatterlist sg[MAX_SKB_FRAGS + 8]; + struct sk_buff *trailer; + unsigned int offset; + int num_frags; + +- if (unlikely(!key)) ++ if (unlikely(!keypair)) + return false; + +- if (unlikely(!READ_ONCE(key->is_valid) || +- wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) || +- key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) { +- WRITE_ONCE(key->is_valid, false); ++ if (unlikely(!READ_ONCE(keypair->receiving.is_valid) || ++ wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) || ++ keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) { ++ WRITE_ONCE(keypair->receiving.is_valid, false); + return false; + } + +@@ -283,7 +283,7 @@ static bool decrypt_packet(struct sk_buf + + if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0, + PACKET_CB(skb)->nonce, +- key->key)) ++ keypair->receiving.key)) + return false; + + /* Another ugly situation of pushing and pulling the header so as to +@@ -298,41 +298,41 @@ static bool decrypt_packet(struct sk_buf + } + + /* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */ +-static bool counter_validate(union noise_counter *counter, u64 their_counter) ++static bool counter_validate(struct noise_replay_counter *counter, u64 their_counter) + { + unsigned long index, index_current, top, i; + bool ret = false; + +- spin_lock_bh(&counter->receive.lock); ++ spin_lock_bh(&counter->lock); + +- if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 || ++ if (unlikely(counter->counter >= REJECT_AFTER_MESSAGES + 1 || + their_counter >= REJECT_AFTER_MESSAGES)) + goto out; + + ++their_counter; + + if (unlikely((COUNTER_WINDOW_SIZE + their_counter) < +- counter->receive.counter)) ++ counter->counter)) + goto out; + + index = their_counter >> ilog2(BITS_PER_LONG); + +- if (likely(their_counter > counter->receive.counter)) { +- index_current = counter->receive.counter >> ilog2(BITS_PER_LONG); ++ if (likely(their_counter > counter->counter)) { ++ index_current = counter->counter >> ilog2(BITS_PER_LONG); + top = min_t(unsigned long, index - index_current, + COUNTER_BITS_TOTAL / BITS_PER_LONG); + for (i = 1; i <= top; ++i) +- counter->receive.backtrack[(i + index_current) & ++ counter->backtrack[(i + index_current) & + ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; +- counter->receive.counter = their_counter; ++ counter->counter = their_counter; + } + + index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; + ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1), +- &counter->receive.backtrack[index]); ++ &counter->backtrack[index]); + + out: +- spin_unlock_bh(&counter->receive.lock); ++ spin_unlock_bh(&counter->lock); + return ret; + } + +@@ -472,12 +472,12 @@ int wg_packet_rx_poll(struct napi_struct + if (unlikely(state != PACKET_STATE_CRYPTED)) + goto next; + +- if (unlikely(!counter_validate(&keypair->receiving.counter, ++ if (unlikely(!counter_validate(&keypair->receiving_counter, + PACKET_CB(skb)->nonce))) { + net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", + peer->device->dev->name, + PACKET_CB(skb)->nonce, +- keypair->receiving.counter.receive.counter); ++ keypair->receiving_counter.counter); + goto next; + } + +@@ -511,8 +511,8 @@ void wg_packet_decrypt_worker(struct wor + struct sk_buff *skb; + + while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) { +- enum packet_state state = likely(decrypt_packet(skb, +- &PACKET_CB(skb)->keypair->receiving)) ? ++ enum packet_state state = ++ likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ? + PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; + wg_queue_enqueue_per_peer_napi(skb, state); + if (need_resched()) +--- a/drivers/net/wireguard/selftest/counter.c ++++ b/drivers/net/wireguard/selftest/counter.c +@@ -6,18 +6,24 @@ + #ifdef DEBUG + bool __init wg_packet_counter_selftest(void) + { ++ struct noise_replay_counter *counter; + unsigned int test_num = 0, i; +- union noise_counter counter; + bool success = true; + +-#define T_INIT do { \ +- memset(&counter, 0, sizeof(union noise_counter)); \ +- spin_lock_init(&counter.receive.lock); \ ++ counter = kmalloc(sizeof(*counter), GFP_KERNEL); ++ if (unlikely(!counter)) { ++ pr_err("nonce counter self-test malloc: FAIL\n"); ++ return false; ++ } ++ ++#define T_INIT do { \ ++ memset(counter, 0, sizeof(*counter)); \ ++ spin_lock_init(&counter->lock); \ + } while (0) + #define T_LIM (COUNTER_WINDOW_SIZE + 1) + #define T(n, v) do { \ + ++test_num; \ +- if (counter_validate(&counter, n) != (v)) { \ ++ if (counter_validate(counter, n) != (v)) { \ + pr_err("nonce counter self-test %u: FAIL\n", \ + test_num); \ + success = false; \ +@@ -99,6 +105,7 @@ bool __init wg_packet_counter_selftest(v + + if (success) + pr_info("nonce counter self-tests: pass\n"); ++ kfree(counter); + return success; + } + #endif +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -129,7 +129,7 @@ static void keep_key_fresh(struct wg_pee + rcu_read_lock_bh(); + keypair = rcu_dereference_bh(peer->keypairs.current_keypair); + send = keypair && READ_ONCE(keypair->sending.is_valid) && +- (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES || ++ (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES || + (keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); + rcu_read_unlock_bh(); +@@ -349,7 +349,6 @@ void wg_packet_purge_staged_packets(stru + + void wg_packet_send_staged_packets(struct wg_peer *peer) + { +- struct noise_symmetric_key *key; + struct noise_keypair *keypair; + struct sk_buff_head packets; + struct sk_buff *skb; +@@ -369,10 +368,9 @@ void wg_packet_send_staged_packets(struc + rcu_read_unlock_bh(); + if (unlikely(!keypair)) + goto out_nokey; +- key = &keypair->sending; +- if (unlikely(!READ_ONCE(key->is_valid))) ++ if (unlikely(!READ_ONCE(keypair->sending.is_valid))) + goto out_nokey; +- if (unlikely(wg_birthdate_has_expired(key->birthdate, ++ if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, + REJECT_AFTER_TIME))) + goto out_invalid; + +@@ -387,7 +385,7 @@ void wg_packet_send_staged_packets(struc + */ + PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); + PACKET_CB(skb)->nonce = +- atomic64_inc_return(&key->counter.counter) - 1; ++ atomic64_inc_return(&keypair->sending_counter) - 1; + if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) + goto out_invalid; + } +@@ -399,7 +397,7 @@ void wg_packet_send_staged_packets(struc + return; + + out_invalid: +- WRITE_ONCE(key->is_valid, false); ++ WRITE_ONCE(keypair->sending.is_valid, false); + out_nokey: + wg_noise_keypair_put(keypair, false); + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0107-wireguard-noise-do-not-assign-initiation-time-in-if-.patch b/target/linux/generic/backport-5.4/080-wireguard-0107-wireguard-noise-do-not-assign-initiation-time-in-if-.patch new file mode 100644 index 0000000000..b549b32258 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0107-wireguard-noise-do-not-assign-initiation-time-in-if-.patch @@ -0,0 +1,33 @@ +From adb4079f56d1f6c7d4dc827d7eba14e3436512f9 Mon Sep 17 00:00:00 2001 +From: Frank Werner-Krippendorf +Date: Tue, 23 Jun 2020 03:59:44 -0600 +Subject: [PATCH 107/124] wireguard: noise: do not assign initiation time in if + condition + +commit 558b353c9c2a717509f291c066c6bd8f5f5e21be upstream. + +Fixes an error condition reported by checkpatch.pl which caused by +assigning a variable in an if condition in wg_noise_handshake_consume_ +initiation(). + +Signed-off-by: Frank Werner-Krippendorf +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/noise.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/noise.c ++++ b/drivers/net/wireguard/noise.c +@@ -617,8 +617,8 @@ wg_noise_handshake_consume_initiation(st + memcpy(handshake->hash, hash, NOISE_HASH_LEN); + memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN); + handshake->remote_index = src->sender_index; +- if ((s64)(handshake->last_initiation_consumption - +- (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0) ++ initiation_consumption = ktime_get_coarse_boottime_ns(); ++ if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0) + handshake->last_initiation_consumption = initiation_consumption; + handshake->state = HANDSHAKE_CONSUMED_INITIATION; + up_write(&handshake->lock); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0108-wireguard-device-avoid-circular-netns-references.patch b/target/linux/generic/backport-5.4/080-wireguard-0108-wireguard-device-avoid-circular-netns-references.patch new file mode 100644 index 0000000000..8021b9bf23 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0108-wireguard-device-avoid-circular-netns-references.patch @@ -0,0 +1,296 @@ +From 40d881393cfc6953778691444ab27a29d51d24aa Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Tue, 23 Jun 2020 03:59:45 -0600 +Subject: [PATCH 108/124] wireguard: device: avoid circular netns references + +commit 900575aa33a3eaaef802b31de187a85c4a4b4bd0 upstream. + +Before, we took a reference to the creating netns if the new netns was +different. This caused issues with circular references, with two +wireguard interfaces swapping namespaces. The solution is to rather not +take any extra references at all, but instead simply invalidate the +creating netns pointer when that netns is deleted. + +In order to prevent this from happening again, this commit improves the +rough object leak tracking by allowing it to account for created and +destroyed interfaces, aside from just peers and keys. That then makes it +possible to check for the object leak when having two interfaces take a +reference to each others' namespaces. