[PATCH v3 1/7] arm64/crypto: SHA-1 using ARMv8 Crypto Extensions
Ard Biesheuvel
ard.biesheuvel at linaro.org
Tue Apr 1 06:47:33 PDT 2014
This patch adds support for the SHA-1 Secure Hash Algorithm for CPUs that
have support for the SHA-1 part of the ARM v8 Crypto Extensions.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel at linaro.org>
---
arch/arm64/Kconfig | 3 +
arch/arm64/Makefile | 1 +
arch/arm64/crypto/Kconfig | 16 ++++
arch/arm64/crypto/Makefile | 12 +++
arch/arm64/crypto/sha1-ce-core.S | 153 ++++++++++++++++++++++++++++++++++
arch/arm64/crypto/sha1-ce-glue.c | 174 +++++++++++++++++++++++++++++++++++++++
6 files changed, 359 insertions(+)
create mode 100644 arch/arm64/crypto/Kconfig
create mode 100644 arch/arm64/crypto/Makefile
create mode 100644 arch/arm64/crypto/sha1-ce-core.S
create mode 100644 arch/arm64/crypto/sha1-ce-glue.c
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3d27a1c4e4ad..11f366a6f09d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -317,5 +317,8 @@ source "arch/arm64/Kconfig.debug"
source "security/Kconfig"
source "crypto/Kconfig"
+if CRYPTO
+source "arch/arm64/crypto/Kconfig"
+endif
source "lib/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index e0b75464b7f1..a4b3e253557d 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -46,6 +46,7 @@ core-y += arch/arm64/emu/
core-y += arch/arm64/kernel/ arch/arm64/mm/
core-$(CONFIG_KVM) += arch/arm64/kvm/
core-$(CONFIG_XEN) += arch/arm64/xen/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
libs-y := arch/arm64/lib/ $(libs-y)
libs-y += $(LIBGCC)
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 000000000000..7956881b5986
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,16 @@
+
+menuconfig ARM64_CRYPTO
+ bool "ARM64 Accelerated Cryptographic Algorithms"
+ depends on ARM64
+ help
+ Say Y here to choose from a selection of cryptographic algorithms
+ implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA1_ARM64_CE
+ tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 000000000000..0ed3caaec81b
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,12 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel at linaro.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 000000000000..bd4af29f2722
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,153 @@
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel at linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ k0 .req v0
+ k1 .req v1
+ k2 .req v2
+ k3 .req v3
+
+ t0 .req v4
+ t1 .req v5
+
+ dga .req q6
+ dgav .req v6
+ dgb .req s7
+ dgbv .req v7
+
+ dg0q .req q12
+ dg0s .req s12
+ dg0v .req v12
+ dg1s .req s13
+ dg1v .req v13
+ dg2s .req s14
+
+ .macro add_only, op, ev, rc, s0, dg1
+ .ifc \ev, ev
+ add t1.4s, v\s0\().4s, \rc\().4s
+ sha1h dg2s, dg0s
+ .ifnb \dg1
+ sha1\op dg0q, \dg1, t0.4s
+ .else
+ sha1\op dg0q, dg1s, t0.4s
+ .endif
+ .else
+ .ifnb \s0
+ add t0.4s, v\s0\().4s, \rc\().4s
+ .endif
+ sha1h dg1s, dg0s
+ sha1\op dg0q, dg2s, t1.4s
+ .endif
+ .endm
+
+ .macro add_update, op, ev, rc, s0, s1, s2, s3, dg1
+ sha1su0 v\s0\().4s, v\s1\().4s, v\s2\().4s
+ sha1su1 v\s0\().4s, v\s3\().4s
+ add_only \op, \ev, \rc, \s1, \dg1
+ .endm
+
+ /*
+ * The SHA1 round constants
+ */
+ .align 4
+.Lsha1_rcon:
+ .word 0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+
+ /*
+ * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+ * u8 *head, long bytes)
+ */
+ENTRY(sha1_ce_transform)
+ /* load round constants */
+ adr x6, .Lsha1_rcon
+ ld1r {k0.4s}, [x6], #4
+ ld1r {k1.4s}, [x6], #4
+ ld1r {k2.4s}, [x6], #4
+ ld1r {k3.4s}, [x6]
+
+ /* load state */
+ ldr dga, [x2]
+ ldr dgb, [x2, #16]
+
+ /* load partial state (if supplied) */
+ cbz x3, 0f
+ ld1 {v8.4s-v11.4s}, [x3]
+ b 1f
+
+ /* load input */
+0: ld1 {v8.4s-v11.4s}, [x1], #64
+ sub w0, w0, #1
+
+1:
+CPU_LE( rev32 v8.16b, v8.16b )
+CPU_LE( rev32 v9.16b, v9.16b )
+CPU_LE( rev32 v10.16b, v10.16b )
+CPU_LE( rev32 v11.16b, v11.16b )
+
+2: add t0.4s, v8.4s, k0.4s
+ mov dg0v.16b, dgav.16b
+
+ add_update c, ev, k0, 8, 9, 10, 11, dgb
+ add_update c, od, k0, 9, 10, 11, 8
+ add_update c, ev, k0, 10, 11, 8, 9
+ add_update c, od, k0, 11, 8, 9, 10
+ add_update c, ev, k1, 8, 9, 10, 11
+
+ add_update p, od, k1, 9, 10, 11, 8
