Blame view
crypto/async_tx/async_pq.c
12.5 KB
b2f46fd8e async_tx: add sup... |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 |
/* * Copyright(c) 2007 Yuri Tikhonov <yur@emcraft.com> * Copyright(c) 2009 Intel Corporation * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * * This program is distributed in the hope that it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * * You should have received a copy of the GNU General Public License along with * this program; if not, write to the Free Software Foundation, Inc., 59 * Temple Place - Suite 330, Boston, MA 02111-1307, USA. * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ #include <linux/kernel.h> #include <linux/interrupt.h> |
4bb33cc89 crypto: add modul... |
24 |
#include <linux/module.h> |
b2f46fd8e async_tx: add sup... |
25 26 27 |
#include <linux/dma-mapping.h> #include <linux/raid/pq.h> #include <linux/async_tx.h> |
5a0e3ad6a include cleanup: ... |
28 |
#include <linux/gfp.h> |
b2f46fd8e async_tx: add sup... |
29 30 |
/** |
030b07720 async_pq: rename ... |
31 32 |
* pq_scribble_page - space to hold throwaway P or Q buffer for * synchronous gen_syndrome |
b2f46fd8e async_tx: add sup... |
33 |
*/ |
030b07720 async_pq: rename ... |
34 |
static struct page *pq_scribble_page; |
b2f46fd8e async_tx: add sup... |
35 |
|
b2f46fd8e async_tx: add sup... |
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 |
/* the struct page *blocks[] parameter passed to async_gen_syndrome() * and async_syndrome_val() contains the 'P' destination address at * blocks[disks-2] and the 'Q' destination address at blocks[disks-1] * * note: these are macros as they are used as lvalues */ #define P(b, d) (b[d-2]) #define Q(b, d) (b[d-1]) /** * do_async_gen_syndrome - asynchronously calculate P and/or Q */ static __async_inline struct dma_async_tx_descriptor * do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks, const unsigned char *scfs, unsigned int offset, int disks, size_t len, dma_addr_t *dma_src, struct async_submit_ctl *submit) { struct dma_async_tx_descriptor *tx = NULL; struct dma_device *dma = chan->device; enum dma_ctrl_flags dma_flags = 0; enum async_tx_flags flags_orig = submit->flags; dma_async_tx_callback cb_fn_orig = submit->cb_fn; dma_async_tx_callback cb_param_orig = submit->cb_param; int src_cnt = disks - 2; unsigned char coefs[src_cnt]; unsigned short pq_src_cnt; dma_addr_t dma_dest[2]; int src_off = 0; int idx; int i; /* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */ if (P(blocks, disks)) dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset, len, DMA_BIDIRECTIONAL); else dma_flags |= DMA_PREP_PQ_DISABLE_P; if (Q(blocks, disks)) dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset, len, DMA_BIDIRECTIONAL); else dma_flags |= DMA_PREP_PQ_DISABLE_Q; /* convert source addresses being careful to collapse 'empty' * sources and update the coefficients accordingly */ for (i = 0, idx = 0; i < src_cnt; i++) { |
5dd33c9a4 md/async: don't p... |
84 |
if (blocks[i] == NULL) |
b2f46fd8e async_tx: add sup... |
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
continue; dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len, DMA_TO_DEVICE); coefs[idx] = scfs[i]; idx++; } src_cnt = idx; while (src_cnt > 0) { submit->flags = flags_orig; pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags)); /* if we are submitting additional pqs, leave the chain open, * clear the callback parameters, and leave the destination * buffers mapped */ if (src_cnt > pq_src_cnt) { submit->flags &= ~ASYNC_TX_ACK; |
0403e3827 dmaengine: add fe... |
102 |
submit->flags |= ASYNC_TX_FENCE; |
b2f46fd8e async_tx: add sup... |
