| 4 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> #include <linux/sfp.h> #include "netlink.h" #include "common.h" struct eeprom_req_info { struct ethnl_req_info base; u32 offset; u32 length; u8 page; u8 bank; u8 i2c_address; }; struct eeprom_reply_data { struct ethnl_reply_data base; u32 length; u8 *data; }; #define MODULE_EEPROM_REQINFO(__req_base) \ container_of(__req_base, struct eeprom_req_info, base) #define MODULE_EEPROM_REPDATA(__reply_base) \ container_of(__reply_base, struct eeprom_reply_data, base) static int fallback_set_params(struct eeprom_req_info *request, struct ethtool_modinfo *modinfo, struct ethtool_eeprom *eeprom) { u32 offset = request->offset; u32 length = request->length; if (request->page) offset = request->page * ETH_MODULE_EEPROM_PAGE_LEN + offset; if (modinfo->type == ETH_MODULE_SFF_8472 && request->i2c_address == 0x51) offset += ETH_MODULE_EEPROM_PAGE_LEN * 2; if (offset >= modinfo->eeprom_len) return -EINVAL; eeprom->cmd = ETHTOOL_GMODULEEEPROM; eeprom->len = length; eeprom->offset = offset; return 0; } static int eeprom_fallback(struct eeprom_req_info *request, struct eeprom_reply_data *reply) { struct net_device *dev = reply->base.dev; struct ethtool_modinfo modinfo = {0}; struct ethtool_eeprom eeprom = {0}; u8 *data; int err; modinfo.cmd = ETHTOOL_GMODULEINFO; err = ethtool_get_module_info_call(dev, &modinfo); if (err < 0) return err; err = fallback_set_params(request, &modinfo, &eeprom); if (err < 0) return err; data = kmalloc(eeprom.len, GFP_KERNEL); if (!data) return -ENOMEM; err = ethtool_get_module_eeprom_call(dev, &eeprom, data); if (err < 0) goto err_out; reply->data = data; reply->length = eeprom.len; return 0; err_out: kfree(data); return err; } static int get_module_eeprom_by_page(struct net_device *dev, struct ethtool_module_eeprom *page_data, struct netlink_ext_ack *extack) { const struct ethtool_ops *ops = dev->ethtool_ops; if (dev->ethtool->module_fw_flash_in_progress) { NL_SET_ERR_MSG(extack, "Module firmware flashing is in progress"); return -EBUSY; } if (dev->sfp_bus) return sfp_get_module_eeprom_by_page(dev->sfp_bus, page_data, extack); if (ops->get_module_eeprom_by_page) return ops->get_module_eeprom_by_page(dev, page_data, extack); return -EOPNOTSUPP; } static int eeprom_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct eeprom_reply_data *reply = MODULE_EEPROM_REPDATA(reply_base); struct eeprom_req_info *request = MODULE_EEPROM_REQINFO(req_base); struct ethtool_module_eeprom page_data = {0}; struct net_device *dev = reply_base->dev; int ret; page_data.offset = request->offset; page_data.length = request->length; page_data.i2c_address = request->i2c_address; page_data.page = request->page; page_data.bank = request->bank; page_data.data = kmalloc(page_data.length, GFP_KERNEL); if (!page_data.data) return -ENOMEM; ret = ethnl_ops_begin(dev); if (ret) goto err_free; ret = get_module_eeprom_by_page(dev, &page_data, info->extack); if (ret < 0) goto err_ops; reply->length = ret; reply->data = page_data.data; ethnl_ops_complete(dev); return 0; err_ops: ethnl_ops_complete(dev); err_free: kfree(page_data.data); if (ret == -EOPNOTSUPP) return eeprom_fallback(request, reply); return ret; } static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, struct netlink_ext_ack *extack) { struct eeprom_req_info *request = MODULE_EEPROM_REQINFO(req_info); if (!tb[ETHTOOL_A_MODULE_EEPROM_OFFSET] || !tb[ETHTOOL_A_MODULE_EEPROM_LENGTH] || !tb[ETHTOOL_A_MODULE_EEPROM_PAGE] || !tb[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS]) return -EINVAL; request->i2c_address = nla_get_u8(tb[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS]); request->offset = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_OFFSET]); request->length = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_LENGTH]); /* The following set of conditions limit the API to only dump 1/2 * EEPROM page without crossing low page boundary located at offset 128. * This means user may only request dumps of length limited to 128 from * either low 128 bytes or high 128 bytes. * For pages higher than 0 only high 128 bytes are accessible. */ request->page = nla_get_u8(tb[ETHTOOL_A_MODULE_EEPROM_PAGE]); if (request->page && request->offset < ETH_MODULE_EEPROM_PAGE_LEN) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_PAGE], "reading from lower half page is allowed for page 0 only"); return -EINVAL; } if (request->offset < ETH_MODULE_EEPROM_PAGE_LEN && request->offset + request->length > ETH_MODULE_EEPROM_PAGE_LEN) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross half page boundary is illegal"); return -EINVAL; } else if (request->offset + request->length > ETH_MODULE_EEPROM_PAGE_LEN * 2) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross page boundary is illegal"); return -EINVAL; } if (tb[ETHTOOL_A_MODULE_EEPROM_BANK]) request->bank = nla_get_u8(tb[ETHTOOL_A_MODULE_EEPROM_BANK]); return 0; } static int eeprom_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct eeprom_req_info *request = MODULE_EEPROM_REQINFO(req_base); return nla_total_size(sizeof(u8) * request->length); /* _EEPROM_DATA */ } static int eeprom_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { struct eeprom_reply_data *reply = MODULE_EEPROM_REPDATA(reply_base); return nla_put(skb, ETHTOOL_A_MODULE_EEPROM_DATA, reply->length, reply->data); } static void eeprom_cleanup_data(struct ethnl_reply_data *reply_base) { struct eeprom_reply_data *reply = MODULE_EEPROM_REPDATA(reply_base); kfree(reply->data); } const struct ethnl_request_ops ethnl_module_eeprom_request_ops = { .request_cmd = ETHTOOL_MSG_MODULE_EEPROM_GET, .reply_cmd = ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, .hdr_attr = ETHTOOL_A_MODULE_EEPROM_HEADER, .req_info_size = sizeof(struct eeprom_req_info), .reply_data_size = sizeof(struct eeprom_reply_data), .parse_request = eeprom_parse_request, .prepare_data = eeprom_prepare_data, .reply_size = eeprom_reply_size, .fill_reply = eeprom_fill_reply, .cleanup_data = eeprom_cleanup_data, }; const struct nla_policy ethnl_module_eeprom_get_policy[] = { [ETHTOOL_A_MODULE_EEPROM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_MODULE_EEPROM_OFFSET] = NLA_POLICY_MAX(NLA_U32, ETH_MODULE_EEPROM_PAGE_LEN * 2 - 1), [ETHTOOL_A_MODULE_EEPROM_LENGTH] = NLA_POLICY_RANGE(NLA_U32, 1, ETH_MODULE_EEPROM_PAGE_LEN), [ETHTOOL_A_MODULE_EEPROM_PAGE] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_BANK] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS] = NLA_POLICY_RANGE(NLA_U8, 0, ETH_MODULE_MAX_I2C_ADDRESS), }; |
| 229 2 228 221 46 46 336 335 229 228 53 218 43 219 329 2 327 366 2 372 8 323 323 6 6 150 149 2 2 9 9 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 | /* * PCM Interface - misc routines * Copyright (c) 1998 by Jaroslav Kysela <perex@perex.cz> * * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Library 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 Library General Public License for more details. * * You should have received a copy of the GNU Library General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ #include <linux/time.h> #include <linux/export.h> #include <sound/core.h> #include <sound/pcm.h> #include "pcm_local.h" #define SND_PCM_FORMAT_UNKNOWN (-1) /* NOTE: "signed" prefix must be given below since the default char is * unsigned on some architectures! */ struct pcm_format_data { unsigned char width; /* bit width */ unsigned char phys; /* physical bit width */ signed char le; /* 0 = big-endian, 1 = little-endian, -1 = others */ signed char signd; /* 0 = unsigned, 1 = signed, -1 = others */ unsigned char silence[8]; /* silence data to fill */ }; /* we do lots of calculations on snd_pcm_format_t; shut up sparse */ #define INT __force int static bool valid_format(snd_pcm_format_t format) { return (INT)format >= 0 && (INT)format <= (INT)SNDRV_PCM_FORMAT_LAST; } static const struct pcm_format_data pcm_formats[(INT)SNDRV_PCM_FORMAT_LAST+1] = { [SNDRV_PCM_FORMAT_S8] = { .width = 8, .phys = 8, .le = -1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U8] = { .width = 8, .phys = 8, .le = -1, .signd = 0, .silence = { 0x80 }, }, [SNDRV_PCM_FORMAT_S16_LE] = { .width = 16, .phys = 16, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S16_BE] = { .width = 16, .phys = 16, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U16_LE] = { .width = 16, .phys = 16, .le = 1, .signd = 0, .silence = { 0x00, 0x80 }, }, [SNDRV_PCM_FORMAT_U16_BE] = { .width = 16, .phys = 16, .le = 0, .signd = 0, .silence = { 0x80, 0x00 }, }, [SNDRV_PCM_FORMAT_S24_LE] = { .width = 24, .phys = 32, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S24_BE] = { .width = 24, .phys = 32, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U24_LE] = { .width = 24, .phys = 32, .le = 1, .signd = 0, .silence = { 0x00, 0x00, 0x80 }, }, [SNDRV_PCM_FORMAT_U24_BE] = { .width = 24, .phys = 32, .le = 0, .signd = 0, .silence = { 0x00, 0x80, 0x00, 0x00 }, }, [SNDRV_PCM_FORMAT_S32_LE] = { .width = 32, .phys = 32, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S32_BE] = { .width = 32, .phys = 32, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U32_LE] = { .width = 32, .phys = 32, .le = 1, .signd = 0, .silence = { 0x00, 0x00, 0x00, 0x80 }, }, [SNDRV_PCM_FORMAT_U32_BE] = { .width = 32, .phys = 32, .le = 0, .signd = 0, .silence = { 0x80, 0x00, 0x00, 0x00 }, }, [SNDRV_PCM_FORMAT_FLOAT_LE] = { .width = 32, .phys = 32, .le = 1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_FLOAT_BE] = { .width = 32, .phys = 32, .le = 0, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_FLOAT64_LE] = { .width = 64, .phys = 64, .le = 1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_FLOAT64_BE] = { .width = 64, .phys = 64, .le = 0, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE] = { .width = 32, .phys = 32, .le = 1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE] = { .width = 32, .phys = 32, .le = 0, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_MU_LAW] = { .width = 8, .phys = 8, .le = -1, .signd = -1, .silence = { 0x7f }, }, [SNDRV_PCM_FORMAT_A_LAW] = { .width = 8, .phys = 8, .le = -1, .signd = -1, .silence = { 0x55 }, }, [SNDRV_PCM_FORMAT_IMA_ADPCM] = { .width = 4, .phys = 4, .le = -1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_G723_24] = { .width = 3, .phys = 3, .le = -1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_G723_40] = { .width = 5, .phys = 5, .le = -1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_DSD_U8] = { .width = 8, .phys = 8, .le = 1, .signd = 0, .silence = { 0x69 }, }, [SNDRV_PCM_FORMAT_DSD_U16_LE] = { .width = 16, .phys = 16, .le = 1, .signd = 0, .silence = { 0x69, 0x69 }, }, [SNDRV_PCM_FORMAT_DSD_U32_LE] = { .width = 32, .phys = 32, .le = 1, .signd = 0, .silence = { 0x69, 0x69, 0x69, 0x69 }, }, [SNDRV_PCM_FORMAT_DSD_U16_BE] = { .width = 16, .phys = 16, .le = 0, .signd = 0, .silence = { 0x69, 0x69 }, }, [SNDRV_PCM_FORMAT_DSD_U32_BE] = { .width = 32, .phys = 32, .le = 0, .signd = 0, .silence = { 0x69, 0x69, 0x69, 0x69 }, }, /* FIXME: the following two formats are not defined properly yet */ [SNDRV_PCM_FORMAT_MPEG] = { .le = -1, .signd = -1, }, [SNDRV_PCM_FORMAT_GSM] = { .le = -1, .signd = -1, }, [SNDRV_PCM_FORMAT_S20_LE] = { .width = 20, .phys = 32, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S20_BE] = { .width = 20, .phys = 32, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U20_LE] = { .width = 20, .phys = 32, .le = 1, .signd = 0, .silence = { 0x00, 0x00, 0x08, 0x00 }, }, [SNDRV_PCM_FORMAT_U20_BE] = { .width = 20, .phys = 32, .le = 0, .signd = 0, .silence = { 0x00, 0x08, 0x00, 0x00 }, }, /* FIXME: the following format is not defined properly yet */ [SNDRV_PCM_FORMAT_SPECIAL] = { .le = -1, .signd = -1, }, [SNDRV_PCM_FORMAT_S24_3LE] = { .width = 24, .phys = 24, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S24_3BE] = { .width = 24, .phys = 24, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U24_3LE] = { .width = 24, .phys = 24, .le = 1, .signd = 0, .silence = { 0x00, 0x00, 0x80 }, }, [SNDRV_PCM_FORMAT_U24_3BE] = { .width = 24, .phys = 24, .le = 0, .signd = 0, .silence = { 0x80, 0x00, 0x00 }, }, [SNDRV_PCM_FORMAT_S20_3LE] = { .width = 20, .phys = 24, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S20_3BE] = { .width = 20, .phys = 24, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U20_3LE] = { .width = 20, .phys = 24, .le = 1, .signd = 0, .silence = { 0x00, 0x00, 0x08 }, }, [SNDRV_PCM_FORMAT_U20_3BE] = { .width = 20, .phys = 24, .le = 0, .signd = 0, .silence = { 0x08, 0x00, 0x00 }, }, [SNDRV_PCM_FORMAT_S18_3LE] = { .width = 18, .phys = 24, .le = 1, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_S18_3BE] = { .width = 18, .phys = 24, .le = 0, .signd = 1, .silence = {}, }, [SNDRV_PCM_FORMAT_U18_3LE] = { .width = 18, .phys = 24, .le = 1, .signd = 0, .silence = { 0x00, 0x00, 0x02 }, }, [SNDRV_PCM_FORMAT_U18_3BE] = { .width = 18, .phys = 24, .le = 0, .signd = 0, .silence = { 0x02, 0x00, 0x00 }, }, [SNDRV_PCM_FORMAT_G723_24_1B] = { .width = 3, .phys = 8, .le = -1, .signd = -1, .silence = {}, }, [SNDRV_PCM_FORMAT_G723_40_1B] = { .width = 5, .phys = 8, .le = -1, .signd = -1, .silence = {}, }, }; /** * snd_pcm_format_signed - Check the PCM format is signed linear * @format: the format to check * * Return: 1 if the given PCM format is signed linear, 0 if unsigned * linear, and a negative error code for non-linear formats. */ int snd_pcm_format_signed(snd_pcm_format_t format) { int val; if (!valid_format(format)) return -EINVAL; val = pcm_formats[(INT)format].signd; if (val < 0) return -EINVAL; return val; } EXPORT_SYMBOL(snd_pcm_format_signed); /** * snd_pcm_format_unsigned - Check the PCM format is unsigned linear * @format: the format to check * * Return: 1 if the given PCM format is unsigned linear, 0 if signed * linear, and a negative error code for non-linear formats. */ int snd_pcm_format_unsigned(snd_pcm_format_t format) { int val; val = snd_pcm_format_signed(format); if (val < 0) return val; return !val; } EXPORT_SYMBOL(snd_pcm_format_unsigned); /** * snd_pcm_format_linear - Check the PCM format is linear * @format: the format to check * * Return: 1 if the given PCM format is linear, 0 if not. */ int snd_pcm_format_linear(snd_pcm_format_t format) { return snd_pcm_format_signed(format) >= 0; } EXPORT_SYMBOL(snd_pcm_format_linear); /** * snd_pcm_format_little_endian - Check the PCM format is little-endian * @format: the format to check * * Return: 1 if the given PCM format is little-endian, 0 if * big-endian, or a negative error code if endian not specified. */ int snd_pcm_format_little_endian(snd_pcm_format_t format) { int val; if (!valid_format(format)) return -EINVAL; val = pcm_formats[(INT)format].le; if (val < 0) return -EINVAL; return val; } EXPORT_SYMBOL(snd_pcm_format_little_endian); /** * snd_pcm_format_big_endian - Check the PCM format is big-endian * @format: the format to check * * Return: 1 if the given PCM format is big-endian, 0 if * little-endian, or a negative error code if endian not specified. */ int snd_pcm_format_big_endian(snd_pcm_format_t format) { int val; val = snd_pcm_format_little_endian(format); if (val < 0) return val; return !val; } EXPORT_SYMBOL(snd_pcm_format_big_endian); /** * snd_pcm_format_width - return the bit-width of the format * @format: the format to check * * Return: The bit-width of the format, or a negative error code * if unknown format. */ int snd_pcm_format_width(snd_pcm_format_t format) { int val; if (!valid_format(format)) return -EINVAL; val = pcm_formats[(INT)format].width; if (!val) return -EINVAL; return val; } EXPORT_SYMBOL(snd_pcm_format_width); /** * snd_pcm_format_physical_width - return the physical bit-width of the format * @format: the format to check * * Return: The physical bit-width of the format, or a negative error code * if unknown format. */ int snd_pcm_format_physical_width(snd_pcm_format_t format) { int val; if (!valid_format(format)) return -EINVAL; val = pcm_formats[(INT)format].phys; if (!val) return -EINVAL; return val; } EXPORT_SYMBOL(snd_pcm_format_physical_width); /** * snd_pcm_format_size - return the byte size of samples on the given format * @format: the format to check * @samples: sampling rate * * Return: The byte size of the given samples for the format, or a * negative error code if unknown format. */ ssize_t snd_pcm_format_size(snd_pcm_format_t format, size_t samples) { int phys_width = snd_pcm_format_physical_width(format); if (phys_width < 0) return -EINVAL; return samples * phys_width / 8; } EXPORT_SYMBOL(snd_pcm_format_size); /** * snd_pcm_format_silence_64 - return the silent data in 8 bytes array * @format: the format to check * * Return: The format pattern to fill or %NULL if error. */ const unsigned char *snd_pcm_format_silence_64(snd_pcm_format_t format) { if (!valid_format(format)) return NULL; if (! pcm_formats[(INT)format].phys) return NULL; return pcm_formats[(INT)format].silence; } EXPORT_SYMBOL(snd_pcm_format_silence_64); /** * snd_pcm_format_set_silence - set the silence data on the buffer * @format: the PCM format * @data: the buffer pointer * @samples: the number of samples to set silence * * Sets the silence data on the buffer for the given samples. * * Return: Zero if successful, or a negative error code on failure. */ int snd_pcm_format_set_silence(snd_pcm_format_t format, void *data, unsigned int samples) { int width; unsigned char *dst; const unsigned char *pat; if (!valid_format(format)) return -EINVAL; if (samples == 0) return 0; width = pcm_formats[(INT)format].phys; /* physical width */ if (!width) return -EINVAL; pat = pcm_formats[(INT)format].silence; /* signed or 1 byte data */ if (pcm_formats[(INT)format].signd == 1 || width <= 8) { unsigned int bytes = samples * width / 8; memset(data, *pat, bytes); return 0; } /* non-zero samples, fill using a loop */ width /= 8; dst = data; #if 0 while (samples--) { memcpy(dst, pat, width); dst += width; } #else /* a bit optimization for constant width */ switch (width) { case 2: while (samples--) { memcpy(dst, pat, 2); dst += 2; } break; case 3: while (samples--) { memcpy(dst, pat, 3); dst += 3; } break; case 4: while (samples--) { memcpy(dst, pat, 4); dst += 4; } break; case 8: while (samples--) { memcpy(dst, pat, 8); dst += 8; } break; } #endif return 0; } EXPORT_SYMBOL(snd_pcm_format_set_silence); /** * snd_pcm_hw_limit_rates - determine rate_min/rate_max fields * @hw: the pcm hw instance * * Determines the rate_min and rate_max fields from the rates bits of * the given hw. * * Return: Zero if successful. */ int snd_pcm_hw_limit_rates(struct snd_pcm_hardware *hw) { int i; unsigned int rmin, rmax; rmin = UINT_MAX; rmax = 0; for (i = 0; i < (int)snd_pcm_known_rates.count; i++) { if (hw->rates & (1 << i)) { rmin = min(rmin, snd_pcm_known_rates.list[i]); rmax = max(rmax, snd_pcm_known_rates.list[i]); } } if (rmin > rmax) return -EINVAL; hw->rate_min = rmin; hw->rate_max = rmax; return 0; } EXPORT_SYMBOL(snd_pcm_hw_limit_rates); /** * snd_pcm_rate_to_rate_bit - converts sample rate to SNDRV_PCM_RATE_xxx bit * @rate: the sample rate to convert * * Return: The SNDRV_PCM_RATE_xxx flag that corresponds to the given rate, or * SNDRV_PCM_RATE_KNOT for an unknown rate. */ unsigned int snd_pcm_rate_to_rate_bit(unsigned int rate) { unsigned int i; for (i = 0; i < snd_pcm_known_rates.count; i++) if (snd_pcm_known_rates.list[i] == rate) return 1u << i; return SNDRV_PCM_RATE_KNOT; } EXPORT_SYMBOL(snd_pcm_rate_to_rate_bit); /** * snd_pcm_rate_bit_to_rate - converts SNDRV_PCM_RATE_xxx bit to sample rate * @rate_bit: the rate bit to convert * * Return: The sample rate that corresponds to the given SNDRV_PCM_RATE_xxx flag * or 0 for an unknown rate bit. */ unsigned int snd_pcm_rate_bit_to_rate(unsigned int rate_bit) { unsigned int i; for (i = 0; i < snd_pcm_known_rates.count; i++) if ((1u << i) == rate_bit) return snd_pcm_known_rates.list[i]; return 0; } EXPORT_SYMBOL(snd_pcm_rate_bit_to_rate); static unsigned int snd_pcm_rate_mask_sanitize(unsigned int rates) { if (rates & SNDRV_PCM_RATE_CONTINUOUS) return SNDRV_PCM_RATE_CONTINUOUS; else if (rates & SNDRV_PCM_RATE_KNOT) return SNDRV_PCM_RATE_KNOT; return rates; } /** * snd_pcm_rate_mask_intersect - computes the intersection between two rate masks * @rates_a: The first rate mask * @rates_b: The second rate mask * * This function computes the rates that are supported by both rate masks passed * to the function. It will take care of the special handling of * SNDRV_PCM_RATE_CONTINUOUS and SNDRV_PCM_RATE_KNOT. * * Return: A rate mask containing the rates that are supported by both rates_a * and rates_b. */ unsigned int snd_pcm_rate_mask_intersect(unsigned int rates_a, unsigned int rates_b) { rates_a = snd_pcm_rate_mask_sanitize(rates_a); rates_b = snd_pcm_rate_mask_sanitize(rates_b); if (rates_a & SNDRV_PCM_RATE_CONTINUOUS) return rates_b; else if (rates_b & SNDRV_PCM_RATE_CONTINUOUS) return rates_a; else if (rates_a & SNDRV_PCM_RATE_KNOT) return rates_b; else if (rates_b & SNDRV_PCM_RATE_KNOT) return rates_a; return rates_a & rates_b; } EXPORT_SYMBOL_GPL(snd_pcm_rate_mask_intersect); |
| 6 1851 2611 686 2272 1261 773 2611 1851 16 44 16 2 2 35 34 101 4 73 8 4 320 322 89 249 250 251 9 308 797 931 797 163 541 163 12 271 43 44 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { struct folio *folio; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); if (folio && user_alloc_needs_zeroing()) clear_user_highpage(&folio->page, vaddr); return folio; } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) { } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memcpy_folio(struct folio *dst_folio, size_t dst_off, struct folio *src_folio, size_t src_off, size_t len) { VM_BUG_ON(dst_off + len > folio_size(dst_folio)); VM_BUG_ON(src_off + len > folio_size(src_folio)); do { char *dst = kmap_local_folio(dst_folio, dst_off); const char *src = kmap_local_folio(src_folio, src_off); size_t chunk = len; if (folio_test_highmem(dst_folio) && chunk > PAGE_SIZE - offset_in_page(dst_off)) chunk = PAGE_SIZE - offset_in_page(dst_off); if (folio_test_highmem(src_folio) && chunk > PAGE_SIZE - offset_in_page(src_off)) chunk = PAGE_SIZE - offset_in_page(src_off); memcpy(dst, src, chunk); kunmap_local(src); kunmap_local(dst); dst_off += chunk; src_off += chunk; len -= chunk; } while (len > 0); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_partial_kmap(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } static inline void unmap_and_put_page(struct page *page, void *addr) { folio_release_kmap(page_folio(page), addr); } #endif /* _LINUX_HIGHMEM_H */ |
| 4 1 1 1 1 4 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 | // SPDX-License-Identifier: GPL-2.0+ /* * KOBIL USB Smart Card Terminal Driver * * Copyright (C) 2002 KOBIL Systems GmbH * Author: Thomas Wahrenbruch * * Contact: linuxusb@kobil.de * * This program is largely derived from work by the linux-usb group * and associated source files. Please see the usb/serial files for * individual credits and copyrights. * * Thanks to Greg Kroah-Hartman (greg@kroah.com) for his help and * patience. * * Supported readers: USB TWIN, KAAN Standard Plus and SecOVID Reader Plus * (Adapter K), B1 Professional and KAAN Professional (Adapter B) */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include <linux/ioctl.h> #include "kobil_sct.h" #define DRIVER_AUTHOR "KOBIL Systems GmbH - http://www.kobil.com" #define DRIVER_DESC "KOBIL USB Smart Card Terminal Driver (experimental)" #define KOBIL_VENDOR_ID 0x0D46 #define KOBIL_ADAPTER_B_PRODUCT_ID 0x2011 #define KOBIL_ADAPTER_K_PRODUCT_ID 0x2012 #define KOBIL_USBTWIN_PRODUCT_ID 0x0078 #define KOBIL_KAAN_SIM_PRODUCT_ID 0x0081 #define KOBIL_TIMEOUT 500 #define KOBIL_BUF_LENGTH 300 /* Function prototypes */ static int kobil_port_probe(struct usb_serial_port *probe); static void kobil_port_remove(struct usb_serial_port *probe); static int kobil_open(struct tty_struct *tty, struct usb_serial_port *port); static void kobil_close(struct usb_serial_port *port); static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count); static unsigned int kobil_write_room(struct tty_struct *tty); static int kobil_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg); static int kobil_tiocmget(struct tty_struct *tty); static int kobil_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear); static void kobil_read_int_callback(struct urb *urb); static void kobil_write_int_callback(struct urb *urb); static void kobil_set_termios(struct tty_struct *tty, struct usb_serial_port *port, const struct ktermios *old); static void kobil_init_termios(struct tty_struct *tty); static const struct usb_device_id id_table[] = { { USB_DEVICE(KOBIL_VENDOR_ID, KOBIL_ADAPTER_B_PRODUCT_ID) }, { USB_DEVICE(KOBIL_VENDOR_ID, KOBIL_ADAPTER_K_PRODUCT_ID) }, { USB_DEVICE(KOBIL_VENDOR_ID, KOBIL_USBTWIN_PRODUCT_ID) }, { USB_DEVICE(KOBIL_VENDOR_ID, KOBIL_KAAN_SIM_PRODUCT_ID) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); static struct usb_serial_driver kobil_device = { .driver = { .name = "kobil", }, .description = "KOBIL USB smart card terminal", .id_table = id_table, .num_ports = 1, .num_interrupt_out = 1, .port_probe = kobil_port_probe, .port_remove = kobil_port_remove, .ioctl = kobil_ioctl, .set_termios = kobil_set_termios, .init_termios = kobil_init_termios, .tiocmget = kobil_tiocmget, .tiocmset = kobil_tiocmset, .open = kobil_open, .close = kobil_close, .write = kobil_write, .write_room = kobil_write_room, .read_int_callback = kobil_read_int_callback, .write_int_callback = kobil_write_int_callback, }; static struct usb_serial_driver * const serial_drivers[] = { &kobil_device, NULL }; struct kobil_private { unsigned char buf[KOBIL_BUF_LENGTH]; /* buffer for the APDU to send */ int filled; /* index of the last char in buf */ int cur_pos; /* index of the next char to send in buf */ __u16 device_type; }; static int kobil_port_probe(struct usb_serial_port *port) { struct usb_serial *serial = port->serial; struct kobil_private *priv; priv = kmalloc(sizeof(struct kobil_private), GFP_KERNEL); if (!priv) return -ENOMEM; priv->filled = 0; priv->cur_pos = 0; priv->device_type = le16_to_cpu(serial->dev->descriptor.idProduct); switch (priv->device_type) { case KOBIL_ADAPTER_B_PRODUCT_ID: dev_dbg(&serial->dev->dev, "KOBIL B1 PRO / KAAN PRO detected\n"); break; case KOBIL_ADAPTER_K_PRODUCT_ID: dev_dbg(&serial->dev->dev, "KOBIL KAAN Standard Plus / SecOVID Reader Plus detected\n"); break; case KOBIL_USBTWIN_PRODUCT_ID: dev_dbg(&serial->dev->dev, "KOBIL USBTWIN detected\n"); break; case KOBIL_KAAN_SIM_PRODUCT_ID: dev_dbg(&serial->dev->dev, "KOBIL KAAN SIM detected\n"); break; } usb_set_serial_port_data(port, priv); return 0; } static void kobil_port_remove(struct usb_serial_port *port) { struct kobil_private *priv; priv = usb_get_serial_port_data(port); kfree(priv); } static void kobil_init_termios(struct tty_struct *tty) { /* Default to echo off and other sane device settings */ tty->termios.c_lflag = 0; tty->termios.c_iflag = IGNBRK | IGNPAR | IXOFF; /* do NOT translate CR to CR-NL (0x0A -> 0x0A 0x0D) */ tty->termios.c_oflag &= ~ONLCR; } static int kobil_open(struct tty_struct *tty, struct usb_serial_port *port) { struct device *dev = &port->dev; int result = 0; struct kobil_private *priv; unsigned char *transfer_buffer; int transfer_buffer_length = 8; priv = usb_get_serial_port_data(port); /* allocate memory for transfer buffer */ transfer_buffer = kzalloc(transfer_buffer_length, GFP_KERNEL); if (!transfer_buffer) return -ENOMEM; /* get hardware version */ result = usb_control_msg(port->serial->dev, usb_rcvctrlpipe(port->serial->dev, 0), SUSBCRequest_GetMisc, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_IN, SUSBCR_MSC_GetHWVersion, 0, transfer_buffer, transfer_buffer_length, KOBIL_TIMEOUT ); dev_dbg(dev, "%s - Send get_HW_version URB returns: %i\n", __func__, result); if (result >= 3) { dev_dbg(dev, "Hardware version: %i.%i.%i\n", transfer_buffer[0], transfer_buffer[1], transfer_buffer[2]); } /* get firmware version */ result = usb_control_msg(port->serial->dev, usb_rcvctrlpipe(port->serial->dev, 0), SUSBCRequest_GetMisc, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_IN, SUSBCR_MSC_GetFWVersion, 0, transfer_buffer, transfer_buffer_length, KOBIL_TIMEOUT ); dev_dbg(dev, "%s - Send get_FW_version URB returns: %i\n", __func__, result); if (result >= 3) { dev_dbg(dev, "Firmware version: %i.%i.%i\n", transfer_buffer[0], transfer_buffer[1], transfer_buffer[2]); } if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID || priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID) { /* Setting Baudrate, Parity and Stopbits */ result = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_SetBaudRateParityAndStopBits, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, SUSBCR_SBR_9600 | SUSBCR_SPASB_EvenParity | SUSBCR_SPASB_1StopBit, 0, NULL, 0, KOBIL_TIMEOUT ); dev_dbg(dev, "%s - Send set_baudrate URB returns: %i\n", __func__, result); /* reset all queues */ result = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_Misc, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, SUSBCR_MSC_ResetAllQueues, 0, NULL, 0, KOBIL_TIMEOUT ); dev_dbg(dev, "%s - Send reset_all_queues URB returns: %i\n", __func__, result); } if (priv->device_type == KOBIL_USBTWIN_PRODUCT_ID || priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID || priv->device_type == KOBIL_KAAN_SIM_PRODUCT_ID) { /* start reading (Adapter B 'cause PNP string) */ result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); dev_dbg(dev, "%s - Send read URB returns: %i\n", __func__, result); } kfree(transfer_buffer); return 0; } static void kobil_close(struct usb_serial_port *port) { /* FIXME: Add rts/dtr methods */ usb_kill_urb(port->interrupt_out_urb); usb_kill_urb(port->interrupt_in_urb); } static void kobil_read_int_callback(struct urb *urb) { int result; struct usb_serial_port *port = urb->context; unsigned char *data = urb->transfer_buffer; int status = urb->status; if (status) { dev_dbg(&port->dev, "%s - Read int status not zero: %d\n", __func__, status); return; } if (urb->actual_length) { usb_serial_debug_data(&port->dev, __func__, urb->actual_length, data); tty_insert_flip_string(&port->port, data, urb->actual_length); tty_flip_buffer_push(&port->port); } result = usb_submit_urb(port->interrupt_in_urb, GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send read URB returns: %i\n", __func__, result); } static void kobil_write_int_callback(struct urb *urb) { } static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count) { int length = 0; int result = 0; int todo = 0; struct kobil_private *priv; if (count == 0) { dev_dbg(&port->dev, "%s - write request of 0 bytes\n", __func__); return 0; } priv = usb_get_serial_port_data(port); if (count > (KOBIL_BUF_LENGTH - priv->filled)) { dev_dbg(&port->dev, "%s - Error: write request bigger than buffer size\n", __func__); return -ENOMEM; } /* Copy data to buffer */ memcpy(priv->buf + priv->filled, buf, count); usb_serial_debug_data(&port->dev, __func__, count, priv->buf + priv->filled); priv->filled = priv->filled + count; /* only send complete block. TWIN, KAAN SIM and adapter K use the same protocol. */ if (((priv->device_type != KOBIL_ADAPTER_B_PRODUCT_ID) && (priv->filled > 2) && (priv->filled >= (priv->buf[1] + 3))) || ((priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID) && (priv->filled > 3) && (priv->filled >= (priv->buf[2] + 4)))) { /* stop reading (except TWIN and KAAN SIM) */ if ((priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID) || (priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID)) usb_kill_urb(port->interrupt_in_urb); todo = priv->filled - priv->cur_pos; while (todo > 0) { /* max 8 byte in one urb (endpoint size) */ length = min(todo, port->interrupt_out_size); /* copy data to transfer buffer */ memcpy(port->interrupt_out_buffer, priv->buf + priv->cur_pos, length); port->interrupt_out_urb->transfer_buffer_length = length; priv->cur_pos = priv->cur_pos + length; result = usb_submit_urb(port->interrupt_out_urb, GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send write URB returns: %i\n", __func__, result); todo = priv->filled - priv->cur_pos; if (todo > 0) msleep(24); } priv->filled = 0; priv->cur_pos = 0; /* start reading (except TWIN and KAAN SIM) */ if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID || priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID) { result = usb_submit_urb(port->interrupt_in_urb, GFP_ATOMIC); dev_dbg(&port->dev, "%s - Send read URB returns: %i\n", __func__, result); } } return count; } static unsigned int kobil_write_room(struct tty_struct *tty) { /* FIXME */ return 8; } static int kobil_tiocmget(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct kobil_private *priv; int result; unsigned char *transfer_buffer; int transfer_buffer_length = 8; priv = usb_get_serial_port_data(port); if (priv->device_type == KOBIL_USBTWIN_PRODUCT_ID || priv->device_type == KOBIL_KAAN_SIM_PRODUCT_ID) { /* This device doesn't support ioctl calls */ return -EINVAL; } /* allocate memory for transfer buffer */ transfer_buffer = kzalloc(transfer_buffer_length, GFP_KERNEL); if (!transfer_buffer) return -ENOMEM; result = usb_control_msg(port->serial->dev, usb_rcvctrlpipe(port->serial->dev, 0), SUSBCRequest_GetStatusLineState, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_IN, 0, 0, transfer_buffer, transfer_buffer_length, KOBIL_TIMEOUT); dev_dbg(&port->dev, "Send get_status_line_state URB returns: %i\n", result); if (result < 1) { if (result >= 0) result = -EIO; goto out_free; } dev_dbg(&port->dev, "Statusline: %02x\n", transfer_buffer[0]); result = 0; if ((transfer_buffer[0] & SUSBCR_GSL_DSR) != 0) result = TIOCM_DSR; out_free: kfree(transfer_buffer); return result; } static int kobil_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct usb_serial_port *port = tty->driver_data; struct device *dev = &port->dev; struct kobil_private *priv; int result; int dtr = 0; int rts = 0; /* FIXME: locking ? */ priv = usb_get_serial_port_data(port); if (priv->device_type == KOBIL_USBTWIN_PRODUCT_ID || priv->device_type == KOBIL_KAAN_SIM_PRODUCT_ID) { /* This device doesn't support ioctl calls */ return -EINVAL; } if (set & TIOCM_RTS) rts = 1; if (set & TIOCM_DTR) dtr = 1; if (clear & TIOCM_RTS) rts = 0; if (clear & TIOCM_DTR) dtr = 0; if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID) { if (dtr != 0) dev_dbg(dev, "%s - Setting DTR\n", __func__); else dev_dbg(dev, "%s - Clearing DTR\n", __func__); result = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_SetStatusLinesOrQueues, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, ((dtr != 0) ? SUSBCR_SSL_SETDTR : SUSBCR_SSL_CLRDTR), 0, NULL, 0, KOBIL_TIMEOUT); } else { if (rts != 0) dev_dbg(dev, "%s - Setting RTS\n", __func__); else dev_dbg(dev, "%s - Clearing RTS\n", __func__); result = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_SetStatusLinesOrQueues, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, ((rts != 0) ? SUSBCR_SSL_SETRTS : SUSBCR_SSL_CLRRTS), 0, NULL, 0, KOBIL_TIMEOUT); } dev_dbg(dev, "%s - Send set_status_line URB returns: %i\n", __func__, result); return (result < 0) ? result : 0; } static void kobil_set_termios(struct tty_struct *tty, struct usb_serial_port *port, const struct ktermios *old) { struct kobil_private *priv; int result; unsigned short urb_val = 0; int c_cflag = tty->termios.c_cflag; speed_t speed; priv = usb_get_serial_port_data(port); if (priv->device_type == KOBIL_USBTWIN_PRODUCT_ID || priv->device_type == KOBIL_KAAN_SIM_PRODUCT_ID) { /* This device doesn't support ioctl calls */ tty_termios_copy_hw(&tty->termios, old); return; } speed = tty_get_baud_rate(tty); switch (speed) { case 1200: urb_val = SUSBCR_SBR_1200; break; default: speed = 9600; fallthrough; case 9600: urb_val = SUSBCR_SBR_9600; break; } urb_val |= (c_cflag & CSTOPB) ? SUSBCR_SPASB_2StopBits : SUSBCR_SPASB_1StopBit; if (c_cflag & PARENB) { if (c_cflag & PARODD) urb_val |= SUSBCR_SPASB_OddParity; else urb_val |= SUSBCR_SPASB_EvenParity; } else urb_val |= SUSBCR_SPASB_NoParity; tty->termios.c_cflag &= ~CMSPAR; tty_encode_baud_rate(tty, speed, speed); result = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_SetBaudRateParityAndStopBits, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, urb_val, 0, NULL, 0, KOBIL_TIMEOUT ); if (result) { dev_err(&port->dev, "failed to update line settings: %d\n", result); } } static int kobil_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct usb_serial_port *port = tty->driver_data; struct kobil_private *priv = usb_get_serial_port_data(port); int result; if (priv->device_type == KOBIL_USBTWIN_PRODUCT_ID || priv->device_type == KOBIL_KAAN_SIM_PRODUCT_ID) /* This device doesn't support ioctl calls */ return -ENOIOCTLCMD; switch (cmd) { case TCFLSH: result = usb_control_msg(port->serial->dev, usb_sndctrlpipe(port->serial->dev, 0), SUSBCRequest_Misc, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT | USB_DIR_OUT, SUSBCR_MSC_ResetAllQueues, 0, NULL, 0, KOBIL_TIMEOUT ); dev_dbg(&port->dev, "%s - Send reset_all_queues (FLUSH) URB returns: %i\n", __func__, result); return (result < 0) ? -EIO: 0; default: return -ENOIOCTLCMD; } } module_usb_serial_driver(serial_drivers, id_table); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 331 3 329 329 1 228 228 1 1 1 1 3 4 1 3 2 2 1 1 12 12 304 304 461 461 32 32 462 459 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) STRATO AG 2012. All rights reserved. */ #include <linux/sched.h> #include <linux/bio.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/kthread.h> #include <linux/math64.h> #include "misc.h" #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "volumes.h" #include "async-thread.h" #include "dev-replace.h" #include "sysfs.h" #include "zoned.h" #include "block-group.h" #include "fs.h" #include "accessors.h" #include "scrub.h" /* * Device replace overview * * [Objective] * To copy all extents (both new and on-disk) from source device to target * device, while still keeping the filesystem read-write. * * [Method] * There are two main methods involved: * * - Write duplication * * All new writes will be written to both target and source devices, so even * if replace gets canceled, sources device still contains up-to-date data. * * Location: handle_ops_on_dev_replace() from btrfs_map_block() * Start: btrfs_dev_replace_start() * End: btrfs_dev_replace_finishing() * Content: Latest data/metadata * * - Copy existing extents * * This happens by reusing scrub facility, as scrub also iterates through * existing extents from commit root. * * Location: scrub_write_block_to_dev_replace() from * scrub_block_complete() * Content: Data/meta from commit root. * * Due to the content difference, we need to avoid nocow write when dev-replace * is happening. This is done by marking the block group read-only and waiting * for NOCOW writes. * * After replace is done, the finishing part is done by swapping the target and * source devices. * * Location: btrfs_dev_replace_update_device_in_mapping_tree() from * btrfs_dev_replace_finishing() */ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret); static int btrfs_dev_replace_kthread(void *data); int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) { struct btrfs_dev_lookup_args args = { .devid = BTRFS_DEV_REPLACE_DEVID }; struct btrfs_key key; struct btrfs_root *dev_root = fs_info->dev_root; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; struct extent_buffer *eb; int slot; int ret = 0; BTRFS_PATH_AUTO_FREE(path); int item_size; struct btrfs_dev_replace_item *ptr; u64 src_devid; if (!dev_root) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = 0; key.type = BTRFS_DEV_REPLACE_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { no_valid_dev_replace_entry_found: /* * We don't have a replace item or it's corrupted. If there is * a replace target, fail the mount. */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, "found replace target device without a valid replace item"); return -EUCLEAN; } dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; dev_replace->cont_reading_from_srcdev_mode = BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS; dev_replace->time_started = 0; dev_replace->time_stopped = 0; atomic64_set(&dev_replace->num_write_errors, 0); atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0); dev_replace->cursor_left = 0; dev_replace->committed_cursor_left = 0; dev_replace->cursor_left_last_write_of_item = 0; dev_replace->cursor_right = 0; dev_replace->srcdev = NULL; dev_replace->tgtdev = NULL; dev_replace->is_valid = 0; dev_replace->item_needs_writeback = 0; return 0; } slot = path->slots[0]; eb = path->nodes[0]; item_size = btrfs_item_size(eb, slot); ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_replace_item); if (item_size != sizeof(struct btrfs_dev_replace_item)) { btrfs_warn(fs_info, "dev_replace entry found has unexpected size, ignore entry"); goto no_valid_dev_replace_entry_found; } src_devid = btrfs_dev_replace_src_devid(eb, ptr); dev_replace->cont_reading_from_srcdev_mode = btrfs_dev_replace_cont_reading_from_srcdev_mode(eb, ptr); dev_replace->replace_state = btrfs_dev_replace_replace_state(eb, ptr); dev_replace->time_started = btrfs_dev_replace_time_started(eb, ptr); dev_replace->time_stopped = btrfs_dev_replace_time_stopped(eb, ptr); atomic64_set(&dev_replace->num_write_errors, btrfs_dev_replace_num_write_errors(eb, ptr)); atomic64_set(&dev_replace->num_uncorrectable_read_errors, btrfs_dev_replace_num_uncorrectable_read_errors(eb, ptr)); dev_replace->cursor_left = btrfs_dev_replace_cursor_left(eb, ptr); dev_replace->committed_cursor_left = dev_replace->cursor_left; dev_replace->cursor_left_last_write_of_item = dev_replace->cursor_left; dev_replace->cursor_right = btrfs_dev_replace_cursor_right(eb, ptr); dev_replace->is_valid = 1; dev_replace->item_needs_writeback = 0; switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: /* * We don't have an active replace item but if there is a * replace target, fail the mount. */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, "replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { dev_replace->srcdev = NULL; dev_replace->tgtdev = NULL; } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices, &args); args.devid = src_devid; dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices, &args); /* * allow 'btrfs dev replace_cancel' if src/tgt device is * missing */ if (!dev_replace->srcdev && !btrfs_test_opt(fs_info, DEGRADED)) { ret = -EIO; btrfs_warn(fs_info, "cannot mount because device replace operation is ongoing and"); btrfs_warn(fs_info, "srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?", src_devid); } if (!dev_replace->tgtdev && !btrfs_test_opt(fs_info, DEGRADED)) { ret = -EIO; btrfs_warn(fs_info, "cannot mount because device replace operation is ongoing and"); btrfs_warn(fs_info, "tgtdev (devid %llu) is missing, need to run 'btrfs dev scan'?", BTRFS_DEV_REPLACE_DEVID); } if (dev_replace->tgtdev) { if (dev_replace->srcdev) { dev_replace->tgtdev->total_bytes = dev_replace->srcdev->total_bytes; dev_replace->tgtdev->disk_total_bytes = dev_replace->srcdev->disk_total_bytes; dev_replace->tgtdev->commit_total_bytes = dev_replace->srcdev->commit_total_bytes; dev_replace->tgtdev->bytes_used = dev_replace->srcdev->bytes_used; dev_replace->tgtdev->commit_bytes_used = dev_replace->srcdev->commit_bytes_used; } set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &dev_replace->tgtdev->dev_state); WARN_ON(fs_info->fs_devices->rw_devices == 0); dev_replace->tgtdev->io_width = fs_info->sectorsize; dev_replace->tgtdev->io_align = fs_info->sectorsize; dev_replace->tgtdev->sector_size = fs_info->sectorsize; dev_replace->tgtdev->fs_info = fs_info; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev_replace->tgtdev->dev_state); } break; } return ret; } /* * Initialize a new device for device replace target from a given source dev * and path. * * Return 0 and new device in @device_out, otherwise return < 0 */ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, const char *device_path, struct btrfs_device *srcdev, struct btrfs_device **device_out) { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; struct file *bdev_file; struct block_device *bdev; u64 devid = BTRFS_DEV_REPLACE_DEVID; int ret = 0; *device_out = NULL; if (srcdev->fs_devices->seeding) { btrfs_err(fs_info, "the filesystem is a seed filesystem!"); return -EINVAL; } bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE, fs_info->bdev_holder, NULL); if (IS_ERR(bdev_file)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); return PTR_ERR(bdev_file); } bdev = file_bdev(bdev_file); if (!btrfs_check_device_zone_type(fs_info, bdev)) { btrfs_err(fs_info, "dev-replace: zoned type of target device mismatch with filesystem"); ret = -EINVAL; goto error; } sync_blockdev(bdev); list_for_each_entry(device, &fs_devices->devices, dev_list) { if (device->bdev == bdev) { btrfs_err(fs_info, "target device is in the filesystem!"); ret = -EEXIST; goto error; } } if (bdev_nr_bytes(bdev) < btrfs_device_get_total_bytes(srcdev)) { btrfs_err(fs_info, "target device is smaller than source device!"); ret = -EINVAL; goto error; } device = btrfs_alloc_device(NULL, &devid, NULL, device_path); if (IS_ERR(device)) { ret = PTR_ERR(device); goto error; } ret = lookup_bdev(device_path, &device->devt); if (ret) goto error; set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); device->generation = 0; device->io_width = fs_info->sectorsize; device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; device->total_bytes = btrfs_device_get_total_bytes(srcdev); device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev); device->bytes_used = btrfs_device_get_bytes_used(srcdev); device->commit_total_bytes = srcdev->commit_total_bytes; device->commit_bytes_used = device->bytes_used; device->fs_info = fs_info; device->bdev = bdev; device->bdev_file = bdev_file; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); device->dev_stats_valid = 1; set_blocksize(bdev_file, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; ret = btrfs_get_dev_zone_info(device, false); if (ret) goto error; mutex_lock(&fs_devices->device_list_mutex); list_add(&device->dev_list, &fs_devices->devices); fs_devices->num_devices++; fs_devices->open_devices++; mutex_unlock(&fs_devices->device_list_mutex); *device_out = device; return 0; error: fput(bdev_file); return ret; } /* * called from commit_transaction. Writes changed device replace state to * disk. */ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; struct btrfs_root *dev_root = fs_info->dev_root; BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct extent_buffer *eb; struct btrfs_dev_replace_item *ptr; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; down_read(&dev_replace->rwsem); if (!dev_replace->is_valid || !dev_replace->item_needs_writeback) { up_read(&dev_replace->rwsem); return 0; } up_read(&dev_replace->rwsem); key.objectid = 0; key.type = BTRFS_DEV_REPLACE_KEY; key.offset = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); if (ret < 0) { btrfs_warn(fs_info, "error %d while searching for dev_replace item!", ret); return ret; } if (ret == 0 && btrfs_item_size(path->nodes[0], path->slots[0]) < sizeof(*ptr)) { /* * need to delete old one and insert a new one. * Since no attempt is made to recover any old state, if the * dev_replace state is 'running', the data on the target * drive is lost. * It would be possible to recover the state: just make sure * that the beginning of the item is never changed and always * contains all the essential information. Then read this * minimal set of information and use it as a base for the * new state. */ ret = btrfs_del_item(trans, dev_root, path); if (ret != 0) { btrfs_warn(fs_info, "delete too small dev_replace item failed %d!", ret); return ret; } ret = 1; } if (ret == 1) { /* need to insert a new item */ btrfs_release_path(path); ret = btrfs_insert_empty_item(trans, dev_root, path, &key, sizeof(*ptr)); if (ret < 0) { btrfs_warn(fs_info, "insert dev_replace item failed %d!", ret); return ret; } } eb = path->nodes[0]; ptr = btrfs_item_ptr(eb, path->slots[0], struct btrfs_dev_replace_item); down_write(&dev_replace->rwsem); if (dev_replace->srcdev) btrfs_set_dev_replace_src_devid(eb, ptr, dev_replace->srcdev->devid); else btrfs_set_dev_replace_src_devid(eb, ptr, (u64)-1); btrfs_set_dev_replace_cont_reading_from_srcdev_mode(eb, ptr, dev_replace->cont_reading_from_srcdev_mode); btrfs_set_dev_replace_replace_state(eb, ptr, dev_replace->replace_state); btrfs_set_dev_replace_time_started(eb, ptr, dev_replace->time_started); btrfs_set_dev_replace_time_stopped(eb, ptr, dev_replace->time_stopped); btrfs_set_dev_replace_num_write_errors(eb, ptr, atomic64_read(&dev_replace->num_write_errors)); btrfs_set_dev_replace_num_uncorrectable_read_errors(eb, ptr, atomic64_read(&dev_replace->num_uncorrectable_read_errors)); dev_replace->cursor_left_last_write_of_item = dev_replace->cursor_left; btrfs_set_dev_replace_cursor_left(eb, ptr, dev_replace->cursor_left_last_write_of_item); btrfs_set_dev_replace_cursor_right(eb, ptr, dev_replace->cursor_right); dev_replace->item_needs_writeback = 0; up_write(&dev_replace->rwsem); return ret; } static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, struct btrfs_device *src_dev) { struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_root *root = fs_info->dev_root; struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_block_group *cache; struct btrfs_trans_handle *trans; int iter_ret = 0; int ret = 0; u64 chunk_offset; /* Do not use "to_copy" on non zoned filesystem for now */ if (!btrfs_is_zoned(fs_info)) return 0; mutex_lock(&fs_info->chunk_mutex); /* Ensure we don't have pending new block group */ spin_lock(&fs_info->trans_lock); while (fs_info->running_transaction && !list_empty(&fs_info->running_transaction->dev_update_list)) { spin_unlock(&fs_info->trans_lock); mutex_unlock(&fs_info->chunk_mutex); trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); mutex_lock(&fs_info->chunk_mutex); if (ret == -ENOENT) { spin_lock(&fs_info->trans_lock); continue; } else { goto unlock; } } ret = btrfs_commit_transaction(trans); mutex_lock(&fs_info->chunk_mutex); if (ret) goto unlock; spin_lock(&fs_info->trans_lock); } spin_unlock(&fs_info->trans_lock); path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto unlock; } path->reada = READA_FORWARD; path->search_commit_root = 1; path->skip_locking = 1; key.objectid = src_dev->devid; key.type = BTRFS_DEV_EXTENT_KEY; key.offset = 0; btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) { struct extent_buffer *leaf = path->nodes[0]; if (found_key.objectid != src_dev->devid) break; if (found_key.type != BTRFS_DEV_EXTENT_KEY) break; if (found_key.offset < key.offset) break; dev_extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent); cache = btrfs_lookup_block_group(fs_info, chunk_offset); if (!cache) continue; set_bit(BLOCK_GROUP_FLAG_TO_COPY, &cache->runtime_flags); btrfs_put_block_group(cache); } if (iter_ret < 0) ret = iter_ret; btrfs_free_path(path); unlock: mutex_unlock(&fs_info->chunk_mutex); return ret; } bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, struct btrfs_block_group *cache, u64 physical) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_chunk_map *map; u64 chunk_offset = cache->start; int num_extents, cur_extent; int i; /* Do not use "to_copy" on non zoned filesystem for now */ if (!btrfs_is_zoned(fs_info)) return true; spin_lock(&cache->lock); if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &cache->runtime_flags)) { spin_unlock(&cache->lock); return true; } spin_unlock(&cache->lock); map = btrfs_get_chunk_map(fs_info, chunk_offset, 1); ASSERT(!IS_ERR(map)); num_extents = 0; cur_extent = 0; for (i = 0; i < map->num_stripes; i++) { /* We have more device extent to copy */ if (srcdev != map->stripes[i].dev) continue; num_extents++; if (physical == map->stripes[i].physical) cur_extent = i; } btrfs_free_chunk_map(map); if (num_extents > 1 && cur_extent < num_extents - 1) { /* * Has more stripes on this device. Keep this block group * readonly until we finish all the stripes. */ return false; } /* Last stripe on this device */ clear_bit(BLOCK_GROUP_FLAG_TO_COPY, &cache->runtime_flags); return true; } static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, const char *tgtdev_name, u64 srcdevid, const char *srcdev_name, int read_src) { struct btrfs_root *root = fs_info->dev_root; struct btrfs_trans_handle *trans; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; int ret; struct btrfs_device *tgt_device = NULL; struct btrfs_device *src_device = NULL; src_device = btrfs_find_device_by_devspec(fs_info, srcdevid, srcdev_name); if (IS_ERR(src_device)) return PTR_ERR(src_device); if (btrfs_pinned_by_swapfile(fs_info, src_device)) { btrfs_warn_in_rcu(fs_info, "cannot replace device %s (devid %llu) due to active swapfile", btrfs_dev_name(src_device), src_device->devid); return -ETXTBSY; } /* * Here we commit the transaction to make sure commit_total_bytes * of all the devices are updated. */ trans = btrfs_attach_transaction(root); if (!IS_ERR(trans)) { ret = btrfs_commit_transaction(trans); if (ret) return ret; } else if (PTR_ERR(trans) != -ENOENT) { return PTR_ERR(trans); } ret = btrfs_init_dev_replace_tgtdev(fs_info, tgtdev_name, src_device, &tgt_device); if (ret) return ret; ret = mark_block_group_to_copy(fs_info, src_device); if (ret) return ret; down_write(&dev_replace->rwsem); dev_replace->replace_task = current; switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: DEBUG_WARN("unexpected STARTED ot SUSPENDED dev-replace state"); ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED; up_write(&dev_replace->rwsem); goto leave; } dev_replace->cont_reading_from_srcdev_mode = read_src; dev_replace->srcdev = src_device; dev_replace->tgtdev = tgt_device; btrfs_info_in_rcu(fs_info, "dev_replace from %s (devid %llu) to %s started", btrfs_dev_name(src_device), src_device->devid, btrfs_dev_name(tgt_device)); /* * from now on, the writes to the srcdev are all duplicated to * go to the tgtdev as well (refer to btrfs_map_block()). */ dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED; dev_replace->time_started = ktime_get_real_seconds(); dev_replace->cursor_left = 0; dev_replace->committed_cursor_left = 0; dev_replace->cursor_left_last_write_of_item = 0; dev_replace->cursor_right = 0; dev_replace->is_valid = 1; dev_replace->item_needs_writeback = 1; atomic64_set(&dev_replace->num_write_errors, 0); atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0); up_write(&dev_replace->rwsem); ret = btrfs_sysfs_add_device(tgt_device); if (ret) btrfs_err(fs_info, "kobj add dev failed %d", ret); btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL); /* * Commit dev_replace state and reserve 1 item for it. * This is crucial to ensure we won't miss copying extents for new block * groups that are allocated after we started the device replace, and * must be done after setting up the device replace state. */ trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); down_write(&dev_replace->rwsem); dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; dev_replace->srcdev = NULL; dev_replace->tgtdev = NULL; up_write(&dev_replace->rwsem); goto leave; } ret = btrfs_commit_transaction(trans); WARN_ON(ret); /* the disk copy procedure reuses the scrub code */ ret = btrfs_scrub_dev(fs_info, src_device->devid, 0, btrfs_device_get_total_bytes(src_device), &dev_replace->scrub_progress, 0, 1); ret = btrfs_dev_replace_finishing(fs_info, ret); if (ret == -EINPROGRESS) ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS; return ret; leave: btrfs_destroy_dev_replace_tgtdev(tgt_device); return ret; } static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args) { if (args->start.srcdevid == 0) { if (memchr(args->start.srcdev_name, 0, sizeof(args->start.srcdev_name)) == NULL) return -ENAMETOOLONG; } else { args->start.srcdev_name[0] = 0; } if (memchr(args->start.tgtdev_name, 0, sizeof(args->start.tgtdev_name)) == NULL) return -ENAMETOOLONG; return 0; } int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { int ret; switch (args->start.cont_reading_from_srcdev_mode) { case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS: case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID: break; default: return -EINVAL; } ret = btrfs_check_replace_dev_names(args); if (ret < 0) return ret; ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name, args->start.srcdevid, args->start.srcdev_name, args->start.cont_reading_from_srcdev_mode); args->result = ret; /* don't warn if EINPROGRESS, someone else might be running scrub */ if (ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS || ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR) return 0; return ret; } /* * blocked until all in-flight bios operations are finished. */ static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info) { set_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state); wait_event(fs_info->dev_replace.replace_wait, !percpu_counter_sum( &fs_info->dev_replace.bio_counter)); } /* * we have removed target device, it is safe to allow new bios request. */ static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info) { clear_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state); wake_up(&fs_info->dev_replace.replace_wait); } /* * When finishing the device replace, before swapping the source device with the * target device we must update the chunk allocation state in the target device, * as it is empty because replace works by directly copying the chunks and not * through the normal chunk allocation path. */ static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev, struct btrfs_device *tgtdev) { struct extent_state *cached_state = NULL; u64 start = 0; u64 found_start; u64 found_end; int ret = 0; lockdep_assert_held(&srcdev->fs_info->chunk_mutex); while (btrfs_find_first_extent_bit(&srcdev->alloc_state, start, &found_start, &found_end, CHUNK_ALLOCATED, &cached_state)) { ret = btrfs_set_extent_bit(&tgtdev->alloc_state, found_start, found_end, CHUNK_ALLOCATED, NULL); if (ret) break; start = found_end + 1; } btrfs_free_extent_state(cached_state); return ret; } static void btrfs_dev_replace_update_device_in_mapping_tree( struct btrfs_fs_info *fs_info, struct btrfs_device *srcdev, struct btrfs_device *tgtdev) { struct rb_node *node; /* * The chunk mutex must be held so that no new chunks can be created * while we are updating existing chunks. This guarantees we don't miss * any new chunk that gets created for a range that falls before the * range of the last chunk we processed. */ lockdep_assert_held(&fs_info->chunk_mutex); write_lock(&fs_info->mapping_tree_lock); node = rb_first_cached(&fs_info->mapping_tree); while (node) { struct rb_node *next = rb_next(node); struct btrfs_chunk_map *map; u64 next_start; map = rb_entry(node, struct btrfs_chunk_map, rb_node); next_start = map->start + map->chunk_len; for (int i = 0; i < map->num_stripes; i++) if (srcdev == map->stripes[i].dev) map->stripes[i].dev = tgtdev; if (cond_resched_rwlock_write(&fs_info->mapping_tree_lock)) { map = btrfs_find_chunk_map_nolock(fs_info, next_start, U64_MAX); if (!map) break; node = &map->rb_node; /* * Drop the lookup reference since we are holding the * lock in write mode and no one can remove the chunk * map from the tree and drop its tree reference. */ btrfs_free_chunk_map(map); } else { node = next; } } write_unlock(&fs_info->mapping_tree_lock); } static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *tgt_device; struct btrfs_device *src_device; struct btrfs_root *root = fs_info->tree_root; u8 uuid_tmp[BTRFS_UUID_SIZE]; struct btrfs_trans_handle *trans; int ret = 0; /* don't allow cancel or unmount to disturb the finishing procedure */ mutex_lock(&dev_replace->lock_finishing_cancel_unmount); down_read(&dev_replace->rwsem); /* was the operation canceled, or is it finished? */ if (dev_replace->replace_state != BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED) { up_read(&dev_replace->rwsem); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return 0; } tgt_device = dev_replace->tgtdev; src_device = dev_replace->srcdev; up_read(&dev_replace->rwsem); /* * flush all outstanding I/O and inode extent mappings before the * copy operation is declared as being finished */ ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL); /* * We have to use this loop approach because at this point src_device * has to be available for transaction commit to complete, yet new * chunks shouldn't be allocated on the device. */ while (1) { trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return PTR_ERR(trans); } ret = btrfs_commit_transaction(trans); WARN_ON(ret); /* Prevent write_all_supers() during the finishing procedure */ mutex_lock(&fs_devices->device_list_mutex); /* Prevent new chunks being allocated on the source device */ mutex_lock(&fs_info->chunk_mutex); if (!list_empty(&src_device->post_commit_list)) { mutex_unlock(&fs_devices->device_list_mutex); mutex_unlock(&fs_info->chunk_mutex); } else { break; } } down_write(&dev_replace->rwsem); dev_replace->replace_state = scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED; dev_replace->tgtdev = NULL; dev_replace->srcdev = NULL; dev_replace->time_stopped = ktime_get_real_seconds(); dev_replace->item_needs_writeback = 1; /* * Update allocation state in the new device and replace the old device * with the new one in the mapping tree. */ if (!scrub_ret) { scrub_ret = btrfs_set_target_alloc_state(src_device, tgt_device); if (scrub_ret) goto error; btrfs_dev_replace_update_device_in_mapping_tree(fs_info, src_device, tgt_device); } else { if (scrub_ret != -ECANCELED) btrfs_err_in_rcu(fs_info, "btrfs_scrub_dev(%s, %llu, %s) failed %d", btrfs_dev_name(src_device), src_device->devid, btrfs_dev_name(tgt_device), scrub_ret); error: up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_devices->device_list_mutex); btrfs_rm_dev_replace_blocked(fs_info); if (tgt_device) btrfs_destroy_dev_replace_tgtdev(tgt_device); btrfs_rm_dev_replace_unblocked(fs_info); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return scrub_ret; } btrfs_info_in_rcu(fs_info, "dev_replace from %s (devid %llu) to %s finished", btrfs_dev_name(src_device), src_device->devid, btrfs_dev_name(tgt_device)); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &tgt_device->dev_state); tgt_device->devid = src_device->devid; src_device->devid = BTRFS_DEV_REPLACE_DEVID; memcpy(uuid_tmp, tgt_device->uuid, sizeof(uuid_tmp)); memcpy(tgt_device->uuid, src_device->uuid, sizeof(tgt_device->uuid)); memcpy(src_device->uuid, uuid_tmp, sizeof(src_device->uuid)); btrfs_device_set_total_bytes(tgt_device, src_device->total_bytes); btrfs_device_set_disk_total_bytes(tgt_device, src_device->disk_total_bytes); btrfs_device_set_bytes_used(tgt_device, src_device->bytes_used); tgt_device->commit_bytes_used = src_device->bytes_used; btrfs_assign_next_active_device(src_device, tgt_device); list_add(&tgt_device->dev_alloc_list, &fs_devices->alloc_list); fs_devices->rw_devices++; dev_replace->replace_task = NULL; up_write(&dev_replace->rwsem); btrfs_rm_dev_replace_blocked(fs_info); btrfs_rm_dev_replace_remove_srcdev(src_device); btrfs_rm_dev_replace_unblocked(fs_info); /* * Increment dev_stats_ccnt so that btrfs_run_dev_stats() will * update on-disk dev stats value during commit transaction */ atomic_inc(&tgt_device->dev_stats_ccnt); /* * this is again a consistent state where no dev_replace procedure * is running, the target device is part of the filesystem, the * source device is not part of the filesystem anymore and its 1st * superblock is scratched out so that it is no longer marked to * belong to this filesystem. */ mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_devices->device_list_mutex); /* replace the sysfs entry */ btrfs_sysfs_remove_device(src_device); btrfs_sysfs_update_devid(tgt_device); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state)) btrfs_scratch_superblocks(fs_info, src_device); /* write back the superblocks */ trans = btrfs_start_transaction(root, 0); if (!IS_ERR(trans)) btrfs_commit_transaction(trans); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); btrfs_rm_dev_replace_free_srcdev(src_device); return 0; } /* * Read progress of device replace status according to the state and last * stored position. The value format is the same as for * btrfs_dev_replace::progress_1000 */ static u64 btrfs_dev_replace_progress(struct btrfs_fs_info *fs_info) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; u64 ret = 0; switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: ret = 0; break; case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: ret = 1000; break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: ret = div64_u64(dev_replace->cursor_left, div_u64(btrfs_device_get_total_bytes( dev_replace->srcdev), 1000)); break; } return ret; } void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; down_read(&dev_replace->rwsem); /* even if !dev_replace_is_valid, the values are good enough for * the replace_status ioctl */ args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; args->status.replace_state = dev_replace->replace_state; args->status.time_started = dev_replace->time_started; args->status.time_stopped = dev_replace->time_stopped; args->status.num_write_errors = atomic64_read(&dev_replace->num_write_errors); args->status.num_uncorrectable_read_errors = atomic64_read(&dev_replace->num_uncorrectable_read_errors); args->status.progress_1000 = btrfs_dev_replace_progress(fs_info); up_read(&dev_replace->rwsem); } int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; struct btrfs_device *tgt_device = NULL; struct btrfs_device *src_device = NULL; struct btrfs_trans_handle *trans; struct btrfs_root *root = fs_info->tree_root; int result; int ret; if (sb_rdonly(fs_info->sb)) return -EROFS; mutex_lock(&dev_replace->lock_finishing_cancel_unmount); down_write(&dev_replace->rwsem); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED; up_write(&dev_replace->rwsem); break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: tgt_device = dev_replace->tgtdev; src_device = dev_replace->srcdev; up_write(&dev_replace->rwsem); ret = btrfs_scrub_cancel(fs_info); if (ret < 0) { result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED; } else { result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; /* * btrfs_dev_replace_finishing() will handle the * cleanup part */ btrfs_info_in_rcu(fs_info, "dev_replace from %s (devid %llu) to %s canceled", btrfs_dev_name(src_device), src_device->devid, btrfs_dev_name(tgt_device)); } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: /* * Scrub doing the replace isn't running so we need to do the * cleanup step of btrfs_dev_replace_finishing() here */ result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; tgt_device = dev_replace->tgtdev; src_device = dev_replace->srcdev; dev_replace->tgtdev = NULL; dev_replace->srcdev = NULL; dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED; dev_replace->time_stopped = ktime_get_real_seconds(); dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); /* Scrub for replace must not be running in suspended state */ btrfs_scrub_cancel(fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return PTR_ERR(trans); } ret = btrfs_commit_transaction(trans); WARN_ON(ret); btrfs_info_in_rcu(fs_info, "suspended dev_replace from %s (devid %llu) to %s canceled", btrfs_dev_name(src_device), src_device->devid, btrfs_dev_name(tgt_device)); if (tgt_device) btrfs_destroy_dev_replace_tgtdev(tgt_device); break; default: up_write(&dev_replace->rwsem); result = -EINVAL; } mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return result; } void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; mutex_lock(&dev_replace->lock_finishing_cancel_unmount); down_write(&dev_replace->rwsem); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED; dev_replace->time_stopped = ktime_get_real_seconds(); dev_replace->item_needs_writeback = 1; btrfs_info(fs_info, "suspending dev_replace for unmount"); break; } up_write(&dev_replace->rwsem); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); } /* resume dev_replace procedure that was interrupted by unmount */ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info) { struct task_struct *task; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; down_write(&dev_replace->rwsem); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: up_write(&dev_replace->rwsem); return 0; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: break; case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED; break; } if (!dev_replace->tgtdev || !dev_replace->tgtdev->bdev) { btrfs_info(fs_info, "cannot continue dev_replace, tgtdev is missing"); btrfs_info(fs_info, "you may cancel the operation after 'mount -o degraded'"); dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED; up_write(&dev_replace->rwsem); return 0; } up_write(&dev_replace->rwsem); /* * This could collide with a paused balance, but the exclusive op logic * should never allow both to start and pause. We don't want to allow * dev-replace to start anyway. */ if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REPLACE)) { down_write(&dev_replace->rwsem); dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED; up_write(&dev_replace->rwsem); btrfs_info(fs_info, "cannot resume dev-replace, other exclusive operation running"); return 0; } task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl"); return PTR_ERR_OR_ZERO(task); } static int btrfs_dev_replace_kthread(void *data) { struct btrfs_fs_info *fs_info = data; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; u64 progress; int ret; progress = btrfs_dev_replace_progress(fs_info); progress = div_u64(progress, 10); btrfs_info_in_rcu(fs_info, "continuing dev_replace from %s (devid %llu) to target %s @%u%%", btrfs_dev_name(dev_replace->srcdev), dev_replace->srcdev->devid, btrfs_dev_name(dev_replace->tgtdev), (unsigned int)progress); ret = btrfs_scrub_dev(fs_info, dev_replace->srcdev->devid, dev_replace->committed_cursor_left, btrfs_device_get_total_bytes(dev_replace->srcdev), &dev_replace->scrub_progress, 0, 1); ret = btrfs_dev_replace_finishing(fs_info, ret); WARN_ON(ret && ret != -ECANCELED); btrfs_exclop_finish(fs_info); return 0; } bool __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace) { if (!dev_replace->is_valid) return false; switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: return false; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: /* * return true even if tgtdev is missing (this is * something that can happen if the dev_replace * procedure is suspended by an umount and then * the tgtdev is missing (or "btrfs dev scan") was * not called and the filesystem is remounted * in degraded state. This does not stop the * dev_replace procedure. It needs to be canceled * manually if the cancellation is wanted. */ break; } return true; } void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount) { percpu_counter_sub(&fs_info->dev_replace.bio_counter, amount); cond_wake_up_nomb(&fs_info->dev_replace.replace_wait); } void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info) { while (1) { percpu_counter_inc(&fs_info->dev_replace.bio_counter); if (likely(!test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state))) break; btrfs_bio_counter_dec(fs_info); wait_event(fs_info->dev_replace.replace_wait, !test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state)); } } |
| 35 7 28 35 35 35 1 16 16 15 1 16 16 16 16 16 16 16 16 9 9 9 16 16 28 34 1 34 27 27 12 15 27 27 27 27 35 35 27 1 1 1 1 1 2 1 35 7 11 9 7 16 7 5 2 8 2 19 2 8 1 7 2 2 2 48 1 1 47 45 47 1 35 35 1 35 16 19 35 35 25 10 29 6 35 7 28 18 9 1 28 19 9 22 6 28 27 27 27 27 27 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 | // SPDX-License-Identifier: GPL-2.0+ // // em28xx-cards.c - driver for Empia EM2800/EM2820/2840 USB // video capture devices // // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it> // Markus Rechberger <mrechberger@gmail.com> // Mauro Carvalho Chehab <mchehab@kernel.org> // Sascha Sommer <saschasommer@freenet.de> // Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com> #include "em28xx.h" #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/i2c.h> #include <linux/usb.h> #include <media/tuner.h> #include <media/drv-intf/msp3400.h> #include <media/i2c/saa7115.h> #include <dt-bindings/media/tvp5150.h> #include <media/i2c/tvaudio.h> #include <media/tveeprom.h> #include <media/v4l2-common.h> #include <sound/ac97_codec.h> #define DRIVER_NAME "em28xx" static int tuner = -1; module_param(tuner, int, 0444); MODULE_PARM_DESC(tuner, "tuner type"); static unsigned int disable_ir; module_param(disable_ir, int, 0444); MODULE_PARM_DESC(disable_ir, "disable infrared remote support"); static unsigned int disable_usb_speed_check; module_param(disable_usb_speed_check, int, 0444); MODULE_PARM_DESC(disable_usb_speed_check, "override min bandwidth requirement of 480M bps"); static unsigned int card[] = {[0 ... (EM28XX_MAXBOARDS - 1)] = -1U }; module_param_array(card, int, NULL, 0444); MODULE_PARM_DESC(card, "card type"); static int usb_xfer_mode = -1; module_param(usb_xfer_mode, int, 0444); MODULE_PARM_DESC(usb_xfer_mode, "USB transfer mode for frame data (-1 = auto, 0 = prefer isoc, 1 = prefer bulk)"); /* Bitmask marking allocated devices from 0 to EM28XX_MAXBOARDS - 1 */ static DECLARE_BITMAP(em28xx_devused, EM28XX_MAXBOARDS); struct em28xx_hash_table { unsigned long hash; unsigned int model; unsigned int tuner; }; static void em28xx_pre_card_setup(struct em28xx *dev); /* * Reset sequences for analog/digital modes */ /* Reset for the most [analog] boards */ static const struct em28xx_reg_seq default_analog[] = { {EM2820_R08_GPIO_CTRL, 0x6d, ~EM_GPIO_4, 10}, { -1, -1, -1, -1}, }; /* Reset for the most [digital] boards */ static const struct em28xx_reg_seq default_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6e, ~EM_GPIO_4, 10}, { -1, -1, -1, -1}, }; /* Board :Zolid Hybrid Tv Stick */ static struct em28xx_reg_seq zolid_tuner[] = { {EM2820_R08_GPIO_CTRL, 0xfd, 0xff, 100}, {EM2820_R08_GPIO_CTRL, 0xfe, 0xff, 100}, { -1, -1, -1, -1}, }; static struct em28xx_reg_seq zolid_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6a, 0xff, 100}, {EM2820_R08_GPIO_CTRL, 0x7a, 0xff, 100}, {EM2880_R04_GPO, 0x04, 0xff, 100}, {EM2880_R04_GPO, 0x0c, 0xff, 100}, { -1, -1, -1, -1}, }; /* Board Hauppauge WinTV HVR 900 analog */ static const struct em28xx_reg_seq hauppauge_wintv_hvr_900_analog[] = { {EM2820_R08_GPIO_CTRL, 0x2d, ~EM_GPIO_4, 10}, { 0x05, 0xff, 0x10, 10}, { -1, -1, -1, -1}, }; /* Board Hauppauge WinTV HVR 900 digital */ static const struct em28xx_reg_seq hauppauge_wintv_hvr_900_digital[] = { {EM2820_R08_GPIO_CTRL, 0x2e, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x04, 0x0f, 10}, {EM2880_R04_GPO, 0x0c, 0x0f, 10}, { -1, -1, -1, -1}, }; /* Board Hauppauge WinTV HVR 900 (R2) digital */ static const struct em28xx_reg_seq hauppauge_wintv_hvr_900R2_digital[] = { {EM2820_R08_GPIO_CTRL, 0x2e, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x0c, 0x0f, 10}, { -1, -1, -1, -1}, }; /* Boards - EM2880 MSI DIGIVOX AD and EM2880_BOARD_MSI_DIGIVOX_AD_II */ static const struct em28xx_reg_seq em2880_msi_digivox_ad_analog[] = { {EM2820_R08_GPIO_CTRL, 0x69, ~EM_GPIO_4, 10}, { -1, -1, -1, -1}, }; /* Board - EM2882 Kworld 315U digital */ static const struct em28xx_reg_seq em2882_kworld_315u_digital[] = { {EM2820_R08_GPIO_CTRL, 0xff, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0xfe, 0xff, 10}, {EM2880_R04_GPO, 0x04, 0xff, 10}, {EM2880_R04_GPO, 0x0c, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0x7e, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq em2882_kworld_315u_tuner_gpio[] = { {EM2880_R04_GPO, 0x08, 0xff, 10}, {EM2880_R04_GPO, 0x0c, 0xff, 10}, {EM2880_R04_GPO, 0x08, 0xff, 10}, {EM2880_R04_GPO, 0x0c, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq kworld_330u_analog[] = { {EM2820_R08_GPIO_CTRL, 0x6d, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x00, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq kworld_330u_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6e, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x08, 0xff, 10}, { -1, -1, -1, -1}, }; /* * Evga inDtube * GPIO0 - Enable digital power (s5h1409) - low to enable * GPIO1 - Enable analog power (tvp5150/emp202) - low to enable * GPIO4 - xc3028 reset * GOP3 - s5h1409 reset */ static const struct em28xx_reg_seq evga_indtube_analog[] = { {EM2820_R08_GPIO_CTRL, 0x79, 0xff, 60}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq evga_indtube_digital[] = { {EM2820_R08_GPIO_CTRL, 0x7a, 0xff, 1}, {EM2880_R04_GPO, 0x04, 0xff, 10}, {EM2880_R04_GPO, 0x0c, 0xff, 1}, { -1, -1, -1, -1}, }; /* * KWorld PlusTV 340U, UB435-Q and UB435-Q V2 (ATSC) GPIOs map: * EM_GPIO_0 - currently unknown * EM_GPIO_1 - LED disable/enable (1 = off, 0 = on) * EM_GPIO_2 - currently unknown * EM_GPIO_3 - currently unknown * EM_GPIO_4 - TDA18271HD/C1 tuner (1 = active, 0 = in reset) * EM_GPIO_5 - LGDT3304 ATSC/QAM demod (1 = active, 0 = in reset) * EM_GPIO_6 - currently unknown * EM_GPIO_7 - currently unknown */ static const struct em28xx_reg_seq kworld_a340_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6d, ~EM_GPIO_4, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq kworld_ub435q_v3_digital[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xfe, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xbe, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xfe, 0xff, 100}, { -1, -1, -1, -1}, }; /* Pinnacle Hybrid Pro eb1a:2881 */ static const struct em28xx_reg_seq pinnacle_hybrid_pro_analog[] = { {EM2820_R08_GPIO_CTRL, 0xfd, ~EM_GPIO_4, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq pinnacle_hybrid_pro_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6e, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x04, 0xff, 100},/* zl10353 reset */ {EM2880_R04_GPO, 0x0c, 0xff, 1}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq terratec_cinergy_USB_XS_FR_analog[] = { {EM2820_R08_GPIO_CTRL, 0x6d, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x00, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq terratec_cinergy_USB_XS_FR_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6e, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x08, 0xff, 10}, { -1, -1, -1, -1}, }; /* * PCTV HD Mini (80e) GPIOs * 0-5: not used * 6: demod reset, active low * 7: LED on, active high */ static const struct em28xx_reg_seq em2874_pctv_80e_digital[] = { {EM28XX_R06_I2C_CLK, 0x45, 0xff, 10}, /*400 KHz*/ {EM2874_R80_GPIO_P0_CTRL, 0x00, 0xff, 100},/*Demod reset*/ {EM2874_R80_GPIO_P0_CTRL, 0x40, 0xff, 10}, { -1, -1, -1, -1}, }; /* * eb1a:2868 Reddo DVB-C USB TV Box * GPIO4 - CU1216L NIM * Other GPIOs seems to be don't care. */ static const struct em28xx_reg_seq reddo_dvb_c_usb_box[] = { {EM2820_R08_GPIO_CTRL, 0xfe, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0xde, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0xfe, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0xff, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0x7f, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0x6f, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0xff, 0xff, 10}, { -1, -1, -1, -1}, }; /* Callback for the most boards */ static const struct em28xx_reg_seq default_tuner_gpio[] = { {EM2820_R08_GPIO_CTRL, EM_GPIO_4, EM_GPIO_4, 10}, {EM2820_R08_GPIO_CTRL, 0, EM_GPIO_4, 10}, {EM2820_R08_GPIO_CTRL, EM_GPIO_4, EM_GPIO_4, 10}, { -1, -1, -1, -1}, }; /* Mute/unmute */ static const struct em28xx_reg_seq compro_unmute_tv_gpio[] = { {EM2820_R08_GPIO_CTRL, 5, 7, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq compro_unmute_svid_gpio[] = { {EM2820_R08_GPIO_CTRL, 4, 7, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq compro_mute_gpio[] = { {EM2820_R08_GPIO_CTRL, 6, 7, 10}, { -1, -1, -1, -1}, }; /* Terratec AV350 */ static const struct em28xx_reg_seq terratec_av350_mute_gpio[] = { {EM2820_R08_GPIO_CTRL, 0xff, 0x7f, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq terratec_av350_unmute_gpio[] = { {EM2820_R08_GPIO_CTRL, 0xff, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq silvercrest_reg_seq[] = { {EM2820_R08_GPIO_CTRL, 0xff, 0xff, 10}, {EM2820_R08_GPIO_CTRL, 0x01, 0xf7, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq vc211a_enable[] = { {EM2820_R08_GPIO_CTRL, 0xff, 0x07, 10}, {EM2820_R08_GPIO_CTRL, 0xff, 0x0f, 10}, {EM2820_R08_GPIO_CTRL, 0xff, 0x0b, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq dikom_dk300_digital[] = { {EM2820_R08_GPIO_CTRL, 0x6e, ~EM_GPIO_4, 10}, {EM2880_R04_GPO, 0x08, 0xff, 10}, { -1, -1, -1, -1}, }; /* Reset for the most [digital] boards */ static const struct em28xx_reg_seq leadership_digital[] = { {EM2874_R80_GPIO_P0_CTRL, 0x70, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq leadership_reset[] = { {EM2874_R80_GPIO_P0_CTRL, 0xf0, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xb0, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xf0, 0xff, 10}, { -1, -1, -1, -1}, }; /* * 2013:024f PCTV nanoStick T2 290e * GPIO_6 - demod reset * GPIO_7 - LED */ static const struct em28xx_reg_seq pctv_290e[] = { {EM2874_R80_GPIO_P0_CTRL, 0x00, 0xff, 80}, {EM2874_R80_GPIO_P0_CTRL, 0x40, 0xff, 80}, /* GPIO_6 = 1 */ {EM2874_R80_GPIO_P0_CTRL, 0xc0, 0xff, 80}, /* GPIO_7 = 1 */ { -1, -1, -1, -1}, }; #if 0 static const struct em28xx_reg_seq terratec_h5_gpio[] = { {EM2820_R08_GPIO_CTRL, 0xff, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xf6, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xf2, 0xff, 50}, {EM2874_R80_GPIO_P0_CTRL, 0xf6, 0xff, 50}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq terratec_h5_digital[] = { {EM2874_R80_GPIO_P0_CTRL, 0xf6, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xe6, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xa6, 0xff, 10}, { -1, -1, -1, -1}, }; #endif /* * 2013:024f PCTV DVB-S2 Stick 460e * GPIO_0 - POWER_ON * GPIO_1 - BOOST * GPIO_2 - VUV_LNB (red LED) * GPIO_3 - EXT_12V * GPIO_4 - INT_DEM (DEMOD GPIO_0) * GPIO_5 - INT_LNB * GPIO_6 - RESET_DEM * GPIO_7 - LED (green LED) */ static const struct em28xx_reg_seq pctv_460e[] = { {EM2874_R80_GPIO_P0_CTRL, 0x01, 0xff, 50}, { 0x0d, 0xff, 0xff, 50}, {EM2874_R80_GPIO_P0_CTRL, 0x41, 0xff, 50}, /* GPIO_6=1 */ { 0x0d, 0x42, 0xff, 50}, {EM2874_R80_GPIO_P0_CTRL, 0x61, 0xff, 50}, /* GPIO_5=1 */ { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq c3tech_digital_duo_digital[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xfd, 0xff, 10}, /* xc5000 reset */ {EM2874_R80_GPIO_P0_CTRL, 0xf9, 0xff, 35}, {EM2874_R80_GPIO_P0_CTRL, 0xfd, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xfe, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xbe, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xfe, 0xff, 20}, { -1, -1, -1, -1}, }; /* * 2013:0258 PCTV DVB-S2 Stick (461e) * GPIO 0 = POWER_ON * GPIO 1 = BOOST * GPIO 2 = VUV_LNB (red LED) * GPIO 3 = #EXT_12V * GPIO 4 = INT_DEM * GPIO 5 = INT_LNB * GPIO 6 = #RESET_DEM * GPIO 7 = P07_LED (green LED) */ static const struct em28xx_reg_seq pctv_461e[] = { {EM2874_R80_GPIO_P0_CTRL, 0x7f, 0xff, 0}, {0x0d, 0xff, 0xff, 0}, {EM2874_R80_GPIO_P0_CTRL, 0x3f, 0xff, 100}, /* reset demod */ {EM2874_R80_GPIO_P0_CTRL, 0x7f, 0xff, 200}, /* reset demod */ {0x0d, 0x42, 0xff, 0}, {EM2874_R80_GPIO_P0_CTRL, 0xeb, 0xff, 0}, {EM2874_R5F_TS_ENABLE, 0x84, 0x84, 0}, /* parallel? | null discard */ { -1, -1, -1, -1}, }; #if 0 static const struct em28xx_reg_seq hauppauge_930c_gpio[] = { {EM2874_R80_GPIO_P0_CTRL, 0x6f, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0x4f, 0xff, 10}, /* xc5000 reset */ {EM2874_R80_GPIO_P0_CTRL, 0x6f, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0x4f, 0xff, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq hauppauge_930c_digital[] = { {EM2874_R80_GPIO_P0_CTRL, 0xf6, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xe6, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xa6, 0xff, 10}, { -1, -1, -1, -1}, }; #endif /* * 1b80:e425 MaxMedia UB425-TC * 1b80:e1cc Delock 61959 * GPIO_6 - demod reset, 0=active * GPIO_7 - LED, 0=active */ static const struct em28xx_reg_seq maxmedia_ub425_tc[] = { {EM2874_R80_GPIO_P0_CTRL, 0x83, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xc3, 0xff, 100}, /* GPIO_6 = 1 */ {EM2874_R80_GPIO_P0_CTRL, 0x43, 0xff, 000}, /* GPIO_7 = 0 */ { -1, -1, -1, -1}, }; /* * 2304:0242 PCTV QuatroStick (510e) * GPIO_2: decoder reset, 0=active * GPIO_4: decoder suspend, 0=active * GPIO_6: demod reset, 0=active * GPIO_7: LED, 1=active */ static const struct em28xx_reg_seq pctv_510e[] = { {EM2874_R80_GPIO_P0_CTRL, 0x10, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0x14, 0xff, 100}, /* GPIO_2 = 1 */ {EM2874_R80_GPIO_P0_CTRL, 0x54, 0xff, 050}, /* GPIO_6 = 1 */ { -1, -1, -1, -1}, }; /* * 2013:0251 PCTV QuatroStick nano (520e) * GPIO_2: decoder reset, 0=active * GPIO_4: decoder suspend, 0=active * GPIO_6: demod reset, 0=active * GPIO_7: LED, 1=active */ static const struct em28xx_reg_seq pctv_520e[] = { {EM2874_R80_GPIO_P0_CTRL, 0x10, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0x14, 0xff, 100}, /* GPIO_2 = 1 */ {EM2874_R80_GPIO_P0_CTRL, 0x54, 0xff, 050}, /* GPIO_6 = 1 */ {EM2874_R80_GPIO_P0_CTRL, 0xd4, 0xff, 000}, /* GPIO_7 = 1 */ { -1, -1, -1, -1}, }; /* * 1ae7:9003/9004 SpeedLink Vicious And Devine Laplace webcam * reg 0x80/0x84: * GPIO_0: capturing LED, 0=on, 1=off * GPIO_2: AV mute button, 0=pressed, 1=unpressed * GPIO 3: illumination button, 0=pressed, 1=unpressed * GPIO_6: illumination/flash LED, 0=on, 1=off * reg 0x81/0x85: * GPIO_7: snapshot button, 0=pressed, 1=unpressed */ static const struct em28xx_reg_seq speedlink_vad_laplace_reg_seq[] = { {EM2820_R08_GPIO_CTRL, 0xf7, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xb2, 10}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq pctv_292e[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 0}, {0x0d, 0xff, 0xff, 950}, {EM2874_R80_GPIO_P0_CTRL, 0xbd, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xfd, 0xff, 410}, {EM2874_R80_GPIO_P0_CTRL, 0x7d, 0xff, 300}, {EM2874_R80_GPIO_P0_CTRL, 0x7c, 0xff, 60}, {0x0d, 0x42, 0xff, 50}, {EM2874_R5F_TS_ENABLE, 0x85, 0xff, 0}, {-1, -1, -1, -1}, }; static const struct em28xx_reg_seq terratec_t2_stick_hd[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 0}, {0x0d, 0xff, 0xff, 600}, {EM2874_R80_GPIO_P0_CTRL, 0xfc, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xbc, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xfc, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0x00, 0xff, 300}, {EM2874_R80_GPIO_P0_CTRL, 0xf8, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xfc, 0xff, 300}, {0x0d, 0x42, 0xff, 1000}, {EM2874_R5F_TS_ENABLE, 0x85, 0xff, 0}, {-1, -1, -1, -1}, }; static const struct em28xx_reg_seq plex_px_bcud[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 0}, {0x0d, 0xff, 0xff, 0}, {EM2874_R50_IR_CONFIG, 0x01, 0xff, 0}, {EM28XX_R06_I2C_CLK, 0x40, 0xff, 0}, {EM2874_R80_GPIO_P0_CTRL, 0xfd, 0xff, 100}, {EM28XX_R12_VINENABLE, 0x20, 0x20, 0}, {0x0d, 0x42, 0xff, 1000}, {EM2874_R80_GPIO_P0_CTRL, 0xfc, 0xff, 10}, {EM2874_R80_GPIO_P0_CTRL, 0xfd, 0xff, 10}, {0x73, 0xfd, 0xff, 100}, {-1, -1, -1, -1}, }; /* * 2040:0265 Hauppauge WinTV-dualHD DVB Isoc * 2040:8265 Hauppauge WinTV-dualHD DVB Bulk * 2040:026d Hauppauge WinTV-dualHD ATSC/QAM Isoc * 2040:826d Hauppauge WinTV-dualHD ATSC/QAM Bulk * reg 0x80/0x84: * GPIO_0: Yellow LED tuner 1, 0=on, 1=off * GPIO_1: Green LED tuner 1, 0=on, 1=off * GPIO_2: Yellow LED tuner 2, 0=on, 1=off * GPIO_3: Green LED tuner 2, 0=on, 1=off * GPIO_5: Reset #2, 0=active * GPIO_6: Reset #1, 0=active */ static const struct em28xx_reg_seq hauppauge_dualhd_dvb[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 0}, {0x0d, 0xff, 0xff, 200}, {0x50, 0x04, 0xff, 300}, {EM2874_R80_GPIO_P0_CTRL, 0xbf, 0xff, 100}, /* demod 1 reset */ {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xdf, 0xff, 100}, /* demod 2 reset */ {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 100}, {EM2874_R5F_TS_ENABLE, 0x00, 0xff, 50}, /* disable TS filters */ {EM2874_R5D_TS1_PKT_SIZE, 0x05, 0xff, 50}, {EM2874_R5E_TS2_PKT_SIZE, 0x05, 0xff, 50}, {-1, -1, -1, -1}, }; /* Hauppauge USB QuadHD */ static struct em28xx_reg_seq hauppauge_usb_quadhd_atsc_reg_seq[] = { {EM2874_R80_GPIO_P0_CTRL, 0xff, 0xff, 0}, {0x0d, 0xff, 0xff, 200}, {0x50, 0x04, 0xff, 300}, {EM2874_R80_GPIO_P0_CTRL, 0xb0, 0xf0, 100}, /* demod 1 reset */ {EM2874_R80_GPIO_P0_CTRL, 0xf0, 0xf0, 100}, {EM2874_R80_GPIO_P0_CTRL, 0xd0, 0xf0, 100}, /* demod 2 reset */ {EM2874_R80_GPIO_P0_CTRL, 0xf0, 0xf0, 100}, {EM2874_R5F_TS_ENABLE, 0x44, 0xff, 50}, {EM2874_R5D_TS1_PKT_SIZE, 0x05, 0xff, 50}, {EM2874_R5E_TS2_PKT_SIZE, 0x05, 0xff, 50}, {-1, -1, -1, -1}, }; /* * MyGica USB TV Box * GPIO_1,0: 00=Composite audio * 01=Tuner audio * 10=Mute audio * 11=FM radio? (if equipped) * GPIO_2-6: Unused * GPIO_7: ?? */ static const struct em28xx_reg_seq mygica_utv3_composite_audio_gpio[] = { {EM2820_R08_GPIO_CTRL, 0xfc, 0xff, 0}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq mygica_utv3_tuner_audio_gpio[] = { {EM2820_R08_GPIO_CTRL, 0xfd, 0xff, 0}, { -1, -1, -1, -1}, }; static const struct em28xx_reg_seq mygica_utv3_suspend_gpio[] = { {EM2820_R08_GPIO_CTRL, 0xfe, 0xff, 0}, { -1, -1, -1, -1}, }; /* * Button definitions */ static const struct em28xx_button std_snapshot_button[] = { { .role = EM28XX_BUTTON_SNAPSHOT, .reg_r = EM28XX_R0C_USBSUSP, .reg_clearing = EM28XX_R0C_USBSUSP, .mask = EM28XX_R0C_USBSUSP_SNAPSHOT, .inverted = 0, }, {-1, 0, 0, 0, 0}, }; static const struct em28xx_button speedlink_vad_laplace_buttons[] = { { .role = EM28XX_BUTTON_SNAPSHOT, .reg_r = EM2874_R85_GPIO_P1_STATE, .mask = 0x80, .inverted = 1, }, { .role = EM28XX_BUTTON_ILLUMINATION, .reg_r = EM2874_R84_GPIO_P0_STATE, .mask = 0x08, .inverted = 1, }, {-1, 0, 0, 0, 0}, }; /* * LED definitions */ static struct em28xx_led speedlink_vad_laplace_leds[] = { { .role = EM28XX_LED_ANALOG_CAPTURING, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = 0x01, .inverted = 1, }, { .role = EM28XX_LED_ILLUMINATION, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = 0x40, .inverted = 1, }, {-1, 0, 0, 0}, }; static struct em28xx_led kworld_ub435q_v3_leds[] = { { .role = EM28XX_LED_DIGITAL_CAPTURING, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = 0x80, .inverted = 1, }, {-1, 0, 0, 0}, }; static struct em28xx_led pctv_80e_leds[] = { { .role = EM28XX_LED_DIGITAL_CAPTURING, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = 0x80, .inverted = 0, }, {-1, 0, 0, 0}, }; static struct em28xx_led terratec_grabby_leds[] = { { .role = EM28XX_LED_ANALOG_CAPTURING, .gpio_reg = EM2820_R08_GPIO_CTRL, .gpio_mask = EM_GPIO_3, .inverted = 1, }, {-1, 0, 0, 0}, }; static struct em28xx_led hauppauge_dualhd_leds[] = { { .role = EM28XX_LED_DIGITAL_CAPTURING, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = EM_GPIO_1, .inverted = 1, }, { .role = EM28XX_LED_DIGITAL_CAPTURING_TS2, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = EM_GPIO_3, .inverted = 1, }, {-1, 0, 0, 0}, }; static struct em28xx_led hauppauge_usb_quadhd_leds[] = { { .role = EM28XX_LED_DIGITAL_CAPTURING, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = EM_GPIO_2, .inverted = 1, }, { .role = EM28XX_LED_DIGITAL_CAPTURING_TS2, .gpio_reg = EM2874_R80_GPIO_P0_CTRL, .gpio_mask = EM_GPIO_0, .inverted = 1, }, {-1, 0, 0, 0}, }; /* * Board definitions */ const struct em28xx_board em28xx_boards[] = { [EM2750_BOARD_UNKNOWN] = { .name = "EM2710/EM2750/EM2751 webcam grabber", .xclk = EM28XX_XCLK_FREQUENCY_20MHZ, .tuner_type = TUNER_ABSENT, .is_webcam = 1, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = 0, .amux = EM28XX_AMUX_VIDEO, .gpio = silvercrest_reg_seq, } }, }, [EM2800_BOARD_UNKNOWN] = { .name = "Unknown EM2800 video grabber", .is_em2800 = 1, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .tuner_type = TUNER_ABSENT, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_UNKNOWN] = { .name = "Unknown EM2750/28xx video grabber", .tuner_type = TUNER_ABSENT, .is_webcam = 1, /* To enable sensor probe */ }, [EM2882_BOARD_ZOLID_HYBRID_TV_STICK] = { .name = ":ZOLID HYBRID TV STICK", .tuner_type = TUNER_XC2028, .tuner_gpio = zolid_tuner, .decoder = EM28XX_TVP5150, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = zolid_digital, }, [EM2750_BOARD_DLCW_130] = { /* Beijing Huaqi Information Digital Technology Co., Ltd */ .name = "Huaqi DLCW-130", .valid = EM28XX_BOARD_NOT_VALIDATED, .xclk = EM28XX_XCLK_FREQUENCY_48MHZ, .tuner_type = TUNER_ABSENT, .is_webcam = 1, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = 0, .amux = EM28XX_AMUX_VIDEO, } }, }, [EM2820_BOARD_KWORLD_PVRTV2800RF] = { .name = "Kworld PVR TV 2800 RF", .tuner_type = TUNER_TEMIC_PAL, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_GADMEI_TVR200] = { .name = "Gadmei TVR200", .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_TERRATEC_CINERGY_250] = { .name = "Terratec Cinergy 250 USB", .tuner_type = TUNER_LG_PAL_NEW_TAPC, .has_ir_i2c = 1, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_PINNACLE_USB_2] = { .name = "Pinnacle PCTV USB 2", .tuner_type = TUNER_LG_PAL_NEW_TAPC, .has_ir_i2c = 1, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_HAUPPAUGE_WINTV_USB_2] = { .name = "Hauppauge WinTV USB 2", .tuner_type = TUNER_PHILIPS_FM1236_MK3, .tda9887_conf = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE | TDA9887_PORT2_ACTIVE, .decoder = EM28XX_TVP5150, .has_msp34xx = 1, .has_ir_i2c = 1, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = MSP_INPUT_DEFAULT, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = MSP_INPUT(MSP_IN_SCART1, MSP_IN_TUNER1, MSP_DSP_IN_SCART, MSP_DSP_IN_SCART), } }, }, [EM2820_BOARD_DLINK_USB_TV] = { .name = "D-Link DUB-T210 TV Tuner", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_HERCULES_SMART_TV_USB2] = { .name = "Hercules Smart TV USB 2.0", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_PINNACLE_USB_2_FM1216ME] = { .name = "Pinnacle PCTV USB 2 (Philips FM1216ME)", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_PHILIPS_FM1216ME_MK3, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_GADMEI_UTV310] = { .name = "Gadmei UTV310", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_TNF_5335MF, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_LEADTEK_WINFAST_USBII_DELUXE] = { .name = "Leadtek Winfast USB II Deluxe", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_PHILIPS_FM1216ME_MK3, .has_ir_i2c = 1, .tvaudio_addr = 0x58, .tda9887_conf = TDA9887_PRESENT | TDA9887_PORT2_ACTIVE | TDA9887_QSS, .decoder = EM28XX_SAA711X, .adecoder = EM28XX_TVAUDIO, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE4, .amux = EM28XX_AMUX_AUX, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE5, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, .radio = { .type = EM28XX_RADIO, .amux = EM28XX_AMUX_AUX, } }, [EM2820_BOARD_VIDEOLOGY_20K14XUSB] = { .name = "Videology 20K14XUSB USB2.0", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_ABSENT, .is_webcam = 1, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = 0, .amux = EM28XX_AMUX_VIDEO, } }, }, [EM2820_BOARD_SILVERCREST_WEBCAM] = { .name = "Silvercrest Webcam 1.3mpix", .tuner_type = TUNER_ABSENT, .is_webcam = 1, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = 0, .amux = EM28XX_AMUX_VIDEO, .gpio = silvercrest_reg_seq, } }, }, [EM2821_BOARD_SUPERCOMP_USB_2] = { .name = "Supercomp USB 2.0 TV", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_PHILIPS_FM1236_MK3, .tda9887_conf = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE | TDA9887_PORT2_ACTIVE, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2821_BOARD_USBGEAR_VD204] = { .name = "Usbgear VD204v9", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_ABSENT, /* Capture only device */ .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2860_BOARD_NETGMBH_CAM] = { /* Beijing Huaqi Information Digital Technology Co., Ltd */ .name = "NetGMBH Cam", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_ABSENT, .is_webcam = 1, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = 0, .amux = EM28XX_AMUX_VIDEO, } }, }, [EM2860_BOARD_TYPHOON_DVD_MAKER] = { .name = "Typhoon DVD Maker", .decoder = EM28XX_SAA711X, .tuner_type = TUNER_ABSENT, /* Capture only device */ .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2860_BOARD_GADMEI_UTV330] = { .name = "Gadmei UTV330", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_TNF_5335MF, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2861_BOARD_GADMEI_UTV330PLUS] = { .name = "Gadmei UTV330+", .tuner_type = TUNER_TNF_5335MF, .tda9887_conf = TDA9887_PRESENT, .ir_codes = RC_MAP_GADMEI_RM008Z, .decoder = EM28XX_SAA711X, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2860_BOARD_TERRATEC_HYBRID_XS] = { .name = "Terratec Cinergy A Hybrid XS", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2861_BOARD_KWORLD_PVRTV_300U] = { .name = "KWorld PVRTV 300U", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2861_BOARD_YAKUMO_MOVIE_MIXER] = { .name = "Yakumo MovieMixer", .tuner_type = TUNER_ABSENT, /* Capture only device */ .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2860_BOARD_TVP5150_REFERENCE_DESIGN] = { .name = "EM2860/TVP5150 Reference Design", .tuner_type = TUNER_ABSENT, /* Capture only device */ .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2861_BOARD_PLEXTOR_PX_TV100U] = { .name = "Plextor ConvertX PX-TV100U", .tuner_type = TUNER_TNF_5335MF, .xclk = EM28XX_XCLK_I2S_MSB_TIMING | EM28XX_XCLK_FREQUENCY_12MHZ, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_TVP5150, .has_msp34xx = 1, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, .gpio = pinnacle_hybrid_pro_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = pinnacle_hybrid_pro_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = pinnacle_hybrid_pro_analog, } }, }, /* Those boards with em2870 are DVB Only*/ [EM2870_BOARD_TERRATEC_XS] = { .name = "Terratec Cinergy T XS", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, }, [EM2870_BOARD_TERRATEC_XS_MT2060] = { .name = "Terratec Cinergy T XS (MT2060)", .xclk = EM28XX_XCLK_IR_RC5_MODE | EM28XX_XCLK_FREQUENCY_12MHZ, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE, .tuner_type = TUNER_ABSENT, /* MT2060 */ .has_dvb = 1, .tuner_gpio = default_tuner_gpio, }, [EM2870_BOARD_KWORLD_350U] = { .name = "Kworld 350 U DVB-T", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, }, [EM2870_BOARD_KWORLD_355U] = { .name = "Kworld 355 U DVB-T", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_ABSENT, .tuner_gpio = default_tuner_gpio, .has_dvb = 1, .dvb_gpio = default_digital, }, [EM2870_BOARD_PINNACLE_PCTV_DVB] = { .name = "Pinnacle PCTV DVB-T", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_ABSENT, /* MT2060 */ /* djh - I have serious doubts this is right... */ .xclk = EM28XX_XCLK_IR_RC5_MODE | EM28XX_XCLK_FREQUENCY_10MHZ, }, [EM2870_BOARD_COMPRO_VIDEOMATE] = { .name = "Compro, VideoMate U3", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_ABSENT, /* MT2060 */ }, [EM2880_BOARD_TERRATEC_HYBRID_XS_FR] = { .name = "Terratec Hybrid XS Secam", .has_msp34xx = 1, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .has_dvb = 1, .dvb_gpio = terratec_cinergy_USB_XS_FR_digital, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = terratec_cinergy_USB_XS_FR_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = terratec_cinergy_USB_XS_FR_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = terratec_cinergy_USB_XS_FR_analog, } }, }, [EM2884_BOARD_TERRATEC_H5] = { .name = "Terratec Cinergy H5", .has_dvb = 1, #if 0 .tuner_type = TUNER_PHILIPS_TDA8290, .tuner_addr = 0x41, .dvb_gpio = terratec_h5_digital, /* FIXME: probably wrong */ .tuner_gpio = terratec_h5_gpio, #else .tuner_type = TUNER_ABSENT, #endif .