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 58 ++++++++++------------ + drivers/net/wireguard/device.h | 3 +- + drivers/net/wireguard/netlink.c | 14 ++++-- + drivers/net/wireguard/socket.c | 25 +++++++--- + tools/testing/selftests/wireguard/netns.sh | 13 ++++- + 5 files changed, 67 insertions(+), 46 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -45,17 +45,18 @@ static int wg_open(struct net_device *de + if (dev_v6) + dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; + ++ mutex_lock(&wg->device_update_lock); + ret = wg_socket_init(wg, wg->incoming_port); + if (ret < 0) +- return ret; +- mutex_lock(&wg->device_update_lock); ++ goto out; + list_for_each_entry(peer, &wg->peer_list, peer_list) { + wg_packet_send_staged_packets(peer); + if (peer->persistent_keepalive_interval) + wg_packet_send_keepalive(peer); + } ++out: + mutex_unlock(&wg->device_update_lock); +- return 0; ++ return ret; + } + + #ifdef CONFIG_PM_SLEEP +@@ -225,6 +226,7 @@ static void wg_destruct(struct net_devic + list_del(&wg->device_list); + rtnl_unlock(); + mutex_lock(&wg->device_update_lock); ++ rcu_assign_pointer(wg->creating_net, NULL); + wg->incoming_port = 0; + wg_socket_reinit(wg, NULL, NULL); + /* The final references are cleared in the below calls to destroy_workqueue. */ +@@ -240,13 +242,11 @@ static void wg_destruct(struct net_devic + skb_queue_purge(&wg->incoming_handshakes); + free_percpu(dev->tstats); + free_percpu(wg->incoming_handshakes_worker); +- if (wg->have_creating_net_ref) +- put_net(wg->creating_net); + kvfree(wg->index_hashtable); + kvfree(wg->peer_hashtable); + mutex_unlock(&wg->device_update_lock); + +- pr_debug("%s: Interface deleted\n", dev->name); ++ pr_debug("%s: Interface destroyed\n", dev->name); + free_netdev(dev); + } + +@@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_ne + struct wg_device *wg = netdev_priv(dev); + int ret = -ENOMEM; + +- wg->creating_net = src_net; ++ rcu_assign_pointer(wg->creating_net, src_net); + init_rwsem(&wg->static_identity.lock); + mutex_init(&wg->socket_update_lock); + mutex_init(&wg->device_update_lock); +@@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __r + .newlink = wg_newlink, + }; + +-static int wg_netdevice_notification(struct notifier_block *nb, +- unsigned long action, void *data) ++static void wg_netns_pre_exit(struct net *net) + { +- struct net_device *dev = ((struct netdev_notifier_info *)data)->dev; +- struct wg_device *wg = netdev_priv(dev); +- +- ASSERT_RTNL(); +- +- if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops) +- return 0; ++ struct wg_device *wg; + +- if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) { +- put_net(wg->creating_net); +- wg->have_creating_net_ref = false; +- } else if (dev_net(dev) != wg->creating_net && +- !wg->have_creating_net_ref) { +- wg->have_creating_net_ref = true; +- get_net(wg->creating_net); ++ rtnl_lock(); ++ list_for_each_entry(wg, &device_list, device_list) { ++ if (rcu_access_pointer(wg->creating_net) == net) { ++ pr_debug("%s: Creating namespace exiting\n", wg->dev->name); ++ netif_carrier_off(wg->dev); ++ mutex_lock(&wg->device_update_lock); ++ rcu_assign_pointer(wg->creating_net, NULL); ++ wg_socket_reinit(wg, NULL, NULL); ++ mutex_unlock(&wg->device_update_lock); ++ } + } +- return 0; ++ rtnl_unlock(); + } + +-static struct notifier_block netdevice_notifier = { +- .notifier_call = wg_netdevice_notification ++static struct pernet_operations pernet_ops = { ++ .pre_exit = wg_netns_pre_exit + }; + + int __init wg_device_init(void) +@@ -429,18 +425,18 @@ int __init wg_device_init(void) + return ret; + #endif + +- ret = register_netdevice_notifier(&netdevice_notifier); ++ ret = register_pernet_device(&pernet_ops); + if (ret) + goto error_pm; + + ret = rtnl_link_register(&link_ops); + if (ret) +- goto error_netdevice; ++ goto error_pernet; + + return 0; + +-error_netdevice: +- unregister_netdevice_notifier(&netdevice_notifier); ++error_pernet: ++ unregister_pernet_device(&pernet_ops); + error_pm: + #ifdef CONFIG_PM_SLEEP + unregister_pm_notifier(&pm_notifier); +@@ -451,7 +447,7 @@ error_pm: + void wg_device_uninit(void) + { + rtnl_link_unregister(&link_ops); +- unregister_netdevice_notifier(&netdevice_notifier); ++ unregister_pernet_device(&pernet_ops); + #ifdef CONFIG_PM_SLEEP + unregister_pm_notifier(&pm_notifier); + #endif +--- a/drivers/net/wireguard/device.h ++++ b/drivers/net/wireguard/device.h +@@ -40,7 +40,7 @@ struct wg_device { + struct net_device *dev; + struct crypt_queue encrypt_queue, decrypt_queue; + struct sock __rcu *sock4, *sock6; +- struct net *creating_net; ++ struct net __rcu *creating_net; + struct noise_static_identity static_identity; + struct workqueue_struct *handshake_receive_wq, *handshake_send_wq; + struct workqueue_struct *packet_crypt_wq; +@@ -56,7 +56,6 @@ struct wg_device { + unsigned int num_peers, device_update_gen; + u32 fwmark; + u16 incoming_port; +- bool have_creating_net_ref; + }; + + int wg_device_init(void); +--- a/drivers/net/wireguard/netlink.c ++++ b/drivers/net/wireguard/netlink.c +@@ -517,11 +517,15 @@ static int wg_set_device(struct sk_buff + if (flags & ~__WGDEVICE_F_ALL) + goto out; + +- ret = -EPERM; +- if ((info->attrs[WGDEVICE_A_LISTEN_PORT] || +- info->attrs[WGDEVICE_A_FWMARK]) && +- !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN)) +- goto out; ++ if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) { ++ struct net *net; ++ rcu_read_lock(); ++ net = rcu_dereference(wg->creating_net); ++ ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0; ++ rcu_read_unlock(); ++ if (ret) ++ goto out; ++ } + + ++wg->device_update_gen; + +--- a/drivers/net/wireguard/socket.c ++++ b/drivers/net/wireguard/socket.c +@@ -347,6 +347,7 @@ static void set_sock_opts(struct socket + + int wg_socket_init(struct wg_device *wg, u16 port) + { ++ struct net *net; + int ret; + struct udp_tunnel_sock_cfg cfg = { + .sk_user_data = wg, +@@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg, + }; + #endif + ++ rcu_read_lock(); ++ net = rcu_dereference(wg->creating_net); ++ net = net ? maybe_get_net(net) : NULL; ++ rcu_read_unlock(); ++ if (unlikely(!net)) ++ return -ENONET; ++ + #if IS_ENABLED(CONFIG_IPV6) + retry: + #endif + +- ret = udp_sock_create(wg->creating_net, &port4, &new4); ++ ret = udp_sock_create(net, &port4, &new4); + if (ret < 0) { + pr_err("%s: Could not create IPv4 socket\n", wg->dev->name); +- return ret; ++ goto out; + } + set_sock_opts(new4); +- setup_udp_tunnel_sock(wg->creating_net, new4, &cfg); ++ setup_udp_tunnel_sock(net, new4, &cfg); + + #if IS_ENABLED(CONFIG_IPV6) + if (ipv6_mod_enabled()) { + port6.local_udp_port = inet_sk(new4->sk)->inet_sport; +- ret = udp_sock_create(wg->creating_net, &port6, &new6); ++ ret = udp_sock_create(net, &port6, &new6); + if (ret < 0) { + udp_tunnel_sock_release(new4); + if (ret == -EADDRINUSE && !port && retries++ < 100) + goto retry; + pr_err("%s: Could not create IPv6 socket\n", + wg->dev->name); +- return ret; ++ goto out; + } + set_sock_opts(new6); +- setup_udp_tunnel_sock(wg->creating_net, new6, &cfg); ++ setup_udp_tunnel_sock(net, new6, &cfg); + } + #endif + + wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL); +- return 0; ++ ret = 0; ++out: ++ put_net(net); ++ return ret; + } + + void wg_socket_reinit(struct wg_device *wg, struct sock *new4, +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -587,9 +587,20 @@ ip0 link set wg0 up + kill $ncat_pid + ip0 link del wg0 + ++# Ensure there aren't circular reference loops ++ip1 link add wg1 type wireguard ++ip2 link add wg2 type wireguard ++ip1 link set wg1 netns $netns2 ++ip2 link set wg2 netns $netns1 ++pp ip netns delete $netns1 ++pp ip netns delete $netns2 ++pp ip netns add $netns1 ++pp ip netns add $netns2 ++ ++sleep 2 # Wait for cleanup and grace periods + declare -A objects + while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do +- [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue ++ [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ ?[0-9]*)\ .*(created|destroyed).* ]] || continue + objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}" + done < /dev/kmsg + alldeleted=1 diff --git a/target/linux/generic/backport-5.4/080-wireguard-0109-wireguard-receive-account-for-napi_gro_receive-never.patch b/target/linux/generic/backport-5.4/080-wireguard-0109-wireguard-receive-account-for-napi_gro_receive-never.patch new file mode 100644 index 0000000000..edcbc8a856 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0109-wireguard-receive-account-for-napi_gro_receive-never.patch @@ -0,0 +1,42 @@ +From b7077a2f4d374d3f2108af9d0a1b94fd2c346ba7 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 24 Jun 2020 16:06:03 -0600 +Subject: [PATCH 109/124] wireguard: receive: account for napi_gro_receive + never returning GRO_DROP + +commit df08126e3833e9dca19e2407db5f5860a7c194fb upstream. + +The napi_gro_receive function no longer returns GRO_DROP ever, making +handling GRO_DROP dead code. This commit removes that dead code. +Further, it's not even clear that device drivers have any business in +taking action after passing off received packets; that's arguably out of +their hands. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Fixes: 6570bc79c0df ("net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/receive.c | 10 ++-------- + 1 file changed, 2 insertions(+), 8 deletions(-) + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -414,14 +414,8 @@ static void wg_packet_consume_data_done( + if (unlikely(routed_peer != peer)) + goto dishonest_packet_peer; + +- if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) { +- ++dev->stats.rx_dropped; +- net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n", +- dev->name, peer->internal_id, +- &peer->endpoint.addr); +- } else { +- update_rx_stats(peer, message_data_len(len_before_trim)); +- } ++ napi_gro_receive(&peer->napi, skb); ++ update_rx_stats(peer, message_data_len(len_before_trim)); + return; + + dishonest_packet_peer: diff --git a/target/linux/generic/backport-5.4/080-wireguard-0110-net-ip_tunnel-add-header_ops-for-layer-3-devices.patch b/target/linux/generic/backport-5.4/080-wireguard-0110-net-ip_tunnel-add-header_ops-for-layer-3-devices.patch new file mode 100644 index 0000000000..4e925d7f99 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0110-net-ip_tunnel-add-header_ops-for-layer-3-devices.patch @@ -0,0 +1,58 @@ +From 5effaa566cea8d862bf00ff81d2e3fa40521d296 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 29 Jun 2020 19:06:18 -0600 +Subject: [PATCH 110/124] net: ip_tunnel: add header_ops for layer 3 devices + +commit 2606aff916854b61234bf85001be9777bab2d5f8 upstream. + +Some devices that take straight up layer 3 packets benefit from having a +shared header_ops so that AF_PACKET sockets can inject packets that are +recognized. This shared infrastructure will be used by other drivers +that currently can't inject packets using AF_PACKET. It also exposes the +parser function, as it is useful in standalone form too. + +Signed-off-by: Jason A. Donenfeld +Acked-by: Willem de Bruijn +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + include/net/ip_tunnels.h | 3 +++ + net/ipv4/ip_tunnel_core.c | 18 ++++++++++++++++++ + 2 files changed, 21 insertions(+) + +--- a/include/net/ip_tunnels.h ++++ b/include/net/ip_tunnels.h +@@ -289,6 +289,9 @@ int ip_tunnel_newlink(struct net_device + struct ip_tunnel_parm *p, __u32 fwmark); + void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); + ++extern const struct header_ops ip_tunnel_header_ops; ++__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); ++ + struct ip_tunnel_encap_ops { + size_t (*encap_hlen)(struct ip_tunnel_encap *e); + int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, +--- a/net/ipv4/ip_tunnel_core.c ++++ b/net/ipv4/ip_tunnel_core.c +@@ -446,3 +446,21 @@ void ip_tunnel_unneed_metadata(void) + static_branch_dec(&ip_tunnel_metadata_cnt); + } + EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); ++ ++/* Returns either the correct skb->protocol value, or 0 if invalid. */ ++__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb) ++{ ++ if (skb_network_header(skb) >= skb->head && ++ (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) && ++ ip_hdr(skb)->version == 4) ++ return htons(ETH_P_IP); ++ if (skb_network_header(skb) >= skb->head && ++ (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) && ++ ipv6_hdr(skb)->version == 6) ++ return htons(ETH_P_IPV6); ++ return 0; ++} ++EXPORT_SYMBOL(ip_tunnel_parse_protocol); ++ ++const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol }; ++EXPORT_SYMBOL(ip_tunnel_header_ops); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0111-wireguard-implement-header_ops-parse_protocol-for-AF.patch b/target/linux/generic/backport-5.4/080-wireguard-0111-wireguard-implement-header_ops-parse_protocol-for-AF.patch new file mode 100644 index 0000000000..4cc67a72a6 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0111-wireguard-implement-header_ops-parse_protocol-for-AF.patch @@ -0,0 +1,37 @@ +From cf413ab742788eeb47e789934d492bb546aa4aa8 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 29 Jun 2020 19:06:20 -0600 +Subject: [PATCH 111/124] wireguard: implement header_ops->parse_protocol for + AF_PACKET + +commit 01a4967c71c004f8ecad4ab57021348636502fa9 upstream. + +WireGuard uses skb->protocol to determine packet type, and bails out if +it's not set or set to something it's not expecting. For AF_PACKET +injection, we need to support its call chain of: + + packet_sendmsg -> packet_snd -> packet_parse_headers -> + dev_parse_header_protocol -> parse_protocol + +Without a valid parse_protocol, this returns zero, and wireguard then +rejects the skb. So, this wires up the ip_tunnel handler for layer 3 +packets for that case. + +Reported-by: Hans Wippel +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -262,6 +262,7 @@ static void wg_setup(struct net_device * + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); + + dev->netdev_ops = &netdev_ops; ++ dev->header_ops = &ip_tunnel_header_ops; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->needed_headroom = DATA_PACKET_HEAD_ROOM; diff --git a/target/linux/generic/backport-5.4/080-wireguard-0112-wireguard-queueing-make-use-of-ip_tunnel_parse_proto.patch b/target/linux/generic/backport-5.4/080-wireguard-0112-wireguard-queueing-make-use-of-ip_tunnel_parse_proto.patch new file mode 100644 index 0000000000..1f8766c9e1 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0112-wireguard-queueing-make-use-of-ip_tunnel_parse_proto.patch @@ -0,0 +1,69 @@ +From 83313326c87e7c1aacebce4f8411505e2b68bf25 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 29 Jun 2020 19:06:21 -0600 +Subject: [PATCH 112/124] wireguard: queueing: make use of + ip_tunnel_parse_protocol + +commit 1a574074ae7d1d745c16f7710655f38a53174c27 upstream. + +Now that wg_examine_packet_protocol has been added for general +consumption as ip_tunnel_parse_protocol, it's possible to remove +wg_examine_packet_protocol and simply use the new +ip_tunnel_parse_protocol function directly. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/queueing.h | 19 ++----------------- + drivers/net/wireguard/receive.c | 2 +- + 2 files changed, 3 insertions(+), 18 deletions(-) + +--- a/drivers/net/wireguard/queueing.h ++++ b/drivers/net/wireguard/queueing.h +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + + struct wg_device; + struct wg_peer; +@@ -65,25 +66,9 @@ struct packet_cb { + #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) + #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) + +-/* Returns either the correct skb->protocol value, or 0 if invalid. */ +-static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb) +-{ +- if (skb_network_header(skb) >= skb->head && +- (skb_network_header(skb) + sizeof(struct iphdr)) <= +- skb_tail_pointer(skb) && +- ip_hdr(skb)->version == 4) +- return htons(ETH_P_IP); +- if (skb_network_header(skb) >= skb->head && +- (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= +- skb_tail_pointer(skb) && +- ipv6_hdr(skb)->version == 6) +- return htons(ETH_P_IPV6); +- return 0; +-} +- + static inline bool wg_check_packet_protocol(struct sk_buff *skb) + { +- __be16 real_protocol = wg_examine_packet_protocol(skb); ++ __be16 real_protocol = ip_tunnel_parse_protocol(skb); + return real_protocol && skb->protocol == real_protocol; + } + +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -387,7 +387,7 @@ static void wg_packet_consume_data_done( + */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = ~0; /* All levels */ +- skb->protocol = wg_examine_packet_protocol(skb); ++ skb->protocol = ip_tunnel_parse_protocol(skb); + if (skb->protocol == htons(ETH_P_IP)) { + len = ntohs(ip_hdr(skb)->tot_len); + if (unlikely(len < sizeof(struct iphdr))) diff --git a/target/linux/generic/backport-5.4/080-wireguard-0113-netlink-consistently-use-NLA_POLICY_EXACT_LEN.patch b/target/linux/generic/backport-5.4/080-wireguard-0113-netlink-consistently-use-NLA_POLICY_EXACT_LEN.patch new file mode 100644 index 0000000000..f343ed8f41 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0113-netlink-consistently-use-NLA_POLICY_EXACT_LEN.patch @@ -0,0 +1,49 @@ +From 605843f571026155514f83127885ae81b83479ae Mon Sep 17 00:00:00 2001 +From: Johannes Berg +Date: Tue, 18 Aug 2020 10:17:31 +0200 +Subject: [PATCH 113/124] netlink: consistently use NLA_POLICY_EXACT_LEN() + +commit 8140860c817f3e9f78bcd1e420b9777ddcbaa629 upstream. + +Change places that open-code NLA_POLICY_EXACT_LEN() to +use the macro instead, giving us flexibility in how we +handle the details of the macro. + +Signed-off-by: Johannes Berg +Acked-by: Matthieu Baerts +Signed-off-by: David S. Miller +[Jason: only picked the drivers/net/wireguard/* part] +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/netlink.