+ add_update p, ev, k1, 10, 11, 8, 9
+ add_update p, od, k1, 11, 8, 9, 10
+ add_update p, ev, k1, 8, 9, 10, 11
+ add_update p, od, k2, 9, 10, 11, 8
+
+ add_update m, ev, k2, 10, 11, 8, 9
+ add_update m, od, k2, 11, 8, 9, 10
+ add_update m, ev, k2, 8, 9, 10, 11
+ add_update m, od, k2, 9, 10, 11, 8
+ add_update m, ev, k3, 10, 11, 8, 9
+
+ add_update p, od, k3, 11, 8, 9, 10
+ add_only p, ev, k3, 9
+ add_only p, od, k3, 10
+ add_only p, ev, k3, 11
+ add_only p, od
+
+ /* update state */
+ add dgbv.2s, dgbv.2s, dg1v.2s
+ add dgav.4s, dgav.4s, dg0v.4s
+
+ cbnz w0, 0b
+
+ /*
+ * Final block: add padding and total bit count.
+ * Skip if we have no total byte count in x4. In that case, the input
+ * size was not a round multiple of the block size, and the padding is
+ * handled by the C code.
+ */
+ cbz x4, 3f
+ movi v9.2d, #0
+ mov x8, #0x80000000
+ movi v10.2d, #0
+ ror x7, x4, #29 // ror(lsl(x4, 3), 32)
+ fmov d8, x8
+ mov x4, #0
+ mov v11.d[0], xzr
+ mov v11.d[1], x7
+ b 2b
+
+ /* store new state */
+3: str dga, [x2]
+ str dgb, [x2, #16]
+ ret
+ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 000000000000..6fe83f37a750
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,174 @@
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel at linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel at linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+ u8 *head, long bytes);
+
+static int sha1_init(struct shash_desc *desc)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha1_state){
+ .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+ };
+ return 0;
+}
+
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+
+ sctx->count += len;
+
+ if ((partial + len) >= SHA1_BLOCK_SIZE) {
+ int blocks;
+
+ if (partial) {
+ int p = SHA1_BLOCK_SIZE - partial;
+
+ memcpy(sctx->buffer + partial, data, p);
+ data += p;
+ len -= p;
+ }
+
+ blocks = len / SHA1_BLOCK_SIZE;
+ len %= SHA1_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(16);
+ sha1_ce_transform(blocks, data, sctx->state,
+ partial ? sctx->buffer : NULL, 0);
+ kernel_neon_end();
+
+ data += blocks * SHA1_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(sctx->buffer + partial, data, len);
+ return 0;
+}
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+ static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ __be64 bits = cpu_to_be64(sctx->count << 3);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ u32 padlen = SHA1_BLOCK_SIZE
+ - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
+
+ sha1_update(desc, padding, padlen);
+ sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+
+ for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha1_state){};
+ return 0;
+}
+
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int blocks;
+ int i;
+
+ if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
+ sha1_update(desc, data, len);
+ return sha1_final(desc, out);
+ }
+
+ /*
+ * Use a fast path if the input is a multiple of 64 bytes. In
+ * this case, there is no need to copy data around, and we can
+ * perform the entire digest calculation in a single invocation
+ * of sha1_ce_transform()
+ */
+ blocks = len / SHA1_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(16);
+ sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+ kernel_neon_end();
+
+ for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha1_state){};
+ return 0;
+}
+
+static int sha1_export(struct shash_desc *desc, void *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ struct sha1_state *dst = out;
+
+ *dst = *sctx;
+ return 0;
+}
+
+static int sha1_import(struct shash_desc *desc, const void *in)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ struct sha1_state const *src = in;
+
+ *sctx = *src;
+ return 0;
+}
+
+static struct shash_alg alg = {
+ .init = sha1_init,
+ .update = sha1_update,
+ .final = sha1_final,
+ .finup = sha1_finup,
+ .export = sha1_export,
+ .import = sha1_import,
+ .descsize = sizeof(struct sha1_state),
+ .digestsize = SHA1_DIGEST_SIZE,
+ .statesize = sizeof(struct sha1_state),
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+ return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
--
1.8.3.2
More information about the linux-arm-kernel
mailing list