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, [EM2884_BOARD_TERRATEC_H6] = { .name = "Terratec Cinergy H6 rev. 2", .has_dvb = 1, .ir_codes = RC_MAP_NEC_TERRATEC_CINERGY_XS, #if 0 .tuner_type = TUNER_PHILIPS_TDA8290, .tuner_addr = 0x41, .dvb_gpio = terratec_h5_digital, /* FIXME: probably wrong */ .tuner_gpio = terratec_h5_gpio, #else .tuner_type = TUNER_ABSENT, #endif .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, [EM2884_BOARD_HAUPPAUGE_WINTV_HVR_930C] = { .name = "Hauppauge WinTV HVR 930C", .has_dvb = 1, #if 0 /* FIXME: Add analog support */ .tuner_type = TUNER_XC5000, .tuner_addr = 0x41, .dvb_gpio = hauppauge_930c_digital, .tuner_gpio = hauppauge_930c_gpio, #else .tuner_type = TUNER_ABSENT, #endif .ir_codes = RC_MAP_HAUPPAUGE, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, [EM2884_BOARD_C3TECH_DIGITAL_DUO] = { .name = "C3 Tech Digital Duo HDTV/SDTV USB", .has_dvb = 1, /* FIXME: Add analog support - need a saa7136 driver */ .tuner_type = TUNER_ABSENT, /* Digital-only TDA18271HD */ .ir_codes = RC_MAP_EMPTY, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE, .dvb_gpio = c3tech_digital_duo_digital, }, [EM2884_BOARD_CINERGY_HTC_STICK] = { .name = "Terratec Cinergy HTC Stick", .has_dvb = 1, .ir_codes = RC_MAP_NEC_TERRATEC_CINERGY_XS, .tuner_type = TUNER_ABSENT, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, [EM2884_BOARD_ELGATO_EYETV_HYBRID_2008] = { .name = "Elgato EyeTV Hybrid 2008 INT", .has_dvb = 1, .ir_codes = RC_MAP_NEC_TERRATEC_CINERGY_XS, .tuner_type = TUNER_ABSENT, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, [EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900] = { .name = "Hauppauge WinTV HVR 900", .tda9887_conf = TDA9887_PRESENT, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900_digital, .ir_codes = RC_MAP_HAUPPAUGE, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900_R2] = { .name = "Hauppauge WinTV HVR 900 (R2)", .tda9887_conf = TDA9887_PRESENT, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900R2_digital, .ir_codes = RC_MAP_HAUPPAUGE, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2883_BOARD_HAUPPAUGE_WINTV_HVR_850] = { .name = "Hauppauge WinTV HVR 850", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900_digital, .ir_codes = RC_MAP_HAUPPAUGE, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2883_BOARD_HAUPPAUGE_WINTV_HVR_950] = { .name = "Hauppauge WinTV HVR 950", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900_digital, .ir_codes = RC_MAP_HAUPPAUGE, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2880_BOARD_PINNACLE_PCTV_HD_PRO] = { .name = "Pinnacle PCTV HD Pro Stick", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900_digital, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2880_BOARD_AMD_ATI_TV_WONDER_HD_600] = { .name = "AMD ATI TV Wonder HD 600", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900_digital, .ir_codes = RC_MAP_ATI_TV_WONDER_HD_600, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2880_BOARD_TERRATEC_HYBRID_XS] = { .name = "Terratec Hybrid XS", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .has_dvb = 1, .dvb_gpio = default_digital, .ir_codes = RC_MAP_TERRATEC_CINERGY_XS, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, /* NEC IR */ .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = default_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, } }, }, /* * maybe there's a reason behind it why Terratec sells the Hybrid XS * as Prodigy XS with a different PID, let's keep it separated for now * maybe we'll need it later on */ [EM2880_BOARD_TERRATEC_PRODIGY_XS] = { .name = "Terratec Prodigy XS", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2820_BOARD_MSI_VOX_USB_2] = { .name = "MSI VOX USB 2.0", .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tda9887_conf = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE | TDA9887_PORT2_ACTIVE, .max_range_640_480 = 1, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE4, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2800_BOARD_TERRATEC_CINERGY_200] = { .name = "Terratec Cinergy 200 USB", .is_em2800 = 1, .has_ir_i2c = 1, .tuner_type = TUNER_LG_TALN, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2800_BOARD_GRABBEEX_USB2800] = { .name = "eMPIA Technology, Inc. GrabBeeX+ Video Encoder", .is_em2800 = 1, .decoder = EM28XX_SAA711X, .tuner_type = TUNER_ABSENT, /* capture only board */ .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2800_BOARD_VC211A] = { .name = "Actionmaster/LinXcel/Digitus VC211A", .is_em2800 = 1, .tuner_type = TUNER_ABSENT, /* Capture-only board */ .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, .gpio = vc211a_enable, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, .gpio = vc211a_enable, } }, }, [EM2800_BOARD_LEADTEK_WINFAST_USBII] = { .name = "Leadtek Winfast USB II", .is_em2800 = 1, .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2800_BOARD_KWORLD_USB2800] = { .name = "Kworld USB2800", .is_em2800 = 1, .tuner_type = TUNER_PHILIPS_FCV1236D, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_PINNACLE_DVC_90] = { .name = "Pinnacle Dazzle DVC 90/100/101/107 / Kaiser Baas Video to DVD maker / Kworld DVD Maker 2 / Plextor ConvertX PX-AV100U", .tuner_type = TUNER_ABSENT, /* capture only board */ .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2800_BOARD_VGEAR_POCKETTV] = { .name = "V-Gear PocketTV", .is_em2800 = 1, .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_PROLINK_PLAYTV_BOX4_USB2] = { .name = "Pixelview PlayTV Box 4 USB 2.0", .tda9887_conf = TDA9887_PRESENT, .tuner_type = TUNER_YMEC_TVF_5533MF, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, .aout = EM28XX_AOUT_MONO | /* I2S */ EM28XX_AOUT_MASTER, /* Line out pin */ }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_PROLINK_PLAYTV_USB2] = { .name = "SIIG AVTuner-PVR / Pixelview Prolink PlayTV USB 2.0", .buttons = std_snapshot_button, .tda9887_conf = TDA9887_PRESENT, .tuner_type = TUNER_YMEC_TVF_5533MF, .tuner_addr = 0x60, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, .aout = EM28XX_AOUT_MONO | /* I2S */ EM28XX_AOUT_MASTER, /* Line out pin */ }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2860_BOARD_SAA711X_REFERENCE_DESIGN] = { .name = "EM2860/SAA711X Reference Design", .buttons = std_snapshot_button, .tuner_type = TUNER_ABSENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, } }, }, [EM2874_BOARD_LEADERSHIP_ISDBT] = { .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_100_KHZ, .xclk = EM28XX_XCLK_FREQUENCY_10MHZ, .name = "EM2874 Leadership ISDBT", .tuner_type = TUNER_ABSENT, .tuner_gpio = leadership_reset, .dvb_gpio = leadership_digital, .has_dvb = 1, }, [EM2880_BOARD_MSI_DIGIVOX_AD] = { .name = "MSI DigiVox A/D", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = em2880_msi_digivox_ad_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = em2880_msi_digivox_ad_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = em2880_msi_digivox_ad_analog, } }, }, [EM2880_BOARD_MSI_DIGIVOX_AD_II] = { .name = "MSI DigiVox A/D II", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = em2880_msi_digivox_ad_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = em2880_msi_digivox_ad_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = em2880_msi_digivox_ad_analog, } }, }, [EM2880_BOARD_KWORLD_DVB_305U] = { .name = "KWorld DVB-T 305U", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2880_BOARD_KWORLD_DVB_310U] = { .name = "KWorld DVB-T 310U", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .has_dvb = 1, .dvb_gpio = default_digital, .mts_firmware = 1, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = default_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, }, { /* S-video has not been tested yet */ .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, } }, }, [EM2882_BOARD_KWORLD_ATSC_315U] = { .name = "KWorld ATSC 315U HDTV TV Box", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_THOMSON_DTT761X, .tuner_gpio = em2882_kworld_315u_tuner_gpio, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_SAA711X, .has_dvb = 1, .dvb_gpio = em2882_kworld_315u_digital, .ir_codes = RC_MAP_KWORLD_315U, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE, #if 0 /* FIXME: Analog mode - still not ready */ .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, .gpio = em2882_kworld_315u_analog, .aout = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, .gpio = em2882_kworld_315u_analog1, .aout = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, .gpio = em2882_kworld_315u_analog1, .aout = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO, } }, #endif }, [EM2880_BOARD_EMPIRE_DUAL_TV] = { .name = "Empire dual TV", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .has_dvb = 1, .dvb_gpio = default_digital, .mts_firmware = 1, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = default_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, } }, }, [EM2881_BOARD_DNT_DA2_HYBRID] = { .name = "DNT DA2 Hybrid", .valid = EM28XX_BOARD_NOT_VALIDATED, .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = default_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = default_analog, } }, }, [EM2881_BOARD_PINNACLE_HYBRID_PRO] = { .name = "Pinnacle Hybrid Pro", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .has_dvb = 1, .dvb_gpio = pinnacle_hybrid_pro_digital, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = pinnacle_hybrid_pro_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = pinnacle_hybrid_pro_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = pinnacle_hybrid_pro_analog, } }, }, [EM2882_BOARD_PINNACLE_HYBRID_PRO_330E] = { .name = "Pinnacle Hybrid Pro (330e)", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900R2_digital, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2882_BOARD_KWORLD_VS_DVBT] = { .name = "Kworld VS-DVB-T 323UR", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = kworld_330u_digital, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, /* NEC IR */ .ir_codes = RC_MAP_KWORLD_315U, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2882_BOARD_TERRATEC_HYBRID_XS] = { .name = "Terratec Cinergy Hybrid T USB XS (em2882)", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .mts_firmware = 1, .decoder = EM28XX_TVP5150, .has_dvb = 1, .dvb_gpio = hauppauge_wintv_hvr_900_digital, .ir_codes = RC_MAP_TERRATEC_CINERGY_XS, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = hauppauge_wintv_hvr_900_analog, } }, }, [EM2882_BOARD_DIKOM_DK300] = { .name = "Dikom DK300", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = dikom_dk300_digital, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = default_analog, } }, }, [EM2883_BOARD_KWORLD_HYBRID_330U] = { .name = "Kworld PlusTV HD Hybrid 330", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = kworld_330u_digital, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_EEPROM_ON_BOARD | EM28XX_I2C_EEPROM_KEY_VALID, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = kworld_330u_analog, .aout = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = kworld_330u_analog, .aout = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = kworld_330u_analog, } }, }, [EM2820_BOARD_COMPRO_VIDEOMATE_FORYOU] = { .name = "Compro VideoMate ForYou/Stereo", .tuner_type = TUNER_LG_PAL_NEW_TAPC, .tvaudio_addr = 0xb0, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_TVP5150, .adecoder = EM28XX_TVAUDIO, .mute_gpio = compro_mute_gpio, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = compro_unmute_tv_gpio, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = compro_unmute_svid_gpio, } }, }, [EM2860_BOARD_KAIOMY_TVNPC_U2] = { .name = "Kaiomy TVnPC U2", .vchannels = 3, .tuner_type = TUNER_XC2028, .tuner_addr = 0x61, .mts_firmware = 1, .decoder = EM28XX_TVP5150, .tuner_gpio = default_tuner_gpio, .ir_codes = RC_MAP_KAIOMY, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, .radio = { .type = EM28XX_RADIO, .amux = EM28XX_AMUX_LINE_IN, } }, [EM2860_BOARD_EASYCAP] = { .name = "Easy Cap Capture DC-60", .vchannels = 2, .tuner_type = TUNER_ABSENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2820_BOARD_IODATA_GVMVP_SZ] = { .name = "IO-DATA GV-MVP/SZ", .tuner_type = TUNER_PHILIPS_FM1236_MK3, .tuner_gpio = default_tuner_gpio, .tda9887_conf = TDA9887_PRESENT, .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, }, { /* Composite has not been tested yet */ .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_VIDEO, }, { /* S-video has not been tested yet */ .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_VIDEO, } }, }, [EM2860_BOARD_TERRATEC_GRABBY] = { .name = "Terratec Grabby", .vchannels = 2, .tuner_type = TUNER_ABSENT, .decoder = EM28XX_SAA711X, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, .buttons = std_snapshot_button, .leds = terratec_grabby_leds, }, [EM2860_BOARD_TERRATEC_AV350] = { .name = "Terratec AV350", .vchannels = 2, .tuner_type = TUNER_ABSENT, .decoder = EM28XX_TVP5150, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, .mute_gpio = terratec_av350_mute_gpio, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = terratec_av350_unmute_gpio, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = terratec_av350_unmute_gpio, } }, }, [EM2860_BOARD_ELGATO_VIDEO_CAPTURE] = { .name = "Elgato Video Capture", .decoder = EM28XX_SAA711X, .tuner_type = TUNER_ABSENT, /* Capture only device */ .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2882_BOARD_EVGA_INDTUBE] = { .name = "Evga inDtube", .tuner_type = TUNER_XC2028, .tuner_gpio = default_tuner_gpio, .decoder = EM28XX_TVP5150, .xclk = EM28XX_XCLK_FREQUENCY_12MHZ, /* NEC IR */ .mts_firmware = 1, .has_dvb = 1, .dvb_gpio = evga_indtube_digital, .ir_codes = RC_MAP_EVGA_INDTUBE, .input = { { .type = EM28XX_VMUX_TELEVISION, .vmux = TVP5150_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = evga_indtube_analog, }, { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, .gpio = evga_indtube_analog, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, .gpio = evga_indtube_analog, } }, }, /* * eb1a:2868 Empia EM2870 + Philips CU1216L NIM * (Philips TDA10023 + Infineon TUA6034) */ [EM2870_BOARD_REDDO_DVB_C_USB_BOX] = { .name = "Reddo DVB-C USB TV Box", .tuner_type = TUNER_ABSENT, .tuner_gpio = reddo_dvb_c_usb_box, .has_dvb = 1, }, /* * 1b80:a340 - Empia EM2870, NXP TDA18271HD and LG DT3304, sold * initially as the KWorld PlusTV 340U, then as the UB435-Q. * Early variants have a TDA18271HD/C1, later ones a TDA18271HD/C2 */ [EM2870_BOARD_KWORLD_A340] = { .name = "KWorld PlusTV 340U or UB435-Q (ATSC)", .tuner_type = TUNER_ABSENT, /* Digital-only TDA18271HD */ .has_dvb = 1, .dvb_gpio = kworld_a340_digital, .tuner_gpio = default_tuner_gpio, }, /* * 2013:024f PCTV nanoStick T2 290e. * Empia EM28174, Sony CXD2820R and NXP TDA18271HD/C2 */ [EM28174_BOARD_PCTV_290E] = { .name = "PCTV nanoStick T2 290e", .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_100_KHZ, .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_290e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, }, /* * 2013:024f PCTV DVB-S2 Stick 460e * Empia EM28174, NXP TDA10071, Conexant CX24118A and Allegro A8293 */ [EM28174_BOARD_PCTV_460E] = { .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .name = "PCTV DVB-S2 Stick (460e)", .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_460e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, }, /* * eb1a:5006 Honestech VIDBOX NW03 * Empia EM2860, Philips SAA7113, Empia EMP202, No Tuner */ [EM2860_BOARD_HT_VIDBOX_NW03] = { .name = "Honestech Vidbox NW03", .tuner_type = TUNER_ABSENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, /* S-VIDEO needs check */ .amux = EM28XX_AMUX_LINE_IN, } }, }, /* * 1b80:e425 MaxMedia UB425-TC * Empia EM2874B + Micronas DRX 3913KA2 + NXP TDA18271HDC2 */ [EM2874_BOARD_MAXMEDIA_UB425_TC] = { .name = "MaxMedia UB425-TC", .tuner_type = TUNER_ABSENT, .tuner_gpio = maxmedia_ub425_tc, .has_dvb = 1, .ir_codes = RC_MAP_REDDO, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, /* * 2304:0242 PCTV QuatroStick (510e) * Empia EM2884 + Micronas DRX 3926K + NXP TDA18271HDC2 */ [EM2884_BOARD_PCTV_510E] = { .name = "PCTV QuatroStick (510e)", .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_510e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, /* * 2013:0251 PCTV QuatroStick nano (520e) * Empia EM2884 + Micronas DRX 3926K + NXP TDA18271HDC2 */ [EM2884_BOARD_PCTV_520E] = { .name = "PCTV QuatroStick nano (520e)", .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_520e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, [EM2884_BOARD_TERRATEC_HTC_USB_XS] = { .name = "Terratec Cinergy HTC USB XS", .has_dvb = 1, .ir_codes = RC_MAP_NEC_TERRATEC_CINERGY_XS, .tuner_type = TUNER_ABSENT, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, /* * 1b80:e1cc Delock 61959 * Empia EM2874B + Micronas DRX 3913KA2 + NXP TDA18271HDC2 * mostly the same as MaxMedia UB-425-TC but different remote */ [EM2874_BOARD_DELOCK_61959] = { .name = "Delock 61959", .tuner_type = TUNER_ABSENT, .tuner_gpio = maxmedia_ub425_tc, .has_dvb = 1, .ir_codes = RC_MAP_DELOCK_61959, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, }, /* * 1b80:e346 KWorld USB ATSC TV Stick UB435-Q V2 * Empia EM2874B + LG DT3305 + NXP TDA18271HDC2 */ [EM2874_BOARD_KWORLD_UB435Q_V2] = { .name = "KWorld USB ATSC TV Stick UB435-Q V2", .tuner_type = TUNER_ABSENT, .has_dvb = 1, .dvb_gpio = kworld_a340_digital, .tuner_gpio = default_tuner_gpio, .def_i2c_bus = 1, }, /* * 1b80:e34c KWorld USB ATSC TV Stick UB435-Q V3 * Empia EM2874B + LG DT3305 + NXP TDA18271HDC2 */ [EM2874_BOARD_KWORLD_UB435Q_V3] = { .name = "KWorld USB ATSC TV Stick UB435-Q V3", .tuner_type = TUNER_ABSENT, .has_dvb = 1, .tuner_gpio = kworld_ub435q_v3_digital, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_100_KHZ, .leds = kworld_ub435q_v3_leds, }, [EM2874_BOARD_PCTV_HD_MINI_80E] = { .name = "Pinnacle PCTV HD Mini", .tuner_type = TUNER_ABSENT, .has_dvb = 1, .dvb_gpio = em2874_pctv_80e_digital, .decoder = EM28XX_NODECODER, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, .leds = pctv_80e_leds, }, /* * 1ae7:9003/9004 SpeedLink Vicious And Devine Laplace webcam * Empia EM2765 + OmniVision OV2640 */ [EM2765_BOARD_SPEEDLINK_VAD_LAPLACE] = { .name = "SpeedLink Vicious And Devine Laplace webcam", .xclk = EM28XX_XCLK_FREQUENCY_24MHZ, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_100_KHZ, .def_i2c_bus = 1, .tuner_type = TUNER_ABSENT, .is_webcam = 1, .input = { { .type = EM28XX_VMUX_COMPOSITE, .amux = EM28XX_AMUX_VIDEO, .gpio = speedlink_vad_laplace_reg_seq, } }, .buttons = speedlink_vad_laplace_buttons, .leds = speedlink_vad_laplace_leds, }, /* * 2013:0258 PCTV DVB-S2 Stick (461e) * Empia EM28178, Montage M88DS3103, Montage M88TS2022, Allegro A8293 */ [EM28178_BOARD_PCTV_461E] = { .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .name = "PCTV DVB-S2 Stick (461e)", .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_461e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, }, /* * 2013:0259 PCTV DVB-S2 Stick (461e_v2) * Empia EM28178, Montage M88DS3103b, Montage M88TS2022, Allegro A8293 */ [EM28178_BOARD_PCTV_461E_V2] = { .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .name = "PCTV DVB-S2 Stick (461e v2)", .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_461e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, }, /* * 2013:025f PCTV tripleStick (292e). * Empia EM28178, Silicon Labs Si2168, Silicon Labs Si2157 */ [EM28178_BOARD_PCTV_292E] = { .name = "PCTV tripleStick (292e)", .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .tuner_type = TUNER_ABSENT, .tuner_gpio = pctv_292e, .has_dvb = 1, .ir_codes = RC_MAP_PINNACLE_PCTV_HD, }, [EM2861_BOARD_LEADTEK_VC100] = { .name = "Leadtek VC100", .tuner_type = TUNER_ABSENT, /* Capture only device */ .decoder = EM28XX_TVP5150, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = TVP5150_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, /* * eb1a:8179 Terratec Cinergy T2 Stick HD. * Empia EM28178, Silicon Labs Si2168, Silicon Labs Si2146 */ [EM28178_BOARD_TERRATEC_T2_STICK_HD] = { .name = "Terratec Cinergy T2 Stick HD", .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .tuner_type = TUNER_ABSENT, .tuner_gpio = terratec_t2_stick_hd, .has_dvb = 1, .ir_codes = RC_MAP_TERRATEC_SLIM_2, }, /* * 3275:0085 PLEX PX-BCUD. * Empia EM28178, TOSHIBA TC90532XBG, Sharp QM1D1C0042 */ [EM28178_BOARD_PLEX_PX_BCUD] = { .name = "PLEX PX-BCUD", .xclk = EM28XX_XCLK_FREQUENCY_4_3MHZ, .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE, .tuner_type = TUNER_ABSENT, .tuner_gpio = plex_px_bcud, .has_dvb = 1, }, /* * 2040:0265 Hauppauge WinTV-dualHD (DVB version) Isoc. * 2040:8265 Hauppauge WinTV-dualHD (DVB version) Bulk. * Empia EM28274, 2x Silicon Labs Si2168, 2x Silicon Labs Si2157 */ [EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_DVB] = { .name = "Hauppauge WinTV-dualHD DVB", .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .tuner_type = TUNER_SI2157, .tuner_gpio = hauppauge_dualhd_dvb, .has_dvb = 1, .has_dual_ts = 1, .ir_codes = RC_MAP_HAUPPAUGE, .leds = hauppauge_dualhd_leds, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = TVP5150_COMPOSITE1, .amux = EM28XX_AMUX_LINE_IN, } }, }, /* * 2040:026d Hauppauge WinTV-dualHD (model 01595 - ATSC/QAM) Isoc. * 2040:826d Hauppauge WinTV-dualHD (model 01595 - ATSC/QAM) Bulk. * Empia EM28274, 2x LG LGDT3306A, 2x Silicon Labs Si2157 */ [EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_01595] = { .name = "Hauppauge WinTV-dualHD 01595 ATSC/QAM", .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, .tuner_type = TUNER_ABSENT, .tuner_gpio = hauppauge_dualhd_dvb, .has_dvb = 1, .has_dual_ts = 1, .ir_codes = RC_MAP_HAUPPAUGE, .leds = hauppauge_dualhd_leds, }, /* * 1b80:e349 Magix USB Videowandler-2 * (same chips as Honestech VIDBOX NW03) * Empia EM2860, Philips SAA7113, Empia EMP202, No Tuner */ [EM2861_BOARD_MAGIX_VIDEOWANDLER2] = { .name = "Magix USB Videowandler-2", .tuner_type = TUNER_ABSENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .amux = EM28XX_AMUX_LINE_IN, } }, }, /* * 1f4d:1abe MyGica iGrabber * (same as several other EM2860 devices) * Empia EM2860, Philips SAA7113, Empia EMP202, No Tuner */ [EM2860_BOARD_MYGICA_IGRABBER] = { .name = "MyGica iGrabber", .vchannels = 2, .tuner_type = TUNER_ABSENT, .decoder = EM28XX_SAA711X, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, .amux = EM28XX_AMUX_LINE_IN, } }, }, /* 2040:826d Hauppauge USB QuadHD * Empia 28274, Max Linear 692 ATSC combo demod/tuner */ [EM2874_BOARD_HAUPPAUGE_USB_QUADHD] = { .name = "Hauppauge USB QuadHD ATSC", .def_i2c_bus = 1, .has_dual_ts = 1, .has_dvb = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_100_KHZ, .tuner_type = TUNER_ABSENT, .tuner_gpio = hauppauge_usb_quadhd_atsc_reg_seq, .leds = hauppauge_usb_quadhd_leds, }, /* * eb1a:2860 MyGica UTV3 Analog USB2.0 TV Box * Empia EM2860, Philips SAA7113, NXP TDA9801T demod, * Tena TNF931D-DFDR1 tuner (contains NXP TDA6509A), * ST HCF4052 demux (switches audio to line out), * no audio over USB */ [EM2860_BOARD_MYGICA_UTV3] = { .name = "MyGica UTV3 Analog USB2.0 TV Box", .xclk = EM28XX_XCLK_IR_RC5_MODE | EM28XX_XCLK_FREQUENCY_12MHZ, .tuner_type = TUNER_TENA_TNF_931D_DFDR1, .ir_codes = RC_MAP_MYGICA_UTV3, .decoder = EM28XX_SAA711X, .suspend_gpio = mygica_utv3_suspend_gpio, .input = { { .type = EM28XX_VMUX_COMPOSITE, .vmux = SAA7115_COMPOSITE0, .amux = EM28XX_AMUX_VIDEO, .gpio = mygica_utv3_composite_audio_gpio, }, { .type = EM28XX_VMUX_TELEVISION, .vmux = SAA7115_COMPOSITE2, .amux = EM28XX_AMUX_VIDEO, .gpio = mygica_utv3_tuner_audio_gpio, } }, }, }; EXPORT_SYMBOL_GPL(em28xx_boards); static const unsigned int em28xx_bcount = ARRAY_SIZE(em28xx_boards); /* table of devices that work with this driver */ struct usb_device_id em28xx_id_table[] = { { USB_DEVICE(0xeb1a, 0x2750), .driver_info = EM2750_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2751), .driver_info = EM2750_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2800), .driver_info = EM2800_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2710), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2820), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2821), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2860), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2861), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2862), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2863), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2870), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2881), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2883), /* used by :Zolid Hybrid Tv Stick */ .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2868), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2875), .driver_info = EM2820_BOARD_UNKNOWN }, { USB_DEVICE(0xeb1a, 0x2885), /* MSI Digivox Trio */ .driver_info = EM2884_BOARD_TERRATEC_H5 }, { USB_DEVICE(0xeb1a, 0xe300), .driver_info = EM2861_BOARD_KWORLD_PVRTV_300U }, { USB_DEVICE(0xeb1a, 0xe303), .driver_info = EM2860_BOARD_KAIOMY_TVNPC_U2 }, { USB_DEVICE(0xeb1a, 0xe305), .driver_info = EM2880_BOARD_KWORLD_DVB_305U }, { USB_DEVICE(0xeb1a, 0xe310), .driver_info = EM2880_BOARD_MSI_DIGIVOX_AD }, { USB_DEVICE(0xeb1a, 0xa313), .driver_info = EM2882_BOARD_KWORLD_ATSC_315U }, { USB_DEVICE(0xeb1a, 0xa316), .driver_info = EM2883_BOARD_KWORLD_HYBRID_330U }, { USB_DEVICE(0xeb1a, 0xe320), .driver_info = EM2880_BOARD_MSI_DIGIVOX_AD_II }, { USB_DEVICE(0xeb1a, 0xe323), .driver_info = EM2882_BOARD_KWORLD_VS_DVBT }, { USB_DEVICE(0xeb1a, 0xe350), .driver_info = EM2870_BOARD_KWORLD_350U }, { USB_DEVICE(0xeb1a, 0xe355), .driver_info = EM2870_BOARD_KWORLD_355U }, { USB_DEVICE(0xeb1a, 0x2801), .driver_info = EM2800_BOARD_GRABBEEX_USB2800 }, { USB_DEVICE(0xeb1a, 0xe357), .driver_info = EM2870_BOARD_KWORLD_355U }, { USB_DEVICE(0xeb1a, 0xe359), .driver_info = EM2870_BOARD_KWORLD_355U }, { USB_DEVICE(0x1b80, 0xe302), /* Kaiser Baas Video to DVD maker */ .driver_info = EM2820_BOARD_PINNACLE_DVC_90 }, { USB_DEVICE(0x1b80, 0xe304), /* Kworld DVD Maker 2 */ .driver_info = EM2820_BOARD_PINNACLE_DVC_90 }, { USB_DEVICE(0x0ccd, 0x0036), .driver_info = EM2820_BOARD_TERRATEC_CINERGY_250 }, { USB_DEVICE(0x0ccd, 0x004c), .driver_info = EM2880_BOARD_TERRATEC_HYBRID_XS_FR }, { USB_DEVICE(0x0ccd, 0x004f), .driver_info = EM2860_BOARD_TERRATEC_HYBRID_XS }, { USB_DEVICE(0x0ccd, 0x005e), .driver_info = EM2882_BOARD_TERRATEC_HYBRID_XS }, { USB_DEVICE(0x0ccd, 0x0042), .driver_info = EM2882_BOARD_TERRATEC_HYBRID_XS }, { USB_DEVICE(0x0ccd, 0x0043), .driver_info = EM2870_BOARD_TERRATEC_XS_MT2060 }, { USB_DEVICE(0x0ccd, 0x008e), /* Cinergy HTC USB XS Rev. 1 */ .driver_info = EM2884_BOARD_TERRATEC_HTC_USB_XS }, { USB_DEVICE(0x0ccd, 0x00ac), /* Cinergy HTC USB XS Rev. 2 */ .driver_info = EM2884_BOARD_TERRATEC_HTC_USB_XS }, { USB_DEVICE(0x0ccd, 0x10a2), /* H5 Rev. 1 */ .driver_info = EM2884_BOARD_TERRATEC_H5 }, { USB_DEVICE(0x0ccd, 0x10ad), /* H5 Rev. 2 */ .driver_info = EM2884_BOARD_TERRATEC_H5 }, { USB_DEVICE(0x0ccd, 0x10b6), /* H5 Rev. 3 */ .driver_info = EM2884_BOARD_TERRATEC_H5 }, { USB_DEVICE(0x0ccd, 0x10b2), /* H6 */ .driver_info = EM2884_BOARD_TERRATEC_H6 }, { USB_DEVICE(0x0ccd, 0x0084), .driver_info = EM2860_BOARD_TERRATEC_AV350 }, { USB_DEVICE(0x0ccd, 0x0096), .driver_info = EM2860_BOARD_TERRATEC_GRABBY }, { USB_DEVICE(0x0ccd, 0x10AF), .driver_info = EM2860_BOARD_TERRATEC_GRABBY }, { USB_DEVICE(0x0ccd, 0x00b2), .driver_info = EM2884_BOARD_CINERGY_HTC_STICK }, { USB_DEVICE(0x0fd9, 0x0018), .driver_info = EM2884_BOARD_ELGATO_EYETV_HYBRID_2008 }, { USB_DEVICE(0x0fd9, 0x0033), .driver_info = EM2860_BOARD_ELGATO_VIDEO_CAPTURE }, { USB_DEVICE(0x185b, 0x2870), .driver_info = EM2870_BOARD_COMPRO_VIDEOMATE }, { USB_DEVICE(0x185b, 0x2041), .driver_info = EM2820_BOARD_COMPRO_VIDEOMATE_FORYOU }, { USB_DEVICE(0x2040, 0x4200), .driver_info = EM2820_BOARD_HAUPPAUGE_WINTV_USB_2 }, { USB_DEVICE(0x2040, 0x4201), .driver_info = EM2820_BOARD_HAUPPAUGE_WINTV_USB_2 }, { USB_DEVICE(0x2040, 0x6500), .driver_info = EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900 }, { USB_DEVICE(0x2040, 0x6502), .driver_info = EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900_R2 }, { USB_DEVICE(0x2040, 0x6513), /* HCW HVR-980 */ .driver_info = EM2883_BOARD_HAUPPAUGE_WINTV_HVR_950 }, { USB_DEVICE(0x2040, 0x6517), /* HP HVR-950 */ .driver_info = EM2883_BOARD_HAUPPAUGE_WINTV_HVR_950 }, { USB_DEVICE(0x2040, 0x651b), /* RP HVR-950 */ .driver_info = EM2883_BOARD_HAUPPAUGE_WINTV_HVR_950 }, { USB_DEVICE(0x2040, 0x651f), .driver_info = EM2883_BOARD_HAUPPAUGE_WINTV_HVR_850 }, { USB_DEVICE(0x2040, 0x0265), .driver_info = EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_DVB }, { USB_DEVICE(0x2040, 0x8265), .driver_info = EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_DVB }, { USB_DEVICE(0x2040, 0x026d), .driver_info = EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_01595 }, { USB_DEVICE(0x2040, 0x826d), .driver_info = EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_01595 }, { USB_DEVICE(0x2040, 0x846d), .driver_info = EM2874_BOARD_HAUPPAUGE_USB_QUADHD }, { USB_DEVICE(0x0438, 0xb002), .driver_info = EM2880_BOARD_AMD_ATI_TV_WONDER_HD_600 }, { USB_DEVICE(0x2001, 0xf112), .driver_info = EM2820_BOARD_DLINK_USB_TV }, { USB_DEVICE(0x2304, 0x0207), .driver_info = EM2820_BOARD_PINNACLE_DVC_90 }, { USB_DEVICE(0x2304, 0x0208), .driver_info = EM2820_BOARD_PINNACLE_USB_2 }, { USB_DEVICE(0x2304, 0x021a), .driver_info = EM2820_BOARD_PINNACLE_DVC_90 }, { USB_DEVICE(0x2304, 0x0226), .driver_info = EM2882_BOARD_PINNACLE_HYBRID_PRO_330E }, { USB_DEVICE(0x2304, 0x0227), .driver_info = EM2880_BOARD_PINNACLE_PCTV_HD_PRO }, { USB_DEVICE(0x2304, 0x023f), .driver_info = EM2874_BOARD_PCTV_HD_MINI_80E }, { USB_DEVICE(0x0413, 0x6023), .driver_info = EM2800_BOARD_LEADTEK_WINFAST_USBII }, { USB_DEVICE(0x093b, 0xa003), .driver_info = EM2820_BOARD_PINNACLE_DVC_90 }, { USB_DEVICE(0x093b, 0xa005), .driver_info = EM2861_BOARD_PLEXTOR_PX_TV100U }, { USB_DEVICE(0x04bb, 0x0515), .driver_info = EM2820_BOARD_IODATA_GVMVP_SZ }, { USB_DEVICE(0xeb1a, 0x50a6), .driver_info = EM2860_BOARD_GADMEI_UTV330 }, { USB_DEVICE(0x1b80, 0xa340), .driver_info = EM2870_BOARD_KWORLD_A340 }, { USB_DEVICE(0x1b80, 0xe346), .driver_info = EM2874_BOARD_KWORLD_UB435Q_V2 }, { USB_DEVICE(0x1b80, 0xe34c), .driver_info = EM2874_BOARD_KWORLD_UB435Q_V3 }, { USB_DEVICE(0x2013, 0x024f), .driver_info = EM28174_BOARD_PCTV_290E }, { USB_DEVICE(0x2013, 0x024c), .driver_info = EM28174_BOARD_PCTV_460E }, { USB_DEVICE(0x2040, 0x1605), .driver_info = EM2884_BOARD_HAUPPAUGE_WINTV_HVR_930C }, { USB_DEVICE(0x1b80, 0xe755), .driver_info = EM2884_BOARD_C3TECH_DIGITAL_DUO }, { USB_DEVICE(0xeb1a, 0x5006), .driver_info = EM2860_BOARD_HT_VIDBOX_NW03 }, { USB_DEVICE(0x1b80, 0xe309), /* Sveon STV40 */ .driver_info = EM2860_BOARD_EASYCAP }, { USB_DEVICE(0x1b80, 0xe425), .driver_info = EM2874_BOARD_MAXMEDIA_UB425_TC }, { USB_DEVICE(0x1f4d, 0x1abe), .driver_info = EM2860_BOARD_MYGICA_IGRABBER }, { USB_DEVICE(0x2304, 0x0242), .driver_info = EM2884_BOARD_PCTV_510E }, { USB_DEVICE(0x2013, 0x0251), .driver_info = EM2884_BOARD_PCTV_520E }, { USB_DEVICE(0x1b80, 0xe1cc), .driver_info = EM2874_BOARD_DELOCK_61959 }, { USB_DEVICE(0x1ae7, 0x9003), .driver_info = EM2765_BOARD_SPEEDLINK_VAD_LAPLACE }, { USB_DEVICE(0x1ae7, 0x9004), .driver_info = EM2765_BOARD_SPEEDLINK_VAD_LAPLACE }, { USB_DEVICE(0x2013, 0x0258), .driver_info = EM28178_BOARD_PCTV_461E }, { USB_DEVICE(0x2013, 0x8258), /* Bulk transport 461e */ .driver_info = EM28178_BOARD_PCTV_461E }, { USB_DEVICE(0x2013, 0x0461), .driver_info = EM28178_BOARD_PCTV_461E_V2 }, { USB_DEVICE(0x2013, 0x8461), /* Bulk transport 461e v2 */ .driver_info = EM28178_BOARD_PCTV_461E_V2 }, { USB_DEVICE(0x2013, 0x0259), .driver_info = EM28178_BOARD_PCTV_461E_V2 }, { USB_DEVICE(0x2013, 0x025f), .driver_info = EM28178_BOARD_PCTV_292E }, { USB_DEVICE(0x2013, 0x0264), /* Hauppauge WinTV-soloHD 292e SE */ .driver_info = EM28178_BOARD_PCTV_292E }, { USB_DEVICE(0x2040, 0x0264), /* Hauppauge WinTV-soloHD Isoc */ .driver_info = EM28178_BOARD_PCTV_292E }, { USB_DEVICE(0x2040, 0x8264), /* Hauppauge OEM Generic WinTV-soloHD Bulk */ .driver_info = EM28178_BOARD_PCTV_292E }, { USB_DEVICE(0x2040, 0x8268), /* Hauppauge Retail WinTV-soloHD Bulk */ .driver_info = EM28178_BOARD_PCTV_292E }, { USB_DEVICE(0x0413, 0x6f07), .driver_info = EM2861_BOARD_LEADTEK_VC100 }, { USB_DEVICE(0xeb1a, 0x8179), .driver_info = EM28178_BOARD_TERRATEC_T2_STICK_HD }, { USB_DEVICE(0x3275, 0x0085), .driver_info = EM28178_BOARD_PLEX_PX_BCUD }, { USB_DEVICE(0xeb1a, 0x5051), /* Ion Video 2 PC MKII / Startech svid2usb23 / Raygo R12-41373 */ .driver_info = EM2860_BOARD_TVP5150_REFERENCE_DESIGN }, { USB_DEVICE(0x1b80, 0xe349), /* Magix USB Videowandler-2 */ .driver_info = EM2861_BOARD_MAGIX_VIDEOWANDLER2 }, { }, }; MODULE_DEVICE_TABLE(usb, em28xx_id_table); /* * EEPROM hash table for devices with generic USB IDs */ static const struct em28xx_hash_table em28xx_eeprom_hash[] = { /* P/N: SA 60002070465 Tuner: TVF7533-MF */ {0x6ce05a8f, EM2820_BOARD_PROLINK_PLAYTV_USB2, TUNER_YMEC_TVF_5533MF}, {0x72cc5a8b, EM2820_BOARD_PROLINK_PLAYTV_BOX4_USB2, TUNER_YMEC_TVF_5533MF}, {0x966a0441, EM2880_BOARD_KWORLD_DVB_310U, TUNER_XC2028}, {0x166a0441, EM2880_BOARD_EMPIRE_DUAL_TV, TUNER_XC2028}, {0xcee44a99, EM2882_BOARD_EVGA_INDTUBE, TUNER_XC2028}, {0xb8846b20, EM2881_BOARD_PINNACLE_HYBRID_PRO, TUNER_XC2028}, {0x63f653bd, EM2870_BOARD_REDDO_DVB_C_USB_BOX, TUNER_ABSENT}, {0x4e913442, EM2882_BOARD_DIKOM_DK300, TUNER_XC2028}, {0x85dd871e, EM2882_BOARD_ZOLID_HYBRID_TV_STICK, TUNER_XC2028}, {0x8f597549, EM2860_BOARD_MYGICA_UTV3, TUNER_TENA_TNF_931D_DFDR1}, }; /* I2C devicelist hash table for devices with generic USB IDs */ static const struct em28xx_hash_table em28xx_i2c_hash[] = { {0xb06a32c3, EM2800_BOARD_TERRATEC_CINERGY_200, TUNER_LG_PAL_NEW_TAPC}, {0xf51200e3, EM2800_BOARD_VGEAR_POCKETTV, TUNER_LG_PAL_NEW_TAPC}, {0x1ba50080, EM2860_BOARD_SAA711X_REFERENCE_DESIGN, TUNER_ABSENT}, {0x77800080, EM2860_BOARD_TVP5150_REFERENCE_DESIGN, TUNER_ABSENT}, {0xc51200e3, EM2820_BOARD_GADMEI_TVR200, TUNER_LG_PAL_NEW_TAPC}, {0x4ba50080, EM2861_BOARD_GADMEI_UTV330PLUS, TUNER_TNF_5335MF}, {0x6b800080, EM2874_BOARD_LEADERSHIP_ISDBT, TUNER_ABSENT}, {0x27e10080, EM2882_BOARD_ZOLID_HYBRID_TV_STICK, TUNER_XC2028}, {0x840d0484, EM2860_BOARD_MYGICA_UTV3, TUNER_TENA_TNF_931D_DFDR1}, }; /* NOTE: introduce a separate hash table for devices with 16 bit eeproms */ int em28xx_tuner_callback(void *ptr, int component, int command, int arg) { struct em28xx_i2c_bus *i2c_bus = ptr; struct em28xx *dev = i2c_bus->dev; int rc = 0; if (dev->tuner_type != TUNER_XC2028 && dev->tuner_type != TUNER_XC5000) return 0; if (command != XC2028_TUNER_RESET && command != XC5000_TUNER_RESET) return 0; rc = em28xx_gpio_set(dev, dev->board.tuner_gpio); return rc; } EXPORT_SYMBOL_GPL(em28xx_tuner_callback); static inline void em28xx_set_xclk_i2c_speed(struct em28xx *dev) { const struct em28xx_board *board = &em28xx_boards[dev->model]; u8 xclk = board->xclk, i2c_speed = board->i2c_speed; /* * Those are the default values for the majority of boards * Use those values if not specified otherwise at boards entry */ if (!xclk) xclk = EM28XX_XCLK_IR_RC5_MODE | EM28XX_XCLK_FREQUENCY_12MHZ; em28xx_write_reg(dev, EM28XX_R0F_XCLK, xclk); if (!i2c_speed) i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_100_KHZ; dev->i2c_speed = i2c_speed & 0x03; if (!dev->board.is_em2800) em28xx_write_reg(dev, EM28XX_R06_I2C_CLK, i2c_speed); msleep(50); } static inline void em28xx_set_model(struct em28xx *dev) { dev->board = em28xx_boards[dev->model]; dev->has_msp34xx = dev->board.has_msp34xx; dev->is_webcam = dev->board.is_webcam; em28xx_set_xclk_i2c_speed(dev); /* Should be initialized early, for I2C to work */ dev->def_i2c_bus = dev->board.def_i2c_bus; } /* * Wait until AC97_RESET reports the expected value reliably before proceeding. * We also check that two unrelated registers accesses don't return the same * value to avoid premature return. * This procedure helps ensuring AC97 register accesses are reliable. */ static int em28xx_wait_until_ac97_features_equals(struct em28xx *dev, int expected_feat) { unsigned long timeout = jiffies + msecs_to_jiffies(2000); int feat, powerdown; while (time_is_after_jiffies(timeout)) { feat = em28xx_read_ac97(dev, AC97_RESET); if (feat < 0) return feat; powerdown = em28xx_read_ac97(dev, AC97_POWERDOWN); if (powerdown < 0) return powerdown; if (feat == expected_feat && feat != powerdown) return 0; msleep(50); } dev_warn(&dev->intf->dev, "AC97 registers access is not reliable !\n"); return -ETIMEDOUT; } /* * Since em28xx_pre_card_setup() requires a proper dev->model, * this won't work for boards with generic PCI IDs */ static void em28xx_pre_card_setup(struct em28xx *dev) { /* * Set the initial XCLK and I2C clock values based on the board * definition */ em28xx_set_xclk_i2c_speed(dev); /* request some modules */ switch (dev->model) { case EM2861_BOARD_PLEXTOR_PX_TV100U: /* Sets the msp34xx I2S speed */ dev->i2s_speed = 2048000; break; case EM2861_BOARD_KWORLD_PVRTV_300U: case EM2880_BOARD_KWORLD_DVB_305U: em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0x6d); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0x7d); usleep_range(10000, 11000); break; case EM2870_BOARD_COMPRO_VIDEOMATE: /* * TODO: someone can do some cleanup here... * not everything's needed */ em28xx_write_reg(dev, EM2880_R04_GPO, 0x00); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2880_R04_GPO, 0x01); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfc); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xdc); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfc); msleep(70); break; case EM2870_BOARD_TERRATEC_XS_MT2060: /* * this device needs some gpio writes to get the DVB-T * demod work */ em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xde); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe); msleep(70); break; case EM2870_BOARD_PINNACLE_PCTV_DVB: /* * this device needs some gpio writes to get the * DVB-T demod work */ em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xde); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe); msleep(70); break; case EM2820_BOARD_GADMEI_UTV310: case EM2820_BOARD_MSI_VOX_USB_2: /* enables audio for that devices */ em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd); break; case EM2882_BOARD_KWORLD_ATSC_315U: em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xff); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2880_R04_GPO, 0x00); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2880_R04_GPO, 0x08); usleep_range(10000, 11000); break; case EM2860_BOARD_KAIOMY_TVNPC_U2: em28xx_write_regs(dev, EM28XX_R0F_XCLK, "\x07", 1); em28xx_write_regs(dev, EM28XX_R06_I2C_CLK, "\x40", 1); em28xx_write_regs(dev, 0x0d, "\x42", 1); em28xx_write_regs(dev, 0x08, "\xfd", 1); usleep_range(10000, 11000); em28xx_write_regs(dev, 0x08, "\xff", 1); usleep_range(10000, 11000); em28xx_write_regs(dev, 0x08, "\x7f", 1); usleep_range(10000, 11000); em28xx_write_regs(dev, 0x08, "\x6b", 1); break; case EM2860_BOARD_EASYCAP: em28xx_write_regs(dev, 0x08, "\xf8", 1); break; case EM2820_BOARD_IODATA_GVMVP_SZ: em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xff); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xf7); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe); msleep(70); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd); msleep(70); break; case EM2860_BOARD_TERRATEC_GRABBY: /* * HACK?: Ensure AC97 register reading is reliable before * proceeding. In practice, this will wait about 1.6 seconds. */ em28xx_wait_until_ac97_features_equals(dev, 0x6a90); break; } em28xx_gpio_set(dev, dev->board.tuner_gpio); em28xx_set_mode(dev, EM28XX_ANALOG_MODE); /* Unlock device */ em28xx_set_mode(dev, EM28XX_SUSPEND); } static int em28xx_hint_board(struct em28xx *dev) { int i; if (dev->is_webcam) { if (dev->em28xx_sensor == EM28XX_MT9V011) { dev->model = EM2820_BOARD_SILVERCREST_WEBCAM; } else if (dev->em28xx_sensor == EM28XX_MT9M001 || dev->em28xx_sensor == EM28XX_MT9M111) { dev->model = EM2750_BOARD_UNKNOWN; } /* FIXME: IMPROVE ! */ return 0; } /* * HINT method: EEPROM * * This method works only for boards with eeprom. * Uses a hash of all eeprom bytes. The hash should be * unique for a vendor/tuner pair. * There are a high chance that tuners for different * video standards produce different hashes. */ for (i = 0; i < ARRAY_SIZE(em28xx_eeprom_hash); i++) { if (dev->hash == em28xx_eeprom_hash[i].hash) { dev->model = em28xx_eeprom_hash[i].model; dev->tuner_type = em28xx_eeprom_hash[i].tuner; dev_err(&dev->intf->dev, "Your board has no unique USB ID.\n" "A hint were successfully done, based on eeprom hash.\n" "This method is not 100%% failproof.\n" "If the board were misdetected, please email this log to:\n" "\tV4L Mailing List <linux-media@vger.kernel.org>\n" "Board detected as %s\n", em28xx_boards[dev->model].name); return 0; } } /* * HINT method: I2C attached devices * * This method works for all boards. * Uses a hash of i2c scanned devices. * Devices with the same i2c attached chips will * be considered equal. * This method is less precise than the eeprom one. */ /* user did not request i2c scanning => do it now */ if (!dev->i2c_hash) em28xx_do_i2c_scan(dev, dev->def_i2c_bus); for (i = 0; i < ARRAY_SIZE(em28xx_i2c_hash); i++) { if (dev->i2c_hash == em28xx_i2c_hash[i].hash) { dev->model = em28xx_i2c_hash[i].model; dev->tuner_type = em28xx_i2c_hash[i].tuner; dev_err(&dev->intf->dev, "Your board has no unique USB ID.\n" "A hint were successfully done, based on i2c devicelist hash.\n" "This method is not 100%% failproof.\n" "If the board were misdetected, please email this log to:\n" "\tV4L Mailing List <linux-media@vger.kernel.org>\n" "Board detected as %s\n", em28xx_boards[dev->model].name); return 0; } } dev_err(&dev->intf->dev, "Your board has no unique USB ID and thus need a hint to be detected.\n" "You may try to use card=<n> insmod option to workaround that.\n" "Please send an email with this log to:\n" "\tV4L Mailing List <linux-media@vger.kernel.org>\n" "Board eeprom hash is 0x%08lx\n" "Board i2c devicelist hash is 0x%08lx\n", dev->hash, dev->i2c_hash); dev_err(&dev->intf->dev, "Here is a list of valid choices for the card=<n> insmod option:\n"); for (i = 0; i < em28xx_bcount; i++) { dev_err(&dev->intf->dev, " card=%d -> %s\n", i, em28xx_boards[i].name); } return -1; } static void em28xx_card_setup(struct em28xx *dev) { int i, j, idx; bool duplicate_entry; /* * If the device can be a webcam, seek for a sensor. * If sensor is not found, then it isn't a webcam. */ if (dev->is_webcam) { em28xx_detect_sensor(dev); if (dev->em28xx_sensor == EM28XX_NOSENSOR) /* NOTE: error/unknown sensor/no sensor */ dev->is_webcam = 0; } switch (dev->model) { case EM2750_BOARD_UNKNOWN: case EM2820_BOARD_UNKNOWN: case EM2800_BOARD_UNKNOWN: /* * The K-WORLD DVB-T 310U is detected as an MSI Digivox AD. * * This occurs because they share identical USB vendor and * product IDs. * * What we do here is look up the EEPROM hash of the K-WORLD * and if it is found then we decide that we do not have * a DIGIVOX and reset the device to the K-WORLD instead. * * This solution is only valid if they do not share eeprom * hash identities which has not been determined as yet. */ if (em28xx_hint_board(dev) < 0) { dev_err(&dev->intf->dev, "Board not discovered\n"); } else { em28xx_set_model(dev); em28xx_pre_card_setup(dev); } break; default: em28xx_set_model(dev); } dev_info(&dev->intf->dev, "Identified as %s (card=%d)\n", dev->board.name, dev->model); dev->tuner_type = em28xx_boards[dev->model].tuner_type; /* request some modules */ switch (dev->model) { case EM2820_BOARD_HAUPPAUGE_WINTV_USB_2: case EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900: case EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900_R2: case EM2883_BOARD_HAUPPAUGE_WINTV_HVR_850: case EM2883_BOARD_HAUPPAUGE_WINTV_HVR_950: case EM2884_BOARD_HAUPPAUGE_WINTV_HVR_930C: case EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_DVB: case EM28174_BOARD_HAUPPAUGE_WINTV_DUALHD_01595: { struct tveeprom tv; if (!dev->eedata) break; #if defined(CONFIG_MODULES) && defined(MODULE) request_module("tveeprom"); #endif /* Call first TVeeprom */ tveeprom_hauppauge_analog(&tv, dev->eedata); dev->tuner_type = tv.tuner_type; if (tv.audio_processor == TVEEPROM_AUDPROC_MSP) { dev->i2s_speed = 2048000; dev->has_msp34xx = 1; } break; } case EM2882_BOARD_KWORLD_ATSC_315U: em28xx_write_reg(dev, 0x0d, 0x42); usleep_range(10000, 11000); em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd); usleep_range(10000, 11000); break; case EM2820_BOARD_KWORLD_PVRTV2800RF: /* GPIO enables sound on KWORLD PVR TV 2800RF */ em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xf9); break; case EM2820_BOARD_UNKNOWN: case EM2800_BOARD_UNKNOWN: /* * The K-WORLD DVB-T 310U is detected as an MSI Digivox AD. * * This occurs because they share identical USB vendor and * product IDs. * * What we do here is look up the EEPROM hash of the K-WORLD * and if it is found then we decide that we do not have * a DIGIVOX and reset the device to the K-WORLD instead. * * This solution is only valid if they do not share eeprom * hash identities which has not been determined as yet. */ case EM2880_BOARD_MSI_DIGIVOX_AD: if (!em28xx_hint_board(dev)) em28xx_set_model(dev); /* * In cases where we had to use a board hint, the call to * em28xx_set_mode() in em28xx_pre_card_setup() was a no-op, * so make the call now so the analog GPIOs are set properly * before probing the i2c bus. */ em28xx_gpio_set(dev, dev->board.tuner_gpio); em28xx_set_mode(dev, EM28XX_ANALOG_MODE); break; /* * The Dikom DK300 is detected as an Kworld VS-DVB-T 323UR. * * This occurs because they share identical USB vendor and * product IDs. * * What we do here is look up the EEPROM hash of the Dikom * and if it is found then we decide that we do not have * a Kworld and reset the device to the Dikom instead. * * This solution is only valid if they do not share eeprom * hash identities which has not been determined as yet. */ case EM2882_BOARD_KWORLD_VS_DVBT: if (!em28xx_hint_board(dev)) em28xx_set_model(dev); /* * In cases where we had to use a board hint, the call to * em28xx_set_mode() in em28xx_pre_card_setup() was a no-op, * so make the call now so the analog GPIOs are set properly * before probing the i2c bus. */ em28xx_gpio_set(dev, dev->board.tuner_gpio); em28xx_set_mode(dev, EM28XX_ANALOG_MODE); break; } if (dev->board.valid == EM28XX_BOARD_NOT_VALIDATED) { dev_err(&dev->intf->dev, "\n\n" "The support for this board weren't valid yet.\n" "Please send a report of having this working\n" "not to V4L mailing list (and/or to other addresses)\n\n"); } /* Free eeprom data memory */ kfree(dev->eedata); dev->eedata = NULL; /* Allow override tuner type by a module parameter */ if (tuner >= 0) dev->tuner_type = tuner; /* * Dynamically generate a list of valid audio inputs for this * specific board, mapping them via enum em28xx_amux. */ idx = 0; for (i = 0; i < MAX_EM28XX_INPUT; i++) { if (!INPUT(i)->type) continue; /* Skip already mapped audio inputs */ duplicate_entry = false; for (j = 0; j < idx; j++) { if (INPUT(i)->amux == dev->amux_map[j]) { duplicate_entry = true; break; } } if (duplicate_entry) continue; dev->amux_map[idx++] = INPUT(i)->amux; } for (; idx < MAX_EM28XX_INPUT; idx++) dev->amux_map[idx] = EM28XX_AMUX_UNUSED; } void em28xx_setup_xc3028(struct em28xx *dev, struct xc2028_ctrl *ctl) { memset(ctl, 0, sizeof(*ctl)); ctl->fname = XC2028_DEFAULT_FIRMWARE; ctl->max_len = 64; ctl->mts = em28xx_boards[dev->model].mts_firmware; switch (dev->model) { case EM2880_BOARD_EMPIRE_DUAL_TV: case EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900: case EM2882_BOARD_TERRATEC_HYBRID_XS: case EM2880_BOARD_TERRATEC_HYBRID_XS: case EM2880_BOARD_TERRATEC_HYBRID_XS_FR: case EM2881_BOARD_PINNACLE_HYBRID_PRO: case EM2882_BOARD_ZOLID_HYBRID_TV_STICK: ctl->demod = XC3028_FE_ZARLINK456; break; case EM2880_BOARD_HAUPPAUGE_WINTV_HVR_900_R2: case EM2882_BOARD_PINNACLE_HYBRID_PRO_330E: ctl->demod = XC3028_FE_DEFAULT; break; case EM2880_BOARD_AMD_ATI_TV_WONDER_HD_600: ctl->demod = XC3028_FE_DEFAULT; ctl->fname = XC3028L_DEFAULT_FIRMWARE; break; case EM2883_BOARD_HAUPPAUGE_WINTV_HVR_850: case EM2883_BOARD_HAUPPAUGE_WINTV_HVR_950: case EM2880_BOARD_PINNACLE_PCTV_HD_PRO: /* FIXME: Better to specify the needed IF */ ctl->demod = XC3028_FE_DEFAULT; break; case EM2883_BOARD_KWORLD_HYBRID_330U: case EM2882_BOARD_DIKOM_DK300: case EM2882_BOARD_KWORLD_VS_DVBT: ctl->demod = XC3028_FE_CHINA; ctl->fname = XC2028_DEFAULT_FIRMWARE; break; case EM2882_BOARD_EVGA_INDTUBE: ctl->demod = XC3028_FE_CHINA; ctl->fname = XC3028L_DEFAULT_FIRMWARE; break; default: ctl->demod = XC3028_FE_OREN538; } } EXPORT_SYMBOL_GPL(em28xx_setup_xc3028); static void request_module_async(struct work_struct *work) { struct em28xx *dev = container_of(work, struct em28xx, request_module_wk); /* * The em28xx extensions can be modules or builtin. If the * modules are already loaded or are built in, those extensions * can be initialised right now. Otherwise, the module init * code will do it. */ /* * Devices with an audio-only intf also have a V4L/DVB/RC * intf. Don't register extensions twice on those devices. */ if (dev->is_audio_only) { #if defined(CONFIG_MODULES) && defined(MODULE) request_module("em28xx-alsa"); #endif return; } em28xx_init_extension(dev); #if defined(CONFIG_MODULES) && defined(MODULE) if (dev->has_video) request_module("em28xx-v4l"); if (dev->usb_audio_type == EM28XX_USB_AUDIO_CLASS) request_module("snd-usb-audio"); else if (dev->usb_audio_type == EM28XX_USB_AUDIO_VENDOR) request_module("em28xx-alsa"); if (dev->board.has_dvb) request_module("em28xx-dvb"); if (dev->board.buttons || ((dev->board.ir_codes || dev->board.has_ir_i2c) && !disable_ir)) request_module("em28xx-rc"); #endif /* CONFIG_MODULES */ } static void request_modules(struct em28xx *dev) { INIT_WORK(&dev->request_module_wk, request_module_async); schedule_work(&dev->request_module_wk); } static void flush_request_modules(struct em28xx *dev) { flush_work(&dev->request_module_wk); } static int em28xx_media_device_init(struct em28xx *dev, struct usb_device *udev) { #ifdef CONFIG_MEDIA_CONTROLLER struct media_device *mdev; mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return -ENOMEM; if (udev->product) media_device_usb_init(mdev, udev, udev->product); else if (udev->manufacturer) media_device_usb_init(mdev, udev, udev->manufacturer); else media_device_usb_init(mdev, udev, dev_name(&dev->intf->dev)); dev->media_dev = mdev; #endif return 0; } static void em28xx_unregister_media_device(struct em28xx *dev) { #ifdef CONFIG_MEDIA_CONTROLLER if (dev->media_dev) { media_device_unregister(dev->media_dev); media_device_cleanup(dev->media_dev); kfree(dev->media_dev); dev->media_dev = NULL; } #endif } /* * em28xx_release_resources() * unregisters the v4l2,i2c and usb devices * called when the device gets disconnected or at module unload */ static void em28xx_release_resources(struct em28xx *dev) { struct usb_device *udev = interface_to_usbdev(dev->intf); /*FIXME: I2C IR should be disconnected */ mutex_lock(&dev->lock); em28xx_unregister_media_device(dev); if (dev->def_i2c_bus) em28xx_i2c_unregister(dev, 1); em28xx_i2c_unregister(dev, 0); if (dev->ts == PRIMARY_TS) usb_put_dev(udev); /* Mark device as unused */ clear_bit(dev->devno, em28xx_devused); mutex_unlock(&dev->lock); }; /** * em28xx_free_device() - Free em28xx device * * @ref: struct kref for em28xx device * * This is called when all extensions and em28xx core unregisters a device */ void em28xx_free_device(struct kref *ref) { struct em28xx *dev = kref_to_dev(ref); dev_info(&dev->intf->dev, "Freeing device\n"); if (!dev->disconnected) em28xx_release_resources(dev); if (dev->ts == PRIMARY_TS) kfree(dev->alt_max_pkt_size_isoc); kfree(dev); } EXPORT_SYMBOL_GPL(em28xx_free_device); /* * em28xx_init_dev() * allocates and inits the device structs, registers i2c bus and v4l device */ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev, struct usb_interface *intf, int minor) { int retval; const char *chip_name = NULL; dev->intf = intf; mutex_init(&dev->ctrl_urb_lock); spin_lock_init(&dev->slock); dev->em28xx_write_regs = em28xx_write_regs; dev->em28xx_read_reg = em28xx_read_reg; dev->em28xx_read_reg_req_len = em28xx_read_reg_req_len; dev->em28xx_write_regs_req = em28xx_write_regs_req; dev->em28xx_read_reg_req = em28xx_read_reg_req; dev->board.is_em2800 = em28xx_boards[dev->model].is_em2800; em28xx_set_model(dev); dev->wait_after_write = 5; /* Based on the Chip ID, set the device configuration */ retval = em28xx_read_reg(dev, EM28XX_R0A_CHIPID); if (retval > 0) { dev->chip_id = retval; switch (dev->chip_id) { case CHIP_ID_EM2800: chip_name = "em2800"; break; case CHIP_ID_EM2710: chip_name = "em2710"; break; case CHIP_ID_EM2750: chip_name = "em2750"; break; case CHIP_ID_EM2765: chip_name = "em2765"; dev->wait_after_write = 0; dev->is_em25xx = 1; dev->eeprom_addrwidth_16bit = 1; break; case CHIP_ID_EM2820: chip_name = "em2710/2820"; if (le16_to_cpu(udev->descriptor.idVendor) == 0xeb1a) { __le16 idProd = udev->descriptor.idProduct; if (le16_to_cpu(idProd) == 0x2710) chip_name = "em2710"; else if (le16_to_cpu(idProd) == 0x2820) chip_name = "em2820"; } /* NOTE: the em2820 is used in webcams, too ! */ break; case CHIP_ID_EM2840: chip_name = "em2840"; break; case CHIP_ID_EM2860: chip_name = "em2860"; break; case CHIP_ID_EM2870: chip_name = "em2870"; dev->wait_after_write = 0; break; case CHIP_ID_EM2874: chip_name = "em2874"; dev->wait_after_write = 0; dev->eeprom_addrwidth_16bit = 1; break; case CHIP_ID_EM28174: chip_name = "em28174"; dev->wait_after_write = 0; dev->eeprom_addrwidth_16bit = 1; break; case CHIP_ID_EM28178: chip_name = "em28178"; dev->wait_after_write = 0; dev->eeprom_addrwidth_16bit = 1; break; case CHIP_ID_EM2883: chip_name = "em2882/3"; dev->wait_after_write = 0; break; case CHIP_ID_EM2884: chip_name = "em2884"; dev->wait_after_write = 0; dev->eeprom_addrwidth_16bit = 1; break; } } if (!chip_name) dev_info(&dev->intf->dev, "unknown em28xx chip ID (%d)\n", dev->chip_id); else dev_info(&dev->intf->dev, "chip ID is %s\n", chip_name); em28xx_media_device_init(dev, udev); if (dev->is_audio_only) { retval = em28xx_audio_setup(dev); if (retval) { retval = -ENODEV; goto err_deinit_media; } em28xx_init_extension(dev); return 0; } em28xx_pre_card_setup(dev); rt_mutex_init(&dev->i2c_bus_lock); /* register i2c bus 0 */ if (dev->board.is_em2800) retval = em28xx_i2c_register(dev, 0, EM28XX_I2C_ALGO_EM2800); else retval = em28xx_i2c_register(dev, 0, EM28XX_I2C_ALGO_EM28XX); if (retval < 0) { dev_err(&dev->intf->dev, "%s: em28xx_i2c_register bus 0 - error [%d]!\n", __func__, retval); goto err_deinit_media; } /* register i2c bus 1 */ if (dev->def_i2c_bus) { if (dev->is_em25xx) retval = em28xx_i2c_register(dev, 1, EM28XX_I2C_ALGO_EM25XX_BUS_B); else retval = em28xx_i2c_register(dev, 1, EM28XX_I2C_ALGO_EM28XX); if (retval < 0) { dev_err(&dev->intf->dev, "%s: em28xx_i2c_register bus 1 - error [%d]!\n", __func__, retval); goto err_unreg_i2c; } } /* Do board specific init and eeprom reading */ em28xx_card_setup(dev); return 0; err_unreg_i2c: em28xx_i2c_unregister(dev, 0); err_deinit_media: em28xx_unregister_media_device(dev); return retval; } static int em28xx_duplicate_dev(struct em28xx *dev) { int nr; struct em28xx *sec_dev = kmemdup(dev, sizeof(*sec_dev), GFP_KERNEL); if (!sec_dev) { dev->dev_next = NULL; return -ENOMEM; } /* Check to see next free device and mark as used */ do { nr = find_first_zero_bit(em28xx_devused, EM28XX_MAXBOARDS); if (nr >= EM28XX_MAXBOARDS) { /* No free device slots */ dev_warn(&dev->intf->dev, ": Supports only %i em28xx boards.\n", EM28XX_MAXBOARDS); kfree(sec_dev); dev->dev_next = NULL; return -ENOMEM; } } while (test_and_set_bit(nr, em28xx_devused)); sec_dev->devno = nr; snprintf(sec_dev->name, 28, "em28xx #%d", nr); sec_dev->dev_next = NULL; dev->dev_next = sec_dev; return 0; } /* high bandwidth multiplier, as encoded in highspeed endpoint descriptors */ #define hb_mult(wMaxPacketSize) (1 + (((wMaxPacketSize) >> 11) & 0x03)) static void em28xx_check_usb_descriptor(struct em28xx *dev, struct usb_device *udev, struct usb_interface *intf, int alt, int ep, bool *has_vendor_audio, bool *has_video, bool *has_dvb) { const struct usb_endpoint_descriptor *e; int sizedescr, size; /* * NOTE: * * Old logic with support for isoc transfers only was: * 0x82 isoc => analog * 0x83 isoc => audio * 0x84 isoc => digital * * New logic with support for bulk transfers * 0x82 isoc => analog * 0x82 bulk => analog * 0x83 isoc* => audio * 0x84 isoc => digital * 0x84 bulk => analog or digital** * 0x85 isoc => digital TS2 * 0x85 bulk => digital TS2 * (*: audio should always be isoc) * (**: analog, if ep 0x82 is isoc, otherwise digital) * * The new logic preserves backwards compatibility and * reflects the endpoint configurations we have seen * so far. But there might be devices for which this * logic is not sufficient... */ e = &intf->altsetting[alt].endpoint[ep].desc; if (!usb_endpoint_dir_in(e)) return; sizedescr = le16_to_cpu(e->wMaxPacketSize); size = sizedescr & 0x7ff; if (udev->speed == USB_SPEED_HIGH) size = size * hb_mult(sizedescr); /* Only inspect input endpoints */ switch (e->bEndpointAddress) { case 0x82: *has_video = true; if (usb_endpoint_xfer_isoc(e)) { dev->analog_ep_isoc = e->bEndpointAddress; dev->alt_max_pkt_size_isoc[alt] = size; } else if (usb_endpoint_xfer_bulk(e)) { dev->analog_ep_bulk = e->bEndpointAddress; } return; case 0x83: if (usb_endpoint_xfer_isoc(e)) *has_vendor_audio = true; else dev_err(&intf->dev, "error: skipping audio endpoint 0x83, because it uses bulk transfers !\n"); return; case 0x84: if (*has_video && (usb_endpoint_xfer_bulk(e))) { dev->analog_ep_bulk = e->bEndpointAddress; } else { if (usb_endpoint_xfer_isoc(e)) { if (size > dev->dvb_max_pkt_size_isoc) { /* * 2) some manufacturers (e.g. Terratec) * disable endpoints by setting * wMaxPacketSize to 0 bytes for all * alt settings. So far, we've seen * this for DVB isoc endpoints only. */ *has_dvb = true; dev->dvb_ep_isoc = e->bEndpointAddress; dev->dvb_max_pkt_size_isoc = size; dev->dvb_alt_isoc = alt; } } else { *has_dvb = true; dev->dvb_ep_bulk = e->bEndpointAddress; } } return; case 0x85: if (usb_endpoint_xfer_isoc(e)) { if (size > dev->dvb_max_pkt_size_isoc_ts2) { dev->dvb_ep_isoc_ts2 = e->bEndpointAddress; dev->dvb_max_pkt_size_isoc_ts2 = size; dev->dvb_alt_isoc = alt; } } else { dev->dvb_ep_bulk_ts2 = e->bEndpointAddress; } return; } } /* * em28xx_usb_probe() * checks for supported devices */ static int em28xx_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev; struct em28xx *dev = NULL; int retval; bool has_vendor_audio = false, has_video = false, has_dvb = false; int i, nr, try_bulk; const int ifnum = intf->altsetting[0].desc.bInterfaceNumber; char *speed; udev = usb_get_dev(interface_to_usbdev(intf)); /* Check to see next free device and mark as used */ do { nr = find_first_zero_bit(em28xx_devused, EM28XX_MAXBOARDS); if (nr >= EM28XX_MAXBOARDS) { /* No free device slots */ dev_err(&intf->dev, "Driver supports up to %i em28xx boards.\n", EM28XX_MAXBOARDS); retval = -ENOMEM; goto err_no_slot; } } while (test_and_set_bit(nr, em28xx_devused)); /* Don't register audio interfaces */ if (intf->altsetting[0].desc.bInterfaceClass == USB_CLASS_AUDIO) { dev_info(&intf->dev, "audio device (%04x:%04x): interface %i, class %i\n", le16_to_cpu(udev->descriptor.idVendor), le16_to_cpu(udev->descriptor.idProduct), ifnum, intf->altsetting[0].desc.bInterfaceClass); retval = -ENODEV; goto err; } /* allocate memory for our device state and initialize it */ dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) { retval = -ENOMEM; goto err; } /* compute alternate max packet sizes */ dev->alt_max_pkt_size_isoc = kcalloc(intf->num_altsetting, sizeof(dev->alt_max_pkt_size_isoc[0]), GFP_KERNEL); if (!dev->alt_max_pkt_size_isoc) { kfree(dev); retval = -ENOMEM; goto err; } /* Get endpoints */ for (i = 0; i < intf->num_altsetting; i++) { int ep; for (ep = 0; ep < intf->altsetting[i].desc.bNumEndpoints; ep++) em28xx_check_usb_descriptor(dev, udev, intf, i, ep, &has_vendor_audio, &has_video, &has_dvb); } if (!(has_vendor_audio || has_video || has_dvb)) { retval = -ENODEV; goto err_free; } switch (udev->speed) { case USB_SPEED_LOW: speed = "1.5"; break; case USB_SPEED_UNKNOWN: case USB_SPEED_FULL: speed = "12"; break; case USB_SPEED_HIGH: speed = "480"; break; default: speed = "unknown"; } dev_info(&intf->dev, "New device %s %s @ %s Mbps (%04x:%04x, interface %d, class %d)\n", udev->manufacturer ? udev->manufacturer : "", udev->product ? udev->product : "", speed, le16_to_cpu(udev->descriptor.idVendor), le16_to_cpu(udev->descriptor.idProduct), ifnum, intf->altsetting->desc.bInterfaceNumber); /* * Make sure we have 480 Mbps of bandwidth, otherwise things like * video stream wouldn't likely work, since 12 Mbps is generally * not enough even for most Digital TV streams. */ if (udev->speed != USB_SPEED_HIGH && disable_usb_speed_check == 0) { dev_err(&intf->dev, "Device initialization failed.\n"); dev_err(&intf->dev, "Device must be connected to a high-speed USB 2.0 port.\n"); retval = -ENODEV; goto err_free; } kref_init(&dev->ref); dev->devno = nr; dev->model = id->driver_info; dev->alt = -1; dev->is_audio_only = has_vendor_audio && !(has_video || has_dvb); dev->has_video = has_video; dev->ifnum = ifnum; dev->ts = PRIMARY_TS; snprintf(dev->name, 28, "em28xx"); dev->dev_next = NULL; if (has_vendor_audio) { dev_info(&intf->dev, "Audio interface %i found (Vendor Class)\n", ifnum); dev->usb_audio_type = EM28XX_USB_AUDIO_VENDOR; } /* Checks if audio is provided by a USB Audio Class intf */ for (i = 0; i < udev->config->desc.bNumInterfaces; i++) { struct usb_interface *uif = udev->config->interface[i]; if (uif->altsetting[0].desc.bInterfaceClass == USB_CLASS_AUDIO) { if (has_vendor_audio) dev_err(&intf->dev, "em28xx: device seems to have vendor AND usb audio class interfaces !\n" "\t\tThe vendor interface will be ignored. Please contact the developers <linux-media@vger.kernel.org>\n"); dev->usb_audio_type = EM28XX_USB_AUDIO_CLASS; break; } } if (has_video) dev_info(&intf->dev, "Video interface %i found:%s%s\n", ifnum, dev->analog_ep_bulk ? " bulk" : "", dev->analog_ep_isoc ? " isoc" : ""); if (has_dvb) dev_info(&intf->dev, "DVB interface %i found:%s%s\n", ifnum, dev->dvb_ep_bulk ? " bulk" : "", dev->dvb_ep_isoc ? " isoc" : ""); dev->num_alt = intf->num_altsetting; if ((unsigned int)card[nr] < em28xx_bcount) dev->model = card[nr]; /* save our data pointer in this intf device */ usb_set_intfdata(intf, dev); /* allocate device struct and check if the device is a webcam */ mutex_init(&dev->lock); retval = em28xx_init_dev(dev, udev, intf, nr); if (retval) goto err_free; if (usb_xfer_mode < 0) { if (dev->is_webcam) try_bulk = 1; else try_bulk = 0; } else { try_bulk = usb_xfer_mode > 0; } /* Disable V4L2 if the device doesn't have a decoder or image sensor */ if (has_video && dev->board.decoder == EM28XX_NODECODER && dev->em28xx_sensor == EM28XX_NOSENSOR) { dev_err(&intf->dev, "Currently, V4L2 is not supported on this model\n"); has_video = false; dev->has_video = false; } if (dev->board.has_dual_ts && (dev->tuner_type != TUNER_ABSENT || INPUT(0)->type)) { /* * The logic with sets alternate is not ready for dual-tuners * which analog modes. */ dev_err(&intf->dev, "We currently don't support analog TV or stream capture on dual tuners.\n"); has_video = false; } /* Select USB transfer types to use */ if (has_video) { if (!dev->analog_ep_isoc || (try_bulk && dev->analog_ep_bulk)) dev->analog_xfer_bulk = 1; dev_info(&intf->dev, "analog set to %s mode.\n", dev->analog_xfer_bulk ? "bulk" : "isoc"); } if (has_dvb) { if (!dev->dvb_ep_isoc || (try_bulk && dev->dvb_ep_bulk)) dev->dvb_xfer_bulk = 1; dev_info(&intf->dev, "dvb set to %s mode.\n", dev->dvb_xfer_bulk ? "bulk" : "isoc"); } if (dev->board.has_dual_ts && em28xx_duplicate_dev(dev) == 0) { kref_init(&dev->dev_next->ref); dev->dev_next->ts = SECONDARY_TS; dev->dev_next->alt = -1; dev->dev_next->is_audio_only = has_vendor_audio && !(has_video || has_dvb); dev->dev_next->has_video = false; dev->dev_next->ifnum = ifnum; dev->dev_next->model = id->driver_info; mutex_init(&dev->dev_next->lock); retval = em28xx_init_dev(dev->dev_next, udev, intf, dev->dev_next->devno); if (retval) goto err_free; dev->dev_next->board.ir_codes = NULL; /* No IR for 2nd tuner */ dev->dev_next->board.has_ir_i2c = 0; /* No IR for 2nd tuner */ if (usb_xfer_mode < 0) { if (dev->dev_next->is_webcam) try_bulk = 1; else try_bulk = 0; } else { try_bulk = usb_xfer_mode > 0; } /* Select USB transfer types to use */ if (has_dvb) { if (!dev->dvb_ep_isoc_ts2 || (try_bulk && dev->dvb_ep_bulk_ts2)) dev->dev_next->dvb_xfer_bulk = 1; dev_info(&dev->intf->dev, "dvb ts2 set to %s mode.\n", dev->dev_next->dvb_xfer_bulk ? "bulk" : "isoc"); } dev->dev_next->dvb_ep_isoc = dev->dvb_ep_isoc_ts2; dev->dev_next->dvb_ep_bulk = dev->dvb_ep_bulk_ts2; dev->dev_next->dvb_max_pkt_size_isoc = dev->dvb_max_pkt_size_isoc_ts2; dev->dev_next->dvb_alt_isoc = dev->dvb_alt_isoc; /* Configure hardware to support TS2*/ if (dev->dvb_xfer_bulk) { /* The ep4 and ep5 are configured for BULK */ em28xx_write_reg(dev, 0x0b, 0x96); mdelay(100); em28xx_write_reg(dev, 0x0b, 0x80); mdelay(100); } else { /* The ep4 and ep5 are configured for ISO */ em28xx_write_reg(dev, 0x0b, 0x96); mdelay(100); em28xx_write_reg(dev, 0x0b, 0x82); mdelay(100); } } request_modules(dev); /* * Do it at the end, to reduce dynamic configuration changes during * the device init. Yet, as request_modules() can be async, the * topology will likely change after the load of the em28xx subdrivers. */ #ifdef CONFIG_MEDIA_CONTROLLER /* * No need to check the return value, the device will still be * usable without media controller API. */ retval = media_device_register(dev->media_dev); #endif return 0; err_free: kfree(dev->alt_max_pkt_size_isoc); kfree(dev); err: clear_bit(nr, em28xx_devused); err_no_slot: usb_put_dev(udev); return retval; } /* * em28xx_usb_disconnect() * called when the device gets disconnected * video device will be unregistered on v4l2_close in case it is still open */ static void em28xx_usb_disconnect(struct usb_interface *intf) { struct em28xx *dev; dev = usb_get_intfdata(intf); usb_set_intfdata(intf, NULL); if (!dev) return; if (dev->dev_next) { dev->dev_next->disconnected = 1; dev_info(&dev->intf->dev, "Disconnecting %s\n", dev->dev_next->name); } dev->disconnected = 1; dev_info(&dev->intf->dev, "Disconnecting %s\n", dev->name); flush_request_modules(dev); em28xx_close_extension(dev); if (dev->dev_next) em28xx_release_resources(dev->dev_next); em28xx_release_resources(dev); if (dev->dev_next) { kref_put(&dev->dev_next->ref, em28xx_free_device); dev->dev_next = NULL; } kref_put(&dev->ref, em28xx_free_device); } static int em28xx_usb_suspend(struct usb_interface *intf, pm_message_t message) { struct em28xx *dev; dev = usb_get_intfdata(intf); if (!dev) return 0; em28xx_suspend_extension(dev); return 0; } static int em28xx_usb_resume(struct usb_interface *intf) { struct em28xx *dev; dev = usb_get_intfdata(intf); if (!dev) return 0; em28xx_resume_extension(dev); return 0; } static struct usb_driver em28xx_usb_driver = { .name = "em28xx", .probe = em28xx_usb_probe, .disconnect = em28xx_usb_disconnect, .suspend = em28xx_usb_suspend, .resume = em28xx_usb_resume, .reset_resume = em28xx_usb_resume, .id_table = em28xx_id_table, }; module_usb_driver(em28xx_usb_driver); |
| 9 2 1 2 4 4 6 2 1 3 1 1 2 2 1 1 2 17 9 6 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2016 Laura Garcia <nevola@gmail.com> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <linux/jhash.h> struct nft_jhash { u8 sreg; u8 dreg; u8 len; bool autogen_seed:1; u32 modulus; u32 seed; u32 offset; }; static void nft_jhash_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_jhash *priv = nft_expr_priv(expr); const void *data = ®s->data[priv->sreg]; u32 h; h = reciprocal_scale(jhash(data, priv->len, priv->seed), priv->modulus); regs->data[priv->dreg] = h + priv->offset; } struct nft_symhash { u8 dreg; u32 modulus; u32 offset; }; static void nft_symhash_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_symhash *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; u32 h; h = reciprocal_scale(__skb_get_hash_symmetric_net(nft_net(pkt), skb), priv->modulus); regs->data[priv->dreg] = h + priv->offset; } static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, [NFTA_HASH_LEN] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_HASH_MODULUS] = { .type = NLA_U32 }, [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, [NFTA_HASH_TYPE] = { .type = NLA_U32 }, }; static int nft_jhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_jhash *priv = nft_expr_priv(expr); u32 len; int err; if (!tb[NFTA_HASH_SREG] || !tb[NFTA_HASH_DREG] || !tb[NFTA_HASH_LEN] || !tb[NFTA_HASH_MODULUS]) return -EINVAL; if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); if (err < 0) return err; if (len == 0) return -ERANGE; priv->len = len; err = nft_parse_register_load(ctx, tb[NFTA_HASH_SREG], &priv->sreg, len); if (err < 0) return err; priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; if (tb[NFTA_HASH_SEED]) { priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED])); } else { priv->autogen_seed = true; get_random_bytes(&priv->seed, sizeof(priv->seed)); } return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_symhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_symhash *priv = nft_expr_priv(expr); if (!tb[NFTA_HASH_DREG] || !tb[NFTA_HASH_MODULUS]) return -EINVAL; if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_jhash_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_jhash *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg)) goto nla_put_failure; if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_LEN, htonl(priv->len))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) goto nla_put_failure; if (!priv->autogen_seed && nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed))) goto nla_put_failure; if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static bool nft_jhash_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { const struct nft_jhash *priv = nft_expr_priv(expr); nft_reg_track_cancel(track, priv->dreg, sizeof(u32)); return false; } static int nft_symhash_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_symhash *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) goto nla_put_failure; if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static bool nft_symhash_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { struct nft_symhash *priv = nft_expr_priv(expr); struct nft_symhash *symhash; if (!nft_reg_track_cmp(track, expr, priv->dreg)) { nft_reg_track_update(track, expr, priv->dreg, sizeof(u32)); return false; } symhash = nft_expr_priv(track->regs[priv->dreg].selector); if (priv->offset != symhash->offset || priv->modulus != symhash->modulus) { nft_reg_track_update(track, expr, priv->dreg, sizeof(u32)); return false; } if (!track->regs[priv->dreg].bitwise) return true; return false; } static struct nft_expr_type nft_hash_type; static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), .eval = nft_jhash_eval, .init = nft_jhash_init, .dump = nft_jhash_dump, .reduce = nft_jhash_reduce, }; static const struct nft_expr_ops nft_symhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), .eval = nft_symhash_eval, .init = nft_symhash_init, .dump = nft_symhash_dump, .reduce = nft_symhash_reduce, }; static const struct nft_expr_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { u32 type; if (!tb[NFTA_HASH_TYPE]) return &nft_jhash_ops; type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); switch (type) { case NFT_HASH_SYM: return &nft_symhash_ops; case NFT_HASH_JENKINS: return &nft_jhash_ops; default: break; } return ERR_PTR(-EOPNOTSUPP); } static struct nft_expr_type nft_hash_type __read_mostly = { .name = "hash", .select_ops = nft_hash_select_ops, .policy = nft_hash_policy, .maxattr = NFTA_HASH_MAX, .owner = THIS_MODULE, }; static int __init nft_hash_module_init(void) { return nft_register_expr(&nft_hash_type); } static void __exit nft_hash_module_exit(void) { nft_unregister_expr(&nft_hash_type); } module_init(nft_hash_module_init); module_exit(nft_hash_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); MODULE_ALIAS_NFT_EXPR("hash"); MODULE_DESCRIPTION("Netfilter nftables hash module"); |
| 6 3 3 2 2 2 2 4 2 6 6 1 1 1 1 1 4 1 1 2 3 1 2 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * Copyright (c) 2022-2024 Oracle. * All rights reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_bmap_btree.h" #include "xfs_inode.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_ioctl.h" #include "xfs_parent.h" #include "xfs_handle.h" #include "xfs_health.h" #include "xfs_icache.h" #include "xfs_export.h" #include "xfs_xattr.h" #include "xfs_acl.h" #include <linux/namei.h> static inline size_t xfs_filehandle_fid_len(void) { struct xfs_handle *handle = NULL; return sizeof(struct xfs_fid) - sizeof(handle->ha_fid.fid_len); } static inline size_t xfs_filehandle_init( struct xfs_mount *mp, xfs_ino_t ino, uint32_t gen, struct xfs_handle *handle) { memcpy(&handle->ha_fsid, mp->m_fixedfsid, sizeof(struct xfs_fsid)); handle->ha_fid.fid_len = xfs_filehandle_fid_len(); handle->ha_fid.fid_pad = 0; handle->ha_fid.fid_gen = gen; handle->ha_fid.fid_ino = ino; return sizeof(struct xfs_handle); } static inline size_t xfs_fshandle_init( struct xfs_mount *mp, struct xfs_handle *handle) { memcpy(&handle->ha_fsid, mp->m_fixedfsid, sizeof(struct xfs_fsid)); memset(&handle->ha_fid, 0, sizeof(handle->ha_fid)); return sizeof(struct xfs_fsid); } /* * xfs_find_handle maps from userspace xfs_fsop_handlereq structure to * a file or fs handle. * * XFS_IOC_PATH_TO_FSHANDLE * returns fs handle for a mount point or path within that mount point * XFS_IOC_FD_TO_HANDLE * returns full handle for a FD opened in user space * XFS_IOC_PATH_TO_HANDLE * returns full handle for a path */ int xfs_find_handle( unsigned int cmd, xfs_fsop_handlereq_t *hreq) { int hsize; xfs_handle_t handle; struct inode *inode; struct path path; int error; struct xfs_inode *ip; if (cmd == XFS_IOC_FD_TO_HANDLE) { CLASS(fd, f)(hreq->fd); if (fd_empty(f)) return -EBADF; path = fd_file(f)->f_path; path_get(&path); } else { error = user_path_at(AT_FDCWD, hreq->path, 0, &path); if (error) return error; } inode = d_inode(path.dentry); ip = XFS_I(inode); /* * We can only generate handles for inodes residing on a XFS filesystem, * and only for regular files, directories or symbolic links. */ error = -EINVAL; if (inode->i_sb->s_magic != XFS_SB_MAGIC) goto out_put; error = -EBADF; if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) && !S_ISLNK(inode->i_mode)) goto out_put; memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t)); if (cmd == XFS_IOC_PATH_TO_FSHANDLE) hsize = xfs_fshandle_init(ip->i_mount, &handle); else hsize = xfs_filehandle_init(ip->i_mount, ip->i_ino, inode->i_generation, &handle); error = -EFAULT; if (copy_to_user(hreq->ohandle, &handle, hsize) || copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32))) goto out_put; error = 0; out_put: path_put(&path); return error; } /* * No need to do permission checks on the various pathname components * as the handle operations are privileged. */ STATIC int xfs_handle_acceptable( void *context, struct dentry *dentry) { return 1; } /* Convert handle already copied to kernel space into a dentry. */ static struct dentry * xfs_khandle_to_dentry( struct file *file, struct xfs_handle *handle) { struct xfs_fid64 fid = { .ino = handle->ha_fid.fid_ino, .gen = handle->ha_fid.fid_gen, }; /* * Only allow handle opens under a directory. */ if (!S_ISDIR(file_inode(file)->i_mode)) return ERR_PTR(-ENOTDIR); if (handle->ha_fid.fid_len != xfs_filehandle_fid_len()) return ERR_PTR(-EINVAL); return exportfs_decode_fh(file->f_path.mnt, (struct fid *)&fid, 3, FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG, xfs_handle_acceptable, NULL); } /* Convert handle already copied to kernel space into an xfs_inode. */ static struct xfs_inode * xfs_khandle_to_inode( struct file *file, struct xfs_handle *handle) { struct xfs_inode *ip = XFS_I(file_inode(file)); struct xfs_mount *mp = ip->i_mount; struct inode *inode; if (!S_ISDIR(VFS_I(ip)->i_mode)) return ERR_PTR(-ENOTDIR); if (handle->ha_fid.fid_len != xfs_filehandle_fid_len()) return ERR_PTR(-EINVAL); inode = xfs_nfs_get_inode(mp->m_super, handle->ha_fid.fid_ino, handle->ha_fid.fid_gen); if (IS_ERR(inode)) return ERR_CAST(inode); return XFS_I(inode); } /* * Convert userspace handle data into a dentry. */ struct dentry * xfs_handle_to_dentry( struct file *parfilp, void __user *uhandle, u32 hlen) { xfs_handle_t handle; if (hlen != sizeof(xfs_handle_t)) return ERR_PTR(-EINVAL); if (copy_from_user(&handle, uhandle, hlen)) return ERR_PTR(-EFAULT); return xfs_khandle_to_dentry(parfilp, &handle); } STATIC struct dentry * xfs_handlereq_to_dentry( struct file *parfilp, xfs_fsop_handlereq_t *hreq) { return xfs_handle_to_dentry(parfilp, hreq->ihandle, hreq->ihandlen); } int xfs_open_by_handle( struct file *parfilp, xfs_fsop_handlereq_t *hreq) { const struct cred *cred = current_cred(); int error; int fd; int permflag; struct file *filp; struct inode *inode; struct dentry *dentry; fmode_t fmode; struct path path; if (!capable(CAP_SYS_ADMIN)) return -EPERM; dentry = xfs_handlereq_to_dentry(parfilp, hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); inode = d_inode(dentry); /* Restrict xfs_open_by_handle to directories & regular files. */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) { error = -EPERM; goto out_dput; } #if BITS_PER_LONG != 32 hreq->oflags |= O_LARGEFILE; #endif permflag = hreq->oflags; fmode = OPEN_FMODE(permflag); if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) && (fmode & FMODE_WRITE) && IS_APPEND(inode)) { error = -EPERM; goto out_dput; } if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) { error = -EPERM; goto out_dput; } /* Can't write directories. */ if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) { error = -EISDIR; goto out_dput; } fd = get_unused_fd_flags(0); if (fd < 0) { error = fd; goto out_dput; } path.mnt = parfilp->f_path.mnt; path.dentry = dentry; filp = dentry_open(&path, hreq->oflags, cred); dput(dentry); if (IS_ERR(filp)) { put_unused_fd(fd); return PTR_ERR(filp); } if (S_ISREG(inode->i_mode)) { filp->f_flags |= O_NOATIME; filp->f_mode |= FMODE_NOCMTIME; } fd_install(fd, filp); return fd; out_dput: dput(dentry); return error; } int xfs_readlink_by_handle( struct file *parfilp, xfs_fsop_handlereq_t *hreq) { struct dentry *dentry; __u32 olen; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; dentry = xfs_handlereq_to_dentry(parfilp, hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); /* Restrict this handle operation to symlinks only. */ if (!d_is_symlink(dentry)) { error = -EINVAL; goto out_dput; } if (copy_from_user(&olen, hreq->ohandlen, sizeof(__u32))) { error = -EFAULT; goto out_dput; } error = vfs_readlink(dentry, hreq->ohandle, olen); out_dput: dput(dentry); return error; } /* * Format an attribute and copy it out to the user's buffer. * Take care to check values and protect against them changing later, * we may be reading them directly out of a user buffer. */ static void xfs_ioc_attr_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, int namelen, void *value, int valuelen) { struct xfs_attrlist *alist = context->buffer; struct xfs_attrlist_ent *aep; int arraytop; ASSERT(!context->seen_enough); ASSERT(context->count >= 0); ASSERT(context->count < (ATTR_MAX_VALUELEN/8)); ASSERT(context->firstu >= sizeof(*alist)); ASSERT(context->firstu <= context->bufsize); /* * Only list entries in the right namespace. */ if (context->attr_filter != (flags & XFS_ATTR_NSP_ONDISK_MASK)) return; arraytop = sizeof(*alist) + context->count * sizeof(alist->al_offset[0]); /* decrement by the actual bytes used by the attr */ context->firstu -= round_up(offsetof(struct xfs_attrlist_ent, a_name) + namelen + 1, sizeof(uint32_t)); if (context->firstu < arraytop) { trace_xfs_attr_list_full(context); alist->al_more = 1; context->seen_enough = 1; return; } aep = context->buffer + context->firstu; aep->a_valuelen = valuelen; memcpy(aep->a_name, name, namelen); aep->a_name[namelen] = 0; alist->al_offset[context->count++] = context->firstu; alist->al_count = context->count; trace_xfs_attr_list_add(context); } static unsigned int xfs_attr_filter( u32 ioc_flags) { if (ioc_flags & XFS_IOC_ATTR_ROOT) return XFS_ATTR_ROOT; if (ioc_flags & XFS_IOC_ATTR_SECURE) return XFS_ATTR_SECURE; return 0; } static inline enum xfs_attr_update xfs_xattr_flags( u32 ioc_flags, void *value) { if (!value) return XFS_ATTRUPDATE_REMOVE; if (ioc_flags & XFS_IOC_ATTR_CREATE) return XFS_ATTRUPDATE_CREATE; if (ioc_flags & XFS_IOC_ATTR_REPLACE) return XFS_ATTRUPDATE_REPLACE; return XFS_ATTRUPDATE_UPSERT; } int xfs_ioc_attr_list( struct xfs_inode *dp, void __user *ubuf, size_t bufsize, int flags, struct xfs_attrlist_cursor __user *ucursor) { struct xfs_attr_list_context context = { }; struct xfs_attrlist *alist; void *buffer; int error; if (bufsize < sizeof(struct xfs_attrlist) || bufsize > XFS_XATTR_LIST_MAX) return -EINVAL; /* * Reject flags, only allow namespaces. */ if (flags & ~(XFS_IOC_ATTR_ROOT | XFS_IOC_ATTR_SECURE)) return -EINVAL; if (flags == (XFS_IOC_ATTR_ROOT | XFS_IOC_ATTR_SECURE)) return -EINVAL; /* * Validate the cursor. */ if (copy_from_user(&context.cursor, ucursor, sizeof(context.cursor))) return -EFAULT; if (context.cursor.pad1 || context.cursor.pad2) return -EINVAL; if (!context.cursor.initted && (context.cursor.hashval || context.cursor.blkno || context.cursor.offset)) return -EINVAL; buffer = kvzalloc(bufsize, GFP_KERNEL); if (!buffer) return -ENOMEM; /* * Initialize the output buffer. */ context.dp = dp; context.resynch = 1; context.attr_filter = xfs_attr_filter(flags); context.buffer = buffer; context.bufsize = round_down(bufsize, sizeof(uint32_t)); context.firstu = context.bufsize; context.put_listent = xfs_ioc_attr_put_listent; alist = context.buffer; alist->al_count = 0; alist->al_more = 0; alist->al_offset[0] = context.bufsize; error = xfs_attr_list(&context); if (error) goto out_free; if (copy_to_user(ubuf, buffer, bufsize) || copy_to_user(ucursor, &context.cursor, sizeof(context.cursor))) error = -EFAULT; out_free: kvfree(buffer); return error; } int xfs_attrlist_by_handle( struct file *parfilp, struct xfs_fsop_attrlist_handlereq __user *p) { struct xfs_fsop_attrlist_handlereq al_hreq; struct dentry *dentry; int error = -ENOMEM; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&al_hreq, p, sizeof(al_hreq))) return -EFAULT; dentry = xfs_handlereq_to_dentry(parfilp, &al_hreq.hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = xfs_ioc_attr_list(XFS_I(d_inode(dentry)), al_hreq.buffer, al_hreq.buflen, al_hreq.flags, &p->pos); dput(dentry); return error; } static int xfs_attrmulti_attr_get( struct inode *inode, unsigned char *name, unsigned char __user *ubuf, uint32_t *len, uint32_t flags) { struct xfs_da_args args = { .dp = XFS_I(inode), .attr_filter = xfs_attr_filter(flags), .name = name, .namelen = strlen(name), .valuelen = *len, }; int error; if (*len > XFS_XATTR_SIZE_MAX) return -EINVAL; error = xfs_attr_get(&args); if (error) goto out_kfree; *len = args.valuelen; if (copy_to_user(ubuf, args.value, args.valuelen)) error = -EFAULT; out_kfree: kvfree(args.value); return error; } static int xfs_attrmulti_attr_set( struct inode *inode, unsigned char *name, const unsigned char __user *ubuf, uint32_t len, uint32_t flags) { struct xfs_da_args args = { .dp = XFS_I(inode), .attr_filter = xfs_attr_filter(flags), .name = name, .namelen = strlen(name), }; int error; if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; if (ubuf) { if (len > XFS_XATTR_SIZE_MAX) return -EINVAL; args.value = memdup_user(ubuf, len); if (IS_ERR(args.value)) return PTR_ERR(args.value); args.valuelen = len; } error = xfs_attr_change(&args, xfs_xattr_flags(flags, args.value)); if (!error && (flags & XFS_IOC_ATTR_ROOT)) xfs_forget_acl(inode, name); kfree(args.value); return error; } int xfs_ioc_attrmulti_one( struct file *parfilp, struct inode *inode, uint32_t opcode, void __user *uname, void __user *value, uint32_t *len, uint32_t flags) { unsigned char *name; int error; if ((flags & XFS_IOC_ATTR_ROOT) && (flags & XFS_IOC_ATTR_SECURE)) return -EINVAL; name = strndup_user(uname, MAXNAMELEN); if (IS_ERR(name)) return PTR_ERR(name); switch (opcode) { case ATTR_OP_GET: error = xfs_attrmulti_attr_get(inode, name, value, len, flags); break; case ATTR_OP_REMOVE: value = NULL; *len = 0; fallthrough; case ATTR_OP_SET: error = mnt_want_write_file(parfilp); if (error) break; error = xfs_attrmulti_attr_set(inode, name, value, *len, flags); mnt_drop_write_file(parfilp); break; default: error = -EINVAL; break; } kfree(name); return error; } int xfs_attrmulti_by_handle( struct file *parfilp, void __user *arg) { int error; xfs_attr_multiop_t *ops; xfs_fsop_attrmulti_handlereq_t am_hreq; struct dentry *dentry; unsigned int i, size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&am_hreq, arg, sizeof(xfs_fsop_attrmulti_handlereq_t))) return -EFAULT; /* overflow check */ if (am_hreq.opcount >= INT_MAX / sizeof(xfs_attr_multiop_t)) return -E2BIG; dentry = xfs_handlereq_to_dentry(parfilp, &am_hreq.hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = -E2BIG; size = am_hreq.opcount * sizeof(xfs_attr_multiop_t); if (!size || size > 16 * PAGE_SIZE) goto out_dput; ops = memdup_user(am_hreq.ops, size); if (IS_ERR(ops)) { error = PTR_ERR(ops); goto out_dput; } error = 0; for (i = 0; i < am_hreq.opcount; i++) { ops[i].am_error = xfs_ioc_attrmulti_one(parfilp, d_inode(dentry), ops[i].am_opcode, ops[i].am_attrname, ops[i].am_attrvalue, &ops[i].am_length, ops[i].am_flags); } if (copy_to_user(am_hreq.ops, ops, size)) error = -EFAULT; kfree(ops); out_dput: dput(dentry); return error; } struct xfs_getparents_ctx { struct xfs_attr_list_context context; struct xfs_getparents_by_handle gph; /* File to target */ struct xfs_inode *ip; /* Internal buffer where we format records */ void *krecords; /* Last record filled out */ struct xfs_getparents_rec *lastrec; unsigned int count; }; static inline unsigned int xfs_getparents_rec_sizeof( unsigned int namelen) { return round_up(sizeof(struct xfs_getparents_rec) + namelen + 1, sizeof(uint64_t)); } static void xfs_getparents_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, int namelen, void *value, int valuelen) { struct xfs_getparents_ctx *gpx = container_of(context, struct xfs_getparents_ctx, context); struct xfs_inode *ip = context->dp; struct xfs_mount *mp = ip->i_mount; struct xfs_getparents *gp = &gpx->gph.gph_request; struct xfs_getparents_rec *gpr = gpx->krecords + context->firstu; unsigned short reclen = xfs_getparents_rec_sizeof(namelen); xfs_ino_t ino; uint32_t gen; int error; if (!(flags & XFS_ATTR_PARENT)) return; error = xfs_parent_from_attr(mp, flags, name, namelen, value, valuelen, &ino, &gen); if (error) { xfs_inode_mark_sick(ip, XFS_SICK_INO_PARENT); context->seen_enough = -EFSCORRUPTED; return; } /* * We found a parent pointer, but we've filled up the buffer. Signal * to the caller that we did /not/ reach the end of the parent pointer * recordset. */ if (context->firstu > context->bufsize - reclen) { context->seen_enough = 1; return; } /* Format the parent pointer directly into the caller buffer. */ gpr->gpr_reclen = reclen; xfs_filehandle_init(mp, ino, gen, &gpr->gpr_parent); memcpy(gpr->gpr_name, name, namelen); gpr->gpr_name[namelen] = 0; trace_xfs_getparents_put_listent(ip, gp, context, gpr); context->firstu += reclen; gpx->count++; gpx->lastrec = gpr; } /* Expand the last record to fill the rest of the caller's buffer. */ static inline void xfs_getparents_expand_lastrec( struct xfs_getparents_ctx *gpx) { struct xfs_getparents *gp = &gpx->gph.gph_request; struct xfs_getparents_rec *gpr = gpx->lastrec; if (!gpx->lastrec) gpr = gpx->krecords; gpr->gpr_reclen = gp->gp_bufsize - ((void *)gpr - gpx->krecords); trace_xfs_getparents_expand_lastrec(gpx->ip, gp, &gpx->context, gpr); } /* Retrieve the parent pointers for a given inode. */ STATIC int xfs_getparents( struct xfs_getparents_ctx *gpx) { struct xfs_getparents *gp = &gpx->gph.gph_request; struct xfs_inode *ip = gpx->ip; struct xfs_mount *mp = ip->i_mount; size_t bufsize; int error; /* Check size of buffer requested by user */ if (gp->gp_bufsize > XFS_XATTR_LIST_MAX) return -ENOMEM; if (gp->gp_bufsize < xfs_getparents_rec_sizeof(1)) return -EINVAL; if (gp->gp_iflags & ~XFS_GETPARENTS_IFLAGS_ALL) return -EINVAL; if (gp->gp_reserved) return -EINVAL; bufsize = round_down(gp->gp_bufsize, sizeof(uint64_t)); gpx->krecords = kvzalloc(bufsize, GFP_KERNEL); if (!gpx->krecords) { bufsize = min(bufsize, PAGE_SIZE); gpx->krecords = kvzalloc(bufsize, GFP_KERNEL); if (!gpx->krecords) return -ENOMEM; } gpx->context.dp = ip; gpx->context.resynch = 1; gpx->context.put_listent = xfs_getparents_put_listent; gpx->context.bufsize = bufsize; /* firstu is used to track the bytes filled in the buffer */ gpx->context.firstu = 0; /* Copy the cursor provided by caller */ memcpy(&gpx->context.cursor, &gp->gp_cursor, sizeof(struct xfs_attrlist_cursor)); gpx->count = 0; gp->gp_oflags = 0; trace_xfs_getparents_begin(ip, gp, &gpx->context.cursor); error = xfs_attr_list(&gpx->context); if (error) goto out_free_buf; if (gpx->context.seen_enough < 0) { error = gpx->context.seen_enough; goto out_free_buf; } xfs_getparents_expand_lastrec(gpx); /* Update the caller with the current cursor position */ memcpy(&gp->gp_cursor, &gpx->context.cursor, sizeof(struct xfs_attrlist_cursor)); /* Is this the root directory? */ if (ip->i_ino == mp->m_sb.sb_rootino) gp->gp_oflags |= XFS_GETPARENTS_OFLAG_ROOT; if (gpx->context.seen_enough == 0) { /* * If we did not run out of buffer space, then we reached the * end of the pptr recordset, so set the DONE flag. */ gp->gp_oflags |= XFS_GETPARENTS_OFLAG_DONE; } else if (gpx->count == 0) { /* * If we ran out of buffer space before copying any parent * pointers at all, the caller's buffer was too short. Tell * userspace that, erm, the message is too long. */ error = -EMSGSIZE; goto out_free_buf; } trace_xfs_getparents_end(ip, gp, &gpx->context.cursor); ASSERT(gpx->context.firstu <= gpx->gph.gph_request.gp_bufsize); /* Copy the records to userspace. */ if (copy_to_user(u64_to_user_ptr(gpx->gph.gph_request.gp_buffer), gpx->krecords, gpx->context.firstu)) error = -EFAULT; out_free_buf: kvfree(gpx->krecords); gpx->krecords = NULL; return error; } /* Retrieve the parents of this file and pass them back to userspace. */ int xfs_ioc_getparents( struct file *file, struct xfs_getparents __user *ureq) { struct xfs_getparents_ctx gpx = { .ip = XFS_I(file_inode(file)), }; struct xfs_getparents *kreq = &gpx.gph.gph_request; struct xfs_mount *mp = gpx.ip->i_mount; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!xfs_has_parent(mp)) return -EOPNOTSUPP; if (copy_from_user(kreq, ureq, sizeof(*kreq))) return -EFAULT; error = xfs_getparents(&gpx); if (error) return error; if (copy_to_user(ureq, kreq, sizeof(*kreq))) return -EFAULT; return 0; } /* Retrieve the parents of this file handle and pass them back to userspace. */ int xfs_ioc_getparents_by_handle( struct file *file, struct xfs_getparents_by_handle __user *ureq) { struct xfs_getparents_ctx gpx = { }; struct xfs_inode *ip = XFS_I(file_inode(file)); struct xfs_mount *mp = ip->i_mount; struct xfs_getparents_by_handle *kreq = &gpx.gph; struct xfs_handle *handle = &kreq->gph_handle; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!xfs_has_parent(mp)) return -EOPNOTSUPP; if (copy_from_user(kreq, ureq, sizeof(*kreq))) return -EFAULT; /* * We don't use exportfs_decode_fh because it does too much work here. * If the handle refers to a directory, the exportfs code will walk * upwards through the directory tree to connect the dentries to the * root directory dentry. For GETPARENTS we don't care about that * because we're not actually going to open a file descriptor; we only * want to open an inode and read its parent pointers. * * Note that xfs_scrub uses GETPARENTS to log that it will try to fix a * corrupted file's metadata. For this usecase we would really rather * userspace single-step the path reconstruction to avoid loops or * other strange things if the directory tree is corrupt. */ gpx.ip = xfs_khandle_to_inode(file, handle); if (IS_ERR(gpx.ip)) return PTR_ERR(gpx.ip); error = xfs_getparents(&gpx); if (error) goto out_rele; if (copy_to_user(ureq, kreq, sizeof(*kreq))) error = -EFAULT; out_rele: xfs_irele(gpx.ip); return error; } |
