crypto: arm - add support for SHA-224/256 using ARMv8 Crypto Extensions
This implements the SHA-224/256 secure hash algorithm using the AArch32
versions of the ARMv8 Crypto Extensions for SHA2.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index d7bc10b..9c1478e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -37,6 +37,15 @@
SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
using special ARMv8 Crypto Extensions.
+config CRYPTO_SHA2_ARM_CE
+ tristate "SHA-224/256 digest algorithm (ARM v8 Crypto Extensions)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_SHA256
+ select CRYPTO_HASH
+ help
+ SHA-256 secure hash standard (DFIPS 180-2) implemented
+ using special ARMv8 Crypto Extensions.
+
config CRYPTO_SHA512_ARM_NEON
tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
depends on KERNEL_MODE_NEON
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index d92d05b..4ea9f96 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -8,6 +8,7 @@
obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
+obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
aes-arm-y := aes-armv4.o aes_glue.o
aes-arm-bs-y := aesbs-core.o aesbs-glue.o
@@ -15,6 +16,7 @@
sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o
sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o
+sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)
diff --git a/arch/arm/crypto/sha2-ce-core.S b/arch/arm/crypto/sha2-ce-core.S
new file mode 100644
index 0000000..96af09f
--- /dev/null
+++ b/arch/arm/crypto/sha2-ce-core.S
@@ -0,0 +1,134 @@
+/*
+ * sha2-ce-core.S - SHA-224/256 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@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
+ .fpu crypto-neon-fp-armv8
+
+ k0 .req q7
+ k1 .req q8
+ rk .req r3
+
+ ta0 .req q9
+ ta1 .req q10
+ tb0 .req q10
+ tb1 .req q9
+
+ dga .req q11
+ dgb .req q12
+
+ dg0 .req q13
+ dg1 .req q14
+ dg2 .req q15
+
+ .macro add_only, ev, s0
+ vmov dg2, dg0
+ .ifnb \s0
+ vld1.32 {k\ev}, [rk, :128]!
+ .endif
+ sha256h.32 dg0, dg1, tb\ev
+ sha256h2.32 dg1, dg2, tb\ev
+ .ifnb \s0
+ vadd.u32 ta\ev, q\s0, k\ev
+ .endif
+ .endm
+
+ .macro add_update, ev, s0, s1, s2, s3
+ sha256su0.32 q\s0, q\s1
+ add_only \ev, \s1
+ sha256su1.32 q\s0, q\s2, q\s3
+ .endm
+
+ .align 6
+.Lsha256_rcon:
+ .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+ .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+ .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+ .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+ .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+ .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+ .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+ .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+ .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+ .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+ .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+ .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+ .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+ .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+ .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+ .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+ /*
+ * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+ * u8 *head);
+ */
+ENTRY(sha2_ce_transform)
+ /* load state */
+ vld1.32 {dga-dgb}, [r2]
+
+ /* load partial input (if supplied) */
+ teq r3, #0
+ beq 0f
+ vld1.32 {q0-q1}, [r3]!
+ vld1.32 {q2-q3}, [r3]
+ teq r0, #0
+ b 1f
+
+ /* load input */
+0: vld1.32 {q0-q1}, [r1]!
+ vld1.32 {q2-q3}, [r1]!
+ subs r0, r0, #1
+
+1:
+#ifndef CONFIG_CPU_BIG_ENDIAN
+ vrev32.8 q0, q0
+ vrev32.8 q1, q1
+ vrev32.8 q2, q2
+ vrev32.8 q3, q3
+#endif
+
+ /* load first round constant */
+ adr rk, .Lsha256_rcon
+ vld1.32 {k0}, [rk, :128]!
+
+ vadd.u32 ta0, q0, k0
+ vmov dg0, dga
+ vmov dg1, dgb
+
+ add_update 1, 0, 1, 2, 3
+ add_update 0, 1, 2, 3, 0
+ add_update 1, 2, 3, 0, 1
+ add_update 0, 3, 0, 1, 2
+ add_update 1, 0, 1, 2, 3
+ add_update 0, 1, 2, 3, 0
+ add_update 1, 2, 3, 0, 1
+ add_update 0, 3, 0, 1, 2
+ add_update 1, 0, 1, 2, 3
+ add_update 0, 1, 2, 3, 0
+ add_update 1, 2, 3, 0, 1
+ add_update 0, 3, 0, 1, 2
+
+ add_only 1, 1
+ add_only 0, 2
+ add_only 1, 3
+ add_only 0
+
+ /* update state */
+ vadd.u32 dga, dga, dg0
+ vadd.u32 dgb, dgb, dg1
+ bne 0b
+
+ /* store new state */
+ vst1.32 {dga-dgb}, [r2]
+ bx lr
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
new file mode 100644
index 0000000..9ffe8ad
--- /dev/null
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -0,0 +1,203 @@
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@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 <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+ u8 *head);
+
+static int sha224_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha256_state){
+ .state = {
+ SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
+ SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
+ }
+ };
+ return 0;
+}
+
+static int sha256_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha256_state){
+ .state = {
+ SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+ SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
+ }
+ };
+ return 0;
+}
+
+static int sha2_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial;
+
+ if (!may_use_simd())
+ return crypto_sha256_update(desc, data, len);
+
+ partial = sctx->count % SHA256_BLOCK_SIZE;
+ sctx->count += len;
+
+ if ((partial + len) >= SHA256_BLOCK_SIZE) {
+ int blocks;
+
+ if (partial) {
+ int p = SHA256_BLOCK_SIZE - partial;
+
+ memcpy(sctx->buf + partial, data, p);
+ data += p;
+ len -= p;
+ }
+
+ blocks = len / SHA256_BLOCK_SIZE;
+ len %= SHA256_BLOCK_SIZE;
+
+ kernel_neon_begin();
+ sha2_ce_transform(blocks, data, sctx->state,
+ partial ? sctx->buf : NULL);
+ kernel_neon_end();
+
+ data += blocks * SHA256_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(sctx->buf + partial, data, len);
+ return 0;
+}
+
+static void sha2_final(struct shash_desc *desc)
+{
+ static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be64 bits = cpu_to_be64(sctx->count << 3);
+ u32 padlen = SHA256_BLOCK_SIZE
+ - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
+
+ sha2_update(desc, padding, padlen);
+ sha2_update(desc, (const u8 *)&bits, sizeof(bits));
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_final(desc);
+
+ for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_final(desc);
+
+ for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha2_export(struct shash_desc *desc, void *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ struct sha256_state *dst = out;
+
+ *dst = *sctx;
+ return 0;
+}
+
+static int sha2_import(struct shash_desc *desc, const void *in)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ struct sha256_state const *src = in;
+
+ *sctx = *src;
+ return 0;
+}
+
+static struct shash_alg algs[] = { {
+ .init = sha224_init,
+ .update = sha2_update,
+ .final = sha224_final,
+ .export = sha2_export,
+ .import = sha2_import,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA224_DIGEST_SIZE,
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .init = sha256_init,
+ .update = sha2_update,
+ .final = sha256_final,
+ .export = sha2_export,
+ .import = sha2_import,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA256_DIGEST_SIZE,
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+ if (!(elf_hwcap2 & HWCAP2_SHA2))
+ return -ENODEV;
+ return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_init(sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);