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
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
|
// SPDX-License-Identifier: GPL-2.0-only
/**
* SHA-256 routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
*
* Author: Kent Yoder <yoder1@us.ibm.com>
*/
#include <crypto/internal/hash.h>
#include <crypto/sha.h>
#include <linux/module.h>
#include <asm/vio.h>
#include <asm/byteorder.h>
#include "nx_csbcpb.h"
#include "nx.h"
static int nx_crypto_ctx_sha256_init(struct crypto_tfm *tfm)
{
struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
int err;
err = nx_crypto_ctx_sha_init(tfm);
if (err)
return err;
nx_ctx_init(nx_ctx, HCOP_FC_SHA);
nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA256];
NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA256);
return 0;
}
static int nx_sha256_init(struct shash_desc *desc) {
struct sha256_state *sctx = shash_desc_ctx(desc);
memset(sctx, 0, sizeof *sctx);
sctx->state[0] = __cpu_to_be32(SHA256_H0);
sctx->state[1] = __cpu_to_be32(SHA256_H1);
sctx->state[2] = __cpu_to_be32(SHA256_H2);
sctx->state[3] = __cpu_to_be32(SHA256_H3);
sctx->state[4] = __cpu_to_be32(SHA256_H4);
sctx->state[5] = __cpu_to_be32(SHA256_H5);
sctx->state[6] = __cpu_to_be32(SHA256_H6);
sctx->state[7] = __cpu_to_be32(SHA256_H7);
sctx->count = 0;
return 0;
}
static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
struct nx_sg *out_sg;
u64 to_process = 0, leftover, total;
unsigned long irq_flags;
int rc = 0;
int data_len;
u32 max_sg_len;
u64 buf_len = (sctx->count % SHA256_BLOCK_SIZE);
spin_lock_irqsave(&nx_ctx->lock, irq_flags);
/* 2 cases for total data len:
* 1: < SHA256_BLOCK_SIZE: copy into state, return 0
* 2: >= SHA256_BLOCK_SIZE: process X blocks, copy in leftover
*/
total = (sctx->count % SHA256_BLOCK_SIZE) + len;
if (total < SHA256_BLOCK_SIZE) {
memcpy(sctx->buf + buf_len, data, len);
sctx->count += len;
goto out;
}
memcpy(csbcpb->cpb.sha256.message_digest, sctx->state, SHA256_DIGEST_SIZE);
NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
max_sg_len = min_t(u64, nx_ctx->ap->sglen,
nx_driver.of.max_sg_len/sizeof(struct nx_sg));
max_sg_len = min_t(u64, max_sg_len,
nx_ctx->ap->databytelen/NX_PAGE_SIZE);
data_len = SHA256_DIGEST_SIZE;
out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
&data_len, max_sg_len);
nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
if (data_len != SHA256_DIGEST_SIZE) {
rc = -EINVAL;
goto out;
}
do {
int used_sgs = 0;
struct nx_sg *in_sg = nx_ctx->in_sg;
if (buf_len) {
data_len = buf_len;
in_sg = nx_build_sg_list(in_sg,
(u8 *) sctx->buf,
&data_len,
max_sg_len);
if (data_len != buf_len) {
rc = -EINVAL;
goto out;
}
used_sgs = in_sg - nx_ctx->in_sg;
}
/* to_process: SHA256_BLOCK_SIZE aligned chunk to be
* processed in this iteration. This value is restricted
* by sg list limits and number of sgs we already used
* for leftover data. (see above)
* In ideal case, we could allow NX_PAGE_SIZE * max_sg_len,
* but because data may not be aligned, we need to account
* for that too. */
to_process = min_t(u64, total,
(max_sg_len - 1 - used_sgs) * NX_PAGE_SIZE);
to_process = to_process & ~(SHA256_BLOCK_SIZE - 1);
data_len = to_process - buf_len;
in_sg = nx_build_sg_list(in_sg, (u8 *) data,
&data_len, max_sg_len);
nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
to_process = data_len + buf_len;
leftover = total - to_process;
/*
* we've hit the nx chip previously and we're updating
* again, so copy over the partial digest.