| 57 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 | // SPDX-License-Identifier: GPL-2.0 /* Bareudp: UDP tunnel encasulation for different Payload types like * MPLS, NSH, IP, etc. * Copyright (c) 2019 Nokia, Inc. * Authors: Martin Varghese, <martin.varghese@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/protocol.h> #include <net/ip6_tunnel.h> #include <net/ip_tunnels.h> #include <net/udp_tunnel.h> #include <net/bareudp.h> #define BAREUDP_BASE_HLEN sizeof(struct udphdr) #define BAREUDP_IPV4_HLEN (sizeof(struct iphdr) + \ sizeof(struct udphdr)) #define BAREUDP_IPV6_HLEN (sizeof(struct ipv6hdr) + \ sizeof(struct udphdr)) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); /* per-network namespace private data for this module */ static unsigned int bareudp_net_id; struct bareudp_net { struct list_head bareudp_list; }; struct bareudp_conf { __be16 ethertype; __be16 port; u16 sport_min; bool multi_proto_mode; }; /* Pseudo network device */ struct bareudp_dev { struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for bareudp tunnel */ __be16 ethertype; __be16 port; u16 sport_min; bool multi_proto_mode; struct socket __rcu *sock; struct list_head next; /* bareudp node on namespace list */ struct gro_cells gro_cells; }; static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct metadata_dst *tun_dst = NULL; IP_TUNNEL_DECLARE_FLAGS(key) = { }; struct bareudp_dev *bareudp; unsigned short family; unsigned int len; __be16 proto; void *oiph; int err; int nh; bareudp = rcu_dereference_sk_user_data(sk); if (!bareudp) goto drop; if (skb->protocol == htons(ETH_P_IP)) family = AF_INET; else family = AF_INET6; if (bareudp->ethertype == htons(ETH_P_IP)) { __u8 ipversion; if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion, sizeof(ipversion))) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } ipversion >>= 4; if (ipversion == 4) { proto = htons(ETH_P_IP); } else if (ipversion == 6 && bareudp->multi_proto_mode) { proto = htons(ETH_P_IPV6); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) { struct iphdr *tunnel_hdr; tunnel_hdr = (struct iphdr *)skb_network_header(skb); if (tunnel_hdr->version == 4) { if (!ipv4_is_multicast(tunnel_hdr->daddr)) { proto = bareudp->ethertype; } else if (bareudp->multi_proto_mode && ipv4_is_multicast(tunnel_hdr->daddr)) { proto = htons(ETH_P_MPLS_MC); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } else { int addr_type; struct ipv6hdr *tunnel_hdr_v6; tunnel_hdr_v6 = (struct ipv6hdr *)skb_network_header(skb); addr_type = ipv6_addr_type((struct in6_addr *)&tunnel_hdr_v6->daddr); if (!(addr_type & IPV6_ADDR_MULTICAST)) { proto = bareudp->ethertype; } else if (bareudp->multi_proto_mode && (addr_type & IPV6_ADDR_MULTICAST)) { proto = htons(ETH_P_MPLS_MC); } else { dev_dstats_rx_dropped(bareudp->dev); goto drop; } } } else { proto = bareudp->ethertype; } if (iptunnel_pull_header(skb, BAREUDP_BASE_HLEN, proto, !net_eq(bareudp->net, dev_net(bareudp->dev)))) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } __set_bit(IP_TUNNEL_KEY_BIT, key); tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0); if (!tun_dst) { dev_dstats_rx_dropped(bareudp->dev); goto drop; } skb_dst_set(skb, &tun_dst->dst); skb->dev = bareudp->dev; skb_reset_mac_header(skb); /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(bareudp->dev, rx_length_errors); DEV_STATS_INC(bareudp->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!ipv6_mod_enabled() || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); else err = IP6_ECN_decapsulate(oiph, skb); if (unlikely(err)) { if (log_ecn_error) { if (!ipv6_mod_enabled() || family == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } if (err > 1) { DEV_STATS_INC(bareudp->dev, rx_frame_errors); DEV_STATS_INC(bareudp->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&bareudp->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_dstats_rx_add(bareudp->dev, len); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } static int bareudp_err_lookup(struct sock *sk, struct sk_buff *skb) { return 0; } static int bareudp_init(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); int err; err = gro_cells_init(&bareudp->gro_cells, dev); if (err) return err; return 0; } static void bareudp_uninit(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); gro_cells_destroy(&bareudp->gro_cells); } static struct socket *bareudp_create_sock(struct net *net, __be16 port) { struct udp_port_cfg udp_conf; struct socket *sock; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6_mod_enabled()) udp_conf.family = AF_INET6; else udp_conf.family = AF_INET; udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } /* Create new listen socket if needed */ static int bareudp_socket_create(struct bareudp_dev *bareudp, __be16 port) { struct udp_tunnel_sock_cfg tunnel_cfg; struct socket *sock; sock = bareudp_create_sock(bareudp->net, port); if (IS_ERR(sock)) return PTR_ERR(sock); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = bareudp; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = bareudp_udp_encap_recv; tunnel_cfg.encap_err_lookup = bareudp_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(bareudp->net, sock, &tunnel_cfg); rcu_assign_pointer(bareudp->sock, sock); return 0; } static int bareudp_open(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); int ret = 0; ret = bareudp_socket_create(bareudp, bareudp->port); return ret; } static void bareudp_sock_release(struct bareudp_dev *bareudp) { struct socket *sock; sock = bareudp->sock; rcu_assign_pointer(bareudp->sock, NULL); synchronize_net(); udp_tunnel_sock_release(sock); } static int bareudp_stop(struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); bareudp_sock_release(bareudp); return 0; } static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct socket *sock = rcu_dereference(bareudp->sock); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; __be16 sport, df; int min_headroom; __u8 tos, ttl; __be32 saddr; int err; if (skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB))) return -EINVAL; if (!sock) return -ESHUTDOWN; sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, bareudp->net, 0, &saddr, &info->key, sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); skb_tunnel_check_pmtu(skb, &rt->dst, BAREUDP_IPV4_HLEN + info->options_len, false); tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; skb_scrub_packet(skb, xnet); err = -ENOSPC; if (!skb_pull(skb, skb_network_offset(skb))) goto free_dst; min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; skb_set_inner_protocol(skb, bareudp->ethertype); udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, bareudp->port, !net_eq(bareudp->net, dev_net(bareudp->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; free_dst: dst_release(&rt->dst); return err; } static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct socket *sock = rcu_dereference(bareudp->sock); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr, daddr; int min_headroom; __u8 prio, ttl; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB))) return -EINVAL; if (!sock) return -ESHUTDOWN; sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr, key, sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *) &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len, false); prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; skb_scrub_packet(skb, xnet); err = -ENOSPC; if (!skb_pull(skb, skb_network_offset(skb))) goto free_dst; min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct ipv6hdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; daddr = info->key.u.ipv6.dst; udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev, &saddr, &daddr, prio, ttl, info->key.label, sport, bareudp->port, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; free_dst: dst_release(dst); return err; } static bool bareudp_proto_valid(struct bareudp_dev *bareudp, __be16 proto) { if (bareudp->ethertype == proto) return true; if (!bareudp->multi_proto_mode) return false; if (bareudp->ethertype == htons(ETH_P_MPLS_UC) && proto == htons(ETH_P_MPLS_MC)) return true; if (bareudp->ethertype == htons(ETH_P_IP) && proto == htons(ETH_P_IPV6)) return true; return false; } static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (!bareudp_proto_valid(bareudp, skb->protocol)) { err = -EINVAL; goto tx_error; } info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { err = -EINVAL; goto tx_error; } rcu_read_lock(); if (ipv6_mod_enabled() && info->mode & IP_TUNNEL_INFO_IPV6) err = bareudp6_xmit_skb(skb, dev, bareudp, info); else err = bareudp_xmit_skb(skb, dev, bareudp, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; tx_error: dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int bareudp_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct bareudp_dev *bareudp = netdev_priv(dev); bool use_cache; __be16 sport; use_cache = ip_tunnel_dst_cache_usable(skb, info); sport = udp_flow_src_port(bareudp->net, skb, bareudp->sport_min, USHRT_MAX, true); if (!ipv6_mod_enabled() || ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; __be32 saddr; rt = udp_tunnel_dst_lookup(skb, dev, bareudp->net, 0, &saddr, &info->key, sport, bareudp->port, info->key.tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = saddr; } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct in6_addr saddr; struct socket *sock = rcu_dereference(bareudp->sock); dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr, &info->key, sport, bareudp->port, info->key.tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); info->key.u.ipv6.src = saddr; } else { return -EINVAL; } info->key.tp_src = sport; info->key.tp_dst = bareudp->port; return 0; } static const struct net_device_ops bareudp_netdev_ops = { .ndo_init = bareudp_init, .ndo_uninit = bareudp_uninit, .ndo_open = bareudp_open, .ndo_stop = bareudp_stop, .ndo_start_xmit = bareudp_xmit, .ndo_fill_metadata_dst = bareudp_fill_metadata_dst, }; static const struct nla_policy bareudp_policy[IFLA_BAREUDP_MAX + 1] = { [IFLA_BAREUDP_PORT] = { .type = NLA_U16 }, [IFLA_BAREUDP_ETHERTYPE] = { .type = NLA_U16 }, [IFLA_BAREUDP_SRCPORT_MIN] = { .type = NLA_U16 }, [IFLA_BAREUDP_MULTIPROTO_MODE] = { .type = NLA_FLAG }, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type bareudp_type = { .name = "bareudp", }; /* Initialize the device structure. */ static void bareudp_setup(struct net_device *dev) { dev->netdev_ops = &bareudp_netdev_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &bareudp_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = ETH_DATA_LEN; dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - BAREUDP_BASE_HLEN; dev->type = ARPHRD_NONE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) { NL_SET_ERR_MSG(extack, "Not enough attributes provided to perform the operation"); return -EINVAL; } return 0; } static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf, struct netlink_ext_ack *extack) { memset(conf, 0, sizeof(*conf)); if (!data[IFLA_BAREUDP_PORT]) { NL_SET_ERR_MSG(extack, "port not specified"); return -EINVAL; } if (!data[IFLA_BAREUDP_ETHERTYPE]) { NL_SET_ERR_MSG(extack, "ethertype not specified"); return -EINVAL; } conf->port = nla_get_u16(data[IFLA_BAREUDP_PORT]); conf->ethertype = nla_get_u16(data[IFLA_BAREUDP_ETHERTYPE]); if (data[IFLA_BAREUDP_SRCPORT_MIN]) conf->sport_min = nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]); if (data[IFLA_BAREUDP_MULTIPROTO_MODE]) conf->multi_proto_mode = true; return 0; } static struct bareudp_dev *bareudp_find_dev(struct bareudp_net *bn, const struct bareudp_conf *conf) { struct bareudp_dev *bareudp, *t = NULL; list_for_each_entry(bareudp, &bn->bareudp_list, next) { if (conf->port == bareudp->port) t = bareudp; } return t; } static int bareudp_configure(struct net *net, struct net_device *dev, struct bareudp_conf *conf, struct netlink_ext_ack *extack) { struct bareudp_net *bn = net_generic(net, bareudp_net_id); struct bareudp_dev *t, *bareudp = netdev_priv(dev); int err; bareudp->net = net; bareudp->dev = dev; t = bareudp_find_dev(bn, conf); if (t) { NL_SET_ERR_MSG(extack, "Another bareudp device using the same port already exists"); return -EBUSY; } if (conf->multi_proto_mode && (conf->ethertype != htons(ETH_P_MPLS_UC) && conf->ethertype != htons(ETH_P_IP))) { NL_SET_ERR_MSG(extack, "Cannot set multiproto mode for this ethertype (only IPv4 and unicast MPLS are supported)"); return -EINVAL; } bareudp->port = conf->port; bareudp->ethertype = conf->ethertype; bareudp->sport_min = conf->sport_min; bareudp->multi_proto_mode = conf->multi_proto_mode; err = register_netdevice(dev); if (err) return err; list_add(&bareudp->next, &bn->bareudp_list); return 0; } static int bareudp_link_config(struct net_device *dev, struct nlattr *tb[]) { int err; if (tb[IFLA_MTU]) { err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); if (err) return err; } return 0; } static void bareudp_dellink(struct net_device *dev, struct list_head *head) { struct bareudp_dev *bareudp = netdev_priv(dev); list_del(&bareudp->next); unregister_netdevice_queue(dev, head); } static int bareudp_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct bareudp_conf conf; int err; err = bareudp2info(data, &conf, extack); if (err) return err; err = bareudp_configure(link_net, dev, &conf, extack); if (err) return err; err = bareudp_link_config(dev, tb); if (err) goto err_unconfig; return 0; err_unconfig: bareudp_dellink(dev, NULL); return err; } static size_t bareudp_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_PORT */ nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_ETHERTYPE */ nla_total_size(sizeof(__u16)) + /* IFLA_BAREUDP_SRCPORT_MIN */ nla_total_size(0) + /* IFLA_BAREUDP_MULTIPROTO_MODE */ 0; } static int bareudp_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); if (nla_put_be16(skb, IFLA_BAREUDP_PORT, bareudp->port)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_BAREUDP_ETHERTYPE, bareudp->ethertype)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BAREUDP_SRCPORT_MIN, bareudp->sport_min)) goto nla_put_failure; if (bareudp->multi_proto_mode && nla_put_flag(skb, IFLA_BAREUDP_MULTIPROTO_MODE)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops bareudp_link_ops __read_mostly = { .kind = "bareudp", .maxtype = IFLA_BAREUDP_MAX, .policy = bareudp_policy, .priv_size = sizeof(struct bareudp_dev), .setup = bareudp_setup, .validate = bareudp_validate, .newlink = bareudp_newlink, .dellink = bareudp_dellink, .get_size = bareudp_get_size, .fill_info = bareudp_fill_info, }; static __net_init int bareudp_init_net(struct net *net) { struct bareudp_net *bn = net_generic(net, bareudp_net_id); INIT_LIST_HEAD(&bn->bareudp_list); return 0; } static void __net_exit bareudp_exit_rtnl_net(struct net *net, struct list_head *dev_kill_list) { struct bareudp_net *bn = net_generic(net, bareudp_net_id); struct bareudp_dev *bareudp, *next; list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next) bareudp_dellink(bareudp->dev, dev_kill_list); } static struct pernet_operations bareudp_net_ops = { .init = bareudp_init_net, .exit_rtnl = bareudp_exit_rtnl_net, .id = &bareudp_net_id, .size = sizeof(struct bareudp_net), }; static int __init bareudp_init_module(void) { int rc; rc = register_pernet_subsys(&bareudp_net_ops); if (rc) goto out1; rc = rtnl_link_register(&bareudp_link_ops); if (rc) goto out2; return 0; out2: unregister_pernet_subsys(&bareudp_net_ops); out1: return rc; } late_initcall(bareudp_init_module); static void __exit bareudp_cleanup_module(void) { rtnl_link_unregister(&bareudp_link_ops); unregister_pernet_subsys(&bareudp_net_ops); } module_exit(bareudp_cleanup_module); MODULE_ALIAS_RTNL_LINK("bareudp"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Varghese <martin.varghese@nokia.com>"); MODULE_DESCRIPTION("Interface driver for UDP encapsulated traffic"); |
| 8536 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 27 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions of structures and functions for quota formats using trie */ #ifndef _LINUX_DQBLK_QTREE_H #define _LINUX_DQBLK_QTREE_H #include <linux/types.h> /* Numbers of blocks needed for updates - we count with the smallest * possible block size (1024) */ #define QTREE_INIT_ALLOC 4 #define QTREE_INIT_REWRITE 2 #define QTREE_DEL_ALLOC 0 #define QTREE_DEL_REWRITE 6 struct dquot; struct kqid; /* Operations */ struct qtree_fmt_operations { void (*mem2disk_dqblk)(void *disk, struct dquot *dquot); /* Convert given entry from in memory format to disk one */ void (*disk2mem_dqblk)(struct dquot *dquot, void *disk); /* Convert given entry from disk format to in memory one */ int (*is_id)(void *disk, struct dquot *dquot); /* Is this structure for given id? */ }; /* Inmemory copy of version specific information */ struct qtree_mem_dqinfo { struct super_block *dqi_sb; /* Sb quota is on */ int dqi_type; /* Quota type */ unsigned int dqi_blocks; /* # of blocks in quota file */ unsigned int dqi_free_blk; /* First block in list of free blocks */ unsigned int dqi_free_entry; /* First block with free entry */ unsigned int dqi_blocksize_bits; /* Block size of quota file */ unsigned int dqi_entry_size; /* Size of quota entry in quota file */ unsigned int dqi_usable_bs; /* Space usable in block for quota data */ unsigned int dqi_qtree_depth; /* Precomputed depth of quota tree */ const struct qtree_fmt_operations *dqi_ops; /* Operations for entry manipulation */ }; int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_delete_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); int qtree_entry_unused(struct qtree_mem_dqinfo *info, char *disk); static inline int qtree_depth(struct qtree_mem_dqinfo *info) { unsigned int epb = info->dqi_usable_bs >> 2; unsigned long long entries = epb; int i; for (i = 1; entries < (1ULL << 32); i++) entries *= epb; return i; } int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid); #endif /* _LINUX_DQBLK_QTREE_H */ |
| 13 13 13 13 13 13 1 13 6 5 13 13 1 12 8 8 8 13 13 13 12 13 8 13 13 13 13 13 13 13 13 13 13 13 13 13 6 13 6 6 13 13 7 7 7 7 7 7 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 | // SPDX-License-Identifier: GPL-2.0-only /* * hwmon.c - part of lm_sensors, Linux kernel modules for hardware monitoring * * This file defines the sysfs class "hwmon", for use by sensors drivers. * * Copyright (C) 2005 Mark M. Hoffman <mhoffman@lightlink.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitops.h> #include <linux/device.h> #include <linux/err.h> #include <linux/gfp.h> #include <linux/hwmon.h> #include <linux/i2c.h> #include <linux/idr.h> #include <linux/kstrtox.h> #include <linux/list.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/property.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/thermal.h> #define CREATE_TRACE_POINTS #include <trace/events/hwmon.h> #define HWMON_ID_PREFIX "hwmon" #define HWMON_ID_FORMAT HWMON_ID_PREFIX "%d" struct hwmon_device { const char *name; const char *label; struct device dev; const struct hwmon_chip_info *chip; struct list_head tzdata; struct attribute_group group; const struct attribute_group **groups; }; #define to_hwmon_device(d) container_of(d, struct hwmon_device, dev) #define MAX_SYSFS_ATTR_NAME_LENGTH 32 struct hwmon_device_attribute { struct device_attribute dev_attr; const struct hwmon_ops *ops; enum hwmon_sensor_types type; u32 attr; int index; char name[MAX_SYSFS_ATTR_NAME_LENGTH]; }; #define to_hwmon_attr(d) \ container_of(d, struct hwmon_device_attribute, dev_attr) #define to_dev_attr(a) container_of(a, struct device_attribute, attr) /* * Thermal zone information */ struct hwmon_thermal_data { struct list_head node; /* hwmon tzdata list entry */ struct device *dev; /* Reference to hwmon device */ int index; /* sensor index */ struct thermal_zone_device *tzd;/* thermal zone device */ }; static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%s\n", to_hwmon_device(dev)->name); } static DEVICE_ATTR_RO(name); static ssize_t label_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", to_hwmon_device(dev)->label); } static DEVICE_ATTR_RO(label); static struct attribute *hwmon_dev_attrs[] = { &dev_attr_name.attr, &dev_attr_label.attr, NULL }; static umode_t hwmon_dev_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) { struct device *dev = kobj_to_dev(kobj); struct hwmon_device *hdev = to_hwmon_device(dev); if (attr == &dev_attr_name.attr && hdev->name == NULL) return 0; if (attr == &dev_attr_label.attr && hdev->label == NULL) return 0; return attr->mode; } static const struct attribute_group hwmon_dev_attr_group = { .attrs = hwmon_dev_attrs, .is_visible = hwmon_dev_attr_is_visible, }; static const struct attribute_group *hwmon_dev_attr_groups[] = { &hwmon_dev_attr_group, NULL }; static void hwmon_free_attrs(struct attribute **attrs) { int i; for (i = 0; attrs[i]; i++) { struct device_attribute *dattr = to_dev_attr(attrs[i]); struct hwmon_device_attribute *hattr = to_hwmon_attr(dattr); kfree(hattr); } kfree(attrs); } static void hwmon_dev_release(struct device *dev) { struct hwmon_device *hwdev = to_hwmon_device(dev); if (hwdev->group.attrs) hwmon_free_attrs(hwdev->group.attrs); kfree(hwdev->groups); kfree(hwdev->label); kfree(hwdev); } static const struct class hwmon_class = { .name = "hwmon", .dev_groups = hwmon_dev_attr_groups, .dev_release = hwmon_dev_release, }; static DEFINE_IDA(hwmon_ida); static umode_t hwmon_is_visible(const struct hwmon_ops *ops, const void *drvdata, enum hwmon_sensor_types type, u32 attr, int channel) { if (ops->visible) return ops->visible; return ops->is_visible(drvdata, type, attr, channel); } /* Thermal zone handling */ static int hwmon_thermal_get_temp(struct thermal_zone_device *tz, int *temp) { struct hwmon_thermal_data *tdata = thermal_zone_device_priv(tz); struct hwmon_device *hwdev = to_hwmon_device(tdata->dev); int ret; long t; ret = hwdev->chip->ops->read(tdata->dev, hwmon_temp, hwmon_temp_input, tdata->index, &t); if (ret < 0) return ret; *temp = t; return 0; } static int hwmon_thermal_set_trips(struct thermal_zone_device *tz, int low, int high) { struct hwmon_thermal_data *tdata = thermal_zone_device_priv(tz); struct hwmon_device *hwdev = to_hwmon_device(tdata->dev); const struct hwmon_chip_info *chip = hwdev->chip; const struct hwmon_channel_info * const *info = chip->info; unsigned int i; int err; if (!chip->ops->write) return 0; for (i = 0; info[i] && info[i]->type != hwmon_temp; i++) continue; if (!info[i]) return 0; if (info[i]->config[tdata->index] & HWMON_T_MIN) { err = chip->ops->write(tdata->dev, hwmon_temp, hwmon_temp_min, tdata->index, low); if (err && err != -EOPNOTSUPP) return err; } if (info[i]->config[tdata->index] & HWMON_T_MAX) { err = chip->ops->write(tdata->dev, hwmon_temp, hwmon_temp_max, tdata->index, high); if (err && err != -EOPNOTSUPP) return err; } return 0; } static const struct thermal_zone_device_ops hwmon_thermal_ops = { .get_temp = hwmon_thermal_get_temp, .set_trips = hwmon_thermal_set_trips, }; static void hwmon_thermal_remove_sensor(void *data) { list_del(data); } static int hwmon_thermal_add_sensor(struct device *dev, int index) { struct hwmon_device *hwdev = to_hwmon_device(dev); struct hwmon_thermal_data *tdata; struct thermal_zone_device *tzd; int err; tdata = devm_kzalloc(dev, sizeof(*tdata), GFP_KERNEL); if (!tdata) return -ENOMEM; tdata->dev = dev; tdata->index = index; tzd = devm_thermal_of_zone_register(dev, index, tdata, &hwmon_thermal_ops); if (IS_ERR(tzd)) { if (PTR_ERR(tzd) != -ENODEV) return PTR_ERR(tzd); dev_info(dev, "temp%d_input not attached to any thermal zone\n", index + 1); devm_kfree(dev, tdata); return 0; } err = devm_add_action(dev, hwmon_thermal_remove_sensor, &tdata->node); if (err) return err; tdata->tzd = tzd; list_add(&tdata->node, &hwdev->tzdata); return 0; } static int hwmon_thermal_register_sensors(struct device *dev) { struct hwmon_device *hwdev = to_hwmon_device(dev); const struct hwmon_chip_info *chip = hwdev->chip; const struct hwmon_channel_info * const *info = chip->info; void *drvdata = dev_get_drvdata(dev); int i; if (!IS_ENABLED(CONFIG_THERMAL_OF)) return 0; for (i = 1; info[i]; i++) { int j; if (info[i]->type != hwmon_temp) continue; for (j = 0; info[i]->config[j]; j++) { int err; if (!(info[i]->config[j] & HWMON_T_INPUT) || !hwmon_is_visible(chip->ops, drvdata, hwmon_temp, hwmon_temp_input, j)) continue; err = hwmon_thermal_add_sensor(dev, j); if (err) return err; } } return 0; } static void hwmon_thermal_notify(struct device *dev, int index) { struct hwmon_device *hwdev = to_hwmon_device(dev); struct hwmon_thermal_data *tzdata; if (!IS_ENABLED(CONFIG_THERMAL_OF)) return; list_for_each_entry(tzdata, &hwdev->tzdata, node) { if (tzdata->index == index) { thermal_zone_device_update(tzdata->tzd, THERMAL_EVENT_UNSPECIFIED); } } } static int hwmon_attr_base(enum hwmon_sensor_types type) { if (type == hwmon_in || type == hwmon_intrusion) return 0; return 1; } #if IS_REACHABLE(CONFIG_I2C) /* * PEC support * * The 'pec' attribute is attached to I2C client devices. It is only provided * if the i2c controller supports PEC. * * The mutex ensures that PEC configuration between i2c device and the hardware * is consistent. Use a single mutex because attribute writes are supposed to be * rare, and maintaining a separate mutex for each hardware monitoring device * would add substantial complexity to the driver for little if any gain. * * The hardware monitoring device is identified as child of the i2c client * device. This assumes that only a single hardware monitoring device is * attached to an i2c client device. */ static DEFINE_MUTEX(hwmon_pec_mutex); static int hwmon_match_device(struct device *dev, const void *data) { return dev->class == &hwmon_class; } static ssize_t pec_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct i2c_client *client = to_i2c_client(dev); return sysfs_emit(buf, "%d\n", !!(client->flags & I2C_CLIENT_PEC)); } static ssize_t pec_store(struct device *dev, struct device_attribute *devattr, const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct hwmon_device *hwdev; struct device *hdev; bool val; int err; err = kstrtobool(buf, &val); if (err < 0) return err; hdev = device_find_child(dev, NULL, hwmon_match_device); if (!hdev) return -ENODEV; mutex_lock(&hwmon_pec_mutex); /* * If there is no write function, we assume that chip specific * handling is not required. */ hwdev = to_hwmon_device(hdev); if (hwdev->chip->ops->write) { err = hwdev->chip->ops->write(hdev, hwmon_chip, hwmon_chip_pec, 0, val); if (err && err != -EOPNOTSUPP) goto unlock; } if (!val) client->flags &= ~I2C_CLIENT_PEC; else client->flags |= I2C_CLIENT_PEC; err = count; unlock: mutex_unlock(&hwmon_pec_mutex); put_device(hdev); return err; } static DEVICE_ATTR_RW(pec); static void hwmon_remove_pec(void *dev) { device_remove_file(dev, &dev_attr_pec); } static int hwmon_pec_register(struct device *hdev) { struct i2c_client *client = i2c_verify_client(hdev->parent); int err; if (!client) return -EINVAL; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_PEC)) return 0; err = device_create_file(&client->dev, &dev_attr_pec); if (err) return err; return devm_add_action_or_reset(hdev, hwmon_remove_pec, &client->dev); } #else /* CONFIG_I2C */ static int hwmon_pec_register(struct device *hdev) { return -EINVAL; } #endif /* CONFIG_I2C */ /* sysfs attribute management */ static ssize_t hwmon_attr_show(struct device *dev, struct device_attribute *devattr, char *buf) { struct hwmon_device_attribute *hattr = to_hwmon_attr(devattr); long val; int ret; ret = hattr->ops->read(dev, hattr->type, hattr->attr, hattr->index, &val); if (ret < 0) return ret; trace_hwmon_attr_show(hattr->index + hwmon_attr_base(hattr->type), hattr->name, val); return sprintf(buf, "%ld\n", val); } static ssize_t hwmon_attr_show_string(struct device *dev, struct device_attribute *devattr, char *buf) { struct hwmon_device_attribute *hattr = to_hwmon_attr(devattr); enum hwmon_sensor_types type = hattr->type; const char *s; int ret; ret = hattr->ops->read_string(dev, hattr->type, hattr->attr, hattr->index, &s); if (ret < 0) return ret; trace_hwmon_attr_show_string(hattr->index + hwmon_attr_base(type), hattr->name, s); return sprintf(buf, "%s\n", s); } static ssize_t hwmon_attr_store(struct device *dev, struct device_attribute *devattr, const char *buf, size_t count) { struct hwmon_device_attribute *hattr = to_hwmon_attr(devattr); long val; int ret; ret = kstrtol(buf, 10, &val); if (ret < 0) return ret; ret = hattr->ops->write(dev, hattr->type, hattr->attr, hattr->index, val); if (ret < 0) return ret; trace_hwmon_attr_store(hattr->index + hwmon_attr_base(hattr->type), hattr->name, val); return count; } static bool is_string_attr(enum hwmon_sensor_types type, u32 attr) { return (type == hwmon_temp && attr == hwmon_temp_label) || (type == hwmon_in && attr == hwmon_in_label) || (type == hwmon_curr && attr == hwmon_curr_label) || (type == hwmon_power && attr == hwmon_power_label) || (type == hwmon_energy && attr == hwmon_energy_label) || (type == hwmon_humidity && attr == hwmon_humidity_label) || (type == hwmon_fan && attr == hwmon_fan_label); } static struct attribute *hwmon_genattr(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int index, const char *template, const struct hwmon_ops *ops) { struct hwmon_device_attribute *hattr; struct device_attribute *dattr; struct attribute *a; umode_t mode; const char *name; bool is_string = is_string_attr(type, attr); mode = hwmon_is_visible(ops, drvdata, type, attr, index); if (!mode) return ERR_PTR(-ENOENT); if ((mode & 0444) && ((is_string && !ops->read_string) || (!is_string && !ops->read))) return ERR_PTR(-EINVAL); if ((mode & 0222) && !ops->write) return ERR_PTR(-EINVAL); hattr = kzalloc(sizeof(*hattr), GFP_KERNEL); if (!hattr) return ERR_PTR(-ENOMEM); if (type == hwmon_chip) { name = template; } else { scnprintf(hattr->name, sizeof(hattr->name), template, index + hwmon_attr_base(type)); name = hattr->name; } hattr->type = type; hattr->attr = attr; hattr->index = index; hattr->ops = ops; dattr = &hattr->dev_attr; dattr->show = is_string ? hwmon_attr_show_string : hwmon_attr_show; dattr->store = hwmon_attr_store; a = &dattr->attr; sysfs_attr_init(a); a->name = name; a->mode = mode; return a; } /* * Chip attributes are not attribute templates but actual sysfs attributes. * See hwmon_genattr() for special handling. */ static const char * const hwmon_chip_attrs[] = { [hwmon_chip_temp_reset_history] = "temp_reset_history", [hwmon_chip_in_reset_history] = "in_reset_history", [hwmon_chip_curr_reset_history] = "curr_reset_history", [hwmon_chip_power_reset_history] = "power_reset_history", [hwmon_chip_update_interval] = "update_interval", [hwmon_chip_alarms] = "alarms", [hwmon_chip_samples] = "samples", [hwmon_chip_curr_samples] = "curr_samples", [hwmon_chip_in_samples] = "in_samples", [hwmon_chip_power_samples] = "power_samples", [hwmon_chip_temp_samples] = "temp_samples", [hwmon_chip_beep_enable] = "beep_enable", }; static const char * const hwmon_temp_attr_templates[] = { [hwmon_temp_enable] = "temp%d_enable", [hwmon_temp_input] = "temp%d_input", [hwmon_temp_type] = "temp%d_type", [hwmon_temp_lcrit] = "temp%d_lcrit", [hwmon_temp_lcrit_hyst] = "temp%d_lcrit_hyst", [hwmon_temp_min] = "temp%d_min", [hwmon_temp_min_hyst] = "temp%d_min_hyst", [hwmon_temp_max] = "temp%d_max", [hwmon_temp_max_hyst] = "temp%d_max_hyst", [hwmon_temp_crit] = "temp%d_crit", [hwmon_temp_crit_hyst] = "temp%d_crit_hyst", [hwmon_temp_emergency] = "temp%d_emergency", [hwmon_temp_emergency_hyst] = "temp%d_emergency_hyst", [hwmon_temp_alarm] = "temp%d_alarm", [hwmon_temp_lcrit_alarm] = "temp%d_lcrit_alarm", [hwmon_temp_min_alarm] = "temp%d_min_alarm", [hwmon_temp_max_alarm] = "temp%d_max_alarm", [hwmon_temp_crit_alarm] = "temp%d_crit_alarm", [hwmon_temp_emergency_alarm] = "temp%d_emergency_alarm", [hwmon_temp_fault] = "temp%d_fault", [hwmon_temp_offset] = "temp%d_offset", [hwmon_temp_label] = "temp%d_label", [hwmon_temp_lowest] = "temp%d_lowest", [hwmon_temp_highest] = "temp%d_highest", [hwmon_temp_reset_history] = "temp%d_reset_history", [hwmon_temp_rated_min] = "temp%d_rated_min", [hwmon_temp_rated_max] = "temp%d_rated_max", [hwmon_temp_beep] = "temp%d_beep", }; static const char * const hwmon_in_attr_templates[] = { [hwmon_in_enable] = "in%d_enable", [hwmon_in_input] = "in%d_input", [hwmon_in_min] = "in%d_min", [hwmon_in_max] = "in%d_max", [hwmon_in_lcrit] = "in%d_lcrit", [hwmon_in_crit] = "in%d_crit", [hwmon_in_average] = "in%d_average", [hwmon_in_lowest] = "in%d_lowest", [hwmon_in_highest] = "in%d_highest", [hwmon_in_reset_history] = "in%d_reset_history", [hwmon_in_label] = "in%d_label", [hwmon_in_alarm] = "in%d_alarm", [hwmon_in_min_alarm] = "in%d_min_alarm", [hwmon_in_max_alarm] = "in%d_max_alarm", [hwmon_in_lcrit_alarm] = "in%d_lcrit_alarm", [hwmon_in_crit_alarm] = "in%d_crit_alarm", [hwmon_in_rated_min] = "in%d_rated_min", [hwmon_in_rated_max] = "in%d_rated_max", [hwmon_in_beep] = "in%d_beep", [hwmon_in_fault] = "in%d_fault", }; static const char * const hwmon_curr_attr_templates[] = { [hwmon_curr_enable] = "curr%d_enable", [hwmon_curr_input] = "curr%d_input", [hwmon_curr_min] = "curr%d_min", [hwmon_curr_max] = "curr%d_max", [hwmon_curr_lcrit] = "curr%d_lcrit", [hwmon_curr_crit] = "curr%d_crit", [hwmon_curr_average] = "curr%d_average", [hwmon_curr_lowest] = "curr%d_lowest", [hwmon_curr_highest] = "curr%d_highest", [hwmon_curr_reset_history] = "curr%d_reset_history", [hwmon_curr_label] = "curr%d_label", [hwmon_curr_alarm] = "curr%d_alarm", [hwmon_curr_min_alarm] = "curr%d_min_alarm", [hwmon_curr_max_alarm] = "curr%d_max_alarm", [hwmon_curr_lcrit_alarm] = "curr%d_lcrit_alarm", [hwmon_curr_crit_alarm] = "curr%d_crit_alarm", [hwmon_curr_rated_min] = "curr%d_rated_min", [hwmon_curr_rated_max] = "curr%d_rated_max", [hwmon_curr_beep] = "curr%d_beep", }; static const char * const hwmon_power_attr_templates[] = { [hwmon_power_enable] = "power%d_enable", [hwmon_power_average] = "power%d_average", [hwmon_power_average_interval] = "power%d_average_interval", [hwmon_power_average_interval_max] = "power%d_average_interval_max", [hwmon_power_average_interval_min] = "power%d_average_interval_min", [hwmon_power_average_highest] = "power%d_average_highest", [hwmon_power_average_lowest] = "power%d_average_lowest", [hwmon_power_average_max] = "power%d_average_max", [hwmon_power_average_min] = "power%d_average_min", [hwmon_power_input] = "power%d_input", [hwmon_power_input_highest] = "power%d_input_highest", [hwmon_power_input_lowest] = "power%d_input_lowest", [hwmon_power_reset_history] = "power%d_reset_history", [hwmon_power_accuracy] = "power%d_accuracy", [hwmon_power_cap] = "power%d_cap", [hwmon_power_cap_hyst] = "power%d_cap_hyst", [hwmon_power_cap_max] = "power%d_cap_max", [hwmon_power_cap_min] = "power%d_cap_min", [hwmon_power_min] = "power%d_min", [hwmon_power_max] = "power%d_max", [hwmon_power_lcrit] = "power%d_lcrit", [hwmon_power_crit] = "power%d_crit", [hwmon_power_label] = "power%d_label", [hwmon_power_alarm] = "power%d_alarm", [hwmon_power_cap_alarm] = "power%d_cap_alarm", [hwmon_power_min_alarm] = "power%d_min_alarm", [hwmon_power_max_alarm] = "power%d_max_alarm", [hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm", [hwmon_power_crit_alarm] = "power%d_crit_alarm", [hwmon_power_rated_min] = "power%d_rated_min", [hwmon_power_rated_max] = "power%d_rated_max", }; static const char * const hwmon_energy_attr_templates[] = { [hwmon_energy_enable] = "energy%d_enable", [hwmon_energy_input] = "energy%d_input", [hwmon_energy_label] = "energy%d_label", }; static const char * const hwmon_humidity_attr_templates[] = { [hwmon_humidity_enable] = "humidity%d_enable", [hwmon_humidity_input] = "humidity%d_input", [hwmon_humidity_label] = "humidity%d_label", [hwmon_humidity_min] = "humidity%d_min", [hwmon_humidity_min_hyst] = "humidity%d_min_hyst", [hwmon_humidity_max] = "humidity%d_max", [hwmon_humidity_max_hyst] = "humidity%d_max_hyst", [hwmon_humidity_alarm] = "humidity%d_alarm", [hwmon_humidity_fault] = "humidity%d_fault", [hwmon_humidity_rated_min] = "humidity%d_rated_min", [hwmon_humidity_rated_max] = "humidity%d_rated_max", [hwmon_humidity_min_alarm] = "humidity%d_min_alarm", [hwmon_humidity_max_alarm] = "humidity%d_max_alarm", }; static const char * const hwmon_fan_attr_templates[] = { [hwmon_fan_enable] = "fan%d_enable", [hwmon_fan_input] = "fan%d_input", [hwmon_fan_label] = "fan%d_label", [hwmon_fan_min] = "fan%d_min", [hwmon_fan_max] = "fan%d_max", [hwmon_fan_div] = "fan%d_div", [hwmon_fan_pulses] = "fan%d_pulses", [hwmon_fan_target] = "fan%d_target", [hwmon_fan_alarm] = "fan%d_alarm", [hwmon_fan_min_alarm] = "fan%d_min_alarm", [hwmon_fan_max_alarm] = "fan%d_max_alarm", [hwmon_fan_fault] = "fan%d_fault", [hwmon_fan_beep] = "fan%d_beep", }; static const char * const hwmon_pwm_attr_templates[] = { [hwmon_pwm_input] = "pwm%d", [hwmon_pwm_enable] = "pwm%d_enable", [hwmon_pwm_mode] = "pwm%d_mode", [hwmon_pwm_freq] = "pwm%d_freq", [hwmon_pwm_auto_channels_temp] = "pwm%d_auto_channels_temp", }; static const char * const hwmon_intrusion_attr_templates[] = { [hwmon_intrusion_alarm] = "intrusion%d_alarm", [hwmon_intrusion_beep] = "intrusion%d_beep", }; static const char * const *__templates[] = { [hwmon_chip] = hwmon_chip_attrs, [hwmon_temp] = hwmon_temp_attr_templates, [hwmon_in] = hwmon_in_attr_templates, [hwmon_curr] = hwmon_curr_attr_templates, [hwmon_power] = hwmon_power_attr_templates, [hwmon_energy] = hwmon_energy_attr_templates, [hwmon_humidity] = hwmon_humidity_attr_templates, [hwmon_fan] = hwmon_fan_attr_templates, [hwmon_pwm] = hwmon_pwm_attr_templates, [hwmon_intrusion] = hwmon_intrusion_attr_templates, }; static const int __templates_size[] = { [hwmon_chip] = ARRAY_SIZE(hwmon_chip_attrs), [hwmon_temp] = ARRAY_SIZE(hwmon_temp_attr_templates), [hwmon_in] = ARRAY_SIZE(hwmon_in_attr_templates), [hwmon_curr] = ARRAY_SIZE(hwmon_curr_attr_templates), [hwmon_power] = ARRAY_SIZE(hwmon_power_attr_templates), [hwmon_energy] = ARRAY_SIZE(hwmon_energy_attr_templates), [hwmon_humidity] = ARRAY_SIZE(hwmon_humidity_attr_templates), [hwmon_fan] = ARRAY_SIZE(hwmon_fan_attr_templates), [hwmon_pwm] = ARRAY_SIZE(hwmon_pwm_attr_templates), [hwmon_intrusion] = ARRAY_SIZE(hwmon_intrusion_attr_templates), }; int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel) { char event[MAX_SYSFS_ATTR_NAME_LENGTH + 5]; char sattr[MAX_SYSFS_ATTR_NAME_LENGTH]; char *envp[] = { event, NULL }; const char * const *templates; const char *template; int base; if (type >= ARRAY_SIZE(__templates)) return -EINVAL; if (attr >= __templates_size[type]) return -EINVAL; templates = __templates[type]; template = templates[attr]; base = hwmon_attr_base(type); scnprintf(sattr, MAX_SYSFS_ATTR_NAME_LENGTH, template, base + channel); scnprintf(event, sizeof(event), "NAME=%s", sattr); sysfs_notify(&dev->kobj, NULL, sattr); kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp); if (type == hwmon_temp) hwmon_thermal_notify(dev, channel); return 0; } EXPORT_SYMBOL_GPL(hwmon_notify_event); static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info) { int i, n; for (i = n = 0; info->config[i]; i++) n += hweight32(info->config[i]); return n; } static int hwmon_genattrs(const void *drvdata, struct attribute **attrs, const struct hwmon_ops *ops, const struct hwmon_channel_info *info) { const char * const *templates; int template_size; int i, aindex = 0; if (info->type >= ARRAY_SIZE(__templates)) return -EINVAL; templates = __templates[info->type]; template_size = __templates_size[info->type]; for (i = 0; info->config[i]; i++) { u32 attr_mask = info->config[i]; u32 attr; while (attr_mask) { struct attribute *a; attr = __ffs(attr_mask); attr_mask &= ~BIT(attr); if (attr >= template_size || !templates[attr]) continue; /* attribute is invisible */ a = hwmon_genattr(drvdata, info->type, attr, i, templates[attr], ops); if (IS_ERR(a)) { if (PTR_ERR(a) != -ENOENT) return PTR_ERR(a); continue; } attrs[aindex++] = a; } } return aindex; } static struct attribute ** __hwmon_create_attrs(const void *drvdata, const struct hwmon_chip_info *chip) { int ret, i, aindex = 0, nattrs = 0; struct attribute **attrs; for (i = 0; chip->info[i]; i++) nattrs += hwmon_num_channel_attrs(chip->info[i]); if (nattrs == 0) return ERR_PTR(-EINVAL); attrs = kcalloc(nattrs + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return ERR_PTR(-ENOMEM); for (i = 0; chip->info[i]; i++) { ret = hwmon_genattrs(drvdata, &attrs[aindex], chip->ops, chip->info[i]); if (ret < 0) { hwmon_free_attrs(attrs); return ERR_PTR(ret); } aindex += ret; } return attrs; } static struct device * __hwmon_device_register(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *chip, const struct attribute_group **groups) { struct hwmon_device *hwdev; const char *label; struct device *hdev; struct device *tdev = dev; int i, err, id; /* Complain about invalid characters in hwmon name attribute */ if (name && (!strlen(name) || strpbrk(name, "-* \t\n"))) dev_warn(dev, "hwmon: '%s' is not a valid name attribute, please fix\n", name); id = ida_alloc(&hwmon_ida, GFP_KERNEL); if (id < 0) return ERR_PTR(id); hwdev = kzalloc(sizeof(*hwdev), GFP_KERNEL); if (hwdev == NULL) { err = -ENOMEM; goto ida_remove; } hdev = &hwdev->dev; if (chip) { struct attribute **attrs; int ngroups = 2; /* terminating NULL plus &hwdev->groups */ if (groups) for (i = 0; groups[i]; i++) ngroups++; hwdev->groups = kcalloc(ngroups, sizeof(*groups), GFP_KERNEL); if (!hwdev->groups) { err = -ENOMEM; goto free_hwmon; } attrs = __hwmon_create_attrs(drvdata, chip); if (IS_ERR(attrs)) { err = PTR_ERR(attrs); goto free_hwmon; } hwdev->group.attrs = attrs; ngroups = 0; hwdev->groups[ngroups++] = &hwdev->group; if (groups) { for (i = 0; groups[i]; i++) hwdev->groups[ngroups++] = groups[i]; } hdev->groups = hwdev->groups; } else { hdev->groups = groups; } if (dev && device_property_present(dev, "label")) { err = device_property_read_string(dev, "label", &label); if (err < 0) goto free_hwmon; hwdev->label = kstrdup(label, GFP_KERNEL); if (hwdev->label == NULL) { err = -ENOMEM; goto free_hwmon; } } hwdev->name = name; hdev->class = &hwmon_class; hdev->parent = dev; while (tdev && !tdev->of_node) tdev = tdev->parent; hdev->of_node = tdev ? tdev->of_node : NULL; hwdev->chip = chip; dev_set_drvdata(hdev, drvdata); dev_set_name(hdev, HWMON_ID_FORMAT, id); err = device_register(hdev); if (err) { put_device(hdev); goto ida_remove; } INIT_LIST_HEAD(&hwdev->tzdata); if (hdev->of_node && chip && chip->ops->read && chip->info[0]->type == hwmon_chip) { u32 config = chip->info[0]->config[0]; if (config & HWMON_C_REGISTER_TZ) { err = hwmon_thermal_register_sensors(hdev); if (err) { device_unregister(hdev); /* * Don't worry about hwdev; hwmon_dev_release(), * called from device_unregister(), will free it. */ goto ida_remove; } } if (config & HWMON_C_PEC) { err = hwmon_pec_register(hdev); if (err) { device_unregister(hdev); goto ida_remove; } } } return hdev; free_hwmon: hwmon_dev_release(hdev); ida_remove: ida_free(&hwmon_ida, id); return ERR_PTR(err); } /** * hwmon_device_register_with_groups - register w/ hwmon * @dev: the parent device * @name: hwmon name attribute * @drvdata: driver data to attach to created device * @groups: List of attribute groups to create * * hwmon_device_unregister() must be called when the device is no * longer needed. * * Returns the pointer to the new device. */ struct device * hwmon_device_register_with_groups(struct device *dev, const char *name, void *drvdata, const struct attribute_group **groups) { if (!name) return ERR_PTR(-EINVAL); return __hwmon_device_register(dev, name, drvdata, NULL, groups); } EXPORT_SYMBOL_GPL(hwmon_device_register_with_groups); /** * hwmon_device_register_with_info - register w/ hwmon * @dev: the parent device (mandatory) * @name: hwmon name attribute (mandatory) * @drvdata: driver data to attach to created device (optional) * @chip: pointer to hwmon chip information (mandatory) * @extra_groups: pointer to list of additional non-standard attribute groups * (optional) * * hwmon_device_unregister() must be called when the device is no * longer needed. * * Returns the pointer to the new device. */ struct device * hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *chip, const struct attribute_group **extra_groups) { if (!dev || !name || !chip) return ERR_PTR(-EINVAL); if (!chip->ops || !(chip->ops->visible || chip->ops->is_visible) || !chip->info) return ERR_PTR(-EINVAL); return __hwmon_device_register(dev, name, drvdata, chip, extra_groups); } EXPORT_SYMBOL_GPL(hwmon_device_register_with_info); /** * hwmon_device_register_for_thermal - register hwmon device for thermal subsystem * @dev: the parent device * @name: hwmon name attribute * @drvdata: driver data to attach to created device * * The use of this function is restricted. It is provided for legacy reasons * and must only be called from the thermal subsystem. * * hwmon_device_unregister() must be called when the device is no * longer needed. * * Returns the pointer to the new device. */ struct device * hwmon_device_register_for_thermal(struct device *dev, const char *name, void *drvdata) { if (!name || !dev) return ERR_PTR(-EINVAL); return __hwmon_device_register(dev, name, drvdata, NULL, NULL); } EXPORT_SYMBOL_NS_GPL(hwmon_device_register_for_thermal, "HWMON_THERMAL"); /** * hwmon_device_register - register w/ hwmon * @dev: the device to register * * hwmon_device_unregister() must be called when the device is no * longer needed. * * Returns the pointer to the new device. */ struct device *hwmon_device_register(struct device *dev) { dev_warn(dev, "hwmon_device_register() is deprecated. Please convert the driver to use hwmon_device_register_with_info().\n"); return __hwmon_device_register(dev, NULL, NULL, NULL, NULL); } EXPORT_SYMBOL_GPL(hwmon_device_register); /** * hwmon_device_unregister - removes the previously registered class device * * @dev: the class device to destroy */ void hwmon_device_unregister(struct device *dev) { int id; if (likely(sscanf(dev_name(dev), HWMON_ID_FORMAT, &id) == 1)) { device_unregister(dev); ida_free(&hwmon_ida, id); } else dev_dbg(dev->parent, "hwmon_device_unregister() failed: bad class ID!\n"); } EXPORT_SYMBOL_GPL(hwmon_device_unregister); static void devm_hwmon_release(struct device *dev, void *res) { struct device *hwdev = *(struct device **)res; hwmon_device_unregister(hwdev); } /** * devm_hwmon_device_register_with_groups - register w/ hwmon * @dev: the parent device * @name: hwmon name attribute * @drvdata: driver data to attach to created device * @groups: List of attribute groups to create * * Returns the pointer to the new device. The new device is automatically * unregistered with the parent device. */ struct device * devm_hwmon_device_register_with_groups(struct device *dev, const char *name, void *drvdata, const struct attribute_group **groups) { struct device **ptr, *hwdev; if (!dev) return ERR_PTR(-EINVAL); ptr = devres_alloc(devm_hwmon_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); hwdev = hwmon_device_register_with_groups(dev, name, drvdata, groups); if (IS_ERR(hwdev)) goto error; *ptr = hwdev; devres_add(dev, ptr); return hwdev; error: devres_free(ptr); return hwdev; } EXPORT_SYMBOL_GPL(devm_hwmon_device_register_with_groups); /** * devm_hwmon_device_register_with_info - register w/ hwmon * @dev: the parent device * @name: hwmon name attribute * @drvdata: driver data to attach to created device * @chip: pointer to hwmon chip information * @extra_groups: pointer to list of driver specific attribute groups * * Returns the pointer to the new device. The new device is automatically * unregistered with the parent device. */ struct device * devm_hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *chip, const struct attribute_group **extra_groups) { struct device **ptr, *hwdev; if (!dev) return ERR_PTR(-EINVAL); if (!name) { name = devm_hwmon_sanitize_name(dev, dev_name(dev)); if (IS_ERR(name)) return ERR_CAST(name); } ptr = devres_alloc(devm_hwmon_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); hwdev = hwmon_device_register_with_info(dev, name, drvdata, chip, extra_groups); if (IS_ERR(hwdev)) goto error; *ptr = hwdev; devres_add(dev, ptr); return hwdev; error: devres_free(ptr); return hwdev; } EXPORT_SYMBOL_GPL(devm_hwmon_device_register_with_info); static char *__hwmon_sanitize_name(struct device *dev, const char *old_name) { char *name, *p; if (dev) name = devm_kstrdup(dev, old_name, GFP_KERNEL); else name = kstrdup(old_name, GFP_KERNEL); if (!name) return ERR_PTR(-ENOMEM); for (p = name; *p; p++) if (hwmon_is_bad_char(*p)) *p = '_'; return name; } /** * hwmon_sanitize_name - Replaces invalid characters in a hwmon name * @name: NUL-terminated name * * Allocates a new string where any invalid characters will be replaced * by an underscore. It is the responsibility of the caller to release * the memory. * * Returns newly allocated name, or ERR_PTR on error. */ char *hwmon_sanitize_name(const char *name) { return __hwmon_sanitize_name(NULL, name); } EXPORT_SYMBOL_GPL(hwmon_sanitize_name); /** * devm_hwmon_sanitize_name - resource managed hwmon_sanitize_name() * @dev: device to allocate memory for * @name: NUL-terminated name * * Allocates a new string where any invalid characters will be replaced * by an underscore. * * Returns newly allocated name, or ERR_PTR on error. */ char *devm_hwmon_sanitize_name(struct device *dev, const char *name) { if (!dev) return ERR_PTR(-EINVAL); return __hwmon_sanitize_name(dev, name); } EXPORT_SYMBOL_GPL(devm_hwmon_sanitize_name); static void __init hwmon_pci_quirks(void) { #if defined CONFIG_X86 && defined CONFIG_PCI struct pci_dev *sb; u16 base; u8 enable; /* Open access to 0x295-0x296 on MSI MS-7031 */ sb = pci_get_device(PCI_VENDOR_ID_ATI, 0x436c, NULL); if (sb) { if (sb->subsystem_vendor == 0x1462 && /* MSI */ sb->subsystem_device == 0x0031) { /* MS-7031 */ pci_read_config_byte(sb, 0x48, &enable); pci_read_config_word(sb, 0x64, &base); if (base == 0 && !(enable & BIT(2))) { dev_info(&sb->dev, "Opening wide generic port at 0x295\n"); pci_write_config_word(sb, 0x64, 0x295); pci_write_config_byte(sb, 0x48, enable | BIT(2)); } } pci_dev_put(sb); } #endif } static int __init hwmon_init(void) { int err; hwmon_pci_quirks(); err = class_register(&hwmon_class); if (err) { pr_err("couldn't register hwmon sysfs class\n"); return err; } return 0; } static void __exit hwmon_exit(void) { class_unregister(&hwmon_class); } subsys_initcall(hwmon_init); module_exit(hwmon_exit); MODULE_AUTHOR("Mark M. Hoffman <mhoffman@lightlink.com>"); MODULE_DESCRIPTION("hardware monitoring sysfs/class support"); MODULE_LICENSE("GPL"); |
| 28 27 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM thp #if !defined(_TRACE_THP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_THP_H #include <linux/types.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(hugepage_set, TP_PROTO(unsigned long addr, unsigned long pte), TP_ARGS(addr, pte), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, pte) ), TP_fast_assign( __entry->addr = addr; __entry->pte = pte; ), TP_printk("Set page table entry with 0x%lx with 0x%lx", __entry->addr, __entry->pte) ); DEFINE_EVENT(hugepage_set, hugepage_set_pmd, TP_PROTO(unsigned long addr, unsigned long pmd), TP_ARGS(addr, pmd) ); DEFINE_EVENT(hugepage_set, hugepage_set_pud, TP_PROTO(unsigned long addr, unsigned long pud), TP_ARGS(addr, pud) ); DECLARE_EVENT_CLASS(hugepage_update, TP_PROTO(unsigned long addr, unsigned long pte, unsigned long clr, unsigned long set), TP_ARGS(addr, pte, clr, set), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, pte) __field(unsigned long, clr) __field(unsigned long, set) ), TP_fast_assign( __entry->addr = addr; __entry->pte = pte; __entry->clr = clr; __entry->set = set; ), TP_printk("hugepage update at addr 0x%lx and pte = 0x%lx clr = 0x%lx, set = 0x%lx", __entry->addr, __entry->pte, __entry->clr, __entry->set) ); DEFINE_EVENT(hugepage_update, hugepage_update_pmd, TP_PROTO(unsigned long addr, unsigned long pmd, unsigned long clr, unsigned long set), TP_ARGS(addr, pmd, clr, set) ); DEFINE_EVENT(hugepage_update, hugepage_update_pud, TP_PROTO(unsigned long addr, unsigned long pud, unsigned long clr, unsigned long set), TP_ARGS(addr, pud, clr, set) ); DECLARE_EVENT_CLASS(migration_pmd, TP_PROTO(unsigned long addr, unsigned long pmd), TP_ARGS(addr, pmd), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, pmd) ), TP_fast_assign( __entry->addr = addr; __entry->pmd = pmd; ), TP_printk("addr=%lx, pmd=%lx", __entry->addr, __entry->pmd) ); DEFINE_EVENT(migration_pmd, set_migration_pmd, TP_PROTO(unsigned long addr, unsigned long pmd), TP_ARGS(addr, pmd) ); DEFINE_EVENT(migration_pmd, remove_migration_pmd, TP_PROTO(unsigned long addr, unsigned long pmd), TP_ARGS(addr, pmd) ); #endif /* _TRACE_THP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) International Business Machines Corp., 2006 * Copyright (c) Nokia Corporation, 2006, 2007 * * Author: Artem Bityutskiy (Битюцкий Артём) */ #ifndef __UBI_UBI_H__ #define __UBI_UBI_H__ #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/cdev.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/notifier.h> #include <linux/mtd/mtd.h> #include <linux/mtd/ubi.h> #include <linux/pgtable.h> #include "ubi-media.h" /* Maximum number of supported UBI devices */ #define UBI_MAX_DEVICES 32 /* UBI name used for character devices, sysfs, etc */ #define UBI_NAME_STR "ubi" struct ubi_device; /* Normal UBI messages */ __printf(2, 3) void ubi_msg(const struct ubi_device *ubi, const char *fmt, ...); /* UBI warning messages */ __printf(2, 3) void ubi_warn(const struct ubi_device *ubi, const char *fmt, ...); /* UBI error messages */ __printf(2, 3) void ubi_err(const struct ubi_device *ubi, const char *fmt, ...); /* Background thread name pattern */ #define UBI_BGT_NAME_PATTERN "ubi_bgt%dd" /* * This marker in the EBA table means that the LEB is um-mapped. * NOTE! It has to have the same value as %UBI_ALL. */ #define UBI_LEB_UNMAPPED -1 /* * In case of errors, UBI tries to repeat the operation several times before * returning error. The below constant defines how many times UBI re-tries. */ #define UBI_IO_RETRIES 3 /* * Length of the protection queue. The length is effectively equivalent to the * number of (global) erase cycles PEBs are protected from the wear-leveling * worker. */ #define UBI_PROT_QUEUE_LEN 10 /* The volume ID/LEB number/erase counter is unknown */ #define UBI_UNKNOWN -1 /* * The UBI debugfs directory name pattern and maximum name length (3 for "ubi" * + 2 for the number plus 1 for the trailing zero byte. */ #define UBI_DFS_DIR_NAME "ubi%d" #define UBI_DFS_DIR_LEN (3 + 2 + 1) /* Number of physical eraseblocks reserved for atomic LEB change operation */ #define EBA_RESERVED_PEBS 1 /* * Error codes returned by the I/O sub-system. * * UBI_IO_FF: the read region of flash contains only 0xFFs * UBI_IO_FF_BITFLIPS: the same as %UBI_IO_FF, but also there was a data * integrity error reported by the MTD driver * (uncorrectable ECC error in case of NAND) * UBI_IO_BAD_HDR: the EC or VID header is corrupted (bad magic or CRC) * UBI_IO_BAD_HDR_EBADMSG: the same as %UBI_IO_BAD_HDR, but also there was a * data integrity error reported by the MTD driver * (uncorrectable ECC error in case of NAND) * UBI_IO_BITFLIPS: bit-flips were detected and corrected * * Note, it is probably better to have bit-flip and ebadmsg as flags which can * be or'ed with other error code. But this is a big change because there are * may callers, so it does not worth the risk of introducing a bug */ enum { UBI_IO_FF = 1, UBI_IO_FF_BITFLIPS, UBI_IO_BAD_HDR, UBI_IO_BAD_HDR_EBADMSG, UBI_IO_BITFLIPS, }; /* * Return codes of the 'ubi_eba_copy_leb()' function. * * MOVE_CANCEL_RACE: canceled because the volume is being deleted, the source * PEB was put meanwhile, or there is I/O on the source PEB * MOVE_SOURCE_RD_ERR: canceled because there was a read error from the source * PEB * MOVE_TARGET_RD_ERR: canceled because there was a read error from the target * PEB * MOVE_TARGET_WR_ERR: canceled because there was a write error to the target * PEB * MOVE_TARGET_BITFLIPS: canceled because a bit-flip was detected in the * target PEB * MOVE_RETRY: retry scrubbing the PEB */ enum { MOVE_CANCEL_RACE = 1, MOVE_SOURCE_RD_ERR, MOVE_TARGET_RD_ERR, MOVE_TARGET_WR_ERR, MOVE_TARGET_BITFLIPS, MOVE_RETRY, }; /* * Return codes of the fastmap sub-system * * UBI_NO_FASTMAP: No fastmap super block was found * UBI_BAD_FASTMAP: A fastmap was found but it's unusable */ enum { UBI_NO_FASTMAP = 1, UBI_BAD_FASTMAP, }; /** * struct ubi_vid_io_buf - VID buffer used to read/write VID info to/from the * flash. * @hdr: a pointer to the VID header stored in buffer * @buffer: underlying buffer */ struct ubi_vid_io_buf { struct ubi_vid_hdr *hdr; void *buffer; }; /** * struct ubi_wl_entry - wear-leveling entry. * @u.rb: link in the corresponding (free/used) RB-tree * @u.list: link in the protection queue * @ec: erase counter * @pnum: physical eraseblock number * * This data structure is used in the WL sub-system. Each physical eraseblock * has a corresponding &struct wl_entry object which may be kept in different * RB-trees. See WL sub-system for details. */ struct ubi_wl_entry { union { struct rb_node rb; struct list_head list; } u; int ec; int pnum; }; /** * struct ubi_ltree_entry - an entry in the lock tree. * @rb: links RB-tree nodes * @vol_id: volume ID of the locked logical eraseblock * @lnum: locked logical eraseblock number * @users: how many tasks are using this logical eraseblock or wait for it * @mutex: read/write mutex to implement read/write access serialization to * the (@vol_id, @lnum) logical eraseblock * * This data structure is used in the EBA sub-system to implement per-LEB * locking. When a logical eraseblock is being locked - corresponding * &struct ubi_ltree_entry object is inserted to the lock tree (@ubi->ltree). * See EBA sub-system for details. */ struct ubi_ltree_entry { struct rb_node rb; int vol_id; int lnum; int users; struct rw_semaphore mutex; }; /** * struct ubi_rename_entry - volume re-name description data structure. * @new_name_len: new volume name length * @new_name: new volume name * @remove: if not zero, this volume should be removed, not re-named * @desc: descriptor of the volume * @list: links re-name entries into a list * * This data structure is utilized in the multiple volume re-name code. Namely, * UBI first creates a list of &struct ubi_rename_entry objects from the * &struct ubi_rnvol_req request object, and then utilizes this list to do all * the job. */ struct ubi_rename_entry { int new_name_len; char new_name[UBI_VOL_NAME_MAX + 1]; int remove; struct ubi_volume_desc *desc; struct list_head list; }; struct ubi_volume_desc; /** * struct ubi_fastmap_layout - in-memory fastmap data structure. * @e: PEBs used by the current fastmap * @to_be_tortured: if non-zero tortured this PEB * @used_blocks: number of used PEBs * @max_pool_size: maximal size of the user pool * @max_wl_pool_size: maximal size of the pool used by the WL sub-system */ struct ubi_fastmap_layout { struct ubi_wl_entry *e[UBI_FM_MAX_BLOCKS]; int to_be_tortured[UBI_FM_MAX_BLOCKS]; int used_blocks; int max_pool_size; int max_wl_pool_size; }; /** * struct ubi_fm_pool - in-memory fastmap pool * @pebs: PEBs in this pool * @used: number of used PEBs * @size: total number of PEBs in this pool * @max_size: maximal size of the pool * * A pool gets filled with up to max_size. * If all PEBs within the pool are used a new fastmap will be written * to the flash and the pool gets refilled with empty PEBs. * */ struct ubi_fm_pool { int pebs[UBI_FM_MAX_POOL_SIZE]; int used; int size; int max_size; }; /** * struct ubi_eba_leb_desc - EBA logical eraseblock descriptor * @lnum: the logical eraseblock number * @pnum: the physical eraseblock where the LEB can be found * * This structure is here to hide EBA's internal from other part of the * UBI implementation. * * One can query the position of a LEB by calling ubi_eba_get_ldesc(). */ struct ubi_eba_leb_desc { int lnum; int pnum; }; /** * struct ubi_volume - UBI volume description data structure. * @dev: device object to make use of the Linux device model * @cdev: character device object to create character device * @ubi: reference to the UBI device description object * @vol_id: volume ID * @ref_count: volume reference count * @readers: number of users holding this volume in read-only mode * @writers: number of users holding this volume in read-write mode * @exclusive: whether somebody holds this volume in exclusive mode * @metaonly: whether somebody is altering only meta data of this volume * * @reserved_pebs: how many physical eraseblocks are reserved for this volume * @vol_type: volume type (%UBI_DYNAMIC_VOLUME or %UBI_STATIC_VOLUME) * @usable_leb_size: logical eraseblock size without padding * @used_ebs: how many logical eraseblocks in this volume contain data * @last_eb_bytes: how many bytes are stored in the last logical eraseblock * @used_bytes: how many bytes of data this volume contains * @alignment: volume alignment * @data_pad: how many bytes are not used at the end of physical eraseblocks to * satisfy the requested alignment * @name_len: volume name length * @name: volume name * * @upd_ebs: how many eraseblocks are expected to be updated * @ch_lnum: LEB number which is being changing by the atomic LEB change * operation * @upd_bytes: how many bytes are expected to be received for volume update or * atomic LEB change * @upd_received: how many bytes were already received for volume update or * atomic LEB change * @upd_buf: update buffer which is used to collect update data or data for * atomic LEB change * * @eba_tbl: EBA table of this volume (LEB->PEB mapping) * @skip_check: %1 if CRC check of this static volume should be skipped. * Directly reflects the presence of the * %UBI_VTBL_SKIP_CRC_CHECK_FLG flag in the vtbl entry * @checked: %1 if this static volume was checked * @corrupted: %1 if the volume is corrupted (static volumes only) * @upd_marker: %1 if the update marker is set for this volume * @updating: %1 if the volume is being updated * @changing_leb: %1 if the atomic LEB change ioctl command is in progress * @direct_writes: %1 if direct writes are enabled for this volume * * @checkmap: bitmap to remember which PEB->LEB mappings got checked, * protected by UBI LEB lock tree. * * The @corrupted field indicates that the volume's contents is corrupted. * Since UBI protects only static volumes, this field is not relevant to * dynamic volumes - it is user's responsibility to assure their data * integrity. * * The @upd_marker flag indicates that this volume is either being updated at * the moment or is damaged because of an unclean reboot. */ struct ubi_volume { struct device dev; struct cdev cdev; struct ubi_device *ubi; int vol_id; int ref_count; int readers; int writers; int exclusive; int metaonly; bool is_dead; int reserved_pebs; int vol_type; int usable_leb_size; int used_ebs; int last_eb_bytes; long long used_bytes; int alignment; int data_pad; int name_len; char name[UBI_VOL_NAME_MAX + 1]; int upd_ebs; int ch_lnum; long long upd_bytes; long long upd_received; void *upd_buf; struct ubi_eba_table *eba_tbl; unsigned int skip_check:1; unsigned int checked:1; unsigned int corrupted:1; unsigned int upd_marker:1; unsigned int updating:1; unsigned int changing_leb:1; unsigned int direct_writes:1; #ifdef CONFIG_MTD_UBI_FASTMAP unsigned long *checkmap; #endif }; /** * struct ubi_volume_desc - UBI volume descriptor returned when it is opened. * @vol: reference to the corresponding volume description object * @mode: open mode (%UBI_READONLY, %UBI_READWRITE, %UBI_EXCLUSIVE * or %UBI_METAONLY) */ struct ubi_volume_desc { struct ubi_volume *vol; int mode; }; /** * struct ubi_debug_info - debugging information for an UBI device. * * @chk_gen: if UBI general extra checks are enabled * @chk_io: if UBI I/O extra checks are enabled * @chk_fastmap: if UBI fastmap extra checks are enabled * @disable_bgt: disable the background task for testing purposes * @emulate_bitflips: emulate bit-flips for testing purposes * @emulate_io_failures: emulate write/erase failures for testing purposes * @emulate_power_cut: emulate power cut for testing purposes * @power_cut_counter: count down for writes left until emulated power cut * @power_cut_min: minimum number of writes before emulating a power cut * @power_cut_max: maximum number of writes until emulating a power cut * @emulate_failures: emulate failures for testing purposes * @dfs_dir_name: name of debugfs directory containing files of this UBI device * @dfs_dir: direntry object of the UBI device debugfs directory * @dfs_chk_gen: debugfs knob to enable UBI general extra checks * @dfs_chk_io: debugfs knob to enable UBI I/O extra checks * @dfs_chk_fastmap: debugfs knob to enable UBI fastmap extra checks * @dfs_disable_bgt: debugfs knob to disable the background task * @dfs_emulate_bitflips: debugfs knob to emulate bit-flips * @dfs_emulate_io_failures: debugfs knob to emulate write/erase failures * @dfs_emulate_power_cut: debugfs knob to emulate power cuts * @dfs_power_cut_min: debugfs knob for minimum writes before power cut * @dfs_power_cut_max: debugfs knob for maximum writes until power cut * @dfs_emulate_failures: debugfs entry to control the fault injection type */ struct ubi_debug_info { unsigned int chk_gen:1; unsigned int chk_io:1; unsigned int chk_fastmap:1; unsigned int disable_bgt:1; unsigned int emulate_bitflips:1; unsigned int emulate_io_failures:1; unsigned int emulate_power_cut:2; unsigned int power_cut_counter; unsigned int power_cut_min; unsigned int power_cut_max; unsigned int emulate_failures; char dfs_dir_name[UBI_DFS_DIR_LEN]; struct dentry *dfs_dir; struct dentry *dfs_chk_gen; struct dentry *dfs_chk_io; struct dentry *dfs_chk_fastmap; struct dentry *dfs_disable_bgt; struct dentry *dfs_emulate_bitflips; struct dentry *dfs_emulate_io_failures; struct dentry *dfs_emulate_power_cut; struct dentry *dfs_power_cut_min; struct dentry *dfs_power_cut_max; struct dentry *dfs_emulate_failures; }; /** * struct ubi_device - UBI device description structure * @dev: UBI device object to use the Linux device model * @cdev: character device object to create character device * @ubi_num: UBI device number * @ubi_name: UBI device name * @vol_count: number of volumes in this UBI device * @volumes: volumes of this UBI device * @volumes_lock: protects @volumes, @rsvd_pebs, @avail_pebs, beb_rsvd_pebs, * @beb_rsvd_level, @bad_peb_count, @good_peb_count, @vol_count, * @vol->readers, @vol->writers, @vol->exclusive, * @vol->metaonly, @vol->ref_count, @vol->mapping and * @vol->eba_tbl. * @ref_count: count of references on the UBI device * @image_seq: image sequence number recorded on EC headers * * @rsvd_pebs: count of reserved physical eraseblocks * @avail_pebs: count of available physical eraseblocks * @beb_rsvd_pebs: how many physical eraseblocks are reserved for bad PEB * handling * @beb_rsvd_level: normal level of PEBs reserved for bad PEB handling * * @autoresize_vol_id: ID of the volume which has to be auto-resized at the end * of UBI initialization * @vtbl_slots: how many slots are available in the volume table * @vtbl_size: size of the volume table in bytes * @vtbl: in-RAM volume table copy * @device_mutex: protects on-flash volume table and serializes volume * creation, deletion, update, re-size, re-name and set * property * * @max_ec: current highest erase counter value * @mean_ec: current mean erase counter value * * @global_sqnum: global sequence number * @ltree_lock: protects the lock tree and @global_sqnum * @ltree: the lock tree * @alc_mutex: serializes "atomic LEB change" operations * * @fm_disabled: non-zero if fastmap is disabled (default) * @fm: in-memory data structure of the currently used fastmap * @fm_pool: in-memory data structure of the fastmap pool * @fm_wl_pool: in-memory data structure of the fastmap pool used by the WL * sub-system * @fm_protect: serializes ubi_update_fastmap(), protects @fm_buf and makes sure * that critical sections cannot be interrupted by ubi_update_fastmap() * @fm_buf: vmalloc()'d buffer which holds the raw fastmap * @fm_size: fastmap size in bytes * @fm_eba_sem: allows ubi_update_fastmap() to block EBA table changes * @fm_work: fastmap work queue * @fm_work_scheduled: non-zero if fastmap work was scheduled * @fast_attach: non-zero if UBI was attached by fastmap * @fm_anchor: The next anchor PEB to use for fastmap * @fm_do_produce_anchor: If true produce an anchor PEB in wl * @fm_pool_rsv_cnt: Number of reserved PEBs for filling pool/wl_pool * * @used: RB-tree of used physical eraseblocks * @erroneous: RB-tree of erroneous used physical eraseblocks * @free: RB-tree of free physical eraseblocks * @free_count: Contains the number of elements in @free * @scrub: RB-tree of physical eraseblocks which need scrubbing * @pq: protection queue (contain physical eraseblocks which are temporarily * protected from the wear-leveling worker) * @pq_head: protection queue head * @wl_lock: protects the @used, @free, @pq, @pq_head, @lookuptbl, @move_from, * @move_to, @move_to_put @erase_pending, @wl_scheduled, @works, * @erroneous, @erroneous_peb_count, @fm_work_scheduled, @fm_pool, * and @fm_wl_pool fields * @move_mutex: serializes eraseblock moves * @work_sem: used to wait for all the scheduled works to finish and prevent * new works from being submitted * @wl_scheduled: non-zero if the wear-leveling was scheduled * @lookuptbl: a table to quickly find a &struct ubi_wl_entry object for any * physical eraseblock * @move_from: physical eraseblock from where the data is being moved * @move_to: physical eraseblock where the data is being moved to * @move_to_put: if the "to" PEB was put * @works: list of pending works * @works_count: count of pending works * @bgt_thread: background thread description object * @thread_enabled: if the background thread is enabled * @bgt_name: background thread name * * @flash_size: underlying MTD device size (in bytes) * @peb_count: count of physical eraseblocks on the MTD device * @peb_size: physical eraseblock size * @bad_peb_limit: top limit of expected bad physical eraseblocks * @bad_peb_count: count of bad physical eraseblocks * @good_peb_count: count of good physical eraseblocks * @corr_peb_count: count of corrupted physical eraseblocks (preserved and not * used by UBI) * @erroneous_peb_count: count of erroneous physical eraseblocks in @erroneous * @max_erroneous: maximum allowed amount of erroneous physical eraseblocks * @min_io_size: minimal input/output unit size of the underlying MTD device * @hdrs_min_io_size: minimal I/O unit size used for VID and EC headers * @ro_mode: if the UBI device is in read-only mode * @leb_size: logical eraseblock size * @leb_start: starting offset of logical eraseblocks within physical * eraseblocks * @ec_hdr_alsize: size of the EC header aligned to @hdrs_min_io_size * @vid_hdr_alsize: size of the VID header aligned to @hdrs_min_io_size * @vid_hdr_offset: starting offset of the volume identifier header (might be * unaligned) * @vid_hdr_aloffset: starting offset of the VID header aligned to * @hdrs_min_io_size * @vid_hdr_shift: contains @vid_hdr_offset - @vid_hdr_aloffset * @bad_allowed: whether the MTD device admits bad physical eraseblocks or not * @nor_flash: non-zero if working on top of NOR flash * @max_write_size: maximum amount of bytes the underlying flash can write at a * time (MTD write buffer size) * @mtd: MTD device descriptor * * @peb_buf: a buffer of PEB size used for different purposes * @buf_mutex: protects @peb_buf * @ckvol_mutex: serializes static volume checking when opening * * @dbg: debugging information for this UBI device */ struct ubi_device { struct cdev cdev; struct device dev; int ubi_num; char ubi_name[sizeof(UBI_NAME_STR)+5]; int vol_count; struct ubi_volume *volumes[UBI_MAX_VOLUMES+UBI_INT_VOL_COUNT]; spinlock_t volumes_lock; int ref_count; int image_seq; bool is_dead; int rsvd_pebs; int avail_pebs; int beb_rsvd_pebs; int beb_rsvd_level; int bad_peb_limit; int autoresize_vol_id; int vtbl_slots; int vtbl_size; struct ubi_vtbl_record *vtbl; struct mutex device_mutex; int max_ec; /* Note, mean_ec is not updated run-time - should be fixed */ int mean_ec; /* EBA sub-system's stuff */ unsigned long long global_sqnum; spinlock_t ltree_lock; struct rb_root ltree; struct mutex alc_mutex; /* Fastmap stuff */ int fm_disabled; struct ubi_fastmap_layout *fm; struct ubi_fm_pool fm_pool; struct ubi_fm_pool fm_wl_pool; struct rw_semaphore fm_eba_sem; struct rw_semaphore fm_protect; void *fm_buf; size_t fm_size; struct work_struct fm_work; int fm_work_scheduled; int fast_attach; struct ubi_wl_entry *fm_anchor; int fm_do_produce_anchor; int fm_pool_rsv_cnt; /* Wear-leveling sub-system's stuff */ struct rb_root used; struct rb_root erroneous; struct rb_root free; int free_count; struct rb_root scrub; struct list_head pq[UBI_PROT_QUEUE_LEN]; int pq_head; spinlock_t wl_lock; struct mutex move_mutex; struct rw_semaphore work_sem; int wl_scheduled; struct ubi_wl_entry **lookuptbl; struct ubi_wl_entry *move_from; struct ubi_wl_entry *move_to; int move_to_put; struct list_head works; int works_count; struct task_struct *bgt_thread; int thread_enabled; char bgt_name[sizeof(UBI_BGT_NAME_PATTERN)+2]; /* I/O sub-system's stuff */ long long flash_size; int peb_count; int peb_size; int bad_peb_count; int good_peb_count; int corr_peb_count; int erroneous_peb_count; int max_erroneous; int min_io_size; int hdrs_min_io_size; int ro_mode; int leb_size; int leb_start; int ec_hdr_alsize; int vid_hdr_alsize; int vid_hdr_offset; int vid_hdr_aloffset; int vid_hdr_shift; unsigned int bad_allowed:1; unsigned int nor_flash:1; int max_write_size; struct mtd_info *mtd; void *peb_buf; struct mutex buf_mutex; struct mutex ckvol_mutex; struct ubi_debug_info dbg; }; /** * struct ubi_ainf_peb - attach information about a physical eraseblock. * @ec: erase counter (%UBI_UNKNOWN if it is unknown) * @pnum: physical eraseblock number * @vol_id: ID of the volume this LEB belongs to * @lnum: logical eraseblock number * @scrub: if this physical eraseblock needs scrubbing * @copy_flag: this LEB is a copy (@copy_flag is set in VID header of this LEB) * @sqnum: sequence number * @u: unions RB-tree or @list links * @u.rb: link in the per-volume RB-tree of &struct ubi_ainf_peb objects * @u.list: link in one of the eraseblock lists * * One object of this type is allocated for each physical eraseblock when * attaching an MTD device. Note, if this PEB does not belong to any LEB / * volume, the @vol_id and @lnum fields are initialized to %UBI_UNKNOWN. */ struct ubi_ainf_peb { int ec; int pnum; int vol_id; int lnum; unsigned int scrub:1; unsigned int copy_flag:1; unsigned long long sqnum; union { struct rb_node rb; struct list_head list; } u; }; /** * struct ubi_ainf_volume - attaching information about a volume. * @vol_id: volume ID * @highest_lnum: highest logical eraseblock number in this volume * @leb_count: number of logical eraseblocks in this volume * @vol_type: volume type * @used_ebs: number of used logical eraseblocks in this volume (only for * static volumes) * @last_data_size: amount of data in the last logical eraseblock of this * volume (always equivalent to the usable logical eraseblock * size in case of dynamic volumes) * @data_pad: how many bytes at the end of logical eraseblocks of this volume * are not used (due to volume alignment) * @compat: compatibility flags of this volume * @rb: link in the volume RB-tree * @root: root of the RB-tree containing all the eraseblock belonging to this * volume (&struct ubi_ainf_peb objects) * * One object of this type is allocated for each volume when attaching an MTD * device. */ struct ubi_ainf_volume { int vol_id; int highest_lnum; int leb_count; int vol_type; int used_ebs; int last_data_size; int data_pad; int compat; struct rb_node rb; struct rb_root root; }; /** * struct ubi_attach_info - MTD device attaching information. * @volumes: root of the volume RB-tree * @corr: list of corrupted physical eraseblocks * @free: list of free physical eraseblocks * @erase: list of physical eraseblocks which have to be erased * @alien: list of physical eraseblocks which should not be used by UBI (e.g., * those belonging to "preserve"-compatible internal volumes) * @fastmap: list of physical eraseblocks which relate to fastmap (e.g., * eraseblocks of the current and not yet erased old fastmap blocks) * @corr_peb_count: count of PEBs in the @corr list * @empty_peb_count: count of PEBs which are presumably empty (contain only * 0xFF bytes) * @alien_peb_count: count of PEBs in the @alien list * @bad_peb_count: count of bad physical eraseblocks * @maybe_bad_peb_count: count of bad physical eraseblocks which are not marked * as bad yet, but which look like bad * @vols_found: number of volumes found * @highest_vol_id: highest volume ID * @is_empty: flag indicating whether the MTD device is empty or not * @force_full_scan: flag indicating whether we need to do a full scan and drop all existing Fastmap data structures * @min_ec: lowest erase counter value * @max_ec: highest erase counter value * @max_sqnum: highest sequence number value * @mean_ec: mean erase counter value * @ec_sum: a temporary variable used when calculating @mean_ec * @ec_count: a temporary variable used when calculating @mean_ec * @aeb_slab_cache: slab cache for &struct ubi_ainf_peb objects * @ech: temporary EC header. Only available during scan * @vidh: temporary VID buffer. Only available during scan * * This data structure contains the result of attaching an MTD device and may * be used by other UBI sub-systems to build final UBI data structures, further * error-recovery and so on. */ struct ubi_attach_info { struct rb_root volumes; struct list_head corr; struct list_head free; struct list_head erase; struct list_head alien; struct list_head fastmap; int corr_peb_count; int empty_peb_count; int alien_peb_count; int bad_peb_count; int maybe_bad_peb_count; int vols_found; int highest_vol_id; int is_empty; int force_full_scan; int min_ec; int max_ec; unsigned long long max_sqnum; int mean_ec; uint64_t ec_sum; int ec_count; struct kmem_cache *aeb_slab_cache; struct ubi_ec_hdr *ech; struct ubi_vid_io_buf *vidb; }; /** * struct ubi_work - UBI work description data structure. * @list: a link in the list of pending works * @func: worker function * @e: physical eraseblock to erase * @vol_id: the volume ID on which this erasure is being performed * @lnum: the logical eraseblock number * @torture: if the physical eraseblock has to be tortured * * The @func pointer points to the worker function. If the @shutdown argument is * not zero, the worker has to free the resources and exit immediately as the * WL sub-system is shutting down. * The worker has to return zero in case of success and a negative error code in * case of failure. */ struct ubi_work { struct list_head list; int (*func)(struct ubi_device *ubi, struct ubi_work *wrk, int shutdown); /* The below fields are only relevant to erasure works */ struct ubi_wl_entry *e; int vol_id; int lnum; int torture; }; #include "debug.h" extern struct kmem_cache *ubi_wl_entry_slab; extern const struct file_operations ubi_ctrl_cdev_operations; extern const struct file_operations ubi_cdev_operations; extern const struct file_operations ubi_vol_cdev_operations; extern const struct class ubi_class; extern struct mutex ubi_devices_mutex; extern struct blocking_notifier_head ubi_notifiers; /* attach.c */ struct ubi_ainf_peb *ubi_alloc_aeb(struct ubi_attach_info *ai, int pnum, int ec); void ubi_free_aeb(struct ubi_attach_info *ai, struct ubi_ainf_peb *aeb); int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum, int ec, const struct ubi_vid_hdr *vid_hdr, int bitflips); struct ubi_ainf_volume *ubi_add_av(struct ubi_attach_info *ai, int vol_id); struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai, int vol_id); void ubi_remove_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av); struct ubi_ainf_peb *ubi_early_get_peb(struct ubi_device *ubi, struct ubi_attach_info *ai); int ubi_attach(struct ubi_device *ubi, int force_scan); /* vtbl.c */ int ubi_change_vtbl_record(struct ubi_device *ubi, int idx, struct ubi_vtbl_record *vtbl_rec); int ubi_vtbl_rename_volumes(struct ubi_device *ubi, struct list_head *rename_list); int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai); /* vmt.c */ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req); int ubi_remove_volume(struct ubi_volume_desc *desc, int no_vtbl); int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs); int ubi_rename_volumes(struct ubi_device *ubi, struct list_head *rename_list); int ubi_add_volume(struct ubi_device *ubi, struct ubi_volume *vol); void ubi_free_volume(struct ubi_device *ubi, struct ubi_volume *vol); /* upd.c */ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, long long bytes); int ubi_more_update_data(struct ubi_device *ubi, struct ubi_volume *vol, const void __user *buf, int count); int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, const struct ubi_leb_change_req *req); int ubi_more_leb_change_data(struct ubi_device *ubi, struct ubi_volume *vol, const void __user *buf, int count); /* misc.c */ int ubi_calc_data_len(const struct ubi_device *ubi, const void *buf, int length); int ubi_check_volume(struct ubi_device *ubi, int vol_id); void ubi_update_reserved(struct ubi_device *ubi); void ubi_calculate_reserved(struct ubi_device *ubi); int ubi_check_pattern(const void *buf, uint8_t patt, int size); static inline bool ubi_leb_valid(struct ubi_volume *vol, int lnum) { return lnum >= 0 && lnum < vol->reserved_pebs; } /* eba.c */ struct ubi_eba_table *ubi_eba_create_table(struct ubi_volume *vol, int nentries); void ubi_eba_destroy_table(struct ubi_eba_table *tbl); void ubi_eba_copy_table(struct ubi_volume *vol, struct ubi_eba_table *dst, int nentries); void ubi_eba_replace_table(struct ubi_volume *vol, struct ubi_eba_table *tbl); void ubi_eba_get_ldesc(struct ubi_volume *vol, int lnum, struct ubi_eba_leb_desc *ldesc); bool ubi_eba_is_mapped(struct ubi_volume *vol, int lnum); int ubi_eba_unmap_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum); int ubi_eba_read_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum, void *buf, int offset, int len, int check); int ubi_eba_read_leb_sg(struct ubi_device *ubi, struct ubi_volume *vol, struct ubi_sgl *sgl, int lnum, int offset, int len, int check); int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum, const void *buf, int offset, int len); int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol, int lnum, const void *buf, int len, int used_ebs); int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, int lnum, const void *buf, int len); int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to, struct ubi_vid_io_buf *vidb); int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai); unsigned long long ubi_next_sqnum(struct ubi_device *ubi); int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap, struct ubi_attach_info *ai_scan); /* wl.c */ int ubi_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int torture); int ubi_wl_get_peb(struct ubi_device *ubi); int ubi_wl_put_peb(struct ubi_device *ubi, int vol_id, int lnum, int pnum, int torture); int ubi_wl_flush(struct ubi_device *ubi, int vol_id, int lnum); int ubi_wl_scrub_peb(struct ubi_device *ubi, int pnum); int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai); void ubi_wl_close(struct ubi_device *ubi); int ubi_thread(void *u); struct ubi_wl_entry *ubi_wl_get_fm_peb(struct ubi_device *ubi, int anchor); int ubi_wl_put_fm_peb(struct ubi_device *ubi, struct ubi_wl_entry *used_e, int lnum, int torture); int ubi_is_erase_work(struct ubi_work *wrk); void ubi_refill_pools_and_lock(struct ubi_device *ubi); int ubi_ensure_anchor_pebs(struct ubi_device *ubi); int ubi_bitflip_check(struct ubi_device *ubi, int pnum, int force_scrub); /* io.c */ int ubi_io_read(const struct ubi_device *ubi, void *buf, int pnum, int offset, int len); int ubi_io_write(struct ubi_device *ubi, const void *buf, int pnum, int offset, int len); int ubi_io_sync_erase(struct ubi_device *ubi, int pnum, int torture); int ubi_io_is_bad(const struct ubi_device *ubi, int pnum); int ubi_io_mark_bad(const struct ubi_device *ubi, int pnum); int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum, struct ubi_ec_hdr *ec_hdr, int verbose); int ubi_io_write_ec_hdr(struct ubi_device *ubi, int pnum, struct ubi_ec_hdr *ec_hdr); int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum, struct ubi_vid_io_buf *vidb, int verbose); int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum, struct ubi_vid_io_buf *vidb); /* build.c */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset, int max_beb_per1024, bool disable_fm, bool need_resv_pool); int ubi_detach_mtd_dev(int ubi_num, int anyway); struct ubi_device *ubi_get_device(int ubi_num); void ubi_put_device(struct ubi_device *ubi); struct ubi_device *ubi_get_by_major(int major); int ubi_major2num(int major); int ubi_volume_notify(struct ubi_device *ubi, struct ubi_volume *vol, int ntype); int ubi_notify_all(struct ubi_device *ubi, int ntype, struct notifier_block *nb); int ubi_enumerate_volumes(struct notifier_block *nb); void ubi_free_all_volumes(struct ubi_device *ubi); void ubi_free_internal_volumes(struct ubi_device *ubi); /* kapi.c */ void ubi_do_get_device_info(struct ubi_device *ubi, struct ubi_device_info *di); void ubi_do_get_volume_info(struct ubi_device *ubi, struct ubi_volume *vol, struct ubi_volume_info *vi); int ubi_get_num_by_path(const char *pathname, int *ubi_num, int *vol_id); /* scan.c */ int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, int pnum, const struct ubi_vid_hdr *vid_hdr); /* fastmap.c */ #ifdef CONFIG_MTD_UBI_FASTMAP size_t ubi_calc_fm_size(struct ubi_device *ubi); int ubi_update_fastmap(struct ubi_device *ubi); int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai, struct ubi_attach_info *scan_ai); int ubi_fastmap_init_checkmap(struct ubi_volume *vol, int leb_count); void ubi_fastmap_destroy_checkmap(struct ubi_volume *vol); #else static inline int ubi_update_fastmap(struct ubi_device *ubi) { return 0; } static inline int ubi_fastmap_init_checkmap(struct ubi_volume *vol, int leb_count) { return 0; } static inline void ubi_fastmap_destroy_checkmap(struct ubi_volume *vol) {} #endif /* block.c */ #ifdef CONFIG_MTD_UBI_BLOCK int ubiblock_init(void); void ubiblock_exit(void); int ubiblock_create(struct ubi_volume_info *vi); int ubiblock_remove(struct ubi_volume_info *vi); #else static inline int ubiblock_init(void) { return 0; } static inline void ubiblock_exit(void) {} static inline int ubiblock_create(struct ubi_volume_info *vi) { return -ENOSYS; } static inline int ubiblock_remove(struct ubi_volume_info *vi) { return -ENOSYS; } #endif /* * ubi_for_each_free_peb - walk the UBI free RB tree. * @ubi: UBI device description object * @e: a pointer to a ubi_wl_entry to use as cursor * @pos: a pointer to RB-tree entry type to use as a loop counter */ #define ubi_for_each_free_peb(ubi, e, tmp_rb) \ ubi_rb_for_each_entry((tmp_rb), (e), &(ubi)->free, u.rb) /* * ubi_for_each_used_peb - walk the UBI used RB tree. * @ubi: UBI device description object * @e: a pointer to a ubi_wl_entry to use as cursor * @pos: a pointer to RB-tree entry type to use as a loop counter */ #define ubi_for_each_used_peb(ubi, e, tmp_rb) \ ubi_rb_for_each_entry((tmp_rb), (e), &(ubi)->used, u.rb) /* * ubi_for_each_scub_peb - walk the UBI scub RB tree. * @ubi: UBI device description object * @e: a pointer to a ubi_wl_entry to use as cursor * @pos: a pointer to RB-tree entry type to use as a loop counter */ #define ubi_for_each_scrub_peb(ubi, e, tmp_rb) \ ubi_rb_for_each_entry((tmp_rb), (e), &(ubi)->scrub, u.rb) /* * ubi_for_each_protected_peb - walk the UBI protection queue. * @ubi: UBI device description object * @i: a integer used as counter * @e: a pointer to a ubi_wl_entry to use as cursor */ #define ubi_for_each_protected_peb(ubi, i, e) \ for ((i) = 0; (i) < UBI_PROT_QUEUE_LEN; (i)++) \ list_for_each_entry((e), &(ubi->pq[(i)]), u.list) /* * ubi_rb_for_each_entry - walk an RB-tree. * @rb: a pointer to type 'struct rb_node' to use as a loop counter * @pos: a pointer to RB-tree entry type to use as a loop counter * @root: RB-tree's root * @member: the name of the 'struct rb_node' within the RB-tree entry */ #define ubi_rb_for_each_entry(rb, pos, root, member) \ for (rb = rb_first(root), \ pos = (rb ? container_of(rb, typeof(*pos), member) : NULL); \ rb; \ rb = rb_next(rb), \ pos = (rb ? container_of(rb, typeof(*pos), member) : NULL)) /* * ubi_move_aeb_to_list - move a PEB from the volume tree to a list. * * @av: volume attaching information * @aeb: attaching eraseblock information * @list: the list to move to */ static inline void ubi_move_aeb_to_list(struct ubi_ainf_volume *av, struct ubi_ainf_peb *aeb, struct list_head *list) { rb_erase(&aeb->u.rb, &av->root); list_add_tail(&aeb->u.list, list); } /** * ubi_init_vid_buf - Initialize a VID buffer * @ubi: the UBI device * @vidb: the VID buffer to initialize * @buf: the underlying buffer */ static inline void ubi_init_vid_buf(const struct ubi_device *ubi, struct ubi_vid_io_buf *vidb, void *buf) { if (buf) memset(buf, 0, ubi->vid_hdr_alsize); vidb->buffer = buf; vidb->hdr = buf + ubi->vid_hdr_shift; } /** * ubi_init_vid_buf - Allocate a VID buffer * @ubi: the UBI device * @gfp_flags: GFP flags to use for the allocation */ static inline struct ubi_vid_io_buf * ubi_alloc_vid_buf(const struct ubi_device *ubi, gfp_t gfp_flags) { struct ubi_vid_io_buf *vidb; void *buf; vidb = kzalloc(sizeof(*vidb), gfp_flags); if (!vidb) return NULL; buf = kmalloc(ubi->vid_hdr_alsize, gfp_flags); if (!buf) { kfree(vidb); return NULL; } ubi_init_vid_buf(ubi, vidb, buf); return vidb; } /** * ubi_free_vid_buf - Free a VID buffer * @vidb: the VID buffer to free */ static inline void ubi_free_vid_buf(struct ubi_vid_io_buf *vidb) { if (!vidb) return; kfree(vidb->buffer); kfree(vidb); } /** * ubi_get_vid_hdr - Get the VID header attached to a VID buffer * @vidb: VID buffer */ static inline struct ubi_vid_hdr *ubi_get_vid_hdr(struct ubi_vid_io_buf *vidb) { return vidb->hdr; } /** * ubi_ro_mode - switch to read-only mode. * @ubi: UBI device description object */ static inline void ubi_ro_mode(struct ubi_device *ubi) { if (!ubi->ro_mode) { ubi->ro_mode = 1; ubi_warn(ubi, "switch to read-only mode"); dump_stack(); } } /* * This function is equivalent to 'ubi_io_read()', but @offset is relative to * the beginning of the logical eraseblock, not to the beginning of the * physical eraseblock. */ static inline int ubi_io_read_data(const struct ubi_device *ubi, void *buf, int pnum, int offset, int len) { ubi_assert(offset >= 0); return ubi_io_read(ubi, buf, pnum, offset + ubi->leb_start, len); } /* * This function is equivalent to 'ubi_io_write()', but @offset is relative to * the beginning of the logical eraseblock, not to the beginning of the * physical eraseblock. */ static inline int ubi_io_write_data(struct ubi_device *ubi, const void *buf, int pnum, int offset, int len) { ubi_assert(offset >= 0); if (ubi_dbg_power_cut(ubi, MASK_POWER_CUT_DATA)) { ubi_warn(ubi, "XXXXX emulating a power cut when writing data XXXXX"); ubi_ro_mode(ubi); return -EROFS; } return ubi_io_write(ubi, buf, pnum, offset + ubi->leb_start, len); } /** * vol_id2idx - get table index by volume ID. * @ubi: UBI device description object * @vol_id: volume ID */ static inline int vol_id2idx(const struct ubi_device *ubi, int vol_id) { if (vol_id >= UBI_INTERNAL_VOL_START) return vol_id - UBI_INTERNAL_VOL_START + ubi->vtbl_slots; else return vol_id; } /** * idx2vol_id - get volume ID by table index. * @ubi: UBI device description object * @idx: table index */ static inline int idx2vol_id(const struct ubi_device *ubi, int idx) { if (idx >= ubi->vtbl_slots) return idx - ubi->vtbl_slots + UBI_INTERNAL_VOL_START; else return idx; } /** * ubi_is_fm_vol - check whether a volume ID is a Fastmap volume. * @vol_id: volume ID */ static inline bool ubi_is_fm_vol(int vol_id) { switch (vol_id) { case UBI_FM_SB_VOLUME_ID: case UBI_FM_DATA_VOLUME_ID: return true; } return false; } /** * ubi_find_fm_block - check whether a PEB is part of the current Fastmap. * @ubi: UBI device description object * @pnum: physical eraseblock to look for * * This function returns a wear leveling object if @pnum relates to the current * fastmap, @NULL otherwise. */ static inline struct ubi_wl_entry *ubi_find_fm_block(const struct ubi_device *ubi, int pnum) { int i; if (ubi->fm) { for (i = 0; i < ubi->fm->used_blocks; i++) { if (ubi->fm->e[i]->pnum == pnum) return ubi->fm->e[i]; } } return NULL; } #endif /* !__UBI_UBI_H__ */ |
| 261 250 153 272 24 15 10 261 273 272 173 144 250 116 261 261 180 42 153 107 272 9 33 250 250 226 24 248 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/static_key.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> #include <net/netfilter/nft_meta.h> #ifdef CONFIG_MITIGATION_RETPOLINE static struct static_key_false nf_tables_skip_direct_calls; static inline bool nf_skip_indirect_calls(void) { return static_branch_likely(&nf_tables_skip_direct_calls); } static inline void __init nf_skip_indirect_calls_enable(void) { if (!cpu_feature_enabled(X86_FEATURE_RETPOLINE)) static_branch_enable(&nf_tables_skip_direct_calls); } #else static inline void nf_skip_indirect_calls_enable(void) { } #endif /* CONFIG_MITIGATION_RETPOLINE */ static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info, enum nft_trace_types type) { if (!info->trace || !info->nf_trace) return; info->type = type; nft_trace_notify(pkt, verdict, rule, info); } static inline void nft_trace_packet(const struct nft_pktinfo *pkt, struct nft_verdict *verdict, struct nft_traceinfo *info, const struct nft_rule_dp *rule, enum nft_trace_types type) { if (static_branch_unlikely(&nft_trace_enabled)) { info->nf_trace = pkt->skb->nf_trace; __nft_trace_packet(pkt, verdict, rule, info, type); } } static inline void nft_trace_copy_nftrace(const struct nft_pktinfo *pkt, struct nft_traceinfo *info) { if (static_branch_unlikely(&nft_trace_enabled)) info->nf_trace = pkt->skb->nf_trace; } static void nft_bitwise_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; *dst = (*src & priv->mask) ^ priv->xor; } static void nft_cmp_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); if (((regs->data[priv->sreg] & priv->mask) == priv->data) ^ priv->inv) return; regs->verdict.code = NFT_BREAK; } static void nft_cmp16_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); const u64 *reg_data = (const u64 *)®s->data[priv->sreg]; const u64 *mask = (const u64 *)&priv->mask; const u64 *data = (const u64 *)&priv->data; if (((reg_data[0] & mask[0]) == data[0] && ((reg_data[1] & mask[1]) == data[1])) ^ priv->inv) return; regs->verdict.code = NFT_BREAK; } static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, struct nft_traceinfo *info, const struct nft_rule_dp *rule, const struct nft_regs *regs) { enum nft_trace_types type; switch (regs->verdict.code & NF_VERDICT_MASK) { case NFT_CONTINUE: case NFT_RETURN: type = NFT_TRACETYPE_RETURN; break; case NF_STOLEN: type = NFT_TRACETYPE_RULE; /* can't access skb->nf_trace; use copy */ break; default: type = NFT_TRACETYPE_RULE; if (info->trace) info->nf_trace = pkt->skb->nf_trace; break; } __nft_trace_packet(pkt, ®s->verdict, rule, info, type); } static inline void nft_trace_verdict(const struct nft_pktinfo *pkt, struct nft_traceinfo *info, const struct nft_rule_dp *rule, const struct nft_regs *regs) { if (static_branch_unlikely(&nft_trace_enabled)) __nft_trace_verdict(pkt, info, rule, regs); } static bool nft_payload_fast_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; u32 *dest = ®s->data[priv->dreg]; unsigned char *ptr; if (priv->base == NFT_PAYLOAD_NETWORK_HEADER) ptr = skb_network_header(skb); else { if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; ptr = skb->data + nft_thoff(pkt); } ptr += priv->offset; if (unlikely(ptr + priv->len > skb_tail_pointer(skb))) return false; *dest = 0; if (priv->len == 2) *(u16 *)dest = *(u16 *)ptr; else if (priv->len == 4) *(u32 *)dest = *(u32 *)ptr; else *(u8 *)dest = *(u8 *)ptr; return true; } DEFINE_STATIC_KEY_FALSE(nft_counters_enabled); static noinline void nft_update_chain_stats(const struct nft_chain *chain, const struct nft_pktinfo *pkt) { struct nft_base_chain *base_chain; struct nft_stats __percpu *pstats; struct nft_stats *stats; base_chain = nft_base_chain(chain); pstats = READ_ONCE(base_chain->stats); if (pstats) { local_bh_disable(); stats = this_cpu_ptr(pstats); u64_stats_update_begin(&stats->syncp); stats->pkts++; stats->bytes += pkt->skb->len; u64_stats_update_end(&stats->syncp); local_bh_enable(); } } struct nft_jumpstack { const struct nft_rule_dp *rule; }; static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_pktinfo *pkt) { #ifdef CONFIG_MITIGATION_RETPOLINE unsigned long e; if (nf_skip_indirect_calls()) goto indirect_call; e = (unsigned long)expr->ops->eval; #define X(e, fun) \ do { if ((e) == (unsigned long)(fun)) \ return fun(expr, regs, pkt); } while (0) X(e, nft_payload_eval); X(e, nft_cmp_eval); X(e, nft_counter_eval); X(e, nft_meta_get_eval); X(e, nft_lookup_eval); #if IS_ENABLED(CONFIG_NFT_CT) X(e, nft_ct_get_fast_eval); #endif X(e, nft_range_eval); X(e, nft_immediate_eval); X(e, nft_byteorder_eval); X(e, nft_dynset_eval); X(e, nft_rt_get_eval); X(e, nft_bitwise_eval); X(e, nft_objref_eval); X(e, nft_objref_map_eval); #undef X indirect_call: #endif /* CONFIG_MITIGATION_RETPOLINE */ expr->ops->eval(expr, regs, pkt); } #define nft_rule_expr_first(rule) (struct nft_expr *)&rule->data[0] #define nft_rule_expr_next(expr) ((void *)expr) + expr->ops->size #define nft_rule_expr_last(rule) (struct nft_expr *)&rule->data[rule->dlen] #define nft_rule_dp_for_each_expr(expr, last, rule) \ for ((expr) = nft_rule_expr_first(rule), (last) = nft_rule_expr_last(rule); \ (expr) != (last); \ (expr) = nft_rule_expr_next(expr)) unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv) { const struct nft_chain *chain = priv, *basechain = chain; const struct net *net = nft_net(pkt); const struct nft_expr *expr, *last; const struct nft_rule_dp *rule; struct nft_regs regs; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); struct nft_rule_blob *blob; struct nft_traceinfo info; info.trace = false; if (static_branch_unlikely(&nft_trace_enabled)) nft_trace_init(&info, pkt, basechain); do_chain: if (genbit) blob = rcu_dereference(chain->blob_gen_1); else blob = rcu_dereference(chain->blob_gen_0); rule = (struct nft_rule_dp *)blob->data; next_rule: regs.verdict.code = NFT_CONTINUE; for (; !rule->is_last ; rule = nft_rule_next(rule)) { nft_rule_dp_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) nft_cmp_fast_eval(expr, ®s); else if (expr->ops == &nft_cmp16_fast_ops) nft_cmp16_fast_eval(expr, ®s); else if (expr->ops == &nft_bitwise_fast_ops) nft_bitwise_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || !nft_payload_fast_eval(expr, ®s, pkt)) expr_call_ops_eval(expr, ®s, pkt); if (regs.verdict.code != NFT_CONTINUE) break; } switch (regs.verdict.code) { case NFT_BREAK: regs.verdict.code = NFT_CONTINUE; nft_trace_copy_nftrace(pkt, &info); continue; case NFT_CONTINUE: nft_trace_packet(pkt, ®s.verdict, &info, rule, NFT_TRACETYPE_RULE); continue; } break; } nft_trace_verdict(pkt, &info, rule, ®s); switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_QUEUE: case NF_STOLEN: return regs.verdict.code; case NF_DROP: return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); } switch (regs.verdict.code) { case NFT_JUMP: if (WARN_ON_ONCE(stackptr >= NFT_JUMP_STACK_SIZE)) return NF_DROP; jumpstack[stackptr].rule = nft_rule_next(rule); stackptr++; fallthrough; case NFT_GOTO: chain = regs.verdict.chain; goto do_chain; case NFT_CONTINUE: case NFT_RETURN: break; default: WARN_ON_ONCE(1); } if (stackptr > 0) { stackptr--; rule = jumpstack[stackptr].rule; goto next_rule; } nft_trace_packet(pkt, ®s.verdict, &info, NULL, NFT_TRACETYPE_POLICY); if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); if (nft_base_chain(basechain)->policy == NF_DROP) return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); return nft_base_chain(basechain)->policy; } EXPORT_SYMBOL_GPL(nft_do_chain); static struct nft_expr_type *nft_basic_types[] = { &nft_imm_type, &nft_cmp_type, &nft_lookup_type, &nft_bitwise_type, &nft_byteorder_type, &nft_payload_type, &nft_dynset_type, &nft_range_type, &nft_meta_type, &nft_rt_type, &nft_exthdr_type, &nft_last_type, &nft_counter_type, &nft_objref_type, &nft_inner_type, }; static struct nft_object_type *nft_basic_objects[] = { #ifdef CONFIG_NETWORK_SECMARK &nft_secmark_obj_type, #endif &nft_counter_obj_type, }; int __init nf_tables_core_module_init(void) { int err, i, j = 0; nft_counter_init_seqcount(); for (i = 0; i < ARRAY_SIZE(nft_basic_objects); i++) { err = nft_register_obj(nft_basic_objects[i]); if (err) goto err; } for (j = 0; j < ARRAY_SIZE(nft_basic_types); j++) { err = nft_register_expr(nft_basic_types[j]); if (err) goto err; } nf_skip_indirect_calls_enable(); return 0; err: while (j-- > 0) nft_unregister_expr(nft_basic_types[j]); while (i-- > 0) nft_unregister_obj(nft_basic_objects[i]); return err; } void nf_tables_core_module_exit(void) { int i; i = ARRAY_SIZE(nft_basic_types); while (i-- > 0) nft_unregister_expr(nft_basic_types[i]); i = ARRAY_SIZE(nft_basic_objects); while (i-- > 0) nft_unregister_obj(nft_basic_objects[i]); } |
