* [RFC PATCH 01/20] crypto: chacha - move existing library code into lib/crypto
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 02/20] crypto: x86/chacha - expose SIMD ChaCha routine as library function Ard Biesheuvel
` (15 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Move the existing shared ChaCha code into lib/crypto, and at the
same time, split the support header into a public version, and an
internal version that is only intended for consumption by crypto
implementations.
Also, refactor the generic implementation so it only gets exposed as the
chacha_crypt() library function if the architecture does not override it
with its own implementation, potentially falling back to the generic
routine if needed.
And while at it, tidy up lib/crypto/Makefile a bit so we are ready for
some new arrivals.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
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 | 8 ++++
crypto/chacha_generic.c | 44 ++----------------
include/crypto/chacha.h | 49 +++++++++++++-------
include/crypto/internal/chacha.h | 25 ++++++++++
lib/Makefile | 3 +-
lib/crypto/Makefile | 19 ++++----
lib/{ => crypto}/chacha.c | 37 +++++++++++++--
10 files changed, 118 insertions(+), 73 deletions(-)
diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c
index a8e9b534c8da..26576772f18b 100644
--- a/arch/arm/crypto/chacha-neon-glue.c
+++ b/arch/arm/crypto/chacha-neon-glue.c
@@ -20,7 +20,7 @@
*/
#include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <linux/kernel.h>
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index 1495d2b18518..d4cc61bfe79d 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -20,7 +20,7 @@
*/
#include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <linux/kernel.h>
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 388f95a4ec24..bc62daa8dafd 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -7,7 +7,7 @@
*/
#include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <linux/kernel.h>
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 9ea2b22aff90..5826381aca3a 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1374,6 +1374,14 @@ config CRYPTO_SALSA20
The Salsa20 stream cipher algorithm is designed by Daniel J.
Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
+config CRYPTO_ARCH_HAVE_LIB_CHACHA
+ tristate
+
+config CRYPTO_LIB_CHACHA
+ tristate
+ default y
+ depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
+
config CRYPTO_CHACHA20
tristate "ChaCha stream cipher algorithms"
select CRYPTO_BLKCIPHER
diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c
index 085d8d219987..15a244e2f410 100644
--- a/crypto/chacha_generic.c
+++ b/crypto/chacha_generic.c
@@ -8,29 +8,10 @@
#include <asm/unaligned.h>
#include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
#include <crypto/internal/skcipher.h>
#include <linux/module.h>
-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 skcipher_request *req,
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);
}
@@ -58,22 +39,7 @@ static int chacha_stream_xor(struct skcipher_request *req,
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);
@@ -126,7 +92,7 @@ int crypto_xchacha_crypt(struct skcipher_request *req)
/* 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 */
diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h
index d1e723c6a37d..c29d8f7d69ed 100644
--- a/include/crypto/chacha.h
+++ b/include/crypto/chacha.h
@@ -15,9 +15,8 @@
#ifndef _CRYPTO_CHACHA_H
#define _CRYPTO_CHACHA_H
-#include <crypto/skcipher.h>
+#include <asm/unaligned.h>
#include <linux/types.h>
-#include <linux/crypto.h>
/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
#define CHACHA_IV_SIZE 16
@@ -29,26 +28,42 @@
/* 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_generic(const u32 *in, u32 *out, int nrounds);
+
+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);
}
-void hchacha_block(const u32 *in, u32 *out, int nrounds);
-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv)
+{
+ chacha_init_generic(state, key, iv);
+}
-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_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ int nrounds);
-int crypto_chacha_crypt(struct skcipher_request *req);
-int crypto_xchacha_crypt(struct skcipher_request *req);
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+ unsigned int bytes, int nrounds);
#endif /* _CRYPTO_CHACHA_H */
diff --git a/include/crypto/internal/chacha.h b/include/crypto/internal/chacha.h
new file mode 100644
index 000000000000..f7ffe0f3fa47
--- /dev/null
+++ b/include/crypto/internal/chacha.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CRYPTO_INTERNAL_CHACHA_H
+#define _CRYPTO_INTERNAL_CHACHA_H
+
+#include <crypto/chacha.h>
+#include <crypto/skcipher.h>
+#include <linux/crypto.h>
+
+struct chacha_ctx {
+ u32 key[8];
+ int nrounds;
+};
+
+void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+
+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/lib/Makefile b/lib/Makefile
index 29c02a924973..1436c9608fdb 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,8 +30,7 @@ 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 \
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index cbe0b6a6450d..24dad058f2ae 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -1,13 +1,16 @@
# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o
-libaes-y := aes.o
+# chacha is used by the /dev/random driver which is always builtin
+obj-y += chacha.o
-obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o
-libarc4-y := arc4.o
+obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o
+libaes-y := aes.o
-obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o
-libdes-y := des.o
+obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o
+libarc4-y := arc4.o
-obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o
-libsha256-y := sha256.o
+obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o
+libdes-y := des.o
+
+obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o
+libsha256-y := sha256.o
diff --git a/lib/chacha.c b/lib/crypto/chacha.c
similarity index 76%
rename from lib/chacha.c
rename to lib/crypto/chacha.c
index c7c9826564d3..d4b7c391d934 100644
--- a/lib/chacha.c
+++ b/lib/crypto/chacha.c
@@ -5,11 +5,14 @@
* Copyright (C) 2015 Martin Willi
*/
+#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/bitops.h>
+#include <linux/string.h>
#include <linux/cryptohash.h>
#include <asm/unaligned.h>
+#include <crypto/algapi.h> // for crypto_xor_cpy
#include <crypto/chacha.h>
static void chacha_permute(u32 *x, int nrounds)
@@ -72,7 +75,7 @@ static void chacha_permute(u32 *x, int nrounds)
* 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)
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds)
{
u32 x[16];
int i;
@@ -86,7 +89,7 @@ void chacha_block(u32 *state, u8 *stream, int nrounds)
state[12]++;
}
-EXPORT_SYMBOL(chacha_block);
+EXPORT_SYMBOL(chacha_block_generic);
/**
* hchacha_block - abbreviated ChaCha core, for XChaCha
@@ -99,7 +102,7 @@ EXPORT_SYMBOL(chacha_block);
* 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)
+void hchacha_block_generic(const u32 *in, u32 *out, int nrounds)
{
u32 x[16];
@@ -110,4 +113,30 @@ void hchacha_block(const u32 *in, u32 *out, int nrounds)
memcpy(&out[0], &x[0], 16);
memcpy(&out[4], &x[12], 16);
}
-EXPORT_SYMBOL(hchacha_block);
+EXPORT_SYMBOL(hchacha_block_generic);
+
+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);
+
+#ifndef CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA
+extern void chacha_crypt(u32 *, u8 *, const u8 *, unsigned int, int)
+ __alias(chacha_crypt_generic);
+EXPORT_SYMBOL(chacha_crypt);
+#endif
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 02/20] crypto: x86/chacha - expose SIMD ChaCha routine as library function
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 01/20] crypto: chacha - move existing library code into lib/crypto Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 03/20] crypto: arm64/chacha - expose arm64 " Ard Biesheuvel
` (14 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Wire the existing x86 SIMD ChaCha code into the new ChaCha library
interface.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/x86/crypto/chacha_glue.c | 14 ++++++++++++++
crypto/Kconfig | 1 +
include/crypto/chacha.h | 9 +++++++++
3 files changed, 24 insertions(+)
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index bc62daa8dafd..1ea31d77fa00 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -123,6 +123,20 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
}
}
+void chacha_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ int nrounds)
+{
+ state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+ if (bytes <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
+ 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);
+
static int chacha_simd_stream_xor(struct skcipher_walk *walk,
const struct chacha_ctx *ctx, const u8 *iv)
{
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 5826381aca3a..780d080fc5ec 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1408,6 +1408,7 @@ config CRYPTO_CHACHA20_X86_64
depends on X86 && 64BIT
select CRYPTO_BLKCIPHER
select CRYPTO_CHACHA20
+ select CRYPTO_ARCH_HAVE_LIB_CHACHA
help
SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20,
XChaCha20, and XChaCha12 stream ciphers.
diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h
index c29d8f7d69ed..23747b20d470 100644
--- 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
@@ -57,6 +63,9 @@ static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv)
static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv)
{
+ if (IS_ENABLED(CONFIG_X86_64))
+ state = PTR_ALIGN(state, 16);
+
chacha_init_generic(state, key, iv);
}
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 03/20] crypto: arm64/chacha - expose arm64 ChaCha routine as library function
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 01/20] crypto: chacha - move existing library code into lib/crypto Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 02/20] crypto: x86/chacha - expose SIMD ChaCha routine as library function Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 04/20] crypto: arm/chacha - expose ARM " Ard Biesheuvel
` (13 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Expose the accelerated NEON ChaCha routine directly as a symbol
export so that users of the ChaCha library can use it directly.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/Kconfig | 1 +
arch/arm64/crypto/chacha-neon-glue.c | 12 ++++++++++++
2 files changed, 13 insertions(+)
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 4922c4451e7c..09aa69ccc792 100644
--- 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_CHACHA20
+ select CRYPTO_ARCH_HAVE_LIB_CHACHA
config CRYPTO_NHPOLY1305_NEON
tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)"
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index d4cc61bfe79d..26c12b19a4ad 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -59,6 +59,18 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
}
}
+void chacha_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ int nrounds)
+{
+ if (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);
+
static int chacha_neon_stream_xor(struct skcipher_request *req,
const struct chacha_ctx *ctx, const u8 *iv)
{
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 04/20] crypto: arm/chacha - expose ARM ChaCha routine as library function
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (2 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 03/20] crypto: arm64/chacha - expose arm64 " Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 05/20] crypto: poly1305 - move into lib/crypto and refactor into library Ard Biesheuvel
` (12 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Expose the accelerated NEON ChaCha routine directly as a symbol
export so that users of the ChaCha library can use it directly.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm/crypto/Kconfig | 1 +
arch/arm/crypto/chacha-neon-glue.c | 19 +++++++++++++++++--
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index b24df84a1d7a..70e4d5fe5bdb 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -130,6 +130,7 @@ config CRYPTO_CHACHA20_NEON
depends on KERNEL_MODE_NEON
select CRYPTO_BLKCIPHER
select CRYPTO_CHACHA20
+ select CRYPTO_ARCH_HAVE_LIB_CHACHA
config CRYPTO_NHPOLY1305_NEON
tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)"
diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c
index 26576772f18b..1a32c6e5c885 100644
--- a/arch/arm/crypto/chacha-neon-glue.c
+++ b/arch/arm/crypto/chacha-neon-glue.c
@@ -36,6 +36,8 @@ 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 bool have_neon __ro_after_init;
+
static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
unsigned int bytes, int nrounds)
{
@@ -62,6 +64,18 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
}
}
+void chacha_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ int nrounds)
+{
+ if (!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);
+
static int chacha_neon_stream_xor(struct skcipher_request *req,
const struct chacha_ctx *ctx, const u8 *iv)
{
@@ -177,8 +191,9 @@ static struct skcipher_alg algs[] = {
static int __init chacha_simd_mod_init(void)
{
- if (!(elf_hwcap & HWCAP_NEON))
- return -ENODEV;
+ have_neon = (elf_hwcap & HWCAP_NEON);
+ if (!have_neon)
+ return 0;
return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
}
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 05/20] crypto: poly1305 - move into lib/crypto and refactor into library
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (3 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 04/20] crypto: arm/chacha - expose ARM " Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 06/20] crypto: x86/poly1305 - expose existing driver as poly1305 library Ard Biesheuvel
` (11 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Move the core Poly1305 transformation into a separate library in
lib/crypto so it can be used by other subsystems without going
through the entire crypto API. Also, expose the usual init, update
and final routines as library functions so that the transformation
can be invoked without going through the crypto API.
Also, add the plumbing that permits the library routine entrypoints to
be superseded by per-arch accelerated versions. This will be used in
subsequent patches to expose the crypto API implementations via the
library interface as well.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/x86/crypto/poly1305_glue.c | 90 +++----
crypto/Kconfig | 12 +
crypto/adiantum.c | 5 +-
crypto/nhpoly1305.c | 3 +-
crypto/poly1305_generic.c | 196 ++--------------
include/crypto/internal/poly1305.h | 45 ++++
include/crypto/poly1305.h | 43 ++--
lib/crypto/Makefile | 3 +
lib/crypto/poly1305.c | 247 ++++++++++++++++++++
9 files changed, 368 insertions(+), 276 deletions(-)
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 4a1c05dce950..b43b93c95e79 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -7,47 +7,21 @@
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
#include <crypto/internal/simd.h>
-#include <crypto/poly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/simd.h>
-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, const u32 *b)
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 shash_desc *desc,
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(void)
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);
}
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 780d080fc5ec..f40e8dca57d1 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -654,9 +654,21 @@ config CRYPTO_GHASH
GHASH is the hash function used in GCM (Galois/Counter Mode).
It is not a general-purpose cryptographic hash function.
+config CRYPTO_ARCH_HAVE_LIB_POLY1305
+ tristate
+
+config CRYPTO_LIB_POLY1305_RSIZE
+ int
+ default 1
+
+config CRYPTO_LIB_POLY1305
+ tristate "Poly1305 authenticator library"
+ depends on CRYPTO_ARCH_HAVE_LIB_POLY1305 || !CRYPTO_ARCH_HAVE_LIB_POLY1305
+
config CRYPTO_POLY1305
tristate "Poly1305 authenticator algorithm"
select CRYPTO_HASH
+ select CRYPTO_LIB_POLY1305
help
Poly1305 authenticator algorithm, RFC7539.
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 395a3ddd3707..aded26092268 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -33,6 +33,7 @@
#include <crypto/b128ops.h>
#include <crypto/chacha.h>
#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
#include <crypto/internal/skcipher.h>
#include <crypto/nhpoly1305.h>
#include <crypto/scatterwalk.h>
@@ -242,11 +243,11 @@ static void adiantum_hash_header(struct skcipher_request *req)
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);
}
diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c
index 9ab4e07cde4d..f6b6a52092b4 100644
--- a/crypto/nhpoly1305.c
+++ b/crypto/nhpoly1305.c
@@ -33,6 +33,7 @@
#include <asm/unaligned.h>
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
#include <crypto/nhpoly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
@@ -78,7 +79,7 @@ static void process_nh_hash_value(struct nhpoly1305_state *state,
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);
}
/*
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index adc40298c749..35fdb35c1188 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -13,51 +13,25 @@
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
-#include <crypto/poly1305.h>
+#include <crypto/internal/poly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/unaligned.h>
-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);
poly1305_core_init(&dctx->h);
dctx->buflen = 0;
- dctx->rset = false;
+ dctx->rset = 0;
dctx->sset = false;
return 0;
}
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
@@ -68,10 +42,10 @@ unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
{
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);
@@ -87,84 +61,8 @@ unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
}
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;
@@ -174,14 +72,14 @@ static void poly1305_blocks(struct poly1305_desc_ctx *dctx,
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,
+int crypto_poly1305_update(struct shash_desc *shash_desc,
const u8 *src, unsigned int srclen)
{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(shash_desc);
unsigned int bytes;
if (unlikely(dctx->buflen)) {
@@ -193,13 +91,13 @@ int crypto_poly1305_update(struct shash_desc *desc,
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;
}
@@ -213,82 +111,14 @@ int crypto_poly1305_update(struct shash_desc *desc,
}
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);
- __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_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 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);
diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h
new file mode 100644
index 000000000000..e819df14bb78
--- /dev/null
+++ b/include/crypto/internal/poly1305.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values for the Poly1305 algorithm
+ */
+
+#ifndef _CRYPTO_INTERNAL_POLY1305_H
+#define _CRYPTO_INTERNAL_POLY1305_H
+
+#include <linux/types.h>
+#include <crypto/poly1305.h>
+
+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);
+
+void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key);
+
+void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src,
+ unsigned int nbytes);
+
+void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *digest);
+
+/* 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
diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h
index 34317ed2071e..39afea016ac3 100644
--- a/include/crypto/poly1305.h
+++ b/include/crypto/poly1305.h
@@ -22,43 +22,26 @@ 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[CONFIG_CRYPTO_LIB_POLY1305_RSIZE];
};
-/*
- * 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);
+void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key);
-/* 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);
+void poly1305_update(struct poly1305_desc_ctx *desc, const u8 *src,
+ unsigned int nbytes);
+void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest);
#endif
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 24dad058f2ae..6bf8a0a4ee0e 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -12,5 +12,8 @@ libarc4-y := arc4.o
obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o
libdes-y := des.o
+obj-$(CONFIG_CRYPTO_LIB_POLY1305) += libpoly1305.o
+libpoly1305-y := poly1305.o
+
obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o
libsha256-y := sha256.o
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
new file mode 100644
index 000000000000..19d6441cc30a
--- /dev/null
+++ b/lib/crypto/poly1305.c
@@ -0,0 +1,247 @@
+// 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 <crypto/internal/poly1305.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm/unaligned.h>
+
+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);
+ 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);
+}
+EXPORT_SYMBOL_GPL(poly1305_final_generic);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+
+#ifndef CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305
+
+extern void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key)
+ __alias(poly1305_init_generic);
+EXPORT_SYMBOL_GPL(poly1305_init);
+
+extern void poly1305_update(struct poly1305_desc_ctx *desc, const u8 *src,
+ unsigned int nbytes)
+ __alias(poly1305_update_generic);
+EXPORT_SYMBOL_GPL(poly1305_update);
+
+extern void poly1305_final(struct poly1305_desc_ctx *desc, u8 *dst)
+ __alias(poly1305_final_generic);
+EXPORT_SYMBOL_GPL(poly1305_final);
+
+#endif
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 06/20] crypto: x86/poly1305 - expose existing driver as poly1305 library
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (4 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 05/20] crypto: poly1305 - move into lib/crypto and refactor into library Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 07/20] crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation Ard Biesheuvel
` (10 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Implement the init/update/final Poly1305 library routines in the
accelerated SIMD driver for x86 so they are accessible to users of
the Poly1305 library interface.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/x86/crypto/poly1305_glue.c | 60 +++++++++++++++-----
crypto/Kconfig | 2 +
2 files changed, 48 insertions(+), 14 deletions(-)
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index b43b93c95e79..d3cc92996f58 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -85,18 +85,11 @@ static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx,
return srclen;
}
-static int poly1305_simd_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen)
+static int poly1305_simd_do_update(struct poly1305_desc_ctx *dctx,
+ const u8 *src, unsigned int srclen)
{
- 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);
@@ -117,8 +110,6 @@ static int poly1305_simd_update(struct shash_desc *desc,
srclen = bytes;
}
- kernel_fpu_end();
-
if (unlikely(srclen)) {
dctx->buflen = srclen;
memcpy(dctx->buf, src, srclen);
@@ -127,6 +118,47 @@ static int poly1305_simd_update(struct shash_desc *desc,
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);
+ int ret;
+
+ /* 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();
+ ret = poly1305_simd_do_update(dctx, src, srclen);
+ kernel_fpu_end();
+
+ return ret;
+}
+
+void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key)
+{
+ poly1305_init_generic(desc, key);
+}
+EXPORT_SYMBOL(poly1305_init);
+
+void poly1305_update(struct poly1305_desc_ctx *dctx, const u8 *src,
+ unsigned int nbytes)
+{
+ if (nbytes <= 288 || !crypto_simd_usable())
+ return poly1305_update_generic(dctx, src, nbytes);
+
+ kernel_fpu_begin();
+ poly1305_simd_do_update(dctx, src, nbytes);
+ kernel_fpu_end();
+}
+EXPORT_SYMBOL(poly1305_update);
+
+void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest)
+{
+ poly1305_final_generic(desc, digest);
+}
+EXPORT_SYMBOL(poly1305_final);
+
static struct shash_alg alg = {
.digestsize = POLY1305_DIGEST_SIZE,
.init = crypto_poly1305_init,
@@ -151,9 +183,9 @@ static int __init poly1305_simd_mod_init(void)
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);
+ alg.descsize = sizeof(struct poly1305_desc_ctx);
+ if (!poly1305_use_avx2)
+ alg.descsize -= 10 * sizeof(u32);
return crypto_register_shash(&alg);
}
diff --git a/crypto/Kconfig b/crypto/Kconfig
index f40e8dca57d1..6a952a61675b 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -659,6 +659,7 @@ config CRYPTO_ARCH_HAVE_LIB_POLY1305
config CRYPTO_LIB_POLY1305_RSIZE
int
+ default 4 if X86_64
default 1
config CRYPTO_LIB_POLY1305
@@ -680,6 +681,7 @@ config CRYPTO_POLY1305_X86_64
tristate "Poly1305 authenticator algorithm (x86_64/SSE2/AVX2)"
depends on X86 && 64BIT
select CRYPTO_POLY1305
+ select CRYPTO_ARCH_HAVE_LIB_POLY1305
help
Poly1305 authenticator algorithm, RFC7539.
