Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Glue code for SHA-1 implementation for SPE instructions (PPC) * * Based on generic implementation. * * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de> */ #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <crypto/sha1.h> #include <crypto/sha1_base.h> #include <asm/byteorder.h> #include <asm/switch_to.h> #include <linux/hardirq.h> /* * MAX_BYTES defines the number of bytes that are allowed to be processed * between preempt_disable() and preempt_enable(). SHA1 takes ~1000 * operations per 64 bytes. e500 cores can issue two arithmetic instructions * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2). * Thus 2KB of input data will need an estimated maximum of 18,000 cycles. * Headroom for cache misses included. Even with the low end model clocked * at 667 MHz this equals to a critical time window of less than 27us. * */ #define MAX_BYTES 2048 extern void ppc_spe_sha1_transform(u32 *state, const u8 *src, u32 blocks); static void spe_begin(void) { /* We just start SPE operations and will save SPE registers later. */ preempt_disable(); enable_kernel_spe(); } static void spe_end(void) { disable_kernel_spe(); /* reenable preemption */ preempt_enable(); } static inline void ppc_sha1_clear_context(struct sha1_state *sctx) { int count = sizeof(struct sha1_state) >> 2; u32 *ptr = (u32 *)sctx; /* make sure we can clear the fast way */ BUILD_BUG_ON(sizeof(struct sha1_state) % 4); do { *ptr++ = 0; } while (--count); } static int ppc_spe_sha1_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct sha1_state *sctx = shash_desc_ctx(desc); const unsigned int offset = sctx->count & 0x3f; const unsigned int avail = 64 - offset; unsigned int bytes; const u8 *src = data; if (avail > len) { sctx->count += len; memcpy((char *)sctx->buffer + offset, src, len); return 0; } sctx->count += len; if (offset) { memcpy((char *)sctx->buffer + offset, src, avail); spe_begin(); ppc_spe_sha1_transform(sctx->state, (const u8 *)sctx->buffer, 1); spe_end(); len -= avail; src += avail; } while (len > 63) { bytes = (len > MAX_BYTES) ? MAX_BYTES : len; bytes = bytes & ~0x3f; spe_begin(); ppc_spe_sha1_transform(sctx->state, src, bytes >> 6); spe_end(); src += bytes; len -= bytes; } memcpy((char *)sctx->buffer, src, len); return 0; } static int ppc_spe_sha1_final(struct shash_desc *desc, u8 *out) { struct sha1_state *sctx = shash_desc_ctx(desc); const unsigned int offset = sctx->count & 0x3f; char *p = (char *)sctx->buffer + offset; int padlen; __be64 *pbits = (__be64 *)(((char *)&sctx->buffer) + 56); __be32 *dst = (__be32 *)out; padlen = 55 - offset; *p++ = 0x80; spe_begin(); if (padlen < 0) { memset(p, 0x00, padlen + sizeof (u64)); ppc_spe_sha1_transform(sctx->state, sctx->buffer, 1); p = (char *)sctx->buffer; padlen = 56; } memset(p, 0, padlen); *pbits = cpu_to_be64(sctx->count << 3); ppc_spe_sha1_transform(sctx->state, sctx->buffer, 1); spe_end(); dst[0] = cpu_to_be32(sctx->state[0]); dst[1] = cpu_to_be32(sctx->state[1]); dst[2] = cpu_to_be32(sctx->state[2]); dst[3] = cpu_to_be32(sctx->state[3]); dst[4] = cpu_to_be32(sctx->state[4]); ppc_sha1_clear_context(sctx); return 0; } static int ppc_spe_sha1_export(struct shash_desc *desc, void *out) { struct sha1_state *sctx = shash_desc_ctx(desc); memcpy(out, sctx, sizeof(*sctx)); return 0; } static int ppc_spe_sha1_import(struct shash_desc *desc, const void *in) { struct sha1_state *sctx = shash_desc_ctx(desc); memcpy(sctx, in, sizeof(*sctx)); return 0; } static struct shash_alg alg = { .digestsize = SHA1_DIGEST_SIZE, .init = sha1_base_init, .update = ppc_spe_sha1_update, .final = ppc_spe_sha1_final, .export = ppc_spe_sha1_export, .import = ppc_spe_sha1_import, .descsize = sizeof(struct sha1_state), .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name= "sha1-ppc-spe", .cra_priority = 300, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, } }; static int __init ppc_spe_sha1_mod_init(void) { return crypto_register_shash(&alg); } static void __exit ppc_spe_sha1_mod_fini(void) { crypto_unregister_shash(&alg); } module_init(ppc_spe_sha1_mod_init); module_exit(ppc_spe_sha1_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, SPE optimized"); MODULE_ALIAS_CRYPTO("sha1"); MODULE_ALIAS_CRYPTO("sha1-ppc-spe"); |