| 57 57 11 1 6 7 1 5 5 5 5 1 5 4 7 10 10 10 10 11 11 11 11 1 1 1 1 1 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/module.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfctrl.h> #include <net/caif/cfmuxl.h> #include <net/caif/cffrml.h> #include <net/caif/cfserl.h> #include <net/caif/cfsrvl.h> #include <net/caif/caif_dev.h> #define container_obj(layr) container_of(layr, struct cfcnfg, layer) /* Information about CAIF physical interfaces held by Config Module in order * to manage physical interfaces */ struct cfcnfg_phyinfo { struct list_head node; bool up; /* Pointer to the layer below the MUX (framing layer) */ struct cflayer *frm_layer; /* Pointer to the lowest actual physical layer */ struct cflayer *phy_layer; /* Unique identifier of the physical interface */ unsigned int id; /* Preference of the physical in interface */ enum cfcnfg_phy_preference pref; /* Information about the physical device */ struct dev_info dev_info; /* Interface index */ int ifindex; /* Protocol head room added for CAIF link layer */ int head_room; /* Use Start of frame checksum */ bool use_fcs; }; struct cfcnfg { struct cflayer layer; struct cflayer *ctrl; struct cflayer *mux; struct list_head phys; struct mutex lock; }; static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer); static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id); static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer); static void cfctrl_resp_func(void); static void cfctrl_enum_resp(void); struct cfcnfg *cfcnfg_create(void) { struct cfcnfg *this; struct cfctrl_rsp *resp; might_sleep(); /* Initiate this layer */ this = kzalloc(sizeof(struct cfcnfg), GFP_ATOMIC); if (!this) return NULL; this->mux = cfmuxl_create(); if (!this->mux) goto out_of_mem; this->ctrl = cfctrl_create(); if (!this->ctrl) goto out_of_mem; /* Initiate response functions */ resp = cfctrl_get_respfuncs(this->ctrl); resp->enum_rsp = cfctrl_enum_resp; resp->linkerror_ind = cfctrl_resp_func; resp->linkdestroy_rsp = cfcnfg_linkdestroy_rsp; resp->sleep_rsp = cfctrl_resp_func; resp->wake_rsp = cfctrl_resp_func; resp->restart_rsp = cfctrl_resp_func; resp->radioset_rsp = cfctrl_resp_func; resp->linksetup_rsp = cfcnfg_linkup_rsp; resp->reject_rsp = cfcnfg_reject_rsp; INIT_LIST_HEAD(&this->phys); cfmuxl_set_uplayer(this->mux, this->ctrl, 0); layer_set_dn(this->ctrl, this->mux); layer_set_up(this->ctrl, this); mutex_init(&this->lock); return this; out_of_mem: synchronize_rcu(); kfree(this->mux); kfree(this->ctrl); kfree(this); return NULL; } void cfcnfg_remove(struct cfcnfg *cfg) { might_sleep(); if (cfg) { synchronize_rcu(); kfree(cfg->mux); cfctrl_remove(cfg->ctrl); kfree(cfg); } } static void cfctrl_resp_func(void) { } static struct cfcnfg_phyinfo *cfcnfg_get_phyinfo_rcu(struct cfcnfg *cnfg, u8 phyid) { struct cfcnfg_phyinfo *phy; list_for_each_entry_rcu(phy, &cnfg->phys, node) if (phy->id == phyid) return phy; return NULL; } static void cfctrl_enum_resp(void) { } static struct dev_info *cfcnfg_get_phyid(struct cfcnfg *cnfg, enum cfcnfg_phy_preference phy_pref) { /* Try to match with specified preference */ struct cfcnfg_phyinfo *phy; list_for_each_entry_rcu(phy, &cnfg->phys, node) { if (phy->up && phy->pref == phy_pref && phy->frm_layer != NULL) return &phy->dev_info; } /* Otherwise just return something */ list_for_each_entry_rcu(phy, &cnfg->phys, node) if (phy->up) return &phy->dev_info; return NULL; } static int cfcnfg_get_id_from_ifi(struct cfcnfg *cnfg, int ifi) { struct cfcnfg_phyinfo *phy; list_for_each_entry_rcu(phy, &cnfg->phys, node) if (phy->ifindex == ifi && phy->up) return phy->id; return -ENODEV; } int caif_disconnect_client(struct net *net, struct cflayer *adap_layer) { u8 channel_id; struct cfcnfg *cfg = get_cfcnfg(net); caif_assert(adap_layer != NULL); cfctrl_cancel_req(cfg->ctrl, adap_layer); channel_id = adap_layer->id; if (channel_id != 0) { struct cflayer *servl; servl = cfmuxl_remove_uplayer(cfg->mux, channel_id); cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer); if (servl != NULL) layer_set_up(servl, NULL); } else pr_debug("nothing to disconnect\n"); /* Do RCU sync before initiating cleanup */ synchronize_rcu(); if (adap_layer->ctrlcmd != NULL) adap_layer->ctrlcmd(adap_layer, CAIF_CTRLCMD_DEINIT_RSP, 0); return 0; } EXPORT_SYMBOL(caif_disconnect_client); static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id) { } static const int protohead[CFCTRL_SRV_MASK] = { [CFCTRL_SRV_VEI] = 4, [CFCTRL_SRV_DATAGRAM] = 7, [CFCTRL_SRV_UTIL] = 4, [CFCTRL_SRV_RFM] = 3, [CFCTRL_SRV_DBG] = 3, }; static int caif_connect_req_to_link_param(struct cfcnfg *cnfg, struct caif_connect_request *s, struct cfctrl_link_param *l) { struct dev_info *dev_info; enum cfcnfg_phy_preference pref; int res; memset(l, 0, sizeof(*l)); /* In caif protocol low value is high priority */ l->priority = CAIF_PRIO_MAX - s->priority + 1; if (s->ifindex != 0) { res = cfcnfg_get_id_from_ifi(cnfg, s->ifindex); if (res < 0) return res; l->phyid = res; } else { switch (s->link_selector) { case CAIF_LINK_HIGH_BANDW: pref = CFPHYPREF_HIGH_BW; break; case CAIF_LINK_LOW_LATENCY: pref = CFPHYPREF_LOW_LAT; break; default: return -EINVAL; } dev_info = cfcnfg_get_phyid(cnfg, pref); if (dev_info == NULL) return -ENODEV; l->phyid = dev_info->id; } switch (s->protocol) { case CAIFPROTO_AT: l->linktype = CFCTRL_SRV_VEI; l->endpoint = (s->sockaddr.u.at.type >> 2) & 0x3; l->chtype = s->sockaddr.u.at.type & 0x3; break; case CAIFPROTO_DATAGRAM: l->linktype = CFCTRL_SRV_DATAGRAM; l->chtype = 0x00; l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; break; case CAIFPROTO_DATAGRAM_LOOP: l->linktype = CFCTRL_SRV_DATAGRAM; l->chtype = 0x03; l->endpoint = 0x00; l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; break; case CAIFPROTO_RFM: l->linktype = CFCTRL_SRV_RFM; l->u.datagram.connid = s->sockaddr.u.rfm.connection_id; strscpy(l->u.rfm.volume, s->sockaddr.u.rfm.volume, sizeof(l->u.rfm.volume)); break; case CAIFPROTO_UTIL: l->linktype = CFCTRL_SRV_UTIL; l->endpoint = 0x00; l->chtype = 0x00; strscpy(l->u.utility.name, s->sockaddr.u.util.service, sizeof(l->u.utility.name)); caif_assert(sizeof(l->u.utility.name) > 10); l->u.utility.paramlen = s->param.size; if (l->u.utility.paramlen > sizeof(l->u.utility.params)) l->u.utility.paramlen = sizeof(l->u.utility.params); memcpy(l->u.utility.params, s->param.data, l->u.utility.paramlen); break; case CAIFPROTO_DEBUG: l->linktype = CFCTRL_SRV_DBG; l->endpoint = s->sockaddr.u.dbg.service; l->chtype = s->sockaddr.u.dbg.type; break; default: return -EINVAL; } return 0; } int caif_connect_client(struct net *net, struct caif_connect_request *conn_req, struct cflayer *adap_layer, int *ifindex, int *proto_head, int *proto_tail) { struct cflayer *frml; struct cfcnfg_phyinfo *phy; int err; struct cfctrl_link_param param; struct cfcnfg *cfg = get_cfcnfg(net); rcu_read_lock(); err = caif_connect_req_to_link_param(cfg, conn_req, ¶m); if (err) goto unlock; phy = cfcnfg_get_phyinfo_rcu(cfg, param.phyid); if (!phy) { err = -ENODEV; goto unlock; } err = -EINVAL; if (adap_layer == NULL) { pr_err("adap_layer is zero\n"); goto unlock; } if (adap_layer->receive == NULL) { pr_err("adap_layer->receive is NULL\n"); goto unlock; } if (adap_layer->ctrlcmd == NULL) { pr_err("adap_layer->ctrlcmd == NULL\n"); goto unlock; } err = -ENODEV; frml = phy->frm_layer; if (frml == NULL) { pr_err("Specified PHY type does not exist!\n"); goto unlock; } caif_assert(param.phyid == phy->id); caif_assert(phy->frm_layer->id == param.phyid); caif_assert(phy->phy_layer->id == param.phyid); *ifindex = phy->ifindex; *proto_tail = 2; *proto_head = protohead[param.linktype] + phy->head_room; rcu_read_unlock(); /* FIXME: ENUMERATE INITIALLY WHEN ACTIVATING PHYSICAL INTERFACE */ cfctrl_enum_req(cfg->ctrl, param.phyid); return cfctrl_linkup_request(cfg->ctrl, ¶m, adap_layer); unlock: rcu_read_unlock(); return err; } EXPORT_SYMBOL(caif_connect_client); static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer) { if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL) adapt_layer->ctrlcmd(adapt_layer, CAIF_CTRLCMD_INIT_FAIL_RSP, 0); } static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer) { struct cfcnfg *cnfg = container_obj(layer); struct cflayer *servicel = NULL; struct cfcnfg_phyinfo *phyinfo; struct net_device *netdev; if (channel_id == 0) { pr_warn("received channel_id zero\n"); if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL) adapt_layer->ctrlcmd(adapt_layer, CAIF_CTRLCMD_INIT_FAIL_RSP, 0); return; } rcu_read_lock(); if (adapt_layer == NULL) { pr_debug("link setup response but no client exist, send linkdown back\n"); cfctrl_linkdown_req(cnfg->ctrl, channel_id, NULL); goto unlock; } caif_assert(cnfg != NULL); caif_assert(phyid != 0); phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phyid); if (phyinfo == NULL) { pr_err("ERROR: Link Layer Device disappeared while connecting\n"); goto unlock; } caif_assert(phyinfo != NULL); caif_assert(phyinfo->id == phyid); caif_assert(phyinfo->phy_layer != NULL); caif_assert(phyinfo->phy_layer->id == phyid); adapt_layer->id = channel_id; switch (serv) { case CFCTRL_SRV_VEI: servicel = cfvei_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DATAGRAM: servicel = cfdgml_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_RFM: netdev = phyinfo->dev_info.dev; servicel = cfrfml_create(channel_id, &phyinfo->dev_info, netdev->mtu); break; case CFCTRL_SRV_UTIL: servicel = cfutill_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_VIDEO: servicel = cfvidl_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DBG: servicel = cfdbgl_create(channel_id, &phyinfo->dev_info); break; default: pr_err("Protocol error. Link setup response - unknown channel type\n"); goto unlock; } if (!servicel) goto unlock; layer_set_dn(servicel, cnfg->mux); cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id); layer_set_up(servicel, adapt_layer); layer_set_dn(adapt_layer, servicel); rcu_read_unlock(); servicel->ctrlcmd(servicel, CAIF_CTRLCMD_INIT_RSP, 0); return; unlock: rcu_read_unlock(); } int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, struct cflayer *link_support, bool fcs, int head_room) { struct cflayer *frml; struct cfcnfg_phyinfo *phyinfo = NULL; int i, res = 0; u8 phyid; mutex_lock(&cnfg->lock); /* CAIF protocol allow maximum 6 link-layers */ for (i = 0; i < 7; i++) { phyid = (dev->ifindex + i) & 0x7; if (phyid == 0) continue; if (cfcnfg_get_phyinfo_rcu(cnfg, phyid) == NULL) goto got_phyid; } pr_warn("Too many CAIF Link Layers (max 6)\n"); res = -EEXIST; goto out; got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); if (!phyinfo) { res = -ENOMEM; goto out; } phy_layer->id = phyid; phyinfo->pref = pref; phyinfo->id = phyid; phyinfo->dev_info.id = phyid; phyinfo->dev_info.dev = dev; phyinfo->phy_layer = phy_layer; phyinfo->ifindex = dev->ifindex; phyinfo->head_room = head_room; phyinfo->use_fcs = fcs; frml = cffrml_create(phyid, fcs); if (!frml) { res = -ENOMEM; goto out_err; } phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux); if (link_support != NULL) { link_support->id = phyid; layer_set_dn(frml, link_support); layer_set_up(link_support, frml); layer_set_dn(link_support, phy_layer); layer_set_up(phy_layer, link_support); } else { layer_set_dn(frml, phy_layer); layer_set_up(phy_layer, frml); } list_add_rcu(&phyinfo->node, &cnfg->phys); out: mutex_unlock(&cnfg->lock); return res; out_err: kfree(phyinfo); mutex_unlock(&cnfg->lock); return res; } EXPORT_SYMBOL(cfcnfg_add_phy_layer); int cfcnfg_set_phy_state(struct cfcnfg *cnfg, struct cflayer *phy_layer, bool up) { struct cfcnfg_phyinfo *phyinfo; rcu_read_lock(); phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phy_layer->id); if (phyinfo == NULL) { rcu_read_unlock(); return -ENODEV; } if (phyinfo->up == up) { rcu_read_unlock(); return 0; } phyinfo->up = up; if (up) { cffrml_hold(phyinfo->frm_layer); cfmuxl_set_dnlayer(cnfg->mux, phyinfo->frm_layer, phy_layer->id); } else { cfmuxl_remove_dnlayer(cnfg->mux, phy_layer->id); cffrml_put(phyinfo->frm_layer); } rcu_read_unlock(); return 0; } EXPORT_SYMBOL(cfcnfg_set_phy_state); int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer) { struct cflayer *frml, *frml_dn; u16 phyid; struct cfcnfg_phyinfo *phyinfo; might_sleep(); mutex_lock(&cnfg->lock); phyid = phy_layer->id; phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phyid); if (phyinfo == NULL) { mutex_unlock(&cnfg->lock); return 0; } caif_assert(phyid == phyinfo->id); caif_assert(phy_layer == phyinfo->phy_layer); caif_assert(phy_layer->id == phyid); caif_assert(phyinfo->frm_layer->id == phyid); list_del_rcu(&phyinfo->node); synchronize_rcu(); /* Fail if reference count is not zero */ if (cffrml_refcnt_read(phyinfo->frm_layer) != 0) { pr_info("Wait for device inuse\n"); list_add_rcu(&phyinfo->node, &cnfg->phys); mutex_unlock(&cnfg->lock); return -EAGAIN; } frml = phyinfo->frm_layer; frml_dn = frml->dn; cffrml_set_uplayer(frml, NULL); cffrml_set_dnlayer(frml, NULL); if (phy_layer != frml_dn) { layer_set_up(frml_dn, NULL); layer_set_dn(frml_dn, NULL); } layer_set_up(phy_layer, NULL); if (phyinfo->phy_layer != frml_dn) kfree(frml_dn); cffrml_free(frml); kfree(phyinfo); mutex_unlock(&cnfg->lock); return 0; } EXPORT_SYMBOL(cfcnfg_del_phy_layer); |
| 1 15 15 14 15 1 21 15 7 8 1 7 5 2 5 2 5 2 5 2 5 2 7 7 8 1 6 6 6 6 4 4 | 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 OR BSD-3-Clause /* * Codel - The Controlled-Delay Active Queue Management algorithm * * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> * * Implemented on linux by : * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/prefetch.h> #include <net/pkt_sched.h> #include <net/codel.h> #include <net/codel_impl.h> #include <net/codel_qdisc.h> #define DEFAULT_CODEL_LIMIT 1000 struct codel_sched_data { struct codel_params params; struct codel_vars vars; struct codel_stats stats; u32 drop_overlimit; }; /* This is the specific function called from codel_dequeue() * to dequeue a packet from queue. Note: backlog is handled in * codel, we dont need to reduce it here. */ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) { struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); prefetch(&skb->end); /* we'll need skb_shinfo() */ } return skb; } static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) { struct codel_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; skb = codel_dequeue(sch, &sch->qstats.backlog, &q->params, &q->vars, &q->stats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); if (q->stats.drop_count) { qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; q->stats.drop_len = 0; } if (skb) qdisc_bstats_update(sch, skb); return skb; } static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct codel_sched_data *q; if (likely(qdisc_qlen(sch) < sch->limit)) { codel_set_enqueue_time(skb); return qdisc_enqueue_tail(skb, sch); } q = qdisc_priv(sch); q->drop_overlimit++; return qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); } static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { [TCA_CODEL_TARGET] = { .type = NLA_U32 }, [TCA_CODEL_LIMIT] = { .type = NLA_U32 }, [TCA_CODEL_INTERVAL] = { .type = NLA_U32 }, [TCA_CODEL_ECN] = { .type = NLA_U32 }, [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 }, }; static int codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, codel_policy, NULL); if (err < 0) return err; sch_tree_lock(sch); if (tb[TCA_CODEL_TARGET]) { u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]); WRITE_ONCE(q->params.target, ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]); WRITE_ONCE(q->params.ce_threshold, (val * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_INTERVAL]) { u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); WRITE_ONCE(q->params.interval, ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_LIMIT]) WRITE_ONCE(sch->limit, nla_get_u32(tb[TCA_CODEL_LIMIT])); if (tb[TCA_CODEL_ECN]) WRITE_ONCE(q->params.ecn, !!nla_get_u32(tb[TCA_CODEL_ECN])); qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); rtnl_qdisc_drop(skb, sch); } qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; } static int codel_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct codel_sched_data *q = qdisc_priv(sch); sch->limit = DEFAULT_CODEL_LIMIT; codel_params_init(&q->params); codel_vars_init(&q->vars); codel_stats_init(&q->stats); q->params.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { int err = codel_change(sch, opt, extack); if (err) return err; } if (sch->limit >= 1) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct codel_sched_data *q = qdisc_priv(sch); codel_time_t ce_threshold; struct nlattr *opts; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put_u32(skb, TCA_CODEL_TARGET, codel_time_to_us(READ_ONCE(q->params.target))) || nla_put_u32(skb, TCA_CODEL_LIMIT, READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_CODEL_INTERVAL, codel_time_to_us(READ_ONCE(q->params.interval))) || nla_put_u32(skb, TCA_CODEL_ECN, READ_ONCE(q->params.ecn))) goto nla_put_failure; ce_threshold = READ_ONCE(q->params.ce_threshold); if (ce_threshold != CODEL_DISABLED_THRESHOLD && nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD, codel_time_to_us(ce_threshold))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -1; } static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { const struct codel_sched_data *q = qdisc_priv(sch); struct tc_codel_xstats st = { .maxpacket = q->stats.maxpacket, .count = q->vars.count, .lastcount = q->vars.lastcount, .drop_overlimit = q->drop_overlimit, .ldelay = codel_time_to_us(q->vars.ldelay), .dropping = q->vars.dropping, .ecn_mark = q->stats.ecn_mark, .ce_mark = q->stats.ce_mark, }; if (q->vars.dropping) { codel_tdiff_t delta = q->vars.drop_next - codel_get_time(); if (delta >= 0) st.drop_next = codel_time_to_us(delta); else st.drop_next = -codel_time_to_us(-delta); } return gnet_stats_copy_app(d, &st, sizeof(st)); } static void codel_reset(struct Qdisc *sch) { struct codel_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); codel_vars_init(&q->vars); } static struct Qdisc_ops codel_qdisc_ops __read_mostly = { .id = "codel", .priv_size = sizeof(struct codel_sched_data), .enqueue = codel_qdisc_enqueue, .dequeue = codel_qdisc_dequeue, .peek = qdisc_peek_dequeued, .init = codel_init, .reset = codel_reset, .change = codel_change, .dump = codel_dump, .dump_stats = codel_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("codel"); static int __init codel_module_init(void) { return register_qdisc(&codel_qdisc_ops); } static void __exit codel_module_exit(void) { unregister_qdisc(&codel_qdisc_ops); } module_init(codel_module_init) module_exit(codel_module_exit) MODULE_DESCRIPTION("Controlled Delay queue discipline"); MODULE_AUTHOR("Dave Taht"); MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("Dual BSD/GPL"); |
| 12 12 12 10 2 12 1 1 6 3 1 2 3 1 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor /proc/<pid>/attr/ interface functions * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #include "include/apparmor.h" #include "include/cred.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/domain.h" #include "include/procattr.h" /** * aa_getprocattr - Return the label information for @label * @label: the label to print label info about (NOT NULL) * @string: Returns - string containing the label info (NOT NULL) * @newline: indicates that a newline should be added * * Requires: label != NULL && string != NULL * * Creates a string containing the label information for @label. * * Returns: size of string placed in @string else error code on failure */ int aa_getprocattr(struct aa_label *label, char **string, bool newline) { struct aa_ns *ns = labels_ns(label); struct aa_ns *current_ns = aa_get_current_ns(); int len; if (!aa_ns_visible(current_ns, ns, true)) { aa_put_ns(current_ns); return -EACCES; } len = aa_label_snxprint(NULL, 0, current_ns, label, FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED); AA_BUG(len < 0); *string = kmalloc(len + 2, GFP_KERNEL); if (!*string) { aa_put_ns(current_ns); return -ENOMEM; } len = aa_label_snxprint(*string, len + 2, current_ns, label, FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED); if (len < 0) { aa_put_ns(current_ns); return len; } if (newline) (*string)[len++] = '\n'; (*string)[len] = 0; aa_put_ns(current_ns); return len; } /** * split_token_from_name - separate a string of form <token>^<name> * @op: operation being checked * @args: string to parse (NOT NULL) * @token: stores returned parsed token value (NOT NULL) * * Returns: start position of name after token else NULL on failure */ static char *split_token_from_name(const char *op, char *args, u64 *token) { char *name; *token = simple_strtoull(args, &name, 16); if ((name == args) || *name != '^') { AA_ERROR("%s: Invalid input '%s'", op, args); return ERR_PTR(-EINVAL); } name++; /* skip ^ */ if (!*name) name = NULL; return name; } /** * aa_setprocattr_changehat - handle procattr interface to change_hat * @args: args received from writing to /proc/<pid>/attr/current (NOT NULL) * @size: size of the args * @flags: set of flags governing behavior * * Returns: %0 or error code if change_hat fails */ int aa_setprocattr_changehat(char *args, size_t size, int flags) { char *hat; u64 token; const char *hats[16]; /* current hard limit on # of names */ int count = 0; hat = split_token_from_name(OP_CHANGE_HAT, args, &token); if (IS_ERR(hat)) return PTR_ERR(hat); if (!hat && !token) { AA_ERROR("change_hat: Invalid input, NULL hat and NULL magic"); return -EINVAL; } if (hat) { /* set up hat name vector, args guaranteed null terminated * at args[size] by setprocattr. * * If there are multiple hat names in the buffer each is * separated by a \0. Ie. userspace writes them pre tokenized */ char *end = args + size; for (count = 0; (hat < end) && count < 16; ++count) { char *next = hat + strlen(hat) + 1; hats[count] = hat; AA_DEBUG(DEBUG_DOMAIN, "%s: (pid %d) Magic 0x%llx count %d hat '%s'\n" , __func__, current->pid, token, count, hat); hat = next; } } else AA_DEBUG(DEBUG_DOMAIN, "%s: (pid %d) Magic 0x%llx count %d Hat '%s'\n", __func__, current->pid, token, count, "<NULL>"); return aa_change_hat(hats, count, token, flags); } |
| 4 4 2477 461 461 3861 461 460 3864 867 867 101 101 461 21 2628 2644 2647 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> #include "internal.h" static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* * User space expects anonymous inodes to have no file type in st_mode. * * In particular, 'lsof' has this legacy logic: * * type = s->st_mode & S_IFMT; * switch (type) { * ... * case 0: * if (!strcmp(p, "anon_inode")) * Lf->ntype = Ntype = N_ANON_INODE; * * to detect our old anon_inode logic. * * Rather than mess with our internal sane inode data, just fix it * up here in getattr() by masking off the format bits. */ int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->mode &= ~S_IFMT; return 0; } int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EOPNOTSUPP; } static const struct inode_operations anon_inode_operations = { .getattr = anon_inode_getattr, .setattr = anon_inode_setattr, }; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; fc->s_iflags |= SB_I_NOEXEC; fc->s_iflags |= SB_I_NODEV; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *anon_inode_make_secure_inode( const char *name, const struct inode *context_inode) { struct inode *inode; int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; inode->i_op = &anon_inode_operations; error = security_inode_init_security_anon(inode, &QSTR(name), context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (make_inode) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @f_mode: [in] fmode * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Allows setting the fmode. Returns the newly created file* or an error * pointer. */ struct file *anon_inode_getfile_fmode(const char *name, const struct file_operations *fops, void *priv, int flags, fmode_t f_mode) { struct file *file; file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); if (!IS_ERR(file)) file->f_mode |= f_mode; return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); /** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns the newly created file* or an error pointer. */ struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, make_inode); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns a newly created file descriptor or an error code. */ int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); anon_inode_inode->i_op = &anon_inode_operations; return 0; } fs_initcall(anon_inode_init); |
| 88 88 33 58 11 10 79 82 9 9 43 43 3 18 18 31 13 13 8 5 3 15 9 6 20 2 2 1 8 2 6 5 6 7 1 12 1 10 1 113 11 103 103 15 19 92 29 1 1 27 1 14 15 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/eventfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #include <linux/file.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/kref.h> #include <linux/eventfd.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/idr.h> #include <linux/uio.h> static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { struct kref kref; wait_queue_head_t wqh; /* * Every time that a write(2) is performed on an eventfd, the * value of the __u64 being written is added to "count" and a * wakeup is performed on "wqh". If EFD_SEMAPHORE flag was not * specified, a read(2) will return the "count" value to userspace, * and will reset "count" to zero. The kernel side eventfd_signal() * also, adds to the "count" counter and issue a wakeup. */ __u64 count; unsigned int flags; int id; }; /** * eventfd_signal_mask - Increment the event counter * @ctx: [in] Pointer to the eventfd context. * @mask: [in] poll mask * * This function is supposed to be called by the kernel in paths that do not * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX * value, and we signal this as overflow condition by returning a EPOLLERR * to poll(2). */ void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask) { unsigned long flags; /* * Deadlock or stack overflow issues can happen if we recurse here * through waitqueue wakeup handlers. If the caller users potentially * nested waitqueues with custom wakeup handlers, then it should * check eventfd_signal_allowed() before calling this function. If * it returns false, the eventfd_signal() call should be deferred to a * safe context. */ if (WARN_ON_ONCE(current->in_eventfd)) return; spin_lock_irqsave(&ctx->wqh.lock, flags); current->in_eventfd = 1; if (ctx->count < ULLONG_MAX) ctx->count++; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask); current->in_eventfd = 0; spin_unlock_irqrestore(&ctx->wqh.lock, flags); } EXPORT_SYMBOL_GPL(eventfd_signal_mask); static void eventfd_free_ctx(struct eventfd_ctx *ctx) { if (ctx->id >= 0) ida_free(&eventfd_ida, ctx->id); kfree(ctx); } static void eventfd_free(struct kref *kref) { struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref); eventfd_free_ctx(ctx); } /** * eventfd_ctx_put - Releases a reference to the internal eventfd context. * @ctx: [in] Pointer to eventfd context. * * The eventfd context reference must have been previously acquired either * with eventfd_ctx_fdget() or eventfd_ctx_fileget(). */ void eventfd_ctx_put(struct eventfd_ctx *ctx) { kref_put(&ctx->kref, eventfd_free); } EXPORT_SYMBOL_GPL(eventfd_ctx_put); static int eventfd_release(struct inode *inode, struct file *file) { struct eventfd_ctx *ctx = file->private_data; wake_up_poll(&ctx->wqh, EPOLLHUP); eventfd_ctx_put(ctx); return 0; } static __poll_t eventfd_poll(struct file *file, poll_table *wait) { struct eventfd_ctx *ctx = file->private_data; __poll_t events = 0; u64 count; poll_wait(file, &ctx->wqh, wait); /* * All writes to ctx->count occur within ctx->wqh.lock. This read * can be done outside ctx->wqh.lock because we know that poll_wait * takes that lock (through add_wait_queue) if our caller will sleep. * * The read _can_ therefore seep into add_wait_queue's critical * section, but cannot move above it! add_wait_queue's spin_lock acts * as an acquire barrier and ensures that the read be ordered properly * against the writes. The following CAN happen and is safe: * * poll write * ----------------- ------------ * lock ctx->wqh.lock (in poll_wait) * count = ctx->count * __add_wait_queue * unlock ctx->wqh.lock * lock ctx->qwh.lock * ctx->count += n * if (waitqueue_active) * wake_up_locked_poll * unlock ctx->qwh.lock * eventfd_poll returns 0 * * but the following, which would miss a wakeup, cannot happen: * * poll write * ----------------- ------------ * count = ctx->count (INVALID!) * lock ctx->qwh.lock * ctx->count += n * **waitqueue_active is false** * **no wake_up_locked_poll!** * unlock ctx->qwh.lock * lock ctx->wqh.lock (in poll_wait) * __add_wait_queue * unlock ctx->wqh.lock * eventfd_poll returns 0 */ count = READ_ONCE(ctx->count); if (count > 0) events |= EPOLLIN; if (count == ULLONG_MAX) events |= EPOLLERR; if (ULLONG_MAX - 1 > count) events |= EPOLLOUT; return events; } void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { lockdep_assert_held(&ctx->wqh.lock); *cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count; ctx->count -= *cnt; } EXPORT_SYMBOL_GPL(eventfd_ctx_do_read); /** * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. * @ctx: [in] Pointer to eventfd context. * @wait: [in] Wait queue to be removed. * @cnt: [out] Pointer to the 64-bit counter value. * * Returns %0 if successful, or the following error codes: * * -EAGAIN : The operation would have blocked. * * This is used to atomically remove a wait queue entry from the eventfd wait * queue head, and read/reset the counter value. */ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt) { unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); eventfd_ctx_do_read(ctx, cnt); __remove_wait_queue(&ctx->wqh, wait); if (*cnt != 0 && waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLOUT); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return *cnt != 0 ? 0 : -EAGAIN; } EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue); static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct eventfd_ctx *ctx = file->private_data; __u64 ucnt = 0; if (iov_iter_count(to) < sizeof(ucnt)) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); if (!ctx->count) { if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { spin_unlock_irq(&ctx->wqh.lock); return -EAGAIN; } if (wait_event_interruptible_locked_irq(ctx->wqh, ctx->count)) { spin_unlock_irq(&ctx->wqh.lock); return -ERESTARTSYS; } } eventfd_ctx_do_read(ctx, &ucnt); current->in_eventfd = 1; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLOUT); current->in_eventfd = 0; spin_unlock_irq(&ctx->wqh.lock); if (unlikely(copy_to_iter(&ucnt, sizeof(ucnt), to) != sizeof(ucnt))) return -EFAULT; return sizeof(ucnt); } static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct eventfd_ctx *ctx = file->private_data; ssize_t res; __u64 ucnt; if (count != sizeof(ucnt)) return -EINVAL; if (copy_from_user(&ucnt, buf, sizeof(ucnt))) return -EFAULT; if (ucnt == ULLONG_MAX) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); res = -EAGAIN; if (ULLONG_MAX - ctx->count > ucnt) res = sizeof(ucnt); else if (!(file->f_flags & O_NONBLOCK)) { res = wait_event_interruptible_locked_irq(ctx->wqh, ULLONG_MAX - ctx->count > ucnt); if (!res) res = sizeof(ucnt); } if (likely(res > 0)) { ctx->count += ucnt; current->in_eventfd = 1; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); current->in_eventfd = 0; } spin_unlock_irq(&ctx->wqh.lock); return res; } #ifdef CONFIG_PROC_FS static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) { struct eventfd_ctx *ctx = f->private_data; __u64 cnt; spin_lock_irq(&ctx->wqh.lock); cnt = ctx->count; spin_unlock_irq(&ctx->wqh.lock); seq_printf(m, "eventfd-count: %16llx\n" "eventfd-id: %d\n" "eventfd-semaphore: %d\n", cnt, ctx->id, !!(ctx->flags & EFD_SEMAPHORE)); } #endif static const struct file_operations eventfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = eventfd_show_fdinfo, #endif .release = eventfd_release, .poll = eventfd_poll, .read_iter = eventfd_read, .write = eventfd_write, .llseek = noop_llseek, }; /** * eventfd_fget - Acquire a reference of an eventfd file descriptor. * @fd: [in] Eventfd file descriptor. * * Returns a pointer to the eventfd file structure in case of success, or the * following error pointer: * * -EBADF : Invalid @fd file descriptor. * -EINVAL : The @fd file descriptor is not an eventfd file. */ struct file *eventfd_fget(int fd) { struct file *file; file = fget(fd); if (!file) return ERR_PTR(-EBADF); if (file->f_op != &eventfd_fops) { fput(file); return ERR_PTR(-EINVAL); } return file; } EXPORT_SYMBOL_GPL(eventfd_fget); /** * eventfd_ctx_fdget - Acquires a reference to the internal eventfd context. * @fd: [in] Eventfd file descriptor. * * Returns a pointer to the internal eventfd context, otherwise the error * pointers returned by the following functions: * * eventfd_fget */ struct eventfd_ctx *eventfd_ctx_fdget(int fd) { CLASS(fd, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF); return eventfd_ctx_fileget(fd_file(f)); } EXPORT_SYMBOL_GPL(eventfd_ctx_fdget); /** * eventfd_ctx_fileget - Acquires a reference to the internal eventfd context. * @file: [in] Eventfd file pointer. * * Returns a pointer to the internal eventfd context, otherwise the error * pointer: * * -EINVAL : The @fd file descriptor is not an eventfd file. */ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file) { struct eventfd_ctx *ctx; if (file->f_op != &eventfd_fops) return ERR_PTR(-EINVAL); ctx = file->private_data; kref_get(&ctx->kref); return ctx; } EXPORT_SYMBOL_GPL(eventfd_ctx_fileget); static int do_eventfd(unsigned int count, int flags) { struct eventfd_ctx *ctx; struct file *file; int fd; /* Check the EFD_* constants for consistency. */ BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK); BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0)); if (flags & ~EFD_FLAGS_SET) return -EINVAL; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; kref_init(&ctx->kref); init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL); flags &= EFD_SHARED_FCNTL_FLAGS; flags |= O_RDWR; fd = get_unused_fd_flags(flags); if (fd < 0) goto err; file = anon_inode_getfile_fmode("[eventfd]", &eventfd_fops, ctx, flags, FMODE_NOWAIT); if (IS_ERR(file)) { put_unused_fd(fd); fd = PTR_ERR(file); goto err; } fd_install(fd, file); return fd; err: eventfd_free_ctx(ctx); return fd; } SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) { return do_eventfd(count, flags); } SYSCALL_DEFINE1(eventfd, unsigned int, count) { return do_eventfd(count, 0); } |
| 2 2 1 1 3 39 39 38 35 35 35 288 288 7 7 7 7 7 34 27 6 1 6 1 7 34 7 27 41 7 34 32 4 33 1 34 34 34 35 1 34 39 12 4 6 2 1 4 56 3 56 3 59 59 21 43 45 39 32 5 3 5 39 39 39 39 4 39 39 27 27 5 5 11 11 19 19 45 44 45 45 45 45 45 45 7 7 7 13 4 9 12 12 12 12 12 9 3 11 16 3 1 12 12 12 55 3 52 4 46 2 1 44 1 43 1 18 16 1 1 11 11 1 1 1 16 16 2 1 14 1 13 14 14 14 10 10 4 8 1 8 5 3 8 8 1 10 6 6 36 2 28 6 29 5 3 3 1 1 1 5 29 3 28 29 5 23 3 24 23 3 6 1 3 2 2 1 1 3 1 1 1 1 1 1 1 207 1 2 203 193 25 34 169 94 64 4 9 1 1 2 2 3 49 5 44 19 1 1 2 1 2 1 3 1 2 5 3 3 2 2 9 39 32 1 1 30 32 57 57 57 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 | // SPDX-License-Identifier: GPL-2.0-only /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * AF_SMC protocol family socket handler keeping the AF_INET sock address type * applies to SOCK_STREAM sockets only * offers an alternative communication option for TCP-protocol sockets * applicable with RoCE-cards only * * Initial restrictions: * - support for alternate links postponed * * Copyright IBM Corp. 2016, 2018 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> * based on prototype from Frank Blaschka */ #define KMSG_COMPONENT "smc" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/socket.h> #include <linux/workqueue.h> #include <linux/in.h> #include <linux/sched/signal.h> #include <linux/if_vlan.h> #include <linux/rcupdate_wait.h> #include <linux/ctype.h> #include <linux/splice.h> #include <net/sock.h> #include <net/tcp.h> #include <net/smc.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc.h" #include "smc_clc.h" #include "smc_llc.h" #include "smc_cdc.h" #include "smc_core.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_pnet.h" #include "smc_netlink.h" #include "smc_tx.h" #include "smc_rx.h" #include "smc_close.h" #include "smc_stats.h" #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_loopback.h" #include "smc_inet.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server */ static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group * creation on client */ static struct workqueue_struct *smc_tcp_ls_wq; /* wq for tcp listen work */ struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ struct workqueue_struct *smc_close_wq; /* wq for close work */ static void smc_tcp_listen_work(struct work_struct *); static void smc_connect_work(struct work_struct *); int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); void *hdr; if (cb_ctx->pos[0]) goto out; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_DUMP_HS_LIMITATION); if (!hdr) return -ENOMEM; if (nla_put_u8(skb, SMC_NLA_HS_LIMITATION_ENABLED, sock_net(skb->sk)->smc.limit_smc_hs)) goto err; genlmsg_end(skb, hdr); cb_ctx->pos[0] = 1; out: return skb->len; err: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info) { sock_net(skb->sk)->smc.limit_smc_hs = true; return 0; } int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info) { sock_net(skb->sk)->smc.limit_smc_hs = false; return 0; } static void smc_set_keepalive(struct sock *sk, int val) { struct smc_sock *smc = smc_sk(sk); smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val); } static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct smc_sock *smc; struct sock *child; smc = smc_clcsock_user_data(sk); if (READ_ONCE(sk->sk_ack_backlog) + atomic_read(&smc->queued_smc_hs) > sk->sk_max_ack_backlog) goto drop; if (sk_acceptq_is_full(&smc->sk)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; } /* passthrough to original syn recv sock fct */ child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, own_req); /* child must not inherit smc or its ops */ if (child) { rcu_assign_sk_user_data(child, NULL); /* v4-mapped sockets don't inherit parent ops. Don't restore. */ if (inet_csk(child)->icsk_af_ops == inet_csk(sk)->icsk_af_ops) inet_csk(child)->icsk_af_ops = smc->ori_af_ops; } return child; drop: dst_release(dst); tcp_listendrop(sk); return NULL; } static bool smc_hs_congested(const struct sock *sk) { const struct smc_sock *smc; smc = smc_clcsock_user_data(sk); if (!smc) return true; if (workqueue_congested(WORK_CPU_UNBOUND, smc_hs_wq)) return true; return false; } struct smc_hashinfo smc_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; struct smc_hashinfo smc_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock), }; int smc_hash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; struct hlist_head *head; head = &h->ht; write_lock_bh(&h->lock); sk_add_node(sk, head); write_unlock_bh(&h->lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); return 0; } void smc_unhash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; write_lock_bh(&h->lock); if (sk_del_node_init(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); write_unlock_bh(&h->lock); } /* This will be called before user really release sock_lock. So do the * work which we didn't do because of user hold the sock_lock in the * BH context */ void smc_release_cb(struct sock *sk) { struct smc_sock *smc = smc_sk(sk); if (smc->conn.tx_in_release_sock) { smc_tx_pending(&smc->conn); smc->conn.tx_in_release_sock = false; } } struct proto smc_proto = { .name = "SMC", .owner = THIS_MODULE, .keepalive = smc_set_keepalive, .hash = smc_hash_sk, .unhash = smc_unhash_sk, .release_cb = smc_release_cb, .obj_size = sizeof(struct smc_sock), .h.smc_hash = &smc_v4_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, }; EXPORT_SYMBOL_GPL(smc_proto); struct proto smc_proto6 = { .name = "SMC6", .owner = THIS_MODULE, .keepalive = smc_set_keepalive, .hash = smc_hash_sk, .unhash = smc_unhash_sk, .release_cb = smc_release_cb, .obj_size = sizeof(struct smc_sock), .h.smc_hash = &smc_v6_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, }; EXPORT_SYMBOL_GPL(smc_proto6); static void smc_fback_restore_callbacks(struct smc_sock *smc) { struct sock *clcsk = smc->clcsock->sk; write_lock_bh(&clcsk->sk_callback_lock); clcsk->sk_user_data = NULL; smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change); smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready); smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space); smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report); write_unlock_bh(&clcsk->sk_callback_lock); } static void smc_restore_fallback_changes(struct smc_sock *smc) { if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ smc->clcsock->file->private_data = smc->sk.sk_socket; smc->clcsock->file = NULL; smc_fback_restore_callbacks(smc); } } static int __smc_release(struct smc_sock *smc) { struct sock *sk = &smc->sk; int rc = 0; if (!smc->use_fallback) { rc = smc_close_active(smc); smc_sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } else { if (sk->sk_state != SMC_CLOSED) { if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) sock_put(sk); /* passive closing */ if (sk->sk_state == SMC_LISTEN) { /* wake up clcsock accept */ rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } smc_restore_fallback_changes(smc); } sk->sk_prot->unhash(sk); if (sk->sk_state == SMC_CLOSED) { if (smc->clcsock) { release_sock(sk); smc_clcsock_release(smc); lock_sock(sk); } if (!smc->use_fallback) smc_conn_free(&smc->conn); } return rc; } int smc_release(struct socket *sock) { struct sock *sk = sock->sk; struct smc_sock *smc; int old_state, rc = 0; if (!sk) goto out; sock_hold(sk); /* sock_put below */ smc = smc_sk(sk); old_state = sk->sk_state; /* cleanup for a dangling non-blocking connect */ if (smc->connect_nonblock && old_state == SMC_INIT) tcp_abort(smc->clcsock->sk, ECONNABORTED); if (cancel_work_sync(&smc->connect_work)) sock_put(&smc->sk); /* sock_hold in smc_connect for passive closing */ if (sk->sk_state == SMC_LISTEN) /* smc_close_non_accepted() is called and acquires * sock lock for child sockets again */ lock_sock_nested(sk, SINGLE_DEPTH_NESTING); else lock_sock(sk); if (old_state == SMC_INIT && sk->sk_state == SMC_ACTIVE && !smc->use_fallback) smc_close_active_abort(smc); rc = __smc_release(smc); /* detach socket */ sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); /* sock_hold above */ sock_put(sk); /* final sock_put */ out: return rc; } static void smc_destruct(struct sock *sk) { if (sk->sk_state != SMC_CLOSED) return; if (!sock_flag(sk, SOCK_DEAD)) return; } static struct lock_class_key smc_key; static struct lock_class_key smc_slock_key; void smc_sk_init(struct net *net, struct sock *sk, int protocol) { struct smc_sock *smc = smc_sk(sk); sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); INIT_LIST_HEAD(&smc->accept_q); sock_lock_init_class_and_name(sk, "slock-AF_SMC", &smc_slock_key, "sk_lock-AF_SMC", &smc_key); spin_lock_init(&smc->accept_q_lock); spin_lock_init(&smc->conn.send_lock); sk->sk_prot->hash(sk); mutex_init(&smc->clcsock_release_lock); smc_init_saved_callbacks(smc); smc->limit_smc_hs = net->smc.limit_smc_hs; smc->use_fallback = false; /* assume rdma capability first */ smc->fallback_rsn = 0; smc_close_init(smc); } static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, int protocol) { struct proto *prot; struct sock *sk; prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); if (!sk) return NULL; sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ smc_sk_init(net, sk, protocol); return sk; } int smc_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; struct smc_sock *smc; int rc; smc = smc_sk(sk); /* replicate tests from inet_bind(), to be safe wrt. future changes */ rc = -EINVAL; if (addr_len < sizeof(struct sockaddr_in)) goto out; rc = -EAFNOSUPPORT; if (addr->sin_family != AF_INET && addr->sin_family != AF_INET6 && addr->sin_family != AF_UNSPEC) goto out; /* accept AF_UNSPEC (mapped to AF_INET) only if s_addr is INADDR_ANY */ if (addr->sin_family == AF_UNSPEC && addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; lock_sock(sk); /* Check if socket is already active */ rc = -EINVAL; if (sk->sk_state != SMC_INIT || smc->connect_nonblock) goto out_rel; smc->clcsock->sk->sk_reuse = sk->sk_reuse; smc->clcsock->sk->sk_reuseport = sk->sk_reuseport; rc = kernel_bind(smc->clcsock, uaddr, addr_len); out_rel: release_sock(sk); out: return rc; } /* copy only relevant settings and flags of SOL_SOCKET level from smc to * clc socket (since smc is not called for these options from net/core) */ #define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ (1UL << SOCK_LINGER) | \ (1UL << SOCK_BROADCAST) | \ (1UL << SOCK_TIMESTAMP) | \ (1UL << SOCK_DBG) | \ (1UL << SOCK_RCVTSTAMP) | \ (1UL << SOCK_RCVTSTAMPNS) | \ (1UL << SOCK_LOCALROUTE) | \ (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ (1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_WIFI_STATUS) | \ (1UL << SOCK_NOFCS) | \ (1UL << SOCK_FILTER_LOCKED) | \ (1UL << SOCK_TSTAMP_NEW)) /* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, unsigned long mask) { nsk->sk_userlocks = osk->sk_userlocks; if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) nsk->sk_sndbuf = osk->sk_sndbuf; if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) nsk->sk_rcvbuf = osk->sk_rcvbuf; } static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, unsigned long mask) { /* options we don't get control via setsockopt for */ nsk->sk_type = osk->sk_type; nsk->sk_sndtimeo = osk->sk_sndtimeo; nsk->sk_rcvtimeo = osk->sk_rcvtimeo; nsk->sk_mark = READ_ONCE(osk->sk_mark); nsk->sk_priority = READ_ONCE(osk->sk_priority); nsk->sk_rcvlowat = osk->sk_rcvlowat; nsk->sk_bound_dev_if = osk->sk_bound_dev_if; nsk->sk_err = osk->sk_err; nsk->sk_flags &= ~mask; nsk->sk_flags |= osk->sk_flags & mask; smc_adjust_sock_bufsizes(nsk, osk, mask); } static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); } #define SK_FLAGS_CLC_TO_SMC ((1UL << SOCK_URGINLINE) | \ (1UL << SOCK_KEEPOPEN) | \ (1UL << SOCK_LINGER) | \ (1UL << SOCK_DBG)) /* copy only settings and flags relevant for smc from clc to smc socket */ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc) { smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC); } /* register the new vzalloced sndbuf on all links */ static int smcr_lgr_reg_sndbufs(struct smc_link *link, struct smc_buf_desc *snd_desc) { struct smc_link_group *lgr = link->lgr; int i, rc = 0; if (!snd_desc->is_vm) return -EINVAL; /* protect against parallel smcr_link_reg_buf() */ down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; rc = smcr_link_reg_buf(&lgr->lnk[i], snd_desc); if (rc) break; } up_write(&lgr->llc_conf_mutex); return rc; } /* register the new rmb on all links */ static int smcr_lgr_reg_rmbs(struct smc_link *link, struct smc_buf_desc *rmb_desc) { struct smc_link_group *lgr = link->lgr; bool do_slow = false; int i, rc = 0; rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (rc) return rc; down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; if (!rmb_desc->is_reg_mr[link->link_idx]) { up_read(&lgr->llc_conf_mutex); goto slow_path; } } /* mr register already */ goto fast_path; slow_path: do_slow = true; /* protect against parallel smc_llc_cli_rkey_exchange() and * parallel smcr_link_reg_buf() */ down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; rc = smcr_link_reg_buf(&lgr->lnk[i], rmb_desc); if (rc) goto out; } fast_path: /* exchange confirm_rkey msg with peer */ rc = smc_llc_do_confirm_rkey(link, rmb_desc); if (rc) { rc = -EFAULT; goto out; } rmb_desc->is_conf_rkey = true; out: do_slow ? up_write(&lgr->llc_conf_mutex) : up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); return rc; } static int smcr_clnt_conf_first_link(struct smc_sock *smc) { struct smc_link *link = smc->conn.lnk; struct smc_llc_qentry *qentry; int rc; /* Receive CONFIRM LINK request from server over RoCE fabric. * Increasing the client's timeout by twice as much as the server's * timeout by default can temporarily avoid decline messages of * both sides crossing or colliding */ qentry = smc_llc_wait(link->lgr, NULL, 2 * SMC_LLC_WAIT_TIME, SMC_LLC_CONFIRM_LINK); if (!qentry) { struct smc_clc_msg_decline dclc; rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc), SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT); return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc; } smc_llc_save_peer_uid(qentry); rc = smc_llc_eval_conf_link(qentry, SMC_LLC_REQ); smc_llc_flow_qentry_del(&link->lgr->llc_flow_lcl); if (rc) return SMC_CLC_DECL_RMBE_EC; rc = smc_ib_modify_qp_rts(link); if (rc) return SMC_CLC_DECL_ERR_RDYLNK; smc_wr_remember_qp_attr(link); /* reg the sndbuf if it was vzalloced */ if (smc->conn.sndbuf_desc->is_vm) { if (smcr_link_reg_buf(link, smc->conn.sndbuf_desc)) return SMC_CLC_DECL_ERR_REGBUF; } /* reg the rmb */ if (smcr_link_reg_buf(link, smc->conn.rmb_desc)) return SMC_CLC_DECL_ERR_REGBUF; /* confirm_rkey is implicit on 1st contact */ smc->conn.rmb_desc->is_conf_rkey = true; /* send CONFIRM LINK response over RoCE fabric */ rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP); if (rc < 0) return SMC_CLC_DECL_TIMEOUT_CL; smc_llc_link_active(link); smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE); if (link->lgr->max_links > 1) { /* optional 2nd link, receive ADD LINK request from server */ qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME, SMC_LLC_ADD_LINK); if (!qentry) { struct smc_clc_msg_decline dclc; rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc), SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT); if (rc == -EAGAIN) rc = 0; /* no DECLINE received, go with one link */ return rc; } smc_llc_flow_qentry_clr(&link->lgr->llc_flow_lcl); smc_llc_cli_add_link(link, qentry); } return 0; } static bool smc_isascii(char *hostname) { int i; for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++) if (!isascii(hostname[i])) return false; return true; } static void smc_conn_save_peer_info_fce(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { struct smc_clc_first_contact_ext *fce; int clc_v2_len; if (clc->hdr.version == SMC_V1 || !(clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) return; if (smc->conn.lgr->is_smcd) { memcpy(smc->conn.lgr->negotiated_eid, clc->d1.eid, SMC_MAX_EID_LEN); clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, d1); } else { memcpy(smc->conn.lgr->negotiated_eid, clc->r1.eid, SMC_MAX_EID_LEN); clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, r1); } fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc) + clc_v2_len); smc->conn.lgr->peer_os = fce->os_type; smc->conn.lgr->peer_smc_release = fce->release; if (smc_isascii(fce->hostname)) memcpy(smc->conn.lgr->peer_hostname, fce->hostname, SMC_MAX_HOSTNAME_LEN); } static void smcr_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { int bufsize = smc_uncompress_bufsize(clc->r0.rmbe_size); smc->conn.peer_rmbe_idx = clc->r0.rmbe_idx; smc->conn.local_tx_ctrl.token = ntohl(clc->r0.rmbe_alert_token); smc->conn.peer_rmbe_size = bufsize; atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); } static void smcd_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size); smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx; smc->conn.peer_token = ntohll(clc->d0.token); /* msg header takes up space in the buffer */ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx; } static void smc_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { if (smc->conn.lgr->is_smcd) smcd_conn_save_peer_info(smc, clc); else smcr_conn_save_peer_info(smc, clc); smc_conn_save_peer_info_fce(smc, clc); } static void smc_link_save_peer_info(struct smc_link *link, struct smc_clc_msg_accept_confirm *clc, struct smc_init_info *ini) { link->peer_qpn = ntoh24(clc->r0.qpn); memcpy(link->peer_gid, ini->peer_gid, SMC_GID_SIZE); memcpy(link->peer_mac, ini->peer_mac, sizeof(link->peer_mac)); link->peer_psn = ntoh24(clc->r0.psn); link->peer_mtu = clc->r0.qp_mtu; } static void smc_stat_inc_fback_rsn_cnt(struct smc_sock *smc, struct smc_stats_fback *fback_arr) { int cnt; for (cnt = 0; cnt < SMC_MAX_FBACK_RSN_CNT; cnt++) { if (fback_arr[cnt].fback_code == smc->fallback_rsn) { fback_arr[cnt].count++; break; } if (!fback_arr[cnt].fback_code) { fback_arr[cnt].fback_code = smc->fallback_rsn; fback_arr[cnt].count++; break; } } } static void smc_stat_fallback(struct smc_sock *smc) { struct net *net = sock_net(&smc->sk); mutex_lock(&net->smc.mutex_fback_rsn); if (smc->listen_smc) { smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->srv); net->smc.fback_rsn->srv_fback_cnt++; } else { smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->clnt); net->smc.fback_rsn->clnt_fback_cnt++; } mutex_unlock(&net->smc.mutex_fback_rsn); } /* must be called under rcu read lock */ static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key) { struct socket_wq *wq; __poll_t flags; wq = rcu_dereference(smc->sk.sk_wq); if (!skwq_has_sleeper(wq)) return; /* wake up smc sk->sk_wq */ if (!key) { /* sk_state_change */ wake_up_interruptible_all(&wq->wait); } else { flags = key_to_poll(key); if (flags & (EPOLLIN | EPOLLOUT)) /* sk_data_ready or sk_write_space */ wake_up_interruptible_sync_poll(&wq->wait, flags); else if (flags & EPOLLERR) /* sk_error_report */ wake_up_interruptible_poll(&wq->wait, flags); } } static int smc_fback_mark_woken(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct smc_mark_woken *mark = container_of(wait, struct smc_mark_woken, wait_entry); mark->woken = true; mark->key = key; return 0; } static void smc_fback_forward_wakeup(struct smc_sock *smc, struct sock *clcsk, void (*clcsock_callback)(struct sock *sk)) { struct smc_mark_woken mark = { .woken = false }; struct socket_wq *wq; init_waitqueue_func_entry(&mark.wait_entry, smc_fback_mark_woken); rcu_read_lock(); wq = rcu_dereference(clcsk->sk_wq); if (!wq) goto out; add_wait_queue(sk_sleep(clcsk), &mark.wait_entry); clcsock_callback(clcsk); remove_wait_queue(sk_sleep(clcsk), &mark.wait_entry); if (mark.woken) smc_fback_wakeup_waitqueue(smc, mark.key); out: rcu_read_unlock(); } static void smc_fback_state_change(struct sock *clcsk) { struct smc_sock *smc; read_lock_bh(&clcsk->sk_callback_lock); smc = smc_clcsock_user_data(clcsk); if (smc) smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_data_ready(struct sock *clcsk) { struct smc_sock *smc; read_lock_bh(&clcsk->sk_callback_lock); smc = smc_clcsock_user_data(clcsk); if (smc) smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_write_space(struct sock *clcsk) { struct smc_sock *smc; read_lock_bh(&clcsk->sk_callback_lock); smc = smc_clcsock_user_data(clcsk); if (smc) smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_error_report(struct sock *clcsk) { struct smc_sock *smc; read_lock_bh(&clcsk->sk_callback_lock); smc = smc_clcsock_user_data(clcsk); if (smc) smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_replace_callbacks(struct smc_sock *smc) { struct sock *clcsk = smc->clcsock->sk; write_lock_bh(&clcsk->sk_callback_lock); clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change, &smc->clcsk_state_change); smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready, &smc->clcsk_data_ready); smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space, &smc->clcsk_write_space); smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report, &smc->clcsk_error_report); write_unlock_bh(&clcsk->sk_callback_lock); } static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { int rc = 0; mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { rc = -EBADF; goto out; } smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); trace_smc_switch_to_fallback(smc, reason_code); if (smc->sk.sk_socket && smc->sk.sk_socket->file) { smc->clcsock->file = smc->sk.sk_socket->file; smc->clcsock->file->private_data = smc->clcsock; smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; smc->sk.sk_socket->wq.fasync_list = NULL; /* There might be some wait entries remaining * in smc sk->sk_wq and they should be woken up * as clcsock's wait queue is woken up. */ smc_fback_replace_callbacks(smc); } out: mutex_unlock(&smc->clcsock_release_lock); return rc; } /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { struct net *net = sock_net(&smc->sk); int rc = 0; rc = smc_switch_to_fallback(smc, reason_code); if (rc) { /* fallback fails */ this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return rc; } smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) smc->sk.sk_state = SMC_ACTIVE; return 0; } /* decline and fall back during connect */ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, u8 version) { struct net *net = sock_net(&smc->sk); int rc; if (reason_code < 0) { /* error, fallback is not possible */ this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return reason_code; } if (reason_code != SMC_CLC_DECL_PEERDECL) { rc = smc_clc_send_decline(smc, reason_code, version); if (rc < 0) { this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return rc; } } return smc_connect_fallback(smc, reason_code); } static void smc_conn_abort(struct smc_sock *smc, int local_first) { struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; bool lgr_valid = false; if (smc_conn_lgr_valid(conn)) lgr_valid = true; smc_conn_free(conn); if (local_first && lgr_valid) smc_lgr_cleanup_early(lgr); } /* check if there is a rdma device available for this connection. */ /* called for connect and listen */ static int smc_find_rdma_device(struct smc_sock *smc, struct smc_init_info *ini) { /* PNET table look up: search active ib_device and port * within same PNETID that also contains the ethernet device * used for the internal TCP socket */ smc_pnet_find_roce_resource(smc->clcsock->sk, ini); if (!ini->check_smcrv2 && !ini->ib_dev) return SMC_CLC_DECL_NOSMCRDEV; if (ini->check_smcrv2 && !ini->smcrv2.ib_dev_v2) return SMC_CLC_DECL_NOSMCRDEV; return 0; } /* check if there is an ISM device available for this connection. */ /* called for connect and listen */ static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini) { /* Find ISM device with same PNETID as connecting interface */ smc_pnet_find_ism_resource(smc->clcsock->sk, ini); if (!ini->ism_dev[0]) return SMC_CLC_DECL_NOSMCDDEV; else ini->ism_chid[0] = smc_ism_get_chid(ini->ism_dev[0]); return 0; } /* is chid unique for the ism devices that are already determined? */ static bool smc_find_ism_v2_is_unique_chid(u16 chid, struct smc_init_info *ini, int cnt) { int i = (!ini->ism_dev[0]) ? 1 : 0; for (; i < cnt; i++) if (ini->ism_chid[i] == chid) return false; return true; } /* determine possible V2 ISM devices (either without PNETID or with PNETID plus * PNETID matching net_device) */ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, struct smc_init_info *ini) { int rc = SMC_CLC_DECL_NOSMCDDEV; struct smcd_dev *smcd; int i = 1, entry = 1; bool is_emulated; u16 chid; if (smcd_indicated(ini->smc_type_v1)) rc = 0; /* already initialized for V1 */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->going_away || smcd == ini->ism_dev[0]) continue; chid = smc_ism_get_chid(smcd); if (!smc_find_ism_v2_is_unique_chid(chid, ini, i)) continue; is_emulated = __smc_ism_is_emulated(chid); if (!smc_pnet_is_pnetid_set(smcd->pnetid) || smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) { if (is_emulated && entry == SMCD_CLC_MAX_V2_GID_ENTRIES) /* It's the last GID-CHID entry left in CLC * Proposal SMC-Dv2 extension, but an Emulated- * ISM device will take two entries. So give * up it and try the next potential ISM device. */ continue; ini->ism_dev[i] = smcd; ini->ism_chid[i] = chid; ini->is_smcd = true; rc = 0; i++; entry = is_emulated ? entry + 2 : entry + 1; if (entry > SMCD_CLC_MAX_V2_GID_ENTRIES) break; } } mutex_unlock(&smcd_dev_list.mutex); ini->ism_offered_cnt = i - 1; if (!ini->ism_dev[0] && !ini->ism_dev[1]) ini->smcd_version = 0; return rc; } /* Check for VLAN ID and register it on ISM device just for CLC handshake */ static int smc_connect_ism_vlan_setup(struct smc_sock *smc, struct smc_init_info *ini) { if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev[0], ini->vlan_id)) return SMC_CLC_DECL_ISMVLANERR; return 0; } static int smc_find_proposal_devices(struct smc_sock *smc, struct smc_init_info *ini) { int rc = 0; /* check if there is an ism device available */ if (!(ini->smcd_version & SMC_V1) || smc_find_ism_device(smc, ini) || smc_connect_ism_vlan_setup(smc, ini)) ini->smcd_version &= ~SMC_V1; /* else ISM V1 is supported for this connection */ /* check if there is an rdma device available */ if (!(ini->smcr_version & SMC_V1) || smc_find_rdma_device(smc, ini)) ini->smcr_version &= ~SMC_V1; /* else RDMA is supported for this connection */ ini->smc_type_v1 = smc_indicated_type(ini->smcd_version & SMC_V1, ini->smcr_version & SMC_V1); /* check if there is an ism v2 device available */ if (!(ini->smcd_version & SMC_V2) || !smc_ism_is_v2_capable() || smc_find_ism_v2_device_clnt(smc, ini)) ini->smcd_version &= ~SMC_V2; /* check if there is an rdma v2 device available */ ini->check_smcrv2 = true; ini->smcrv2.saddr = smc->clcsock->sk->sk_rcv_saddr; if (!(ini->smcr_version & SMC_V2) || #if IS_ENABLED(CONFIG_IPV6) (smc->clcsock->sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&smc->clcsock->sk->sk_v6_rcv_saddr)) || #endif !smc_clc_ueid_count() || smc_find_rdma_device(smc, ini)) ini->smcr_version &= ~SMC_V2; ini->check_smcrv2 = false; ini->smc_type_v2 = smc_indicated_type(ini->smcd_version & SMC_V2, ini->smcr_version & SMC_V2); /* if neither ISM nor RDMA are supported, fallback */ if (ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N) rc = SMC_CLC_DECL_NOSMCDEV; return rc; } /* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is * used, the VLAN ID will be registered again during the connection setup. */ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, struct smc_init_info *ini) { if (!smcd_indicated(ini->smc_type_v1)) return 0; if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev[0], ini->vlan_id)) return SMC_CLC_DECL_CNFERR; return 0; } #define SMC_CLC_MAX_ACCEPT_LEN \ (sizeof(struct smc_clc_msg_accept_confirm) + \ sizeof(struct smc_clc_first_contact_ext_v2x) + \ sizeof(struct smc_clc_msg_trail)) /* CLC handshake during connect */ static int smc_connect_clc(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { int rc = 0; /* do inband token exchange */ rc = smc_clc_send_proposal(smc, ini); if (rc) return rc; /* receive SMC Accept CLC message */ return smc_clc_wait_msg(smc, aclc, SMC_CLC_MAX_ACCEPT_LEN, SMC_CLC_ACCEPT, CLC_WAIT_TIME); } void smc_fill_gid_list(struct smc_link_group *lgr, struct smc_gidlist *gidlist, struct smc_ib_device *known_dev, u8 *known_gid) { struct smc_init_info *alt_ini = NULL; memset(gidlist, 0, sizeof(*gidlist)); memcpy(gidlist->list[gidlist->len++], known_gid, SMC_GID_SIZE); alt_ini = kzalloc(sizeof(*alt_ini), GFP_KERNEL); if (!alt_ini) goto out; alt_ini->vlan_id = lgr->vlan_id; alt_ini->check_smcrv2 = true; alt_ini->smcrv2.saddr = lgr->saddr; smc_pnet_find_alt_roce(lgr, alt_ini, known_dev); if (!alt_ini->smcrv2.ib_dev_v2) goto out; memcpy(gidlist->list[gidlist->len++], alt_ini->smcrv2.ib_gid_v2, SMC_GID_SIZE); out: kfree(alt_ini); } static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { struct smc_clc_first_contact_ext *fce = smc_get_clc_first_contact_ext(aclc, false); struct net *net = sock_net(&smc->sk); int rc; if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1) return 0; if (fce->v2_direct) { memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN); ini->smcrv2.uses_gateway = false; } else { if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr, smc_ib_gid_to_ipv4(aclc->r0.lcl.gid), ini->smcrv2.nexthop_mac, &ini->smcrv2.uses_gateway)) return SMC_CLC_DECL_NOROUTE; if (!ini->smcrv2.uses_gateway) { /* mismatch: peer claims indirect, but its direct */ return SMC_CLC_DECL_NOINDIRECT; } } ini->release_nr = fce->release; rc = smc_clc_clnt_v2x_features_validate(fce, ini); if (rc) return rc; return 0; } /* setup for RDMA connection of client */ static int smc_connect_rdma(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { int i, reason_code = 0; struct smc_link *link; u8 *eid = NULL; ini->is_smcd = false; ini->ib_clcqpn = ntoh24(aclc->r0.qpn); ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; memcpy(ini->peer_systemid, aclc->r0.lcl.id_for_peer, SMC_SYSTEMID_LEN); memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE); memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN); ini->max_conns = SMC_CONN_PER_LGR_MAX; ini->max_links = SMC_LINKS_ADD_LNK_MAX; reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini); if (reason_code) return reason_code; mutex_lock(&smc_client_lgr_pending); reason_code = smc_conn_create(smc, ini); if (reason_code) { mutex_unlock(&smc_client_lgr_pending); return reason_code; } smc_conn_save_peer_info(smc, aclc); if (ini->first_contact_local) { link = smc->conn.lnk; } else { /* set link that was assigned by server */ link = NULL; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *l = &smc->conn.lgr->lnk[i]; if (l->peer_qpn == ntoh24(aclc->r0.qpn) && !memcmp(l->peer_gid, &aclc->r0.lcl.gid, SMC_GID_SIZE) && (aclc->hdr.version > SMC_V1 || !memcmp(l->peer_mac, &aclc->r0.lcl.mac, sizeof(l->peer_mac)))) { link = l; break; } } if (!link) { reason_code = SMC_CLC_DECL_NOSRVLINK; goto connect_abort; } smc_switch_link_and_count(&smc->conn, link); } /* create send buffer and rmb */ if (smc_buf_create(smc, false)) { reason_code = SMC_CLC_DECL_MEM; goto connect_abort; } if (ini->first_contact_local) smc_link_save_peer_info(link, aclc, ini); if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) { reason_code = SMC_CLC_DECL_ERR_RTOK; goto connect_abort; } smc_rx_init(smc); if (ini->first_contact_local) { if (smc_ib_ready_link(link)) { reason_code = SMC_CLC_DECL_ERR_RDYLNK; goto connect_abort; } } else { /* reg sendbufs if they were vzalloced */ if (smc->conn.sndbuf_desc->is_vm) { if (smcr_lgr_reg_sndbufs(link, smc->conn.sndbuf_desc)) { reason_code = SMC_CLC_DECL_ERR_REGBUF; goto connect_abort; } } if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc)) { reason_code = SMC_CLC_DECL_ERR_REGBUF; goto connect_abort; } } if (aclc->hdr.version > SMC_V1) { eid = aclc->r1.eid; if (ini->first_contact_local) smc_fill_gid_list(link->lgr, &ini->smcrv2.gidlist, link->smcibdev, link->gid); } reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, aclc->hdr.version, eid, ini); if (reason_code) goto connect_abort; smc_tx_init(smc); if (ini->first_contact_local) { /* QP confirmation over RoCE fabric */ smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK); reason_code = smcr_clnt_conf_first_link(smc); smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl); if (reason_code) goto connect_abort; } mutex_unlock(&smc_client_lgr_pending); smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) smc->sk.sk_state = SMC_ACTIVE; return 0; connect_abort: smc_conn_abort(smc, ini->first_contact_local); mutex_unlock(&smc_client_lgr_pending); smc->connect_nonblock = 0; return reason_code; } /* The server has chosen one of the proposed ISM devices for the communication. * Determine from the CHID of the received CLC ACCEPT the ISM device chosen. */ static int smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { int i; for (i = 0; i < ini->ism_offered_cnt + 1; i++) { if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) { ini->ism_selected = i; return 0; } } return -EPROTO; } /* setup for ISM connection of client */ static int smc_connect_ism(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { u8 *eid = NULL; int rc = 0; ini->is_smcd = true; ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; if (aclc->hdr.version == SMC_V2) { if (ini->first_contact_peer) { struct smc_clc_first_contact_ext *fce = smc_get_clc_first_contact_ext(aclc, true); ini->release_nr = fce->release; rc = smc_clc_clnt_v2x_features_validate(fce, ini); if (rc) return rc; } rc = smc_v2_determine_accepted_chid(aclc, ini); if (rc) return rc; if (__smc_ism_is_emulated(ini->ism_chid[ini->ism_selected])) ini->ism_peer_gid[ini->ism_selected].gid_ext = ntohll(aclc->d1.gid_ext); /* for non-Emulated-ISM devices, peer gid_ext remains 0. */ } ini->ism_peer_gid[ini->ism_selected].gid = ntohll(aclc->d0.gid); /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); rc = smc_conn_create(smc, ini); if (rc) { mutex_unlock(&smc_server_lgr_pending); return rc; } /* Create send and receive buffers */ rc = smc_buf_create(smc, true); if (rc) { rc = (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB : SMC_CLC_DECL_MEM; goto connect_abort; } smc_conn_save_peer_info(smc, aclc); if (smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) { rc = smcd_buf_attach(smc); if (rc) { rc = SMC_CLC_DECL_MEM; /* try to fallback */ goto connect_abort; } } smc_rx_init(smc); smc_tx_init(smc); if (aclc->hdr.version > SMC_V1) eid = aclc->d1.eid; rc = smc_clc_send_confirm(smc, ini->first_contact_local, aclc->hdr.version, eid, ini); if (rc) goto connect_abort; mutex_unlock(&smc_server_lgr_pending); smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) smc->sk.sk_state = SMC_ACTIVE; return 0; connect_abort: smc_conn_abort(smc, ini->first_contact_local); mutex_unlock(&smc_server_lgr_pending); smc->connect_nonblock = 0; return rc; } /* check if received accept type and version matches a proposed one */ static int smc_connect_check_aclc(struct smc_init_info *ini, struct smc_clc_msg_accept_confirm *aclc) { if (aclc->hdr.version >= SMC_V2) { if ((aclc->hdr.typev1 == SMC_TYPE_R && !smcr_indicated(ini->smc_type_v2)) || (aclc->hdr.typev1 == SMC_TYPE_D && !smcd_indicated(ini->smc_type_v2))) return SMC_CLC_DECL_MODEUNSUPP; } else { if ((aclc->hdr.typev1 == SMC_TYPE_R && !smcr_indicated(ini->smc_type_v1)) || (aclc->hdr.typev1 == SMC_TYPE_D && !smcd_indicated(ini->smc_type_v1))) return SMC_CLC_DECL_MODEUNSUPP; } return 0; } /* perform steps before actually connecting */ static int __smc_connect(struct smc_sock *smc) { u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1; struct smc_clc_msg_accept_confirm *aclc; struct smc_init_info *ini = NULL; u8 *buf = NULL; int rc = 0; if (smc->use_fallback) return smc_connect_fallback(smc, smc->fallback_rsn); /* if peer has not signalled SMC-capability, fall back */ if (!tcp_sk(smc->clcsock->sk)->syn_smc) return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC); /* IPSec connections opt out of SMC optimizations */ if (using_ipsec(smc)) return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC, version); ini = kzalloc(sizeof(*ini), GFP_KERNEL); if (!ini) return smc_connect_decline_fallback(smc, SMC_CLC_DECL_MEM, version); ini->smcd_version = SMC_V1 | SMC_V2; ini->smcr_version = SMC_V1 | SMC_V2; ini->smc_type_v1 = SMC_TYPE_B; ini->smc_type_v2 = SMC_TYPE_B; /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(smc->clcsock, ini)) { ini->smcd_version &= ~SMC_V1; ini->smcr_version = 0; ini->smc_type_v1 = SMC_TYPE_N; } rc = smc_find_proposal_devices(smc, ini); if (rc) goto fallback; buf = kzalloc(SMC_CLC_MAX_ACCEPT_LEN, GFP_KERNEL); if (!buf) { rc = SMC_CLC_DECL_MEM; goto fallback; } aclc = (struct smc_clc_msg_accept_confirm *)buf; /* perform CLC handshake */ rc = smc_connect_clc(smc, aclc, ini); if (rc) { /* -EAGAIN on timeout, see tcp_recvmsg() */ if (rc == -EAGAIN) { rc = -ETIMEDOUT; smc->sk.sk_err = ETIMEDOUT; } goto vlan_cleanup; } /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2; if (rc) goto vlan_cleanup; /* depending on previous steps, connect using rdma or ism */ if (aclc->hdr.typev1 == SMC_TYPE_R) { ini->smcr_version = version; rc = smc_connect_rdma(smc, aclc, ini); } else if (aclc->hdr.typev1 == SMC_TYPE_D) { ini->smcd_version = version; rc = smc_connect_ism(smc, aclc, ini); } if (rc) goto vlan_cleanup; SMC_STAT_CLNT_SUCC_INC(sock_net(smc->clcsock->sk), aclc); smc_connect_ism_vlan_cleanup(smc, ini); kfree(buf); kfree(ini); return 0; vlan_cleanup: smc_connect_ism_vlan_cleanup(smc, ini); kfree(buf); fallback: kfree(ini); return smc_connect_decline_fallback(smc, rc, version); } static void smc_connect_work(struct work_struct *work) { struct smc_sock *smc = container_of(work, struct smc_sock, connect_work); long timeo = smc->sk.sk_sndtimeo; int rc = 0; if (!timeo) timeo = MAX_SCHEDULE_TIMEOUT; lock_sock(smc->clcsock->sk); if (smc->clcsock->sk->sk_err) { smc->sk.sk_err = smc->clcsock->sk->sk_err; } else if ((1 << smc->clcsock->sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo); if ((rc == -EPIPE) && ((1 << smc->clcsock->sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))) rc = 0; } release_sock(smc->clcsock->sk); lock_sock(&smc->sk); if (rc != 0 || smc->sk.sk_err) { smc->sk.sk_state = SMC_CLOSED; if (rc == -EPIPE || rc == -EAGAIN) smc->sk.sk_err = EPIPE; else if (rc == -ECONNREFUSED) smc->sk.sk_err = ECONNREFUSED; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); sock_put(&smc->sk); /* passive closing */ goto out; } rc = __smc_connect(smc); if (rc < 0) smc->sk.sk_err = -rc; out: if (!sock_flag(&smc->sk, SOCK_DEAD)) { if (smc->sk.sk_err) { smc->sk.sk_state_change(&smc->sk); } else { /* allow polling before and after fallback decision */ smc->clcsock->sk->sk_write_space(smc->clcsock->sk); smc->sk.sk_write_space(&smc->sk); } } release_sock(&smc->sk); } int smc_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; int rc = -EINVAL; smc = smc_sk(sk); /* separate smc parameter checking to be safe */ if (alen < sizeof(addr->sa_family)) goto out_err; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6) goto out_err; lock_sock(sk); switch (sock->state) { default: rc = -EINVAL; goto out; case SS_CONNECTED: rc = sk->sk_state == SMC_ACTIVE ? -EISCONN : -EINVAL; goto out; case SS_CONNECTING: if (sk->sk_state == SMC_ACTIVE) goto connected; break; case SS_UNCONNECTED: sock->state = SS_CONNECTING; break; } switch (sk->sk_state) { default: goto out; case SMC_CLOSED: rc = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; goto out; case SMC_ACTIVE: rc = -EISCONN; goto out; case SMC_INIT: break; } smc_copy_sock_settings_to_clc(smc); tcp_sk(smc->clcsock->sk)->syn_smc = 1; if (smc->connect_nonblock) { rc = -EALREADY; goto out; } rc = kernel_connect(smc->clcsock, addr, alen, flags); if (rc && rc != -EINPROGRESS) goto out; if (smc->use_fallback) { sock->state = rc ? SS_CONNECTING : SS_CONNECTED; goto out; } sock_hold(&smc->sk); /* sock put in passive closing */ if (flags & O_NONBLOCK) { if (queue_work(smc_hs_wq, &smc->connect_work)) smc->connect_nonblock = 1; rc = -EINPROGRESS; goto out; } else { rc = __smc_connect(smc); if (rc < 0) goto out; } connected: rc = 0; sock->state = SS_CONNECTED; out: release_sock(sk); out_err: return rc; } static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) { struct socket *new_clcsock = NULL; struct sock *lsk = &lsmc->sk; struct sock *new_sk; int rc = -EINVAL; release_sock(lsk); new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol); if (!new_sk) { rc = -ENOMEM; lsk->sk_err = ENOMEM; *new_smc = NULL; lock_sock(lsk); goto out; } *new_smc = smc_sk(new_sk); mutex_lock(&lsmc->clcsock_release_lock); if (lsmc->clcsock) rc = kernel_accept(lsmc->clcsock, &new_clcsock, SOCK_NONBLOCK); mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); if (rc < 0 && rc != -EAGAIN) lsk->sk_err = -rc; if (rc < 0 || lsk->sk_state == SMC_CLOSED) { new_sk->sk_prot->unhash(new_sk); if (new_clcsock) sock_release(new_clcsock); new_sk->sk_state = SMC_CLOSED; smc_sock_set_flag(new_sk, SOCK_DEAD); sock_put(new_sk); /* final */ *new_smc = NULL; goto out; } /* new clcsock has inherited the smc listen-specific sk_data_ready * function; switch it back to the original sk_data_ready function */ new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; /* if new clcsock has also inherited the fallback-specific callback * functions, switch them back to the original ones. */ if (lsmc->use_fallback) { if (lsmc->clcsk_state_change) new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change; if (lsmc->clcsk_write_space) new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space; if (lsmc->clcsk_error_report) new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report; } (*new_smc)->clcsock = new_clcsock; out: return rc; } /* add a just created sock to the accept queue of the listen sock as * candidate for a following socket accept call from user space */ static void smc_accept_enqueue(struct sock *parent, struct sock *sk) { struct smc_sock *par = smc_sk(parent); sock_hold(sk); /* sock_put in smc_accept_unlink () */ spin_lock(&par->accept_q_lock); list_add_tail(&smc_sk(sk)->accept_q, &par->accept_q); spin_unlock(&par->accept_q_lock); sk_acceptq_added(parent); } /* remove a socket from the accept queue of its parental listening socket */ static void smc_accept_unlink(struct sock *sk) { struct smc_sock *par = smc_sk(sk)->listen_smc; spin_lock(&par->accept_q_lock); list_del_init(&smc_sk(sk)->accept_q); spin_unlock(&par->accept_q_lock); sk_acceptq_removed(&smc_sk(sk)->listen_smc->sk); sock_put(sk); /* sock_hold in smc_accept_enqueue */ } /* remove a sock from the accept queue to bind it to a new socket created * for a socket accept call from user space */ struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock) { struct smc_sock *isk, *n; struct sock *new_sk; list_for_each_entry_safe(isk, n, &smc_sk(parent)->accept_q, accept_q) { new_sk = (struct sock *)isk; smc_accept_unlink(new_sk); if (new_sk->sk_state == SMC_CLOSED) { new_sk->sk_prot->unhash(new_sk); if (isk->clcsock) { sock_release(isk->clcsock); isk->clcsock = NULL; } sock_put(new_sk); /* final */ continue; } if (new_sock) { sock_graft(new_sk, new_sock); new_sock->state = SS_CONNECTED; if (isk->use_fallback) { smc_sk(new_sk)->clcsock->file = new_sock->file; isk->clcsock->file->private_data = isk->clcsock; } } return new_sk; } return NULL; } /* clean up for a created but never accepted sock */ void smc_close_non_accepted(struct sock *sk) { struct smc_sock *smc = smc_sk(sk); sock_hold(sk); /* sock_put below */ lock_sock(sk); if (!sk->sk_lingertime) /* wait for peer closing */ WRITE_ONCE(sk->sk_lingertime, SMC_MAX_STREAM_WAIT_TIMEOUT); __smc_release(smc); release_sock(sk); sock_put(sk); /* sock_hold above */ sock_put(sk); /* final sock_put */ } static int smcr_serv_conf_first_link(struct smc_sock *smc) { struct smc_link *link = smc->conn.lnk; struct smc_llc_qentry *qentry; int rc; /* reg the sndbuf if it was vzalloced*/ if (smc->conn.sndbuf_desc->is_vm) { if (smcr_link_reg_buf(link, smc->conn.sndbuf_desc)) return SMC_CLC_DECL_ERR_REGBUF; } /* reg the rmb */ if (smcr_link_reg_buf(link, smc->conn.rmb_desc)) return SMC_CLC_DECL_ERR_REGBUF; /* send CONFIRM LINK request to client over the RoCE fabric */ rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ); if (rc < 0) return SMC_CLC_DECL_TIMEOUT_CL; /* receive CONFIRM LINK response from client over the RoCE fabric */ qentry = smc_llc_wait(link->lgr, link, SMC_LLC_WAIT_TIME, SMC_LLC_CONFIRM_LINK); if (!qentry) { struct smc_clc_msg_decline dclc; rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc), SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT); return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc; } smc_llc_save_peer_uid(qentry); rc = smc_llc_eval_conf_link(qentry, SMC_LLC_RESP); smc_llc_flow_qentry_del(&link->lgr->llc_flow_lcl); if (rc) return SMC_CLC_DECL_RMBE_EC; /* confirm_rkey is implicit on 1st contact */ smc->conn.rmb_desc->is_conf_rkey = true; smc_llc_link_active(link); smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE); if (link->lgr->max_links > 1) { down_write(&link->lgr->llc_conf_mutex); /* initial contact - try to establish second link */ smc_llc_srv_add_link(link, NULL); up_write(&link->lgr->llc_conf_mutex); } return 0; } /* listen worker: finish */ static void smc_listen_out(struct smc_sock *new_smc) { struct smc_sock *lsmc = new_smc->listen_smc; struct sock *newsmcsk = &new_smc->sk; if (tcp_sk(new_smc->clcsock->sk)->syn_smc) atomic_dec(&lsmc->queued_smc_hs); release_sock(newsmcsk); /* lock in smc_listen_work() */ if (lsmc->sk.sk_state == SMC_LISTEN) { lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); release_sock(&lsmc->sk); } else { /* no longer listening */ smc_close_non_accepted(newsmcsk); } /* Wake up accept */ lsmc->sk.sk_data_ready(&lsmc->sk); sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */ } /* listen worker: finish in state connected */ static void smc_listen_out_connected(struct smc_sock *new_smc) { struct sock *newsmcsk = &new_smc->sk; if (newsmcsk->sk_state == SMC_INIT) newsmcsk->sk_state = SMC_ACTIVE; smc_listen_out(new_smc); } /* listen worker: finish in error state */ static void smc_listen_out_err(struct smc_sock *new_smc) { struct sock *newsmcsk = &new_smc->sk; struct net *net = sock_net(newsmcsk); this_cpu_inc(net->smc.smc_stats->srv_hshake_err_cnt); if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; smc_listen_out(new_smc); } /* listen worker: decline and fall back if possible */ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, int local_first, u8 version) { /* RDMA setup failed, switch back to TCP */ smc_conn_abort(new_smc, local_first); if (reason_code < 0 || smc_switch_to_fallback(new_smc, reason_code)) { /* error, no fallback possible */ smc_listen_out_err(new_smc); return; } if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code, version) < 0) { smc_listen_out_err(new_smc); return; } } smc_listen_out_connected(new_smc); } /* listen worker: version checking */ static int smc_listen_v2_check(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext; struct smc_clc_v2_extension *pclc_v2_ext; int rc = SMC_CLC_DECL_PEERNOSMC; ini->smc_type_v1 = pclc->hdr.typev1; ini->smc_type_v2 = pclc->hdr.typev2; ini->smcd_version = smcd_indicated(ini->smc_type_v1) ? SMC_V1 : 0; ini->smcr_version = smcr_indicated(ini->smc_type_v1) ? SMC_V1 : 0; if (pclc->hdr.version > SMC_V1) { if (smcd_indicated(ini->smc_type_v2)) ini->smcd_version |= SMC_V2; if (smcr_indicated(ini->smc_type_v2)) ini->smcr_version |= SMC_V2; } if (!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) { rc = SMC_CLC_DECL_PEERNOSMC; goto out; } pclc_v2_ext = smc_get_clc_v2_ext(pclc); if (!pclc_v2_ext) { ini->smcd_version &= ~SMC_V2; ini->smcr_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOV2EXT; goto out; } pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext); if (ini->smcd_version & SMC_V2) { if (!smc_ism_is_v2_capable()) { ini->smcd_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOISM2SUPP; } else if (!pclc_smcd_v2_ext) { ini->smcd_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOV2DEXT; } else if (!pclc_v2_ext->hdr.eid_cnt && !pclc_v2_ext->hdr.flag.seid) { ini->smcd_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOUEID; } } if (ini->smcr_version & SMC_V2) { if (!pclc_v2_ext->hdr.eid_cnt) { ini->smcr_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOUEID; } } ini->release_nr = pclc_v2_ext->hdr.flag.release; if (pclc_v2_ext->hdr.flag.release > SMC_RELEASE) ini->release_nr = SMC_RELEASE; out: if (!ini->smcd_version && !ini->smcr_version) return rc; return 0; } /* listen worker: check prefixes */ static int smc_listen_prfx_check(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc) { struct smc_clc_msg_proposal_prefix *pclc_prfx; struct socket *newclcsock = new_smc->clcsock; if (pclc->hdr.typev1 == SMC_TYPE_N) return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); if (!pclc_prfx) return -EPROTO; if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; return 0; } /* listen worker: initialize connection and buffers */ static int smc_listen_rdma_init(struct smc_sock *new_smc, struct smc_init_info *ini) { int rc; /* allocate connection / link group */ rc = smc_conn_create(new_smc, ini); if (rc) return rc; /* create send buffer and rmb */ if (smc_buf_create(new_smc, false)) { smc_conn_abort(new_smc, ini->first_contact_local); return SMC_CLC_DECL_MEM; } return 0; } /* listen worker: initialize connection and buffers for SMC-D */ static int smc_listen_ism_init(struct smc_sock *new_smc, struct smc_init_info *ini) { int rc; rc = smc_conn_create(new_smc, ini); if (rc) return rc; /* Create send and receive buffers */ rc = smc_buf_create(new_smc, true); if (rc) { smc_conn_abort(new_smc, ini->first_contact_local); return (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB : SMC_CLC_DECL_MEM; } return 0; } static bool smc_is_already_selected(struct smcd_dev *smcd, struct smc_init_info *ini, int matches) { int i; for (i = 0; i < matches; i++) if (smcd == ini->ism_dev[i]) return true; return false; } /* check for ISM devices matching proposed ISM devices */ static void smc_check_ism_v2_match(struct smc_init_info *ini, u16 proposed_chid, struct smcd_gid *proposed_gid, unsigned int *matches) { struct smcd_dev *smcd; list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->going_away) continue; if (smc_is_already_selected(smcd, ini, *matches)) continue; if (smc_ism_get_chid(smcd) == proposed_chid && !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) { ini->ism_peer_gid[*matches].gid = proposed_gid->gid; if (__smc_ism_is_emulated(proposed_chid)) ini->ism_peer_gid[*matches].gid_ext = proposed_gid->gid_ext; /* non-Emulated-ISM's peer gid_ext remains 0. */ ini->ism_dev[*matches] = smcd; (*matches)++; break; } } } static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini) { if (!ini->rc) ini->rc = rc; } static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { struct smc_clc_smcd_v2_extension *smcd_v2_ext; struct smc_clc_v2_extension *smc_v2_ext; struct smc_clc_msg_smcd *pclc_smcd; unsigned int matches = 0; struct smcd_gid smcd_gid; u8 smcd_version; u8 *eid = NULL; int i, rc; u16 chid; if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2)) goto not_found; pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext) goto not_found; mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) { /* check for ISM device matching proposed native ISM device */ smcd_gid.gid = ntohll(pclc_smcd->ism.gid); smcd_gid.gid_ext = 0; smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid), &smcd_gid, &matches); } for (i = 0; i < smc_v2_ext->hdr.ism_gid_cnt; i++) { /* check for ISM devices matching proposed non-native ISM * devices */ smcd_gid.gid = ntohll(smcd_v2_ext->gidchid[i].gid); smcd_gid.gid_ext = 0; chid = ntohs(smcd_v2_ext->gidchid[i].chid); if (__smc_ism_is_emulated(chid)) { if ((i + 1) == smc_v2_ext->hdr.ism_gid_cnt || chid != ntohs(smcd_v2_ext->gidchid[i + 1].chid)) /* each Emulated-ISM device takes two GID-CHID * entries and CHID of the second entry repeats * that of the first entry. * * So check if the next GID-CHID entry exists * and both two entries' CHIDs are the same. */ continue; smcd_gid.gid_ext = ntohll(smcd_v2_ext->gidchid[++i].gid); } smc_check_ism_v2_match(ini, chid, &smcd_gid, &matches); } mutex_unlock(&smcd_dev_list.mutex); if (!ini->ism_dev[0]) { smc_find_ism_store_rc(SMC_CLC_DECL_NOSMCD2DEV, ini); goto not_found; } smc_ism_get_system_eid(&eid); if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, smcd_v2_ext->system_eid, eid)) goto not_found; /* separate - outside the smcd_dev_list.lock */ smcd_version = ini->smcd_version; for (i = 0; i < matches; i++) { ini->smcd_version = SMC_V2; ini->is_smcd = true; ini->ism_selected = i; rc = smc_listen_ism_init(new_smc, ini); if (rc) { smc_find_ism_store_rc(rc, ini); /* try next active ISM device */ continue; } return; /* matching and usable V2 ISM device found */ } /* no V2 ISM device could be initialized */ ini->smcd_version = smcd_version; /* restore original value */ ini->negotiated_eid[0] = 0; not_found: ini->smcd_version &= ~SMC_V2; ini->ism_dev[0] = NULL; ini->is_smcd = false; } static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc); int rc = 0; /* check if ISM V1 is available */ if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1) || !pclc_smcd) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); ini->ism_peer_gid[0].gid_ext = 0; rc = smc_find_ism_device(new_smc, ini); if (rc) goto not_found; ini->ism_selected = 0; rc = smc_listen_ism_init(new_smc, ini); if (!rc) return; /* V1 ISM device found */ not_found: smc_find_ism_store_rc(rc, ini); ini->smcd_version &= ~SMC_V1; ini->ism_dev[0] = NULL; ini->is_smcd = false; } /* listen worker: register buffers */ static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first) { struct smc_connection *conn = &new_smc->conn; if (!local_first) { /* reg sendbufs if they were vzalloced */ if (conn->sndbuf_desc->is_vm) { if (smcr_lgr_reg_sndbufs(conn->lnk, conn->sndbuf_desc)) return SMC_CLC_DECL_ERR_REGBUF; } if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc)) return SMC_CLC_DECL_ERR_REGBUF; } return 0; } static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { struct smc_clc_v2_extension *smc_v2_ext; u8 smcr_version; int rc; if (!(ini->smcr_version & SMC_V2) || !smcr_indicated(ini->smc_type_v2)) goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); if (!smc_v2_ext || !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ memcpy(ini->peer_systemid, pclc->lcl.id_for_peer, SMC_SYSTEMID_LEN); memcpy(ini->peer_gid, smc_v2_ext->roce, SMC_GID_SIZE); memcpy(ini->peer_mac, pclc->lcl.mac, ETH_ALEN); ini->check_smcrv2 = true; ini->smcrv2.clc_sk = new_smc->clcsock->sk; ini->smcrv2.saddr = new_smc->clcsock->sk->sk_rcv_saddr; ini->smcrv2.daddr = smc_ib_gid_to_ipv4(smc_v2_ext->roce); rc = smc_find_rdma_device(new_smc, ini); if (rc) { smc_find_ism_store_rc(rc, ini); goto not_found; } if (!ini->smcrv2.uses_gateway) memcpy(ini->smcrv2.nexthop_mac, pclc->lcl.mac, ETH_ALEN); smcr_version = ini->smcr_version; ini->smcr_version = SMC_V2; rc = smc_listen_rdma_init(new_smc, ini); if (!rc) { rc = smc_listen_rdma_reg(new_smc, ini->first_contact_local); if (rc) smc_conn_abort(new_smc, ini->first_contact_local); } if (!rc) return; ini->smcr_version = smcr_version; smc_find_ism_store_rc(rc, ini); not_found: ini->smcr_version &= ~SMC_V2; ini->smcrv2.ib_dev_v2 = NULL; ini->check_smcrv2 = false; } static int smc_find_rdma_v1_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { int rc; if (!(ini->smcr_version & SMC_V1) || !smcr_indicated(ini->smc_type_v1)) return SMC_CLC_DECL_NOSMCDEV; /* prepare RDMA check */ memcpy(ini->peer_systemid, pclc->lcl.id_for_peer, SMC_SYSTEMID_LEN); memcpy(ini->peer_gid, pclc->lcl.gid, SMC_GID_SIZE); memcpy(ini->peer_mac, pclc->lcl.mac, ETH_ALEN); rc = smc_find_rdma_device(new_smc, ini); if (rc) { /* no RDMA device found */ return SMC_CLC_DECL_NOSMCDEV; } rc = smc_listen_rdma_init(new_smc, ini); if (rc) return rc; return smc_listen_rdma_reg(new_smc, ini->first_contact_local); } /* determine the local device matching to proposal */ static int smc_listen_find_device(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { int prfx_rc; /* check for ISM device matching V2 proposed device */ smc_find_ism_v2_device_serv(new_smc, pclc, ini); if (ini->ism_dev[0]) return 0; /* check for matching IP prefix and subnet length (V1) */ prfx_rc = smc_listen_prfx_check(new_smc, pclc); if (prfx_rc) smc_find_ism_store_rc(prfx_rc, ini); /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) return ini->rc ?: SMC_CLC_DECL_GETVLANERR; /* check for ISM device matching V1 proposed device */ if (!prfx_rc) smc_find_ism_v1_device_serv(new_smc, pclc, ini); if (ini->ism_dev[0]) return 0; if (!smcr_indicated(pclc->hdr.typev1) && !smcr_indicated(pclc->hdr.typev2)) /* skip RDMA and decline */ return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV; /* check if RDMA V2 is available */ smc_find_rdma_v2_device_serv(new_smc, pclc, ini); if (ini->smcrv2.ib_dev_v2) return 0; /* check if RDMA V1 is available */ if (!prfx_rc) { int rc; rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); smc_find_ism_store_rc(rc, ini); return (!rc) ? 0 : ini->rc; } return prfx_rc; } /* listen worker: finish RDMA setup */ static int smc_listen_rdma_finish(struct smc_sock *new_smc, struct smc_clc_msg_accept_confirm *cclc, bool local_first, struct smc_init_info *ini) { struct smc_link *link = new_smc->conn.lnk; int reason_code = 0; if (local_first) smc_link_save_peer_info(link, cclc, ini); if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) return SMC_CLC_DECL_ERR_RTOK; if (local_first) { if (smc_ib_ready_link(link)) return SMC_CLC_DECL_ERR_RDYLNK; /* QP confirmation over RoCE fabric */ smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK); reason_code = smcr_serv_conf_first_link(new_smc); smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl); } return reason_code; } /* setup for connection of server */ static void smc_listen_work(struct work_struct *work) { struct smc_sock *new_smc = container_of(work, struct smc_sock, smc_listen_work); struct socket *newclcsock = new_smc->clcsock; struct smc_clc_msg_accept_confirm *cclc; struct smc_clc_msg_proposal_area *buf; struct smc_clc_msg_proposal *pclc; struct smc_init_info *ini = NULL; u8 proposal_version = SMC_V1; u8 accept_version; int rc = 0; lock_sock(&new_smc->sk); /* release in smc_listen_out() */ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) return smc_listen_out_err(new_smc); if (new_smc->use_fallback) { smc_listen_out_connected(new_smc); return; } /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { rc = smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC); if (rc) smc_listen_out_err(new_smc); else smc_listen_out_connected(new_smc); return; } /* do inband token exchange - * wait for and receive SMC Proposal CLC message */ buf = kzalloc(sizeof(*buf), GFP_KERNEL); if (!buf) { rc = SMC_CLC_DECL_MEM; goto out_decl; } pclc = (struct smc_clc_msg_proposal *)buf; rc = smc_clc_wait_msg(new_smc, pclc, sizeof(*buf), SMC_CLC_PROPOSAL, CLC_WAIT_TIME); if (rc) goto out_decl; if (pclc->hdr.version > SMC_V1) proposal_version = SMC_V2; /* IPSec connections opt out of SMC optimizations */ if (using_ipsec(new_smc)) { rc = SMC_CLC_DECL_IPSEC; goto out_decl; } ini = kzalloc(sizeof(*ini), GFP_KERNEL); if (!ini) { rc = SMC_CLC_DECL_MEM; goto out_decl; } /* initial version checking */ rc = smc_listen_v2_check(new_smc, pclc, ini); if (rc) goto out_decl; rc = smc_clc_srv_v2x_features_validate(new_smc, pclc, ini); if (rc) goto out_decl; mutex_lock(&smc_server_lgr_pending); smc_rx_init(new_smc); smc_tx_init(new_smc); /* determine ISM or RoCE device used for connection */ rc = smc_listen_find_device(new_smc, pclc, ini); if (rc) goto out_unlock; /* send SMC Accept CLC message */ accept_version = ini->is_smcd ? ini->smcd_version : ini->smcr_version; rc = smc_clc_send_accept(new_smc, ini->first_contact_local, accept_version, ini->negotiated_eid, ini); if (rc) goto out_unlock; /* SMC-D does not need this lock any more */ if (ini->is_smcd) mutex_unlock(&smc_server_lgr_pending); /* receive SMC Confirm CLC message */ memset(buf, 0, sizeof(*buf)); cclc = (struct smc_clc_msg_accept_confirm *)buf; rc = smc_clc_wait_msg(new_smc, cclc, sizeof(*buf), SMC_CLC_CONFIRM, CLC_WAIT_TIME); if (rc) { if (!ini->is_smcd) goto out_unlock; goto out_decl; } rc = smc_clc_v2x_features_confirm_check(cclc, ini); if (rc) { if (!ini->is_smcd) goto out_unlock; goto out_decl; } /* fce smc release version is needed in smc_listen_rdma_finish, * so save fce info here. */ smc_conn_save_peer_info_fce(new_smc, cclc); /* finish worker */ if (!ini->is_smcd) { rc = smc_listen_rdma_finish(new_smc, cclc, ini->first_contact_local, ini); if (rc) goto out_unlock; mutex_unlock(&smc_server_lgr_pending); } smc_conn_save_peer_info(new_smc, cclc); if (ini->is_smcd && smc_ism_support_dmb_nocopy(new_smc->conn.lgr->smcd)) { rc = smcd_buf_attach(new_smc); if (rc) goto out_decl; } smc_listen_out_connected(new_smc); SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); goto out_free; out_unlock: mutex_unlock(&smc_server_lgr_pending); out_decl: smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0, proposal_version); out_free: kfree(ini); kfree(buf); } static void smc_tcp_listen_work(struct work_struct *work) { struct smc_sock *lsmc = container_of(work, struct smc_sock, tcp_listen_work); struct sock *lsk = &lsmc->sk; struct smc_sock *new_smc; int rc = 0; lock_sock(lsk); while (lsk->sk_state == SMC_LISTEN) { rc = smc_clcsock_accept(lsmc, &new_smc); if (rc) /* clcsock accept queue empty or error */ goto out; if (!new_smc) continue; if (tcp_sk(new_smc->clcsock->sk)->syn_smc) atomic_inc(&lsmc->queued_smc_hs); new_smc->listen_smc = lsmc; new_smc->use_fallback = lsmc->use_fallback; new_smc->fallback_rsn = lsmc->fallback_rsn; sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); } out: release_sock(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_clcsock_data_ready() */ } static void smc_clcsock_data_ready(struct sock *listen_clcsock) { struct smc_sock *lsmc; read_lock_bh(&listen_clcsock->sk_callback_lock); lsmc = smc_clcsock_user_data(listen_clcsock); if (!lsmc) goto out; lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } out: read_unlock_bh(&listen_clcsock->sk_callback_lock); } int smc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct smc_sock *smc; int rc; smc = smc_sk(sk); lock_sock(sk); rc = -EINVAL; if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) || smc->connect_nonblock || sock->state != SS_UNCONNECTED) goto out; rc = 0; if (sk->sk_state == SMC_LISTEN) { sk->sk_max_ack_backlog = backlog; goto out; } /* some socket options are handled in core, so we could not apply * them to the clc socket -- copy smc socket options to clc socket */ smc_copy_sock_settings_to_clc(smc); if (!smc->use_fallback) tcp_sk(smc->clcsock->sk)->syn_smc = 1; /* save original sk_data_ready function and establish * smc-specific sk_data_ready function */ write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready, smc_clcsock_data_ready, &smc->clcsk_data_ready); write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); /* save original ops */ smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; smc->af_ops = *smc->ori_af_ops; smc->af_ops.syn_recv_sock = smc_tcp_syn_recv_sock; inet_csk(smc->clcsock->sk)->icsk_af_ops = &smc->af_ops; if (smc->limit_smc_hs) tcp_sk(smc->clcsock->sk)->smc_hs_congested = smc_hs_congested; rc = kernel_listen(smc->clcsock, backlog); if (rc) { write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); goto out; } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; out: release_sock(sk); return rc; } int smc_accept(struct socket *sock, struct socket *new_sock, struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); struct smc_sock *lsmc; long timeo; int rc = 0; lsmc = smc_sk(sk); sock_hold(sk); /* sock_put below */ lock_sock(sk); if (lsmc->sk.sk_state != SMC_LISTEN) { rc = -EINVAL; release_sock(sk); goto out; } /* Wait for an incoming connection */ timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(nsk = smc_accept_dequeue(sk, new_sock))) { set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { rc = -EAGAIN; break; } release_sock(sk); timeo = schedule_timeout(timeo); /* wakeup by sk_data_ready in smc_listen_work() */ sched_annotate_sleep(); lock_sock(sk); if (signal_pending(current)) { rc = sock_intr_errno(timeo); break; } } set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (!rc) rc = sock_error(nsk); release_sock(sk); if (rc) goto out; if (lsmc->sockopt_defer_accept && !(arg->flags & O_NONBLOCK)) { /* wait till data arrives on the socket */ timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept * MSEC_PER_SEC); if (smc_sk(nsk)->use_fallback) { struct sock *clcsk = smc_sk(nsk)->clcsock->sk; lock_sock(clcsk); if (skb_queue_empty(&clcsk->sk_receive_queue)) sk_wait_data(clcsk, &timeo, NULL); release_sock(clcsk); } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) { lock_sock(nsk); smc_rx_wait(smc_sk(nsk), &timeo, 0, smc_rx_data_available); release_sock(nsk); } } out: sock_put(sk); /* sock_hold above */ return rc; } int smc_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct smc_sock *smc; if (peer && (sock->sk->sk_state != SMC_ACTIVE) && (sock->sk->sk_state != SMC_APPCLOSEWAIT1)) return -ENOTCONN; smc = smc_sk(sock->sk); return smc->clcsock->ops->getname(smc->clcsock, addr, peer); } int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct smc_sock *smc; int rc; smc = smc_sk(sk); lock_sock(sk); /* SMC does not support connect with fastopen */ if (msg->msg_flags & MSG_FASTOPEN) { /* not connected yet, fallback */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { rc = smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); if (rc) goto out; } else { rc = -EINVAL; goto out; } } else if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_APPCLOSEWAIT1) && (sk->sk_state != SMC_INIT)) { rc = -EPIPE; goto out; } if (smc->use_fallback) { rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len); } else { rc = smc_tx_sendmsg(smc, msg, len); SMC_STAT_TX_PAYLOAD(smc, len, rc); } out: release_sock(sk); return rc; } int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; int rc = -ENOTCONN; smc = smc_sk(sk); lock_sock(sk); if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { /* socket was connected before, no more data to read */ rc = 0; goto out; } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) goto out; if (sk->sk_state == SMC_PEERFINCLOSEWAIT) { rc = 0; goto out; } if (smc->use_fallback) { rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags); } else { msg->msg_namelen = 0; rc = smc_rx_recvmsg(smc, msg, NULL, len, flags); SMC_STAT_RX_PAYLOAD(smc, rc, rc); } out: release_sock(sk); return rc; } static __poll_t smc_accept_poll(struct sock *parent) { struct smc_sock *isk = smc_sk(parent); __poll_t mask = 0; spin_lock(&isk->accept_q_lock); if (!list_empty(&isk->accept_q)) mask = EPOLLIN | EPOLLRDNORM; spin_unlock(&isk->accept_q_lock); return mask; } __poll_t smc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct smc_sock *smc; __poll_t mask = 0; if (!sk) return EPOLLNVAL; smc = smc_sk(sock->sk); if (smc->use_fallback) { /* delegate to CLC child sock */ mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); sk->sk_err = smc->clcsock->sk->sk_err; } else { if (sk->sk_state != SMC_CLOSED) sock_poll_wait(file, sock, wait); if (sk->sk_err) mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || (sk->sk_state == SMC_CLOSED)) mask |= EPOLLHUP; if (sk->sk_state == SMC_LISTEN) { /* woken up by sk_data_ready in smc_listen_work() */ mask |= smc_accept_poll(sk); } else if (smc->use_fallback) { /* as result of connect_work()*/ mask |= smc->clcsock->ops->poll(file, smc->clcsock, wait); sk->sk_err = smc->clcsock->sk->sk_err; } else { if ((sk->sk_state != SMC_INIT && atomic_read(&smc->conn.sndbuf_space)) || sk->sk_shutdown & SEND_SHUTDOWN) { mask |= EPOLLOUT | EPOLLWRNORM; } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (sk->sk_state != SMC_INIT) { /* Race breaker the same way as tcp_poll(). */ smp_mb__after_atomic(); if (atomic_read(&smc->conn.sndbuf_space)) mask |= EPOLLOUT | EPOLLWRNORM; } } if (atomic_read(&smc->conn.bytes_to_rcv)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (sk->sk_state == SMC_APPCLOSEWAIT1) mask |= EPOLLIN; if (smc->conn.urg_state == SMC_URG_VALID) mask |= EPOLLPRI; } } return mask; } int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; int old_state; int rc1 = 0; smc = smc_sk(sk); if ((how < SHUT_RD) || (how > SHUT_RDWR)) return rc; lock_sock(sk); if (sock->state == SS_CONNECTING) { if (sk->sk_state == SMC_ACTIVE) sock->state = SS_CONNECTED; else if (sk->sk_state == SMC_PEERCLOSEWAIT1 || sk->sk_state == SMC_PEERCLOSEWAIT2 || sk->sk_state == SMC_APPCLOSEWAIT1 || sk->sk_state == SMC_APPCLOSEWAIT2 || sk->sk_state == SMC_APPFINCLOSEWAIT) sock->state = SS_DISCONNECTING; } rc = -ENOTCONN; if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_PEERCLOSEWAIT1) && (sk->sk_state != SMC_PEERCLOSEWAIT2) && (sk->sk_state != SMC_APPCLOSEWAIT1) && (sk->sk_state != SMC_APPCLOSEWAIT2) && (sk->sk_state != SMC_APPFINCLOSEWAIT)) goto out; if (smc->use_fallback) { rc = kernel_sock_shutdown(smc->clcsock, how); sk->sk_shutdown = smc->clcsock->sk->sk_shutdown; if (sk->sk_shutdown == SHUTDOWN_MASK) { sk->sk_state = SMC_CLOSED; sk->sk_socket->state = SS_UNCONNECTED; sock_put(sk); } goto out; } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ old_state = sk->sk_state; rc = smc_close_active(smc); if (old_state == SMC_ACTIVE && sk->sk_state == SMC_PEERCLOSEWAIT1) do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); break; case SHUT_RD: rc = 0; /* nothing more to do because peer is not involved */ break; } if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; if (sk->sk_state == SMC_CLOSED) sock->state = SS_UNCONNECTED; else sock->state = SS_DISCONNECTING; out: release_sock(sk); return rc ? rc : rc1; } static int __smc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct smc_sock *smc; int val, len; smc = smc_sk(sock->sk); if (get_user(len, optlen)) return -EFAULT; len = min_t(int, len, sizeof(int)); if (len < 0) return -EINVAL; switch (optname) { case SMC_LIMIT_HS: val = smc->limit_smc_hs; break; default: return -EOPNOTSUPP; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int __smc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct smc_sock *smc; int val, rc; smc = smc_sk(sk); lock_sock(sk); switch (optname) { case SMC_LIMIT_HS: if (optlen < sizeof(int)) { rc = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(int))) { rc = -EFAULT; break; } smc->limit_smc_hs = !!val; rc = 0; break; default: rc = -EOPNOTSUPP; break; } release_sock(sk); return rc; } int smc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct smc_sock *smc; int val, rc; if (level == SOL_TCP && optname == TCP_ULP) return -EOPNOTSUPP; else if (level == SOL_SMC) return __smc_setsockopt(sock, level, optname, optval, optlen); smc = smc_sk(sk); /* generic setsockopts reaching us here always apply to the * CLC socket */ mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { mutex_unlock(&smc->clcsock_release_lock); return -EBADF; } if (unlikely(!smc->clcsock->ops->setsockopt)) rc = -EOPNOTSUPP; else rc = smc->clcsock->ops->setsockopt(smc->clcsock, level, optname, optval, optlen); if (smc->clcsock->sk->sk_err) { sk->sk_err = smc->clcsock->sk->sk_err; sk_error_report(sk); } mutex_unlock(&smc->clcsock_release_lock); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; lock_sock(sk); if (rc || smc->use_fallback) goto out; switch (optname) { case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { rc = smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { if (val) { SMC_STAT_INC(smc, ndly_cnt); smc_tx_pending(&smc->conn); cancel_delayed_work(&smc->conn.tx_work); } } break; case TCP_CORK: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { if (!val) { SMC_STAT_INC(smc, cork_cnt); smc_tx_pending(&smc->conn); cancel_delayed_work(&smc->conn.tx_work); } } break; case TCP_DEFER_ACCEPT: smc->sockopt_defer_accept = val; break; default: break; } out: release_sock(sk); return rc; } int smc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct smc_sock *smc; int rc; if (level == SOL_SMC) return __smc_getsockopt(sock, level, optname, optval, optlen); smc = smc_sk(sock->sk); mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { mutex_unlock(&smc->clcsock_release_lock); return -EBADF; } /* socket options apply to the CLC socket */ if (unlikely(!smc->clcsock->ops->getsockopt)) { mutex_unlock(&smc->clcsock_release_lock); return -EOPNOTSUPP; } rc = smc->clcsock->ops->getsockopt(smc->clcsock, level, optname, optval, optlen); mutex_unlock(&smc->clcsock_release_lock); return rc; } int smc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { union smc_host_cursor cons, urg; struct smc_connection *conn; struct smc_sock *smc; int answ; smc = smc_sk(sock->sk); conn = &smc->conn; lock_sock(&smc->sk); if (smc->use_fallback) { if (!smc->clcsock) { release_sock(&smc->sk); return -EBADF; } answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); release_sock(&smc->sk); return answ; } switch (cmd) { case SIOCINQ: /* same as FIONREAD */ if (smc->sk.sk_state == SMC_LISTEN) { release_sock(&smc->sk); return -EINVAL; } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; else answ = atomic_read(&smc->conn.bytes_to_rcv); break; case SIOCOUTQ: /* output queue size (not send + not acked) */ if (smc->sk.sk_state == SMC_LISTEN) { release_sock(&smc->sk); return -EINVAL; } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; else answ = smc->conn.sndbuf_desc->len - atomic_read(&smc->conn.sndbuf_space); break; case SIOCOUTQNSD: /* output queue size (not send only) */ if (smc->sk.sk_state == SMC_LISTEN) { release_sock(&smc->sk); return -EINVAL; } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; else answ = smc_tx_prepared_sends(&smc->conn); break; case SIOCATMARK: if (smc->sk.sk_state == SMC_LISTEN) { release_sock(&smc->sk); return -EINVAL; } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) { answ = 0; } else { smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn); smc_curs_copy(&urg, &conn->urg_curs, conn); answ = smc_curs_diff(conn->rmb_desc->len, &cons, &urg) == 1; } break; default: release_sock(&smc->sk); return -ENOIOCTLCMD; } release_sock(&smc->sk); return put_user(answ, (int __user *)arg); } /* Map the affected portions of the rmbe into an spd, note the number of bytes * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor * updates till whenever a respective page has been fully processed. * Note that subsequent recv() calls have to wait till all splice() processing * completed. */ ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; int rc = -ENOTCONN; smc = smc_sk(sk); lock_sock(sk); if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { /* socket was connected before, no more data to read */ rc = 0; goto out; } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) goto out; if (sk->sk_state == SMC_PEERFINCLOSEWAIT) { rc = 0; goto out; } if (smc->use_fallback) { rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos, pipe, len, flags); } else { if (*ppos) { rc = -ESPIPE; goto out; } if (flags & SPLICE_F_NONBLOCK) flags = MSG_DONTWAIT; else flags = 0; SMC_STAT_INC(smc, splice_cnt); rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags); } out: release_sock(sk); return rc; } /* must look like tcp */ static const struct proto_ops smc_sock_ops = { .family = PF_SMC, .owner = THIS_MODULE, .release = smc_release, .bind = smc_bind, .connect = smc_connect, .socketpair = sock_no_socketpair, .accept = smc_accept, .getname = smc_getname, .poll = smc_poll, .ioctl = smc_ioctl, .listen = smc_listen, .shutdown = smc_shutdown, .setsockopt = smc_setsockopt, .getsockopt = smc_getsockopt, .sendmsg = smc_sendmsg, .recvmsg = smc_recvmsg, .mmap = sock_no_mmap, .splice_read = smc_splice_read, }; int smc_create_clcsk(struct net *net, struct sock *sk, int family) { struct smc_sock *smc = smc_sk(sk); int rc; rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); if (rc) return rc; /* smc_clcsock_release() does not wait smc->clcsock->sk's * destruction; its sk_state might not be TCP_CLOSE after * smc->sk is close()d, and TCP timers can be fired later, * which need net ref. */ sk = smc->clcsock->sk; sk_net_refcnt_upgrade(sk); return 0; } static int __smc_create(struct net *net, struct socket *sock, int protocol, int kern, struct socket *clcsock) { int family = (protocol == SMCPROTO_SMC6) ? PF_INET6 : PF_INET; struct smc_sock *smc; struct sock *sk; int rc; rc = -ESOCKTNOSUPPORT; if (sock->type != SOCK_STREAM) goto out; rc = -EPROTONOSUPPORT; if (protocol != SMCPROTO_SMC && protocol != SMCPROTO_SMC6) goto out; rc = -ENOBUFS; sock->ops = &smc_sock_ops; sock->state = SS_UNCONNECTED; sk = smc_sock_alloc(net, sock, protocol); if (!sk) goto out; /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); rc = 0; if (clcsock) smc->clcsock = clcsock; else rc = smc_create_clcsk(net, sk, family); if (rc) { sk_common_release(sk); sock->sk = NULL; } out: return rc; } static int smc_create(struct net *net, struct socket *sock, int protocol, int kern) { return __smc_create(net, sock, protocol, kern, NULL); } static const struct net_proto_family smc_sock_family_ops = { .family = PF_SMC, .owner = THIS_MODULE, .create = smc_create, }; static int smc_ulp_init(struct sock *sk) { struct socket *tcp = sk->sk_socket; struct net *net = sock_net(sk); struct socket *smcsock; int protocol, ret; /* only TCP can be replaced */ if (tcp->type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) return -ESOCKTNOSUPPORT; /* don't handle wq now */ if (tcp->state != SS_UNCONNECTED || !tcp->file || tcp->wq.fasync_list) return -ENOTCONN; if (sk->sk_family == AF_INET) protocol = SMCPROTO_SMC; else protocol = SMCPROTO_SMC6; smcsock = sock_alloc(); if (!smcsock) return -ENFILE; smcsock->type = SOCK_STREAM; __module_get(THIS_MODULE); /* tried in __tcp_ulp_find_autoload */ ret = __smc_create(net, smcsock, protocol, 1, tcp); if (ret) { sock_release(smcsock); /* module_put() which ops won't be NULL */ return ret; } /* replace tcp socket to smc */ smcsock->file = tcp->file; smcsock->file->private_data = smcsock; smcsock->file->f_inode = SOCK_INODE(smcsock); /* replace inode when sock_close */ smcsock->file->f_path.dentry->d_inode = SOCK_INODE(smcsock); /* dput() in __fput */ tcp->file = NULL; return ret; } static void smc_ulp_clone(const struct request_sock *req, struct sock *newsk, const gfp_t priority) { struct inet_connection_sock *icsk = inet_csk(newsk); /* don't inherit ulp ops to child when listen */ icsk->icsk_ulp_ops = NULL; } static struct tcp_ulp_ops smc_ulp_ops __read_mostly = { .name = "smc", .owner = THIS_MODULE, .init = smc_ulp_init, .clone = smc_ulp_clone, }; unsigned int smc_net_id; static __net_init int smc_net_init(struct net *net) { int rc; rc = smc_sysctl_net_init(net); if (rc) return rc; return smc_pnet_net_init(net); } static void __net_exit smc_net_exit(struct net *net) { smc_sysctl_net_exit(net); smc_pnet_net_exit(net); } static __net_init int smc_net_stat_init(struct net *net) { return smc_stats_init(net); } static void __net_exit smc_net_stat_exit(struct net *net) { smc_stats_exit(net); } static struct pernet_operations smc_net_ops = { .init = smc_net_init, .exit = smc_net_exit, .id = &smc_net_id, .size = sizeof(struct smc_net), }; static struct pernet_operations smc_net_stat_ops = { .init = smc_net_stat_init, .exit = smc_net_stat_exit, }; static int __init smc_init(void) { int rc; rc = register_pernet_subsys(&smc_net_ops); if (rc) return rc; rc = register_pernet_subsys(&smc_net_stat_ops); if (rc) goto out_pernet_subsys; rc = smc_ism_init(); if (rc) goto out_pernet_subsys_stat; smc_clc_init(); rc = smc_nl_init(); if (rc) goto out_ism; rc = smc_pnet_init(); if (rc) goto out_nl; rc = -ENOMEM; smc_tcp_ls_wq = alloc_workqueue("smc_tcp_ls_wq", 0, 0); if (!smc_tcp_ls_wq) goto out_pnet; smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0); if (!smc_hs_wq) goto out_alloc_tcp_ls_wq; smc_close_wq = alloc_workqueue("smc_close_wq", 0, 0); if (!smc_close_wq) goto out_alloc_hs_wq; rc = smc_core_init(); if (rc) { pr_err("%s: smc_core_init fails with %d\n", __func__, rc); goto out_alloc_wqs; } rc = smc_llc_init(); if (rc) { pr_err("%s: smc_llc_init fails with %d\n", __func__, rc); goto out_core; } rc = smc_cdc_init(); if (rc) { pr_err("%s: smc_cdc_init fails with %d\n", __func__, rc); goto out_core; } rc = proto_register(&smc_proto, 1); if (rc) { pr_err("%s: proto_register(v4) fails with %d\n", __func__, rc); goto out_core; } rc = proto_register(&smc_proto6, 1); if (rc) { pr_err("%s: proto_register(v6) fails with %d\n", __func__, rc); goto out_proto; } rc = sock_register(&smc_sock_family_ops); if (rc) { pr_err("%s: sock_register fails with %d\n", __func__, rc); goto out_proto6; } INIT_HLIST_HEAD(&smc_v4_hashinfo.ht); INIT_HLIST_HEAD(&smc_v6_hashinfo.ht); rc = smc_ib_register_client(); if (rc) { pr_err("%s: ib_register fails with %d\n", __func__, rc); goto out_sock; } rc = smc_loopback_init(); if (rc) { pr_err("%s: smc_loopback_init fails with %d\n", __func__, rc); goto out_ib; } rc = tcp_register_ulp(&smc_ulp_ops); if (rc) { pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); goto out_lo; } rc = smc_inet_init(); if (rc) { pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); goto out_ulp; } static_branch_enable(&tcp_have_smc); return 0; out_ulp: tcp_unregister_ulp(&smc_ulp_ops); out_lo: smc_loopback_exit(); out_ib: smc_ib_unregister_client(); out_sock: sock_unregister(PF_SMC); out_proto6: proto_unregister(&smc_proto6); out_proto: proto_unregister(&smc_proto); out_core: smc_core_exit(); out_alloc_wqs: destroy_workqueue(smc_close_wq); out_alloc_hs_wq: destroy_workqueue(smc_hs_wq); out_alloc_tcp_ls_wq: destroy_workqueue(smc_tcp_ls_wq); out_pnet: smc_pnet_exit(); out_nl: smc_nl_exit(); out_ism: smc_clc_exit(); smc_ism_exit(); out_pernet_subsys_stat: unregister_pernet_subsys(&smc_net_stat_ops); out_pernet_subsys: unregister_pernet_subsys(&smc_net_ops); return rc; } static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); smc_inet_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); smc_loopback_exit(); smc_ib_unregister_client(); smc_ism_exit(); destroy_workqueue(smc_close_wq); destroy_workqueue(smc_tcp_ls_wq); destroy_workqueue(smc_hs_wq); proto_unregister(&smc_proto6); proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); smc_clc_exit(); unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); } module_init(smc_init); module_exit(smc_exit); MODULE_AUTHOR("Ursula Braun <ubraun@linux.vnet.ibm.com>"); MODULE_DESCRIPTION("smc socket address family"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_SMC); MODULE_ALIAS_TCP_ULP("smc"); /* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1); #if IS_ENABLED(CONFIG_IPV6) MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1); #endif /* CONFIG_IPV6 */ MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME); |