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 07/20] crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (5 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 06/20] crypto: x86/poly1305 - expose existing driver as poly1305 library Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 08/20] crypto: arm/poly1305 " Ard Biesheuvel
` (9 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Andy Polyakov, Samuel Neves, Will Deacon, Dan Carpenter,
Andy Lutomirski, Marc Zyngier, Linus Torvalds, David Miller,
linux-arm-kernel
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 <appro@cryptogams.org>
Signed-off-by: Andy Polyakov <appro@cryptogams.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/crypto/Kconfig | 5 +
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 | 227 +++++
crypto/Kconfig | 1 +
6 files changed, 1990 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 09aa69ccc792..05607de28181 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -106,6 +106,11 @@ config CRYPTO_CHACHA20_NEON
select CRYPTO_CHACHA20
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_ARCH_HAVE_LIB_POLY1305
+
config CRYPTO_NHPOLY1305_NEON
tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)"
depends on KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 0435f2a0610e..d0901e610df3 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -50,6 +50,10 @@ sha512-arm64-y := sha512-glue.o sha512-core.o
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
$(call cmd,perlasm)
+
endif
-clean-files += sha256-core.S sha512-core.S
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/crypto/poly1305-armv8.pl
new file mode 100644
index 000000000000..6e5576d19af8
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-armv8.pl
@@ -0,0 +1,913 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+# This module implements Poly1305 hash for ARMv8.
+#
+# June 2015
+#
+# Numbers are cycles per processed byte with poly1305_blocks alone.
+#
+# IALU/gcc-4.9 NEON
+#
+# Apple A7 1.86/+5% 0.72
+# Cortex-A53 2.69/+58% 1.47
+# Cortex-A57 2.70/+7% 1.14
+# Denver 1.64/+50% 1.18(*)
+# X-Gene 2.13/+68% 2.27
+# Mongoose 1.77/+75% 1.12
+# Kryo 2.70/+55% 1.13
+# ThunderX2 1.17/+95% 1.36
+#
+# (*) estimate based on resources availability is less than 1.0,
+# i.e. measured result is worse than expected, presumably binary
+# translator is not almighty;
+
+$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;
diff --git a/arch/arm64/crypto/poly1305-core.S_shipped b/arch/arm64/crypto/poly1305-core.S_shipped
new file mode 100644
index 000000000000..8d1c4e420ccd
--- /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
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..9d6bc3f4c5db
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+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);
+
+void poly1305_init(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);
+
+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(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 (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 (do_neon)
+ kernel_neon_begin();
+ neon_poly1305_do_update(dctx, src, srclen, do_neon);
+ if (do_neon)
+ kernel_neon_end();
+ return 0;
+}
+
+void poly1305_update(struct poly1305_desc_ctx *dctx, const u8 *src,
+ unsigned int nbytes)
+{
+ bool do_neon = crypto_simd_usable() && nbytes > 128;
+
+ 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 (do_neon) {
+ 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);
+
+void poly1305_final(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, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+ }
+
+ poly1305_emit(dctx, 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);
+}
+EXPORT_SYMBOL(poly1305_final);
+
+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(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)
+{
+ return crypto_register_shash(&neon_poly1305_alg);
+}
+
+static void __exit neon_poly1305_mod_exit(void)
+{
+ 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");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 6a952a61675b..5b3250034288 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -660,6 +660,7 @@ config CRYPTO_ARCH_HAVE_LIB_POLY1305
config CRYPTO_LIB_POLY1305_RSIZE
int
default 4 if X86_64
+ default 9 if ARM64
default 1
config CRYPTO_LIB_POLY1305
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 08/20] crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (6 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 07/20] crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 09/20] int128: move __uint128_t compiler test to Kconfig Ard Biesheuvel
` (8 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Andy Polyakov, Samuel Neves, Will Deacon, Dan Carpenter,
Andy Lutomirski, Marc Zyngier, Linus Torvalds, David Miller,
linux-arm-kernel
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 <appro@cryptogams.org>
Signed-off-by: Andy Polyakov <appro@cryptogams.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm/crypto/Kconfig | 4 +
arch/arm/crypto/Makefile | 7 +-
arch/arm/crypto/poly1305-armv4.pl | 1236 ++++++++++++++++++++
arch/arm/crypto/poly1305-core.S_shipped | 1158 ++++++++++++++++++
arch/arm/crypto/poly1305-glue.c | 271 +++++
crypto/Kconfig | 2 +-
6 files changed, 2676 insertions(+), 2 deletions(-)
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 70e4d5fe5bdb..8a603698b296 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -132,6 +132,10 @@ config CRYPTO_CHACHA20_NEON
select CRYPTO_CHACHA20
select CRYPTO_ARCH_HAVE_LIB_CHACHA
+config CRYPTO_POLY1305_ARM
+ tristate "Accelerated scalar and SIMD Poly1305 hash implementations"
+ select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
config CRYPTO_NHPOLY1305_NEON
tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)"
depends on KERNEL_MODE_NEON
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 4180f3a13512..c9d5fab8ad45 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+obj-$(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
@@ -54,12 +55,16 @@ 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
+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)
@@ -67,4 +72,4 @@ $(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
$(call cmd,perl)
endif
-clean-files += sha256-core.S sha512-core.S
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
diff --git a/arch/arm/crypto/poly1305-armv4.pl b/arch/arm/crypto/poly1305-armv4.pl
new file mode 100644
index 000000000000..6d79498d3115
--- /dev/null
+++ b/arch/arm/crypto/poly1305-armv4.pl
@@ -0,0 +1,1236 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+# IALU(*)/gcc-4.4 NEON
+#
+# ARM11xx(ARMv6) 7.78/+100% -
+# Cortex-A5 6.35/+130% 3.00
+# Cortex-A8 6.25/+115% 2.36
+# Cortex-A9 5.10/+95% 2.55
+# Cortex-A15 3.85/+85% 1.25(**)
+# Snapdragon S4 5.70/+100% 1.48(**)
+#
+# (*) this is for -march=armv6, i.e. with bunch of ldrb loading data;
+# (**) these are trade-off results, they can be improved by ~8% but at
+# the cost of 15/12% regression on Cortex-A5/A7, it's even possible
+# to improve Cortex-A9 result, but then A5/A7 loose more than 20%;
+
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+ ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+ ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+ die "can't locate arm-xlate.pl";
+
+ open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+ open STDOUT,">$output";
+}
+
+($ctx,$inp,$len,$padbit)=map("r$_",(0..3));
+
+$code.=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit poly1305_emit_arm
+.globl poly1305_blocks_neon
+#endif
+
+#if defined(__thumb2__)
+.syntax unified
+.thumb
+#else
+.code 32
+#endif
+
+.text
+
+.globl poly1305_emit
+.globl poly1305_blocks
+.globl poly1305_init
+.type poly1305_init,%function
+.align 5
+poly1305_init:
+.Lpoly1305_init:
+ stmdb sp!,{r4-r11}
+
+ eor r3,r3,r3
+ cmp $inp,#0
+ str r3,[$ctx,#0] @ zero hash value
+ str r3,[$ctx,#4]
+ str r3,[$ctx,#8]
+ str r3,[$ctx,#12]
+ str r3,[$ctx,#16]
+ str r3,[$ctx,#36] @ clear is_base2_26
+ add $ctx,$ctx,#20
+
+#ifdef __thumb2__
+ it eq
+#endif
+ moveq r0,#0
+ beq .Lno_key
+
+#if __ARM_MAX_ARCH__>=7
+ mov r3,#-1
+ str r3,[$ctx,#28] @ impossible key power value
+# ifndef __KERNEL__
+ adr r11,.Lpoly1305_init
+ ldr r12,.LOPENSSL_armcap
+# endif
+#endif
+ ldrb r4,[$inp,#0]
+ mov r10,#0x0fffffff
+ ldrb r5,[$inp,#1]
+ and r3,r10,#-4 @ 0x0ffffffc
+ ldrb r6,[$inp,#2]
+ ldrb r7,[$inp,#3]
+ orr r4,r4,r5,lsl#8
+ ldrb r5,[$inp,#4]
+ orr r4,r4,r6,lsl#16
+ ldrb r6,[$inp,#5]
+ orr r4,r4,r7,lsl#24
+ ldrb r7,[$inp,#6]
+ and r4,r4,r10
+
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+# if !defined(_WIN32)
+ ldr r12,[r11,r12] @ OPENSSL_armcap_P
+# endif
+# if defined(__APPLE__) || defined(_WIN32)
+ ldr r12,[r12]
+# endif
+#endif
+ ldrb r8,[$inp,#7]
+ orr r5,r5,r6,lsl#8
+ ldrb r6,[$inp,#8]
+ orr r5,r5,r7,lsl#16
+ ldrb r7,[$inp,#9]
+ orr r5,r5,r8,lsl#24
+ ldrb r8,[$inp,#10]
+ and r5,r5,r3
+
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ tst r12,#ARMV7_NEON @ check for NEON
+# ifdef __thumb2__
+ adr r9,.Lpoly1305_blocks_neon
+ adr r11,.Lpoly1305_blocks
+ it ne
+ movne r11,r9
+ adr r12,.Lpoly1305_emit
+ orr r11,r11,#1 @ thumb-ify addresses
+ orr r12,r12,#1
+# else
+ add r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
+ ite eq
+ addeq r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
+ addne r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
+# endif
+#endif
+ ldrb r9,[$inp,#11]
+ orr r6,r6,r7,lsl#8
+ ldrb r7,[$inp,#12]
+ orr r6,r6,r8,lsl#16
+ ldrb r8,[$inp,#13]
+ orr r6,r6,r9,lsl#24
+ ldrb r9,[$inp,#14]
+ and r6,r6,r3
+
+ ldrb r10,[$inp,#15]
+ orr r7,r7,r8,lsl#8
+ str r4,[$ctx,#0]
+ orr r7,r7,r9,lsl#16
+ str r5,[$ctx,#4]
+ orr r7,r7,r10,lsl#24
+ str r6,[$ctx,#8]
+ and r7,r7,r3
+ str r7,[$ctx,#12]
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ stmia r2,{r11,r12} @ fill functions table
+ mov r0,#1
+#else
+ mov r0,#0
+#endif
+.Lno_key:
+ ldmia sp!,{r4-r11}
+#if __ARM_ARCH__>=5
+ ret @ bx lr
+#else
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size poly1305_init,.-poly1305_init
+___
+{
+my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
+my ($s1,$s2,$s3)=($r1,$r2,$r3);
+
+$code.=<<___;
+.type poly1305_blocks,%function
+.align 5
+poly1305_blocks:
+.Lpoly1305_blocks:
+ stmdb sp!,{r3-r11,lr}
+
+ ands $len,$len,#-16
+ beq .Lno_data
+
+ add $len,$len,$inp @ end pointer
+ sub sp,sp,#32
+
+#if __ARM_ARCH__<7
+ ldmia $ctx,{$h0-$r3} @ load context
+ add $ctx,$ctx,#20
+ str $len,[sp,#16] @ offload stuff
+ str $ctx,[sp,#12]
+#else
+ ldr lr,[$ctx,#36] @ is_base2_26
+ ldmia $ctx!,{$h0-$h4} @ load hash value
+ str $len,[sp,#16] @ offload stuff
+ str $ctx,[sp,#12]
+
+ adds $r0,$h0,$h1,lsl#26 @ base 2^26 -> base 2^32
+ mov $r1,$h1,lsr#6
+ adcs $r1,$r1,$h2,lsl#20
+ mov $r2,$h2,lsr#12
+ adcs $r2,$r2,$h3,lsl#14
+ mov $r3,$h3,lsr#18
+ adcs $r3,$r3,$h4,lsl#8
+ mov $len,#0
+ teq lr,#0
+ str $len,[$ctx,#16] @ clear is_base2_26
+ adc $len,$len,$h4,lsr#24
+
+ itttt ne
+ movne $h0,$r0 @ choose between radixes
+ movne $h1,$r1
+ movne $h2,$r2
+ movne $h3,$r3
+ ldmia $ctx,{$r0-$r3} @ load key
+ it ne
+ movne $h4,$len
+#endif
+
+ mov lr,$inp
+ cmp $padbit,#0
+ str $r1,[sp,#20]
+ str $r2,[sp,#24]
+ str $r3,[sp,#28]
+ b .Loop
+
+.align 4
+.Loop:
+#if __ARM_ARCH__<7
+ ldrb r0,[lr],#16 @ load input
+# ifdef __thumb2__
+ it hi
+# endif
+ addhi $h4,$h4,#1 @ 1<<128
+ ldrb r1,[lr,#-15]
+ ldrb r2,[lr,#-14]
+ ldrb r3,[lr,#-13]
+ orr r1,r0,r1,lsl#8
+ ldrb r0,[lr,#-12]
+ orr r2,r1,r2,lsl#16
+ ldrb r1,[lr,#-11]
+ orr r3,r2,r3,lsl#24
+ ldrb r2,[lr,#-10]
+ adds $h0,$h0,r3 @ accumulate input
+
+ ldrb r3,[lr,#-9]
+ orr r1,r0,r1,lsl#8
+ ldrb r0,[lr,#-8]
+ orr r2,r1,r2,lsl#16
+ ldrb r1,[lr,#-7]
+ orr r3,r2,r3,lsl#24
+ ldrb r2,[lr,#-6]
+ adcs $h1,$h1,r3
+
+ ldrb r3,[lr,#-5]
+ orr r1,r0,r1,lsl#8
+ ldrb r0,[lr,#-4]
+ orr r2,r1,r2,lsl#16
+ ldrb r1,[lr,#-3]
+ orr r3,r2,r3,lsl#24
+ ldrb r2,[lr,#-2]
+ adcs $h2,$h2,r3
+
+ ldrb r3,[lr,#-1]
+ orr r1,r0,r1,lsl#8
+ str lr,[sp,#8] @ offload input pointer
+ orr r2,r1,r2,lsl#16
+ add $s1,$r1,$r1,lsr#2
+ orr r3,r2,r3,lsl#24
+#else
+ ldr r0,[lr],#16 @ load input
+ it hi
+ addhi $h4,$h4,#1 @ padbit
+ ldr r1,[lr,#-12]
+ ldr r2,[lr,#-8]
+ ldr r3,[lr,#-4]
+# ifdef __ARMEB__
+ rev r0,r0
+ rev r1,r1
+ rev r2,r2
+ rev r3,r3
+# endif
+ adds $h0,$h0,r0 @ accumulate input
+ str lr,[sp,#8] @ offload input pointer
+ adcs $h1,$h1,r1
+ add $s1,$r1,$r1,lsr#2
+ adcs $h2,$h2,r2
+#endif
+ add $s2,$r2,$r2,lsr#2
+ adcs $h3,$h3,r3
+ add $s3,$r3,$r3,lsr#2
+
+ umull r2,r3,$h1,$r0
+ adc $h4,$h4,#0
+ umull r0,r1,$h0,$r0
+ umlal r2,r3,$h4,$s1
+ umlal r0,r1,$h3,$s1
+ ldr $r1,[sp,#20] @ reload $r1
+ umlal r2,r3,$h2,$s3
+ umlal r0,r1,$h1,$s3
+ umlal r2,r3,$h3,$s2
+ umlal r0,r1,$h2,$s2
+ umlal r2,r3,$h0,$r1
+ str r0,[sp,#0] @ future $h0
+ mul r0,$s2,$h4
+ ldr $r2,[sp,#24] @ reload $r2
+ adds r2,r2,r1 @ d1+=d0>>32
+ eor r1,r1,r1
+ adc lr,r3,#0 @ future $h2
+ str r2,[sp,#4] @ future $h1
+
+ mul r2,$s3,$h4
+ eor r3,r3,r3
+ umlal r0,r1,$h3,$s3
+ ldr $r3,[sp,#28] @ reload $r3
+ umlal r2,r3,$h3,$r0
+ umlal r0,r1,$h2,$r0
+ umlal r2,r3,$h2,$r1
+ umlal r0,r1,$h1,$r1
+ umlal r2,r3,$h1,$r2
+ umlal r0,r1,$h0,$r2
+ umlal r2,r3,$h0,$r3
+ ldr $h0,[sp,#0]
+ mul $h4,$r0,$h4
+ ldr $h1,[sp,#4]
+
+ adds $h2,lr,r0 @ d2+=d1>>32
+ ldr lr,[sp,#8] @ reload input pointer
+ adc r1,r1,#0
+ adds $h3,r2,r1 @ d3+=d2>>32
+ ldr r0,[sp,#16] @ reload end pointer
+ adc r3,r3,#0
+ add $h4,$h4,r3 @ h4+=d3>>32
+
+ and r1,$h4,#-4
+ and $h4,$h4,#3
+ add r1,r1,r1,lsr#2 @ *=5
+ adds $h0,$h0,r1
+ adcs $h1,$h1,#0
+ adcs $h2,$h2,#0
+ adcs $h3,$h3,#0
+ adc $h4,$h4,#0
+
+ cmp r0,lr @ done yet?
