that is part of the ARMv8 Crypto Extensions, or a slower variant that
uses the vmull.p8 instruction that is part of the basic NEON ISA.
-config CRYPTO_NHPOLY1305_NEON
- tristate "Hash functions: NHPoly1305 (NEON)"
- depends on KERNEL_MODE_NEON
- select CRYPTO_NHPOLY1305
- help
- NHPoly1305 hash function (Adiantum)
-
- Architecture: arm using:
- - NEON (Advanced SIMD) extensions
-
config CRYPTO_AES_ARM
tristate "Ciphers: AES"
select CRYPTO_ALGAPI
obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
-obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
aes-arm-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o
ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o
-nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * NH - ε-almost-universal hash function, NEON accelerated version
- *
- * Copyright 2018 Google LLC
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-
-#include <linux/linkage.h>
-
- .text
- .fpu neon
-
- KEY .req r0
- MESSAGE .req r1
- MESSAGE_LEN .req r2
- HASH .req r3
-
- PASS0_SUMS .req q0
- PASS0_SUM_A .req d0
- PASS0_SUM_B .req d1
- PASS1_SUMS .req q1
- PASS1_SUM_A .req d2
- PASS1_SUM_B .req d3
- PASS2_SUMS .req q2
- PASS2_SUM_A .req d4
- PASS2_SUM_B .req d5
- PASS3_SUMS .req q3
- PASS3_SUM_A .req d6
- PASS3_SUM_B .req d7
- K0 .req q4
- K1 .req q5
- K2 .req q6
- K3 .req q7
- T0 .req q8
- T0_L .req d16
- T0_H .req d17
- T1 .req q9
- T1_L .req d18
- T1_H .req d19
- T2 .req q10
- T2_L .req d20
- T2_H .req d21
- T3 .req q11
- T3_L .req d22
- T3_H .req d23
-
-.macro _nh_stride k0, k1, k2, k3
-
- // Load next message stride
- vld1.8 {T3}, [MESSAGE]!
-
- // Load next key stride
- vld1.32 {\k3}, [KEY]!
-
- // Add message words to key words
- vadd.u32 T0, T3, \k0
- vadd.u32 T1, T3, \k1
- vadd.u32 T2, T3, \k2
- vadd.u32 T3, T3, \k3
-
- // Multiply 32x32 => 64 and accumulate
- vmlal.u32 PASS0_SUMS, T0_L, T0_H
- vmlal.u32 PASS1_SUMS, T1_L, T1_H
- vmlal.u32 PASS2_SUMS, T2_L, T2_H
- vmlal.u32 PASS3_SUMS, T3_L, T3_H
-.endm
-
-/*
- * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
- * __le64 hash[NH_NUM_PASSES])
- *
- * It's guaranteed that message_len % 16 == 0.
- */
-ENTRY(nh_neon)
-
- vld1.32 {K0,K1}, [KEY]!
- vmov.u64 PASS0_SUMS, #0
- vmov.u64 PASS1_SUMS, #0
- vld1.32 {K2}, [KEY]!
- vmov.u64 PASS2_SUMS, #0
- vmov.u64 PASS3_SUMS, #0
-
- subs MESSAGE_LEN, MESSAGE_LEN, #64
- blt .Lloop4_done
-.Lloop4:
- _nh_stride K0, K1, K2, K3
- _nh_stride K1, K2, K3, K0
- _nh_stride K2, K3, K0, K1
- _nh_stride K3, K0, K1, K2
- subs MESSAGE_LEN, MESSAGE_LEN, #64
- bge .Lloop4
-
-.Lloop4_done:
- ands MESSAGE_LEN, MESSAGE_LEN, #63
- beq .Ldone
- _nh_stride K0, K1, K2, K3
-
- subs MESSAGE_LEN, MESSAGE_LEN, #16
- beq .Ldone
- _nh_stride K1, K2, K3, K0
-
- subs MESSAGE_LEN, MESSAGE_LEN, #16
- beq .Ldone
- _nh_stride K2, K3, K0, K1
-
-.Ldone:
- // Sum the accumulators for each pass, then store the sums to 'hash'
- vadd.u64 T0_L, PASS0_SUM_A, PASS0_SUM_B
- vadd.u64 T0_H, PASS1_SUM_A, PASS1_SUM_B
- vadd.u64 T1_L, PASS2_SUM_A, PASS2_SUM_B
- vadd.u64 T1_H, PASS3_SUM_A, PASS3_SUM_B
- vst1.8 {T0-T1}, [HASH]
- bx lr
-ENDPROC(nh_neon)
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
- * (NEON accelerated version)
- *
- * Copyright 2018 Google LLC
- */
-
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/nhpoly1305.h>
-#include <linux/module.h>
-
-asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len,
- __le64 hash[NH_NUM_PASSES]);
-
-static int nhpoly1305_neon_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen)
-{
- if (srclen < 64 || !crypto_simd_usable())
- return crypto_nhpoly1305_update(desc, src, srclen);
-
- do {