| 3109 2998 3000 3109 3057 3167 3170 3176 3176 3223 25 3048 3028 63 1348 137 1346 3685 68 3565 3142 3155 3102 70 3086 3086 2950 2978 2980 2978 2976 2983 2977 2976 2894 3653 3658 3649 1031 3023 3028 3 2878 58 58 3655 3076 3084 61 3047 17 25 3041 2996 33 2915 2915 93 3014 3015 3011 3012 2891 2893 3452 3462 36 1266 60 3179 3113 1 7 7 189 3041 40 22 35 156 93 79 162 11 156 156 156 60 3043 101 60 3437 163 3637 3193 3404 3111 3639 3077 171 3023 171 3453 3457 3458 3052 3057 3052 2983 2950 1073 2973 38 2949 2950 2949 2981 2982 3098 3098 3098 18 4 3095 4 1 4 3076 3077 3077 3804 3752 2900 2902 2898 3058 3051 2974 2950 233 2933 2935 123 19 107 2874 2877 2962 2965 2960 2959 2936 5606 2992 2851 3867 2811 3869 3780 3783 2962 2965 2965 2964 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/runtime.c - Helper functions for device runtime PM * * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu> */ #include <linux/sched/mm.h> #include <linux/ktime.h> #include <linux/hrtimer.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeirq.h> #include <linux/rculist.h> #include <trace/events/rpm.h> #include "../base.h" #include "power.h" typedef int (*pm_callback_t)(struct device *); static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) { pm_callback_t cb; const struct dev_pm_ops *ops; if (dev->pm_domain) ops = &dev->pm_domain->ops; else if (dev->type && dev->type->pm) ops = dev->type->pm; else if (dev->class && dev->class->pm) ops = dev->class->pm; else if (dev->bus && dev->bus->pm) ops = dev->bus->pm; else ops = NULL; if (ops) cb = *(pm_callback_t *)((void *)ops + cb_offset); else cb = NULL; if (!cb && dev->driver && dev->driver->pm) cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset); return cb; } #define RPM_GET_CALLBACK(dev, callback) \ __rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback)) static int rpm_resume(struct device *dev, int rpmflags); static int rpm_suspend(struct device *dev, int rpmflags); /** * update_pm_runtime_accounting - Update the time accounting of power states * @dev: Device to update the accounting for * * In order to be able to have time accounting of the various power states * (as used by programs such as PowerTOP to show the effectiveness of runtime * PM), we need to track the time spent in each state. * update_pm_runtime_accounting must be called each time before the * runtime_status field is updated, to account the time in the old state * correctly. */ static void update_pm_runtime_accounting(struct device *dev) { u64 now, last, delta; if (dev->power.disable_depth > 0) return; last = dev->power.accounting_timestamp; now = ktime_get_mono_fast_ns(); dev->power.accounting_timestamp = now; /* * Because ktime_get_mono_fast_ns() is not monotonic during * timekeeping updates, ensure that 'now' is after the last saved * timesptamp. */ if (now < last) return; delta = now - last; if (dev->power.runtime_status == RPM_SUSPENDED) dev->power.suspended_time += delta; else dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) { update_pm_runtime_accounting(dev); trace_rpm_status(dev, status); dev->power.runtime_status = status; } static u64 rpm_get_accounted_time(struct device *dev, bool suspended) { u64 time; unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); update_pm_runtime_accounting(dev); time = suspended ? dev->power.suspended_time : dev->power.active_time; spin_unlock_irqrestore(&dev->power.lock, flags); return time; } u64 pm_runtime_active_time(struct device *dev) { return rpm_get_accounted_time(dev, false); } u64 pm_runtime_suspended_time(struct device *dev) { return rpm_get_accounted_time(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. */ static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } /** * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests. * @dev: Device to handle. */ static void pm_runtime_cancel_pending(struct device *dev) { pm_runtime_deactivate_timer(dev); /* * In case there's a request pending, make sure its work function will * return without doing anything. */ dev->power.request = RPM_REQ_NONE; } /* * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time. * @dev: Device to handle. * * Compute the autosuspend-delay expiration time based on the device's * power.last_busy time. If the delay has already expired or is disabled * (negative) or the power.use_autosuspend flag isn't set, return 0. * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero). * * This function may be called either with or without dev->power.lock held. * Either way it can be racy, since power.last_busy may be updated at any time. */ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 expires; if (!dev->power.use_autosuspend) return 0; autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) return 0; expires = READ_ONCE(dev->power.last_busy); expires += (u64)autosuspend_delay * NSEC_PER_MSEC; if (expires > ktime_get_mono_fast_ns()) return expires; /* Expires in the future */ return 0; } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); static int dev_memalloc_noio(struct device *dev, void *data) { return dev->power.memalloc_noio; } /* * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag. * @dev: Device to handle. * @enable: True for setting the flag and False for clearing the flag. * * Set the flag for all devices in the path from the device to the * root device in the device tree if @enable is true, otherwise clear * the flag for devices in the path whose siblings don't set the flag. * * The function should only be called by block device, or network * device driver for solving the deadlock problem during runtime * resume/suspend: * * If memory allocation with GFP_KERNEL is called inside runtime * resume/suspend callback of any one of its ancestors(or the * block device itself), the deadlock may be triggered inside the * memory allocation since it might not complete until the block * device becomes active and the involed page I/O finishes. The * situation is pointed out first by Alan Stern. Network device * are involved in iSCSI kind of situation. * * The lock of dev_hotplug_mutex is held in the function for handling * hotplug race because pm_runtime_set_memalloc_noio() may be called * in async probe(). * * The function should be called between device_add() and device_del() * on the affected device(block/network device). */ void pm_runtime_set_memalloc_noio(struct device *dev, bool enable) { static DEFINE_MUTEX(dev_hotplug_mutex); mutex_lock(&dev_hotplug_mutex); for (;;) { bool enabled; /* hold power lock since bitfield is not SMP-safe. */ spin_lock_irq(&dev->power.lock); enabled = dev->power.memalloc_noio; dev->power.memalloc_noio = enable; spin_unlock_irq(&dev->power.lock); /* * not need to enable ancestors any more if the device * has been enabled. */ if (enabled && enable) break; dev = dev->parent; /* * clear flag of the parent device only if all the * children don't set the flag because ancestor's * flag was set by any one of the descendants. */ if (!dev || (!enable && device_for_each_child(dev, NULL, dev_memalloc_noio))) break; } mutex_unlock(&dev_hotplug_mutex); } EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio); /** * rpm_check_suspend_allowed - Test whether a device may be suspended. * @dev: Device to test. */ static int rpm_check_suspend_allowed(struct device *dev) { int retval = 0; if (dev->power.runtime_error) retval = -EINVAL; else if (dev->power.disable_depth > 0) retval = -EACCES; else if (atomic_read(&dev->power.usage_count)) retval = -EAGAIN; else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ else if ((dev->power.deferred_resume && dev->power.runtime_status == RPM_SUSPENDING) || (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME)) retval = -EAGAIN; else if (__dev_pm_qos_resume_latency(dev) == 0) retval = -EPERM; else if (dev->power.runtime_status == RPM_SUSPENDED) retval = 1; return retval; } static int rpm_get_suppliers(struct device *dev) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { int retval; if (!(link->flags & DL_FLAG_PM_RUNTIME)) continue; retval = pm_runtime_get_sync(link->supplier); /* Ignore suppliers with disabled runtime PM. */ if (retval < 0 && retval != -EACCES) { pm_runtime_put_noidle(link->supplier); return retval; } refcount_inc(&link->rpm_active); } return 0; } /** * pm_runtime_release_supplier - Drop references to device link's supplier. * @link: Target device link. * * Drop all runtime PM references associated with @link to its supplier device. */ void pm_runtime_release_supplier(struct device_link *link) { struct device *supplier = link->supplier; /* * The additional power.usage_count check is a safety net in case * the rpm_active refcount becomes saturated, in which case * refcount_dec_not_one() would return true forever, but it is not * strictly necessary. */ while (refcount_dec_not_one(&link->rpm_active) && atomic_read(&supplier->power.usage_count) > 0) pm_runtime_put_noidle(supplier); } static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { pm_runtime_release_supplier(link); if (try_to_suspend) pm_request_idle(link->supplier); } } static void rpm_put_suppliers(struct device *dev) { __rpm_put_suppliers(dev, true); } static void rpm_suspend_suppliers(struct device *dev) { struct device_link *link; int idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) pm_request_idle(link->supplier); device_links_read_unlock(idx); } /** * __rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int retval = 0, idx; bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); } else { spin_unlock_irq(&dev->power.lock); /* * Resume suppliers if necessary. * * The device's runtime PM status cannot change until this * routine returns, so it is safe to read the status outside of * the lock. */ if (use_links && dev->power.runtime_status == RPM_RESUMING) { idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); if (retval) { rpm_put_suppliers(dev); goto fail; } device_links_read_unlock(idx); } } if (cb) retval = cb(dev); if (dev->power.irq_safe) { spin_lock(&dev->power.lock); } else { /* * If the device is suspending and the callback has returned * success, drop the usage counters of the suppliers that have * been reference counted on its resume. * * Do that if resume fails too. */ if (use_links && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) || (dev->power.runtime_status == RPM_RESUMING && retval))) { idx = device_links_read_lock(); __rpm_put_suppliers(dev, false); fail: device_links_read_unlock(idx); } spin_lock_irq(&dev->power.lock); } return retval; } /** * rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int rpm_callback(int (*cb)(struct device *), struct device *dev) { int retval; if (dev->power.memalloc_noio) { unsigned int noio_flag; /* * Deadlock might be caused if memory allocation with * GFP_KERNEL happens inside runtime_suspend and * runtime_resume callbacks of one block device's * ancestor or the block device itself. Network * device might be thought as part of iSCSI block * device, so network device and its ancestor should * be marked as memalloc_noio too. */ noio_flag = memalloc_noio_save(); retval = __rpm_callback(cb, dev); memalloc_noio_restore(noio_flag); } else { retval = __rpm_callback(cb, dev); } /* * Since -EACCES means that runtime PM is disabled for the given device, * it should not be returned by runtime PM callbacks. If it is returned * nevertheless, assume it to be a transient error and convert it to * -EAGAIN. */ if (retval == -EACCES) retval = -EAGAIN; if (retval != -EAGAIN && retval != -EBUSY) dev->power.runtime_error = retval; return retval; } /** * rpm_idle - Notify device bus type if the device can be suspended. * @dev: Device to notify the bus type about. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. If * another idle notification has been started earlier, return immediately. If * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise * run the ->runtime_idle() callback directly. If the ->runtime_idle callback * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_idle(struct device *dev, int rpmflags) { int (*callback)(struct device *); int retval; trace_rpm_idle(dev, rpmflags); retval = rpm_check_suspend_allowed(dev); if (retval < 0) ; /* Conditions are wrong. */ /* Idle notifications are allowed only in the RPM_ACTIVE state. */ else if (dev->power.runtime_status != RPM_ACTIVE) retval = -EAGAIN; /* * Any pending request other than an idle notification takes * precedence over us, except that the timer may be running. */ else if (dev->power.request_pending && dev->power.request > RPM_REQ_IDLE) retval = -EAGAIN; /* Act as though RPM_NOWAIT is always set. */ else if (dev->power.idle_notification) retval = -EINPROGRESS; if (retval) goto out; /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; callback = RPM_GET_CALLBACK(dev, runtime_idle); /* If no callback assume success. */ if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_IDLE; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } trace_rpm_return_int(dev, _THIS_IP_, 0); return 0; } dev->power.idle_notification = true; if (dev->power.irq_safe) spin_unlock(&dev->power.lock); else spin_unlock_irq(&dev->power.lock); retval = callback(dev); if (dev->power.irq_safe) spin_lock(&dev->power.lock); else spin_lock_irq(&dev->power.lock); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); out: trace_rpm_return_int(dev, _THIS_IP_, retval); return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO); } /** * rpm_suspend - Carry out runtime suspend of given device. * @dev: Device to suspend. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. * Cancel a pending idle notification, autosuspend or suspend. If * another suspend has been started earlier, either return immediately * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC * flags. If the RPM_ASYNC flag is set then queue a suspend request; * otherwise run the ->runtime_suspend() callback directly. When * ->runtime_suspend succeeded, if a deferred resume was requested while * the callback was running then carry it out, otherwise send an idle * notification for its parent (if the suspend succeeded and both * ignore_children of parent->power and irq_safe of dev->power are not set). * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO * flag is set and the next autosuspend-delay expiration time is in the * future, schedule another autosuspend attempt. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_suspend(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval; trace_rpm_suspend(dev, rpmflags); repeat: retval = rpm_check_suspend_allowed(dev); if (retval < 0) goto out; /* Conditions are wrong. */ /* Synchronous suspends are not allowed in the RPM_RESUMING state. */ if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC)) retval = -EAGAIN; if (retval) goto out; /* If the autosuspend_delay time hasn't expired yet, reschedule. */ if ((rpmflags & RPM_AUTO) && dev->power.runtime_status != RPM_SUSPENDING) { u64 expires = pm_runtime_autosuspend_expiration(dev); if (expires != 0) { /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; /* * Optimization: If the timer is already running and is * set to expire at or before the autosuspend delay, * avoid the overhead of resetting it. Just let it * expire; pm_suspend_timer_fn() will take care of the * rest. */ if (!(dev->power.timer_expires && dev->power.timer_expires <= expires)) { /* * We add a slack of 25% to gather wakeups * without sacrificing the granularity. */ u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) * (NSEC_PER_MSEC >> 2); dev->power.timer_expires = expires; hrtimer_start_range_ns(&dev->power.suspend_timer, ns_to_ktime(expires), slack, HRTIMER_MODE_ABS); } dev->power.timer_autosuspends = 1; goto out; } } /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); if (dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { retval = -EINPROGRESS; goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the other suspend running in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ /* Carry out an asynchronous or a synchronous suspend. */ if (rpmflags & RPM_ASYNC) { dev->power.request = (rpmflags & RPM_AUTO) ? RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } goto out; } __update_runtime_status(dev, RPM_SUSPENDING); callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); retval = rpm_callback(callback, dev); if (retval) goto fail; dev_pm_enable_wake_irq_complete(dev); no_callback: __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_deactivate_timer(dev); if (dev->parent) { parent = dev->parent; atomic_add_unless(&parent->power.child_count, -1, 0); } wake_up_all(&dev->power.wait_queue); if (dev->power.deferred_resume) { dev->power.deferred_resume = false; rpm_resume(dev, 0); retval = -EAGAIN; goto out; } if (dev->power.irq_safe) goto out; /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } /* Maybe the suppliers are now able to suspend. */ if (dev->power.links_count > 0) { spin_unlock_irq(&dev->power.lock); rpm_suspend_suppliers(dev); spin_lock_irq(&dev->power.lock); } out: trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; fail: dev_pm_disable_wake_irq_check(dev, true); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); /* * On transient errors, if the callback routine failed an autosuspend, * and if the last_busy time has been updated so that there is a new * autosuspend expiration time, automatically reschedule another * autosuspend. */ if (!dev->power.runtime_error && (rpmflags & RPM_AUTO) && pm_runtime_autosuspend_expiration(dev) != 0) goto repeat; pm_runtime_cancel_pending(dev); goto out; } /** * rpm_resume - Carry out runtime resume of given device. * @dev: Device to resume. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be resumed. Cancel * any scheduled or pending requests. If another resume has been started * earlier, either return immediately or wait for it to finish, depending on the * RPM_NOWAIT and RPM_ASYNC flags. Similarly, if there's a suspend running in * parallel with this function, either tell the other process to resume after * suspending (deferred_resume) or wait for it to finish. If the RPM_ASYNC * flag is set then queue a resume request; otherwise run the * ->runtime_resume() callback directly. Queue an idle notification for the * device if the resume succeeded. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_resume(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval = 0; trace_rpm_resume(dev, rpmflags); repeat: if (dev->power.runtime_error) { retval = -EINVAL; } else if (dev->power.disable_depth > 0) { if (dev->power.runtime_status == RPM_ACTIVE && dev->power.last_status == RPM_ACTIVE) retval = 1; else retval = -EACCES; } if (retval) goto out; /* * Other scheduled or pending requests need to be canceled. Small * optimization: If an autosuspend timer is running, leave it running * rather than cancelling it now only to restart it again in the near * future. */ dev->power.request = RPM_REQ_NONE; if (!dev->power.timer_autosuspends) pm_runtime_deactivate_timer(dev); if (dev->power.runtime_status == RPM_ACTIVE) { retval = 1; goto out; } if (dev->power.runtime_status == RPM_RESUMING || dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { if (dev->power.runtime_status == RPM_SUSPENDING) { dev->power.deferred_resume = true; if (rpmflags & RPM_NOWAIT) retval = -EINPROGRESS; } else { retval = -EINPROGRESS; } goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the operation carried out in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_RESUMING && dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } /* * See if we can skip waking up the parent. This is safe only if * power.no_callbacks is set, because otherwise we don't know whether * the resume will actually succeed. */ if (dev->power.no_callbacks && !parent && dev->parent) { spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING); if (dev->parent->power.disable_depth > 0 || dev->parent->power.ignore_children || dev->parent->power.runtime_status == RPM_ACTIVE) { atomic_inc(&dev->parent->power.child_count); spin_unlock(&dev->parent->power.lock); retval = 1; goto no_callback; /* Assume success. */ } spin_unlock(&dev->parent->power.lock); } /* Carry out an asynchronous or a synchronous resume. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_RESUME; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } retval = 0; goto out; } if (!parent && dev->parent) { /* * Increment the parent's usage counter and resume it if * necessary. Not needed if dev is irq-safe; then the * parent is permanently resumed. */ parent = dev->parent; if (dev->power.irq_safe) goto skip_parent; spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); spin_lock(&parent->power.lock); /* * Resume the parent if it has runtime PM enabled and not been * set to ignore its children. */ if (!parent->power.disable_depth && !parent->power.ignore_children) { rpm_resume(parent, 0); if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); if (retval) goto out; goto repeat; } skip_parent: if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ __update_runtime_status(dev, RPM_RESUMING); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); dev_pm_enable_wake_irq_check(dev, false); } else { no_callback: __update_runtime_status(dev, RPM_ACTIVE); pm_runtime_mark_last_busy(dev); if (parent) atomic_inc(&parent->power.child_count); } wake_up_all(&dev->power.wait_queue); if (retval >= 0) rpm_idle(dev, RPM_ASYNC); out: if (parent && !dev->power.irq_safe) { spin_unlock_irq(&dev->power.lock); pm_runtime_put(parent); spin_lock_irq(&dev->power.lock); } trace_rpm_return_int(dev, _THIS_IP_, retval); return retval; } /** * pm_runtime_work - Universal runtime PM work function. * @work: Work structure used for scheduling the execution of this function. * * Use @work to get the device object the work is to be done for, determine what * is to be done and execute the appropriate runtime PM function. */ static void pm_runtime_work(struct work_struct *work) { struct device *dev = container_of(work, struct device, power.work); enum rpm_request req; spin_lock_irq(&dev->power.lock); if (!dev->power.request_pending) goto out; req = dev->power.request; dev->power.request = RPM_REQ_NONE; dev->power.request_pending = false; switch (req) { case RPM_REQ_NONE: break; case RPM_REQ_IDLE: rpm_idle(dev, RPM_NOWAIT); break; case RPM_REQ_SUSPEND: rpm_suspend(dev, RPM_NOWAIT); break; case RPM_REQ_AUTOSUSPEND: rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO); break; case RPM_REQ_RESUME: rpm_resume(dev, RPM_NOWAIT); break; } out: spin_unlock_irq(&dev->power.lock); } /** * pm_suspend_timer_fn - Timer function for pm_schedule_suspend(). * @timer: hrtimer used by pm_schedule_suspend(). * * Check if the time is right and queue a suspend request. */ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) { struct device *dev = container_of(timer, struct device, power.suspend_timer); unsigned long flags; u64 expires; spin_lock_irqsave(&dev->power.lock, flags); expires = dev->power.timer_expires; /* * If 'expires' is after the current time, we've been called * too early. */ if (expires > 0 && expires <= ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); } spin_unlock_irqrestore(&dev->power.lock, flags); return HRTIMER_NORESTART; } /** * pm_schedule_suspend - Set up a timer to submit a suspend request in future. * @dev: Device to suspend. * @delay: Time to wait before submitting a suspend request, in milliseconds. */ int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (!delay) { retval = rpm_suspend(dev, RPM_ASYNC); goto out; } retval = rpm_check_suspend_allowed(dev); if (retval) goto out; /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); out: spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(pm_schedule_suspend); static int rpm_drop_usage_count(struct device *dev) { int ret; ret = atomic_sub_return(1, &dev->power.usage_count); if (ret >= 0) return ret; /* * Because rpm_resume() does not check the usage counter, it will resume * the device even if the usage counter is 0 or negative, so it is * sufficient to increment the usage counter here to reverse the change * made above. */ atomic_inc(&dev->power.usage_count); dev_warn(dev, "Runtime PM usage count underflow!\n"); return -EINVAL; } /** * __pm_runtime_idle - Entry point for runtime idle operations. * @dev: Device to send idle notification for. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out an idle * notification, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_idle(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_idle); /** * __pm_runtime_suspend - Entry point for runtime put/suspend operations. * @dev: Device to suspend. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out a suspend, * either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_suspend(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_suspend); /** * __pm_runtime_resume - Entry point for runtime resume operations. * @dev: Device to resume. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, increment the device's usage count. Then * carry out a resume, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_resume(struct device *dev, int rpmflags) { unsigned long flags; int retval; might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_resume(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_resume); /** * pm_runtime_get_conditional - Conditionally bump up device usage counter. * @dev: Device to handle. * @ign_usage_count: Whether or not to look at the current usage counter value. * * Return -EINVAL if runtime PM is disabled for @dev. * * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either * @ign_usage_count is %true or the runtime PM usage counter of @dev is not * zero, increment the usage counter of @dev and return 1. Otherwise, return 0 * without changing the usage counter. * * If @ign_usage_count is %true, this function can be used to prevent suspending * the device when its runtime PM status is %RPM_ACTIVE. * * If @ign_usage_count is %false, this function can be used to prevent * suspending the device when both its runtime PM status is %RPM_ACTIVE and its * runtime PM usage counter is not zero. * * The caller is responsible for decrementing the runtime PM usage counter of * @dev after this function has returned a positive value for it. */ static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count) { unsigned long flags; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.disable_depth > 0) { retval = -EINVAL; } else if (dev->power.runtime_status != RPM_ACTIVE) { retval = 0; } else if (ign_usage_count) { retval = 1; atomic_inc(&dev->power.usage_count); } else { retval = atomic_inc_not_zero(&dev->power.usage_count); } trace_rpm_usage(dev, 0); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } /** * pm_runtime_get_if_active - Bump up runtime PM usage counter if the device is * in active state * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE, in which case it returns 1. If the device is in a different * state, 0 is returned. -EINVAL is returned if runtime PM is disabled for the * device, in which case also the usage_count will remain unmodified. */ int pm_runtime_get_if_active(struct device *dev) { return pm_runtime_get_conditional(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_get_if_active); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE and its runtime PM usage counter is greater than 0, in which case * it returns 1. If the device is in a different state or its usage_count is 0, * 0 is returned. -EINVAL is returned if runtime PM is disabled for the device, * in which case also the usage_count will remain unmodified. */ int pm_runtime_get_if_in_use(struct device *dev) { return pm_runtime_get_conditional(dev, false); } EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use); /** * __pm_runtime_set_status - Set runtime PM status of a device. * @dev: Device to handle. * @status: New runtime PM status of the device. * * If runtime PM of the device is disabled or its power.runtime_error field is * different from zero, the status may be changed either to RPM_ACTIVE, or to * RPM_SUSPENDED, as long as that reflects the actual state of the device. * However, if the device has a parent and the parent is not active, and the * parent's power.ignore_children flag is unset, the device's status cannot be * set to RPM_ACTIVE, so -EBUSY is returned in that case. * * If successful, __pm_runtime_set_status() clears the power.runtime_error field * and the device parent's counter of unsuspended children is modified to * reflect the new status. If the new status is RPM_SUSPENDED, an idle * notification request for the parent is submitted. * * If @dev has any suppliers (as reflected by device links to them), and @status * is RPM_ACTIVE, they will be activated upfront and if the activation of one * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead * of the @status value) and the suppliers will be deacticated on exit. The * error returned by the failing supplier activation will be returned in that * case. */ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; bool notify_parent = false; unsigned long flags; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) return -EINVAL; spin_lock_irqsave(&dev->power.lock, flags); /* * Prevent PM-runtime from being enabled for the device or return an * error if it is enabled already and working. */ if (dev->power.runtime_error || dev->power.disable_depth) dev->power.disable_depth++; else error = -EAGAIN; spin_unlock_irqrestore(&dev->power.lock, flags); if (error) return error; /* * If the new status is RPM_ACTIVE, the suppliers can be activated * upfront regardless of the current status, because next time * rpm_put_suppliers() runs, the rpm_active refcounts of the links * involved will be dropped down to one anyway. */ if (status == RPM_ACTIVE) { int idx = device_links_read_lock(); error = rpm_get_suppliers(dev); if (error) status = RPM_SUSPENDED; device_links_read_unlock(idx); } spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.runtime_status == status || !parent) goto out_set; if (status == RPM_SUSPENDED) { atomic_add_unless(&parent->power.child_count, -1, 0); notify_parent = !parent->power.ignore_children; } else { spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING); /* * It is invalid to put an active child under a parent that is * not active, has runtime PM enabled and the * 'power.ignore_children' flag unset. */ if (!parent->power.disable_depth && !parent->power.ignore_children && parent->power.runtime_status != RPM_ACTIVE) { dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n", dev_name(dev), dev_name(parent)); error = -EBUSY; } else if (dev->power.runtime_status == RPM_SUSPENDED) { atomic_inc(&parent->power.child_count); } spin_unlock(&parent->power.lock); if (error) { status = RPM_SUSPENDED; goto out; } } out_set: __update_runtime_status(dev, status); if (!error) dev->power.runtime_error = 0; out: spin_unlock_irqrestore(&dev->power.lock, flags); if (notify_parent) pm_request_idle(parent); if (status == RPM_SUSPENDED) { int idx = device_links_read_lock(); rpm_put_suppliers(dev); device_links_read_unlock(idx); } pm_runtime_enable(dev); return error; } EXPORT_SYMBOL_GPL(__pm_runtime_set_status); /** * __pm_runtime_barrier - Cancel pending requests and wait for completions. * @dev: Device to handle. * * Flush all pending requests for the device from pm_wq and wait for all * runtime PM operations involving the device in progress to complete. * * Should be called under dev->power.lock with interrupts disabled. */ static void __pm_runtime_barrier(struct device *dev) { pm_runtime_deactivate_timer(dev); if (dev->power.request_pending) { dev->power.request = RPM_REQ_NONE; spin_unlock_irq(&dev->power.lock); cancel_work_sync(&dev->power.work); spin_lock_irq(&dev->power.lock); dev->power.request_pending = false; } if (dev->power.runtime_status == RPM_SUSPENDING || dev->power.runtime_status == RPM_RESUMING || dev->power.idle_notification) { DEFINE_WAIT(wait); /* Suspend, wake-up or idle notification in progress. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING && dev->power.runtime_status != RPM_RESUMING && !dev->power.idle_notification) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); } } /** * pm_runtime_barrier - Flush pending requests and wait for completions. * @dev: Device to handle. * * Prevent the device from being suspended by incrementing its usage counter and * if there's a pending resume request for the device, wake the device up. * Next, make sure that all pending requests for the device have been flushed * from pm_wq and wait for all runtime PM operations involving the device in * progress to complete. * * Return value: * 1, if there was a resume request pending and the device had to be woken up, * 0, otherwise */ int pm_runtime_barrier(struct device *dev) { int retval = 0; pm_runtime_get_noresume(dev); spin_lock_irq(&dev->power.lock); if (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { rpm_resume(dev, 0); retval = 1; } __pm_runtime_barrier(dev); spin_unlock_irq(&dev->power.lock); pm_runtime_put_noidle(dev); return retval; } EXPORT_SYMBOL_GPL(pm_runtime_barrier); bool pm_runtime_block_if_disabled(struct device *dev) { bool ret; spin_lock_irq(&dev->power.lock); ret = !pm_runtime_enabled(dev); if (ret && dev->power.last_status == RPM_INVALID) dev->power.last_status = RPM_BLOCKED; spin_unlock_irq(&dev->power.lock); return ret; } void pm_runtime_unblock(struct device *dev) { spin_lock_irq(&dev->power.lock); if (dev->power.last_status == RPM_BLOCKED) dev->power.last_status = RPM_INVALID; spin_unlock_irq(&dev->power.lock); } void __pm_runtime_disable(struct device *dev, bool check_resume) { spin_lock_irq(&dev->power.lock); if (dev->power.disable_depth > 0) { dev->power.disable_depth++; goto out; } /* * Wake up the device if there's a resume request pending, because that * means there probably is some I/O to process and disabling runtime PM * shouldn't prevent the device from processing the I/O. */ if (check_resume && dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { /* * Prevent suspends and idle notifications from being carried * out after we have woken up the device. */ pm_runtime_get_noresume(dev); rpm_resume(dev, 0); pm_runtime_put_noidle(dev); } /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); dev->power.last_status = dev->power.runtime_status; } out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_disable); /** * pm_runtime_enable - Enable runtime PM of a device. * @dev: Device to handle. */ void pm_runtime_enable(struct device *dev) { unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); goto out; } if (--dev->power.disable_depth > 0) goto out; if (dev->power.last_status == RPM_BLOCKED) { dev_warn(dev, "Attempt to enable runtime PM when it is blocked\n"); dump_stack(); } dev->power.last_status = RPM_INVALID; dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); if (dev->power.runtime_status == RPM_SUSPENDED && !dev->power.ignore_children && atomic_read(&dev->power.child_count) > 0) dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); static void pm_runtime_set_suspended_action(void *data) { pm_runtime_set_suspended(data); } /** * devm_pm_runtime_set_active_enabled - set_active version of devm_pm_runtime_enable. * * @dev: Device to handle. */ int devm_pm_runtime_set_active_enabled(struct device *dev) { int err; err = pm_runtime_set_active(dev); if (err) return err; err = devm_add_action_or_reset(dev, pm_runtime_set_suspended_action, dev); if (err) return err; return devm_pm_runtime_enable(dev); } EXPORT_SYMBOL_GPL(devm_pm_runtime_set_active_enabled); static void pm_runtime_disable_action(void *data) { pm_runtime_dont_use_autosuspend(data); pm_runtime_disable(data); } /** * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. * * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for * you at driver exit time if needed. * * @dev: Device to handle. */ int devm_pm_runtime_enable(struct device *dev) { pm_runtime_enable(dev); return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); } EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); static void pm_runtime_put_noidle_action(void *data) { pm_runtime_put_noidle(data); } /** * devm_pm_runtime_get_noresume - devres-enabled version of pm_runtime_get_noresume. * * @dev: Device to handle. */ int devm_pm_runtime_get_noresume(struct device *dev) { pm_runtime_get_noresume(dev); return devm_add_action_or_reset(dev, pm_runtime_put_noidle_action, dev); } EXPORT_SYMBOL_GPL(devm_pm_runtime_get_noresume); /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. * * Increase the device's usage count and clear its power.runtime_auto flag, * so that it cannot be suspended at run time until pm_runtime_allow() is called * for it. */ void pm_runtime_forbid(struct device *dev) { spin_lock_irq(&dev->power.lock); if (!dev->power.runtime_auto) goto out; dev->power.runtime_auto = false; atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_forbid); /** * pm_runtime_allow - Unblock runtime PM of a device. * @dev: Device to handle. * * Decrease the device's usage count and set its power.runtime_auto flag. */ void pm_runtime_allow(struct device *dev) { int ret; spin_lock_irq(&dev->power.lock); if (dev->power.runtime_auto) goto out; dev->power.runtime_auto = true; ret = rpm_drop_usage_count(dev); if (ret == 0) rpm_idle(dev, RPM_AUTO | RPM_ASYNC); else if (ret > 0) trace_rpm_usage(dev, RPM_AUTO | RPM_ASYNC); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_allow); /** * pm_runtime_no_callbacks - Ignore runtime PM callbacks for a device. * @dev: Device to handle. * * Set the power.no_callbacks flag, which tells the PM core that this * device is power-managed through its parent and has no runtime PM * callbacks of its own. The runtime sysfs attributes will be removed. */ void pm_runtime_no_callbacks(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.no_callbacks = 1; spin_unlock_irq(&dev->power.lock); if (device_is_registered(dev)) rpm_sysfs_remove(dev); } EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks); /** * pm_runtime_irq_safe - Leave interrupts disabled during callbacks. * @dev: Device to handle * * Set the power.irq_safe flag, which tells the PM core that the * ->runtime_suspend() and ->runtime_resume() callbacks for this device should * always be invoked with the spinlock held and interrupts disabled. It also * causes the parent's usage counter to be permanently incremented, preventing * the parent from runtime suspending -- otherwise an irq-safe child might have * to wait for a non-irq-safe parent. */ void pm_runtime_irq_safe(struct device *dev) { if (dev->parent) pm_runtime_get_sync(dev->parent); spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 1; spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_irq_safe); /** * update_autosuspend - Handle a change to a device's autosuspend settings. * @dev: Device to handle. * @old_delay: The former autosuspend_delay value. * @old_use: The former use_autosuspend value. * * Prevent runtime suspend if the new delay is negative and use_autosuspend is * set; otherwise allow it. Send an idle notification if suspends are allowed. * * This function must be called under dev->power.lock with interrupts disabled. */ static void update_autosuspend(struct device *dev, int old_delay, int old_use) { int delay = dev->power.autosuspend_delay; /* Should runtime suspend be prevented now? */ if (dev->power.use_autosuspend && delay < 0) { /* If it used to be allowed then prevent it. */ if (!old_use || old_delay >= 0) { atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); } else { trace_rpm_usage(dev, 0); } } /* Runtime suspend should be allowed now. */ else { /* If it used to be prevented then allow it. */ if (old_use && old_delay < 0) atomic_dec(&dev->power.usage_count); /* Maybe we can autosuspend now. */ rpm_idle(dev, RPM_AUTO); } } /** * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value. * @dev: Device to handle. * @delay: Value of the new delay in milliseconds. * * Set the device's power.autosuspend_delay value. If it changes to negative * and the power.use_autosuspend flag is set, prevent runtime suspends. If it * changes the other way, allow runtime suspends. */ void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.autosuspend_delay = delay; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay); /** * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag. * @dev: Device to handle. * @use: New value for use_autosuspend. * * Set the device's power.use_autosuspend flag, and allow or prevent runtime * suspends as needed. */ void __pm_runtime_use_autosuspend(struct device *dev, bool use) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.use_autosuspend = use; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); /** * pm_runtime_init - Initialize runtime PM fields in given device object. * @dev: Device object to initialize. */ void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; atomic_set(&dev->power.usage_count, 0); dev->power.runtime_error = 0; atomic_set(&dev->power.child_count, 0); pm_suspend_ignore_children(dev, false); dev->power.runtime_auto = true; dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; dev->power.needs_force_resume = 0; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; hrtimer_setup(&dev->power.suspend_timer, pm_suspend_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); init_waitqueue_head(&dev->power.wait_queue); } /** * pm_runtime_reinit - Re-initialize runtime PM fields in given device object. * @dev: Device object to re-initialize. */ void pm_runtime_reinit(struct device *dev) { if (!pm_runtime_enabled(dev)) { if (dev->power.runtime_status == RPM_ACTIVE) pm_runtime_set_suspended(dev); if (dev->power.irq_safe) { spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 0; spin_unlock_irq(&dev->power.lock); if (dev->parent) pm_runtime_put(dev->parent); } } } /** * pm_runtime_remove - Prepare for removing a device from device hierarchy. * @dev: Device object being removed from device hierarchy. */ void pm_runtime_remove(struct device *dev) { __pm_runtime_disable(dev, false); pm_runtime_reinit(dev); } /** * pm_runtime_get_suppliers - Resume and reference-count supplier devices. * @dev: Consumer device. */ void pm_runtime_get_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; pm_runtime_get_sync(link->supplier); } device_links_read_unlock(idx); } /** * pm_runtime_put_suppliers - Drop references to supplier devices. * @dev: Consumer device. */ void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; pm_runtime_put(link->supplier); } device_links_read_unlock(idx); } void pm_runtime_new_link(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.links_count++; spin_unlock_irq(&dev->power.lock); } static void pm_runtime_drop_link_count(struct device *dev) { spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); dev->power.links_count--; spin_unlock_irq(&dev->power.lock); } /** * pm_runtime_drop_link - Prepare for device link removal. * @link: Device link going away. * * Drop the link count of the consumer end of @link and decrement the supplier * device's runtime PM usage counter as many times as needed to drop all of the * PM runtime reference to it from the consumer. */ void pm_runtime_drop_link(struct device_link *link) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) return; pm_runtime_drop_link_count(link->consumer); pm_runtime_release_supplier(link); pm_request_idle(link->supplier); } bool pm_runtime_need_not_resume(struct device *dev) { return atomic_read(&dev->power.usage_count) <= 1 && (atomic_read(&dev->power.child_count) == 0 || dev->power.ignore_children); } /** * pm_runtime_force_suspend - Force a device into suspend state if needed. * @dev: Device to suspend. * * Disable runtime PM so we safely can check the device's runtime PM status and * if it is active, invoke its ->runtime_suspend callback to suspend it and * change its runtime PM status field to RPM_SUSPENDED. Also, if the device's * usage and children counters don't indicate that the device was in use before * the system-wide transition under way, decrement its parent's children counter * (if there is a parent). Keep runtime PM disabled to preserve the state * unless we encounter errors. * * Typically this function may be invoked from a system suspend callback to make * sure the device is put into low power state and it should only be used during * system-wide PM transitions to sleep states. It assumes that the analogous * pm_runtime_force_resume() will be used to resume the device. * * Do not use with DPM_FLAG_SMART_SUSPEND as this can lead to an inconsistent * state where this function has called the ->runtime_suspend callback but the * PM core marks the driver as runtime active. */ int pm_runtime_force_suspend(struct device *dev) { int (*callback)(struct device *); int ret; pm_runtime_disable(dev); if (pm_runtime_status_suspended(dev)) return 0; callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; if (ret) goto err; dev_pm_enable_wake_irq_complete(dev); /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of * its parent, but set its status to RPM_SUSPENDED anyway in case this * function will be called again for it in the meantime. */ if (pm_runtime_need_not_resume(dev)) { pm_runtime_set_suspended(dev); } else { __update_runtime_status(dev, RPM_SUSPENDED); dev->power.needs_force_resume = 1; } return 0; err: dev_pm_disable_wake_irq_check(dev, true); pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); /** * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * * Prior invoking this function we expect the user to have brought the device * into low power state by a call to pm_runtime_force_suspend(). Here we reverse * those actions and bring the device into full power, if it is expected to be * used on system resume. In the other case, we defer the resume to be managed * via runtime PM. * * Typically this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { int (*callback)(struct device *); int ret = 0; if (!dev->power.needs_force_resume) goto out; /* * The value of the parent's children counter is correct already, so * just update the status of the device. */ __update_runtime_status(dev, RPM_ACTIVE); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; if (ret) { pm_runtime_set_suspended(dev); dev_pm_enable_wake_irq_check(dev, false); goto out; } pm_runtime_mark_last_busy(dev); out: dev->power.needs_force_resume = 0; pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_resume); |
| 271 50 331 1 330 934 608 89 79 13 13 25 25 25 25 25 323 576 714 715 717 664 672 673 672 688 689 683 672 672 674 692 706 412 412 55 369 368 411 59 744 1 1 53 53 1 1 603 604 605 604 605 606 605 1 3 740 742 745 744 742 509 659 505 680 743 705 745 744 440 743 125 704 742 745 745 1150 662 660 1 660 662 663 662 1 1 1 1 1 1 1640 753 754 752 751 1647 1615 783 785 1623 754 754 751 1638 1641 1587 1590 69 609 782 782 740 740 738 815 814 815 814 64 63 62 3 708 369 367 80 80 424 9 599 601 414 415 414 414 412 413 1 414 486 486 484 34 395 455 416 294 178 416 413 5 416 414 606 606 606 604 605 606 606 606 296 338 606 53 53 53 54 54 54 270 270 124 125 3 123 20 9 13 374 264 1 1 1 104 6 5 1 5 1 1 1 1 7 117 7 13 122 3 4 3 3 4 4 7 224 1 6 9 9 713 616 7 1 1 1 5 83 6 88 83 6 88 83 6 88 8 1 3 6 6 6 1 5 2 1 7 4 4 1 3 2 4 6 6 5 11 114 1 4 9 8 11 29 3 2 2 3 3 3 4 1 3 1 576 89 574 8 679 677 141 668 1 300 19 275 283 365 365 365 115 4 4 29 29 29 365 365 365 574 574 244 377 224 1 690 691 432 665 9 667 4 4 428 432 678 681 650 4 4 4 4 1 1 1 1 1 1 349 6 342 12 587 587 587 587 587 340 224 139 1 587 587 42 681 680 679 682 680 679 672 246 673 251 252 494 495 495 3 491 55 493 495 495 495 495 492 5 672 674 533 533 643 636 643 1 305 306 306 305 305 306 302 306 244 243 630 631 113 113 113 138 138 137 221 221 221 138 138 138 3 3 1 2 1 53 52 1 46 2 47 45 45 45 1 44 56 3 3 1 54 52 48 1 45 263 263 263 263 263 113 365 4 29 331 1 86 259 259 330 329 2 331 3 88 258 259 329 282 9 9 9 9 1 1 1 1 1 1 1 13 13 13 13 13 318 318 318 318 318 318 318 318 318 318 318 318 318 318 318 318 318 318 318 396 396 354 53 396 43 256 1 284 85 354 354 354 354 354 353 82 286 354 354 353 354 354 258 258 258 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 256 43 256 256 1 255 1 255 263 8 256 263 263 263 263 263 263 262 263 263 263 263 263 263 263 263 263 263 263 263 263 263 263 39 39 5 5 5 45 45 43 2 45 45 23 21 23 23 61 16 58 26 15 32 22 22 22 22 22 22 597 65 653 653 652 650 3 653 1 1 1 197 197 191 18 18 1 17 5 10 3 4 389 86 120 120 64 77 8 250 132 4 4 268 268 250 132 1 7 3 8 7 38 39 2 39 36 1 2 18 16 19 18 18 18 18 18 385 385 2 1 1 22 22 22 22 712 713 390 634 711 713 711 45 25 22 21 1 1 1 745 746 746 22 6 3 3 333 334 334 333 2 22 22 742 738 1 59 20 2 690 400 726 30 153 3 1 389 16 45 720 743 743 741 85 84 14 84 9 9 9 9 9 131 131 5 16 126 126 126 82 82 197 389 743 1 742 390 197 612 636 636 738 700 393 21 4 232 160 2 582 580 581 739 744 40 9 10 18 619 628 727 722 155 27 88 744 743 1 744 743 744 744 669 744 714 742 744 720 18 740 744 744 744 744 744 742 739 59 37 3 742 743 27 728 728 23 25 24 25 258 258 258 258 258 256 2 258 45 256 256 256 2 2 2 239 239 239 239 239 239 574 573 574 354 95 95 95 95 95 95 95 95 95 95 95 95 94 95 95 89 89 89 89 89 95 354 86 283 354 275 95 354 354 354 282 85 354 4 4 4 4 4 29 29 29 8 25 18 11 22 22 682 672 18 53 225 149 210 209 12 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * This module enables machines with Intel VT-x extensions to run virtual * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/highmem.h> #include <linux/hrtimer.h> #include <linux/kernel.h> #include <linux/kvm_host.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/mod_devicetable.h> #include <linux/mm.h> #include <linux/objtool.h> #include <linux/sched.h> #include <linux/sched/smt.h> #include <linux/slab.h> #include <linux/tboot.h> #include <linux/trace_events.h> #include <linux/entry-kvm.h> #include <asm/apic.h> #include <asm/asm.h> #include <asm/cpu.h> #include <asm/cpu_device_id.h> #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> #include <asm/fred.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> #include <asm/reboot.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> #include <asm/msr.h> #include <asm/mwait.h> #include <asm/spec-ctrl.h> #include <asm/vmx.h> #include <trace/events/ipi.h> #include "capabilities.h" #include "common.h" #include "cpuid.h" #include "hyperv.h" #include "kvm_onhyperv.h" #include "irq.h" #include "kvm_cache_regs.h" #include "lapic.h" #include "mmu.h" #include "nested.h" #include "pmu.h" #include "sgx.h" #include "trace.h" #include "vmcs.h" #include "vmcs12.h" #include "vmx.h" #include "x86.h" #include "x86_ops.h" #include "smm.h" #include "vmx_onhyperv.h" #include "posted_intr.h" MODULE_AUTHOR("Qumranet"); MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions"); MODULE_LICENSE("GPL"); #ifdef MODULE static const struct x86_cpu_id vmx_cpu_id[] = { X86_MATCH_FEATURE(X86_FEATURE_VMX, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); #endif bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); static bool __read_mostly enable_vnmi = 1; module_param_named(vnmi, enable_vnmi, bool, 0444); bool __read_mostly flexpriority_enabled = 1; module_param_named(flexpriority, flexpriority_enabled, bool, 0444); bool __read_mostly enable_ept = 1; module_param_named(ept, enable_ept, bool, 0444); bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, 0444); bool __read_mostly enable_ept_ad_bits = 1; module_param_named(eptad, enable_ept_ad_bits, bool, 0444); static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, 0444); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, 0444); module_param(enable_apicv, bool, 0444); bool __read_mostly enable_ipiv = true; module_param(enable_ipiv, bool, 0444); module_param(enable_device_posted_irqs, bool, 0444); /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not * use VMX instructions. */ static bool __read_mostly nested = 1; module_param(nested, bool, 0444); bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, 0444); static bool __read_mostly error_on_inconsistent_vmcs_config = true; module_param(error_on_inconsistent_vmcs_config, bool, 0444); static bool __read_mostly dump_invalid_vmcs = 0; module_param(dump_invalid_vmcs, bool, 0644); #define MSR_BITMAP_MODE_X2APIC 1 #define MSR_BITMAP_MODE_X2APIC_APICV 2 #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ static int __read_mostly cpu_preemption_timer_multi; static bool __read_mostly enable_preemption_timer = 1; #ifdef CONFIG_X86_64 module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #endif extern bool __read_mostly allow_smaller_maxphyaddr; module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) #define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM)) #define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \ RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \ RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \ RTIT_STATUS_BYTECNT)) /* * List of MSRs that can be directly passed to the guest. * In addition to these x2apic, PT and LBR MSRs are handled specially. */ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, MSR_IA32_PRED_CMD, MSR_IA32_FLUSH_CMD, MSR_IA32_TSC, #ifdef CONFIG_X86_64 MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE, MSR_IA32_XFD, MSR_IA32_XFD_ERR, #endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_CORE_C1_RES, MSR_CORE_C3_RESIDENCY, MSR_CORE_C6_RESIDENCY, MSR_CORE_C7_RESIDENCY, }; /* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive * executions of PAUSE in a loop. Also indicate if ple enabled. * According to test, this time is usually smaller than 128 cycles. * ple_window: upper bound on the amount of time a guest is allowed to execute * in a PAUSE loop. Tests indicate that most spinlocks are held for * less than 2^12 cycles * Time is measured based on a counter that runs at the same rate as the TSC, * refer SDM volume 3b section 21.6.13 & 22.1.3. */ static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP; module_param(ple_gap, uint, 0444); static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, uint, 0444); /* Default doubles per-vcpu window every exit. */ static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW; module_param(ple_window_grow, uint, 0444); /* Default resets per-vcpu window every exit to ple_window. */ static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK; module_param(ple_window_shrink, uint, 0444); /* Default is to compute the maximum so we can never overflow. */ static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; module_param(ple_window_max, uint, 0444); /* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */ int __read_mostly pt_mode = PT_MODE_SYSTEM; #ifdef CONFIG_BROKEN module_param(pt_mode, int, S_IRUGO); #endif struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); /* Storage for pre module init parameter parsing */ static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO; static const struct { const char *option; bool for_parse; } vmentry_l1d_param[] = { [VMENTER_L1D_FLUSH_AUTO] = {"auto", true}, [VMENTER_L1D_FLUSH_NEVER] = {"never", true}, [VMENTER_L1D_FLUSH_COND] = {"cond", true}, [VMENTER_L1D_FLUSH_ALWAYS] = {"always", true}, [VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false}, [VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false}, }; #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; unsigned int i; if (!boot_cpu_has_bug(X86_BUG_L1TF)) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; return 0; } if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; } if (kvm_host.arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; return 0; } /* If set to auto use the default l1tf mitigation method */ if (l1tf == VMENTER_L1D_FLUSH_AUTO) { switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: l1tf = VMENTER_L1D_FLUSH_NEVER; break; case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH_NOWARN: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: l1tf = VMENTER_L1D_FLUSH_COND; break; case L1TF_MITIGATION_FULL: case L1TF_MITIGATION_FULL_FORCE: l1tf = VMENTER_L1D_FLUSH_ALWAYS; break; } } else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) { l1tf = VMENTER_L1D_FLUSH_ALWAYS; } if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { /* * This allocation for vmx_l1d_flush_pages is not tied to a VM * lifetime and so should not be charged to a memcg. */ page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); if (!page) return -ENOMEM; vmx_l1d_flush_pages = page_address(page); /* * Initialize each page with a different pattern in * order to protect against KSM in the nested * virtualization case. */ for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) { memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1, PAGE_SIZE); } } l1tf_vmx_mitigation = l1tf; if (l1tf != VMENTER_L1D_FLUSH_NEVER) static_branch_enable(&vmx_l1d_should_flush); else static_branch_disable(&vmx_l1d_should_flush); if (l1tf == VMENTER_L1D_FLUSH_COND) static_branch_enable(&vmx_l1d_flush_cond); else static_branch_disable(&vmx_l1d_flush_cond); return 0; } static int vmentry_l1d_flush_parse(const char *s) { unsigned int i; if (s) { for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { if (vmentry_l1d_param[i].for_parse && sysfs_streq(s, vmentry_l1d_param[i].option)) return i; } } return -EINVAL; } static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) { int l1tf, ret; l1tf = vmentry_l1d_flush_parse(s); if (l1tf < 0) return l1tf; if (!boot_cpu_has(X86_BUG_L1TF)) return 0; /* * Has vmx_init() run already? If not then this is the pre init * parameter parsing. In that case just store the value and let * vmx_init() do the proper setup after enable_ept has been * established. */ if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) { vmentry_l1d_flush_param = l1tf; return 0; } mutex_lock(&vmx_l1d_flush_mutex); ret = vmx_setup_l1d_flush(l1tf); mutex_unlock(&vmx_l1d_flush_mutex); return ret; } static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) { if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param))) return sysfs_emit(s, "???\n"); return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) { u64 msr; if (!vmx->disable_fb_clear) return; msr = native_rdmsrq(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) { if (!vmx->disable_fb_clear) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); } static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { /* * Disable VERW's behavior of clearing CPU buffers for the guest if the * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled * the mitigation. Disabling the clearing behavior provides a * performance boost for guests that aren't aware that manually clearing * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry * and VM-Exit. */ vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && (kvm_host.arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA); /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS * at VMEntry. Skip the MSR read/write when a guest has no use case to * execute VERW. */ if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) || ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) && (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO))) vmx->disable_fb_clear = false; } static const struct kernel_param_ops vmentry_l1d_flush_ops = { .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, }; module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); static u32 vmx_segment_access_rights(struct kvm_segment *var); void vmx_vmexit(void); #define vmx_insn_failed(fmt...) \ do { \ WARN_ONCE(1, fmt); \ pr_warn_ratelimited(fmt); \ } while (0) noinline void vmread_error(unsigned long field) { vmx_insn_failed("vmread failed: field=%lx\n", field); } #ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT noinstr void vmread_error_trampoline2(unsigned long field, bool fault) { if (fault) { kvm_spurious_fault(); } else { instrumentation_begin(); vmread_error(field); instrumentation_end(); } } #endif noinline void vmwrite_error(unsigned long field, unsigned long value) { vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) { vmx_insn_failed("vmclear failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) { vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) { vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", ext, vpid, gva); } noinline void invept_error(unsigned long ext, u64 eptp) { vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx\n", ext, eptp); } static DEFINE_PER_CPU(struct vmcs *, vmxarea); DEFINE_PER_CPU(struct vmcs *, current_vmcs); /* * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. */ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); struct vmcs_config vmcs_config __ro_after_init; struct vmx_capability vmx_capability __ro_after_init; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ .selector = GUEST_##seg##_SELECTOR, \ .base = GUEST_##seg##_BASE, \ .limit = GUEST_##seg##_LIMIT, \ .ar_bytes = GUEST_##seg##_AR_BYTES, \ } static const struct kvm_vmx_segment_field { unsigned selector; unsigned base; unsigned limit; unsigned ar_bytes; } kvm_vmx_segment_fields[] = { VMX_SEGMENT_FIELD(CS), VMX_SEGMENT_FIELD(DS), VMX_SEGMENT_FIELD(ES), VMX_SEGMENT_FIELD(FS), VMX_SEGMENT_FIELD(GS), VMX_SEGMENT_FIELD(SS), VMX_SEGMENT_FIELD(TR), VMX_SEGMENT_FIELD(LDTR), }; static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); if (partition_assist_page == INVALID_PAGE) return -ENOMEM; evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; evmcs->partition_assist_page = partition_assist_page; evmcs->hv_vm_id = (unsigned long)vcpu->kvm; evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; return 0; } static __init void hv_init_evmcs(void) { int cpu; if (!enlightened_vmcs) return; /* * Enlightened VMCS usage should be recommended and the host needs * to support eVMCS v1 or above. */ if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= KVM_EVMCS_VERSION) { /* Check that we have assist pages on all online CPUs */ for_each_online_cpu(cpu) { if (!hv_get_vp_assist_page(cpu)) { enlightened_vmcs = false; break; } } if (enlightened_vmcs) { pr_info("Using Hyper-V Enlightened VMCS\n"); static_branch_enable(&__kvm_is_using_evmcs); } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) vt_x86_ops.enable_l2_tlb_flush = hv_enable_l2_tlb_flush; } else { enlightened_vmcs = false; } } static void hv_reset_evmcs(void) { struct hv_vp_assist_page *vp_ap; if (!kvm_is_using_evmcs()) return; /* * KVM should enable eVMCS if and only if all CPUs have a VP assist * page, and should reject CPU onlining if eVMCS is enabled the CPU * doesn't have a VP assist page allocated. */ vp_ap = hv_get_vp_assist_page(smp_processor_id()); if (WARN_ON_ONCE(!vp_ap)) return; /* * Reset everything to support using non-enlightened VMCS access later * (e.g. when we reload the module with enlightened_vmcs=0) */ vp_ap->nested_control.features.directhypercall = 0; vp_ap->current_nested_vmcs = 0; vp_ap->enlighten_vmentry = 0; } #else /* IS_ENABLED(CONFIG_HYPERV) */ static void hv_init_evmcs(void) {} static void hv_reset_evmcs(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* * Comment's format: document - errata name - stepping - processor name. * Refer from * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp */ static u32 vmx_preemption_cpu_tfms[] = { /* 323344.pdf - BA86 - D0 - Xeon 7500 Series */ 0x000206E6, /* 323056.pdf - AAX65 - C2 - Xeon L3406 */ /* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */ /* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */ 0x00020652, /* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */ 0x00020655, /* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */ /* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */ /* * 320767.pdf - AAP86 - B1 - * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile */ 0x000106E5, /* 321333.pdf - AAM126 - C0 - Xeon 3500 */ 0x000106A0, /* 321333.pdf - AAM126 - C1 - Xeon 3500 */ 0x000106A1, /* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */ 0x000106A4, /* 321333.pdf - AAM126 - D0 - Xeon 3500 */ /* 321324.pdf - AAK139 - D0 - Xeon 5500 */ /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */ 0x000106A5, /* Xeon E3-1220 V2 */ 0x000306A8, }; static inline bool cpu_has_broken_vmx_preemption_timer(void) { u32 eax = cpuid_eax(0x00000001), i; /* Clear the reserved bits */ eax &= ~(0x3U << 14 | 0xfU << 28); for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++) if (eax == vmx_preemption_cpu_tfms[i]) return true; return false; } static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) { return flexpriority_enabled && lapic_in_kernel(vcpu); } static int vmx_get_passthrough_msr_slot(u32 msr) { int i; switch (msr) { case 0x800 ... 0x8ff: /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */ return -ENOENT; case MSR_IA32_RTIT_STATUS: case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: case MSR_IA32_RTIT_CR3_MATCH: case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: /* PT MSRs. These are handled in pt_update_intercept_for_msr() */ case MSR_LBR_SELECT: case MSR_LBR_TOS: case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31: case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31: case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31: case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ return -ENOENT; } for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { if (vmx_possible_passthrough_msrs[i] == msr) return i; } WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); return -ENOENT; } struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; i = kvm_find_user_return_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; } static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, struct vmx_uret_msr *msr, u64 data) { unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; if (msr->load_into_hardware) { preempt_disable(); ret = kvm_set_user_return_msr(slot, data, msr->mask); preempt_enable(); } if (!ret) msr->data = data; return ret; } /* * Disable VMX and clear CR4.VMXE (even if VMXOFF faults) * * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to * atomically track post-VMXON state, e.g. this may be called in NMI context. * Eat all faults as all other faults on VMXOFF faults are mode related, i.e. * faults are guaranteed to be due to the !post-VMXON check unless the CPU is * magically in RM, VM86, compat mode, or at CPL>0. */ static int kvm_cpu_vmxoff(void) { asm goto("1: vmxoff\n\t" _ASM_EXTABLE(1b, %l[fault]) ::: "cc", "memory" : fault); cr4_clear_bits(X86_CR4_VMXE); return 0; fault: cr4_clear_bits(X86_CR4_VMXE); return -EIO; } void vmx_emergency_disable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; kvm_rebooting = true; /* * Note, CR4.VMXE can be _cleared_ in NMI context, but it can only be * set in task context. If this races with VMX is disabled by an NMI, * VMCLEAR and VMXOFF may #UD, but KVM will eat those faults due to * kvm_rebooting set. */ if (!(__read_cr4() & X86_CR4_VMXE)) return; list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) { vmcs_clear(v->vmcs); if (v->shadow_vmcs) vmcs_clear(v->shadow_vmcs); } kvm_cpu_vmxoff(); } static void __loaded_vmcs_clear(void *arg) { struct loaded_vmcs *loaded_vmcs = arg; int cpu = raw_smp_processor_id(); if (loaded_vmcs->cpu != cpu) return; /* vcpu migration can race with cpu offline */ if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; vmcs_clear(loaded_vmcs->vmcs); if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) vmcs_clear(loaded_vmcs->shadow_vmcs); list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); /* * Ensure all writes to loaded_vmcs, including deleting it from its * current percpu list, complete before setting loaded_vmcs->cpu to * -1, otherwise a different cpu can see loaded_vmcs->cpu == -1 first * and add loaded_vmcs to its percpu list before it's deleted from this * cpu's list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs(). */ smp_wmb(); loaded_vmcs->cpu = -1; loaded_vmcs->launched = 0; } void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) { int cpu = loaded_vmcs->cpu; if (cpu != -1) smp_call_function_single(cpu, __loaded_vmcs_clear, loaded_vmcs, 1); } static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, unsigned field) { bool ret; u32 mask = 1 << (seg * SEG_FIELD_NR + field); if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) { kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS); vmx->segment_cache.bitmask = 0; } ret = vmx->segment_cache.bitmask & mask; vmx->segment_cache.bitmask |= mask; return ret; } static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg) { u16 *p = &vmx->segment_cache.seg[seg].selector; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL)) *p = vmcs_read16(kvm_vmx_segment_fields[seg].selector); return *p; } static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg) { ulong *p = &vmx->segment_cache.seg[seg].base; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE)) *p = vmcs_readl(kvm_vmx_segment_fields[seg].base); return *p; } static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg) { u32 *p = &vmx->segment_cache.seg[seg].limit; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT)) *p = vmcs_read32(kvm_vmx_segment_fields[seg].limit); return *p; } static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) { u32 *p = &vmx->segment_cache.seg[seg].ar; if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR)) *p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes); return *p; } void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); /* * #VE isn't used for VMX. To test against unexpected changes * related to #VE for VMX, intercept unexpected #VE and warn on it. */ if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) eb |= 1u << VE_VECTOR; /* * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway * as VMware does. */ if (enable_vmware_backdoor) eb |= (1u << GP_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) eb |= 1u << BP_VECTOR; if (to_vmx(vcpu)->rmode.vm86_active) eb = ~0; if (!vmx_need_pf_intercept(vcpu)) eb &= ~(1u << PF_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass * them to L1. When running L2, we will only handle the exceptions * specified above if L1 did not want them. */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; else { int mask = 0, match = 0; if (enable_ept && (eb & (1u << PF_VECTOR))) { /* * If EPT is enabled, #PF is currently only intercepted * if MAXPHYADDR is smaller on the guest than on the * host. In that case we only care about present, * non-reserved faults. For vmcs02, however, PFEC_MASK * and PFEC_MATCH are set in prepare_vmcs02_rare. */ mask = PFERR_PRESENT_MASK | PFERR_RSVD_MASK; match = PFERR_PRESENT_MASK; } vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match); } /* * Disabling xfd interception indicates that dynamic xfeatures * might be used in the guest. Always trap #NM in this case * to save guest xfd_err timely. */ if (vcpu->arch.xfd_no_write_intercept) eb |= (1u << NM_VECTOR); vmcs_write32(EXCEPTION_BITMAP, eb); } /* * Check if MSR is intercepted for currently loaded MSR bitmap. */ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) { if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr); } unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) { unsigned int flags = 0; if (vmx->loaded_vmcs->launched) flags |= VMX_RUN_VMRESUME; /* * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free * to change it directly without causing a vmexit. In that case read * it after vmexit and store it in vmx->spec_ctrl. */ if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= VMX_RUN_SAVE_SPEC_CTRL; return flags; } static __always_inline void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { vm_entry_controls_clearbit(vmx, entry); vm_exit_controls_clearbit(vmx, exit); } int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr) { unsigned int i; for (i = 0; i < m->nr; ++i) { if (m->val[i].index == msr) return i; } return -ENOENT; } static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) { int i; struct msr_autoload *m = &vmx->msr_autoload; switch (msr) { case MSR_EFER: if (cpu_has_load_ia32_efer()) { clear_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER); return; } break; case MSR_CORE_PERF_GLOBAL_CTRL: if (cpu_has_load_perf_global_ctrl()) { clear_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); return; } break; } i = vmx_find_loadstore_msr_slot(&m->guest, msr); if (i < 0) goto skip_guest; --m->guest.nr; m->guest.val[i] = m->guest.val[m->guest.nr]; vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); skip_guest: i = vmx_find_loadstore_msr_slot(&m->host, msr); if (i < 0) return; --m->host.nr; m->host.val[i] = m->host.val[m->host.nr]; vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } static __always_inline void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit, unsigned long guest_val_vmcs, unsigned long host_val_vmcs, u64 guest_val, u64 host_val) { vmcs_write64(guest_val_vmcs, guest_val); if (host_val_vmcs != HOST_IA32_EFER) vmcs_write64(host_val_vmcs, host_val); vm_entry_controls_setbit(vmx, entry); vm_exit_controls_setbit(vmx, exit); } static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, u64 guest_val, u64 host_val, bool entry_only) { int i, j = 0; struct msr_autoload *m = &vmx->msr_autoload; switch (msr) { case MSR_EFER: if (cpu_has_load_ia32_efer()) { add_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER, GUEST_IA32_EFER, HOST_IA32_EFER, guest_val, host_val); return; } break; case MSR_CORE_PERF_GLOBAL_CTRL: if (cpu_has_load_perf_global_ctrl()) { add_atomic_switch_msr_special(vmx, VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL, GUEST_IA32_PERF_GLOBAL_CTRL, HOST_IA32_PERF_GLOBAL_CTRL, guest_val, host_val); return; } break; case MSR_IA32_PEBS_ENABLE: /* PEBS needs a quiescent period after being disabled (to write * a record). Disabling PEBS through VMX MSR swapping doesn't * provide that period, so a CPU could write host's record into * guest's memory. */ wrmsrq(MSR_IA32_PEBS_ENABLE, 0); } i = vmx_find_loadstore_msr_slot(&m->guest, msr); if (!entry_only) j = vmx_find_loadstore_msr_slot(&m->host, msr); if ((i < 0 && m->guest.nr == MAX_NR_LOADSTORE_MSRS) || (j < 0 && m->host.nr == MAX_NR_LOADSTORE_MSRS)) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; } if (i < 0) { i = m->guest.nr++; vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); } m->guest.val[i].index = msr; m->guest.val[i].value = guest_val; if (entry_only) return; if (j < 0) { j = m->host.nr++; vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } m->host.val[j].index = msr; m->host.val[j].value = host_val; } static bool update_transition_efer(struct vcpu_vmx *vmx) { u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; int i; /* Shadow paging assumes NX to be available. */ if (!enable_ept) guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. */ ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif /* * On EPT, we can't emulate NX, so we must switch EFER atomically. * On CPUs that support "load IA32_EFER", always switch EFER * atomically, since it's faster than switching it manually. */ if (cpu_has_load_ia32_efer() || (enable_ept && ((vmx->vcpu.arch.efer ^ kvm_host.efer) & EFER_NX))) { if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != kvm_host.efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, kvm_host.efer, false); else clear_atomic_switch_msr(vmx, MSR_EFER); return false; } i = kvm_find_user_return_msr(MSR_EFER); if (i < 0) return false; clear_atomic_switch_msr(vmx, MSR_EFER); guest_efer &= ~ignore_bits; guest_efer |= kvm_host.efer & ignore_bits; vmx->guest_uret_msrs[i].data = guest_efer; vmx->guest_uret_msrs[i].mask = ~ignore_bits; return true; } #ifdef CONFIG_X86_32 /* * On 32-bit kernels, VM exits still load the FS and GS bases from the * VMCS rather than the segment table. KVM uses this helper to figure * out the current bases to poke them into the VMCS before entry. */ static unsigned long segment_base(u16 selector) { struct desc_struct *table; unsigned long v; if (!(selector & ~SEGMENT_RPL_MASK)) return 0; table = get_current_gdt_ro(); if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); if (!(ldt_selector & ~SEGMENT_RPL_MASK)) return 0; table = (struct desc_struct *)segment_base(ldt_selector); } v = get_desc_base(&table[selector >> 3]); return v; } #endif static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) { return vmx_pt_mode_is_host_guest() && !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); } static inline bool pt_output_base_valid(struct kvm_vcpu *vcpu, u64 base) { /* The base must be 128-byte aligned and a legal physical address. */ return kvm_vcpu_is_legal_aligned_gpa(vcpu, base, 128); } static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; wrmsrq(MSR_IA32_RTIT_STATUS, ctx->status); wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); wrmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { wrmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); wrmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; rdmsrq(MSR_IA32_RTIT_STATUS, ctx->status); rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); rdmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { rdmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); rdmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } static void pt_guest_enter(struct vcpu_vmx *vmx) { if (vmx_pt_mode_is_system()) return; /* * GUEST_IA32_RTIT_CTL is already set in the VMCS. * Save host state before VM entry. */ rdmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { wrmsrq(MSR_IA32_RTIT_CTL, 0); pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); } } static void pt_guest_exit(struct vcpu_vmx *vmx) { if (vmx_pt_mode_is_system()) return; if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); } /* * KVM requires VM_EXIT_CLEAR_IA32_RTIT_CTL to expose PT to the guest, * i.e. RTIT_CTL is always cleared on VM-Exit. Restore it if necessary. */ if (vmx->pt_desc.host.ctl) wrmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base) { if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); else vmcs_write16(HOST_FS_SELECTOR, 0); host->fs_sel = fs_sel; } if (unlikely(gs_sel != host->gs_sel)) { if (!(gs_sel & 7)) vmcs_write16(HOST_GS_SELECTOR, gs_sel); else vmcs_write16(HOST_GS_SELECTOR, 0); host->gs_sel = gs_sel; } if (unlikely(fs_base != host->fs_base)) { vmcs_writel(HOST_FS_BASE, fs_base); host->fs_base = fs_base; } if (unlikely(gs_base != host->gs_base)) { vmcs_writel(HOST_GS_BASE, gs_base); host->gs_base = gs_base; } } void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vcpu_vt *vt = to_vt(vcpu); struct vmcs_host_state *host_state; #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); #endif unsigned long fs_base, gs_base; u16 fs_sel, gs_sel; int i; /* * Note that guest MSRs to be saved/restored can also be changed * when guest state is loaded. This happens when guest transitions * to/from long-mode by setting MSR_EFER.LMA. */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; for (i = 0; i < kvm_nr_uret_msrs; ++i) { if (!vmx->guest_uret_msrs[i].load_into_hardware) continue; kvm_set_user_return_msr(i, vmx->guest_uret_msrs[i].data, vmx->guest_uret_msrs[i].mask); } } if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); if (vt->guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; /* * Set host fs and gs selectors. Unfortunately, 22.2.3 does not * allow segment selectors with cpl > 0 or ti == 1. */ host_state->ldt_sel = kvm_read_ldt(); #ifdef CONFIG_X86_64 savesegment(ds, host_state->ds_sel); savesegment(es, host_state->es_sel); gs_base = cpu_kernelmode_gs_base(cpu); if (likely(is_64bit_mm(current->mm))) { current_save_fsgs(); fs_sel = current->thread.fsindex; gs_sel = current->thread.gsindex; fs_base = current->thread.fsbase; vt->msr_host_kernel_gs_base = current->thread.gsbase; } else { savesegment(fs, fs_sel); savesegment(gs, gs_sel); fs_base = read_msr(MSR_FS_BASE); vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); fs_base = segment_base(fs_sel); gs_base = segment_base(gs_sel); #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); vt->guest_state_loaded = true; } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) { struct vmcs_host_state *host_state; if (!vmx->vt.guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; ++vmx->vcpu.stat.host_state_reload; #ifdef CONFIG_X86_64 rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); #ifdef CONFIG_X86_64 load_gs_index(host_state->gs_sel); #else loadsegment(gs, host_state->gs_sel); #endif } if (host_state->fs_sel & 7) loadsegment(fs, host_state->fs_sel); #ifdef CONFIG_X86_64 if (unlikely(host_state->ds_sel | host_state->es_sel)) { loadsegment(ds, host_state->ds_sel); loadsegment(es, host_state->es_sel); } #endif invalidate_tss_limit(); #ifdef CONFIG_X86_64 wrmsrq(MSR_KERNEL_GS_BASE, vmx->vt.msr_host_kernel_gs_base); #endif load_fixmap_gdt(raw_smp_processor_id()); vmx->vt.guest_state_loaded = false; vmx->guest_uret_msrs_loaded = false; } #ifdef CONFIG_X86_64 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { preempt_disable(); if (vmx->vt.guest_state_loaded) rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); preempt_enable(); return vmx->msr_guest_kernel_gs_base; } static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { preempt_disable(); if (vmx->vt.guest_state_loaded) wrmsrq(MSR_KERNEL_GS_BASE, data); preempt_enable(); vmx->msr_guest_kernel_gs_base = data; } #endif static void grow_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned int old = vmx->ple_window; vmx->ple_window = __grow_ple_window(old, ple_window, ple_window_grow, ple_window_max); if (vmx->ple_window != old) { vmx->ple_window_dirty = true; trace_kvm_ple_window_update(vcpu->vcpu_id, vmx->ple_window, old); } } static void shrink_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned int old = vmx->ple_window; vmx->ple_window = __shrink_ple_window(old, ple_window, ple_window_shrink, ple_window); if (vmx->ple_window != old) { vmx->ple_window_dirty = true; trace_kvm_ple_window_update(vcpu->vcpu_id, vmx->ple_window, old); } } void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; struct vmcs *prev; if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); /* * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to * this cpu's percpu list, otherwise it may not yet be deleted * from its previous cpu's percpu list. Pairs with the * smb_wmb() in __loaded_vmcs_clear(). */ smp_rmb(); list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, &per_cpu(loaded_vmcss_on_cpu, cpu)); local_irq_enable(); } prev = per_cpu(current_vmcs, cpu); if (prev != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); } if (!already_loaded) { void *gdt = get_current_gdt_ro(); /* * Flush all EPTP/VPID contexts, the new pCPU may have stale * TLB entries from its previous association with the vCPU. */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); /* * Linux uses per-cpu TSS and GDT, so set these when switching * processors. See 22.2.4. */ vmcs_writel(HOST_TR_BASE, (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) { /* 22.2.3 */ vmcs_writel(HOST_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); } vmx->loaded_vmcs->cpu = cpu; } } /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); vmx_vcpu_load_vmcs(vcpu, cpu); vmx_vcpu_pi_load(vcpu, cpu); } void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); vmx_prepare_switch_to_host(to_vmx(vcpu)); } bool vmx_emulation_required(struct kvm_vcpu *vcpu) { return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu); } unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long rflags, save_rflags; if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) { kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); rflags = vmcs_readl(GUEST_RFLAGS); if (vmx->rmode.vm86_active) { rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; save_rflags = vmx->rmode.save_rflags; rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; } vmx->rflags = rflags; } return vmx->rflags; } void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long old_rflags; /* * Unlike CR0 and CR4, RFLAGS handling requires checking if the vCPU * is an unrestricted guest in order to mark L2 as needing emulation * if L1 runs L2 as a restricted guest. */ if (is_unrestricted_guest(vcpu)) { kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); vmx->rflags = rflags; vmcs_writel(GUEST_RFLAGS, rflags); return; } old_rflags = vmx_get_rflags(vcpu); vmx->rflags = rflags; if (vmx->rmode.vm86_active) { vmx->rmode.save_rflags = rflags; rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; } vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) vmx->vt.emulation_required = vmx_emulation_required(vcpu); } bool vmx_get_if_flag(struct kvm_vcpu *vcpu) { return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); int ret = 0; if (interruptibility & GUEST_INTR_STATE_STI) ret |= KVM_X86_SHADOW_INT_STI; if (interruptibility & GUEST_INTR_STATE_MOV_SS) ret |= KVM_X86_SHADOW_INT_MOV_SS; return ret; } void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) { u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); u32 interruptibility = interruptibility_old; interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS); if (mask & KVM_X86_SHADOW_INT_MOV_SS) interruptibility |= GUEST_INTR_STATE_MOV_SS; else if (mask & KVM_X86_SHADOW_INT_STI) interruptibility |= GUEST_INTR_STATE_STI; if ((interruptibility != interruptibility_old)) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility); } static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long value; /* * Any MSR write that attempts to change bits marked reserved will * case a #GP fault. */ if (data & vmx->pt_desc.ctl_bitmask) return 1; /* * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will * result in a #GP unless the same write also clears TraceEn. */ if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && (data & RTIT_CTL_TRACEEN) && data != vmx->pt_desc.guest.ctl) return 1; /* * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit * and FabricEn would cause #GP, if * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0 */ if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) && !