103 104 105 106 107 108 109 110 111 112 |
dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP; submit->cb_fn = NULL; submit->cb_param = NULL; } else { dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP; submit->cb_fn = cb_fn_orig; submit->cb_param = cb_param_orig; if (cb_fn_orig) dma_flags |= DMA_PREP_INTERRUPT; } |
0403e3827 dmaengine: add fe... |
113 114 |
if (submit->flags & ASYNC_TX_FENCE) dma_flags |= DMA_PREP_FENCE; |
b2f46fd8e async_tx: add sup... |
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 |
/* Since we have clobbered the src_list we are committed * to doing this asynchronously. Drivers force forward * progress in case they can not provide a descriptor */ for (;;) { tx = dma->device_prep_dma_pq(chan, dma_dest, &dma_src[src_off], pq_src_cnt, &coefs[src_off], len, dma_flags); if (likely(tx)) break; async_tx_quiesce(&submit->depend_tx); dma_async_issue_pending(chan); } async_tx_submit(chan, tx, submit); submit->depend_tx = tx; /* drop completed sources */ src_cnt -= pq_src_cnt; src_off += pq_src_cnt; dma_flags |= DMA_PREP_CONTINUE; } return tx; } /** * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome */ static void do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks, size_t len, struct async_submit_ctl *submit) { void **srcs; int i; if (submit->scribble) srcs = submit->scribble; else srcs = (void **) blocks; for (i = 0; i < disks; i++) { |
5dd33c9a4 md/async: don't p... |
161 |
if (blocks[i] == NULL) { |
b2f46fd8e async_tx: add sup... |
162 |
BUG_ON(i > disks - 3); /* P or Q can't be zero */ |
5dd33c9a4 md/async: don't p... |
163 |
srcs[i] = (void*)raid6_empty_zero_page; |
b2f46fd8e async_tx: add sup... |
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 |
} else srcs[i] = page_address(blocks[i]) + offset; } raid6_call.gen_syndrome(disks, len, srcs); async_tx_sync_epilog(submit); } /** * async_gen_syndrome - asynchronously calculate a raid6 syndrome * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1 * @offset: common offset into each block (src and dest) to start transaction * @disks: number of blocks (including missing P or Q, see below) * @len: length of operation in bytes * @submit: submission/completion modifiers * * General note: This routine assumes a field of GF(2^8) with a * primitive polynomial of 0x11d and a generator of {02}. * * 'disks' note: callers can optionally omit either P or Q (but not * both) from the calculation by setting blocks[disks-2] or * blocks[disks-1] to NULL. When P or Q is omitted 'len' must be <= * PAGE_SIZE as a temporary buffer of this size is used in the * synchronous path. 'disks' always accounts for both destination |
5676470f0 async_pq: kill a ... |
187 188 189 190 |
* buffers. If any source buffers (blocks[i] where i < disks - 2) are * set to NULL those buffers will be replaced with the raid6_zero_page * in the synchronous path and omitted in the hardware-asynchronous * path. |
b2f46fd8e async_tx: add sup... |
191 192 |
* * 'blocks' note: if submit->scribble is NULL then the contents of |
5676470f0 async_pq: kill a ... |
193 194 |
* 'blocks' may be overwritten to perform address conversions * (dma_map_page() or page_address()). |
b2f46fd8e async_tx: add sup... |
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
*/ struct dma_async_tx_descriptor * async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, size_t len, struct async_submit_ctl *submit) { int src_cnt = disks - 2; struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ, &P(blocks, disks), 2, blocks, src_cnt, len); struct dma_device *device = chan ? chan->device : NULL; dma_addr_t *dma_src = NULL; BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks))); if (submit->scribble) dma_src = submit->scribble; else if (sizeof(dma_addr_t) <= sizeof(struct page *)) dma_src = (dma_addr_t *) blocks; if (dma_src && device && (src_cnt <= dma_maxpq(device, 0) || |