- unsigned int n = min_t(unsigned int, srclen, SZ_4K);
-
- kernel_neon_begin();
- crypto_nhpoly1305_update_helper(desc, src, n, nh_neon);
- kernel_neon_end();
- src += n;
- srclen -= n;
- } while (srclen);
- return 0;
-}
-
-static 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 (!(elf_hwcap & HWCAP_NEON))
- return -ENODEV;
-
- return crypto_register_shash(&nhpoly1305_alg);
-}
-
-static void __exit nhpoly1305_mod_exit(void)
-{
- crypto_unregister_shash(&nhpoly1305_alg);
-}
-
-module_init(nhpoly1305_mod_init);
-module_exit(nhpoly1305_mod_exit);
-
-MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
-MODULE_ALIAS_CRYPTO("nhpoly1305");
-MODULE_ALIAS_CRYPTO("nhpoly1305-neon");
config CRYPTO_LIB_NH_ARCH
bool
depends on CRYPTO_LIB_NH && !UML
+ default y if ARM && KERNEL_MODE_NEON
config CRYPTO_LIB_POLY1305
tristate
libnh-y := nh.o
ifeq ($(CONFIG_CRYPTO_LIB_NH_ARCH),y)
CFLAGS_nh.o += -I$(src)/$(SRCARCH)
+libnh-$(CONFIG_ARM) += arm/nh-neon-core.o
endif
################################################################################
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, NEON accelerated version
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .fpu neon
+
+ KEY .req r0
+ MESSAGE .req r1
+ MESSAGE_LEN .req r2
+ HASH .req r3
+
+ PASS0_SUMS .req q0
+ PASS0_SUM_A .req d0
+ PASS0_SUM_B .req d1
+ PASS1_SUMS .req q1
+ PASS1_SUM_A .req d2
+ PASS1_SUM_B .req d3
+ PASS2_SUMS .req q2
+ PASS2_SUM_A .req d4
+ PASS2_SUM_B .req d5
+ PASS3_SUMS .req q3
+ PASS3_SUM_A .req d6
+ PASS3_SUM_B .req d7
+ K0 .req q4
+ K1 .req q5
+ K2 .req q6
+ K3 .req q7
+ T0 .req q8
+ T0_L .req d16
+ T0_H .req d17
+ T1 .req q9
+ T1_L .req d18
+ T1_H .req d19
+ T2 .req q10
+ T2_L .req d20
+ T2_H .req d21
+ T3 .req q11
+ T3_L .req d22
+ T3_H .req d23
+
+.macro _nh_stride k0, k1, k2, k3
+
+ // Load next message stride
+ vld1.8 {T3}, [MESSAGE]!
+
+ // Load next key stride
+ vld1.32 {\k3}, [KEY]!
+
+ // Add message words to key words
+ vadd.u32 T0, T3, \k0
+ vadd.u32 T1, T3, \k1
+ vadd.u32 T2, T3, \k2
+ vadd.u32 T3, T3, \k3
+
+ // Multiply 32x32 => 64 and accumulate
+ vmlal.u32 PASS0_SUMS, T0_L, T0_H
+ vmlal.u32 PASS1_SUMS, T1_L, T1_H
+ vmlal.u32 PASS2_SUMS, T2_L, T2_H
+ vmlal.u32 PASS3_SUMS, T3_L, T3_H
+.endm
+
+/*
+ * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ * __le64 hash[NH_NUM_PASSES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+ENTRY(nh_neon)
+
+ vld1.32 {K0,K1}, [KEY]!
+ vmov.u64 PASS0_SUMS, #0
+ vmov.u64 PASS1_SUMS, #0
+ vld1.32 {K2}, [KEY]!
+ vmov.u64 PASS2_SUMS, #0
+ vmov.u64 PASS3_SUMS, #0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ blt .Lloop4_done
+.Lloop4:
+ _nh_stride K0, K1, K2, K3
+ _nh_stride K1, K2, K3, K0
+ _nh_stride K2, K3, K0, K1
+ _nh_stride K3, K0, K1, K2
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ bge .Lloop4
+
+.Lloop4_done:
+ ands MESSAGE_LEN, MESSAGE_LEN, #63
+ beq .Ldone
+ _nh_stride K0, K1, K2, K3
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K1, K2, K3, K0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K2, K3, K0, K1
+
+.Ldone:
+ // Sum the accumulators for each pass, then store the sums to 'hash'
+ vadd.u64 T0_L, PASS0_SUM_A, PASS0_SUM_B
+ vadd.u64 T0_H, PASS1_SUM_A, PASS1_SUM_B
+ vadd.u64 T1_L, PASS2_SUM_A, PASS2_SUM_B
+ vadd.u64 T1_H, PASS3_SUM_A, PASS3_SUM_B
+ vst1.8 {T0-T1}, [HASH]
+ bx lr
+ENDPROC(nh_neon)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM32 accelerated implementation of NH
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.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 (elf_hwcap & HWCAP_NEON)
+ static_branch_enable(&have_neon);
+}
projects / linux-2.6-microblaze.git / commitdiff