(data & RTIT_CTL_FABRIC_EN) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output)) return 1; /* * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that * utilize encodings marked reserved will cause a #GP fault. */ value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && !test_bit((data & RTIT_CTL_MTC_RANGE) >> RTIT_CTL_MTC_RANGE_OFFSET, &value)) return 1; value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cycle_thresholds); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && !test_bit((data & RTIT_CTL_CYC_THRESH) >> RTIT_CTL_CYC_THRESH_OFFSET, &value)) return 1; value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && !test_bit((data & RTIT_CTL_PSB_FREQ) >> RTIT_CTL_PSB_FREQ_OFFSET, &value)) return 1; /* * If ADDRx_CFG is reserved or the encodings is >2 will * cause a #GP fault. */ value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 1)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 2)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 3)) || (value > 2)) return 1; value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET; if ((value && (vmx->pt_desc.num_address_ranges < 4)) || (value > 2)) return 1; return 0; } int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does * not point at the failing instruction, and even if it did, the code * stream is inaccessible. Inject #UD instead of exiting to userspace * so that guest userspace can't DoS the guest simply by triggering * emulation (enclaves are CPL3 only). */ if (vmx_get_exit_reason(vcpu).enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); return X86EMUL_PROPAGATE_FAULT; } /* Check that emulation is possible during event vectoring */ if ((to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && !kvm_can_emulate_event_vectoring(emul_type)) return X86EMUL_UNHANDLEABLE_VECTORING; return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); unsigned long rip, orig_rip; u32 instr_len; /* * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on * undefined behavior: Intel's SDM doesn't mandate the VMCS field be * set when EPT misconfig occurs. In practice, real hardware updates * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors * (namely Hyper-V) don't set it due to it being undefined behavior, * i.e. we end up advancing IP with some random value. */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || exit_reason.basic != EXIT_REASON_EPT_MISCONFIG) { instr_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); /* * Emulating an enclave's instructions isn't supported as KVM * cannot access the enclave's memory or its true RIP, e.g. the * vmcs.GUEST_RIP points at the exit point of the enclave, not * the RIP that actually triggered the VM-Exit. But, because * most instructions that cause VM-Exit will #UD in an enclave, * most instruction-based VM-Exits simply do not occur. * * There are a few exceptions, notably the debug instructions * INT1ICEBRK and INT3, as they are allowed in debug enclaves * and generate #DB/#BP as expected, which KVM might intercept. * But again, the CPU does the dirty work and saves an instr * length of zero so VMMs don't shoot themselves in the foot. * WARN if KVM tries to skip a non-zero length instruction on * a VM-Exit from an enclave. */ if (!instr_len) goto rip_updated; WARN_ONCE(exit_reason.enclave_mode, "skipping instruction after SGX enclave VM-Exit"); orig_rip = kvm_rip_read(vcpu); rip = orig_rip + instr_len; #ifdef CONFIG_X86_64 /* * We need to mask out the high 32 bits of RIP if not in 64-bit * mode, but just finding out that we are in 64-bit mode is * quite expensive. Only do it if there was a carry. */ if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu)) rip = (u32)rip; #endif kvm_rip_write(vcpu, rip); } else { if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) return 0; } rip_updated: /* skipping an emulated instruction also counts */ vmx_set_interrupt_shadow(vcpu, 0); return 1; } /* * Recognizes a pending MTF VM-exit and records the nested state for later * delivery. */ void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); if (!is_guest_mode(vcpu)) return; /* * Per the SDM, MTF takes priority over debug-trap exceptions besides * TSS T-bit traps and ICEBP (INT1). KVM doesn't emulate T-bit traps * or ICEBP (in the emulator proper), and skipping of ICEBP after an * intercepted #DB deliberately avoids single-step #DB and MTF updates * as ICEBP is higher priority than both. As instruction emulation is * completed at this point (i.e. KVM is at the instruction boundary), * any #DB exception pending delivery must be a debug-trap of lower * priority than MTF. Record the pending MTF state to be delivered in * vmx_check_nested_events(). */ if (nested_cpu_has_mtf(vmcs12) && (!vcpu->arch.exception.pending || vcpu->arch.exception.vector == DB_VECTOR) && (!vcpu->arch.exception_vmexit.pending || vcpu->arch.exception_vmexit.vector == DB_VECTOR)) { vmx->nested.mtf_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); } else { vmx->nested.mtf_pending = false; } } int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) { vmx_update_emulated_instruction(vcpu); return skip_emulated_instruction(vcpu); } static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* * Ensure that we clear the HLT state in the VMCS. We don't need to * explicitly skip the instruction because if the HLT state is set, * then the instruction is already executing and RIP has already been * advanced. */ if (kvm_hlt_in_guest(vcpu->kvm) && vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } void vmx_inject_exception(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vcpu_vmx *vmx = to_vmx(vcpu); kvm_deliver_exception_payload(vcpu, ex); if (ex->has_error_code) { /* * Despite the error code being architecturally defined as 32 * bits, and the VMCS field being 32 bits, Intel CPUs and thus * VMX don't actually supporting setting bits 31:16. Hardware * will (should) never provide a bogus error code, but AMD CPUs * do generate error codes with bits 31:16 set, and so KVM's * ABI lets userspace shove in arbitrary 32-bit values. Drop * the upper bits to avoid VM-Fail, losing information that * doesn't really exist is preferable to killing the VM. */ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } if (vmx->rmode.vm86_active) { int inc_eip = 0; if (kvm_exception_is_soft(ex->vector)) inc_eip = vcpu->arch.event_exit_inst_len; kvm_inject_realmode_interrupt(vcpu, ex->vector, inc_eip); return; } WARN_ON_ONCE(vmx->vt.emulation_required); if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); intr_info |= INTR_TYPE_SOFT_EXCEPTION; } else intr_info |= INTR_TYPE_HARD_EXCEPTION; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); vmx_clear_hlt(vcpu); } static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, bool load_into_hardware) { struct vmx_uret_msr *uret_msr; uret_msr = vmx_find_uret_msr(vmx, msr); if (!uret_msr) return; uret_msr->load_into_hardware = load_into_hardware; } /* * Configuring user return MSRs to automatically save, load, and restore MSRs * that need to be shoved into hardware when running the guest. Note, omitting * an MSR here does _NOT_ mean it's not emulated, only that it will not be * loaded into hardware when running the guest. */ static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) { #ifdef CONFIG_X86_64 bool load_syscall_msrs; /* * The SYSCALL MSRs are only needed on long mode guests, and only * when EFER.SCE is set. */ load_syscall_msrs = is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE); vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs); vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs); vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs); #endif vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); vmx_setup_uret_msr(vmx, MSR_TSC_AUX, guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDPID)); /* * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new * kernel and old userspace. If those guests run on a tsx=off host, do * allow guests to use TSX_CTRL, but don't change the value in hardware * so that TSX remains always disabled. */ vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); /* * The set of MSRs to load may have changed, reload MSRs before the * next VM-Enter. */ vmx->guest_uret_msrs_loaded = false; } u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING)) return vmcs12->tsc_offset; return 0; } u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETTING) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) return vmcs12->tsc_multiplier; return kvm_caps.default_tsc_scaling_ratio; } void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } /* * Userspace is allowed to set any supported IA32_FEATURE_CONTROL regardless of * guest CPUID. Note, KVM allows userspace to set "VMX in SMX" to maintain * backwards compatibility even though KVM doesn't support emulating SMX. And * because userspace set "VMX in SMX", the guest must also be allowed to set it, * e.g. if the MSR is left unlocked and the guest does a RMW operation. */ #define KVM_SUPPORTED_FEATURE_CONTROL (FEAT_CTL_LOCKED | \ FEAT_CTL_VMX_ENABLED_INSIDE_SMX | \ FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX | \ FEAT_CTL_SGX_LC_ENABLED | \ FEAT_CTL_SGX_ENABLED | \ FEAT_CTL_LMCE_ENABLED) static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, struct msr_data *msr) { uint64_t valid_bits; /* * Ensure KVM_SUPPORTED_FEATURE_CONTROL is updated when new bits are * exposed to the guest. */ WARN_ON_ONCE(vmx->msr_ia32_feature_control_valid_bits & ~KVM_SUPPORTED_FEATURE_CONTROL); if (!msr->host_initiated && (vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED)) return false; if (msr->host_initiated) valid_bits = KVM_SUPPORTED_FEATURE_CONTROL; else valid_bits = vmx->msr_ia32_feature_control_valid_bits; return !(msr->data & ~valid_bits); } int vmx_get_feature_msr(u32 msr, u64 *data) { switch (msr) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: return KVM_MSR_RET_UNSUPPORTED; } } /* * Reads an msr value (of 'msr_info->index') into 'msr_info->data'. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; u32 index; switch (msr_info->index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: msr_info->data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: msr_info->data = vmx_read_guest_kernel_gs_base(vmx); break; #endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSX_CTRL: if (!msr_info->host_initiated && !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) return 1; goto find_uret_msr; case MSR_IA32_UMWAIT_CONTROL: if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) return 1; msr_info->data = vmx->msr_ia32_umwait_control; break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_has_spec_ctrl_msr(vcpu)) return 1; msr_info->data = to_vmx(vcpu)->spec_ctrl; break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; case MSR_IA32_MCG_EXT_CTL: if (!msr_info->host_initiated && !(vmx->msr_ia32_feature_control & FEAT_CTL_LMCE_ENABLED)) return 1; msr_info->data = vcpu->arch.mcg_ext_ctl; break; case MSR_IA32_FEAT_CTL: msr_info->data = vmx->msr_ia32_feature_control; break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) return 1; msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; #ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V * versions are either trying to use them and fail or do some * sanity checking and refuse to boot. Filter all unsupported * features out. */ if (!msr_info->host_initiated && guest_cpu_cap_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); #endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.ctl; break; case MSR_IA32_RTIT_STATUS: if (!vmx_pt_mode_is_host_guest()) return 1; msr_info->data = vmx->pt_desc.guest.status; break; case MSR_IA32_RTIT_CR3_MATCH: if (!vmx_pt_mode_is_host_guest() || !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) return 1; msr_info->data = vmx->pt_desc.guest.cr3_match; break; case MSR_IA32_RTIT_OUTPUT_BASE: if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output))) return 1; msr_info->data = vmx->pt_desc.guest.output_base; break; case MSR_IA32_RTIT_OUTPUT_MASK: if (!vmx_pt_mode_is_host_guest() || (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output))) return 1; msr_info->data = vmx->pt_desc.guest.output_mask; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (!vmx_pt_mode_is_host_guest() || (index >= 2 * vmx->pt_desc.num_address_ranges)) return 1; if (index % 2) msr_info->data = vmx->pt_desc.guest.addr_b[index / 2]; else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); break; default: find_uret_msr: msr = vmx_find_uret_msr(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; break; } return kvm_get_msr_common(vcpu, msr_info); } return 0; } static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, u64 data) { #ifdef CONFIG_X86_64 if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return (u32)data; #endif return (unsigned long)data; } static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0; if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; int ret = 0; u32 msr_index = msr_info->index; u64 data = msr_info->data; u32 index; switch (msr_index) { case MSR_EFER: ret = kvm_set_msr_common(vcpu, msr_info); break; #ifdef CONFIG_X86_64 case MSR_FS_BASE: vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_FS_BASE, data); break; case MSR_GS_BASE: vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_GS_BASE, data); break; case MSR_KERNEL_GS_BASE: vmx_write_guest_kernel_gs_base(vmx, data); break; case MSR_IA32_XFD: ret = kvm_set_msr_common(vcpu, msr_info); /* * Always intercepting WRMSR could incur non-negligible * overhead given xfd might be changed frequently in * guest context switch. Disable write interception * upon the first write with a non-zero value (indicating * potential usage on dynamic xfeatures). Also update * exception bitmap to trap #NM for proper virtualization * of guest xfd_err. */ if (!ret && data) { vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW); vcpu->arch.xfd_no_write_intercept = true; vmx_update_exception_bitmap(vcpu); } break; #endif case MSR_IA32_SYSENTER_CS: if (is_guest_mode(vcpu)) get_vmcs12(vcpu)->guest_sysenter_cs = data; vmcs_write32(GUEST_SYSENTER_CS, data); break; case MSR_IA32_SYSENTER_EIP: if (is_guest_mode(vcpu)) { data = nested_vmx_truncate_sysenter_addr(vcpu, data); get_vmcs12(vcpu)->guest_sysenter_eip = data; } vmcs_writel(GUEST_SYSENTER_EIP, data); break; case MSR_IA32_SYSENTER_ESP: if (is_guest_mode(vcpu)) { data = nested_vmx_truncate_sysenter_addr(vcpu, data); get_vmcs12(vcpu)->guest_sysenter_esp = data; } vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: { u64 invalid; invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); } if (invalid) return 1; if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; vmcs_write64(GUEST_IA32_DEBUGCTL, data); if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; if (is_guest_mode(vcpu) && ((vmx->nested.msrs.entry_ctls_high & VM_ENTRY_LOAD_BNDCFGS) || (vmx->nested.msrs.exit_ctls_high & VM_EXIT_CLEAR_BNDCFGS))) get_vmcs12(vcpu)->guest_bndcfgs = data; vmcs_write64(GUEST_BNDCFGS, data); break; case MSR_IA32_UMWAIT_CONTROL: if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) return 1; /* The reserved bit 1 and non-32 bit [63:32] should be zero */ if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32))) return 1; vmx->msr_ia32_umwait_control = data; break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && !guest_has_spec_ctrl_msr(vcpu)) return 1; if (kvm_spec_ctrl_test_value(data)) return 1; vmx->spec_ctrl = data; if (!data) break; /* * For non-nested: * When it's written (to non-zero) for the first time, pass * it through. * * For nested: * The handling of the MSR bitmap for L2 guests is done in * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. We update the vmcs01 here for L1 as well * since it will end up touching the MSR anyway now. */ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); break; case MSR_IA32_TSX_CTRL: if (!msr_info->host_initiated && !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) return 1; if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) return 1; goto find_uret_msr; case MSR_IA32_CR_PAT: ret = kvm_set_msr_common(vcpu, msr_info); if (ret) break; if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) get_vmcs12(vcpu)->guest_ia32_pat = data; if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, data); break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && !(to_vmx(vcpu)->msr_ia32_feature_control & FEAT_CTL_LMCE_ENABLED)) || (data & ~MCG_EXT_CTL_LMCE_EN)) return 1; vcpu->arch.mcg_ext_ctl = data; break; case MSR_IA32_FEAT_CTL: if (!is_vmx_feature_control_msr_valid(vmx, msr_info)) return 1; vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) vmx_leave_nested(vcpu); /* SGX may be enabled/disabled by guest's firmware */ vmx_write_encls_bitmap(vcpu, NULL); break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: /* * On real hardware, the LE hash MSRs are writable before * the firmware sets bit 0 in MSR 0x7a ("activating" SGX), * at which point SGX related bits in IA32_FEATURE_CONTROL * become writable. * * KVM does not emulate SGX activation for simplicity, so * allow writes to the LE hash MSRs if IA32_FEATURE_CONTROL * is unlocked. This is technically not architectural * behavior, but it's close enough. */ if (!msr_info->host_initiated && (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC) || ((vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED) && !(vmx->msr_ia32_feature_control & FEAT_CTL_SGX_LC_ENABLED)))) return 1; vmx->msr_ia32_sgxlepubkeyhash [msr_index - MSR_IA32_SGXLEPUBKEYHASH0] = data; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest() || vmx_rtit_ctl_check(vcpu, data) || vmx->nested.vmxon) return 1; vmcs_write64(GUEST_IA32_RTIT_CTL, data); vmx->pt_desc.guest.ctl = data; pt_update_intercept_for_msr(vcpu); break; case MSR_IA32_RTIT_STATUS: if (!pt_can_write_msr(vmx)) return 1; if (data & MSR_IA32_RTIT_STATUS_MASK) return 1; vmx->pt_desc.guest.status = data; break; case MSR_IA32_RTIT_CR3_MATCH: if (!pt_can_write_msr(vmx)) return 1; if (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) return 1; vmx->pt_desc.guest.cr3_match = data; break; case MSR_IA32_RTIT_OUTPUT_BASE: if (!pt_can_write_msr(vmx)) return 1; if (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output)) return 1; if (!pt_output_base_valid(vcpu, data)) return 1; vmx->pt_desc.guest.output_base = data; break; case MSR_IA32_RTIT_OUTPUT_MASK: if (!pt_can_write_msr(vmx)) return 1; if (!intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output) && !intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_single_range_output)) return 1; vmx->pt_desc.guest.output_mask = data; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: if (!pt_can_write_msr(vmx)) return 1; index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; if (is_noncanonical_msr_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; else vmx->pt_desc.guest.addr_a[index / 2] = data; break; case MSR_IA32_PERF_CAPABILITIES: if (data & PMU_CAP_LBR_FMT) { if ((data & PMU_CAP_LBR_FMT) != (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; } if (data & PERF_CAP_PEBS_FORMAT) { if ((data & PERF_CAP_PEBS_MASK) != (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DS)) return 1; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DTES64)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; } ret = kvm_set_msr_common(vcpu, msr_info); break; default: find_uret_msr: msr = vmx_find_uret_msr(vmx, msr_index); if (msr) ret = vmx_set_guest_uret_msr(vmx, msr, data); else ret = kvm_set_msr_common(vcpu, msr_info); } /* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */ if (msr_index == MSR_IA32_ARCH_CAPABILITIES) vmx_update_fb_clear_dis(vcpu, vmx); return ret; } void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { unsigned long guest_owned_bits; kvm_register_mark_available(vcpu, reg); switch (reg) { case VCPU_REGS_RSP: vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); break; case VCPU_REGS_RIP: vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP); break; case VCPU_EXREG_PDPTR: if (enable_ept) ept_save_pdptrs(vcpu); break; case VCPU_EXREG_CR0: guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; vcpu->arch.cr0 &= ~guest_owned_bits; vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & guest_owned_bits; break; case VCPU_EXREG_CR3: /* * When intercepting CR3 loads, e.g. for shadowing paging, KVM's * CR3 is loaded into hardware, not the guest's CR3. */ if (!(exec_controls_get(to_vmx(vcpu)) & CPU_BASED_CR3_LOAD_EXITING)) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); break; case VCPU_EXREG_CR4: guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; vcpu->arch.cr4 &= ~guest_owned_bits; vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & guest_owned_bits; break; default: KVM_BUG_ON(1, vcpu->kvm); break; } } /* * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID * directly instead of going through cpu_has(), to ensure KVM is trapping * ENCLS whenever it's supported in hardware. It does not matter whether * the host OS supports or has enabled SGX. */ static bool cpu_has_sgx(void) { return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; u32 ctl = ctl_min | ctl_opt; rdmsr(msr, vmx_msr_low, vmx_msr_high); ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ /* Ensure minimum (required) set of control bits are supported. */ if (ctl_min & ~ctl) return -EIO; *result = ctl; return 0; } static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; rdmsrq(msr, allowed); return ctl_opt & allowed; } #define vmx_check_entry_exit_pairs(pairs, entry_controls, exit_controls) \ ({ \ int i, r = 0; \ \ BUILD_BUG_ON(sizeof(pairs[0].entry_control) != sizeof(entry_controls)); \ BUILD_BUG_ON(sizeof(pairs[0].exit_control) != sizeof(exit_controls)); \ \ for (i = 0; i < ARRAY_SIZE(pairs); i++) { \ typeof(entry_controls) n_ctrl = pairs[i].entry_control; \ typeof(exit_controls) x_ctrl = pairs[i].exit_control; \ \ if (!(entry_controls & n_ctrl) == !(exit_controls & x_ctrl)) \ continue; \ \ pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, " \ "entry = %llx (%llx), exit = %llx (%llx)\n", \ (u64)(entry_controls & n_ctrl), (u64)n_ctrl, \ (u64)(exit_controls & x_ctrl), (u64)x_ctrl); \ \ if (error_on_inconsistent_vmcs_config) \ r = -EIO; \ \ entry_controls &= ~n_ctrl; \ exit_controls &= ~x_ctrl; \ } \ r; \ }) static int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; u64 basic_msr; u64 misc_msr; /* * LOAD/SAVE_DEBUG_CONTROLS are absent because both are mandatory. * SAVE_IA32_PAT and SAVE_IA32_EFER are absent because KVM always * intercepts writes to PAT and EFER, i.e. never enables those controls. */ struct { u32 entry_control; u32 exit_control; } const vmcs_entry_exit_pairs[] = { { VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL }, { VM_ENTRY_LOAD_IA32_PAT, VM_EXIT_LOAD_IA32_PAT }, { VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER }, { VM_ENTRY_LOAD_BNDCFGS, VM_EXIT_CLEAR_BNDCFGS }, { VM_ENTRY_LOAD_IA32_RTIT_CTL, VM_EXIT_CLEAR_IA32_RTIT_CTL }, }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); if (adjust_vmx_controls(KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL, KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS, &_cpu_based_exec_control)) return -EIO; if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { if (adjust_vmx_controls(KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL, KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control)) return -EIO; } if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; #endif if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) _cpu_based_2nd_exec_control &= ~( SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &vmx_cap->ept, &vmx_cap->vpid); if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) && vmx_cap->ept) { pr_warn_once("EPT CAP should not exist if not support " "1-setting enable EPT VM-execution control\n"); if (error_on_inconsistent_vmcs_config) return -EIO; vmx_cap->ept = 0; _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && vmx_cap->vpid) { pr_warn_once("VPID CAP should not exist if not support " "1-setting enable VPID VM-execution control\n"); if (error_on_inconsistent_vmcs_config) return -EIO; vmx_cap->vpid = 0; } if (!cpu_has_sgx()) _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_ENCLS_EXITING; if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) _cpu_based_3rd_exec_control = adjust_vmx_controls64(KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS3); if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_EXIT_CONTROLS, KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control)) return -EIO; if (adjust_vmx_controls(KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL, KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL, MSR_IA32_VMX_PINBASED_CTLS, &_pin_based_exec_control)) return -EIO; if (cpu_has_broken_vmx_preemption_timer()) _pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS, KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS, MSR_IA32_VMX_ENTRY_CTLS, &_vmentry_control)) return -EIO; if (vmx_check_entry_exit_pairs(vmcs_entry_exit_pairs, _vmentry_control, _vmexit_control)) return -EIO; /* * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they * can't be used due to an errata where VM Exit may incorrectly clear * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. */ switch (boot_cpu_data.x86_vfm) { case INTEL_NEHALEM_EP: /* AAK155 */ case INTEL_NEHALEM: /* AAP115 */ case INTEL_WESTMERE: /* AAT100 */ case INTEL_WESTMERE_EP: /* BC86,AAY89,BD102 */ case INTEL_NEHALEM_EX: /* BA97 */ _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " "does not work properly. Using workaround\n"); break; default: break; } rdmsrq(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 /* * KVM expects to be able to shove all legal physical addresses into * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always * 0 for processors that support Intel 64 architecture". */ if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; rdmsrq(MSR_IA32_VMX_MISC, misc_msr); vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control; vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; vmcs_conf->misc = misc_msr; #if IS_ENABLED(CONFIG_HYPERV) if (enlightened_vmcs) evmcs_sanitize_exec_ctrls(vmcs_conf); #endif return 0; } static bool __kvm_is_vmx_supported(void) { int cpu = smp_processor_id(); if (!(cpuid_ecx(1) & feature_bit(VMX))) { pr_err("VMX not supported by CPU %d\n", cpu); return false; } if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !this_cpu_has(X86_FEATURE_VMX)) { pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu); return false; } return true; } static bool kvm_is_vmx_supported(void) { bool supported; migrate_disable(); supported = __kvm_is_vmx_supported(); migrate_enable(); return supported; } int vmx_check_processor_compat(void) { int cpu = raw_smp_processor_id(); struct vmcs_config vmcs_conf; struct vmx_capability vmx_cap; if (!__kvm_is_vmx_supported()) return -EIO; if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { pr_err("Failed to setup VMCS config on CPU %d\n", cpu); return -EIO; } if (nested) nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) { pr_err("Inconsistent VMCS config on CPU %d\n", cpu); return -EIO; } return 0; } static int kvm_cpu_vmxon(u64 vmxon_pointer) { u64 msr; cr4_set_bits(X86_CR4_VMXE); asm goto("1: vmxon %[vmxon_pointer]\n\t" _ASM_EXTABLE(1b, %l[fault]) : : [vmxon_pointer] "m"(vmxon_pointer) : : fault); return 0; fault: WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); cr4_clear_bits(X86_CR4_VMXE); return -EFAULT; } int vmx_enable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); int r; if (cr4_read_shadow() & X86_CR4_VMXE) return -EBUSY; /* * This can happen if we hot-added a CPU but failed to allocate * VP assist page for it. */ if (kvm_is_using_evmcs() && !hv_get_vp_assist_page(cpu)) return -EFAULT; intel_pt_handle_vmx(1); r = kvm_cpu_vmxon(phys_addr); if (r) { intel_pt_handle_vmx(0); return r; } return 0; } static void vmclear_local_loaded_vmcss(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v, *n; list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) __loaded_vmcs_clear(v); } void vmx_disable_virtualization_cpu(void) { vmclear_local_loaded_vmcss(); if (kvm_cpu_vmxoff()) kvm_spurious_fault(); hv_reset_evmcs(); intel_pt_handle_vmx(0); } struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); struct page *pages; struct vmcs *vmcs; pages = __alloc_pages_node(node, flags, 0); if (!pages) return NULL; vmcs = page_address(pages); memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; return vmcs; } void free_vmcs(struct vmcs *vmcs) { free_page((unsigned long)vmcs); } /* * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded */ void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) { if (!loaded_vmcs->vmcs) return; loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; if (loaded_vmcs->msr_bitmap) free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) { loaded_vmcs->vmcs = alloc_vmcs(false); if (!loaded_vmcs->vmcs) return -ENOMEM; vmcs_clear(loaded_vmcs->vmcs); loaded_vmcs->shadow_vmcs = NULL; loaded_vmcs->hv_timer_soft_disabled = false; loaded_vmcs->cpu = -1; loaded_vmcs->launched = 0; if (cpu_has_vmx_msr_bitmap()) { loaded_vmcs->msr_bitmap = (unsigned long *) __get_free_page(GFP_KERNEL_ACCOUNT); if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); memset(&loaded_vmcs->controls_shadow, 0, sizeof(struct vmcs_controls_shadow)); return 0; out_vmcs: free_loaded_vmcs(loaded_vmcs); return -ENOMEM; } static void free_kvm_area(void) { int cpu; for_each_possible_cpu(cpu) { free_vmcs(per_cpu(vmxarea, cpu)); per_cpu(vmxarea, cpu) = NULL; } } static __init int alloc_kvm_area(void) { int cpu; for_each_possible_cpu(cpu) { struct vmcs *vmcs; vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL); if (!vmcs) { free_kvm_area(); return -ENOMEM; } /* * When eVMCS is enabled, alloc_vmcs_cpu() sets * vmcs->revision_id to KVM_EVMCS_VERSION instead of * revision_id reported by MSR_IA32_VMX_BASIC. * * However, even though not explicitly documented by * TLFS, VMXArea passed as VMXON argument should * still be marked with revision_id reported by * physical CPU. */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); per_cpu(vmxarea, cpu) = vmcs; } return 0; } static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save) { if (!emulate_invalid_guest_state) { /* * CS and SS RPL should be equal during guest entry according * to VMX spec, but in reality it is not always so. Since vcpu * is in the middle of the transition from real mode to * protected mode it is safe to assume that RPL 0 is a good * default value. */ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) save->selector &= ~SEGMENT_RPL_MASK; save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } __vmx_set_segment(vcpu, save, seg); } static void enter_pmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); /* * Update real mode segment cache. It may be not up-to-date if segment * register was written while vcpu was in a guest mode. */ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); vmx->rmode.vm86_active = 0; __vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); flags = vmcs_readl(GUEST_RFLAGS); flags &= RMODE_GUEST_OWNED_EFLAGS_BITS; flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); vmx_update_exception_bitmap(vcpu); fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); } static void fix_rmode_seg(int seg, struct kvm_segment *save) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; struct kvm_segment var = *save; var.dpl = 0x3; if (seg == VCPU_SREG_CS) var.type = 0x3; if (!emulate_invalid_guest_state) { var.selector = var.base >> 4; var.base = var.base & 0xffff0; var.limit = 0xffff; var.g = 0; var.db = 0; var.present = 1; var.s = 1; var.l = 0; var.unusable = 0; var.type = 0x3; var.avl = 0; if (save->base & 0xf) pr_warn_once("segment base is not paragraph aligned " "when entering protected mode (seg=%d)", seg); } vmcs_write16(sf->selector, var.selector); vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); /* * KVM should never use VM86 to virtualize Real Mode when L2 is active, * as using VM86 is unnecessary if unrestricted guest is enabled, and * if unrestricted guest is disabled, VM-Enter (from L1) with CR0.PG=0 * should VM-Fail and KVM should reject userspace attempts to stuff * CR0.PG=0 when L2 is active. */ WARN_ON_ONCE(is_guest_mode(vcpu)); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); vmx->rmode.vm86_active = 1; vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr); vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); flags = vmcs_readl(GUEST_RFLAGS); vmx->rmode.save_rflags = flags; flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); vmx_update_exception_bitmap(vcpu); fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); } int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* Nothing to do if hardware doesn't support EFER. */ if (!vmx_find_uret_msr(vmx, MSR_EFER)) return 0; vcpu->arch.efer = efer; #ifdef CONFIG_X86_64 if (efer & EFER_LMA) vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE); else vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE); #else if (KVM_BUG_ON(efer & EFER_LMA, vcpu->kvm)) return 1; #endif vmx_setup_uret_msrs(vmx); return 0; } #ifdef CONFIG_X86_64 static void enter_lmode(struct kvm_vcpu *vcpu) { u32 guest_tr_ar; vmx_segment_cache_clear(to_vmx(vcpu)); guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { pr_debug_ratelimited("%s: tss fixup for long mode. \n", __func__); vmcs_write32(GUEST_TR_AR_BYTES, (guest_tr_ar & ~VMX_AR_TYPE_MASK) | VMX_AR_TYPE_BUSY_64_TSS); } vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } static void exit_lmode(struct kvm_vcpu *vcpu) { vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); } #endif void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * INVEPT must be issued when EPT is enabled, irrespective of VPID, as * the CPU is not required to invalidate guest-physical mappings on * VM-Entry, even if VPID is disabled. Guest-physical mappings are * associated with the root EPT structure and not any particular VPID * (INVVPID also isn't required to invalidate guest-physical mappings). */ if (enable_ept) { ept_sync_global(); } else if (enable_vpid) { if (cpu_has_vmx_invvpid_global()) { vpid_sync_vcpu_global(); } else { vpid_sync_vcpu_single(vmx->vpid); vpid_sync_vcpu_single(vmx->nested.vpid02); } } } static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu))) return nested_get_vpid02(vcpu); return to_vmx(vcpu)->vpid; } void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 root_hpa = mmu->root.hpa; /* No flush required if the current context is invalid. */ if (!VALID_PAGE(root_hpa)) return; if (enable_ept) ept_sync_context(construct_eptp(vcpu, root_hpa, mmu->root_role.level)); else vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in * vmx_flush_tlb_guest() for an explanation of why this is ok. */ vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a * vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit are * required to flush GVA->{G,H}PA mappings from the TLB if vpid is * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), * i.e. no explicit INVVPID is necessary. */ vpid_sync_context(vmx_get_current_vpid(vcpu)); } void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR)) return; if (is_pae_paging(vcpu)) { vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]); } } void ept_save_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; if (WARN_ON_ONCE(!is_pae_paging(vcpu))) return; mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR); } #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_guest_mode(vcpu)) return nested_guest_cr0_valid(vcpu, cr0); if (to_vmx(vcpu)->nested.vmxon) return nested_host_cr0_valid(vcpu, cr0); return true; } void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long hw_cr0, old_cr0_pg; u32 tmp; old_cr0_pg = kvm_read_cr0_bits(vcpu, X86_CR0_PG); hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF); if (enable_unrestricted_guest) hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; else { hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; if (!enable_ept) hw_cr0 |= X86_CR0_WP; if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) enter_pmode(vcpu); if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) enter_rmode(vcpu); } vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; kvm_register_mark_available(vcpu, VCPU_EXREG_CR0); #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { if (!old_cr0_pg && (cr0 & X86_CR0_PG)) enter_lmode(vcpu); else if (old_cr0_pg && !(cr0 & X86_CR0_PG)) exit_lmode(vcpu); } #endif if (enable_ept && !enable_unrestricted_guest) { /* * Ensure KVM has an up-to-date snapshot of the guest's CR3. If * the below code _enables_ CR3 exiting, vmx_cache_reg() will * (correctly) stop reading vmcs.GUEST_CR3 because it thinks * KVM's CR3 is installed. */ if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) vmx_cache_reg(vcpu, VCPU_EXREG_CR3); /* * When running with EPT but not unrestricted guest, KVM must * intercept CR3 accesses when paging is _disabled_. This is * necessary because restricted guests can't actually run with * paging disabled, and so KVM stuffs its own CR3 in order to * run the guest when identity mapped page tables. * * Do _NOT_ check the old CR0.PG, e.g. to optimize away the * update, it may be stale with respect to CR3 interception, * e.g. after nested VM-Enter. * * Lastly, honor L1's desires, i.e. intercept CR3 loads and/or * stores to forward them to L1, even if KVM does not need to * intercept them to preserve its identity mapped page tables. */ if (!(cr0 & X86_CR0_PG)) { exec_controls_setbit(vmx, CR3_EXITING_BITS); } else if (!is_guest_mode(vcpu)) { exec_controls_clearbit(vmx, CR3_EXITING_BITS); } else { tmp = exec_controls_get(vmx); tmp &= ~CR3_EXITING_BITS; tmp |= get_vmcs12(vcpu)->cpu_based_vm_exec_control & CR3_EXITING_BITS; exec_controls_set(vmx, tmp); } /* Note, vmx_set_cr4() consumes the new vcpu->arch.cr0. */ if ((old_cr0_pg ^ cr0) & X86_CR0_PG) vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); /* * When !CR0_PG -> CR0_PG, vcpu->arch.cr3 becomes active, but * GUEST_CR3 is still vmx->ept_identity_map_addr if EPT + !URG. */ if (!(old_cr0_pg & X86_CR0_PG) && (cr0 & X86_CR0_PG)) kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); } /* depends on vcpu->arch.cr0 to be set to a new value */ vmx->vt.emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_ept_level(void) { if (cpu_has_vmx_ept_5levels()) return 5; return 4; } u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { u64 eptp = VMX_EPTP_MT_WB; eptp |= (root_level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; if (enable_ept_ad_bits && (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) eptp |= VMX_EPTP_AD_ENABLE_BIT; eptp |= root_hpa; return eptp; } void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; if (enable_ept) { eptp = construct_eptp(vcpu, root_hpa, root_level); vmcs_write64(EPT_POINTER, eptp); hv_track_root_tdp(vcpu, root_hpa); if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; else if (kvm_register_is_dirty(vcpu, VCPU_EXREG_CR3)) guest_cr3 = vcpu->arch.cr3; else /* vmcs.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) | kvm_get_active_cr3_lam_bits(vcpu); } if (update_guest_cr3) vmcs_writel(GUEST_CR3, guest_cr3); } bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be * enabled under SMM. Note, whether or not VMXE is allowed at all, * i.e. is a reserved bit, is handled by common x86 code. */ if ((cr4 & X86_CR4_VMXE) && is_smm(vcpu)) return false; if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) return false; return true; } void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long hw_cr4; /* * Pass through host's Machine Check Enable value to hw_cr4, which * is in force while we are in guest mode. Do not let guests control * this bit, even if host CR4.MCE == 0. */ hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); if (enable_unrestricted_guest) hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; else if (vmx->rmode.vm86_active) hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON; else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; if (vmx_umip_emulated()) { if (cr4 & X86_CR4_UMIP) { secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; } else if (!is_guest_mode(vcpu) || !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_DESC); } } vcpu->arch.cr4 = cr4; kvm_register_mark_available(vcpu, VCPU_EXREG_CR4); if (!enable_unrestricted_guest) { if (enable_ept) { if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } } /* * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in * hardware. To emulate this behavior, SMEP/SMAP/PKU needs * to be manually disabled when guest switches to non-paging * mode. * * If !enable_unrestricted_guest, the CPU is always running * with CR0.PG=1 and CR4 needs to be modified. * If enable_unrestricted_guest, the CPU automatically * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0. */ if (!is_paging(vcpu)) hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); } vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) vcpu->arch.cpuid_dynamic_bits_dirty = true; } void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 ar; if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { *var = vmx->rmode.segs[seg]; if (seg == VCPU_SREG_TR || var->selector == vmx_read_guest_seg_selector(vmx, seg)) return; var->base = vmx_read_guest_seg_base(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); return; } var->base = vmx_read_guest_seg_base(vmx, seg); var->limit = vmx_read_guest_seg_limit(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); ar = vmx_read_guest_seg_ar(vmx, seg); var->unusable = (ar >> 16) & 1; var->type = ar & 15; var->s = (ar >> 4) & 1; var->dpl = (ar >> 5) & 3; /* * Some userspaces do not preserve unusable property. Since usable * segment has to be present according to VMX spec we can use present * property to amend userspace bug by making unusable segment always * nonpresent. vmx_segment_access_rights() already marks nonpresent * segment as unusable. */ var->present = !var->unusable; var->avl = (ar >> 12) & 1; var->l = (ar >> 13) & 1; var->db = (ar >> 14) & 1; var->g = (ar >> 15) & 1; } u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment s; if (to_vmx(vcpu)->rmode.vm86_active) { vmx_get_segment(vcpu, &s, seg); return s.base; } return vmx_read_guest_seg_base(to_vmx(vcpu), seg); } static int __vmx_get_cpl(struct kvm_vcpu *vcpu, bool no_cache) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ar; if (unlikely(vmx->rmode.vm86_active)) return 0; if (no_cache) ar = vmcs_read32(GUEST_SS_AR_BYTES); else ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); return VMX_AR_DPL(ar); } int vmx_get_cpl(struct kvm_vcpu *vcpu) { return __vmx_get_cpl(vcpu, false); } int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu) { return __vmx_get_cpl(vcpu, true); } static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; ar = var->type & 15; ar |= (var->s & 1) << 4; ar |= (var->dpl & 3) << 5; ar |= (var->present & 1) << 7; ar |= (var->avl & 1) << 12; ar |= (var->l & 1) << 13; ar |= (var->db & 1) << 14; ar |= (var->g & 1) << 15; ar |= (var->unusable || !var->present) << 16; return ar; } void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct vcpu_vmx *vmx = to_vmx(vcpu); const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; vmx_segment_cache_clear(vmx); if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { vmx->rmode.segs[seg] = *var; if (seg == VCPU_SREG_TR) vmcs_write16(sf->selector, var->selector); else if (var->s) fix_rmode_seg(seg, &vmx->rmode.segs[seg]); return; } vmcs_writel(sf->base, var->base); vmcs_write32(sf->limit, var->limit); vmcs_write16(sf->selector, var->selector); /* * Fix the "Accessed" bit in AR field of segment registers for older * qemu binaries. * IA32 arch specifies that at the time of processor reset the * "Accessed" bit in the AR field of segment registers is 1. And qemu * is setting it to 0 in the userland code. This causes invalid guest * state vmexit when "unrestricted guest" mode is turned on. * Fix for this setup issue in cpu_reset is being pushed in the qemu * tree. Newer qemu binaries with that qemu fix would not need this * kvm hack. */ if (is_unrestricted_guest(vcpu) && (seg != VCPU_SREG_LDTR)) var->type |= 0x1; /* Accessed */ vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); } void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { __vmx_set_segment(vcpu, var, seg); to_vmx(vcpu)->vt.emulation_required = vmx_emulation_required(vcpu); } void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); *db = (ar >> 14) & 1; *l = (ar >> 13) & 1; } void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_IDTR_LIMIT); dt->address = vmcs_readl(GUEST_IDTR_BASE); } void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->size); vmcs_writel(GUEST_IDTR_BASE, dt->address); } void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_GDTR_LIMIT); dt->address = vmcs_readl(GUEST_GDTR_BASE); } void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->size); vmcs_writel(GUEST_GDTR_BASE, dt->address); } static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment var; u32 ar; vmx_get_segment(vcpu, &var, seg); var.dpl = 0x3; if (seg == VCPU_SREG_CS) var.type = 0x3; ar = vmx_segment_access_rights(&var); if (var.base != (var.selector << 4)) return false; if (var.limit != 0xffff) return false; if (ar != 0xf3) return false; return true; } static bool code_segment_valid(struct kvm_vcpu *vcpu) { struct kvm_segment cs; unsigned int cs_rpl; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); cs_rpl = cs.selector & SEGMENT_RPL_MASK; if (cs.unusable) return false; if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; } else { if (cs.dpl != cs_rpl) return false; } if (!cs.present) return false; /* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */ return true; } static bool stack_segment_valid(struct kvm_vcpu *vcpu) { struct kvm_segment ss; unsigned int ss_rpl; vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); ss_rpl = ss.selector & SEGMENT_RPL_MASK; if (ss.unusable) return true; if (ss.type != 3 && ss.type != 7) return false; if (!ss.s) return false; if (ss.dpl != ss_rpl) /* DPL != RPL */ return false; if (!ss.present) return false; return true; } static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment var; unsigned int rpl; vmx_get_segment(vcpu, &var, seg); rpl = var.selector & SEGMENT_RPL_MASK; if (var.unusable) return true; if (!var.s) return false; if (!var.present) return false; if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { if (var.dpl < rpl) /* DPL < RPL */ return false; } /* TODO: Add other members to kvm_segment_field to allow checking for other access * rights flags */ return true; } static bool tr_valid(struct kvm_vcpu *vcpu) { struct kvm_segment tr; vmx_get_segment(vcpu, &tr, VCPU_SREG_TR); if (tr.unusable) return false; if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; if (!tr.present) return false; return true; } static bool ldtr_valid(struct kvm_vcpu *vcpu) { struct kvm_segment ldtr; vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR); if (ldtr.unusable) return true; if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) return false; if (!ldtr.present) return false; return true; } static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) { struct kvm_segment cs, ss; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); return ((cs.selector & SEGMENT_RPL_MASK) == (ss.selector & SEGMENT_RPL_MASK)); } /* * Check if guest state is valid. Returns true if valid, false if * not. * We assume that registers are always usable */ bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu) { /* real mode guest state checks */ if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) { if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_SS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_DS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_ES)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_FS)) return false; if (!rmode_segment_valid(vcpu, VCPU_SREG_GS)) return false; } else { /* protected mode guest state checks */ if (!cs_ss_rpl_check(vcpu)) return false; if (!code_segment_valid(vcpu)) return false; if (!stack_segment_valid(vcpu)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_DS)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_ES)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_FS)) return false; if (!data_segment_valid(vcpu, VCPU_SREG_GS)) return false; if (!tr_valid(vcpu)) return false; if (!ldtr_valid(vcpu)) return false; } /* TODO: * - Add checks on RIP * - Add checks on RFLAGS */ return true; } static int init_rmode_tss(struct kvm *kvm, void __user *ua) { const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); u16 data; int i; for (i = 0; i < 3; i++) { if (__copy_to_user(ua + PAGE_SIZE * i, zero_page, PAGE_SIZE)) return -EFAULT; } data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; if (__copy_to_user(ua + TSS_IOPB_BASE_OFFSET, &data, sizeof(u16))) return -EFAULT; data = ~0; if (__copy_to_user(ua + RMODE_TSS_SIZE - 1, &data, sizeof(u8))) return -EFAULT; return 0; } static int init_rmode_identity_map(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); int i, r = 0; void __user *uaddr; u32 tmp; /* Protect kvm_vmx->ept_identity_pagetable_done. */ mutex_lock(&kvm->slots_lock); if (likely(kvm_vmx->ept_identity_pagetable_done)) goto out; if (!kvm_vmx->ept_identity_map_addr) kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; uaddr = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, kvm_vmx->ept_identity_map_addr, PAGE_SIZE); if (IS_ERR(uaddr)) { r = PTR_ERR(uaddr); goto out; } /* Set up identity-mapping pagetable for EPT in real mode */ for (i = 0; i < (PAGE_SIZE / sizeof(tmp)); i++) { tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); if (__copy_to_user(uaddr + i * sizeof(tmp), &tmp, sizeof(tmp))) { r = -EFAULT; goto out; } } kvm_vmx->ept_identity_pagetable_done = true; out: mutex_unlock(&kvm->slots_lock); return r; } static void seg_setup(int seg) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; unsigned int ar; vmcs_write16(sf->selector, 0); vmcs_writel(sf->base, 0); vmcs_write32(sf->limit, 0xffff); ar = 0x93; if (seg == VCPU_SREG_CS) ar |= 0x08; /* code segment */ vmcs_write32(sf->ar_bytes, ar); } int allocate_vpid(void) { int vpid; if (!enable_vpid) return 0; spin_lock(&vmx_vpid_lock); vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); if (vpid < VMX_NR_VPIDS) __set_bit(vpid, vmx_vpid_bitmap); else vpid = 0; spin_unlock(&vmx_vpid_lock); return vpid; } void free_vpid(int vpid) { if (!enable_vpid || vpid == 0) return; spin_lock(&vmx_vpid_lock); __clear_bit(vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); } static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) { /* * When KVM is a nested hypervisor on top of Hyper-V and uses * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ if (kvm_is_using_evmcs()) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; if (evmcs->hv_enlightenments_control.msr_bitmap) evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; } vmx->nested.force_msr_bitmap_recalc = true; } void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; int idx; if (!cpu_has_vmx_msr_bitmap()) return; vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filters change. */ idx = vmx_get_passthrough_msr_slot(msr); if (idx >= 0) { if (type & MSR_TYPE_R) clear_bit(idx, vmx->shadow_msr_intercept.read); if (type & MSR_TYPE_W) clear_bit(idx, vmx->shadow_msr_intercept.write); } if ((type & MSR_TYPE_R) && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) { vmx_set_msr_bitmap_read(msr_bitmap, msr); type &= ~MSR_TYPE_R; } if ((type & MSR_TYPE_W) && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) { vmx_set_msr_bitmap_write(msr_bitmap, msr); type &= ~MSR_TYPE_W; } if (type & MSR_TYPE_R) vmx_clear_msr_bitmap_read(msr_bitmap, msr); if (type & MSR_TYPE_W) vmx_clear_msr_bitmap_write(msr_bitmap, msr); } void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; int idx; if (!cpu_has_vmx_msr_bitmap()) return; vmx_msr_bitmap_l01_changed(vmx); /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filter changes. */ idx = vmx_get_passthrough_msr_slot(msr); if (idx >= 0) { if (type & MSR_TYPE_R) set_bit(idx, vmx->shadow_msr_intercept.read); if (type & MSR_TYPE_W) set_bit(idx, vmx->shadow_msr_intercept.write); } if (type & MSR_TYPE_R) vmx_set_msr_bitmap_read(msr_bitmap, msr); if (type & MSR_TYPE_W) vmx_set_msr_bitmap_write(msr_bitmap, msr); } static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) { /* * x2APIC indices for 64-bit accesses into the RDMSR and WRMSR halves * of the MSR bitmap. KVM emulates APIC registers up through 0x3f0, * i.e. MSR 0x83f, and so only needs to dynamically manipulate 64 bits. */ const int read_idx = APIC_BASE_MSR / BITS_PER_LONG_LONG; const int write_idx = read_idx + (0x800 / sizeof(u64)); struct vcpu_vmx *vmx = to_vmx(vcpu); u64 *msr_bitmap = (u64 *)vmx->vmcs01.msr_bitmap; u8 mode; if (!cpu_has_vmx_msr_bitmap() || WARN_ON_ONCE(!lapic_in_kernel(vcpu))) return; if (cpu_has_secondary_exec_ctrls() && (secondary_exec_controls_get(vmx) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { mode = MSR_BITMAP_MODE_X2APIC; if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) mode |= MSR_BITMAP_MODE_X2APIC_APICV; } else { mode = 0; } if (mode == vmx->x2apic_msr_bitmap_mode) return; vmx->x2apic_msr_bitmap_mode = mode; /* * Reset the bitmap for MSRs 0x800 - 0x83f. Leave AMD's uber-extended * registers (0x840 and above) intercepted, KVM doesn't support them. * Intercept all writes by default and poke holes as needed. Pass * through reads for all valid registers by default in x2APIC+APICv * mode, only the current timer count needs on-demand emulation by KVM. */ if (mode & MSR_BITMAP_MODE_X2APIC_APICV) msr_bitmap[read_idx] = ~kvm_lapic_readable_reg_mask(vcpu->arch.apic); else msr_bitmap[read_idx] = ~0ull; msr_bitmap[write_idx] = ~0ull; /* * TPR reads and writes can be virtualized even if virtual interrupt * delivery is not in use. */ vmx_set_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW, !(mode & MSR_BITMAP_MODE_X2APIC)); if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); if (enable_ipiv) vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_ICR), MSR_TYPE_RW); } } void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); u32 i; vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_STATUS, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag); for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) { vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag); vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag); } } void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 i; if (!cpu_has_vmx_msr_bitmap()) return; /* * Redo intercept permissions for MSRs that KVM is passing through to * the guest. Disabling interception will check the new MSR filter and * ensure that KVM enables interception if usersepace wants to filter * the MSR. MSRs that KVM is already intercepting don't need to be * refreshed since KVM is going to intercept them regardless of what * userspace wants. */ for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { u32 msr = vmx_possible_passthrough_msrs[i]; if (!test_bit(i, vmx->shadow_msr_intercept.read)) vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_R); if (!test_bit(i, vmx->shadow_msr_intercept.write)) vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_W); } /* PT MSRs can be passed through iff PT is exposed to the guest. */ if (vmx_pt_mode_is_host_guest()) pt_update_intercept_for_msr(vcpu); } static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated * and freed, and must not be accessed outside of vcpu->mutex. The * vCPU's cached PI NV is valid if and only if posted interrupts * enabled in its vmcs12, i.e. checking the vector also checks that * L1 has enabled posted interrupts for L2. */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); /* * This pairs with the smp_mb_*() after setting vcpu->mode in * vcpu_enter_guest() to guarantee the vCPU sees the event * request if triggering a posted interrupt "fails" because * vcpu->mode != IN_GUEST_MODE. The extra barrier is needed as * the smb_wmb() in kvm_make_request() only ensures everything * done before making the request is visible when the request * is visible, it doesn't ensure ordering between the store to * vcpu->requests and the load from vcpu->mode. */ smp_mb__after_atomic(); /* the PIR and ON have been set by L1. */ kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_NESTED_VECTOR); return 0; } return -1; } /* * Send interrupt to vcpu via posted interrupt way. * 1. If target vcpu is running(non-root mode), send posted interrupt * notification to vcpu and hardware will sync PIR to vIRR atomically. * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vt *vt = to_vt(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) return 0; /* Note, this is called iff the local APIC is in-kernel. */ if (!vcpu->arch.apic->apicv_active) return -1; __vmx_deliver_posted_interrupt(vcpu, &vt->pi_desc, vector); return 0; } void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector) { struct kvm_vcpu *vcpu = apic->vcpu; if (vmx_deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } else { trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); } } /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. * Note that host-state that does change is set elsewhere. E.g., host-state * that is set differently for each CPU is set in vmx_vcpu_load(), not here. */ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) { u32 low32, high32; unsigned long tmpl; unsigned long cr0, cr3, cr4; cr0 = read_cr0(); WARN_ON(cr0 & X86_CR0_TS); vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ /* * Save the most likely value for this task's CR3 in the VMCS. * We can't use __get_current_cr3_fast() because we're not atomic. */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ vmx->loaded_vmcs->host_state.cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ vmx->loaded_vmcs->host_state.cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 /* * Load null selectors, so we can avoid reloading them in * vmx_prepare_switch_to_host(), in case userspace uses * the null selectors too (the expected case). */ vmcs_write16(HOST_DS_SELECTOR, 0); vmcs_write16(HOST_ES_SELECTOR, 0); #else vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ #endif vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ vmcs_writel(HOST_IDTR_BASE, host_idt_base); /* 22.2.4 */ vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */ rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); vmcs_write32(HOST_IA32_SYSENTER_CS, low32); /* * SYSENTER is used for 32-bit system calls on either 32-bit or * 64-bit kernels. It is always zero If neither is allowed, otherwise * vmx_vcpu_load_vmcs loads it with the per-CPU entry stack (and may * have already done so!). */ if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); rdmsrq(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) { rdmsr(MSR_IA32_CR_PAT, low32, high32); vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32)); } if (cpu_has_load_ia32_efer()) vmcs_write64(HOST_IA32_EFER, kvm_host.efer); } void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { struct kvm_vcpu *vcpu = &vmx->vcpu; vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS & ~vcpu->arch.cr4_guest_rsvd_bits; if (!enable_ept) { vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS; vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS; } if (is_guest_mode(&vmx->vcpu)) vcpu->arch.cr4_guest_owned_bits &= ~get_vmcs12(vcpu)->cr4_guest_host_mask; vmcs_writel(CR4_GUEST_HOST_MASK, ~vcpu->arch.cr4_guest_owned_bits); } static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; if (!enable_vnmi) pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS; if (!enable_preemption_timer) pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; return pin_based_exec_ctrl; } static u32 vmx_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); /* * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. */ vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER | VM_ENTRY_IA32E_MODE); return vmentry_ctrl; } static u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; /* * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for * nested virtualization and thus allowed to be set in vmcs12. */ vmexit_ctrl &= ~(VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER); if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); } void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (is_guest_mode(vcpu)) { vmx->nested.update_vmcs01_apicv_status = true; return; } pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (kvm_vcpu_apicv_active(vcpu)) { secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); if (enable_ipiv) tertiary_exec_controls_setbit(vmx, TERTIARY_EXEC_IPI_VIRT); } else { secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); if (enable_ipiv) tertiary_exec_controls_clearbit(vmx, TERTIARY_EXEC_IPI_VIRT); } vmx_update_msr_bitmap_x2apic(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; /* * Not used by KVM, but fully supported for nesting, i.e. are allowed in * vmcs12 and propagated to vmcs02 when set in vmcs12. */ exec_control &= ~(CPU_BASED_RDTSC_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | CPU_BASED_PAUSE_EXITING); /* INTR_WINDOW_EXITING and NMI_WINDOW_EXITING are toggled dynamically */ exec_control &= ~(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; if (!cpu_need_tpr_shadow(&vmx->vcpu)) exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 if (exec_control & CPU_BASED_TPR_SHADOW) exec_control &= ~(CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING); else exec_control |= CPU_BASED_CR8_STORE_EXITING | CPU_BASED_CR8_LOAD_EXITING; #endif /* No need to intercept CR3 access or INVPLG when using EPT. */ if (enable_ept) exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | CPU_BASED_INVLPG_EXITING); if (kvm_mwait_in_guest(vmx->vcpu.kvm)) exec_control &= ~(CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING); if (kvm_hlt_in_guest(vmx->vcpu.kvm)) exec_control &= ~CPU_BASED_HLT_EXITING; return exec_control; } static u64 vmx_tertiary_exec_control(struct vcpu_vmx *vmx) { u64 exec_control = vmcs_config.cpu_based_3rd_exec_ctrl; /* * IPI virtualization relies on APICv. Disable IPI virtualization if * APICv is inhibited. */ if (!enable_ipiv || !kvm_vcpu_apicv_active(&vmx->vcpu)) exec_control &= ~TERTIARY_EXEC_IPI_VIRT; return exec_control; } /* * Adjust a single secondary execution control bit to intercept/allow an * instruction in the guest. This is usually done based on whether or not a * feature has been exposed to the guest in order to correctly emulate faults. */ static inline void vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, u32 control, bool enabled, bool exiting) { /* * If the control is for an opt-in feature, clear the control if the * feature is not exposed to the guest, i.e. not enabled. If the * control is opt-out, i.e. an exiting control, clear the control if * the feature _is_ exposed to the guest, i.e. exiting/interception is * disabled for the associated instruction. Note, the caller is * responsible presetting exec_control to set all supported bits. */ if (enabled == exiting) *exec_control &= ~control; /* * Update the nested MSR settings so that a nested VMM can/can't set * controls for features that are/aren't exposed to the guest. */ if (nested && kvm_check_has_quirk(vmx->vcpu.kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { /* * All features that can be added or removed to VMX MSRs must * be supported in the first place for nested virtualization. */ if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) enabled = false; if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else vmx->nested.msrs.secondary_ctls_high &= ~control; } } /* * Wrapper macro for the common case of adjusting a secondary execution control * based on a single guest CPUID bit, with a dedicated feature bit. This also * verifies that the control is actually supported by KVM and hardware. */ #define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \ ({ \ struct kvm_vcpu *__vcpu = &(vmx)->vcpu; \ bool __enabled; \ \ if (cpu_has_vmx_##name()) { \ __enabled = guest_cpu_cap_has(__vcpu, X86_FEATURE_##feat_name); \ vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ __enabled, exiting); \ } \ }) /* More macro magic for ENABLE_/opt-in versus _EXITING/opt-out controls. */ #define vmx_adjust_sec_exec_feature(vmx, exec_control, lname, uname) \ vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, ENABLE_##uname, false) #define vmx_adjust_sec_exec_exiting(vmx, exec_control, lname, uname) \ vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, uname##_EXITING, true) static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { struct kvm_vcpu *vcpu = &vmx->vcpu; u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; if (vmx_pt_mode_is_system()) exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX); if (!cpu_need_virtualize_apic_accesses(vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; enable_unrestricted_guest = 0; } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (kvm_pause_in_guest(vmx->vcpu.kvm)) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; if (!kvm_vcpu_apicv_active(vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; /* * KVM doesn't support VMFUNC for L1, but the control is set in KVM's * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2. */ exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC; /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, * in vmx_set_cr4. */ exec_control &= ~SECONDARY_EXEC_DESC; /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD (handle_vmptrld). We can NOT enable shadow_vmcs here because we don't have yet a current VMCS12 */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; /* * PML is enabled/disabled when dirty logging of memsmlots changes, but * it needs to be set here when dirty logging is already active, e.g. * if this vCPU was created after dirty logging was enabled. */ if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; vmx_adjust_sec_exec_feature(vmx, &exec_control, xsaves, XSAVES); /* * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either * feature is exposed to the guest. This creates a virtualization hole * if both are supported in hardware but only one is exposed to the * guest, but letting the guest execute RDTSCP or RDPID when either one * is advertised is preferable to emulating the advertised instruction * in KVM on #UD, and obviously better than incorrectly injecting #UD. */ if (cpu_has_vmx_rdtscp()) { bool rdpid_or_rdtscp_enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); vmx_adjust_secondary_exec_control(vmx, &exec_control, SECONDARY_EXEC_ENABLE_RDTSCP, rdpid_or_rdtscp_enabled, false); } vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED); vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG, ENABLE_USR_WAIT_PAUSE, false); if (!vcpu->kvm->arch.bus_lock_detection_enabled) exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; if (!kvm_notify_vmexit_enabled(vcpu->kvm)) exec_control &= ~SECONDARY_EXEC_NOTIFY_VM_EXITING; return exec_control; } static inline int vmx_get_pid_table_order(struct kvm *kvm) { return get_order(kvm->arch.max_vcpu_ids * sizeof(*to_kvm_vmx(kvm)->pid_table)); } static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) { struct page *pages; struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); if (!irqchip_in_kernel(kvm) || !enable_ipiv) return 0; if (kvm_vmx->pid_table) return 0; pages = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, vmx_get_pid_table_order(kvm)); if (!pages) return -ENOMEM; kvm_vmx->pid_table = (void *)page_address(pages); return 0; } int vmx_vcpu_precreate(struct kvm *kvm) { return vmx_alloc_ipiv_pid_table(kvm); } #define VMX_XSS_EXIT_BITMAP 0 static void init_vmcs(struct vcpu_vmx *vmx) { struct kvm *kvm = vmx->vcpu.kvm; struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); if (nested) nested_vmx_set_vmcs_shadowing_bitmap(); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); /* 22.3.1.5 */ /* Control */ pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); exec_controls_set(vmx, vmx_exec_control(vmx)); if (cpu_has_secondary_exec_ctrls()) { secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); if (vmx->ve_info) vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); } if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx)); if (enable_apicv && lapic_in_kernel(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); vmcs_write64(EOI_EXIT_BITMAP3, 0); vmcs_write16(GUEST_INTR_STATUS, 0); vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->vt.pi_desc))); } if (vmx_can_use_ipiv(&vmx->vcpu)) { vmcs_write64(PID_POINTER_TABLE, __pa(kvm_vmx->pid_table)); vmcs_write16(LAST_PID_POINTER_INDEX, kvm->arch.max_vcpu_ids - 1); } if (!kvm_pause_in_guest(kvm)) { vmcs_write32(PLE_GAP, ple_gap); vmx->ple_window = ple_window; vmx->ple_window_dirty = true; } if (kvm_notify_vmexit_enabled(kvm)) vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ vmx_set_constant_host_state(vmx); vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ if (cpu_has_vmx_vmfunc()) vmcs_write64(VM_FUNCTION_CONTROL, 0); vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); if (cpu_has_vmx_xsaves()) vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } vmx_write_encls_bitmap(&vmx->vcpu, NULL); if (vmx_pt_mode_is_host_guest()) { memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); /* Bit[6~0] are forced to 1, writes are ignored. */ vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); if (cpu_need_tpr_shadow(&vmx->vcpu)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, __pa(vmx->vcpu.arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } vmx_setup_uret_msrs(vmx); } static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); init_vmcs(vmx); if (nested && kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs)); vcpu_setup_sgx_lepubkeyhash(vcpu); vmx->nested.posted_intr_nv = -1; vmx->nested.vmxon_ptr = INVALID_GPA; vmx->nested.current_vmptr = INVALID_GPA; #ifdef CONFIG_KVM_HYPERV vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; #endif if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR * or POSTED_INTR_WAKEUP_VECTOR. */ vmx->vt.pi_desc.nv = POSTED_INTR_VECTOR; __pi_set_sn(&vmx->vt.pi_desc); } void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!init_event) __vmx_vcpu_reset(vcpu); vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; vmx->msr_ia32_umwait_control = 0; vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); seg_setup(VCPU_SREG_FS); seg_setup(VCPU_SREG_GS); seg_setup(VCPU_SREG_SS); vmcs_write16(GUEST_TR_SELECTOR, 0); vmcs_writel(GUEST_TR_BASE, 0); vmcs_write32(GUEST_TR_LIMIT, 0xffff); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); vmcs_write16(GUEST_LDTR_SELECTOR, 0); vmcs_writel(GUEST_LDTR_BASE, 0); vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); vmcs_writel(GUEST_IDTR_BASE, 0); vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); vmx_segment_cache_clear(vmx); kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); if (kvm_mpx_supported()) vmcs_write64(GUEST_BNDCFGS, 0); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); vpid_sync_context(vmx->vpid); vmx_update_fb_clear_dis(vcpu, vmx); } void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { vmx_enable_irq_window(vcpu); return; } exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; int irq = vcpu->arch.interrupt.nr; trace_kvm_inj_virq(irq, vcpu->arch.interrupt.soft, reinjected); ++vcpu->stat.irq_injections; if (vmx->rmode.vm86_active) { int inc_eip = 0; if (vcpu->arch.interrupt.soft) inc_eip = vcpu->arch.event_exit_inst_len; kvm_inject_realmode_interrupt(vcpu, irq, inc_eip); return; } intr = irq | INTR_INFO_VALID_MASK; if (vcpu->arch.interrupt.soft) { intr |= INTR_TYPE_SOFT_INTR; vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); } else intr |= INTR_TYPE_EXT_INTR; vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr); vmx_clear_hlt(vcpu); } void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!enable_vnmi) { /* * Tracking the NMI-blocked state in software is built upon * finding the next open IRQ window. This, in turn, depends on * well-behaving guests: They have to keep IRQs disabled at * least as long as the NMI handler runs. Otherwise we may * cause NMI nesting, maybe breaking the guest. But as this is * highly unlikely, we can live with the residual risk. */ vmx->loaded_vmcs->soft_vnmi_blocked = 1; vmx->loaded_vmcs->vnmi_blocked_time = 0; } ++vcpu->stat.nmi_injections; vmx->loaded_vmcs->nmi_known_unmasked = false; if (vmx->rmode.vm86_active) { kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0); return; } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); vmx_clear_hlt(vcpu); } bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool masked; if (!enable_vnmi) return vmx->loaded_vmcs->soft_vnmi_blocked; if (vmx->loaded_vmcs->nmi_known_unmasked) return false; masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; vmx->loaded_vmcs->nmi_known_unmasked = !masked; return masked; } void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!enable_vnmi) { if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) { vmx->loaded_vmcs->soft_vnmi_blocked = masked; vmx->loaded_vmcs->vnmi_blocked_time = 0; } } else { vmx->loaded_vmcs->nmi_known_unmasked = !masked; if (masked) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); else vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); } } bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_nmi(vcpu)) return false; if (!enable_vnmi && to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) return true; return (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI | GUEST_INTR_STATE_NMI)); } int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(vcpu)) return -EBUSY; return !vmx_nmi_blocked(vcpu); } bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); } bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; return __vmx_interrupt_blocked(vcpu); } int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; /* * An IRQ must not be injected into L2 if it's supposed to VM-Exit, * e.g. if the IRQ arrived asynchronously after checking nested events. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return -EBUSY; return !vmx_interrupt_blocked(vcpu); } int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { void __user *ret; if (enable_unrestricted_guest) return 0; mutex_lock(&kvm->slots_lock); ret = __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, PAGE_SIZE * 3); mutex_unlock(&kvm->slots_lock); if (IS_ERR(ret)) return PTR_ERR(ret); to_kvm_vmx(kvm)->tss_addr = addr; return init_rmode_tss(kvm, ret); } int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; return 0; } static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) { switch (vec) { case BP_VECTOR: /* * Update instruction length as we may reinject the exception * from user space while in guest debugging mode. */ to_vmx(vcpu)->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return false; fallthrough; case DB_VECTOR: return !(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)); case DE_VECTOR: case OF_VECTOR: case BR_VECTOR: case UD_VECTOR: case DF_VECTOR: case SS_VECTOR: case GP_VECTOR: case MF_VECTOR: return true; } return false; } static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { /* * Instruction with address size override prefix opcode 0x67 * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { if (kvm_emulate_instruction(vcpu, 0)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_emulate_halt_noskip(vcpu); } return 1; } return 0; } /* * Forward all other exceptions that are valid in real mode. * FIXME: Breaks guest debugging in real mode, needs to be fixed with * the required debugging infrastructure rework. */ kvm_queue_exception(vcpu, vec); return 1; } static int handle_machine_check(struct kvm_vcpu *vcpu) { /* handled by vmx_vcpu_run() */ return 1; } /* * If the host has split lock detection disabled, then #AC is * unconditionally injected into the guest, which is the pre split lock * detection behaviour. * * If the host has split lock detection enabled then #AC is * only injected into the guest when: * - Guest CPL == 3 (user mode) * - Guest has #AC detection enabled in CR0 * - Guest EFLAGS has AC bit set */ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) { if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) return true; return vmx_get_cpl(vcpu) == 3 && kvm_is_cr0_bit_set(vcpu, X86_CR0_AM) && (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); } static bool is_xfd_nm_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.guest_fpu.fpstate->xfd && !kvm_is_cr0_bit_set(vcpu, X86_CR0_TS); } static int handle_exception_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; unsigned long cr2, dr6; u32 vect_info; vect_info = vmx->idt_vectoring_info; intr_info = vmx_get_intr_info(vcpu); /* * Machine checks are handled by handle_exception_irqoff(), or by * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by * vmx_vcpu_enter_exit(). */ if (is_machine_check(intr_info) || is_nmi(intr_info)) return 1; /* * Queue the exception here instead of in handle_nm_fault_irqoff(). * This ensures the nested_vmx check is not skipped so vmexit can * be reflected to L1 (when it intercepts #NM) before reaching this * point. */ if (is_nm_fault(intr_info)) { kvm_queue_exception_p(vcpu, NM_VECTOR, is_xfd_nm_fault(vcpu) ? vcpu->arch.guest_fpu.xfd_err : 0); return 1; } if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); if (WARN_ON_ONCE(is_ve_fault(intr_info))) { struct vmx_ve_information *ve_info = vmx->ve_info; WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION, "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason); dump_vmcs(vcpu); kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE"); return 1; } error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); /* * VMware backdoor emulation on #GP interception only handles * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero * error code on #GP. */ if (error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); return 1; } return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); } /* * The #PF with PFEC.RSVD = 1 indicates the guest is accessing * MMIO, it is better to report an internal error. * See the comments in vmx_handle_exit. */ if ((vect_info & VECTORING_INFO_VALID_MASK) && !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; vcpu->run->internal.ndata = 4; vcpu->run->internal.data[0] = vect_info; vcpu->run->internal.data[1] = intr_info; vcpu->run->internal.data[2] = error_code; vcpu->run->internal.data[3] = vcpu->arch.last_vmentry_cpu; return 0; } if (is_page_fault(intr_info)) { cr2 = vmx_get_exit_qual(vcpu); if (enable_ept && !vcpu->arch.apf.host_apf_flags) { /* * EPT will cause page fault only if we need to * detect illegal GPAs. */ WARN_ON_ONCE(!allow_smaller_maxphyaddr); kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); return 1; } else return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0); } ex_no = intr_info & INTR_INFO_VECTOR_MASK; if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no)) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { case DB_VECTOR: dr6 = vmx_get_exit_qual(vcpu); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { /* * If the #DB was due to ICEBP, a.k.a. INT1, skip the * instruction. ICEBP generates a trap-like #DB, but * despite its interception control being tied to #DB, * is an instruction intercept, i.e. the VM-Exit occurs * on the ICEBP itself. Use the inner "skip" helper to * avoid single-step #DB and MTF updates, as ICEBP is * higher priority. Note, skipping ICEBP still clears * STI and MOVSS blocking. * * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS * if single-step is enabled in RFLAGS and STI or MOVSS * blocking is active, as the CPU doesn't set the bit * on VM-Exit due to #DB interception. VM-Entry has a * consistency check that a single-step #DB is pending * in this scenario as the previous instruction cannot * have toggled RFLAGS.TF 0=>1 (because STI and POP/MOV * don't modify RFLAGS), therefore the one instruction * delay when activating single-step breakpoints must * have already expired. Note, the CPU sets/clears BS * as appropriate for all other VM-Exits types. */ if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); else if ((vmx_get_rflags(vcpu) & X86_EFLAGS_TF) && (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS))) vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS) | DR6_BS); kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; } kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); fallthrough; case BP_VECTOR: /* * Update instruction length as we may reinject #BP from * user space while in guest debugging mode. Reading it for * #DB as well causes no harm, it is not used in that case. */ vmx->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = ex_no; break; case AC_VECTOR: if (vmx_guest_inject_ac(vcpu)) { kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); return 1; } /* * Handle split lock. Depending on detection mode this will * either warn and disable split lock detection for this * task or force SIGBUS on it. */ if (handle_guest_split_lock(kvm_rip_read(vcpu))) return 1; fallthrough; default: kvm_run->exit_reason = KVM_EXIT_EXCEPTION; kvm_run->ex.exception = ex_no; kvm_run->ex.error_code = error_code; break; } return 0; } static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; } static int handle_triple_fault(struct kvm_vcpu *vcpu) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; return 0; } static int handle_io(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int size, in, string; unsigned port; exit_qualification = vmx_get_exit_qual(vcpu); string = (exit_qualification & 16) != 0; ++vcpu->stat.io_exits; if (string) return kvm_emulate_instruction(vcpu, 0); port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; in = (exit_qualification & 8) != 0; return kvm_fast_pio(vcpu, size, port, in); } void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: */ hypercall[0] = 0x0f; hypercall[1] = 0x01; hypercall[2] = 0xc1; } /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { if (is_guest_mode(vcpu)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long orig_val = val; /* * We get here when L2 changed cr0 in a way that did not change * any of L1's shadowed bits (see nested_vmx_exit_handled_cr), * but did change L0 shadowed bits. So we first calculate the * effective cr0 value that L1 would like to write into the * hardware. It consists of the L2-owned bits from the new * value combined with the L1-owned bits from L1's guest_cr0. */ val = (val & ~vmcs12->cr0_guest_host_mask) | (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); if (kvm_set_cr0(vcpu, val)) return 1; vmcs_writel(CR0_READ_SHADOW, orig_val); return 0; } else { return kvm_set_cr0(vcpu, val); } } static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) { if (is_guest_mode(vcpu)) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long orig_val = val; /* analogously to handle_set_cr0 */ val = (val & ~vmcs12->cr4_guest_host_mask) | (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask); if (kvm_set_cr4(vcpu, val)) return 1; vmcs_writel(CR4_READ_SHADOW, orig_val); return 0; } else return kvm_set_cr4(vcpu, val); } static int handle_desc(struct kvm_vcpu *vcpu) { /* * UMIP emulation relies on intercepting writes to CR4.UMIP, i.e. this * and other code needs to be updated if UMIP can be guest owned. */ BUILD_BUG_ON(KVM_POSSIBLE_CR4_GUEST_BITS & X86_CR4_UMIP); WARN_ON_ONCE(!kvm_is_cr4_bit_set(vcpu, X86_CR4_UMIP)); return kvm_emulate_instruction(vcpu, 0); } static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; int cr; int reg; int err; int ret; exit_qualification = vmx_get_exit_qual(vcpu); cr = exit_qualification & 15; reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ val = kvm_register_read(vcpu, reg); trace_kvm_cr_write(cr, val); switch (cr) { case 0: err = handle_set_cr0(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 3: WARN_ON_ONCE(enable_unrestricted_guest); err = kvm_set_cr3(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 4: err = handle_set_cr4(vcpu, val); return kvm_complete_insn_gp(vcpu, err); case 8: { u8 cr8_prev = kvm_get_cr8(vcpu); u8 cr8 = (u8)val; err = kvm_set_cr8(vcpu, cr8); ret = kvm_complete_insn_gp(vcpu, err); if (lapic_in_kernel(vcpu)) return ret; if (cr8_prev <= cr8) return ret; /* * TODO: we might be squashing a * KVM_GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } } break; case 2: /* clts */ KVM_BUG(1, vcpu->kvm, "Guest always owns CR0.TS"); return -EIO; case 1: /*mov from cr*/ switch (cr) { case 3: WARN_ON_ONCE(enable_unrestricted_guest); val = kvm_read_cr3(vcpu); kvm_register_write(vcpu, reg, val); trace_kvm_cr_read(cr, val); return kvm_skip_emulated_instruction(vcpu); case 8: val = kvm_get_cr8(vcpu); kvm_register_write(vcpu, reg, val); trace_kvm_cr_read(cr, val); return kvm_skip_emulated_instruction(vcpu); } break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val); return kvm_skip_emulated_instruction(vcpu); default: break; } vcpu->run->exit_reason = 0; vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int dr, dr7, reg; int err = 1; exit_qualification = vmx_get_exit_qual(vcpu); dr = exit_qualification & DEBUG_REG_ACCESS_NUM; /* First, if DR does not exist, trigger UD */ if (!kvm_require_dr(vcpu, dr)) return 1; if (vmx_get_cpl(vcpu) > 0) goto out; dr7 = vmcs_readl(GUEST_DR7); if (dr7 & DR7_GD) { /* * As the vm-exit takes precedence over the debug trap, we * need to emulate the latter, either for the host or the * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { vcpu->run->debug.arch.dr6 = DR6_BD | DR6_ACTIVE_LOW; vcpu->run->debug.arch.dr7 = dr7; vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); vcpu->run->debug.arch.exception = DB_VECTOR; vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BD); return 1; } } if (vcpu->guest_debug == 0) { exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); /* * No more DR vmexits; force a reload of the debug registers * and reenter on this instruction. The next vmexit will * retrieve the full state of the debug registers. */ vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; return 1; } reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); err = 0; } else { err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); } out: return kvm_complete_insn_gp(vcpu, err); } void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); get_debugreg(vcpu->arch.db[2], 2); get_debugreg(vcpu->arch.db[3], 3); get_debugreg(vcpu->arch.dr6, 6); vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); /* * exc_debug expects dr6 to be cleared after it runs, avoid that it sees * a stale dr6 from the guest. */ set_debugreg(DR6_RESERVED, 6); } void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) { lockdep_assert_irqs_disabled(); set_debugreg(vcpu->arch.dr6, 6); } void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); } static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { kvm_apic_update_ppr(vcpu); return 1; } static int handle_interrupt_window(struct kvm_vcpu *vcpu) { exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); kvm_make_request(KVM_REQ_EVENT, vcpu); ++vcpu->stat.irq_window_exits; return 1; } static int handle_invlpg(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); kvm_mmu_invlpg(vcpu, exit_qualification); return kvm_skip_emulated_instruction(vcpu); } static int handle_apic_access(struct kvm_vcpu *vcpu) { if (likely(fasteoi)) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int access_type, offset; access_type = exit_qualification & APIC_ACCESS_TYPE; offset = exit_qualification & APIC_ACCESS_OFFSET; /* * Sane guest uses MOV to write EOI, with written value * not cared. So make a short-circuit here by avoiding * heavy instruction emulation. */ if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && (offset == APIC_EOI)) { kvm_lapic_set_eoi(vcpu); return kvm_skip_emulated_instruction(vcpu); } } return kvm_emulate_instruction(vcpu, 0); } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int vector = exit_qualification & 0xff; /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ kvm_apic_set_eoi_accelerated(vcpu, vector); return 1; } static int handle_apic_write(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); /* * APIC-write VM-Exit is trap-like, KVM doesn't need to advance RIP and * hardware has done any necessary aliasing, offset adjustments, etc... * for the access. I.e. the correct value has already been written to * the vAPIC page for the correct 16-byte chunk. KVM needs only to * retrieve the register value and emulate the access. */ u32 offset = exit_qualification & 0xff0; kvm_apic_write_nodecode(vcpu, offset); return 1; } static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; bool has_error_code = false; u32 error_code = 0; u16 tss_selector; int reason, type, idt_v, idt_index; idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); exit_qualification = vmx_get_exit_qual(vcpu); reason = (u32)exit_qualification >> 30; if (reason == TASK_SWITCH_GATE && idt_v) { switch (type) { case INTR_TYPE_NMI_INTR: vcpu->arch.nmi_injected = false; vmx_set_nmi_mask(vcpu, true); break; case INTR_TYPE_EXT_INTR: case INTR_TYPE_SOFT_INTR: kvm_clear_interrupt_queue(vcpu); break; case INTR_TYPE_HARD_EXCEPTION: if (vmx->idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { has_error_code = true; error_code = vmcs_read32(IDT_VECTORING_ERROR_CODE); } fallthrough; case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; default: break; } } tss_selector = exit_qualification; if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION && type != INTR_TYPE_EXT_INTR && type != INTR_TYPE_NMI_INTR)) WARN_ON(!skip_emulated_instruction(vcpu)); /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? */ return kvm_task_switch(vcpu, tss_selector, type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason, has_error_code, error_code); } static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmx_get_exit_qual(vcpu); gpa_t gpa; /* * EPT violation happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. * There are errata that may cause this bit to not be set: * AAK134, BY25. */ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && enable_vnmi && (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(vcpu, gpa, exit_qualification); /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because * if the illegal address is that of a paging structure, then * EPT_VIOLATION_ACC_WRITE bit is set. Alternatively, if supported we * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification); } static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* * A nested guest cannot optimize MMIO vmexits, because we have an * nGPA here instead of the required GPA. */ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); if (!is_guest_mode(vcpu) && !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { trace_kvm_fast_mmio(gpa); return kvm_skip_emulated_instruction(vcpu); } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); } static int handle_nmi_window(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(!enable_vnmi, vcpu->kvm)) return -EIO; exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } /* * Returns true if emulation is required (due to the vCPU having invalid state * with unsrestricted guest mode disabled) and KVM can't faithfully emulate the * current vCPU state. */ static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!vmx->vt.emulation_required) return false; /* * It is architecturally impossible for emulation to be required when a * nested VM-Enter is pending completion, as VM-Enter will VM-Fail if * guest state is invalid and unrestricted guest is disabled, i.e. KVM * should synthesize VM-Fail instead emulation L2 code. This path is * only reachable if userspace modifies L2 guest state after KVM has * performed the nested VM-Enter consistency checks. */ if (vmx->nested.nested_run_pending) return true; /* * KVM only supports emulating exceptions if the vCPU is in Real Mode. * If emulation is required, KVM can't perform a successful VM-Enter to * inject the exception. */ return !vmx->rmode.vm86_active && (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool intr_window_requested; unsigned count = 130; intr_window_requested = exec_controls_get(vmx) & CPU_BASED_INTR_WINDOW_EXITING; while (vmx->vt.emulation_required && count-- != 0) { if (intr_window_requested && !vmx_interrupt_blocked(vcpu)) return handle_interrupt_window(&vmx->vcpu); if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; if (!kvm_emulate_instruction(vcpu, 0)) return 0; if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_emulate_halt_noskip(vcpu); } /* * Note, return 1 and not 0, vcpu_run() will invoke * xfer_to_guest_mode() which will create a proper return * code. */ if (__xfer_to_guest_mode_work_pending()) return 1; } return 1; } int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) { if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } return 1; } /* * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. */ static int handle_pause(struct kvm_vcpu *vcpu) { if (!kvm_pause_in_guest(vcpu->kvm)) grow_ple_window(vcpu); /* * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting" * VM-execution control is ignored if CPL > 0. OTOH, KVM * never set PAUSE_EXITING and just set PLE if supported, * so the vcpu must be CPL=0 if it gets a PAUSE exit. */ kvm_vcpu_on_spin(vcpu, true); return kvm_skip_emulated_instruction(vcpu); } static int handle_monitor_trap(struct kvm_vcpu *vcpu) { return 1; } static int handle_invpcid(struct kvm_vcpu *vcpu) { u32 vmx_instruction_info; unsigned long type; gva_t gva; struct { u64 pcid; u64 gla; } operand; int gpr_index; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info); type = kvm_register_read(vcpu, gpr_index); /* According to the Intel instruction reference, the memory operand * is read even if it isn't needed (e.g., for type==all) */ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; return kvm_handle_invpcid(vcpu, type, gva); } static int handle_pml_full(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; trace_kvm_pml_full(vcpu->vcpu_id); exit_qualification = vmx_get_exit_qual(vcpu); /* * PML buffer FULL happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. */ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && enable_vnmi && (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); /* * PML buffer already flushed at beginning of VMEXIT. Nothing to do * here.., and there's no userspace involvement needed for PML. */ return 1; } static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * In the *extremely* unlikely scenario that this is a spurious VM-Exit * due to the timer expiring while it was "soft" disabled, just eat the * exit and re-enter the guest. */ if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) return EXIT_FASTPATH_REENTER_GUEST; /* * If the timer expired because KVM used it to force an immediate exit, * then mission accomplished. */ if (force_immediate_exit) return EXIT_FASTPATH_EXIT_HANDLED; /* * If L2 is active, go down the slow path as emulating the guest timer * expiration likely requires synthesizing a nested VM-Exit. */ if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; kvm_lapic_expired_hv_timer(vcpu); return EXIT_FASTPATH_REENTER_GUEST; } static int handle_preemption_timer(struct kvm_vcpu *vcpu) { /* * This non-fastpath handler is reached if and only if the preemption * timer was being used to emulate a guest timer while L2 is active. * All other scenarios are supposed to be handled in the fastpath. */ WARN_ON_ONCE(!is_guest_mode(vcpu)); kvm_lapic_expired_hv_timer(vcpu); return 1; } /* * When nested=0, all VMX instruction VM Exits filter here. The handlers * are overwritten by nested_vmx_hardware_setup() when nested=1. */ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } #ifndef CONFIG_X86_SGX_KVM static int handle_encls(struct kvm_vcpu *vcpu) { /* * SGX virtualization is disabled. There is no software enable bit for * SGX, so KVM intercepts all ENCLS leafs and injects a #UD to prevent * the guest from executing ENCLS (when SGX is supported by hardware). */ kvm_queue_exception(vcpu, UD_VECTOR); return 1; } #endif /* CONFIG_X86_SGX_KVM */ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) { /* * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK * VM-Exits. Unconditionally set the flag here and leave the handling to * vmx_handle_exit(). */ to_vt(vcpu)->exit_reason.bus_lock_detected = true; return 1; } static int handle_notify(struct kvm_vcpu *vcpu) { unsigned long exit_qual = vmx_get_exit_qual(vcpu); bool context_invalid = exit_qual & NOTIFY_VM_CONTEXT_INVALID; ++vcpu->stat.notify_window_exits; /* * Notify VM exit happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. */ if (enable_vnmi && (exit_qual & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); if (vcpu->kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_USER || context_invalid) { vcpu->run->exit_reason = KVM_EXIT_NOTIFY; vcpu->run->notify.flags = context_invalid ? KVM_NOTIFY_CONTEXT_INVALID : 0; return 0; } return 1; } /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs * to be done to userspace and return 0. */ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EXCEPTION_NMI] = handle_exception_nmi, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, [EXIT_REASON_NMI_WINDOW] = handle_nmi_window, [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, [EXIT_REASON_CPUID] = kvm_emulate_cpuid, [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = kvm_emulate_invd, [EXIT_REASON_INVLPG] = handle_invlpg, [EXIT_REASON_RDPMC] = kvm_emulate_rdpmc, [EXIT_REASON_VMCALL] = kvm_emulate_hypercall, [EXIT_REASON_VMCLEAR] = handle_vmx_instruction, [EXIT_REASON_VMLAUNCH] = handle_vmx_instruction, [EXIT_REASON_VMPTRLD] = handle_vmx_instruction, [EXIT_REASON_VMPTRST] = handle_vmx_instruction, [EXIT_REASON_VMREAD] = handle_vmx_instruction, [EXIT_REASON_VMRESUME] = handle_vmx_instruction, [EXIT_REASON_VMWRITE] = handle_vmx_instruction, [EXIT_REASON_VMOFF] = handle_vmx_instruction, [EXIT_REASON_VMON] = handle_vmx_instruction, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_APIC_WRITE] = handle_apic_write, [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, [EXIT_REASON_WBINVD] = kvm_emulate_wbinvd, [EXIT_REASON_XSETBV] = kvm_emulate_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_GDTR_IDTR] = handle_desc, [EXIT_REASON_LDTR_TR] = handle_desc, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = kvm_emulate_mwait, [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, [EXIT_REASON_MONITOR_INSTRUCTION] = kvm_emulate_monitor, [EXIT_REASON_INVEPT] = handle_vmx_instruction, [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = kvm_handle_invalid_op, [EXIT_REASON_RDSEED] = kvm_handle_invalid_op, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, [EXIT_REASON_NOTIFY] = handle_notify, }; static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); *reason = vmx->vt.exit_reason.full; *info1 = vmx_get_exit_qual(vcpu); if (!