83544ae9f dmaengine, async_... |
216 217 |
dma_maxpq(device, DMA_PREP_CONTINUE) > 0) && is_dma_pq_aligned(device, offset, 0, len)) { |
b2f46fd8e async_tx: add sup... |
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
/* run the p+q asynchronously */ pr_debug("%s: (async) disks: %d len: %zu ", __func__, disks, len); return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset, disks, len, dma_src, submit); } /* run the pq synchronously */ pr_debug("%s: (sync) disks: %d len: %zu ", __func__, disks, len); /* wait for any prerequisite operations */ async_tx_quiesce(&submit->depend_tx); if (!P(blocks, disks)) { |
030b07720 async_pq: rename ... |
234 |
P(blocks, disks) = pq_scribble_page; |
b2f46fd8e async_tx: add sup... |
235 236 237 |
BUG_ON(len + offset > PAGE_SIZE); } if (!Q(blocks, disks)) { |
030b07720 async_pq: rename ... |
238 |
Q(blocks, disks) = pq_scribble_page; |
b2f46fd8e async_tx: add sup... |
239 240 241 242 243 244 245 |
BUG_ON(len + offset > PAGE_SIZE); } do_sync_gen_syndrome(blocks, offset, disks, len, submit); return NULL; } EXPORT_SYMBOL_GPL(async_gen_syndrome); |
7b3cc2b1f async_tx: build-t... |
246 247 248 249 250 251 252 253 254 |
static inline struct dma_chan * pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, size_t len) { #ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA return NULL; #endif return async_tx_find_channel(submit, DMA_PQ_VAL, NULL, 0, blocks, disks, len); } |
b2f46fd8e async_tx: add sup... |
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 |
/** * async_syndrome_val - asynchronously validate a raid6 syndrome * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1 * @offset: common offset into each block (src and dest) to start transaction * @disks: number of blocks (including missing P or Q, see below) * @len: length of operation in bytes * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set * @spare: temporary result buffer for the synchronous case * @submit: submission / completion modifiers * * The same notes from async_gen_syndrome apply to the 'blocks', * and 'disks' parameters of this routine. The synchronous path * requires a temporary result buffer and submit->scribble to be * specified. */ struct dma_async_tx_descriptor * async_syndrome_val(struct page **blocks, unsigned int offset, int disks, size_t len, enum sum_check_flags *pqres, struct page *spare, struct async_submit_ctl *submit) { |
7b3cc2b1f async_tx: build-t... |
275 |
struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len); |
b2f46fd8e async_tx: add sup... |
276 277 |
struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx; |
b2141e695 raid6/async_tx: h... |
278 |
unsigned char coefs[disks-2]; |
b2f46fd8e async_tx: add sup... |
279 280 |
enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; dma_addr_t *dma_src = NULL; |
b2141e695 raid6/async_tx: h... |
281 |
int src_cnt = 0; |
b2f46fd8e async_tx: add sup... |
282 283 284 285 286 287 288 |
BUG_ON(disks < 4); if (submit->scribble) dma_src = submit->scribble; else if (sizeof(dma_addr_t) <= sizeof(struct page *)) dma_src = (dma_addr_t *) blocks; |
83544ae9f dmaengine, async_... |
289 290 |
if (dma_src && device && disks <= dma_maxpq(device, 0) && is_dma_pq_aligned(device, offset, 0, len)) { |
b2f46fd8e async_tx: add sup... |
291 292 293 294 295 296 297 298 299 |
struct device *dev = device->dev; dma_addr_t *pq = &dma_src[disks-2]; int i; pr_debug("%s: (async) disks: %d len: %zu ", __func__, disks, len); if (!P(blocks, disks)) dma_flags |= DMA_PREP_PQ_DISABLE_P; |