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +--- a/drivers/net/wireguard/netlink.c ++++ b/drivers/net/wireguard/netlink.c +@@ -22,8 +22,8 @@ static struct genl_family genl_family; + static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = { + [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 }, + [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, +- [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, +- [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, ++ [WGDEVICE_A_PRIVATE_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), ++ [WGDEVICE_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), + [WGDEVICE_A_FLAGS] = { .type = NLA_U32 }, + [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 }, + [WGDEVICE_A_FWMARK] = { .type = NLA_U32 }, +@@ -31,12 +31,12 @@ static const struct nla_policy device_po + }; + + static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = { +- [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN }, +- [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN }, ++ [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), ++ [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN), + [WGPEER_A_FLAGS] = { .type = NLA_U32 }, + [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) }, + [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 }, +- [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) }, ++ [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)), + [WGPEER_A_RX_BYTES] = { .type = NLA_U64 }, + [WGPEER_A_TX_BYTES] = { .type = NLA_U64 }, + [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED }, diff --git a/target/linux/generic/backport-5.4/080-wireguard-0114-netlink-consistently-use-NLA_POLICY_MIN_LEN.patch b/target/linux/generic/backport-5.4/080-wireguard-0114-netlink-consistently-use-NLA_POLICY_MIN_LEN.patch new file mode 100644 index 0000000000..a859e7c72b --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0114-netlink-consistently-use-NLA_POLICY_MIN_LEN.patch @@ -0,0 +1,39 @@ +From 2c778b2cd59a12f0dcba236e6441a318d1c6486c Mon Sep 17 00:00:00 2001 +From: Johannes Berg +Date: Tue, 18 Aug 2020 10:17:32 +0200 +Subject: [PATCH 114/124] netlink: consistently use NLA_POLICY_MIN_LEN() + +commit bc0435855041d7fff0b83dd992fc4be34aa11afb upstream. + +Change places that open-code NLA_POLICY_MIN_LEN() to +use the macro instead, giving us flexibility in how we +handle the details of the macro. + +Signed-off-by: Johannes Berg +Signed-off-by: David S. Miller +[Jason: only picked the drivers/net/wireguard/* part] +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/netlink.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/netlink.c ++++ b/drivers/net/wireguard/netlink.c +@@ -34,7 +34,7 @@ static const struct nla_policy peer_poli + [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN), + [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN), + [WGPEER_A_FLAGS] = { .type = NLA_U32 }, +- [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) }, ++ [WGPEER_A_ENDPOINT] = NLA_POLICY_MIN_LEN(sizeof(struct sockaddr)), + [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 }, + [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)), + [WGPEER_A_RX_BYTES] = { .type = NLA_U64 }, +@@ -45,7 +45,7 @@ static const struct nla_policy peer_poli + + static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = { + [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 }, +- [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) }, ++ [WGALLOWEDIP_A_IPADDR] = NLA_POLICY_MIN_LEN(sizeof(struct in_addr)), + [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 } + }; + diff --git a/target/linux/generic/backport-5.4/080-wireguard-0115-wireguard-noise-take-lock-when-removing-handshake-en.patch b/target/linux/generic/backport-5.4/080-wireguard-0115-wireguard-noise-take-lock-when-removing-handshake-en.patch new file mode 100644 index 0000000000..74448edfe0 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0115-wireguard-noise-take-lock-when-removing-handshake-en.patch @@ -0,0 +1,127 @@ +From 9d4c0f8cd4cca2c65c7927f839469d6c1bef088f Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 9 Sep 2020 13:58:14 +0200 +Subject: [PATCH 115/124] wireguard: noise: take lock when removing handshake + entry from table + +commit 9179ba31367bcf481c3c79b5f028c94faad9f30a upstream. + +Eric reported that syzkaller found a race of this variety: + +CPU 1 CPU 2 +-------------------------------------------|--------------------------------------- +wg_index_hashtable_replace(old, ...) | + if (hlist_unhashed(&old->index_hash)) | + | wg_index_hashtable_remove(old) + | hlist_del_init_rcu(&old->index_hash) + | old->index_hash.pprev = NULL + hlist_replace_rcu(&old->index_hash, ...) | + *old->index_hash.pprev | + +Syzbot wasn't actually able to reproduce this more than once or create a +reproducer, because the race window between checking "hlist_unhashed" and +calling "hlist_replace_rcu" is just so small. Adding an mdelay(5) or +similar there helps make this demonstrable using this simple script: + + #!/bin/bash + set -ex + trap 'kill $pid1; kill $pid2; ip link del wg0; ip link del wg1' EXIT + ip link add wg0 type wireguard + ip link add wg1 type wireguard + wg set wg0 private-key <(wg genkey) listen-port 9999 + wg set wg1 private-key <(wg genkey) peer $(wg show wg0 public-key) endpoint 127.0.0.1:9999 persistent-keepalive 1 + wg set wg0 peer $(wg show wg1 public-key) + ip link set wg0 up + yes link set wg1 up | ip -force -batch - & + pid1=$! + yes link set wg1 down | ip -force -batch - & + pid2=$! + wait + +The fundumental underlying problem is that we permit calls to wg_index_ +hashtable_remove(handshake.entry) without requiring the caller to take +the handshake mutex that is intended to protect members of handshake +during mutations. This is consistently the case with calls to wg_index_ +hashtable_insert(handshake.entry) and wg_index_hashtable_replace( +handshake.entry), but it's missing from a pertinent callsite of wg_ +index_hashtable_remove(handshake.entry). So, this patch makes sure that +mutex is taken. + +The original code was a little bit funky though, in the form of: + + remove(handshake.entry) + lock(), memzero(handshake.some_members), unlock() + remove(handshake.entry) + +The original intention of that double removal pattern outside the lock +appears to be some attempt to prevent insertions that might happen while +locks are dropped during expensive crypto operations, but actually, all +callers of wg_index_hashtable_insert(handshake.entry) take the write +lock and then explicitly check handshake.state, as they should, which +the aforementioned memzero clears, which means an insertion should +already be impossible. And regardless, the original intention was +necessarily racy, since it wasn't guaranteed that something else would +run after the unlock() instead of after the remove(). So, from a +soundness perspective, it seems positive to remove what looks like a +hack at best. + +The crash from both syzbot and from the script above is as follows: + + general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN + KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] + CPU: 0 PID: 7395 Comm: kworker/0:3 Not tainted 5.9.0-rc4-syzkaller #0 + Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 + Workqueue: wg-kex-wg1 wg_packet_handshake_receive_worker + RIP: 0010:hlist_replace_rcu include/linux/rculist.h:505 [inline] + RIP: 0010:wg_index_hashtable_replace+0x176/0x330 drivers/net/wireguard/peerlookup.c:174 + Code: 00 fc ff df 48 89 f9 48 c1 e9 03 80 3c 01 00 0f 85 44 01 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 10 48 89 c6 48 c1 ee 03 <80> 3c 0e 00 0f 85 06 01 00 00 48 85 d2 4c 89 28 74 47 e8 a3 4f b5 + RSP: 0018:ffffc90006a97bf8 EFLAGS: 00010246 + RAX: 0000000000000000 RBX: ffff888050ffc4f8 RCX: dffffc0000000000 + RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88808e04e010 + RBP: ffff88808e04e000 R08: 0000000000000001 R09: ffff8880543d0000 + R10: ffffed100a87a000 R11: 000000000000016e R12: ffff8880543d0000 + R13: ffff88808e04e008 R14: ffff888050ffc508 R15: ffff888050ffc500 + FS: 0000000000000000(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000 + CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + CR2: 00000000f5505db0 CR3: 0000000097cf7000 CR4: 00000000001526f0 + DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 + DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 + Call Trace: + wg_noise_handshake_begin_session+0x752/0xc9a drivers/net/wireguard/noise.c:820 + wg_receive_handshake_packet drivers/net/wireguard/receive.c:183 [inline] + wg_packet_handshake_receive_worker+0x33b/0x730 drivers/net/wireguard/receive.c:220 + process_one_work+0x94c/0x1670 kernel/workqueue.c:2269 + worker_thread+0x64c/0x1120 kernel/workqueue.c:2415 + kthread+0x3b5/0x4a0 kernel/kthread.c:292 + ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294 + +Reported-by: syzbot +Reported-by: Eric Dumazet +Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/ +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/noise.c | 5 +---- + 1 file changed, 1 insertion(+), 4 deletions(-) + +--- a/drivers/net/wireguard/noise.c ++++ b/drivers/net/wireguard/noise.c +@@ -87,15 +87,12 @@ static void handshake_zero(struct noise_ + + void wg_noise_handshake_clear(struct noise_handshake *handshake) + { ++ down_write(&handshake->lock); + wg_index_hashtable_remove( + handshake->entry.peer->device->index_hashtable, + &handshake->entry); +- down_write(&handshake->lock); + handshake_zero(handshake); + up_write(&handshake->lock); +- wg_index_hashtable_remove( +- handshake->entry.peer->device->index_hashtable, +- &handshake->entry); + } + + static