(vmx->vt.exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; *intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(*intr_info)) *error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); else *error_code = 0; } else { *info2 = 0; *intr_info = 0; *error_code = 0; } } void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) { *intr_info = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); if (is_exception_with_error_code(*intr_info)) *error_code = vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE); else *error_code = 0; } static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { __free_page(vmx->pml_pg); vmx->pml_pg = NULL; } } static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u16 pml_idx, pml_tail_index; u64 *pml_buf; int i; pml_idx = vmcs_read16(GUEST_PML_INDEX); /* Do nothing if PML buffer is empty */ if (pml_idx == PML_HEAD_INDEX) return; /* * PML index always points to the next available PML buffer entity * unless PML log has just overflowed. */ pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1; /* * PML log is written backwards: the CPU first writes the entry 511 * then the entry 510, and so on. * * Read the entries in the same order they were written, to ensure that * the dirty ring is filled in the same order the CPU wrote them. */ pml_buf = page_address(vmx->pml_pg); for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) { u64 gpa; gpa = pml_buf[i]; WARN_ON(gpa & (PAGE_SIZE - 1)); kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); } static void vmx_dump_dtsel(char *name, uint32_t limit) { pr_err("%s limit=0x%08x, base=0x%016lx\n", name, vmcs_read32(limit), vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); } static void vmx_dump_msrs(char *name, struct vmx_msrs *m) { unsigned int i; struct vmx_msr_entry *e; pr_err("MSR %s:\n", name); for (i = 0, e = m->val; i < m->nr; ++i, ++e) pr_err(" %2d: msr=0x%08x value=0x%016llx\n", i, e->index, e->value); } void dump_vmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmentry_ctl, vmexit_ctl; u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; u64 tertiary_exec_control; unsigned long cr4; int efer_slot; if (!dump_invalid_vmcs) { pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n"); return; } vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); cr4 = vmcs_readl(GUEST_CR4); if (cpu_has_secondary_exec_ctrls()) secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); else secondary_exec_control = 0; if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_control = vmcs_read64(TERTIARY_VM_EXEC_CONTROL); else tertiary_exec_control = 0; pr_err("VMCS %p, last attempted VM-entry on CPU %d\n", vmx->loaded_vmcs->vmcs, vcpu->arch.last_vmentry_cpu); pr_err("*** Guest State ***\n"); pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), vmcs_readl(CR0_GUEST_HOST_MASK)); pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); if (cpu_has_vmx_ept()) { pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); } pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", vmcs_readl(GUEST_SYSENTER_ESP), vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); efer_slot = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest, MSR_EFER); if (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER) pr_err("EFER= 0x%016llx\n", vmcs_read64(GUEST_IA32_EFER)); else if (efer_slot >= 0) pr_err("EFER= 0x%016llx (autoload)\n", vmx->msr_autoload.guest.val[efer_slot].value); else if (vmentry_ctl & VM_ENTRY_IA32E_MODE) pr_err("EFER= 0x%016llx (effective)\n", vcpu->arch.efer | (EFER_LMA | EFER_LME)); else pr_err("EFER= 0x%016llx (effective)\n", vcpu->arch.efer & ~(EFER_LMA | EFER_LME)); if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT) pr_err("PAT = 0x%016llx\n", vmcs_read64(GUEST_IA32_PAT)); pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", vmcs_read64(GUEST_IA32_DEBUGCTL), vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); if (cpu_has_load_perf_global_ctrl() && vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) pr_err("PerfGlobCtl = 0x%016llx\n", vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); pr_err("Interruptibility = %08x ActivityState = %08x\n", vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), vmcs_read32(GUEST_ACTIVITY_STATE)); if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) pr_err("InterruptStatus = %04x\n", vmcs_read16(GUEST_INTR_STATUS)); if (vmcs_read32(VM_ENTRY_MSR_LOAD_COUNT) > 0) vmx_dump_msrs("guest autoload", &vmx->msr_autoload.guest); if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0) vmx_dump_msrs("guest autostore", &vmx->msr_autostore.guest); pr_err("*** Host State ***\n"); pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), vmcs_read16(HOST_TR_SELECTOR)); pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), vmcs_readl(HOST_TR_BASE)); pr_err("GDTBase=%016lx IDTBase=%016lx\n", vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), vmcs_readl(HOST_CR4)); pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", vmcs_readl(HOST_IA32_SYSENTER_ESP), vmcs_read32(HOST_IA32_SYSENTER_CS), vmcs_readl(HOST_IA32_SYSENTER_EIP)); if (vmexit_ctl & VM_EXIT_LOAD_IA32_EFER) pr_err("EFER= 0x%016llx\n", vmcs_read64(HOST_IA32_EFER)); if (vmexit_ctl & VM_EXIT_LOAD_IA32_PAT) pr_err("PAT = 0x%016llx\n", vmcs_read64(HOST_IA32_PAT)); if (cpu_has_load_perf_global_ctrl() && vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) pr_err("PerfGlobCtl = 0x%016llx\n", vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); if (vmcs_read32(VM_EXIT_MSR_LOAD_COUNT) > 0) vmx_dump_msrs("host autoload", &vmx->msr_autoload.host); pr_err("*** Control State ***\n"); pr_err("CPUBased=0x%08x SecondaryExec=0x%08x TertiaryExec=0x%016llx\n", cpu_based_exec_ctrl, secondary_exec_control, tertiary_exec_control); pr_err("PinBased=0x%08x EntryControls=%08x ExitControls=%08x\n", pin_based_exec_ctrl, vmentry_ctl, vmexit_ctl); pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", vmcs_read32(EXCEPTION_BITMAP), vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", vmcs_read32(VM_EXIT_INTR_INFO), vmcs_read32(VM_EXIT_INTR_ERROR_CODE), vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); pr_err(" reason=%08x qualification=%016lx\n", vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); pr_err("IDTVectoring: info=%08x errcode=%08x\n", vmcs_read32(IDT_VECTORING_INFO_FIELD), vmcs_read32(IDT_VECTORING_ERROR_CODE)); pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) pr_err("TSC Multiplier = 0x%016llx\n", vmcs_read64(TSC_MULTIPLIER)); if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) { if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { u16 status = vmcs_read16(GUEST_INTR_STATUS); pr_err("SVI|RVI = %02x|%02x ", status >> 8, status & 0xff); } pr_cont("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); if (secondary_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) pr_err("APIC-access addr = 0x%016llx ", vmcs_read64(APIC_ACCESS_ADDR)); pr_cont("virt-APIC addr = 0x%016llx\n", vmcs_read64(VIRTUAL_APIC_PAGE_ADDR)); } if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) pr_err("PLE Gap=%08x Window=%08x\n", vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) pr_err("Virtual processor ID = 0x%04x\n", vmcs_read16(VIRTUAL_PROCESSOR_ID)); if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) { struct vmx_ve_information *ve_info = vmx->ve_info; u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS); /* * If KVM is dumping the VMCS, then something has gone wrong * already. Derefencing an address from the VMCS, which could * very well be corrupted, is a terrible idea. The virtual * address is known so use it. */ pr_err("VE info address = 0x%016llx%s\n", ve_info_pa, ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)"); pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n", ve_info->exit_reason, ve_info->delivery, ve_info->exit_qualification, ve_info->guest_linear_address, ve_info->guest_physical_address, ve_info->eptp_index); } } /* * The guest has exited. See if we can fix it or if we need userspace * assistance. */ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; u16 exit_handler_index; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before * querying dirty_bitmap, we only need to kick all vcpus out of guest * mode as if vcpus is in root mode, the PML buffer must has been * flushed already. Note, PML is never enabled in hardware while * running L2. */ if (enable_pml && !is_guest_mode(vcpu)) vmx_flush_pml_buffer(vcpu); /* * KVM should never reach this point with a pending nested VM-Enter. * More specifically, short-circuiting VM-Entry to emulate L2 due to * invalid guest state should never happen as that means KVM knowingly * allowed a nested VM-Enter with an invalid vmcs12. More below. */ if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm)) return -EIO; if (is_guest_mode(vcpu)) { /* * PML is never enabled when running L2, bail immediately if a * PML full exit occurs as something is horribly wrong. */ if (exit_reason.basic == EXIT_REASON_PML_FULL) goto unexpected_vmexit; /* * The host physical addresses of some pages of guest memory * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC * Page). The CPU may write to these pages via their host * physical address while L2 is running, bypassing any * address-translation-based dirty tracking (e.g. EPT write * protection). * * Mark them dirty on every exit from L2 to prevent them from * getting out of sync with dirty tracking. */ nested_mark_vmcs12_pages_dirty(vcpu); /* * Synthesize a triple fault if L2 state is invalid. In normal * operation, nested VM-Enter rejects any attempt to enter L2 * with invalid state. However, those checks are skipped if * state is being stuffed via RSM or KVM_SET_NESTED_STATE. If * L2 state is invalid, it means either L1 modified SMRAM state * or userspace provided bad state. Synthesize TRIPLE_FAULT as * doing so is architecturally allowed in the RSM case, and is * the least awful solution for the userspace case without * risking false positives. */ if (vmx->vt.emulation_required) { nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); return 1; } if (nested_vmx_reflect_vmexit(vcpu)) return 1; } /* If guest state is invalid, start emulating. L2 is handled above. */ if (vmx->vt.emulation_required) return handle_invalid_guest_state(vcpu); if (exit_reason.failed_vmentry) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason.full; vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; return 0; } if (unlikely(vmx->fail)) { dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; return 0; } if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH && exit_reason.basic != EXIT_REASON_NOTIFY && exit_reason.basic != EXIT_REASON_EPT_MISCONFIG)) { kvm_prepare_event_vectoring_exit(vcpu, INVALID_GPA); return 0; } if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) { if (!vmx_interrupt_blocked(vcpu)) { vmx->loaded_vmcs->soft_vnmi_blocked = 0; } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL && vcpu->arch.nmi_pending) { /* * This CPU don't support us in finding the end of an * NMI-blocked window if the guest runs with IRQs * disabled. So we pull the trigger after 1 s of * futile waiting, but inform the user about this. */ printk(KERN_WARNING "%s: Breaking out of NMI-blocked " "state on VCPU %d after 1 s timeout\n", __func__, vcpu->vcpu_id); vmx->loaded_vmcs->soft_vnmi_blocked = 0; } } if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; #ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) return handle_preemption_timer(vcpu); else if (exit_reason.basic == EXIT_REASON_INTERRUPT_WINDOW) return handle_interrupt_window(vcpu); else if (exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) return handle_external_interrupt(vcpu); else if (exit_reason.basic == EXIT_REASON_HLT) return kvm_emulate_halt(vcpu); else if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) return handle_ept_misconfig(vcpu); #endif exit_handler_index = array_index_nospec((u16)exit_reason.basic, kvm_vmx_max_exit_handlers); if (!kvm_vmx_exit_handlers[exit_handler_index]) goto unexpected_vmexit; return kvm_vmx_exit_handlers[exit_handler_index](vcpu); unexpected_vmexit: vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason.full); dump_vmcs(vcpu); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; vcpu->run->internal.ndata = 2; vcpu->run->internal.data[0] = exit_reason.full; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; return 0; } int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { int ret = __vmx_handle_exit(vcpu, exit_fastpath); /* * Exit to user space when bus lock detected to inform that there is * a bus lock in guest. */ if (vmx_get_exit_reason(vcpu).bus_lock_detected) { if (ret > 0) vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK; return 0; } return ret; } /* * Software based L1D cache flush which is used when microcode providing * the cache control MSR is not loaded. * * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to * flush it is required to read in 64 KiB because the replacement algorithm * is not exactly LRU. This could be sized at runtime via topology * information but as all relevant affected CPUs have 32KiB L1D cache size * there is no point in doing so. */ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) { int size = PAGE_SIZE << L1D_CACHE_ORDER; /* * This code is only executed when the flush mode is 'cond' or * 'always' */ if (static_branch_likely(&vmx_l1d_flush_cond)) { bool flush_l1d; /* * Clear the per-vcpu flush bit, it gets set again if the vCPU * is reloaded, i.e. if the vCPU is scheduled out or if KVM * exits to userspace, or if KVM reaches one of the unsafe * VMEXIT handlers, e.g. if KVM calls into the emulator. */ flush_l1d = vcpu->arch.l1tf_flush_l1d; vcpu->arch.l1tf_flush_l1d = false; /* * Clear the per-cpu flush bit, it gets set again from * the interrupt handlers. */ flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); kvm_clear_cpu_l1tf_flush_l1d(); if (!flush_l1d) return; } vcpu->stat.l1d_flush++; if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); return; } asm volatile( /* First ensure the pages are in the TLB */ "xorl %%eax, %%eax\n" ".Lpopulate_tlb:\n\t" "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" "addl $4096, %%eax\n\t" "cmpl %%eax, %[size]\n\t" "jne .Lpopulate_tlb\n\t" "xorl %%eax, %%eax\n\t" "cpuid\n\t" /* Now fill the cache */ "xorl %%eax, %%eax\n" ".Lfill_cache:\n" "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" "addl $64, %%eax\n\t" "cmpl %%eax, %[size]\n\t" "jne .Lfill_cache\n\t" "lfence\n" :: [flush_pages] "r" (vmx_l1d_flush_pages), [size] "r" (size) : "eax", "ebx", "ecx", "edx"); } void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; if (is_guest_mode(vcpu) && nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) return; tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; if (is_guest_mode(vcpu)) to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold; else vmcs_write32(TPR_THRESHOLD, tpr_threshold); } void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 sec_exec_control; if (!lapic_in_kernel(vcpu)) return; if (!flexpriority_enabled && !cpu_has_vmx_virtualize_x2apic_mode()) return; /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { vmx->nested.change_vmcs01_virtual_apic_mode = true; return; } sec_exec_control = secondary_exec_controls_get(vmx); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); switch (kvm_get_apic_mode(vcpu)) { case LAPIC_MODE_INVALID: WARN_ONCE(true, "Invalid local APIC state"); break; case LAPIC_MODE_DISABLED: break; case LAPIC_MODE_XAPIC: if (flexpriority_enabled) { sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); /* * Flush the TLB, reloading the APIC access page will * only do so if its physical address has changed, but * the guest may have inserted a non-APIC mapping into * the TLB while the APIC access page was disabled. */ kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } break; case LAPIC_MODE_X2APIC: if (cpu_has_vmx_virtualize_x2apic_mode()) sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; break; } secondary_exec_controls_set(vmx, sec_exec_control); vmx_update_msr_bitmap_x2apic(vcpu); } void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; struct page *refcounted_page; unsigned long mmu_seq; kvm_pfn_t pfn; bool writable; /* Defer reload until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { to_vmx(vcpu)->nested.reload_vmcs01_apic_access_page = true; return; } if (!(secondary_exec_controls_get(to_vmx(vcpu)) & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) return; /* * Explicitly grab the memslot using KVM's internal slot ID to ensure * KVM doesn't unintentionally grab a userspace memslot. It _should_ * be impossible for userspace to create a memslot for the APIC when * APICv is enabled, but paranoia won't hurt in this case. */ slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return; /* * Ensure that the mmu_notifier sequence count is read before KVM * retrieves the pfn from the primary MMU. Note, the memslot is * protected by SRCU, not the mmu_notifier. Pairs with the smp_wmb() * in kvm_mmu_invalidate_end(). */ mmu_seq = kvm->mmu_invalidate_seq; smp_rmb(); /* * No need to retry if the memslot does not exist or is invalid. KVM * controls the APIC-access page memslot, and only deletes the memslot * if APICv is permanently inhibited, i.e. the memslot won't reappear. */ pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &refcounted_page); if (is_error_noslot_pfn(pfn)) return; read_lock(&vcpu->kvm->mmu_lock); if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); else vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); /* * Do not pin the APIC access page in memory so that it can be freely * migrated, the MMU notifier will call us again if it is migrated or * swapped out. KVM backs the memslot with anonymous memory, the pfn * should always point at a refcounted page (if the pfn is valid). */ if (!WARN_ON_ONCE(!refcounted_page)) kvm_release_page_clean(refcounted_page); /* * No need for a manual TLB flush at this point, KVM has already done a * flush if there were SPTEs pointing at the previous page. */ read_unlock(&vcpu->kvm->mmu_lock); } void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; /* * If L2 is active, defer the SVI update until vmcs01 is loaded, as SVI * is only relevant for if and only if Virtual Interrupt Delivery is * enabled in vmcs12, and if VID is enabled then L2 EOIs affect L2's * vAPIC, not L1's vAPIC. KVM must update vmcs01 on the next nested * VM-Exit, otherwise L1 with run with a stale SVI. */ if (is_guest_mode(vcpu)) { /* * KVM is supposed to forward intercepted L2 EOIs to L1 if VID * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC. * Note, userspace can stuff state while L2 is active; assert * that VID is disabled if and only if the vCPU is in KVM_RUN * to avoid false positives if userspace is setting APIC state. */ WARN_ON_ONCE(vcpu->wants_to_run && nested_cpu_has_vid(get_vmcs12(vcpu))); to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true; return; } if (max_isr == -1) max_isr = 0; status = vmcs_read16(GUEST_INTR_STATUS); old = status >> 8; if (max_isr != old) { status &= 0xff; status |= max_isr << 8; vmcs_write16(GUEST_INTR_STATUS, status); } } static void vmx_set_rvi(int vector) { u16 status; u8 old; if (vector == -1) vector = 0; status = vmcs_read16(GUEST_INTR_STATUS); old = (u8)status & 0xff; if ((u8)vector != old) { status &= ~0xff; status |= (u8)vector; vmcs_write16(GUEST_INTR_STATUS, status); } } int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vt *vt = to_vt(vcpu); int max_irr; bool got_posted_interrupt; if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; if (pi_test_on(&vt->pi_desc)) { pi_clear_on(&vt->pi_desc); /* * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); got_posted_interrupt = kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); got_posted_interrupt = false; } /* * Newly recognized interrupts are injected via either virtual interrupt * delivery (RVI) or KVM_REQ_EVENT. Virtual interrupt delivery is * disabled in two cases: * * 1) If L2 is running and the vCPU has a new pending interrupt. If L1 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a * VM-Exit to L1. If L1 doesn't want to exit, the interrupt is injected * into L2, but KVM doesn't use virtual interrupt delivery to inject * interrupts into L2, and so KVM_REQ_EVENT is again needed. * * 2) If APICv is disabled for this vCPU, assigned devices may still * attempt to post interrupts. The posted interrupt vector will cause * a VM-Exit and the subsequent entry will call sync_pir_to_irr. */ if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu)) vmx_set_rvi(max_irr); else if (got_posted_interrupt) kvm_make_request(KVM_REQ_EVENT, vcpu); return max_irr; } void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } void vmx_do_interrupt_irqoff(unsigned long entry); void vmx_do_nmi_irqoff(void); static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { /* * Save xfd_err to guest_fpu before interrupt is enabled, so the * MSR value is not clobbered by the host activity before the guest * has chance to consume it. * * Update the guest's XFD_ERR if and only if XFD is enabled, as the #NM * interception may have been caused by L1 interception. Per the SDM, * XFD_ERR is not modified for non-XFD #NM, i.e. if CR0.TS=1. * * Note, XFD_ERR is updated _before_ the #NM interception check, i.e. * unlike CR2 and DR6, the value is not a payload that is attached to * the #NM exception. */ if (is_xfd_nm_fault(vcpu)) rdmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { /* if exit due to PF check for async PF */ if (is_page_fault(intr_info)) vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* if exit due to NM, handle before interrupts are enabled */ else if (is_nm_fault(intr_info)) handle_nm_fault_irqoff(vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); if (cpu_feature_enabled(X86_FEATURE_FRED)) fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); else vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); kvm_after_interrupt(vcpu); vcpu->arch.at_instruction_boundary = true; } void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { if (to_vt(vcpu)->emulation_required) return; if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); else if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXCEPTION_NMI) handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM)) return false; /* * We cannot do SMM unless we can run the guest in big * real mode. */ return enable_unrestricted_guest || emulate_invalid_guest_state; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return nested; case MSR_AMD64_VIRT_SPEC_CTRL: case MSR_AMD64_TSC_RATIO: /* This is AMD only. */ return false; default: return true; } } static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; bool unblock_nmi; u8 vector; bool idtv_info_valid; idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; if (enable_vnmi) { if (vmx->loaded_vmcs->nmi_known_unmasked) return; exit_intr_info = vmx_get_intr_info(&vmx->vcpu); unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; vector = exit_intr_info & INTR_INFO_VECTOR_MASK; /* * SDM 3: 27.7.1.2 (September 2008) * Re-set bit "block by NMI" before VM entry if vmexit caused by * a guest IRET fault. * SDM 3: 23.2.2 (September 2008) * Bit 12 is undefined in any of the following cases: * If the VM exit sets the valid bit in the IDT-vectoring * information field. * If the VM exit is due to a double fault. */ if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi && vector != DF_VECTOR && !idtv_info_valid) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); else vmx->loaded_vmcs->nmi_known_unmasked = !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI); } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->vnmi_blocked_time += ktime_to_ns(ktime_sub(ktime_get(), vmx->loaded_vmcs->entry_time)); } static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, u32 idt_vectoring_info, int instr_len_field, int error_code_field) { u8 vector; int type; bool idtv_info_valid; idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; vcpu->arch.nmi_injected = false; kvm_clear_exception_queue(vcpu); kvm_clear_interrupt_queue(vcpu); if (!idtv_info_valid) return; kvm_make_request(KVM_REQ_EVENT, vcpu); vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; switch (type) { case INTR_TYPE_NMI_INTR: vcpu->arch.nmi_injected = true; /* * SDM 3: 27.7.1.2 (September 2008) * Clear bit "block by NMI" before VM entry if a NMI * delivery faulted. */ vmx_set_nmi_mask(vcpu, false); break; case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; case INTR_TYPE_HARD_EXCEPTION: { u32 error_code = 0; if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(error_code_field); kvm_requeue_exception(vcpu, vector, idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK, error_code); break; } case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; case INTR_TYPE_EXT_INTR: kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; default: break; } } static void vmx_complete_interrupts(struct vcpu_vmx *vmx) { __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info, VM_EXIT_INSTRUCTION_LEN, IDT_VECTORING_ERROR_CODE); } void vmx_cancel_injection(struct kvm_vcpu *vcpu) { __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), VM_ENTRY_INSTRUCTION_LEN, VM_ENTRY_EXCEPTION_ERROR_CODE); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) { int i, nr_msrs; struct perf_guest_switch_msr *msrs; struct kvm_pmu *pmu = vcpu_to_pmu(&vmx->vcpu); pmu->host_cross_mapped_mask = 0; if (pmu->pebs_enable & pmu->global_ctrl) intel_pmu_cross_mapped_check(pmu); /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */ msrs = perf_guest_get_msrs(&nr_msrs, (void *)pmu); if (!msrs) return; for (i = 0; i < nr_msrs; i++) if (msrs[i].host == msrs[i].guest) clear_atomic_switch_msr(vmx, msrs[i].msr); else add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest, msrs[i].host, false); } static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; if (force_immediate_exit) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (vmx->hv_deadline_tsc != -1) { tscl = rdtsc(); if (vmx->hv_deadline_tsc > tscl) /* set_hv_timer ensures the delta fits in 32-bits */ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> cpu_preemption_timer_multi); else delta_tsc = 0; vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1); vmx->loaded_vmcs->hv_timer_soft_disabled = true; } } void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) { if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) { vmx->loaded_vmcs->host_state.rsp = host_rsp; vmcs_writel(HOST_RSP, host_rsp); } } void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags) { u64 hostval = this_cpu_read(x86_spec_ctrl_current); if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) return; if (flags & VMX_RUN_SAVE_SPEC_CTRL) vmx->spec_ctrl = native_rdmsrq(MSR_IA32_SPEC_CTRL); /* * If the guest/host SPEC_CTRL values differ, restore the host value. * * For legacy IBRS, the IBRS bit always needs to be written after * transitioning from a less privileged predictor mode, regardless of * whether the guest/host values differ. */ if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || vmx->spec_ctrl != hostval) native_wrmsrq(MSR_IA32_SPEC_CTRL, hostval); barrier_nospec(); } static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, bool force_immediate_exit) { /* * If L2 is active, some VMX preemption timer exits can be handled in * the fastpath even, all other exits must use the slow path. */ if (is_guest_mode(vcpu) && vmx_get_exit_reason(vcpu).basic != EXIT_REASON_PREEMPTION_TIMER) return EXIT_FASTPATH_NONE; switch (vmx_get_exit_reason(vcpu).basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); case EXIT_REASON_HLT: return handle_fastpath_hlt(vcpu); default: return EXIT_FASTPATH_NONE; } } noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu) { if ((u16)vmx_get_exit_reason(vcpu).basic != EXIT_REASON_EXCEPTION_NMI || !is_nmi(vmx_get_intr_info(vcpu))) return; kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); if (cpu_feature_enabled(X86_FEATURE_FRED)) fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); else vmx_do_nmi_irqoff(); kvm_after_interrupt(vcpu); } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, unsigned int flags) { struct vcpu_vmx *vmx = to_vmx(vcpu); guest_state_enter_irqoff(); /* * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW * mitigation for MDS is done late in VMentry and is still * executed in spite of L1D Flush. This is because an extra VERW * should not matter much after the big hammer L1D Flush. * * cpu_buf_vm_clear is used when system is not vulnerable to MDS/TAA, * and is affected by MMIO Stale Data. In such cases mitigation in only * needed against an MMIO capable guest. */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&cpu_buf_vm_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); vmx_disable_fb_clear(vmx); if (vcpu->arch.cr2 != native_read_cr2()) native_write_cr2(vcpu->arch.cr2); vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, flags); vcpu->arch.cr2 = native_read_cr2(); vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; vmx->idt_vectoring_info = 0; vmx_enable_fb_clear(vmx); if (unlikely(vmx->fail)) { vmx->vt.exit_reason.full = 0xdead; goto out; } vmx->vt.exit_reason.full = vmcs_read32(VM_EXIT_REASON); if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry)) vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_handle_nmi(vcpu); out: guest_state_exit_irqoff(); } fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->entry_time = ktime_get(); /* * Don't enter VMX if guest state is invalid, let the exit handler * start emulation until we arrive back to a valid state. Synthesize a * consistency check VM-Exit due to invalid guest state and bail. */ if (unlikely(vmx->vt.emulation_required)) { vmx->fail = 0; vmx->vt.exit_reason.full = EXIT_REASON_INVALID_STATE; vmx->vt.exit_reason.failed_vmentry = 1; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); vmx->vt.exit_qualification = ENTRY_FAIL_DEFAULT; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); vmx->vt.exit_intr_info = 0; return EXIT_FASTPATH_NONE; } trace_kvm_entry(vcpu, force_immediate_exit); if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; vmcs_write32(PLE_WINDOW, vmx->ple_window); } /* * We did this in prepare_switch_to_guest, because it needs to * be within srcu_read_lock. */ WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time * it switches back to the current->mm, which can occur in KVM context * when switching to a temporary mm to patch kernel code, e.g. if KVM * toggles a static key while handling a VM-Exit. */ cr3 = __get_current_cr3_fast(); if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { vmcs_writel(HOST_CR3, cr3); vmx->loaded_vmcs->host_state.cr3 = cr3; } cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); vmx->loaded_vmcs->host_state.cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug * exceptions being set, but that's not correct for the guest debugging * case. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); kvm_load_guest_xsave_state(vcpu); pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); if (intel_pmu_lbr_is_enabled(vcpu)) vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) vmx_update_hv_timer(vcpu, force_immediate_exit); else if (force_immediate_exit) smp_send_reschedule(vcpu->cpu); kvm_wait_lapic_expire(vcpu); /* The actual VMENTER/EXIT is in the .noinstr.text section. */ vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ if (kvm_is_using_evmcs()) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; current_evmcs->hv_vp_id = kvm_hv_get_vpindex(vcpu); } /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (vcpu->arch.host_debugctl) update_debugctlmsr(vcpu->arch.host_debugctl); #ifndef CONFIG_X86_64 /* * The sysexit path does not restore ds/es, so we must set them to * a reasonable value ourselves. * * We can't defer this to vmx_prepare_switch_to_host() since that * function may be executed in interrupt context, which saves and * restore segments around it, nullifying its effect. */ loadsegment(ds, __USER_DS); loadsegment(es, __USER_DS); #endif pt_guest_exit(vmx); kvm_load_host_xsave_state(vcpu); if (is_guest_mode(vcpu)) { /* * Track VMLAUNCH/VMRESUME that have made past guest state * checking. */ if (vmx->nested.nested_run_pending && !vmx_get_exit_reason(vcpu).failed_vmentry) ++vcpu->stat.nested_run; vmx->nested.nested_run_pending = 0; } if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; if (unlikely((u16)vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } void vmx_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (enable_pml) vmx_destroy_pml_buffer(vmx); free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); free_page((unsigned long)vmx->ve_info); } int vmx_vcpu_create(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; int i, err; BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); vmx = to_vmx(vcpu); INIT_LIST_HEAD(&vmx->vt.pi_wakeup_list); err = -ENOMEM; vmx->vpid = allocate_vpid(); /* * If PML is turned on, failure on enabling PML just results in failure * of creating the vcpu, therefore we can simplify PML logic (by * avoiding dealing with cases, such as enabling PML partially on vcpus * for the guest), etc. */ if (enable_pml) { vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) goto free_vpid; } for (i = 0; i < kvm_nr_uret_msrs; ++i) vmx->guest_uret_msrs[i].mask = -1ull; if (boot_cpu_has(X86_FEATURE_RTM)) { /* * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. * Keep the host value unchanged to avoid changing CPUID bits * under the host kernel's feet. */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); if (err < 0) goto free_pml; /* * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the * feature only for vmcs01, KVM currently isn't equipped to realize any * performance benefits from enabling it for vmcs02. */ if (kvm_is_using_evmcs() && (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; evmcs->hv_enlightenments_control.msr_bitmap = 1; } /* The MSR bitmap starts with all ones */ bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); #ifdef CONFIG_X86_64 vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); if (kvm_cstate_in_guest(vcpu->kvm)) { vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); } vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { err = kvm_alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } if (enable_ept && !enable_unrestricted_guest) { err = init_rmode_identity_map(vcpu->kvm); if (err) goto free_vmcs; } err = -ENOMEM; if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) { struct page *page; BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE); /* ve_info must be page aligned. */ page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) goto free_vmcs; vmx->ve_info = page_to_virt(page); } if (vmx_can_use_ipiv(vcpu)) WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], __pa(&vmx->vt.pi_desc) | PID_TABLE_ENTRY_VALID); return 0; free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); free_pml: vmx_destroy_pml_buffer(vmx); free_vpid: free_vpid(vmx->vpid); return err; } #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" #define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) kvm->arch.pause_in_guest = true; if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: case L1TF_MITIGATION_FLUSH_NOWARN: /* 'I explicitly don't care' is set */ break; case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: case L1TF_MITIGATION_FULL: /* * Warn upon starting the first VM in a potentially * insecure environment. */ if (sched_smt_active()) pr_warn_once(L1TF_MSG_SMT); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) pr_warn_once(L1TF_MSG_L1D); break; case L1TF_MITIGATION_FULL_FORCE: /* Flush is enforced */ break; } } if (enable_pml) kvm->arch.cpu_dirty_log_size = PML_LOG_NR_ENTRIES; return 0; } static inline bool vmx_ignore_guest_pat(struct kvm *kvm) { /* * Non-coherent DMA devices need the guest to flush CPU properly. * In that case it is not possible to map all guest RAM as WB, so * always trust guest PAT. */ return !kvm_arch_has_noncoherent_dma(kvm) && kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT); } u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { /* * Force UC for host MMIO regions, as allowing the guest to access MMIO * with cacheable accesses will result in Machine Checks. */ if (is_mmio) return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; /* Force WB if ignoring guest PAT */ if (vmx_ignore_guest_pat(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) { /* * These bits in the secondary execution controls field * are dynamic, the others are mostly based on the hypervisor * architecture and the guest's CPUID. Do not touch the * dynamic bits. */ u32 mask = SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC; u32 cur_ctl = secondary_exec_controls_get(vmx); secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask)); } /* * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits * (indicating "allowed-1") if they are supported in the guest's CPUID. */ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_cpuid_entry2 *entry; vmx->nested.msrs.cr0_fixed1 = 0xffffffff; vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE; #define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do { \ if (entry && (entry->_reg & (_cpuid_mask))) \ vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask); \ } while (0) entry = kvm_find_cpuid_entry(vcpu, 0x1); cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); cr4_fixed1_update(X86_CR4_DE, edx, feature_bit(DE)); cr4_fixed1_update(X86_CR4_PSE, edx, feature_bit(PSE)); cr4_fixed1_update(X86_CR4_PAE, edx, feature_bit(PAE)); cr4_fixed1_update(X86_CR4_MCE, edx, feature_bit(MCE)); cr4_fixed1_update(X86_CR4_PGE, edx, feature_bit(PGE)); cr4_fixed1_update(X86_CR4_OSFXSR, edx, feature_bit(FXSR)); cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, feature_bit(XMM)); cr4_fixed1_update(X86_CR4_VMXE, ecx, feature_bit(VMX)); cr4_fixed1_update(X86_CR4_SMXE, ecx, feature_bit(SMX)); cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 0); cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); #undef cr4_fixed1_update } static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_cpuid_entry2 *best = NULL; int i; for (i = 0; i < PT_CPUID_LEAVES; i++) { best = kvm_find_cpuid_entry_index(vcpu, 0x14, i); if (!best) return; vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax; vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx; vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx; vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx; } /* Get the number of configurable Address Ranges for filtering */ vmx->pt_desc.num_address_ranges = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_num_address_ranges); /* Initialize and clear the no dependency bits */ vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS | RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC | RTIT_CTL_BRANCH_EN); /* * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise * will inject an #GP */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN; /* * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and * PSBFreq can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC | RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ); /* * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn and MTCFreq can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN | RTIT_CTL_MTC_RANGE); /* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite)) vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW | RTIT_CTL_PTW_EN); /* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_power_event_trace)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN; /* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabricEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; /* unmask address range configure area */ for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * XSAVES is effectively enabled if and only if XSAVE is also exposed * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be * set if and only if XSAVE is supported. */ if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)) guest_cpu_cap_clear(vcpu, X86_FEATURE_XSAVES); vmx_setup_uret_msrs(vmx); if (cpu_has_secondary_exec_ctrls()) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; else vmx->msr_ia32_feature_control_valid_bits &= ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpu_cap_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); if (boot_cpu_has(X86_FEATURE_RTM)) { struct vmx_uret_msr *msr; msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (msr) { bool enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RTM); vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); } } if (kvm_cpu_cap_has(X86_FEATURE_XFD)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); if (boot_cpu_has(X86_FEATURE_IBPB)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, !guest_has_pred_cmd_msr(vcpu)); if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_ENABLED; if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_LC_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_LC_ENABLED; /* Refresh #PF interception to account for MAXPHYADDR changes. */ vmx_update_exception_bitmap(vcpu); } static __init u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; u64 host_perf_cap = 0; if (!enable_pmu) return 0; if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrq(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { x86_perf_get_lbr(&vmx_lbr_caps); /* * KVM requires LBR callstack support, as the overhead due to * context switching LBRs without said support is too high. * See intel_pmu_create_guest_lbr_event() for more info. */ if (!vmx_lbr_caps.has_callstack) memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; /* * Disallow adaptive PEBS as it is functionally broken, can be * used by the guest to read *host* LBRs, and can be used to * bypass userspace event filters. To correctly and safely * support adaptive PEBS, KVM needs to: * * 1. Account for the ADAPTIVE flag when (re)programming fixed * counters. * * 2. Gain support from perf (or take direct control of counter * programming) to support events without adaptive PEBS * enabled for the hardware counter. * * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. * * 4. Document which PMU events are effectively exposed to the * guest via adaptive PEBS, and make adaptive PEBS mutually * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. */ perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; } static __init void vmx_set_cpu_caps(void) { kvm_set_cpu_caps(); /* CPUID 0x1 */ if (nested) kvm_cpu_cap_set(X86_FEATURE_VMX); /* CPUID 0x7 */ if (kvm_mpx_supported()) kvm_cpu_cap_check_and_set(X86_FEATURE_MPX); if (!cpu_has_vmx_invpcid()) kvm_cpu_cap_clear(X86_FEATURE_INVPCID); if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); if (vmx_pebs_supported()) { kvm_cpu_cap_check_and_set(X86_FEATURE_DS); kvm_cpu_cap_check_and_set(X86_FEATURE_DTES64); } if (!enable_pmu) kvm_cpu_cap_clear(X86_FEATURE_PDCM); kvm_caps.supported_perf_cap = vmx_get_perf_capabilities(); if (!enable_sgx) { kvm_cpu_cap_clear(X86_FEATURE_SGX); kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) kvm_cpu_cap_set(X86_FEATURE_UMIP); /* CPUID 0xD.1 */ kvm_caps.supported_xss = 0; if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); /* CPUID 0x80000001 and 0x7 (RDPID) */ if (!cpu_has_vmx_rdtscp()) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); kvm_cpu_cap_clear(X86_FEATURE_RDPID); } if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); } static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, unsigned long *exit_qualification) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned short port; int size; bool imm; /* * If the 'use IO bitmaps' VM-execution control is 0, IO instruction * VM-exits depend on the 'unconditional IO exiting' VM-execution * control. * * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. */ if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); if (info->intercept == x86_intercept_in || info->intercept == x86_intercept_ins) { port = info->src_val; size = info->dst_bytes; imm = info->src_type == OP_IMM; } else { port = info->dst_val; size = info->src_bytes; imm = info->dst_type == OP_IMM; } *exit_qualification = ((unsigned long)port << 16) | (size - 1); if (info->intercept == x86_intercept_ins || info->intercept == x86_intercept_outs) *exit_qualification |= BIT(4); if (info->rep_prefix) *exit_qualification |= BIT(5); if (imm) *exit_qualification |= BIT(6); return nested_vmx_check_io_bitmaps(vcpu, port, size); } int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage, struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned long exit_qualification = 0; u32 vm_exit_reason; u64 exit_insn_len; switch (info->intercept) { case x86_intercept_rdpid: /* * RDPID causes #UD if not enabled through secondary execution * controls (ENABLE_RDTSCP). Note, the implicit MSR access to * TSC_AUX is NOT subject to interception, i.e. checking only * the dedicated execution control is architecturally correct. */ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; return X86EMUL_PROPAGATE_FAULT; } return X86EMUL_CONTINUE; case x86_intercept_in: case x86_intercept_ins: case x86_intercept_out: case x86_intercept_outs: if (!vmx_is_io_intercepted(vcpu, info, &exit_qualification)) return X86EMUL_CONTINUE; vm_exit_reason = EXIT_REASON_IO_INSTRUCTION; break; case x86_intercept_lgdt: case x86_intercept_lidt: case x86_intercept_lldt: case x86_intercept_ltr: case x86_intercept_sgdt: case x86_intercept_sidt: case x86_intercept_sldt: case x86_intercept_str: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) return X86EMUL_CONTINUE; if (info->intercept == x86_intercept_lldt || info->intercept == x86_intercept_ltr || info->intercept == x86_intercept_sldt || info->intercept == x86_intercept_str) vm_exit_reason = EXIT_REASON_LDTR_TR; else vm_exit_reason = EXIT_REASON_GDTR_IDTR; /* * FIXME: Decode the ModR/M to generate the correct exit * qualification for memory operands. */ break; case x86_intercept_hlt: if (!nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING)) return X86EMUL_CONTINUE; vm_exit_reason = EXIT_REASON_HLT; break; case x86_intercept_pause: /* * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides * with vanilla NOPs in the emulator. Apply the interception * check only to actual PAUSE instructions. Don't check * PAUSE-loop-exiting, software can't expect a given PAUSE to * exit, i.e. KVM is within its rights to allow L2 to execute * the PAUSE. */ if ((info->rep_prefix != REPE_PREFIX) || !nested_cpu_has(vmcs12, CPU_BASED_PAUSE_EXITING)) return X86EMUL_CONTINUE; vm_exit_reason = EXIT_REASON_PAUSE_INSTRUCTION; break; /* TODO: check more intercepts... */ default: return X86EMUL_UNHANDLEABLE; } exit_insn_len = abs_diff((s64)info->next_rip, (s64)info->rip); if (!exit_insn_len || exit_insn_len > X86_MAX_INSTRUCTION_LENGTH) return X86EMUL_UNHANDLEABLE; __nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification, exit_insn_len); return X86EMUL_INTERCEPTED; } #ifdef CONFIG_X86_64 /* (a << shift) / divisor, return 1 if overflow otherwise 0 */ static inline int u64_shl_div_u64(u64 a, unsigned int shift, u64 divisor, u64 *result) { u64 low = a << shift, high = a >> (64 - shift); /* To avoid the overflow on divq */ if (high >= divisor) return 1; /* Low hold the result, high hold rem which is discarded */ asm("divq %2\n\t" : "=a" (low), "=d" (high) : "rm" (divisor), "0" (low), "1" (high)); *result = low; return 0; } int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; vmx = to_vmx(vcpu); tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; lapic_timer_advance_cycles = nsec_to_cycles(vcpu, ktimer->timer_advance_ns); if (delta_tsc > lapic_timer_advance_cycles) delta_tsc -= lapic_timer_advance_cycles; else delta_tsc = 0; /* Convert to host delta tsc if tsc scaling is enabled */ if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio && delta_tsc && u64_shl_div_u64(delta_tsc, kvm_caps.tsc_scaling_ratio_frac_bits, vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc)) return -ERANGE; /* * If the delta tsc can't fit in the 32 bit after the multi shift, * we can't use the preemption timer. * It's possible that it fits on later vmentries, but checking * on every vmentry is costly so we just use an hrtimer. */ if (delta_tsc >> (cpu_preemption_timer_multi + 32)) return -ERANGE; vmx->hv_deadline_tsc = tscl + delta_tsc; *expired = !delta_tsc; return 0; } void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (WARN_ON_ONCE(!enable_pml)) return; if (is_guest_mode(vcpu)) { vmx->nested.update_vmcs01_cpu_dirty_logging = true; return; } /* * Note, nr_memslots_dirty_logging can be changed concurrent with this * code, but in that case another update request will be made and so * the guest will never run with a stale PML value. */ if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); else secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= FEAT_CTL_LMCE_ENABLED; else to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_LMCE_ENABLED; } #ifdef CONFIG_KVM_SMM int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; return !is_smm(vcpu); } int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); /* * TODO: Implement custom flows for forcing the vCPU out/in of L2 on * SMI and RSM. Using the common VM-Exit + VM-Enter routines is wrong * SMI and RSM only modify state that is saved and restored via SMRAM. * E.g. most MSRs are left untouched, but many are modified by VM-Exit * and VM-Enter, and thus L2's values may be corrupted on SMI+RSM. */ vmx->nested.smm.guest_mode = is_guest_mode(vcpu); if (vmx->nested.smm.guest_mode) nested_vmx_vmexit(vcpu, -1, 0, 0); vmx->nested.smm.vmxon = vmx->nested.vmxon; vmx->nested.vmxon = false; vmx_clear_hlt(vcpu); return 0; } int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; if (vmx->nested.smm.vmxon) { vmx->nested.vmxon = true; vmx->nested.smm.vmxon = false; } if (vmx->nested.smm.guest_mode) { ret = nested_vmx_enter_non_root_mode(vcpu, false); if (ret) return ret; vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; } return 0; } void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } #endif bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } void vmx_migrate_timers(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; if (hrtimer_try_to_cancel(timer) == 1) hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); } } void vmx_hardware_unsetup(void) { kvm_set_posted_intr_wakeup_handler(NULL); if (nested) nested_vmx_hardware_unsetup(); free_kvm_area(); } void vmx_vm_destroy(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm)); } /* * Note, the SDM states that the linear address is masked *after* the modified * canonicality check, whereas KVM masks (untags) the address and then performs * a "normal" canonicality check. Functionally, the two methods are identical, * and when the masking occurs relative to the canonicality check isn't visible * to software, i.e. KVM's behavior doesn't violate the SDM. */ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags) { int lam_bit; unsigned long cr3_bits; if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) return gva; if (!is_64_bit_mode(vcpu)) return gva; /* * Bit 63 determines if the address should be treated as user address * or a supervisor address. */ if (!(gva & BIT_ULL(63))) { cr3_bits = kvm_get_active_cr3_lam_bits(vcpu); if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48))) return gva; /* LAM_U48 is ignored if LAM_U57 is set. */ lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47; } else { if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP)) return gva; lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; } /* * Untag the address by sign-extending the lam_bit, but NOT to bit 63. * Bit 63 is retained from the raw virtual address so that untagging * doesn't change a user access to a supervisor access, and vice versa. */ return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); } static unsigned int vmx_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* '0' on failure so that the !PT case can use a RET0 static call. */ if (!vcpu || !kvm_handling_nmi_from_guest(vcpu)) return 0; kvm_make_request(KVM_REQ_PMI, vcpu); __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT, (unsigned long *)&vcpu->arch.pmu.global_status); return 1; } static __init void vmx_setup_user_return_msrs(void) { /* * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm * will emulate SYSCALL in legacy mode if the vendor string in guest * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To * support this emulation, MSR_STAR is included in the list for i386, * but is never loaded into hardware. MSR_CSTAR is also never loaded * into hardware and is here purely for emulation purposes. */ const u32 vmx_uret_msrs_list[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_TSC_AUX, MSR_STAR, MSR_IA32_TSX_CTRL, }; int i; BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) kvm_add_user_return_msr(vmx_uret_msrs_list[i]); } static void __init vmx_setup_me_spte_mask(void) { u64 me_mask = 0; /* * On pre-MKTME system, boot_cpu_data.x86_phys_bits equals to * kvm_host.maxphyaddr. On MKTME and/or TDX capable systems, * boot_cpu_data.x86_phys_bits holds the actual physical address * w/o the KeyID bits, and kvm_host.maxphyaddr equals to * MAXPHYADDR reported by CPUID. Those bits between are KeyID bits. */ if (boot_cpu_data.x86_phys_bits != kvm_host.maxphyaddr) me_mask = rsvd_bits(boot_cpu_data.x86_phys_bits, kvm_host.maxphyaddr - 1); /* * Unlike SME, host kernel doesn't support setting up any * MKTME KeyID on Intel platforms. No memory encryption * bits should be included into the SPTE. */ kvm_mmu_set_me_spte_mask(0, me_mask); } __init int vmx_hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; int r; store_idt(&dt); host_idt_base = dt.address; vmx_setup_user_return_msrs(); if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); if (boot_cpu_has(X86_FEATURE_MPX)) { rdmsrq(MSR_IA32_BNDCFGS, host_bndcfgs); WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels() || !cpu_has_vmx_ept_mt_wb() || !cpu_has_vmx_invept_global()) enable_ept = 0; /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { pr_err_ratelimited("NX (Execute Disable) not supported\n"); return -EOPNOTSUPP; } if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; if (!cpu_has_vmx_unrestricted_guest() || !enable_ept) enable_unrestricted_guest = 0; if (!cpu_has_vmx_flexpriority()) flexpriority_enabled = 0; if (!cpu_has_virtual_nmis()) enable_vnmi = 0; #ifdef CONFIG_X86_SGX_KVM if (!cpu_has_vmx_encls_vmexit()) enable_sgx = false; #endif /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) vt_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) vt_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif if (!cpu_has_vmx_ple()) { ple_gap = 0; ple_window = 0; ple_window_grow = 0; ple_window_max = 0; ple_window_shrink = 0; } if (!cpu_has_vmx_apicv()) enable_apicv = 0; if (!enable_apicv) vt_x86_ops.sync_pir_to_irr = NULL; if (!enable_apicv || !cpu_has_vmx_ipiv()) enable_ipiv = false; if (cpu_has_vmx_tsc_scaling()) kvm_caps.has_tsc_control = true; kvm_caps.max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; kvm_caps.tsc_scaling_ratio_frac_bits = 48; kvm_caps.has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); kvm_caps.has_notify_vmexit = cpu_has_notify_vmexit(); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ if (enable_ept) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); else vt_x86_ops.get_mt_mask = NULL; /* * Setup shadow_me_value/shadow_me_mask to include MKTME KeyID * bits to shadow_zero_check. */ vmx_setup_me_spte_mask(); kvm_configure_mmu(enable_ept, 0, vmx_get_max_ept_level(), ept_caps_to_lpage_level(vmx_capability.ept)); /* * Only enable PML when hardware supports PML feature, and both EPT * and EPT A/D bit features are enabled -- PML depends on them to work. */ if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; if (enable_preemption_timer) { u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; use_timer_freq >>= cpu_preemption_timer_multi; /* * KVM "disables" the preemption timer by setting it to its max * value. Don't use the timer if it might cause spurious exits * at a rate faster than 0.1 Hz (of uninterrupted guest time). */ if (use_timer_freq > 0xffffffffu / 10) enable_preemption_timer = false; } if (!enable_preemption_timer) { vt_x86_ops.set_hv_timer = NULL; vt_x86_ops.cancel_hv_timer = NULL; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; kvm_caps.supported_mce_cap |= MCG_CMCI_P; if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) return -EINVAL; if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; else vt_init_ops.handle_intel_pt_intr = NULL; setup_default_sgx_lepubkeyhash(); if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) return r; } vmx_set_cpu_caps(); r = alloc_kvm_area(); if (r && nested) nested_vmx_hardware_unsetup(); kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); /* * On Intel CPUs that lack self-snoop feature, letting the guest control * memory types may result in unexpected behavior. So always ignore guest * PAT on those CPUs and map VM as writeback, not allowing userspace to * disable the quirk. * * On certain Intel CPUs (e.g. SPR, ICX), though self-snoop feature is * supported, UC is slow enough to cause issues with some older guests (e.g. * an old version of bochs driver uses ioremap() instead of ioremap_wc() to * map the video RAM, causing wayland desktop to fail to get started * correctly). To avoid breaking those older guests that rely on KVM to force * memory type to WB, provide KVM_X86_QUIRK_IGNORE_GUEST_PAT to preserve the * safer (for performance) default behavior. * * On top of this, non-coherent DMA devices need the guest to flush CPU * caches properly. This also requires honoring guest PAT, and is forced * independent of the quirk in vmx_ignore_guest_pat(). */ if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; return r; } static void vmx_cleanup_l1d_flush(void) { if (vmx_l1d_flush_pages) { free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); vmx_l1d_flush_pages = NULL; } /* Restore state so sysfs ignores VMX */ l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } void vmx_exit(void) { allow_smaller_maxphyaddr = false; vmx_cleanup_l1d_flush(); kvm_x86_vendor_exit(); } int __init vmx_init(void) { int r, cpu; if (!kvm_is_vmx_supported()) return -EOPNOTSUPP; /* * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing * to unwind if a later step fails. */ hv_init_evmcs(); r = kvm_x86_vendor_init(&vt_init_ops); if (r) return r; /* * Must be called after common x86 init so enable_ept is properly set * up. Hand the parameter mitigation value in which was stored in * the pre module init parser. If no parameter was given, it will * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); if (r) goto err_l1d_flush; for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); pi_init_cpu(cpu); } vmx_check_vmcs12_offsets(); /* * Shadow paging doesn't have a (further) performance penalty * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it * by default */ if (!enable_ept) allow_smaller_maxphyaddr = true; return 0; err_l1d_flush: kvm_x86_vendor_exit(); return r; } |
| 9 6 15 3 12 3 15 9 15 6 6 6 2 8 1 3 15 6 6 3 58 1 20 2 35 10 5 40 39 7 32 2 1 9 28 9 2 26 1 1 3 3 1 1 8 8 8 37 40 37 15 15 13 31 1 3 4 23 15 15 4 5 19 4 20 9 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/plist.h> #include <linux/sched/signal.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * On PREEMPT_RT, the hash bucket lock is a 'sleeping' spinlock with an * underlying rtmutex. The task which is about to be requeued could have * just woken up (timeout, signal). After the wake up the task has to * acquire hash bucket lock, which is held by the requeue code. As a task * can only be blocked on _ONE_ rtmutex at a time, the proxy lock blocking * and the hash bucket lock blocking would collide and corrupt state. * * On !PREEMPT_RT this is not a problem and everything could be serialized * on hash bucket lock, but aside of having the benefit of common code, * this allows to avoid doing the requeue when the task is already on the * way out and taking the hash bucket lock of the original uaddr1 when the * requeue has been completed. * * The following state transitions are valid: * * On the waiter side: * Q_REQUEUE_PI_NONE -> Q_REQUEUE_PI_IGNORE * Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_WAIT * * On the requeue side: * Q_REQUEUE_PI_NONE -> Q_REQUEUE_PI_INPROGRESS * Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_DONE/LOCKED * Q_REQUEUE_PI_IN_PROGRESS -> Q_REQUEUE_PI_NONE (requeue failed) * Q_REQUEUE_PI_WAIT -> Q_REQUEUE_PI_DONE/LOCKED * Q_REQUEUE_PI_WAIT -> Q_REQUEUE_PI_IGNORE (requeue failed) * * The requeue side ignores a waiter with state Q_REQUEUE_PI_IGNORE as this * signals that the waiter is already on the way out. It also means that * the waiter is still on the 'wait' futex, i.e. uaddr1. * * The waiter side signals early wakeup to the requeue side either through * setting state to Q_REQUEUE_PI_IGNORE or to Q_REQUEUE_PI_WAIT depending * on the current state. In case of Q_REQUEUE_PI_IGNORE it can immediately * proceed to take the hash bucket lock of uaddr1. If it set state to WAIT, * which means the wakeup is interleaving with a requeue in progress it has * to wait for the requeue side to change the state. Either to DONE/LOCKED * or to IGNORE. DONE/LOCKED means the waiter q is now on the uaddr2 futex * and either blocked (DONE) or has acquired it (LOCKED). IGNORE is set by * the requeue side when the requeue attempt failed via deadlock detection * and therefore the waiter q is still on the uaddr1 futex. */ enum { Q_REQUEUE_PI_NONE = 0, Q_REQUEUE_PI_IGNORE, Q_REQUEUE_PI_IN_PROGRESS, Q_REQUEUE_PI_WAIT, Q_REQUEUE_PI_DONE, Q_REQUEUE_PI_LOCKED, }; const struct futex_q futex_q_init = { /* list gets initialized in futex_queue()*/ .wake = futex_wake_mark, .key = FUTEX_KEY_INIT, .bitset = FUTEX_BITSET_MATCH_ANY, .requeue_state = ATOMIC_INIT(Q_REQUEUE_PI_NONE), }; /** * requeue_futex() - Requeue a futex_q from one hb to another * @q: the futex_q to requeue * @hb1: the source hash_bucket * @hb2: the target hash_bucket * @key2: the new key for the requeued futex_q */ static inline void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2, union futex_key *key2) { /* * If key1 and key2 hash to the same bucket, no need to * requeue. */ if (likely(&hb1->chain != &hb2->chain)) { plist_del(&q->list, &hb1->chain); futex_hb_waiters_dec(hb1); futex_hb_waiters_inc(hb2); plist_add(&q->list, &hb2->chain); q->lock_ptr = &hb2->lock; /* * hb1 and hb2 belong to the same futex_hash_bucket_private * because if we managed get a reference on hb1 then it can't be * replaced. Therefore we avoid put(hb1)+get(hb2) here. */ } q->key = *key2; } static inline bool futex_requeue_pi_prepare(struct futex_q *q, struct futex_pi_state *pi_state) { int old, new; /* * Set state to Q_REQUEUE_PI_IN_PROGRESS unless an early wakeup has * already set Q_REQUEUE_PI_IGNORE to signal that requeue should * ignore the waiter. */ old = atomic_read_acquire(&q->requeue_state); do { if (old == Q_REQUEUE_PI_IGNORE) return false; /* * futex_proxy_trylock_atomic() might have set it to * IN_PROGRESS and a interleaved early wake to WAIT. * * It was considered to have an extra state for that * trylock, but that would just add more conditionals * all over the place for a dubious value. */ if (old != Q_REQUEUE_PI_NONE) break; new = Q_REQUEUE_PI_IN_PROGRESS; } while (!atomic_try_cmpxchg(&q->requeue_state, &old, new)); q->pi_state = pi_state; return true; } static inline void futex_requeue_pi_complete(struct futex_q *q, int locked) { int old, new; old = atomic_read_acquire(&q->requeue_state); do { if (old == Q_REQUEUE_PI_IGNORE) return; if (locked >= 0) { /* Requeue succeeded. Set DONE or LOCKED */ WARN_ON_ONCE(old != Q_REQUEUE_PI_IN_PROGRESS && old != Q_REQUEUE_PI_WAIT); new = Q_REQUEUE_PI_DONE + locked; } else if (old == Q_REQUEUE_PI_IN_PROGRESS) { /* Deadlock, no early wakeup interleave */ new = Q_REQUEUE_PI_NONE; } else { /* Deadlock, early wakeup interleave. */ WARN_ON_ONCE(old != Q_REQUEUE_PI_WAIT); new = Q_REQUEUE_PI_IGNORE; } } while (!atomic_try_cmpxchg(&q->requeue_state, &old, new)); #ifdef CONFIG_PREEMPT_RT /* If the waiter interleaved with the requeue let it know */ if (unlikely(old == Q_REQUEUE_PI_WAIT)) rcuwait_wake_up(&q->requeue_wait); #endif } static inline int futex_requeue_pi_wakeup_sync(struct futex_q *q) { int old, new; old = atomic_read_acquire(&q->requeue_state); do { /* Is requeue done already? */ if (old >= Q_REQUEUE_PI_DONE) return old; /* * If not done, then tell the requeue code to either ignore * the waiter or to wake it up once the requeue is done. */ new = Q_REQUEUE_PI_WAIT; if (old == Q_REQUEUE_PI_NONE) new = Q_REQUEUE_PI_IGNORE; } while (!atomic_try_cmpxchg(&q->requeue_state, &old, new)); /* If the requeue was in progress, wait for it to complete */ if (old == Q_REQUEUE_PI_IN_PROGRESS) { #ifdef CONFIG_PREEMPT_RT rcuwait_wait_event(&q->requeue_wait, atomic_read(&q->requeue_state) != Q_REQUEUE_PI_WAIT, TASK_UNINTERRUPTIBLE); #else (void)atomic_cond_read_relaxed(&q->requeue_state, VAL != Q_REQUEUE_PI_WAIT); #endif } /* * Requeue is now either prohibited or complete. Reread state * because during the wait above it might have changed. Nothing * will modify q->requeue_state after this point. */ return atomic_read(&q->requeue_state); } /** * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue * @q: the futex_q * @key: the key of the requeue target futex * @hb: the hash_bucket of the requeue target futex * * During futex_requeue, with requeue_pi=1, it is possible to acquire the * target futex if it is uncontended or via a lock steal. * * 1) Set @q::key to the requeue target futex key so the waiter can detect * the wakeup on the right futex. * * 2) Dequeue @q from the hash bucket. * * 3) Set @q::rt_waiter to NULL so the woken up task can detect atomic lock * acquisition. * * 4) Set the q->lock_ptr to the requeue target hb->lock for the case that * the waiter has to fixup the pi state. * * 5) Complete the requeue state so the waiter can make progress. After * this point the waiter task can return from the syscall immediately in * case that the pi state does not have to be fixed up. * * 6) Wake the waiter task. * * Must be called with both q->lock_ptr and hb->lock held. */ static inline void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, struct futex_hash_bucket *hb) { q->key = *key; __futex_unqueue(q); WARN_ON(!q->rt_waiter); q->rt_waiter = NULL; /* * Acquire a reference for the waiter to ensure valid * futex_q::lock_ptr. */ futex_hash_get(hb); q->drop_hb_ref = true; q->lock_ptr = &hb->lock; /* Signal locked state to the waiter */ futex_requeue_pi_complete(q, 1); wake_up_state(q->task, TASK_NORMAL); } /** * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter * @pifutex: the user address of the to futex * @hb1: the from futex hash bucket, must be locked by the caller * @hb2: the to futex hash bucket, must be locked by the caller * @key1: the from futex key * @key2: the to futex key * @ps: address to store the pi_state pointer * @exiting: Pointer to store the task pointer of the owner task * which is in the middle of exiting * @set_waiters: force setting the FUTEX_WAITERS bit (1) or not (0) * * Try and get the lock on behalf of the top waiter if we can do it atomically. * Wake the top waiter if we succeed. If the caller specified set_waiters, * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit. * hb1 and hb2 must be held by the caller. * * @exiting is only set when the return value is -EBUSY. If so, this holds * a refcount on the exiting task on return and the caller needs to drop it * after waiting for the exit to complete. * * Return: * - 0 - failed to acquire the lock atomically; * - >0 - acquired the lock, return value is vpid of the top_waiter * - <0 - error */ static int futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2, union futex_key *key1, union futex_key *key2, struct futex_pi_state **ps, struct task_struct **exiting, int set_waiters) { struct futex_q *top_waiter; u32 curval; int ret; if (futex_get_value_locked(&curval, pifutex)) return -EFAULT; if (unlikely(should_fail_futex(true))) return -EFAULT; /* * Find the top_waiter and determine if there are additional waiters. * If the caller intends to requeue more than 1 waiter to pifutex, * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now, * as we have means to handle the possible fault. If not, don't set * the bit unnecessarily as it will force the subsequent unlock to enter * the kernel. */ top_waiter = futex_top_waiter(hb1, key1); /* There are no waiters, nothing for us to do. */ if (!top_waiter) return 0; /* * Ensure that this is a waiter sitting in futex_wait_requeue_pi() * and waiting on the 'waitqueue' futex which is always !PI. */ if (!top_waiter->rt_waiter || top_waiter->pi_state) return -EINVAL; /* Ensure we requeue to the expected futex. */ if (!futex_match(top_waiter->requeue_pi_key, key2)) return -EINVAL; /* Ensure that this does not race against an early wakeup */ if (!futex_requeue_pi_prepare(top_waiter, NULL)) return -EAGAIN; /* * Try to take the lock for top_waiter and set the FUTEX_WAITERS bit * in the contended case or if @set_waiters is true. * * In the contended case PI state is attached to the lock owner. If * the user space lock can be acquired then PI state is attached to * the new owner (@top_waiter->task) when @set_waiters is true. */ ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, exiting, set_waiters); if (ret == 1) { /* * Lock was acquired in user space and PI state was * attached to @top_waiter->task. That means state is fully * consistent and the waiter can return to user space * immediately after the wakeup. */ requeue_pi_wake_futex(top_waiter, key2, hb2); } else if (ret < 0) { /* Rewind top_waiter::requeue_state */ futex_requeue_pi_complete(top_waiter, ret); } else { /* * futex_lock_pi_atomic() did not acquire the user space * futex, but managed to establish the proxy lock and pi * state. top_waiter::requeue_state cannot be fixed up here * because the waiter is not enqueued on the rtmutex * yet. This is handled at the callsite depending on the * result of rt_mutex_start_proxy_lock() which is * guaranteed to be reached with this function returning 0. */ } return ret; } /** * futex_requeue() - Requeue waiters from uaddr1 to uaddr2 * @uaddr1: source futex user address * @flags1: futex flags (FLAGS_SHARED, etc.) * @uaddr2: target futex user address * @flags2: futex flags (FLAGS_SHARED, etc.) * @nr_wake: number of waiters to wake (must be 1 for requeue_pi) * @nr_requeue: number of waiters to requeue (0-INT_MAX) * @cmpval: @uaddr1 expected value (or %NULL) * @requeue_pi: if we are attempting to requeue from a non-pi futex to a * pi futex (pi to pi requeue is not supported) * * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire * uaddr2 atomically on behalf of the top waiter. * * Return: * - >=0 - on success, the number of tasks requeued or woken; * - <0 - on error */ int futex_requeue(u32 __user *uaddr1, unsigned int flags1, u32 __user *uaddr2, unsigned int flags2, int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; int task_count = 0, ret; struct futex_pi_state *pi_state = NULL; struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); if (nr_wake < 0 || nr_requeue < 0) return -EINVAL; /* * When PI not supported: return -ENOSYS if requeue_pi is true, * consequently the compiler knows requeue_pi is always false past * this point which will optimize away all the conditional code * further down. */ if (!IS_ENABLED(CONFIG_FUTEX_PI) && requeue_pi) return -ENOSYS; if (requeue_pi) { /* * Requeue PI only works on two distinct uaddrs. This * check is only valid for private futexes. See below. */ if (uaddr1 == uaddr2) return -EINVAL; /* * futex_requeue() allows the caller to define the number * of waiters to wake up via the @nr_wake argument. With * REQUEUE_PI, waking up more than one waiter is creating * more problems than it solves. Waking up a waiter makes * only sense if the PI futex @uaddr2 is uncontended as * this allows the requeue code to acquire the futex * @uaddr2 before waking the waiter. The waiter can then * return to user space without further action. A secondary * wakeup would just make the futex_wait_requeue_pi() * handling more complex, because that code would have to * look up pi_state and do more or less all the handling * which the requeue code has to do for the to be requeued * waiters. So restrict the number of waiters to wake to * one, and only wake it up when the PI futex is * uncontended. Otherwise requeue it and let the unlock of * the PI futex handle the wakeup. * * All REQUEUE_PI users, e.g. pthread_cond_signal() and * pthread_cond_broadcast() must use nr_wake=1. */ if (nr_wake != 1) return -EINVAL; /* * requeue_pi requires a pi_state, try to allocate it now * without any locks in case it fails. */ if (refill_pi_state_cache()) return -ENOMEM; } retry: ret = get_futex_key(uaddr1, flags1, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; ret = get_futex_key(uaddr2, flags2, &key2, requeue_pi ? FUTEX_WRITE : FUTEX_READ); if (unlikely(ret != 0)) return ret; /* * The check above which compares uaddrs is not sufficient for * shared futexes. We need to compare the keys: */ if (requeue_pi && futex_match(&key1, &key2)) return -EINVAL; retry_private: if (1) { CLASS(hb, hb1)(&key1); CLASS(hb, hb2)(&key2); futex_hb_waiters_inc(hb2); double_lock_hb(hb1, hb2); if (likely(cmpval != NULL)) { u32 curval; ret = futex_get_value_locked(&curval, uaddr1); if (unlikely(ret)) { futex_hb_waiters_dec(hb2); double_unlock_hb(hb1, hb2); ret = get_user(curval, uaddr1); if (ret) return ret; if (!(flags1 & FLAGS_SHARED)) goto retry_private; goto retry; } if (curval != *cmpval) { ret = -EAGAIN; goto out_unlock; } } if (requeue_pi) { struct task_struct *exiting = NULL; /* * Attempt to acquire uaddr2 and wake the top waiter. If we * intend to requeue waiters, force setting the FUTEX_WAITERS * bit. We force this here where we are able to easily handle * faults rather in the requeue loop below. * * Updates topwaiter::requeue_state if a top waiter exists. */ ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1, &key2, &pi_state, &exiting, nr_requeue); /* * At this point the top_waiter has either taken uaddr2 or * is waiting on it. In both cases pi_state has been * established and an initial refcount on it. In case of an * error there's nothing. * * The top waiter's requeue_state is up to date: * * - If the lock was acquired atomically (ret == 1), then * the state is Q_REQUEUE_PI_LOCKED. * * The top waiter has been dequeued and woken up and can * return to user space immediately. The kernel/user * space state is consistent. In case that there must be * more waiters requeued the WAITERS bit in the user * space futex is set so the top waiter task has to go * into the syscall slowpath to unlock the futex. This * will block until this requeue operation has been * completed and the hash bucket locks have been * dropped. * * - If the trylock failed with an error (ret < 0) then * the state is either Q_REQUEUE_PI_NONE, i.e. "nothing * happened", or Q_REQUEUE_PI_IGNORE when there was an * interleaved early wakeup. * * - If the trylock did not succeed (ret == 0) then the * state is either Q_REQUEUE_PI_IN_PROGRESS or * Q_REQUEUE_PI_WAIT if an early wakeup interleaved. * This will be cleaned up in the loop below, which * cannot fail because futex_proxy_trylock_atomic() did * the same sanity checks for requeue_pi as the loop * below does. */ switch (ret) { case 0: /* We hold a reference on the pi state. */ break; case 1: /* * futex_proxy_trylock_atomic() acquired the user space * futex. Adjust task_count. */ task_count++; ret = 0; break; /* * If the above failed, then pi_state is NULL and * waiter::requeue_state is correct. */ case -EFAULT: futex_hb_waiters_dec(hb2); double_unlock_hb(hb1, hb2); ret = fault_in_user_writeable(uaddr2); if (!ret) goto retry; return ret; case -EBUSY: case -EAGAIN: /* * Two reasons for this: * - EBUSY: Owner is exiting and we just wait for the * exit to complete. * - EAGAIN: The user space value changed. */ futex_hb_waiters_dec(hb2); double_unlock_hb(hb1, hb2); /* * Handle the case where the owner is in the middle of * exiting. Wait for the exit to complete otherwise * this task might loop forever, aka. live lock. */ wait_for_owner_exiting(ret, exiting); cond_resched(); goto retry; default: goto out_unlock; } } plist_for_each_entry_safe(this, next, &hb1->chain, list) { if (task_count - nr_wake >= nr_requeue) break; if (!futex_match(&this->key, &key1)) continue; /* * FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI should always * be paired with each other and no other futex ops. * * We should never be requeueing a futex_q with a pi_state, * which is awaiting a futex_unlock_pi(). */ if ((requeue_pi && !this->rt_waiter) || (!requeue_pi && this->rt_waiter) || this->pi_state) { ret = -EINVAL; break; } /* Plain futexes just wake or requeue and are done */ if (!requeue_pi) { if (++task_count <= nr_wake) this->wake(&wake_q, this); else requeue_futex(this, hb1, hb2, &key2); continue; } /* Ensure we requeue to the expected futex for requeue_pi. */ if (!futex_match(this->requeue_pi_key, &key2)) { ret = -EINVAL; break; } /* * Requeue nr_requeue waiters and possibly one more in the case * of requeue_pi if we couldn't acquire the lock atomically. * * Prepare the waiter to take the rt_mutex. Take a refcount * on the pi_state and store the pointer in the futex_q * object of the waiter. */ get_pi_state(pi_state); /* Don't requeue when the waiter is already on the way out. */ if (!futex_requeue_pi_prepare(this, pi_state)) { /* * Early woken waiter signaled that it is on the * way out. Drop the pi_state reference and try the * next waiter. @this->pi_state is still NULL. */ put_pi_state(pi_state); continue; } ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, this->rt_waiter, this->task); if (ret == 1) { /* * We got the lock. We do neither drop the refcount * on pi_state nor clear this->pi_state because the * waiter needs the pi_state for cleaning up the * user space value. It will drop the refcount * after doing so. this::requeue_state is updated * in the wakeup as well. */ requeue_pi_wake_futex(this, &key2, hb2); task_count++; } else if (!ret) { /* Waiter is queued, move it to hb2 */ requeue_futex(this, hb1, hb2, &key2); futex_requeue_pi_complete(this, 0); task_count++; } else { /* * rt_mutex_start_proxy_lock() detected a potential * deadlock when we tried to queue that waiter. * Drop the pi_state reference which we took above * and remove the pointer to the state from the * waiters futex_q object. */ this->pi_state = NULL; put_pi_state(pi_state); futex_requeue_pi_complete(this, ret); /* * We stop queueing more waiters and let user space * deal with the mess. */ break; } } /* * We took an extra initial reference to the pi_state in * futex_proxy_trylock_atomic(). We need to drop it here again. */ put_pi_state(pi_state); out_unlock: futex_hb_waiters_dec(hb2); double_unlock_hb(hb1, hb2); } wake_up_q(&wake_q); return ret ? ret : task_count; } /** * handle_early_requeue_pi_wakeup() - Handle early wakeup on the initial futex * @hb: the hash_bucket futex_q was original enqueued on * @q: the futex_q woken while waiting to be requeued * @timeout: the timeout associated with the wait (NULL if none) * * Determine the cause for the early wakeup. * * Return: * -EWOULDBLOCK or -ETIMEDOUT or -ERESTARTNOINTR */ static inline int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout) { int ret; /* * With the hb lock held, we avoid races while we process the wakeup. * We only need to hold hb (and not hb2) to ensure atomicity as the * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb. * It can't be requeued from uaddr2 to something else since we don't * support a PI aware source futex for requeue. */ WARN_ON_ONCE(&hb->lock != q->lock_ptr); /* * We were woken prior to requeue by a timeout or a signal. * Unqueue the futex_q and determine which it was. */ plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); /* Handle spurious wakeups gracefully */ ret = -EWOULDBLOCK; if (timeout && !timeout->task) ret = -ETIMEDOUT; else if (signal_pending(current)) ret = -ERESTARTNOINTR; return ret; } /** * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2 * @uaddr: the futex we initially wait on (non-pi) * @flags: futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), they must be * the same type, no requeueing from private to shared, etc. * @val: the expected value of uaddr * @abs_time: absolute timeout * @bitset: 32 bit wakeup bitset set by userspace, defaults to all * @uaddr2: the pi futex we will take prior to returning to user-space * * The caller will wait on uaddr and will be requeued by futex_requeue() to * uaddr2 which must be PI aware and unique from uaddr. Normal wakeup will wake * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to * userspace. This ensures the rt_mutex maintains an owner when it has waiters; * without one, the pi logic would not know which task to boost/deboost, if * there was a need to. * * We call schedule in futex_wait_queue() when we enqueue and return there * via the following-- * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue() * 2) wakeup on uaddr2 after a requeue * 3) signal * 4) timeout * * If 3, cleanup and return -ERESTARTNOINTR. * * If 2, we may then block on trying to take the rt_mutex and return via: * 5) successful lock * 6) signal * 7) timeout * 8) other lock acquisition failure * * If 6, return -EWOULDBLOCK (restarting the syscall would do the same). * * If 4 or 7, we cleanup and return with -ETIMEDOUT. * * Return: * - 0 - On success; * - <0 - On error */ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, u32 __user *uaddr2) { struct hrtimer_sleeper timeout, *to; struct rt_mutex_waiter rt_waiter; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; struct rt_mutex_base *pi_mutex; int res, ret; if (!IS_ENABLED(CONFIG_FUTEX_PI)) return -ENOSYS; if (uaddr == uaddr2) return -EINVAL; if (!bitset) return -EINVAL; to = futex_setup_timer(abs_time, &timeout, flags, current->timer_slack_ns); /* * The waiter is allocated on our stack, manipulated by the requeue * code while we sleep on uaddr. */ rt_mutex_init_waiter(&rt_waiter); ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) goto out; q.bitset = bitset; q.rt_waiter = &rt_waiter; q.requeue_pi_key = &key2; /* * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ ret = futex_wait_setup(uaddr, val, flags, &q, &key2, current); if (ret) goto out; /* Queue the futex_q, drop the hb lock, wait for wakeup. */ futex_do_wait(&q, to); switch (futex_requeue_pi_wakeup_sync(&q)) { case Q_REQUEUE_PI_IGNORE: { CLASS(hb, hb)(&q.key); /* The waiter is still on uaddr1 */ spin_lock(&hb->lock); ret = handle_early_requeue_pi_wakeup(hb, &q, to); spin_unlock(&hb->lock); } break; case Q_REQUEUE_PI_LOCKED: /* The requeue acquired the lock */ if (q.pi_state && (q.pi_state->owner != current)) { futex_q_lockptr_lock(&q); ret = fixup_pi_owner(uaddr2, &q, true); /* * Drop the reference to the pi state which the * requeue_pi() code acquired for us. */ put_pi_state(q.pi_state); spin_unlock(q.lock_ptr); /* * Adjust the return value. It's either -EFAULT or * success (1) but the caller expects 0 for success. */ ret = ret < 0 ? ret : 0; } break; case Q_REQUEUE_PI_DONE: /* Requeue completed. Current is 'pi_blocked_on' the rtmutex */ pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); /* * See futex_unlock_pi()'s cleanup: comment. */ if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) ret = 0; futex_q_lockptr_lock(&q); debug_rt_mutex_free_waiter(&rt_waiter); /* * Fixup the pi_state owner and possibly acquire the lock if we * haven't already. */ res = fixup_pi_owner(uaddr2, &q, !ret); /* * If fixup_pi_owner() returned an error, propagate that. If it * acquired the lock, clear -ETIMEDOUT or -EINTR. */ if (res) ret = (res < 0) ? res : 0; futex_unqueue_pi(&q); spin_unlock(q.lock_ptr); if (ret == -EINTR) { /* * We've already been requeued, but cannot restart * by calling futex_lock_pi() directly. We could * restart this syscall, but it would detect that * the user space "val" changed and return * -EWOULDBLOCK. Save the overhead of the restart * and return -EWOULDBLOCK directly. */ ret = -EWOULDBLOCK; } break; default: BUG(); } if (q.drop_hb_ref) { CLASS(hb, hb)(&q.key); /* Additional reference from requeue_pi_wake_futex() */ futex_hash_put(hb); } out: if (to) { hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); } return ret; } |
| 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_QUOTA_DEFS_H__ #define __XFS_QUOTA_DEFS_H__ /* * Quota definitions shared between user and kernel source trees. */ /* * Even though users may not have quota limits occupying all 64-bits, * they may need 64-bit accounting. Hence, 64-bit quota-counters, * and quota-limits. This is a waste in the common case, but hey ... */ typedef uint64_t xfs_qcnt_t; typedef uint8_t xfs_dqtype_t; #define XFS_DQTYPE_STRINGS \ { XFS_DQTYPE_USER, "USER" }, \ { XFS_DQTYPE_PROJ, "PROJ" }, \ { XFS_DQTYPE_GROUP, "GROUP" }, \ { XFS_DQTYPE_BIGTIME, "BIGTIME" } /* * flags for q_flags field in the dquot. */ #define XFS_DQFLAG_DIRTY (1u << 0) /* dquot is dirty */ #define XFS_DQFLAG_FREEING (1u << 1) /* dquot is being torn down */ #define XFS_DQFLAG_STRINGS \ { XFS_DQFLAG_DIRTY, "DIRTY" }, \ { XFS_DQFLAG_FREEING, "FREEING" } /* * We have the possibility of all three quota types being active at once, and * hence free space modification requires modification of all three current * dquots in a single transaction. For this case we need to have a reservation * of at least 3 dquots. * * However, a chmod operation can change both UID and GID in a single * transaction, resulting in requiring {old, new} x {uid, gid} dquots to be * modified. Hence for this case we need to reserve space for at least 4 dquots. * * And in the worst case, there's a rename operation that can be modifying up to * 4 inodes with dquots attached to them. In reality, the only inodes that can * have their dquots modified are the source and destination directory inodes * due to directory name creation and removal. That can require space allocation * and/or freeing on both directory inodes, and hence all three dquots on each * inode can be modified. And if the directories are world writeable, all the * dquots can be unique and so 6 dquots can be modified.... * * And, of course, we also need to take into account the dquot log format item * used to describe each dquot. */ #define XFS_DQUOT_LOGRES \ ((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6) #define XFS_IS_QUOTA_ON(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ACCT) #define XFS_IS_UQUOTA_ON(mp) ((mp)->m_qflags & XFS_UQUOTA_ACCT) #define XFS_IS_PQUOTA_ON(mp) ((mp)->m_qflags & XFS_PQUOTA_ACCT) #define XFS_IS_GQUOTA_ON(mp) ((mp)->m_qflags & XFS_GQUOTA_ACCT) #define XFS_IS_UQUOTA_ENFORCED(mp) ((mp)->m_qflags & XFS_UQUOTA_ENFD) #define XFS_IS_GQUOTA_ENFORCED(mp) ((mp)->m_qflags & XFS_GQUOTA_ENFD) #define XFS_IS_PQUOTA_ENFORCED(mp) ((mp)->m_qflags & XFS_PQUOTA_ENFD) /* * Flags to tell various functions what to do. Not all of these are meaningful * to a single function. None of these XFS_QMOPT_* flags are meant to have * persistent values (ie. their values can and will change between versions) */ #define XFS_QMOPT_UQUOTA (1u << 0) /* user dquot requested */ #define XFS_QMOPT_GQUOTA (1u << 1) /* group dquot requested */ #define XFS_QMOPT_PQUOTA (1u << 2) /* project dquot requested */ #define XFS_QMOPT_FORCE_RES (1u << 3) /* ignore quota limits */ #define XFS_QMOPT_SBVERSION (1u << 4) /* change superblock version num */ /* * flags to xfs_trans_mod_dquot to indicate which field needs to be * modified. */ #define XFS_QMOPT_RES_REGBLKS (1u << 7) #define XFS_QMOPT_RES_RTBLKS (1u << 8) #define XFS_QMOPT_BCOUNT (1u << 9) #define XFS_QMOPT_ICOUNT (1u << 10) #define XFS_QMOPT_RTBCOUNT (1u << 11) #define XFS_QMOPT_DELBCOUNT (1u << 12) #define XFS_QMOPT_DELRTBCOUNT (1u << 13) #define XFS_QMOPT_RES_INOS (1u << 14) /* * flags for dqalloc. */ #define XFS_QMOPT_INHERIT (1u << 31) #define XFS_QMOPT_FLAGS \ { XFS_QMOPT_UQUOTA, "UQUOTA" }, \ { XFS_QMOPT_PQUOTA, "PQUOTA" }, \ { XFS_QMOPT_FORCE_RES, "FORCE_RES" }, \ { XFS_QMOPT_SBVERSION, "SBVERSION" }, \ { XFS_QMOPT_GQUOTA, "GQUOTA" }, \ { XFS_QMOPT_INHERIT, "INHERIT" }, \ { XFS_QMOPT_RES_REGBLKS, "RES_REGBLKS" }, \ { XFS_QMOPT_RES_RTBLKS, "RES_RTBLKS" }, \ { XFS_QMOPT_BCOUNT, "BCOUNT" }, \ { XFS_QMOPT_ICOUNT, "ICOUNT" }, \ { XFS_QMOPT_RTBCOUNT, "RTBCOUNT" }, \ { XFS_QMOPT_DELBCOUNT, "DELBCOUNT" }, \ { XFS_QMOPT_DELRTBCOUNT, "DELRTBCOUNT" }, \ { XFS_QMOPT_RES_INOS, "RES_INOS" } /* * flags to xfs_trans_mod_dquot. */ #define XFS_TRANS_DQ_RES_BLKS XFS_QMOPT_RES_REGBLKS #define XFS_TRANS_DQ_RES_RTBLKS XFS_QMOPT_RES_RTBLKS #define XFS_TRANS_DQ_RES_INOS XFS_QMOPT_RES_INOS #define XFS_TRANS_DQ_BCOUNT XFS_QMOPT_BCOUNT #define XFS_TRANS_DQ_DELBCOUNT XFS_QMOPT_DELBCOUNT #define XFS_TRANS_DQ_ICOUNT XFS_QMOPT_ICOUNT #define XFS_TRANS_DQ_RTBCOUNT XFS_QMOPT_RTBCOUNT #define XFS_TRANS_DQ_DELRTBCOUNT XFS_QMOPT_DELRTBCOUNT #define XFS_QMOPT_QUOTALL \ (XFS_QMOPT_UQUOTA | XFS_QMOPT_PQUOTA | XFS_QMOPT_GQUOTA) #define XFS_QMOPT_RESBLK_MASK (XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS) extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp, struct xfs_disk_dquot *ddq, xfs_dqid_t id); extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp, struct xfs_dqblk *dqb, xfs_dqid_t id); extern int xfs_calc_dquots_per_chunk(unsigned int nbblks); extern void xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb, xfs_dqid_t id, xfs_dqtype_t type); struct xfs_dquot; time64_t xfs_dquot_from_disk_ts(struct xfs_disk_dquot *ddq, __be32 dtimer); __be32 xfs_dquot_to_disk_ts(struct xfs_dquot *ddq, time64_t timer); static inline const char * xfs_dqinode_path(xfs_dqtype_t type) { switch (type) { case XFS_DQTYPE_USER: return "user"; case XFS_DQTYPE_GROUP: return "group"; case XFS_DQTYPE_PROJ: return "project"; } ASSERT(0); return NULL; } static inline enum xfs_metafile_type xfs_dqinode_metafile_type(xfs_dqtype_t type) { switch (type) { case XFS_DQTYPE_USER: return XFS_METAFILE_USRQUOTA; case XFS_DQTYPE_GROUP: return XFS_METAFILE_GRPQUOTA; case XFS_DQTYPE_PROJ: return XFS_METAFILE_PRJQUOTA; } ASSERT(0); return XFS_METAFILE_UNKNOWN; } unsigned int xfs_dqinode_sick_mask(xfs_dqtype_t type); int xfs_dqinode_load(struct xfs_trans *tp, struct xfs_inode *dp, xfs_dqtype_t type, struct xfs_inode **ipp); int xfs_dqinode_metadir_create(struct xfs_inode *dp, xfs_dqtype_t type, struct xfs_inode **ipp); int xfs_dqinode_metadir_link(struct xfs_inode *dp, xfs_dqtype_t type, struct xfs_inode *ip); int xfs_dqinode_mkdir_parent(struct xfs_mount *mp, struct xfs_inode **dpp); int xfs_dqinode_load_parent(struct xfs_trans *tp, struct xfs_inode **dpp); #endif /* __XFS_QUOTA_H__ */ |
| 10 3 10 10 3 1 3 3 1 1 2 3 3 3 7 1 2 1 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IguanaWorks USB IR Transceiver support * * Copyright (C) 2012 Sean Young <sean@mess.org> */ #include <linux/device.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/input.h> #include <linux/slab.h> #include <linux/completion.h> #include <media/rc-core.h> #define BUF_SIZE 152 struct iguanair { struct rc_dev *rc; struct device *dev; struct usb_device *udev; uint16_t version; uint8_t bufsize; uint8_t cycle_overhead; /* receiver support */ bool receiver_on; dma_addr_t dma_in, dma_out; uint8_t *buf_in; struct urb *urb_in, *urb_out; struct completion completion; /* transmit support */ bool tx_overflow; uint32_t carrier; struct send_packet *packet; char name[64]; char phys[64]; }; #define CMD_NOP 0x00 #define CMD_GET_VERSION 0x01 #define CMD_GET_BUFSIZE 0x11 #define CMD_GET_FEATURES 0x10 #define CMD_SEND 0x15 #define CMD_EXECUTE 0x1f #define CMD_RX_OVERFLOW 0x31 #define CMD_TX_OVERFLOW 0x32 #define CMD_RECEIVER_ON 0x12 #define CMD_RECEIVER_OFF 0x14 #define DIR_IN 0xdc #define DIR_OUT 0xcd #define MAX_IN_PACKET 8u #define MAX_OUT_PACKET (sizeof(struct send_packet) + BUF_SIZE) #define TIMEOUT 1000 #define RX_RESOLUTION 21 struct packet { uint16_t start; uint8_t direction; uint8_t cmd; }; struct send_packet { struct packet header; uint8_t length; uint8_t channels; uint8_t busy7; uint8_t busy4; uint8_t payload[]; }; static void process_ir_data(struct iguanair *ir, unsigned len) { if (len >= 4 && ir->buf_in[0] == 0 && ir->buf_in[1] == 0) { switch (ir->buf_in[3]) { case CMD_GET_VERSION: if (len == 6) { ir->version = (ir->buf_in[5] << 8) | ir->buf_in[4]; complete(&ir->completion); } break; case CMD_GET_BUFSIZE: if (len >= 5) { ir->bufsize = ir->buf_in[4]; complete(&ir->completion); } break; case CMD_GET_FEATURES: if (len > 5) { ir->cycle_overhead = ir->buf_in[5]; complete(&ir->completion); } break; case CMD_TX_OVERFLOW: ir->tx_overflow = true; fallthrough; case CMD_RECEIVER_OFF: case CMD_RECEIVER_ON: case CMD_SEND: complete(&ir->completion); break; case CMD_RX_OVERFLOW: dev_warn(ir->dev, "receive overflow\n"); ir_raw_event_overflow(ir->rc); break; default: dev_warn(ir->dev, "control code %02x received\n", ir->buf_in[3]); break; } } else if (len >= 7) { struct ir_raw_event rawir = {}; unsigned i; bool event = false; for (i = 0; i < 7; i++) { if (ir->buf_in[i] == 0x80) { rawir.pulse = false; rawir.duration = 21845; } else { rawir.pulse = (ir->buf_in[i] & 0x80) == 0; rawir.duration = ((ir->buf_in[i] & 0x7f) + 1) * RX_RESOLUTION; } if (ir_raw_event_store_with_filter(ir->rc, &rawir)) event = true; } if (event) ir_raw_event_handle(ir->rc); } } static void iguanair_rx(struct urb *urb) { struct iguanair *ir; int rc; if (!urb) return; ir = urb->context; if (!ir) return; switch (urb->status) { case 0: process_ir_data(ir, urb->actual_length); break; case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: return; case -EPIPE: default: dev_dbg(ir->dev, "Error: urb status = %d\n", urb->status); break; } rc = usb_submit_urb(urb, GFP_ATOMIC); if (rc && rc != -ENODEV) dev_warn(ir->dev, "failed to resubmit urb: %d\n", rc); } static void iguanair_irq_out(struct urb *urb) { struct iguanair *ir = urb->context; if (urb->status) dev_dbg(ir->dev, "Error: out urb status = %d\n", urb->status); /* if we sent an nop packet, do not expect a response */ if (urb->status == 0 && ir->packet->header.cmd == CMD_NOP) complete(&ir->completion); } static int iguanair_send(struct iguanair *ir, unsigned size) { int rc; reinit_completion(&ir->completion); ir->urb_out->transfer_buffer_length = size; rc = usb_submit_urb(ir->urb_out, GFP_KERNEL); if (rc) return rc; if (wait_for_completion_timeout(&ir->completion, TIMEOUT) == 0) { usb_kill_urb(ir->urb_out); return -ETIMEDOUT; } return rc; } static int iguanair_get_features(struct iguanair *ir) { int rc; /* * On cold boot, the iguanair initializes on the first packet * received but does not process that packet. Send an empty * packet. */ ir->packet->header.start = 0; ir->packet->header.direction = DIR_OUT; ir->packet->header.cmd = CMD_NOP; iguanair_send(ir, sizeof(ir->packet->header)); ir->packet->header.cmd = CMD_GET_VERSION; rc = iguanair_send(ir, sizeof(ir->packet->header)); if (rc) { dev_info(ir->dev, "failed to get version\n"); goto out; } if (ir->version < 0x205) { dev_err(ir->dev, "firmware 0x%04x is too old\n", ir->version); rc = -ENODEV; goto out; } ir->bufsize = 150; ir->cycle_overhead = 65; ir->packet->header.cmd = CMD_GET_BUFSIZE; rc = iguanair_send(ir, sizeof(ir->packet->header)); if (rc) { dev_info(ir->dev, "failed to get buffer size\n"); goto out; } if (ir->bufsize > BUF_SIZE) { dev_info(ir->dev, "buffer size %u larger than expected\n", ir->bufsize); ir->bufsize = BUF_SIZE; } ir->packet->header.cmd = CMD_GET_FEATURES; rc = iguanair_send(ir, sizeof(ir->packet->header)); if (rc) dev_info(ir->dev, "failed to get features\n"); out: return rc; } static int iguanair_receiver(struct iguanair *ir, bool enable) { ir->packet->header.start = 0; ir->packet->header.direction = DIR_OUT; ir->packet->header.cmd = enable ? CMD_RECEIVER_ON : CMD_RECEIVER_OFF; return iguanair_send(ir, sizeof(ir->packet->header)); } /* * The iguanair creates the carrier by busy spinning after each half period. * This is counted in CPU cycles, with the CPU running at 24MHz. It is * broken down into 7-cycles and 4-cyles delays, with a preference for * 4-cycle delays, minus the overhead of the loop itself (cycle_overhead). */ static int iguanair_set_tx_carrier(struct rc_dev *dev, uint32_t carrier) { struct iguanair *ir = dev->priv; if (carrier < 25000 || carrier > 150000) return -EINVAL; if (carrier != ir->carrier) { uint32_t cycles, fours, sevens; ir->carrier = carrier; cycles = DIV_ROUND_CLOSEST(24000000, carrier * 2) - ir->cycle_overhead; /* * Calculate minimum number of 7 cycles needed so * we are left with a multiple of 4; so we want to have * (sevens * 7) & 3 == cycles & 3 */ sevens = (4 - cycles) & 3; fours = (cycles - sevens * 7) / 4; /* * The firmware interprets these values as a relative offset * for a branch. Immediately following the branches, there * 4 instructions of 7 cycles (2 bytes each) and 110 * instructions of 4 cycles (1 byte each). A relative branch * of 0 will execute all of them, branch further for less * cycle burning. */ ir->packet->busy7 = (4 - sevens) * 2; ir->packet->busy4 = 110 - fours; } return 0; } static int iguanair_set_tx_mask(struct rc_dev *dev, uint32_t mask) { struct iguanair *ir = dev->priv; if (mask > 15) return 4; ir->packet->channels = mask << 4; return 0; } static int iguanair_tx(struct rc_dev *dev, unsigned *txbuf, unsigned count) { struct iguanair *ir = dev->priv; unsigned int i, size, p, periods; int rc; /* convert from us to carrier periods */ for (i = size = 0; i < count; i++) { periods = DIV_ROUND_CLOSEST(txbuf[i] * ir->carrier, 1000000); while (periods) { p = min(periods, 127u); if (size >= ir->bufsize) { rc = -EINVAL; goto out; } ir->packet->payload[size++] = p | ((i & 1) ? 0x80 : 0); periods -= p; } } ir->packet->header.start = 0; ir->packet->header.direction = DIR_OUT; ir->packet->header.cmd = CMD_SEND; ir->packet->length = size; ir->tx_overflow = false; rc = iguanair_send(ir, sizeof(*ir->packet) + size); if (rc == 0 && ir->tx_overflow) rc = -EOVERFLOW; out: return rc ? rc : count; } static int iguanair_open(struct rc_dev *rdev) { struct iguanair *ir = rdev->priv; int rc; rc = iguanair_receiver(ir, true); if (rc == 0) ir->receiver_on = true; return rc; } static void iguanair_close(struct rc_dev *rdev) { struct iguanair *ir = rdev->priv; int rc; rc = iguanair_receiver(ir, false); ir->receiver_on = false; if (rc && rc != -ENODEV) dev_warn(ir->dev, "failed to disable receiver: %d\n", rc); } static int iguanair_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); struct iguanair *ir; struct rc_dev *rc; int ret, pipein, pipeout; struct usb_host_interface *idesc; idesc = intf->cur_altsetting; if (idesc->desc.bNumEndpoints < 2) return -ENODEV; ir = kzalloc(sizeof(*ir), GFP_KERNEL); rc = rc_allocate_device(RC_DRIVER_IR_RAW); if (!ir || !rc) { ret = -ENOMEM; goto out; } ir->buf_in = usb_alloc_coherent(udev, MAX_IN_PACKET, GFP_KERNEL, &ir->dma_in); ir->packet = usb_alloc_coherent(udev, MAX_OUT_PACKET, GFP_KERNEL, &ir->dma_out); ir->urb_in = usb_alloc_urb(0, GFP_KERNEL); ir->urb_out = usb_alloc_urb(0, GFP_KERNEL); if (!ir->buf_in || !ir->packet || !ir->urb_in || !ir->urb_out || !usb_endpoint_is_int_in(&idesc->endpoint[0].desc) || !usb_endpoint_is_int_out(&idesc->endpoint[1].desc)) { ret = -ENOMEM; goto out; } ir->rc = rc; ir->dev = &intf->dev; ir->udev = udev; init_completion(&ir->completion); pipeout = usb_sndintpipe(udev, idesc->endpoint[1].desc.bEndpointAddress); usb_fill_int_urb(ir->urb_out, udev, pipeout, ir->packet, MAX_OUT_PACKET, iguanair_irq_out, ir, 1); ir->urb_out->transfer_dma = ir->dma_out; ir->urb_out->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; pipein = usb_rcvintpipe(udev, idesc->endpoint[0].desc.bEndpointAddress); usb_fill_int_urb(ir->urb_in, udev, pipein, ir->buf_in, MAX_IN_PACKET, iguanair_rx, ir, 1); ir->urb_in->transfer_dma = ir->dma_in; ir->urb_in->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; ret = usb_submit_urb(ir->urb_in, GFP_KERNEL); if (ret) { dev_warn(&intf->dev, "failed to submit urb: %d\n", ret); goto out; } ret = iguanair_get_features(ir); if (ret) goto out2; snprintf(ir->name, sizeof(ir->name), "IguanaWorks USB IR Transceiver version 0x%04x", ir->version); usb_make_path(ir->udev, ir->phys, sizeof(ir->phys)); rc->device_name = ir->name; rc->input_phys = ir->phys; usb_to_input_id(ir->udev, &rc->input_id); rc->dev.parent = &intf->dev; rc->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER; rc->priv = ir; rc->open = iguanair_open; rc->close = iguanair_close; rc->s_tx_mask = iguanair_set_tx_mask; rc->s_tx_carrier = iguanair_set_tx_carrier; rc->tx_ir = iguanair_tx; rc->driver_name = KBUILD_MODNAME; rc->map_name = RC_MAP_RC6_MCE; rc->min_timeout = 1; rc->timeout = IR_DEFAULT_TIMEOUT; rc->max_timeout = 10 * IR_DEFAULT_TIMEOUT; rc->rx_resolution = RX_RESOLUTION; iguanair_set_tx_carrier(rc, 38000); iguanair_set_tx_mask(rc, 0); ret = rc_register_device(rc); if (ret < 0) { dev_err(&intf->dev, "failed to register rc device %d", ret); goto out2; } usb_set_intfdata(intf, ir); return 0; out2: usb_kill_urb(ir->urb_in); usb_kill_urb(ir->urb_out); out: if (ir) { usb_free_urb(ir->urb_in); usb_free_urb(ir->urb_out); usb_free_coherent(udev, MAX_IN_PACKET, ir->buf_in, ir->dma_in); usb_free_coherent(udev, MAX_OUT_PACKET, ir->packet, ir->dma_out); } rc_free_device(rc); kfree(ir); return ret; } static void iguanair_disconnect(struct usb_interface *intf) { struct iguanair *ir = usb_get_intfdata(intf); rc_unregister_device(ir->rc); usb_set_intfdata(intf, NULL); usb_kill_urb(ir->urb_in); usb_kill_urb(ir->urb_out); usb_free_urb(ir->urb_in); usb_free_urb(ir->urb_out); usb_free_coherent(ir->udev, MAX_IN_PACKET, ir->buf_in, ir->dma_in); usb_free_coherent(ir->udev, MAX_OUT_PACKET, ir->packet, ir->dma_out); kfree(ir); } static int iguanair_suspend(struct usb_interface *intf, pm_message_t message) { struct iguanair *ir = usb_get_intfdata(intf); int rc = 0; if (ir->receiver_on) { rc = iguanair_receiver(ir, false); if (rc) dev_warn(ir->dev, "failed to disable receiver for suspend\n"); } usb_kill_urb(ir->urb_in); usb_kill_urb(ir->urb_out); return rc; } static int iguanair_resume(struct usb_interface *intf) { struct iguanair *ir = usb_get_intfdata(intf); int rc; rc = usb_submit_urb(ir->urb_in, GFP_KERNEL); if (rc) dev_warn(&intf->dev, "failed to submit urb: %d\n", rc); if (ir->receiver_on) { rc = iguanair_receiver(ir, true); if (rc) dev_warn(ir->dev, "failed to enable receiver after resume\n"); } return rc; } static const struct usb_device_id iguanair_table[] = { { USB_DEVICE(0x1781, 0x0938) }, { } }; static struct usb_driver iguanair_driver = { .name = KBUILD_MODNAME, .probe = iguanair_probe, .disconnect = iguanair_disconnect, .suspend = iguanair_suspend, .resume = iguanair_resume, .reset_resume = iguanair_resume, .id_table = iguanair_table, .soft_unbind = 1 /* we want to disable receiver on unbind */ }; module_usb_driver(iguanair_driver); MODULE_DESCRIPTION("IguanaWorks USB IR Transceiver"); MODULE_AUTHOR("Sean Young <sean@mess.org>"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(usb, iguanair_table); |