+ bhi .Loop
+
+ ldr $ctx,[sp,#12]
+ add sp,sp,#32
+ stmdb $ctx,{$h0-$h4} @ store the result
+
+.Lno_data:
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r3-r11,pc}
+#else
+ ldmia sp!,{r3-r11,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size poly1305_blocks,.-poly1305_blocks
+___
+}
+{
+my ($ctx,$mac,$nonce)=map("r$_",(0..2));
+my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
+my $g4=$ctx;
+
+$code.=<<___;
+.type poly1305_emit,%function
+.align 5
+poly1305_emit:
+.Lpoly1305_emit:
+ stmdb sp!,{r4-r11}
+
+ ldmia $ctx,{$h0-$h4}
+
+#if __ARM_ARCH__>=7
+ ldr ip,[$ctx,#36] @ is_base2_26
+
+ adds $g0,$h0,$h1,lsl#26 @ base 2^26 -> base 2^32
+ mov $g1,$h1,lsr#6
+ adcs $g1,$g1,$h2,lsl#20
+ mov $g2,$h2,lsr#12
+ adcs $g2,$g2,$h3,lsl#14
+ mov $g3,$h3,lsr#18
+ adcs $g3,$g3,$h4,lsl#8
+ mov $g4,#0
+ adc $g4,$g4,$h4,lsr#24
+
+ tst ip,ip
+ itttt ne
+ movne $h0,$g0
+ movne $h1,$g1
+ movne $h2,$g2
+ movne $h3,$g3
+ it ne
+ movne $h4,$g4
+#endif
+
+ adds $g0,$h0,#5 @ compare to modulus
+ adcs $g1,$h1,#0
+ adcs $g2,$h2,#0
+ adcs $g3,$h3,#0
+ adc $g4,$h4,#0
+ tst $g4,#4 @ did it carry/borrow?
+
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h0,$g0
+ ldr $g0,[$nonce,#0]
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h1,$g1
+ ldr $g1,[$nonce,#4]
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h2,$g2
+ ldr $g2,[$nonce,#8]
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h3,$g3
+ ldr $g3,[$nonce,#12]
+
+ adds $h0,$h0,$g0
+ adcs $h1,$h1,$g1
+ adcs $h2,$h2,$g2
+ adc $h3,$h3,$g3
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+ rev $h0,$h0
+ rev $h1,$h1
+ rev $h2,$h2
+ rev $h3,$h3
+# endif
+ str $h0,[$mac,#0]
+ str $h1,[$mac,#4]
+ str $h2,[$mac,#8]
+ str $h3,[$mac,#12]
+#else
+ strb $h0,[$mac,#0]
+ mov $h0,$h0,lsr#8
+ strb $h1,[$mac,#4]
+ mov $h1,$h1,lsr#8
+ strb $h2,[$mac,#8]
+ mov $h2,$h2,lsr#8
+ strb $h3,[$mac,#12]
+ mov $h3,$h3,lsr#8
+
+ strb $h0,[$mac,#1]
+ mov $h0,$h0,lsr#8
+ strb $h1,[$mac,#5]
+ mov $h1,$h1,lsr#8
+ strb $h2,[$mac,#9]
+ mov $h2,$h2,lsr#8
+ strb $h3,[$mac,#13]
+ mov $h3,$h3,lsr#8
+
+ strb $h0,[$mac,#2]
+ mov $h0,$h0,lsr#8
+ strb $h1,[$mac,#6]
+ mov $h1,$h1,lsr#8
+ strb $h2,[$mac,#10]
+ mov $h2,$h2,lsr#8
+ strb $h3,[$mac,#14]
+ mov $h3,$h3,lsr#8
+
+ strb $h0,[$mac,#3]
+ strb $h1,[$mac,#7]
+ strb $h2,[$mac,#11]
+ strb $h3,[$mac,#15]
+#endif
+ ldmia sp!,{r4-r11}
+#if __ARM_ARCH__>=5
+ ret @ bx lr
+#else
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size poly1305_emit,.-poly1305_emit
+___
+{
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
+my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
+my ($T0,$T1,$MASK) = map("q$_",(15,4,0));
+
+my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.fpu neon
+
+.type poly1305_init_neon,%function
+.align 5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+ ldr r3,[$ctx,#48] @ first table element
+ cmp r3,#-1 @ is value impossible?
+ bne .Lno_init_neon
+
+ ldr r4,[$ctx,#20] @ load key base 2^32
+ ldr r5,[$ctx,#24]
+ ldr r6,[$ctx,#28]
+ ldr r7,[$ctx,#32]
+
+ and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
+ mov r3,r4,lsr#26
+ mov r4,r5,lsr#20
+ orr r3,r3,r5,lsl#6
+ mov r5,r6,lsr#14
+ orr r4,r4,r6,lsl#12
+ mov r6,r7,lsr#8
+ orr r5,r5,r7,lsl#18
+ and r3,r3,#0x03ffffff
+ and r4,r4,#0x03ffffff
+ and r5,r5,#0x03ffffff
+
+ vdup.32 $R0,r2 @ r^1 in both lanes
+ add r2,r3,r3,lsl#2 @ *5
+ vdup.32 $R1,r3
+ add r3,r4,r4,lsl#2
+ vdup.32 $S1,r2
+ vdup.32 $R2,r4
+ add r4,r5,r5,lsl#2
+ vdup.32 $S2,r3
+ vdup.32 $R3,r5
+ add r5,r6,r6,lsl#2
+ vdup.32 $S3,r4
+ vdup.32 $R4,r6
+ vdup.32 $S4,r5
+
+ mov $zeros,#2 @ counter
+
+.Lsquare_neon:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+ @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
+ @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
+ @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
+ @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
+
+ vmull.u32 $D0,$R0,${R0}[1]
+ vmull.u32 $D1,$R1,${R0}[1]
+ vmull.u32 $D2,$R2,${R0}[1]
+ vmull.u32 $D3,$R3,${R0}[1]
+ vmull.u32 $D4,$R4,${R0}[1]
+
+ vmlal.u32 $D0,$R4,${S1}[1]
+ vmlal.u32 $D1,$R0,${R1}[1]
+ vmlal.u32 $D2,$R1,${R1}[1]
+ vmlal.u32 $D3,$R2,${R1}[1]
+ vmlal.u32 $D4,$R3,${R1}[1]
+
+ vmlal.u32 $D0,$R3,${S2}[1]
+ vmlal.u32 $D1,$R4,${S2}[1]
+ vmlal.u32 $D3,$R1,${R2}[1]
+ vmlal.u32 $D2,$R0,${R2}[1]
+ vmlal.u32 $D4,$R2,${R2}[1]
+
+ vmlal.u32 $D0,$R2,${S3}[1]
+ vmlal.u32 $D3,$R0,${R3}[1]
+ vmlal.u32 $D1,$R3,${S3}[1]
+ vmlal.u32 $D2,$R4,${S3}[1]
+ vmlal.u32 $D4,$R1,${R3}[1]
+
+ vmlal.u32 $D3,$R4,${S4}[1]
+ vmlal.u32 $D0,$R1,${S4}[1]
+ vmlal.u32 $D1,$R2,${S4}[1]
+ vmlal.u32 $D2,$R3,${S4}[1]
+ vmlal.u32 $D4,$R0,${R4}[1]
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+ @ and P. Schwabe
+ @
+ @ H0>>+H1>>+H2>>+H3>>+H4
+ @ H3>>+H4>>*5+H0>>+H1
+ @
+ @ Trivia.
+ @
+ @ Result of multiplication of n-bit number by m-bit number is
+ @ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+ @ m-bit number multiplied by 2^n is still n+m bits wide.
+ @
+ @ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+ @ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+ @ one is n+1 bits wide.
+ @
+ @ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+ @ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+ @ can be 27. However! In cases when their width exceeds 26 bits
+ @ they are limited by 2^26+2^6. This in turn means that *sum*
+ @ of the products with these values can still be viewed as sum
+ @ of 52-bit numbers as long as the amount of addends is not a
+ @ power of 2. For example,
+ @
+ @ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+ @
+ @ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+ @ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+ @ 8 * (2^52) or 2^55. However, the value is then multiplied by
+ @ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+ @ which is less than 32 * (2^52) or 2^57. And when processing
+ @ data we are looking at triple as many addends...
+ @
+ @ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+ @ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+ @ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+ @ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+ @ instruction accepts 2x32-bit input and writes 2x64-bit result.
+ @ This means that result of reduction have to be compressed upon
+ @ loop wrap-around. This can be done in the process of reduction
+ @ to minimize amount of instructions [as well as amount of
+ @ 128-bit instructions, which benefits low-end processors], but
+ @ one has to watch for H2 (which is narrower than H0) and 5*H4
+ @ not being wider than 58 bits, so that result of right shift
+ @ by 26 bits fits in 32 bits. This is also useful on x86,
+ @ because it allows to use paddd in place for paddq, which
+ @ benefits Atom, where paddq is ridiculously slow.
+
+ vshr.u64 $T0,$D3,#26
+ vmovn.i64 $D3#lo,$D3
+ vshr.u64 $T1,$D0,#26
+ vmovn.i64 $D0#lo,$D0
+ vadd.i64 $D4,$D4,$T0 @ h3 -> h4
+ vbic.i32 $D3#lo,#0xfc000000 @ &=0x03ffffff
+ vadd.i64 $D1,$D1,$T1 @ h0 -> h1
+ vbic.i32 $D0#lo,#0xfc000000
+
+ vshrn.u64 $T0#lo,$D4,#26
+ vmovn.i64 $D4#lo,$D4
+ vshr.u64 $T1,$D1,#26
+ vmovn.i64 $D1#lo,$D1
+ vadd.i64 $D2,$D2,$T1 @ h1 -> h2
+ vbic.i32 $D4#lo,#0xfc000000
+ vbic.i32 $D1#lo,#0xfc000000
+
+ vadd.i32 $D0#lo,$D0#lo,$T0#lo
+ vshl.u32 $T0#lo,$T0#lo,#2
+ vshrn.u64 $T1#lo,$D2,#26
+ vmovn.i64 $D2#lo,$D2
+ vadd.i32 $D0#lo,$D0#lo,$T0#lo @ h4 -> h0
+ vadd.i32 $D3#lo,$D3#lo,$T1#lo @ h2 -> h3
+ vbic.i32 $D2#lo,#0xfc000000
+
+ vshr.u32 $T0#lo,$D0#lo,#26
+ vbic.i32 $D0#lo,#0xfc000000
+ vshr.u32 $T1#lo,$D3#lo,#26
+ vbic.i32 $D3#lo,#0xfc000000
+ vadd.i32 $D1#lo,$D1#lo,$T0#lo @ h0 -> h1
+ vadd.i32 $D4#lo,$D4#lo,$T1#lo @ h3 -> h4
+
+ subs $zeros,$zeros,#1
+ beq .Lsquare_break_neon
+
+ add $tbl0,$ctx,#(48+0*9*4)
+ add $tbl1,$ctx,#(48+1*9*4)
+
+ vtrn.32 $R0,$D0#lo @ r^2:r^1
+ vtrn.32 $R2,$D2#lo
+ vtrn.32 $R3,$D3#lo
+ vtrn.32 $R1,$D1#lo
+ vtrn.32 $R4,$D4#lo
+
+ vshl.u32 $S2,$R2,#2 @ *5
+ vshl.u32 $S3,$R3,#2
+ vshl.u32 $S1,$R1,#2
+ vshl.u32 $S4,$R4,#2
+ vadd.i32 $S2,$S2,$R2
+ vadd.i32 $S1,$S1,$R1
+ vadd.i32 $S3,$S3,$R3
+ vadd.i32 $S4,$S4,$R4
+
+ vst4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+ vst4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+ vst4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vst4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vst1.32 {${S4}[0]},[$tbl0,:32]
+ vst1.32 {${S4}[1]},[$tbl1,:32]
+
+ b .Lsquare_neon
+
+.align 4
+.Lsquare_break_neon:
+ add $tbl0,$ctx,#(48+2*4*9)
+ add $tbl1,$ctx,#(48+3*4*9)
+
+ vmov $R0,$D0#lo @ r^4:r^3
+ vshl.u32 $S1,$D1#lo,#2 @ *5
+ vmov $R1,$D1#lo
+ vshl.u32 $S2,$D2#lo,#2
+ vmov $R2,$D2#lo
+ vshl.u32 $S3,$D3#lo,#2
+ vmov $R3,$D3#lo
+ vshl.u32 $S4,$D4#lo,#2
+ vmov $R4,$D4#lo
+ vadd.i32 $S1,$S1,$D1#lo
+ vadd.i32 $S2,$S2,$D2#lo
+ vadd.i32 $S3,$S3,$D3#lo
+ vadd.i32 $S4,$S4,$D4#lo
+
+ vst4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+ vst4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+ vst4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vst4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vst1.32 {${S4}[0]},[$tbl0]
+ vst1.32 {${S4}[1]},[$tbl1]
+
+.Lno_init_neon:
+ ret @ bx lr
+.size poly1305_init_neon,.-poly1305_init_neon
+
+.type poly1305_blocks_neon,%function
+.align 5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+ ldr ip,[$ctx,#36] @ is_base2_26
+
+ cmp $len,#64
+ blo .Lpoly1305_blocks
+
+ stmdb sp!,{r4-r7}
+ vstmdb sp!,{d8-d15} @ ABI specification says so
+
+ tst ip,ip @ is_base2_26?
+ bne .Lbase2_26_neon
+
+ stmdb sp!,{r1-r3,lr}
+ bl .Lpoly1305_init_neon
+
+ ldr r4,[$ctx,#0] @ load hash value base 2^32
+ ldr r5,[$ctx,#4]
+ ldr r6,[$ctx,#8]
+ ldr r7,[$ctx,#12]
+ ldr ip,[$ctx,#16]
+
+ and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
+ mov r3,r4,lsr#26
+ veor $D0#lo,$D0#lo,$D0#lo
+ mov r4,r5,lsr#20
+ orr r3,r3,r5,lsl#6
+ veor $D1#lo,$D1#lo,$D1#lo
+ mov r5,r6,lsr#14
+ orr r4,r4,r6,lsl#12
+ veor $D2#lo,$D2#lo,$D2#lo
+ mov r6,r7,lsr#8
+ orr r5,r5,r7,lsl#18
+ veor $D3#lo,$D3#lo,$D3#lo
+ and r3,r3,#0x03ffffff
+ orr r6,r6,ip,lsl#24
+ veor $D4#lo,$D4#lo,$D4#lo
+ and r4,r4,#0x03ffffff
+ mov r1,#1
+ and r5,r5,#0x03ffffff
+ str r1,[$ctx,#36] @ set is_base2_26
+
+ vmov.32 $D0#lo[0],r2
+ vmov.32 $D1#lo[0],r3
+ vmov.32 $D2#lo[0],r4
+ vmov.32 $D3#lo[0],r5
+ vmov.32 $D4#lo[0],r6
+ adr $zeros,.Lzeros
+
+ ldmia sp!,{r1-r3,lr}
+ b .Lhash_loaded
+
+.align 4
+.Lbase2_26_neon:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ load hash value
+
+ veor $D0#lo,$D0#lo,$D0#lo
+ veor $D1#lo,$D1#lo,$D1#lo
+ veor $D2#lo,$D2#lo,$D2#lo
+ veor $D3#lo,$D3#lo,$D3#lo
+ veor $D4#lo,$D4#lo,$D4#lo
+ vld4.32 {$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+ adr $zeros,.Lzeros
+ vld1.32 {$D4#lo[0]},[$ctx]
+ sub $ctx,$ctx,#16 @ rewind
+
+.Lhash_loaded:
+ add $in2,$inp,#32
+ mov $padbit,$padbit,lsl#24
+ tst $len,#31
+ beq .Leven
+
+ vld4.32 {$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
+ vmov.32 $H4#lo[0],$padbit
+ sub $len,$len,#16
+ add $in2,$inp,#32
+
+# ifdef __ARMEB__
+ vrev32.8 $H0,$H0
+ vrev32.8 $H3,$H3
+ vrev32.8 $H1,$H1
+ vrev32.8 $H2,$H2
+# endif
+ vsri.u32 $H4#lo,$H3#lo,#8 @ base 2^32 -> base 2^26
+ vshl.u32 $H3#lo,$H3#lo,#18
+
+ vsri.u32 $H3#lo,$H2#lo,#14
+ vshl.u32 $H2#lo,$H2#lo,#12
+ vadd.i32 $H4#hi,$H4#lo,$D4#lo @ add hash value and move to #hi
+
+ vbic.i32 $H3#lo,#0xfc000000
+ vsri.u32 $H2#lo,$H1#lo,#20
+ vshl.u32 $H1#lo,$H1#lo,#6
+
+ vbic.i32 $H2#lo,#0xfc000000
+ vsri.u32 $H1#lo,$H0#lo,#26
+ vadd.i32 $H3#hi,$H3#lo,$D3#lo
+
+ vbic.i32 $H0#lo,#0xfc000000
+ vbic.i32 $H1#lo,#0xfc000000
+ vadd.i32 $H2#hi,$H2#lo,$D2#lo
+
+ vadd.i32 $H0#hi,$H0#lo,$D0#lo
+ vadd.i32 $H1#hi,$H1#lo,$D1#lo
+
+ mov $tbl1,$zeros
+ add $tbl0,$ctx,#48
+
+ cmp $len,$len
+ b .Long_tail
+
+.align 4
+.Leven:
+ subs $len,$len,#64
+ it lo
+ movlo $in2,$zeros
+
+ vmov.i32 $H4,#1<<24 @ padbit, yes, always
+ vld4.32 {$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp] @ inp[0:1]
+ add $inp,$inp,#64
+ vld4.32 {$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2] @ inp[2:3] (or 0)
+ add $in2,$in2,#64
+ itt hi
+ addhi $tbl1,$ctx,#(48+1*9*4)
+ addhi $tbl0,$ctx,#(48+3*9*4)
+
+# ifdef __ARMEB__
+ vrev32.8 $H0,$H0
+ vrev32.8 $H3,$H3
+ vrev32.8 $H1,$H1
+ vrev32.8 $H2,$H2
+# endif
+ vsri.u32 $H4,$H3,#8 @ base 2^32 -> base 2^26
+ vshl.u32 $H3,$H3,#18
+
+ vsri.u32 $H3,$H2,#14
+ vshl.u32 $H2,$H2,#12
+
+ vbic.i32 $H3,#0xfc000000
+ vsri.u32 $H2,$H1,#20
+ vshl.u32 $H1,$H1,#6
+
+ vbic.i32 $H2,#0xfc000000
+ vsri.u32 $H1,$H0,#26
+
+ vbic.i32 $H0,#0xfc000000
+ vbic.i32 $H1,#0xfc000000
+
+ bls .Lskip_loop
+
+ vld4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]! @ load r^2
+ vld4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]! @ load r^4
+ vld4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vld4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ b .Loop_neon
+
+.align 5
+.Loop_neon:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+ @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+ @ \___________________/
+ @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+ @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+ @ \___________________/ \____________________/
+ @
+ @ Note that we start with inp[2:3]*r^2. This is because it
+ @ doesn't depend on reduction in previous iteration.