struct noise_keypair *keypair_create(struct wg_peer *peer) diff --git a/target/linux/generic/backport-5.4/080-wireguard-0116-wireguard-peerlookup-take-lock-before-checking-hash-.patch b/target/linux/generic/backport-5.4/080-wireguard-0116-wireguard-peerlookup-take-lock-before-checking-hash-.patch new file mode 100644 index 0000000000..b329d41688 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0116-wireguard-peerlookup-take-lock-before-checking-hash-.patch @@ -0,0 +1,62 @@ +From 1f5495019fce5680d54f94204500ee59d43fa15a Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Wed, 9 Sep 2020 13:58:15 +0200 +Subject: [PATCH 116/124] wireguard: peerlookup: take lock before checking hash + in replace operation + +commit 6147f7b1e90ff09bd52afc8b9206a7fcd133daf7 upstream. + +Eric's suggested fix for the previous commit's mentioned race condition +was to simply take the table->lock in wg_index_hashtable_replace(). The +table->lock of the hash table is supposed to protect the bucket heads, +not the entires, but actually, since all the mutator functions are +already taking it, it makes sense to take it too for the test to +hlist_unhashed, as a defense in depth measure, so that it no longer +races with deletions, regardless of what other locks are protecting +individual entries. This is sensible from a performance perspective +because, as Eric pointed out, the case of being unhashed is already the +unlikely case, so this won't add common contention. And comparing +instructions, this basically doesn't make much of a difference other +than pushing and popping %r13, used by the new `bool ret`. More +generally, I like the idea of locking consistency across table mutator +functions, and this might let me rest slightly easier at night. + +Suggested-by: Eric Dumazet +Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/ +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: David S. Miller +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/peerlookup.c | 11 ++++++++--- + 1 file changed, 8 insertions(+), 3 deletions(-) + +--- a/drivers/net/wireguard/peerlookup.c ++++ b/drivers/net/wireguard/peerlookup.c +@@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct i + struct index_hashtable_entry *old, + struct index_hashtable_entry *new) + { +- if (unlikely(hlist_unhashed(&old->index_hash))) +- return false; ++ bool ret; ++ + spin_lock_bh(&table->lock); ++ ret = !hlist_unhashed(&old->index_hash); ++ if (unlikely(!ret)) ++ goto out; ++ + new->index = old->index; + hlist_replace_rcu(&old->index_hash, &new->index_hash); + +@@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct i + * simply gets dropped, which isn't terrible. + */ + INIT_HLIST_NODE(&old->index_hash); ++out: + spin_unlock_bh(&table->lock); +- return true; ++ return ret; + } + + void wg_index_hashtable_remove(struct index_hashtable *table, diff --git a/target/linux/generic/backport-5.4/080-wireguard-0117-wireguard-selftests-check-that-route_me_harder-packe.patch b/target/linux/generic/backport-5.4/080-wireguard-0117-wireguard-selftests-check-that-route_me_harder-packe.patch new file mode 100644 index 0000000000..8a6e75b56f --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0117-wireguard-selftests-check-that-route_me_harder-packe.patch @@ -0,0 +1,56 @@ +From 7e687dff94e8acf478f787c75007d180c9c2dcc0 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Thu, 29 Oct 2020 03:56:05 +0100 +Subject: [PATCH 117/124] wireguard: selftests: check that route_me_harder + packets use the right sk + +commit af8afcf1fdd5f365f70e2386c2d8c7a1abd853d7 upstream. + +If netfilter changes the packet mark, the packet is rerouted. The +ip_route_me_harder family of functions fails to use the right sk, opting +to instead use skb->sk, resulting in a routing loop when used with +tunnels. With the next change fixing this issue in netfilter, test for +the relevant condition inside our test suite, since wireguard was where +the bug was discovered. + +Reported-by: Chen Minqiang +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/netns.sh | 8 ++++++++ + tools/testing/selftests/wireguard/qemu/kernel.config | 2 ++ + 2 files changed, 10 insertions(+) + +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -316,6 +316,14 @@ pp sleep 3 + n2 ping -W 1 -c 1 192.168.241.1 + n1 wg set wg0 peer "$pub2" persistent-keepalive 0 + ++# Test that sk_bound_dev_if works ++n1 ping -I wg0 -c 1 -W 1 192.168.241.2 ++# What about when the mark changes and the packet must be rerouted? ++n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 ++n1 ping -c 1 -W 1 192.168.241.2 # First the boring case ++n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case ++n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 ++ + # Test that onion routing works, even when it loops + n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 + ip1 addr add 192.168.242.1/24 dev wg0 +--- a/tools/testing/selftests/wireguard/qemu/kernel.config ++++ b/tools/testing/selftests/wireguard/qemu/kernel.config +@@ -18,10 +18,12 @@ CONFIG_NF_NAT=y + CONFIG_NETFILTER_XTABLES=y + CONFIG_NETFILTER_XT_NAT=y + CONFIG_NETFILTER_XT_MATCH_LENGTH=y ++CONFIG_NETFILTER_XT_MARK=y + CONFIG_NF_CONNTRACK_IPV4=y + CONFIG_NF_NAT_IPV4=y + CONFIG_IP_NF_IPTABLES=y + CONFIG_IP_NF_FILTER=y ++CONFIG_IP_NF_MANGLE=y + CONFIG_IP_NF_NAT=y + CONFIG_IP_ADVANCED_ROUTER=y + CONFIG_IP_MULTIPLE_TABLES=y diff --git a/target/linux/generic/backport-5.4/080-wireguard-0118-wireguard-avoid-double-unlikely-notation-when-using-.patch b/target/linux/generic/backport-5.4/080-wireguard-0118-wireguard-avoid-double-unlikely-notation-when-using-.patch new file mode 100644 index 0000000000..b461b771dd --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0118-wireguard-avoid-double-unlikely-notation-when-using-.patch @@ -0,0 +1,55 @@ +From 6f5f2660a44325a75ff2ccbf799103c3613e78bb Mon Sep 17 00:00:00 2001 +From: Antonio Quartulli +Date: Mon, 22 Feb 2021 17:25:43 +0100 +Subject: [PATCH 118/124] wireguard: avoid double unlikely() notation when + using IS_ERR() + +commit 30ac4e2f54ec067b7b9ca0db27e75681581378d6 upstream. + +The definition of IS_ERR() already applies the unlikely() notation +when checking the error status of the passed pointer. For this +reason there is no need to have the same notation outside of +IS_ERR() itself. + +Clean up code by removing redundant notation. + +Signed-off-by: Antonio Quartulli +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 2 +- + drivers/net/wireguard/socket.c | 4 ++-- + 2 files changed, 3 insertions(+), 3 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -157,7 +157,7 @@ static netdev_tx_t wg_xmit(struct sk_buf + } else { + struct sk_buff *segs = skb_gso_segment(skb, 0); + +- if (unlikely(IS_ERR(segs))) { ++ if (IS_ERR(segs)) { + ret = PTR_ERR(segs); + goto err_peer; + } +--- a/drivers/net/wireguard/socket.c ++++ b/drivers/net/wireguard/socket.c +@@ -71,7 +71,7 @@ static int send4(struct wg_device *wg, s + ip_rt_put(rt); + rt = ip_route_output_flow(sock_net(sock), &fl, sock); + } +- if (unlikely(IS_ERR(rt))) { ++ if (IS_ERR(rt)) { + ret = PTR_ERR(rt); + net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", + wg->dev->name, &endpoint->addr, ret); +@@ -138,7 +138,7 @@ static int send6(struct wg_device *wg, s + } + dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl, + NULL); +- if (unlikely(IS_ERR(dst))) { ++ if (IS_ERR(dst)) { + ret = PTR_ERR(dst); + net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", + wg->dev->name, &endpoint->addr, ret); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0119-wireguard-socket-remove-bogus-__be32-annotation.patch b/target/linux/generic/backport-5.4/080-wireguard-0119-wireguard-socket-remove-bogus-__be32-annotation.patch new file mode 100644 index 0000000000..c497ce5719 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0119-wireguard-socket-remove-bogus-__be32-annotation.patch @@ -0,0 +1,52 @@ +From 03928cbd7e0c7906c7ab2a490e31d89d6ae3965a Mon Sep 17 00:00:00 2001 +From: Jann Horn +Date: Mon, 22 Feb 2021 17:25:44 +0100 +Subject: [PATCH 119/124] wireguard: socket: remove bogus __be32 annotation + +commit 7f57bd8dc22de35ddd895294aa554003e4f19a72 upstream. + +The endpoint->src_if4 has nothing to do with fixed-endian numbers; remove +the bogus annotation. + +This was introduced in +https://git.zx2c4.com/wireguard-monolithic-historical/commit?id=14e7d0a499a676ec55176c0de2f9fcbd34074a82 +in the historical WireGuard repo because the old code used to +zero-initialize multiple members as follows: + + endpoint->src4.s_addr = endpoint->src_if4 = fl.saddr = 0; + +Because fl.saddr is fixed-endian and an assignment returns a value with the +type of its left operand, this meant that sparse detected an assignment +between values of different endianness. + +Since then, this assignment was already split up into separate statements; +just the cast survived. + +Signed-off-by: Jann Horn +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/socket.