| 2 2 2 8 1 1 2 1 1 2 1 1 1 57 57 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_simple.c Simple example of an action * * Authors: Jamal Hadi Salim (2005-8) */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> static struct tc_action_ops act_simp_ops; #define SIMP_MAX_DATA 32 TC_INDIRECT_SCOPE int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_defact *d = to_defact(a); spin_lock(&d->tcf_lock); tcf_lastuse_update(&d->tcf_tm); bstats_update(&d->tcf_bstats, skb); /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) */ pr_info("simple: %s_%llu\n", (char *)d->tcfd_defdata, u64_stats_read(&d->tcf_bstats.packets)); spin_unlock(&d->tcf_lock); return d->tcf_action; } static void tcf_simp_release(struct tc_action *a) { struct tcf_defact *d = to_defact(a); kfree(d->tcfd_defdata); } static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata) { d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL); if (unlikely(!d->tcfd_defdata)) return -ENOMEM; nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); return 0; } static int reset_policy(struct tc_action *a, const struct nlattr *defdata, struct tc_defact *p, struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcf_chain *goto_ch = NULL; struct tcf_defact *d; int err; err = tcf_action_check_ctrlact(p->action, tp, &goto_ch, extack); if (err < 0) return err; d = to_defact(a); spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch); memset(d->tcfd_defdata, 0, SIMP_MAX_DATA); nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); spin_unlock_bh(&d->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); return 0; } static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { [TCA_DEF_PARMS] = { .len = sizeof(struct tc_defact) }, [TCA_DEF_DATA] = { .type = NLA_STRING, .len = SIMP_MAX_DATA }, }; static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_simp_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_DEF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_defact *parm; struct tcf_defact *d; bool exists = false; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_DEF_MAX, nla, simple_policy, NULL); if (err < 0) return err; if (tb[TCA_DEF_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (tb[TCA_DEF_DATA] == NULL) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } d = to_defact(*a); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; err = alloc_defdata(d, tb[TCA_DEF_DATA]); if (err < 0) goto put_chain; tcf_action_set_ctrlact(*a, parm->action, goto_ch); ret = ACT_P_CREATED; } else { if (!(flags & TCA_ACT_FLAGS_REPLACE)) { err = -EEXIST; goto release_idr; } err = reset_policy(*a, tb[TCA_DEF_DATA], parm, tp, extack); if (err) goto release_idr; } return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_defact *d = to_defact(a); struct tc_defact opt = { .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) || nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata)) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD)) goto nla_put_failure; spin_unlock_bh(&d->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } static struct tc_action_ops act_simp_ops = { .kind = "simple", .id = TCA_ID_SIMP, .owner = THIS_MODULE, .act = tcf_simp_act, .dump = tcf_simp_dump, .cleanup = tcf_simp_release, .init = tcf_simp_init, .size = sizeof(struct tcf_defact), }; MODULE_ALIAS_NET_ACT("simple"); static __net_init int simp_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_simp_ops.net_id); return tc_action_net_init(net, tn, &act_simp_ops); } static void __net_exit simp_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_simp_ops.net_id); } static struct pernet_operations simp_net_ops = { .init = simp_init_net, .exit_batch = simp_exit_net, .id = &act_simp_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); MODULE_DESCRIPTION("Simple example action"); MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { int ret = tcf_register_action(&act_simp_ops, &simp_net_ops); if (!ret) pr_info("Simple TC action Loaded\n"); return ret; } static void __exit simp_cleanup_module(void) { tcf_unregister_action(&act_simp_ops, &simp_net_ops); } module_init(simp_init_module); module_exit(simp_cleanup_module); |
| 46 3 2 2 1 1 16 11 3 14 2 3 3 1 1 1 5 5 3 7 5 236 227 11 11 8 8 11 267 3 268 1 1 189 43 204 1 188 27 1 37 35 4 4 26 26 7 6 6 31 2 5 2 14 2 6 3 3 2 17 3 1 1 15 11 16 2 9 2 4 2 15 34 32 2 5 1 24 2 2 20 2 12 8 4 73 16 7 28 11 12 2 7 35 5 7 2 2 1 1 12 4 6 3 7 7 35 43 46 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool_netlink.h> #include <linux/bitmap.h> #include "netlink.h" #include "bitset.h" /* Some bitmaps are internally represented as an array of unsigned long, some * as an array of u32 (some even as single u32 for now). To avoid the need of * wrappers on caller side, we provide two set of functions: those with "32" * suffix in their names expect u32 based bitmaps, those without it expect * unsigned long bitmaps. */ static u32 ethnl_lower_bits(unsigned int n) { return ~(u32)0 >> (32 - n % 32); } static u32 ethnl_upper_bits(unsigned int n) { return ~(u32)0 << (n % 32); } /** * ethnl_bitmap32_clear() - Clear u32 based bitmap * @dst: bitmap to clear * @start: beginning of the interval * @end: end of the interval * @mod: set if bitmap was modified * * Clear @nbits bits of a bitmap with indices @start <= i < @end */ static void ethnl_bitmap32_clear(u32 *dst, unsigned int start, unsigned int end, bool *mod) { unsigned int start_word = start / 32; unsigned int end_word = end / 32; unsigned int i; u32 mask; if (end <= start) return; if (start % 32) { mask = ethnl_upper_bits(start); if (end_word == start_word) { mask &= ethnl_lower_bits(end); if (dst[start_word] & mask) { dst[start_word] &= ~mask; *mod = true; } return; } if (dst[start_word] & mask) { dst[start_word] &= ~mask; *mod = true; } start_word++; } for (i = start_word; i < end_word; i++) { if (dst[i]) { dst[i] = 0; *mod = true; } } if (end % 32) { mask = ethnl_lower_bits(end); if (dst[end_word] & mask) { dst[end_word] &= ~mask; *mod = true; } } } /** * ethnl_bitmap32_not_zero() - Check if any bit is set in an interval * @map: bitmap to test * @start: beginning of the interval * @end: end of the interval * * Return: true if there is non-zero bit with index @start <= i < @end, * false if the whole interval is zero */ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, unsigned int end) { unsigned int start_word = start / 32; unsigned int end_word = end / 32; u32 mask; if (end <= start) return true; if (start % 32) { mask = ethnl_upper_bits(start); if (end_word == start_word) { mask &= ethnl_lower_bits(end); return map[start_word] & mask; } if (map[start_word] & mask) return true; start_word++; } if (!memchr_inv(map + start_word, '\0', (end_word - start_word) * sizeof(u32))) return true; if (end % 32 == 0) return true; return map[end_word] & ethnl_lower_bits(end); } /** * ethnl_bitmap32_update() - Modify u32 based bitmap according to value/mask * pair * @dst: bitmap to update * @nbits: bit size of the bitmap * @value: values to set * @mask: mask of bits to set * @mod: set to true if bitmap is modified, preserve if not * * Set bits in @dst bitmap which are set in @mask to values from @value, leave * the rest untouched. If destination bitmap was modified, set @mod to true, * leave as it is if not. */ static void ethnl_bitmap32_update(u32 *dst, unsigned int nbits, const u32 *value, const u32 *mask, bool *mod) { while (nbits > 0) { u32 real_mask = mask ? *mask : ~(u32)0; u32 new_value; if (nbits < 32) real_mask &= ethnl_lower_bits(nbits); new_value = (*dst & ~real_mask) | (*value & real_mask); if (new_value != *dst) { *dst = new_value; *mod = true; } if (nbits <= 32) break; dst++; nbits -= 32; value++; if (mask) mask++; } } static bool ethnl_bitmap32_test_bit(const u32 *map, unsigned int index) { return map[index / 32] & (1U << (index % 32)); } /** * ethnl_bitset32_size() - Calculate size of bitset nested attribute * @val: value bitmap (u32 based) * @mask: mask bitmap (u32 based, optional) * @nbits: bit length of the bitset * @names: array of bit names (optional) * @compact: assume compact format for output * * Estimate length of netlink attribute composed by a later call to * ethnl_put_bitset32() call with the same arguments. * * Return: negative error code or attribute length estimate */ int ethnl_bitset32_size(const u32 *val, const u32 *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { unsigned int len = 0; /* list flag */ if (!mask) len += nla_total_size(sizeof(u32)); /* size */ len += nla_total_size(sizeof(u32)); if (compact) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); /* value, mask */ len += (mask ? 2 : 1) * nla_total_size(nwords * sizeof(u32)); } else { unsigned int bits_len = 0; unsigned int bit_len, i; for (i = 0; i < nbits; i++) { const char *name = names ? names[i] : NULL; if (!ethnl_bitmap32_test_bit(mask ?: val, i)) continue; /* index */ bit_len = nla_total_size(sizeof(u32)); /* name */ if (name) bit_len += ethnl_strz_size(name); /* value */ if (mask && ethnl_bitmap32_test_bit(val, i)) bit_len += nla_total_size(0); /* bit nest */ bits_len += nla_total_size(bit_len); } /* bits nest */ len += nla_total_size(bits_len); } /* outermost nest */ return nla_total_size(len); } /** * ethnl_put_bitset32() - Put a bitset nest into a message * @skb: skb with the message * @attrtype: attribute type for the bitset nest * @val: value bitmap (u32 based) * @mask: mask bitmap (u32 based, optional) * @nbits: bit length of the bitset * @names: array of bit names (optional) * @compact: use compact format for the output * * Compose a nested attribute representing a bitset. If @mask is null, simple * bitmap (bit list) is created, if @mask is provided, represent a value/mask * pair. Bit names are only used in verbose mode and when provided by calller. * * Return: 0 on success, negative error value on error */ int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, const u32 *val, const u32 *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { struct nlattr *nest; struct nlattr *attr; nest = nla_nest_start(skb, attrtype); if (!nest) return -EMSGSIZE; if (!mask && nla_put_flag(skb, ETHTOOL_A_BITSET_NOMASK)) goto nla_put_failure; if (nla_put_u32(skb, ETHTOOL_A_BITSET_SIZE, nbits)) goto nla_put_failure; if (compact) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); unsigned int nbytes = nwords * sizeof(u32); u32 *dst; attr = nla_reserve(skb, ETHTOOL_A_BITSET_VALUE, nbytes); if (!attr) goto nla_put_failure; dst = nla_data(attr); memcpy(dst, val, nbytes); if (nbits % 32) dst[nwords - 1] &= ethnl_lower_bits(nbits); if (mask) { attr = nla_reserve(skb, ETHTOOL_A_BITSET_MASK, nbytes); if (!attr) goto nla_put_failure; dst = nla_data(attr); memcpy(dst, mask, nbytes); if (nbits % 32) dst[nwords - 1] &= ethnl_lower_bits(nbits); } } else { struct nlattr *bits; unsigned int i; bits = nla_nest_start(skb, ETHTOOL_A_BITSET_BITS); if (!bits) goto nla_put_failure; for (i = 0; i < nbits; i++) { const char *name = names ? names[i] : NULL; if (!ethnl_bitmap32_test_bit(mask ?: val, i)) continue; attr = nla_nest_start(skb, ETHTOOL_A_BITSET_BITS_BIT); if (!attr) goto nla_put_failure; if (nla_put_u32(skb, ETHTOOL_A_BITSET_BIT_INDEX, i)) goto nla_put_failure; if (name && ethnl_put_strz(skb, ETHTOOL_A_BITSET_BIT_NAME, name)) goto nla_put_failure; if (mask && ethnl_bitmap32_test_bit(val, i) && nla_put_flag(skb, ETHTOOL_A_BITSET_BIT_VALUE)) goto nla_put_failure; nla_nest_end(skb, attr); } nla_nest_end(skb, bits); } nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static const struct nla_policy bitset_policy[] = { [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, ETHNL_MAX_BITSET_SIZE), [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, }; static const struct nla_policy bit_policy[] = { [ETHTOOL_A_BITSET_BIT_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_BITSET_BIT_NAME] = { .type = NLA_NUL_STRING }, [ETHTOOL_A_BITSET_BIT_VALUE] = { .type = NLA_FLAG }, }; /** * ethnl_bitset_is_compact() - check if bitset attribute represents a compact * bitset * @bitset: nested attribute representing a bitset * @compact: pointer for return value * * Return: 0 on success, negative error code on failure */ int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact) { struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; int ret; ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, bitset, bitset_policy, NULL); if (ret < 0) return ret; if (tb[ETHTOOL_A_BITSET_BITS]) { if (tb[ETHTOOL_A_BITSET_VALUE] || tb[ETHTOOL_A_BITSET_MASK]) return -EINVAL; *compact = false; return 0; } if (!tb[ETHTOOL_A_BITSET_SIZE] || !tb[ETHTOOL_A_BITSET_VALUE]) return -EINVAL; *compact = true; return 0; } /** * ethnl_name_to_idx() - look up string index for a name * @names: array of ETH_GSTRING_LEN sized strings * @n_names: number of strings in the array * @name: name to look up * * Return: index of the string if found, -ENOENT if not found */ static int ethnl_name_to_idx(ethnl_string_array_t names, unsigned int n_names, const char *name) { unsigned int i; if (!names) return -ENOENT; for (i = 0; i < n_names; i++) { /* names[i] may not be null terminated */ if (!strncmp(names[i], name, ETH_GSTRING_LEN) && strlen(name) <= ETH_GSTRING_LEN) return i; } return -ENOENT; } static int ethnl_parse_bit(unsigned int *index, bool *val, unsigned int nbits, const struct nlattr *bit_attr, bool no_mask, ethnl_string_array_t names, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(bit_policy)]; int ret, idx; ret = nla_parse_nested(tb, ARRAY_SIZE(bit_policy) - 1, bit_attr, bit_policy, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_BITSET_BIT_INDEX]) { const char *name; idx = nla_get_u32(tb[ETHTOOL_A_BITSET_BIT_INDEX]); if (idx >= nbits) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_BIT_INDEX], "bit index too high"); return -EOPNOTSUPP; } name = names ? names[idx] : NULL; if (tb[ETHTOOL_A_BITSET_BIT_NAME] && name && strncmp(nla_data(tb[ETHTOOL_A_BITSET_BIT_NAME]), name, nla_len(tb[ETHTOOL_A_BITSET_BIT_NAME]))) { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "bit index and name mismatch"); return -EINVAL; } } else if (tb[ETHTOOL_A_BITSET_BIT_NAME]) { idx = ethnl_name_to_idx(names, nbits, nla_data(tb[ETHTOOL_A_BITSET_BIT_NAME])); if (idx < 0) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_BIT_NAME], "bit name not found"); return -EOPNOTSUPP; } } else { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "neither bit index nor name specified"); return -EINVAL; } *index = idx; *val = no_mask || tb[ETHTOOL_A_BITSET_BIT_VALUE]; return 0; } /** * ethnl_bitmap32_equal() - Compare two bitmaps * @map1: first bitmap * @map2: second bitmap * @nbits: bit size to compare * * Return: true if first @nbits are equal, false if not */ static bool ethnl_bitmap32_equal(const u32 *map1, const u32 *map2, unsigned int nbits) { if (memcmp(map1, map2, nbits / 32 * sizeof(u32))) return false; if (nbits % 32 == 0) return true; return !((map1[nbits / 32] ^ map2[nbits / 32]) & ethnl_lower_bits(nbits % 32)); } static int ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, const struct nlattr *attr, struct nlattr **tb, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { u32 *saved_bitmap = NULL; struct nlattr *bit_attr; bool no_mask; int rem; int ret; if (tb[ETHTOOL_A_BITSET_VALUE]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], "value only allowed in compact bitset"); return -EINVAL; } if (tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "mask only allowed in compact bitset"); return -EINVAL; } no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; if (no_mask) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); unsigned int nbytes = nwords * sizeof(u32); bool dummy; /* The bitmap size is only the size of the map part without * its mask part. */ saved_bitmap = kcalloc(nwords, sizeof(u32), GFP_KERNEL); if (!saved_bitmap) return -ENOMEM; memcpy(saved_bitmap, bitmap, nbytes); ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy); } nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; unsigned int idx; if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS"); kfree(saved_bitmap); return -EINVAL; } ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask, names, extack); if (ret < 0) { kfree(saved_bitmap); return ret; } old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32)); if (new_val != old_val) { if (new_val) bitmap[idx / 32] |= ((u32)1 << (idx % 32)); else bitmap[idx / 32] &= ~((u32)1 << (idx % 32)); if (!no_mask) *mod = true; } } if (no_mask && !ethnl_bitmap32_equal(saved_bitmap, bitmap, nbits)) *mod = true; kfree(saved_bitmap); return 0; } static int ethnl_compact_sanity_checks(unsigned int nbits, const struct nlattr *nest, struct nlattr **tb, struct netlink_ext_ack *extack) { bool no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; unsigned int attr_nbits, attr_nwords; const struct nlattr *test_attr; if (no_mask && tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "mask not allowed in list bitset"); return -EINVAL; } if (!tb[ETHTOOL_A_BITSET_SIZE]) { NL_SET_ERR_MSG_ATTR(extack, nest, "missing size in compact bitset"); return -EINVAL; } if (!tb[ETHTOOL_A_BITSET_VALUE]) { NL_SET_ERR_MSG_ATTR(extack, nest, "missing value in compact bitset"); return -EINVAL; } if (!no_mask && !tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, nest, "missing mask in compact nonlist bitset"); return -EINVAL; } attr_nbits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); attr_nwords = DIV_ROUND_UP(attr_nbits, 32); if (nla_len(tb[ETHTOOL_A_BITSET_VALUE]) != attr_nwords * sizeof(u32)) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], "bitset value length does not match size"); return -EINVAL; } if (tb[ETHTOOL_A_BITSET_MASK] && nla_len(tb[ETHTOOL_A_BITSET_MASK]) != attr_nwords * sizeof(u32)) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "bitset mask length does not match size"); return -EINVAL; } if (attr_nbits <= nbits) return 0; test_attr = no_mask ? tb[ETHTOOL_A_BITSET_VALUE] : tb[ETHTOOL_A_BITSET_MASK]; if (ethnl_bitmap32_not_zero(nla_data(test_attr), nbits, attr_nbits)) { NL_SET_ERR_MSG_ATTR(extack, test_attr, "cannot modify bits past kernel bitset size"); return -EINVAL; } return 0; } /** * ethnl_update_bitset32() - Apply a bitset nest to a u32 based bitmap * @bitmap: bitmap to update * @nbits: size of the updated bitmap in bits * @attr: nest attribute to parse and apply * @names: array of bit names; may be null for compact format * @extack: extack for error reporting * @mod: set this to true if bitmap is modified, leave as it is if not * * Apply bitset netsted attribute to a bitmap. If the attribute represents * a bit list, @bitmap is set to its contents; otherwise, bits in mask are * set to values from value. Bitmaps in the attribute may be longer than * @nbits but the message must not request modifying any bits past @nbits. * * Return: negative error code on failure, 0 on success */ int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; unsigned int change_bits; bool no_mask; int ret; if (!attr) return 0; ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr, bitset_policy, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_BITSET_BITS]) return ethnl_update_bitset32_verbose(bitmap, nbits, attr, tb, names, extack, mod); ret = ethnl_compact_sanity_checks(nbits, attr, tb, extack); if (ret < 0) return ret; no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; change_bits = min_t(unsigned int, nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]), nbits); ethnl_bitmap32_update(bitmap, change_bits, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), no_mask ? NULL : nla_data(tb[ETHTOOL_A_BITSET_MASK]), mod); if (no_mask && change_bits < nbits) ethnl_bitmap32_clear(bitmap, change_bits, nbits, mod); return 0; } /** * ethnl_parse_bitset() - Compute effective value and mask from bitset nest * @val: unsigned long based bitmap to put value into * @mask: unsigned long based bitmap to put mask into * @nbits: size of @val and @mask bitmaps * @attr: nest attribute to parse and apply * @names: array of bit names; may be null for compact format * @extack: extack for error reporting * * Provide @nbits size long bitmaps for value and mask so that * x = (val & mask) | (x & ~mask) would modify any @nbits sized bitmap x * the same way ethnl_update_bitset() with the same bitset attribute would. * * Return: negative error code on failure, 0 on success */ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; const struct nlattr *bit_attr; bool no_mask; int rem; int ret; if (!attr) return 0; ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr, bitset_policy, extack); if (ret < 0) return ret; no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; if (!tb[ETHTOOL_A_BITSET_BITS]) { unsigned int change_bits; ret = ethnl_compact_sanity_checks(nbits, attr, tb, extack); if (ret < 0) return ret; change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); if (change_bits > nbits) change_bits = nbits; bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), change_bits); if (change_bits < nbits) bitmap_clear(val, change_bits, nbits - change_bits); if (no_mask) { bitmap_fill(mask, nbits); } else { bitmap_from_arr32(mask, nla_data(tb[ETHTOOL_A_BITSET_MASK]), change_bits); if (change_bits < nbits) bitmap_clear(mask, change_bits, nbits - change_bits); } return 0; } if (tb[ETHTOOL_A_BITSET_VALUE]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], "value only allowed in compact bitset"); return -EINVAL; } if (tb[ETHTOOL_A_BITSET_MASK]) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], "mask only allowed in compact bitset"); return -EINVAL; } bitmap_zero(val, nbits); if (no_mask) bitmap_fill(mask, nbits); else bitmap_zero(mask, nbits); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { unsigned int idx; bool bit_val; ret = ethnl_parse_bit(&idx, &bit_val, nbits, bit_attr, no_mask, names, extack); if (ret < 0) return ret; if (bit_val) __set_bit(idx, val); if (!no_mask) __set_bit(idx, mask); } return 0; } #if BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) /* 64-bit big endian architectures are the only case when u32 based bitmaps * and unsigned long based bitmaps have different memory layout so that we * cannot simply cast the latter to the former and need actual wrappers * converting the latter to the former. * * To reduce the number of slab allocations, the wrappers use fixed size local * variables for bitmaps up to ETHNL_SMALL_BITMAP_BITS bits which is the * majority of bitmaps used by ethtool. */ #define ETHNL_SMALL_BITMAP_BITS 128 #define ETHNL_SMALL_BITMAP_WORDS DIV_ROUND_UP(ETHNL_SMALL_BITMAP_BITS, 32) int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { u32 small_mask32[ETHNL_SMALL_BITMAP_WORDS]; u32 small_val32[ETHNL_SMALL_BITMAP_WORDS]; u32 *mask32; u32 *val32; int ret; if (nbits > ETHNL_SMALL_BITMAP_BITS) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); val32 = kmalloc_array(2 * nwords, sizeof(u32), GFP_KERNEL); if (!val32) return -ENOMEM; mask32 = val32 + nwords; } else { val32 = small_val32; mask32 = small_mask32; } bitmap_to_arr32(val32, val, nbits); if (mask) bitmap_to_arr32(mask32, mask, nbits); else mask32 = NULL; ret = ethnl_bitset32_size(val32, mask32, nbits, names, compact); if (nbits > ETHNL_SMALL_BITMAP_BITS) kfree(val32); return ret; } int ethnl_put_bitset(struct sk_buff *skb, int attrtype, const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { u32 small_mask32[ETHNL_SMALL_BITMAP_WORDS]; u32 small_val32[ETHNL_SMALL_BITMAP_WORDS]; u32 *mask32; u32 *val32; int ret; if (nbits > ETHNL_SMALL_BITMAP_BITS) { unsigned int nwords = DIV_ROUND_UP(nbits, 32); val32 = kmalloc_array(2 * nwords, sizeof(u32), GFP_KERNEL); if (!val32) return -ENOMEM; mask32 = val32 + nwords; } else { val32 = small_val32; mask32 = small_mask32; } bitmap_to_arr32(val32, val, nbits); if (mask) bitmap_to_arr32(mask32, mask, nbits); else mask32 = NULL; ret = ethnl_put_bitset32(skb, attrtype, val32, mask32, nbits, names, compact); if (nbits > ETHNL_SMALL_BITMAP_BITS) kfree(val32); return ret; } int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { u32 small_bitmap32[ETHNL_SMALL_BITMAP_WORDS]; u32 *bitmap32 = small_bitmap32; bool u32_mod = false; int ret; if (nbits > ETHNL_SMALL_BITMAP_BITS) { unsigned int dst_words = DIV_ROUND_UP(nbits, 32); bitmap32 = kmalloc_array(dst_words, sizeof(u32), GFP_KERNEL); if (!bitmap32) return -ENOMEM; } bitmap_to_arr32(bitmap32, bitmap, nbits); ret = ethnl_update_bitset32(bitmap32, nbits, attr, names, extack, &u32_mod); if (u32_mod) { bitmap_from_arr32(bitmap, bitmap32, nbits); *mod = true; } if (nbits > ETHNL_SMALL_BITMAP_BITS) kfree(bitmap32); return ret; } #else /* On little endian 64-bit and all 32-bit architectures, an unsigned long * based bitmap can be interpreted as u32 based one using a simple cast. */ int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { return ethnl_bitset32_size((const u32 *)val, (const u32 *)mask, nbits, names, compact); } int ethnl_put_bitset(struct sk_buff *skb, int attrtype, const unsigned long *val, const unsigned long *mask, unsigned int nbits, ethnl_string_array_t names, bool compact) { return ethnl_put_bitset32(skb, attrtype, (const u32 *)val, (const u32 *)mask, nbits, names, compact); } int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { return ethnl_update_bitset32((u32 *)bitmap, nbits, attr, names, extack, mod); } #endif /* BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) */ |
| 55 55 57 57 56 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/inode.c * * Copyright (C) 1992 Rick Sladkey * * nfs inode and superblock handling functions * * Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some * experimental NFS changes. Modularisation taken straight from SYS5 fs. * * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. * J.S.Peatfield@damtp.cam.ac.uk * */ #include <linux/module.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <linux/time.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/unistd.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/metrics.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/lockd/bind.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/inet.h> #include <linux/nfs_xdr.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/freezer.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include "nfs4_fs.h" #include "callback.h" #include "delegation.h" #include "iostat.h" #include "internal.h" #include "fscache.h" #include "pnfs.h" #include "nfs.h" #include "netns.h" #include "sysfs.h" #include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_64_BIT_INODE_NUMBERS_ENABLED 1 /* Default is to see 64-bit inode numbers */ static bool enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED; static int nfs_update_inode(struct inode *, struct nfs_fattr *); static struct kmem_cache * nfs_inode_cachep; static inline unsigned long nfs_fattr_to_ino_t(struct nfs_fattr *fattr) { return nfs_fileid_to_ino_t(fattr->fileid); } int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { if (unlikely(nfs_current_task_exiting())) return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid * * This function returns a 32-bit inode number if the boot parameter * nfs.enable_ino64 is zero. */ u64 nfs_compat_user_ino64(u64 fileid) { #ifdef CONFIG_COMPAT compat_ulong_t ino; #else unsigned long ino; #endif if (enable_ino64) return fileid; ino = fileid; if (sizeof(ino) < sizeof(fileid)) ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8; return ino; } int nfs_drop_inode(struct inode *inode) { return NFS_STALE(inode) || generic_drop_inode(inode); } EXPORT_SYMBOL_GPL(nfs_drop_inode); void nfs_clear_inode(struct inode *inode) { /* * The following should never happen... */ WARN_ON_ONCE(nfs_have_writebacks(inode)); WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files)); nfs_zap_acl_cache(inode); nfs_access_zap_cache(inode); nfs_fscache_clear_inode(inode); } EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nfs_clear_inode(inode); } int nfs_sync_inode(struct inode *inode) { inode_dio_wait(inode); return nfs_wb_all(inode); } EXPORT_SYMBOL_GPL(nfs_sync_inode); /** * nfs_sync_mapping - helper to flush all mmapped dirty data to disk * @mapping: pointer to struct address_space */ int nfs_sync_mapping(struct address_space *mapping) { int ret = 0; if (mapping->nrpages != 0) { unmap_mapping_range(mapping, 0, 0, 0); ret = nfs_wb_all(mapping->host); } return ret; } static int nfs_attribute_timeout(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); } static bool nfs_check_cache_flags_invalid(struct inode *inode, unsigned long flags) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); return (cache_validity & flags) != 0; } bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) { if (nfs_check_cache_flags_invalid(inode, flags)) return true; return nfs_attribute_cache_expired(inode); } EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); #ifdef CONFIG_NFS_V4_2 static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return nfsi->xattr_cache != NULL; } #else static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return false; } #endif void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); if (nfs_have_delegated_attributes(inode)) { if (!(flags & NFS_INO_REVAL_FORCED)) flags &= ~(NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) nfs_fscache_invalidate(inode, 0); flags &= ~NFS_INO_REVAL_FORCED; flags |= nfsi->cache_validity; if (inode->i_mapping->nrpages == 0) flags &= ~NFS_INO_INVALID_DATA; /* pairs with nfs_clear_invalid_mapping()'s smp_load_acquire() */ smp_store_release(&nfsi->cache_validity, flags); if (inode->i_mapping->nrpages == 0 || nfsi->cache_validity & NFS_INO_INVALID_DATA) { nfs_ooo_clear(nfsi); } trace_nfs_set_cache_invalid(inode, 0); } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); /* * Invalidate the local caches */ static void nfs_zap_caches_locked(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); int mode = inode->i_mode; nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR); nfs_zap_label_cache_locked(nfsi); } void nfs_zap_caches(struct inode *inode) { spin_lock(&inode->i_lock); nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { if (mapping->nrpages != 0) { spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); spin_unlock(&inode->i_lock); } } void nfs_zap_acl_cache(struct inode *inode) { void (*clear_acl_cache)(struct inode *); clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache; if (clear_acl_cache != NULL) clear_acl_cache(inode); spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); void nfs_invalidate_atime(struct inode *inode) { if (nfs_have_delegated_atime(inode)) return; spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_invalidate_atime); /* * Invalidate, but do not unhash, the inode. * NB: must be called with inode->i_lock held! */ static void nfs_set_inode_stale_locked(struct inode *inode) { set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); nfs_zap_caches_locked(inode); trace_nfs_set_inode_stale(inode); } void nfs_set_inode_stale(struct inode *inode) { spin_lock(&inode->i_lock); nfs_set_inode_stale_locked(inode); spin_unlock(&inode->i_lock); } struct nfs_find_desc { struct nfs_fh *fh; struct nfs_fattr *fattr; }; /* * In NFSv3 we can have 64bit inode numbers. In order to support * this, and re-exported directories (also seen in NFSv2) * we are forced to allow 2 different inodes to have the same * i_ino. */ static int nfs_find_actor(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = opaque; struct nfs_fh *fh = desc->fh; struct nfs_fattr *fattr = desc->fattr; if (NFS_FILEID(inode) != fattr->fileid) return 0; if (inode_wrong_type(inode, fattr->mode)) return 0; if (nfs_compare_fh(NFS_FH(inode), fh)) return 0; if (is_bad_inode(inode) || NFS_STALE(inode)) return 0; return 1; } static int nfs_init_locked(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = opaque; struct nfs_fattr *fattr = desc->fattr; set_nfs_fileid(inode, fattr->fileid); inode->i_mode = fattr->mode; nfs_copy_fh(NFS_FH(inode), desc->fh); return 0; } #ifdef CONFIG_NFS_V4_SECURITY_LABEL static void nfs_clear_label_invalid(struct inode *inode) { spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; spin_unlock(&inode->i_lock); } void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { int error; if (fattr->label == NULL) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { error = security_inode_notifysecctx(inode, fattr->label->label, fattr->label->len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, (char *)fattr->label->label, fattr->label->len, error); nfs_clear_label_invalid(inode); } } struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { struct nfs4_label *label; if (!(server->caps & NFS_CAP_SECURITY_LABEL)) return NULL; label = kzalloc(sizeof(struct nfs4_label), flags); if (label == NULL) return ERR_PTR(-ENOMEM); label->label = kzalloc(NFS4_MAXLABELLEN, flags); if (label->label == NULL) { kfree(label); return ERR_PTR(-ENOMEM); } label->len = NFS4_MAXLABELLEN; return label; } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { } #endif EXPORT_SYMBOL_GPL(nfs_setsecurity); /* Search for inode identified by fh, fileid and i_mode in inode cache. */ struct inode * nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr, }; struct inode *inode; unsigned long hash; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) || !(fattr->valid & NFS_ATTR_FATTR_TYPE)) return NULL; hash = nfs_fattr_to_ino_t(fattr); inode = ilookup5(sb, hash, nfs_find_actor, &desc); dprintk("%s: returning %p\n", __func__, inode); return inode; } static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); mutex_init(&nfsi->commit_mutex); } static void nfs_inode_init_dir(struct nfs_inode *nfsi) { nfsi->cache_change_attribute = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); init_rwsem(&nfsi->rmdir_sem); } /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. */ struct inode * nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr }; struct inode *inode = ERR_PTR(-ENOENT); u64 fattr_supported = NFS_SB(sb)->fattr_valid; unsigned long hash; nfs_attr_check_mountpoint(sb, fattr); if (nfs_attr_use_mounted_on_fileid(fattr)) fattr->fileid = fattr->mounted_on_fileid; else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; hash = nfs_fattr_to_ino_t(fattr); inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc); if (inode == NULL) { inode = ERR_PTR(-ENOMEM); goto out_no_inode; } if (inode->i_state & I_NEW) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long now = jiffies; /* We set i_ino for the few things that still rely on it, * such as stat(2) */ inode->i_ino = hash; /* We can't support update_atime(), since the server will reset it */ inode->i_flags |= S_NOATIME|S_NOCMTIME; inode->i_mode = fattr->mode; nfsi->cache_validity = 0; if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 && (fattr_supported & NFS_ATTR_FATTR_MODE)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops; if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; nfs_inode_init_regular(nfsi); mapping_set_large_folios(inode->i_mapping); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; nfs_inode_init_dir(nfsi); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) inode->i_op = &nfs_referral_inode_operations; else inode->i_op = &nfs_mountpoint_inode_operations; inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; inode_nohighmem(inode); } else init_special_inode(inode, inode->i_mode, fattr->rdev); inode_set_atime(inode, 0, 0); inode_set_mtime(inode, 0, 0); inode_set_ctime(inode, 0, 0); inode_set_iversion_raw(inode, 0); inode->i_size = 0; clear_nlink(inode); inode->i_uid = make_kuid(&init_user_ns, -2); inode->i_gid = make_kgid(&init_user_ns, -2); inode->i_blocks = 0; nfsi->write_io = 0; nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode_set_iversion_raw(inode, fattr->change_attr); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE); if (fattr->valid & NFS_ATTR_FATTR_NLINK) set_nlink(inode, fattr->nlink); else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK); else set_nlink(inode, 1); if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_setsecurity(inode, fattr); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; nfsi->access_cache = RB_ROOT; nfs_fscache_init_inode(inode); unlock_new_inode(inode); } else { int err = nfs_refresh_inode(inode, fattr); if (err < 0) { iput(inode); inode = ERR_PTR(err); goto out_no_inode; } } dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), nfs_display_fhandle_hash(fh), atomic_read(&inode->i_count)); out: return inode; out_no_inode: dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode)); goto out; } EXPORT_SYMBOL_GPL(nfs_fhget); static void nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr) { unsigned long cache_validity = NFS_I(inode)->cache_validity; if (nfs_have_delegated_mtime(inode)) { if (!(cache_validity & NFS_INO_INVALID_CTIME)) fattr->valid &= ~(NFS_ATTR_FATTR_PRECTIME | NFS_ATTR_FATTR_CTIME); if (!(cache_validity & NFS_INO_INVALID_MTIME)) fattr->valid &= ~(NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_MTIME); if (!(cache_validity & NFS_INO_INVALID_ATIME)) fattr->valid &= ~NFS_ATTR_FATTR_ATIME; } else if (nfs_have_delegated_atime(inode)) { if (!(cache_validity & NFS_INO_INVALID_ATIME)) fattr->valid &= ~NFS_ATTR_FATTR_ATIME; } } static void nfs_set_timestamps_to_ts(struct inode *inode, struct iattr *attr) { unsigned int cache_flags = 0; if (attr->ia_valid & ATTR_MTIME_SET) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 mtime = inode_get_mtime(inode); struct timespec64 now; int updated = 0; now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; inode_set_mtime_to_ts(inode, attr->ia_mtime); if (!timespec64_equal(&now, &mtime)) updated |= S_MTIME; inode_maybe_inc_iversion(inode, updated); cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME; } if (attr->ia_valid & ATTR_ATIME_SET) { inode_set_atime_to_ts(inode, attr->ia_atime); cache_flags |= NFS_INO_INVALID_ATIME; } NFS_I(inode)->cache_validity &= ~cache_flags; } static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid) { enum file_time_flags time_flags = 0; unsigned int cache_flags = 0; if (ia_valid & ATTR_MTIME) { time_flags |= S_MTIME | S_CTIME; cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME; } if (ia_valid & ATTR_ATIME) { time_flags |= S_ATIME; cache_flags |= NFS_INO_INVALID_ATIME; } inode_update_timestamps(inode, time_flags); NFS_I(inode)->cache_validity &= ~cache_flags; } void nfs_update_delegated_atime(struct inode *inode) { spin_lock(&inode->i_lock); if (nfs_have_delegated_atime(inode)) nfs_update_timestamps(inode, ATTR_ATIME); spin_unlock(&inode->i_lock); } void nfs_update_delegated_mtime_locked(struct inode *inode) { if (nfs_have_delegated_mtime(inode)) nfs_update_timestamps(inode, ATTR_MTIME); } void nfs_update_delegated_mtime(struct inode *inode) { spin_lock(&inode->i_lock); nfs_update_delegated_mtime_locked(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_update_delegated_mtime); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) int nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); /* skip mode change if it's just for clearing setuid/setgid */ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; if (attr->ia_size == i_size_read(inode)) attr->ia_valid &= ~ATTR_SIZE; } if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { spin_lock(&inode->i_lock); if (attr->ia_valid & ATTR_MTIME_SET) { nfs_set_timestamps_to_ts(inode, attr); attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| ATTR_ATIME|ATTR_ATIME_SET); } else { nfs_update_timestamps(inode, attr->ia_valid); attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME); } spin_unlock(&inode->i_lock); } else if (nfs_have_delegated_atime(inode) && attr->ia_valid & ATTR_ATIME && !(attr->ia_valid & ATTR_MTIME)) { if (attr->ia_valid & ATTR_ATIME_SET) { spin_lock(&inode->i_lock); nfs_set_timestamps_to_ts(inode, attr); spin_unlock(&inode->i_lock); attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); } else { nfs_update_delegated_atime(inode); attr->ia_valid &= ~ATTR_ATIME; } } /* Optimization: if the end result is no change, don't RPC */ if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0) return 0; trace_nfs_setattr_enter(inode); /* Write all dirty data */ if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { error = -ENOMEM; goto out; } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); if (error == 0) error = nfs_refresh_inode(inode, fattr); nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); return error; } EXPORT_SYMBOL_GPL(nfs_setattr); /** * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall * @inode: inode of the file used * @offset: file offset to start truncating * * This is a copy of the common vmtruncate, but with the locking * corrected to take into account the fact that NFS requires * inode->i_size to be updated under the inode->i_lock. * Note: must be called with inode->i_lock held! */ static int nfs_vmtruncate(struct inode * inode, loff_t offset) { int err; err = inode_newsize_ok(inode, offset); if (err) goto out; trace_nfs_size_truncate(inode, offset); i_size_write(inode, offset); /* Optimisation */ if (offset == 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA; nfs_ooo_clear(NFS_I(inode)); } NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; spin_unlock(&inode->i_lock); truncate_pagecache(inode, offset); nfs_update_delegated_mtime_locked(inode); spin_lock(&inode->i_lock); out: return err; } /** * nfs_setattr_update_inode - Update inode metadata after a setattr call. * @inode: pointer to struct inode * @attr: pointer to struct iattr * @fattr: pointer to struct nfs_fattr * * Note: we do this in the *proc.c in order to ensure that * it works for things like exclusive creates too. */ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *fattr) { /* Barrier: bump the attribute generation count. */ nfs_fattr_set_barrier(fattr); spin_lock(&inode->i_lock); NFS_I(inode)->attr_gencount = fattr->gencount; if ((attr->ia_valid & ATTR_SIZE) != 0) { if (!nfs_have_delegated_mtime(inode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC); nfs_vmtruncate(inode, attr->ia_size); } if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME; if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; if (setattr_should_drop_sgid(&nop_mnt_idmap, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; } if ((attr->ia_valid & ATTR_UID) != 0) inode->i_uid = attr->ia_uid; if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL); } if (attr->ia_valid & (ATTR_ATIME_SET|ATTR_ATIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (attr->ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (attr->ia_valid & (ATTR_MTIME_SET|ATTR_MTIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (attr->ia_valid & ATTR_MTIME_SET) inode_set_mtime_to_ts(inode, attr->ia_mtime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (fattr->valid) nfs_update_inode(inode, fattr); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); /* * Don't request help from readdirplus if the file is being written to, * or if attribute caching is turned off */ static bool nfs_getattr_readdirplus_enable(const struct inode *inode) { return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) && !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ; } static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) { if (!IS_ROOT(dentry)) { struct dentry *parent = dget_parent(dentry); nfs_readdir_record_entry_cache_miss(d_inode(parent)); dput(parent); } } static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry) { if (!IS_ROOT(dentry)) { struct dentry *parent = dget_parent(dentry); nfs_readdir_record_entry_cache_hit(d_inode(parent)); dput(parent); } } static u32 nfs_get_valid_attrmask(struct inode *inode) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); u32 reply_mask = STATX_INO | STATX_TYPE; if (!(cache_validity & NFS_INO_INVALID_ATIME)) reply_mask |= STATX_ATIME; if (!(cache_validity & NFS_INO_INVALID_CTIME)) reply_mask |= STATX_CTIME; if (!(cache_validity & NFS_INO_INVALID_MTIME)) reply_mask |= STATX_MTIME; if (!(cache_validity & NFS_INO_INVALID_SIZE)) reply_mask |= STATX_SIZE; if (!(cache_validity & NFS_INO_INVALID_NLINK)) reply_mask |= STATX_NLINK; if (!(cache_validity & NFS_INO_INVALID_MODE)) reply_mask |= STATX_MODE; if (!(cache_validity & NFS_INO_INVALID_OTHER)) reply_mask |= STATX_UID | STATX_GID; if (!(cache_validity & NFS_INO_INVALID_BLOCKS)) reply_mask |= STATX_BLOCKS; if (!(cache_validity & NFS_INO_INVALID_CHANGE)) reply_mask |= STATX_CHANGE_COOKIE; return reply_mask; } int nfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct nfs_server *server = NFS_SERVER(inode); unsigned long cache_validity; int err = 0; bool force_sync = query_flags & AT_STATX_FORCE_SYNC; bool do_update = false; bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode); trace_nfs_getattr_enter(inode); request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID | STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME | STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_CHANGE_COOKIE; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_revalidate; } /* Flush out writes to the server in order to update c/mtime/version. */ if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_CHANGE_COOKIE)) && S_ISREG(inode->i_mode)) { if (nfs_have_delegated_mtime(inode)) filemap_fdatawrite(inode->i_mapping); else filemap_write_and_wait(inode->i_mapping); } /* * We may force a getattr if the user cares about atime. * * Note that we only have to check the vfsmount flags here: * - NFS always sets S_NOATIME by so checking it would give a * bogus result * - NFS never sets SB_NOATIME or SB_NODIRATIME so there is * no point in checking those. */ if ((path->mnt->mnt_flags & MNT_NOATIME) || ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))) request_mask &= ~STATX_ATIME; /* Is the user requesting attributes that might need revalidation? */ if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME| STATX_MTIME|STATX_UID|STATX_GID| STATX_SIZE|STATX_BLOCKS| STATX_CHANGE_COOKIE))) goto out_no_revalidate; /* Check whether the cached attributes are stale */ do_update |= force_sync || nfs_attribute_cache_expired(inode); cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); do_update |= cache_validity & NFS_INO_INVALID_CHANGE; if (request_mask & STATX_ATIME) do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & STATX_CTIME) do_update |= cache_validity & NFS_INO_INVALID_CTIME; if (request_mask & STATX_MTIME) do_update |= cache_validity & NFS_INO_INVALID_MTIME; if (request_mask & STATX_SIZE) do_update |= cache_validity & NFS_INO_INVALID_SIZE; if (request_mask & STATX_NLINK) do_update |= cache_validity & NFS_INO_INVALID_NLINK; if (request_mask & STATX_MODE) do_update |= cache_validity & NFS_INO_INVALID_MODE; if (request_mask & (STATX_UID | STATX_GID)) do_update |= cache_validity & NFS_INO_INVALID_OTHER; if (request_mask & STATX_BLOCKS) do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { if (readdirplus_enabled) nfs_readdirplus_parent_cache_miss(path->dentry); err = __nfs_revalidate_inode(server, inode); if (err) goto out; } else if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); out_no_revalidate: /* Only return attributes that were revalidated. */ stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); stat->change_cookie = inode_peek_iversion_raw(inode); stat->attributes_mask |= STATX_ATTR_CHANGE_MONOTONIC; if (server->change_attr_type != NFS4_CHANGE_TYPE_IS_UNDEFINED) stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC; if (S_ISDIR(inode->i_mode)) stat->blksize = NFS_SERVER(inode)->dtsize; out: trace_nfs_getattr_exit(inode, err); return err; } EXPORT_SYMBOL_GPL(nfs_getattr); static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) { refcount_set(&l_ctx->count, 1); l_ctx->lockowner = current->files; INIT_LIST_HEAD(&l_ctx->list); atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *pos; list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) { if (pos->lockowner != current->files) continue; if (refcount_inc_not_zero(&pos->count)) return pos; } return NULL; } struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *res, *new = NULL; struct inode *inode = d_inode(ctx->dentry); rcu_read_lock(); res = __nfs_find_lock_context(ctx); rcu_read_unlock(); if (res == NULL) { new = kmalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (new == NULL) return ERR_PTR(-ENOMEM); nfs_init_lock_context(new); spin_lock(&inode->i_lock); res = __nfs_find_lock_context(ctx); if (res == NULL) { new->open_context = get_nfs_open_context(ctx); if (new->open_context) { list_add_tail_rcu(&new->list, &ctx->lock_context.list); res = new; new = NULL; } else res = ERR_PTR(-EBADF); } spin_unlock(&inode->i_lock); kfree(new); } return res; } EXPORT_SYMBOL_GPL(nfs_get_lock_context); void nfs_put_lock_context(struct nfs_lock_context *l_ctx) { struct nfs_open_context *ctx = l_ctx->open_context; struct inode *inode = d_inode(ctx->dentry); if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock)) return; list_del_rcu(&l_ctx->list); spin_unlock(&inode->i_lock); put_nfs_open_context(ctx); kfree_rcu(l_ctx, rcu_head); } EXPORT_SYMBOL_GPL(nfs_put_lock_context); /** * nfs_close_context - Common close_context() routine NFSv2/v3 * @ctx: pointer to context * @is_sync: is this a synchronous close * * Ensure that the attributes are up to date if we're mounted * with close-to-open semantics and we have cached data that will * need to be revalidated on open. */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) { struct nfs_inode *nfsi; struct inode *inode; if (!(ctx->mode & FMODE_WRITE)) return; if (!is_sync) return; inode = d_inode(ctx->dentry); if (nfs_have_read_or_write_delegation(inode)) return; nfsi = NFS_I(inode); if (inode->i_mapping->nrpages == 0) return; if (nfsi->cache_validity & NFS_INO_INVALID_DATA) return; if (!list_empty(&nfsi->open_files)) return; if (NFS_SERVER(inode)->flags & NFS_MOUNT_NOCTO) return; nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } EXPORT_SYMBOL_GPL(nfs_close_context); struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp) { struct nfs_open_context *ctx; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (!ctx) return ERR_PTR(-ENOMEM); nfs_sb_active(dentry->d_sb); ctx->dentry = dget(dentry); if (filp) ctx->cred = get_cred(filp->f_cred); else ctx->cred = get_current_cred(); rcu_assign_pointer(ctx->ll_cred, NULL); ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; ctx->error = 0; ctx->flock_owner = (fl_owner_t)filp; nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); ctx->mdsthreshold = NULL; nfs_localio_file_init(&ctx->nfl); return ctx; } EXPORT_SYMBOL_GPL(alloc_nfs_open_context); struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) { if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count)) return ctx; return NULL; } EXPORT_SYMBOL_GPL(get_nfs_open_context); static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { struct inode *inode = d_inode(ctx->dentry); struct super_block *sb = ctx->dentry->d_sb; if (!refcount_dec_and_test(&ctx->lock_context.count)) return; if (!list_empty(&ctx->list)) { spin_lock(&inode->i_lock); list_del_rcu(&ctx->list); spin_unlock(&inode->i_lock); } if (inode != NULL) NFS_PROTO(inode)->close_context(ctx, is_sync); put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); nfs_close_local_fh(&ctx->nfl); kfree_rcu(ctx, rcu_head); } void put_nfs_open_context(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 0); } EXPORT_SYMBOL_GPL(put_nfs_open_context); static void put_nfs_open_context_sync(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 1); } /* * Ensure that mmap has a recent RPC credential for use when writing out * shared pages */ void nfs_inode_attach_open_context(struct nfs_open_context *ctx) { struct inode *inode = d_inode(ctx->dentry); struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); if (list_empty(&nfsi->open_files) && nfs_ooo_test(nfsi)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add_tail_rcu(&ctx->list, &nfsi->open_files); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) { filp->private_data = get_nfs_open_context(ctx); set_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); if (list_empty(&ctx->list)) nfs_inode_attach_open_context(ctx); } EXPORT_SYMBOL_GPL(nfs_file_set_open_context); /* * Given an inode, search for an open context with the desired characteristics */ struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *pos, *ctx = NULL; rcu_read_lock(); list_for_each_entry_rcu(pos, &nfsi->open_files, list) { if (cred != NULL && cred_fscmp(pos->cred, cred) != 0) continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; if (!test_bit(NFS_CONTEXT_FILE_OPEN, &pos->flags)) continue; ctx = get_nfs_open_context(pos); if (ctx) break; } rcu_read_unlock(); return ctx; } void nfs_file_clear_open_context(struct file *filp) { struct nfs_open_context *ctx = nfs_file_open_context(filp); if (ctx) { struct inode *inode = d_inode(ctx->dentry); clear_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); /* * We fatal error on write before. Try to writeback * every page again. */ if (ctx->error < 0) invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; put_nfs_open_context_sync(ctx); } } /* * These allocate and release file read/write context information. */ int nfs_open(struct inode *inode, struct file *filp) { struct nfs_open_context *ctx; ctx = alloc_nfs_open_context(file_dentry(filp), flags_to_mode(filp->f_flags), filp); if (IS_ERR(ctx)) return PTR_ERR(ctx); nfs_file_set_open_context(filp, ctx); put_nfs_open_context(ctx); nfs_fscache_open_file(inode, filp); return 0; } /* * This function is called whenever some part of NFS notices that * the cached attributes have to be refreshed. */ int __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { int status = -ESTALE; struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); trace_nfs_revalidate_inode_enter(inode); if (is_bad_inode(inode)) goto out; if (NFS_STALE(inode)) goto out; /* pNFS: Attributes aren't updated until we layoutcommit */ if (S_ISREG(inode->i_mode)) { status = pnfs_sync_inode(inode, false); if (status) goto out; } status = -ENOMEM; fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) goto out; nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, inode); if (status != 0) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); switch (status) { case -ETIMEDOUT: /* A soft timeout occurred. Use cached information? */ if (server->flags & NFS_MOUNT_SOFTREVAL) status = 0; break; case -ESTALE: if (!S_ISDIR(inode->i_mode)) nfs_set_inode_stale(inode); else nfs_zap_caches(inode); } goto out; } status = nfs_refresh_inode(inode, fattr); if (status) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); goto out; } if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); nfs_setsecurity(inode, fattr); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); out: nfs_free_fattr(fattr); trace_nfs_revalidate_inode_exit(inode, status); return status; } int nfs_attribute_cache_expired(struct inode *inode) { if (nfs_have_delegated_attributes(inode)) return 0; return nfs_attribute_timeout(inode); } /** * nfs_revalidate_inode - Revalidate the inode attributes * @inode: pointer to inode struct * @flags: cache flags to check * * Updates inode attribute information by retrieving the data from the server. */ int nfs_revalidate_inode(struct inode *inode, unsigned long flags) { if (!nfs_check_cache_invalid(inode, flags)) return NFS_STALE(inode) ? -ESTALE : 0; return __nfs_revalidate_inode(NFS_SERVER(inode), inode); } EXPORT_SYMBOL_GPL(nfs_revalidate_inode); static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { int ret; nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); if (ret < 0) return ret; } ret = invalidate_inode_pages2(mapping); if (ret < 0) return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); return 0; } /** * nfs_clear_invalid_mapping - Conditionally clear a mapping * @mapping: pointer to mapping * * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. */ int nfs_clear_invalid_mapping(struct address_space *mapping) { struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; /* * We must clear NFS_INO_INVALID_DATA first to ensure that * invalidations that come in while we're shooting down the mappings * are respected. But, that leaves a race window where one revalidator * can clear the flag, and then another checks it before the mapping * gets invalidated. Fix that by serializing access to this part of * the function. * * At the same time, we need to allow other tasks to see whether we * might be in the middle of invalidating the pages, so we only set * the bit lock here if it looks like we're going to be doing that. */ for (;;) { ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (ret) goto out; smp_rmb(); /* pairs with smp_wmb() below */ if (test_bit(NFS_INO_INVALIDATING, bitlock)) continue; /* pairs with nfs_set_cache_invalid()'s smp_store_release() */ if (!(smp_load_acquire(&nfsi->cache_validity) & NFS_INO_INVALID_DATA)) goto out; /* Slow-path that double-checks with spinlock held */ spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock)) { spin_unlock(&inode->i_lock); continue; } if (nfsi->cache_validity & NFS_INO_INVALID_DATA) break; spin_unlock(&inode->i_lock); goto out; } set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; nfs_ooo_clear(nfsi); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); trace_nfs_invalidate_mapping_exit(inode, ret); clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); smp_mb__after_atomic(); wake_up_bit(bitlock, NFS_INO_INVALIDATING); out: return ret; } bool nfs_mapping_need_revalidate_inode(struct inode *inode) { return nfs_check_cache_invalid(inode, NFS_INO_INVALID_CHANGE) || NFS_STALE(inode); } int nfs_revalidate_mapping_rcu(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; if (IS_SWAPFILE(inode)) goto out; if (nfs_mapping_need_revalidate_inode(inode)) { ret = -ECHILD; goto out; } spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock) || (nfsi->cache_validity & NFS_INO_INVALID_DATA)) ret = -ECHILD; spin_unlock(&inode->i_lock); out: return ret; } /** * nfs_revalidate_mapping - Revalidate the pagecache * @inode: pointer to host inode * @mapping: pointer to mapping */ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { /* swapfiles are not supposed to be shared. */ if (IS_SWAPFILE(inode)) return 0; if (nfs_mapping_need_revalidate_inode(inode)) { int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) return ret; } return nfs_clear_invalid_mapping(mapping); } static bool nfs_file_has_writers(struct nfs_inode *nfsi) { struct inode *inode = &nfsi->vfs_inode; if (!S_ISREG(inode->i_mode)) return false; if (list_empty(&nfsi->open_files)) return false; return inode_is_open_for_write(inode); } static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) { return nfs_file_has_writers(nfsi) && nfs_file_io_is_buffered(nfsi); } static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct timespec64 ts; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) && inode_eq_iversion_raw(inode, fattr->pre_change_attr)) { inode_set_iversion_raw(inode, fattr->change_attr); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); else if (nfs_server_capable(inode, NFS_CAP_XATTR)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); } /* If we have atomic WCC data, we may update some attributes */ ts = inode_get_ctime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) && timespec64_equal(&ts, &fattr->pre_ctime)) { inode_set_ctime_to_ts(inode, fattr->ctime); } ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec64_equal(&ts, &fattr->pre_mtime)) { inode_set_mtime_to_ts(inode, fattr->mtime); } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) && !nfs_have_writebacks(inode)) { trace_nfs_size_wcc(inode, fattr->size); i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } } /** * nfs_check_inode_attributes - verify consistency of the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Verifies the attribute cache. If we have just changed the attributes, * so that fattr carries weak cache consistency data, then it may * also update the ctime/mtime/change_attribute. */ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; struct timespec64 ts; if (nfs_have_delegated_attributes(inode)) return 0; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; return -ESTALE; } if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr)) invalid |= NFS_INO_INVALID_CHANGE; ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; ts = inode_get_ctime(inode); if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); if (cur_size != new_isize) invalid |= NFS_INO_INVALID_SIZE; } } /* Have any file permissions changed? */ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) invalid |= NFS_INO_INVALID_MODE; if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid)) invalid |= NFS_INO_INVALID_OTHER; if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid)) invalid |= NFS_INO_INVALID_OTHER; /* Has the link count changed? */ if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_NLINK; ts = inode_get_atime(inode); if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) nfs_set_cache_invalid(inode, invalid); nfsi->read_cache_jiffies = fattr->time_start; return 0; } static atomic_long_t nfs_attr_generation_counter; static unsigned long nfs_read_attr_generation_counter(void) { return atomic_long_read(&nfs_attr_generation_counter); } unsigned long nfs_inc_attr_generation_counter(void) { return atomic_long_inc_return(&nfs_attr_generation_counter); } EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter); void nfs_fattr_init(struct nfs_fattr *fattr) { fattr->valid = 0; fattr->time_start = jiffies; fattr->gencount = nfs_inc_attr_generation_counter(); fattr->owner_name = NULL; fattr->group_name = NULL; fattr->mdsthreshold = NULL; } EXPORT_SYMBOL_GPL(nfs_fattr_init); /** * nfs_fattr_set_barrier * @fattr: attributes * * Used to set a barrier after an attribute was updated. This * barrier ensures that older attributes from RPC calls that may * have raced with our update cannot clobber these new values. * Note that you are still responsible for ensuring that other * operations which change the attribute on the server do not * collide. */ void nfs_fattr_set_barrier(struct nfs_fattr *fattr) { fattr->gencount = nfs_inc_attr_generation_counter(); } struct nfs_fattr *nfs_alloc_fattr(void) { struct nfs_fattr *fattr; fattr = kmalloc(sizeof(*fattr), GFP_KERNEL); if (fattr != NULL) { nfs_fattr_init(fattr); fattr->label = NULL; } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr); struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) { struct nfs_fattr *fattr = nfs_alloc_fattr(); if (!fattr) return NULL; fattr->label = nfs4_label_alloc(server, GFP_KERNEL); if (IS_ERR(fattr->label)) { kfree(fattr); return NULL; } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr_with_label); struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; fh = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); if (fh != NULL) fh->size = 0; return fh; } EXPORT_SYMBOL_GPL(nfs_alloc_fhandle); #ifdef NFS_DEBUG /* * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle * in the same way that wireshark does * * @fh: file handle * * For debugging only. */ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) { /* wireshark uses 32-bit AUTODIN crc and does a bitwise * not on the result */ return nfs_fhandle_hash(fh); } EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); /* * _nfs_display_fhandle - display an NFS file handle on the console * * @fh: file handle to display * @caption: display caption * * For debugging only. */ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) { unsigned short i; if (fh == NULL || fh->size == 0) { printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh); return; } printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n", caption, fh, fh->size, _nfs_display_fhandle_hash(fh)); for (i = 0; i < fh->size; i += 16) { __be32 *pos = (__be32 *)&fh->data[i]; switch ((fh->size - i - 1) >> 2) { case 0: printk(KERN_DEFAULT " %08x\n", be32_to_cpup(pos)); break; case 1: printk(KERN_DEFAULT " %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1)); break; case 2: printk(KERN_DEFAULT " %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2)); break; default: printk(KERN_DEFAULT " %08x %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2), be32_to_cpup(pos + 3)); } } } EXPORT_SYMBOL_GPL(_nfs_display_fhandle); #endif /** * nfs_inode_attrs_cmp_generic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * Note also the check for wraparound of 'attr_gencount' * * The function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. Otherwise it returns * the value '0'. */ static int nfs_inode_attrs_cmp_generic(const struct nfs_fattr *fattr, const struct inode *inode) { unsigned long attr_gencount = NFS_I(inode)->attr_gencount; return (long)(fattr->gencount - attr_gencount) > 0 || (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0; } /** * nfs_inode_attrs_cmp_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '0' indicates no measurable change * A return value of '-1' means that the attributes in @inode are * more recent. */ static int nfs_inode_attrs_cmp_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { s64 diff = fattr->change_attr - inode_peek_iversion_raw(inode); if (diff > 0) return 1; return diff == 0 ? 0 : -1; } /** * nfs_inode_attrs_cmp_strict_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes strictly monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '-1' means that the attributes in @inode are * more recent or unchanged. */ static int nfs_inode_attrs_cmp_strict_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { return nfs_inode_attrs_cmp_monotonic(fattr, inode) > 0 ? 1 : -1; } /** * nfs_inode_attrs_cmp - compare attributes * @fattr: attributes * @inode: pointer to inode * * This function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. It returns '-1' if * the attributes in @inode are more recent than the ones in @fattr, * and it returns 0 if not sure. */ static int nfs_inode_attrs_cmp(const struct nfs_fattr *fattr, const struct inode *inode) { if (nfs_inode_attrs_cmp_generic(fattr, inode) > 0) return 1; switch (NFS_SERVER(inode)->change_attr_type) { case NFS4_CHANGE_TYPE_IS_UNDEFINED: break; case NFS4_CHANGE_TYPE_IS_TIME_METADATA: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_monotonic(fattr, inode); default: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_strict_monotonic(fattr, inode); } return 0; } /** * nfs_inode_finish_partial_attr_update - complete a previous inode update * @fattr: attributes * @inode: pointer to inode * * Returns '1' if the last attribute update left the inode cached * attributes in a partially unrevalidated state, and @fattr * matches the change attribute of that partial update. * Otherwise returns '0'. */ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, const struct inode *inode) { const unsigned long check_valid = NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_NLINK; unsigned long cache_validity = NFS_I(inode)->cache_validity; enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type; if (ctype != NFS4_CHANGE_TYPE_IS_UNDEFINED && !(cache_validity & NFS_INO_INVALID_CHANGE) && (cache_validity & check_valid) != 0 && (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0) return 1; return 0; } static void nfs_ooo_merge(struct nfs_inode *nfsi, u64 start, u64 end) { int i, cnt; if (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) /* No point merging anything */ return; if (!nfsi->ooo) { nfsi->ooo = kmalloc(sizeof(*nfsi->ooo), GFP_ATOMIC); if (!nfsi->ooo) { nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; return; } nfsi->ooo->cnt = 0; } /* add this range, merging if possible */ cnt = nfsi->ooo->cnt; for (i = 0; i < cnt; i++) { if (end == nfsi->ooo->gap[i].start) end = nfsi->ooo->gap[i].end; else if (start == nfsi->ooo->gap[i].end) start = nfsi->ooo->gap[i].start; else continue; /* Remove 'i' from table and loop to insert the new range */ cnt -= 1; nfsi->ooo->gap[i] = nfsi->ooo->gap[cnt]; i = -1; } if (start != end) { if (cnt >= ARRAY_SIZE(nfsi->ooo->gap)) { nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; kfree(nfsi->ooo); nfsi->ooo = NULL; return; } nfsi->ooo->gap[cnt].start = start; nfsi->ooo->gap[cnt].end = end; cnt += 1; } nfsi->ooo->cnt = cnt; } static void nfs_ooo_record(struct nfs_inode *nfsi, struct nfs_fattr *fattr) { /* This reply was out-of-order, so record in the * pre/post change id, possibly cancelling * gaps created when iversion was jumpped forward. */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) nfs_ooo_merge(nfsi, fattr->change_attr, fattr->pre_change_attr); } static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int ret = 0; trace_nfs_refresh_inode_enter(inode); if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode)) ret = nfs_update_inode(inode, fattr); else { nfs_ooo_record(NFS_I(inode), fattr); if (attr_cmp == 0) ret = nfs_check_inode_attributes(inode, fattr); } trace_nfs_refresh_inode_exit(inode, ret); return ret; } /** * nfs_refresh_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Check that an RPC call that returned attributes has not overlapped with * other recent updates of the inode metadata, then decide whether it is * safe to do a full update of the inode attributes, or whether just to * call nfs_check_inode_attributes. */ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; spin_lock(&inode->i_lock); status = nfs_refresh_inode_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_refresh_inode); static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr, unsigned int invalid) { if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; return nfs_refresh_inode_locked(inode, fattr); } /** * nfs_post_op_update_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. * * NB: if the server didn't return any post op attributes, this * function will force the retrieval of attributes before the next * NFS request. Thus it should be used only for operations that * are expected to change one or more attributes, to avoid * unnecessary NFS requests and trips through nfs_update_inode(). */ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_REVAL_FORCED); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); /** * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int status; /* Don't do a WCC update if these attributes are already stale */ if (attr_cmp < 0) return 0; if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) { /* Record the pre/post change info before clearing PRECHANGE */ nfs_ooo_record(NFS_I(inode), fattr); fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PRESIZE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME); goto out_noforce; } if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { fattr->pre_change_attr = inode_peek_iversion_raw(inode); fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { fattr->pre_ctime = inode_get_ctime(inode); fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { fattr->pre_mtime = inode_get_mtime(inode); fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) { fattr->pre_size = i_size_read(inode); fattr->valid |= NFS_ATTR_FATTR_PRESIZE; } out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_BLOCKS); return status; } /** * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc); /* * Many nfs protocol calls return the new file attributes after * an operation. Here we update the inode to reflect the state * of the server's inode. * * This is a bit tricky because we have to make sure all dirty pages * have been sent off to the server before calling invalidate_inode_pages. * To make sure no other process adds more write requests while we try * our best to flush them, we make them sleep during the attribute refresh. * * A very similar scenario holds for the dir cache. */ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_isize, new_isize; u64 fattr_supported = server->fattr_valid; unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; bool have_writers = nfs_file_has_buffered_writers(nfsi); bool cache_revalidated = true; bool attr_changed = false; bool have_delegation; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; printk(KERN_ERR "NFS: server %s error: fileid changed\n" "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id, (long long)nfsi->fileid, (long long)fattr->fileid); goto out_err; } /* * Make sure the inode's type hasn't changed. */ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) { /* * Big trouble! The inode has become a different object. */ printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n", __func__, inode->i_ino, inode->i_mode, fattr->mode); goto out_err; } /* Update the fsid? */ if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) && !nfs_fsid_equal(&server->fsid, &fattr->fsid) && !IS_AUTOMOUNT(inode)) server->fsid = fattr->fsid; /* Save the delegation state before clearing cache_validity */ have_delegation = nfs_have_delegated_attributes(inode); /* * Update the read time so we don't revalidate too often. */ nfsi->read_cache_jiffies = fattr->time_start; /* Fix up any delegated attributes in the struct nfs_fattr */ nfs_fattr_fixup_delegated(inode, fattr); save_cache_validity = nfsi->cache_validity; nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); if (pnfs_layoutcommit_outstanding(inode)) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS); cache_revalidated = false; } /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { if (!have_writers && nfsi->ooo && nfsi->ooo->cnt == 1 && nfsi->ooo->gap[0].end == inode_peek_iversion_raw(inode)) { /* There is one remaining gap that hasn't been * merged into iversion - do that now. */ inode_set_iversion_raw(inode, nfsi->ooo->gap[0].start); kfree(nfsi->ooo); nfsi->ooo = NULL; } if (!inode_eq_iversion_raw(inode, fattr->change_attr)) { /* Could it be a race with writeback? */ if (!(have_writers || have_delegation)) { invalid |= NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR; /* Force revalidate of all attributes */ save_cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); attr_changed = true; dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); } else if (!have_delegation) { nfs_ooo_record(nfsi, fattr); nfs_ooo_merge(nfsi, inode_peek_iversion_raw(inode), fattr->change_attr); } inode_set_iversion_raw(inode, fattr->change_attr); } } else { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CHANGE; if (!have_delegation || (nfsi->cache_validity & NFS_INO_INVALID_CHANGE) != 0) cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MTIME; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CTIME; /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { new_isize = nfs_size_to_loff_t(fattr->size); cur_isize = i_size_read(inode); if (new_isize != cur_isize && !have_delegation) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ if (!nfs_have_writebacks(inode) || new_isize > cur_isize) { trace_nfs_size_update(inode, new_isize); i_size_write(inode, new_isize); if (!have_writers) invalid |= NFS_INO_INVALID_DATA; } } if (new_isize == 0 && !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED | NFS_ATTR_FATTR_BLOCKS_USED))) { fattr->du.nfs3.used = 0; fattr->valid |= NFS_ATTR_FATTR_SPACE_USED; } } else nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_SIZE; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATIME; if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { umode_t newmode = inode->i_mode & S_IFMT; newmode |= fattr->mode & S_IALLUGO; inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; } } else if (fattr_supported & NFS_ATTR_FATTR_MODE) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MODE; if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } } else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } } else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) set_nlink(inode, fattr->nlink); } else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_NLINK; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { if (cache_revalidated) { if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { nfsi->attrtimeo <<= 1; if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ if ((long)(fattr->gencount - nfsi->attr_gencount) > 0) nfsi->attr_gencount = fattr->gencount; } /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); return 0; out_err: /* * No need to worry about unhashing the dentry, as the * lookup validation will know that the inode is bad. * (But we fall through to invalidate the caches.) */ nfs_set_inode_stale_locked(inode); return -ESTALE; } struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; nfsi = alloc_inode_sb(sb, nfs_inode_cachep, GFP_KERNEL); if (!nfsi) return NULL; nfsi->flags = 0UL; nfsi->cache_validity = 0UL; nfsi->ooo = NULL; #if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_V4_2 nfsi->xattr_cache = NULL; #endif nfs_netfs_inode_init(nfsi); return &nfsi->vfs_inode; } EXPORT_SYMBOL_GPL(nfs_alloc_inode); void nfs_free_inode(struct inode *inode) { kfree(NFS_I(inode)->ooo); kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } EXPORT_SYMBOL_GPL(nfs_free_inode); static inline void nfs4_init_once(struct nfs_inode *nfsi) { #if IS_ENABLED(CONFIG_NFS_V4) INIT_LIST_HEAD(&nfsi->open_states); nfsi->delegation = NULL; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; #endif } static void init_once(void *foo) { struct nfs_inode *nfsi = foo; inode_init_once(&nfsi->vfs_inode); INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); nfs4_init_once(nfsi); } static int __init nfs_init_inodecache(void) { nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (nfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void nfs_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(nfs_inode_cachep); } struct workqueue_struct *nfslocaliod_workqueue; struct workqueue_struct *nfsiod_workqueue; EXPORT_SYMBOL_GPL(nfsiod_workqueue); /* * Destroy the nfsiod workqueues */ static void nfsiod_stop(void) { struct workqueue_struct *wq; wq = nfsiod_workqueue; if (wq != NULL) { nfsiod_workqueue = NULL; destroy_workqueue(wq); } #if IS_ENABLED(CONFIG_NFS_LOCALIO) wq = nfslocaliod_workqueue; if (wq != NULL) { nfslocaliod_workqueue = NULL; destroy_workqueue(wq); } #endif /* CONFIG_NFS_LOCALIO */ } /* * Start the nfsiod workqueues */ static int nfsiod_start(void) { dprintk("RPC: creating workqueue nfsiod\n"); nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (nfsiod_workqueue == NULL) return -ENOMEM; #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* * localio writes need to use a normal (non-memreclaim) workqueue. * When we start getting low on space, XFS goes and calls flush_work() on * a non-memreclaim work queue, which causes a priority inversion problem. */ dprintk("RPC: creating workqueue nfslocaliod\n"); nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0); if (unlikely(nfslocaliod_workqueue == NULL)) { nfsiod_stop(); return -ENOMEM; } #endif /* CONFIG_NFS_LOCALIO */ return 0; } unsigned int nfs_net_id; EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); nfs_clients_init(net); if (!rpc_proc_register(net, &nn->rpcstats)) { nfs_clients_exit(net); return -ENOMEM; } return nfs_fs_proc_net_init(net); } static void nfs_net_exit(struct net *net) { rpc_proc_unregister(net, "nfs"); nfs_fs_proc_net_exit(net); nfs_clients_exit(net); } static struct pernet_operations nfs_net_ops = { .init = nfs_net_init, .exit = nfs_net_exit, .id = &nfs_net_id, .size = sizeof(struct nfs_net), }; /* * Initialize NFS */ static int __init init_nfs_fs(void) { int err; err = nfs_sysfs_init(); if (err < 0) goto out10; err = register_pernet_subsys(&nfs_net_ops); if (err < 0) goto out9; err = nfsiod_start(); if (err) goto out7; err = nfs_fs_proc_init(); if (err) goto out6; err = nfs_init_nfspagecache(); if (err) goto out5; err = nfs_init_inodecache(); if (err) goto out4; err = nfs_init_readpagecache(); if (err) goto out3; err = nfs_init_writepagecache(); if (err) goto out2; err = nfs_init_directcache(); if (err) goto out1; err = register_nfs_fs(); if (err) goto out0; return 0; out0: nfs_destroy_directcache(); out1: nfs_destroy_writepagecache(); out2: nfs_destroy_readpagecache(); out3: nfs_destroy_inodecache(); out4: nfs_destroy_nfspagecache(); out5: nfs_fs_proc_exit(); out6: nfsiod_stop(); out7: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); out10: return err; } static void __exit exit_nfs_fs(void) { nfs_destroy_directcache(); nfs_destroy_writepagecache(); nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); unregister_pernet_subsys(&nfs_net_ops); unregister_nfs_fs(); nfs_fs_proc_exit(); nfsiod_stop(); nfs_sysfs_exit(); } /* Not quite true; I just maintain it */ MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); MODULE_DESCRIPTION("NFS client support"); MODULE_LICENSE("GPL"); module_param(enable_ino64, bool, 0644); module_init(init_nfs_fs) module_exit(exit_nfs_fs) |
| 7652 126 7525 7663 3 3200 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to generic timeout handling of requests. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/blkdev.h> #include <linux/fault-inject.h> #include "blk.h" #include "blk-mq.h" #ifdef CONFIG_FAIL_IO_TIMEOUT static DECLARE_FAULT_ATTR(fail_io_timeout); static int __init setup_fail_io_timeout(char *str) { return setup_fault_attr(&fail_io_timeout, str); } __setup("fail_io_timeout=", setup_fail_io_timeout); bool __blk_should_fake_timeout(struct request_queue *q) { return should_fail(&fail_io_timeout, 1); } EXPORT_SYMBOL_GPL(__blk_should_fake_timeout); static int __init fail_io_timeout_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout", NULL, &fail_io_timeout); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_io_timeout_debugfs); ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags); return sprintf(buf, "%d\n", set != 0); } ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); int val; if (count) { struct request_queue *q = disk->queue; char *p = (char *) buf; val = simple_strtoul(p, &p, 10); if (val) blk_queue_flag_set(QUEUE_FLAG_FAIL_IO, q); else blk_queue_flag_clear(QUEUE_FLAG_FAIL_IO, q); } return count; } #endif /* CONFIG_FAIL_IO_TIMEOUT */ /** * blk_abort_request - Request recovery for the specified command * @req: pointer to the request of interest * * This function requests that the block layer start recovery for the * request by deleting the timer and calling the q's timeout function. * LLDDs who implement their own error recovery MAY ignore the timeout * event if they generated blk_abort_request. */ void blk_abort_request(struct request *req) { /* * All we need to ensure is that timeout scan takes place * immediately and that scan sees the new timeout value. * No need for fancy synchronizations. */ WRITE_ONCE(req->deadline, jiffies); kblockd_schedule_work(&req->q->timeout_work); } EXPORT_SYMBOL_GPL(blk_abort_request); static unsigned long blk_timeout_mask __read_mostly; static int __init blk_timeout_init(void) { blk_timeout_mask = roundup_pow_of_two(HZ) - 1; return 0; } late_initcall(blk_timeout_init); /* * Just a rough estimate, we don't care about specific values for timeouts. */ static inline unsigned long blk_round_jiffies(unsigned long j) { return (j + blk_timeout_mask) + 1; } unsigned long blk_rq_timeout(unsigned long timeout) { unsigned long maxt; maxt = blk_round_jiffies(jiffies + BLK_MAX_TIMEOUT); if (time_after(timeout, maxt)) timeout = maxt; return timeout; } /** * blk_add_timer - Start timeout timer for a single request * @req: request that is about to start running. * * Notes: * Each request has its own timer, and as it is added to the queue, we * set up the timer. When the request completes, we cancel the timer. */ void blk_add_timer(struct request *req) { struct request_queue *q = req->q; unsigned long expiry; /* * Some LLDs, like scsi, peek at the timeout to prevent a * command from being retried forever. */ if (!req->timeout) req->timeout = q->rq_timeout; req->rq_flags &= ~RQF_TIMED_OUT; expiry = jiffies + req->timeout; WRITE_ONCE(req->deadline, expiry); /* * If the timer isn't already pending or this timeout is earlier * than an existing one, modify the timer. Round up to next nearest * second. */ expiry = blk_rq_timeout(blk_round_jiffies(expiry)); if (!timer_pending(&q->timeout) || time_before(expiry, q->timeout.expires)) { unsigned long diff = q->timeout.expires - expiry; /* * Due to added timer slack to group timers, the timer * will often be a little in front of what we asked for. * So apply some tolerance here too, otherwise we keep * modifying the timer because expires for value X * will be X + something. */ if (!timer_pending(&q->timeout) || (diff >= HZ / 2)) mod_timer(&q->timeout, expiry); } } |
| 173 9 173 172 174 174 174 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 | // SPDX-License-Identifier: GPL-2.0+ #include <linux/kernel.h> #include <linux/minmax.h> #include <drm/drm_blend.h> #include <drm/drm_rect.h> #include <drm/drm_fixed.h> #include <kunit/visibility.h> #include "vkms_formats.h" /** * packed_pixels_offset() - Get the offset of the block containing the pixel at coordinates x/y * * @frame_info: Buffer metadata * @x: The x coordinate of the wanted pixel in the buffer * @y: The y coordinate of the wanted pixel in the buffer * @plane_index: The index of the plane to use * @offset: The returned offset inside the buffer of the block * @rem_x: The returned X coordinate of the requested pixel in the block * @rem_y: The returned Y coordinate of the requested pixel in the block * * As some pixel formats store multiple pixels in a block (DRM_FORMAT_R* for example), some * pixels are not individually addressable. This function return 3 values: the offset of the * whole block, and the coordinate of the requested pixel inside this block. * For example, if the format is DRM_FORMAT_R1 and the requested coordinate is 13,5, the offset * will point to the byte 5*pitches + 13/8 (second byte of the 5th line), and the rem_x/rem_y * coordinates will be (13 % 8, 5 % 1) = (5, 0) * * With this function, the caller just have to extract the correct pixel from the block. */ static void packed_pixels_offset(const struct vkms_frame_info *frame_info, int x, int y, int plane_index, int *offset, int *rem_x, int *rem_y) { struct drm_framebuffer *fb = frame_info->fb; const struct drm_format_info *format = frame_info->fb->format; /* Directly using x and y to multiply pitches and format->ccp is not sufficient because * in some formats a block can represent multiple pixels. * * Dividing x and y by the block size allows to extract the correct offset of the block * containing the pixel. */ int block_x = x / drm_format_info_block_width(format, plane_index); int block_y = y / drm_format_info_block_height(format, plane_index); int block_pitch = fb->pitches[plane_index] * drm_format_info_block_height(format, plane_index); *rem_x = x % drm_format_info_block_width(format, plane_index); *rem_y = y % drm_format_info_block_height(format, plane_index); *offset = fb->offsets[plane_index] + block_y * block_pitch + block_x * format->char_per_block[plane_index]; } /** * packed_pixels_addr() - Get the pointer to the block containing the pixel at the given * coordinates * * @frame_info: Buffer metadata * @x: The x (width) coordinate inside the plane * @y: The y (height) coordinate inside the plane * @plane_index: The index of the plane * @addr: The returned pointer * @rem_x: The returned X coordinate of the requested pixel in the block * @rem_y: The returned Y coordinate of the requested pixel in the block * * Takes the information stored in the frame_info, a pair of coordinates, and returns the address * of the block containing this pixel and the pixel position inside this block. * * See @packed_pixels_offset for details about rem_x/rem_y behavior. */ static void packed_pixels_addr(const struct vkms_frame_info *frame_info, int x, int y, int plane_index, u8 **addr, int *rem_x, int *rem_y) { int offset; packed_pixels_offset(frame_info, x, y, plane_index, &offset, rem_x, rem_y); *addr = (u8 *)frame_info->map[0].vaddr + offset; } /** * get_block_step_bytes() - Common helper to compute the correct step value between each pixel block * to read in a certain direction. * * @fb: Framebuffer to iter on * @direction: Direction of the reading * @plane_index: Plane to get the step from * * As the returned count is the number of bytes between two consecutive blocks in a direction, * the caller may have to read multiple pixels before using the next one (for example, to read from * left to right in a DRM_FORMAT_R1 plane, each block contains 8 pixels, so the step must be used * only every 8 pixels). */ static int get_block_step_bytes(struct drm_framebuffer *fb, enum pixel_read_direction direction, int plane_index) { switch (direction) { case READ_LEFT_TO_RIGHT: return fb->format->char_per_block[plane_index]; case READ_RIGHT_TO_LEFT: return -fb->format->char_per_block[plane_index]; case READ_TOP_TO_BOTTOM: return (int)fb->pitches[plane_index] * drm_format_info_block_width(fb->format, plane_index); case READ_BOTTOM_TO_TOP: return -(int)fb->pitches[plane_index] * drm_format_info_block_width(fb->format, plane_index); } return 0; } /** * packed_pixels_addr_1x1() - Get the pointer to the block containing the pixel at the given * coordinates * * @frame_info: Buffer metadata * @x: The x (width) coordinate inside the plane * @y: The y (height) coordinate inside the plane * @plane_index: The index of the plane * @addr: The returned pointer * * This function can only be used with format where block_h == block_w == 1. */ static void packed_pixels_addr_1x1(const struct vkms_frame_info *frame_info, int x, int y, int plane_index, u8 **addr) { int offset, rem_x, rem_y; WARN_ONCE(drm_format_info_block_width(frame_info->fb->format, plane_index) != 1, "%s() only support formats with block_w == 1", __func__); WARN_ONCE(drm_format_info_block_height(frame_info->fb->format, plane_index) != 1, "%s() only support formats with block_h == 1", __func__); packed_pixels_offset(frame_info, x, y, plane_index, &offset, &rem_x, &rem_y); *addr = (u8 *)frame_info->map[0].vaddr + offset; } /** * get_subsampling() - Get the subsampling divisor value on a specific direction * * @format: format to extarct the subsampling from * @direction: direction of the subsampling requested */ static int get_subsampling(const struct drm_format_info *format, enum pixel_read_direction direction) { switch (direction) { case READ_BOTTOM_TO_TOP: case READ_TOP_TO_BOTTOM: return format->vsub; case READ_RIGHT_TO_LEFT: case READ_LEFT_TO_RIGHT: return format->hsub; } WARN_ONCE(true, "Invalid direction for pixel reading: %d\n", direction); return 1; } /** * get_subsampling_offset() - An offset for keeping the chroma siting consistent regardless of * x_start and y_start values * * @direction: direction of the reading to properly compute this offset * @x_start: x coordinate of the starting point of the readed line * @y_start: y coordinate of the starting point of the readed line */ static int get_subsampling_offset(enum pixel_read_direction direction, int x_start, int y_start) { switch (direction) { case READ_BOTTOM_TO_TOP: return -y_start - 1; case READ_TOP_TO_BOTTOM: return y_start; case READ_RIGHT_TO_LEFT: return -x_start - 1; case READ_LEFT_TO_RIGHT: return x_start; } WARN_ONCE(true, "Invalid direction for pixel reading: %d\n", direction); return 0; } /* * The following functions take pixel data (a, r, g, b, pixel, ...) and convert them to * &struct pixel_argb_u16 * * They are used in the `read_line`s functions to avoid duplicate work for some pixel formats. */ static struct pixel_argb_u16 argb_u16_from_u8888(u8 a, u8 r, u8 g, u8 b) { struct pixel_argb_u16 out_pixel; /* * The 257 is the "conversion ratio". This number is obtained by the * (2^16 - 1) / (2^8 - 1) division. Which, in this case, tries to get * the best color value in a pixel format with more possibilities. * A similar idea applies to others RGB color conversions. */ out_pixel.a = (u16)a * 257; out_pixel.r = (u16)r * 257; out_pixel.g = (u16)g * 257; out_pixel.b = (u16)b * 257; return out_pixel; } static struct pixel_argb_u16 argb_u16_from_u16161616(u16 a, u16 r, u16 g, u16 b) { struct pixel_argb_u16 out_pixel; out_pixel.a = a; out_pixel.r = r; out_pixel.g = g; out_pixel.b = b; return out_pixel; } static struct pixel_argb_u16 argb_u16_from_le16161616(__le16 a, __le16 r, __le16 g, __le16 b) { return argb_u16_from_u16161616(le16_to_cpu(a), le16_to_cpu(r), le16_to_cpu(g), le16_to_cpu(b)); } static struct pixel_argb_u16 argb_u16_from_RGB565(const __le16 *pixel) { struct pixel_argb_u16 out_pixel; s64 fp_rb_ratio = drm_fixp_div(drm_int2fixp(65535), drm_int2fixp(31)); s64 fp_g_ratio = drm_fixp_div(drm_int2fixp(65535), drm_int2fixp(63)); u16 rgb_565 = le16_to_cpu(*pixel); s64 fp_r = drm_int2fixp((rgb_565 >> 11) & 0x1f); s64 fp_g = drm_int2fixp((rgb_565 >> 5) & 0x3f); s64 fp_b = drm_int2fixp(rgb_565 & 0x1f); out_pixel.a = (u16)0xffff; out_pixel.r = drm_fixp2int_round(drm_fixp_mul(fp_r, fp_rb_ratio)); out_pixel.g = drm_fixp2int_round(drm_fixp_mul(fp_g, fp_g_ratio)); out_pixel.b = drm_fixp2int_round(drm_fixp_mul(fp_b, fp_rb_ratio)); return out_pixel; } static struct pixel_argb_u16 argb_u16_from_gray8(u8 gray) { return argb_u16_from_u8888(255, gray, gray, gray); } static struct pixel_argb_u16 argb_u16_from_grayu16(u16 gray) { return argb_u16_from_u16161616(0xFFFF, gray, gray, gray); } VISIBLE_IF_KUNIT struct pixel_argb_u16 argb_u16_from_yuv888(u8 y, u8 channel_1, u8 channel_2, const struct conversion_matrix *matrix) { u16 r, g, b; s64 fp_y, fp_channel_1, fp_channel_2; s64 fp_r, fp_g, fp_b; fp_y = drm_int2fixp(((int)y - matrix->y_offset) * 257); fp_channel_1 = drm_int2fixp(((int)channel_1 - 128) * 257); fp_channel_2 = drm_int2fixp(((int)channel_2 - 128) * 257); fp_r = drm_fixp_mul(matrix->matrix[0][0], fp_y) + drm_fixp_mul(matrix->matrix[0][1], fp_channel_1) + drm_fixp_mul(matrix->matrix[0][2], fp_channel_2); fp_g = drm_fixp_mul(matrix->matrix[1][0], fp_y) + drm_fixp_mul(matrix->matrix[1][1], fp_channel_1) + drm_fixp_mul(matrix->matrix[1][2], fp_channel_2); fp_b = drm_fixp_mul(matrix->matrix[2][0], fp_y) + drm_fixp_mul(matrix->matrix[2][1], fp_channel_1) + drm_fixp_mul(matrix->matrix[2][2], fp_ch |