b2141e695 raid6/async_tx: h... |
300 |
else |
5676470f0 async_pq: kill a ... |
301 |
pq[0] = dma_map_page(dev, P(blocks, disks), |
b2141e695 raid6/async_tx: h... |
302 303 |
offset, len, DMA_TO_DEVICE); |
b2f46fd8e async_tx: add sup... |
304 305 |
if (!Q(blocks, disks)) dma_flags |= DMA_PREP_PQ_DISABLE_Q; |
b2141e695 raid6/async_tx: h... |
306 |
else |
5676470f0 async_pq: kill a ... |
307 |
pq[1] = dma_map_page(dev, Q(blocks, disks), |
b2141e695 raid6/async_tx: h... |
308 309 |
offset, len, DMA_TO_DEVICE); |
0403e3827 dmaengine: add fe... |
310 311 |
if (submit->flags & ASYNC_TX_FENCE) dma_flags |= DMA_PREP_FENCE; |
b2141e695 raid6/async_tx: h... |
312 313 314 315 316 317 318 319 |
for (i = 0; i < disks-2; i++) if (likely(blocks[i])) { dma_src[src_cnt] = dma_map_page(dev, blocks[i], offset, len, DMA_TO_DEVICE); coefs[src_cnt] = raid6_gfexp[i]; src_cnt++; } |
b2f46fd8e async_tx: add sup... |
320 321 322 |
for (;;) { tx = device->device_prep_dma_pq_val(chan, pq, dma_src, |
b2141e695 raid6/async_tx: h... |
323 324 |
src_cnt, coefs, |
b2f46fd8e async_tx: add sup... |
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 |
len, pqres, dma_flags); if (likely(tx)) break; async_tx_quiesce(&submit->depend_tx); dma_async_issue_pending(chan); } async_tx_submit(chan, tx, submit); return tx; } else { struct page *p_src = P(blocks, disks); struct page *q_src = Q(blocks, disks); enum async_tx_flags flags_orig = submit->flags; dma_async_tx_callback cb_fn_orig = submit->cb_fn; void *scribble = submit->scribble; void *cb_param_orig = submit->cb_param; void *p, *q, *s; pr_debug("%s: (sync) disks: %d len: %zu ", __func__, disks, len); /* caller must provide a temporary result buffer and * allow the input parameters to be preserved */ BUG_ON(!spare || !scribble); /* wait for any prerequisite operations */ async_tx_quiesce(&submit->depend_tx); /* recompute p and/or q into the temporary buffer and then * check to see the result matches the current value */ tx = NULL; *pqres = 0; if (p_src) { init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL, NULL, NULL, scribble); tx = async_xor(spare, blocks, offset, disks-2, len, submit); async_tx_quiesce(&tx); p = page_address(p_src) + offset; s = page_address(spare) + offset; *pqres |= !!memcmp(p, s, len) << SUM_CHECK_P; } if (q_src) { P(blocks, disks) = NULL; Q(blocks, disks) = spare; init_async_submit(submit, 0, NULL, NULL, NULL, scribble); tx = async_gen_syndrome(blocks, offset, disks, len, submit); async_tx_quiesce(&tx); q = page_address(q_src) + offset; s = page_address(spare) + offset; *pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q; } /* restore P, Q and submit */ P(blocks, disks) = p_src; Q(blocks, disks) = q_src; submit->cb_fn = cb_fn_orig; submit->cb_param = cb_param_orig; submit->flags = flags_orig; async_tx_sync_epilog(submit); return NULL; } } EXPORT_SYMBOL_GPL(async_syndrome_val); static int __init async_pq_init(void) { |
030b07720 async_pq: rename ... |
398 |
pq_scribble_page = alloc_page(GFP_KERNEL); |
b2f46fd8e async_tx: add sup... |
399 |
|
030b07720 async_pq: rename ... |
400 |
if (pq_scribble_page) |
b2f46fd8e async_tx: add sup... |
401 402 403 404 405 406 407 408 409 410 |
return 0; pr_err("%s: failed to allocate required spare page ", __func__); return -ENOMEM; } static void __exit async_pq_exit(void) { |
030b07720 async_pq: rename ... |
411 |
put_page(pq_scribble_page); |
b2f46fd8e async_tx: add sup... |
412 413 414 415 416 417 418 |
} module_init(async_pq_init); module_exit(async_pq_exit); MODULE_DESCRIPTION("asynchronous raid6 syndrome generation/validation"); MODULE_LICENSE("GPL"); |