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/socket.c ++++ b/drivers/net/wireguard/socket.c +@@ -53,7 +53,7 @@ static int send4(struct wg_device *wg, s + if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0, + fl.saddr, RT_SCOPE_HOST))) { + endpoint->src4.s_addr = 0; +- *(__force __be32 *)&endpoint->src_if4 = 0; ++ endpoint->src_if4 = 0; + fl.saddr = 0; + if (cache) + dst_cache_reset(cache); +@@ -63,7 +63,7 @@ static int send4(struct wg_device *wg, s + PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) && + rt->dst.dev->ifindex != endpoint->src_if4)))) { + endpoint->src4.s_addr = 0; +- *(__force __be32 *)&endpoint->src_if4 = 0; ++ endpoint->src_if4 = 0; + fl.saddr = 0; + if (cache) + dst_cache_reset(cache); diff --git a/target/linux/generic/backport-5.4/080-wireguard-0120-wireguard-selftests-test-multiple-parallel-streams.patch b/target/linux/generic/backport-5.4/080-wireguard-0120-wireguard-selftests-test-multiple-parallel-streams.patch new file mode 100644 index 0000000000..269f30f885 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0120-wireguard-selftests-test-multiple-parallel-streams.patch @@ -0,0 +1,52 @@ +From 5c4e6ed057bcaa6ece0386344ba787d88c8307d2 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 22 Feb 2021 17:25:45 +0100 +Subject: [PATCH 120/124] wireguard: selftests: test multiple parallel streams + +commit d5a49aa6c3e264a93a7d08485d66e346be0969dd upstream. + +In order to test ndo_start_xmit being called in parallel, explicitly add +separate tests, which should all run on different cores. This should +help tease out bugs associated with queueing up packets from different +cores in parallel. Currently, it hasn't found those types of bugs, but +given future planned work, this is a useful regression to avoid. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + tools/testing/selftests/wireguard/netns.sh | 15 ++++++++++++++- + 1 file changed, 14 insertions(+), 1 deletion(-) + +--- a/tools/testing/selftests/wireguard/netns.sh ++++ b/tools/testing/selftests/wireguard/netns.sh +@@ -39,7 +39,7 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0 + ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } + ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } + sleep() { read -t "$1" -N 1 || true; } +-waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } ++waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } + waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } + waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } + +@@ -141,6 +141,19 @@ tests() { + n2 iperf3 -s -1 -B fd00::2 & + waitiperf $netns2 $! + n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 ++ ++ # TCP over IPv4, in parallel ++ for max in 4 5 50; do ++ local pids=( ) ++ for ((i=0; i < max; ++i)) do ++ n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & ++ pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) ++ done ++ for ((i=0; i < max; ++i)) do ++ n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & ++ done ++ wait "${pids[@]}" ++ done + } + + [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" diff --git a/target/linux/generic/backport-5.4/080-wireguard-0121-wireguard-peer-put-frequently-used-members-above-cac.patch b/target/linux/generic/backport-5.4/080-wireguard-0121-wireguard-peer-put-frequently-used-members-above-cac.patch new file mode 100644 index 0000000000..bd4fd77380 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0121-wireguard-peer-put-frequently-used-members-above-cac.patch @@ -0,0 +1,42 @@ +From a13827e9091c07e25cdeec9a402d74a27e2a1111 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 22 Feb 2021 17:25:46 +0100 +Subject: [PATCH 121/124] wireguard: peer: put frequently used members above + cache lines + +commit 5a0598695634a6bb4126818902dd9140cd9df8b6 upstream. + +The is_dead boolean is checked for every single packet, while the +internal_id member is used basically only for pr_debug messages. So it +makes sense to hoist up is_dead into some space formerly unused by a +struct hole, while demoting internal_api to below the lowest struct +cache line. + +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/peer.h | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/net/wireguard/peer.h ++++ b/drivers/net/wireguard/peer.h +@@ -39,6 +39,7 @@ struct wg_peer { + struct crypt_queue tx_queue, rx_queue; + struct sk_buff_head staged_packet_queue; + int serial_work_cpu; ++ bool is_dead; + struct noise_keypairs keypairs; + struct endpoint endpoint; + struct dst_cache endpoint_cache; +@@ -61,9 +62,8 @@ struct wg_peer { + struct rcu_head rcu; + struct list_head peer_list; + struct list_head allowedips_list; +- u64 internal_id; + struct napi_struct napi; +- bool is_dead; ++ u64 internal_id; + }; + + struct wg_peer *wg_peer_create(struct wg_device *wg, diff --git a/target/linux/generic/backport-5.4/080-wireguard-0122-wireguard-device-do-not-generate-ICMP-for-non-IP-pac.patch b/target/linux/generic/backport-5.4/080-wireguard-0122-wireguard-device-do-not-generate-ICMP-for-non-IP-pac.patch new file mode 100644 index 0000000000..07a3662cd2 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0122-wireguard-device-do-not-generate-ICMP-for-non-IP-pac.patch @@ -0,0 +1,48 @@ +From 49da2a610d63cef849f0095e601821ad6edfbef7 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 22 Feb 2021 17:25:47 +0100 +Subject: [PATCH 122/124] wireguard: device: do not generate ICMP for non-IP + packets + +commit 99fff5264e7ab06f45b0ad60243475be0a8d0559 upstream. + +If skb->protocol doesn't match the actual skb->data header, it's +probably not a good idea to pass it off to icmp{,v6}_ndo_send, which is +expecting to reply to a valid IP packet. So this commit has that early +mismatch case jump to a later error label. + +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 7 ++++--- + 1 file changed, 4 insertions(+), 3 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -138,7 +138,7 @@ static netdev_tx_t wg_xmit(struct sk_buf + else if (skb->protocol == htons(ETH_P_IPV6)) + net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", + dev->name, &ipv6_hdr(skb)->daddr); +- goto err; ++ goto err_icmp; + } + + family = READ_ONCE(peer->endpoint.addr.sa_family); +@@ -201,12 +201,13 @@ static netdev_tx_t wg_xmit(struct sk_buf + + err_peer: + wg_peer_put(peer); +-err: +- ++dev->stats.tx_errors; ++err_icmp: + if (skb->protocol == htons(ETH_P_IP)) + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + else if (skb->protocol == htons(ETH_P_IPV6)) + icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); ++err: ++ ++dev->stats.tx_errors; + kfree_skb(skb); + return ret; + } diff --git a/target/linux/generic/backport-5.4/080-wireguard-0123-wireguard-queueing-get-rid-of-per-peer-ring-buffers.patch b/target/linux/generic/backport-5.4/080-wireguard-0123-wireguard-queueing-get-rid-of-per-peer-ring-buffers.patch new file mode 100644 index 0000000000..147c133919 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0123-wireguard-queueing-get-rid-of-per-peer-ring-buffers.patch @@ -0,0 +1,560 @@ +From 1771bbcc5bc99f569dd82ec9e1b7c397a2fb50ac Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 22 Feb 2021 17:25:48 +0100 +Subject: [PATCH 123/124] wireguard: queueing: get rid of per-peer ring buffers +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +commit 8b5553ace83cced775eefd0f3f18b5c6214ccf7a upstream. + +Having two ring buffers per-peer means that every peer results in two +massive ring allocations. On an 8-core x86_64 machine, this commit +reduces the per-peer allocation from 18,688 bytes to 1,856 bytes, which +is an 90% reduction. Ninety percent! With some single-machine +deployments approaching 500,000 peers, we're talking about a reduction +from 7 gigs of memory down to 700 megs of memory. + +In order to get rid of these per-peer allocations, this commit switches +to using a list-based queueing approach. Currently GSO fragments are +chained together using the skb->next pointer (the skb_list_* singly +linked list approach), so we form the per-peer queue around the unused +skb->prev pointer (which sort of makes sense because the links are +pointing backwards). Use of skb_queue_* is not possible here, because +that is based on doubly linked lists and spinlocks. Multiple cores can +write into the queue at any given time, because its writes occur in the +start_xmit path or in the udp_recv path. But reads happen in a single +workqueue item per-peer, amounting to a multi-producer, single-consumer +paradigm. + +The MPSC queue is implemented locklessly and never blocks. However, it +is not linearizable (though it is serializable), with a very tight and +unlikely race on writes, which, when hit (some tiny fraction of the +0.15% of partial adds on a fully loaded 16-core x86_64 system), causes +the queue reader to terminate early. However, because every packet sent +queues up the same workqueue item after it is fully added, the worker +resumes again, and stopping early isn't actually a problem, since at +that point the packet wouldn't have yet been added to the encryption +queue. These properties allow us to avoid disabling interrupts or +spinning. The design is based on Dmitry Vyukov's algorithm [1]. + +Performance-wise, ordinarily list-based queues aren't preferable to +ringbuffers, because of cache misses when following pointers around. +However, we *already* have to follow the adjacent pointers when working +through fragments, so there shouldn't actually be any change there. A +potential downside is that dequeueing is a