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
+ @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
+ @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
+ @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
+ @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ inp[2:3]*r^2
+
+ vadd.i32 $H2#lo,$H2#lo,$D2#lo @ accumulate inp[0:1]
+ vmull.u32 $D2,$H2#hi,${R0}[1]
+ vadd.i32 $H0#lo,$H0#lo,$D0#lo
+ vmull.u32 $D0,$H0#hi,${R0}[1]
+ vadd.i32 $H3#lo,$H3#lo,$D3#lo
+ vmull.u32 $D3,$H3#hi,${R0}[1]
+ vmlal.u32 $D2,$H1#hi,${R1}[1]
+ vadd.i32 $H1#lo,$H1#lo,$D1#lo
+ vmull.u32 $D1,$H1#hi,${R0}[1]
+
+ vadd.i32 $H4#lo,$H4#lo,$D4#lo
+ vmull.u32 $D4,$H4#hi,${R0}[1]
+ subs $len,$len,#64
+ vmlal.u32 $D0,$H4#hi,${S1}[1]
+ it lo
+ movlo $in2,$zeros
+ vmlal.u32 $D3,$H2#hi,${R1}[1]
+ vld1.32 ${S4}[1],[$tbl1,:32]
+ vmlal.u32 $D1,$H0#hi,${R1}[1]
+ vmlal.u32 $D4,$H3#hi,${R1}[1]
+
+ vmlal.u32 $D0,$H3#hi,${S2}[1]
+ vmlal.u32 $D3,$H1#hi,${R2}[1]
+ vmlal.u32 $D4,$H2#hi,${R2}[1]
+ vmlal.u32 $D1,$H4#hi,${S2}[1]
+ vmlal.u32 $D2,$H0#hi,${R2}[1]
+
+ vmlal.u32 $D3,$H0#hi,${R3}[1]
+ vmlal.u32 $D0,$H2#hi,${S3}[1]
+ vmlal.u32 $D4,$H1#hi,${R3}[1]
+ vmlal.u32 $D1,$H3#hi,${S3}[1]
+ vmlal.u32 $D2,$H4#hi,${S3}[1]
+
+ vmlal.u32 $D3,$H4#hi,${S4}[1]
+ vmlal.u32 $D0,$H1#hi,${S4}[1]
+ vmlal.u32 $D4,$H0#hi,${R4}[1]
+ vmlal.u32 $D1,$H2#hi,${S4}[1]
+ vmlal.u32 $D2,$H3#hi,${S4}[1]
+
+ vld4.32 {$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2] @ inp[2:3] (or 0)
+ add $in2,$in2,#64
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ (hash+inp[0:1])*r^4 and accumulate
+
+ vmlal.u32 $D3,$H3#lo,${R0}[0]
+ vmlal.u32 $D0,$H0#lo,${R0}[0]
+ vmlal.u32 $D4,$H4#lo,${R0}[0]
+ vmlal.u32 $D1,$H1#lo,${R0}[0]
+ vmlal.u32 $D2,$H2#lo,${R0}[0]
+ vld1.32 ${S4}[0],[$tbl0,:32]
+
+ vmlal.u32 $D3,$H2#lo,${R1}[0]
+ vmlal.u32 $D0,$H4#lo,${S1}[0]
+ vmlal.u32 $D4,$H3#lo,${R1}[0]
+ vmlal.u32 $D1,$H0#lo,${R1}[0]
+ vmlal.u32 $D2,$H1#lo,${R1}[0]
+
+ vmlal.u32 $D3,$H1#lo,${R2}[0]
+ vmlal.u32 $D0,$H3#lo,${S2}[0]
+ vmlal.u32 $D4,$H2#lo,${R2}[0]
+ vmlal.u32 $D1,$H4#lo,${S2}[0]
+ vmlal.u32 $D2,$H0#lo,${R2}[0]
+
+ vmlal.u32 $D3,$H0#lo,${R3}[0]
+ vmlal.u32 $D0,$H2#lo,${S3}[0]
+ vmlal.u32 $D4,$H1#lo,${R3}[0]
+ vmlal.u32 $D1,$H3#lo,${S3}[0]
+ vmlal.u32 $D3,$H4#lo,${S4}[0]
+
+ vmlal.u32 $D2,$H4#lo,${S3}[0]
+ vmlal.u32 $D0,$H1#lo,${S4}[0]
+ vmlal.u32 $D4,$H0#lo,${R4}[0]
+ vmov.i32 $H4,#1<<24 @ padbit, yes, always
+ vmlal.u32 $D1,$H2#lo,${S4}[0]
+ vmlal.u32 $D2,$H3#lo,${S4}[0]
+
+ vld4.32 {$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp] @ inp[0:1]
+ add $inp,$inp,#64
+# ifdef __ARMEB__
+ vrev32.8 $H0,$H0
+ vrev32.8 $H1,$H1
+ vrev32.8 $H2,$H2
+ vrev32.8 $H3,$H3
+# endif
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ lazy reduction interleaved with base 2^32 -> base 2^26 of
+ @ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.
+
+ vshr.u64 $T0,$D3,#26
+ vmovn.i64 $D3#lo,$D3
+ vshr.u64 $T1,$D0,#26
+ vmovn.i64 $D0#lo,$D0
+ vadd.i64 $D4,$D4,$T0 @ h3 -> h4
+ vbic.i32 $D3#lo,#0xfc000000
+ vsri.u32 $H4,$H3,#8 @ base 2^32 -> base 2^26
+ vadd.i64 $D1,$D1,$T1 @ h0 -> h1
+ vshl.u32 $H3,$H3,#18
+ vbic.i32 $D0#lo,#0xfc000000
+
+ vshrn.u64 $T0#lo,$D4,#26
+ vmovn.i64 $D4#lo,$D4
+ vshr.u64 $T1,$D1,#26
+ vmovn.i64 $D1#lo,$D1
+ vadd.i64 $D2,$D2,$T1 @ h1 -> h2
+ vsri.u32 $H3,$H2,#14
+ vbic.i32 $D4#lo,#0xfc000000
+ vshl.u32 $H2,$H2,#12
+ vbic.i32 $D1#lo,#0xfc000000
+
+ vadd.i32 $D0#lo,$D0#lo,$T0#lo
+ vshl.u32 $T0#lo,$T0#lo,#2
+ vbic.i32 $H3,#0xfc000000
+ vshrn.u64 $T1#lo,$D2,#26
+ vmovn.i64 $D2#lo,$D2
+ vaddl.u32 $D0,$D0#lo,$T0#lo @ h4 -> h0 [widen for a sec]
+ vsri.u32 $H2,$H1,#20
+ vadd.i32 $D3#lo,$D3#lo,$T1#lo @ h2 -> h3
+ vshl.u32 $H1,$H1,#6
+ vbic.i32 $D2#lo,#0xfc000000
+ vbic.i32 $H2,#0xfc000000
+
+ vshrn.u64 $T0#lo,$D0,#26 @ re-narrow
+ vmovn.i64 $D0#lo,$D0
+ vsri.u32 $H1,$H0,#26
+ vbic.i32 $H0,#0xfc000000
+ vshr.u32 $T1#lo,$D3#lo,#26
+ vbic.i32 $D3#lo,#0xfc000000
+ vbic.i32 $D0#lo,#0xfc000000
+ vadd.i32 $D1#lo,$D1#lo,$T0#lo @ h0 -> h1
+ vadd.i32 $D4#lo,$D4#lo,$T1#lo @ h3 -> h4
+ vbic.i32 $H1,#0xfc000000
+
+ bhi .Loop_neon
+
+.Lskip_loop:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+ add $tbl1,$ctx,#(48+0*9*4)
+ add $tbl0,$ctx,#(48+1*9*4)
+ adds $len,$len,#32
+ it ne
+ movne $len,#0
+ bne .Long_tail
+
+ vadd.i32 $H2#hi,$H2#lo,$D2#lo @ add hash value and move to #hi
+ vadd.i32 $H0#hi,$H0#lo,$D0#lo
+ vadd.i32 $H3#hi,$H3#lo,$D3#lo
+ vadd.i32 $H1#hi,$H1#lo,$D1#lo
+ vadd.i32 $H4#hi,$H4#lo,$D4#lo
+
+.Long_tail:
+ vld4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]! @ load r^1
+ vld4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]! @ load r^2
+
+ vadd.i32 $H2#lo,$H2#lo,$D2#lo @ can be redundant
+ vmull.u32 $D2,$H2#hi,$R0
+ vadd.i32 $H0#lo,$H0#lo,$D0#lo
+ vmull.u32 $D0,$H0#hi,$R0
+ vadd.i32 $H3#lo,$H3#lo,$D3#lo
+ vmull.u32 $D3,$H3#hi,$R0
+ vadd.i32 $H1#lo,$H1#lo,$D1#lo
+ vmull.u32 $D1,$H1#hi,$R0
+ vadd.i32 $H4#lo,$H4#lo,$D4#lo
+ vmull.u32 $D4,$H4#hi,$R0
+
+ vmlal.u32 $D0,$H4#hi,$S1
+ vld4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vmlal.u32 $D3,$H2#hi,$R1
+ vld4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vmlal.u32 $D1,$H0#hi,$R1
+ vmlal.u32 $D4,$H3#hi,$R1
+ vmlal.u32 $D2,$H1#hi,$R1
+
+ vmlal.u32 $D3,$H1#hi,$R2
+ vld1.32 ${S4}[1],[$tbl1,:32]
+ vmlal.u32 $D0,$H3#hi,$S2
+ vld1.32 ${S4}[0],[$tbl0,:32]
+ vmlal.u32 $D4,$H2#hi,$R2
+ vmlal.u32 $D1,$H4#hi,$S2
+ vmlal.u32 $D2,$H0#hi,$R2
+
+ vmlal.u32 $D3,$H0#hi,$R3
+ it ne
+ addne $tbl1,$ctx,#(48+2*9*4)
+ vmlal.u32 $D0,$H2#hi,$S3
+ it ne
+ addne $tbl0,$ctx,#(48+3*9*4)
+ vmlal.u32 $D4,$H1#hi,$R3
+ vmlal.u32 $D1,$H3#hi,$S3
+ vmlal.u32 $D2,$H4#hi,$S3
+
+ vmlal.u32 $D3,$H4#hi,$S4
+ vorn $MASK,$MASK,$MASK @ all-ones, can be redundant
+ vmlal.u32 $D0,$H1#hi,$S4
+ vshr.u64 $MASK,$MASK,#38
+ vmlal.u32 $D4,$H0#hi,$R4
+ vmlal.u32 $D1,$H2#hi,$S4
+ vmlal.u32 $D2,$H3#hi,$S4
+
+ beq .Lshort_tail
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+ vld4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]! @ load r^3
+ vld4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]! @ load r^4
+
+ vmlal.u32 $D2,$H2#lo,$R0
+ vmlal.u32 $D0,$H0#lo,$R0
+ vmlal.u32 $D3,$H3#lo,$R0
+ vmlal.u32 $D1,$H1#lo,$R0
+ vmlal.u32 $D4,$H4#lo,$R0
+
+ vmlal.u32 $D0,$H4#lo,$S1
+ vld4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vmlal.u32 $D3,$H2#lo,$R1
+ vld4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vmlal.u32 $D1,$H0#lo,$R1
+ vmlal.u32 $D4,$H3#lo,$R1
+ vmlal.u32 $D2,$H1#lo,$R1
+
+ vmlal.u32 $D3,$H1#lo,$R2
+ vld1.32 ${S4}[1],[$tbl1,:32]
+ vmlal.u32 $D0,$H3#lo,$S2
+ vld1.32 ${S4}[0],[$tbl0,:32]
+ vmlal.u32 $D4,$H2#lo,$R2
+ vmlal.u32 $D1,$H4#lo,$S2
+ vmlal.u32 $D2,$H0#lo,$R2
+
+ vmlal.u32 $D3,$H0#lo,$R3
+ vmlal.u32 $D0,$H2#lo,$S3
+ vmlal.u32 $D4,$H1#lo,$R3
+ vmlal.u32 $D1,$H3#lo,$S3
+ vmlal.u32 $D2,$H4#lo,$S3
+
+ vmlal.u32 $D3,$H4#lo,$S4
+ vorn $MASK,$MASK,$MASK @ all-ones
+ vmlal.u32 $D0,$H1#lo,$S4
+ vshr.u64 $MASK,$MASK,#38
+ vmlal.u32 $D4,$H0#lo,$R4
+ vmlal.u32 $D1,$H2#lo,$S4
+ vmlal.u32 $D2,$H3#lo,$S4
+
+.Lshort_tail:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ horizontal addition
+
+ vadd.i64 $D3#lo,$D3#lo,$D3#hi
+ vadd.i64 $D0#lo,$D0#lo,$D0#hi
+ vadd.i64 $D4#lo,$D4#lo,$D4#hi
+ vadd.i64 $D1#lo,$D1#lo,$D1#hi
+ vadd.i64 $D2#lo,$D2#lo,$D2#hi
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ lazy reduction, but without narrowing
+
+ vshr.u64 $T0,$D3,#26
+ vand.i64 $D3,$D3,$MASK
+ vshr.u64 $T1,$D0,#26
+ vand.i64 $D0,$D0,$MASK
+ vadd.i64 $D4,$D4,$T0 @ h3 -> h4
+ vadd.i64 $D1,$D1,$T1 @ h0 -> h1
+
+ vshr.u64 $T0,$D4,#26
+ vand.i64 $D4,$D4,$MASK
+ vshr.u64 $T1,$D1,#26
+ vand.i64 $D1,$D1,$MASK
+ vadd.i64 $D2,$D2,$T1 @ h1 -> h2
+
+ vadd.i64 $D0,$D0,$T0
+ vshl.u64 $T0,$T0,#2
+ vshr.u64 $T1,$D2,#26
+ vand.i64 $D2,$D2,$MASK
+ vadd.i64 $D0,$D0,$T0 @ h4 -> h0
+ vadd.i64 $D3,$D3,$T1 @ h2 -> h3
+
+ vshr.u64 $T0,$D0,#26
+ vand.i64 $D0,$D0,$MASK
+ vshr.u64 $T1,$D3,#26
+ vand.i64 $D3,$D3,$MASK
+ vadd.i64 $D1,$D1,$T0 @ h0 -> h1
+ vadd.i64 $D4,$D4,$T1 @ h3 -> h4
+
+ cmp $len,#0
+ bne .Leven
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ store hash value
+
+ vst4.32 {$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+ vst1.32 {$D4#lo[0]},[$ctx]
+
+ vldmia sp!,{d8-d15} @ epilogue
+ ldmia sp!,{r4-r7}
+ ret @ bx lr
+.size poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align 5
+.Lzeros:
+.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+#ifndef __KERNEL__
+.LOPENSSL_armcap:
+# ifdef _WIN32
+.word OPENSSL_armcap_P
+# else
+.word OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+.comm OPENSSL_armcap_P,4,4
+.hidden OPENSSL_armcap_P
+#endif
+#endif
+___
+} }
+$code.=<<___;
+.asciz "Poly1305 for ARMv4/NEON, CRYPTOGAMS by \@dot-asm"
+.align 2
+___
+
+foreach (split("\n",$code)) {
+ s/\`([^\`]*)\`/eval $1/geo;
+
+ s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo or
+ s/\bret\b/bx lr/go or
+ s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4
+
+ print $_,"\n";
+}
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/poly1305-core.S_shipped b/arch/arm/crypto/poly1305-core.S_shipped
new file mode 100644
index 000000000000..37b71d990293
--- /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
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..067e746297e0
--- /dev/null
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void poly1305_init_arm(void *state, const u8 *key);
+asmlinkage void poly1305_blocks_arm(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_arm(void *state, __le32 *digest, const u32 *nonce);
+
+static bool have_neon __ro_after_init;
+
+void poly1305_init(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);
+
+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 (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 (do_neon)
+ kernel_neon_begin();
+ arm_poly1305_do_update(dctx, src, srclen, do_neon);
+ if (do_neon)
+ kernel_neon_end();
+ return 0;
+}
+
+void poly1305_update(struct poly1305_desc_ctx *dctx, const u8 *src,
+ unsigned int nbytes)
+{
+ bool do_neon = have_neon && crypto_simd_usable() && nbytes > 128;
+
+ 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 (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);
+
+void poly1305_final(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);
+}
+EXPORT_SYMBOL(poly1305_final);
+
+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(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)
+{
+ have_neon = IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+ (elf_hwcap & HWCAP_NEON);
+
+ if (!have_neon)
+ /* 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 (!have_neon) {
+ crypto_unregister_shash(&arm_poly1305_algs[0]);
+ return;
+ }
+ crypto_unregister_shashes(arm_poly1305_algs,
+ ARRAY_SIZE(arm_poly1305_algs));
+}
+
+module_init(arm_poly1305_mod_init);
+module_exit(arm_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-arm");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 5b3250034288..d74955ef2853 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -660,7 +660,7 @@ config CRYPTO_ARCH_HAVE_LIB_POLY1305
config CRYPTO_LIB_POLY1305_RSIZE
int
default 4 if X86_64
- default 9 if ARM64
+ default 9 if ARM || ARM64
default 1
config CRYPTO_LIB_POLY1305
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 09/20] int128: move __uint128_t compiler test to Kconfig
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (7 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 08/20] crypto: arm/poly1305 " Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-30 11:00 ` Masahiro Yamada
2019-09-29 17:38 ` [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation Ard Biesheuvel
` (7 subsequent siblings)
16 siblings, 1 reply; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Masahiro Yamada, Will Deacon, Dan Carpenter,
Andy Lutomirski, Marc Zyngier, Linus Torvalds, David Miller,
linux-arm-kernel
In order to use 128-bit integer arithmetic in C code, the architecture
needs to have declared support for it by setting ARCH_SUPPORTS_INT128,
and it requires a version of the toolchain that supports this at build
time. This is why all existing tests for ARCH_SUPPORTS_INT128 also test
whether __SIZEOF_INT128__ is defined, since this is only the case for
compilers that can support 128-bit integers.
