Architecture: arm64 using:
- ARMv8 Crypto Extensions
-config CRYPTO_NHPOLY1305_NEON
- tristate "Hash functions: NHPoly1305 (NEON)"
- depends on KERNEL_MODE_NEON
- select CRYPTO_NHPOLY1305
- help
- NHPoly1305 hash function (Adiantum)
-
- Architecture: arm64 using:
- - NEON (Advanced SIMD) extensions
-
config CRYPTO_SM3_NEON
tristate "Hash functions: SM3 (NEON)"
depends on KERNEL_MODE_NEON
obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
aes-neon-blk-y := aes-glue-neon.o aes-neon.o
-obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
-nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
-
obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * NH - ε-almost-universal hash function, ARM64 NEON accelerated version
- *
- * Copyright 2018 Google LLC
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
- KEY .req x0
- MESSAGE .req x1
- MESSAGE_LEN .req x2
- HASH .req x3
-
- PASS0_SUMS .req v0
- PASS1_SUMS .req v1
- PASS2_SUMS .req v2
- PASS3_SUMS .req v3
- K0 .req v4
- K1 .req v5
- K2 .req v6
- K3 .req v7
- T0 .req v8
- T1 .req v9
- T2 .req v10
- T3 .req v11
- T4 .req v12
- T5 .req v13
- T6 .req v14
- T7 .req v15
-
-.macro _nh_stride k0, k1, k2, k3
-
- // Load next message stride
- ld1 {T3.16b}, [MESSAGE], #16
-
- // Load next key stride
- ld1 {\k3\().4s}, [KEY], #16
-
- // Add message words to key words
- add T0.4s, T3.4s, \k0\().4s
- add T1.4s, T3.4s, \k1\().4s
- add T2.4s, T3.4s, \k2\().4s
- add T3.4s, T3.4s, \k3\().4s
-
- // Multiply 32x32 => 64 and accumulate
- mov T4.d[0], T0.d[1]
- mov T5.d[0], T1.d[1]
- mov T6.d[0], T2.d[1]
- mov T7.d[0], T3.d[1]
- umlal PASS0_SUMS.2d, T0.2s, T4.2s
- umlal PASS1_SUMS.2d, T1.2s, T5.2s
- umlal PASS2_SUMS.2d, T2.2s, T6.2s
- umlal PASS3_SUMS.2d, T3.2s, T7.2s
-.endm
-
-/*
- * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
- * __le64 hash[NH_NUM_PASSES])
- *
- * It's guaranteed that message_len % 16 == 0.
- */
-SYM_TYPED_FUNC_START(nh_neon)
-
- ld1 {K0.4s,K1.4s}, [KEY], #32
- movi PASS0_SUMS.2d, #0
- movi PASS1_SUMS.2d, #0
- ld1 {K2.4s}, [KEY], #16
- movi PASS2_SUMS.2d, #0
- movi PASS3_SUMS.2d, #0
-
- subs MESSAGE_LEN, MESSAGE_LEN, #64
- blt .Lloop4_done
-.Lloop4:
- _nh_stride K0, K1, K2, K3
- _nh_stride K1, K2, K3, K0
- _nh_stride K2, K3, K0, K1
- _nh_stride K3, K0, K1, K2
- subs MESSAGE_LEN, MESSAGE_LEN, #64
- bge .Lloop4
-
-.Lloop4_done:
- ands MESSAGE_LEN, MESSAGE_LEN, #63
- beq .Ldone
- _nh_stride K0, K1, K2, K3
-
- subs MESSAGE_LEN, MESSAGE_LEN, #16
- beq .Ldone
- _nh_stride K1, K2, K3, K0
-
- subs MESSAGE_LEN, MESSAGE_LEN, #16
- beq .Ldone
- _nh_stride K2, K3, K0, K1
-
-.Ldone:
- // Sum the accumulators for each pass, then store the sums to 'hash'
- addp T0.2d, PASS0_SUMS.2d, PASS1_SUMS.2d
- addp T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d
- st1 {T0.16b,T1.16b}, [HASH]
- ret
-SYM_FUNC_END(nh_neon)
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
- * (ARM64 NEON accelerated version)
- *
- * Copyright 2018 Google LLC
- */
-
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/nhpoly1305.h>
-#include <linux/module.h>
-
-asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len,
- __le64 hash[NH_NUM_PASSES]);
-
-static int nhpoly1305_neon_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen)
-{
- if (srclen < 64 || !crypto_simd_usable())
- return crypto_nhpoly1305_update(desc, src, srclen);
-
- do {
- unsigned int n = min_t(unsigned int, srclen, SZ_4K);
-
- scoped_ksimd()
- crypto_nhpoly1305_update_helper(desc, src, n, nh_neon);
- src += n;
- srclen -= n;
- } while (srclen);
- return 0;
-}
-
-static int nhpoly1305_neon_digest(struct shash_desc *desc,
- const u8 *src, unsigned int srclen, u8 *out)
-{
- return crypto_nhpoly1305_init(desc) ?:
- nhpoly1305_neon_update(desc, src, srclen) ?:
- crypto_nhpoly1305_final(desc, out);
-}
-
-static struct shash_alg nhpoly1305_alg = {
- .base.cra_name = "nhpoly1305",
- .base.cra_driver_name = "nhpoly1305-neon",
- .base.cra_priority = 200,
- .base.cra_ctxsize = sizeof(struct nhpoly1305_key),
- .base.cra_module = THIS_MODULE,