bit more complicated, but the +ptr_ring structure used prior had a spinlock when dequeueing, so all and +all the difference appears to be a wash. + +Actually, from profiling, the biggest performance hit, by far, of this +commit winds up being atomic_add_unless(count, 1, max) and atomic_ +dec(count), which account for the majority of CPU time, according to +perf. In that sense, the previous ring buffer was superior in that it +could check if it was full by head==tail, which the list-based approach +cannot do. + +But all and all, this enables us to get massive memory savings, allowing +WireGuard to scale for real world deployments, without taking much of a +performance hit. + +[1] http://www.1024cores.net/home/lock-free-algorithms/queues/intrusive-mpsc-node-based-queue + +Reviewed-by: Dmitry Vyukov +Reviewed-by: Toke Høiland-Jørgensen +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/wireguard/device.c | 12 ++--- + drivers/net/wireguard/device.h | 15 +++--- + drivers/net/wireguard/peer.c | 28 ++++------- + drivers/net/wireguard/peer.h | 4 +- + drivers/net/wireguard/queueing.c | 86 +++++++++++++++++++++++++------- + drivers/net/wireguard/queueing.h | 45 ++++++++++++----- + drivers/net/wireguard/receive.c | 16 +++--- + drivers/net/wireguard/send.c | 31 ++++-------- + 8 files changed, 144 insertions(+), 93 deletions(-) + +--- a/drivers/net/wireguard/device.c ++++ b/drivers/net/wireguard/device.c +@@ -235,8 +235,8 @@ static void wg_destruct(struct net_devic + destroy_workqueue(wg->handshake_receive_wq); + destroy_workqueue(wg->handshake_send_wq); + destroy_workqueue(wg->packet_crypt_wq); +- wg_packet_queue_free(&wg->decrypt_queue, true); +- wg_packet_queue_free(&wg->encrypt_queue, true); ++ wg_packet_queue_free(&wg->decrypt_queue); ++ wg_packet_queue_free(&wg->encrypt_queue); + rcu_barrier(); /* Wait for all the peers to be actually freed. */ + wg_ratelimiter_uninit(); + memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); +@@ -338,12 +338,12 @@ static int wg_newlink(struct net *src_ne + goto err_destroy_handshake_send; + + ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, +- true, MAX_QUEUED_PACKETS); ++ MAX_QUEUED_PACKETS); + if (ret < 0) + goto err_destroy_packet_crypt; + + ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, +- true, MAX_QUEUED_PACKETS); ++ MAX_QUEUED_PACKETS); + if (ret < 0) + goto err_free_encrypt_queue; + +@@ -368,9 +368,9 @@ static int wg_newlink(struct net *src_ne + err_uninit_ratelimiter: + wg_ratelimiter_uninit(); + err_free_decrypt_queue: +- wg_packet_queue_free(&wg->decrypt_queue, true); ++ wg_packet_queue_free(&wg->decrypt_queue); + err_free_encrypt_queue: +- wg_packet_queue_free(&wg->encrypt_queue, true); ++ wg_packet_queue_free(&wg->encrypt_queue); + err_destroy_packet_crypt: + destroy_workqueue(wg->packet_crypt_wq); + err_destroy_handshake_send: +--- a/drivers/net/wireguard/device.h ++++ b/drivers/net/wireguard/device.h +@@ -27,13 +27,14 @@ struct multicore_worker { + + struct crypt_queue { + struct ptr_ring ring; +- union { +- struct { +- struct multicore_worker __percpu *worker; +- int last_cpu; +- }; +- struct work_struct work; +- }; ++ struct multicore_worker __percpu *worker; ++ int last_cpu; ++}; ++ ++struct prev_queue { ++ struct sk_buff *head, *tail, *peeked; ++ struct { struct sk_buff *next, *prev; } empty; // Match first 2 members of struct sk_buff. ++ atomic_t count; + }; + + struct wg_device { +--- a/drivers/net/wireguard/peer.c ++++ b/drivers/net/wireguard/peer.c +@@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct wg + peer = kzalloc(sizeof(*peer), GFP_KERNEL); + if (unlikely(!peer)) + return ERR_PTR(ret); +- peer->device = wg; ++ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) ++ goto err; + ++ peer->device = wg; + wg_noise_handshake_init(&peer->handshake, &wg->static_identity, + public_key, preshared_key, peer); +- if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)) +- goto err_1; +- if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false, +- MAX_QUEUED_PACKETS)) +- goto err_2; +- if (wg_packet_queue_init(&peer->rx_queue, NULL, false, +- MAX_QUEUED_PACKETS)) +- goto err_3; +- + peer->internal_id = atomic64_inc_return(&peer_counter); + peer->serial_work_cpu = nr_cpumask_bits; + wg_cookie_init(&peer->latest_cookie); + wg_timers_init(peer); + wg_cookie_checker_precompute_peer_keys(peer); + spin_lock_init(&peer->keypairs.keypair_update_lock); +- INIT_WORK(&peer->transmit_handshake_work, +- wg_packet_handshake_send_worker); ++ INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker); ++ INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker); ++ wg_prev_queue_init(&peer->tx_queue); ++ wg_prev_queue_init(&peer->rx_queue); + rwlock_init(&peer->endpoint_lock); + kref_init(&peer->refcount); + skb_queue_head_init(&peer->staged_packet_queue); +@@ -68,11 +63,7 @@ struct wg_peer *wg_peer_create(struct wg + pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id); + return peer; + +-err_3: +- wg_packet_queue_free(&peer->tx_queue, false); +-err_2: +- dst_cache_destroy(&peer->endpoint_cache); +-err_1: ++err: + kfree(peer); + return ERR_PTR(ret); + } +@@ -197,8 +188,7 @@ static void rcu_release(struct rcu_head + struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu); + + dst_cache_destroy(&peer->endpoint_cache); +- wg_packet_queue_free(&peer->rx_queue, false); +- wg_packet_queue_free(&peer->tx_queue, false); ++ WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue)); + + /* The final zeroing takes care of clearing any remaining handshake key + * material and other potentially sensitive information. +--- a/drivers/net/wireguard/peer.h ++++ b/drivers/net/wireguard/peer.h +@@ -36,7 +36,7 @@ struct endpoint { + + struct wg_peer { + struct wg_device *device; +- struct crypt_queue tx_queue, rx_queue; ++ struct prev_queue tx_queue, rx_queue; + struct sk_buff_head staged_packet_queue; + int serial_work_cpu; + bool is_dead; +@@ -46,7 +46,7 @@ struct wg_peer { + rwlock_t endpoint_lock; + struct noise_handshake handshake; + atomic64_t last_sent_handshake; +- struct work_struct transmit_handshake_work, clear_peer_work; ++ struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work; + struct cookie latest_cookie; + struct hlist_node pubkey_hash; + u64 rx_bytes, tx_bytes; +--- a/drivers/net/wireguard/queueing.c ++++ b/drivers/net/wireguard/queueing.c +@@ -9,8 +9,7 @@ struct multicore_worker __percpu * + wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr) + { + int cpu; +- struct multicore_worker __percpu *worker = +- alloc_percpu(struct multicore_worker); ++ struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker); + + if (!worker) + return NULL; +@@ -23,7 +22,7 @@ wg_packet_percpu_multicore_worker_alloc( + } + + int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, +- bool multicore, unsigned int len) ++ unsigned int len) + { + int ret; + +@@ -31,25 +30,78 @@ int wg_packet_queue_init(struct crypt_qu + ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); + if (ret) + return ret; +- if (function) { +- if (multicore) { +- queue->worker = wg_packet_percpu_multicore_worker_alloc( +- function, queue); +- if (!queue->worker) { +- ptr_ring_cleanup(&queue->ring, NULL); +- return -ENOMEM; +- } +- } else { +- INIT_WORK(&queue->work, function); +- } ++ queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue); ++ if (!queue->worker) { ++ ptr_ring_cleanup(&queue->ring, NULL); ++ return -ENOMEM; + } + return 0; + } + +-void wg_packet_queue_free(struct crypt_queue *queue, bool multicore) ++void wg_packet_queue_free(struct crypt_queue *queue) + { +- if (multicore) +- free_percpu(queue->worker); ++ free_percpu(queue->worker); + WARN_ON(!__ptr_ring_empty(&queue->ring)); + ptr_ring_cleanup(&queue->ring, NULL); + } ++ ++#define NEXT(skb) ((skb)->prev) ++#define STUB(queue) ((struct sk_buff *)&queue->empty) ++ ++void wg_prev_queue_init(struct prev_queue *queue) ++{ ++ NEXT(STUB(queue)) = NULL; ++ queue->head = queue->tail = STUB(queue); ++ queue->peeked = NULL; ++ atomic_set(&queue->count, 0); ++ BUILD_BUG_ON( ++ offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) - ++ offsetof(struct prev_queue, empty) || ++ offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) - ++ offsetof(struct prev_queue, empty)); ++} ++ ++static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) ++{ ++ WRITE_ONCE(NEXT(skb), NULL); ++ WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb); ++} ++ ++bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb) ++{ ++ if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS)) ++ return false; ++ __wg_prev_queue_enqueue(queue, skb); ++ return true; ++} ++ ++struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue) ++{ ++ struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail)); ++ ++ if (tail == STUB(queue)) { ++ if (!next) ++ return NULL; ++ queue->tail = next; ++ tail = next; ++ next = smp_load_acquire(&NEXT(next)); ++ } ++ if (next) { ++ queue->tail = next; ++ atomic_dec(&queue->count); ++ return tail; ++ } ++ if (tail != READ_ONCE(queue->head)) ++ return NULL; ++ __wg_prev_queue_enqueue(queue, STUB(queue)); ++ next = smp_load_acquire(&NEXT(tail)); ++ if (next) { ++ queue->tail = next; ++ atomic_dec(&queue->count); ++ return tail; ++ } ++ return