Let's fold this additional test into the Kconfig declaration of
ARCH_SUPPORTS_INT128 so that we can also use the symbol in Makefiles,
e.g., to decide whether a certain object needs to be included in the
first place.
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm64/Kconfig | 2 +-
arch/riscv/Kconfig | 2 +-
arch/x86/Kconfig | 2 +-
crypto/ecc.c | 2 +-
init/Kconfig | 4 ++++
lib/ubsan.c | 2 +-
lib/ubsan.h | 2 +-
7 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3adcec05b1f6..a0f764e2f299 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -69,7 +69,7 @@ config ARM64
select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_SUPPORTS_MEMORY_FAILURE
select ARCH_SUPPORTS_ATOMIC_RMW
- select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
+ select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 59a4727ecd6c..99be78ac7b33 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -127,7 +127,7 @@ config ARCH_RV32I
config ARCH_RV64I
bool "RV64I"
select 64BIT
- select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000
+ select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 222855cc0158..97f74a2e1cf3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,7 +24,7 @@ config X86_64
depends on 64BIT
# Options that are inherently 64-bit kernel only:
select ARCH_HAS_GIGANTIC_PAGE
- select ARCH_SUPPORTS_INT128
+ select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
select MODULES_USE_ELF_RELA
diff --git a/crypto/ecc.c b/crypto/ecc.c
index dfe114bc0c4a..6e6aab6c987c 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -336,7 +336,7 @@ static u64 vli_usub(u64 *result, const u64 *left, u64 right,
static uint128_t mul_64_64(u64 left, u64 right)
{
uint128_t result;
-#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
unsigned __int128 m = (unsigned __int128)left * right;
result.m_low = m;
diff --git a/init/Kconfig b/init/Kconfig
index bd7d650d4a99..f5566a985b9e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -780,6 +780,10 @@ config ARCH_SUPPORTS_NUMA_BALANCING
config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
bool
+config CC_HAS_INT128
+ def_bool y
+ depends on !$(cc-option,-D__SIZEOF_INT128__=0)
+
#
# For architectures that know their GCC __int128 support is sound
#
diff --git a/lib/ubsan.c b/lib/ubsan.c
index e7d31735950d..b652cc14dd60 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -119,7 +119,7 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type,
{
if (type_is_int(type)) {
if (type_bit_width(type) == 128) {
-#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
u_max val = get_unsigned_val(type, value);
scnprintf(str, size, "0x%08x%08x%08x%08x",
diff --git a/lib/ubsan.h b/lib/ubsan.h
index b8fa83864467..7b56c09473a9 100644
--- a/lib/ubsan.h
+++ b/lib/ubsan.h
@@ -78,7 +78,7 @@ struct invalid_value_data {
struct type_descriptor *type;
};
-#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#if defined(CONFIG_ARCH_SUPPORTS_INT128)
typedef __int128 s_max;
typedef unsigned __int128 u_max;
#else
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* Re: [RFC PATCH 09/20] int128: move __uint128_t compiler test to Kconfig
2019-09-29 17:38 ` [RFC PATCH 09/20] int128: move __uint128_t compiler test to Kconfig Ard Biesheuvel
@ 2019-09-30 11:00 ` Masahiro Yamada
2019-09-30 11:49 ` Ard Biesheuvel
0 siblings, 1 reply; 23+ messages in thread
From: Masahiro Yamada @ 2019-09-30 11:00 UTC (permalink / raw)
To: Ard Biesheuvel
Cc: linux-arm-kernel, Marc Zyngier, Jason A . Donenfeld, Herbert Xu,
Arnd Bergmann, Eric Biggers, Martin Willi, Catalin Marinas,
Samuel Neves, Linus Torvalds, linux-crypto, Andy Lutomirski,
Greg KH, Will Deacon, David Miller, Dan Carpenter
On Mon, Sep 30, 2019 at 2:41 AM Ard Biesheuvel
<ard.biesheuvel@linaro.org> wrote:
>
> In order to use 128-bit integer arithmetic in C code, the architecture
> needs to have declared support for it by setting ARCH_SUPPORTS_INT128,
> and it requires a version of the toolchain that supports this at build
> time. This is why all existing tests for ARCH_SUPPORTS_INT128 also test
> whether __SIZEOF_INT128__ is defined, since this is only the case for
> compilers that can support 128-bit integers.
>
> Let's fold this additional test into the Kconfig declaration of
> ARCH_SUPPORTS_INT128 so that we can also use the symbol in Makefiles,
> e.g., to decide whether a certain object needs to be included in the
> first place.
>
> Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Do you still need CONFIG_ARCH_SUPPORTS_INT128 ?
I do not know which part in lib/ubsan.c or crypto/ecc.c
is arch-dependent...
> ---
> arch/arm64/Kconfig | 2 +-
> arch/riscv/Kconfig | 2 +-
> arch/x86/Kconfig | 2 +-
> crypto/ecc.c | 2 +-
> init/Kconfig | 4 ++++
> lib/ubsan.c | 2 +-
> lib/ubsan.h | 2 +-
> 7 files changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 3adcec05b1f6..a0f764e2f299 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -69,7 +69,7 @@ config ARM64
> select ARCH_USE_QUEUED_SPINLOCKS
> select ARCH_SUPPORTS_MEMORY_FAILURE
> select ARCH_SUPPORTS_ATOMIC_RMW
> - select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
> + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
> select ARCH_SUPPORTS_NUMA_BALANCING
> select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
> select ARCH_WANT_FRAME_POINTERS
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index 59a4727ecd6c..99be78ac7b33 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -127,7 +127,7 @@ config ARCH_RV32I
> config ARCH_RV64I
> bool "RV64I"
> select 64BIT
> - select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000
> + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
> select HAVE_FUNCTION_TRACER
> select HAVE_FUNCTION_GRAPH_TRACER
> select HAVE_FTRACE_MCOUNT_RECORD
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 222855cc0158..97f74a2e1cf3 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -24,7 +24,7 @@ config X86_64
> depends on 64BIT
> # Options that are inherently 64-bit kernel only:
> select ARCH_HAS_GIGANTIC_PAGE
> - select ARCH_SUPPORTS_INT128
> + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
> select ARCH_USE_CMPXCHG_LOCKREF
> select HAVE_ARCH_SOFT_DIRTY
> select MODULES_USE_ELF_RELA
> diff --git a/crypto/ecc.c b/crypto/ecc.c
> index dfe114bc0c4a..6e6aab6c987c 100644
> --- a/crypto/ecc.c
> +++ b/crypto/ecc.c
> @@ -336,7 +336,7 @@ static u64 vli_usub(u64 *result, const u64 *left, u64 right,
> static uint128_t mul_64_64(u64 left, u64 right)
> {
> uint128_t result;
> -#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> +#if defined(CONFIG_ARCH_SUPPORTS_INT128)
> unsigned __int128 m = (unsigned __int128)left * right;
>
> result.m_low = m;
> diff --git a/init/Kconfig b/init/Kconfig
> index bd7d650d4a99..f5566a985b9e 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -780,6 +780,10 @@ config ARCH_SUPPORTS_NUMA_BALANCING
> config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
> bool
>
> +config CC_HAS_INT128
> + def_bool y
> + depends on !$(cc-option,-D__SIZEOF_INT128__=0)
> +
> #
> # For architectures that know their GCC __int128 support is sound
> #
> diff --git a/lib/ubsan.c b/lib/ubsan.c
> index e7d31735950d..b652cc14dd60 100644
> --- a/lib/ubsan.c
> +++ b/lib/ubsan.c
> @@ -119,7 +119,7 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type,
> {
> if (type_is_int(type)) {
> if (type_bit_width(type) == 128) {
> -#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> +#if defined(CONFIG_ARCH_SUPPORTS_INT128)
> u_max val = get_unsigned_val(type, value);
>
> scnprintf(str, size, "0x%08x%08x%08x%08x",
> diff --git a/lib/ubsan.h b/lib/ubsan.h
> index b8fa83864467..7b56c09473a9 100644
> --- a/lib/ubsan.h
> +++ b/lib/ubsan.h
> @@ -78,7 +78,7 @@ struct invalid_value_data {
> struct type_descriptor *type;
> };
>
> -#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> +#if defined(CONFIG_ARCH_SUPPORTS_INT128)
> typedef __int128 s_max;
> typedef unsigned __int128 u_max;
> #else
> --
> 2.17.1
>
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
--
Best Regards
Masahiro Yamada
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [RFC PATCH 09/20] int128: move __uint128_t compiler test to Kconfig
2019-09-30 11:00 ` Masahiro Yamada
@ 2019-09-30 11:49 ` Ard Biesheuvel
0 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-30 11:49 UTC (permalink / raw)
To: Masahiro Yamada
Cc: linux-arm-kernel, Marc Zyngier, Jason A . Donenfeld, Herbert Xu,
Arnd Bergmann, Eric Biggers, Martin Willi, Catalin Marinas,
Samuel Neves, Linus Torvalds,
open list:HARDWARE RANDOM NUMBER GENERATOR CORE, Andy Lutomirski,
Greg KH, Will Deacon, David Miller, Dan Carpenter
On Mon, 30 Sep 2019 at 13:01, Masahiro Yamada
<yamada.masahiro@socionext.com> wrote:
>
> On Mon, Sep 30, 2019 at 2:41 AM Ard Biesheuvel
> <ard.biesheuvel@linaro.org> wrote:
> >
> > In order to use 128-bit integer arithmetic in C code, the architecture
> > needs to have declared support for it by setting ARCH_SUPPORTS_INT128,
> > and it requires a version of the toolchain that supports this at build
> > time. This is why all existing tests for ARCH_SUPPORTS_INT128 also test
> > whether __SIZEOF_INT128__ is defined, since this is only the case for
> > compilers that can support 128-bit integers.
> >
> > Let's fold this additional test into the Kconfig declaration of
> > ARCH_SUPPORTS_INT128 so that we can also use the symbol in Makefiles,
> > e.g., to decide whether a certain object needs to be included in the
> > first place.
> >
> > Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
> > Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
>
>
> Do you still need CONFIG_ARCH_SUPPORTS_INT128 ?
>
arm64 needs GCC 5 or later for int128_t support, since older versions
emit support library function calls that we don't implement.
I guess we could fold that into the CC_HAS_INT128 test as well though
> I do not know which part in lib/ubsan.c or crypto/ecc.c
> is arch-dependent...
>
>
>
>
>
> > ---
> > arch/arm64/Kconfig | 2 +-
> > arch/riscv/Kconfig | 2 +-
> > arch/x86/Kconfig | 2 +-
> > crypto/ecc.c | 2 +-
> > init/Kconfig | 4 ++++
> > lib/ubsan.c | 2 +-
> > lib/ubsan.h | 2 +-
> > 7 files changed, 10 insertions(+), 6 deletions(-)
> >
> > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> > index 3adcec05b1f6..a0f764e2f299 100644
> > --- a/arch/arm64/Kconfig
> > +++ b/arch/arm64/Kconfig
> > @@ -69,7 +69,7 @@ config ARM64
> > select ARCH_USE_QUEUED_SPINLOCKS
> > select ARCH_SUPPORTS_MEMORY_FAILURE
> > select ARCH_SUPPORTS_ATOMIC_RMW
> > - select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
> > + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
> > select ARCH_SUPPORTS_NUMA_BALANCING
> > select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
> > select ARCH_WANT_FRAME_POINTERS
> > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > index 59a4727ecd6c..99be78ac7b33 100644
> > --- a/arch/riscv/Kconfig
> > +++ b/arch/riscv/Kconfig
> > @@ -127,7 +127,7 @@ config ARCH_RV32I
> > config ARCH_RV64I
> > bool "RV64I"
> > select 64BIT
> > - select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000
> > + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
> > select HAVE_FUNCTION_TRACER
> > select HAVE_FUNCTION_GRAPH_TRACER
> > select HAVE_FTRACE_MCOUNT_RECORD
> > diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> > index 222855cc0158..97f74a2e1cf3 100644
> > --- a/arch/x86/Kconfig
> > +++ b/arch/x86/Kconfig
> > @@ -24,7 +24,7 @@ config X86_64
> > depends on 64BIT
> > # Options that are inherently 64-bit kernel only:
> > select ARCH_HAS_GIGANTIC_PAGE
> > - select ARCH_SUPPORTS_INT128
> > + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
> > select ARCH_USE_CMPXCHG_LOCKREF
> > select HAVE_ARCH_SOFT_DIRTY
> > select MODULES_USE_ELF_RELA
> > diff --git a/crypto/ecc.c b/crypto/ecc.c
> > index dfe114bc0c4a..6e6aab6c987c 100644
> > --- a/crypto/ecc.c
> > +++ b/crypto/ecc.c
> > @@ -336,7 +336,7 @@ static u64 vli_usub(u64 *result, const u64 *left, u64 right,
> > static uint128_t mul_64_64(u64 left, u64 right)
> > {
> > uint128_t result;
> > -#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> > +#if defined(CONFIG_ARCH_SUPPORTS_INT128)
> > unsigned __int128 m = (unsigned __int128)left * right;
> >
> > result.m_low = m;
> > diff --git a/init/Kconfig b/init/Kconfig
> > index bd7d650d4a99..f5566a985b9e 100644
> > --- a/init/Kconfig
> > +++ b/init/Kconfig
> > @@ -780,6 +780,10 @@ config ARCH_SUPPORTS_NUMA_BALANCING
> > config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
> > bool
> >
> > +config CC_HAS_INT128
> > + def_bool y
> > + depends on !$(cc-option,-D__SIZEOF_INT128__=0)
> > +
> > #
> > # For architectures that know their GCC __int128 support is sound
> > #
> > diff --git a/lib/ubsan.c b/lib/ubsan.c
> > index e7d31735950d..b652cc14dd60 100644
> > --- a/lib/ubsan.c
> > +++ b/lib/ubsan.c
> > @@ -119,7 +119,7 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type,
> > {
> > if (type_is_int(type)) {
> > if (type_bit_width(type) == 128) {
> > -#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> > +#if defined(CONFIG_ARCH_SUPPORTS_INT128)
> > u_max val = get_unsigned_val(type, value);
> >
> > scnprintf(str, size, "0x%08x%08x%08x%08x",
> > diff --git a/lib/ubsan.h b/lib/ubsan.h
> > index b8fa83864467..7b56c09473a9 100644
> > --- a/lib/ubsan.h
> > +++ b/lib/ubsan.h
> > @@ -78,7 +78,7 @@ struct invalid_value_data {
> > struct type_descriptor *type;
> > };
> >
> > -#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> > +#if defined(CONFIG_ARCH_SUPPORTS_INT128)
> > typedef __int128 s_max;
> > typedef unsigned __int128 u_max;
> > #else
> > --
> > 2.17.1
> >
> >
> > _______________________________________________
> > linux-arm-kernel mailing list
> > linux-arm-kernel@lists.infradead.org
> > http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
>
>
>
> --
> Best Regards
> Masahiro Yamada
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 23+ messages in thread
* [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (8 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 09/20] int128: move __uint128_t compiler test to Kconfig Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-30 2:42 ` Jason A. Donenfeld
2019-09-29 17:38 ` [RFC PATCH 13/20] crypto: Curve25519 - x86_64 library implementation Ard Biesheuvel
` (6 subsequent siblings)
16 siblings, 1 reply; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
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 <Jason@zx2c4.com>
Signed-off-by: Samuel Neves <sneves@dei.uc.pt>
Co-developed-by: Samuel Neves <sneves@dei.uc.pt>
[ardb: move to arch/x86/crypto, wire into lib/crypto framework]
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/x86/crypto/Makefile | 2 +
arch/x86/crypto/blake2s-core.S | 685 ++++++++++++++++++++
arch/x86/crypto/blake2s-glue.c | 73 +++
crypto/Kconfig | 6 +
4 files changed, 766 insertions(+)
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 759b1a927826..db87c182ce0f 100644
--- 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-$(CONFIG_CRYPTO_LIB_BLAKE2S_X86) += blake2s-x86_64.o
endif
# These modules require assembler to support AVX2.
@@ -70,6 +71,7 @@ serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
+blake2s-x86_64-y := blake2s-core.o blake2s-glue.o
ifeq ($(avx_supported),yes)
camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
new file mode 100644
index 000000000000..675288fa4cca
--- /dev/null
+++ b/arch/x86/crypto/blake2s-core.S
@@ -0,0 +1,685 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2017 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+
+.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
+#ifdef CONFIG_AS_AVX512
+.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 640
+.align 64
+SIGMA:
+.long 0, 2, 4, 6, 1, 3, 5, 7, 8, 10, 12, 14, 9, 11, 13, 15
+.long 11, 2, 12, 14, 9, 8, 15, 3, 4, 0, 13, 6, 10, 1, 7, 5
+.long 10, 12, 11, 6, 5, 9, 13, 3, 4, 15, 14, 2, 0, 7, 8, 1
+.long 10, 9, 7, 0, 11, 14, 1, 12, 6, 2, 15, 3, 13, 8, 5, 4
+.long 4, 9, 8, 13, 14, 0, 10, 11, 7, 3, 12, 1, 5, 6, 15, 2
+.long 2, 10, 4, 14, 13, 3, 9, 11, 6, 5, 7, 12, 15, 1, 8, 0
+.long 4, 11, 14, 8, 13, 10, 12, 5, 2, 1, 15, 3, 9, 7, 0, 6
+.long 6, 12, 0, 13, 15, 2, 1, 10, 4, 5, 11, 14, 8, 3, 9, 7
+.long 14, 5, 4, 12, 9, 7, 3, 10, 2, 0, 6, 15, 11, 1, 13, 8
+.long 11, 7, 13, 10, 12, 14, 0, 15, 4, 5, 6, 9, 2, 1, 8, 3
+#endif /* CONFIG_AS_AVX512 */
+
+.text
+#ifdef CONFIG_AS_AVX
+ENTRY(blake2s_compress_avx)
+ movl %ecx, %ecx
+ testq %rdx, %rdx
+ je .Lendofloop
+ .align 32
+.Lbeginofloop:
+ addq %rcx, 32(%rdi)
+ vmovdqu IV+16(%rip), %xmm1
+ vmovdqu (%rsi), %xmm4
+ vpxor 32(%rdi), %xmm1, %xmm1
+ vmovdqu 16(%rsi), %xmm3
+ vshufps $136, %xmm3, %xmm4, %xmm6
+ vmovdqa ROT16(%rip), %xmm7
+ vpaddd (%rdi), %xmm6, %xmm6
+ vpaddd 16(%rdi), %xmm6, %xmm6
+ vpxor %xmm6, %xmm1, %xmm1
+ vmovdqu IV(%rip), %xmm8
+ vpshufb %xmm7, %xmm1, %xmm1
+ vmovdqu 48(%rsi), %xmm5
+ vpaddd %xmm1, %xmm8, %xmm8
+ vpxor 16(%rdi), %xmm8, %xmm9
+ vmovdqu 32(%rsi), %xmm2
+ vpblendw $12, %xmm3, %xmm5, %xmm13
+ vshufps $221, %xmm5, %xmm2, %xmm12
+ vpunpckhqdq %xmm2, %xmm4, %xmm14
+ vpslld $20, %xmm9, %xmm0
+ vpsrld $12, %xmm9, %xmm9
+ vpxor %xmm0, %xmm9, %xmm0
+ vshufps $221, %xmm3, %xmm4, %xmm9
+ vpaddd %xmm9, %xmm6, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vmovdqa ROR328(%rip), %xmm6
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm8, %xmm8
+ vpxor %xmm8, %xmm0, %xmm0
+ vpshufd $147, %xmm1, %xmm1
+ vpshufd $78, %xmm8, %xmm8
+ vpslld $25, %xmm0, %xmm10
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm10, %xmm0, %xmm0
+ vshufps $136, %xmm5, %xmm2, %xmm10
+ vpshufd $57, %xmm0, %xmm0
+ vpaddd %xmm10, %xmm9, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpaddd %xmm12, %xmm9, %xmm9
+ vpblendw $12, %xmm2, %xmm3, %xmm12
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm8, %xmm8
+ vpxor %xmm8, %xmm0, %xmm10
+ vpslld $20, %xmm10, %xmm0
+ vpsrld $12, %xmm10, %xmm10
+ vpxor %xmm0, %xmm10, %xmm0
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm8, %xmm8
+ vpxor %xmm8, %xmm0, %xmm0
+ vpshufd $57, %xmm1, %xmm1
+ vpshufd $78, %xmm8, %xmm8
+ vpslld $25, %xmm0, %xmm10
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm10, %xmm0, %xmm0
+ vpslldq $4, %xmm5, %xmm10
+ vpblendw $240, %xmm10, %xmm12, %xmm12
+ vpshufd $147, %xmm0, %xmm0
+ vpshufd $147, %xmm12, %xmm12
+ vpaddd %xmm9, %xmm12, %xmm12
+ vpaddd %xmm0, %xmm12, %xmm12
+ vpxor %xmm12, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm8, %xmm8
+ vpxor %xmm8, %xmm0, %xmm11
+ vpslld $20, %xmm11, %xmm9
+ vpsrld $12, %xmm11, %xmm11
+ vpxor %xmm9, %xmm11, %xmm0
+ vpshufd $8, %xmm2, %xmm9
+ vpblendw $192, %xmm5, %xmm3, %xmm11
+ vpblendw $240, %xmm11, %xmm9, %xmm9
+ vpshufd $177, %xmm9, %xmm9
+ vpaddd %xmm12, %xmm9, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm11
+ vpxor %xmm11, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm8, %xmm8
+ vpxor %xmm8, %xmm0, %xmm9
+ vpshufd $147, %xmm1, %xmm1
+ vpshufd $78, %xmm8, %xmm8
+ vpslld $25, %xmm9, %xmm0
+ vpsrld $7, %xmm9, %xmm9
+ vpxor %xmm0, %xmm9, %xmm0
+ vpslldq $4, %xmm3, %xmm9
+ vpblendw $48, %xmm9, %xmm2, %xmm9
+ vpblendw $240, %xmm9, %xmm4, %xmm9
+ vpshufd $57, %xmm0, %xmm0
+ vpshufd $177, %xmm9, %xmm9
+ vpaddd %xmm11, %xmm9, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm8, %xmm11
+ vpxor %xmm11, %xmm0, %xmm0
+ vpslld $20, %xmm0, %xmm8
+ vpsrld $12, %xmm0, %xmm0
+ vpxor %xmm8, %xmm0, %xmm0
+ vpunpckhdq %xmm3, %xmm4, %xmm8
+ vpblendw $12, %xmm10, %xmm8, %xmm12
+ vpshufd $177, %xmm12, %xmm12
+ vpaddd %xmm9, %xmm12, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm11
+ vpxor %xmm11, %xmm0, %xmm0
+ vpshufd $57, %xmm1, %xmm1
+ vpshufd $78, %xmm11, %xmm11
+ vpslld $25, %xmm0, %xmm12
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm12, %xmm0, %xmm0
+ vpunpckhdq %xmm5, %xmm2, %xmm12
+ vpshufd $147, %xmm0, %xmm0
+ vpblendw $15, %xmm13, %xmm12, %xmm12
+ vpslldq $8, %xmm5, %xmm13
+ vpshufd $210, %xmm12, %xmm12
+ vpaddd %xmm9, %xmm12, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm11
+ vpxor %xmm11, %xmm0, %xmm0
+ vpslld $20, %xmm0, %xmm12
+ vpsrld $12, %xmm0, %xmm0
+ vpxor %xmm12, %xmm0, %xmm0
+ vpunpckldq %xmm4, %xmm2, %xmm12
+ vpblendw $240, %xmm4, %xmm12, %xmm12
+ vpblendw $192, %xmm13, %xmm12, %xmm12
+ vpsrldq $12, %xmm3, %xmm13
+ vpaddd %xmm12, %xmm9, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm11
+ vpxor %xmm11, %xmm0, %xmm0
+ vpshufd $147, %xmm1, %xmm1
+ vpshufd $78, %xmm11, %xmm11
+ vpslld $25, %xmm0, %xmm12
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm12, %xmm0, %xmm0
+ vpblendw $60, %xmm2, %xmm4, %xmm12
+ vpblendw $3, %xmm13, %xmm12, %xmm12
+ vpshufd $57, %xmm0, %xmm0
+ vpshufd $78, %xmm12, %xmm12
+ vpaddd %xmm9, %xmm12, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm11
+ vpxor %xmm11, %xmm0, %xmm12
+ vpslld $20, %xmm12, %xmm13
+ vpsrld $12, %xmm12, %xmm0
+ vpblendw $51, %xmm3, %xmm4, %xmm12
+ vpxor %xmm13, %xmm0, %xmm0
+ vpblendw $192, %xmm10, %xmm12, %xmm10
+ vpslldq $8, %xmm2, %xmm12
+ vpshufd $27, %xmm10, %xmm10
+ vpaddd %xmm9, %xmm10, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm11
+ vpxor %xmm11, %xmm0, %xmm0
+ vpshufd $57, %xmm1, %xmm1
+ vpshufd $78, %xmm11, %xmm11
+ vpslld $25, %xmm0, %xmm10
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm10, %xmm0, %xmm0
+ vpunpckhdq %xmm2, %xmm8, %xmm10
+ vpshufd $147, %xmm0, %xmm0
+ vpblendw $12, %xmm5, %xmm10, %xmm10
+ vpshufd $210, %xmm10, %xmm10
+ vpaddd %xmm9, %xmm10, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm11
+ vpxor %xmm11, %xmm0, %xmm10
+ vpslld $20, %xmm10, %xmm0
+ vpsrld $12, %xmm10, %xmm10
+ vpxor %xmm0, %xmm10, %xmm0
+ vpblendw $12, %xmm4, %xmm5, %xmm10
+ vpblendw $192, %xmm12, %xmm10, %xmm10
+ vpunpckldq %xmm2, %xmm4, %xmm12
+ vpshufd $135, %xmm10, %xmm10
+ vpaddd %xmm9, %xmm10, %xmm9
+ vpaddd %xmm0, %xmm9, %xmm9
+ vpxor %xmm9, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm11, %xmm13
+ vpxor %xmm13, %xmm0, %xmm0
+ vpshufd $147, %xmm1, %xmm1
+ vpshufd $78, %xmm13, %xmm13
+ vpslld $25, %xmm0, %xmm10
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm10, %xmm0, %xmm0
+ vpblendw $15, %xmm3, %xmm4, %xmm10
+ vpblendw $192, %xmm5, %xmm10, %xmm10
+ vpshufd $57, %xmm0, %xmm0
+ vpshufd $198, %xmm10, %xmm10
+ vpaddd %xmm9, %xmm10, %xmm10
+ vpaddd %xmm0, %xmm10, %xmm10
+ vpxor %xmm10, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm13, %xmm13
+ vpxor %xmm13, %xmm0, %xmm9
+ vpslld $20, %xmm9, %xmm0
+ vpsrld $12, %xmm9, %xmm9
+ vpxor %xmm0, %xmm9, %xmm0
+ vpunpckhdq %xmm2, %xmm3, %xmm9
+ vpunpcklqdq %xmm12, %xmm9, %xmm15
+ vpunpcklqdq %xmm12, %xmm8, %xmm12
+ vpblendw $15, %xmm5, %xmm8, %xmm8
+ vpaddd %xmm15, %xmm10, %xmm15
+ vpaddd %xmm0, %xmm15, %xmm15
+ vpxor %xmm15, %xmm1, %xmm1
+ vpshufd $141, %xmm8, %xmm8
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm13, %xmm13
+ vpxor %xmm13, %xmm0, %xmm0
+ vpshufd $57, %xmm1, %xmm1
+ vpshufd $78, %xmm13, %xmm13
+ vpslld $25, %xmm0, %xmm10
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm10, %xmm0, %xmm0
+ vpunpcklqdq %xmm2, %xmm3, %xmm10
+ vpshufd $147, %xmm0, %xmm0
+ vpblendw $51, %xmm14, %xmm10, %xmm14
+ vpshufd $135, %xmm14, %xmm14
+ vpaddd %xmm15, %xmm14, %xmm14
+ vpaddd %xmm0, %xmm14, %xmm14
+ vpxor %xmm14, %xmm1, %xmm1
+ vpunpcklqdq %xmm3, %xmm4, %xmm15
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm13, %xmm13
+ vpxor %xmm13, %xmm0, %xmm0
+ vpslld $20, %xmm0, %xmm11
+ vpsrld $12, %xmm0, %xmm0
+ vpxor %xmm11, %xmm0, %xmm0
+ vpunpckhqdq %xmm5, %xmm3, %xmm11
+ vpblendw $51, %xmm15, %xmm11, %xmm11
+ vpunpckhqdq %xmm3, %xmm5, %xmm15
+ vpaddd %xmm11, %xmm14, %xmm11
+ vpaddd %xmm0, %xmm11, %xmm11
+ vpxor %xmm11, %xmm1, %xmm1
+ vpshufb %xmm6, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm13, %xmm13
+ vpxor %xmm13, %xmm0, %xmm0
+ vpshufd $147, %xmm1, %xmm1
+ vpshufd $78, %xmm13, %xmm13
+ vpslld $25, %xmm0, %xmm14
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm14, %xmm0, %xmm14
+ vpunpckhqdq %xmm4, %xmm2, %xmm0
+ vpshufd $57, %xmm14, %xmm14
+ vpblendw $51, %xmm15, %xmm0, %xmm15
+ vpaddd %xmm15, %xmm11, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm1, %xmm1
+ vpshufb %xmm7, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm13, %xmm13
+ vpxor %xmm13, %xmm14, %xmm14
+ vpslld $20, %xmm14, %xmm11
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm11, %xmm14, %xmm14
+ vpblendw $3, %xmm2, %xmm4, %xmm11
+ vpslldq $8, %xmm11, %xmm0
+ vpblendw $15, %xmm5, %xmm0, %xmm0
+ vpshufd $99, %xmm0, %xmm0
+ vpaddd %xmm15, %xmm0, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm1, %xmm0
+ vpaddd %xmm12, %xmm15, %xmm15
+ vpshufb %xmm6, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm13, %xmm13
+ vpxor %xmm13, %xmm14, %xmm14
+ vpshufd $57, %xmm0, %xmm0
+ vpshufd $78, %xmm13, %xmm13
+ vpslld $25, %xmm14, %xmm1
+ vpsrld $7, %xmm14, %xmm14
+ vpxor %xmm1, %xmm14, %xmm14
+ vpblendw $3, %xmm5, %xmm4, %xmm1
+ vpshufd $147, %xmm14, %xmm14
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpshufb %xmm7, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm13, %xmm13
+ vpxor %xmm13, %xmm14, %xmm14
+ vpslld $20, %xmm14, %xmm12
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm12, %xmm14, %xmm14
+ vpsrldq $4, %xmm2, %xmm12
+ vpblendw $60, %xmm12, %xmm1, %xmm1
+ vpaddd %xmm1, %xmm15, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpblendw $12, %xmm4, %xmm3, %xmm1
+ vpshufb %xmm6, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm13, %xmm13
+ vpxor %xmm13, %xmm14, %xmm14
+ vpshufd $147, %xmm0, %xmm0
+ vpshufd $78, %xmm13, %xmm13
+ vpslld $25, %xmm14, %xmm12
+ vpsrld $7, %xmm14, %xmm14
+ vpxor %xmm12, %xmm14, %xmm14
+ vpsrldq $4, %xmm5, %xmm12
+ vpblendw $48, %xmm12, %xmm1, %xmm1
+ vpshufd $33, %xmm5, %xmm12
+ vpshufd $57, %xmm14, %xmm14
+ vpshufd $108, %xmm1, %xmm1
+ vpblendw $51, %xmm12, %xmm10, %xmm12
+ vpaddd %xmm15, %xmm1, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpaddd %xmm12, %xmm15, %xmm15
+ vpshufb %xmm7, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm13, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpslld $20, %xmm14, %xmm13
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm13, %xmm14, %xmm14
+ vpslldq $12, %xmm3, %xmm13
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpshufb %xmm6, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpshufd $57, %xmm0, %xmm0
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm14, %xmm12
+ vpsrld $7, %xmm14, %xmm14
+ vpxor %xmm12, %xmm14, %xmm14
+ vpblendw $51, %xmm5, %xmm4, %xmm12
+ vpshufd $147, %xmm14, %xmm14
+ vpblendw $192, %xmm13, %xmm12, %xmm12
+ vpaddd %xmm12, %xmm15, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpsrldq $4, %xmm3, %xmm12
+ vpshufb %xmm7, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpslld $20, %xmm14, %xmm13
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm13, %xmm14, %xmm14
+ vpblendw $48, %xmm2, %xmm5, %xmm13
+ vpblendw $3, %xmm12, %xmm13, %xmm13
+ vpshufd $156, %xmm13, %xmm13
+ vpaddd %xmm15, %xmm13, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpshufb %xmm6, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpshufd $147, %xmm0, %xmm0
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm14, %xmm13
+ vpsrld $7, %xmm14, %xmm14
+ vpxor %xmm13, %xmm14, %xmm14
+ vpunpcklqdq %xmm2, %xmm4, %xmm13
+ vpshufd $57, %xmm14, %xmm14
+ vpblendw $12, %xmm12, %xmm13, %xmm12
+ vpshufd $180, %xmm12, %xmm12
+ vpaddd %xmm15, %xmm12, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpshufb %xmm7, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpslld $20, %xmm14, %xmm12
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm12, %xmm14, %xmm14
+ vpunpckhqdq %xmm9, %xmm4, %xmm12
+ vpshufd $198, %xmm12, %xmm12
+ vpaddd %xmm15, %xmm12, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpaddd %xmm15, %xmm8, %xmm15
+ vpshufb %xmm6, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpshufd $57, %xmm0, %xmm0
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm14, %xmm12
+ vpsrld $7, %xmm14, %xmm14
+ vpxor %xmm12, %xmm14, %xmm14
+ vpsrldq $4, %xmm4, %xmm12
+ vpshufd $147, %xmm14, %xmm14
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm15, %xmm0, %xmm0
+ vpshufb %xmm7, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpslld $20, %xmm14, %xmm8
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm14, %xmm8, %xmm14
+ vpblendw $48, %xmm5, %xmm2, %xmm8
+ vpblendw $3, %xmm12, %xmm8, %xmm8
+ vpunpckhqdq %xmm5, %xmm4, %xmm12
+ vpshufd $75, %xmm8, %xmm8
+ vpblendw $60, %xmm10, %xmm12, %xmm10
+ vpaddd %xmm15, %xmm8, %xmm15
+ vpaddd %xmm14, %xmm15, %xmm15
+ vpxor %xmm0, %xmm15, %xmm0
+ vpshufd $45, %xmm10, %xmm10
+ vpshufb %xmm6, %xmm0, %xmm0
+ vpaddd %xmm15, %xmm10, %xmm15
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm1, %xmm14, %xmm14
+ vpshufd $147, %xmm0, %xmm0
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm14, %xmm8
+ vpsrld $7, %xmm14, %xmm14
+ vpxor %xmm14, %xmm8, %xmm8
+ vpshufd $57, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm15, %xmm15
+ vpxor %xmm0, %xmm15, %xmm0
+ vpshufb %xmm7, %xmm0, %xmm0
+ vpaddd %xmm0, %xmm1, %xmm1
+ vpxor %xmm8, %xmm1, %xmm8
+ vpslld $20, %xmm8, %xmm10
+ vpsrld $12, %xmm8, %xmm8
+ vpxor %xmm8, %xmm10, %xmm10
+ vpunpckldq %xmm3, %xmm4, %xmm8
+ vpunpcklqdq %xmm9, %xmm8, %xmm9
+ vpaddd %xmm9, %xmm15, %xmm9
+ vpaddd %xmm10, %xmm9, %xmm9
+ vpxor %xmm0, %xmm9, %xmm8
+ vpshufb %xmm6, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm1, %xmm1
+ vpxor %xmm1, %xmm10, %xmm10
+ vpshufd $57, %xmm8, %xmm8
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm10, %xmm12
+ vpsrld $7, %xmm10, %xmm10
+ vpxor %xmm10, %xmm12, %xmm10
+ vpblendw $48, %xmm4, %xmm3, %xmm12
+ vpshufd $147, %xmm10, %xmm0
+ vpunpckhdq %xmm5, %xmm3, %xmm10
+ vpshufd $78, %xmm12, %xmm12
+ vpunpcklqdq %xmm4, %xmm10, %xmm10
+ vpblendw $192, %xmm2, %xmm10, %xmm10
+ vpshufhw $78, %xmm10, %xmm10
+ vpaddd %xmm10, %xmm9, %xmm10
+ vpaddd %xmm0, %xmm10, %xmm10
+ vpxor %xmm8, %xmm10, %xmm8
+ vpshufb %xmm7, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm1, %xmm1
+ vpxor %xmm0, %xmm1, %xmm9
+ vpslld $20, %xmm9, %xmm0
+ vpsrld $12, %xmm9, %xmm9
+ vpxor %xmm9, %xmm0, %xmm0
+ vpunpckhdq %xmm5, %xmm4, %xmm9
+ vpblendw $240, %xmm9, %xmm2, %xmm13
+ vpshufd $39, %xmm13, %xmm13
+ vpaddd %xmm10, %xmm13, %xmm10
+ vpaddd %xmm0, %xmm10, %xmm10
+ vpxor %xmm8, %xmm10, %xmm8
+ vpblendw $12, %xmm4, %xmm2, %xmm13
+ vpshufb %xmm6, %xmm8, %xmm8
+ vpslldq $4, %xmm13, %xmm13
+ vpblendw $15, %xmm5, %xmm13, %xmm13
+ vpaddd %xmm8, %xmm1, %xmm1
+ vpxor %xmm1, %xmm0, %xmm0
+ vpaddd %xmm13, %xmm10, %xmm13
+ vpshufd $147, %xmm8, %xmm8
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm0, %xmm14
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm0, %xmm14, %xmm14
+ vpshufd $57, %xmm14, %xmm14
+ vpaddd %xmm14, %xmm13, %xmm13
+ vpxor %xmm8, %xmm13, %xmm8
+ vpaddd %xmm13, %xmm12, %xmm12
+ vpshufb %xmm7, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm1, %xmm1
+ vpxor %xmm14, %xmm1, %xmm14
+ vpslld $20, %xmm14, %xmm10
+ vpsrld $12, %xmm14, %xmm14
+ vpxor %xmm14, %xmm10, %xmm10
+ vpaddd %xmm10, %xmm12, %xmm12
+ vpxor %xmm8, %xmm12, %xmm8
+ vpshufb %xmm6, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm1, %xmm1
+ vpxor %xmm1, %xmm10, %xmm0
+ vpshufd $57, %xmm8, %xmm8
+ vpshufd $78, %xmm1, %xmm1
+ vpslld $25, %xmm0, %xmm10
+ vpsrld $7, %xmm0, %xmm0
+ vpxor %xmm0, %xmm10, %xmm10
+ vpblendw $48, %xmm2, %xmm3, %xmm0
+ vpblendw $15, %xmm11, %xmm0, %xmm0
+ vpshufd $147, %xmm10, %xmm10
+ vpshufd $114, %xmm0, %xmm0
+ vpaddd %xmm12, %xmm0, %xmm0
+ vpaddd %xmm10, %xmm0, %xmm0
+ vpxor %xmm8, %xmm0, %xmm8
+ vpshufb %xmm7, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm1, %xmm1
+ vpxor %xmm10, %xmm1, %xmm10
+ vpslld $20, %xmm10, %xmm11
+ vpsrld $12, %xmm10, %xmm10
+ vpxor %xmm10, %xmm11, %xmm10
+ vpslldq $4, %xmm4, %xmm11
+ vpblendw $192, %xmm11, %xmm3, %xmm3
+ vpunpckldq %xmm5, %xmm4, %xmm4
+ vpshufd $99, %xmm3, %xmm3
+ vpaddd %xmm0, %xmm3, %xmm3
+ vpaddd %xmm10, %xmm3, %xmm3
+ vpxor %xmm8, %xmm3, %xmm11
+ vpunpckldq %xmm5, %xmm2, %xmm0
+ vpblendw $192, %xmm2, %xmm5, %xmm2
+ vpshufb %xmm6, %xmm11, %xmm11
+ vpunpckhqdq %xmm0, %xmm9, %xmm0
+ vpblendw $15, %xmm4, %xmm2, %xmm4
+ vpaddd %xmm11, %xmm1, %xmm1
+ vpxor %xmm1, %xmm10, %xmm10
+ vpshufd $147, %xmm11, %xmm11
+ vpshufd $201, %xmm0, %xmm0
+ vpslld $25, %xmm10, %xmm8
+ vpsrld $7, %xmm10, %xmm10
+ vpxor %xmm10, %xmm8, %xmm10
+ vpshufd $78, %xmm1, %xmm1
+ vpaddd %xmm3, %xmm0, %xmm0
+ vpshufd $27, %xmm4, %xmm4
+ vpshufd $57, %xmm10, %xmm10
+ vpaddd %xmm10, %xmm0, %xmm0
+ vpxor %xmm11, %xmm0, %xmm11
+ vpaddd %xmm0, %xmm4, %xmm0
+ vpshufb %xmm7, %xmm11, %xmm7
+ vpaddd %xmm7, %xmm1, %xmm1
+ vpxor %xmm10, %xmm1, %xmm10
+ vpslld $20, %xmm10, %xmm8
+ vpsrld $12, %xmm10, %xmm10
+ vpxor %xmm10, %xmm8, %xmm8
+ vpaddd %xmm8, %xmm0, %xmm0
+ vpxor %xmm7, %xmm0, %xmm7
+ vpshufb %xmm6, %xmm7, %xmm6
+ vpaddd %xmm6, %xmm1, %xmm1
+ vpxor %xmm1, %xmm8, %xmm8
+ vpshufd $78, %xmm1, %xmm1
+ vpshufd $57, %xmm6, %xmm6
+ vpslld $25, %xmm8, %xmm2
+ vpsrld $7, %xmm8, %xmm8
+ vpxor %xmm8, %xmm2, %xmm8
+ vpxor (%rdi), %xmm1, %xmm1
+ vpshufd $147, %xmm8, %xmm8
+ vpxor %xmm0, %xmm1, %xmm0
+ vmovups %xmm0, (%rdi)
+ vpxor 16(%rdi), %xmm8, %xmm0
+ vpxor %xmm6, %xmm0, %xmm6
+ vmovups %xmm6, 16(%rdi)
+ addq $64, %rsi
+ decq %rdx
+ jnz .Lbeginofloop
+.Lendofloop:
+ ret
+ENDPROC(blake2s_compress_avx)
+#endif /* CONFIG_AS_AVX */
+
+#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 SIGMA(%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 $0x39,%xmm1,%xmm1
+ vpshufd $0x4e,%xmm2,%xmm2
+ vpshufd $0x93,%xmm3,%xmm3
+ 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 $0x93,%xmm1,%xmm1
+ vpshufd $0x4e,%xmm2,%xmm2
+ vpshufd $0x39,%xmm3,%xmm3
+ 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 */
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
new file mode 100644
index 000000000000..f3b80ffa513a
--- /dev/null
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <crypto/blake2s.h>
+#include <crypto/internal/simd.h>
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/processor.h>
+#include <asm/simd.h>
+
+asmlinkage void blake2s_compress_avx(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 bool blake2s_use_avx __ro_after_init;
+static bool blake2s_use_avx512 __ro_after_init;
+
+bool 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 (!blake2s_use_avx || !crypto_simd_usable())
+ return false;
+
+ for (;;) {
+ const size_t blocks = min_t(size_t, nblocks,
+ PAGE_SIZE / BLAKE2S_BLOCK_SIZE);
+
+ kernel_fpu_begin();
+ if (IS_ENABLED(CONFIG_AS_AVX512) && blake2s_use_avx512)
+ blake2s_compress_avx512(state, block, blocks, inc);
+ else
+ blake2s_compress_avx(state, block, blocks, inc);
+ kernel_fpu_end();
+
+ nblocks -= blocks;
+ if (!nblocks)
+ break;
+ block += blocks * BLAKE2S_BLOCK_SIZE;
+ }
+ return true;
+}
+
+static int __init blake2s_mod_init(void)
+{
+ blake2s_use_avx =
+ boot_cpu_has(X86_FEATURE_AVX) &&
+ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
+ blake2s_use_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);
+
+ return 0;
+}
+
+module_init(blake2s_mod_init);
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 7e1c794b570e..5055e05e8f80 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1010,6 +1010,12 @@ config CRYPTO_LIB_BLAKE2S
tristate "BLAKE2s hash function library"
depends on CRYPTO_ARCH_HAVE_LIB_BLAKE2S || !CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+config CRYPTO_LIB_BLAKE2S_X86
+ tristate "BLAKE2s hash function library (x86 accelerated version)"
+ depends on X86 && 64BIT
+ select CRYPTO_LIB_BLAKE2S
+ select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+
comment "Ciphers"
config CRYPTO_LIB_AES
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* Re: [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation
2019-09-29 17:38 ` [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation Ard Biesheuvel
@ 2019-09-30 2:42 ` Jason A. Donenfeld
2019-09-30 2:51 ` Linus Torvalds
2019-09-30 7:35 ` Sebastian Siewior
0 siblings, 2 replies; 23+ messages in thread
From: Jason A. Donenfeld @ 2019-09-30 2:42 UTC (permalink / raw)
To: Sebastian Siewior, Thomas Gleixner
Cc: Catalin Marinas, Herbert Xu, Arnd Bergmann, Ard Biesheuvel,
Martin Willi, Greg KH, Eric Biggers, Samuel Neves, Will Deacon,
Linux Crypto Mailing List, Andy Lutomirski, Marc Zyngier,
Dan Carpenter, Linus Torvalds, David Miller, linux-arm-kernel
Hi Sebastian, Thomas,
Take a look at the below snippet from this patch.
I had previously put quite some effort into the simd_get, simd_put,
simd_relax mechanism, so that the simd state could be persisted during
both several calls to the same function and within long loops like
below, with simd_relax existing to reenable preemption briefly if
things were getting out of hand. Ard got rid of this and has moved the
kernel_fpu_begin and kernel_fpu_end calls into the inner loop:
On Sun, Sep 29, 2019 at 7:39 PM Ard Biesheuvel
<ard.biesheuvel@linaro.org> wrote:
> + for (;;) {
> + const size_t blocks = min_t(size_t, nblocks,
> + PAGE_SIZE / BLAKE2S_BLOCK_SIZE);
> +
> + kernel_fpu_begin();
> + if (IS_ENABLED(CONFIG_AS_AVX512) && blake2s_use_avx512)
> + blake2s_compress_avx512(state, block, blocks, inc);
> + else
> + blake2s_compress_avx(state, block, blocks, inc);
> + kernel_fpu_end();
> +
> + nblocks -= blocks;
> + if (!nblocks)
> + break;
> + block += blocks * BLAKE2S_BLOCK_SIZE;
> + }
> + return true;
> +}
I'm wondering if on modern kernels this is actually fine and whether
my simd_get/put/relax thing no longer has a good use case.
Specifically, I recall last year there were a lot of patches and
discussions about doing FPU register restoration lazily -- on context
switch or the like. Did those land? Did the theory of action work out
in the end?
Regards,
Jason
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation
2019-09-30 2:42 ` Jason A. Donenfeld
@ 2019-09-30 2:51 ` Linus Torvalds
2019-09-30 7:35 ` Sebastian Siewior
1 sibling, 0 replies; 23+ messages in thread
From: Linus Torvalds @ 2019-09-30 2:51 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: Catalin Marinas, Herbert Xu, Arnd Bergmann, Ard Biesheuvel,
Martin Willi, Greg KH, Sebastian Siewior, Eric Biggers,
Samuel Neves, Linux Crypto Mailing List, Andy Lutomirski,
Marc Zyngier, Thomas Gleixner, Dan Carpenter, Will Deacon,
David Miller, linux-arm-kernel
On Sun, Sep 29, 2019 at 7:42 PM Jason A. Donenfeld <Jason@zx2c4.com> wrote:
>
> I had previously put quite some effort into the simd_get, simd_put,
> simd_relax mechanism, so that the simd state could be persisted during
> both several calls to the same function and within long loops like
> below, with simd_relax existing to reenable preemption briefly if
> things were getting out of hand. Ard got rid of this and has moved the
> kernel_fpu_begin and kernel_fpu_end calls into the inner loop:
Actually, that should be ok these days.
What has happened fairly recently (it got merged into 5.2 back in May)
is that we no longer do the FPU save/restore on each
kernel_fpu_begin/end.
Instead, we save it on kernel_fpu_begin(), and set a flag that it
needs to be restored when returning to user space.
So the kernel now on its own merges that FPU save/restore overhead
when you do it repeatedly.
The core change happened in
5f409e20b794 ("x86/fpu: Defer FPU state load until return to userspace")
but there are a few commits around it for cleanups etc. The code was merged in
8ff468c29e9a ("Merge branch 'x86-fpu-for-linus' of
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip")
if you want to see the whole series.
That said, it would be _lovely_ if you or somebody else actually
double-checked that it works as expected and that the numbers bear out
the improvements.
It should be superior to the old model of manually trying to merge FPU
use regions, both from a performance angle (because it will merge much
more), but also from a code simplicity angle and the whole preemption
latency worry also basically goes away.
Linus
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation
2019-09-30 2:42 ` Jason A. Donenfeld
2019-09-30 2:51 ` Linus Torvalds
@ 2019-09-30 7:35 ` Sebastian Siewior
1 sibling, 0 replies; 23+ messages in thread
From: Sebastian Siewior @ 2019-09-30 7:35 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: Catalin Marinas, Herbert Xu, Arnd Bergmann, Ard Biesheuvel,
Martin Willi, Greg KH, Eric Biggers, Samuel Neves, Will Deacon,
Linux Crypto Mailing List, Andy Lutomirski, Marc Zyngier,
Thomas Gleixner, Dan Carpenter, Linus Torvalds, David Miller,
linux-arm-kernel
On 2019-09-30 04:42:06 [+0200], Jason A. Donenfeld wrote:
> Hi Sebastian, Thomas,
Hi Jason,
> On Sun, Sep 29, 2019 at 7:39 PM Ard Biesheuvel
> <ard.biesheuvel@linaro.org> wrote:
> > + for (;;) {
> > + const size_t blocks = min_t(size_t, nblocks,
> > + PAGE_SIZE / BLAKE2S_BLOCK_SIZE);
> > +
> > + kernel_fpu_begin();
> > + if (IS_ENABLED(CONFIG_AS_AVX512) && blake2s_use_avx512)
> > + blake2s_compress_avx512(state, block, blocks, inc);
> > + else
> > + blake2s_compress_avx(state, block, blocks, inc);
> > + kernel_fpu_end();
> > +
> > + nblocks -= blocks;
> > + if (!nblocks)
> > + break;
> > + block += blocks * BLAKE2S_BLOCK_SIZE;
> > + }
> > + return true;
> > +}
>
> I'm wondering if on modern kernels this is actually fine and whether
> my simd_get/put/relax thing no longer has a good use case.
> Specifically, I recall last year there were a lot of patches and
> discussions about doing FPU register restoration lazily -- on context
> switch or the like. Did those land? Did the theory of action work out
> in the end?
That optimisation landed in v5.2. With that change (on x86)
kernel_fpu_end() does almost nothing (and so the following
kernel_fpu_begin()) and the FPU context will be restored once the task
returns to user land. (Note that this counts only for user-tasks because
we don't save the FPU state of a kernel thread.)
I haven't look at crypto code since that change was merged but looking
at the snippet from Ard is actually what I was aiming for.
> Regards,
> Jason
Sebastian
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 23+ messages in thread
* [RFC PATCH 13/20] crypto: Curve25519 - x86_64 library implementation
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (9 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 11/20] crypto: BLAKE2s - x86_64 implementation Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 14/20] crypto: arm - import Bernstein and Schwabe's Curve25519 ARM implementation Ard Biesheuvel
` (5 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
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 <Jason@zx2c4.com>
Signed-off-by: Samuel Neves <sneves@dei.uc.pt>
Co-developed-by: Samuel Neves <sneves@dei.uc.pt>
[ardb: move to arch/x86/crypto, wire into lib/crypto framework]
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/x86/crypto/Makefile | 1 +
arch/x86/crypto/curve25519-x86_64.c | 2379 ++++++++++++++++++++
crypto/Kconfig | 7 +
3 files changed, 2387 insertions(+)
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index db87c182ce0f..ac7c076133a0 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
+obj-$(CONFIG_CRYPTO_LIB_CURVE25519_X86) += curve25519-x86_64.o
# These modules require assembler to support AVX.
ifeq ($(avx_supported),yes)
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
new file mode 100644
index 000000000000..1f7857fbd399
--- /dev/null
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -0,0 +1,2379 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (c) 2017 Armando Faz <armfazh@ic.unicamp.br>. All Rights Reserved.
+ * Copyright (C) 2018-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
+ */
+
+#include <crypto/curve25519.h>
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/processor.h>
+
+static bool curve25519_use_bmi2 __ro_after_init;
+static bool curve25519_use_adx __ro_after_init;
+
+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));
+}
+
+bool curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE],
+ const u8 basepoint[CURVE25519_KEY_SIZE])
+{
+ if (curve25519_use_adx) {
+ curve25519_adx(mypublic, secret, basepoint);
+ return true;
+ } else if (curve25519_use_bmi2) {
+ curve25519_bmi2(mypublic, secret, basepoint);
+ return true;
+ }
+ return false;
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+bool curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE])
+{
+ if (curve25519_use_adx) {
+ curve25519_adx_base(pub, secret);
+ return true;
+ } else if (curve25519_use_bmi2) {
+ curve25519_bmi2_base(pub, secret);
+ return true;
+ }
+ return false;
+}
+EXPORT_SYMBOL(curve25519_base_arch);
+
+static int __init curve25519_mod_init(void)
+{
+ curve25519_use_bmi2 = boot_cpu_has(X86_FEATURE_BMI2);
+ curve25519_use_adx = boot_cpu_has(X86_FEATURE_BMI2) &&
+ boot_cpu_has(X86_FEATURE_ADX);
+
+ return 0;
+}
+
+module_init(curve25519_mod_init);
diff --git a/crypto/Kconfig b/crypto/Kconfig
index ce80c5bd8a4f..9b7789277cd1 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -274,6 +274,13 @@ config CRYPTO_LIB_CURVE25519
tristate "Curve25519 scalar multiplication library"
depends on CRYPTO_ARCH_HAVE_LIB_CURVE25519 || !CRYPTO_ARCH_HAVE_LIB_CURVE25519
+config CRYPTO_LIB_CURVE25519_X86
+ tristate "x86_64 accelerated Curve25519 scalar multiplication library"
+ depends on X86 && 64BIT
+ select CRYPTO_LIB_CURVE25519
+ select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+ select CRYPTO_ARCH_HAVE_LIB_CURVE25519_BASE
+
comment "Authenticated Encryption with Associated Data"
config CRYPTO_CCM
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 14/20] crypto: arm - import Bernstein and Schwabe's Curve25519 ARM implementation
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (10 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 13/20] crypto: Curve25519 - x86_64 library implementation Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 15/20] crypto: arm/Curve25519 - wire up NEON implementation Ard Biesheuvel
` (4 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
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
<https://bench.cr.yp.to/supercop.html>.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm/crypto/curve25519-core.S | 2105 ++++++++++++++++++++
1 file changed, 2105 insertions(+)
diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S
new file mode 100644
index 000000000000..f33b85fef382
--- /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
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 15/20] crypto: arm/Curve25519 - wire up NEON implementation
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (11 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 14/20] crypto: arm - import Bernstein and Schwabe's Curve25519 ARM implementation Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 17/20] crypto: lib/chacha20poly1305 - reimplement crypt_from_sg() routine Ard Biesheuvel
` (3 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
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 <Jason@zx2c4.com>
[ardb: move to arch/arm/crypto, wire into lib/crypto framework]
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
arch/arm/crypto/Kconfig | 6 +
arch/arm/crypto/Makefile | 2 +
arch/arm/crypto/curve25519-core.S | 347 +++++++++-----------
arch/arm/crypto/curve25519-glue.c | 45 +++
4 files changed, 205 insertions(+), 195 deletions(-)
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 8a603698b296..0af6ce740d20 100644
--- 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_LIB_CURVE25519_NEON
+ tristate "NEON accelerated Curve25519 scalar multiplication library"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_LIB_CURVE25519
+ select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+
endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index c9d5fab8ad45..bd37e9fa491c 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -12,6 +12,7 @@ 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-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
+obj-$(CONFIG_CRYPTO_LIB_CURVE25519_NEON) += libcurve25519-neon.o
ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -57,6 +58,7 @@ crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
poly1305-arm-y := poly1305-core.o poly1305-glue.o
nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
+libcurve25519-neon-y := curve25519-core.o curve25519-glue.o
ifdef REGENERATE_ARM_CRYPTO
quiet_cmd_perl = PERL $@
diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S
index f33b85fef382..be18af52e7dc 100644
--- 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 <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
*/
-.fpu neon
+#include <linux/linkage.h>
+
.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)
diff --git a/arch/arm/crypto/curve25519-glue.c b/arch/arm/crypto/curve25519-glue.c
new file mode 100644
index 000000000000..9697fbe8c38d
--- /dev/null
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/simd.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <crypto/curve25519.h>
+
+asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE],
+ const u8 basepoint[CURVE25519_KEY_SIZE]);
+
+static bool have_neon __ro_after_init;
+
+bool curve25519_arch(u8 out[CURVE25519_KEY_SIZE],
+ const u8 scalar[CURVE25519_KEY_SIZE],
+ const u8 point[CURVE25519_KEY_SIZE])
+{
+ if (!have_neon || !crypto_simd_usable())
+ return false;
+ kernel_neon_begin();
+ curve25519_neon(out, scalar, point);
+ kernel_neon_end();
+ return true;
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+static int __init mod_init(void)
+{
+ have_neon = (elf_hwcap & HWCAP_NEON);
+ return 0;
+}
+
+module_init(mod_init);
+MODULE_LICENSE("GPL v2");
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 17/20] crypto: lib/chacha20poly1305 - reimplement crypt_from_sg() routine
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (12 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 15/20] crypto: arm/Curve25519 - wire up NEON implementation Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 19/20] netlink: use new strict length types in policy for 5.2 Ard Biesheuvel
` (2 subsequent siblings)
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
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 <ard.biesheuvel@linaro.org>
---
include/crypto/chacha20poly1305.h | 11 ++
lib/crypto/chacha20poly1305-selftest.c | 45 ++++++
lib/crypto/chacha20poly1305.c | 151 ++++++++++++++++++++
3 files changed, 207 insertions(+)
diff --git a/include/crypto/chacha20poly1305.h b/include/crypto/chacha20poly1305.h
index ad3b1de58df8..f395d244a49e 100644
--- a/include/crypto/chacha20poly1305.h
+++ b/include/crypto/chacha20poly1305.h
@@ -7,6 +7,7 @@
#define __CHACHA20POLY1305_H
#include <linux/types.h>
+#include <linux/scatterlist.h>
enum chacha20poly1305_lengths {
XCHACHA20POLY1305_NONCE_SIZE = 24,
@@ -34,4 +35,14 @@ bool __must_check xchacha20poly1305_decrypt(
const size_t ad_len, const u8 nonce[XCHACHA20POLY1305_NONCE_SIZE],
const u8 key[CHACHA20POLY1305_KEY_SIZE]);
+void 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 */
diff --git a/lib/crypto/chacha20poly1305-selftest.c b/lib/crypto/chacha20poly1305-selftest.c
index 618bdd4ab36f..5b496b5c15e3 100644
--- a/lib/crypto/chacha20poly1305-selftest.c
+++ b/lib/crypto/chacha20poly1305-selftest.c
@@ -7251,6 +7251,7 @@ 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;
bool success = true, ret;
heap_src = kmalloc(MAXIMUM_TEST_BUFFER_LEN, GFP_KERNEL);
@@ -7281,6 +7282,29 @@ bool __init chacha20poly1305_selftest(void)
}
}
+ 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,
@@ -7302,6 +7326,27 @@ bool __init chacha20poly1305_selftest(void)
}
}
+ 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);
diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c
index 3127d09c483f..115e00d7417c 100644
--- a/lib/crypto/chacha20poly1305.c
+++ b/lib/crypto/chacha20poly1305.c
@@ -11,6 +11,7 @@
#include <crypto/chacha20poly1305.h>
#include <crypto/chacha.h>
#include <crypto/poly1305.h>
+#include <crypto/scatterwalk.h>
#include <asm/unaligned.h>
#include <linux/kernel.h>
@@ -205,6 +206,156 @@ bool xchacha20poly1305_decrypt(u8 *dst, const u8 *src, const size_t src_len,
}
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 length, partial = 0;
+ unsigned int flags;
+ bool ret = true;
+ u8 *addr;
+ 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) {
+ addr = miter.addr;
+ 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;
+ addr += 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;
+}
+
+void 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])
+{
+ 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))
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 19/20] netlink: use new strict length types in policy for 5.2
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (13 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 17/20] crypto: lib/chacha20poly1305 - reimplement crypt_from_sg() routine Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-29 17:38 ` [RFC PATCH 20/20] wg switch to lib/crypto algos Ard Biesheuvel
2019-09-30 11:51 ` [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
Taken from
https://git.zx2c4.com/WireGuard/commit/src?id=3120425f69003be287cb2d308f89c7a6a0335ff0
Reported-by: Bruno Wolff III <bruno@wolff.to>
---
drivers/net/wireguard/netlink.c | 17 ++++++++---------
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 3763e8c14ea5..676d36725120 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -21,8 +21,8 @@ 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] = { .len = NOISE_PUBLIC_KEY_LEN },
- [WGDEVICE_A_PUBLIC_KEY] = { .len = NOISE_PUBLIC_KEY_LEN },
+ [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 },
@@ -30,12 +30,12 @@ static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = {
};
static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = {
- [WGPEER_A_PUBLIC_KEY] = { .len = NOISE_PUBLIC_KEY_LEN },
- [WGPEER_A_PRESHARED_KEY] = { .len = NOISE_SYMMETRIC_KEY_LEN },
+ [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] = { .len = sizeof(struct sockaddr) },
+ [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
- [WGPEER_A_LAST_HANDSHAKE_TIME] = { .len = sizeof(struct __kernel_timespec) },
+ [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 },
@@ -44,7 +44,7 @@ static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = {
static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = {
[WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 },
- [WGALLOWEDIP_A_IPADDR] = { .len = sizeof(struct in_addr) },
+ [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) },
[WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }
};
@@ -591,12 +591,10 @@ static const struct genl_ops genl_ops[] = {
.start = wg_get_device_start,
.dumpit = wg_get_device_dump,
.done = wg_get_device_done,
- .policy = device_policy,
.flags = GENL_UNS_ADMIN_PERM
}, {
.cmd = WG_CMD_SET_DEVICE,
.doit = wg_set_device,
- .policy = device_policy,
.flags = GENL_UNS_ADMIN_PERM
}
};
@@ -608,6 +606,7 @@ static struct genl_family genl_family __ro_after_init = {
.version = WG_GENL_VERSION,
.maxattr = WGDEVICE_A_MAX,
.module = THIS_MODULE,
+ .policy = device_policy,
.netnsok = true
};
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* [RFC PATCH 20/20] wg switch to lib/crypto algos
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (14 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 19/20] netlink: use new strict length types in policy for 5.2 Ard Biesheuvel
@ 2019-09-29 17:38 ` Ard Biesheuvel
2019-09-30 11:51 ` [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-29 17:38 UTC (permalink / raw)
To: linux-crypto
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Ard Biesheuvel, Martin Willi, Greg KH, Eric Biggers,
Samuel Neves, Will Deacon, Dan Carpenter, Andy Lutomirski,
Marc Zyngier, Linus Torvalds, David Miller, linux-arm-kernel
This switches WireGuard to use lib/crypto libraries instead of the
Zinc ones.
This patch is intended to be squashed at merge time, or it will break
bisection.
---
drivers/net/Kconfig | 6 +++---
drivers/net/wireguard/cookie.c | 4 ++--
drivers/net/wireguard/messages.h | 6 +++---
drivers/net/wireguard/receive.c | 17 ++++-------------
drivers/net/wireguard/send.c | 19 ++++++-------------
5 files changed, 18 insertions(+), 34 deletions(-)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index c26aef673538..3bd4dc662392 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -77,9 +77,9 @@ config WIREGUARD
depends on IPV6 || !IPV6
select NET_UDP_TUNNEL
select DST_CACHE
- select ZINC_CHACHA20POLY1305
- select ZINC_BLAKE2S
- select ZINC_CURVE25519
+ select CRYPTO_LIB_CHACHA20POLY1305
+ select CRYPTO_LIB_BLAKE2S
+ select CRYPTO_LIB_CURVE25519
help
WireGuard is a secure, fast, and easy to use replacement for IPSec
that uses modern cryptography and clever networking tricks. It's
diff --git a/drivers/net/wireguard/cookie.c b/drivers/net/wireguard/cookie.c
index bd23a14ff87f..104b739c327f 100644
--- a/drivers/net/wireguard/cookie.c
+++ b/drivers/net/wireguard/cookie.c
@@ -10,8 +10,8 @@
#include "ratelimiter.h"
#include "timers.h"
-#include <zinc/blake2s.h>
-#include <zinc/chacha20poly1305.h>
+#include <crypto/blake2s.h>
+#include <crypto/chacha20poly1305.h>
#include <net/ipv6.h>
#include <crypto/algapi.h>
diff --git a/drivers/net/wireguard/messages.h b/drivers/net/wireguard/messages.h
index 3cfd1c5e9b02..4bbb1f97af04 100644
--- a/drivers/net/wireguard/messages.h
+++ b/drivers/net/wireguard/messages.h
@@ -6,9 +6,9 @@
#ifndef _WG_MESSAGES_H
#define _WG_MESSAGES_H
-#include <zinc/curve25519.h>
-#include <zinc/chacha20poly1305.h>
-#include <zinc/blake2s.h>
+#include <crypto/blake2s.h>
+#include <crypto/chacha20poly1305.h>
+#include <crypto/curve25519.h>
#include <linux/kernel.h>
#include <linux/param.h>
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 900c76edb9d6..ae7ffba5fc48 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -11,7 +11,6 @@
#include "cookie.h"
#include "socket.h"
-#include <linux/simd.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/udp.h>
@@ -244,8 +243,7 @@ static void keep_key_fresh(struct wg_peer *peer)
}
}
-static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key,
- simd_context_t *simd_context)
+static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
{
struct scatterlist sg[MAX_SKB_FRAGS + 8];
struct sk_buff *trailer;
@@ -281,9 +279,8 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key,
if (skb_to_sgvec(skb, sg, 0, skb->len) <= 0)
return false;
- if (!chacha20poly1305_decrypt_sg(sg, sg, skb->len, NULL, 0,
- PACKET_CB(skb)->nonce, key->key,
- simd_context))
+ 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
@@ -510,21 +507,15 @@ void wg_packet_decrypt_worker(struct work_struct *work)
{
struct crypt_queue *queue = container_of(work, struct multicore_worker,
work)->ptr;
- simd_context_t simd_context;
struct sk_buff *skb;
- simd_get(&simd_context);
while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
enum packet_state state = likely(decrypt_packet(skb,
- &PACKET_CB(skb)->keypair->receiving,
- &simd_context)) ?
+ &PACKET_CB(skb)->keypair->receiving)) ?
PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
wg_queue_enqueue_per_peer_napi(&PACKET_PEER(skb)->rx_queue, skb,
state);
- simd_relax(&simd_context);
}
-
- simd_put(&simd_context);
}
static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb)
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index b0df5c717502..37bd2599ae44 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -11,7 +11,6 @@
#include "messages.h"
#include "cookie.h"
-#include <linux/simd.h>
#include <linux/uio.h>
#include <linux/inetdevice.h>
#include <linux/socket.h>
@@ -157,8 +156,7 @@ static unsigned int calculate_skb_padding(struct sk_buff *skb)
return padded_size - last_unit;
}
-static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair,
- simd_context_t *simd_context)
+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];
@@ -207,9 +205,10 @@ static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair,
if (skb_to_sgvec(skb, sg, sizeof(struct message_data),
noise_encrypted_len(plaintext_len)) <= 0)
return false;
- return chacha20poly1305_encrypt_sg(sg, sg, plaintext_len, NULL, 0,
- PACKET_CB(skb)->nonce,
- keypair->sending.key, simd_context);
+ chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0,
+ PACKET_CB(skb)->nonce,
+ keypair->sending.key);
+ return true;
}
void wg_packet_send_keepalive(struct wg_peer *peer)
@@ -296,16 +295,13 @@ 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;
- simd_context_t simd_context;
- simd_get(&simd_context);
while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) {
enum packet_state state = PACKET_STATE_CRYPTED;
skb_walk_null_queue_safe(first, skb, next) {
if (likely(encrypt_packet(skb,
- PACKET_CB(first)->keypair,
- &simd_context))) {
+ PACKET_CB(first)->keypair))) {
wg_reset_packet(skb);
} else {
state = PACKET_STATE_DEAD;
@@ -314,10 +310,7 @@ void wg_packet_encrypt_worker(struct work_struct *work)
}
wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
state);
-
- simd_relax(&simd_context);
}
- simd_put(&simd_context);
}
static void wg_packet_create_data(struct sk_buff *first)
--
2.17.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 23+ messages in thread
* Re: [RFC PATCH 00/20] crypto: wireguard with crypto API library interface
2019-09-29 17:38 [RFC PATCH 00/20] crypto: wireguard with crypto API library interface Ard Biesheuvel
` (15 preceding siblings ...)
2019-09-29 17:38 ` [RFC PATCH 20/20] wg switch to lib/crypto algos Ard Biesheuvel
@ 2019-09-30 11:51 ` Ard Biesheuvel
16 siblings, 0 replies; 23+ messages in thread
From: Ard Biesheuvel @ 2019-09-30 11:51 UTC (permalink / raw)
To: open list:HARDWARE RANDOM NUMBER GENERATOR CORE
Cc: Jason A . Donenfeld, Catalin Marinas, Herbert Xu, Arnd Bergmann,
Eric Biggers, Martin Willi, Greg KH, Samuel Neves, Will Deacon,
Dan Carpenter, Andy Lutomirski, Marc Zyngier, Linus Torvalds,
David Miller, linux-arm-kernel
On Sun, 29 Sep 2019 at 19:38, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
...
>
> Patches can be found here:
> https://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git/log/?h=wireguard-crypto-library-api
>
Note: I touched up some minor issues spotted by the build robots, so
if anyone pulled this for testing, you may want to pull again.
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 23+ messages in thread