- .digestsize = POLY1305_DIGEST_SIZE,
- .init = crypto_nhpoly1305_init,
- .update = nhpoly1305_neon_update,
- .final = crypto_nhpoly1305_final,
- .digest = nhpoly1305_neon_digest,
- .setkey = crypto_nhpoly1305_setkey,
- .descsize = sizeof(struct nhpoly1305_state),
-};
-
-static int __init nhpoly1305_mod_init(void)
-{
- if (!cpu_have_named_feature(ASIMD))
- return -ENODEV;
-
- return crypto_register_shash(&nhpoly1305_alg);
-}
-
-static void __exit nhpoly1305_mod_exit(void)
-{
- crypto_unregister_shash(&nhpoly1305_alg);
-}
-
-module_init(nhpoly1305_mod_init);
-module_exit(nhpoly1305_mod_exit);
-
-MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
-MODULE_ALIAS_CRYPTO("nhpoly1305");
-MODULE_ALIAS_CRYPTO("nhpoly1305-neon");
bool
depends on CRYPTO_LIB_NH && !UML
default y if ARM && KERNEL_MODE_NEON
+ default y if ARM64 && KERNEL_MODE_NEON
config CRYPTO_LIB_POLY1305
tristate
ifeq ($(CONFIG_CRYPTO_LIB_NH_ARCH),y)
CFLAGS_nh.o += -I$(src)/$(SRCARCH)
libnh-$(CONFIG_ARM) += arm/nh-neon-core.o
+libnh-$(CONFIG_ARM64) += arm64/nh-neon-core.o
endif
################################################################################
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, ARM64 NEON accelerated version
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+ KEY .req x0
+ MESSAGE .req x1
+ MESSAGE_LEN .req x2
+ HASH .req x3
+
+ PASS0_SUMS .req v0
+ PASS1_SUMS .req v1
+ PASS2_SUMS .req v2
+ PASS3_SUMS .req v3
+ K0 .req v4
+ K1 .req v5
+ K2 .req v6
+ K3 .req v7
+ T0 .req v8
+ T1 .req v9
+ T2 .req v10
+ T3 .req v11
+ T4 .req v12
+ T5 .req v13
+ T6 .req v14
+ T7 .req v15
+
+.macro _nh_stride k0, k1, k2, k3
+
+ // Load next message stride
+ ld1 {T3.16b}, [MESSAGE], #16
+
+ // Load next key stride
+ ld1 {\k3\().4s}, [KEY], #16
+
+ // Add message words to key words
+ add T0.4s, T3.4s, \k0\().4s
+ add T1.4s, T3.4s, \k1\().4s
+ add T2.4s, T3.4s, \k2\().4s
+ add T3.4s, T3.4s, \k3\().4s
+
+ // Multiply 32x32 => 64 and accumulate
+ mov T4.d[0], T0.d[1]
+ mov T5.d[0], T1.d[1]
+ mov T6.d[0], T2.d[1]
+ mov T7.d[0], T3.d[1]
+ umlal PASS0_SUMS.2d, T0.2s, T4.2s
+ umlal PASS1_SUMS.2d, T1.2s, T5.2s
+ umlal PASS2_SUMS.2d, T2.2s, T6.2s
+ umlal PASS3_SUMS.2d, T3.2s, T7.2s
+.endm
+
+/*
+ * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ * __le64 hash[NH_NUM_PASSES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+SYM_FUNC_START(nh_neon)
+
+ ld1 {K0.4s,K1.4s}, [KEY], #32
+ movi PASS0_SUMS.2d, #0
+ movi PASS1_SUMS.2d, #0
+ ld1 {K2.4s}, [KEY], #16
+ movi PASS2_SUMS.2d, #0
+ movi PASS3_SUMS.2d, #0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ blt .Lloop4_done
+.Lloop4:
+ _nh_stride K0, K1, K2, K3
+ _nh_stride K1, K2, K3, K0
+ _nh_stride K2, K3, K0, K1
+ _nh_stride K3, K0, K1, K2
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ bge .Lloop4
+
+.Lloop4_done:
+ ands MESSAGE_LEN, MESSAGE_LEN, #63
+ beq .Ldone
+ _nh_stride K0, K1, K2, K3
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K1, K2, K3, K0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K2, K3, K0, K1
+
+.Ldone:
+ // Sum the accumulators for each pass, then store the sums to 'hash'
+ addp T0.2d, PASS0_SUMS.2d, PASS1_SUMS.2d
+ addp T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d
+ st1 {T0.16b,T1.16b}, [HASH]
+ ret
+SYM_FUNC_END(nh_neon)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM64 accelerated implementation of NH
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <asm/hwcap.h>
+#include <asm/simd.h>
+#include <linux/cpufeature.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ __le64 hash[NH_NUM_PASSES]);
+
+static bool nh_arch(const u32 *key, const u8 *message, size_t message_len,
+ __le64 hash[NH_NUM_PASSES])
+{
+ if (static_branch_likely(&have_neon) && message_len >= 64 &&
+ may_use_simd()) {
+ scoped_ksimd()
+ nh_neon(key, message, message_len, hash);
+ return true;
+ }
+ return false;
+}
+
+#define nh_mod_init_arch nh_mod_init_arch
+static void nh_mod_init_arch(void)
+{
+ if (cpu_have_named_feature(ASIMD))
+ static_branch_enable(&have_neon);
+}
projects / linux-2.6-microblaze.git / commitdiff