*/
memcpy(csbcpb->cpb.sha256.input_partial_digest,
csbcpb->cpb.sha256.message_digest,
SHA256_DIGEST_SIZE);
if (!nx_ctx->op.inlen || !nx_ctx->op.outlen) {
rc = -EINVAL;
goto out;
}
rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
if (rc)
goto out;
atomic_inc(&(nx_ctx->stats->sha256_ops));
total -= to_process;
data += to_process - buf_len;
buf_len = 0;
} while (leftover >= SHA256_BLOCK_SIZE);
/* copy the leftover back into the state struct */
if (leftover)
memcpy(sctx->buf, data, leftover);
sctx->count += len;
memcpy(sctx->state, csbcpb->cpb.sha256.message_digest, SHA256_DIGEST_SIZE);
out:
spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
return rc;
}
static int nx_sha256_final(struct shash_desc *desc, u8 *out)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
struct nx_sg *in_sg, *out_sg;
unsigned long irq_flags;
u32 max_sg_len;
int rc = 0;
int len;
spin_lock_irqsave(&nx_ctx->lock, irq_flags);
max_sg_len = min_t(u64, nx_ctx->ap->sglen,
nx_driver.of.max_sg_len/sizeof(struct nx_sg));
max_sg_len = min_t(u64, max_sg_len,
nx_ctx->ap->databytelen/NX_PAGE_SIZE);
/* final is represented by continuing the operation and indicating that
* this is not an intermediate operation */
if (sctx->count >= SHA256_BLOCK_SIZE) {
/* we've hit the nx chip previously, now we're finalizing,
* so copy over the partial digest */
memcpy(csbcpb->cpb.sha256.input_partial_digest, sctx->state, SHA256_DIGEST_SIZE);
NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
} else {
NX_CPB_FDM(csbcpb) &= ~NX_FDM_INTERMEDIATE;
NX_CPB_FDM(csbcpb) &= ~NX_FDM_CONTINUATION;
}
csbcpb->cpb.sha256.message_bit_length = (u64) (sctx->count * 8);
len = sctx->count & (SHA256_BLOCK_SIZE - 1);
in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) sctx->buf,
&len, max_sg_len);
if (len != (sctx->count & (SHA256_BLOCK_SIZE - 1))) {
rc = -EINVAL;
goto out;
}
len = SHA256_DIGEST_SIZE;
out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len, max_sg_len);
if (len != SHA256_DIGEST_SIZE) {
rc = -EINVAL;
goto out;
}
nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
if (!nx_ctx->op.outlen) {
rc = -EINVAL;
goto out;
}
rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
if (rc)
goto out;
atomic_inc(&(nx_ctx->stats->sha256_ops));
atomic64_add(sctx->count, &(nx_ctx->stats->sha256_bytes));
memcpy(out, csbcpb->cpb.sha256.message_digest, SHA256_DIGEST_SIZE);
out:
spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
return rc;
}
static int nx_sha256_export(struct shash_desc *desc, void *out)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
memcpy(out, sctx, sizeof(*sctx));
return 0;
}
static int nx_sha256_import(struct shash_desc *desc, const void *in)
{
struct sha256_state *sctx = shash_desc_ctx(desc);
memcpy(sctx, in, sizeof(*sctx));
return 0;
}
struct shash_alg nx_shash_sha256_alg = {
.digestsize = SHA256_DIGEST_SIZE,
.init = nx_sha256_init,
.update = nx_sha256_update,
.final = nx_sha256_final,
.export = nx_sha256_export,
.import = nx_sha256_import,
.descsize = sizeof(struct sha256_state),
.statesize = sizeof(struct sha256_state),
.base = {
.cra_name = "sha256",
.cra_driver_name = "sha256-nx",
.cra_priority = 300,
.cra_blocksize = SHA256_BLOCK_SIZE,
.cra_module = THIS_MODULE,
.cra_ctxsize = sizeof(struct nx_crypto_ctx),
.cra_init = nx_crypto_ctx_sha256_init,
.cra_exit = nx_crypto_ctx_exit,
}
};
|