NULL; ++} ++ ++#undef NEXT ++#undef STUB +--- a/drivers/net/wireguard/queueing.h ++++ b/drivers/net/wireguard/queueing.h +@@ -17,12 +17,13 @@ struct wg_device; + struct wg_peer; + struct multicore_worker; + struct crypt_queue; ++struct prev_queue; + struct sk_buff; + + /* queueing.c APIs: */ + int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, +- bool multicore, unsigned int len); +-void wg_packet_queue_free(struct crypt_queue *queue, bool multicore); ++ unsigned int len); ++void wg_packet_queue_free(struct crypt_queue *queue); + struct multicore_worker __percpu * + wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); + +@@ -135,8 +136,31 @@ static inline int wg_cpumask_next_online + return cpu; + } + ++void wg_prev_queue_init(struct prev_queue *queue); ++ ++/* Multi producer */ ++bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb); ++ ++/* Single consumer */ ++struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue); ++ ++/* Single consumer */ ++static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue) ++{ ++ if (queue->peeked) ++ return queue->peeked; ++ queue->peeked = wg_prev_queue_dequeue(queue); ++ return queue->peeked; ++} ++ ++/* Single consumer */ ++static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) ++{ ++ queue->peeked = NULL; ++} ++ + static inline int wg_queue_enqueue_per_device_and_peer( +- struct crypt_queue *device_queue, struct crypt_queue *peer_queue, ++ struct crypt_queue *device_queue, struct prev_queue *peer_queue, + struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) + { + int cpu; +@@ -145,8 +169,9 @@ static inline int wg_queue_enqueue_per_d + /* We first queue this up for the peer ingestion, but the consumer + * will wait for the state to change to CRYPTED or DEAD before. + */ +- if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb))) ++ if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb))) + return -ENOSPC; ++ + /* Then we queue it up in the device queue, which consumes the + * packet as soon as it can. + */ +@@ -157,9 +182,7 @@ static inline int wg_queue_enqueue_per_d + return 0; + } + +-static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue, +- struct sk_buff *skb, +- enum packet_state state) ++static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state) + { + /* We take a reference, because as soon as we call atomic_set, the + * peer can be freed from below us. +@@ -167,14 +190,12 @@ static inline void wg_queue_enqueue_per_ + struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); + + atomic_set_release(&PACKET_CB(skb)->state, state); +- queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, +- peer->internal_id), +- peer->device->packet_crypt_wq, &queue->work); ++ queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id), ++ peer->device->packet_crypt_wq, &peer->transmit_packet_work); + wg_peer_put(peer); + } + +-static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb, +- enum packet_state state) ++static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state) + { + /* We take a reference, because as soon as we call atomic_set, the + * peer can be freed from below us. +--- a/drivers/net/wireguard/receive.c ++++ b/drivers/net/wireguard/receive.c +@@ -444,7 +444,6 @@ packet_processed: + int wg_packet_rx_poll(struct napi_struct *napi, int budget) + { + struct wg_peer *peer = container_of(napi, struct wg_peer, napi); +- struct crypt_queue *queue = &peer->rx_queue; + struct noise_keypair *keypair; + struct endpoint endpoint; + enum packet_state state; +@@ -455,11 +454,10 @@ int wg_packet_rx_poll(struct napi_struct + if (unlikely(budget <= 0)) + return 0; + +- while ((skb = __ptr_ring_peek(&queue->ring)) != NULL && ++ while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL && + (state = atomic_read_acquire(&PACKET_CB(skb)->state)) != + PACKET_STATE_UNCRYPTED) { +- __ptr_ring_discard_one(&queue->ring); +- peer = PACKET_PEER(skb); ++ wg_prev_queue_drop_peeked(&peer->rx_queue); + keypair = PACKET_CB(skb)->keypair; + free = true; + +@@ -508,7 +506,7 @@ void wg_packet_decrypt_worker(struct wor + enum packet_state state = + likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ? + PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; +- wg_queue_enqueue_per_peer_napi(skb, state); ++ wg_queue_enqueue_per_peer_rx(skb, state); + if (need_resched()) + cond_resched(); + } +@@ -531,12 +529,10 @@ static void wg_packet_consume_data(struc + if (unlikely(READ_ONCE(peer->is_dead))) + goto err; + +- ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, +- &peer->rx_queue, skb, +- wg->packet_crypt_wq, +- &wg->decrypt_queue.last_cpu); ++ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, ++ wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu); + if (unlikely(ret == -EPIPE)) +- wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD); ++ wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); + if (likely(!ret || ret == -EPIPE)) { + rcu_read_unlock_bh(); + return; +--- a/drivers/net/wireguard/send.c ++++ b/drivers/net/wireguard/send.c +@@ -239,8 +239,7 @@ void wg_packet_send_keepalive(struct wg_ + wg_packet_send_staged_packets(peer); + } + +-static void wg_packet_create_data_done(struct sk_buff *first, +- struct wg_peer *peer) ++static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) + { + struct sk_buff *skb, *next; + bool is_keepalive, data_sent = false; +@@ -262,22 +261,19 @@ static void wg_packet_create_data_done(s + + void wg_packet_tx_worker(struct work_struct *work) + { +- struct crypt_queue *queue = container_of(work, struct crypt_queue, +- work); ++ struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); + struct noise_keypair *keypair; + enum packet_state state; + struct sk_buff *first; +- struct wg_peer *peer; + +- while ((first = __ptr_ring_peek(&queue->ring)) != NULL && ++ while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && + (state = atomic_read_acquire(&PACKET_CB(first)->state)) != + PACKET_STATE_UNCRYPTED) { +- __ptr_ring_discard_one(&queue->ring); +- peer = PACKET_PEER(first); ++ wg_prev_queue_drop_peeked(&peer->tx_queue); + keypair = PACKET_CB(first)->keypair; + + if (likely(state == PACKET_STATE_CRYPTED)) +- wg_packet_create_data_done(first, peer); ++ wg_packet_create_data_done(peer, first); + else + kfree_skb_list(first); + +@@ -306,16 +302,14 @@ void wg_packet_encrypt_worker(struct wor + break; + } + } +- wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, +- state); ++ wg_queue_enqueue_per_peer_tx(first, state); + if (need_resched()) + cond_resched(); + } + } + +-static void wg_packet_create_data(struct sk_buff *first) ++static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) + { +- struct wg_peer *peer = PACKET_PEER(first); + struct wg_device *wg = peer->device; + int ret = -EINVAL; + +@@ -323,13 +317,10 @@ static void wg_packet_create_data(struct + if (unlikely(READ_ONCE(peer->is_dead))) + goto err; + +- ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, +- &peer->tx_queue, first, +- wg->packet_crypt_wq, +- &wg->encrypt_queue.last_cpu); ++ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, ++ wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); + if (unlikely(ret == -EPIPE)) +- wg_queue_enqueue_per_peer(&peer->tx_queue, first, +- PACKET_STATE_DEAD); ++ wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); + err: + rcu_read_unlock_bh(); + if (likely(!ret || ret == -EPIPE)) +@@ -393,7 +384,7 @@ void wg_packet_send_staged_packets(struc + packets.prev->next = NULL; + wg_peer_get(keypair->entry.peer); + PACKET_CB(packets.next)->keypair = keypair; +- wg_packet_create_data(packets.next); ++ wg_packet_create_data(peer, packets.next); + return; + + out_invalid: diff --git a/target/linux/generic/backport-5.4/080-wireguard-0124-wireguard-kconfig-use-arm-chacha-even-with-no-neon.patch b/target/linux/generic/backport-5.4/080-wireguard-0124-wireguard-kconfig-use-arm-chacha-even-with-no-neon.patch new file mode 100644 index 0000000000..3c62dc6c56 --- /dev/null +++ b/target/linux/generic/backport-5.4/080-wireguard-0124-wireguard-kconfig-use-arm-chacha-even-with-no-neon.patch @@ -0,0 +1,30 @@ +From 514091206bc055a159348ae8575276dc925aea24 Mon Sep 17 00:00:00 2001 +From: "Jason A. Donenfeld" +Date: Mon, 22 Feb 2021 17:25:49 +0100 +Subject: [PATCH 124/124] wireguard: kconfig: use arm chacha even with no neon + +commit bce2473927af8de12ad131a743f55d69d358c0b9 upstream. + +The condition here was incorrect: a non-neon fallback implementation is +available on arm32 when NEON is not supported. + +Reported-by: Ilya Lipnitskiy +Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") +Signed-off-by: Jason A. Donenfeld +Signed-off-by: Jakub Kicinski +Signed-off-by: Jason A. Donenfeld +--- + drivers/net/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/Kconfig ++++ b/drivers/net/Kconfig +@@ -87,7 +87,7 @@ config WIREGUARD + select CRYPTO_CURVE25519_X86 if X86 && 64BIT + select ARM_CRYPTO if ARM + select ARM64_CRYPTO if ARM64 +- select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON ++ select CRYPTO_CHACHA20_NEON if ARM || (ARM64 && KERNEL_MODE_NEON) + select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON + select CRYPTO_POLY1305_ARM if ARM + select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON