| 63 35 34 34 34 34 10 34 34 34 34 34 34 34 34 34 34 34 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * MLO link handling * * Copyright (C) 2022-2025 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "key.h" #include "debugfs_netdev.h" static void ieee80211_update_apvlan_links(struct ieee80211_sub_if_data *sdata) { struct ieee80211_sub_if_data *vlan; struct ieee80211_link_data *link; u16 ap_bss_links = sdata->vif.valid_links; u16 new_links, vlan_links; unsigned long add; list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { int link_id; if (!vlan) continue; /* No support for 4addr with MLO yet */ if (vlan->wdev.use_4addr) return; vlan_links = vlan->vif.valid_links; new_links = ap_bss_links; add = new_links & ~vlan_links; if (!add) continue; ieee80211_vif_set_links(vlan, add, 0); for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { link = sdata_dereference(vlan->link[link_id], vlan); ieee80211_link_vlan_copy_chanctx(link); } } } void ieee80211_apvlan_link_setup(struct ieee80211_sub_if_data *sdata) { struct ieee80211_sub_if_data *ap_bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); u16 new_links = ap_bss->vif.valid_links; unsigned long add; int link_id; if (!ap_bss->vif.valid_links) return; add = new_links; for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { sdata->wdev.valid_links |= BIT(link_id); ether_addr_copy(sdata->wdev.links[link_id].addr, ap_bss->wdev.links[link_id].addr); } ieee80211_vif_set_links(sdata, new_links, 0); } void ieee80211_apvlan_link_clear(struct ieee80211_sub_if_data *sdata) { if (!sdata->wdev.valid_links) return; sdata->wdev.valid_links = 0; ieee80211_vif_clear_links(sdata); } void ieee80211_link_setup(struct ieee80211_link_data *link) { if (link->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_mgd_setup_link(link); } void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, int link_id, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf) { bool deflink = link_id < 0; if (link_id < 0) link_id = 0; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { struct ieee80211_sub_if_data *ap_bss; struct ieee80211_bss_conf *ap_bss_conf; ap_bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); ap_bss_conf = sdata_dereference(ap_bss->vif.link_conf[link_id], ap_bss); memcpy(link_conf, ap_bss_conf, sizeof(*link_conf)); } link->sdata = sdata; link->link_id = link_id; link->conf = link_conf; link_conf->link_id = link_id; link_conf->vif = &sdata->vif; link->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; link->user_power_level = sdata->local->user_power_level; link_conf->txpower = INT_MIN; wiphy_work_init(&link->csa.finalize_work, ieee80211_csa_finalize_work); wiphy_work_init(&link->color_change_finalize_work, ieee80211_color_change_finalize_work); wiphy_delayed_work_init(&link->color_collision_detect_work, ieee80211_color_collision_detection_work); INIT_LIST_HEAD(&link->assigned_chanctx_list); INIT_LIST_HEAD(&link->reserved_chanctx_list); wiphy_delayed_work_init(&link->dfs_cac_timer_work, ieee80211_dfs_cac_timer_work); if (!deflink) { switch (sdata->vif.type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: ether_addr_copy(link_conf->addr, sdata->wdev.links[link_id].addr); link_conf->bssid = link_conf->addr; WARN_ON(!(sdata->wdev.valid_links & BIT(link_id))); break; case NL80211_IFTYPE_STATION: /* station sets the bssid in ieee80211_mgd_setup_link */ break; default: WARN_ON(1); } ieee80211_link_debugfs_add(link); } rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf); rcu_assign_pointer(sdata->link[link_id], link); } void ieee80211_link_stop(struct ieee80211_link_data *link) { if (link->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_mgd_stop_link(link); wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, &link->color_collision_detect_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->color_change_finalize_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->csa.finalize_work); if (link->sdata->wdev.links[link->link_id].cac_started) { wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, &link->dfs_cac_timer_work); cfg80211_cac_event(link->sdata->dev, &link->conf->chanreq.oper, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL, link->link_id); } ieee80211_link_release_channel(link); } struct link_container { struct ieee80211_link_data data; struct ieee80211_bss_conf conf; }; static void ieee80211_tear_down_links(struct ieee80211_sub_if_data *sdata, struct link_container **links, u16 mask) { struct ieee80211_link_data *link; LIST_HEAD(keys); unsigned int link_id; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { if (!(mask & BIT(link_id))) continue; link = &links[link_id]->data; if (link_id == 0 && !link) link = &sdata->deflink; if (WARN_ON(!link)) continue; ieee80211_remove_link_keys(link, &keys); ieee80211_link_debugfs_remove(link); ieee80211_link_stop(link); } synchronize_rcu(); ieee80211_free_key_list(sdata->local, &keys); } static void ieee80211_free_links(struct ieee80211_sub_if_data *sdata, struct link_container **links) { unsigned int link_id; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) kfree(links[link_id]); } static int ieee80211_check_dup_link_addrs(struct ieee80211_sub_if_data *sdata) { unsigned int i, j; for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { struct ieee80211_link_data *link1; link1 = sdata_dereference(sdata->link[i], sdata); if (!link1) continue; for (j = i + 1; j < IEEE80211_MLD_MAX_NUM_LINKS; j++) { struct ieee80211_link_data *link2; link2 = sdata_dereference(sdata->link[j], sdata); if (!link2) continue; if (ether_addr_equal(link1->conf->addr, link2->conf->addr)) return -EALREADY; } } return 0; } static void ieee80211_set_vif_links_bitmaps(struct ieee80211_sub_if_data *sdata, u16 valid_links, u16 dormant_links) { sdata->vif.valid_links = valid_links; sdata->vif.dormant_links = dormant_links; if (!valid_links || WARN((~valid_links & dormant_links) || !(valid_links & ~dormant_links), "Invalid links: valid=0x%x, dormant=0x%x", valid_links, dormant_links)) { sdata->vif.active_links = 0; sdata->vif.dormant_links = 0; return; } switch (sdata->vif.type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* in an AP all links are always active */ sdata->vif.active_links = valid_links; /* AP links are not expected to be disabled */ WARN_ON(dormant_links); break; case NL80211_IFTYPE_STATION: if (sdata->vif.active_links) break; sdata->vif.active_links = valid_links & ~dormant_links; WARN_ON(hweight16(sdata->vif.active_links) > 1); break; default: WARN_ON(1); } } static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata, struct link_container **to_free, u16 new_links, u16 dormant_links) { u16 old_links = sdata->vif.valid_links; u16 old_active = sdata->vif.active_links; unsigned long add = new_links & ~old_links; unsigned long rem = old_links & ~new_links; unsigned int link_id; int ret; struct link_container *links[IEEE80211_MLD_MAX_NUM_LINKS] = {}, *link; struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]; struct ieee80211_link_data *old_data[IEEE80211_MLD_MAX_NUM_LINKS]; bool use_deflink = old_links == 0; /* set for error case */ lockdep_assert_wiphy(sdata->local->hw.wiphy); memset(to_free, 0, sizeof(links)); if (old_links == new_links && dormant_links == sdata->vif.dormant_links) return 0; /* if there were no old links, need to clear the pointers to deflink */ if (!old_links) rem |= BIT(0); /* allocate new link structures first */ for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; goto free; } links[link_id] = link; } /* keep track of the old pointers for the driver */ BUILD_BUG_ON(sizeof(old) != sizeof(sdata->vif.link_conf)); memcpy(old, sdata->vif.link_conf, sizeof(old)); /* and for us in error cases */ BUILD_BUG_ON(sizeof(old_data) != sizeof(sdata->link)); memcpy(old_data, sdata->link, sizeof(old_data)); /* grab old links to free later */ for_each_set_bit(link_id, &rem, IEEE80211_MLD_MAX_NUM_LINKS) { if (rcu_access_pointer(sdata->link[link_id]) != &sdata->deflink) { /* * we must have allocated the data through this path so * we know we can free both at the same time */ to_free[link_id] = container_of(rcu_access_pointer(sdata->link[link_id]), typeof(*links[link_id]), data); } RCU_INIT_POINTER(sdata->link[link_id], NULL); RCU_INIT_POINTER(sdata->vif.link_conf[link_id], NULL); } if (!old_links) ieee80211_debugfs_recreate_netdev(sdata, true); /* link them into data structures */ for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { WARN_ON(!use_deflink && rcu_access_pointer(sdata->link[link_id]) == &sdata->deflink); link = links[link_id]; ieee80211_link_init(sdata, link_id, &link->data, &link->conf); ieee80211_link_setup(&link->data); } if (new_links == 0) ieee80211_link_init(sdata, -1, &sdata->deflink, &sdata->vif.bss_conf); ret = ieee80211_check_dup_link_addrs(sdata); if (!ret) { /* for keys we will not be able to undo this */ ieee80211_tear_down_links(sdata, to_free, rem); ieee80211_set_vif_links_bitmaps(sdata, new_links, dormant_links); /* tell the driver */ if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) ret = drv_change_vif_links(sdata->local, sdata, old_links & old_active, new_links & sdata->vif.active_links, old); if (!new_links) ieee80211_debugfs_recreate_netdev(sdata, false); if (sdata->vif.type == NL80211_IFTYPE_AP) ieee80211_update_apvlan_links(sdata); } /* * Ignore errors if we are only removing links as removal should * always succeed */ if (!new_links) ret = 0; if (ret) { /* restore config */ memcpy(sdata->link, old_data, sizeof(old_data)); memcpy(sdata->vif.link_conf, old, sizeof(old)); ieee80211_set_vif_links_bitmaps(sdata, old_links, dormant_links); /* and free (only) the newly allocated links */ memset(to_free, 0, sizeof(links)); goto free; } /* use deflink/bss_conf again if and only if there are no more links */ use_deflink = new_links == 0; goto deinit; free: /* if we failed during allocation, only free all */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { kfree(links[link_id]); links[link_id] = NULL; } deinit: if (use_deflink) ieee80211_link_init(sdata, -1, &sdata->deflink, &sdata->vif.bss_conf); return ret; } int ieee80211_vif_set_links(struct ieee80211_sub_if_data *sdata, u16 new_links, u16 dormant_links) { struct link_container *links[IEEE80211_MLD_MAX_NUM_LINKS]; int ret; ret = ieee80211_vif_update_links(sdata, links, new_links, dormant_links); ieee80211_free_links(sdata, links); return ret; } static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, u16 active_links) { struct ieee80211_bss_conf *link_confs[IEEE80211_MLD_MAX_NUM_LINKS]; struct ieee80211_local *local = sdata->local; u16 old_active = sdata->vif.active_links; unsigned long rem = old_active & ~active_links; unsigned long add = active_links & ~old_active; struct sta_info *sta; unsigned int link_id; int ret, i; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EINVAL; if (active_links & ~ieee80211_vif_usable_links(&sdata->vif)) return -EINVAL; /* nothing to do */ if (old_active == active_links) return 0; for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) link_confs[i] = sdata_dereference(sdata->vif.link_conf[i], sdata); if (add) { sdata->vif.active_links |= active_links; ret = drv_change_vif_links(local, sdata, old_active, sdata->vif.active_links, link_confs); if (ret) { sdata->vif.active_links = old_active; return ret; } } for_each_set_bit(link_id, &rem, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_teardown_tdls_peers(link); __ieee80211_link_release_channel(link, true); /* * If CSA is (still) active while the link is deactivated, * just schedule the channel switch work for the time we * had previously calculated, and we'll take the process * from there. */ if (link->conf->csa_active) wiphy_hrtimer_work_queue(local->hw.wiphy, &link->u.mgd.csa.switch_work, link->u.mgd.csa.time - ktime_get_boottime()); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); /* * This call really should not fail. Unfortunately, it appears * that this may happen occasionally with some drivers. Should * it happen, we are stuck in a bad place as going backwards is * not really feasible. * * So lets just tell link_use_channel that it must not fail to * assign the channel context (from mac80211's perspective) and * assume the driver is going to trigger a recovery flow if it * had a failure. * That really is not great nor guaranteed to work. But at least * the internal mac80211 state remains consistent and there is * a chance that we can recover. */ ret = _ieee80211_link_use_channel(link, &link->conf->chanreq, IEEE80211_CHANCTX_SHARED, true); WARN_ON_ONCE(ret); /* * inform about the link info changed parameters after all * stations are also added */ } list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; /* this is very temporary, but do it anyway */ __ieee80211_sta_recalc_aggregates(sta, old_active | active_links); ret = drv_change_sta_links(local, sdata, &sta->sta, old_active, old_active | active_links); WARN_ON_ONCE(ret); } ret = ieee80211_key_switch_links(sdata, rem, add); WARN_ON_ONCE(ret); list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; __ieee80211_sta_recalc_aggregates(sta, active_links); ret = drv_change_sta_links(local, sdata, &sta->sta, old_active | active_links, active_links); WARN_ON_ONCE(ret); /* * Do it again, just in case - the driver might very * well have called ieee80211_sta_recalc_aggregates() * from there when filling in the new links, which * would set it wrong since the vif's active links are * not switched yet... */ __ieee80211_sta_recalc_aggregates(sta, active_links); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_mgd_set_link_qos_params(link); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_ERP_PREAMBLE | BSS_CHANGED_ERP_SLOT | BSS_CHANGED_HT | BSS_CHANGED_BASIC_RATES | BSS_CHANGED_BSSID | BSS_CHANGED_CQM | BSS_CHANGED_QOS | BSS_CHANGED_TXPOWER | BSS_CHANGED_BANDWIDTH | BSS_CHANGED_TWT | BSS_CHANGED_HE_OBSS_PD | BSS_CHANGED_HE_BSS_COLOR); } old_active = sdata->vif.active_links; sdata->vif.active_links = active_links; if (rem) { ret = drv_change_vif_links(local, sdata, old_active, active_links, link_confs); WARN_ON_ONCE(ret); } return 0; } int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; u16 old_active; int ret; lockdep_assert_wiphy(local->hw.wiphy); if (WARN_ON(!active_links)) return -EINVAL; old_active = sdata->vif.active_links; if (old_active == active_links) return 0; if (!drv_can_activate_links(local, sdata, active_links)) return -EINVAL; if (old_active & active_links) { /* * if there's at least one link that stays active across * the change then switch to it (to those) first, and * then enable the additional links */ ret = _ieee80211_set_active_links(sdata, old_active & active_links); if (!ret) ret = _ieee80211_set_active_links(sdata, active_links); } else { /* otherwise switch directly */ ret = _ieee80211_set_active_links(sdata, active_links); } return ret; } EXPORT_SYMBOL_GPL(ieee80211_set_active_links); void ieee80211_set_active_links_async(struct ieee80211_vif *vif, u16 active_links) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (WARN_ON(!active_links)) return; if (!ieee80211_sdata_running(sdata)) return; if (sdata->vif.type != NL80211_IFTYPE_STATION) return; if (active_links & ~ieee80211_vif_usable_links(&sdata->vif)) return; /* nothing to do */ if (sdata->vif.active_links == active_links) return; sdata->desired_active_links = active_links; wiphy_work_queue(sdata->local->hw.wiphy, &sdata->activate_links_work); } EXPORT_SYMBOL_GPL(ieee80211_set_active_links_async); |
| 2 2 2 2 2 2 2 2 2 2 2 2 1310 9 7 2 7 1 6 6 1 5 1 5 5 5 4 4 1 1 10 9 10 10 10 5 10 10 10 14 14 8 7 8 14 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Frame handler other utility functions for HSR and PRP. */ #include "hsr_slave.h" #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_forward.h" #include "hsr_framereg.h" bool hsr_invalid_dan_ingress_frame(__be16 protocol) { return (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)); } static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; struct hsr_priv *hsr; __be16 protocol; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); return RX_HANDLER_PASS; } port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; hsr = port->hsr; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ kfree_skb(skb); goto finish_consume; } /* For HSR, only tagged frames are expected (unless the device offloads * HSR tag removal), but for PRP there could be non tagged frames as * well from Single attached nodes (SANs). */ protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || protocol == htons(ETH_P_HSR)) { if (!pskb_may_pull(skb, ETH_HLEN + HSR_HLEN)) { kfree_skb(skb); goto finish_consume; } skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); } skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a * sequence number and require synchronisation vs other sender. */ if (port->type == HSR_PT_INTERLINK) { spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); } else { hsr_forward_skb(skb, port); } finish_consume: return RX_HANDLER_CONSUMED; finish_pass: return RX_HANDLER_PASS; } bool hsr_port_exists(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; } static int hsr_check_dev_ok(struct net_device *dev, struct netlink_ext_ack *extack) { /* Don't allow HSR on non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) { NL_SET_ERR_MSG_MOD(extack, "Cannot use loopback or non-ethernet device as HSR slave."); return -EINVAL; } /* Don't allow enslaving hsr devices */ if (is_hsr_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Cannot create trees of HSR devices."); return -EINVAL; } if (hsr_port_exists(dev)) { NL_SET_ERR_MSG_MOD(extack, "This device is already a HSR slave."); return -EINVAL; } if (is_vlan_dev(dev)) { NL_SET_ERR_MSG_MOD(extack, "HSR on top of VLAN is not yet supported in this driver."); return -EINVAL; } if (dev->priv_flags & IFF_DONT_BRIDGE) { NL_SET_ERR_MSG_MOD(extack, "This device does not support bridging."); return -EOPNOTSUPP; } /* HSR over bonded devices has not been tested, but I'm not sure it * won't work... */ return 0; } /* Setup device to be added to the HSR bridge. */ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, struct hsr_port *port, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; struct net_device *hsr_dev; struct hsr_port *master; int res; /* Don't use promiscuous mode for offload since L2 frame forward * happens at the offloaded hardware. */ if (!port->hsr->fwd_offloaded) { res = dev_set_promiscuity(dev, 1); if (res) return res; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr_dev = master->dev; lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_BROADCAST; lag_upper_info.hash_type = NETDEV_LAG_HASH_UNKNOWN; res = netdev_master_upper_dev_link(dev, hsr_dev, NULL, &lag_upper_info, extack); if (res) goto fail_upper_dev_link; res = netdev_rx_handler_register(dev, hsr_handle_frame, port); if (res) goto fail_rx_handler; dev_disable_lro(dev); return 0; fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: if (!port->hsr->fwd_offloaded) dev_set_promiscuity(dev, -1); return res; } int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type type, struct netlink_ext_ack *extack) { struct hsr_port *port, *master; int res; if (type != HSR_PT_MASTER) { res = hsr_check_dev_ok(dev, extack); if (res) return res; } port = hsr_port_get_hsr(hsr, type); if (port) return -EBUSY; /* This port already exists */ port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; port->hsr = hsr; port->dev = dev; port->type = type; ether_addr_copy(port->original_macaddress, dev->dev_addr); if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } list_add_tail_rcu(&port->port_list, &hsr->ports); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); return 0; fail_dev_setup: kfree(port); return res; } void hsr_del_port(struct hsr_port *port) { struct hsr_priv *hsr; struct hsr_port *master; hsr = port->hsr; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); list_del_rcu(&port->port_list); if (port != master) { netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); if (!port->hsr->fwd_offloaded) dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); eth_hw_addr_set(port->dev, port->original_macaddress); } kfree_rcu(port, rcu); } |
| 157 155 156 135 8 157 156 69 69 22 68 13 13 67 67 4 67 2 63 67 61 57 57 13 16 16 46 41 51 56 56 10 10 8 8 2 2 8 3 3 5 8 8 160 160 32 64 64 56 56 11 2 9 57 8 57 8 57 24 57 57 3 54 6 72 72 49 45 45 2 45 43 72 72 72 54 54 72 64 72 71 54 60 10 71 71 74 2 72 72 158 158 74 32 130 8 130 156 87 86 1 87 85 86 11 87 1 86 87 156 156 1 156 4 143 141 141 5 141 140 87 154 154 156 155 156 156 156 12 84 84 86 85 84 86 86 70 59 58 86 154 155 7 7 7 6 1 6 6 3 1 6 6 6 6 7 7 7 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/dqblk_v2.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/quotaops.h> #include <asm/byteorder.h> #include "quota_tree.h" MODULE_AUTHOR("Jan Kara"); MODULE_DESCRIPTION("Quota trie support"); MODULE_LICENSE("GPL"); /* * Maximum quota tree depth we support. Only to limit recursion when working * with the tree. */ #define MAX_QTREE_DEPTH 6 #define __QUOTA_QT_PARANOIA static int __get_index(struct qtree_mem_dqinfo *info, qid_t id, int depth) { unsigned int epb = info->dqi_usable_bs >> 2; depth = info->dqi_qtree_depth - depth - 1; while (depth--) id /= epb; return id % epb; } static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth) { qid_t id = from_kqid(&init_user_ns, qid); return __get_index(info, id, depth); } /* Number of entries in one blocks */ static int qtree_dqstr_in_blk(struct qtree_mem_dqinfo *info) { return (info->dqi_usable_bs - sizeof(struct qt_disk_dqdbheader)) / info->dqi_entry_size; } static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) { struct super_block *sb = info->dqi_sb; memset(buf, 0, info->dqi_usable_bs); return sb->s_op->quota_read(sb, info->dqi_type, buf, info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); } static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) { struct super_block *sb = info->dqi_sb; ssize_t ret; ret = sb->s_op->quota_write(sb, info->dqi_type, buf, info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits); if (ret != info->dqi_usable_bs) { quota_error(sb, "dquota write failed"); if (ret >= 0) ret = -EIO; } return ret; } static inline int do_check_range(struct super_block *sb, const char *val_name, uint val, uint min_val, uint max_val) { if (val < min_val || val > max_val) { quota_error(sb, "Getting %s %u out of range %u-%u", val_name, val, min_val, max_val); return -EUCLEAN; } return 0; } static int check_dquot_block_header(struct qtree_mem_dqinfo *info, struct qt_disk_dqdbheader *dh) { int err = 0; err = do_check_range(info->dqi_sb, "dqdh_next_free", le32_to_cpu(dh->dqdh_next_free), 0, info->dqi_blocks - 1); if (err) return err; err = do_check_range(info->dqi_sb, "dqdh_prev_free", le32_to_cpu(dh->dqdh_prev_free), 0, info->dqi_blocks - 1); if (err) return err; err = do_check_range(info->dqi_sb, "dqdh_entries", le16_to_cpu(dh->dqdh_entries), 0, qtree_dqstr_in_blk(info)); return err; } /* Remove empty block from list and return it */ static int get_free_dqblk(struct qtree_mem_dqinfo *info) { char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; int ret, blk; if (!buf) return -ENOMEM; if (info->dqi_free_blk) { blk = info->dqi_free_blk; ret = read_blk(info, blk, buf); if (ret < 0) goto out_buf; ret = check_dquot_block_header(info, dh); if (ret) goto out_buf; info->dqi_free_blk = le32_to_cpu(dh->dqdh_next_free); } else { memset(buf, 0, info->dqi_usable_bs); /* Assure block allocation... */ ret = write_blk(info, info->dqi_blocks, buf); if (ret < 0) goto out_buf; blk = info->dqi_blocks++; } mark_info_dirty(info->dqi_sb, info->dqi_type); ret = blk; out_buf: kfree(buf); return ret; } /* Insert empty block to the list */ static int put_free_dqblk(struct qtree_mem_dqinfo *info, char *buf, uint blk) { struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; int err; dh->dqdh_next_free = cpu_to_le32(info->dqi_free_blk); dh->dqdh_prev_free = cpu_to_le32(0); dh->dqdh_entries = cpu_to_le16(0); err = write_blk(info, blk, buf); if (err < 0) return err; info->dqi_free_blk = blk; mark_info_dirty(info->dqi_sb, info->dqi_type); return 0; } /* Remove given block from the list of blocks with free entries */ static int remove_free_dqentry(struct qtree_mem_dqinfo *info, char *buf, uint blk) { char *tmpbuf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; uint nextblk = le32_to_cpu(dh->dqdh_next_free); uint prevblk = le32_to_cpu(dh->dqdh_prev_free); int err; if (!tmpbuf) return -ENOMEM; if (nextblk) { err = read_blk(info, nextblk, tmpbuf); if (err < 0) goto out_buf; ((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_prev_free = dh->dqdh_prev_free; err = write_blk(info, nextblk, tmpbuf); if (err < 0) goto out_buf; } if (prevblk) { err = read_blk(info, prevblk, tmpbuf); if (err < 0) goto out_buf; ((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_next_free = dh->dqdh_next_free; err = write_blk(info, prevblk, tmpbuf); if (err < 0) goto out_buf; } else { info->dqi_free_entry = nextblk; mark_info_dirty(info->dqi_sb, info->dqi_type); } kfree(tmpbuf); dh->dqdh_next_free = dh->dqdh_prev_free = cpu_to_le32(0); /* No matter whether write succeeds block is out of list */ if (write_blk(info, blk, buf) < 0) quota_error(info->dqi_sb, "Can't write block (%u) " "with free entries", blk); return 0; out_buf: kfree(tmpbuf); return err; } /* Insert given block to the beginning of list with free entries */ static int insert_free_dqentry(struct qtree_mem_dqinfo *info, char *buf, uint blk) { char *tmpbuf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; int err; if (!tmpbuf) return -ENOMEM; dh->dqdh_next_free = cpu_to_le32(info->dqi_free_entry); dh->dqdh_prev_free = cpu_to_le32(0); err = write_blk(info, blk, buf); if (err < 0) goto out_buf; if (info->dqi_free_entry) { err = read_blk(info, info->dqi_free_entry, tmpbuf); if (err < 0) goto out_buf; ((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_prev_free = cpu_to_le32(blk); err = write_blk(info, info->dqi_free_entry, tmpbuf); if (err < 0) goto out_buf; } kfree(tmpbuf); info->dqi_free_entry = blk; mark_info_dirty(info->dqi_sb, info->dqi_type); return 0; out_buf: kfree(tmpbuf); return err; } /* Is the entry in the block free? */ int qtree_entry_unused(struct qtree_mem_dqinfo *info, char *disk) { int i; for (i = 0; i < info->dqi_entry_size; i++) if (disk[i]) return 0; return 1; } EXPORT_SYMBOL(qtree_entry_unused); /* Find space for dquot */ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, int *err) { uint blk, i; struct qt_disk_dqdbheader *dh; char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); char *ddquot; *err = 0; if (!buf) { *err = -ENOMEM; return 0; } dh = (struct qt_disk_dqdbheader *)buf; if (info->dqi_free_entry) { blk = info->dqi_free_entry; *err = read_blk(info, blk, buf); if (*err < 0) goto out_buf; *err = check_dquot_block_header(info, dh); if (*err) goto out_buf; } else { blk = get_free_dqblk(info); if ((int)blk < 0) { *err = blk; kfree(buf); return 0; } memset(buf, 0, info->dqi_usable_bs); /* This is enough as the block is already zeroed and the entry * list is empty... */ info->dqi_free_entry = blk; mark_info_dirty(dquot->dq_sb, dquot->dq_id.type); } /* Block will be full? */ if (le16_to_cpu(dh->dqdh_entries) + 1 >= qtree_dqstr_in_blk(info)) { *err = remove_free_dqentry(info, buf, blk); if (*err < 0) { quota_error(dquot->dq_sb, "Can't remove block (%u) " "from entry free list", blk); goto out_buf; } } le16_add_cpu(&dh->dqdh_entries, 1); /* Find free structure in block */ ddquot = buf + sizeof(struct qt_disk_dqdbheader); for (i = 0; i < qtree_dqstr_in_blk(info); i++) { if (qtree_entry_unused(info, ddquot)) break; ddquot += info->dqi_entry_size; } #ifdef __QUOTA_QT_PARANOIA if (i == qtree_dqstr_in_blk(info)) { quota_error(dquot->dq_sb, "Data block full but it shouldn't"); *err = -EIO; goto out_buf; } #endif *err = write_blk(info, blk, buf); if (*err < 0) { quota_error(dquot->dq_sb, "Can't write quota data block %u", blk); goto out_buf; } dquot->dq_off = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; kfree(buf); return blk; out_buf: kfree(buf); return 0; } /* Insert reference to structure into the trie */ static int do_insert_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint *blks, int depth) { char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); int ret = 0, newson = 0, newact = 0; __le32 *ref; uint newblk; int i; if (!buf) return -ENOMEM; if (!blks[depth]) { ret = get_free_dqblk(info); if (ret < 0) goto out_buf; for (i = 0; i < depth; i++) if (ret == blks[i]) { quota_error(dquot->dq_sb, "Free block already used in tree: block %u", ret); ret = -EIO; goto out_buf; } blks[depth] = ret; memset(buf, 0, info->dqi_usable_bs); newact = 1; } else { ret = read_blk(info, blks[depth], buf); if (ret < 0) { quota_error(dquot->dq_sb, "Can't read tree quota " "block %u", blks[depth]); goto out_buf; } } ref = (__le32 *)buf; newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); ret = do_check_range(dquot->dq_sb, "block", newblk, 0, info->dqi_blocks - 1); if (ret) goto out_buf; if (!newblk) { newson = 1; } else { for (i = 0; i <= depth; i++) if (newblk == blks[i]) { quota_error(dquot->dq_sb, "Cycle in quota tree detected: block %u index %u", blks[depth], get_index(info, dquot->dq_id, depth)); ret = -EIO; goto out_buf; } } blks[depth + 1] = newblk; if (depth == info->dqi_qtree_depth - 1) { #ifdef __QUOTA_QT_PARANOIA if (newblk) { quota_error(dquot->dq_sb, "Inserting already present " "quota entry (block %u)", le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)])); ret = -EIO; goto out_buf; } #endif blks[depth + 1] = find_free_dqentry(info, dquot, &ret); } else { ret = do_insert_tree(info, dquot, blks, depth + 1); } if (newson && ret >= 0) { ref[get_index(info, dquot->dq_id, depth)] = cpu_to_le32(blks[depth + 1]); ret = write_blk(info, blks[depth], buf); } else if (newact && ret < 0) { put_free_dqblk(info, buf, blks[depth]); } out_buf: kfree(buf); return ret; } /* Wrapper for inserting quota structure into tree */ static inline int dq_insert_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot) { uint blks[MAX_QTREE_DEPTH] = { QT_TREEOFF }; #ifdef __QUOTA_QT_PARANOIA if (info->dqi_blocks <= QT_TREEOFF) { quota_error(dquot->dq_sb, "Quota tree root isn't allocated!"); return -EIO; } #endif if (info->dqi_qtree_depth >= MAX_QTREE_DEPTH) { quota_error(dquot->dq_sb, "Quota tree depth too big!"); return -EIO; } return do_insert_tree(info, dquot, blks, 0); } /* * We don't have to be afraid of deadlocks as we never have quotas on quota * files... */ int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) { int type = dquot->dq_id.type; struct super_block *sb = dquot->dq_sb; ssize_t ret; char *ddquot = kmalloc(info->dqi_entry_size, GFP_KERNEL); if (!ddquot) return -ENOMEM; /* dq_off is guarded by dqio_sem */ if (!dquot->dq_off) { ret = dq_insert_tree(info, dquot); if (ret < 0) { quota_error(sb, "Error %zd occurred while creating " "quota", ret); kfree(ddquot); return ret; } } spin_lock(&dquot->dq_dqb_lock); info->dqi_ops->mem2disk_dqblk(ddquot, dquot); spin_unlock(&dquot->dq_dqb_lock); ret = sb->s_op->quota_write(sb, type, ddquot, info->dqi_entry_size, dquot->dq_off); if (ret != info->dqi_entry_size) { quota_error(sb, "dquota write failed"); if (ret >= 0) ret = -ENOSPC; } else { ret = 0; } dqstats_inc(DQST_WRITES); kfree(ddquot); return ret; } EXPORT_SYMBOL(qtree_write_dquot); /* Free dquot entry in data block */ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint blk) { struct qt_disk_dqdbheader *dh; char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); int ret = 0; if (!buf) return -ENOMEM; if (dquot->dq_off >> info->dqi_blocksize_bits != blk) { quota_error(dquot->dq_sb, "Quota structure has offset to " "other block (%u) than it should (%u)", blk, (uint)(dquot->dq_off >> info->dqi_blocksize_bits)); ret = -EIO; goto out_buf; } ret = read_blk(info, blk, buf); if (ret < 0) { quota_error(dquot->dq_sb, "Can't read quota data block %u", blk); goto out_buf; } dh = (struct qt_disk_dqdbheader *)buf; ret = check_dquot_block_header(info, dh); if (ret) goto out_buf; le16_add_cpu(&dh->dqdh_entries, -1); if (!le16_to_cpu(dh->dqdh_entries)) { /* Block got free? */ ret = remove_free_dqentry(info, buf, blk); if (ret >= 0) ret = put_free_dqblk(info, buf, blk); if (ret < 0) { quota_error(dquot->dq_sb, "Can't move quota data block " "(%u) to free list", blk); goto out_buf; } } else { memset(buf + (dquot->dq_off & ((1 << info->dqi_blocksize_bits) - 1)), 0, info->dqi_entry_size); if (le16_to_cpu(dh->dqdh_entries) == qtree_dqstr_in_blk(info) - 1) { /* Insert will write block itself */ ret = insert_free_dqentry(info, buf, blk); if (ret < 0) { quota_error(dquot->dq_sb, "Can't insert quota " "data block (%u) to free entry list", blk); goto out_buf; } } else { ret = write_blk(info, blk, buf); if (ret < 0) { quota_error(dquot->dq_sb, "Can't write quota " "data block %u", blk); goto out_buf; } } } dquot->dq_off = 0; /* Quota is now unattached */ out_buf: kfree(buf); return ret; } /* Remove reference to dquot from tree */ static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint *blks, int depth) { char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); int ret = 0; uint newblk; __le32 *ref = (__le32 *)buf; int i; if (!buf) return -ENOMEM; ret = read_blk(info, blks[depth], buf); if (ret < 0) { quota_error(dquot->dq_sb, "Can't read quota data block %u", blks[depth]); goto out_buf; } newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); ret = do_check_range(dquot->dq_sb, "block", newblk, QT_TREEOFF, info->dqi_blocks - 1); if (ret) goto out_buf; for (i = 0; i <= depth; i++) if (newblk == blks[i]) { quota_error(dquot->dq_sb, "Cycle in quota tree detected: block %u index %u", blks[depth], get_index(info, dquot->dq_id, depth)); ret = -EIO; goto out_buf; } if (depth == info->dqi_qtree_depth - 1) { ret = free_dqentry(info, dquot, newblk); blks[depth + 1] = 0; } else { blks[depth + 1] = newblk; ret = remove_tree(info, dquot, blks, depth + 1); } if (ret >= 0 && !blks[depth + 1]) { ref[get_index(info, dquot->dq_id, depth)] = cpu_to_le32(0); /* Block got empty? */ for (i = 0; i < (info->dqi_usable_bs >> 2) && !ref[i]; i++) ; /* Don't put the root block into the free block list */ if (i == (info->dqi_usable_bs >> 2) && blks[depth] != QT_TREEOFF) { put_free_dqblk(info, buf, blks[depth]); blks[depth] = 0; } else { ret = write_blk(info, blks[depth], buf); if (ret < 0) quota_error(dquot->dq_sb, "Can't write quota tree block %u", blks[depth]); } } out_buf: kfree(buf); return ret; } /* Delete dquot from tree */ int qtree_delete_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) { uint blks[MAX_QTREE_DEPTH] = { QT_TREEOFF }; if (!dquot->dq_off) /* Even not allocated? */ return 0; if (info->dqi_qtree_depth >= MAX_QTREE_DEPTH) { quota_error(dquot->dq_sb, "Quota tree depth too big!"); return -EIO; } return remove_tree(info, dquot, blks, 0); } EXPORT_SYMBOL(qtree_delete_dquot); /* Find entry in block */ static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint blk) { char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); loff_t ret = 0; int i; char *ddquot; if (!buf) return -ENOMEM; ret = read_blk(info, blk, buf); if (ret < 0) { quota_error(dquot->dq_sb, "Can't read quota tree " "block %u", blk); goto out_buf; } ddquot = buf + sizeof(struct qt_disk_dqdbheader); for (i = 0; i < qtree_dqstr_in_blk(info); i++) { if (info->dqi_ops->is_id(ddquot, dquot)) break; ddquot += info->dqi_entry_size; } if (i == qtree_dqstr_in_blk(info)) { quota_error(dquot->dq_sb, "Quota for id %u referenced but not present", from_kqid(&init_user_ns, dquot->dq_id)); ret = -EIO; goto out_buf; } else { ret = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct qt_disk_dqdbheader) + i * info->dqi_entry_size; } out_buf: kfree(buf); return ret; } /* Find entry for given id in the tree */ static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint *blks, int depth) { char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); loff_t ret = 0; __le32 *ref = (__le32 *)buf; uint blk; int i; if (!buf) return -ENOMEM; ret = read_blk(info, blks[depth], buf); if (ret < 0) { quota_error(dquot->dq_sb, "Can't read quota tree block %u", blks[depth]); goto out_buf; } ret = 0; blk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]); if (!blk) /* No reference? */ goto out_buf; ret = do_check_range(dquot->dq_sb, "block", blk, QT_TREEOFF, info->dqi_blocks - 1); if (ret) goto out_buf; /* Check for cycles in the tree */ for (i = 0; i <= depth; i++) if (blk == blks[i]) { quota_error(dquot->dq_sb, "Cycle in quota tree detected: block %u index %u", blks[depth], get_index(info, dquot->dq_id, depth)); ret = -EIO; goto out_buf; } blks[depth + 1] = blk; if (depth < info->dqi_qtree_depth - 1) ret = find_tree_dqentry(info, dquot, blks, depth + 1); else ret = find_block_dqentry(info, dquot, blk); out_buf: kfree(buf); return ret; } /* Find entry for given id in the tree - wrapper function */ static inline loff_t find_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot) { uint blks[MAX_QTREE_DEPTH] = { QT_TREEOFF }; if (info->dqi_qtree_depth >= MAX_QTREE_DEPTH) { quota_error(dquot->dq_sb, "Quota tree depth too big!"); return -EIO; } return find_tree_dqentry(info, dquot, blks, 0); } int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) { int type = dquot->dq_id.type; struct super_block *sb = dquot->dq_sb; loff_t offset; char *ddquot; int ret = 0; #ifdef __QUOTA_QT_PARANOIA /* Invalidated quota? */ if (!sb_dqopt(dquot->dq_sb)->files[type]) { quota_error(sb, "Quota invalidated while reading!"); return -EIO; } #endif /* Do we know offset of the dquot entry in the quota file? */ if (!dquot->dq_off) { offset = find_dqentry(info, dquot); if (offset <= 0) { /* Entry not present? */ if (offset < 0) quota_error(sb,"Can't read quota structure " "for id %u", from_kqid(&init_user_ns, dquot->dq_id)); dquot->dq_off = 0; set_bit(DQ_FAKE_B, &dquot->dq_flags); memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk)); ret = offset; goto out; } dquot->dq_off = offset; } ddquot = kmalloc(info->dqi_entry_size, GFP_KERNEL); if (!ddquot) return -ENOMEM; ret = sb->s_op->quota_read(sb, type, ddquot, info->dqi_entry_size, dquot->dq_off); if (ret != info->dqi_entry_size) { if (ret >= 0) ret = -EIO; quota_error(sb, "Error while reading quota structure for id %u", from_kqid(&init_user_ns, dquot->dq_id)); set_bit(DQ_FAKE_B, &dquot->dq_flags); memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk)); kfree(ddquot); goto out; } spin_lock(&dquot->dq_dqb_lock); info->dqi_ops->disk2mem_dqblk(dquot, ddquot); if (!dquot->dq_dqb.dqb_bhardlimit && !dquot->dq_dqb.dqb_bsoftlimit && !dquot->dq_dqb.dqb_ihardlimit && !dquot->dq_dqb.dqb_isoftlimit) set_bit(DQ_FAKE_B, &dquot->dq_flags); spin_unlock(&dquot->dq_dqb_lock); kfree(ddquot); out: dqstats_inc(DQST_READS); return ret; } EXPORT_SYMBOL(qtree_read_dquot); /* Check whether dquot should not be deleted. We know we are * the only one operating on dquot (thanks to dq_lock) */ int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) { if (test_bit(DQ_FAKE_B, &dquot->dq_flags) && !(dquot->dq_dqb.dqb_curinodes | dquot->dq_dqb.dqb_curspace)) return qtree_delete_dquot(info, dquot); return 0; } EXPORT_SYMBOL(qtree_release_dquot); static int find_next_id(struct qtree_mem_dqinfo *info, qid_t *id, unsigned int blk, int depth) { char *buf = kmalloc(info->dqi_usable_bs, GFP_KERNEL); __le32 *ref = (__le32 *)buf; ssize_t ret; unsigned int epb = info->dqi_usable_bs >> 2; unsigned int level_inc = 1; int i; if (!buf) return -ENOMEM; for (i = depth; i < info->dqi_qtree_depth - 1; i++) level_inc *= epb; ret = read_blk(info, blk, buf); if (ret < 0) { quota_error(info->dqi_sb, "Can't read quota tree block %u", blk); goto out_buf; } for (i = __get_index(info, *id, depth); i < epb; i++) { uint blk_no = le32_to_cpu(ref[i]); if (blk_no == 0) { *id += level_inc; continue; } ret = do_check_range(info->dqi_sb, "block", blk_no, 0, info->dqi_blocks - 1); if (ret) goto out_buf; if (depth == info->dqi_qtree_depth - 1) { ret = 0; goto out_buf; } ret = find_next_id(info, id, blk_no, depth + 1); if (ret != -ENOENT) break; } if (i == epb) { ret = -ENOENT; goto out_buf; } out_buf: kfree(buf); return ret; } int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid) { qid_t id = from_kqid(&init_user_ns, *qid); int ret; ret = find_next_id(info, &id, QT_TREEOFF, 0); if (ret < 0) return ret; *qid = make_kqid(&init_user_ns, qid->type, id); return 0; } EXPORT_SYMBOL(qtree_get_next_id); |
| 787 1258 1251 1256 342 189 326 315 190 190 189 189 1250 188 157 111 152 1258 1213 1214 360 359 107 359 359 350 350 350 349 236 364 365 360 358 235 212 358 184 380 380 165 73 128 107 107 107 97 97 9 97 96 133 130 90 124 7 133 108 108 103 658 645 647 646 657 1097 1231 645 1087 1086 1084 784 786 784 787 6 5 6 46 46 46 62 45 62 117 119 119 119 119 97 96 96 97 97 71 71 71 273 1087 2 2 2 624 624 624 623 3 340 335 339 337 4 119 119 119 118 118 97 97 97 97 97 71 71 71 274 1090 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/dev_addr_lists.c - Functions for handling net device lists * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> * * This file contains functions for working with unicast, multicast and device * addresses lists. */ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/export.h> #include <linux/list.h> #include "dev.h" /* * General list handling functions */ static int __hw_addr_insert(struct netdev_hw_addr_list *list, struct netdev_hw_addr *new, int addr_len) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(new->addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&new->type, &ha->type, sizeof(new->type)); parent = *ins_point; if (diff < 0) ins_point = &parent->rb_left; else if (diff > 0) ins_point = &parent->rb_right; else return -EEXIST; } rb_link_node_rcu(&new->node, parent, ins_point); rb_insert_color(&new->node, &list->tree); return 0; } static struct netdev_hw_addr* __hw_addr_create(const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; alloc_size = sizeof(*ha); if (alloc_size < L1_CACHE_BYTES) alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, int sync_count, bool exclusive) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); parent = *ins_point; if (diff < 0) { ins_point = &parent->rb_left; } else if (diff > 0) { ins_point = &parent->rb_right; } else { if (exclusive) return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) return 0; else ha->global_use = true; } if (sync) { if (ha->synced && sync_count) return -EEXIST; else ha->synced++; } ha->refcount++; return 0; } } ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); if (!ha) return -ENOMEM; rb_link_node(&ha->node, parent, ins_point); rb_insert_color(&ha->node, &list->tree); list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, struct netdev_hw_addr *ha, bool global, bool sync) { if (global && !ha->global_use) return -ENOENT; if (sync && !ha->synced) return -ENOENT; if (global) ha->global_use = false; if (sync) ha->synced--; if (--ha->refcount) return 0; rb_erase(&ha->node, &list->tree); list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { struct rb_node *node; node = list->tree.rb_node; while (node) { struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); int diff = memcmp(addr, ha->addr, addr_len); if (diff == 0 && addr_type) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); if (diff < 0) node = node->rb_left; else if (diff > 0) node = node->rb_right; else return ha; } return NULL; } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); if (!ha) return -ENOENT; return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); } static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; if (!err) { ha->sync_cnt++; ha->refcount++; } return 0; } static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, false, true); if (err) return; ha->sync_cnt--; /* address on from list is not marked synced */ __hw_addr_del_entry(from_list, ha, false, false); } int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt == ha->refcount) { __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } else { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } } return err; } EXPORT_SYMBOL(__hw_addr_sync_multiple); /* This function only works where there is a strict 1-1 relationship * between source and destination of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (!ha->sync_cnt) { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } else if (ha->refcount == 1) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } return err; } EXPORT_SYMBOL(__hw_addr_sync); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } } EXPORT_SYMBOL(__hw_addr_unsync); /** * __hw_addr_sync_dev - Synchronize device's multicast list * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address add/remove * notifications. The unsync function may be NULL in which case * the addresses requiring removal will simply be removed without * any notification to the device. **/ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; int err; /* first go through and flush out any stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt || ha->refcount != 1) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (ha->sync_cnt) continue; err = sync(dev, ha->addr); if (err) return err; ha->sync_cnt++; ha->refcount++; } return 0; } EXPORT_SYMBOL(__hw_addr_sync_dev); /** * __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking * into account references * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address or reference on it should be added * @unsync: function to call if address or some reference on it should removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address or references on it * add/remove notifications. The unsync function may be NULL in which case * the addresses or references on it requiring removal will simply be * removed without any notification to the device. That is responsibility of * the driver to identify and distribute address or references on it between * internal address tables. **/ int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; int err, ref_cnt; /* first go through and flush out any unsynced/stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address is not used */ if ((ha->sync_cnt << 1) <= ha->refcount) continue; /* if fails defer unsyncing address */ ref_cnt = ha->refcount - ha->sync_cnt; if (unsync && unsync(dev, ha->addr, ref_cnt)) continue; ha->refcount = (ref_cnt << 1) + 1; ha->sync_cnt = ref_cnt; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync updated/new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address added or reused */ if ((ha->sync_cnt << 1) >= ha->refcount) continue; ref_cnt = ha->refcount - ha->sync_cnt; err = sync(dev, ha->addr, ref_cnt); if (err) return err; ha->refcount = ref_cnt << 1; ha->sync_cnt = ref_cnt; } return 0; } EXPORT_SYMBOL(__hw_addr_ref_sync_dev); /** * __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on * it from device * @list: address list to remove synchronized addresses (references on it) from * @dev: device to sync * @unsync: function to call if address and references on it should be removed * * Remove all addresses that were added to the device by * __hw_addr_ref_sync_dev(). This function is intended to be called from the * ndo_stop or ndo_open functions on devices that require explicit address (or * references on it) add/remove notifications. If the unsync function pointer * is NULL then this function can be used to just reset the sync_cnt for the * addresses in the list. **/ void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr, ha->sync_cnt)) continue; ha->refcount -= ha->sync_cnt - 1; ha->sync_cnt = 0; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_ref_unsync_dev); /** * __hw_addr_unsync_dev - Remove synchronized addresses from device * @list: address list to remove synchronized addresses from * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by __hw_addr_sync_dev(). * This function is intended to be called from the ndo_stop or ndo_open * functions on devices that require explicit address add/remove * notifications. If the unsync function pointer is NULL then this function * can be used to just reset the sync_cnt for the addresses in the list. **/ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_unsync_dev); static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); } list->count = 0; } void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); /* * Device addresses handling functions */ /* Check that netdev->dev_addr is not written to directly as this would * break the rbtree layout. All changes should go thru dev_addr_set() and co. * Remove this check in mid-2024. */ void dev_addr_check(struct net_device *dev) { if (!memcmp(dev->dev_addr, dev->dev_addr_shadow, MAX_ADDR_LEN)) return; netdev_warn(dev, "Current addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr); netdev_warn(dev, "Expected addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr_shadow); netdev_WARN(dev, "Incorrect netdev->dev_addr\n"); } /** * dev_addr_flush - Flush device address list * @dev: device * * Flush device address list and reset ->dev_addr. * * The caller must hold the rtnl_mutex. */ void dev_addr_flush(struct net_device *dev) { /* rtnl_mutex must be held here */ dev_addr_check(dev); __hw_addr_flush(&dev->dev_addrs); dev->dev_addr = NULL; } /** * dev_addr_init - Init device address list * @dev: device * * Init device address list and create the first element, * used by ->dev_addr. * * The caller must hold the rtnl_mutex. */ int dev_addr_init(struct net_device *dev) { unsigned char addr[MAX_ADDR_LEN]; struct netdev_hw_addr *ha; int err; /* rtnl_mutex must be held here */ __hw_addr_init(&dev->dev_addrs); memset(addr, 0, sizeof(addr)); err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), NETDEV_HW_ADDR_T_LAN); if (!err) { /* * Get the first (previously created) address from the list * and set dev_addr pointer to this location. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); dev->dev_addr = ha->addr; } return err; } void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len) { struct netdev_hw_addr *ha; dev_addr_check(dev); ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); rb_erase(&ha->node, &dev->dev_addrs.tree); memcpy(&ha->addr[offset], addr, len); memcpy(&dev->dev_addr_shadow[offset], addr, len); WARN_ON(__hw_addr_insert(&dev->dev_addrs, ha, dev->addr_len)); } EXPORT_SYMBOL(dev_addr_mod); /** * dev_addr_add - Add a device address * @dev: device * @addr: address to add * @addr_type: address type * * Add a device address to the device or increase the reference count if * it already exists. * * The caller must hold the rtnl_mutex. */ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; ASSERT_RTNL(); err = netif_pre_changeaddr_notify(dev, addr, NULL); if (err) return err; err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_add); /** * dev_addr_del - Release a device address. * @dev: device * @addr: address to delete * @addr_type: address type * * Release reference to a device address and remove it from the device * if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; struct netdev_hw_addr *ha; ASSERT_RTNL(); /* * We can not remove the first address from the list because * dev->dev_addr points to that. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); if (!memcmp(ha->addr, addr, dev->addr_len) && ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_del); /* * Unicast list handling functions */ /** * dev_uc_add_excl - Add a global secondary unicast address * @dev: device * @addr: address to add */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add_excl); /** * dev_uc_add - Add a secondary unicast address * @dev: device * @addr: address to add * * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add); /** * dev_uc_del - Release secondary unicast address. * @dev: device * @addr: address to delete * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_del); /** * dev_uc_sync - Synchronize device's unicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. This function assumes that * addresses will only ever be synced to the @to devices and no other. */ int dev_uc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); /** * dev_uc_sync_multiple - Synchronize device's unicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have been deleted from the source. The source device * must be locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. It allows for a single source * device to be synced to multiple destination devices. */ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync_multiple); /** * dev_uc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_uc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_uc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two * reasons: * 1) This is always called without any addr_list_lock, so as the * outermost one here, it must be 0. * 2) This is called by some callers after unlinking the upper device, * so the dev->lower_level becomes 1 again. * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or * larger. */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_uc_unsync); /** * dev_uc_flush - Flush unicast addresses * @dev: device * * Flush unicast addresses. */ void dev_uc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_uc_flush); /** * dev_uc_init - Init unicast address list * @dev: device * * Init unicast address list. */ void dev_uc_init(struct net_device *dev) { __hw_addr_init(&dev->uc); } EXPORT_SYMBOL(dev_uc_init); /* * Multicast list handling functions */ /** * dev_mc_add_excl - Add a global secondary multicast address * @dev: device * @addr: address to add */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_mc_add_excl); static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false, 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_add - Add a multicast address * @dev: device * @addr: address to add * * Add a multicast address to the device or increase * the reference count if it already exists. */ int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } EXPORT_SYMBOL(dev_mc_add); /** * dev_mc_add_global - Add a global multicast address * @dev: device * @addr: address to add * * Add a global multicast address to the device. */ int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_del - Delete a multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } EXPORT_SYMBOL(dev_mc_del); /** * dev_mc_del_global - Delete a global multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } EXPORT_SYMBOL(dev_mc_del_global); /** * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); /** * dev_mc_sync_multiple - Synchronize device's multicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. It allows for a single * source device to be synced to multiple destination devices. */ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync_multiple); /** * dev_mc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_mc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_mc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_mc_unsync); /** * dev_mc_flush - Flush multicast addresses * @dev: device * * Flush multicast addresses. */ void dev_mc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->mc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_mc_flush); /** * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. */ void dev_mc_init(struct net_device *dev) { __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); |
| 3 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2000,2002-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_BMAP_BTREE_H__ #define __XFS_BMAP_BTREE_H__ struct xfs_btree_cur; struct xfs_btree_block; struct xfs_mount; struct xfs_inode; struct xfs_trans; struct xbtree_ifakeroot; /* * Maximum number of bmap btree levels. */ #define XFS_BM_MAXLEVELS(mp,w) ((mp)->m_bm_maxlevels[(w)]) /* * Prototypes for xfs_bmap.c to call. */ extern void xfs_bmdr_to_bmbt(struct xfs_inode *, xfs_bmdr_block_t *, int, struct xfs_btree_block *, int); void xfs_bmbt_disk_set_all(struct xfs_bmbt_rec *r, struct xfs_bmbt_irec *s); extern xfs_filblks_t xfs_bmbt_disk_get_blockcount(const struct xfs_bmbt_rec *r); extern xfs_fileoff_t xfs_bmbt_disk_get_startoff(const struct xfs_bmbt_rec *r); void xfs_bmbt_disk_get_all(const struct xfs_bmbt_rec *r, struct xfs_bmbt_irec *s); extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int, xfs_bmdr_block_t *, int); extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level); extern int xfs_bmdr_maxrecs(int blocklen, int leaf); unsigned int xfs_bmbt_maxrecs(struct xfs_mount *mp, unsigned int blocklen, bool leaf); extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, xfs_ino_t new_owner, struct list_head *buffer_list); extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *, struct xfs_trans *, struct xfs_inode *, int); void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur, struct xfs_trans *tp, int whichfork); extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp, unsigned long long len); unsigned int xfs_bmbt_maxlevels_ondisk(void); int __init xfs_bmbt_init_cur_cache(void); void xfs_bmbt_destroy_cur_cache(void); void xfs_bmbt_init_block(struct xfs_inode *ip, struct xfs_btree_block *buf, struct xfs_buf *bp, __u16 level, __u16 numrecs); /* * Btree block header size depends on a superblock flag. */ static inline size_t xfs_bmbt_block_len(struct xfs_mount *mp) { return xfs_has_crc(mp) ? XFS_BTREE_LBLOCK_CRC_LEN : XFS_BTREE_LBLOCK_LEN; } /* Addresses of key, pointers, and records within an incore bmbt block. */ static inline struct xfs_bmbt_rec * xfs_bmbt_rec_addr( struct xfs_mount *mp, struct xfs_btree_block *block, unsigned int index) { return (struct xfs_bmbt_rec *) ((char *)block + xfs_bmbt_block_len(mp) + (index - 1) * sizeof(struct xfs_bmbt_rec)); } static inline struct xfs_bmbt_key * xfs_bmbt_key_addr( struct xfs_mount *mp, struct xfs_btree_block *block, unsigned int index) { return (struct xfs_bmbt_key *) ((char *)block + xfs_bmbt_block_len(mp) + (index - 1) * sizeof(struct xfs_bmbt_key *)); } static inline xfs_bmbt_ptr_t * xfs_bmbt_ptr_addr( struct xfs_mount *mp, struct xfs_btree_block *block, unsigned int index, unsigned int maxrecs) { return (xfs_bmbt_ptr_t *) ((char *)block + xfs_bmbt_block_len(mp) + maxrecs * sizeof(struct xfs_bmbt_key) + (index - 1) * sizeof(xfs_bmbt_ptr_t)); } /* Addresses of key, pointers, and records within an ondisk bmbt block. */ static inline struct xfs_bmbt_rec * xfs_bmdr_rec_addr( struct xfs_bmdr_block *block, unsigned int index) { return (struct xfs_bmbt_rec *) ((char *)(block + 1) + (index - 1) * sizeof(struct xfs_bmbt_rec)); } static inline struct xfs_bmbt_key * xfs_bmdr_key_addr( struct xfs_bmdr_block *block, unsigned int index) { return (struct xfs_bmbt_key *) ((char *)(block + 1) + (index - 1) * sizeof(struct xfs_bmbt_key)); } static inline xfs_bmbt_ptr_t * xfs_bmdr_ptr_addr( struct xfs_bmdr_block *block, unsigned int index, unsigned int maxrecs) { return (xfs_bmbt_ptr_t *) ((char *)(block + 1) + maxrecs * sizeof(struct xfs_bmbt_key) + (index - 1) * sizeof(xfs_bmbt_ptr_t)); } /* * Address of pointers within the incore btree root. * * These are to be used when we know the size of the block and * we don't have a cursor. */ static inline xfs_bmbt_ptr_t * xfs_bmap_broot_ptr_addr( struct xfs_mount *mp, struct xfs_btree_block *bb, unsigned int i, unsigned int sz) { return xfs_bmbt_ptr_addr(mp, bb, i, xfs_bmbt_maxrecs(mp, sz, false)); } /* * Compute the space required for the incore btree root containing the given * number of records. */ static inline size_t xfs_bmap_broot_space_calc( struct xfs_mount *mp, unsigned int nrecs) { return xfs_bmbt_block_len(mp) + (nrecs * (sizeof(struct xfs_bmbt_key) + sizeof(xfs_bmbt_ptr_t))); } /* * Compute the space required for the incore btree root given the ondisk * btree root block. */ static inline size_t xfs_bmap_broot_space( struct xfs_mount *mp, struct xfs_bmdr_block *bb) { return xfs_bmap_broot_space_calc(mp, be16_to_cpu(bb->bb_numrecs)); } /* Compute the space required for the ondisk root block. */ static inline size_t xfs_bmdr_space_calc(unsigned int nrecs) { return sizeof(struct xfs_bmdr_block) + (nrecs * (sizeof(struct xfs_bmbt_key) + sizeof(xfs_bmbt_ptr_t))); } /* * Compute the space required for the ondisk root block given an incore root * block. */ static inline size_t xfs_bmap_bmdr_space(struct xfs_btree_block *bb) { return xfs_bmdr_space_calc(be16_to_cpu(bb->bb_numrecs)); } struct xfs_btree_block *xfs_bmap_broot_realloc(struct xfs_inode *ip, int whichfork, unsigned int new_numrecs); #endif /* __XFS_BMAP_BTREE_H__ */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/sunrpc/svc_xprt.h * * RPC server transport I/O */ #ifndef SUNRPC_SVC_XPRT_H #define SUNRPC_SVC_XPRT_H #include <linux/sunrpc/svc.h> struct module; struct svc_xprt_ops { struct svc_xprt *(*xpo_create)(struct svc_serv *, struct net *net, struct sockaddr *, int, int); struct svc_xprt *(*xpo_accept)(struct svc_xprt *); int (*xpo_has_wspace)(struct svc_xprt *); int (*xpo_recvfrom)(struct svc_rqst *); int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); void (*xpo_handshake)(struct svc_xprt *xprt); }; struct svc_xprt_class { const char *xcl_name; struct module *xcl_owner; const struct svc_xprt_ops *xcl_ops; struct list_head xcl_list; u32 xcl_max_payload; int xcl_ident; }; /* * This is embedded in an object that wants a callback before deleting * an xprt; intended for use by NFSv4.1, which needs to know when a * client's tcp connection (and hence possibly a backchannel) goes away. */ struct svc_xpt_user { struct list_head list; void (*callback)(struct svc_xpt_user *); }; struct svc_xprt { struct svc_xprt_class *xpt_class; const struct svc_xprt_ops *xpt_ops; struct kref xpt_ref; ktime_t xpt_qtime; struct list_head xpt_list; struct lwq_node xpt_ready; unsigned long xpt_flags; struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ atomic_t xpt_nr_rqsts; /* Number of requests */ struct mutex xpt_mutex; /* to serialize sending data */ spinlock_t xpt_lock; /* protects sk_deferred * and xpt_auth_cache */ void *xpt_auth_cache;/* auth cache */ struct list_head xpt_deferred; /* deferred requests that need * to be revisted */ struct sockaddr_storage xpt_local; /* local address */ size_t xpt_locallen; /* length of address */ struct sockaddr_storage xpt_remote; /* remote peer's address */ size_t xpt_remotelen; /* length of address */ char xpt_remotebuf[INET6_ADDRSTRLEN + 10]; struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ }; /* flag bits for xpt_flags */ enum { XPT_BUSY, /* enqueued/receiving */ XPT_CONN, /* conn pending */ XPT_CLOSE, /* dead or dying */ XPT_DATA, /* data pending */ XPT_TEMP, /* connected transport */ XPT_DEAD, /* transport closed */ XPT_CHNGBUF, /* need to change snd/rcv buf sizes */ XPT_DEFERRED, /* deferred request pending */ XPT_OLD, /* used for xprt aging mark+sweep */ XPT_LISTENER, /* listening endpoint */ XPT_CACHE_AUTH, /* cache auth info */ XPT_LOCAL, /* connection from loopback interface */ XPT_KILL_TEMP, /* call xpo_kill_temp_xprt before closing */ XPT_CONG_CTRL, /* has congestion control */ XPT_HANDSHAKE, /* xprt requests a handshake */ XPT_TLS_SESSION, /* transport-layer security established */ XPT_PEER_AUTH, /* peer has been authenticated */ XPT_PEER_VALID, /* peer has presented a filehandle that * it has access to. It is NOT counted * in ->sv_tmpcnt. */ XPT_RPCB_UNREG, /* transport that needs unregistering * with rpcbind (TCP, UDP) on destroy */ }; /* * Maximum number of "tmp" connections - those without XPT_PEER_VALID - * permitted on any service. */ #define XPT_MAX_TMP_CONN 64 static inline void svc_xprt_set_valid(struct svc_xprt *xpt) { if (test_bit(XPT_TEMP, &xpt->xpt_flags) && !test_and_set_bit(XPT_PEER_VALID, &xpt->xpt_flags)) { struct svc_serv *serv = xpt->xpt_server; spin_lock(&serv->sv_lock); serv->sv_tmpcnt -= 1; spin_unlock(&serv->sv_lock); } } static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u) { spin_lock(&xpt->xpt_lock); list_del_init(&u->list); spin_unlock(&xpt->xpt_lock); } static inline int register_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u) { spin_lock(&xpt->xpt_lock); if (test_bit(XPT_CLOSE, &xpt->xpt_flags)) { /* * The connection is about to be deleted soon (or, * worse, may already be deleted--in which case we've * already notified the xpt_users). */ spin_unlock(&xpt->xpt_lock); return -ENOTCONN; } list_add(&u->list, &xpt->xpt_users); spin_unlock(&xpt->xpt_lock); return 0; } static inline bool svc_xprt_is_dead(const struct svc_xprt *xprt) { return (test_bit(XPT_DEAD, &xprt->xpt_flags) != 0) || (test_bit(XPT_CLOSE, &xprt->xpt_flags) != 0); } int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); int svc_xprt_create_from_sa(struct svc_serv *serv, const char *xprt_name, struct net *net, struct sockaddr *sap, int flags, const struct cred *cred); int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, const struct cred *cred); void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net, bool unregister); void svc_xprt_received(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); struct svc_xprt *svc_find_listener(struct svc_serv *serv, const char *xcl_name, struct net *net, const struct sockaddr *sa); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, struct net *net, const sa_family_t af, const unsigned short port); int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen); void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *xprt); void svc_age_temp_xprts_now(struct svc_serv *, struct sockaddr *); void svc_xprt_deferred_close(struct svc_xprt *xprt); static inline void svc_xprt_get(struct svc_xprt *xprt) { kref_get(&xprt->xpt_ref); } static inline void svc_xprt_set_local(struct svc_xprt *xprt, const struct sockaddr *sa, const size_t salen) { memcpy(&xprt->xpt_local, sa, salen); xprt->xpt_locallen = salen; } static inline void svc_xprt_set_remote(struct svc_xprt *xprt, const struct sockaddr *sa, const size_t salen) { memcpy(&xprt->xpt_remote, sa, salen); xprt->xpt_remotelen = salen; snprintf(xprt->xpt_remotebuf, sizeof(xprt->xpt_remotebuf) - 1, "%pISpc", sa); } static inline unsigned short svc_addr_port(const struct sockaddr *sa) { const struct sockaddr_in *sin = (const struct sockaddr_in *)sa; const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sa; switch (sa->sa_family) { case AF_INET: return ntohs(sin->sin_port); case AF_INET6: return ntohs(sin6->sin6_port); } return 0; } static inline size_t svc_addr_len(const struct sockaddr *sa) { switch (sa->sa_family) { case AF_INET: return sizeof(struct sockaddr_in); case AF_INET6: return sizeof(struct sockaddr_in6); } BUG(); } static inline unsigned short svc_xprt_local_port(const struct svc_xprt *xprt) { return svc_addr_port((const struct sockaddr *)&xprt->xpt_local); } static inline unsigned short svc_xprt_remote_port(const struct svc_xprt *xprt) { return svc_addr_port((const struct sockaddr *)&xprt->xpt_remote); } static inline char *__svc_print_addr(const struct sockaddr *addr, char *buf, const size_t len) { const struct sockaddr_in *sin = (const struct sockaddr_in *)addr; const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)addr; switch (addr->sa_family) { case AF_INET: snprintf(buf, len, "%pI4, port=%u", &sin->sin_addr, ntohs(sin->sin_port)); break; case AF_INET6: snprintf(buf, len, "%pI6, port=%u", &sin6->sin6_addr, ntohs(sin6->sin6_port)); break; default: snprintf(buf, len, "unknown address type: %d", addr->sa_family); break; } return buf; } #endif /* SUNRPC_SVC_XPRT_H */ |
| 20 | 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-or-later */ /* X.509 certificate parser internal definitions * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/cleanup.h> #include <linux/time.h> #include <crypto/public_key.h> #include <keys/asymmetric-type.h> struct x509_certificate { struct x509_certificate *next; struct x509_certificate *signer; /* Certificate that signed this one */ struct public_key *pub; /* Public key details */ struct public_key_signature *sig; /* Signature parameters */ char *issuer; /* Name of certificate issuer */ char *subject; /* Name of certificate subject */ struct asymmetric_key_id *id; /* Issuer + Serial number */ struct asymmetric_key_id *skid; /* Subject + subjectKeyId (optional) */ time64_t valid_from; time64_t valid_to; const void *tbs; /* Signed data */ unsigned tbs_size; /* Size of signed data */ unsigned raw_sig_size; /* Size of signature */ const void *raw_sig; /* Signature data */ const void *raw_serial; /* Raw serial number in ASN.1 */ unsigned raw_serial_size; unsigned raw_issuer_size; const void *raw_issuer; /* Raw issuer name in ASN.1 */ const void *raw_subject; /* Raw subject name in ASN.1 */ unsigned raw_subject_size; unsigned raw_skid_size; const void *raw_skid; /* Raw subjectKeyId in ASN.1 */ unsigned index; bool seen; /* Infinite recursion prevention */ bool verified; bool self_signed; /* T if self-signed (check unsupported_sig too) */ bool unsupported_sig; /* T if signature uses unsupported crypto */ bool blacklisted; }; /* * x509_cert_parser.c */ extern void x509_free_certificate(struct x509_certificate *cert); DEFINE_FREE(x509_free_certificate, struct x509_certificate *, if (!IS_ERR(_T)) x509_free_certificate(_T)) extern struct x509_certificate *x509_cert_parse(const void *data, size_t datalen); extern int x509_decode_time(time64_t *_t, size_t hdrlen, unsigned char tag, const unsigned char *value, size_t vlen); /* * x509_public_key.c */ extern int x509_get_sig_params(struct x509_certificate *cert); extern int x509_check_for_self_signed(struct x509_certificate *cert); |
| 2 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Driver for USB ethernet port of Conexant CX82310-based ADSL routers * Copyright (C) 2010 by Ondrej Zary * some parts inspired by the cxacru driver */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/workqueue.h> #include <linux/mii.h> #include <linux/usb.h> #include <linux/usb/usbnet.h> enum cx82310_cmd { CMD_START = 0x84, /* no effect? */ CMD_STOP = 0x85, /* no effect? */ CMD_GET_STATUS = 0x90, /* returns nothing? */ CMD_GET_MAC_ADDR = 0x91, /* read MAC address */ CMD_GET_LINK_STATUS = 0x92, /* not useful, link is always up */ CMD_ETHERNET_MODE = 0x99, /* unknown, needed during init */ }; enum cx82310_status { STATUS_UNDEFINED, STATUS_SUCCESS, STATUS_ERROR, STATUS_UNSUPPORTED, STATUS_UNIMPLEMENTED, STATUS_PARAMETER_ERROR, STATUS_DBG_LOOPBACK, }; #define CMD_PACKET_SIZE 64 #define CMD_TIMEOUT 100 #define CMD_REPLY_RETRY 5 #define CX82310_MTU 1514 #define CMD_EP 0x01 struct cx82310_priv { struct work_struct reenable_work; struct usbnet *dev; }; /* * execute control command * - optionally send some data (command parameters) * - optionally wait for the reply * - optionally read some data from the reply */ static int cx82310_cmd(struct usbnet *dev, enum cx82310_cmd cmd, bool reply, u8 *wdata, int wlen, u8 *rdata, int rlen) { int actual_len, retries, ret; struct usb_device *udev = dev->udev; u8 *buf = kzalloc(CMD_PACKET_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; /* create command packet */ buf[0] = cmd; if (wdata) memcpy(buf + 4, wdata, min_t(int, wlen, CMD_PACKET_SIZE - 4)); /* send command packet */ ret = usb_bulk_msg(udev, usb_sndbulkpipe(udev, CMD_EP), buf, CMD_PACKET_SIZE, &actual_len, CMD_TIMEOUT); if (ret < 0) { if (cmd != CMD_GET_LINK_STATUS) netdev_err(dev->net, "send command %#x: error %d\n", cmd, ret); goto end; } if (reply) { /* wait for reply, retry if it's empty */ for (retries = 0; retries < CMD_REPLY_RETRY; retries++) { ret = usb_bulk_msg(udev, usb_rcvbulkpipe(udev, CMD_EP), buf, CMD_PACKET_SIZE, &actual_len, CMD_TIMEOUT); if (ret < 0) { if (cmd != CMD_GET_LINK_STATUS) netdev_err(dev->net, "reply receive error %d\n", ret); goto end; } if (actual_len > 0) break; } if (actual_len == 0) { netdev_err(dev->net, "no reply to command %#x\n", cmd); ret = -EIO; goto end; } if (buf[0] != cmd) { netdev_err(dev->net, "got reply to command %#x, expected: %#x\n", buf[0], cmd); ret = -EIO; goto end; } if (buf[1] != STATUS_SUCCESS) { netdev_err(dev->net, "command %#x failed: %#x\n", cmd, buf[1]); ret = -EIO; goto end; } if (rdata) memcpy(rdata, buf + 4, min_t(int, rlen, CMD_PACKET_SIZE - 4)); } end: kfree(buf); return ret; } static int cx82310_enable_ethernet(struct usbnet *dev) { int ret = cx82310_cmd(dev, CMD_ETHERNET_MODE, true, "\x01", 1, NULL, 0); if (ret) netdev_err(dev->net, "unable to enable ethernet mode: %d\n", ret); return ret; } static void cx82310_reenable_work(struct work_struct *work) { struct cx82310_priv *priv = container_of(work, struct cx82310_priv, reenable_work); cx82310_enable_ethernet(priv->dev); } #define partial_len data[0] /* length of partial packet data */ #define partial_rem data[1] /* remaining (missing) data length */ #define partial_data data[2] /* partial packet data */ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) { int ret; char buf[15]; struct usb_device *udev = dev->udev; u8 link[3]; int timeout = 50; struct cx82310_priv *priv; u8 addr[ETH_ALEN]; /* avoid ADSL modems - continue only if iProduct is "USB NET CARD" */ if (usb_string(udev, udev->descriptor.iProduct, buf, sizeof(buf)) > 0 && strcmp(buf, "USB NET CARD")) { dev_info(&udev->dev, "ignoring: probably an ADSL modem\n"); return -ENODEV; } ret = usbnet_get_endpoints(dev, intf); if (ret) return ret; /* * this must not include ethernet header as the device can send partial * packets with no header (and sometimes even empty URBs) */ dev->net->hard_header_len = 0; /* we can send at most 1514 bytes of data (+ 2-byte header) per URB */ dev->hard_mtu = CX82310_MTU + 2; /* we can receive URBs up to 4KB from the device */ dev->rx_urb_size = 4096; dev->partial_data = (unsigned long) kmalloc(dev->hard_mtu, GFP_KERNEL); if (!dev->partial_data) return -ENOMEM; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) { ret = -ENOMEM; goto err_partial; } dev->driver_priv = priv; INIT_WORK(&priv->reenable_work, cx82310_reenable_work); priv->dev = dev; /* wait for firmware to become ready (indicated by the link being up) */ while (--timeout) { ret = cx82310_cmd(dev, CMD_GET_LINK_STATUS, true, NULL, 0, link, sizeof(link)); /* the command can time out during boot - it's not an error */ if (!ret && link[0] == 1 && link[2] == 1) break; msleep(500); } if (!timeout) { netdev_err(dev->net, "firmware not ready in time\n"); ret = -ETIMEDOUT; goto err; } /* enable ethernet mode (?) */ ret = cx82310_enable_ethernet(dev); if (ret) goto err; /* get the MAC address */ ret = cx82310_cmd(dev, CMD_GET_MAC_ADDR, true, NULL, 0, addr, ETH_ALEN); if (ret) { netdev_err(dev->net, "unable to read MAC address: %d\n", ret); goto err; } eth_hw_addr_set(dev->net, addr); /* start (does not seem to have any effect?) */ ret = cx82310_cmd(dev, CMD_START, false, NULL, 0, NULL, 0); if (ret) goto err; return 0; err: kfree(dev->driver_priv); err_partial: kfree((void *)dev->partial_data); return ret; } static void cx82310_unbind(struct usbnet *dev, struct usb_interface *intf) { struct cx82310_priv *priv = dev->driver_priv; kfree((void *)dev->partial_data); cancel_work_sync(&priv->reenable_work); kfree(dev->driver_priv); } /* * RX is NOT easy - we can receive multiple packets per skb, each having 2-byte * packet length at the beginning. * The last packet might be incomplete (when it crosses the 4KB URB size), * continuing in the next skb (without any headers). * If a packet has odd length, there is one extra byte at the end (before next * packet or at the end of the URB). */ static int cx82310_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { int len; struct sk_buff *skb2; struct cx82310_priv *priv = dev->driver_priv; /* * If the last skb ended with an incomplete packet, this skb contains * end of that packet at the beginning. */ if (dev->partial_rem) { len = dev->partial_len + dev->partial_rem; skb2 = alloc_skb(len, GFP_ATOMIC); if (!skb2) return 0; skb_put(skb2, len); memcpy(skb2->data, (void *)dev->partial_data, dev->partial_len); memcpy(skb2->data + dev->partial_len, skb->data, dev->partial_rem); usbnet_skb_return(dev, skb2); skb_pull(skb, (dev->partial_rem + 1) & ~1); dev->partial_rem = 0; if (skb->len < 2) return 1; } /* a skb can contain multiple packets */ while (skb->len > 1) { /* first two bytes are packet length */ len = skb->data[0] | (skb->data[1] << 8); skb_pull(skb, 2); /* if last packet in the skb, let usbnet to process it */ if (len == skb->len || len + 1 == skb->len) { skb_trim(skb, len); break; } if (len == 0xffff) { netdev_info(dev->net, "router was rebooted, re-enabling ethernet mode"); schedule_work(&priv->reenable_work); } else if (len > CX82310_MTU) { netdev_err(dev->net, "RX packet too long: %d B\n", len); return 0; } /* incomplete packet, save it for the next skb */ if (len > skb->len) { dev->partial_len = skb->len; dev->partial_rem = len - skb->len; memcpy((void *)dev->partial_data, skb->data, dev->partial_len); skb_pull(skb, skb->len); break; } skb2 = alloc_skb(len, GFP_ATOMIC); if (!skb2) return 0; skb_put(skb2, len); memcpy(skb2->data, skb->data, len); /* process the packet */ usbnet_skb_return(dev, skb2); skb_pull(skb, (len + 1) & ~1); } /* let usbnet process the last packet */ return 1; } /* TX is easy, just add 2 bytes of length at the beginning */ static struct sk_buff *cx82310_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { int len = skb->len; if (skb_cow_head(skb, 2)) { dev_kfree_skb_any(skb); return NULL; } skb_push(skb, 2); skb->data[0] = len; skb->data[1] = len >> 8; return skb; } static const struct driver_info cx82310_info = { .description = "Conexant CX82310 USB ethernet", .flags = FLAG_ETHER, .bind = cx82310_bind, .unbind = cx82310_unbind, .rx_fixup = cx82310_rx_fixup, .tx_fixup = cx82310_tx_fixup, }; #define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ USB_DEVICE_ID_MATCH_DEV_INFO, \ .idVendor = (vend), \ .idProduct = (prod), \ .bDeviceClass = (cl), \ .bDeviceSubClass = (sc), \ .bDeviceProtocol = (pr) static const struct usb_device_id products[] = { { USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0), .driver_info = (unsigned long) &cx82310_info }, { }, }; MODULE_DEVICE_TABLE(usb, products); static struct usb_driver cx82310_driver = { .name = "cx82310_eth", .id_table = products, .probe = usbnet_probe, .disconnect = usbnet_disconnect, .suspend = usbnet_suspend, .resume = usbnet_resume, .disable_hub_initiated_lpm = 1, }; module_usb_driver(cx82310_driver); MODULE_AUTHOR("Ondrej Zary"); MODULE_DESCRIPTION("Conexant CX82310-based ADSL router USB ethernet driver"); MODULE_LICENSE("GPL"); |
| 30 2 168 176 129 227 176 15118 315 15075 6 129 8 414 14024 16 345 825 1561 9900 10978 57 14 9 10156 126 15367 95 98 3 2 5 11415 314 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/mm_types.h> #include <linux/ucopysize.h> #include <uapi/linux/uio.h> struct page; struct folio_queue; typedef unsigned int __bitwise iov_iter_extraction_t; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_UBUF, ITER_IOVEC, ITER_BVEC, ITER_KVEC, ITER_FOLIOQ, ITER_XARRAY, ITER_DISCARD, }; #define ITER_SOURCE 1 // == WRITE #define ITER_DEST 0 // == READ struct iov_iter_state { size_t iov_offset; size_t count; unsigned long nr_segs; }; struct iov_iter { u8 iter_type; bool nofault; bool data_source; size_t iov_offset; /* * Hack alert: overlay ubuf_iovec with iovec + count, so * that the members resolve correctly regardless of the type * of iterator used. This means that you can use: * * &iter->__ubuf_iovec or iter->__iov * * interchangably for the user_backed cases, hence simplifying * some of the cases that need to deal with both. */ union { /* * This really should be a const, but we cannot do that without * also modifying any of the zero-filling iter init functions. * Leave it non-const for now, but it should be treated as such. */ struct iovec __ubuf_iovec; struct { union { /* use iter_iov() to get the current vec */ const struct iovec *__iov; const struct kvec *kvec; const struct bio_vec *bvec; const struct folio_queue *folioq; struct xarray *xarray; void __user *ubuf; }; size_t count; }; }; union { unsigned long nr_segs; u8 folioq_slot; loff_t xarray_start; }; }; typedef __u16 uio_meta_flags_t; struct uio_meta { uio_meta_flags_t flags; u16 app_tag; u64 seed; struct iov_iter iter; }; static inline const struct iovec *iter_iov(const struct iov_iter *iter) { if (iter->iter_type == ITER_UBUF) return (const struct iovec *) &iter->__ubuf_iovec; return iter->__iov; } #define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) static inline size_t iter_iov_len(const struct iov_iter *i) { if (i->iter_type == ITER_UBUF) return i->count; return iter_iov(i)->iov_len - i->iov_offset; } static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; } static inline void iov_iter_save_state(struct iov_iter *iter, struct iov_iter_state *state) { state->iov_offset = iter->iov_offset; state->count = iter->count; state->nr_segs = iter->nr_segs; } static inline bool iter_is_ubuf(const struct iov_iter *i) { return iov_iter_type(i) == ITER_UBUF; } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline bool iov_iter_is_folioq(const struct iov_iter *i) { return iov_iter_type(i) == ITER_FOLIOQ; } static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->data_source ? WRITE : READ; } static inline bool user_backed_iter(const struct iov_iter *i) { return iter_is_ubuf(i) || iter_is_iovec(i); } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_to_iter(&folio->page, offset, bytes, i); } static inline size_t copy_folio_from_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_from_iter(&folio->page, offset, bytes, i); } size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, true)) return _copy_to_iter(addr, bytes, i); return 0; } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_to_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter_nocache(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter_nocache(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_mc_to_iter _copy_to_iter #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, const struct folio_queue *folioq, unsigned int first_slot, unsigned int offset, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } static inline int iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) { size_t shorted = 0; int npages; if (iov_iter_count(i) > max_bytes) { shorted = iov_iter_count(i) - max_bytes; iov_iter_truncate(i, max_bytes); } npages = iov_iter_npages(i, maxpages); if (shorted) iov_iter_reexpand(i, iov_iter_count(i) + shorted); return npages; } struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, void __user *buf, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, .data_source = direction, .ubuf = buf, .count = count, .nr_segs = 1 }; } /* Flags for iov_iter_get/extract_pages*() */ /* Allow P2PDMA on the extracted pages */ #define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0); /** * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained * @iter: The iterator * * Examine the iterator and indicate by returning true or false as to how, if * at all, pages extracted from the iterator will be retained by the extraction * function. * * %true indicates that the pages will have a pin placed in them that the * caller must unpin. This is must be done for DMA/async DIO to force fork() * to forcibly copy a page for the child (the parent must retain the original * page). * * %false indicates that no measures are taken and that it's up to the caller * to retain the pages. */ static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter) { return user_backed_iter(iter); } struct sg_table; ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t len, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags); #endif |
| 2 2 2 2 2 1 1 2 2 2 1 2 1 1 1 1 5 5 5 5 5 5 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> #include <linux/firmware.h> #include <linux/sfp.h> #include <net/devlink.h> #include <net/netdev_lock.h> #include "netlink.h" #include "common.h" #include "bitset.h" #include "module_fw.h" struct module_req_info { struct ethnl_req_info base; }; struct module_reply_data { struct ethnl_reply_data base; struct ethtool_module_power_mode_params power; }; #define MODULE_REPDATA(__reply_base) \ container_of(__reply_base, struct module_reply_data, base) /* MODULE_GET */ const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1] = { [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int module_get_power_mode(struct net_device *dev, struct module_reply_data *data, struct netlink_ext_ack *extack) { const struct ethtool_ops *ops = dev->ethtool_ops; if (!ops->get_module_power_mode) return 0; if (dev->ethtool->module_fw_flash_in_progress) { NL_SET_ERR_MSG(extack, "Module firmware flashing is in progress"); return -EBUSY; } return ops->get_module_power_mode(dev, &data->power, extack); } static int module_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct module_reply_data *data = MODULE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = module_get_power_mode(dev, data, info->extack); if (ret < 0) goto out_complete; out_complete: ethnl_ops_complete(dev); return ret; } static int module_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { struct module_reply_data *data = MODULE_REPDATA(reply_base); int len = 0; if (data->power.policy) len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE_POLICY */ if (data->power.mode) len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE */ return len; } static int module_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct module_reply_data *data = MODULE_REPDATA(reply_base); if (data->power.policy && nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE_POLICY, data->power.policy)) return -EMSGSIZE; if (data->power.mode && nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE, data->power.mode)) return -EMSGSIZE; return 0; } /* MODULE_SET */ const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1] = { [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_MODULE_POWER_MODE_POLICY] = NLA_POLICY_RANGE(NLA_U8, ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH, ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO), }; static int ethnl_set_module_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; struct nlattr **tb = info->attrs; if (!tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]) return 0; if (req_info->dev->ethtool->module_fw_flash_in_progress) { NL_SET_ERR_MSG(info->extack, "Module firmware flashing is in progress"); return -EBUSY; } if (!ops->get_module_power_mode || !ops->set_module_power_mode) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY], "Setting power mode policy is not supported by this device"); return -EOPNOTSUPP; } return 1; } static int ethnl_set_module(struct ethnl_req_info *req_info, struct genl_info *info) { struct ethtool_module_power_mode_params power = {}; struct ethtool_module_power_mode_params power_new; const struct ethtool_ops *ops; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; int ret; ops = dev->ethtool_ops; power_new.policy = nla_get_u8(tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]); ret = ops->get_module_power_mode(dev, &power, info->extack); if (ret < 0) return ret; if (power_new.policy == power.policy) return 0; ret = ops->set_module_power_mode(dev, &power_new, info->extack); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_module_request_ops = { .request_cmd = ETHTOOL_MSG_MODULE_GET, .reply_cmd = ETHTOOL_MSG_MODULE_GET_REPLY, .hdr_attr = ETHTOOL_A_MODULE_HEADER, .req_info_size = sizeof(struct module_req_info), .reply_data_size = sizeof(struct module_reply_data), .prepare_data = module_prepare_data, .reply_size = module_reply_size, .fill_reply = module_fill_reply, .set_validate = ethnl_set_module_validate, .set = ethnl_set_module, .set_ntf_cmd = ETHTOOL_MSG_MODULE_NTF, }; /* MODULE_FW_FLASH_ACT */ const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1] = { [ETHTOOL_A_MODULE_FW_FLASH_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME] = { .type = NLA_NUL_STRING }, [ETHTOOL_A_MODULE_FW_FLASH_PASSWORD] = { .type = NLA_U32 }, }; static LIST_HEAD(module_fw_flash_work_list); static DEFINE_SPINLOCK(module_fw_flash_work_list_lock); static int module_flash_fw_work_list_add(struct ethtool_module_fw_flash *module_fw, struct genl_info *info) { struct ethtool_module_fw_flash *work; /* First, check if already registered. */ spin_lock(&module_fw_flash_work_list_lock); list_for_each_entry(work, &module_fw_flash_work_list, list) { if (work->fw_update.ntf_params.portid == info->snd_portid && work->fw_update.dev == module_fw->fw_update.dev) { spin_unlock(&module_fw_flash_work_list_lock); return -EALREADY; } } list_add_tail(&module_fw->list, &module_fw_flash_work_list); spin_unlock(&module_fw_flash_work_list_lock); return 0; } static void module_flash_fw_work_list_del(struct list_head *list) { spin_lock(&module_fw_flash_work_list_lock); list_del(list); spin_unlock(&module_fw_flash_work_list_lock); } static void module_flash_fw_work(struct work_struct *work) { struct ethtool_module_fw_flash *module_fw; module_fw = container_of(work, struct ethtool_module_fw_flash, work); ethtool_cmis_fw_update(&module_fw->fw_update); module_flash_fw_work_list_del(&module_fw->list); module_fw->fw_update.dev->ethtool->module_fw_flash_in_progress = false; netdev_put(module_fw->fw_update.dev, &module_fw->dev_tracker); release_firmware(module_fw->fw_update.fw); kfree(module_fw); } #define MODULE_EEPROM_PHYS_ID_PAGE 0 #define MODULE_EEPROM_PHYS_ID_I2C_ADDR 0x50 static int module_flash_fw_work_init(struct ethtool_module_fw_flash *module_fw, struct net_device *dev, struct netlink_ext_ack *extack) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_module_eeprom page_data = {}; u8 phys_id; int err; /* Fetch the SFF-8024 Identifier Value. For all supported standards, it * is located at I2C address 0x50, byte 0. See section 4.1 in SFF-8024, * revision 4.9. */ page_data.page = MODULE_EEPROM_PHYS_ID_PAGE; page_data.offset = SFP_PHYS_ID; page_data.length = sizeof(phys_id); page_data.i2c_address = MODULE_EEPROM_PHYS_ID_I2C_ADDR; page_data.data = &phys_id; err = ops->get_module_eeprom_by_page(dev, &page_data, extack); if (err < 0) return err; switch (phys_id) { case SFF8024_ID_QSFP_DD: case SFF8024_ID_OSFP: case SFF8024_ID_DSFP: case SFF8024_ID_QSFP_PLUS_CMIS: case SFF8024_ID_SFP_DD_CMIS: case SFF8024_ID_SFP_PLUS_CMIS: INIT_WORK(&module_fw->work, module_flash_fw_work); break; default: NL_SET_ERR_MSG(extack, "Module type does not support firmware flashing"); return -EOPNOTSUPP; } return 0; } void ethnl_module_fw_flash_sock_destroy(struct ethnl_sock_priv *sk_priv) { struct ethtool_module_fw_flash *work; spin_lock(&module_fw_flash_work_list_lock); list_for_each_entry(work, &module_fw_flash_work_list, list) { if (work->fw_update.dev == sk_priv->dev && work->fw_update.ntf_params.portid == sk_priv->portid) { work->fw_update.ntf_params.closed_sock = true; break; } } spin_unlock(&module_fw_flash_work_list_lock); } static int module_flash_fw_schedule(struct net_device *dev, const char *file_name, struct ethtool_module_fw_flash_params *params, struct sk_buff *skb, struct genl_info *info) { struct ethtool_cmis_fw_update_params *fw_update; struct ethtool_module_fw_flash *module_fw; int err; module_fw = kzalloc(sizeof(*module_fw), GFP_KERNEL); if (!module_fw) return -ENOMEM; fw_update = &module_fw->fw_update; fw_update->params = *params; err = request_firmware_direct(&fw_update->fw, file_name, &dev->dev); if (err) { NL_SET_ERR_MSG(info->extack, "Failed to request module firmware image"); goto err_free; } err = module_flash_fw_work_init(module_fw, dev, info->extack); if (err < 0) goto err_release_firmware; dev->ethtool->module_fw_flash_in_progress = true; netdev_hold(dev, &module_fw->dev_tracker, GFP_KERNEL); fw_update->dev = dev; fw_update->ntf_params.portid = info->snd_portid; fw_update->ntf_params.seq = info->snd_seq; fw_update->ntf_params.closed_sock = false; err = ethnl_sock_priv_set(skb, dev, fw_update->ntf_params.portid, ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH); if (err < 0) goto err_release_firmware; err = module_flash_fw_work_list_add(module_fw, info); if (err < 0) goto err_release_firmware; schedule_work(&module_fw->work); return 0; err_release_firmware: release_firmware(fw_update->fw); err_free: kfree(module_fw); return err; } static int module_flash_fw(struct net_device *dev, struct nlattr **tb, struct sk_buff *skb, struct genl_info *info) { struct ethtool_module_fw_flash_params params = {}; const char *file_name; struct nlattr *attr; if (GENL_REQ_ATTR_CHECK(info, ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME)) return -EINVAL; file_name = nla_data(tb[ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME]); attr = tb[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD]; if (attr) { params.password = cpu_to_be32(nla_get_u32(attr)); params.password_valid = true; } return module_flash_fw_schedule(dev, file_name, ¶ms, skb, info); } static int ethnl_module_fw_flash_validate(struct net_device *dev, struct netlink_ext_ack *extack) { struct devlink_port *devlink_port = dev->devlink_port; const struct ethtool_ops *ops = dev->ethtool_ops; if (!ops->set_module_eeprom_by_page || !ops->get_module_eeprom_by_page) { NL_SET_ERR_MSG(extack, "Flashing module firmware is not supported by this device"); return -EOPNOTSUPP; } if (!ops->reset) { NL_SET_ERR_MSG(extack, "Reset module is not supported by this device, so flashing is not permitted"); return -EOPNOTSUPP; } if (dev->ethtool->module_fw_flash_in_progress) { NL_SET_ERR_MSG(extack, "Module firmware flashing already in progress"); return -EBUSY; } if (dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Netdevice is up, so flashing is not permitted"); return -EBUSY; } if (devlink_port && devlink_port->attrs.split) { NL_SET_ERR_MSG(extack, "Can't perform firmware flashing on a split port"); return -EOPNOTSUPP; } return 0; } int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info) { struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; struct net_device *dev; int ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MODULE_FW_FLASH_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; rtnl_lock(); netdev_lock_ops(dev); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_unlock; ret = ethnl_module_fw_flash_validate(dev, info->extack); if (ret < 0) goto out_unlock; ret = module_flash_fw(dev, tb, skb, info); ethnl_ops_complete(dev); out_unlock: netdev_unlock_ops(dev); rtnl_unlock(); ethnl_parse_header_dev_put(&req_info); return ret; } /* MODULE_FW_FLASH_NTF */ static int ethnl_module_fw_flash_ntf_put_err(struct sk_buff *skb, char *err_msg, char *sub_err_msg) { int err_msg_len, sub_err_msg_len, total_len; struct nlattr *attr; if (!err_msg) return 0; err_msg_len = strlen(err_msg); total_len = err_msg_len + 2; /* For period and NUL. */ if (sub_err_msg) { sub_err_msg_len = strlen(sub_err_msg); total_len += sub_err_msg_len + 2; /* For ", ". */ } attr = nla_reserve(skb, ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG, total_len); if (!attr) return -ENOMEM; if (sub_err_msg) sprintf(nla_data(attr), "%s, %s.", err_msg, sub_err_msg); else sprintf(nla_data(attr), "%s.", err_msg); return 0; } static void ethnl_module_fw_flash_ntf(struct net_device *dev, enum ethtool_module_fw_flash_status status, struct ethnl_module_fw_flash_ntf_params *ntf_params, char *err_msg, char *sub_err_msg, u64 done, u64 total) { struct sk_buff *skb; void *hdr; int ret; if (ntf_params->closed_sock) return; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return; hdr = ethnl_unicast_put(skb, ntf_params->portid, ++ntf_params->seq, ETHTOOL_MSG_MODULE_FW_FLASH_NTF); if (!hdr) goto err_skb; ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_MODULE_FW_FLASH_HEADER); if (ret < 0) goto err_skb; if (nla_put_u32(skb, ETHTOOL_A_MODULE_FW_FLASH_STATUS, status)) goto err_skb; ret = ethnl_module_fw_flash_ntf_put_err(skb, err_msg, sub_err_msg); if (ret < 0) goto err_skb; if (nla_put_uint(skb, ETHTOOL_A_MODULE_FW_FLASH_DONE, done)) goto err_skb; if (nla_put_uint(skb, ETHTOOL_A_MODULE_FW_FLASH_TOTAL, total)) goto err_skb; genlmsg_end(skb, hdr); genlmsg_unicast(dev_net(dev), skb, ntf_params->portid); return; err_skb: nlmsg_free(skb); } void ethnl_module_fw_flash_ntf_err(struct net_device *dev, struct ethnl_module_fw_flash_ntf_params *params, char *err_msg, char *sub_err_msg) { ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR, params, err_msg, sub_err_msg, 0, 0); } void ethnl_module_fw_flash_ntf_start(struct net_device *dev, struct ethnl_module_fw_flash_ntf_params *params) { ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED, params, NULL, NULL, 0, 0); } void ethnl_module_fw_flash_ntf_complete(struct net_device *dev, struct ethnl_module_fw_flash_ntf_params *params) { ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED, params, NULL, NULL, 0, 0); } void ethnl_module_fw_flash_ntf_in_progress(struct net_device *dev, struct ethnl_module_fw_flash_ntf_params *params, u64 done, u64 total) { ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS, params, NULL, NULL, done, total); } |
| 1 3 3 3 3 27 5 4 4 27 27 25 27 27 27 27 27 27 27 11 11 11 6 7 7 7 7 7 7 7 7 7 7 10 9 1 8 1 7 1 6 6 6 6 6 3 3 3 6 4 4 6 4 6 10 1 1 5 5 3 1 3 2 2 1 2 2 1 1 1 1 1 1 1 5 12 12 11 2 9 9 7 12 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 14 7 14 14 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_gred.c Generic Random Early Detection queue. * * Authors: J Hadi Salim (hadi@cyberus.ca) 1998-2002 * * 991129: - Bug fix with grio mode * - a better sing. AvgQ mode with Grio(WRED) * - A finer grained VQ dequeue based on suggestion * from Ren Liu * - More error checks * * For all the glorious comments look at include/net/red.h */ #include <linux/slab.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/red.h> #define GRED_DEF_PRIO (MAX_DPs / 2) #define GRED_VQ_MASK (MAX_DPs - 1) #define GRED_VQ_RED_FLAGS (TC_RED_ECN | TC_RED_HARDDROP) struct gred_sched_data; struct gred_sched; struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop parameters */ u32 red_flags; /* virtualQ version of red_flags */ u64 bytesin; /* bytes seen on virtualQ so far*/ u32 packetsin; /* packets seen on virtualQ so far*/ u32 backlog; /* bytes on the virtualQ */ u8 prio; /* the prio of this vq */ struct red_parms parms; struct red_vars vars; struct red_stats stats; }; enum { GRED_WRED_MODE = 1, GRED_RIO_MODE, }; struct gred_sched { struct gred_sched_data *tab[MAX_DPs]; unsigned long flags; u32 red_flags; u32 DPs; u32 def; struct red_vars wred_set; struct tc_gred_qopt_offload *opt; }; static inline int gred_wred_mode(struct gred_sched *table) { return test_bit(GRED_WRED_MODE, &table->flags); } static inline void gred_enable_wred_mode(struct gred_sched *table) { __set_bit(GRED_WRED_MODE, &table->flags); } static inline void gred_disable_wred_mode(struct gred_sched *table) { __clear_bit(GRED_WRED_MODE, &table->flags); } static inline int gred_rio_mode(struct gred_sched *table) { return test_bit(GRED_RIO_MODE, &table->flags); } static inline void gred_enable_rio_mode(struct gred_sched *table) { __set_bit(GRED_RIO_MODE, &table->flags); } static inline void gred_disable_rio_mode(struct gred_sched *table) { __clear_bit(GRED_RIO_MODE, &table->flags); } static inline int gred_wred_mode_check(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); int i; /* Really ugly O(n^2) but shouldn't be necessary too frequent. */ for (i = 0; i < table->DPs; i++) { struct gred_sched_data *q = table->tab[i]; int n; if (q == NULL) continue; for (n = i + 1; n < table->DPs; n++) if (table->tab[n] && table->tab[n]->prio == q->prio) return 1; } return 0; } static inline unsigned int gred_backlog(struct gred_sched *table, struct gred_sched_data *q, struct Qdisc *sch) { if (gred_wred_mode(table)) return sch->qstats.backlog; else return q->backlog; } static inline u16 tc_index_to_dp(struct sk_buff *skb) { return skb->tc_index & GRED_VQ_MASK; } static inline void gred_load_wred_set(const struct gred_sched *table, struct gred_sched_data *q) { q->vars.qavg = table->wred_set.qavg; q->vars.qidlestart = table->wred_set.qidlestart; } static inline void gred_store_wred_set(struct gred_sched *table, struct gred_sched_data *q) { table->wred_set.qavg = q->vars.qavg; table->wred_set.qidlestart = q->vars.qidlestart; } static int gred_use_ecn(struct gred_sched_data *q) { return q->red_flags & TC_RED_ECN; } static int gred_use_harddrop(struct gred_sched_data *q) { return q->red_flags & TC_RED_HARDDROP; } static bool gred_per_vq_red_flags_used(struct gred_sched *table) { unsigned int i; /* Local per-vq flags couldn't have been set unless global are 0 */ if (table->red_flags) return false; for (i = 0; i < MAX_DPs; i++) if (table->tab[i] && table->tab[i]->red_flags) return true; return false; } static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct gred_sched_data *q = NULL; struct gred_sched *t = qdisc_priv(sch); unsigned long qavg = 0; u16 dp = tc_index_to_dp(skb); if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { dp = t->def; q = t->tab[dp]; if (!q) { /* Pass through packets not assigned to a DP * if no default DP has been configured. This * allows for DP flows to be left untouched. */ if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) return qdisc_enqueue_tail(skb, sch); else goto drop; } /* fix tc_index? --could be controversial but needed for requeueing */ skb->tc_index = (skb->tc_index & ~GRED_VQ_MASK) | dp; } /* sum up all the qaves of prios < ours to get the new qave */ if (!gred_wred_mode(t) && gred_rio_mode(t)) { int i; for (i = 0; i < t->DPs; i++) { if (t->tab[i] && t->tab[i]->prio < q->prio && !red_is_idling(&t->tab[i]->vars)) qavg += t->tab[i]->vars.qavg; } } q->packetsin++; q->bytesin += qdisc_pkt_len(skb); if (gred_wred_mode(t)) gred_load_wred_set(t, q); q->vars.qavg = red_calc_qavg(&q->parms, &q->vars, gred_backlog(t, q, sch)); if (red_is_idling(&q->vars)) red_end_of_idle_period(&q->vars); if (gred_wred_mode(t)) gred_store_wred_set(t, q); switch (red_action(&q->parms, &q->vars, q->vars.qavg + qavg)) { case RED_DONT_MARK: break; case RED_PROB_MARK: qdisc_qstats_overlimit(sch); if (!gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.prob_drop++; goto congestion_drop; } q->stats.prob_mark++; break; case RED_HARD_MARK: qdisc_qstats_overlimit(sch); if (gred_use_harddrop(q) || !gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.forced_drop++; goto congestion_drop; } q->stats.forced_mark++; break; } if (gred_backlog(t, q, sch) + qdisc_pkt_len(skb) <= q->limit) { q->backlog += qdisc_pkt_len(skb); return qdisc_enqueue_tail(skb, sch); } q->stats.pdrop++; drop: return qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT); congestion_drop: qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_CONGESTED); return NET_XMIT_CN; } static struct sk_buff *gred_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); skb = qdisc_dequeue_head(sch); if (skb) { struct gred_sched_data *q; u16 dp = tc_index_to_dp(skb); if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x after dequeue, screwing up backlog\n", tc_index_to_dp(skb)); } else { q->backlog -= qdisc_pkt_len(skb); if (gred_wred_mode(t)) { if (!sch->qstats.backlog) red_start_of_idle_period(&t->wred_set); } else { if (!q->backlog) red_start_of_idle_period(&q->vars); } } return skb; } return NULL; } static void gred_reset(struct Qdisc *sch) { int i; struct gred_sched *t = qdisc_priv(sch); qdisc_reset_queue(sch); for (i = 0; i < t->DPs; i++) { struct gred_sched_data *q = t->tab[i]; if (!q) continue; red_restart(&q->vars); q->backlog = 0; } } static void gred_offload(struct Qdisc *sch, enum tc_gred_command command) { struct gred_sched *table = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_gred_qopt_offload *opt = table->opt; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; memset(opt, 0, sizeof(*opt)); opt->command = command; opt->handle = sch->handle; opt->parent = sch->parent; if (command == TC_GRED_REPLACE) { unsigned int i; opt->set.grio_on = gred_rio_mode(table); opt->set.wred_on = gred_wred_mode(table); opt->set.dp_cnt = table->DPs; opt->set.dp_def = table->def; for (i = 0; i < table->DPs; i++) { struct gred_sched_data *q = table->tab[i]; if (!q) continue; opt->set.tab[i].present = true; opt->set.tab[i].limit = q->limit; opt->set.tab[i].prio = q->prio; opt->set.tab[i].min = q->parms.qth_min >> q->parms.Wlog; opt->set.tab[i].max = q->parms.qth_max >> q->parms.Wlog; opt->set.tab[i].is_ecn = gred_use_ecn(q); opt->set.tab[i].is_harddrop = gred_use_harddrop(q); opt->set.tab[i].probability = q->parms.max_P; opt->set.tab[i].backlog = &q->backlog; } opt->set.qstats = &sch->qstats; } dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, opt); } static int gred_offload_dump_stats(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt_offload *hw_stats; u64 bytes = 0, packets = 0; unsigned int i; int ret; hw_stats = kzalloc(sizeof(*hw_stats), GFP_KERNEL); if (!hw_stats) return -ENOMEM; hw_stats->command = TC_GRED_STATS; hw_stats->handle = sch->handle; hw_stats->parent = sch->parent; for (i = 0; i < MAX_DPs; i++) { gnet_stats_basic_sync_init(&hw_stats->stats.bstats[i]); if (table->tab[i]) hw_stats->stats.xstats[i] = &table->tab[i]->stats; } ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats); /* Even if driver returns failure adjust the stats - in case offload * ended but driver still wants to adjust the values. */ sch_tree_lock(sch); for (i = 0; i < MAX_DPs; i++) { if (!table->tab[i]) continue; table->tab[i]->packetsin += u64_stats_read(&hw_stats->stats.bstats[i].packets); table->tab[i]->bytesin += u64_stats_read(&hw_stats->stats.bstats[i].bytes); table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog; bytes += u64_stats_read(&hw_stats->stats.bstats[i].bytes); packets += u64_stats_read(&hw_stats->stats.bstats[i].packets); sch->qstats.qlen += hw_stats->stats.qstats[i].qlen; sch->qstats.backlog += hw_stats->stats.qstats[i].backlog; sch->qstats.drops += hw_stats->stats.qstats[i].drops; sch->qstats.requeues += hw_stats->stats.qstats[i].requeues; sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; } _bstats_update(&sch->bstats, bytes, packets); sch_tree_unlock(sch); kfree(hw_stats); return ret; } static inline void gred_destroy_vq(struct gred_sched_data *q) { kfree(q); } static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_sopt *sopt; bool red_flags_changed; int i; if (!dps) return -EINVAL; sopt = nla_data(dps); if (sopt->DPs > MAX_DPs) { NL_SET_ERR_MSG_MOD(extack, "number of virtual queues too high"); return -EINVAL; } if (sopt->DPs == 0) { NL_SET_ERR_MSG_MOD(extack, "number of virtual queues can't be 0"); return -EINVAL; } if (sopt->def_DP >= sopt->DPs) { NL_SET_ERR_MSG_MOD(extack, "default virtual queue above virtual queue count"); return -EINVAL; } if (sopt->flags && gred_per_vq_red_flags_used(table)) { NL_SET_ERR_MSG_MOD(extack, "can't set per-Qdisc RED flags when per-virtual queue flags are used"); return -EINVAL; } sch_tree_lock(sch); table->DPs = sopt->DPs; table->def = sopt->def_DP; red_flags_changed = table->red_flags != sopt->flags; table->red_flags = sopt->flags; /* * Every entry point to GRED is synchronized with the above code * and the DP is checked against DPs, i.e. shadowed VQs can no * longer be found so we can unlock right here. */ sch_tree_unlock(sch); if (sopt->grio) { gred_enable_rio_mode(table); gred_disable_wred_mode(table); if (gred_wred_mode_check(sch)) gred_enable_wred_mode(table); } else { gred_disable_rio_mode(table); gred_disable_wred_mode(table); } if (red_flags_changed) for (i = 0; i < table->DPs; i++) if (table->tab[i]) table->tab[i]->red_flags = table->red_flags & GRED_VQ_RED_FLAGS; for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n", i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } } gred_offload(sch, TC_GRED_REPLACE); return 0; } static inline int gred_change_vq(struct Qdisc *sch, int dp, struct tc_gred_qopt *ctl, int prio, u8 *stab, u32 max_P, struct gred_sched_data **prealloc, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) { NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; } if (!q) { table->tab[dp] = q = *prealloc; *prealloc = NULL; if (!q) return -ENOMEM; q->red_flags = table->red_flags & GRED_VQ_RED_FLAGS; } q->DP = dp; q->prio = prio; if (ctl->limit > sch->limit) q->limit = sch->limit; else q->limit = ctl->limit; if (q->backlog == 0) red_end_of_idle_period(&q->vars); red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, stab, max_P); red_set_vars(&q->vars); return 0; } static const struct nla_policy gred_vq_policy[TCA_GRED_VQ_MAX + 1] = { [TCA_GRED_VQ_DP] = { .type = NLA_U32 }, [TCA_GRED_VQ_FLAGS] = { .type = NLA_U32 }, }; static const struct nla_policy gred_vqe_policy[TCA_GRED_VQ_ENTRY_MAX + 1] = { [TCA_GRED_VQ_ENTRY] = { .type = NLA_NESTED }, }; static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = { [TCA_GRED_PARMS] = { .len = sizeof(struct tc_gred_qopt) }, [TCA_GRED_STAB] = { .len = 256 }, [TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) }, [TCA_GRED_MAX_P] = { .type = NLA_U32 }, [TCA_GRED_LIMIT] = { .type = NLA_U32 }, [TCA_GRED_VQ_LIST] = { .type = NLA_NESTED }, }; static void gred_vq_apply(struct gred_sched *table, const struct nlattr *entry) { struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; u32 dp; nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, NULL); dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); if (tb[TCA_GRED_VQ_FLAGS]) table->tab[dp]->red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); } static void gred_vqs_apply(struct gred_sched *table, struct nlattr *vqs) { const struct nlattr *attr; int rem; nla_for_each_nested(attr, vqs, rem) { switch (nla_type(attr)) { case TCA_GRED_VQ_ENTRY: gred_vq_apply(table, attr); break; } } } static int gred_vq_validate(struct gred_sched *table, u32 cdp, const struct nlattr *entry, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; int err; u32 dp; err = nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, extack); if (err < 0) return err; if (!tb[TCA_GRED_VQ_DP]) { NL_SET_ERR_MSG_MOD(extack, "Virtual queue with no index specified"); return -EINVAL; } dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); if (dp >= table->DPs) { NL_SET_ERR_MSG_MOD(extack, "Virtual queue with index out of bounds"); return -EINVAL; } if (dp != cdp && !table->tab[dp]) { NL_SET_ERR_MSG_MOD(extack, "Virtual queue not yet instantiated"); return -EINVAL; } if (tb[TCA_GRED_VQ_FLAGS]) { u32 red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); if (table->red_flags && table->red_flags != red_flags) { NL_SET_ERR_MSG_MOD(extack, "can't change per-virtual queue RED flags when per-Qdisc flags are used"); return -EINVAL; } if (red_flags & ~GRED_VQ_RED_FLAGS) { NL_SET_ERR_MSG_MOD(extack, "invalid RED flags specified"); return -EINVAL; } } return 0; } static int gred_vqs_validate(struct gred_sched *table, u32 cdp, struct nlattr *vqs, struct netlink_ext_ack *extack) { const struct nlattr *attr; int rem, err; err = nla_validate_nested_deprecated(vqs, TCA_GRED_VQ_ENTRY_MAX, gred_vqe_policy, extack); if (err < 0) return err; nla_for_each_nested(attr, vqs, rem) { switch (nla_type(attr)) { case TCA_GRED_VQ_ENTRY: err = gred_vq_validate(table, cdp, attr, extack); if (err) return err; break; default: NL_SET_ERR_MSG_MOD(extack, "GRED_VQ_LIST can contain only entry attributes"); return -EINVAL; } } if (rem > 0) { NL_SET_ERR_MSG_MOD(extack, "Trailing data after parsing virtual queue list"); return -EINVAL; } return 0; } static int gred_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt *ctl; struct nlattr *tb[TCA_GRED_MAX + 1]; int err, prio = GRED_DEF_PRIO; u8 *stab; u32 max_P; struct gred_sched_data *prealloc; err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy, extack); if (err < 0) return err; if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) { if (tb[TCA_GRED_LIMIT] != NULL) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } if (tb[TCA_GRED_PARMS] == NULL || tb[TCA_GRED_STAB] == NULL || tb[TCA_GRED_LIMIT] != NULL) { NL_SET_ERR_MSG_MOD(extack, "can't configure Qdisc and virtual queue at the same time"); return -EINVAL; } max_P = nla_get_u32_default(tb[TCA_GRED_MAX_P], 0); ctl = nla_data(tb[TCA_GRED_PARMS]); stab = nla_data(tb[TCA_GRED_STAB]); if (ctl->DP >= table->DPs) { NL_SET_ERR_MSG_MOD(extack, "virtual queue index above virtual queue count"); return -EINVAL; } if (tb[TCA_GRED_VQ_LIST]) { err = gred_vqs_validate(table, ctl->DP, tb[TCA_GRED_VQ_LIST], extack); if (err) return err; } if (gred_rio_mode(table)) { if (ctl->prio == 0) { int def_prio = GRED_DEF_PRIO; if (table->tab[table->def]) def_prio = table->tab[table->def]->prio; printk(KERN_DEBUG "GRED: DP %u does not have a prio " "setting default to %d\n", ctl->DP, def_prio); prio = def_prio; } else prio = ctl->prio; } prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); sch_tree_lock(sch); err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc, extack); if (err < 0) goto err_unlock_free; if (tb[TCA_GRED_VQ_LIST]) gred_vqs_apply(table, tb[TCA_GRED_VQ_LIST]); if (gred_rio_mode(table)) { gred_disable_wred_mode(table); if (gred_wred_mode_check(sch)) gred_enable_wred_mode(table); } sch_tree_unlock(sch); kfree(prealloc); gred_offload(sch, TC_GRED_REPLACE); return 0; err_unlock_free: sch_tree_unlock(sch); kfree(prealloc); return err; } static int gred_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct nlattr *tb[TCA_GRED_MAX + 1]; int err; if (!opt) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy, extack); if (err < 0) return err; if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) { NL_SET_ERR_MSG_MOD(extack, "virtual queue configuration can't be specified at initialization time"); return -EINVAL; } if (tb[TCA_GRED_LIMIT]) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); else sch->limit = qdisc_dev(sch)->tx_queue_len * psched_mtu(qdisc_dev(sch)); if (qdisc_dev(sch)->netdev_ops->ndo_setup_tc) { table->opt = kzalloc(sizeof(*table->opt), GFP_KERNEL); if (!table->opt) return -ENOMEM; } return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) { struct gred_sched *table = qdisc_priv(sch); struct nlattr *parms, *vqs, *opts = NULL; int i; u32 max_p[MAX_DPs]; struct tc_gred_sopt sopt = { .DPs = table->DPs, .def_DP = table->def, .grio = gred_rio_mode(table), .flags = table->red_flags, }; if (gred_offload_dump_stats(sch)) goto nla_put_failure; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_GRED_DPS, sizeof(sopt), &sopt)) goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; max_p[i] = q ? q->parms.max_P : 0; } if (nla_put(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit)) goto nla_put_failure; /* Old style all-in-one dump of VQs */ parms = nla_nest_start_noflag(skb, TCA_GRED_PARMS); if (parms == NULL) goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; struct tc_gred_qopt opt; unsigned long qavg; memset(&opt, 0, sizeof(opt)); if (!q) { /* hack -- fix at some point with proper message This is how we indicate to tc that there is no VQ at this DP */ opt.DP = MAX_DPs + i; goto append_opt; } opt.limit = q->limit; opt.DP = q->DP; opt.backlog = gred_backlog(table, q, sch); opt.prio = q->prio; opt.qth_min = q->parms.qth_min >> q->parms.Wlog; opt.qth_max = q->parms.qth_max >> q->parms.Wlog; opt.Wlog = q->parms.Wlog; opt.Plog = q->parms.Plog; opt.Scell_log = q->parms.Scell_log; opt.early = q->stats.prob_drop; opt.forced = q->stats.forced_drop; opt.pdrop = q->stats.pdrop; opt.packets = q->packetsin; opt.bytesin = q->bytesin; if (gred_wred_mode(table)) gred_load_wred_set(table, q); qavg = red_calc_qavg(&q->parms, &q->vars, q->vars.qavg >> q->parms.Wlog); opt.qave = qavg >> q->parms.Wlog; append_opt: if (nla_append(skb, sizeof(opt), &opt) < 0) goto nla_put_failure; } nla_nest_end(skb, parms); /* Dump the VQs again, in more structured way */ vqs = nla_nest_start_noflag(skb, TCA_GRED_VQ_LIST); if (!vqs) goto nla_put_failure; for (i = 0; i < MAX_DPs; i++) { struct gred_sched_data *q = table->tab[i]; struct nlattr *vq; if (!q) continue; vq = nla_nest_start_noflag(skb, TCA_GRED_VQ_ENTRY); if (!vq) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_DP, q->DP)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_FLAGS, q->red_flags)) goto nla_put_failure; /* Stats */ if (nla_put_u64_64bit(skb, TCA_GRED_VQ_STAT_BYTES, q->bytesin, TCA_GRED_VQ_PAD)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PACKETS, q->packetsin)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_BACKLOG, gred_backlog(table, q, sch))) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_DROP, q->stats.prob_drop)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_MARK, q->stats.prob_mark)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_DROP, q->stats.forced_drop)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_MARK, q->stats.forced_mark)) goto nla_put_failure; if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PDROP, q->stats.pdrop)) goto nla_put_failure; nla_nest_end(skb, vq); } nla_nest_end(skb, vqs); return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -EMSGSIZE; } static void gred_destroy(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); int i; for (i = 0; i < table->DPs; i++) gred_destroy_vq(table->tab[i]); if (table->opt) gred_offload(sch, TC_GRED_DESTROY); kfree(table->opt); } static struct Qdisc_ops gred_qdisc_ops __read_mostly = { .id = "gred", .priv_size = sizeof(struct gred_sched), .enqueue = gred_enqueue, .dequeue = gred_dequeue, .peek = qdisc_peek_head, .init = gred_init, .reset = gred_reset, .destroy = gred_destroy, .change = gred_change, .dump = gred_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("gred"); static int __init gred_module_init(void) { return register_qdisc(&gred_qdisc_ops); } static void __exit gred_module_exit(void) { unregister_qdisc(&gred_qdisc_ops); } module_init(gred_module_init) module_exit(gred_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic Random Early Detection qdisc"); |
| 21 21 21 20 20 6 14 13 13 13 13 9 13 13 13 5 6 6 6 6 6 8 6 7 3 2 1 6 6 6 8 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * UDPv6 GSO support */ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/indirect_call_wrapper.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" #include <net/gro.h> #include <net/gso.h> static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; unsigned int unfrag_ip6hlen, unfrag_len; struct frag_hdr *fptr; u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; int err; if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); else { const struct ipv6hdr *ipv6h; struct udphdr *uh; if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ uh = udp_hdr(skb); ipv6h = ipv6_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v6_check(skb->len, &ipv6h->saddr, &ipv6h->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) return ERR_PTR(err); unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + unfrag_ip6hlen + tnl_hlen; packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; skb->mac_header -= frag_hdr_sz; skb->network_header -= frag_hdr_sz; fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() */ segs = skb_segment(skb, features); } out: return segs; } static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = skb_gro_network_header(skb); struct net *net = dev_net_rcu(skb->dev); struct sock *sk; int iif, sdif; sk = udp_tunnel_sk(net, true); if (sk && dport == htons(sk->sk_num)) return sk; inet6_get_iif_sdif(skb, &iif, &sdif); return __udp6_lib_lookup(net, &iph->saddr, sport, &iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, ip6_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, ip6_gro_compute_pseudo); skip: if (static_branch_unlikely(&udpv6_encap_needed_key)) sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } int __init udpv6_offload_init(void) { net_hotdata.udpv6_offload = (struct net_offload) { .callbacks = { .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, }, }; return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } |
| 14 14 14 5 50 50 56 54 54 11 10 1 1 17 9 9 8 8 1 1 1 36 14 14 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2020 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved. */ #ifndef IB_VERBS_H #define IB_VERBS_H #include <linux/ethtool.h> #include <linux/types.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rwsem.h> #include <linux/workqueue.h> #include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> #include <net/ipv6.h> #include <net/ip.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/refcount.h> #include <linux/if_link.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/dim.h> #include <uapi/rdma/ib_user_verbs.h> #include <rdma/rdma_counter.h> #include <rdma/restrack.h> #include <rdma/signature.h> #include <uapi/rdma/rdma_user_ioctl.h> #include <uapi/rdma/ib_user_ioctl_verbs.h> #include <linux/pci-tph.h> #define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN struct ib_umem_odp; struct ib_uqp_object; struct ib_usrq_object; struct ib_uwq_object; struct rdma_cm_id; struct ib_port; struct hw_stats_device_data; extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; extern struct workqueue_struct *ib_comp_unbound_wq; struct ib_ucq_object; __printf(2, 3) __cold void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_alert(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_crit(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_err(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_warn(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_notice(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_info(const struct ib_device *ibdev, const char *format, ...); #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define ibdev_dbg(__dev, format, args...) \ dynamic_ibdev_dbg(__dev, format, ##args) #else __printf(2, 3) __cold static inline void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {} #endif #define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ if (__ratelimit(&_rs)) \ ibdev_level(ibdev, fmt, ##__VA_ARGS__); \ } while (0) #define ibdev_emerg_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__) #define ibdev_alert_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__) #define ibdev_crit_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__) #define ibdev_err_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__) #define ibdev_warn_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__) #define ibdev_notice_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__) #define ibdev_info_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define ibdev_dbg_ratelimited(ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \ __dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \ ##__VA_ARGS__); \ } while (0) #else __printf(2, 3) __cold static inline void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {} #endif union ib_gid { u8 raw[16]; struct { __be64 subnet_prefix; __be64 interface_id; } global; }; extern union ib_gid zgid; enum ib_gid_type { IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB, IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1, IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2, IB_GID_TYPE_SIZE }; #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { struct net_device __rcu *ndev; struct ib_device *device; union ib_gid gid; enum ib_gid_type gid_type; u16 index; u32 port_num; }; enum { /* set the local administered indication */ IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2, }; enum rdma_transport_type { RDMA_TRANSPORT_IB, RDMA_TRANSPORT_IWARP, RDMA_TRANSPORT_USNIC, RDMA_TRANSPORT_USNIC_UDP, RDMA_TRANSPORT_UNSPECIFIED, }; enum rdma_protocol_type { RDMA_PROTOCOL_IB, RDMA_PROTOCOL_IBOE, RDMA_PROTOCOL_IWARP, RDMA_PROTOCOL_USNIC_UDP }; __attribute_const__ enum rdma_transport_type rdma_node_get_transport(unsigned int node_type); enum rdma_network_type { RDMA_NETWORK_IB, RDMA_NETWORK_ROCE_V1, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) { if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; else if (network_type == RDMA_NETWORK_ROCE_V1) return IB_GID_TYPE_ROCE; else return IB_GID_TYPE_IB; } static inline enum rdma_network_type rdma_gid_attr_network_type(const struct ib_gid_attr *attr) { if (attr->gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; if (attr->gid_type == IB_GID_TYPE_ROCE) return RDMA_NETWORK_ROCE_V1; if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid)) return RDMA_NETWORK_IPV4; else return RDMA_NETWORK_IPV6; } enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB * messages and can verify the validity of checksum for * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", * which includes support for fast registrations (IB_WR_REG_MR, * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should * also be set by any iWarp device which must support FRs to comply * to the iWarp verbs spec. iWarp devices also support the * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, /* Placement type attributes */ IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL, IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT, IB_DEVICE_ATOMIC_WRITE = IB_UVERBS_DEVICE_ATOMIC_WRITE, }; enum ib_kernel_cap_flags { /* * This device supports a per-device lkey or stag that can be * used without performing a memory registration for the local * memory. Note that ULPs should never check this flag, but * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ IBK_LOCAL_DMA_LKEY = 1 << 0, /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ IBK_INTEGRITY_HANDOVER = 1 << 1, /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ IBK_ON_DEMAND_PAGING = 1 << 2, /* IB_MR_TYPE_SG_GAPS is supported */ IBK_SG_GAPS_REG = 1 << 3, /* Driver supports RDMA_NLDEV_CMD_DELLINK */ IBK_ALLOW_USER_UNREG = 1 << 4, /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ IBK_UD_TSO = 1 << 6, /* iopib will use the device ops: * get_vf_config * get_vf_guid * get_vf_stats * set_vf_guid * set_vf_link_state */ IBK_VIRTUAL_FUNCTION = 1 << 7, /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ IBK_RDMA_NETDEV_OPA = 1 << 8, }; enum ib_atomic_cap { IB_ATOMIC_NONE, IB_ATOMIC_HCA, IB_ATOMIC_GLOB }; enum ib_odp_general_cap_bits { IB_ODP_SUPPORT = IB_UVERBS_ODP_SUPPORT, IB_ODP_SUPPORT_IMPLICIT = IB_UVERBS_ODP_SUPPORT_IMPLICIT, }; enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_SEND = IB_UVERBS_ODP_SUPPORT_SEND, IB_ODP_SUPPORT_RECV = IB_UVERBS_ODP_SUPPORT_RECV, IB_ODP_SUPPORT_WRITE = IB_UVERBS_ODP_SUPPORT_WRITE, IB_ODP_SUPPORT_READ = IB_UVERBS_ODP_SUPPORT_READ, IB_ODP_SUPPORT_ATOMIC = IB_UVERBS_ODP_SUPPORT_ATOMIC, IB_ODP_SUPPORT_SRQ_RECV = IB_UVERBS_ODP_SUPPORT_SRQ_RECV, IB_ODP_SUPPORT_FLUSH = IB_UVERBS_ODP_SUPPORT_FLUSH, IB_ODP_SUPPORT_ATOMIC_WRITE = IB_UVERBS_ODP_SUPPORT_ATOMIC_WRITE, }; struct ib_odp_caps { uint64_t general_caps; struct { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; uint32_t xrc_odp_caps; } per_transport_caps; }; struct ib_rss_caps { /* Corresponding bit will be set if qp type from * 'enum ib_qp_type' is supported, e.g. * supported_qpts |= 1 << IB_QPT_UD */ u32 supported_qpts; u32 max_rwq_indirection_tables; u32 max_rwq_indirection_table_size; }; enum ib_tm_cap_flags { /* Support tag matching with rendezvous offload for RC transport */ IB_TM_CAP_RNDV_RC = 1 << 0, }; struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ u32 max_num_tags; /* From enum ib_tm_cap_flags */ u32 flags; /* Max number of outstanding list operations */ u32 max_ops; /* Max number of SGE in tag matching entry */ u32 max_sge; }; struct ib_cq_init_attr { unsigned int cqe; u32 comp_vector; u32 flags; }; enum ib_cq_attr_mask { IB_CQ_MODERATE = 1 << 0, }; struct ib_cq_caps { u16 max_cq_moderation_count; u16 max_cq_moderation_period; }; struct ib_dm_mr_attr { u64 length; u64 offset; u32 access_flags; }; struct ib_dm_alloc_attr { u64 length; u32 alignment; u32 flags; }; struct ib_device_attr { u64 fw_ver; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; u32 vendor_id; u32 vendor_part_id; u32 hw_ver; int max_qp; int max_qp_wr; u64 device_cap_flags; u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; int max_cq; int max_cqe; int max_mr; int max_pd; int max_qp_rd_atom; int max_ee_rd_atom; int max_res_rd_atom; int max_qp_init_rd_atom; int max_ee_init_rd_atom; enum ib_atomic_cap atomic_cap; enum ib_atomic_cap masked_atomic_cap; int max_ee; int max_rdd; int max_mw; int max_raw_ipv6_qp; int max_raw_ethy_qp; int max_mcast_grp; int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; int max_srq; int max_srq_wr; int max_srq_sge; unsigned int max_fast_reg_page_list_len; unsigned int max_pi_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; int sig_prot_cap; int sig_guard_cap; struct ib_odp_caps odp_caps; uint64_t timestamp_mask; uint64_t hca_core_clock; /* in KHZ */ struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ struct ib_tm_caps tm_caps; struct ib_cq_caps cq_caps; u64 max_dm_size; /* Max entries for sgl for optimized performance per READ */ u32 max_sgl_rd; }; enum ib_mtu { IB_MTU_256 = 1, IB_MTU_512 = 2, IB_MTU_1024 = 3, IB_MTU_2048 = 4, IB_MTU_4096 = 5 }; enum opa_mtu { OPA_MTU_8192 = 6, OPA_MTU_10240 = 7 }; static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; case IB_MTU_512: return 512; case IB_MTU_1024: return 1024; case IB_MTU_2048: return 2048; case IB_MTU_4096: return 4096; default: return -1; } } static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) { if (mtu >= 4096) return IB_MTU_4096; else if (mtu >= 2048) return IB_MTU_2048; else if (mtu >= 1024) return IB_MTU_1024; else if (mtu >= 512) return IB_MTU_512; else return IB_MTU_256; } static inline int opa_mtu_enum_to_int(enum opa_mtu mtu) { switch (mtu) { case OPA_MTU_8192: return 8192; case OPA_MTU_10240: return 10240; default: return(ib_mtu_enum_to_int((enum ib_mtu)mtu)); } } static inline enum opa_mtu opa_mtu_int_to_enum(int mtu) { if (mtu >= 10240) return OPA_MTU_10240; else if (mtu >= 8192) return OPA_MTU_8192; else return ((enum opa_mtu)ib_mtu_int_to_enum(mtu)); } enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, IB_PORT_INIT = 2, IB_PORT_ARMED = 3, IB_PORT_ACTIVE = 4, IB_PORT_ACTIVE_DEFER = 5 }; static inline const char *__attribute_const__ ib_port_state_to_str(enum ib_port_state state) { const char * const states[] = { [IB_PORT_NOP] = "NOP", [IB_PORT_DOWN] = "DOWN", [IB_PORT_INIT] = "INIT", [IB_PORT_ARMED] = "ARMED", [IB_PORT_ACTIVE] = "ACTIVE", [IB_PORT_ACTIVE_DEFER] = "ACTIVE_DEFER", }; if (state < ARRAY_SIZE(states)) return states[state]; return "UNKNOWN"; } enum ib_port_phys_state { IB_PORT_PHYS_STATE_SLEEP = 1, IB_PORT_PHYS_STATE_POLLING = 2, IB_PORT_PHYS_STATE_DISABLED = 3, IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4, IB_PORT_PHYS_STATE_LINK_UP = 5, IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6, IB_PORT_PHYS_STATE_PHY_TEST = 7, }; enum ib_port_width { IB_WIDTH_1X = 1, IB_WIDTH_2X = 16, IB_WIDTH_4X = 2, IB_WIDTH_8X = 4, IB_WIDTH_12X = 8 }; static inline int ib_width_enum_to_int(enum ib_port_width width) { switch (width) { case IB_WIDTH_1X: return 1; case IB_WIDTH_2X: return 2; case IB_WIDTH_4X: return 4; case IB_WIDTH_8X: return 8; case IB_WIDTH_12X: return 12; default: return -1; } } enum ib_port_speed { IB_SPEED_SDR = 1, IB_SPEED_DDR = 2, IB_SPEED_QDR = 4, IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, IB_SPEED_HDR = 64, IB_SPEED_NDR = 128, IB_SPEED_XDR = 256, }; enum ib_stat_flag { IB_STAT_FLAG_OPTIONAL = 1 << 0, }; /** * struct rdma_stat_desc * @name - The name of the counter * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL * @priv - Driver private information; Core code should not use */ struct rdma_stat_desc { const char *name; unsigned int flags; const void *priv; }; /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters * should be before being updated again. Stored in jiffies, defaults * to 10 milliseconds, drivers can override the default be specifying * their own value during their allocation routine. * @descs - Array of pointers to static descriptors used for the counters * in directory. * @is_disabled - A bitmap to indicate each counter is currently disabled * or not. * @num_counters - How many hardware counters there are. If name is * shorter than this number, a kernel oops will result. Driver authors * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) * in their code to prevent this. * @value - Array of u64 counters that are accessed by the sysfs code and * filled in by the drivers get_stats routine */ struct rdma_hw_stats { struct mutex lock; /* Protect lifespan and values[] */ unsigned long timestamp; unsigned long lifespan; const struct rdma_stat_desc *descs; unsigned long *is_disabled; int num_counters; u64 value[] __counted_by(num_counters); }; #define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const struct rdma_stat_desc *descs, int num_counters, unsigned long lifespan); void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats); /* Define bits for the various functionality this port needs to be supported by * the core. */ /* Management 0x00000FFF */ #define RDMA_CORE_CAP_IB_MAD 0x00000001 #define RDMA_CORE_CAP_IB_SMI 0x00000002 #define RDMA_CORE_CAP_IB_CM 0x00000004 #define RDMA_CORE_CAP_IW_CM 0x00000008 #define RDMA_CORE_CAP_IB_SA 0x00000010 #define RDMA_CORE_CAP_OPA_MAD 0x00000020 /* Address format 0x000FF000 */ #define RDMA_CORE_CAP_AF_IB 0x00001000 #define RDMA_CORE_CAP_ETH_AH 0x00002000 #define RDMA_CORE_CAP_OPA_AH 0x00004000 #define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000 /* Protocol 0xFFF00000 */ #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000 #define RDMA_CORE_CAP_PROT_USNIC 0x02000000 #define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \ | RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP) #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_SMI \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_IB_SA \ | RDMA_CORE_CAP_AF_IB) #define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ | RDMA_CORE_CAP_OPA_MAD) #define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET) #define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC) struct ib_port_attr { u64 subnet_prefix; enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; u32 phys_mtu; int gid_tbl_len; unsigned int ip_gids:1; /* This is the value from PortInfo CapabilityMask, defined by IBA */ u32 port_cap_flags; u32 max_msg_sz; u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; u32 sm_lid; u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; u8 subnet_timeout; u8 init_type_reply; u8 active_width; u16 active_speed; u8 phys_state; u16 port_cap_flags2; }; enum ib_device_modify_flags { IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; #define IB_DEVICE_NODE_DESC_MAX 64 struct ib_device_modify { u64 sys_image_guid; char node_desc[IB_DEVICE_NODE_DESC_MAX]; }; enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), IB_PORT_RESET_QKEY_CNTR = (1<<3), IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { u32 set_port_cap_mask; u32 clr_port_cap_mask; u8 init_type; }; enum ib_event_type { IB_EVENT_CQ_ERR, IB_EVENT_QP_FATAL, IB_EVENT_QP_REQ_ERR, IB_EVENT_QP_ACCESS_ERR, IB_EVENT_COMM_EST, IB_EVENT_SQ_DRAINED, IB_EVENT_PATH_MIG, IB_EVENT_PATH_MIG_ERR, IB_EVENT_DEVICE_FATAL, IB_EVENT_PORT_ACTIVE, IB_EVENT_PORT_ERR, IB_EVENT_LID_CHANGE, IB_EVENT_PKEY_CHANGE, IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); struct ib_event { struct ib_device *device; union { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; struct ib_wq *wq; u32 port_num; } element; enum ib_event_type event; }; struct ib_event_handler { struct ib_device *device; void (*handler)(struct ib_event_handler *, struct ib_event *); struct list_head list; }; #define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \ do { \ (_ptr)->device = _device; \ (_ptr)->handler = _handler; \ INIT_LIST_HEAD(&(_ptr)->list); \ } while (0) struct ib_global_route { const struct ib_gid_attr *sgid_attr; union ib_gid dgid; u32 flow_label; u8 sgid_index; u8 hop_limit; u8 traffic_class; }; struct ib_grh { __be32 version_tclass_flow; __be16 paylen; u8 next_hdr; u8 hop_limit; union ib_gid sgid; union ib_gid dgid; }; union rdma_network_hdr { struct ib_grh ibgrh; struct { /* The IB spec states that if it's IPv4, the header * is located in the last 20 bytes of the header. */ u8 reserved[20]; struct iphdr roce4grh; }; }; #define IB_QPN_MASK 0xFFFFFF enum { IB_MULTICAST_QPN = 0xffffff }; #define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) #define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000) enum ib_ah_flags { IB_AH_GRH = 1 }; enum ib_rate { IB_RATE_PORT_CURRENT = 0, IB_RATE_2_5_GBPS = 2, IB_RATE_5_GBPS = 5, IB_RATE_10_GBPS = 3, IB_RATE_20_GBPS = 6, IB_RATE_30_GBPS = 4, IB_RATE_40_GBPS = 7, IB_RATE_60_GBPS = 8, IB_RATE_80_GBPS = 9, IB_RATE_120_GBPS = 10, IB_RATE_14_GBPS = 11, IB_RATE_56_GBPS = 12, IB_RATE_112_GBPS = 13, IB_RATE_168_GBPS = 14, IB_RATE_25_GBPS = 15, IB_RATE_100_GBPS = 16, IB_RATE_200_GBPS = 17, IB_RATE_300_GBPS = 18, IB_RATE_28_GBPS = 19, IB_RATE_50_GBPS = 20, IB_RATE_400_GBPS = 21, IB_RATE_600_GBPS = 22, IB_RATE_800_GBPS = 23, }; /** * ib_rate_to_mult - Convert the IB rate enum to a multiple of the * base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate); /** * ib_rate_to_mbps - Convert the IB rate enum to Mbps. * For example, IB_RATE_2_5_GBPS will be converted to 2500. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); /** * enum ib_mr_type - memory region type * @IB_MR_TYPE_MEM_REG: memory region that is used for * normal registration * @IB_MR_TYPE_SG_GAPS: memory region that is capable to * register any arbitrary sg lists (without * the normal mr constraints - see * ib_map_mr_sg) * @IB_MR_TYPE_DM: memory region that is used for device * memory registration * @IB_MR_TYPE_USER: memory region that is used for the user-space * application * @IB_MR_TYPE_DMA: memory region that is used for DMA operations * without address translations (VA=PA) * @IB_MR_TYPE_INTEGRITY: memory region that is used for * data integrity operations */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SG_GAPS, IB_MR_TYPE_DM, IB_MR_TYPE_USER, IB_MR_TYPE_DMA, IB_MR_TYPE_INTEGRITY, }; enum ib_mr_status_check { IB_MR_CHECK_SIG_STATUS = 1, }; /** * struct ib_mr_status - Memory region status container * * @fail_status: Bitmask of MR checks status. For each * failed check a corresponding status bit is set. * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS * failure. */ struct ib_mr_status { u32 fail_status; struct ib_sig_err sig_err; }; /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. * @mult: multiple to convert. */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); struct rdma_ah_init_attr { struct rdma_ah_attr *ah_attr; u32 flags; struct net_device *xmit_slave; }; enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, }; struct ib_ah_attr { u16 dlid; u8 src_path_bits; }; struct roce_ah_attr { u8 dmac[ETH_ALEN]; }; struct opa_ah_attr { u32 dlid; u8 src_path_bits; bool make_grd; }; struct rdma_ah_attr { struct ib_global_route grh; u8 sl; u8 static_rate; u32 port_num; u8 ah_flags; enum rdma_ah_attr_type type; union { struct ib_ah_attr ib; struct roce_ah_attr roce; struct opa_ah_attr opa; }; }; enum ib_wc_status { IB_WC_SUCCESS, IB_WC_LOC_LEN_ERR, IB_WC_LOC_QP_OP_ERR, IB_WC_LOC_EEC_OP_ERR, IB_WC_LOC_PROT_ERR, IB_WC_WR_FLUSH_ERR, IB_WC_MW_BIND_ERR, IB_WC_BAD_RESP_ERR, IB_WC_LOC_ACCESS_ERR, IB_WC_REM_INV_REQ_ERR, IB_WC_REM_ACCESS_ERR, IB_WC_REM_OP_ERR, IB_WC_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR, IB_WC_LOC_RDD_VIOL_ERR, IB_WC_REM_INV_RD_REQ_ERR, IB_WC_REM_ABORT_ERR, IB_WC_INV_EECN_ERR, IB_WC_INV_EEC_STATE_ERR, IB_WC_FATAL_ERR, IB_WC_RESP_TIMEOUT_ERR, IB_WC_GENERAL_ERR }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { IB_WC_SEND = IB_UVERBS_WC_SEND, IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE, IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ, IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP, IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD, IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW, IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV, IB_WC_LSO = IB_UVERBS_WC_TSO, IB_WC_ATOMIC_WRITE = IB_UVERBS_WC_ATOMIC_WRITE, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, IB_WC_FLUSH = IB_UVERBS_WC_FLUSH, /* * Set value of IB_WC_RECV so consumers can test if a completion is a * receive by testing (opcode & IB_WC_RECV). */ IB_WC_RECV = 1 << 7, IB_WC_RECV_RDMA_WITH_IMM }; enum ib_wc_flags { IB_WC_GRH = 1, IB_WC_WITH_IMM = (1<<1), IB_WC_WITH_INVALIDATE = (1<<2), IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { union { u64 wr_id; struct ib_cqe *wr_cqe; }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; struct ib_qp *qp; union { __be32 imm_data; u32 invalidate_rkey; } ex; u32 src_qp; u32 slid; int wc_flags; u16 pkey_index; u8 sl; u8 dlid_path_bits; u32 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; u8 network_hdr_type; }; enum ib_cq_notify_flags { IB_CQ_SOLICITED = 1 << 0, IB_CQ_NEXT_COMP = 1 << 1, IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP, IB_CQ_REPORT_MISSED_EVENTS = 1 << 2, }; enum ib_srq_type { IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC, IB_SRQT_XRC = IB_UVERBS_SRQT_XRC, IB_SRQT_TM = IB_UVERBS_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) { return srq_type == IB_SRQT_XRC || srq_type == IB_SRQT_TM; } enum ib_srq_attr_mask { IB_SRQ_MAX_WR = 1 << 0, IB_SRQ_LIMIT = 1 << 1, }; struct ib_srq_attr { u32 max_wr; u32 max_sge; u32 srq_limit; }; struct ib_srq_init_attr { void (*event_handler)(struct ib_event *, void *); void *srq_context; struct ib_srq_attr attr; enum ib_srq_type srq_type; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; } xrc; struct { u32 max_num_tags; } tag_matching; }; } ext; }; struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; /* * Maximum number of rdma_rw_ctx structures in flight at a time. * ib_create_qp() will calculate the right amount of needed WRs * and MRs based on this. */ u32 max_rdma_ctxs; }; enum ib_sig_type { IB_SIGNAL_ALL_WR, IB_SIGNAL_REQ_WR }; enum ib_qp_type { /* * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries * here (and in that order) since the MAD layer uses them as * indices into a 2-entry table. */ IB_QPT_SMI, IB_QPT_GSI, IB_QPT_RC = IB_UVERBS_QPT_RC, IB_QPT_UC = IB_UVERBS_QPT_UC, IB_QPT_UD = IB_UVERBS_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET, IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI, IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT, IB_QPT_MAX, IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer */ IB_QPT_RESERVED1 = 0x1000, IB_QPT_RESERVED2, IB_QPT_RESERVED3, IB_QPT_RESERVED4, IB_QPT_RESERVED5, IB_QPT_RESERVED6, IB_QPT_RESERVED7, IB_QPT_RESERVED8, IB_QPT_RESERVED9, IB_QPT_RESERVED10, }; enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_INTEGRITY_EN = 1 << 6, IB_QP_CREATE_NETDEV_USE = 1 << 7, IB_QP_CREATE_SCATTER_FCS = IB_UVERBS_QP_CREATE_SCATTER_FCS, IB_QP_CREATE_CVLAN_STRIPPING = IB_UVERBS_QP_CREATE_CVLAN_STRIPPING, IB_QP_CREATE_SOURCE_QPN = 1 << 10, IB_QP_CREATE_PCI_WRITE_END_PADDING = IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, }; /* * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler * callback to destroy the passed in QP. */ struct ib_qp_init_attr { /* This callback occurs in workqueue context */ void (*event_handler)(struct ib_event *, void *); void *qp_context; struct ib_cq *send_cq; struct ib_cq *recv_cq; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct ib_qp_cap cap; enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; u32 create_flags; /* * Only needed for special QP types, or when using the RW API. */ u32 port_num; struct ib_rwq_ind_table *rwq_ind_tbl; u32 source_qpn; }; struct ib_qp_open_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; enum ib_qp_type qp_type; }; enum ib_rnr_timeout { IB_RNR_TIMER_655_36 = 0, IB_RNR_TIMER_000_01 = 1, IB_RNR_TIMER_000_02 = 2, IB_RNR_TIMER_000_03 = 3, IB_RNR_TIMER_000_04 = 4, IB_RNR_TIMER_000_06 = 5, IB_RNR_TIMER_000_08 = 6, IB_RNR_TIMER_000_12 = 7, IB_RNR_TIMER_000_16 = 8, IB_RNR_TIMER_000_24 = 9, IB_RNR_TIMER_000_32 = 10, IB_RNR_TIMER_000_48 = 11, IB_RNR_TIMER_000_64 = 12, IB_RNR_TIMER_000_96 = 13, IB_RNR_TIMER_001_28 = 14, IB_RNR_TIMER_001_92 = 15, IB_RNR_TIMER_002_56 = 16, IB_RNR_TIMER_003_84 = 17, IB_RNR_TIMER_005_12 = 18, IB_RNR_TIMER_007_68 = 19, IB_RNR_TIMER_010_24 = 20, IB_RNR_TIMER_015_36 = 21, IB_RNR_TIMER_020_48 = 22, IB_RNR_TIMER_030_72 = 23, IB_RNR_TIMER_040_96 = 24, IB_RNR_TIMER_061_44 = 25, IB_RNR_TIMER_081_92 = 26, IB_RNR_TIMER_122_88 = 27, IB_RNR_TIMER_163_84 = 28, IB_RNR_TIMER_245_76 = 29, IB_RNR_TIMER_327_68 = 30, IB_RNR_TIMER_491_52 = 31 }; enum ib_qp_attr_mask { IB_QP_STATE = 1, IB_QP_CUR_STATE = (1<<1), IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2), IB_QP_ACCESS_FLAGS = (1<<3), IB_QP_PKEY_INDEX = (1<<4), IB_QP_PORT = (1<<5), IB_QP_QKEY = (1<<6), IB_QP_AV = (1<<7), IB_QP_PATH_MTU = (1<<8), IB_QP_TIMEOUT = (1<<9), IB_QP_RETRY_CNT = (1<<10), IB_QP_RNR_RETRY = (1<<11), IB_QP_RQ_PSN = (1<<12), IB_QP_MAX_QP_RD_ATOMIC = (1<<13), IB_QP_ALT_PATH = (1<<14), IB_QP_MIN_RNR_TIMER = (1<<15), IB_QP_SQ_PSN = (1<<16), IB_QP_MAX_DEST_RD_ATOMIC = (1<<17), IB_QP_PATH_MIG_STATE = (1<<18), IB_QP_CAP = (1<<19), IB_QP_DEST_QPN = (1<<20), IB_QP_RESERVED1 = (1<<21), IB_QP_RESERVED2 = (1<<22), IB_QP_RESERVED3 = (1<<23), IB_QP_RESERVED4 = (1<<24), IB_QP_RATE_LIMIT = (1<<25), IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0), }; enum ib_qp_state { IB_QPS_RESET, IB_QPS_INIT, IB_QPS_RTR, IB_QPS_RTS, IB_QPS_SQD, IB_QPS_SQE, IB_QPS_ERR }; enum ib_mig_state { IB_MIG_MIGRATED, IB_MIG_REARM, IB_MIG_ARMED }; enum ib_mw_type { IB_MW_TYPE_1 = 1, IB_MW_TYPE_2 = 2 }; struct ib_qp_attr { enum ib_qp_state qp_state; enum ib_qp_state cur_qp_state; enum ib_mtu path_mtu; enum ib_mig_state path_mig_state; u32 qkey; u32 rq_psn; u32 sq_psn; u32 dest_qp_num; int qp_access_flags; struct ib_qp_cap cap; struct rdma_ah_attr ah_attr; struct rdma_ah_attr alt_ah_attr; u16 pkey_index; u16 alt_pkey_index; u8 en_sqd_async_notify; u8 sq_draining; u8 max_rd_atomic; u8 max_dest_rd_atomic; u8 min_rnr_timer; u32 port_num; u8 timeout; u8 retry_cnt; u8 rnr_retry; u32 alt_port_num; u8 alt_timeout; u32 rate_limit; struct net_device *xmit_slave; }; enum ib_wr_opcode { /* These are shared with userspace */ IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, IB_WR_SEND = IB_UVERBS_WR_SEND, IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, IB_WR_MASKED_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, IB_WR_FLUSH = IB_UVERBS_WR_FLUSH, IB_WR_ATOMIC_WRITE = IB_UVERBS_WR_ATOMIC_WRITE, /* These are kernel only and can not be issued by userspace */ IB_WR_REG_MR = 0x20, IB_WR_REG_MR_INTEGRITY, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ IB_WR_RESERVED1 = 0xf0, IB_WR_RESERVED2, IB_WR_RESERVED3, IB_WR_RESERVED4, IB_WR_RESERVED5, IB_WR_RESERVED6, IB_WR_RESERVED7, IB_WR_RESERVED8, IB_WR_RESERVED9, IB_WR_RESERVED10, }; enum ib_send_flags { IB_SEND_FENCE = 1, IB_SEND_SIGNALED = (1<<1), IB_SEND_SOLICITED = (1<<2), IB_SEND_INLINE = (1<<3), IB_SEND_IP_CSUM = (1<<4), /* reserve bits 26-31 for low level drivers' internal use */ IB_SEND_RESERVED_START = (1 << 26), IB_SEND_RESERVED_END = (1 << 31), }; struct ib_sge { u64 addr; u32 length; u32 lkey; }; struct ib_cqe { void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; int send_flags; union { __be32 imm_data; u32 invalidate_rkey; } ex; }; struct ib_rdma_wr { struct ib_send_wr wr; u64 remote_addr; u32 rkey; }; static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_rdma_wr, wr); } struct ib_atomic_wr { struct ib_send_wr wr; u64 remote_addr; u64 compare_add; u64 swap; u64 compare_add_mask; u64 swap_mask; u32 rkey; }; static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_atomic_wr, wr); } struct ib_ud_wr { struct ib_send_wr wr; struct ib_ah *ah; void *header; int hlen; int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u32 port_num; /* valid for DR SMPs on switch only */ }; static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_ud_wr, wr); } struct ib_reg_wr { struct ib_send_wr wr; struct ib_mr *mr; u32 key; int access; }; static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_reg_wr, wr); } struct ib_recv_wr { struct ib_recv_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; }; enum ib_access_flags { IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE, IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE, IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ, IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC, IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND, IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED, IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND, IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB, IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING, IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL, IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT, IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE, IB_ACCESS_SUPPORTED = ((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL, }; /* * XXX: these are apparently used for ->rereg_user_mr, no idea why they * are hidden here instead of a uapi header! */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), IB_MR_REREG_ACCESS = (1<<2), IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; struct ib_umem; enum rdma_remove_reason { /* * Userspace requested uobject deletion or initial try * to remove uobject via cleanup. Call could fail */ RDMA_REMOVE_DESTROY, /* Context deletion. This call should delete the actual object itself */ RDMA_REMOVE_CLOSE, /* Driver is being hot-unplugged. This call should delete the actual object itself */ RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, /* The driver failed to destroy the uobject and is being disconnected */ RDMA_REMOVE_DRIVER_FAILURE, }; struct ib_rdmacg_object { #ifdef CONFIG_CGROUP_RDMA struct rdma_cgroup *cg; /* owner rdma cgroup */ #endif }; struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; struct ib_rdmacg_object cg_obj; u64 enabled_caps; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; struct xarray mmap_xa; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ /* ufile & ucontext owning this object */ struct ib_uverbs_file *ufile; /* FIXME, save memory: ufile->context == context */ struct ib_ucontext *context; /* associated user context */ void *object; /* containing object */ struct list_head list; /* link to context's list */ struct ib_rdmacg_object cg_obj; /* rdmacg object */ int id; /* index into kernel idr */ struct kref ref; atomic_t usecnt; /* protects exclusive access */ struct rcu_head rcu; /* kfree_rcu() overhead */ const struct uverbs_api_object *uapi_object; }; struct ib_udata { const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; struct ib_pd { u32 local_dma_lkey; u32 flags; struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ u32 unsafe_global_rkey; /* * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; struct rdma_restrack_entry res; }; struct ib_xrcd { struct ib_device *device; atomic_t usecnt; /* count all exposed resources */ struct inode *inode; struct rw_semaphore tgt_qps_rwsem; struct xarray tgt_qps; }; struct ib_ah { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; const struct ib_gid_attr *sgid_attr; enum rdma_ah_attr_type type; }; typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE, IB_POLL_DIRECT, /* caller context, no hw completions */ }; struct ib_cq { struct ib_device *device; struct ib_ucq_object *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; unsigned int cqe_used; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; struct list_head pool_entry; union { struct irq_poll iop; struct work_struct work; }; struct workqueue_struct *comp_wq; struct dim *dim; /* updated only by trace points */ ktime_t timestamp; u8 interrupt:1; u8 shared:1; unsigned int comp_vector; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_srq { struct ib_device *device; struct ib_pd *pd; struct ib_usrq_object *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; enum ib_srq_type srq_type; atomic_t usecnt; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; u32 srq_num; } xrc; }; } ext; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; enum ib_raw_packet_caps { /* * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ IB_RAW_PACKET_CAP_CVLAN_STRIPPING = IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, /* * Scatter FCS field of an incoming packet to host memory is supported. */ IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, /* * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { IB_WQT_RQ = IB_UVERBS_WQT_RQ, }; enum ib_wq_state { IB_WQS_RESET, IB_WQS_RDY, IB_WQS_ERR }; struct ib_wq { struct ib_device *device; struct ib_uwq_object *uobject; void *wq_context; void (*event_handler)(struct ib_event *, void *); struct ib_pd *pd; struct ib_cq *cq; u32 wq_num; enum ib_wq_state state; enum ib_wq_type wq_type; atomic_t usecnt; }; enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING, IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS, IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP, IB_WQ_FLAGS_PCI_WRITE_END_PADDING = IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING, }; struct ib_wq_init_attr { void *wq_context; enum ib_wq_type wq_type; u32 max_wr; u32 max_sge; struct ib_cq *cq; void (*event_handler)(struct ib_event *, void *); u32 create_flags; /* Use enum ib_wq_flags */ }; enum ib_wq_attr_mask { IB_WQ_STATE = 1 << 0, IB_WQ_CUR_STATE = 1 << 1, IB_WQ_FLAGS = 1 << 2, }; struct ib_wq_attr { enum ib_wq_state wq_state; enum ib_wq_state curr_wq_state; u32 flags; /* Use enum ib_wq_flags */ u32 flags_mask; /* Use enum ib_wq_flags */ }; struct ib_rwq_ind_table { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; u32 ind_tbl_num; u32 log_ind_tbl_size; struct ib_wq **ind_tbl; }; struct ib_rwq_ind_table_init_attr { u32 log_ind_tbl_size; /* Each entry is a pointer to Receive Work Queue */ struct ib_wq **ind_tbl; }; enum port_pkey_state { IB_PORT_PKEY_NOT_VALID = 0, IB_PORT_PKEY_VALID = 1, IB_PORT_PKEY_LISTED = 2, }; struct ib_qp_security; struct ib_port_pkey { enum port_pkey_state state; u16 pkey_index; u32 port_num; struct list_head qp_list; struct list_head to_error_list; struct ib_qp_security *sec; }; struct ib_ports_pkeys { struct ib_port_pkey main; struct ib_port_pkey alt; }; struct ib_qp_security { struct ib_qp *qp; struct ib_device *dev; /* Hold this mutex when changing port and pkey settings. */ struct mutex mutex; struct ib_ports_pkeys *ports_pkeys; /* A list of all open shared QP handles. Required to enforce security * properly for all users of a shared QP. */ struct list_head shared_qp_list; void *security; bool destroying; atomic_t error_list_count; struct completion error_complete; int error_comps_pending; }; /* * @max_write_sge: Maximum SGE elements per RDMA WRITE request. * @max_read_sge: Maximum SGE elements per RDMA READ request. */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; spinlock_t mr_lock; int mrs_used; struct list_head rdma_mrs; struct list_head sig_mrs; struct ib_srq *srq; struct completion srq_completion; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; struct ib_qp *real_qp; struct ib_uqp_object *uobject; void (*event_handler)(struct ib_event *, void *); void (*registered_event_handler)(struct ib_event *, void *); void *qp_context; /* sgid_attrs associated with the AV's */ const struct ib_gid_attr *av_sgid_attr; const struct ib_gid_attr *alt_path_sgid_attr; u32 qp_num; u32 max_write_sge; u32 max_read_sge; enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u32 port; bool integrity_en; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; /* The counter the qp is bind to */ struct rdma_counter *counter; }; struct ib_dm { struct ib_device *device; u32 length; u32 flags; struct ib_uobject *uobject; atomic_t usecnt; }; /* bit values to mark existence of ib_dmah fields */ enum { IB_DMAH_CPU_ID_EXISTS, IB_DMAH_MEM_TYPE_EXISTS, IB_DMAH_PH_EXISTS, }; struct ib_dmah { struct ib_device *device; struct ib_uobject *uobject; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; u32 cpu_id; enum tph_mem_type mem_type; atomic_t usecnt; u8 ph; u8 valid_fields; /* use IB_DMAH_XXX_EXISTS */ }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; u32 lkey; u32 rkey; u64 iova; u64 length; unsigned int page_size; enum ib_mr_type type; bool need_inval; union { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; struct ib_dm *dm; struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */ struct ib_dmah *dmah; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_mw { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; enum ib_mw_type type; }; /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ IB_FLOW_ATTR_NORMAL = 0x0, /* default unicast and multicast rule - * receive all Eth traffic which isn't steered to any QP */ IB_FLOW_ATTR_ALL_DEFAULT = 0x1, /* default multicast rule - * receive all Eth multicast traffic which isn't steered to any QP */ IB_FLOW_ATTR_MC_DEFAULT = 0x2, /* sniffer rule - receive all port traffic */ IB_FLOW_ATTR_SNIFFER = 0x3 }; /* Supported steering header types */ enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, IB_FLOW_SPEC_IPV6 = 0x31, IB_FLOW_SPEC_ESP = 0x34, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41, IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50, IB_FLOW_SPEC_GRE = 0x51, IB_FLOW_SPEC_MPLS = 0x60, IB_FLOW_SPEC_INNER = 0x100, /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, IB_FLOW_SPEC_ACTION_HANDLE = 0x1002, IB_FLOW_SPEC_ACTION_COUNT = 0x1003, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10 enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */ }; struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; __be16 ether_type; __be16 vlan_tag; }; struct ib_flow_spec_eth { u32 type; u16 size; struct ib_flow_eth_filter val; struct ib_flow_eth_filter mask; }; struct ib_flow_ib_filter { __be16 dlid; __u8 sl; }; struct ib_flow_spec_ib { u32 type; u16 size; struct ib_flow_ib_filter val; struct ib_flow_ib_filter mask; }; /* IPv4 header flags */ enum ib_ipv4_flags { IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */ IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the last have this flag set */ }; struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; u8 proto; u8 tos; u8 ttl; u8 flags; }; struct ib_flow_spec_ipv4 { u32 type; u16 size; struct ib_flow_ipv4_filter val; struct ib_flow_ipv4_filter mask; }; struct ib_flow_ipv6_filter { u8 src_ip[16]; u8 dst_ip[16]; __be32 flow_label; u8 next_hdr; u8 traffic_class; u8 hop_limit; } __packed; struct ib_flow_spec_ipv6 { u32 type; u16 size; struct ib_flow_ipv6_filter val; struct ib_flow_ipv6_filter mask; }; struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; }; struct ib_flow_spec_tcp_udp { u32 type; u16 size; struct ib_flow_tcp_udp_filter val; struct ib_flow_tcp_udp_filter mask; }; struct ib_flow_tunnel_filter { __be32 tunnel_id; }; /* ib_flow_spec_tunnel describes the Vxlan tunnel * the tunnel_id from val has the vni value */ struct ib_flow_spec_tunnel { u32 type; u16 size; struct ib_flow_tunnel_filter val; struct ib_flow_tunnel_filter mask; }; struct ib_flow_esp_filter { __be32 spi; __be32 seq; }; struct ib_flow_spec_esp { u32 type; u16 size; struct ib_flow_esp_filter val; struct ib_flow_esp_filter mask; }; struct ib_flow_gre_filter { __be16 c_ks_res0_ver; __be16 protocol; __be32 key; }; struct ib_flow_spec_gre { u32 type; u16 size; struct ib_flow_gre_filter val; struct ib_flow_gre_filter mask; }; struct ib_flow_mpls_filter { __be32 tag; }; struct ib_flow_spec_mpls { u32 type; u16 size; struct ib_flow_mpls_filter val; struct ib_flow_mpls_filter mask; }; struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; u32 tag_id; }; struct ib_flow_spec_action_drop { enum ib_flow_spec_type type; u16 size; }; struct ib_flow_spec_action_handle { enum ib_flow_spec_type type; u16 size; struct ib_flow_action *act; }; enum ib_counters_description { IB_COUNTER_PACKETS, IB_COUNTER_BYTES, }; struct ib_flow_spec_action_count { enum ib_flow_spec_type type; u16 size; struct ib_counters *counters; }; union ib_flow_spec { struct { u32 type; u16 size; }; struct ib_flow_spec_eth eth; struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; struct ib_flow_spec_ipv6 ipv6; struct ib_flow_spec_tunnel tunnel; struct ib_flow_spec_esp esp; struct ib_flow_spec_gre gre; struct ib_flow_spec_mpls mpls; struct ib_flow_spec_action_tag flow_tag; struct ib_flow_spec_action_drop drop; struct ib_flow_spec_action_handle action; struct ib_flow_spec_action_count flow_count; }; struct ib_flow_attr { enum ib_flow_attr_type type; u16 size; u16 priority; u32 flags; u8 num_of_specs; u32 port; union ib_flow_spec flows[]; }; struct ib_flow { struct ib_qp *qp; struct ib_device *device; struct ib_uobject *uobject; }; enum ib_flow_action_type { IB_FLOW_ACTION_UNSPECIFIED, IB_FLOW_ACTION_ESP = 1, }; struct ib_flow_action_attrs_esp_keymats { enum ib_uverbs_flow_action_esp_keymat protocol; union { struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm; } keymat; }; struct ib_flow_action_attrs_esp_replays { enum ib_uverbs_flow_action_esp_replay protocol; union { struct ib_uverbs_flow_action_esp_replay_bmp bmp; } replay; }; enum ib_flow_action_attrs_esp_flags { /* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags * This is done in order to share the same flags between user-space and * kernel and spare an unnecessary translation. */ /* Kernel flags */ IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32, IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33, }; struct ib_flow_spec_list { struct ib_flow_spec_list *next; union ib_flow_spec spec; }; struct ib_flow_action_attrs_esp { struct ib_flow_action_attrs_esp_keymats *keymat; struct ib_flow_action_attrs_esp_replays *replay; struct ib_flow_spec_list *encap; /* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled. * Value of 0 is a valid value. */ u32 esn; u32 spi; u32 seq; u32 tfc_pad; /* Use enum ib_flow_action_attrs_esp_flags */ u64 flags; u64 hard_limit_pkts; }; struct ib_flow_action { struct ib_device *device; struct ib_uobject *uobject; enum ib_flow_action_type type; atomic_t usecnt; }; struct ib_mad; enum ib_process_mad_flags { IB_MAD_IGNORE_MKEY = 1, IB_MAD_IGNORE_BKEY = 2, IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY }; enum ib_mad_result { IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */ }; struct ib_port_cache { u64 subnet_prefix; struct ib_pkey_cache *pkey; struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; enum ib_port_state last_port_state; }; struct ib_port_immutable { int pkey_tbl_len; int gid_tbl_len; u32 core_cap_flags; u32 max_mad_size; }; struct ib_port_data { struct ib_device *ib_dev; struct ib_port_immutable immutable; spinlock_t pkey_list_lock; spinlock_t netdev_lock; struct list_head pkey_list; struct ib_port_cache cache; struct net_device __rcu *netdev; netdevice_tracker netdev_tracker; struct hlist_node ndev_hash_link; struct rdma_port_counter port_counter; struct ib_port *sysfs; }; /* rdma netdev type - specifies protocol type */ enum rdma_netdev_t { RDMA_NETDEV_OPA_VNIC, RDMA_NETDEV_IPOIB, }; /** * struct rdma_netdev - rdma netdev * For cases where netstack interfacing is required. */ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u32 port_num; int mtu; /* * cleanup function must be specified. * FIXME: This is only used for OPA_VNIC and that usage should be * removed too. */ void (*free_rdma_netdev)(struct net_device *netdev); /* control functions */ void (*set_id)(struct net_device *netdev, int id); /* send packet */ int (*send)(struct net_device *dev, struct sk_buff *skb, struct ib_ah *address, u32 dqpn); /* multicast */ int (*attach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid, int set_qkey, u32 qkey); int (*detach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid); /* timeout */ void (*tx_timeout)(struct net_device *dev, unsigned int txqueue); }; struct rdma_netdev_alloc_params { size_t sizeof_priv; unsigned int txqs; unsigned int rxqs; void *param; int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num, struct net_device *netdev, void *param); }; struct ib_odp_counters { atomic64_t faults; atomic64_t faults_handled; atomic64_t invalidations; atomic64_t invalidations_handled; atomic64_t prefetch; }; struct ib_counters { struct ib_device *device; struct ib_uobject *uobject; /* num of objects attached */ atomic_t usecnt; }; struct ib_counters_read_attr { u64 *counters_buff; u32 ncounters; u32 flags; /* use enum ib_read_counters_flags */ }; struct uverbs_attr_bundle; struct iw_cm_id; struct iw_cm_conn_param; #define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \ .size_##ib_struct = \ (sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \ BUILD_BUG_ON_ZERO( \ !__same_type(((struct drv_struct *)NULL)->member, \ struct ib_struct))) #define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ gfp, false)) #define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ GFP_KERNEL, true)) #define rdma_zalloc_drv_obj(ib_dev, ib_type) \ rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL) #define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct struct rdma_user_mmap_entry { struct kref ref; struct ib_ucontext *ucontext; unsigned long start_pgoff; size_t npages; bool driver_removed; }; /* Return the offset (in bytes) the user should pass to libc's mmap() */ static inline u64 rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry) { return (u64)entry->start_pgoff << PAGE_SHIFT; } /** * struct ib_device_ops - InfiniBand device operations * This structure defines all the InfiniBand device operations, providers will * need to define the supported operations, otherwise they will be set to null. */ struct ib_device_ops { struct module *owner; enum rdma_driver_id driver_id; u32 uverbs_abi_ver; unsigned int uverbs_no_driver_id_binding:1; /* * NOTE: New drivers should not make use of device_group; instead new * device parameter should be exposed via netlink command. This * mechanism exists only for existing drivers. */ const struct attribute_group *device_group; const struct attribute_group **port_groups; int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr); int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); void (*drain_rq)(struct ib_qp *qp); void (*drain_sq)(struct ib_qp *qp); int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int (*peek_cq)(struct ib_cq *cq, int wc_cnt); int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags); int (*post_srq_recv)(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int (*process_mad)(struct ib_device *device, int process_mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad, size_t *out_mad_size, u16 *out_mad_pkey_index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); int (*modify_device)(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); void (*get_dev_fw_str)(struct ib_device *device, char *str); const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev, int comp_vector); int (*query_port)(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); int (*modify_port)(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); /** * The following mandatory functions are used only at device * registration. Keep functions such as these at the end of this * structure to avoid cache line misses when accessing struct ib_device * in fast paths. */ int (*get_port_immutable)(struct ib_device *device, u32 port_num, struct ib_port_immutable *immutable); enum rdma_link_layer (*get_link_layer)(struct ib_device *device, u32 port_num); /** * When calling get_netdev, the HW vendor's driver should return the * net device of device @device at port @port_num or NULL if such * a net device doesn't exist. The vendor driver should call dev_hold * on this net device. The HW vendor's device driver must guarantee * that this function returns NULL before the net device has finished * NETDEV_UNREGISTER state. */ struct net_device *(*get_netdev)(struct ib_device *device, u32 port_num); /** * rdma netdev operation * * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params * must return -EOPNOTSUPP if it doesn't support the specified type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, struct rdma_netdev_alloc_params *params); /** * query_gid should be return GID value for @device, when @port_num * link layer is either IB or iWarp. It is no-op if @port_num port * is RoCE link layer. */ int (*query_gid)(struct ib_device *device, u32 port_num, int index, union ib_gid *gid); /** * When calling add_gid, the HW vendor's driver should add the gid * of device of port at gid index available at @attr. Meta-info of * that gid (for example, the network device related to this gid) is * available at @attr. @context allows the HW vendor driver to store * extra information together with a GID entry. The HW vendor driver may * allocate memory to contain this information and store it in @context * when a new GID entry is written to. Params are consistent until the * next call of add_gid or delete_gid. The function should return 0 on * success or error otherwise. The function could be called * concurrently for different ports. This function is only called when * roce_gid_table is used. */ int (*add_gid)(const struct ib_gid_attr *attr, void **context); /** * When calling del_gid, the HW vendor's driver should delete the * gid of device @device at gid index gid_index of port port_num * available in @attr. * Upon the deletion of a GID entry, the HW vendor must free any * allocated memory. The caller will clear @context afterwards. * This function is only called when roce_gid_table is used. */ int (*del_gid)(const struct ib_gid_attr *attr, void **context); int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int (*alloc_ucontext)(struct ib_ucontext *context, struct ib_udata *udata); void (*dealloc_ucontext)(struct ib_ucontext *context); int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma); /** * This will be called once refcount of an entry in mmap_xa reaches * zero. The type of the memory that was mapped may differ between * entries and is opaque to the rdma_user_mmap interface. * Therefore needs to be implemented by the driver in mmap_free. */ void (*mmap_free)(struct rdma_user_mmap_entry *entry); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*destroy_ah)(struct ib_ah *ah, u32 flags); int (*create_srq)(struct ib_srq *srq, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata); int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct uverbs_attr_bundle *attrs); int (*create_cq_umem)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct ib_umem *umem, struct uverbs_attr_bundle *attrs); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); /** * pre_destroy_cq - Prevent a cq from generating any new work * completions, but not free any kernel resources */ int (*pre_destroy_cq)(struct ib_cq *cq); /** * post_destroy_cq - Free all kernel resources */ void (*post_destroy_cq)(struct ib_cq *cq); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_dmah *dmah, struct ib_udata *udata); struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset, u64 length, u64 virt_addr, int fd, int mr_access_flags, struct ib_dmah *dmah, struct uverbs_attr_bundle *attrs); struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata); struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); int (*advise_mr)(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); /* * Kernel users should universally support relaxed ordering (RO), as * they are designed to read data only after observing the CQE and use * the DMA API correctly. * * Some drivers implicitly enable RO if platform supports it. */ int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); int (*destroy_flow_action)(struct ib_flow_action *action); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *ivf); int (*get_vf_stats)(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int (*get_vf_guid)(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid, int type); struct ib_wq *(*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table, struct ib_rwq_ind_table_init_attr *init_attr, struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dm *(*alloc_dm)(struct ib_device *device, struct ib_ucontext *context, struct ib_dm_alloc_attr *attr, struct uverbs_attr_bundle *attrs); int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs); int (*alloc_dmah)(struct ib_dmah *ibdmah, struct uverbs_attr_bundle *attrs); int (*dealloc_dmah)(struct ib_dmah *dmah, struct uverbs_attr_bundle *attrs); struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm, struct ib_dm_mr_attr *attr, struct uverbs_attr_bundle *attrs); int (*create_counters)(struct ib_counters *counters, struct uverbs_attr_bundle *attrs); int (*destroy_counters)(struct ib_counters *counters); int (*read_counters)(struct ib_counters *counters, struct ib_counters_read_attr *counters_read_attr, struct uverbs_attr_bundle *attrs); int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset); /** * alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and * fill in the driver initialized data. The struct is kfree()'ed by * the sysfs core when the device is removed. A lifespan of -1 in the * return struct tells the core to set a default lifespan. */ struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device); struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device, u32 port_num); /** * get_hw_stats - Fill in the counter value(s) in the stats struct. * @index - The index in the value array we wish to have updated, or * num_counters if we want all stats updated * Return codes - * < 0 - Error, no counters updated * index - Updated the single counter pointed to by index * num_counters - Updated all counters (will reset the timestamp * and prevent further calls for lifespan milliseconds) * Drivers are allowed to update all counters in leiu of just the * one given in index at their option */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u32 port, int index); /** * modify_hw_stat - Modify the counter configuration * @enable: true/false when enable/disable a counter * Return codes - 0 on success or error code otherwise. */ int (*modify_hw_stat)(struct ib_device *device, u32 port, unsigned int counter_index, bool enable); /** * Allows rdma drivers to add their own restrack attributes. */ int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id); int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq); int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq); /* Device lifecycle callbacks */ /* * Called after the device becomes registered, before clients are * attached */ int (*enable_driver)(struct ib_device *dev); /* * This is called as part of ib_dealloc_device(). */ void (*dealloc_driver)(struct ib_device *dev); /* iWarp CM callbacks */ void (*iw_add_ref)(struct ib_qp *qp); void (*iw_rem_ref)(struct ib_qp *qp); struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn); int (*iw_connect)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_accept)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len); int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog); int (*iw_destroy_listen)(struct iw_cm_id *cm_id); /** * counter_bind_qp - Bind a QP to a counter. * @counter - The counter to be bound. If counter->id is zero then * the driver needs to allocate a new counter and set counter->id */ int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp, u32 port); /** * counter_unbind_qp - Unbind the qp from the dynamically-allocated * counter and bind it onto the default one */ int (*counter_unbind_qp)(struct ib_qp *qp, u32 port); /** * counter_dealloc -De-allocate the hw counter */ int (*counter_dealloc)(struct rdma_counter *counter); /** * counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in * the driver initialized data. */ struct rdma_hw_stats *(*counter_alloc_stats)( struct rdma_counter *counter); /** * counter_update_stats - Query the stats value of this counter */ int (*counter_update_stats)(struct rdma_counter *counter); /** * counter_init - Initialize the driver specific rdma counter struct. */ void (*counter_init)(struct rdma_counter *counter); /** * Allows rdma drivers to add their own restrack attributes * dumped via 'rdma stat' iproute2 command. */ int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); /* query driver for its ucontext properties */ int (*query_ucontext)(struct ib_ucontext *context, struct uverbs_attr_bundle *attrs); /* * Provide NUMA node. This API exists for rdmavt/hfi1 only. * Everyone else relies on Linux memory management model. */ int (*get_numa_node)(struct ib_device *dev); /** * add_sub_dev - Add a sub IB device */ struct ib_device *(*add_sub_dev)(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** * del_sub_dev - Delete a sub IB device */ void (*del_sub_dev)(struct ib_device *sub_dev); /** * ufile_cleanup - Attempt to cleanup ubojects HW resources inside * the ufile. */ void (*ufile_hw_cleanup)(struct ib_uverbs_file *ufile); /** * report_port_event - Drivers need to implement this if they have * some private stuff to handle when link status changes. */ void (*report_port_event)(struct ib_device *ibdev, struct net_device *ndev, unsigned long event); DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); DECLARE_RDMA_OBJ_SIZE(ib_dmah); DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); DECLARE_RDMA_OBJ_SIZE(ib_qp); DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); DECLARE_RDMA_OBJ_SIZE(rdma_counter); }; struct ib_core_device { /* device must be the first element in structure until, * union of ib_core_device and device exists in ib_device. */ struct device dev; possible_net_t rdma_net; struct kobject *ports_kobj; struct list_head port_list; struct ib_device *owner; /* reach back to owner ib_device */ }; struct rdma_restrack_root; struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; struct ib_device_ops ops; char name[IB_DEVICE_NAME_MAX]; struct rcu_head rcu_head; struct list_head event_handler_list; /* Protects event_handler_list */ struct rw_semaphore event_handler_rwsem; /* Protects QP's event_handler calls and open_qp list */ spinlock_t qp_open_list_lock; struct rw_semaphore client_data_rwsem; struct xarray client_data; struct mutex unregistration_lock; /* Synchronize GID, Pkey cache entries, subnet prefix, LMC */ rwlock_t cache_lock; /** * port_data is indexed by port number */ struct ib_port_data *port_data; int num_comp_vectors; union { struct device dev; struct ib_core_device coredev; }; /* First group is for device attributes, * Second group is for driver provided attributes (optional). * Third group is for the hw_stats * It is a NULL terminated array. */ const struct attribute_group *groups[4]; u8 hw_stats_attr_index; u64 uverbs_cmd_mask; char node_desc[IB_DEVICE_NODE_DESC_MAX]; __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; /* Indicates kernel verbs support, should not be used in drivers */ u16 kverbs_provider:1; /* CQ adaptive moderation (RDMA DIM) */ u16 use_cq_dim:1; u8 node_type; u32 phys_port_cnt; struct ib_device_attr attrs; struct hw_stats_device_data *hw_stats_data; #ifdef CONFIG_CGROUP_RDMA struct rdmacg_device cg_device; #endif u32 index; spinlock_t cq_pools_lock; struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1]; struct rdma_restrack_root *res; const struct uapi_definition *driver_def; /* * Positive refcount indicates that the device is currently * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; struct work_struct unregistration_work; const struct rdma_link_ops *link_ops; /* Protects compat_devs xarray modifications */ struct mutex compat_devs_mutex; /* Maintains compat devices for each net namespace */ struct xarray compat_devs; /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; u32 lag_flags; /* A parent device has a list of sub-devices */ struct mutex subdev_lock; struct list_head subdev_list_head; /* A sub device has a type and a parent */ enum rdma_nl_dev_type type; struct ib_device *parent; struct list_head subdev_list; enum rdma_nl_name_assign_type name_assign_type; }; static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size, gfp_t gfp, bool is_numa_aware) { if (is_numa_aware && dev->ops.get_numa_node) return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev)); return kzalloc(size, gfp); } struct ib_client_nl_info; struct ib_client { const char *name; int (*add)(struct ib_device *ibdev); void (*remove)(struct ib_device *, void *client_data); void (*rename)(struct ib_device *dev, void *client_data); int (*get_nl_info)(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res); int (*get_global_nl_info)(struct ib_client_nl_info *res); /* Returns the net_dev belonging to this ib_client and matching the * given parameters. * @dev: An RDMA device that the net_dev use for communication. * @port: A physical port number on the RDMA device. * @pkey: P_Key that the net_dev uses if applicable. * @gid: A GID that the net_dev uses to communicate. * @addr: An IP address the net_dev is configured with. * @client_data: The device's client data set by ib_set_client_data(). * * An ib_client that implements a net_dev on top of RDMA devices * (such as IP over IB) should implement this callback, allowing the * rdma_cm module to find the right net_dev for a given request. * * The caller is responsible for calling dev_put on the returned * netdev. */ struct net_device *(*get_net_dev_by_params)( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); refcount_t uses; struct completion uses_zero; u32 client_id; /* kverbs are not required by the client */ u8 no_kverbs_req:1; }; /* * IB block DMA iterator * * Iterates the DMA-mapped SGL in contiguous memory blocks aligned * to a HW supported page size. */ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ }; struct ib_device *_ib_alloc_device(size_t size, struct net *net); #define ib_alloc_device(drv_struct, member) \ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ struct drv_struct, member)), \ &init_net), \ struct drv_struct, member) #define ib_alloc_device_with_net(drv_struct, member, net) \ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ struct drv_struct, member)), net), \ struct drv_struct, member) void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device); void ib_unregister_device(struct ib_device *device); void ib_unregister_driver(enum rdma_driver_id driver_id); void ib_unregister_device_and_put(struct ib_device *device); void ib_unregister_device_queued(struct ib_device *ib_dev); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); void __rdma_block_iter_start(struct ib_block_iter *biter, struct scatterlist *sglist, unsigned int nents, unsigned long pgsz); bool __rdma_block_iter_next(struct ib_block_iter *biter); /** * rdma_block_iter_dma_address - get the aligned dma address of the current * block held by the block iterator. * @biter: block iterator holding the memory block */ static inline dma_addr_t rdma_block_iter_dma_address(struct ib_block_iter *biter) { return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1); } /** * rdma_for_each_block - iterate over contiguous memory blocks of the sg list * @sglist: sglist to iterate over * @biter: block iterator holding the memory block * @nents: maximum number of sg entries to iterate over * @pgsz: best HW supported page size to use * * Callers may use rdma_block_iter_dma_address() to get each * blocks aligned DMA address. */ #define rdma_for_each_block(sglist, biter, nents, pgsz) \ for (__rdma_block_iter_start(biter, sglist, nents, \ pgsz); \ __rdma_block_iter_next(biter);) /** * ib_get_client_data - Get IB client context * @device:Device to get context for * @client:Client to get context for * * ib_get_client_data() returns the client context data set with * ib_set_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ static inline void *ib_get_client_data(struct ib_device *device, struct ib_client *client) { return xa_load(&device->client_data, client->client_id); } void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); void ib_set_device_ops(struct ib_device *device, const struct ib_device_ops *ops); int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma, unsigned long pfn, unsigned long size, pgprot_t prot, struct rdma_user_mmap_entry *entry); int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length); int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 min_pgoff, u32 max_pgoff); #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) void rdma_user_mmap_disassociate(struct ib_device *device); #else static inline void rdma_user_mmap_disassociate(struct ib_device *device) { } #endif static inline int rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 pgoff) { return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff, pgoff); } struct rdma_user_mmap_entry * rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext, unsigned long pgoff); struct rdma_user_mmap_entry * rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, struct vm_area_struct *vma); void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry); void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry); static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len) { return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0; } static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } static inline bool ib_is_buffer_cleared(const void __user *p, size_t len) { bool ret; u8 *buf; if (len > USHRT_MAX) return false; buf = memdup_user(p, len); if (IS_ERR(buf)) return false; ret = !memchr_inv(buf, 0, len); kfree(buf); return ret; } static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t offset, size_t len) { return ib_is_buffer_cleared(udata->inbuf + offset, len); } /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for * the given QP state transition. * @cur_state: Current QP state * @next_state: Next QP state * @type: QP type * @mask: Mask of supplied QP attributes * * This function is a helper function that a low-level driver's * modify_qp method can use to validate the consumer's input. It * checks that cur_state and next_state are valid QP states, that a * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(const struct ib_event *event); int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u32 port_num); /** * rdma_cap_ib_switch - Check if the device is IB switch * @device: Device to check * * Device driver is responsible for setting is_switch bit on * in ib_device structure at init time. * * Return: true if the device is IB switch. */ static inline bool rdma_cap_ib_switch(const struct ib_device *device) { return device->is_switch; } /** * rdma_start_port - Return the first valid port number for the device * specified * * @device: Device to be checked * * Return start port number */ static inline u32 rdma_start_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : 1; } /** * rdma_for_each_port - Iterate over all valid port numbers of the IB device * @device - The struct ib_device * to iterate over * @iter - The unsigned int to store the port number */ #define rdma_for_each_port(device, iter) \ for (iter = rdma_start_port(device + \ BUILD_BUG_ON_ZERO(!__same_type(u32, \ iter))); \ iter <= rdma_end_port(device); iter++) /** * rdma_end_port - Return the last valid port number for the device * specified * * @device: Device to be checked * * Return last port number */ static inline u32 rdma_end_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline int rdma_is_port_valid(const struct ib_device *device, unsigned int port) { return (port >= rdma_start_port(device) && port <= rdma_end_port(device)); } static inline bool rdma_is_grh_required(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_IB_GRH_REQUIRED; } static inline bool rdma_protocol_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IB; } static inline bool rdma_protocol_roce(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); } static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; } static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } static inline bool rdma_protocol_iwarp(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; } static inline bool rdma_ib_or_roce(const struct ib_device *device, u32 port_num) { return rdma_protocol_ib(device, port_num) || rdma_protocol_roce(device, port_num); } static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET; } static inline bool rdma_protocol_usnic(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_USNIC; } /** * rdma_cap_ib_mad - Check if the port of a device supports Infiniband * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Management Datagrams (MAD) are a required part of the InfiniBand * specification and are supported on all InfiniBand devices. A slightly * extended version are also supported on OPA interfaces. * * Return: true if the port supports sending/receiving of MAD packets. */ static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_MAD; } /** * rdma_cap_opa_mad - Check if the port of device provides support for OPA * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Intel OmniPath devices extend and/or replace the InfiniBand Management * datagrams with their own versions. These OPA MADs share many but not all of * the characteristics of InfiniBand MADs. * * OPA MADs differ in the following ways: * * 1) MADs are variable size up to 2K * IBTA defined MADs remain fixed at 256 bytes * 2) OPA SMPs must carry valid PKeys * 3) OPA SMP packets are a different format * * Return: true if the port supports OPA MAD packet formats. */ static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_MAD; } /** * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). * @device: Device to check * @port_num: Port number to check * * Each InfiniBand node is required to provide a Subnet Management Agent * that the subnet manager can access. Prior to the fabric being fully * configured by the subnet manager, the SMA is accessed via a well known * interface called the Subnet Management Interface (SMI). This interface * uses directed route packets to communicate with the SM to get around the * chicken and egg problem of the SM needing to know what's on the fabric * in order to configure the fabric, and needing to configure the fabric in * order to send packets to the devices on the fabric. These directed * route packets do not need the fabric fully configured in order to reach * their destination. The SMI is the only method allowed to send * directed route packets on an InfiniBand fabric. * * Return: true if the port provides an SMI. */ static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SMI; } /** * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband * Communication Manager. * @device: Device to check * @port_num: Port number to check * * The InfiniBand Communication Manager is one of many pre-defined General * Service Agents (GSA) that are accessed via the General Service * Interface (GSI). It's role is to facilitate establishment of connections * between nodes as well as other management related tasks for established * connections. * * Return: true if the port supports an IB CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_CM; } /** * rdma_cap_iw_cm - Check if the port of device has the capability IWARP * Communication Manager. * @device: Device to check * @port_num: Port number to check * * Similar to above, but specific to iWARP connections which have a different * managment protocol than InfiniBand. * * Return: true if the port supports an iWARP CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IW_CM; } /** * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband * Subnet Administration. * @device: Device to check * @port_num: Port number to check * * An InfiniBand Subnet Administration (SA) service is a pre-defined General * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand * fabrics, devices should resolve routes to other hosts by contacting the * SA to query the proper route. * * Return: true if the port should act as a client to the fabric Subnet * Administration interface. This does not imply that the SA service is * running locally. */ static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SA; } /** * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband * Multicast. * @device: Device to check * @port_num: Port number to check * * InfiniBand multicast registration is more complex than normal IPv4 or * IPv6 multicast registration. Each Host Channel Adapter must register * with the Subnet Manager when it wishes to join a multicast group. It * should do so only once regardless of how many queue pairs it subscribes * to this group. And it should leave the group only after all queue pairs * attached to the group have been detached. * * Return: true if the port must undertake the additional adminstrative * overhead of registering/unregistering with the SM and tracking of the * total number of queue pairs attached to the multicast group. */ static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u32 port_num) { return rdma_cap_ib_sa(device, port_num); } /** * rdma_cap_af_ib - Check if the port of device has the capability * Native Infiniband Address. * @device: Device to check * @port_num: Port number to check * * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default * GID. RoCE uses a different mechanism, but still generates a GID via * a prescribed mechanism and port specific data. * * Return: true if the port uses a GID address to identify devices on the * network. */ static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_AF_IB; } /** * rdma_cap_eth_ah - Check if the port of device has the capability * Ethernet Address Handle. * @device: Device to check * @port_num: Port number to check * * RoCE is InfiniBand over Ethernet, and it uses a well defined technique * to fabricate GIDs over Ethernet/IP specific addresses native to the * port. Normally, packet headers are generated by the sending host * adapter, but when sending connectionless datagrams, we must manually * inject the proper headers for the fabric we are communicating over. * * Return: true if we are running as a RoCE port and must force the * addition of a Global Route Header built from our Ethernet Address * Handle into our header list for connectionless packets. */ static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_ETH_AH; } /** * rdma_cap_opa_ah - Check if the port of device supports * OPA Address handles * @device: Device to check * @port_num: Port number to check * * Return: true if we are running on an OPA device which supports * the extended OPA addressing. */ static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH; } /** * rdma_max_mad_size - Return the max MAD size required by this RDMA Port. * * @device: Device * @port_num: Port number * * This MAD size includes the MAD headers and MAD payload. No other headers * are included. * * Return the max MAD size required by the Port. Will return 0 if the port * does not support MADs */ static inline size_t rdma_max_mad_size(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.max_mad_size; } /** * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table * @device: Device to check * @port_num: Port number to check * * RoCE GID table mechanism manages the various GIDs for a device. * * NOTE: if allocating the port's GID table has failed, this call will still * return true, but any RoCE GID table API will fail. * * Return: true if the port uses RoCE GID table mechanism in order to manage * its GIDs. */ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, u32 port_num) { return rdma_protocol_roce(device, port_num) && device->ops.add_gid && device->ops.del_gid; } /* * Check if the device supports READ W/ INVALIDATE. */ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) { /* * iWarp drivers must support READ W/ INVALIDATE. No other protocol * has support for it yet. */ return rdma_protocol_iwarp(dev, port_num); } /** * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. * @device: Device * @port_num: 1 based Port number * * Return true if port is an Intel OPA port , false if not */ static inline bool rdma_core_cap_opa_port(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA; } /** * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value. * @device: Device * @port_num: Port number * @mtu: enum value of MTU * * Return the MTU size supported by the port as an integer value. Will return * -1 if enum value of mtu is not supported. */ static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port, int mtu) { if (rdma_core_cap_opa_port(device, port)) return opa_mtu_enum_to_int((enum opa_mtu)mtu); else return ib_mtu_enum_to_int((enum ib_mtu)mtu); } /** * rdma_mtu_from_attr - Return the mtu of the port from the port attribute. * @device: Device * @port_num: Port number * @attr: port attribute * * Return the MTU size supported by the port as an integer value. */ static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port, struct ib_port_attr *attr) { if (rdma_core_cap_opa_port(device, port)) return attr->phys_mtu; else return ib_mtu_enum_to_int(attr->max_mtu); } int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *info); int ib_get_vf_stats(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int ib_get_vf_guid(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid, int type); int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index); enum ib_pd_flags { /* * Create a memory registration for all memory in the system and place * the rkey for it into pd->unsafe_global_rkey. This can be used by * ULPs to avoid the overhead of dynamic MRs. * * This flag is generally considered unsafe and must only be used in * extremly trusted environments. Every use of it will log a warning * in the kernel log. */ IB_PD_UNSAFE_GLOBAL_RKEY = 0x01, }; struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); /** * ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. * @flags: protection domain flags * * A protection domain object provides an association between QPs, shared * receive queues, address handles, memory regions, and memory windows. * * Every PD has a local_dma_lkey which can be used as the lkey value for local * memory operations. */ #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), KBUILD_MODNAME) int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); /** * ib_dealloc_pd - Deallocate kernel PD * @pd: The protection domain * * NOTE: for user PD use ib_dealloc_pd_user with valid udata! */ static inline void ib_dealloc_pd(struct ib_pd *pd) { int ret = ib_dealloc_pd_user(pd, NULL); WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail"); } enum rdma_create_ah_flags { /* In a sleepable context */ RDMA_CREATE_AH_SLEEPABLE = BIT(0), }; /** * rdma_create_ah - Creates an address handle for the given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @flags: Create address handle flags (see enum rdma_create_ah_flags). * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags); /** * rdma_create_user_ah - Creates an address handle for the given address vector. * It resolves destination mac address for ah attribute of RoCE type. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @udata: pointer to user's input output buffer information need by * provider driver. * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata); /** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse * @net_type: type of header to parse * @sgid: place to store source gid * @dgid: place to store destination gid */ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid); /** * ib_get_rdma_header_version - Get the header version * @hdr: the L3 header to parse */ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. * @wc: Work completion associated with the received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. * When ib_init_ah_attr_from_wc() returns success, * (a) for IB link layer it optionally contains a reference to SGID attribute * when GRH is present for IB link layer. * (b) for RoCE link layer it contains a reference to SGID attribute. * User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID * attributes which are initialized using ib_init_ah_attr_from_wc(). * */ int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. * @wc: Work completion information associated with a received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @port_num: The outbound port number to associate with the address. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u32 port_num); /** * rdma_modify_ah - Modifies the address vector associated with an address * handle. * @ah: The address handle to modify. * @ah_attr: The new address vector attributes to associate with the * address handle. */ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_query_ah - Queries the address vector associated with an address * handle. * @ah: The address handle to query. * @ah_attr: The address vector attributes associated with the address * handle. */ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); enum rdma_destroy_ah_flags { /* In a sleepable context */ RDMA_DESTROY_AH_SLEEPABLE = BIT(0), }; /** * rdma_destroy_ah_user - Destroys an address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * @udata: Valid user data or NULL for kernel objects */ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata); /** * rdma_destroy_ah - Destroys an kernel address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * * NOTE: for user ah use rdma_destroy_ah_user with valid udata! */ static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags) { int ret = rdma_destroy_ah_user(ah, flags, NULL); WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail"); } struct ib_srq *ib_create_srq_user(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_usrq_object *uobject, struct ib_udata *udata); static inline struct ib_srq * ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr) { if (!pd->device->ops.create_srq) return ERR_PTR(-EOPNOTSUPP); return ib_create_srq_user(pd, srq_init_attr, NULL, NULL); } /** * ib_modify_srq - Modifies the attributes for the specified SRQ. * @srq: The SRQ to modify. * @srq_attr: On input, specifies the SRQ attributes to modify. On output, * the current values of selected SRQ attributes are returned. * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ * are being modified. * * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or * IB_SRQ_LIMIT to set the SRQ's limit and request notification when * the number of receives queued drops below the limit. */ int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask); /** * ib_query_srq - Returns the attribute list and current values for the * specified SRQ. * @srq: The SRQ to query. * @srq_attr: The attributes of the specified SRQ. */ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); /** * ib_destroy_srq_user - Destroys the specified SRQ. * @srq: The SRQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata); /** * ib_destroy_srq - Destroys the specified kernel SRQ. * @srq: The SRQ to destroy. * * NOTE: for user srq use ib_destroy_srq_user with valid udata! */ static inline void ib_destroy_srq(struct ib_srq *srq) { int ret = ib_destroy_srq_user(srq, NULL); WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail"); } /** * ib_post_srq_recv - Posts a list of work requests to the specified SRQ. * @srq: The SRQ to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return srq->device->ops.post_srq_recv(srq, recv_wr, bad_recv_wr ? : &dummy); } struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, const char *caller); /** * ib_create_qp - Creates a kernel QP associated with the specific protection * domain. * @pd: The protection domain associated with the QP. * @init_attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. */ static inline struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr) { return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME); } /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); /** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. * @qp_attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @qp_attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. */ int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask); /** * ib_query_qp - Returns the attribute list and current values for the * specified QP. * @qp: The QP to query. * @qp_attr: The attributes of the specified QP. * @qp_attr_mask: A bit-mask used to select specific attributes to query. * @qp_init_attr: Additional attributes of the selected QP. * * The qp_attr_mask may be used to limit the query to gathering only the * selected attributes. */ int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); /** * ib_destroy_qp - Destroys the specified QP. * @qp: The QP to destroy. * @udata: Valid udata or NULL for kernel objects */ int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata); /** * ib_destroy_qp - Destroys the specified kernel QP. * @qp: The QP to destroy. * * NOTE: for user qp use ib_destroy_qp_user with valid udata! */ static inline int ib_destroy_qp(struct ib_qp *qp) { return ib_destroy_qp_user(qp, NULL); } /** * ib_open_qp - Obtain a reference to an existing sharable QP. * @xrcd - XRC domain * @qp_open_attr: Attributes identifying the QP to open. * * Returns a reference to a sharable QP. */ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr); /** * ib_close_qp - Release an external reference to a QP. * @qp: The QP handle to release * * The opened QP handle is released by the caller. The underlying * shared QP is not destroyed until all internal references are released. */ int ib_close_qp(struct ib_qp *qp); /** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. * * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate * error is returned, the QP state shall not be affected, * ib_post_send() will return an immediate error after queueing any * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr) { const struct ib_send_wr *dummy; return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy); } /** * ib_post_recv - Posts a list of work requests to the receive queue of * the specified QP. * @qp: The QP to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx, const char *caller); /** * ib_alloc_cq_any: Allocate kernel CQ * @dev: The IB device * @private: Private data attached to the CQE * @nr_cqe: Number of CQEs in the CQ * @poll_ctx: Context used for polling the CQ */ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx) { return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx, KBUILD_MODNAME); } void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. * @comp_handler: A user-specified callback that is invoked when a * completion event occurs on the CQ. * @event_handler: A user-specified callback that is invoked when an * asynchronous event not associated with a completion occurs on the CQ. * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cq_attr: The attributes the CQ should be created upon. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *__ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr, const char *caller); #define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME) /** * ib_resize_cq - Modifies the capacity of the CQ. * @cq: The CQ to resize. * @cqe: The minimum size of the CQ. * * Users can examine the cq structure to determine the actual CQ size. */ int ib_resize_cq(struct ib_cq *cq, int cqe); /** * rdma_set_cq_moderation - Modifies moderation params of the CQ * @cq: The CQ to modify. * @cq_count: number of CQEs that will trigger an event * @cq_period: max period of time in usec before triggering an event * */ int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq_user - Destroys the specified CQ. * @cq: The CQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); /** * ib_destroy_cq - Destroys the specified kernel CQ. * @cq: The CQ to destroy. * * NOTE: for user cq use ib_destroy_cq_user with valid udata! */ static inline void ib_destroy_cq(struct ib_cq *cq) { int ret = ib_destroy_cq_user(cq, NULL); WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** * ib_poll_cq - poll a CQ for completion(s) * @cq:the CQ being polled * @num_entries:maximum number of completions to return * @wc:array of at least @num_entries &struct ib_wc where completions * will be returned * * Poll a CQ for (possibly multiple) completions. If the return value * is < 0, an error occurred. If the return value is >= 0, it is the * number of completions returned. If the return value is * non-negative and < num_entries, then the CQ was emptied. */ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { return cq->device->ops.poll_cq(cq, num_entries, wc); } /** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP * to request an event on the next solicited event or next work * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS * may also be |ed in to request a hint about missed events, as * described below. * * Return Value: * < 0 means an error occurred while requesting notification * == 0 means notification was requested successfully, and if * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events * were missed and it is safe to wait for another event. In * this case is it guaranteed that any work completions added * to the CQ since the last CQ poll will trigger a completion * notification event. * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed * in. It means that the consumer must poll the CQ again to * make sure it is empty to avoid missing an event because of a * race between requesting notification and an entry being * added to the CQ. This return value means it is possible * (but not guaranteed) that a work completion has been added * to the CQ since the last poll without triggering a * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags) { return cq->device->ops.req_notify_cq(cq, flags); } struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, int comp_vector_hint, enum ib_poll_context poll_ctx); void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe); /* * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to * NULL. This causes the ib_dma* helpers to just stash the kernel virtual * address into the dma address. */ static inline bool ib_uses_virt_dma(struct ib_device *dev) { return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device; } /* * Check if a IB device's underlying DMA mapping supports P2PDMA transfers. */ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return false; return dma_pci_p2pdma_supported(dev->dma_device); } /** * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after * going through the dma_addr marshalling. */ static inline void *ib_virt_dma_to_ptr(u64 dma_addr) { /* virt_dma mode maps the kvs's directly into the dma addr */ return (void *)(uintptr_t)dma_addr; } /** * ib_virt_dma_to_page - Convert a dma_addr to a struct page * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() device to get back to the struct page after going * through the dma_addr marshalling. */ static inline struct page *ib_virt_dma_to_page(u64 dma_addr) { return virt_to_page(ib_virt_dma_to_ptr(dma_addr)); } /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created * @dma_addr: The DMA address to check */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { if (ib_uses_virt_dma(dev)) return 0; return dma_mapping_error(dev->dma_device, dma_addr); } /** * ib_dma_map_single - Map a kernel virtual address to DMA address * @dev: The device for which the dma_addr is to be created * @cpu_addr: The kernel virtual address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)cpu_addr; return dma_map_single(dev->dma_device, cpu_addr, size, direction); } /** * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_single(dev->dma_device, addr, size, direction); } /** * ib_dma_map_page - Map a physical page to DMA address * @dev: The device for which the dma_addr is to be created * @page: The page to be mapped * @offset: The offset within the page * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_page(struct ib_device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)(page_address(page) + offset); return dma_map_page(dev->dma_device, page, offset, size, direction); } /** * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_page(dev->dma_device, addr, size, direction); } int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents); static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (ib_uses_virt_dma(dev)) return ib_dma_virt_map_sg(dev, sg, nents); return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The sg_table object describing the buffer * @direction: The direction of the DMA * @attrs: Optional DMA attributes for the map operation */ static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { int nents; if (ib_uses_virt_dma(dev)) { nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents); if (!nents) return -EIO; sgt->nents = nents; return 0; } return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs); } static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs); } /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses * @dev: The device for which the DMA addresses were created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_max_seg_size - Return the size limit of a single DMA transfer * @dev: The device to query * * The returned value represents a size in bytes. */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return UINT_MAX; return dma_get_max_seg_size(dev->dma_device); } /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); } /** * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_device(dev->dma_device, addr, size, dir); } /* ib_reg_user_mr - register a memory region for virtual addresses from kernel * space. This function should be called when 'current' is the owning MM. */ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags); /* ib_advise_mr - give an advice about an address range in a memory region */ int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge); /** * ib_dereg_mr_user - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * @udata: Valid user data or NULL for kernel object * * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata); /** * ib_dereg_mr - Deregisters a kernel memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * * This function can fail, if the memory region has memory windows bound to it. * * NOTE: for user mr use ib_dereg_mr_user with valid udata! */ static inline int ib_dereg_mr(struct ib_mr *mr) { return ib_dereg_mr_user(mr, NULL); } struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); /** * ib_update_fast_reg_key - updates the key portion of the fast_reg MR * R_Key and L_Key. * @mr - struct ib_mr pointer to be updated. * @newkey - new key to be used. */ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) { mr->lkey = (mr->lkey & 0xffffff00) | newkey; mr->rkey = (mr->rkey & 0xffffff00) | newkey; } /** * ib_inc_rkey - increments the key portion of the given rkey. Can be used * for calculating a new rkey for type 2 memory windows. * @rkey - the rkey to increment. */ static inline u32 ib_inc_rkey(u32 rkey) { const u32 mask = 0x000000ff; return ((rkey + 1) & mask) | (rkey & ~mask); } /** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. * * In order to send and receive multicast packets, subnet * administration must have created the multicast group and configured * the fabric appropriately. The port associated with the specified * QP must also be a member of the multicast group. */ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_detach_mcast - Detaches the specified QP from a multicast group. * @qp: QP to detach from the multicast group. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. */ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device, struct inode *inode, struct ib_udata *udata); int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata); static inline int ib_check_mr_access(struct ib_device *ib_dev, unsigned int flags) { u64 device_cap = ib_dev->attrs.device_cap_flags; /* * Local write permission is required if remote write or * remote atomic permission is also requested. */ if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && !(flags & IB_ACCESS_LOCAL_WRITE)) return -EINVAL; if (flags & ~IB_ACCESS_SUPPORTED) return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EOPNOTSUPP; if ((flags & IB_ACCESS_FLUSH_GLOBAL && !(device_cap & IB_DEVICE_FLUSH_GLOBAL)) || (flags & IB_ACCESS_FLUSH_PERSISTENT && !(device_cap & IB_DEVICE_FLUSH_PERSISTENT))) return -EOPNOTSUPP; return 0; } static inline bool ib_access_writable(int access_flags) { /* * We have writable memory backing the MR if any of the following * access flags are set. "Local write" and "remote write" obviously * require write access. "Remote atomic" can do things like fetch and * add, which will modify memory, and "MW bind" can change permissions * by binding a window. */ return access_flags & (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND); } /** * ib_check_mr_status: lightweight check of MR status. * This routine may provide status checks on a selected * ib_mr. first use is for signature status check. * * @mr: A memory region. * @check_mask: Bitmask of which checks to perform from * ib_mr_status_check enumeration. * @mr_status: The container of relevant status checks. * failed checks will be indicated in the status bitmask * and the relevant info shall be in the error item. */ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); /** * ib_device_try_get: Hold a registration lock * device: The device to lock * * A device under an active registration lock cannot become unregistered. It * is only possible to obtain a registration lock on a device that is fully * registered, otherwise this function returns false. * * The registration lock is only necessary for actions which require the * device to still be registered. Uses that only require the device pointer to * be valid should use get_device(&ibdev->dev) to hold the memory. * */ static inline bool ib_device_try_get(struct ib_device *dev) { return refcount_inc_not_zero(&dev->refcount); } void ib_device_put(struct ib_device *device); struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id); struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev, u32 *port); static inline enum ib_port_state ib_get_curr_port_state(struct net_device *net_dev) { return (netif_running(net_dev) && netif_carrier_ok(net_dev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; } void ib_dispatch_port_state_event(struct ib_device *ibdev, struct net_device *ndev); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset, unsigned int page_size); static inline int ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { int n; n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_ROCE) return attr->roce.dmac; return NULL; } static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.dlid = (u16)dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.dlid = dlid; } static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.dlid; return 0; } static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl) { attr->sl = sl; } static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr) { return attr->sl; } static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr, u8 src_path_bits) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.src_path_bits = src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.src_path_bits = src_path_bits; } static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.src_path_bits; return 0; } static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr, bool make_grd) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.make_grd = make_grd; } static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.make_grd; return false; } static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num) { attr->port_num = port_num; } static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr) { return attr->port_num; } static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr, u8 static_rate) { attr->static_rate = static_rate; } static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr) { return attr->static_rate; } static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr, enum ib_ah_flags flag) { attr->ah_flags = flag; } static inline enum ib_ah_flags rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr) { return attr->ah_flags; } static inline const struct ib_global_route *rdma_ah_read_grh(const struct rdma_ah_attr *attr) { return &attr->grh; } /*To retrieve and modify the grh */ static inline struct ib_global_route *rdma_ah_retrieve_grh(struct rdma_ah_attr *attr) { return &attr->grh; } static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid)); } static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr, __be64 prefix) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.subnet_prefix = prefix; } static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr, __be64 if_id) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.interface_id = if_id; } static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 sgid_index, u8 hop_limit, u8 traffic_class) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); attr->ah_flags = IB_AH_GRH; if (dgid) grh->dgid = *dgid; grh->flow_label = flow_label; grh->sgid_index = sgid_index; grh->hop_limit = hop_limit; grh->traffic_class = traffic_class; grh->sgid_attr = NULL; } void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr); void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 hop_limit, u8 traffic_class, const struct ib_gid_attr *sgid_attr); void rdma_copy_ah_attr(struct rdma_ah_attr *dest, const struct rdma_ah_attr *src); void rdma_replace_ah_attr(struct rdma_ah_attr *old, const struct rdma_ah_attr *new); void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src); /** * rdma_ah_find_type - Return address handle type. * * @dev: Device to be checked * @port_num: Port number */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u32 port_num) { if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; if (rdma_protocol_ib(dev, port_num)) { if (rdma_cap_opa_ah(dev, port_num)) return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; } if (dev->type == RDMA_DEVICE_TYPE_SMI) return RDMA_AH_ATTR_TYPE_IB; return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** * ib_lid_cpu16 - Return lid in 16bit CPU encoding. * In the current implementation the only way to * get the 32bit lid is from other sources for OPA. * For IB, lids will always be 16bits so cast the * value accordingly. * * @lid: A 32bit LID */ static inline u16 ib_lid_cpu16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return (u16)lid; } /** * ib_lid_be16 - Return lid in 16bit BE encoding. * * @lid: A 32bit LID */ static inline __be16 ib_lid_be16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return cpu_to_be16((u16)lid); } /** * ib_get_vector_affinity - Get the affinity mappings of a given completion * vector * @device: the rdma device * @comp_vector: index of completion vector * * Returns NULL on failure, otherwise a corresponding cpu map of the * completion vector (returns all-cpus map if the device driver doesn't * implement get_vector_affinity). */ static inline const struct cpumask * ib_get_vector_affinity(struct ib_device *device, int comp_vector) { if (comp_vector < 0 || comp_vector >= device->num_comp_vectors || !device->ops.get_vector_affinity) return NULL; return device->ops.get_vector_affinity(device, comp_vector); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @device: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ibdev); void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port); void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev); struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile); #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs); bool rdma_uattrs_has_raw_cap(const struct uverbs_attr_bundle *attrs); #else static inline int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs) { return 0; } static inline bool rdma_uattrs_has_raw_cap(const struct uverbs_attr_bundle *attrs) { return false; } #endif struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int rdma_init_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), struct net_device *netdev); /** * rdma_device_to_ibdev - Get ib_device pointer from device pointer * * @device: device pointer for which ib_device pointer to retrieve * * rdma_device_to_ibdev() retrieves ib_device pointer from device. * */ static inline struct ib_device *rdma_device_to_ibdev(struct device *device) { struct ib_core_device *coredev = container_of(device, struct ib_core_device, dev); return coredev->owner; } /** * ibdev_to_node - return the NUMA node for a given ib_device * @dev: device to get the NUMA node for. */ static inline int ibdev_to_node(struct ib_device *ibdev) { struct device *parent = ibdev->dev.parent; if (!parent) return NUMA_NO_NODE; return dev_to_node(parent); } /** * rdma_device_to_drv_device - Helper macro to reach back to driver's * ib_device holder structure from device pointer. * * NOTE: New drivers should not make use of this API; This API is only for * existing drivers who have exposed sysfs entries using * ops->device_group. */ #define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \ container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member) bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); bool rdma_dev_has_raw_cap(const struct ib_device *dev); static inline struct net *rdma_dev_net(struct ib_device *device) { return read_pnet(&device->coredev.rdma_net); } #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) #define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF) #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) /** * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based * on the flow_label * * This function will convert the 20 bit flow_label input to a valid RoCE v2 * UDP src port 14 bit value. All RoCE V2 drivers should use this same * convention. */ static inline u16 rdma_flow_label_to_udp_sport(u32 fl) { u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000; fl_low ^= fl_high >> 14; return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN); } /** * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on * local and remote qpn values * * This function folded the multiplication results of two qpns, 24 bit each, * fields, and converts it to a 20 bit results. * * This function will create symmetric flow_label value based on the local * and remote qpn values. this will allow both the requester and responder * to calculate the same flow_label for a given connection. * * This helper function should be used by driver in case the upper layer * provide a zero flow_label value. This is to improve entropy of RDMA * traffic in the network. */ static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) { u64 v = (u64)lqpn * rqpn; v ^= v >> 20; v ^= v >> 40; return (u32)(v & IB_GRH_FLOWLABEL_MASK); } /** * rdma_get_udp_sport - Calculate and set UDP source port based on the flow * label. If flow label is not defined in GRH then * calculate it based on lqpn/rqpn. * * @fl: flow label from GRH * @lqpn: local qp number * @rqpn: remote qp number */ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn) { if (!fl) fl = rdma_calc_flow_label(lqpn, rqpn); return rdma_flow_label_to_udp_sport(fl); } const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port); /** ib_add_sub_device - Add a sub IB device on an existing one * * @parent: The IB device that needs to add a sub device * @type: The type of the new sub device * @name: The name of the new sub device * * * Return 0 on success, an error code otherwise */ int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get' * * @sub: The sub device that is going to be deleted * * Return 0 on success, an error code otherwise */ int ib_del_sub_device_and_put(struct ib_device *sub); static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev) { ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER; } #endif /* IB_VERBS_H */ |
| 108 108 107 4 4 4 3 3 3 1 1 2 2 2 12 11 11 9 9 9 2 1 1 3 2 4 9 9 9 12 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * scsi_error.c Copyright (C) 1997 Eric Youngdale * * SCSI error/timeout handling * Initial versions: Eric Youngdale. Based upon conversations with * Leonard Zubkoff and David Miller at Linux Expo, * ideas originating from all over the place. * * Restructured scsi_unjam_host and associated functions. * September 04, 2002 Mike Anderson (andmike@us.ibm.com) * * Forward port of Russell King's (rmk@arm.linux.org.uk) changes and * minor cleanups. * September 30, 2002 Mike Anderson (andmike@us.ibm.com) */ #include <linux/module.h> #include <linux/sched.h> #include <linux/gfp.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/interrupt.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/jiffies.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_common.h> #include <scsi/scsi_transport.h> #include <scsi/scsi_host.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsi_dh.h> #include <scsi/scsi_devinfo.h> #include <scsi/sg.h> #include "scsi_priv.h" #include "scsi_logging.h" #include "scsi_transport_api.h" #include <trace/events/scsi.h> #include <linux/unaligned.h> /* * These should *probably* be handled by the host itself. * Since it is allowed to sleep, it probably should. */ #define BUS_RESET_SETTLE_TIME (10) #define HOST_RESET_SETTLE_TIME (10) static int scsi_eh_try_stu(struct scsi_cmnd *scmd); static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *, struct scsi_cmnd *); void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) { lockdep_assert_held(shost->host_lock); if (busy == shost->host_failed) { trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, "Waking error handler thread\n")); } } /** * scsi_schedule_eh - schedule EH for SCSI host * @shost: SCSI host to invoke error handling on. * * Schedule SCSI EH without scmd. */ void scsi_schedule_eh(struct Scsi_Host *shost) { unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { shost->host_eh_scheduled++; scsi_eh_wakeup(shost, scsi_host_busy(shost)); } spin_unlock_irqrestore(shost->host_lock, flags); } EXPORT_SYMBOL_GPL(scsi_schedule_eh); static int scsi_host_eh_past_deadline(struct Scsi_Host *shost) { if (!shost->last_reset || shost->eh_deadline == -1) return 0; /* * 32bit accesses are guaranteed to be atomic * (on all supported architectures), so instead * of using a spinlock we can as well double check * if eh_deadline has been set to 'off' during the * time_before call. */ if (time_before(jiffies, shost->last_reset + shost->eh_deadline) && shost->eh_deadline > -1) return 0; return 1; } static bool scsi_cmd_retry_allowed(struct scsi_cmnd *cmd) { if (cmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT) return true; return ++cmd->retries <= cmd->allowed; } static bool scsi_eh_should_retry_cmd(struct scsi_cmnd *cmd) { struct scsi_device *sdev = cmd->device; struct Scsi_Host *host = sdev->host; if (host->hostt->eh_should_retry_cmd) return host->hostt->eh_should_retry_cmd(cmd); return true; } /** * scmd_eh_abort_handler - Handle command aborts * @work: command to be aborted. * * Note: this function must be called only for a command that has timed out. * Because the block layer marks a request as complete before it calls * scsi_timeout(), a .scsi_done() call from the LLD for a command that has * timed out do not have any effect. Hence it is safe to call * scsi_finish_command() from this function. */ void scmd_eh_abort_handler(struct work_struct *work) { struct scsi_cmnd *scmd = container_of(work, struct scsi_cmnd, abort_work.work); struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; enum scsi_disposition rtn; unsigned long flags; if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "eh timeout, not aborting\n")); goto out; } SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "aborting command\n")); rtn = scsi_try_to_abort_cmd(shost->hostt, scmd); if (rtn != SUCCESS) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "cmd abort %s\n", (rtn == FAST_IO_FAIL) ? "not send" : "failed")); goto out; } set_host_byte(scmd, DID_TIME_OUT); if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "eh timeout, not retrying " "aborted command\n")); goto out; } spin_lock_irqsave(shost->host_lock, flags); list_del_init(&scmd->eh_entry); /* * If the abort succeeds, and there is no further * EH action, clear the ->last_reset time. */ if (list_empty(&shost->eh_abort_list) && list_empty(&shost->eh_cmd_q)) if (shost->eh_deadline != -1) shost->last_reset = 0; spin_unlock_irqrestore(shost->host_lock, flags); if (!scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) && scsi_eh_should_retry_cmd(scmd)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "retry aborted command\n")); scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY); } else { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_WARNING, scmd, "finish aborted command\n")); scsi_finish_command(scmd); } return; out: spin_lock_irqsave(shost->host_lock, flags); list_del_init(&scmd->eh_entry); spin_unlock_irqrestore(shost->host_lock, flags); scsi_eh_scmd_add(scmd); } /** * scsi_abort_command - schedule a command abort * @scmd: scmd to abort. * * We only need to abort commands after a command timeout */ static int scsi_abort_command(struct scsi_cmnd *scmd) { struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; unsigned long flags; if (!shost->hostt->eh_abort_handler) { /* No abort handler, fail command directly */ return FAILED; } if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { /* * Retry after abort failed, escalate to next level. */ SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "previous abort failed\n")); BUG_ON(delayed_work_pending(&scmd->abort_work)); return FAILED; } spin_lock_irqsave(shost->host_lock, flags); if (shost->eh_deadline != -1 && !shost->last_reset) shost->last_reset = jiffies; BUG_ON(!list_empty(&scmd->eh_entry)); list_add_tail(&scmd->eh_entry, &shost->eh_abort_list); spin_unlock_irqrestore(shost->host_lock, flags); scmd->eh_eflags |= SCSI_EH_ABORT_SCHEDULED; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "abort scheduled\n")); queue_delayed_work(shost->tmf_work_q, &scmd->abort_work, HZ / 100); return SUCCESS; } /** * scsi_eh_reset - call into ->eh_action to reset internal counters * @scmd: scmd to run eh on. * * The scsi driver might be carrying internal state about the * devices, so we need to call into the driver to reset the * internal state once the error handler is started. */ static void scsi_eh_reset(struct scsi_cmnd *scmd) { if (!blk_rq_is_passthrough(scsi_cmd_to_rq(scmd))) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); if (sdrv->eh_reset) sdrv->eh_reset(scmd); } } static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; unsigned int busy = scsi_host_busy(shost); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } /** * scsi_eh_scmd_add - add scsi cmd to error handling. * @scmd: scmd to run eh on. */ void scsi_eh_scmd_add(struct scsi_cmnd *scmd) { struct Scsi_Host *shost = scmd->device->host; unsigned long flags; int ret; WARN_ON_ONCE(!shost->ehandler); WARN_ON_ONCE(!test_bit(SCMD_STATE_INFLIGHT, &scmd->state)); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RECOVERY)) { ret = scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY); WARN_ON_ONCE(ret); } if (shost->eh_deadline != -1 && !shost->last_reset) shost->last_reset = jiffies; scsi_eh_reset(scmd); list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q); spin_unlock_irqrestore(shost->host_lock, flags); /* * Ensure that all tasks observe the host state change before the * host_failed change. */ call_rcu_hurry(&scmd->rcu, scsi_eh_inc_host_failed); } /** * scsi_timeout - Timeout function for normal scsi commands. * @req: request that is timing out. * * Notes: * We do not need to lock this. There is the potential for a race * only in that the normal completion handling might run, but if the * normal completion function determines that the timer has already * fired, then it mustn't do anything. */ enum blk_eh_timer_return scsi_timeout(struct request *req) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); struct Scsi_Host *host = scmd->device->host; trace_scsi_dispatch_cmd_timeout(scmd); scsi_log_completion(scmd, TIMEOUT_ERROR); atomic_inc(&scmd->device->iotmo_cnt); if (host->eh_deadline != -1 && !host->last_reset) host->last_reset = jiffies; if (host->hostt->eh_timed_out) { switch (host->hostt->eh_timed_out(scmd)) { case SCSI_EH_DONE: return BLK_EH_DONE; case SCSI_EH_RESET_TIMER: return BLK_EH_RESET_TIMER; case SCSI_EH_NOT_HANDLED: break; } } /* * If scsi_done() has already set SCMD_STATE_COMPLETE, do not modify * *scmd. */ if (test_and_set_bit(SCMD_STATE_COMPLETE, &scmd->state)) return BLK_EH_DONE; atomic_inc(&scmd->device->iodone_cnt); if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); } return BLK_EH_DONE; } /** * scsi_block_when_processing_errors - Prevent cmds from being queued. * @sdev: Device on which we are performing recovery. * * Description: * We block until the host is out of error recovery, and then check to * see whether the host or the device is offline. * * Return value: * 0 when dev was taken offline by error recovery. 1 OK to proceed. */ int scsi_block_when_processing_errors(struct scsi_device *sdev) { int online; wait_event(sdev->host->host_wait, !scsi_host_in_recovery(sdev->host)); online = scsi_device_online(sdev); return online; } EXPORT_SYMBOL(scsi_block_when_processing_errors); #ifdef CONFIG_SCSI_LOGGING /** * scsi_eh_prt_fail_stats - Log info on failures. * @shost: scsi host being recovered. * @work_q: Queue of scsi cmds to process. */ static inline void scsi_eh_prt_fail_stats(struct Scsi_Host *shost, struct list_head *work_q) { struct scsi_cmnd *scmd; struct scsi_device *sdev; int total_failures = 0; int cmd_failed = 0; int cmd_cancel = 0; int devices_failed = 0; shost_for_each_device(sdev, shost) { list_for_each_entry(scmd, work_q, eh_entry) { if (scmd->device == sdev) { ++total_failures; if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) ++cmd_cancel; else ++cmd_failed; } } if (cmd_cancel || cmd_failed) { SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: cmds failed: %d, cancel: %d\n", __func__, cmd_failed, cmd_cancel)); cmd_cancel = 0; cmd_failed = 0; ++devices_failed; } } SCSI_LOG_ERROR_RECOVERY(2, shost_printk(KERN_INFO, shost, "Total of %d commands on %d" " devices require eh work\n", total_failures, devices_failed)); } #endif /** * scsi_report_lun_change - Set flag on all *other* devices on the same target * to indicate that a UNIT ATTENTION is expected. * @sdev: Device reporting the UNIT ATTENTION */ static void scsi_report_lun_change(struct scsi_device *sdev) { sdev->sdev_target->expecting_lun_change = 1; } /** * scsi_report_sense - Examine scsi sense information and log messages for * certain conditions, also issue uevents for some of them. * @sdev: Device reporting the sense code * @sshdr: sshdr to be examined */ static void scsi_report_sense(struct scsi_device *sdev, struct scsi_sense_hdr *sshdr) { enum scsi_device_event evt_type = SDEV_EVT_MAXBITS; /* i.e. none */ if (sshdr->sense_key == UNIT_ATTENTION) { if (sshdr->asc == 0x3f && sshdr->ascq == 0x03) { evt_type = SDEV_EVT_INQUIRY_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Inquiry data has changed"); } else if (sshdr->asc == 0x3f && sshdr->ascq == 0x0e) { evt_type = SDEV_EVT_LUN_CHANGE_REPORTED; scsi_report_lun_change(sdev); sdev_printk(KERN_WARNING, sdev, "LUN assignments on this target have " "changed. The Linux SCSI layer does not " "automatically remap LUN assignments.\n"); } else if (sshdr->asc == 0x3f) sdev_printk(KERN_WARNING, sdev, "Operating parameters on this target have " "changed. The Linux SCSI layer does not " "automatically adjust these parameters.\n"); if (sshdr->asc == 0x38 && sshdr->ascq == 0x07) { evt_type = SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED; sdev_printk(KERN_WARNING, sdev, "Warning! Received an indication that the " "LUN reached a thin provisioning soft " "threshold.\n"); } if (sshdr->asc == 0x29) { evt_type = SDEV_EVT_POWER_ON_RESET_OCCURRED; /* * Do not print message if it is an expected side-effect * of runtime PM. */ if (!sdev->silence_suspend) sdev_printk(KERN_WARNING, sdev, "Power-on or device reset occurred\n"); } if (sshdr->asc == 0x2a && sshdr->ascq == 0x01) { evt_type = SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Mode parameters changed"); } else if (sshdr->asc == 0x2a && sshdr->ascq == 0x06) { evt_type = SDEV_EVT_ALUA_STATE_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Asymmetric access state changed"); } else if (sshdr->asc == 0x2a && sshdr->ascq == 0x09) { evt_type = SDEV_EVT_CAPACITY_CHANGE_REPORTED; sdev_printk(KERN_WARNING, sdev, "Capacity data has changed"); } else if (sshdr->asc == 0x2a) sdev_printk(KERN_WARNING, sdev, "Parameters changed"); } if (evt_type != SDEV_EVT_MAXBITS) { set_bit(evt_type, sdev->pending_events); schedule_work(&sdev->event_work); } } static inline void set_scsi_ml_byte(struct scsi_cmnd *cmd, u8 status) { cmd->result = (cmd->result & 0xffff00ff) | (status << 8); } /** * scsi_check_sense - Examine scsi cmd sense * @scmd: Cmd to have sense checked. * * Return value: * SUCCESS or FAILED or NEEDS_RETRY or ADD_TO_MLQUEUE * * Notes: * When a deferred error is detected the current command has * not been executed and needs retrying. */ enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd) { struct request *req = scsi_cmd_to_rq(scmd); struct scsi_device *sdev = scmd->device; struct scsi_sense_hdr sshdr; if (! scsi_command_normalize_sense(scmd, &sshdr)) return FAILED; /* no valid sense data */ scsi_report_sense(sdev, &sshdr); if (sshdr.sense_key == UNIT_ATTENTION) { /* * Increment the counters for Power on/Reset or New Media so * that all ULDs interested in these can see that those have * happened, even if someone else gets the sense data. */ if (sshdr.asc == 0x28) atomic_inc(&sdev->ua_new_media_ctr); else if (sshdr.asc == 0x29) atomic_inc(&sdev->ua_por_ctr); } if (scsi_sense_is_deferred(&sshdr)) return NEEDS_RETRY; if (sdev->handler && sdev->handler->check_sense) { enum scsi_disposition rc; rc = sdev->handler->check_sense(sdev, &sshdr); if (rc != SCSI_RETURN_NOT_HANDLED) return rc; /* handler does not care. Drop down to default handling */ } if (scmd->cmnd[0] == TEST_UNIT_READY && scmd->submitter != SUBMITTED_BY_SCSI_ERROR_HANDLER) /* * nasty: for mid-layer issued TURs, we need to return the * actual sense data without any recovery attempt. For eh * issued ones, we need to try to recover and interpret */ return SUCCESS; /* * Previous logic looked for FILEMARK, EOM or ILI which are * mainly associated with tapes and returned SUCCESS. */ if (sshdr.response_code == 0x70) { /* fixed format */ if (scmd->sense_buffer[2] & 0xe0) return SUCCESS; } else { /* * descriptor format: look for "stream commands sense data * descriptor" (see SSC-3). Assume single sense data * descriptor. Ignore ILI from SBC-2 READ LONG and WRITE LONG. */ if ((sshdr.additional_length > 3) && (scmd->sense_buffer[8] == 0x4) && (scmd->sense_buffer[11] & 0xe0)) return SUCCESS; } switch (sshdr.sense_key) { case NO_SENSE: return SUCCESS; case RECOVERED_ERROR: return /* soft_error */ SUCCESS; case ABORTED_COMMAND: if (sshdr.asc == 0x10) /* DIF */ return SUCCESS; /* * Check aborts due to command duration limit policy: * ABORTED COMMAND additional sense code with the * COMMAND TIMEOUT BEFORE PROCESSING or * COMMAND TIMEOUT DURING PROCESSING or * COMMAND TIMEOUT DURING PROCESSING DUE TO ERROR RECOVERY * additional sense code qualifiers. */ if (sshdr.asc == 0x2e && sshdr.ascq >= 0x01 && sshdr.ascq <= 0x03) { set_scsi_ml_byte(scmd, SCSIML_STAT_DL_TIMEOUT); req->cmd_flags |= REQ_FAILFAST_DEV; req->rq_flags |= RQF_QUIET; return SUCCESS; } if (sshdr.asc == 0x44 && sdev->sdev_bflags & BLIST_RETRY_ITF) return ADD_TO_MLQUEUE; if (sshdr.asc == 0xc1 && sshdr.ascq == 0x01 && sdev->sdev_bflags & BLIST_RETRY_ASC_C1) return ADD_TO_MLQUEUE; return NEEDS_RETRY; case NOT_READY: case UNIT_ATTENTION: /* * if we are expecting a cc/ua because of a bus reset that we * performed, treat this just as a retry. otherwise this is * information that we should pass up to the upper-level driver * so that we can deal with it there. */ if (scmd->device->expecting_cc_ua) { /* * Because some device does not queue unit * attentions correctly, we carefully check * additional sense code and qualifier so as * not to squash media change unit attention. */ if (sshdr.asc != 0x28 || sshdr.ascq != 0x00) { scmd->device->expecting_cc_ua = 0; return NEEDS_RETRY; } } /* * we might also expect a cc/ua if another LUN on the target * reported a UA with an ASC/ASCQ of 3F 0E - * REPORTED LUNS DATA HAS CHANGED. */ if (scmd->device->sdev_target->expecting_lun_change && sshdr.asc == 0x3f && sshdr.ascq == 0x0e) return NEEDS_RETRY; /* * if the device is in the process of becoming ready, we * should retry. */ if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01 || sshdr.ascq == 0x0a)) return NEEDS_RETRY; /* * if the device is not started, we need to wake * the error handler to start the motor */ if (scmd->device->allow_restart && (sshdr.asc == 0x04) && (sshdr.ascq == 0x02)) return FAILED; /* * Pass the UA upwards for a determination in the completion * functions. */ return SUCCESS; /* these are not supported */ case DATA_PROTECT: if (sshdr.asc == 0x27 && sshdr.ascq == 0x07) { /* Thin provisioning hard threshold reached */ set_scsi_ml_byte(scmd, SCSIML_STAT_NOSPC); return SUCCESS; } fallthrough; case COPY_ABORTED: case VOLUME_OVERFLOW: case MISCOMPARE: case BLANK_CHECK: set_scsi_ml_byte(scmd, SCSIML_STAT_TGT_FAILURE); return SUCCESS; case MEDIUM_ERROR: if (sshdr.asc == 0x11 || /* UNRECOVERED READ ERR */ sshdr.asc == 0x13 || /* AMNF DATA FIELD */ sshdr.asc == 0x14) { /* RECORD NOT FOUND */ set_scsi_ml_byte(scmd, SCSIML_STAT_MED_ERROR); return SUCCESS; } return NEEDS_RETRY; case HARDWARE_ERROR: if (scmd->device->retry_hwerror) return ADD_TO_MLQUEUE; else set_scsi_ml_byte(scmd, SCSIML_STAT_TGT_FAILURE); fallthrough; case ILLEGAL_REQUEST: if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x22 || /* Invalid function */ sshdr.asc == 0x24 || /* Invalid field in cdb */ sshdr.asc == 0x26 || /* Parameter value invalid */ sshdr.asc == 0x27) { /* Write protected */ set_scsi_ml_byte(scmd, SCSIML_STAT_TGT_FAILURE); } return SUCCESS; case COMPLETED: /* * A command using command duration limits (CDL) with a * descriptor set with policy 0xD may be completed with success * and the sense data DATA CURRENTLY UNAVAILABLE, indicating * that the command was in fact aborted because it exceeded its * duration limit. Never retry these commands. */ if (sshdr.asc == 0x55 && sshdr.ascq == 0x0a) { set_scsi_ml_byte(scmd, SCSIML_STAT_DL_TIMEOUT); req->cmd_flags |= REQ_FAILFAST_DEV; req->rq_flags |= RQF_QUIET; } return SUCCESS; default: return SUCCESS; } } EXPORT_SYMBOL_GPL(scsi_check_sense); static void scsi_handle_queue_ramp_up(struct scsi_device *sdev) { const struct scsi_host_template *sht = sdev->host->hostt; struct scsi_device *tmp_sdev; if (!sht->track_queue_depth || sdev->queue_depth >= sdev->max_queue_depth) return; if (time_before(jiffies, sdev->last_queue_ramp_up + sdev->queue_ramp_up_period)) return; if (time_before(jiffies, sdev->last_queue_full_time + sdev->queue_ramp_up_period)) return; /* * Walk all devices of a target and do * ramp up on them. */ shost_for_each_device(tmp_sdev, sdev->host) { if (tmp_sdev->channel != sdev->channel || tmp_sdev->id != sdev->id || tmp_sdev->queue_depth == sdev->max_queue_depth) continue; scsi_change_queue_depth(tmp_sdev, tmp_sdev->queue_depth + 1); sdev->last_queue_ramp_up = jiffies; } } static void scsi_handle_queue_full(struct scsi_device *sdev) { const struct scsi_host_template *sht = sdev->host->hostt; struct scsi_device *tmp_sdev; if (!sht->track_queue_depth) return; shost_for_each_device(tmp_sdev, sdev->host) { if (tmp_sdev->channel != sdev->channel || tmp_sdev->id != sdev->id) continue; /* * We do not know the number of commands that were at * the device when we got the queue full so we start * from the highest possible value and work our way down. */ scsi_track_queue_full(tmp_sdev, tmp_sdev->queue_depth - 1); } } /** * scsi_eh_completed_normally - Disposition a eh cmd on return from LLD. * @scmd: SCSI cmd to examine. * * Notes: * This is *only* called when we are examining the status of commands * queued during error recovery. the main difference here is that we * don't allow for the possibility of retries here, and we are a lot * more restrictive about what we consider acceptable. */ static enum scsi_disposition scsi_eh_completed_normally(struct scsi_cmnd *scmd) { /* * first check the host byte, to see if there is anything in there * that would indicate what we need to do. */ if (host_byte(scmd->result) == DID_RESET) { /* * rats. we are already in the error handler, so we now * get to try and figure out what to do next. if the sense * is valid, we have a pretty good idea of what to do. * if not, we mark it as FAILED. */ return scsi_check_sense(scmd); } if (host_byte(scmd->result) != DID_OK) return FAILED; /* * now, check the status byte to see if this indicates * anything special. */ switch (get_status_byte(scmd)) { case SAM_STAT_GOOD: scsi_handle_queue_ramp_up(scmd->device); if (scmd->sense_buffer && SCSI_SENSE_VALID(scmd)) /* * If we have sense data, call scsi_check_sense() in * order to set the correct SCSI ML byte (if any). * No point in checking the return value, since the * command has already completed successfully. */ scsi_check_sense(scmd); fallthrough; case SAM_STAT_COMMAND_TERMINATED: return SUCCESS; case SAM_STAT_CHECK_CONDITION: return scsi_check_sense(scmd); case SAM_STAT_CONDITION_MET: case SAM_STAT_INTERMEDIATE: case SAM_STAT_INTERMEDIATE_CONDITION_MET: /* * who knows? FIXME(eric) */ return SUCCESS; case SAM_STAT_RESERVATION_CONFLICT: if (scmd->cmnd[0] == TEST_UNIT_READY) /* it is a success, we probed the device and * found it */ return SUCCESS; /* otherwise, we failed to send the command */ return FAILED; case SAM_STAT_TASK_SET_FULL: scsi_handle_queue_full(scmd->device); fallthrough; case SAM_STAT_BUSY: return NEEDS_RETRY; default: return FAILED; } return FAILED; } /** * scsi_eh_done - Completion function for error handling. * @scmd: Cmd that is done. */ void scsi_eh_done(struct scsi_cmnd *scmd) { struct completion *eh_action; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s result: %x\n", __func__, scmd->result)); eh_action = scmd->device->host->eh_action; if (eh_action) complete(eh_action); } /** * scsi_try_host_reset - ask host adapter to reset itself * @scmd: SCSI cmd to send host reset. */ static enum scsi_disposition scsi_try_host_reset(struct scsi_cmnd *scmd) { unsigned long flags; enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; const struct scsi_host_template *hostt = host->hostt; SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, host, "Snd Host RST\n")); if (!hostt->eh_host_reset_handler) return FAILED; rtn = hostt->eh_host_reset_handler(scmd); if (rtn == SUCCESS) { if (!hostt->skip_settle_delay) ssleep(HOST_RESET_SETTLE_TIME); spin_lock_irqsave(host->host_lock, flags); scsi_report_bus_reset(host, scmd_channel(scmd)); spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } /** * scsi_try_bus_reset - ask host to perform a bus reset * @scmd: SCSI cmd to send bus reset. */ static enum scsi_disposition scsi_try_bus_reset(struct scsi_cmnd *scmd) { unsigned long flags; enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; const struct scsi_host_template *hostt = host->hostt; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: Snd Bus RST\n", __func__)); if (!hostt->eh_bus_reset_handler) return FAILED; rtn = hostt->eh_bus_reset_handler(scmd); if (rtn == SUCCESS) { if (!hostt->skip_settle_delay) ssleep(BUS_RESET_SETTLE_TIME); spin_lock_irqsave(host->host_lock, flags); scsi_report_bus_reset(host, scmd_channel(scmd)); spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } static void __scsi_report_device_reset(struct scsi_device *sdev, void *data) { sdev->was_reset = 1; sdev->expecting_cc_ua = 1; } /** * scsi_try_target_reset - Ask host to perform a target reset * @scmd: SCSI cmd used to send a target reset * * Notes: * There is no timeout for this operation. if this operation is * unreliable for a given host, then the host itself needs to put a * timer on it, and set the host back to a consistent state prior to * returning. */ static enum scsi_disposition scsi_try_target_reset(struct scsi_cmnd *scmd) { unsigned long flags; enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; const struct scsi_host_template *hostt = host->hostt; if (!hostt->eh_target_reset_handler) return FAILED; rtn = hostt->eh_target_reset_handler(scmd); if (rtn == SUCCESS) { spin_lock_irqsave(host->host_lock, flags); __starget_for_each_device(scsi_target(scmd->device), NULL, __scsi_report_device_reset); spin_unlock_irqrestore(host->host_lock, flags); } return rtn; } /** * scsi_try_bus_device_reset - Ask host to perform a BDR on a dev * @scmd: SCSI cmd used to send BDR * * Notes: * There is no timeout for this operation. if this operation is * unreliable for a given host, then the host itself needs to put a * timer on it, and set the host back to a consistent state prior to * returning. */ static enum scsi_disposition scsi_try_bus_device_reset(struct scsi_cmnd *scmd) { enum scsi_disposition rtn; const struct scsi_host_template *hostt = scmd->device->host->hostt; if (!hostt->eh_device_reset_handler) return FAILED; rtn = hostt->eh_device_reset_handler(scmd); if (rtn == SUCCESS) __scsi_report_device_reset(scmd->device, NULL); return rtn; } /** * scsi_try_to_abort_cmd - Ask host to abort a SCSI command * @hostt: SCSI driver host template * @scmd: SCSI cmd used to send a target reset * * Return value: * SUCCESS, FAILED, or FAST_IO_FAIL * * Notes: * SUCCESS does not necessarily indicate that the command * has been aborted; it only indicates that the LLDDs * has cleared all references to that command. * LLDDs should return FAILED only if an abort was required * but could not be executed. LLDDs should return FAST_IO_FAIL * if the device is temporarily unavailable (eg due to a * link down on FibreChannel) */ static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *hostt, struct scsi_cmnd *scmd) { if (!hostt->eh_abort_handler) return FAILED; return hostt->eh_abort_handler(scmd); } static void scsi_abort_eh_cmnd(struct scsi_cmnd *scmd) { if (scsi_try_to_abort_cmd(scmd->device->host->hostt, scmd) != SUCCESS) if (scsi_try_bus_device_reset(scmd) != SUCCESS) if (scsi_try_target_reset(scmd) != SUCCESS) if (scsi_try_bus_reset(scmd) != SUCCESS) scsi_try_host_reset(scmd); } /** * scsi_eh_prep_cmnd - Save a scsi command info as part of error recovery * @scmd: SCSI command structure to hijack * @ses: structure to save restore information * @cmnd: CDB to send. Can be NULL if no new cmnd is needed * @cmnd_size: size in bytes of @cmnd (must be <= MAX_COMMAND_SIZE) * @sense_bytes: size of sense data to copy. or 0 (if != 0 @cmnd is ignored) * * This function is used to save a scsi command information before re-execution * as part of the error recovery process. If @sense_bytes is 0 the command * sent must be one that does not transfer any data. If @sense_bytes != 0 * @cmnd is ignored and this functions sets up a REQUEST_SENSE command * and cmnd buffers to read @sense_bytes into @scmd->sense_buffer. */ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, unsigned char *cmnd, int cmnd_size, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; /* * We need saved copies of a number of fields - this is because * error handling may need to overwrite these with different values * to run different commands, and once error handling is complete, * we will need to restore these values prior to running the actual * command. */ ses->cmd_len = scmd->cmd_len; ses->data_direction = scmd->sc_data_direction; ses->sdb = scmd->sdb; ses->result = scmd->result; ses->resid_len = scmd->resid_len; ses->underflow = scmd->underflow; ses->prot_op = scmd->prot_op; ses->eh_eflags = scmd->eh_eflags; scmd->prot_op = SCSI_PROT_NORMAL; scmd->eh_eflags = 0; memcpy(ses->cmnd, scmd->cmnd, sizeof(ses->cmnd)); memset(scmd->cmnd, 0, sizeof(scmd->cmnd)); memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->result = 0; scmd->resid_len = 0; if (sense_bytes) { scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, sense_bytes); sg_init_one(&ses->sense_sgl, scmd->sense_buffer, scmd->sdb.length); scmd->sdb.table.sgl = &ses->sense_sgl; scmd->sc_data_direction = DMA_FROM_DEVICE; scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1; scmd->cmnd[0] = REQUEST_SENSE; scmd->cmnd[4] = scmd->sdb.length; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } else { scmd->sc_data_direction = DMA_NONE; if (cmnd) { BUG_ON(cmnd_size > sizeof(scmd->cmnd)); memcpy(scmd->cmnd, cmnd, cmnd_size); scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } } scmd->underflow = 0; if (sdev->scsi_level <= SCSI_2 && sdev->scsi_level != SCSI_UNKNOWN) scmd->cmnd[1] = (scmd->cmnd[1] & 0x1f) | (sdev->lun << 5 & 0xe0); /* * Zero the sense buffer. The scsi spec mandates that any * untransferred sense data should be interpreted as being zero. */ memset(scmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); } EXPORT_SYMBOL(scsi_eh_prep_cmnd); /** * scsi_eh_restore_cmnd - Restore a scsi command info as part of error recovery * @scmd: SCSI command structure to restore * @ses: saved information from a coresponding call to scsi_eh_prep_cmnd * * Undo any damage done by above scsi_eh_prep_cmnd(). */ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) { /* * Restore original data */ scmd->cmd_len = ses->cmd_len; memcpy(scmd->cmnd, ses->cmnd, sizeof(ses->cmnd)); scmd->sc_data_direction = ses->data_direction; scmd->sdb = ses->sdb; scmd->result = ses->result; scmd->resid_len = ses->resid_len; scmd->underflow = ses->underflow; scmd->prot_op = ses->prot_op; scmd->eh_eflags = ses->eh_eflags; } EXPORT_SYMBOL(scsi_eh_restore_cmnd); /** * scsi_send_eh_cmnd - submit a scsi command as part of error recovery * @scmd: SCSI command structure to hijack * @cmnd: CDB to send * @cmnd_size: size in bytes of @cmnd * @timeout: timeout for this request * @sense_bytes: size of sense data to copy or 0 * * This function is used to send a scsi command down to a target device * as part of the error recovery process. See also scsi_eh_prep_cmnd() above. * * Return value: * SUCCESS or FAILED or NEEDS_RETRY */ static enum scsi_disposition scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd, int cmnd_size, int timeout, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; DECLARE_COMPLETION_ONSTACK(done); unsigned long timeleft = timeout, delay; struct scsi_eh_save ses; const unsigned long stall_for = msecs_to_jiffies(100); int rtn; retry: scsi_eh_prep_cmnd(scmd, &ses, cmnd, cmnd_size, sense_bytes); shost->eh_action = &done; scsi_log_send(scmd); scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER; scmd->flags |= SCMD_LAST; /* * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can * change the SCSI device state after we have examined it and before * .queuecommand() is called. */ mutex_lock(&sdev->state_mutex); while (sdev->sdev_state == SDEV_BLOCK && timeleft > 0) { mutex_unlock(&sdev->state_mutex); SCSI_LOG_ERROR_RECOVERY(5, sdev_printk(KERN_DEBUG, sdev, "%s: state %d <> %d\n", __func__, sdev->sdev_state, SDEV_BLOCK)); delay = min(timeleft, stall_for); timeleft -= delay; msleep(jiffies_to_msecs(delay)); mutex_lock(&sdev->state_mutex); } if (sdev->sdev_state != SDEV_BLOCK) rtn = shost->hostt->queuecommand(shost, scmd); else rtn = FAILED; mutex_unlock(&sdev->state_mutex); if (rtn) { if (timeleft > stall_for) { scsi_eh_restore_cmnd(scmd, &ses); timeleft -= stall_for; msleep(jiffies_to_msecs(stall_for)); goto retry; } /* signal not to enter either branch of the if () below */ timeleft = 0; rtn = FAILED; } else { timeleft = wait_for_completion_timeout(&done, timeout); rtn = SUCCESS; } shost->eh_action = NULL; scsi_log_completion(scmd, rtn); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s timeleft: %ld\n", __func__, timeleft)); /* * If there is time left scsi_eh_done got called, and we will examine * the actual status codes to see whether the command actually did * complete normally, else if we have a zero return and no time left, * the command must still be pending, so abort it and return FAILED. * If we never actually managed to issue the command, because * ->queuecommand() kept returning non zero, use the rtn = FAILED * value above (so don't execute either branch of the if) */ if (timeleft) { rtn = scsi_eh_completed_normally(scmd); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: scsi_eh_completed_normally %x\n", __func__, rtn)); switch (rtn) { case SUCCESS: case NEEDS_RETRY: case FAILED: break; case ADD_TO_MLQUEUE: rtn = NEEDS_RETRY; break; default: rtn = FAILED; break; } } else if (rtn != FAILED) { scsi_abort_eh_cmnd(scmd); rtn = FAILED; } scsi_eh_restore_cmnd(scmd, &ses); return rtn; } /** * scsi_request_sense - Request sense data from a particular target. * @scmd: SCSI cmd for request sense. * * Notes: * Some hosts automatically obtain this information, others require * that we obtain it on our own. This function will *not* return until * the command either times out, or it completes. */ static enum scsi_disposition scsi_request_sense(struct scsi_cmnd *scmd) { return scsi_send_eh_cmnd(scmd, NULL, 0, scmd->device->eh_timeout, ~0); } static enum scsi_disposition scsi_eh_action(struct scsi_cmnd *scmd, enum scsi_disposition rtn) { if (!blk_rq_is_passthrough(scsi_cmd_to_rq(scmd))) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); if (sdrv->eh_action) rtn = sdrv->eh_action(scmd, rtn); } return rtn; } /** * scsi_eh_finish_cmd - Handle a cmd that eh is finished with. * @scmd: Original SCSI cmd that eh has finished. * @done_q: Queue for processed commands. * * Notes: * We don't want to use the normal command completion while we are are * still handling errors - it may cause other commands to be queued, * and that would disturb what we are doing. Thus we really want to * keep a list of pending commands for final completion, and once we * are ready to leave error handling we handle completion for real. */ void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q) { list_move_tail(&scmd->eh_entry, done_q); } EXPORT_SYMBOL(scsi_eh_finish_cmd); /** * scsi_eh_get_sense - Get device sense data. * @work_q: Queue of commands to process. * @done_q: Queue of processed commands. * * Description: * See if we need to request sense information. if so, then get it * now, so we have a better idea of what to do. * * Notes: * This has the unfortunate side effect that if a shost adapter does * not automatically request sense information, we end up shutting * it down before we request it. * * All drivers should request sense information internally these days, * so for now all I have to say is tough noogies if you end up in here. * * XXX: Long term this code should go away, but that needs an audit of * all LLDDs first. */ int scsi_eh_get_sense(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; struct Scsi_Host *shost; enum scsi_disposition rtn; /* * If SCSI_EH_ABORT_SCHEDULED has been set, it is timeout IO, * should not get sense. */ list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if ((scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) || SCSI_SENSE_VALID(scmd)) continue; shost = scmd->device->host; if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: skip request sense, past eh deadline\n", current->comm)); break; } if (!scsi_status_is_check_condition(scmd->result)) /* * don't request sense if there's no check condition * status because the error we're processing isn't one * that has a sense code (and some devices get * confused by sense requests out of the blue) */ continue; SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd, "%s: requesting sense\n", current->comm)); rtn = scsi_request_sense(scmd); if (rtn != SUCCESS) continue; SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "sense requested, result %x\n", scmd->result)); SCSI_LOG_ERROR_RECOVERY(3, scsi_print_sense(scmd)); rtn = scsi_decide_disposition(scmd); /* * if the result was normal, then just pass it along to the * upper level. */ if (rtn == SUCCESS) /* * We don't want this command reissued, just finished * with the sense data, so set retries to the max * allowed to ensure it won't get reissued. If the user * has requested infinite retries, we also want to * finish this command, so force completion by setting * retries and allowed to the same value. */ if (scmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT) scmd->retries = scmd->allowed = 1; else scmd->retries = scmd->allowed; else if (rtn != NEEDS_RETRY) continue; scsi_eh_finish_cmd(scmd, done_q); } return list_empty(work_q); } EXPORT_SYMBOL_GPL(scsi_eh_get_sense); /** * scsi_eh_tur - Send TUR to device. * @scmd: &scsi_cmnd to send TUR * * Return value: * 0 - Device is ready. 1 - Device NOT ready. */ static int scsi_eh_tur(struct scsi_cmnd *scmd) { static unsigned char tur_command[6] = {TEST_UNIT_READY, 0, 0, 0, 0, 0}; int retry_cnt = 1; enum scsi_disposition rtn; retry_tur: rtn = scsi_send_eh_cmnd(scmd, tur_command, 6, scmd->device->eh_timeout, 0); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s return: %x\n", __func__, rtn)); switch (rtn) { case NEEDS_RETRY: if (retry_cnt--) goto retry_tur; fallthrough; case SUCCESS: return 0; default: return 1; } } /** * scsi_eh_test_devices - check if devices are responding from error recovery. * @cmd_list: scsi commands in error recovery. * @work_q: queue for commands which still need more error recovery * @done_q: queue for commands which are finished * @try_stu: boolean on if a STU command should be tried in addition to TUR. * * Decription: * Tests if devices are in a working state. Commands to devices now in * a working state are sent to the done_q while commands to devices which * are still failing to respond are returned to the work_q for more * processing. **/ static int scsi_eh_test_devices(struct list_head *cmd_list, struct list_head *work_q, struct list_head *done_q, int try_stu) { struct scsi_cmnd *scmd, *next; struct scsi_device *sdev; int finish_cmds; while (!list_empty(cmd_list)) { scmd = list_entry(cmd_list->next, struct scsi_cmnd, eh_entry); sdev = scmd->device; if (!try_stu) { if (scsi_host_eh_past_deadline(sdev->host)) { /* Push items back onto work_q */ list_splice_init(cmd_list, work_q); SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: skip test device, past eh deadline", current->comm)); break; } } finish_cmds = !scsi_device_online(scmd->device) || (try_stu && !scsi_eh_try_stu(scmd) && !scsi_eh_tur(scmd)) || !scsi_eh_tur(scmd); list_for_each_entry_safe(scmd, next, cmd_list, eh_entry) if (scmd->device == sdev) { if (finish_cmds && (try_stu || scsi_eh_action(scmd, SUCCESS) == SUCCESS)) scsi_eh_finish_cmd(scmd, done_q); else list_move_tail(&scmd->eh_entry, work_q); } } return list_empty(work_q); } /** * scsi_eh_try_stu - Send START_UNIT to device. * @scmd: &scsi_cmnd to send START_UNIT * * Return value: * 0 - Device is ready. 1 - Device NOT ready. */ static int scsi_eh_try_stu(struct scsi_cmnd *scmd) { static unsigned char stu_command[6] = {START_STOP, 0, 0, 0, 1, 0}; if (scmd->device->allow_restart) { int i; enum scsi_disposition rtn = NEEDS_RETRY; for (i = 0; rtn == NEEDS_RETRY && i < 2; i++) rtn = scsi_send_eh_cmnd(scmd, stu_command, 6, scmd->device->eh_timeout, 0); if (rtn == SUCCESS) return 0; } return 1; } /** * scsi_eh_stu - send START_UNIT if needed * @shost: &scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. * * Notes: * If commands are failing due to not ready, initializing command required, * try revalidating the device, which will end up sending a start unit. */ static int scsi_eh_stu(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *stu_scmd, *next; struct scsi_device *sdev; shost_for_each_device(sdev, shost) { if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: skip START_UNIT, past eh deadline\n", current->comm)); scsi_device_put(sdev); break; } stu_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) if (scmd->device == sdev && SCSI_SENSE_VALID(scmd) && scsi_check_sense(scmd) == FAILED ) { stu_scmd = scmd; break; } if (!stu_scmd) continue; SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: Sending START_UNIT\n", current->comm)); if (!scsi_eh_try_stu(stu_scmd)) { if (!scsi_device_online(sdev) || !scsi_eh_tur(stu_scmd)) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (scmd->device == sdev && scsi_eh_action(scmd, SUCCESS) == SUCCESS) scsi_eh_finish_cmd(scmd, done_q); } } } else { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: START_UNIT failed\n", current->comm)); } } return list_empty(work_q); } /** * scsi_eh_bus_device_reset - send bdr if needed * @shost: scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. * * Notes: * Try a bus device reset. Still, look to see whether we have multiple * devices that are jammed or not - if we have multiple devices, it * makes no sense to try bus_device_reset - we really would need to try * a bus_reset instead. */ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *bdr_scmd, *next; struct scsi_device *sdev; enum scsi_disposition rtn; shost_for_each_device(sdev, shost) { if (scsi_host_eh_past_deadline(shost)) { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: skip BDR, past eh deadline\n", current->comm)); scsi_device_put(sdev); break; } bdr_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) if (scmd->device == sdev) { bdr_scmd = scmd; break; } if (!bdr_scmd) continue; SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: Sending BDR\n", current->comm)); rtn = scsi_try_bus_device_reset(bdr_scmd); if (rtn == SUCCESS || rtn == FAST_IO_FAIL) { if (!scsi_device_online(sdev) || rtn == FAST_IO_FAIL || !scsi_eh_tur(bdr_scmd)) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (scmd->device == sdev && scsi_eh_action(scmd, rtn) != FAILED) scsi_eh_finish_cmd(scmd, done_q); } } } else { SCSI_LOG_ERROR_RECOVERY(3, sdev_printk(KERN_INFO, sdev, "%s: BDR failed\n", current->comm)); } } return list_empty(work_q); } /** * scsi_eh_target_reset - send target reset if needed * @shost: scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. * * Notes: * Try a target reset. */ static int scsi_eh_target_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { LIST_HEAD(tmp_list); LIST_HEAD(check_list); list_splice_init(work_q, &tmp_list); while (!list_empty(&tmp_list)) { struct scsi_cmnd *next, *scmd; enum scsi_disposition rtn; unsigned int id; if (scsi_host_eh_past_deadline(shost)) { /* push back on work queue for further processing */ list_splice_init(&check_list, work_q); list_splice_init(&tmp_list, work_q); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Skip target reset, past eh deadline\n", current->comm)); return list_empty(work_q); } scmd = list_entry(tmp_list.next, struct scsi_cmnd, eh_entry); id = scmd_id(scmd); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Sending target reset to target %d\n", current->comm, id)); rtn = scsi_try_target_reset(scmd); if (rtn != SUCCESS && rtn != FAST_IO_FAIL) SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Target reset failed" " target: %d\n", current->comm, id)); list_for_each_entry_safe(scmd, next, &tmp_list, eh_entry) { if (scmd_id(scmd) != id) continue; if (rtn == SUCCESS) list_move_tail(&scmd->eh_entry, &check_list); else if (rtn == FAST_IO_FAIL) scsi_eh_finish_cmd(scmd, done_q); else /* push back on work queue for further processing */ list_move(&scmd->eh_entry, work_q); } } return scsi_eh_test_devices(&check_list, work_q, done_q, 0); } /** * scsi_eh_bus_reset - send a bus reset * @shost: &scsi host being recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ static int scsi_eh_bus_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *chan_scmd, *next; LIST_HEAD(check_list); unsigned int channel; enum scsi_disposition rtn; /* * we really want to loop over the various channels, and do this on * a channel by channel basis. we should also check to see if any * of the failed commands are on soft_reset devices, and if so, skip * the reset. */ for (channel = 0; channel <= shost->max_channel; channel++) { if (scsi_host_eh_past_deadline(shost)) { list_splice_init(&check_list, work_q); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: skip BRST, past eh deadline\n", current->comm)); return list_empty(work_q); } chan_scmd = NULL; list_for_each_entry(scmd, work_q, eh_entry) { if (channel == scmd_channel(scmd)) { chan_scmd = scmd; break; /* * FIXME add back in some support for * soft_reset devices. */ } } if (!chan_scmd) continue; SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Sending BRST chan: %d\n", current->comm, channel)); rtn = scsi_try_bus_reset(chan_scmd); if (rtn == SUCCESS || rtn == FAST_IO_FAIL) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { if (channel == scmd_channel(scmd)) { if (rtn == FAST_IO_FAIL) scsi_eh_finish_cmd(scmd, done_q); else list_move_tail(&scmd->eh_entry, &check_list); } } } else { SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: BRST failed chan: %d\n", current->comm, channel)); } } return scsi_eh_test_devices(&check_list, work_q, done_q, 0); } /** * scsi_eh_host_reset - send a host reset * @shost: host to be reset. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ static int scsi_eh_host_reset(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; LIST_HEAD(check_list); enum scsi_disposition rtn; if (!list_empty(work_q)) { scmd = list_entry(work_q->next, struct scsi_cmnd, eh_entry); SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: Sending HRST\n", current->comm)); rtn = scsi_try_host_reset(scmd); if (rtn == SUCCESS) { list_splice_init(work_q, &check_list); } else if (rtn == FAST_IO_FAIL) { list_for_each_entry_safe(scmd, next, work_q, eh_entry) { scsi_eh_finish_cmd(scmd, done_q); } } else { SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "%s: HRST failed\n", current->comm)); } } return scsi_eh_test_devices(&check_list, work_q, done_q, 1); } /** * scsi_eh_offline_sdevs - offline scsi devices that fail to recover * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ static void scsi_eh_offline_sdevs(struct list_head *work_q, struct list_head *done_q) { struct scsi_cmnd *scmd, *next; struct scsi_device *sdev; list_for_each_entry_safe(scmd, next, work_q, eh_entry) { sdev_printk(KERN_INFO, scmd->device, "Device offlined - " "not ready after error recovery\n"); sdev = scmd->device; mutex_lock(&sdev->state_mutex); scsi_device_set_state(sdev, SDEV_OFFLINE); mutex_unlock(&sdev->state_mutex); scsi_eh_finish_cmd(scmd, done_q); } return; } /** * scsi_noretry_cmd - determine if command should be failed fast * @scmd: SCSI cmd to examine. */ bool scsi_noretry_cmd(struct scsi_cmnd *scmd) { struct request *req = scsi_cmd_to_rq(scmd); switch (host_byte(scmd->result)) { case DID_OK: break; case DID_TIME_OUT: goto check_type; case DID_BUS_BUSY: return !!(req->cmd_flags & REQ_FAILFAST_TRANSPORT); case DID_PARITY: return !!(req->cmd_flags & REQ_FAILFAST_DEV); case DID_ERROR: if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT) return false; fallthrough; case DID_SOFT_ERROR: return !!(req->cmd_flags & REQ_FAILFAST_DRIVER); } /* Never retry commands aborted due to a duration limit timeout */ if (scsi_ml_byte(scmd->result) == SCSIML_STAT_DL_TIMEOUT) return true; if (!scsi_status_is_check_condition(scmd->result)) return false; check_type: /* * assume caller has checked sense and determined * the check condition was retryable. */ if (req->cmd_flags & REQ_FAILFAST_DEV || blk_rq_is_passthrough(req)) return true; return false; } /** * scsi_decide_disposition - Disposition a cmd on return from LLD. * @scmd: SCSI cmd to examine. * * Notes: * This is *only* called when we are examining the status after sending * out the actual data command. any commands that are queued for error * recovery (e.g. test_unit_ready) do *not* come through here. * * When this routine returns failed, it means the error handler thread * is woken. In cases where the error code indicates an error that * doesn't require the error handler read (i.e. we don't need to * abort/reset), this function should return SUCCESS. */ enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *scmd) { enum scsi_disposition rtn; /* * if the device is offline, then we clearly just pass the result back * up to the top level. */ if (!scsi_device_online(scmd->device)) { SCSI_LOG_ERROR_RECOVERY(5, scmd_printk(KERN_INFO, scmd, "%s: device offline - report as SUCCESS\n", __func__)); return SUCCESS; } /* * first check the host byte, to see if there is anything in there * that would indicate what we need to do. */ switch (host_byte(scmd->result)) { case DID_PASSTHROUGH: /* * no matter what, pass this through to the upper layer. * nuke this special code so that it looks like we are saying * did_ok. */ scmd->result &= 0xff00ffff; return SUCCESS; case DID_OK: /* * looks good. drop through, and check the next byte. */ break; case DID_ABORT: if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { set_host_byte(scmd, DID_TIME_OUT); return SUCCESS; } fallthrough; case DID_NO_CONNECT: case DID_BAD_TARGET: /* * note - this means that we just report the status back * to the top level driver, not that we actually think * that it indicates SUCCESS. */ return SUCCESS; case DID_SOFT_ERROR: /* * when the low level driver returns did_soft_error, * it is responsible for keeping an internal retry counter * in order to avoid endless loops (db) */ goto maybe_retry; case DID_IMM_RETRY: return NEEDS_RETRY; case DID_REQUEUE: return ADD_TO_MLQUEUE; case DID_TRANSPORT_DISRUPTED: /* * LLD/transport was disrupted during processing of the IO. * The transport class is now blocked/blocking, * and the transport will decide what to do with the IO * based on its timers and recovery capablilities if * there are enough retries. */ goto maybe_retry; case DID_TRANSPORT_FAILFAST: /* * The transport decided to failfast the IO (most likely * the fast io fail tmo fired), so send IO directly upwards. */ return SUCCESS; case DID_TRANSPORT_MARGINAL: /* * caller has decided not to do retries on * abort success, so send IO directly upwards */ return SUCCESS; case DID_ERROR: if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT) /* * execute reservation conflict processing code * lower down */ break; fallthrough; case DID_BUS_BUSY: case DID_PARITY: goto maybe_retry; case DID_TIME_OUT: /* * when we scan the bus, we get timeout messages for * these commands if there is no device available. * other hosts report did_no_connect for the same thing. */ if ((scmd->cmnd[0] == TEST_UNIT_READY || scmd->cmnd[0] == INQUIRY)) { return SUCCESS; } else { return FAILED; } case DID_RESET: return SUCCESS; default: return FAILED; } /* * check the status byte to see if this indicates anything special. */ switch (get_status_byte(scmd)) { case SAM_STAT_TASK_SET_FULL: scsi_handle_queue_full(scmd->device); /* * the case of trying to send too many commands to a * tagged queueing device. */ fallthrough; case SAM_STAT_BUSY: /* * device can't talk to us at the moment. Should only * occur (SAM-3) when the task queue is empty, so will cause * the empty queue handling to trigger a stall in the * device. */ return ADD_TO_MLQUEUE; case SAM_STAT_GOOD: if (scmd->cmnd[0] == REPORT_LUNS) scmd->device->sdev_target->expecting_lun_change = 0; scsi_handle_queue_ramp_up(scmd->device); if (scmd->sense_buffer && SCSI_SENSE_VALID(scmd)) /* * If we have sense data, call scsi_check_sense() in * order to set the correct SCSI ML byte (if any). * No point in checking the return value, since the * command has already completed successfully. */ scsi_check_sense(scmd); fallthrough; case SAM_STAT_COMMAND_TERMINATED: return SUCCESS; case SAM_STAT_TASK_ABORTED: goto maybe_retry; case SAM_STAT_CHECK_CONDITION: rtn = scsi_check_sense(scmd); if (rtn == NEEDS_RETRY) goto maybe_retry; /* if rtn == FAILED, we have no sense information; * returning FAILED will wake the error handler thread * to collect the sense and redo the decide * disposition */ return rtn; case SAM_STAT_CONDITION_MET: case SAM_STAT_INTERMEDIATE: case SAM_STAT_INTERMEDIATE_CONDITION_MET: case SAM_STAT_ACA_ACTIVE: /* * who knows? FIXME(eric) */ return SUCCESS; case SAM_STAT_RESERVATION_CONFLICT: sdev_printk(KERN_INFO, scmd->device, "reservation conflict\n"); set_scsi_ml_byte(scmd, SCSIML_STAT_RESV_CONFLICT); return SUCCESS; /* causes immediate i/o error */ } return FAILED; maybe_retry: /* we requeue for retry because the error was retryable, and * the request was not marked fast fail. Note that above, * even if the request is marked fast fail, we still requeue * for queue congestion conditions (QUEUE_FULL or BUSY) */ if (scsi_cmd_retry_allowed(scmd) && !scsi_noretry_cmd(scmd)) { return NEEDS_RETRY; } else { /* * no more retries - report this one back to upper level. */ return SUCCESS; } } static enum rq_end_io_ret eh_lock_door_done(struct request *req, blk_status_t status) { blk_mq_free_request(req); return RQ_END_IO_NONE; } /** * scsi_eh_lock_door - Prevent medium removal for the specified device * @sdev: SCSI device to prevent medium removal * * Locking: * We must be called from process context. * * Notes: * We queue up an asynchronous "ALLOW MEDIUM REMOVAL" request on the * head of the devices request queue, and continue. */ static void scsi_eh_lock_door(struct scsi_device *sdev) { struct scsi_cmnd *scmd; struct request *req; req = scsi_alloc_request(sdev->request_queue, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) return; scmd = blk_mq_rq_to_pdu(req); scmd->cmnd[0] = ALLOW_MEDIUM_REMOVAL; scmd->cmnd[1] = 0; scmd->cmnd[2] = 0; scmd->cmnd[3] = 0; scmd->cmnd[4] = SCSI_REMOVAL_PREVENT; scmd->cmnd[5] = 0; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); scmd->allowed = 5; req->rq_flags |= RQF_QUIET; req->timeout = 10 * HZ; req->end_io = eh_lock_door_done; blk_execute_rq_nowait(req, true); } /** * scsi_restart_operations - restart io operations to the specified host. * @shost: Host we are restarting. * * Notes: * When we entered the error handler, we blocked all further i/o to * this device. we need to 'reverse' this process. */ static void scsi_restart_operations(struct Scsi_Host *shost) { struct scsi_device *sdev; unsigned long flags; /* * If the door was locked, we need to insert a door lock request * onto the head of the SCSI request queue for the device. There * is no point trying to lock the door of an off-line device. */ shost_for_each_device(sdev, shost) { if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) { scsi_eh_lock_door(sdev); sdev->was_reset = 0; } } /* * next free up anything directly waiting upon the host. this * will be requests for character device operations, and also for * ioctls to queued block devices. */ SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "waking up host to restart\n")); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_RUNNING)) if (scsi_host_set_state(shost, SHOST_CANCEL)) BUG_ON(scsi_host_set_state(shost, SHOST_DEL)); spin_unlock_irqrestore(shost->host_lock, flags); wake_up(&shost->host_wait); /* * finally we need to re-initiate requests that may be pending. we will * have had everything blocked while error handling is taking place, and * now that error recovery is done, we will need to ensure that these * requests are started. */ scsi_run_host_queues(shost); /* * if eh is active and host_eh_scheduled is pending we need to re-run * recovery. we do this check after scsi_run_host_queues() to allow * everything pent up since the last eh run a chance to make forward * progress before we sync again. Either we'll immediately re-run * recovery or scsi_device_unbusy() will wake us again when these * pending commands complete. */ spin_lock_irqsave(shost->host_lock, flags); if (shost->host_eh_scheduled) if (scsi_host_set_state(shost, SHOST_RECOVERY)) WARN_ON(scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)); spin_unlock_irqrestore(shost->host_lock, flags); } /** * scsi_eh_ready_devs - check device ready state and recover if not. * @shost: host to be recovered. * @work_q: &list_head for pending commands. * @done_q: &list_head for processed commands. */ void scsi_eh_ready_devs(struct Scsi_Host *shost, struct list_head *work_q, struct list_head *done_q) { if (!scsi_eh_stu(shost, work_q, done_q)) if (!scsi_eh_bus_device_reset(shost, work_q, done_q)) if (!scsi_eh_target_reset(shost, work_q, done_q)) if (!scsi_eh_bus_reset(shost, work_q, done_q)) if (!scsi_eh_host_reset(shost, work_q, done_q)) scsi_eh_offline_sdevs(work_q, done_q); } EXPORT_SYMBOL_GPL(scsi_eh_ready_devs); /** * scsi_eh_flush_done_q - finish processed commands or retry them. * @done_q: list_head of processed commands. */ void scsi_eh_flush_done_q(struct list_head *done_q) { struct scsi_cmnd *scmd, *next; list_for_each_entry_safe(scmd, next, done_q, eh_entry) { struct scsi_device *sdev = scmd->device; list_del_init(&scmd->eh_entry); if (scsi_device_online(sdev) && !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd) && scsi_eh_should_retry_cmd(scmd)) { SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: flush retry cmd\n", current->comm)); scsi_queue_insert(scmd, SCSI_MLQUEUE_EH_RETRY); blk_mq_kick_requeue_list(sdev->request_queue); } else { /* * If just we got sense for the device (called * scsi_eh_get_sense), scmd->result is already * set, do not set DID_TIME_OUT. */ if (!scmd->result && !(scmd->flags & SCMD_FORCE_EH_SUCCESS)) scmd->result |= (DID_TIME_OUT << 16); SCSI_LOG_ERROR_RECOVERY(3, scmd_printk(KERN_INFO, scmd, "%s: flush finish cmd\n", current->comm)); scsi_finish_command(scmd); } } } EXPORT_SYMBOL(scsi_eh_flush_done_q); /** * scsi_unjam_host - Attempt to fix a host which has a cmd that failed. * @shost: Host to unjam. * * Notes: * When we come in here, we *know* that all commands on the bus have * either completed, failed or timed out. we also know that no further * commands are being sent to the host, so things are relatively quiet * and we have freedom to fiddle with things as we wish. * * This is only the *default* implementation. it is possible for * individual drivers to supply their own version of this function, and * if the maintainer wishes to do this, it is strongly suggested that * this function be taken as a template and modified. this function * was designed to correctly handle problems for about 95% of the * different cases out there, and it should always provide at least a * reasonable amount of error recovery. * * Any command marked 'failed' or 'timeout' must eventually have * scsi_finish_cmd() called for it. we do all of the retry stuff * here, so when we restart the host after we return it should have an * empty queue. */ static void scsi_unjam_host(struct Scsi_Host *shost) { unsigned long flags; LIST_HEAD(eh_work_q); LIST_HEAD(eh_done_q); spin_lock_irqsave(shost->host_lock, flags); list_splice_init(&shost->eh_cmd_q, &eh_work_q); spin_unlock_irqrestore(shost->host_lock, flags); SCSI_LOG_ERROR_RECOVERY(1, scsi_eh_prt_fail_stats(shost, &eh_work_q)); if (!scsi_eh_get_sense(&eh_work_q, &eh_done_q)) scsi_eh_ready_devs(shost, &eh_work_q, &eh_done_q); spin_lock_irqsave(shost->host_lock, flags); if (shost->eh_deadline != -1) shost->last_reset = 0; spin_unlock_irqrestore(shost->host_lock, flags); scsi_eh_flush_done_q(&eh_done_q); } /** * scsi_error_handler - SCSI error handler thread * @data: Host for which we are running. * * Notes: * This is the main error handling loop. This is run as a kernel thread * for every SCSI host and handles all error handling activity. */ int scsi_error_handler(void *data) { struct Scsi_Host *shost = data; /* * We use TASK_INTERRUPTIBLE so that the thread is not * counted against the load average as a running process. * We never actually get interrupted because kthread_run * disables signal delivery for the created thread. */ while (true) { /* * The sequence in kthread_stop() sets the stop flag first * then wakes the process. To avoid missed wakeups, the task * should always be in a non running state before the stop * flag is checked */ set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) break; if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) || shost->host_failed != scsi_host_busy(shost)) { SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "scsi_eh_%d: sleeping\n", shost->host_no)); schedule(); continue; } __set_current_state(TASK_RUNNING); SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "scsi_eh_%d: waking up %d/%d/%d\n", shost->host_no, shost->host_eh_scheduled, shost->host_failed, scsi_host_busy(shost))); /* * We have a host that is failing for some reason. Figure out * what we need to do to get it up and online again (if we can). * If we fail, we end up taking the thing offline. */ if (!shost->eh_noresume && scsi_autopm_get_host(shost) != 0) { SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_ERR, shost, "scsi_eh_%d: unable to autoresume\n", shost->host_no)); continue; } if (shost->transportt->eh_strategy_handler) shost->transportt->eh_strategy_handler(shost); else scsi_unjam_host(shost); /* All scmds have been handled */ shost->host_failed = 0; /* * Note - if the above fails completely, the action is to take * individual devices offline and flush the queue of any * outstanding requests that may have been pending. When we * restart, we restart any I/O to any other devices on the bus * which are still online. */ scsi_restart_operations(shost); if (!shost->eh_noresume) scsi_autopm_put_host(shost); } __set_current_state(TASK_RUNNING); SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_INFO, shost, "Error handler scsi_eh_%d exiting\n", shost->host_no)); shost->ehandler = NULL; return 0; } /** * scsi_report_bus_reset() - report bus reset observed * * Utility function used by low-level drivers to report that * they have observed a bus reset on the bus being handled. * * @shost: Host in question * @channel: channel on which reset was observed. * * Returns: Nothing * * Lock status: Host lock must be held. * * Notes: This only needs to be called if the reset is one which * originates from an unknown location. Resets originated * by the mid-level itself don't need to call this, but there * should be no harm. * * The main purpose of this is to make sure that a CHECK_CONDITION * is properly treated. */ void scsi_report_bus_reset(struct Scsi_Host *shost, int channel) { struct scsi_device *sdev; __shost_for_each_device(sdev, shost) { if (channel == sdev_channel(sdev)) __scsi_report_device_reset(sdev, NULL); } } EXPORT_SYMBOL(scsi_report_bus_reset); /** * scsi_report_device_reset() - report device reset observed * * Utility function used by low-level drivers to report that * they have observed a device reset on the device being handled. * * @shost: Host in question * @channel: channel on which reset was observed * @target: target on which reset was observed * * Returns: Nothing * * Lock status: Host lock must be held * * Notes: This only needs to be called if the reset is one which * originates from an unknown location. Resets originated * by the mid-level itself don't need to call this, but there * should be no harm. * * The main purpose of this is to make sure that a CHECK_CONDITION * is properly treated. */ void scsi_report_device_reset(struct Scsi_Host *shost, int channel, int target) { struct scsi_device *sdev; __shost_for_each_device(sdev, shost) { if (channel == sdev_channel(sdev) && target == sdev_id(sdev)) __scsi_report_device_reset(sdev, NULL); } } EXPORT_SYMBOL(scsi_report_device_reset); /** * scsi_ioctl_reset: explicitly reset a host/bus/target/device * @dev: scsi_device to operate on * @arg: reset type (see sg.h) */ int scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) { struct scsi_cmnd *scmd; struct Scsi_Host *shost = dev->host; struct request *rq; unsigned long flags; int error = 0, val; enum scsi_disposition rtn; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; error = get_user(val, arg); if (error) return error; if (scsi_autopm_get_host(shost) < 0) return -EIO; error = -EIO; rq = kzalloc(sizeof(struct request) + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size, GFP_KERNEL); if (!rq) goto out_put_autopm_host; blk_rq_init(NULL, rq); scmd = (struct scsi_cmnd *)(rq + 1); scsi_init_command(dev, scmd); scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL; scmd->flags |= SCMD_LAST; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->cmd_len = 0; scmd->sc_data_direction = DMA_BIDIRECTIONAL; spin_lock_irqsave(shost->host_lock, flags); shost->tmf_in_progress = 1; spin_unlock_irqrestore(shost->host_lock, flags); switch (val & ~SG_SCSI_RESET_NO_ESCALATE) { case SG_SCSI_RESET_NOTHING: rtn = SUCCESS; break; case SG_SCSI_RESET_DEVICE: rtn = scsi_try_bus_device_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; fallthrough; case SG_SCSI_RESET_TARGET: rtn = scsi_try_target_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; fallthrough; case SG_SCSI_RESET_BUS: rtn = scsi_try_bus_reset(scmd); if (rtn == SUCCESS || (val & SG_SCSI_RESET_NO_ESCALATE)) break; fallthrough; case SG_SCSI_RESET_HOST: rtn = scsi_try_host_reset(scmd); if (rtn == SUCCESS) break; fallthrough; default: rtn = FAILED; break; } error = (rtn == SUCCESS) ? 0 : -EIO; spin_lock_irqsave(shost->host_lock, flags); shost->tmf_in_progress = 0; spin_unlock_irqrestore(shost->host_lock, flags); /* * be sure to wake up anyone who was sleeping or had their queue * suspended while we performed the TMF. */ SCSI_LOG_ERROR_RECOVERY(3, shost_printk(KERN_INFO, shost, "waking up host to restart after TMF\n")); wake_up(&shost->host_wait); scsi_run_host_queues(shost); kfree(rq); out_put_autopm_host: scsi_autopm_put_host(shost); return error; } bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd, struct scsi_sense_hdr *sshdr) { return scsi_normalize_sense(cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE, sshdr); } EXPORT_SYMBOL(scsi_command_normalize_sense); /** * scsi_get_sense_info_fld - get information field from sense data (either fixed or descriptor format) * @sense_buffer: byte array of sense data * @sb_len: number of valid bytes in sense_buffer * @info_out: pointer to 64 integer where 8 or 4 byte information * field will be placed if found. * * Return value: * true if information field found, false if not found. */ bool scsi_get_sense_info_fld(const u8 *sense_buffer, int sb_len, u64 *info_out) { const u8 * ucp; if (sb_len < 7) return false; switch (sense_buffer[0] & 0x7f) { case 0x70: case 0x71: if (sense_buffer[0] & 0x80) { *info_out = get_unaligned_be32(&sense_buffer[3]); return true; } return false; case 0x72: case 0x73: ucp = scsi_sense_desc_find(sense_buffer, sb_len, 0 /* info desc */); if (ucp && (0xa == ucp[1])) { *info_out = get_unaligned_be64(&ucp[4]); return true; } return false; default: return false; } } EXPORT_SYMBOL(scsi_get_sense_info_fld); |
| 23 5 12 26 18 26 26 7 7 7 7 2 2 12 12 5 2 5 12 11 11 9 8 8 4 4 2 394 392 394 2 2 2 2 2 2 2 2 2 2 2 2 392 1310 394 1311 9 5 4 9 13 11 11 11 11 9 4 4 4 13 12 5 5 5 3 2 1 1 5 5 6 6 6 7 7 6 6 4 4 6 6 20 18 17 5 17 2 17 6 3 3 6 17 14 13 12 12 1 12 15 20 5 4 4 3 15 3 1 2 1 1 2 6 6 5 4 4 3 3 3 1 2 1 14 23 23 22 22 22 22 22 22 21 19 21 23 2 2 2 2 2 2 2 2 2 2 2 5 4 1 3 3 1 5 23 23 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /** -*- linux-c -*- *********************************************************** * Linux PPP over Ethernet (PPPoX/PPPoE) Sockets * * PPPoX --- Generic PPP encapsulation socket family * PPPoE --- PPP over Ethernet (RFC 2516) * * Version: 0.7.0 * * 070228 : Fix to allow multiple sessions with same remote MAC and same * session id by including the local device ifindex in the * tuple identifying a session. This also ensures packets can't * be injected into a session from interfaces other than the one * specified by userspace. Florian Zumbiehl <florz@florz.de> * (Oh, BTW, this one is YYMMDD, in case you were wondering ...) * 220102 : Fix module use count on failure in pppoe_create, pppox_sk -acme * 030700 : Fixed connect logic to allow for disconnect. * 270700 : Fixed potential SMP problems; we must protect against * simultaneous invocation of ppp_input * and ppp_unregister_channel. * 040800 : Respect reference count mechanisms on net-devices. * 200800 : fix kfree(skb) in pppoe_rcv (acme) * Module reference count is decremented in the right spot now, * guards against sock_put not actually freeing the sk * in pppoe_release. * 051000 : Initialization cleanup. * 111100 : Fix recvmsg. * 050101 : Fix PADT processing. * 140501 : Use pppoe_rcv_core to handle all backlog. (Alexey) * 170701 : Do not lock_sock with rwlock held. (DaveM) * Ignore discovery frames if user has socket * locked. (DaveM) * Ignore return value of dev_queue_xmit in __pppoe_xmit * or else we may kfree an SKB twice. (DaveM) * 190701 : When doing copies of skb's in __pppoe_xmit, always delete * the original skb that was passed in on success, never on * failure. Delete the copy of the skb on failure to avoid * a memory leak. * 081001 : Misc. cleanup (licence string, non-blocking, prevent * reference of device on close). * 121301 : New ppp channels interface; cannot unregister a channel * from interrupts. Thus, we mark the socket as a ZOMBIE * and do the unregistration later. * 081002 : seq_file support for proc stuff -acme * 111602 : Merge all 2.4 fixes into 2.5/2.6 tree. Label 2.5/2.6 * as version 0.7. Spacing cleanup. * Author: Michal Ostrowski <mostrows@speakeasy.net> * Contributors: * Arnaldo Carvalho de Melo <acme@conectiva.com.br> * David S. Miller (davem@redhat.com) * * License: */ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/if_ether.h> #include <linux/if_pppox.h> #include <linux/ppp_channel.h> #include <linux/ppp_defs.h> #include <linux/ppp-ioctl.h> #include <linux/notifier.h> #include <linux/file.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <linux/uaccess.h> #define PPPOE_HASH_BITS CONFIG_PPPOE_HASH_BITS #define PPPOE_HASH_SIZE (1 << PPPOE_HASH_BITS) #define PPPOE_HASH_MASK (PPPOE_HASH_SIZE - 1) static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb); static const struct proto_ops pppoe_ops; static const struct ppp_channel_ops pppoe_chan_ops; /* per-net private data for this module */ static unsigned int pppoe_net_id __read_mostly; struct pppoe_net { /* * we could use _single_ hash table for all * nets by injecting net id into the hash but * it would increase hash chains and add * a few additional math comparisons messy * as well, moreover in case of SMP less locking * controversy here */ struct pppox_sock __rcu *hash_table[PPPOE_HASH_SIZE]; spinlock_t hash_lock; }; /* * PPPoE could be in the following stages: * 1) Discovery stage (to obtain remote MAC and Session ID) * 2) Session stage (MAC and SID are known) * * Ethernet frames have a special tag for this but * we use simpler approach based on session id */ static inline bool stage_session(__be16 sid) { return sid != 0; } static inline struct pppoe_net *pppoe_pernet(struct net *net) { return net_generic(net, pppoe_net_id); } static inline int cmp_2_addr(struct pppoe_addr *a, struct pppoe_addr *b) { return a->sid == b->sid && ether_addr_equal(a->remote, b->remote); } static inline int cmp_addr(struct pppoe_addr *a, __be16 sid, char *addr) { return a->sid == sid && ether_addr_equal(a->remote, addr); } #if 8 % PPPOE_HASH_BITS #error 8 must be a multiple of PPPOE_HASH_BITS #endif static int hash_item(__be16 sid, unsigned char *addr) { unsigned char hash = 0; unsigned int i; for (i = 0; i < ETH_ALEN; i++) hash ^= addr[i]; for (i = 0; i < sizeof(sid_t) * 8; i += 8) hash ^= (__force __u32)sid >> i; for (i = 8; (i >>= 1) >= PPPOE_HASH_BITS;) hash ^= hash >> i; return hash & PPPOE_HASH_MASK; } /********************************************************************** * * Set/get/delete/rehash items (internal versions) * **********************************************************************/ static struct pppox_sock *__get_item(struct pppoe_net *pn, __be16 sid, unsigned char *addr, int ifindex) { int hash = hash_item(sid, addr); struct pppox_sock *ret; ret = rcu_dereference(pn->hash_table[hash]); while (ret) { if (cmp_addr(&ret->pppoe_pa, sid, addr) && ret->pppoe_ifindex == ifindex) return ret; ret = rcu_dereference(ret->next); } return NULL; } static int __set_item(struct pppoe_net *pn, struct pppox_sock *po) { int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote); struct pppox_sock *ret, *first; first = rcu_dereference_protected(pn->hash_table[hash], lockdep_is_held(&pn->hash_lock)); ret = first; while (ret) { if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa) && ret->pppoe_ifindex == po->pppoe_ifindex) return -EALREADY; ret = rcu_dereference_protected(ret->next, lockdep_is_held(&pn->hash_lock)); } RCU_INIT_POINTER(po->next, first); rcu_assign_pointer(pn->hash_table[hash], po); return 0; } static void __delete_item(struct pppoe_net *pn, __be16 sid, char *addr, int ifindex) { int hash = hash_item(sid, addr); struct pppox_sock *ret, __rcu **src; ret = rcu_dereference_protected(pn->hash_table[hash], lockdep_is_held(&pn->hash_lock)); src = &pn->hash_table[hash]; while (ret) { if (cmp_addr(&ret->pppoe_pa, sid, addr) && ret->pppoe_ifindex == ifindex) { struct pppox_sock *next; next = rcu_dereference_protected(ret->next, lockdep_is_held(&pn->hash_lock)); rcu_assign_pointer(*src, next); break; } src = &ret->next; ret = rcu_dereference_protected(ret->next, lockdep_is_held(&pn->hash_lock)); } } /********************************************************************** * * Set/get/delete/rehash items * **********************************************************************/ static inline struct pppox_sock *get_item(struct pppoe_net *pn, __be16 sid, unsigned char *addr, int ifindex) { struct pppox_sock *po; po = __get_item(pn, sid, addr, ifindex); if (po && !refcount_inc_not_zero(&sk_pppox(po)->sk_refcnt)) po = NULL; return po; } static inline struct pppox_sock *__get_item_by_addr(struct net *net, struct sockaddr_pppox *sp) { struct net_device *dev; struct pppoe_net *pn; struct pppox_sock *pppox_sock = NULL; int ifindex; dev = dev_get_by_name_rcu(net, sp->sa_addr.pppoe.dev); if (dev) { ifindex = dev->ifindex; pn = pppoe_pernet(net); pppox_sock = __get_item(pn, sp->sa_addr.pppoe.sid, sp->sa_addr.pppoe.remote, ifindex); } return pppox_sock; } static inline void delete_item(struct pppoe_net *pn, __be16 sid, char *addr, int ifindex) { spin_lock(&pn->hash_lock); __delete_item(pn, sid, addr, ifindex); spin_unlock(&pn->hash_lock); } /*************************************************************************** * * Handler for device events. * Certain device events require that sockets be unconnected. * **************************************************************************/ static void pppoe_flush_dev(struct net_device *dev) { struct pppoe_net *pn; int i; pn = pppoe_pernet(dev_net(dev)); spin_lock(&pn->hash_lock); for (i = 0; i < PPPOE_HASH_SIZE; i++) { struct pppox_sock *po = rcu_dereference_protected(pn->hash_table[i], lockdep_is_held(&pn->hash_lock)); struct sock *sk; while (po) { while (po && po->pppoe_dev != dev) { po = rcu_dereference_protected(po->next, lockdep_is_held(&pn->hash_lock)); } if (!po) break; sk = sk_pppox(po); /* We always grab the socket lock, followed by the * hash_lock, in that order. Since we should hold the * sock lock while doing any unbinding, we need to * release the lock we're holding. Hold a reference to * the sock so it doesn't disappear as we're jumping * between locks. */ sock_hold(sk); spin_unlock(&pn->hash_lock); lock_sock(sk); if (po->pppoe_dev == dev && sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { pppox_unbind_sock(sk); sk->sk_state_change(sk); po->pppoe_dev = NULL; dev_put(dev); } release_sock(sk); sock_put(sk); /* Restart the process from the start of the current * hash chain. We dropped locks so the world may have * change from underneath us. */ BUG_ON(pppoe_pernet(dev_net(dev)) == NULL); spin_lock(&pn->hash_lock); po = rcu_dereference_protected(pn->hash_table[i], lockdep_is_held(&pn->hash_lock)); } } spin_unlock(&pn->hash_lock); } static int pppoe_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Only look at sockets that are using this specific device. */ switch (event) { case NETDEV_CHANGEADDR: case NETDEV_CHANGEMTU: /* A change in mtu or address is a bad thing, requiring * LCP re-negotiation. */ case NETDEV_GOING_DOWN: case NETDEV_DOWN: /* Find every socket on this device and kill it. */ pppoe_flush_dev(dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block pppoe_notifier = { .notifier_call = pppoe_device_event, }; /************************************************************************ * * Do the real work of receiving a PPPoE Session frame. * ***********************************************************************/ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb) { struct pppox_sock *po = pppox_sk(sk); struct pppox_sock *relay_po; /* Backlog receive. Semantics of backlog rcv preclude any code from * executing in lock_sock()/release_sock() bounds; meaning sk->sk_state * can't change. */ if (sk->sk_state & PPPOX_BOUND) { ppp_input(&po->chan, skb); } else if (sk->sk_state & PPPOX_RELAY) { relay_po = __get_item_by_addr(sock_net(sk), &po->pppoe_relay); if (relay_po == NULL) goto abort_kfree; if ((sk_pppox(relay_po)->sk_state & PPPOX_CONNECTED) == 0) goto abort_kfree; if (!__pppoe_xmit(sk_pppox(relay_po), skb)) goto abort_kfree; } else { if (sock_queue_rcv_skb(sk, skb)) goto abort_kfree; } return NET_RX_SUCCESS; abort_kfree: kfree_skb(skb); return NET_RX_DROP; } /************************************************************************ * * Receive wrapper called in BH context. * ***********************************************************************/ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct pppoe_hdr *ph; struct pppox_sock *po; struct pppoe_net *pn; int len; if (skb->pkt_type == PACKET_OTHERHOST) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto out; if (skb_mac_header_len(skb) < ETH_HLEN) goto drop; if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto drop; ph = pppoe_hdr(skb); len = ntohs(ph->length); skb_pull_rcsum(skb, sizeof(*ph)); if (skb->len < len) goto drop; if (pskb_trim_rcsum(skb, len)) goto drop; ph = pppoe_hdr(skb); pn = pppoe_pernet(dev_net(dev)); po = __get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex); if (!po) goto drop; return __sk_receive_skb(sk_pppox(po), skb, 0, 1, false); drop: kfree_skb(skb); out: return NET_RX_DROP; } static void pppoe_unbind_sock_work(struct work_struct *work) { struct pppox_sock *po = container_of(work, struct pppox_sock, proto.pppoe.padt_work); struct sock *sk = sk_pppox(po); lock_sock(sk); if (po->pppoe_dev) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } pppox_unbind_sock(sk); release_sock(sk); sock_put(sk); } /************************************************************************ * * Receive a PPPoE Discovery frame. * This is solely for detection of PADT frames * ***********************************************************************/ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct pppoe_hdr *ph; struct pppox_sock *po; struct pppoe_net *pn; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto out; if (skb->pkt_type != PACKET_HOST) goto abort; if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto abort; ph = pppoe_hdr(skb); if (ph->code != PADT_CODE) goto abort; pn = pppoe_pernet(dev_net(dev)); po = get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex); if (po) if (!schedule_work(&po->proto.pppoe.padt_work)) sock_put(sk_pppox(po)); abort: kfree_skb(skb); out: return NET_RX_SUCCESS; /* Lies... :-) */ } static struct packet_type pppoes_ptype __read_mostly = { .type = cpu_to_be16(ETH_P_PPP_SES), .func = pppoe_rcv, }; static struct packet_type pppoed_ptype __read_mostly = { .type = cpu_to_be16(ETH_P_PPP_DISC), .func = pppoe_disc_rcv, }; static struct proto pppoe_sk_proto __read_mostly = { .name = "PPPOE", .owner = THIS_MODULE, .obj_size = sizeof(struct pppox_sock), }; static void pppoe_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); } /*********************************************************************** * * Initialize a new struct sock. * **********************************************************************/ static int pppoe_create(struct net *net, struct socket *sock, int kern) { struct sock *sk; sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); sock_set_flag(sk, SOCK_RCU_FREE); sock->state = SS_UNCONNECTED; sock->ops = &pppoe_ops; sk->sk_backlog_rcv = pppoe_rcv_core; sk->sk_destruct = pppoe_destruct; sk->sk_state = PPPOX_NONE; sk->sk_type = SOCK_STREAM; sk->sk_family = PF_PPPOX; sk->sk_protocol = PX_PROTO_OE; INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work, pppoe_unbind_sock_work); return 0; } static int pppoe_release(struct socket *sock) { struct sock *sk = sock->sk; struct pppox_sock *po; struct pppoe_net *pn; struct net *net = NULL; if (!sk) return 0; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD)) { release_sock(sk); return -EBADF; } po = pppox_sk(sk); if (po->pppoe_dev) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } pppox_unbind_sock(sk); /* Signal the death of the socket. */ sk->sk_state = PPPOX_DEAD; net = sock_net(sk); pn = pppoe_pernet(net); /* * protect "po" from concurrent updates * on pppoe_flush_dev */ delete_item(pn, po->pppoe_pa.sid, po->pppoe_pa.remote, po->pppoe_ifindex); sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr; struct pppox_sock *po = pppox_sk(sk); struct net_device *dev = NULL; struct pppoe_net *pn; struct net *net = NULL; int error; lock_sock(sk); error = -EINVAL; if (sockaddr_len != sizeof(struct sockaddr_pppox)) goto end; if (sp->sa_protocol != PX_PROTO_OE) goto end; /* Check for already bound sockets */ error = -EBUSY; if ((sk->sk_state & PPPOX_CONNECTED) && stage_session(sp->sa_addr.pppoe.sid)) goto end; /* Check for already disconnected sockets, on attempts to disconnect */ error = -EALREADY; if ((sk->sk_state & PPPOX_DEAD) && !stage_session(sp->sa_addr.pppoe.sid)) goto end; error = 0; /* Delete the old binding */ if (stage_session(po->pppoe_pa.sid)) { pppox_unbind_sock(sk); pn = pppoe_pernet(sock_net(sk)); delete_item(pn, po->pppoe_pa.sid, po->pppoe_pa.remote, po->pppoe_ifindex); if (po->pppoe_dev) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } po->pppoe_ifindex = 0; memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa)); memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay)); memset(&po->chan, 0, sizeof(po->chan)); po->next = NULL; po->num = 0; sk->sk_state = PPPOX_NONE; } /* Re-bind in session stage only */ if (stage_session(sp->sa_addr.pppoe.sid)) { error = -ENODEV; net = sock_net(sk); dev = dev_get_by_name(net, sp->sa_addr.pppoe.dev); if (!dev) goto err_put; po->pppoe_dev = dev; po->pppoe_ifindex = dev->ifindex; pn = pppoe_pernet(net); if (!(dev->flags & IFF_UP)) { goto err_put; } memcpy(&po->pppoe_pa, &sp->sa_addr.pppoe, sizeof(struct pppoe_addr)); spin_lock(&pn->hash_lock); error = __set_item(pn, po); spin_unlock(&pn->hash_lock); if (error < 0) goto err_put; po->chan.hdrlen = (sizeof(struct pppoe_hdr) + dev->hard_header_len); po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2; po->chan.private = sk; po->chan.ops = &pppoe_chan_ops; po->chan.direct_xmit = true; error = ppp_register_net_channel(dev_net(dev), &po->chan); if (error) { delete_item(pn, po->pppoe_pa.sid, po->pppoe_pa.remote, po->pppoe_ifindex); goto err_put; } sk->sk_state = PPPOX_CONNECTED; } po->num = sp->sa_addr.pppoe.sid; end: release_sock(sk); return error; err_put: if (po->pppoe_dev) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } goto end; } static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; sp.sa_family = AF_PPPOX; sp.sa_protocol = PX_PROTO_OE; memcpy(&sp.sa_addr.pppoe, &pppox_sk(sock->sk)->pppoe_pa, sizeof(struct pppoe_addr)); memcpy(uaddr, &sp, len); return len; } static int pppoe_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; struct pppox_sock *po = pppox_sk(sk); int val; int err; switch (cmd) { case PPPIOCGMRU: err = -ENXIO; if (!(sk->sk_state & PPPOX_CONNECTED)) break; err = -EFAULT; if (put_user(po->pppoe_dev->mtu - sizeof(struct pppoe_hdr) - PPP_HDRLEN, (int __user *)arg)) break; err = 0; break; case PPPIOCSMRU: err = -ENXIO; if (!(sk->sk_state & PPPOX_CONNECTED)) break; err = -EFAULT; if (get_user(val, (int __user *)arg)) break; if (val < (po->pppoe_dev->mtu - sizeof(struct pppoe_hdr) - PPP_HDRLEN)) err = 0; else err = -EINVAL; break; case PPPIOCSFLAGS: err = -EFAULT; if (get_user(val, (int __user *)arg)) break; err = 0; break; case PPPOEIOCSFWD: { struct pppox_sock *relay_po; err = -EBUSY; if (sk->sk_state & (PPPOX_BOUND | PPPOX_DEAD)) break; err = -ENOTCONN; if (!(sk->sk_state & PPPOX_CONNECTED)) break; /* PPPoE address from the user specifies an outbound PPPoE address which frames are forwarded to */ err = -EFAULT; if (copy_from_user(&po->pppoe_relay, (void __user *)arg, sizeof(struct sockaddr_pppox))) break; err = -EINVAL; if (po->pppoe_relay.sa_family != AF_PPPOX || po->pppoe_relay.sa_protocol != PX_PROTO_OE) break; /* Check that the socket referenced by the address actually exists. */ rcu_read_lock(); relay_po = __get_item_by_addr(sock_net(sk), &po->pppoe_relay); rcu_read_unlock(); if (!relay_po) break; sk->sk_state |= PPPOX_RELAY; err = 0; break; } case PPPOEIOCDFWD: err = -EALREADY; if (!(sk->sk_state & PPPOX_RELAY)) break; sk->sk_state &= ~PPPOX_RELAY; err = 0; break; default: err = -ENOTTY; } return err; } static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { struct sk_buff *skb; struct sock *sk = sock->sk; struct pppox_sock *po = pppox_sk(sk); int error; struct pppoe_hdr hdr; struct pppoe_hdr *ph; struct net_device *dev; char *start; int hlen; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) { error = -ENOTCONN; goto end; } hdr.ver = 1; hdr.type = 1; hdr.code = 0; hdr.sid = po->num; dev = po->pppoe_dev; error = -EMSGSIZE; if (total_len > (dev->mtu + dev->hard_header_len)) goto end; hlen = LL_RESERVED_SPACE(dev); skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len + dev->needed_tailroom, 0, GFP_KERNEL); if (!skb) { error = -ENOMEM; goto end; } /* Reserve space for headers. */ skb_reserve(skb, hlen); skb_reset_network_header(skb); skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->protocol = cpu_to_be16(ETH_P_PPP_SES); ph = skb_put(skb, total_len + sizeof(struct pppoe_hdr)); start = (char *)&ph->tag[0]; error = memcpy_from_msg(start, m, total_len); if (error < 0) { kfree_skb(skb); goto end; } error = total_len; dev_hard_header(skb, dev, ETH_P_PPP_SES, po->pppoe_pa.remote, NULL, total_len); memcpy(ph, &hdr, sizeof(struct pppoe_hdr)); ph->length = htons(total_len); dev_queue_xmit(skb); end: release_sock(sk); return error; } /************************************************************************ * * xmit function for internal use. * ***********************************************************************/ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb) { struct pppox_sock *po = pppox_sk(sk); struct net_device *dev = po->pppoe_dev; struct pppoe_hdr *ph; int data_len = skb->len; /* The higher-level PPP code (ppp_unregister_channel()) ensures the PPP * xmit operations conclude prior to an unregistration call. Thus * sk->sk_state cannot change, so we don't need to do lock_sock(). * But, we also can't do a lock_sock since that introduces a potential * deadlock as we'd reverse the lock ordering used when calling * ppp_unregister_channel(). */ if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) goto abort; if (!dev) goto abort; /* Copy the data if there is no space for the header or if it's * read-only. */ if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph))) goto abort; __skb_push(skb, sizeof(*ph)); skb_reset_network_header(skb); ph = pppoe_hdr(skb); ph->ver = 1; ph->type = 1; ph->code = 0; ph->sid = po->num; ph->length = htons(data_len); skb->protocol = cpu_to_be16(ETH_P_PPP_SES); skb->dev = dev; dev_hard_header(skb, dev, ETH_P_PPP_SES, po->pppoe_pa.remote, NULL, data_len); dev_queue_xmit(skb); return 1; abort: kfree_skb(skb); return 1; } /************************************************************************ * * xmit function called by generic PPP driver * sends PPP frame over PPPoE socket * ***********************************************************************/ static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb) { struct sock *sk = chan->private; return __pppoe_xmit(sk, skb); } static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path, const struct ppp_channel *chan) { struct sock *sk = chan->private; struct pppox_sock *po = pppox_sk(sk); struct net_device *dev = po->pppoe_dev; if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED) || !dev) return -1; path->type = DEV_PATH_PPPOE; path->encap.proto = htons(ETH_P_PPP_SES); path->encap.id = be16_to_cpu(po->num); memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN); memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN); path->dev = ctx->dev; ctx->dev = dev; return 0; } static const struct ppp_channel_ops pppoe_chan_ops = { .start_xmit = pppoe_xmit, .fill_forward_path = pppoe_fill_forward_path, }; static int pppoe_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int error = 0; if (sk->sk_state & PPPOX_BOUND) return -EIO; skb = skb_recv_datagram(sk, flags, &error); if (!skb) return error; total_len = min_t(size_t, total_len, skb->len); error = skb_copy_datagram_msg(skb, 0, m, total_len); if (error == 0) { consume_skb(skb); return total_len; } kfree_skb(skb); return error; } #ifdef CONFIG_PROC_FS static int pppoe_seq_show(struct seq_file *seq, void *v) { struct pppox_sock *po; char *dev_name; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Id Address Device\n"); goto out; } po = v; dev_name = po->pppoe_pa.dev; seq_printf(seq, "%08X %pM %8s\n", po->pppoe_pa.sid, po->pppoe_pa.remote, dev_name); out: return 0; } static inline struct pppox_sock *pppoe_get_idx(struct pppoe_net *pn, loff_t pos) { struct pppox_sock *po; int i; for (i = 0; i < PPPOE_HASH_SIZE; i++) { po = rcu_dereference(pn->hash_table[i]); while (po) { if (!pos--) goto out; po = rcu_dereference(po->next); } } out: return po; } static void *pppoe_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq)); loff_t l = *pos; rcu_read_lock(); return l ? pppoe_get_idx(pn, --l) : SEQ_START_TOKEN; } static void *pppoe_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq)); struct pppox_sock *po, *next; ++*pos; if (v == SEQ_START_TOKEN) { po = pppoe_get_idx(pn, 0); goto out; } po = v; next = rcu_dereference(po->next); if (next) po = next; else { int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote); po = NULL; while (++hash < PPPOE_HASH_SIZE) { po = rcu_dereference(pn->hash_table[hash]); if (po) break; } } out: return po; } static void pppoe_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static const struct seq_operations pppoe_seq_ops = { .start = pppoe_seq_start, .next = pppoe_seq_next, .stop = pppoe_seq_stop, .show = pppoe_seq_show, }; #endif /* CONFIG_PROC_FS */ static const struct proto_ops pppoe_ops = { .family = AF_PPPOX, .owner = THIS_MODULE, .release = pppoe_release, .bind = sock_no_bind, .connect = pppoe_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = pppoe_getname, .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = pppoe_sendmsg, .recvmsg = pppoe_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = pppox_compat_ioctl, #endif }; static const struct pppox_proto pppoe_proto = { .create = pppoe_create, .ioctl = pppoe_ioctl, .owner = THIS_MODULE, }; static __net_init int pppoe_init_net(struct net *net) { struct pppoe_net *pn = pppoe_pernet(net); struct proc_dir_entry *pde; spin_lock_init(&pn->hash_lock); pde = proc_create_net("pppoe", 0444, net->proc_net, &pppoe_seq_ops, sizeof(struct seq_net_private)); #ifdef CONFIG_PROC_FS if (!pde) return -ENOMEM; #endif return 0; } static __net_exit void pppoe_exit_net(struct net *net) { remove_proc_entry("pppoe", net->proc_net); } static struct pernet_operations pppoe_net_ops = { .init = pppoe_init_net, .exit = pppoe_exit_net, .id = &pppoe_net_id, .size = sizeof(struct pppoe_net), }; static int __init pppoe_init(void) { int err; err = register_pernet_device(&pppoe_net_ops); if (err) goto out; err = proto_register(&pppoe_sk_proto, 0); if (err) goto out_unregister_net_ops; err = register_pppox_proto(PX_PROTO_OE, &pppoe_proto); if (err) goto out_unregister_pppoe_proto; dev_add_pack(&pppoes_ptype); dev_add_pack(&pppoed_ptype); register_netdevice_notifier(&pppoe_notifier); return 0; out_unregister_pppoe_proto: proto_unregister(&pppoe_sk_proto); out_unregister_net_ops: unregister_pernet_device(&pppoe_net_ops); out: return err; } static void __exit pppoe_exit(void) { unregister_netdevice_notifier(&pppoe_notifier); dev_remove_pack(&pppoed_ptype); dev_remove_pack(&pppoes_ptype); unregister_pppox_proto(PX_PROTO_OE); proto_unregister(&pppoe_sk_proto); unregister_pernet_device(&pppoe_net_ops); } module_init(pppoe_init); module_exit(pppoe_exit); MODULE_AUTHOR("Michal Ostrowski <mostrows@speakeasy.net>"); MODULE_DESCRIPTION("PPP over Ethernet driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OE); |
| 509 508 510 510 510 510 504 504 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/char/misc.c * * Generic misc open routine by Johan Myreen * * Based on code from Linus * * Teemu Rantanen's Microsoft Busmouse support and Derrick Cole's * changes incorporated into 0.97pl4 * by Peter Cervasio (pete%q106fm.uucp@wupost.wustl.edu) (08SEP92) * See busmouse.c for particulars. * * Made things a lot mode modular - easy to compile in just one or two * of the misc drivers, as they are now completely independent. Linus. * * Support for loadable modules. 8-Sep-95 Philip Blundell <pjb27@cam.ac.uk> * * Fixed a failing symbol register to free the device registration * Alan Cox <alan@lxorguk.ukuu.org.uk> 21-Jan-96 * * Dynamic minors and /proc/mice by Alessandro Rubini. 26-Mar-96 * * Renamed to misc and miscdevice to be more accurate. Alan Cox 26-Mar-96 * * Handling of mouse minor numbers for kerneld: * Idea by Jacques Gelinas <jack@solucorp.qc.ca>, * adapted by Bjorn Ekwall <bj0rn@blox.se> * corrected by Alan Cox <alan@lxorguk.ukuu.org.uk> * * Changes for kmod (from kerneld): * Cyrus Durgin <cider@speakeasy.org> * * Added devfs support. Richard Gooch <rgooch@atnf.csiro.au> 10-Jan-1998 */ #include <linux/module.h> #include <linux/fs.h> #include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/device.h> #include <linux/tty.h> #include <linux/kmod.h> #include <linux/gfp.h> /* * Head entry for the doubly linked miscdevice list */ static LIST_HEAD(misc_list); static DEFINE_MUTEX(misc_mtx); /* * Assigned numbers. */ static DEFINE_IDA(misc_minors_ida); static int misc_minor_alloc(int minor) { int ret = 0; if (minor == MISC_DYNAMIC_MINOR) { /* allocate free id */ ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1, MINORMASK, GFP_KERNEL); } else { ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL); } return ret; } static void misc_minor_free(int minor) { ida_free(&misc_minors_ida, minor); } #ifdef CONFIG_PROC_FS static void *misc_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&misc_mtx); return seq_list_start(&misc_list, *pos); } static void *misc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &misc_list, pos); } static void misc_seq_stop(struct seq_file *seq, void *v) { mutex_unlock(&misc_mtx); } static int misc_seq_show(struct seq_file *seq, void *v) { const struct miscdevice *p = list_entry(v, struct miscdevice, list); seq_printf(seq, "%3i %s\n", p->minor, p->name ? p->name : ""); return 0; } static const struct seq_operations misc_seq_ops = { .start = misc_seq_start, .next = misc_seq_next, .stop = misc_seq_stop, .show = misc_seq_show, }; #endif static int misc_open(struct inode *inode, struct file *file) { int minor = iminor(inode); struct miscdevice *c = NULL, *iter; int err = -ENODEV; const struct file_operations *new_fops = NULL; mutex_lock(&misc_mtx); list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor) continue; c = iter; new_fops = fops_get(iter->fops); break; } /* Only request module for fixed minor code */ if (!new_fops && minor < MISC_DYNAMIC_MINOR) { mutex_unlock(&misc_mtx); request_module("char-major-%d-%d", MISC_MAJOR, minor); mutex_lock(&misc_mtx); list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor) continue; c = iter; new_fops = fops_get(iter->fops); break; } } if (!new_fops) goto fail; /* * Place the miscdevice in the file's * private_data so it can be used by the * file operations, including f_op->open below */ file->private_data = c; err = 0; replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file); fail: mutex_unlock(&misc_mtx); return err; } static char *misc_devnode(const struct device *dev, umode_t *mode) { const struct miscdevice *c = dev_get_drvdata(dev); if (mode && c->mode) *mode = c->mode; if (c->nodename) return kstrdup(c->nodename, GFP_KERNEL); return NULL; } static const struct class misc_class = { .name = "misc", .devnode = misc_devnode, }; static const struct file_operations misc_fops = { .owner = THIS_MODULE, .open = misc_open, .llseek = noop_llseek, }; /** * misc_register - register a miscellaneous device * @misc: device structure * * Register a miscellaneous device with the kernel. If the minor * number is set to %MISC_DYNAMIC_MINOR a minor number is assigned * and placed in the minor field of the structure. For other cases * the minor number requested is used. * * The structure passed is linked into the kernel and may not be * destroyed until it has been unregistered. By default, an open() * syscall to the device sets file->private_data to point to the * structure. Drivers don't need open in fops for this. * * A zero is returned on success and a negative errno code for * failure. */ int misc_register(struct miscdevice *misc) { dev_t dev; int err = 0; bool is_dynamic = (misc->minor == MISC_DYNAMIC_MINOR); if (misc->minor > MISC_DYNAMIC_MINOR) { pr_err("Invalid fixed minor %d for miscdevice '%s'\n", misc->minor, misc->name); return -EINVAL; } INIT_LIST_HEAD(&misc->list); mutex_lock(&misc_mtx); if (is_dynamic) { int i = misc_minor_alloc(misc->minor); if (i < 0) { err = -EBUSY; goto out; } misc->minor = i; } else { struct miscdevice *c; int i; list_for_each_entry(c, &misc_list, list) { if (c->minor == misc->minor) { err = -EBUSY; goto out; } } i = misc_minor_alloc(misc->minor); if (i < 0) { err = -EBUSY; goto out; } } dev = MKDEV(MISC_MAJOR, misc->minor); misc->this_device = device_create_with_groups(&misc_class, misc->parent, dev, misc, misc->groups, "%s", misc->name); if (IS_ERR(misc->this_device)) { misc_minor_free(misc->minor); if (is_dynamic) { misc->minor = MISC_DYNAMIC_MINOR; } err = PTR_ERR(misc->this_device); goto out; } /* * Add it to the front, so that later devices can "override" * earlier defaults */ list_add(&misc->list, &misc_list); out: mutex_unlock(&misc_mtx); return err; } EXPORT_SYMBOL(misc_register); /** * misc_deregister - unregister a miscellaneous device * @misc: device to unregister * * Unregister a miscellaneous device that was previously * successfully registered with misc_register(). */ void misc_deregister(struct miscdevice *misc) { mutex_lock(&misc_mtx); list_del_init(&misc->list); device_destroy(&misc_class, MKDEV(MISC_MAJOR, misc->minor)); misc_minor_free(misc->minor); if (misc->minor > MISC_DYNAMIC_MINOR) misc->minor = MISC_DYNAMIC_MINOR; mutex_unlock(&misc_mtx); } EXPORT_SYMBOL(misc_deregister); static int __init misc_init(void) { int err; struct proc_dir_entry *misc_proc_file; misc_proc_file = proc_create_seq("misc", 0, NULL, &misc_seq_ops); err = class_register(&misc_class); if (err) goto fail_remove; err = __register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops); if (err < 0) goto fail_printk; return 0; fail_printk: pr_err("unable to get major %d for misc devices\n", MISC_MAJOR); class_unregister(&misc_class); fail_remove: if (misc_proc_file) remove_proc_entry("misc", NULL); return err; } subsys_initcall(misc_init); |
| 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 HGST, a Western Digital Company. */ #include <linux/err.h> #include <linux/slab.h> #include <rdma/ib_verbs.h> #include "core_priv.h" #include <trace/events/rdma_core.h> /* Max size for shared CQ, may require tuning */ #define IB_MAX_SHARED_CQ_SZ 4096U /* # of WCs to poll for with a single call to ib_poll_cq */ #define IB_POLL_BATCH 16 #define IB_POLL_BATCH_DIRECT 8 /* # of WCs to iterate over before yielding */ #define IB_POLL_BUDGET_IRQ 256 #define IB_POLL_BUDGET_WORKQUEUE 65536 #define IB_POLL_FLAGS \ (IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS) static const struct dim_cq_moder rdma_dim_prof[RDMA_DIM_PARAMS_NUM_PROFILES] = { {1, 0, 1, 0}, {1, 0, 4, 0}, {2, 0, 4, 0}, {2, 0, 8, 0}, {4, 0, 8, 0}, {16, 0, 8, 0}, {16, 0, 16, 0}, {32, 0, 16, 0}, {32, 0, 32, 0}, }; static void ib_cq_rdma_dim_work(struct work_struct *w) { struct dim *dim = container_of(w, struct dim, work); struct ib_cq *cq = dim->priv; u16 usec = rdma_dim_prof[dim->profile_ix].usec; u16 comps = rdma_dim_prof[dim->profile_ix].comps; dim->state = DIM_START_MEASURE; trace_cq_modify(cq, comps, usec); cq->device->ops.modify_cq(cq, comps, usec); } static void rdma_dim_init(struct ib_cq *cq) { struct dim *dim; if (!cq->device->ops.modify_cq || !cq->device->use_cq_dim || cq->poll_ctx == IB_POLL_DIRECT) return; dim = kzalloc(sizeof(struct dim), GFP_KERNEL); if (!dim) return; dim->state = DIM_START_MEASURE; dim->tune_state = DIM_GOING_RIGHT; dim->profile_ix = RDMA_DIM_START_PROFILE; dim->priv = cq; cq->dim = dim; INIT_WORK(&dim->work, ib_cq_rdma_dim_work); } static void rdma_dim_destroy(struct ib_cq *cq) { if (!cq->dim) return; cancel_work_sync(&cq->dim->work); kfree(cq->dim); } static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { int rc; rc = ib_poll_cq(cq, num_entries, wc); trace_cq_poll(cq, num_entries, rc); return rc; } static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs, int batch) { int i, n, completed = 0; trace_cq_process(cq); /* * budget might be (-1) if the caller does not * want to bound this call, thus we need unsigned * minimum here. */ while ((n = __poll_cq(cq, min_t(u32, batch, budget - completed), wcs)) > 0) { for (i = 0; i < n; i++) { struct ib_wc *wc = &wcs[i]; if (wc->wr_cqe) wc->wr_cqe->done(cq, wc); else WARN_ON_ONCE(wc->status == IB_WC_SUCCESS); } completed += n; if (n != batch || (budget != -1 && completed >= budget)) break; } return completed; } /** * ib_process_cq_direct - process a CQ in caller context * @cq: CQ to process * @budget: number of CQEs to poll for * * This function is used to process all outstanding CQ entries. * It does not offload CQ processing to a different context and does * not ask for completion interrupts from the HCA. * Using direct processing on CQ with non IB_POLL_DIRECT type may trigger * concurrent processing. * * Note: do not pass -1 as %budget unless it is guaranteed that the number * of completions that will be processed is small. */ int ib_process_cq_direct(struct ib_cq *cq, int budget) { struct ib_wc wcs[IB_POLL_BATCH_DIRECT]; return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT); } EXPORT_SYMBOL(ib_process_cq_direct); static void ib_cq_completion_direct(struct ib_cq *cq, void *private) { WARN_ONCE(1, "got unsolicited completion for CQ 0x%p\n", cq); } static int ib_poll_handler(struct irq_poll *iop, int budget) { struct ib_cq *cq = container_of(iop, struct ib_cq, iop); struct dim *dim = cq->dim; int completed; completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH); if (completed < budget) { irq_poll_complete(&cq->iop); if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) { trace_cq_reschedule(cq); irq_poll_sched(&cq->iop); } } if (dim) rdma_dim(dim, completed); return completed; } static void ib_cq_completion_softirq(struct ib_cq *cq, void *private) { trace_cq_schedule(cq); irq_poll_sched(&cq->iop); } static void ib_cq_poll_work(struct work_struct *work) { struct ib_cq *cq = container_of(work, struct ib_cq, work); int completed; completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc, IB_POLL_BATCH); if (completed >= IB_POLL_BUDGET_WORKQUEUE || ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) queue_work(cq->comp_wq, &cq->work); else if (cq->dim) rdma_dim(cq->dim, completed); } static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private) { trace_cq_schedule(cq); queue_work(cq->comp_wq, &cq->work); } /** * __ib_alloc_cq - allocate a completion queue * @dev: device to allocate the CQ for * @private: driver private data, accessible from cq->cq_context * @nr_cqe: number of CQEs to allocate * @comp_vector: HCA completion vectors for this CQ * @poll_ctx: context to poll the CQ from. * @caller: module owner name. * * This is the proper interface to allocate a CQ for in-kernel users. A * CQ allocated with this interface will automatically be polled from the * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id * to use this CQ abstraction. */ struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, const char *caller) { struct ib_cq_init_attr cq_attr = { .cqe = nr_cqe, .comp_vector = comp_vector, }; struct ib_cq *cq; int ret = -ENOMEM; cq = rdma_zalloc_drv_obj(dev, ib_cq); if (!cq) return ERR_PTR(ret); cq->device = dev; cq->cq_context = private; cq->poll_ctx = poll_ctx; atomic_set(&cq->usecnt, 0); cq->comp_vector = comp_vector; cq->wc = kmalloc_array(IB_POLL_BATCH, sizeof(*cq->wc), GFP_KERNEL); if (!cq->wc) goto out_free_cq; rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ); rdma_restrack_set_name(&cq->res, caller); ret = dev->ops.create_cq(cq, &cq_attr, NULL); if (ret) goto out_free_wc; rdma_dim_init(cq); switch (cq->poll_ctx) { case IB_POLL_DIRECT: cq->comp_handler = ib_cq_completion_direct; break; case IB_POLL_SOFTIRQ: cq->comp_handler = ib_cq_completion_softirq; irq_poll_init(&cq->iop, IB_POLL_BUDGET_IRQ, ib_poll_handler); ib_req_notify_cq(cq, IB_CQ_NEXT_COMP); break; case IB_POLL_WORKQUEUE: case IB_POLL_UNBOUND_WORKQUEUE: cq->comp_handler = ib_cq_completion_workqueue; INIT_WORK(&cq->work, ib_cq_poll_work); ib_req_notify_cq(cq, IB_CQ_NEXT_COMP); cq->comp_wq = (cq->poll_ctx == IB_POLL_WORKQUEUE) ? ib_comp_wq : ib_comp_unbound_wq; break; default: ret = -EINVAL; goto out_destroy_cq; } rdma_restrack_add(&cq->res); trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx); return cq; out_destroy_cq: rdma_dim_destroy(cq); cq->device->ops.destroy_cq(cq, NULL); out_free_wc: rdma_restrack_put(&cq->res); kfree(cq->wc); out_free_cq: kfree(cq); trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret); return ERR_PTR(ret); } EXPORT_SYMBOL(__ib_alloc_cq); /** * __ib_alloc_cq_any - allocate a completion queue * @dev: device to allocate the CQ for * @private: driver private data, accessible from cq->cq_context * @nr_cqe: number of CQEs to allocate * @poll_ctx: context to poll the CQ from * @caller: module owner name * * Attempt to spread ULP Completion Queues over each device's interrupt * vectors. A simple best-effort mechanism is used. */ struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx, const char *caller) { static atomic_t counter; int comp_vector = 0; if (dev->num_comp_vectors > 1) comp_vector = atomic_inc_return(&counter) % min_t(int, dev->num_comp_vectors, num_online_cpus()); return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, caller); } EXPORT_SYMBOL(__ib_alloc_cq_any); /** * ib_free_cq - free a completion queue * @cq: completion queue to free. */ void ib_free_cq(struct ib_cq *cq) { int ret = 0; if (WARN_ON_ONCE(atomic_read(&cq->usecnt))) return; if (WARN_ON_ONCE(cq->cqe_used)) return; if (cq->device->ops.pre_destroy_cq) { ret = cq->device->ops.pre_destroy_cq(cq); WARN_ONCE(ret, "Disable of kernel CQ shouldn't fail"); } switch (cq->poll_ctx) { case IB_POLL_DIRECT: break; case IB_POLL_SOFTIRQ: irq_poll_disable(&cq->iop); break; case IB_POLL_WORKQUEUE: case IB_POLL_UNBOUND_WORKQUEUE: cancel_work_sync(&cq->work); break; default: WARN_ON_ONCE(1); } rdma_dim_destroy(cq); trace_cq_free(cq); if (cq->device->ops.post_destroy_cq) cq->device->ops.post_destroy_cq(cq); else ret = cq->device->ops.destroy_cq(cq, NULL); WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); rdma_restrack_del(&cq->res); kfree(cq->wc); kfree(cq); } EXPORT_SYMBOL(ib_free_cq); void ib_cq_pool_cleanup(struct ib_device *dev) { struct ib_cq *cq, *n; unsigned int i; for (i = 0; i < ARRAY_SIZE(dev->cq_pools); i++) { list_for_each_entry_safe(cq, n, &dev->cq_pools[i], pool_entry) { WARN_ON(cq->cqe_used); list_del(&cq->pool_entry); cq->shared = false; ib_free_cq(cq); } } } static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes, enum ib_poll_context poll_ctx) { LIST_HEAD(tmp_list); unsigned int nr_cqs, i; struct ib_cq *cq, *n; int ret; if (poll_ctx > IB_POLL_LAST_POOL_TYPE) { WARN_ON_ONCE(poll_ctx > IB_POLL_LAST_POOL_TYPE); return -EINVAL; } /* * Allocate at least as many CQEs as requested, and otherwise * a reasonable batch size so that we can share CQs between * multiple users instead of allocating a larger number of CQs. */ nr_cqes = min_t(unsigned int, dev->attrs.max_cqe, max(nr_cqes, IB_MAX_SHARED_CQ_SZ)); nr_cqs = min_t(unsigned int, dev->num_comp_vectors, num_online_cpus()); for (i = 0; i < nr_cqs; i++) { cq = ib_alloc_cq(dev, NULL, nr_cqes, i, poll_ctx); if (IS_ERR(cq)) { ret = PTR_ERR(cq); goto out_free_cqs; } cq->shared = true; list_add_tail(&cq->pool_entry, &tmp_list); } spin_lock_irq(&dev->cq_pools_lock); list_splice(&tmp_list, &dev->cq_pools[poll_ctx]); spin_unlock_irq(&dev->cq_pools_lock); return 0; out_free_cqs: list_for_each_entry_safe(cq, n, &tmp_list, pool_entry) { cq->shared = false; ib_free_cq(cq); } return ret; } /** * ib_cq_pool_get() - Find the least used completion queue that matches * a given cpu hint (or least used for wild card affinity) and fits * nr_cqe. * @dev: rdma device * @nr_cqe: number of needed cqe entries * @comp_vector_hint: completion vector hint (-1) for the driver to assign * a comp vector based on internal counter * @poll_ctx: cq polling context * * Finds a cq that satisfies @comp_vector_hint and @nr_cqe requirements and * claim entries in it for us. In case there is no available cq, allocate * a new cq with the requirements and add it to the device pool. * IB_POLL_DIRECT cannot be used for shared cqs so it is not a valid value * for @poll_ctx. */ struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, int comp_vector_hint, enum ib_poll_context poll_ctx) { static unsigned int default_comp_vector; unsigned int vector, num_comp_vectors; struct ib_cq *cq, *found = NULL; int ret; if (poll_ctx > IB_POLL_LAST_POOL_TYPE) { WARN_ON_ONCE(poll_ctx > IB_POLL_LAST_POOL_TYPE); return ERR_PTR(-EINVAL); } num_comp_vectors = min_t(unsigned int, dev->num_comp_vectors, num_online_cpus()); /* Project the affinty to the device completion vector range */ if (comp_vector_hint < 0) { comp_vector_hint = (READ_ONCE(default_comp_vector) + 1) % num_comp_vectors; WRITE_ONCE(default_comp_vector, comp_vector_hint); } vector = comp_vector_hint % num_comp_vectors; /* * Find the least used CQ with correct affinity and * enough free CQ entries */ while (!found) { spin_lock_irq(&dev->cq_pools_lock); list_for_each_entry(cq, &dev->cq_pools[poll_ctx], pool_entry) { /* * Check to see if we have found a CQ with the * correct completion vector */ if (vector != cq->comp_vector) continue; if (cq->cqe_used + nr_cqe > cq->cqe) continue; found = cq; break; } if (found) { found->cqe_used += nr_cqe; spin_unlock_irq(&dev->cq_pools_lock); return found; } spin_unlock_irq(&dev->cq_pools_lock); /* * Didn't find a match or ran out of CQs in the device * pool, allocate a new array of CQs. */ ret = ib_alloc_cqs(dev, nr_cqe, poll_ctx); if (ret) return ERR_PTR(ret); } return found; } EXPORT_SYMBOL(ib_cq_pool_get); /** * ib_cq_pool_put - Return a CQ taken from a shared pool. * @cq: The CQ to return. * @nr_cqe: The max number of cqes that the user had requested. */ void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe) { if (WARN_ON_ONCE(nr_cqe > cq->cqe_used)) return; spin_lock_irq(&cq->device->cq_pools_lock); cq->cqe_used -= nr_cqe; spin_unlock_irq(&cq->device->cq_pools_lock); } EXPORT_SYMBOL(ib_cq_pool_put); |
| 14 8 14 1 13 1 12 8 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* iptables module for using new netfilter netlink queue * * (C) 2005 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_NFQUEUE.h> #include <net/netfilter/nf_queue.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet forwarding to netlink"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_NFQUEUE"); MODULE_ALIAS("ip6t_NFQUEUE"); MODULE_ALIAS("arpt_NFQUEUE"); static u32 jhash_initval __read_mostly; static unsigned int nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info *tinfo = par->targinfo; return NF_QUEUE_NR(tinfo->queuenum); } static unsigned int nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v1 *info = par->targinfo; u32 queue = info->queuenum; if (info->queues_total > 1) { queue = nfqueue_hash(skb, queue, info->queues_total, xt_family(par), jhash_initval); } return NF_QUEUE_NR(queue); } static unsigned int nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v2 *info = par->targinfo; unsigned int ret = nfqueue_tg_v1(skb, par); if (info->bypass) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; return ret; } static int nfqueue_tg_check(const struct xt_tgchk_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 maxid; init_hashrandom(&jhash_initval); if (info->queues_total == 0) { pr_info_ratelimited("number of total queues is 0\n"); return -EINVAL; } maxid = info->queues_total - 1 + info->queuenum; if (maxid > 0xffff) { pr_info_ratelimited("number of queues (%u) out of range (got %u)\n", info->queues_total, maxid); return -ERANGE; } if (par->target->revision == 2 && info->flags > 1) return -EINVAL; if (par->target->revision == 3 && info->flags & ~NFQ_FLAG_MASK) return -EINVAL; return 0; } static unsigned int nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 queue = info->queuenum; int ret; if (info->queues_total > 1) { if (info->flags & NFQ_FLAG_CPU_FANOUT) { int cpu = smp_processor_id(); queue = info->queuenum + cpu % info->queues_total; } else { queue = nfqueue_hash(skb, queue, info->queues_total, xt_family(par), jhash_initval); } } ret = NF_QUEUE_NR(queue); if (info->flags & NFQ_FLAG_BYPASS) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; return ret; } static struct xt_target nfqueue_tg_reg[] __read_mostly = { { .name = "NFQUEUE", .family = NFPROTO_UNSPEC, .target = nfqueue_tg, .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v1, .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 2, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v2, .targetsize = sizeof(struct xt_NFQ_info_v2), .me = THIS_MODULE, }, { .name = "NFQUEUE", .revision = 3, .family = NFPROTO_UNSPEC, .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v3, .targetsize = sizeof(struct xt_NFQ_info_v3), .me = THIS_MODULE, }, }; static int __init nfqueue_tg_init(void) { return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } static void __exit nfqueue_tg_exit(void) { xt_unregister_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg)); } module_init(nfqueue_tg_init); module_exit(nfqueue_tg_exit); |
| 6 6 6 5 6 6 6 3 3 6 6 6 6 6 6 6 6 6 5 6 6 6 2 65 65 65 64 2 2 2 9 4 2 2 2 2 7 65 62 3 3 2 2 2 2 2 64 4 1 1 1 64 64 64 5 64 63 63 64 64 64 64 64 64 64 63 5 64 64 64 2 64 3 3 64 2 1 64 3 4 64 5 5 5 5 1 5 1 1 1 64 64 1 64 5 63 5 5 5 4 5 3 5 5 2 5 2 4 63 64 5 5 4 5 5 1 5 2 2 2 5 5 2 5 5 5 5 5 5 5 5 5 5 7 7 7 6 7 7 7 7 7 7 5 6 6 6 6 6 6 6 6 6 6 6 6 5 6 2 6 11 11 6 8 11 5 4 5 4 5 5 41 1 64 9 2 10 7 7 7 7 7 7 5 4 4 5 5 5 2 2 2 2 2 2 2 2 64 64 64 2 63 64 64 64 64 63 64 64 64 10 64 64 35 2 2 2 2 67 3 3 65 37 67 64 2 64 64 64 2 2 62 64 64 64 64 64 64 62 64 64 64 64 64 64 64 63 64 5 64 64 63 64 64 64 63 64 64 64 64 64 64 64 64 64 61 64 64 64 64 64 63 64 63 63 6 5 5 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 6 6 6 5 6 6 5 6 3 3 3 6 5 3 6 6 3 135 127 136 133 136 17 17 17 17 2 2 136 133 5 5 63 62 63 63 63 63 63 62 63 5 63 63 63 63 63 63 63 62 63 63 4 63 62 1 63 47 62 35 63 63 8 8 1 1 2 2 64 64 64 64 64 64 64 64 64 64 64 63 64 4 64 64 63 63 64 64 63 63 5 1 5 5 5 64 63 2 64 2 64 64 64 64 64 64 38 37 35 35 35 35 35 5 5 38 123 116 116 116 124 124 122 50 38 47 13 35 35 34 34 8 9 1 9 9 7 17 101 20 136 135 136 136 135 2 133 134 136 134 136 136 136 102 102 102 2 136 134 2 136 105 125 136 2 3 2 3 2 2 3 2 2 2 2 2 2 1 1 2 3 2 2 2 135 2 2 2 2 135 136 136 135 135 136 136 135 136 135 136 136 23 22 22 23 22 21 3 22 7 22 1 135 134 3 134 135 135 3 3 2 135 135 136 134 106 136 136 136 136 135 135 136 136 136 102 1 1 102 136 136 2 2 2 2 136 6 136 136 136 129 36 2 2 134 3 3 3 64 64 63 64 7 7 7 7 7 7 7 7 7 2 64 64 64 64 64 64 64 62 2 64 64 17 17 17 129 3 129 27 23 12 115 129 129 126 129 3 128 128 116 3 3 3 116 115 129 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 1 3 1 1 1 4 3 4 3 2 3 1 2 2 1 2 3 3 1 3 3 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/sort.h> #include <linux/rcupdate.h> #include <linux/kthread.h> #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/percpu_counter.h> #include <linux/lockdep.h> #include <linux/crc32c.h> #include "ctree.h" #include "extent-tree.h" #include "transaction.h" #include "disk-io.h" #include "print-tree.h" #include "volumes.h" #include "raid56.h" #include "locking.h" #include "free-space-cache.h" #include "free-space-tree.h" #include "qgroup.h" #include "ref-verify.h" #include "space-info.h" #include "block-rsv.h" #include "discard.h" #include "zoned.h" #include "dev-replace.h" #include "fs.h" #include "accessors.h" #include "root-tree.h" #include "file-item.h" #include "orphan.h" #include "tree-checker.h" #include "raid-stripe-tree.h" #undef SCRAMBLE_DELAYED_REFS static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extra_op); static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op, struct extent_buffer *leaf, struct btrfs_extent_item *ei); static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, u64 parent, u64 root_objectid, u64 flags, u64 owner, u64 offset, struct btrfs_key *ins, int ref_mod, u64 oref_root); static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op); static int find_next_key(const struct btrfs_path *path, int level, struct btrfs_key *key); static int block_group_bits(const struct btrfs_block_group *cache, u64 bits) { return (cache->flags & bits) == bits; } /* simple helper to search for an existing data extent at a given offset */ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len) { struct btrfs_root *root = btrfs_extent_root(fs_info, start); struct btrfs_key key; BTRFS_PATH_AUTO_FREE(path); path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = start; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = len; return btrfs_search_slot(NULL, root, &key, path, 0, 0); } /* * helper function to lookup reference count and flags of a tree block. * * the head node for delayed ref is used to store the sum of all the * reference count modifications queued up in the rbtree. the head * node may also store the extent flags to set. This way you can check * to see what the reference count and extent flags would be if all of * the delayed refs are not processed. */ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, u64 offset, int metadata, u64 *refs, u64 *flags, u64 *owning_root) { struct btrfs_root *extent_root; struct btrfs_delayed_ref_head *head; struct btrfs_delayed_ref_root *delayed_refs; BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; u64 num_refs; u64 extent_flags; u64 owner = 0; int ret; /* * If we don't have skinny metadata, don't bother doing anything * different */ if (metadata && !btrfs_fs_incompat(fs_info, SKINNY_METADATA)) { offset = fs_info->nodesize; metadata = 0; } path = btrfs_alloc_path(); if (!path) return -ENOMEM; search_again: key.objectid = bytenr; if (metadata) key.type = BTRFS_METADATA_ITEM_KEY; else key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = offset; extent_root = btrfs_extent_root(fs_info, bytenr); ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) return ret; if (ret > 0 && key.type == BTRFS_METADATA_ITEM_KEY) { if (path->slots[0]) { path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid == bytenr && key.type == BTRFS_EXTENT_ITEM_KEY && key.offset == fs_info->nodesize) ret = 0; } } if (ret == 0) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_extent_item *ei; const u32 item_size = btrfs_item_size(leaf, path->slots[0]); if (unlikely(item_size < sizeof(*ei))) { ret = -EUCLEAN; btrfs_err(fs_info, "unexpected extent item size, has %u expect >= %zu", item_size, sizeof(*ei)); btrfs_abort_transaction(trans, ret); return ret; } ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); num_refs = btrfs_extent_refs(leaf, ei); if (unlikely(num_refs == 0)) { ret = -EUCLEAN; btrfs_err(fs_info, "unexpected zero reference count for extent item (%llu %u %llu)", key.objectid, key.type, key.offset); btrfs_abort_transaction(trans, ret); return ret; } extent_flags = btrfs_extent_flags(leaf, ei); owner = btrfs_get_extent_owner_root(fs_info, leaf, path->slots[0]); } else { num_refs = 0; extent_flags = 0; ret = 0; } delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); head = btrfs_find_delayed_ref_head(fs_info, delayed_refs, bytenr); if (head) { if (!mutex_trylock(&head->mutex)) { refcount_inc(&head->refs); spin_unlock(&delayed_refs->lock); btrfs_release_path(path); /* * Mutex was contended, block until it's released and try * again */ mutex_lock(&head->mutex); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); goto search_again; } spin_lock(&head->lock); if (head->extent_op && head->extent_op->update_flags) extent_flags |= head->extent_op->flags_to_set; num_refs += head->ref_mod; spin_unlock(&head->lock); mutex_unlock(&head->mutex); } spin_unlock(&delayed_refs->lock); WARN_ON(num_refs == 0); if (refs) *refs = num_refs; if (flags) *flags = extent_flags; if (owning_root) *owning_root = owner; return ret; } /* * Back reference rules. Back refs have three main goals: * * 1) differentiate between all holders of references to an extent so that * when a reference is dropped we can make sure it was a valid reference * before freeing the extent. * * 2) Provide enough information to quickly find the holders of an extent * if we notice a given block is corrupted or bad. * * 3) Make it easy to migrate blocks for FS shrinking or storage pool * maintenance. This is actually the same as #2, but with a slightly * different use case. * * There are two kinds of back refs. The implicit back refs is optimized * for pointers in non-shared tree blocks. For a given pointer in a block, * back refs of this kind provide information about the block's owner tree * and the pointer's key. These information allow us to find the block by * b-tree searching. The full back refs is for pointers in tree blocks not * referenced by their owner trees. The location of tree block is recorded * in the back refs. Actually the full back refs is generic, and can be * used in all cases the implicit back refs is used. The major shortcoming * of the full back refs is its overhead. Every time a tree block gets * COWed, we have to update back refs entry for all pointers in it. * * For a newly allocated tree block, we use implicit back refs for * pointers in it. This means most tree related operations only involve * implicit back refs. For a tree block created in old transaction, the * only way to drop a reference to it is COW it. So we can detect the * event that tree block loses its owner tree's reference and do the * back refs conversion. * * When a tree block is COWed through a tree, there are four cases: * * The reference count of the block is one and the tree is the block's * owner tree. Nothing to do in this case. * * The reference count of the block is one and the tree is not the * block's owner tree. In this case, full back refs is used for pointers * in the block. Remove these full back refs, add implicit back refs for * every pointers in the new block. * * The reference count of the block is greater than one and the tree is * the block's owner tree. In this case, implicit back refs is used for * pointers in the block. Add full back refs for every pointers in the * block, increase lower level extents' reference counts. The original * implicit back refs are entailed to the new block. * * The reference count of the block is greater than one and the tree is * not the block's owner tree. Add implicit back refs for every pointer in * the new block, increase lower level extents' reference count. * * Back Reference Key composing: * * The key objectid corresponds to the first byte in the extent, * The key type is used to differentiate between types of back refs. * There are different meanings of the key offset for different types * of back refs. * * File extents can be referenced by: * * - multiple snapshots, subvolumes, or different generations in one subvol * - different files inside a single subvolume * - different offsets inside a file (bookend extents in file.c) * * The extent ref structure for the implicit back refs has fields for: * * - Objectid of the subvolume root * - objectid of the file holding the reference * - original offset in the file * - how many bookend extents * * The key offset for the implicit back refs is hash of the first * three fields. * * The extent ref structure for the full back refs has field for: * * - number of pointers in the tree leaf * * The key offset for the implicit back refs is the first byte of * the tree leaf * * When a file extent is allocated, The implicit back refs is used. * the fields are filled in: * * (root_key.objectid, inode objectid, offset in file, 1) * * When a file extent is removed file truncation, we find the * corresponding implicit back refs and check the following fields: * * (btrfs_header_owner(leaf), inode objectid, offset in file) * * Btree extents can be referenced by: * * - Different subvolumes * * Both the implicit back refs and the full back refs for tree blocks * only consist of key. The key offset for the implicit back refs is * objectid of block's owner tree. The key offset for the full back refs * is the first byte of parent block. * * When implicit back refs is used, information about the lowest key and * level of the tree block are required. These information are stored in * tree block info structure. */ /* * is_data == BTRFS_REF_TYPE_BLOCK, tree block type is required, * is_data == BTRFS_REF_TYPE_DATA, data type is required, * is_data == BTRFS_REF_TYPE_ANY, either type is OK. */ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, const struct btrfs_extent_inline_ref *iref, enum btrfs_inline_ref_type is_data) { struct btrfs_fs_info *fs_info = eb->fs_info; int type = btrfs_extent_inline_ref_type(eb, iref); u64 offset = btrfs_extent_inline_ref_offset(eb, iref); if (type == BTRFS_EXTENT_OWNER_REF_KEY) { ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); return type; } if (type == BTRFS_TREE_BLOCK_REF_KEY || type == BTRFS_SHARED_BLOCK_REF_KEY || type == BTRFS_SHARED_DATA_REF_KEY || type == BTRFS_EXTENT_DATA_REF_KEY) { if (is_data == BTRFS_REF_TYPE_BLOCK) { if (type == BTRFS_TREE_BLOCK_REF_KEY) return type; if (type == BTRFS_SHARED_BLOCK_REF_KEY) { ASSERT(fs_info); /* * Every shared one has parent tree block, * which must be aligned to sector size. */ if (offset && IS_ALIGNED(offset, fs_info->sectorsize)) return type; } } else if (is_data == BTRFS_REF_TYPE_DATA) { if (type == BTRFS_EXTENT_DATA_REF_KEY) return type; if (type == BTRFS_SHARED_DATA_REF_KEY) { ASSERT(fs_info); /* * Every shared one has parent tree block, * which must be aligned to sector size. */ if (offset && IS_ALIGNED(offset, fs_info->sectorsize)) return type; } } else { ASSERT(is_data == BTRFS_REF_TYPE_ANY); return type; } } WARN_ON(1); btrfs_print_leaf(eb); btrfs_err(fs_info, "eb %llu iref 0x%lx invalid extent inline ref type %d", eb->start, (unsigned long)iref, type); return BTRFS_REF_TYPE_INVALID; } u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset) { u32 high_crc = ~(u32)0; u32 low_crc = ~(u32)0; __le64 lenum; lenum = cpu_to_le64(root_objectid); high_crc = crc32c(high_crc, &lenum, sizeof(lenum)); lenum = cpu_to_le64(owner); low_crc = crc32c(low_crc, &lenum, sizeof(lenum)); lenum = cpu_to_le64(offset); low_crc = crc32c(low_crc, &lenum, sizeof(lenum)); return ((u64)high_crc << 31) ^ (u64)low_crc; } static u64 hash_extent_data_ref_item(const struct extent_buffer *leaf, const struct btrfs_extent_data_ref *ref) { return hash_extent_data_ref(btrfs_extent_data_ref_root(leaf, ref), btrfs_extent_data_ref_objectid(leaf, ref), btrfs_extent_data_ref_offset(leaf, ref)); } static bool match_extent_data_ref(const struct extent_buffer *leaf, const struct btrfs_extent_data_ref *ref, u64 root_objectid, u64 owner, u64 offset) { if (btrfs_extent_data_ref_root(leaf, ref) != root_objectid || btrfs_extent_data_ref_objectid(leaf, ref) != owner || btrfs_extent_data_ref_offset(leaf, ref) != offset) return false; return true; } static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid, u64 owner, u64 offset) { struct btrfs_root *root = btrfs_extent_root(trans->fs_info, bytenr); struct btrfs_key key; struct btrfs_extent_data_ref *ref; struct extent_buffer *leaf; u32 nritems; int recow; int ret; key.objectid = bytenr; if (parent) { key.type = BTRFS_SHARED_DATA_REF_KEY; key.offset = parent; } else { key.type = BTRFS_EXTENT_DATA_REF_KEY; key.offset = hash_extent_data_ref(root_objectid, owner, offset); } again: recow = 0; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) return ret; if (parent) { if (ret) return -ENOENT; return 0; } ret = -ENOENT; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); while (1) { if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) { if (ret > 0) return -ENOENT; return ret; } leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); recow = 1; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_DATA_REF_KEY) goto fail; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); if (match_extent_data_ref(leaf, ref, root_objectid, owner, offset)) { if (recow) { btrfs_release_path(path); goto again; } ret = 0; break; } path->slots[0]++; } fail: return ret; } static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_delayed_ref_node *node, u64 bytenr) { struct btrfs_root *root = btrfs_extent_root(trans->fs_info, bytenr); struct btrfs_key key; struct extent_buffer *leaf; u64 owner = btrfs_delayed_ref_owner(node); u64 offset = btrfs_delayed_ref_offset(node); u32 size; u32 num_refs; int ret; key.objectid = bytenr; if (node->parent) { key.type = BTRFS_SHARED_DATA_REF_KEY; key.offset = node->parent; size = sizeof(struct btrfs_shared_data_ref); } else { key.type = BTRFS_EXTENT_DATA_REF_KEY; key.offset = hash_extent_data_ref(node->ref_root, owner, offset); size = sizeof(struct btrfs_extent_data_ref); } ret = btrfs_insert_empty_item(trans, root, path, &key, size); if (ret && ret != -EEXIST) goto fail; leaf = path->nodes[0]; if (node->parent) { struct btrfs_shared_data_ref *ref; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_shared_data_ref); if (ret == 0) { btrfs_set_shared_data_ref_count(leaf, ref, node->ref_mod); } else { num_refs = btrfs_shared_data_ref_count(leaf, ref); num_refs += node->ref_mod; btrfs_set_shared_data_ref_count(leaf, ref, num_refs); } } else { struct btrfs_extent_data_ref *ref; while (ret == -EEXIST) { ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); if (match_extent_data_ref(leaf, ref, node->ref_root, owner, offset)) break; btrfs_release_path(path); key.offset++; ret = btrfs_insert_empty_item(trans, root, path, &key, size); if (ret && ret != -EEXIST) goto fail; leaf = path->nodes[0]; } ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); if (ret == 0) { btrfs_set_extent_data_ref_root(leaf, ref, node->ref_root); btrfs_set_extent_data_ref_objectid(leaf, ref, owner); btrfs_set_extent_data_ref_offset(leaf, ref, offset); btrfs_set_extent_data_ref_count(leaf, ref, node->ref_mod); } else { num_refs = btrfs_extent_data_ref_count(leaf, ref); num_refs += node->ref_mod; btrfs_set_extent_data_ref_count(leaf, ref, num_refs); } } ret = 0; fail: btrfs_release_path(path); return ret; } static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int refs_to_drop) { struct btrfs_key key; struct btrfs_extent_data_ref *ref1 = NULL; struct btrfs_shared_data_ref *ref2 = NULL; struct extent_buffer *leaf; u32 num_refs = 0; int ret = 0; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.type == BTRFS_EXTENT_DATA_REF_KEY) { ref1 = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); num_refs = btrfs_extent_data_ref_count(leaf, ref1); } else if (key.type == BTRFS_SHARED_DATA_REF_KEY) { ref2 = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_shared_data_ref); num_refs = btrfs_shared_data_ref_count(leaf, ref2); } else { btrfs_err(trans->fs_info, "unrecognized backref key (%llu %u %llu)", key.objectid, key.type, key.offset); btrfs_abort_transaction(trans, -EUCLEAN); return -EUCLEAN; } BUG_ON(num_refs < refs_to_drop); num_refs -= refs_to_drop; if (num_refs == 0) { ret = btrfs_del_item(trans, root, path); } else { if (key.type == BTRFS_EXTENT_DATA_REF_KEY) btrfs_set_extent_data_ref_count(leaf, ref1, num_refs); else if (key.type == BTRFS_SHARED_DATA_REF_KEY) btrfs_set_shared_data_ref_count(leaf, ref2, num_refs); } return ret; } static noinline u32 extent_data_ref_count(const struct btrfs_path *path, const struct btrfs_extent_inline_ref *iref) { struct btrfs_key key; struct extent_buffer *leaf; const struct btrfs_extent_data_ref *ref1; const struct btrfs_shared_data_ref *ref2; u32 num_refs = 0; int type; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (iref) { /* * If type is invalid, we should have bailed out earlier than * this call. */ type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); ASSERT(type != BTRFS_REF_TYPE_INVALID); if (type == BTRFS_EXTENT_DATA_REF_KEY) { ref1 = (const struct btrfs_extent_data_ref *)(&iref->offset); num_refs = btrfs_extent_data_ref_count(leaf, ref1); } else { ref2 = (const struct btrfs_shared_data_ref *)(iref + 1); num_refs = btrfs_shared_data_ref_count(leaf, ref2); } } else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) { ref1 = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_data_ref); num_refs = btrfs_extent_data_ref_count(leaf, ref1); } else if (key.type == BTRFS_SHARED_DATA_REF_KEY) { ref2 = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_shared_data_ref); num_refs = btrfs_shared_data_ref_count(leaf, ref2); } else { WARN_ON(1); } return num_refs; } static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans, struct btrfs_path *path, u64 bytenr, u64 parent, u64 root_objectid) { struct btrfs_root *root = btrfs_extent_root(trans->fs_info, bytenr); struct btrfs_key key; int ret; key.objectid = bytenr; if (parent) { key.type = BTRFS_SHARED_BLOCK_REF_KEY; key.offset = parent; } else { key.type = BTRFS_TREE_BLOCK_REF_KEY; key.offset = root_objectid; } ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) ret = -ENOENT; return ret; } static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_delayed_ref_node *node, u64 bytenr) { struct btrfs_root *root = btrfs_extent_root(trans->fs_info, bytenr); struct btrfs_key key; int ret; key.objectid = bytenr; if (node->parent) { key.type = BTRFS_SHARED_BLOCK_REF_KEY; key.offset = node->parent; } else { key.type = BTRFS_TREE_BLOCK_REF_KEY; key.offset = node->ref_root; } ret = btrfs_insert_empty_item(trans, root, path, &key, 0); btrfs_release_path(path); return ret; } static inline int extent_ref_type(u64 parent, u64 owner) { int type; if (owner < BTRFS_FIRST_FREE_OBJECTID) { if (parent > 0) type = BTRFS_SHARED_BLOCK_REF_KEY; else type = BTRFS_TREE_BLOCK_REF_KEY; } else { if (parent > 0) type = BTRFS_SHARED_DATA_REF_KEY; else type = BTRFS_EXTENT_DATA_REF_KEY; } return type; } static int find_next_key(const struct btrfs_path *path, int level, struct btrfs_key *key) { for (; level < BTRFS_MAX_LEVEL; level++) { if (!path->nodes[level]) break; if (path->slots[level] + 1 >= btrfs_header_nritems(path->nodes[level])) continue; if (level == 0) btrfs_item_key_to_cpu(path->nodes[level], key, path->slots[level] + 1); else btrfs_node_key_to_cpu(path->nodes[level], key, path->slots[level] + 1); return 0; } return 1; } /* * look for inline back ref. if back ref is found, *ref_ret is set * to the address of inline back ref, and 0 is returned. * * if back ref isn't found, *ref_ret is set to the address where it * should be inserted, and -ENOENT is returned. * * if insert is true and there are too many inline back refs, the path * points to the extent item, and -EAGAIN is returned. * * NOTE: inline back refs are ordered in the same way that back ref * items in the tree are ordered. */ static noinline_for_stack int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_extent_inline_ref **ref_ret, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset, int insert) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = btrfs_extent_root(fs_info, bytenr); struct btrfs_key key; struct extent_buffer *leaf; struct btrfs_extent_item *ei; struct btrfs_extent_inline_ref *iref; u64 flags; u64 item_size; unsigned long ptr; unsigned long end; int extra_size; int type; int want; int ret; bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA); int needed; key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = num_bytes; want = extent_ref_type(parent, owner); if (insert) { extra_size = btrfs_extent_inline_ref_size(want); path->search_for_extension = 1; } else extra_size = -1; /* * Owner is our level, so we can just add one to get the level for the * block we are interested in. */ if (skinny_metadata && owner < BTRFS_FIRST_FREE_OBJECTID) { key.type = BTRFS_METADATA_ITEM_KEY; key.offset = owner; } again: ret = btrfs_search_slot(trans, root, &key, path, extra_size, 1); if (ret < 0) goto out; /* * We may be a newly converted file system which still has the old fat * extent entries for metadata, so try and see if we have one of those. */ if (ret > 0 && skinny_metadata) { skinny_metadata = false; if (path->slots[0]) { path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid == bytenr && key.type == BTRFS_EXTENT_ITEM_KEY && key.offset == num_bytes) ret = 0; } if (ret) { key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = num_bytes; btrfs_release_path(path); goto again; } } if (ret && !insert) { ret = -ENOENT; goto out; } else if (WARN_ON(ret)) { btrfs_print_leaf(path->nodes[0]); btrfs_err(fs_info, "extent item not found for insert, bytenr %llu num_bytes %llu parent %llu root_objectid %llu owner %llu offset %llu", bytenr, num_bytes, parent, root_objectid, owner, offset); ret = -EUCLEAN; goto out; } leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); if (unlikely(item_size < sizeof(*ei))) { ret = -EUCLEAN; btrfs_err(fs_info, "unexpected extent item size, has %llu expect >= %zu", item_size, sizeof(*ei)); btrfs_abort_transaction(trans, ret); goto out; } ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); flags = btrfs_extent_flags(leaf, ei); ptr = (unsigned long)(ei + 1); end = (unsigned long)ei + item_size; if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK && !skinny_metadata) { ptr += sizeof(struct btrfs_tree_block_info); BUG_ON(ptr > end); } if (owner >= BTRFS_FIRST_FREE_OBJECTID) needed = BTRFS_REF_TYPE_DATA; else needed = BTRFS_REF_TYPE_BLOCK; ret = -ENOENT; while (ptr < end) { iref = (struct btrfs_extent_inline_ref *)ptr; type = btrfs_get_extent_inline_ref_type(leaf, iref, needed); if (type == BTRFS_EXTENT_OWNER_REF_KEY) { ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); ptr += btrfs_extent_inline_ref_size(type); continue; } if (unlikely(type == BTRFS_REF_TYPE_INVALID)) { ret = -EUCLEAN; goto out; } if (want < type) break; if (want > type) { ptr += btrfs_extent_inline_ref_size(type); continue; } if (type == BTRFS_EXTENT_DATA_REF_KEY) { struct btrfs_extent_data_ref *dref; dref = (struct btrfs_extent_data_ref *)(&iref->offset); if (match_extent_data_ref(leaf, dref, root_objectid, owner, offset)) { ret = 0; break; } if (hash_extent_data_ref_item(leaf, dref) < hash_extent_data_ref(root_objectid, owner, offset)) break; } else { u64 ref_offset; ref_offset = btrfs_extent_inline_ref_offset(leaf, iref); if (parent > 0) { if (parent == ref_offset) { ret = 0; break; } if (ref_offset < parent) break; } else { if (root_objectid == ref_offset) { ret = 0; break; } if (ref_offset < root_objectid) break; } } ptr += btrfs_extent_inline_ref_size(type); } if (unlikely(ptr > end)) { ret = -EUCLEAN; btrfs_print_leaf(path->nodes[0]); btrfs_crit(fs_info, "overrun extent record at slot %d while looking for inline extent for root %llu owner %llu offset %llu parent %llu", path->slots[0], root_objectid, owner, offset, parent); goto out; } if (ret == -ENOENT && insert) { if (item_size + extra_size >= BTRFS_MAX_EXTENT_ITEM_SIZE(root)) { ret = -EAGAIN; goto out; } if (path->slots[0] + 1 < btrfs_header_nritems(path->nodes[0])) { struct btrfs_key tmp_key; btrfs_item_key_to_cpu(path->nodes[0], &tmp_key, path->slots[0] + 1); if (tmp_key.objectid == bytenr && tmp_key.type < BTRFS_BLOCK_GROUP_ITEM_KEY) { ret = -EAGAIN; goto out; } goto out_no_entry; } if (!path->keep_locks) { btrfs_release_path(path); path->keep_locks = 1; goto again; } /* * To add new inline back ref, we have to make sure * there is no corresponding back ref item. * For simplicity, we just do not add new inline back * ref if there is any kind of item for this block */ if (find_next_key(path, 0, &key) == 0 && key.objectid == bytenr && key.type < BTRFS_BLOCK_GROUP_ITEM_KEY) { ret = -EAGAIN; goto out; } } out_no_entry: *ref_ret = (struct btrfs_extent_inline_ref *)ptr; out: if (path->keep_locks) { path->keep_locks = 0; btrfs_unlock_up_safe(path, 1); } if (insert) path->search_for_extension = 0; return ret; } /* * helper to add new inline back ref */ static noinline_for_stack void setup_inline_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, u64 parent, u64 root_objectid, u64 owner, u64 offset, int refs_to_add, struct btrfs_delayed_extent_op *extent_op) { struct extent_buffer *leaf; struct btrfs_extent_item *ei; unsigned long ptr; unsigned long end; unsigned long item_offset; u64 refs; int size; int type; leaf = path->nodes[0]; ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); item_offset = (unsigned long)iref - (unsigned long)ei; type = extent_ref_type(parent, owner); size = btrfs_extent_inline_ref_size(type); btrfs_extend_item(trans, path, size); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, ei); refs += refs_to_add; btrfs_set_extent_refs(leaf, ei, refs); if (extent_op) __run_delayed_extent_op(extent_op, leaf, ei); ptr = (unsigned long)ei + item_offset; end = (unsigned long)ei + btrfs_item_size(leaf, path->slots[0]); if (ptr < end - size) memmove_extent_buffer(leaf, ptr + size, ptr, end - size - ptr); iref = (struct btrfs_extent_inline_ref *)ptr; btrfs_set_extent_inline_ref_type(leaf, iref, type); if (type == BTRFS_EXTENT_DATA_REF_KEY) { struct btrfs_extent_data_ref *dref; dref = (struct btrfs_extent_data_ref *)(&iref->offset); btrfs_set_extent_data_ref_root(leaf, dref, root_objectid); btrfs_set_extent_data_ref_objectid(leaf, dref, owner); btrfs_set_extent_data_ref_offset(leaf, dref, offset); btrfs_set_extent_data_ref_count(leaf, dref, refs_to_add); } else if (type == BTRFS_SHARED_DATA_REF_KEY) { struct btrfs_shared_data_ref *sref; sref = (struct btrfs_shared_data_ref *)(iref + 1); btrfs_set_shared_data_ref_count(leaf, sref, refs_to_add); btrfs_set_extent_inline_ref_offset(leaf, iref, parent); } else if (type == BTRFS_SHARED_BLOCK_REF_KEY) { btrfs_set_extent_inline_ref_offset(leaf, iref, parent); } else { btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid); } } static int lookup_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_extent_inline_ref **ref_ret, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset) { int ret; ret = lookup_inline_extent_backref(trans, path, ref_ret, bytenr, num_bytes, parent, root_objectid, owner, offset, 0); if (ret != -ENOENT) return ret; btrfs_release_path(path); *ref_ret = NULL; if (owner < BTRFS_FIRST_FREE_OBJECTID) { ret = lookup_tree_block_ref(trans, path, bytenr, parent, root_objectid); } else { ret = lookup_extent_data_ref(trans, path, bytenr, parent, root_objectid, owner, offset); } return ret; } /* * helper to update/remove inline back ref */ static noinline_for_stack int update_inline_extent_backref( struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, int refs_to_mod, struct btrfs_delayed_extent_op *extent_op) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; struct btrfs_extent_data_ref *dref = NULL; struct btrfs_shared_data_ref *sref = NULL; unsigned long ptr; unsigned long end; u32 item_size; int size; int type; u64 refs; ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, ei); if (unlikely(refs_to_mod < 0 && refs + refs_to_mod <= 0)) { struct btrfs_key key; u32 extent_size; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.type == BTRFS_METADATA_ITEM_KEY) extent_size = fs_info->nodesize; else extent_size = key.offset; btrfs_print_leaf(leaf); btrfs_err(fs_info, "invalid refs_to_mod for extent %llu num_bytes %u, has %d expect >= -%llu", key.objectid, extent_size, refs_to_mod, refs); return -EUCLEAN; } refs += refs_to_mod; btrfs_set_extent_refs(leaf, ei, refs); if (extent_op) __run_delayed_extent_op(extent_op, leaf, ei); type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_ANY); /* * Function btrfs_get_extent_inline_ref_type() has already printed * error messages. */ if (unlikely(type == BTRFS_REF_TYPE_INVALID)) return -EUCLEAN; if (type == BTRFS_EXTENT_DATA_REF_KEY) { dref = (struct btrfs_extent_data_ref *)(&iref->offset); refs = btrfs_extent_data_ref_count(leaf, dref); } else if (type == BTRFS_SHARED_DATA_REF_KEY) { sref = (struct btrfs_shared_data_ref *)(iref + 1); refs = btrfs_shared_data_ref_count(leaf, sref); } else { refs = 1; /* * For tree blocks we can only drop one ref for it, and tree * blocks should not have refs > 1. * * Furthermore if we're inserting a new inline backref, we * won't reach this path either. That would be * setup_inline_extent_backref(). */ if (unlikely(refs_to_mod != -1)) { struct btrfs_key key; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); btrfs_print_leaf(leaf); btrfs_err(fs_info, "invalid refs_to_mod for tree block %llu, has %d expect -1", key.objectid, refs_to_mod); return -EUCLEAN; } } if (unlikely(refs_to_mod < 0 && refs < -refs_to_mod)) { struct btrfs_key key; u32 extent_size; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.type == BTRFS_METADATA_ITEM_KEY) extent_size = fs_info->nodesize; else extent_size = key.offset; btrfs_print_leaf(leaf); btrfs_err(fs_info, "invalid refs_to_mod for backref entry, iref %lu extent %llu num_bytes %u, has %d expect >= -%llu", (unsigned long)iref, key.objectid, extent_size, refs_to_mod, refs); return -EUCLEAN; } refs += refs_to_mod; if (refs > 0) { if (type == BTRFS_EXTENT_DATA_REF_KEY) btrfs_set_extent_data_ref_count(leaf, dref, refs); else btrfs_set_shared_data_ref_count(leaf, sref, refs); } else { size = btrfs_extent_inline_ref_size(type); item_size = btrfs_item_size(leaf, path->slots[0]); ptr = (unsigned long)iref; end = (unsigned long)ei + item_size; if (ptr + size < end) memmove_extent_buffer(leaf, ptr, ptr + size, end - ptr - size); item_size -= size; btrfs_truncate_item(trans, path, item_size, 1); } return 0; } static noinline_for_stack int insert_inline_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_path *path, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset, int refs_to_add, struct btrfs_delayed_extent_op *extent_op) { struct btrfs_extent_inline_ref *iref; int ret; ret = lookup_inline_extent_backref(trans, path, &iref, bytenr, num_bytes, parent, root_objectid, owner, offset, 1); if (ret == 0) { /* * We're adding refs to a tree block we already own, this * should not happen at all. */ if (unlikely(owner < BTRFS_FIRST_FREE_OBJECTID)) { btrfs_print_leaf(path->nodes[0]); btrfs_crit(trans->fs_info, "adding refs to an existing tree ref, bytenr %llu num_bytes %llu root_objectid %llu slot %u", bytenr, num_bytes, root_objectid, path->slots[0]); return -EUCLEAN; } ret = update_inline_extent_backref(trans, path, iref, refs_to_add, extent_op); } else if (ret == -ENOENT) { setup_inline_extent_backref(trans, path, iref, parent, root_objectid, owner, offset, refs_to_add, extent_op); ret = 0; } return ret; } static int remove_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, int refs_to_drop, int is_data) { int ret = 0; BUG_ON(!is_data && refs_to_drop != 1); if (iref) ret = update_inline_extent_backref(trans, path, iref, -refs_to_drop, NULL); else if (is_data) ret = remove_extent_data_ref(trans, root, path, refs_to_drop); else ret = btrfs_del_item(trans, root, path); return ret; } static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, u64 *discarded_bytes) { int j, ret = 0; u64 bytes_left, end; u64 aligned_start = ALIGN(start, SECTOR_SIZE); /* Adjust the range to be aligned to 512B sectors if necessary. */ if (start != aligned_start) { len -= aligned_start - start; len = round_down(len, SECTOR_SIZE); start = aligned_start; } *discarded_bytes = 0; if (!len) return 0; end = start + len; bytes_left = len; /* Skip any superblocks on this device. */ for (j = 0; j < BTRFS_SUPER_MIRROR_MAX; j++) { u64 sb_start = btrfs_sb_offset(j); u64 sb_end = sb_start + BTRFS_SUPER_INFO_SIZE; u64 size = sb_start - start; if (!in_range(sb_start, start, bytes_left) && !in_range(sb_end, start, bytes_left) && !in_range(start, sb_start, BTRFS_SUPER_INFO_SIZE)) continue; /* * Superblock spans beginning of range. Adjust start and * try again. */ if (sb_start <= start) { start += sb_end - start; if (start > end) { bytes_left = 0; break; } bytes_left = end - start; continue; } if (size) { ret = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, size >> SECTOR_SHIFT, GFP_NOFS); if (!ret) *discarded_bytes += size; else if (ret != -EOPNOTSUPP) return ret; } start = sb_end; if (start > end) { bytes_left = 0; break; } bytes_left = end - start; } while (bytes_left) { u64 bytes_to_discard = min(BTRFS_MAX_DISCARD_CHUNK_SIZE, bytes_left); ret = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, bytes_to_discard >> SECTOR_SHIFT, GFP_NOFS); if (ret) { if (ret != -EOPNOTSUPP) break; continue; } start += bytes_to_discard; bytes_left -= bytes_to_discard; *discarded_bytes += bytes_to_discard; if (btrfs_trim_interrupted()) { ret = -ERESTARTSYS; break; } } return ret; } static int do_discard_extent(struct btrfs_discard_stripe *stripe, u64 *bytes) { struct btrfs_device *dev = stripe->dev; struct btrfs_fs_info *fs_info = dev->fs_info; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; u64 phys = stripe->physical; u64 len = stripe->length; u64 discarded = 0; int ret = 0; /* Zone reset on a zoned filesystem */ if (btrfs_can_zone_reset(dev, phys, len)) { u64 src_disc; ret = btrfs_reset_device_zone(dev, phys, len, &discarded); if (ret) goto out; if (!btrfs_dev_replace_is_ongoing(dev_replace) || dev != dev_replace->srcdev) goto out; src_disc = discarded; /* Send to replace target as well */ ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len, &discarded); discarded += src_disc; } else if (bdev_max_discard_sectors(stripe->dev->bdev)) { ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded); } else { ret = 0; *bytes = 0; } out: *bytes = discarded; return ret; } int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 *actual_bytes) { int ret = 0; u64 discarded_bytes = 0; u64 end = bytenr + num_bytes; u64 cur = bytenr; /* * Avoid races with device replace and make sure the devices in the * stripes don't go away while we are discarding. */ btrfs_bio_counter_inc_blocked(fs_info); while (cur < end) { struct btrfs_discard_stripe *stripes; unsigned int num_stripes; int i; num_bytes = end - cur; stripes = btrfs_map_discard(fs_info, cur, &num_bytes, &num_stripes); if (IS_ERR(stripes)) { ret = PTR_ERR(stripes); if (ret == -EOPNOTSUPP) ret = 0; break; } for (i = 0; i < num_stripes; i++) { struct btrfs_discard_stripe *stripe = stripes + i; u64 bytes; if (!stripe->dev->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &stripe->dev->dev_state)) continue; ret = do_discard_extent(stripe, &bytes); if (ret) { /* * Keep going if discard is not supported by the * device. */ if (ret != -EOPNOTSUPP) break; ret = 0; } else { discarded_bytes += bytes; } } kfree(stripes); if (ret) break; cur += num_bytes; } btrfs_bio_counter_dec(fs_info); if (actual_bytes) *actual_bytes = discarded_bytes; return ret; } /* Can return -ENOMEM */ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; ASSERT(generic_ref->type != BTRFS_REF_NOT_SET && generic_ref->action); BUG_ON(generic_ref->type == BTRFS_REF_METADATA && generic_ref->ref_root == BTRFS_TREE_LOG_OBJECTID); if (generic_ref->type == BTRFS_REF_METADATA) ret = btrfs_add_delayed_tree_ref(trans, generic_ref, NULL); else ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0); btrfs_ref_tree_mod(fs_info, generic_ref); return ret; } /* * Insert backreference for a given extent. * * The counterpart is in __btrfs_free_extent(), with examples and more details * how it works. * * @trans: Handle of transaction * * @node: The delayed ref node used to get the bytenr/length for * extent whose references are incremented. * * @extent_op Pointer to a structure, holding information necessary when * updating a tree block's flags * */ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op) { BTRFS_PATH_AUTO_FREE(path); struct extent_buffer *leaf; struct btrfs_extent_item *item; struct btrfs_key key; u64 bytenr = node->bytenr; u64 num_bytes = node->num_bytes; u64 owner = btrfs_delayed_ref_owner(node); u64 offset = btrfs_delayed_ref_offset(node); u64 refs; int refs_to_add = node->ref_mod; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* this will setup the path even if it fails to insert the back ref */ ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes, node->parent, node->ref_root, owner, offset, refs_to_add, extent_op); if ((ret < 0 && ret != -EAGAIN) || !ret) return ret; /* * Ok we had -EAGAIN which means we didn't have space to insert and * inline extent ref, so just update the reference count and add a * normal backref. */ leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, item); btrfs_set_extent_refs(leaf, item, refs + refs_to_add); if (extent_op) __run_delayed_extent_op(extent_op, leaf, item); btrfs_release_path(path); /* now insert the actual backref */ if (owner < BTRFS_FIRST_FREE_OBJECTID) { ret = insert_tree_block_ref(trans, path, node, bytenr); if (ret) btrfs_abort_transaction(trans, ret); } else { ret = insert_extent_data_ref(trans, path, node, bytenr); if (ret) btrfs_abort_transaction(trans, ret); } return ret; } static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_head *href) { u64 root = href->owning_root; /* * Don't check must_insert_reserved, as this is called from contexts * where it has already been unset. */ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE || !href->is_data || !btrfs_is_fstree(root)) return; btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes, BTRFS_QGROUP_RSV_DATA); } static int run_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op, bool insert_reserved) { int ret = 0; u64 parent = 0; u64 flags = 0; trace_run_delayed_data_ref(trans->fs_info, node); if (node->type == BTRFS_SHARED_DATA_REF_KEY) parent = node->parent; if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { struct btrfs_key key; struct btrfs_squota_delta delta = { .root = href->owning_root, .num_bytes = node->num_bytes, .is_data = true, .is_inc = true, .generation = trans->transid, }; u64 owner = btrfs_delayed_ref_owner(node); u64 offset = btrfs_delayed_ref_offset(node); if (extent_op) flags |= extent_op->flags_to_set; key.objectid = node->bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = node->num_bytes; ret = alloc_reserved_file_extent(trans, parent, node->ref_root, flags, owner, offset, &key, node->ref_mod, href->owning_root); free_head_ref_squota_rsv(trans->fs_info, href); if (!ret) ret = btrfs_record_squota_delta(trans->fs_info, &delta); } else if (node->action == BTRFS_ADD_DELAYED_REF) { ret = __btrfs_inc_extent_ref(trans, node, extent_op); } else if (node->action == BTRFS_DROP_DELAYED_REF) { ret = __btrfs_free_extent(trans, href, node, extent_op); } else { BUG(); } return ret; } static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op, struct extent_buffer *leaf, struct btrfs_extent_item *ei) { u64 flags = btrfs_extent_flags(leaf, ei); if (extent_op->update_flags) { flags |= extent_op->flags_to_set; btrfs_set_extent_flags(leaf, ei, flags); } if (extent_op->update_key) { struct btrfs_tree_block_info *bi; BUG_ON(!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)); bi = (struct btrfs_tree_block_info *)(ei + 1); btrfs_set_tree_block_key(leaf, bi, &extent_op->key); } } static int run_delayed_extent_op(struct btrfs_trans_handle *trans, const struct btrfs_delayed_ref_head *head, struct btrfs_delayed_extent_op *extent_op) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root; struct btrfs_key key; BTRFS_PATH_AUTO_FREE(path); struct btrfs_extent_item *ei; struct extent_buffer *leaf; u32 item_size; int ret; int metadata = 1; if (TRANS_ABORTED(trans)) return 0; if (!btrfs_fs_incompat(fs_info, SKINNY_METADATA)) metadata = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = head->bytenr; if (metadata) { key.type = BTRFS_METADATA_ITEM_KEY; key.offset = head->level; } else { key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = head->num_bytes; } root = btrfs_extent_root(fs_info, key.objectid); again: ret = btrfs_search_slot(trans, root, &key, path, 0, 1); if (ret < 0) { return ret; } else if (ret > 0) { if (metadata) { if (path->slots[0] > 0) { path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid == head->bytenr && key.type == BTRFS_EXTENT_ITEM_KEY && key.offset == head->num_bytes) ret = 0; } if (ret > 0) { btrfs_release_path(path); metadata = 0; key.objectid = head->bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = head->num_bytes; goto again; } } else { ret = -EUCLEAN; btrfs_err(fs_info, "missing extent item for extent %llu num_bytes %llu level %d", head->bytenr, head->num_bytes, head->level); return ret; } } leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); if (unlikely(item_size < sizeof(*ei))) { ret = -EUCLEAN; btrfs_err(fs_info, "unexpected extent item size, has %u expect >= %zu", item_size, sizeof(*ei)); btrfs_abort_transaction(trans, ret); return ret; } ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); __run_delayed_extent_op(extent_op, leaf, ei); return ret; } static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op, bool insert_reserved) { int ret = 0; struct btrfs_fs_info *fs_info = trans->fs_info; u64 parent = 0; u64 ref_root = 0; trace_run_delayed_tree_ref(trans->fs_info, node); if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) parent = node->parent; ref_root = node->ref_root; if (unlikely(node->ref_mod != 1)) { btrfs_err(trans->fs_info, "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu", node->bytenr, node->ref_mod, node->action, ref_root, parent); return -EUCLEAN; } if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { struct btrfs_squota_delta delta = { .root = href->owning_root, .num_bytes = fs_info->nodesize, .is_data = false, .is_inc = true, .generation = trans->transid, }; ret = alloc_reserved_tree_block(trans, node, extent_op); if (!ret) btrfs_record_squota_delta(fs_info, &delta); } else if (node->action == BTRFS_ADD_DELAYED_REF) { ret = __btrfs_inc_extent_ref(trans, node, extent_op); } else if (node->action == BTRFS_DROP_DELAYED_REF) { ret = __btrfs_free_extent(trans, href, node, extent_op); } else { BUG(); } return ret; } /* helper function to actually process a single delayed ref entry */ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op, bool insert_reserved) { int ret = 0; if (TRANS_ABORTED(trans)) { if (insert_reserved) { btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1); free_head_ref_squota_rsv(trans->fs_info, href); } return 0; } if (node->type == BTRFS_TREE_BLOCK_REF_KEY || node->type == BTRFS_SHARED_BLOCK_REF_KEY) ret = run_delayed_tree_ref(trans, href, node, extent_op, insert_reserved); else if (node->type == BTRFS_EXTENT_DATA_REF_KEY || node->type == BTRFS_SHARED_DATA_REF_KEY) ret = run_delayed_data_ref(trans, href, node, extent_op, insert_reserved); else if (node->type == BTRFS_EXTENT_OWNER_REF_KEY) ret = 0; else BUG(); if (ret && insert_reserved) btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1); if (ret < 0) btrfs_err(trans->fs_info, "failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d", node->bytenr, node->num_bytes, node->type, node->action, node->ref_mod, ret); return ret; } static struct btrfs_delayed_extent_op *cleanup_extent_op( struct btrfs_delayed_ref_head *head) { struct btrfs_delayed_extent_op *extent_op = head->extent_op; if (!extent_op) return NULL; if (head->must_insert_reserved) { head->extent_op = NULL; btrfs_free_delayed_extent_op(extent_op); return NULL; } return extent_op; } static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head) { struct btrfs_delayed_extent_op *extent_op; int ret; extent_op = cleanup_extent_op(head); if (!extent_op) return 0; head->extent_op = NULL; spin_unlock(&head->lock); ret = run_delayed_extent_op(trans, head, extent_op); btrfs_free_delayed_extent_op(extent_op); return ret ? ret : 1; } u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_head *head) { u64 ret = 0; /* * We had csum deletions accounted for in our delayed refs rsv, we need * to drop the csum leaves for this update from our delayed_refs_rsv. */ if (head->total_ref_mod < 0 && head->is_data) { int nr_csums; spin_lock(&delayed_refs->lock); delayed_refs->pending_csums -= head->num_bytes; spin_unlock(&delayed_refs->lock); nr_csums = btrfs_csum_bytes_to_leaves(fs_info, head->num_bytes); btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums); ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums); } /* must_insert_reserved can be set only if we didn't run the head ref. */ if (head->must_insert_reserved) free_head_ref_squota_rsv(fs_info, head); return ret; } static int cleanup_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head, u64 *bytes_released) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_root *delayed_refs; int ret; delayed_refs = &trans->transaction->delayed_refs; ret = run_and_cleanup_extent_op(trans, head); if (ret < 0) { btrfs_unselect_ref_head(delayed_refs, head); btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret); return ret; } else if (ret) { return ret; } /* * Need to drop our head ref lock and re-acquire the delayed ref lock * and then re-check to make sure nobody got added. */ spin_unlock(&head->lock); spin_lock(&delayed_refs->lock); spin_lock(&head->lock); if (!RB_EMPTY_ROOT(&head->ref_tree.rb_root) || head->extent_op) { spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); return 1; } btrfs_delete_ref_head(fs_info, delayed_refs, head); spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); if (head->must_insert_reserved) { btrfs_pin_extent(trans, head->bytenr, head->num_bytes, 1); if (head->is_data) { struct btrfs_root *csum_root; csum_root = btrfs_csum_root(fs_info, head->bytenr); ret = btrfs_del_csums(trans, csum_root, head->bytenr, head->num_bytes); } } *bytes_released += btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); trace_run_delayed_ref_head(fs_info, head, 0); btrfs_delayed_ref_unlock(head); btrfs_put_delayed_ref_head(head); return ret; } static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *locked_ref, u64 *bytes_released) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_extent_op *extent_op; struct btrfs_delayed_ref_node *ref; bool must_insert_reserved; int ret; delayed_refs = &trans->transaction->delayed_refs; lockdep_assert_held(&locked_ref->mutex); lockdep_assert_held(&locked_ref->lock); while ((ref = btrfs_select_delayed_ref(locked_ref))) { if (ref->seq && btrfs_check_delayed_seq(fs_info, ref->seq)) { spin_unlock(&locked_ref->lock); btrfs_unselect_ref_head(delayed_refs, locked_ref); return -EAGAIN; } rb_erase_cached(&ref->ref_node, &locked_ref->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); /* * When we play the delayed ref, also correct the ref_mod on * head */ switch (ref->action) { case BTRFS_ADD_DELAYED_REF: case BTRFS_ADD_DELAYED_EXTENT: locked_ref->ref_mod -= ref->ref_mod; break; case BTRFS_DROP_DELAYED_REF: locked_ref->ref_mod += ref->ref_mod; break; default: WARN_ON(1); } /* * Record the must_insert_reserved flag before we drop the * spin lock. */ must_insert_reserved = locked_ref->must_insert_reserved; /* * Unsetting this on the head ref relinquishes ownership of * the rsv_bytes, so it is critical that every possible code * path from here forward frees all reserves including qgroup * reserve. */ locked_ref->must_insert_reserved = false; extent_op = locked_ref->extent_op; locked_ref->extent_op = NULL; spin_unlock(&locked_ref->lock); ret = run_one_delayed_ref(trans, locked_ref, ref, extent_op, must_insert_reserved); btrfs_delayed_refs_rsv_release(fs_info, 1, 0); *bytes_released += btrfs_calc_delayed_ref_bytes(fs_info, 1); btrfs_free_delayed_extent_op(extent_op); if (ret) { btrfs_unselect_ref_head(delayed_refs, locked_ref); btrfs_put_delayed_ref(ref); return ret; } btrfs_put_delayed_ref(ref); cond_resched(); spin_lock(&locked_ref->lock); btrfs_merge_delayed_refs(fs_info, delayed_refs, locked_ref); } return 0; } /* * Returns 0 on success or if called with an already aborted transaction. * Returns -ENOMEM or -EIO on failure and will abort the transaction. */ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, u64 min_bytes) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_head *locked_ref = NULL; int ret; unsigned long count = 0; unsigned long max_count = 0; u64 bytes_processed = 0; delayed_refs = &trans->transaction->delayed_refs; if (min_bytes == 0) { /* * We may be subject to a harmless race if some task is * concurrently adding or removing a delayed ref, so silence * KCSAN and similar tools. */ max_count = data_race(delayed_refs->num_heads_ready); min_bytes = U64_MAX; } do { if (!locked_ref) { locked_ref = btrfs_select_ref_head(fs_info, delayed_refs); if (IS_ERR_OR_NULL(locked_ref)) { if (PTR_ERR(locked_ref) == -EAGAIN) { continue; } else { break; } } count++; } /* * We need to try and merge add/drops of the same ref since we * can run into issues with relocate dropping the implicit ref * and then it being added back again before the drop can * finish. If we merged anything we need to re-loop so we can * get a good ref. * Or we can get node references of the same type that weren't * merged when created due to bumps in the tree mod seq, and * we need to merge them to prevent adding an inline extent * backref before dropping it (triggering a BUG_ON at * insert_inline_extent_backref()). */ spin_lock(&locked_ref->lock); btrfs_merge_delayed_refs(fs_info, delayed_refs, locked_ref); ret = btrfs_run_delayed_refs_for_head(trans, locked_ref, &bytes_processed); if (ret < 0 && ret != -EAGAIN) { /* * Error, btrfs_run_delayed_refs_for_head already * unlocked everything so just bail out */ return ret; } else if (!ret) { /* * Success, perform the usual cleanup of a processed * head */ ret = cleanup_ref_head(trans, locked_ref, &bytes_processed); if (ret > 0 ) { /* We dropped our lock, we need to loop. */ ret = 0; continue; } else if (ret) { return ret; } } /* * Either success case or btrfs_run_delayed_refs_for_head * returned -EAGAIN, meaning we need to select another head */ locked_ref = NULL; cond_resched(); } while ((min_bytes != U64_MAX && bytes_processed < min_bytes) || (max_count > 0 && count < max_count) || locked_ref); return 0; } #ifdef SCRAMBLE_DELAYED_REFS /* * Normally delayed refs get processed in ascending bytenr order. This * correlates in most cases to the order added. To expose dependencies on this * order, we start to process the tree in the middle instead of the beginning */ static u64 find_middle(struct rb_root *root) { struct rb_node *n = root->rb_node; struct btrfs_delayed_ref_node *entry; int alt = 1; u64 middle; u64 first = 0, last = 0; n = rb_first(root); if (n) { entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node); first = entry->bytenr; } n = rb_last(root); if (n) { entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node); last = entry->bytenr; } n = root->rb_node; while (n) { entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node); WARN_ON(!entry->in_tree); middle = entry->bytenr; if (alt) n = n->rb_left; else n = n->rb_right; alt = 1 - alt; } return middle; } #endif /* * Start processing the delayed reference count updates and extent insertions * we have queued up so far. * * @trans: Transaction handle. * @min_bytes: How many bytes of delayed references to process. After this * many bytes we stop processing delayed references if there are * any more. If 0 it means to run all existing delayed references, * but not new ones added after running all existing ones. * Use (u64)-1 (U64_MAX) to run all existing delayed references * plus any new ones that are added. * * Returns 0 on success or if called with an aborted transaction * Returns <0 on error and aborts the transaction */ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, u64 min_bytes) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_root *delayed_refs; int ret; /* We'll clean this up in btrfs_cleanup_transaction */ if (TRANS_ABORTED(trans)) return 0; if (test_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags)) return 0; delayed_refs = &trans->transaction->delayed_refs; again: #ifdef SCRAMBLE_DELAYED_REFS delayed_refs->run_delayed_start = find_middle(&delayed_refs->root); #endif ret = __btrfs_run_delayed_refs(trans, min_bytes); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } if (min_bytes == U64_MAX) { btrfs_create_pending_block_groups(trans); spin_lock(&delayed_refs->lock); if (xa_empty(&delayed_refs->head_refs)) { spin_unlock(&delayed_refs->lock); return 0; } spin_unlock(&delayed_refs->lock); cond_resched(); goto again; } return 0; } int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct extent_buffer *eb, u64 flags) { struct btrfs_delayed_extent_op *extent_op; int ret; extent_op = btrfs_alloc_delayed_extent_op(); if (!extent_op) return -ENOMEM; extent_op->flags_to_set = flags; extent_op->update_flags = true; extent_op->update_key = false; ret = btrfs_add_delayed_extent_op(trans, eb->start, eb->len, btrfs_header_level(eb), extent_op); if (ret) btrfs_free_delayed_extent_op(extent_op); return ret; } static noinline int check_delayed_ref(struct btrfs_inode *inode, struct btrfs_path *path, u64 offset, u64 bytenr) { struct btrfs_root *root = inode->root; struct btrfs_delayed_ref_head *head; struct btrfs_delayed_ref_node *ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_transaction *cur_trans; struct rb_node *node; int ret = 0; spin_lock(&root->fs_info->trans_lock); cur_trans = root->fs_info->running_transaction; if (cur_trans) refcount_inc(&cur_trans->use_count); spin_unlock(&root->fs_info->trans_lock); if (!cur_trans) return 0; delayed_refs = &cur_trans->delayed_refs; spin_lock(&delayed_refs->lock); head = btrfs_find_delayed_ref_head(root->fs_info, delayed_refs, bytenr); if (!head) { spin_unlock(&delayed_refs->lock); btrfs_put_transaction(cur_trans); return 0; } if (!mutex_trylock(&head->mutex)) { if (path->nowait) { spin_unlock(&delayed_refs->lock); btrfs_put_transaction(cur_trans); return -EAGAIN; } refcount_inc(&head->refs); spin_unlock(&delayed_refs->lock); btrfs_release_path(path); /* * Mutex was contended, block until it's released and let * caller try again */ mutex_lock(&head->mutex); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); btrfs_put_transaction(cur_trans); return -EAGAIN; } spin_unlock(&delayed_refs->lock); spin_lock(&head->lock); /* * XXX: We should replace this with a proper search function in the * future. */ for (node = rb_first_cached(&head->ref_tree); node; node = rb_next(node)) { u64 ref_owner; u64 ref_offset; ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); /* If it's a shared ref we know a cross reference exists */ if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) { ret = 1; break; } ref_owner = btrfs_delayed_ref_owner(ref); ref_offset = btrfs_delayed_ref_offset(ref); /* * If our ref doesn't match the one we're currently looking at * then we have a cross reference. */ if (ref->ref_root != btrfs_root_id(root) || ref_owner != btrfs_ino(inode) || ref_offset != offset) { ret = 1; break; } } spin_unlock(&head->lock); mutex_unlock(&head->mutex); btrfs_put_transaction(cur_trans); return ret; } /* * Check if there are references for a data extent other than the one belonging * to the given inode and offset. * * @inode: The only inode we expect to find associated with the data extent. * @path: A path to use for searching the extent tree. * @offset: The only offset we expect to find associated with the data extent. * @bytenr: The logical address of the data extent. * * When the extent does not have any other references other than the one we * expect to find, we always return a value of 0 with the path having a locked * leaf that contains the extent's extent item - this is necessary to ensure * we don't race with a task running delayed references, and our caller must * have such a path when calling check_delayed_ref() - it must lock a delayed * ref head while holding the leaf locked. In case the extent item is not found * in the extent tree, we return -ENOENT with the path having the leaf (locked) * where the extent item should be, in order to prevent races with another task * running delayed references, so that we don't miss any reference when calling * check_delayed_ref(). * * Note: this may return false positives, and this is because we want to be * quick here as we're called in write paths (when flushing delalloc and * in the direct IO write path). For example we can have an extent with * a single reference but that reference is not inlined, or we may have * many references in the extent tree but we also have delayed references * that cancel all the reference except the one for our inode and offset, * but it would be expensive to do such checks and complex due to all * locking to avoid races between the checks and flushing delayed refs, * plus non-inline references may be located on leaves other than the one * that contains the extent item in the extent tree. The important thing * here is to not return false negatives and that the false positives are * not very common. * * Returns: 0 if there are no cross references and with the path having a locked * leaf from the extent tree that contains the extent's extent item. * * 1 if there are cross references (false positives can happen). * * < 0 in case of an error. In case of -ENOENT the leaf in the extent * tree where the extent item should be located at is read locked and * accessible in the given path. */ static noinline int check_committed_ref(struct btrfs_inode *inode, struct btrfs_path *path, u64 offset, u64 bytenr) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *extent_root = btrfs_extent_root(fs_info, bytenr); struct extent_buffer *leaf; struct btrfs_extent_data_ref *ref; struct btrfs_extent_inline_ref *iref; struct btrfs_extent_item *ei; struct btrfs_key key; u32 item_size; u32 expected_size; int type; int ret; key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = (u64)-1; ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) return ret; if (unlikely(ret == 0)) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ return -EUCLEAN; } if (path->slots[0] == 0) return -ENOENT; path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != bytenr || key.type != BTRFS_EXTENT_ITEM_KEY) return -ENOENT; item_size = btrfs_item_size(leaf, path->slots[0]); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); expected_size = sizeof(*ei) + btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY); /* No inline refs; we need to bail before checking for owner ref. */ if (item_size == sizeof(*ei)) return 1; /* Check for an owner ref; skip over it to the real inline refs. */ iref = (struct btrfs_extent_inline_ref *)(ei + 1); type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); if (btrfs_fs_incompat(fs_info, SIMPLE_QUOTA) && type == BTRFS_EXTENT_OWNER_REF_KEY) { expected_size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY); iref = (struct btrfs_extent_inline_ref *)(iref + 1); type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); } /* If extent item has more than 1 inline ref then it's shared */ if (item_size != expected_size) return 1; /* If this extent has SHARED_DATA_REF then it's shared */ if (type != BTRFS_EXTENT_DATA_REF_KEY) return 1; ref = (struct btrfs_extent_data_ref *)(&iref->offset); if (btrfs_extent_refs(leaf, ei) != btrfs_extent_data_ref_count(leaf, ref) || btrfs_extent_data_ref_root(leaf, ref) != btrfs_root_id(root) || btrfs_extent_data_ref_objectid(leaf, ref) != btrfs_ino(inode) || btrfs_extent_data_ref_offset(leaf, ref) != offset) return 1; return 0; } int btrfs_cross_ref_exist(struct btrfs_inode *inode, u64 offset, u64 bytenr, struct btrfs_path *path) { int ret; do { ret = check_committed_ref(inode, path, offset, bytenr); if (ret && ret != -ENOENT) goto out; /* * The path must have a locked leaf from the extent tree where * the extent item for our extent is located, in case it exists, * or where it should be located in case it doesn't exist yet * because it's new and its delayed ref was not yet flushed. * We need to lock the delayed ref head at check_delayed_ref(), * if one exists, while holding the leaf locked in order to not * race with delayed ref flushing, missing references and * incorrectly reporting that the extent is not shared. */ if (IS_ENABLED(CONFIG_BTRFS_ASSERT)) { struct extent_buffer *leaf = path->nodes[0]; ASSERT(leaf != NULL); btrfs_assert_tree_read_locked(leaf); if (ret != -ENOENT) { struct btrfs_key key; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); ASSERT(key.objectid == bytenr); ASSERT(key.type == BTRFS_EXTENT_ITEM_KEY); } } ret = check_delayed_ref(inode, path, offset, bytenr); } while (ret == -EAGAIN && !path->nowait); out: btrfs_release_path(path); if (btrfs_is_data_reloc_root(inode->root)) WARN_ON(ret > 0); return ret; } static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, bool full_backref, bool inc) { struct btrfs_fs_info *fs_info = root->fs_info; u64 parent; u64 ref_root; u32 nritems; struct btrfs_key key; struct btrfs_file_extent_item *fi; bool for_reloc = btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC); int i; int action; int level; int ret = 0; if (btrfs_is_testing(fs_info)) return 0; ref_root = btrfs_header_owner(buf); nritems = btrfs_header_nritems(buf); level = btrfs_header_level(buf); if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && level == 0) return 0; if (full_backref) parent = buf->start; else parent = 0; if (inc) action = BTRFS_ADD_DELAYED_REF; else action = BTRFS_DROP_DELAYED_REF; for (i = 0; i < nritems; i++) { struct btrfs_ref ref = { .action = action, .parent = parent, .ref_root = ref_root, }; if (level == 0) { btrfs_item_key_to_cpu(buf, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; fi = btrfs_item_ptr(buf, i, struct btrfs_file_extent_item); if (btrfs_file_extent_type(buf, fi) == BTRFS_FILE_EXTENT_INLINE) continue; ref.bytenr = btrfs_file_extent_disk_bytenr(buf, fi); if (ref.bytenr == 0) continue; ref.num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi); ref.owning_root = ref_root; key.offset -= btrfs_file_extent_offset(buf, fi); btrfs_init_data_ref(&ref, key.objectid, key.offset, btrfs_root_id(root), for_reloc); if (inc) ret = btrfs_inc_extent_ref(trans, &ref); else ret = btrfs_free_extent(trans, &ref); if (ret) goto fail; } else { /* We don't know the owning_root, leave as 0. */ ref.bytenr = btrfs_node_blockptr(buf, i); ref.num_bytes = fs_info->nodesize; btrfs_init_tree_ref(&ref, level - 1, btrfs_root_id(root), for_reloc); if (inc) ret = btrfs_inc_extent_ref(trans, &ref); else ret = btrfs_free_extent(trans, &ref); if (ret) goto fail; } } return 0; fail: return ret; } int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, bool full_backref) { return __btrfs_mod_ref(trans, root, buf, full_backref, true); } int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, bool full_backref) { return __btrfs_mod_ref(trans, root, buf, full_backref, false); } static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data) { struct btrfs_fs_info *fs_info = root->fs_info; u64 flags; u64 ret; if (data) flags = BTRFS_BLOCK_GROUP_DATA; else if (root == fs_info->chunk_root) flags = BTRFS_BLOCK_GROUP_SYSTEM; else flags = BTRFS_BLOCK_GROUP_METADATA; ret = btrfs_get_alloc_profile(fs_info, flags); return ret; } static u64 first_logical_byte(struct btrfs_fs_info *fs_info) { struct rb_node *leftmost; u64 bytenr = 0; read_lock(&fs_info->block_group_cache_lock); /* Get the block group with the lowest logical start address. */ leftmost = rb_first_cached(&fs_info->block_group_cache_tree); if (leftmost) { struct btrfs_block_group *bg; bg = rb_entry(leftmost, struct btrfs_block_group, cache_node); bytenr = bg->start; } read_unlock(&fs_info->block_group_cache_lock); return bytenr; } static int pin_down_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache, u64 bytenr, u64 num_bytes, int reserved) { spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->pinned += num_bytes; btrfs_space_info_update_bytes_pinned(cache->space_info, num_bytes); if (reserved) { cache->reserved -= num_bytes; cache->space_info->bytes_reserved -= num_bytes; } spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); btrfs_set_extent_bit(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, EXTENT_DIRTY, NULL); return 0; } int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, int reserved) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(trans->fs_info, bytenr); BUG_ON(!cache); /* Logic error */ pin_down_extent(trans, cache, bytenr, num_bytes, reserved); btrfs_put_block_group(cache); return 0; } int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, const struct extent_buffer *eb) { struct btrfs_block_group *cache; int ret; cache = btrfs_lookup_block_group(trans->fs_info, eb->start); if (!cache) return -EINVAL; /* * Fully cache the free space first so that our pin removes the free space * from the cache. */ ret = btrfs_cache_block_group(cache, true); if (ret) goto out; pin_down_extent(trans, cache, eb->start, eb->len, 0); /* remove us from the free space cache (if we're there at all) */ ret = btrfs_remove_free_space(cache, eb->start, eb->len); out: btrfs_put_block_group(cache); return ret; } static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, u64 start, u64 num_bytes) { int ret; struct btrfs_block_group *block_group; block_group = btrfs_lookup_block_group(fs_info, start); if (!block_group) return -EINVAL; ret = btrfs_cache_block_group(block_group, true); if (ret) goto out; ret = btrfs_remove_free_space(block_group, start, num_bytes); out: btrfs_put_block_group(block_group); return ret; } int btrfs_exclude_logged_extents(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_file_extent_item *item; struct btrfs_key key; int found_type; int i; int ret = 0; if (!btrfs_fs_incompat(fs_info, MIXED_GROUPS)) return 0; for (i = 0; i < btrfs_header_nritems(eb); i++) { btrfs_item_key_to_cpu(eb, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; item = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item); found_type = btrfs_file_extent_type(eb, item); if (found_type == BTRFS_FILE_EXTENT_INLINE) continue; if (btrfs_file_extent_disk_bytenr(eb, item) == 0) continue; key.objectid = btrfs_file_extent_disk_bytenr(eb, item); key.offset = btrfs_file_extent_disk_num_bytes(eb, item); ret = __exclude_logged_extent(fs_info, key.objectid, key.offset); if (ret) break; } return ret; } static void btrfs_inc_block_group_reservations(struct btrfs_block_group *bg) { atomic_inc(&bg->reservations); } /* * Returns the free cluster for the given space info and sets empty_cluster to * what it should be based on the mount options. */ static struct btrfs_free_cluster * fetch_cluster_info(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 *empty_cluster) { struct btrfs_free_cluster *ret = NULL; *empty_cluster = 0; if (btrfs_mixed_space_info(space_info)) return ret; if (space_info->flags & BTRFS_BLOCK_GROUP_METADATA) { ret = &fs_info->meta_alloc_cluster; if (btrfs_test_opt(fs_info, SSD)) *empty_cluster = SZ_2M; else *empty_cluster = SZ_64K; } else if ((space_info->flags & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(fs_info, SSD_SPREAD)) { *empty_cluster = SZ_2M; ret = &fs_info->data_alloc_cluster; } return ret; } static int unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end, const bool return_free_space) { struct btrfs_block_group *cache = NULL; struct btrfs_space_info *space_info; struct btrfs_free_cluster *cluster = NULL; u64 total_unpinned = 0; u64 empty_cluster = 0; bool readonly; int ret = 0; while (start <= end) { u64 len; readonly = false; if (!cache || start >= cache->start + cache->length) { if (cache) btrfs_put_block_group(cache); total_unpinned = 0; cache = btrfs_lookup_block_group(fs_info, start); if (unlikely(cache == NULL)) { /* Logic error, something removed the block group. */ ret = -EUCLEAN; goto out; } cluster = fetch_cluster_info(fs_info, cache->space_info, &empty_cluster); empty_cluster <<= 1; } len = cache->start + cache->length - start; len = min(len, end + 1 - start); if (return_free_space) btrfs_add_free_space(cache, start, len); start += len; total_unpinned += len; space_info = cache->space_info; /* * If this space cluster has been marked as fragmented and we've * unpinned enough in this block group to potentially allow a * cluster to be created inside of it go ahead and clear the * fragmented check. */ if (cluster && cluster->fragmented && total_unpinned > empty_cluster) { spin_lock(&cluster->lock); cluster->fragmented = 0; spin_unlock(&cluster->lock); } spin_lock(&space_info->lock); spin_lock(&cache->lock); cache->pinned -= len; btrfs_space_info_update_bytes_pinned(space_info, -len); space_info->max_extent_size = 0; if (cache->ro) { space_info->bytes_readonly += len; readonly = true; } else if (btrfs_is_zoned(fs_info)) { /* Need reset before reusing in a zoned block group */ btrfs_space_info_update_bytes_zone_unusable(space_info, len); readonly = true; } spin_unlock(&cache->lock); if (!readonly && return_free_space) btrfs_return_free_space(space_info, len); spin_unlock(&space_info->lock); } if (cache) btrfs_put_block_group(cache); out: return ret; } int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *block_group, *tmp; struct list_head *deleted_bgs; struct extent_io_tree *unpin = &trans->transaction->pinned_extents; struct extent_state *cached_state = NULL; u64 start; u64 end; int unpin_error = 0; int ret; mutex_lock(&fs_info->unused_bg_unpin_mutex); btrfs_find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, &cached_state); while (!TRANS_ABORTED(trans) && cached_state) { struct extent_state *next_state; if (btrfs_test_opt(fs_info, DISCARD_SYNC)) ret = btrfs_discard_extent(fs_info, start, end + 1 - start, NULL); next_state = btrfs_next_extent_state(unpin, cached_state); btrfs_clear_extent_dirty(unpin, start, end, &cached_state); ret = unpin_extent_range(fs_info, start, end, true); /* * If we get an error unpinning an extent range, store the first * error to return later after trying to unpin all ranges and do * the sync discards. Our caller will abort the transaction * (which already wrote new superblocks) and on the next mount * the space will be available as it was pinned by in-memory * only structures in this phase. */ if (ret) { btrfs_err_rl(fs_info, "failed to unpin extent range [%llu, %llu] when committing transaction %llu: %s (%d)", start, end, trans->transid, btrfs_decode_error(ret), ret); if (!unpin_error) unpin_error = ret; } btrfs_free_extent_state(cached_state); if (need_resched()) { btrfs_free_extent_state(next_state); mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); cached_state = NULL; mutex_lock(&fs_info->unused_bg_unpin_mutex); btrfs_find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, &cached_state); } else { cached_state = next_state; if (cached_state) { start = cached_state->start; end = cached_state->end; } } } mutex_unlock(&fs_info->unused_bg_unpin_mutex); btrfs_free_extent_state(cached_state); if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) { btrfs_discard_calc_delay(&fs_info->discard_ctl); btrfs_discard_schedule_work(&fs_info->discard_ctl, true); } /* * Transaction is finished. We don't need the lock anymore. We * do need to clean up the block groups in case of a transaction * abort. */ deleted_bgs = &trans->transaction->deleted_bgs; list_for_each_entry_safe(block_group, tmp, deleted_bgs, bg_list) { ret = -EROFS; if (!TRANS_ABORTED(trans)) ret = btrfs_discard_extent(fs_info, block_group->start, block_group->length, NULL); /* * Not strictly necessary to lock, as the block_group should be * read-only from btrfs_delete_unused_bgs(). */ ASSERT(block_group->ro); spin_lock(&fs_info->unused_bgs_lock); list_del_init(&block_group->bg_list); spin_unlock(&fs_info->unused_bgs_lock); btrfs_unfreeze_block_group(block_group); btrfs_put_block_group(block_group); if (ret) { const char *errstr = btrfs_decode_error(ret); btrfs_warn(fs_info, "discard failed while removing blockgroup: errno=%d %s", ret, errstr); } } return unpin_error; } /* * Parse an extent item's inline extents looking for a simple quotas owner ref. * * @fs_info: the btrfs_fs_info for this mount * @leaf: a leaf in the extent tree containing the extent item * @slot: the slot in the leaf where the extent item is found * * Returns the objectid of the root that originally allocated the extent item * if the inline owner ref is expected and present, otherwise 0. * * If an extent item has an owner ref item, it will be the first inline ref * item. Therefore the logic is to check whether there are any inline ref * items, then check the type of the first one. */ u64 btrfs_get_extent_owner_root(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, int slot) { struct btrfs_extent_item *ei; struct btrfs_extent_inline_ref *iref; struct btrfs_extent_owner_ref *oref; unsigned long ptr; unsigned long end; int type; if (!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)) return 0; ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item); ptr = (unsigned long)(ei + 1); end = (unsigned long)ei + btrfs_item_size(leaf, slot); /* No inline ref items of any kind, can't check type. */ if (ptr == end) return 0; iref = (struct btrfs_extent_inline_ref *)ptr; type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_ANY); /* We found an owner ref, get the root out of it. */ if (type == BTRFS_EXTENT_OWNER_REF_KEY) { oref = (struct btrfs_extent_owner_ref *)(&iref->offset); return btrfs_extent_owner_ref_root_id(leaf, oref); } /* We have inline refs, but not an owner ref. */ return 0; } static int do_free_extent_accounting(struct btrfs_trans_handle *trans, u64 bytenr, struct btrfs_squota_delta *delta) { int ret; u64 num_bytes = delta->num_bytes; if (delta->is_data) { struct btrfs_root *csum_root; csum_root = btrfs_csum_root(trans->fs_info, bytenr); ret = btrfs_del_csums(trans, csum_root, bytenr, num_bytes); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_delete_raid_extent(trans, bytenr, num_bytes); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } } ret = btrfs_record_squota_delta(trans->fs_info, delta); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_add_to_free_space_tree(trans, bytenr, num_bytes); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_update_block_group(trans, bytenr, num_bytes, false); if (ret) btrfs_abort_transaction(trans, ret); return ret; } #define abort_and_dump(trans, path, fmt, args...) \ ({ \ btrfs_abort_transaction(trans, -EUCLEAN); \ btrfs_print_leaf(path->nodes[0]); \ btrfs_crit(trans->fs_info, fmt, ##args); \ }) /* * Drop one or more refs of @node. * * 1. Locate the extent refs. * It's either inline in EXTENT/METADATA_ITEM or in keyed SHARED_* item. * Locate it, then reduce the refs number or remove the ref line completely. * * 2. Update the refs count in EXTENT/METADATA_ITEM * * Inline backref case: * * in extent tree we have: * * item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 16201 itemsize 82 * refs 2 gen 6 flags DATA * extent data backref root FS_TREE objectid 258 offset 0 count 1 * extent data backref root FS_TREE objectid 257 offset 0 count 1 * * This function gets called with: * * node->bytenr = 13631488 * node->num_bytes = 1048576 * root_objectid = FS_TREE * owner_objectid = 257 * owner_offset = 0 * refs_to_drop = 1 * * Then we should get some like: * * item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 16201 itemsize 82 * refs 1 gen 6 flags DATA * extent data backref root FS_TREE objectid 258 offset 0 count 1 * * Keyed backref case: * * in extent tree we have: * * item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 3971 itemsize 24 * refs 754 gen 6 flags DATA * [...] * item 2 key (13631488 EXTENT_DATA_REF <HASH>) itemoff 3915 itemsize 28 * extent data backref root FS_TREE objectid 866 offset 0 count 1 * * This function get called with: * * node->bytenr = 13631488 * node->num_bytes = 1048576 * root_objectid = FS_TREE * owner_objectid = 866 * owner_offset = 0 * refs_to_drop = 1 * * Then we should get some like: * * item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 3971 itemsize 24 * refs 753 gen 6 flags DATA * * And that (13631488 EXTENT_DATA_REF <HASH>) gets removed. */ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *href, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op) { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_key key; struct btrfs_path *path; struct btrfs_root *extent_root; struct extent_buffer *leaf; struct btrfs_extent_item *ei; struct btrfs_extent_inline_ref *iref; int ret; int is_data; int extent_slot = 0; int found_extent = 0; int num_to_del = 1; int refs_to_drop = node->ref_mod; u32 item_size; u64 refs; u64 bytenr = node->bytenr; u64 num_bytes = node->num_bytes; u64 owner_objectid = btrfs_delayed_ref_owner(node); u64 owner_offset = btrfs_delayed_ref_offset(node); bool skinny_metadata = btrfs_fs_incompat(info, SKINNY_METADATA); u64 delayed_ref_root = href->owning_root; extent_root = btrfs_extent_root(info, bytenr); ASSERT(extent_root); path = btrfs_alloc_path(); if (!path) return -ENOMEM; is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID; if (unlikely(!is_data && refs_to_drop != 1)) { btrfs_crit(info, "invalid refs_to_drop, dropping more than 1 refs for tree block %llu refs_to_drop %u", node->bytenr, refs_to_drop); ret = -EINVAL; btrfs_abort_transaction(trans, ret); goto out; } if (is_data) skinny_metadata = false; ret = lookup_extent_backref(trans, path, &iref, bytenr, num_bytes, node->parent, node->ref_root, owner_objectid, owner_offset); if (ret == 0) { /* * Either the inline backref or the SHARED_DATA_REF/ * SHARED_BLOCK_REF is found * * Here is a quick path to locate EXTENT/METADATA_ITEM. * It's possible the EXTENT/METADATA_ITEM is near current slot. */ extent_slot = path->slots[0]; while (extent_slot >= 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, extent_slot); if (key.objectid != bytenr) break; if (key.type == BTRFS_EXTENT_ITEM_KEY && key.offset == num_bytes) { found_extent = 1; break; } if (key.type == BTRFS_METADATA_ITEM_KEY && key.offset == owner_objectid) { found_extent = 1; break; } /* Quick path didn't find the EXTENT/METADATA_ITEM */ if (path->slots[0] - extent_slot > 5) break; extent_slot--; } if (!found_extent) { if (unlikely(iref)) { abort_and_dump(trans, path, "invalid iref slot %u, no EXTENT/METADATA_ITEM found but has inline extent ref", path->slots[0]); ret = -EUCLEAN; goto out; } /* Must be SHARED_* item, remove the backref first */ ret = remove_extent_backref(trans, extent_root, path, NULL, refs_to_drop, is_data); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_release_path(path); /* Slow path to locate EXTENT/METADATA_ITEM */ key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = num_bytes; if (!is_data && skinny_metadata) { key.type = BTRFS_METADATA_ITEM_KEY; key.offset = owner_objectid; } ret = btrfs_search_slot(trans, extent_root, &key, path, -1, 1); if (ret > 0 && skinny_metadata && path->slots[0]) { /* * Couldn't find our skinny metadata item, * see if we have ye olde extent item. */ path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid == bytenr && key.type == BTRFS_EXTENT_ITEM_KEY && key.offset == num_bytes) ret = 0; } if (ret > 0 && skinny_metadata) { skinny_metadata = false; key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = num_bytes; btrfs_release_path(path); ret = btrfs_search_slot(trans, extent_root, &key, path, -1, 1); } if (ret) { if (ret > 0) btrfs_print_leaf(path->nodes[0]); btrfs_err(info, "umm, got %d back from search, was looking for %llu, slot %d", ret, bytenr, path->slots[0]); } if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out; } extent_slot = path->slots[0]; } } else if (WARN_ON(ret == -ENOENT)) { abort_and_dump(trans, path, "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu slot %d", bytenr, node->parent, node->ref_root, owner_objectid, owner_offset, path->slots[0]); goto out; } else { btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, extent_slot); if (unlikely(item_size < sizeof(*ei))) { ret = -EUCLEAN; btrfs_err(trans->fs_info, "unexpected extent item size, has %u expect >= %zu", item_size, sizeof(*ei)); btrfs_abort_transaction(trans, ret); goto out; } ei = btrfs_item_ptr(leaf, extent_slot, struct btrfs_extent_item); if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID && key.type == BTRFS_EXTENT_ITEM_KEY) { struct btrfs_tree_block_info *bi; if (unlikely(item_size < sizeof(*ei) + sizeof(*bi))) { abort_and_dump(trans, path, "invalid extent item size for key (%llu, %u, %llu) slot %u owner %llu, has %u expect >= %zu", key.objectid, key.type, key.offset, path->slots[0], owner_objectid, item_size, sizeof(*ei) + sizeof(*bi)); ret = -EUCLEAN; goto out; } bi = (struct btrfs_tree_block_info *)(ei + 1); WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi)); } refs = btrfs_extent_refs(leaf, ei); if (unlikely(refs < refs_to_drop)) { abort_and_dump(trans, path, "trying to drop %d refs but we only have %llu for bytenr %llu slot %u", refs_to_drop, refs, bytenr, path->slots[0]); ret = -EUCLEAN; goto out; } refs -= refs_to_drop; if (refs > 0) { if (extent_op) __run_delayed_extent_op(extent_op, leaf, ei); /* * In the case of inline back ref, reference count will * be updated by remove_extent_backref */ if (iref) { if (unlikely(!found_extent)) { abort_and_dump(trans, path, "invalid iref, got inlined extent ref but no EXTENT/METADATA_ITEM found, slot %u", path->slots[0]); ret = -EUCLEAN; goto out; } } else { btrfs_set_extent_refs(leaf, ei, refs); } if (found_extent) { ret = remove_extent_backref(trans, extent_root, path, iref, refs_to_drop, is_data); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } } } else { struct btrfs_squota_delta delta = { .root = delayed_ref_root, .num_bytes = num_bytes, .is_data = is_data, .is_inc = false, .generation = btrfs_extent_generation(leaf, ei), }; /* In this branch refs == 1 */ if (found_extent) { if (unlikely(is_data && refs_to_drop != extent_data_ref_count(path, iref))) { abort_and_dump(trans, path, "invalid refs_to_drop, current refs %u refs_to_drop %u slot %u", extent_data_ref_count(path, iref), refs_to_drop, path->slots[0]); ret = -EUCLEAN; goto out; } if (iref) { if (unlikely(path->slots[0] != extent_slot)) { abort_and_dump(trans, path, "invalid iref, extent item key (%llu %u %llu) slot %u doesn't have wanted iref", key.objectid, key.type, key.offset, path->slots[0]); ret = -EUCLEAN; goto out; } } else { /* * No inline ref, we must be at SHARED_* item, * And it's single ref, it must be: * | extent_slot ||extent_slot + 1| * [ EXTENT/METADATA_ITEM ][ SHARED_* ITEM ] */ if (unlikely(path->slots[0] != extent_slot + 1)) { abort_and_dump(trans, path, "invalid SHARED_* item slot %u, previous item is not EXTENT/METADATA_ITEM", path->slots[0]); ret = -EUCLEAN; goto out; } path->slots[0] = extent_slot; num_to_del = 2; } } /* * We can't infer the data owner from the delayed ref, so we need * to try to get it from the owning ref item. * * If it is not present, then that extent was not written under * simple quotas mode, so we don't need to account for its deletion. */ if (is_data) delta.root = btrfs_get_extent_owner_root(trans->fs_info, leaf, extent_slot); ret = btrfs_del_items(trans, extent_root, path, path->slots[0], num_to_del); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_release_path(path); ret = do_free_extent_accounting(trans, bytenr, &delta); } btrfs_release_path(path); out: btrfs_free_path(path); return ret; } /* * when we free an block, it is possible (and likely) that we free the last * delayed ref for that extent as well. This searches the delayed ref tree for * a given extent, and if there are no other delayed refs to be processed, it * removes it from the tree. */ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, u64 bytenr) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_head *head; struct btrfs_delayed_ref_root *delayed_refs; int ret = 0; delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); head = btrfs_find_delayed_ref_head(fs_info, delayed_refs, bytenr); if (!head) goto out_delayed_unlock; spin_lock(&head->lock); if (!RB_EMPTY_ROOT(&head->ref_tree.rb_root)) goto out; if (cleanup_extent_op(head) != NULL) goto out; /* * waiting for the lock here would deadlock. If someone else has it * locked they are already in the process of dropping it anyway */ if (!mutex_trylock(&head->mutex)) goto out; btrfs_delete_ref_head(fs_info, delayed_refs, head); head->processing = false; spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); BUG_ON(head->extent_op); if (head->must_insert_reserved) ret = 1; btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); return ret; out: spin_unlock(&head->lock); out_delayed_unlock: spin_unlock(&delayed_refs->lock); return 0; } int btrfs_free_tree_block(struct btrfs_trans_handle *trans, u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_block_group *bg; int ret; if (root_id != BTRFS_TREE_LOG_OBJECTID) { struct btrfs_ref generic_ref = { .action = BTRFS_DROP_DELAYED_REF, .bytenr = buf->start, .num_bytes = buf->len, .parent = parent, .owning_root = btrfs_header_owner(buf), .ref_root = root_id, }; /* * Assert that the extent buffer is not cleared due to * EXTENT_BUFFER_ZONED_ZEROOUT. Please refer * btrfs_clear_buffer_dirty() and btree_csum_one_bio() for * detail. */ ASSERT(btrfs_header_bytenr(buf) != 0); btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), 0, false); btrfs_ref_tree_mod(fs_info, &generic_ref); ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); if (ret < 0) return ret; } if (!last_ref) return 0; if (btrfs_header_generation(buf) != trans->transid) goto out; if (root_id != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); if (!ret) goto out; } bg = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { pin_down_extent(trans, bg, buf->start, buf->len, 1); btrfs_put_block_group(bg); goto out; } /* * If there are tree mod log users we may have recorded mod log * operations for this node. If we re-allocate this node we * could replay operations on this node that happened when it * existed in a completely different root. For example if it * was part of root A, then was reallocated to root B, and we * are doing a btrfs_old_search_slot(root b), we could replay * operations that happened when the block was part of root A, * giving us an inconsistent view of the btree. * * We are safe from races here because at this point no other * node or root points to this extent buffer, so if after this * check a new tree mod log user joins we will not have an * existing log of operations on this node that we have to * contend with. */ if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags) || btrfs_is_zoned(fs_info)) { pin_down_extent(trans, bg, buf->start, buf->len, 1); btrfs_put_block_group(bg); goto out; } WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(bg, buf->start, buf->len); btrfs_free_reserved_bytes(bg, buf->len, false); btrfs_put_block_group(bg); trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); out: return 0; } /* Can return -ENOMEM */ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; if (btrfs_is_testing(fs_info)) return 0; /* * tree log blocks never actually go into the extent allocation * tree, just update pinning info and exit early. */ if (ref->ref_root == BTRFS_TREE_LOG_OBJECTID) { btrfs_pin_extent(trans, ref->bytenr, ref->num_bytes, 1); ret = 0; } else if (ref->type == BTRFS_REF_METADATA) { ret = btrfs_add_delayed_tree_ref(trans, ref, NULL); } else { ret = btrfs_add_delayed_data_ref(trans, ref, 0); } if (ref->ref_root != BTRFS_TREE_LOG_OBJECTID) btrfs_ref_tree_mod(fs_info, ref); return ret; } enum btrfs_loop_type { /* * Start caching block groups but do not wait for progress or for them * to be done. */ LOOP_CACHING_NOWAIT, /* * Wait for the block group free_space >= the space we're waiting for if * the block group isn't cached. */ LOOP_CACHING_WAIT, /* * Allow allocations to happen from block groups that do not yet have a * size classification. */ LOOP_UNSET_SIZE_CLASS, /* * Allocate a chunk and then retry the allocation. */ LOOP_ALLOC_CHUNK, /* * Ignore the size class restrictions for this allocation. */ LOOP_WRONG_SIZE_CLASS, /* * Ignore the empty size, only try to allocate the number of bytes * needed for this allocation. */ LOOP_NO_EMPTY_SIZE, }; static inline void btrfs_lock_block_group(struct btrfs_block_group *cache, int delalloc) { if (delalloc) down_read(&cache->data_rwsem); } static inline void btrfs_grab_block_group(struct btrfs_block_group *cache, int delalloc) { btrfs_get_block_group(cache); if (delalloc) down_read(&cache->data_rwsem); } static struct btrfs_block_group *btrfs_lock_cluster( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, int delalloc) __acquires(&cluster->refill_lock) { struct btrfs_block_group *used_bg = NULL; spin_lock(&cluster->refill_lock); while (1) { used_bg = cluster->block_group; if (!used_bg) return NULL; if (used_bg == block_group) return used_bg; btrfs_get_block_group(used_bg); if (!delalloc) return used_bg; if (down_read_trylock(&used_bg->data_rwsem)) return used_bg; spin_unlock(&cluster->refill_lock); /* We should only have one-level nested. */ down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING); spin_lock(&cluster->refill_lock); if (used_bg == cluster->block_group) return used_bg; up_read(&used_bg->data_rwsem); btrfs_put_block_group(used_bg); } } static inline void btrfs_release_block_group(struct btrfs_block_group *cache, int delalloc) { if (delalloc) up_read(&cache->data_rwsem); btrfs_put_block_group(cache); } static bool find_free_extent_check_size_class(const struct find_free_extent_ctl *ffe_ctl, const struct btrfs_block_group *bg) { if (ffe_ctl->policy == BTRFS_EXTENT_ALLOC_ZONED) return true; if (!btrfs_block_group_should_use_size_class(bg)) return true; if (ffe_ctl->loop >= LOOP_WRONG_SIZE_CLASS) return true; if (ffe_ctl->loop >= LOOP_UNSET_SIZE_CLASS && bg->size_class == BTRFS_BG_SZ_NONE) return true; return ffe_ctl->size_class == bg->size_class; } /* * Helper function for find_free_extent(). * * Return -ENOENT to inform caller that we need fallback to unclustered mode. * Return >0 to inform caller that we find nothing * Return 0 means we have found a location and set ffe_ctl->found_offset. */ static int find_free_extent_clustered(struct btrfs_block_group *bg, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **cluster_bg_ret) { struct btrfs_block_group *cluster_bg; struct btrfs_free_cluster *last_ptr = ffe_ctl->last_ptr; u64 aligned_cluster; u64 offset; int ret; cluster_bg = btrfs_lock_cluster(bg, last_ptr, ffe_ctl->delalloc); if (!cluster_bg) goto refill_cluster; if (cluster_bg != bg && (cluster_bg->ro || !block_group_bits(cluster_bg, ffe_ctl->flags) || !find_free_extent_check_size_class(ffe_ctl, cluster_bg))) goto release_cluster; offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr, ffe_ctl->num_bytes, cluster_bg->start, &ffe_ctl->max_extent_size); if (offset) { /* We have a block, we're done */ spin_unlock(&last_ptr->refill_lock); trace_btrfs_reserve_extent_cluster(cluster_bg, ffe_ctl); *cluster_bg_ret = cluster_bg; ffe_ctl->found_offset = offset; return 0; } WARN_ON(last_ptr->block_group != cluster_bg); release_cluster: /* * If we are on LOOP_NO_EMPTY_SIZE, we can't set up a new clusters, so * lets just skip it and let the allocator find whatever block it can * find. If we reach this point, we will have tried the cluster * allocator plenty of times and not have found anything, so we are * likely way too fragmented for the clustering stuff to find anything. * * However, if the cluster is taken from the current block group, * release the cluster first, so that we stand a better chance of * succeeding in the unclustered allocation. */ if (ffe_ctl->loop >= LOOP_NO_EMPTY_SIZE && cluster_bg != bg) { spin_unlock(&last_ptr->refill_lock); btrfs_release_block_group(cluster_bg, ffe_ctl->delalloc); return -ENOENT; } /* This cluster didn't work out, free it and start over */ btrfs_return_cluster_to_free_space(NULL, last_ptr); if (cluster_bg != bg) btrfs_release_block_group(cluster_bg, ffe_ctl->delalloc); refill_cluster: if (ffe_ctl->loop >= LOOP_NO_EMPTY_SIZE) { spin_unlock(&last_ptr->refill_lock); return -ENOENT; } aligned_cluster = max_t(u64, ffe_ctl->empty_cluster + ffe_ctl->empty_size, bg->full_stripe_len); ret = btrfs_find_space_cluster(bg, last_ptr, ffe_ctl->search_start, ffe_ctl->num_bytes, aligned_cluster); if (ret == 0) { /* Now pull our allocation out of this cluster */ offset = btrfs_alloc_from_cluster(bg, last_ptr, ffe_ctl->num_bytes, ffe_ctl->search_start, &ffe_ctl->max_extent_size); if (offset) { /* We found one, proceed */ spin_unlock(&last_ptr->refill_lock); ffe_ctl->found_offset = offset; trace_btrfs_reserve_extent_cluster(bg, ffe_ctl); return 0; } } /* * At this point we either didn't find a cluster or we weren't able to * allocate a block from our cluster. Free the cluster we've been * trying to use, and go to the next block group. */ btrfs_return_cluster_to_free_space(NULL, last_ptr); spin_unlock(&last_ptr->refill_lock); return 1; } /* * Return >0 to inform caller that we find nothing * Return 0 when we found an free extent and set ffe_ctrl->found_offset */ static int find_free_extent_unclustered(struct btrfs_block_group *bg, struct find_free_extent_ctl *ffe_ctl) { struct btrfs_free_cluster *last_ptr = ffe_ctl->last_ptr; u64 offset; /* * We are doing an unclustered allocation, set the fragmented flag so * we don't bother trying to setup a cluster again until we get more * space. */ if (unlikely(last_ptr)) { spin_lock(&last_ptr->lock); last_ptr->fragmented = 1; spin_unlock(&last_ptr->lock); } if (ffe_ctl->cached) { struct btrfs_free_space_ctl *free_space_ctl; free_space_ctl = bg->free_space_ctl; spin_lock(&free_space_ctl->tree_lock); if (free_space_ctl->free_space < ffe_ctl->num_bytes + ffe_ctl->empty_cluster + ffe_ctl->empty_size) { ffe_ctl->total_free_space = max_t(u64, ffe_ctl->total_free_space, free_space_ctl->free_space); spin_unlock(&free_space_ctl->tree_lock); return 1; } spin_unlock(&free_space_ctl->tree_lock); } offset = btrfs_find_space_for_alloc(bg, ffe_ctl->search_start, ffe_ctl->num_bytes, ffe_ctl->empty_size, &ffe_ctl->max_extent_size); if (!offset) return 1; ffe_ctl->found_offset = offset; return 0; } static int do_allocation_clustered(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **bg_ret) { int ret; /* We want to try and use the cluster allocator, so lets look there */ if (ffe_ctl->last_ptr && ffe_ctl->use_cluster) { ret = find_free_extent_clustered(block_group, ffe_ctl, bg_ret); if (ret >= 0) return ret; /* ret == -ENOENT case falls through */ } return find_free_extent_unclustered(block_group, ffe_ctl); } /* * Tree-log block group locking * ============================ * * fs_info::treelog_bg_lock protects the fs_info::treelog_bg which * indicates the starting address of a block group, which is reserved only * for tree-log metadata. * * Lock nesting * ============ * * space_info::lock * block_group::lock * fs_info::treelog_bg_lock */ /* * Simple allocator for sequential-only block group. It only allows sequential * allocation. No need to play with trees. This function also reserves the * bytes as in btrfs_add_reserved_bytes. */ static int do_allocation_zoned(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **bg_ret) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_space_info *space_info = block_group->space_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; u64 start = block_group->start; u64 num_bytes = ffe_ctl->num_bytes; u64 avail; u64 bytenr = block_group->start; u64 log_bytenr; u64 data_reloc_bytenr; int ret = 0; bool skip = false; ASSERT(btrfs_is_zoned(block_group->fs_info)); /* * Do not allow non-tree-log blocks in the dedicated tree-log block * group, and vice versa. */ spin_lock(&fs_info->treelog_bg_lock); log_bytenr = fs_info->treelog_bg; if (log_bytenr && ((ffe_ctl->for_treelog && bytenr != log_bytenr) || (!ffe_ctl->for_treelog && bytenr == log_bytenr))) skip = true; spin_unlock(&fs_info->treelog_bg_lock); if (skip) return 1; /* * Do not allow non-relocation blocks in the dedicated relocation block * group, and vice versa. */ spin_lock(&fs_info->relocation_bg_lock); data_reloc_bytenr = fs_info->data_reloc_bg; if (data_reloc_bytenr && ((ffe_ctl->for_data_reloc && bytenr != data_reloc_bytenr) || (!ffe_ctl->for_data_reloc && bytenr == data_reloc_bytenr))) skip = true; spin_unlock(&fs_info->relocation_bg_lock); if (skip) return 1; /* Check RO and no space case before trying to activate it */ spin_lock(&block_group->lock); if (block_group->ro || btrfs_zoned_bg_is_full(block_group)) { ret = 1; /* * May need to clear fs_info->{treelog,data_reloc}_bg. * Return the error after taking the locks. */ } spin_unlock(&block_group->lock); /* Metadata block group is activated at write time. */ if (!ret && (block_group->flags & BTRFS_BLOCK_GROUP_DATA) && !btrfs_zone_activate(block_group)) { ret = 1; /* * May need to clear fs_info->{treelog,data_reloc}_bg. * Return the error after taking the locks. */ } spin_lock(&space_info->lock); spin_lock(&block_group->lock); spin_lock(&fs_info->treelog_bg_lock); spin_lock(&fs_info->relocation_bg_lock); if (ret) goto out; ASSERT(!ffe_ctl->for_treelog || block_group->start == fs_info->treelog_bg || fs_info->treelog_bg == 0); ASSERT(!ffe_ctl->for_data_reloc || block_group->start == fs_info->data_reloc_bg || fs_info->data_reloc_bg == 0); if (block_group->ro || (!ffe_ctl->for_data_reloc && test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags))) { ret = 1; goto out; } /* * Do not allow currently using block group to be tree-log dedicated * block group. */ if (ffe_ctl->for_treelog && !fs_info->treelog_bg && (block_group->used || block_group->reserved)) { ret = 1; goto out; } /* * Do not allow currently used block group to be the data relocation * dedicated block group. */ if (ffe_ctl->for_data_reloc && !fs_info->data_reloc_bg && (block_group->used || block_group->reserved)) { ret = 1; goto out; } WARN_ON_ONCE(block_group->alloc_offset > block_group->zone_capacity); avail = block_group->zone_capacity - block_group->alloc_offset; if (avail < num_bytes) { if (ffe_ctl->max_extent_size < avail) { /* * With sequential allocator, free space is always * contiguous */ ffe_ctl->max_extent_size = avail; ffe_ctl->total_free_space = avail; } ret = 1; goto out; } if (ffe_ctl->for_treelog && !fs_info->treelog_bg) fs_info->treelog_bg = block_group->start; if (ffe_ctl->for_data_reloc) { if (!fs_info->data_reloc_bg) fs_info->data_reloc_bg = block_group->start; /* * Do not allow allocations from this block group, unless it is * for data relocation. Compared to increasing the ->ro, setting * the ->zoned_data_reloc_ongoing flag still allows nocow * writers to come in. See btrfs_inc_nocow_writers(). * * We need to disable an allocation to avoid an allocation of * regular (non-relocation data) extent. With mix of relocation * extents and regular extents, we can dispatch WRITE commands * (for relocation extents) and ZONE APPEND commands (for * regular extents) at the same time to the same zone, which * easily break the write pointer. * * Also, this flag avoids this block group to be zone finished. */ set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags); } ffe_ctl->found_offset = start + block_group->alloc_offset; block_group->alloc_offset += num_bytes; spin_lock(&ctl->tree_lock); ctl->free_space -= num_bytes; spin_unlock(&ctl->tree_lock); /* * We do not check if found_offset is aligned to stripesize. The * address is anyway rewritten when using zone append writing. */ ffe_ctl->search_start = ffe_ctl->found_offset; out: if (ret && ffe_ctl->for_treelog) fs_info->treelog_bg = 0; if (ret && ffe_ctl->for_data_reloc) fs_info->data_reloc_bg = 0; spin_unlock(&fs_info->relocation_bg_lock); spin_unlock(&fs_info->treelog_bg_lock); spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); return ret; } static int do_allocation(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **bg_ret) { switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: return do_allocation_clustered(block_group, ffe_ctl, bg_ret); case BTRFS_EXTENT_ALLOC_ZONED: return do_allocation_zoned(block_group, ffe_ctl, bg_ret); default: BUG(); } } static void release_block_group(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, int delalloc) { switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: ffe_ctl->retry_uncached = false; break; case BTRFS_EXTENT_ALLOC_ZONED: /* Nothing to do */ break; default: BUG(); } BUG_ON(btrfs_bg_flags_to_raid_index(block_group->flags) != ffe_ctl->index); btrfs_release_block_group(block_group, delalloc); } static void found_extent_clustered(struct find_free_extent_ctl *ffe_ctl, struct btrfs_key *ins) { struct btrfs_free_cluster *last_ptr = ffe_ctl->last_ptr; if (!ffe_ctl->use_cluster && last_ptr) { spin_lock(&last_ptr->lock); last_ptr->window_start = ins->objectid; spin_unlock(&last_ptr->lock); } } static void found_extent(struct find_free_extent_ctl *ffe_ctl, struct btrfs_key *ins) { switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: found_extent_clustered(ffe_ctl, ins); break; case BTRFS_EXTENT_ALLOC_ZONED: /* Nothing to do */ break; default: BUG(); } } static int can_allocate_chunk_zoned(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl) { /* Block group's activeness is not a requirement for METADATA block groups. */ if (!(ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA)) return 0; /* If we can activate new zone, just allocate a chunk and use it */ if (btrfs_can_activate_zone(fs_info->fs_devices, ffe_ctl->flags)) return 0; /* * We already reached the max active zones. Try to finish one block * group to make a room for a new block group. This is only possible * for a data block group because btrfs_zone_finish() may need to wait * for a running transaction which can cause a deadlock for metadata * allocation. */ if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) { int ret = btrfs_zone_finish_one_bg(fs_info); if (ret == 1) return 0; else if (ret < 0) return ret; } /* * If we have enough free space left in an already active block group * and we can't activate any other zone now, do not allow allocating a * new chunk and let find_free_extent() retry with a smaller size. */ if (ffe_ctl->max_extent_size >= ffe_ctl->min_alloc_size) return -ENOSPC; /* * Even min_alloc_size is not left in any block groups. Since we cannot * activate a new block group, allocating it may not help. Let's tell a * caller to try again and hope it progress something by writing some * parts of the region. That is only possible for data block groups, * where a part of the region can be written. */ if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) return -EAGAIN; /* * We cannot activate a new block group and no enough space left in any * block groups. So, allocating a new block group may not help. But, * there is nothing to do anyway, so let's go with it. */ return 0; } static int can_allocate_chunk(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl) { switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: return 0; case BTRFS_EXTENT_ALLOC_ZONED: return can_allocate_chunk_zoned(fs_info, ffe_ctl); default: BUG(); } } /* * Return >0 means caller needs to re-search for free extent * Return 0 means we have the needed free extent. * Return <0 means we failed to locate any free extent. */ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info, struct btrfs_key *ins, struct find_free_extent_ctl *ffe_ctl, struct btrfs_space_info *space_info, bool full_search) { struct btrfs_root *root = fs_info->chunk_root; int ret; if ((ffe_ctl->loop == LOOP_CACHING_NOWAIT) && ffe_ctl->have_caching_bg && !ffe_ctl->orig_have_caching_bg) ffe_ctl->orig_have_caching_bg = true; if (ins->objectid) { found_extent(ffe_ctl, ins); return 0; } if (ffe_ctl->loop >= LOOP_CACHING_WAIT && ffe_ctl->have_caching_bg) return 1; ffe_ctl->index++; if (ffe_ctl->index < BTRFS_NR_RAID_TYPES) return 1; /* See the comments for btrfs_loop_type for an explanation of the phases. */ if (ffe_ctl->loop < LOOP_NO_EMPTY_SIZE) { ffe_ctl->index = 0; /* * We want to skip the LOOP_CACHING_WAIT step if we don't have * any uncached bgs and we've already done a full search * through. */ if (ffe_ctl->loop == LOOP_CACHING_NOWAIT && (!ffe_ctl->orig_have_caching_bg && full_search)) ffe_ctl->loop++; ffe_ctl->loop++; if (ffe_ctl->loop == LOOP_ALLOC_CHUNK) { struct btrfs_trans_handle *trans; int exist = 0; /* Check if allocation policy allows to create a new chunk */ ret = can_allocate_chunk(fs_info, ffe_ctl); if (ret) return ret; trans = current->journal_info; if (trans) exist = 1; else trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); return ret; } ret = btrfs_chunk_alloc(trans, space_info, ffe_ctl->flags, CHUNK_ALLOC_FORCE_FOR_EXTENT); /* Do not bail out on ENOSPC since we can do more. */ if (ret == -ENOSPC) { ret = 0; ffe_ctl->loop++; } else if (ret < 0) btrfs_abort_transaction(trans, ret); else ret = 0; if (!exist) btrfs_end_transaction(trans); if (ret) return ret; } if (ffe_ctl->loop == LOOP_NO_EMPTY_SIZE) { if (ffe_ctl->policy != BTRFS_EXTENT_ALLOC_CLUSTERED) return -ENOSPC; /* * Don't loop again if we already have no empty_size and * no empty_cluster. */ if (ffe_ctl->empty_size == 0 && ffe_ctl->empty_cluster == 0) return -ENOSPC; ffe_ctl->empty_size = 0; ffe_ctl->empty_cluster = 0; } return 1; } return -ENOSPC; } static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl, struct btrfs_space_info *space_info, struct btrfs_key *ins) { /* * If our free space is heavily fragmented we may not be able to make * big contiguous allocations, so instead of doing the expensive search * for free space, simply return ENOSPC with our max_extent_size so we * can go ahead and search for a more manageable chunk. * * If our max_extent_size is large enough for our allocation simply * disable clustering since we will likely not be able to find enough * space to create a cluster and induce latency trying. */ if (space_info->max_extent_size) { spin_lock(&space_info->lock); if (space_info->max_extent_size && ffe_ctl->num_bytes > space_info->max_extent_size) { ins->offset = space_info->max_extent_size; spin_unlock(&space_info->lock); return -ENOSPC; } else if (space_info->max_extent_size) { ffe_ctl->use_cluster = false; } spin_unlock(&space_info->lock); } ffe_ctl->last_ptr = fetch_cluster_info(fs_info, space_info, &ffe_ctl->empty_cluster); if (ffe_ctl->last_ptr) { struct btrfs_free_cluster *last_ptr = ffe_ctl->last_ptr; spin_lock(&last_ptr->lock); if (last_ptr->block_group) ffe_ctl->hint_byte = last_ptr->window_start; if (last_ptr->fragmented) { /* * We still set window_start so we can keep track of the * last place we found an allocation to try and save * some time. */ ffe_ctl->hint_byte = last_ptr->window_start; ffe_ctl->use_cluster = false; } spin_unlock(&last_ptr->lock); } return 0; } static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl, struct btrfs_space_info *space_info) { if (ffe_ctl->for_treelog) { spin_lock(&fs_info->treelog_bg_lock); if (fs_info->treelog_bg) ffe_ctl->hint_byte = fs_info->treelog_bg; spin_unlock(&fs_info->treelog_bg_lock); } else if (ffe_ctl->for_data_reloc) { spin_lock(&fs_info->relocation_bg_lock); if (fs_info->data_reloc_bg) ffe_ctl->hint_byte = fs_info->data_reloc_bg; spin_unlock(&fs_info->relocation_bg_lock); } else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) { struct btrfs_block_group *block_group; spin_lock(&fs_info->zone_active_bgs_lock); list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) { /* * No lock is OK here because avail is monotonically * decreasing, and this is just a hint. */ u64 avail = block_group->zone_capacity - block_group->alloc_offset; if (block_group_bits(block_group, ffe_ctl->flags) && block_group->space_info == space_info && avail >= ffe_ctl->num_bytes) { ffe_ctl->hint_byte = block_group->start; break; } } spin_unlock(&fs_info->zone_active_bgs_lock); } return 0; } static int prepare_allocation(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl, struct btrfs_space_info *space_info, struct btrfs_key *ins) { switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); case BTRFS_EXTENT_ALLOC_ZONED: return prepare_allocation_zoned(fs_info, ffe_ctl, space_info); default: BUG(); } } /* * walks the btree of allocated extents and find a hole of a given size. * The key ins is changed to record the hole: * ins->objectid == start position * ins->flags = BTRFS_EXTENT_ITEM_KEY * ins->offset == the size of the hole. * Any available blocks before search_start are skipped. * * If there is no suitable free space, we will record the max size of * the free space extent currently. * * The overall logic and call chain: * * find_free_extent() * |- Iterate through all block groups * | |- Get a valid block group * | |- Try to do clustered allocation in that block group * | |- Try to do unclustered allocation in that block group * | |- Check if the result is valid * | | |- If valid, then exit * | |- Jump to next block group * | * |- Push harder to find free extents * |- If not found, re-iterate all block groups */ static noinline int find_free_extent(struct btrfs_root *root, struct btrfs_key *ins, struct find_free_extent_ctl *ffe_ctl) { struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; int cache_block_group_error = 0; struct btrfs_block_group *block_group = NULL; struct btrfs_space_info *space_info; bool full_search = false; WARN_ON(ffe_ctl->num_bytes < fs_info->sectorsize); ffe_ctl->search_start = 0; /* For clustered allocation */ ffe_ctl->empty_cluster = 0; ffe_ctl->last_ptr = NULL; ffe_ctl->use_cluster = true; ffe_ctl->have_caching_bg = false; ffe_ctl->orig_have_caching_bg = false; ffe_ctl->index = btrfs_bg_flags_to_raid_index(ffe_ctl->flags); ffe_ctl->loop = 0; ffe_ctl->retry_uncached = false; ffe_ctl->cached = 0; ffe_ctl->max_extent_size = 0; ffe_ctl->total_free_space = 0; ffe_ctl->found_offset = 0; ffe_ctl->policy = BTRFS_EXTENT_ALLOC_CLUSTERED; ffe_ctl->size_class = btrfs_calc_block_group_size_class(ffe_ctl->num_bytes); if (btrfs_is_zoned(fs_info)) ffe_ctl->policy = BTRFS_EXTENT_ALLOC_ZONED; ins->type = BTRFS_EXTENT_ITEM_KEY; ins->objectid = 0; ins->offset = 0; trace_btrfs_find_free_extent(root, ffe_ctl); space_info = btrfs_find_space_info(fs_info, ffe_ctl->flags); if (btrfs_is_zoned(fs_info) && space_info) { /* Use dedicated sub-space_info for dedicated block group users. */ if (ffe_ctl->for_data_reloc) { space_info = space_info->sub_group[0]; ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); } else if (ffe_ctl->for_treelog) { space_info = space_info->sub_group[0]; ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_TREELOG); } } if (!space_info) { btrfs_err(fs_info, "no space info for %llu, tree-log %d, relocation %d", ffe_ctl->flags, ffe_ctl->for_treelog, ffe_ctl->for_data_reloc); return -ENOSPC; } ret = prepare_allocation(fs_info, ffe_ctl, space_info, ins); if (ret < 0) return ret; ffe_ctl->search_start = max(ffe_ctl->search_start, first_logical_byte(fs_info)); ffe_ctl->search_start = max(ffe_ctl->search_start, ffe_ctl->hint_byte); if (ffe_ctl->search_start == ffe_ctl->hint_byte) { block_group = btrfs_lookup_block_group(fs_info, ffe_ctl->search_start); /* * we don't want to use the block group if it doesn't match our * allocation bits, or if its not cached. * * However if we are re-searching with an ideal block group * picked out then we don't care that the block group is cached. */ if (block_group && block_group_bits(block_group, ffe_ctl->flags) && block_group->space_info == space_info && block_group->cached != BTRFS_CACHE_NO) { down_read(&space_info->groups_sem); if (list_empty(&block_group->list) || block_group->ro) { /* * someone is removing this block group, * we can't jump into the have_block_group * target because our list pointers are not * valid */ btrfs_put_block_group(block_group); up_read(&space_info->groups_sem); } else { ffe_ctl->index = btrfs_bg_flags_to_raid_index( block_group->flags); btrfs_lock_block_group(block_group, ffe_ctl->delalloc); ffe_ctl->hinted = true; goto have_block_group; } } else if (block_group) { btrfs_put_block_group(block_group); } } search: trace_btrfs_find_free_extent_search_loop(root, ffe_ctl); ffe_ctl->have_caching_bg = false; if (ffe_ctl->index == btrfs_bg_flags_to_raid_index(ffe_ctl->flags) || ffe_ctl->index == 0) full_search = true; down_read(&space_info->groups_sem); list_for_each_entry(block_group, &space_info->block_groups[ffe_ctl->index], list) { struct btrfs_block_group *bg_ret; ffe_ctl->hinted = false; /* If the block group is read-only, we can skip it entirely. */ if (unlikely(block_group->ro)) { if (ffe_ctl->for_treelog) btrfs_clear_treelog_bg(block_group); if (ffe_ctl->for_data_reloc) btrfs_clear_data_reloc_bg(block_group); continue; } btrfs_grab_block_group(block_group, ffe_ctl->delalloc); ffe_ctl->search_start = block_group->start; /* * this can happen if we end up cycling through all the * raid types, but we want to make sure we only allocate * for the proper type. */ if (!block_group_bits(block_group, ffe_ctl->flags)) { u64 extra = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1_MASK | BTRFS_BLOCK_GROUP_RAID56_MASK | BTRFS_BLOCK_GROUP_RAID10; /* * if they asked for extra copies and this block group * doesn't provide them, bail. This does allow us to * fill raid0 from raid1. */ if ((ffe_ctl->flags & extra) && !(block_group->flags & extra)) goto loop; /* * This block group has different flags than we want. * It's possible that we have MIXED_GROUP flag but no * block group is mixed. Just skip such block group. */ btrfs_release_block_group(block_group, ffe_ctl->delalloc); continue; } have_block_group: trace_btrfs_find_free_extent_have_block_group(root, ffe_ctl, block_group); ffe_ctl->cached = btrfs_block_group_done(block_group); if (unlikely(!ffe_ctl->cached)) { ffe_ctl->have_caching_bg = true; ret = btrfs_cache_block_group(block_group, false); /* * If we get ENOMEM here or something else we want to * try other block groups, because it may not be fatal. * However if we can't find anything else we need to * save our return here so that we return the actual * error that caused problems, not ENOSPC. */ if (ret < 0) { if (!cache_block_group_error) cache_block_group_error = ret; ret = 0; goto loop; } ret = 0; } if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) { if (!cache_block_group_error) cache_block_group_error = -EIO; goto loop; } if (!find_free_extent_check_size_class(ffe_ctl, block_group)) goto loop; bg_ret = NULL; ret = do_allocation(block_group, ffe_ctl, &bg_ret); if (ret > 0) goto loop; if (bg_ret && bg_ret != block_group) { btrfs_release_block_group(block_group, ffe_ctl->delalloc); block_group = bg_ret; } /* Checks */ ffe_ctl->search_start = round_up(ffe_ctl->found_offset, fs_info->stripesize); /* move on to the next group */ if (ffe_ctl->search_start + ffe_ctl->num_bytes > block_group->start + block_group->length) { btrfs_add_free_space_unused(block_group, ffe_ctl->found_offset, ffe_ctl->num_bytes); goto loop; } if (ffe_ctl->found_offset < ffe_ctl->search_start) btrfs_add_free_space_unused(block_group, ffe_ctl->found_offset, ffe_ctl->search_start - ffe_ctl->found_offset); ret = btrfs_add_reserved_bytes(block_group, ffe_ctl->ram_bytes, ffe_ctl->num_bytes, ffe_ctl->delalloc, ffe_ctl->loop >= LOOP_WRONG_SIZE_CLASS); if (ret == -EAGAIN) { btrfs_add_free_space_unused(block_group, ffe_ctl->found_offset, ffe_ctl->num_bytes); goto loop; } btrfs_inc_block_group_reservations(block_group); /* we are all good, lets return */ ins->objectid = ffe_ctl->search_start; ins->offset = ffe_ctl->num_bytes; trace_btrfs_reserve_extent(block_group, ffe_ctl); btrfs_release_block_group(block_group, ffe_ctl->delalloc); break; loop: if (!ffe_ctl->cached && ffe_ctl->loop > LOOP_CACHING_NOWAIT && !ffe_ctl->retry_uncached) { ffe_ctl->retry_uncached = true; btrfs_wait_block_group_cache_progress(block_group, ffe_ctl->num_bytes + ffe_ctl->empty_cluster + ffe_ctl->empty_size); goto have_block_group; } release_block_group(block_group, ffe_ctl, ffe_ctl->delalloc); cond_resched(); } up_read(&space_info->groups_sem); ret = find_free_extent_update_loop(fs_info, ins, ffe_ctl, space_info, full_search); if (ret > 0) goto search; if (ret == -ENOSPC && !cache_block_group_error) { /* * Use ffe_ctl->total_free_space as fallback if we can't find * any contiguous hole. */ if (!ffe_ctl->max_extent_size) ffe_ctl->max_extent_size = ffe_ctl->total_free_space; spin_lock(&space_info->lock); space_info->max_extent_size = ffe_ctl->max_extent_size; spin_unlock(&space_info->lock); ins->offset = ffe_ctl->max_extent_size; } else if (ret == -ENOSPC) { ret = cache_block_group_error; } return ret; } /* * Entry point to the extent allocator. Tries to find a hole that is at least * as big as @num_bytes. * * @root - The root that will contain this extent * * @ram_bytes - The amount of space in ram that @num_bytes take. This * is used for accounting purposes. This value differs * from @num_bytes only in the case of compressed extents. * * @num_bytes - Number of bytes to allocate on-disk. * * @min_alloc_size - Indicates the minimum amount of space that the * allocator should try to satisfy. In some cases * @num_bytes may be larger than what is required and if * the filesystem is fragmented then allocation fails. * However, the presence of @min_alloc_size gives a * chance to try and satisfy the smaller allocation. * * @empty_size - A hint that you plan on doing more COW. This is the * size in bytes the allocator should try to find free * next to the block it returns. This is just a hint and * may be ignored by the allocator. * * @hint_byte - Hint to the allocator to start searching above the byte * address passed. It might be ignored. * * @ins - This key is modified to record the found hole. It will * have the following values: * ins->objectid == start position * ins->flags = BTRFS_EXTENT_ITEM_KEY * ins->offset == the size of the hole. * * @is_data - Boolean flag indicating whether an extent is * allocated for data (true) or metadata (false) * * @delalloc - Boolean flag indicating whether this allocation is for * delalloc or not. If 'true' data_rwsem of block groups * is going to be acquired. * * * Returns 0 when an allocation succeeded or < 0 when an error occurred. In * case -ENOSPC is returned then @ins->offset will contain the size of the * largest available hole the allocator managed to find. */ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc) { struct btrfs_fs_info *fs_info = root->fs_info; struct find_free_extent_ctl ffe_ctl = {}; bool final_tried = num_bytes == min_alloc_size; u64 flags; int ret; bool for_treelog = (btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID); bool for_data_reloc = (btrfs_is_data_reloc_root(root) && is_data); flags = get_alloc_profile_by_root(root, is_data); again: WARN_ON(num_bytes < fs_info->sectorsize); ffe_ctl.ram_bytes = ram_bytes; ffe_ctl.num_bytes = num_bytes; ffe_ctl.min_alloc_size = min_alloc_size; ffe_ctl.empty_size = empty_size; ffe_ctl.flags = flags; ffe_ctl.delalloc = delalloc; ffe_ctl.hint_byte = hint_byte; ffe_ctl.for_treelog = for_treelog; ffe_ctl.for_data_reloc = for_data_reloc; ret = find_free_extent(root, ins, &ffe_ctl); if (!ret && !is_data) { btrfs_dec_block_group_reservations(fs_info, ins->objectid); } else if (ret == -ENOSPC) { if (!final_tried && ins->offset) { num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, fs_info->sectorsize); num_bytes = max(num_bytes, min_alloc_size); ram_bytes = num_bytes; if (num_bytes == min_alloc_size) final_tried = true; goto again; } else if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) { struct btrfs_space_info *sinfo; sinfo = btrfs_find_space_info(fs_info, flags); btrfs_err(fs_info, "allocation failed flags %llu, wanted %llu tree-log %d, relocation: %d", flags, num_bytes, for_treelog, for_data_reloc); if (sinfo) btrfs_dump_space_info(fs_info, sinfo, num_bytes, 1); } } return ret; } int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len, bool is_delalloc) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "Unable to find block group for %llu", start); return -ENOSPC; } btrfs_add_free_space(cache, start, len); btrfs_free_reserved_bytes(cache, len, is_delalloc); trace_btrfs_reserved_extent_free(fs_info, start, len); btrfs_put_block_group(cache); return 0; } int btrfs_pin_reserved_extent(struct btrfs_trans_handle *trans, const struct extent_buffer *eb) { struct btrfs_block_group *cache; int ret = 0; cache = btrfs_lookup_block_group(trans->fs_info, eb->start); if (!cache) { btrfs_err(trans->fs_info, "unable to find block group for %llu", eb->start); return -ENOSPC; } ret = pin_down_extent(trans, cache, eb->start, eb->len, 1); btrfs_put_block_group(cache); return ret; } static int alloc_reserved_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; ret = btrfs_remove_from_free_space_tree(trans, bytenr, num_bytes); if (ret) return ret; ret = btrfs_update_block_group(trans, bytenr, num_bytes, true); if (ret) { ASSERT(!ret); btrfs_err(fs_info, "update block group failed for %llu %llu", bytenr, num_bytes); return ret; } trace_btrfs_reserved_extent_alloc(fs_info, bytenr, num_bytes); return 0; } static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, u64 parent, u64 root_objectid, u64 flags, u64 owner, u64 offset, struct btrfs_key *ins, int ref_mod, u64 oref_root) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *extent_root; int ret; struct btrfs_extent_item *extent_item; struct btrfs_extent_owner_ref *oref; struct btrfs_extent_inline_ref *iref; struct btrfs_path *path; struct extent_buffer *leaf; int type; u32 size; const bool simple_quota = (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE); if (parent > 0) type = BTRFS_SHARED_DATA_REF_KEY; else type = BTRFS_EXTENT_DATA_REF_KEY; size = sizeof(*extent_item); if (simple_quota) size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY); size += btrfs_extent_inline_ref_size(type); path = btrfs_alloc_path(); if (!path) return -ENOMEM; extent_root = btrfs_extent_root(fs_info, ins->objectid); ret = btrfs_insert_empty_item(trans, extent_root, path, ins, size); if (ret) { btrfs_free_path(path); return ret; } leaf = path->nodes[0]; extent_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); btrfs_set_extent_refs(leaf, extent_item, ref_mod); btrfs_set_extent_generation(leaf, extent_item, trans->transid); btrfs_set_extent_flags(leaf, extent_item, flags | BTRFS_EXTENT_FLAG_DATA); iref = (struct btrfs_extent_inline_ref *)(extent_item + 1); if (simple_quota) { btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_EXTENT_OWNER_REF_KEY); oref = (struct btrfs_extent_owner_ref *)(&iref->offset); btrfs_set_extent_owner_ref_root_id(leaf, oref, oref_root); iref = (struct btrfs_extent_inline_ref *)(oref + 1); } btrfs_set_extent_inline_ref_type(leaf, iref, type); if (parent > 0) { struct btrfs_shared_data_ref *ref; ref = (struct btrfs_shared_data_ref *)(iref + 1); btrfs_set_extent_inline_ref_offset(leaf, iref, parent); btrfs_set_shared_data_ref_count(leaf, ref, ref_mod); } else { struct btrfs_extent_data_ref *ref; ref = (struct btrfs_extent_data_ref *)(&iref->offset); btrfs_set_extent_data_ref_root(leaf, ref, root_objectid); btrfs_set_extent_data_ref_objectid(leaf, ref, owner); btrfs_set_extent_data_ref_offset(leaf, ref, offset); btrfs_set_extent_data_ref_count(leaf, ref, ref_mod); } btrfs_free_path(path); return alloc_reserved_extent(trans, ins->objectid, ins->offset); } static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, const struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *extent_root; int ret; struct btrfs_extent_item *extent_item; struct btrfs_key extent_key; struct btrfs_tree_block_info *block_info; struct btrfs_extent_inline_ref *iref; struct btrfs_path *path; struct extent_buffer *leaf; u32 size = sizeof(*extent_item) + sizeof(*iref); const u64 flags = (extent_op ? extent_op->flags_to_set : 0); /* The owner of a tree block is the level. */ int level = btrfs_delayed_ref_owner(node); bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA); extent_key.objectid = node->bytenr; if (skinny_metadata) { /* The owner of a tree block is the level. */ extent_key.offset = level; extent_key.type = BTRFS_METADATA_ITEM_KEY; } else { extent_key.offset = node->num_bytes; extent_key.type = BTRFS_EXTENT_ITEM_KEY; size += sizeof(*block_info); } path = btrfs_alloc_path(); if (!path) return -ENOMEM; extent_root = btrfs_extent_root(fs_info, extent_key.objectid); ret = btrfs_insert_empty_item(trans, extent_root, path, &extent_key, size); if (ret) { btrfs_free_path(path); return ret; } leaf = path->nodes[0]; extent_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); btrfs_set_extent_refs(leaf, extent_item, 1); btrfs_set_extent_generation(leaf, extent_item, trans->transid); btrfs_set_extent_flags(leaf, extent_item, flags | BTRFS_EXTENT_FLAG_TREE_BLOCK); if (skinny_metadata) { iref = (struct btrfs_extent_inline_ref *)(extent_item + 1); } else { block_info = (struct btrfs_tree_block_info *)(extent_item + 1); btrfs_set_tree_block_key(leaf, block_info, &extent_op->key); btrfs_set_tree_block_level(leaf, block_info, level); iref = (struct btrfs_extent_inline_ref *)(block_info + 1); } if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) { btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_SHARED_BLOCK_REF_KEY); btrfs_set_extent_inline_ref_offset(leaf, iref, node->parent); } else { btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_TREE_BLOCK_REF_KEY); btrfs_set_extent_inline_ref_offset(leaf, iref, node->ref_root); } btrfs_free_path(path); return alloc_reserved_extent(trans, node->bytenr, fs_info->nodesize); } int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 owner, u64 offset, u64 ram_bytes, struct btrfs_key *ins) { struct btrfs_ref generic_ref = { .action = BTRFS_ADD_DELAYED_EXTENT, .bytenr = ins->objectid, .num_bytes = ins->offset, .owning_root = btrfs_root_id(root), .ref_root = btrfs_root_id(root), }; ASSERT(generic_ref.ref_root != BTRFS_TREE_LOG_OBJECTID); if (btrfs_is_data_reloc_root(root) && btrfs_is_fstree(root->relocation_src_root)) generic_ref.owning_root = root->relocation_src_root; btrfs_init_data_ref(&generic_ref, owner, offset, 0, false); btrfs_ref_tree_mod(root->fs_info, &generic_ref); return btrfs_add_delayed_data_ref(trans, &generic_ref, ram_bytes); } /* * this is used by the tree logging recovery code. It records that * an extent has been allocated and makes sure to clear the free * space cache bits as well */ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, u64 root_objectid, u64 owner, u64 offset, struct btrfs_key *ins) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret; struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; const struct btrfs_squota_delta delta = { .root = root_objectid, .num_bytes = ins->offset, .generation = trans->transid, .is_data = true, .is_inc = true, }; /* * Mixed block groups will exclude before processing the log so we only * need to do the exclude dance if this fs isn't mixed. */ if (!btrfs_fs_incompat(fs_info, MIXED_GROUPS)) { ret = __exclude_logged_extent(fs_info, ins->objectid, ins->offset); if (ret) return ret; } block_group = btrfs_lookup_block_group(fs_info, ins->objectid); if (!block_group) return -EINVAL; space_info = block_group->space_info; spin_lock(&space_info->lock); spin_lock(&block_group->lock); space_info->bytes_reserved += ins->offset; block_group->reserved += ins->offset; spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner, offset, ins, 1, root_objectid); if (ret) btrfs_pin_extent(trans, ins->objectid, ins->offset, 1); ret = btrfs_record_squota_delta(fs_info, &delta); btrfs_put_block_group(block_group); return ret; } #ifdef CONFIG_BTRFS_DEBUG /* * Extra safety check in case the extent tree is corrupted and extent allocator * chooses to use a tree block which is already used and locked. */ static bool check_eb_lock_owner(const struct extent_buffer *eb) { if (eb->lock_owner == current->pid) { btrfs_err_rl(eb->fs_info, "tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected", eb->start, btrfs_header_owner(eb), current->pid); return true; } return false; } #else static bool check_eb_lock_owner(struct extent_buffer *eb) { return false; } #endif static struct extent_buffer * btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, int level, u64 owner, enum btrfs_lock_nesting nest) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *buf; u64 lockdep_owner = owner; buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level); if (IS_ERR(buf)) return buf; if (unlikely(check_eb_lock_owner(buf))) { free_extent_buffer(buf); return ERR_PTR(-EUCLEAN); } /* * The reloc trees are just snapshots, so we need them to appear to be * just like any other fs tree WRT lockdep. * * The exception however is in replace_path() in relocation, where we * hold the lock on the original fs root and then search for the reloc * root. At that point we need to make sure any reloc root buffers are * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make * lockdep happy. */ if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID && !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) lockdep_owner = BTRFS_FS_TREE_OBJECTID; /* btrfs_clear_buffer_dirty() accesses generation field. */ btrfs_set_header_generation(buf, trans->transid); /* * This needs to stay, because we could allocate a freed block from an * old tree into a new tree, so we need to make sure this new block is * set to the appropriate level and owner. */ btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level); btrfs_tree_lock_nested(buf, nest); btrfs_clear_buffer_dirty(trans, buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); clear_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &buf->bflags); set_extent_buffer_uptodate(buf); memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header)); btrfs_set_header_level(buf, level); btrfs_set_header_bytenr(buf, buf->start); btrfs_set_header_generation(buf, trans->transid); btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV); btrfs_set_header_owner(buf, owner); write_extent_buffer_fsid(buf, fs_info->fs_devices->metadata_uuid); write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid); if (btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID) { buf->log_index = root->log_transid % 2; /* * we allow two log transactions at a time, use different * EXTENT bit to differentiate dirty pages. */ if (buf->log_index == 0) btrfs_set_extent_bit(&root->dirty_log_pages, buf->start, buf->start + buf->len - 1, EXTENT_DIRTY_LOG1, NULL); else btrfs_set_extent_bit(&root->dirty_log_pages, buf->start, buf->start + buf->len - 1, EXTENT_DIRTY_LOG2, NULL); } else { buf->log_index = -1; btrfs_set_extent_bit(&trans->transaction->dirty_pages, buf->start, buf->start + buf->len - 1, EXTENT_DIRTY, NULL); } /* this returns a buffer locked for blocking */ return buf; } /* * finds a free extent and does all the dirty work required for allocation * returns the tree buffer or an ERR_PTR on error. */ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 parent, u64 root_objectid, const struct btrfs_disk_key *key, int level, u64 hint, u64 empty_size, u64 reloc_src_root, enum btrfs_lock_nesting nest) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key ins; struct btrfs_block_rsv *block_rsv; struct extent_buffer *buf; u64 flags = 0; int ret; u32 blocksize = fs_info->nodesize; bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA); u64 owning_root; #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS if (btrfs_is_testing(fs_info)) { buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr, level, root_objectid, nest); if (!IS_ERR(buf)) root->alloc_bytenr += blocksize; return buf; } #endif block_rsv = btrfs_use_block_rsv(trans, root, blocksize); if (IS_ERR(block_rsv)) return ERR_CAST(block_rsv); ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize, empty_size, hint, &ins, 0, 0); if (ret) goto out_unuse; buf = btrfs_init_new_buffer(trans, root, ins.objectid, level, root_objectid, nest); if (IS_ERR(buf)) { ret = PTR_ERR(buf); goto out_free_reserved; } owning_root = btrfs_header_owner(buf); if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) { if (parent == 0) parent = ins.objectid; flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF; owning_root = reloc_src_root; } else BUG_ON(parent > 0); if (root_objectid != BTRFS_TREE_LOG_OBJECTID) { struct btrfs_delayed_extent_op *extent_op; struct btrfs_ref generic_ref = { .action = BTRFS_ADD_DELAYED_EXTENT, .bytenr = ins.objectid, .num_bytes = ins.offset, .parent = parent, .owning_root = owning_root, .ref_root = root_objectid, }; if (!skinny_metadata || flags != 0) { extent_op = btrfs_alloc_delayed_extent_op(); if (!extent_op) { ret = -ENOMEM; goto out_free_buf; } if (key) memcpy(&extent_op->key, key, sizeof(extent_op->key)); else memset(&extent_op->key, 0, sizeof(extent_op->key)); extent_op->flags_to_set = flags; extent_op->update_key = (skinny_metadata ? false : true); extent_op->update_flags = (flags != 0); } else { extent_op = NULL; } btrfs_init_tree_ref(&generic_ref, level, btrfs_root_id(root), false); btrfs_ref_tree_mod(fs_info, &generic_ref); ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op); if (ret) { btrfs_free_delayed_extent_op(extent_op); goto out_free_buf; } } return buf; out_free_buf: btrfs_tree_unlock(buf); free_extent_buffer(buf); out_free_reserved: btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, false); out_unuse: btrfs_unuse_block_rsv(fs_info, block_rsv, blocksize); return ERR_PTR(ret); } struct walk_control { u64 refs[BTRFS_MAX_LEVEL]; u64 flags[BTRFS_MAX_LEVEL]; struct btrfs_key update_progress; struct btrfs_key drop_progress; int drop_level; int stage; int level; int shared_level; int update_ref; int keep_locks; int reada_slot; int reada_count; int restarted; /* Indicate that extent info needs to be looked up when walking the tree. */ int lookup_info; }; /* * This is our normal stage. We are traversing blocks the current snapshot owns * and we are dropping any of our references to any children we are able to, and * then freeing the block once we've processed all of the children. */ #define DROP_REFERENCE 1 /* * We enter this stage when we have to walk into a child block (meaning we can't * simply drop our reference to it from our current parent node) and there are * more than one reference on it. If we are the owner of any of the children * blocks from the current parent node then we have to do the FULL_BACKREF dance * on them in order to drop our normal ref and add the shared ref. */ #define UPDATE_BACKREF 2 /* * Decide if we need to walk down into this node to adjust the references. * * @root: the root we are currently deleting * @wc: the walk control for this deletion * @eb: the parent eb that we're currently visiting * @refs: the number of refs for wc->level - 1 * @flags: the flags for wc->level - 1 * @slot: the slot in the eb that we're currently checking * * This is meant to be called when we're evaluating if a node we point to at * wc->level should be read and walked into, or if we can simply delete our * reference to it. We return true if we should walk into the node, false if we * can skip it. * * We have assertions in here to make sure this is called correctly. We assume * that sanity checking on the blocks read to this point has been done, so any * corrupted file systems must have been caught before calling this function. */ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control *wc, struct extent_buffer *eb, u64 flags, int slot) { struct btrfs_key key; u64 generation; int level = wc->level; ASSERT(level > 0); ASSERT(wc->refs[level - 1] > 0); /* * The update backref stage we only want to skip if we already have * FULL_BACKREF set, otherwise we need to read. */ if (wc->stage == UPDATE_BACKREF) { if (level == 1 && flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) return false; return true; } /* * We're the last ref on this block, we must walk into it and process * any refs it's pointing at. */ if (wc->refs[level - 1] == 1) return true; /* * If we're already FULL_BACKREF then we know we can just drop our * current reference. */ if (level == 1 && flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) return false; /* * This block is older than our creation generation, we can drop our * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* * This block was processed from a previous snapshot deletion run, we * can skip it. */ btrfs_node_key_to_cpu(eb, &key, slot); if (btrfs_comp_cpu_keys(&key, &wc->update_progress) < 0) return false; /* All other cases we need to wander into the node. */ return true; } static noinline void reada_walk_down(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct walk_control *wc, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = root->fs_info; u64 bytenr; u64 generation; u64 refs; u64 flags; u32 nritems; struct extent_buffer *eb; int ret; int slot; int nread = 0; if (path->slots[wc->level] < wc->reada_slot) { wc->reada_count = wc->reada_count * 2 / 3; wc->reada_count = max(wc->reada_count, 2); } else { wc->reada_count = wc->reada_count * 3 / 2; wc->reada_count = min_t(int, wc->reada_count, BTRFS_NODEPTRS_PER_BLOCK(fs_info)); } eb = path->nodes[wc->level]; nritems = btrfs_header_nritems(eb); for (slot = path->slots[wc->level]; slot < nritems; slot++) { if (nread >= wc->reada_count) break; cond_resched(); bytenr = btrfs_node_blockptr(eb, slot); generation = btrfs_node_ptr_generation(eb, slot); if (slot == path->slots[wc->level]) goto reada; if (wc->stage == UPDATE_BACKREF && generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, wc->level - 1, 1, &refs, &flags, NULL); /* We don't care about errors in readahead. */ if (ret < 0) continue; /* * This could be racey, it's conceivable that we raced and end * up with a bogus refs count, if that's the case just skip, if * we are actually corrupt we will notice when we look up * everything again with our locks. */ if (refs == 0) continue; /* If we don't need to visit this node don't reada. */ if (!visit_node_for_delete(root, wc, eb, flags, slot)) continue; reada: btrfs_readahead_node_child(eb, slot); nread++; } wc->reada_slot = slot; } /* * helper to process tree block while walking down the tree. * * when wc->stage == UPDATE_BACKREF, this function updates * back refs for pointers in the block. * * NOTE: return value 1 means we should stop walking down. */ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc) { struct btrfs_fs_info *fs_info = root->fs_info; int level = wc->level; struct extent_buffer *eb = path->nodes[level]; u64 flag = BTRFS_BLOCK_FLAG_FULL_BACKREF; int ret; if (wc->stage == UPDATE_BACKREF && btrfs_header_owner(eb) != btrfs_root_id(root)) return 1; /* * when reference count of tree block is 1, it won't increase * again. once full backref flag is set, we never clear it. */ if (wc->lookup_info && ((wc->stage == DROP_REFERENCE && wc->refs[level] != 1) || (wc->stage == UPDATE_BACKREF && !(wc->flags[level] & flag)))) { ASSERT(path->locks[level]); ret = btrfs_lookup_extent_info(trans, fs_info, eb->start, level, 1, &wc->refs[level], &wc->flags[level], NULL); if (ret) return ret; if (unlikely(wc->refs[level] == 0)) { btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0", eb->start); return -EUCLEAN; } } if (wc->stage == DROP_REFERENCE) { if (wc->refs[level] > 1) return 1; if (path->locks[level] && !wc->keep_locks) { btrfs_tree_unlock_rw(eb, path->locks[level]); path->locks[level] = 0; } return 0; } /* wc->stage == UPDATE_BACKREF */ if (!(wc->flags[level] & flag)) { ASSERT(path->locks[level]); ret = btrfs_inc_ref(trans, root, eb, 1); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_dec_ref(trans, root, eb, 0); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_set_disk_extent_flags(trans, eb, flag); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } wc->flags[level] |= flag; } /* * the block is shared by multiple trees, so it's not good to * keep the tree lock */ if (path->locks[level] && level > 0) { btrfs_tree_unlock_rw(eb, path->locks[level]); path->locks[level] = 0; } return 0; } /* * This is used to verify a ref exists for this root to deal with a bug where we * would have a drop_progress key that hadn't been updated properly. */ static int check_ref_exists(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 parent, int level) { struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_head *head; BTRFS_PATH_AUTO_FREE(path); struct btrfs_extent_inline_ref *iref; int ret; bool exists = false; path = btrfs_alloc_path(); if (!path) return -ENOMEM; again: ret = lookup_extent_backref(trans, path, &iref, bytenr, root->fs_info->nodesize, parent, btrfs_root_id(root), level, 0); if (ret != -ENOENT) { /* * If we get 0 then we found our reference, return 1, else * return the error if it's not -ENOENT; */ return (ret < 0 ) ? ret : 1; } /* * We could have a delayed ref with this reference, so look it up while * we're holding the path open to make sure we don't race with the * delayed ref running. */ delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); head = btrfs_find_delayed_ref_head(root->fs_info, delayed_refs, bytenr); if (!head) goto out; if (!mutex_trylock(&head->mutex)) { /* * We're contended, means that the delayed ref is running, get a * reference and wait for the ref head to be complete and then * try again. */ refcount_inc(&head->refs); spin_unlock(&delayed_refs->lock); btrfs_release_path(path); mutex_lock(&head->mutex); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); goto again; } exists = btrfs_find_delayed_tree_ref(head, btrfs_root_id(root), parent); mutex_unlock(&head->mutex); out: spin_unlock(&delayed_refs->lock); return exists ? 1 : 0; } /* * We may not have an uptodate block, so if we are going to walk down into this * block we need to drop the lock, read it off of the disk, re-lock it and * return to continue dropping the snapshot. */ static int check_next_block_uptodate(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc, struct extent_buffer *next) { struct btrfs_tree_parent_check check = { 0 }; u64 generation; int level = wc->level; int ret; btrfs_assert_tree_write_locked(next); generation = btrfs_node_ptr_generation(path->nodes[level], path->slots[level]); if (btrfs_buffer_uptodate(next, generation, false)) return 0; check.level = level - 1; check.transid = generation; check.owner_root = btrfs_root_id(root); check.has_first_key = true; btrfs_node_key_to_cpu(path->nodes[level], &check.first_key, path->slots[level]); btrfs_tree_unlock(next); if (level == 1) reada_walk_down(trans, root, wc, path); ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); return ret; } btrfs_tree_lock(next); wc->lookup_info = 1; return 0; } /* * If we determine that we don't have to visit wc->level - 1 then we need to * determine if we can drop our reference. * * If we are UPDATE_BACKREF then we will not, we need to update our backrefs. * * If we are DROP_REFERENCE this will figure out if we need to drop our current * reference, skipping it if we dropped it from a previous uncompleted drop, or * dropping it if we still have a reference to it. */ static int maybe_drop_reference(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc, struct extent_buffer *next, u64 owner_root) { struct btrfs_ref ref = { .action = BTRFS_DROP_DELAYED_REF, .bytenr = next->start, .num_bytes = root->fs_info->nodesize, .owning_root = owner_root, .ref_root = btrfs_root_id(root), }; int level = wc->level; int ret; /* We are UPDATE_BACKREF, we're not dropping anything. */ if (wc->stage == UPDATE_BACKREF) return 0; if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) { ref.parent = path->nodes[level]->start; } else { ASSERT(btrfs_root_id(root) == btrfs_header_owner(path->nodes[level])); if (unlikely(btrfs_root_id(root) != btrfs_header_owner(path->nodes[level]))) { btrfs_err(root->fs_info, "mismatched block owner"); return -EIO; } } /* * If we had a drop_progress we need to verify the refs are set as * expected. If we find our ref then we know that from here on out * everything should be correct, and we can clear the * ->restarted flag. */ if (wc->restarted) { ret = check_ref_exists(trans, root, next->start, ref.parent, level - 1); if (ret <= 0) return ret; ret = 0; wc->restarted = 0; } /* * Reloc tree doesn't contribute to qgroup numbers, and we have already * accounted them at merge time (replace_path), thus we could skip * expensive subtree trace here. */ if (btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID && wc->refs[level - 1] > 1) { u64 generation = btrfs_node_ptr_generation(path->nodes[level], path->slots[level]); ret = btrfs_qgroup_trace_subtree(trans, next, generation, level - 1); if (ret) { btrfs_err_rl(root->fs_info, "error %d accounting shared subtree, quota is out of sync, rescan required", ret); } } /* * We need to update the next key in our walk control so we can update * the drop_progress key accordingly. We don't care if find_next_key * doesn't find a key because that means we're at the end and are going * to clean up now. */ wc->drop_level = level; find_next_key(path, level, &wc->drop_progress); btrfs_init_tree_ref(&ref, level - 1, 0, false); return btrfs_free_extent(trans, &ref); } /* * helper to process tree block pointer. * * when wc->stage == DROP_REFERENCE, this function checks * reference count of the block pointed to. if the block * is shared and we need update back refs for the subtree * rooted at the block, this function changes wc->stage to * UPDATE_BACKREF. if the block is shared and there is no * need to update back, this function drops the reference * to the block. * * NOTE: return value 1 means we should stop walking down. */ static noinline int do_walk_down(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc) { struct btrfs_fs_info *fs_info = root->fs_info; u64 bytenr; u64 generation; u64 owner_root = 0; struct extent_buffer *next; int level = wc->level; int ret = 0; generation = btrfs_node_ptr_generation(path->nodes[level], path->slots[level]); /* * if the lower level block was created before the snapshot * was created, we know there is no need to update back refs * for the subtree */ if (wc->stage == UPDATE_BACKREF && generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]); next = btrfs_find_create_tree_block(fs_info, bytenr, btrfs_root_id(root), level - 1); if (IS_ERR(next)) return PTR_ERR(next); btrfs_tree_lock(next); ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1, &wc->refs[level - 1], &wc->flags[level - 1], &owner_root); if (ret < 0) goto out_unlock; if (unlikely(wc->refs[level - 1] == 0)) { btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0", bytenr); ret = -EUCLEAN; goto out_unlock; } wc->lookup_info = 0; /* If we don't have to walk into this node skip it. */ if (!visit_node_for_delete(root, wc, path->nodes[level], wc->flags[level - 1], path->slots[level])) goto skip; /* * We have to walk down into this node, and if we're currently at the * DROP_REFERENCE stage and this block is shared then we need to switch * to the UPDATE_BACKREF stage in order to convert to FULL_BACKREF. */ if (wc->stage == DROP_REFERENCE && wc->refs[level - 1] > 1) { wc->stage = UPDATE_BACKREF; wc->shared_level = level - 1; } ret = check_next_block_uptodate(trans, root, path, wc, next); if (ret) return ret; level--; ASSERT(level == btrfs_header_level(next)); if (unlikely(level != btrfs_header_level(next))) { btrfs_err(root->fs_info, "mismatched level"); ret = -EIO; goto out_unlock; } path->nodes[level] = next; path->slots[level] = 0; path->locks[level] = BTRFS_WRITE_LOCK; wc->level = level; if (wc->level == 1) wc->reada_slot = 0; return 0; skip: ret = maybe_drop_reference(trans, root, path, wc, next, owner_root); if (ret) goto out_unlock; wc->refs[level - 1] = 0; wc->flags[level - 1] = 0; wc->lookup_info = 1; ret = 1; out_unlock: btrfs_tree_unlock(next); free_extent_buffer(next); return ret; } /* * helper to process tree block while walking up the tree. * * when wc->stage == DROP_REFERENCE, this function drops * reference count on the block. * * when wc->stage == UPDATE_BACKREF, this function changes * wc->stage back to DROP_REFERENCE if we changed wc->stage * to UPDATE_BACKREF previously while processing the block. * * NOTE: return value 1 means we should stop walking up. */ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc) { struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; int level = wc->level; struct extent_buffer *eb = path->nodes[level]; u64 parent = 0; if (wc->stage == UPDATE_BACKREF) { ASSERT(wc->shared_level >= level); if (level < wc->shared_level) goto out; ret = find_next_key(path, level + 1, &wc->update_progress); if (ret > 0) wc->update_ref = 0; wc->stage = DROP_REFERENCE; wc->shared_level = -1; path->slots[level] = 0; /* * check reference count again if the block isn't locked. * we should start walking down the tree again if reference * count is one. */ if (!path->locks[level]) { ASSERT(level > 0); btrfs_tree_lock(eb); path->locks[level] = BTRFS_WRITE_LOCK; ret = btrfs_lookup_extent_info(trans, fs_info, eb->start, level, 1, &wc->refs[level], &wc->flags[level], NULL); if (ret < 0) { btrfs_tree_unlock_rw(eb, path->locks[level]); path->locks[level] = 0; return ret; } if (unlikely(wc->refs[level] == 0)) { btrfs_tree_unlock_rw(eb, path->locks[level]); btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0", eb->start); return -EUCLEAN; } if (wc->refs[level] == 1) { btrfs_tree_unlock_rw(eb, path->locks[level]); path->locks[level] = 0; return 1; } } } /* wc->stage == DROP_REFERENCE */ ASSERT(path->locks[level] || wc->refs[level] == 1); if (wc->refs[level] == 1) { if (level == 0) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) { ret = btrfs_dec_ref(trans, root, eb, 1); if (ret) { btrfs_abort_transaction(trans, ret); return ret; } } else { ret = btrfs_dec_ref(trans, root, eb, 0); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } } if (btrfs_is_fstree(btrfs_root_id(root))) { ret = btrfs_qgroup_trace_leaf_items(trans, eb); if (ret) { btrfs_err_rl(fs_info, "error %d accounting leaf items, quota is out of sync, rescan required", ret); } } } /* Make block locked assertion in btrfs_clear_buffer_dirty happy. */ if (!path->locks[level]) { btrfs_tree_lock(eb); path->locks[level] = BTRFS_WRITE_LOCK; } btrfs_clear_buffer_dirty(trans, eb); } if (eb == root->node) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) parent = eb->start; else if (unlikely(btrfs_root_id(root) != btrfs_header_owner(eb))) goto owner_mismatch; } else { if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF) parent = path->nodes[level + 1]->start; else if (unlikely(btrfs_root_id(root) != btrfs_header_owner(path->nodes[level + 1]))) goto owner_mismatch; } ret = btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent, wc->refs[level] == 1); if (ret < 0) btrfs_abort_transaction(trans, ret); out: wc->refs[level] = 0; wc->flags[level] = 0; return ret; owner_mismatch: btrfs_err_rl(fs_info, "unexpected tree owner, have %llu expect %llu", btrfs_header_owner(eb), btrfs_root_id(root)); return -EUCLEAN; } /* * walk_down_tree consists of two steps. * * walk_down_proc(). Look up the reference count and reference of our current * wc->level. At this point path->nodes[wc->level] should be populated and * uptodate, and in most cases should already be locked. If we are in * DROP_REFERENCE and our refcount is > 1 then we've entered a shared node and * we can walk back up the tree. If we are UPDATE_BACKREF we have to set * FULL_BACKREF on this node if it's not already set, and then do the * FULL_BACKREF conversion dance, which is to drop the root reference and add * the shared reference to all of this nodes children. * * do_walk_down(). This is where we actually start iterating on the children of * our current path->nodes[wc->level]. For DROP_REFERENCE that means dropping * our reference to the children that return false from visit_node_for_delete(), * which has various conditions where we know we can just drop our reference * without visiting the node. For UPDATE_BACKREF we will skip any children that * visit_node_for_delete() returns false for, only walking down when necessary. * The bulk of the work for UPDATE_BACKREF occurs in the walk_up_tree() part of * snapshot deletion. */ static noinline int walk_down_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc) { int level = wc->level; int ret = 0; wc->lookup_info = 1; while (level >= 0) { ret = walk_down_proc(trans, root, path, wc); if (ret) break; if (level == 0) break; if (path->slots[level] >= btrfs_header_nritems(path->nodes[level])) break; ret = do_walk_down(trans, root, path, wc); if (ret > 0) { path->slots[level]++; continue; } else if (ret < 0) break; level = wc->level; } return (ret == 1) ? 0 : ret; } /* * walk_up_tree() is responsible for making sure we visit every slot on our * current node, and if we're at the end of that node then we call * walk_up_proc() on our current node which will do one of a few things based on * our stage. * * UPDATE_BACKREF. If we wc->level is currently less than our wc->shared_level * then we need to walk back up the tree, and then going back down into the * other slots via walk_down_tree to update any other children from our original * wc->shared_level. Once we're at or above our wc->shared_level we can switch * back to DROP_REFERENCE, lookup the current nodes refs and flags, and carry on. * * DROP_REFERENCE. If our refs == 1 then we're going to free this tree block. * If we're level 0 then we need to btrfs_dec_ref() on all of the data extents * in our current leaf. After that we call btrfs_free_tree_block() on the * current node and walk up to the next node to walk down the next slot. */ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct walk_control *wc, int max_level) { int level = wc->level; int ret; path->slots[level] = btrfs_header_nritems(path->nodes[level]); while (level < max_level && path->nodes[level]) { wc->level = level; if (path->slots[level] + 1 < btrfs_header_nritems(path->nodes[level])) { path->slots[level]++; return 0; } else { ret = walk_up_proc(trans, root, path, wc); if (ret > 0) return 0; if (ret < 0) return ret; if (path->locks[level]) { btrfs_tree_unlock_rw(path->nodes[level], path->locks[level]); path->locks[level] = 0; } free_extent_buffer(path->nodes[level]); path->nodes[level] = NULL; level++; } } return 1; } /* * drop a subvolume tree. * * this function traverses the tree freeing any blocks that only * referenced by the tree. * * when a shared tree block is found. this function decreases its * reference count by one. if update_ref is true, this function * also make sure backrefs for the shared block and all lower level * blocks are properly updated. * * If called with for_reloc set, may exit early with -EAGAIN */ int btrfs_drop_snapshot(struct btrfs_root *root, bool update_ref, bool for_reloc) { const bool is_reloc_root = (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID); struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_path *path; struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root_item *root_item = &root->root_item; struct walk_control *wc; struct btrfs_key key; const u64 rootid = btrfs_root_id(root); int ret = 0; int level; bool root_dropped = false; bool unfinished_drop = false; btrfs_debug(fs_info, "Drop subvolume %llu", btrfs_root_id(root)); path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } wc = kzalloc(sizeof(*wc), GFP_NOFS); if (!wc) { btrfs_free_path(path); ret = -ENOMEM; goto out; } /* * Use join to avoid potential EINTR from transaction start. See * wait_reserve_ticket and the whole reservation callchain. */ if (for_reloc) trans = btrfs_join_transaction(tree_root); else trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_free; } ret = btrfs_run_delayed_items(trans); if (ret) goto out_end_trans; /* * This will help us catch people modifying the fs tree while we're * dropping it. It is unsafe to mess with the fs tree while it's being * dropped as we unlock the root node and parent nodes as we walk down * the tree, assuming nothing will change. If something does change * then we'll have stale information and drop references to blocks we've * already dropped. */ set_bit(BTRFS_ROOT_DELETING, &root->state); unfinished_drop = test_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state); if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) { level = btrfs_header_level(root->node); path->nodes[level] = btrfs_lock_root_node(root); path->slots[level] = 0; path->locks[level] = BTRFS_WRITE_LOCK; memset(&wc->update_progress, 0, sizeof(wc->update_progress)); } else { btrfs_disk_key_to_cpu(&key, &root_item->drop_progress); memcpy(&wc->update_progress, &key, sizeof(wc->update_progress)); level = btrfs_root_drop_level(root_item); BUG_ON(level == 0); path->lowest_level = level; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); path->lowest_level = 0; if (ret < 0) goto out_end_trans; WARN_ON(ret > 0); ret = 0; /* * unlock our path, this is safe because only this * function is allowed to delete this snapshot */ btrfs_unlock_up_safe(path, 0); level = btrfs_header_level(root->node); while (1) { btrfs_tree_lock(path->nodes[level]); path->locks[level] = BTRFS_WRITE_LOCK; /* * btrfs_lookup_extent_info() returns 0 for success, * or < 0 for error. */ ret = btrfs_lookup_extent_info(trans, fs_info, path->nodes[level]->start, level, 1, &wc->refs[level], &wc->flags[level], NULL); if (ret < 0) goto out_end_trans; BUG_ON(wc->refs[level] == 0); if (level == btrfs_root_drop_level(root_item)) break; btrfs_tree_unlock(path->nodes[level]); path->locks[level] = 0; WARN_ON(wc->refs[level] != 1); level--; } } wc->restarted = test_bit(BTRFS_ROOT_DEAD_TREE, &root->state); wc->level = level; wc->shared_level = -1; wc->stage = DROP_REFERENCE; wc->update_ref = update_ref; wc->keep_locks = 0; wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info); while (1) { ret = walk_down_tree(trans, root, path, wc); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); break; } ret = walk_up_tree(trans, root, path, wc, BTRFS_MAX_LEVEL); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); break; } if (ret > 0) { BUG_ON(wc->stage != DROP_REFERENCE); ret = 0; break; } if (wc->stage == DROP_REFERENCE) { wc->drop_level = wc->level; btrfs_node_key_to_cpu(path->nodes[wc->drop_level], &wc->drop_progress, path->slots[wc->drop_level]); } btrfs_cpu_key_to_disk(&root_item->drop_progress, &wc->drop_progress); btrfs_set_root_drop_level(root_item, wc->drop_level); BUG_ON(wc->level == 0); if (btrfs_should_end_transaction(trans) || (!for_reloc && btrfs_need_cleaner_sleep(fs_info))) { ret = btrfs_update_root(trans, tree_root, &root->root_key, root_item); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out_end_trans; } if (!is_reloc_root) btrfs_set_last_root_drop_gen(fs_info, trans->transid); btrfs_end_transaction_throttle(trans); if (!for_reloc && btrfs_need_cleaner_sleep(fs_info)) { btrfs_debug(fs_info, "drop snapshot early exit"); ret = -EAGAIN; goto out_free; } /* * Use join to avoid potential EINTR from transaction * start. See wait_reserve_ticket and the whole * reservation callchain. */ if (for_reloc) trans = btrfs_join_transaction(tree_root); else trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_free; } } } btrfs_release_path(path); if (ret) goto out_end_trans; ret = btrfs_del_root(trans, &root->root_key); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out_end_trans; } if (!is_reloc_root) { ret = btrfs_find_root(tree_root, &root->root_key, path, NULL, NULL); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out_end_trans; } else if (ret > 0) { ret = 0; /* * If we fail to delete the orphan item this time * around, it'll get picked up the next time. * * The most common failure here is just -ENOENT. */ btrfs_del_orphan_item(trans, tree_root, btrfs_root_id(root)); } } /* * This subvolume is going to be completely dropped, and won't be * recorded as dirty roots, thus pertrans meta rsv will not be freed at * commit transaction time. So free it here manually. */ btrfs_qgroup_convert_reserved_meta(root, INT_MAX); btrfs_qgroup_free_meta_all_pertrans(root); if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) btrfs_add_dropped_root(trans, root); else btrfs_put_root(root); root_dropped = true; out_end_trans: if (!is_reloc_root) btrfs_set_last_root_drop_gen(fs_info, trans->transid); btrfs_end_transaction_throttle(trans); out_free: kfree(wc); btrfs_free_path(path); out: if (!ret && root_dropped) { ret = btrfs_qgroup_cleanup_dropped_subvolume(fs_info, rootid); if (ret < 0) btrfs_warn_rl(fs_info, "failed to cleanup qgroup 0/%llu: %d", rootid, ret); ret = 0; } /* * We were an unfinished drop root, check to see if there are any * pending, and if not clear and wake up any waiters. */ if (!ret && unfinished_drop) btrfs_maybe_wake_unfinished_drop(fs_info); /* * So if we need to stop dropping the snapshot for whatever reason we * need to make sure to add it back to the dead root list so that we * keep trying to do the work later. This also cleans up roots if we * don't have it in the radix (like when we recover after a power fail * or unmount) so we don't leak memory. */ if (!for_reloc && !root_dropped) btrfs_add_dead_root(root); return ret; } /* * drop subtree rooted at tree block 'node'. * * NOTE: this function will unlock and release tree block 'node' * only used by relocation code */ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, struct extent_buffer *parent) { struct btrfs_fs_info *fs_info = root->fs_info; BTRFS_PATH_AUTO_FREE(path); struct walk_control *wc; int level; int parent_level; int ret = 0; BUG_ON(btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID); path = btrfs_alloc_path(); if (!path) return -ENOMEM; wc = kzalloc(sizeof(*wc), GFP_NOFS); if (!wc) return -ENOMEM; btrfs_assert_tree_write_locked(parent); parent_level = btrfs_header_level(parent); refcount_inc(&parent->refs); path->nodes[parent_level] = parent; path->slots[parent_level] = btrfs_header_nritems(parent); btrfs_assert_tree_write_locked(node); level = btrfs_header_level(node); path->nodes[level] = node; path->slots[level] = 0; path->locks[level] = BTRFS_WRITE_LOCK; wc->refs[parent_level] = 1; wc->flags[parent_level] = BTRFS_BLOCK_FLAG_FULL_BACKREF; wc->level = level; wc->shared_level = -1; wc->stage = DROP_REFERENCE; wc->update_ref = 0; wc->keep_locks = 1; wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info); while (1) { ret = walk_down_tree(trans, root, path, wc); if (ret < 0) break; ret = walk_up_tree(trans, root, path, wc, parent_level); if (ret) { if (ret > 0) ret = 0; break; } } kfree(wc); return ret; } /* * Unpin the extent range in an error context and don't add the space back. * Errors are not propagated further. */ void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end) { unpin_extent_range(fs_info, start, end, false); } /* * It used to be that old block groups would be left around forever. * Iterating over them would be enough to trim unused space. Since we * now automatically remove them, we also need to iterate over unallocated * space. * * We don't want a transaction for this since the discard may take a * substantial amount of time. We don't require that a transaction be * running, but we do need to take a running transaction into account * to ensure that we're not discarding chunks that were released or * allocated in the current transaction. * * Holding the chunks lock will prevent other threads from allocating * or releasing chunks, but it won't prevent a running transaction * from committing and releasing the memory that the pending chunks * list head uses. For that, we need to take a reference to the * transaction and hold the commit root sem. We only need to hold * it while performing the free space search since we have already * held back allocations. */ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) { u64 start = BTRFS_DEVICE_RANGE_RESERVED, len = 0, end = 0; int ret; *trimmed = 0; /* Discard not supported = nothing to do. */ if (!bdev_max_discard_sectors(device->bdev)) return 0; /* Not writable = nothing to do. */ if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) return 0; /* No free space = nothing to do. */ if (device->total_bytes <= device->bytes_used) return 0; ret = 0; while (1) { struct btrfs_fs_info *fs_info = device->fs_info; u64 bytes; ret = mutex_lock_interruptible(&fs_info->chunk_mutex); if (ret) break; btrfs_find_first_clear_extent_bit(&device->alloc_state, start, &start, &end, CHUNK_TRIMMED | CHUNK_ALLOCATED); /* Check if there are any CHUNK_* bits left */ if (start > device->total_bytes) { DEBUG_WARN(); btrfs_warn(fs_info, "ignoring attempt to trim beyond device size: offset %llu length %llu device %s device size %llu", start, end - start + 1, btrfs_dev_name(device), device->total_bytes); mutex_unlock(&fs_info->chunk_mutex); ret = 0; break; } /* Ensure we skip the reserved space on each device. */ start = max_t(u64, start, BTRFS_DEVICE_RANGE_RESERVED); /* * If find_first_clear_extent_bit find a range that spans the * end of the device it will set end to -1, in this case it's up * to the caller to trim the value to the size of the device. */ end = min(end, device->total_bytes - 1); len = end - start + 1; /* We didn't find any extents */ if (!len) { mutex_unlock(&fs_info->chunk_mutex); ret = 0; break; } ret = btrfs_issue_discard(device->bdev, start, len, &bytes); if (!ret) btrfs_set_extent_bit(&device->alloc_state, start, start + bytes - 1, CHUNK_TRIMMED, NULL); mutex_unlock(&fs_info->chunk_mutex); if (ret) break; start += len; *trimmed += bytes; if (btrfs_trim_interrupted()) { ret = -ERESTARTSYS; break; } cond_resched(); } return ret; } /* * Trim the whole filesystem by: * 1) trimming the free space in each block group * 2) trimming the unallocated space on each device * * This will also continue trimming even if a block group or device encounters * an error. The return value will be the last error, or 0 if nothing bad * happens. */ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_block_group *cache = NULL; struct btrfs_device *device; u64 group_trimmed; u64 range_end = U64_MAX; u64 start; u64 end; u64 trimmed = 0; u64 bg_failed = 0; u64 dev_failed = 0; int bg_ret = 0; int dev_ret = 0; int ret = 0; if (range->start == U64_MAX) return -EINVAL; /* * Check range overflow if range->len is set. * The default range->len is U64_MAX. */ if (range->len != U64_MAX && check_add_overflow(range->start, range->len, &range_end)) return -EINVAL; cache = btrfs_lookup_first_block_group(fs_info, range->start); for (; cache; cache = btrfs_next_block_group(cache)) { if (cache->start >= range_end) { btrfs_put_block_group(cache); break; } start = max(range->start, cache->start); end = min(range_end, cache->start + cache->length); if (end - start >= range->minlen) { if (!btrfs_block_group_done(cache)) { ret = btrfs_cache_block_group(cache, true); if (ret) { bg_failed++; bg_ret = ret; continue; } } ret = btrfs_trim_block_group(cache, &group_trimmed, start, end, range->minlen); trimmed += group_trimmed; if (ret) { bg_failed++; bg_ret = ret; continue; } } } if (bg_failed) btrfs_warn(fs_info, "failed to trim %llu block group(s), last error %d", bg_failed, bg_ret); mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry(device, &fs_devices->devices, dev_list) { if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) continue; ret = btrfs_trim_free_extents(device, &group_trimmed); trimmed += group_trimmed; if (ret) { dev_failed++; dev_ret = ret; break; } } mutex_unlock(&fs_devices->device_list_mutex); if (dev_failed) btrfs_warn(fs_info, "failed to trim %llu device(s), last error %d", dev_failed, dev_ret); range->len = trimmed; if (bg_ret) return bg_ret; return dev_ret; } |
| 280 286 286 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Client Manager * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_CLIENTMGR_H #define __SND_SEQ_CLIENTMGR_H #include <sound/seq_kernel.h> #include <linux/bitops.h> #include "seq_fifo.h" #include "seq_ports.h" #include "seq_lock.h" /* client manager */ struct snd_seq_user_client { struct file *file; /* file struct of client */ /* ... */ struct pid *owner; /* fifo */ struct snd_seq_fifo *fifo; /* queue for incoming events */ int fifo_pool_size; }; struct snd_seq_kernel_client { /* ... */ struct snd_card *card; }; struct snd_seq_client { snd_seq_client_type_t type; unsigned int accept_input: 1, accept_output: 1; unsigned int midi_version; unsigned int user_pversion; char name[64]; /* client name */ int number; /* client number */ unsigned int filter; /* filter flags */ DECLARE_BITMAP(event_filter, 256); unsigned short group_filter; snd_use_lock_t use_lock; int event_lost; /* ports */ int num_ports; /* number of ports */ struct list_head ports_list_head; rwlock_t ports_lock; struct mutex ports_mutex; struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ int ump_endpoint_port; /* output pool */ struct snd_seq_pool *pool; /* memory pool for this client */ union { struct snd_seq_user_client user; struct snd_seq_kernel_client kernel; } data; /* for UMP */ void **ump_info; }; /* usage statistics */ struct snd_seq_usage { int cur; int peak; }; int client_init_data(void); int snd_sequencer_device_init(void); void snd_sequencer_device_done(void); /* get locked pointer to client */ struct snd_seq_client *snd_seq_client_use_ptr(int clientid); static inline struct snd_seq_client * snd_seq_client_ref(struct snd_seq_client *client) { snd_use_lock_use(&client->use_lock); return client; } /* unlock pointer to client */ static inline void snd_seq_client_unref(struct snd_seq_client *client) { snd_use_lock_free(&client->use_lock); } DEFINE_FREE(snd_seq_client, struct snd_seq_client *, if (!IS_ERR_OR_NULL(_T)) snd_seq_client_unref(_T)) /* dispatch event to client(s) */ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop); int snd_seq_kernel_client_write_poll(int clientid, struct file *file, poll_table *wait); int snd_seq_client_notify_subscription(int client, int port, struct snd_seq_port_subscribe *info, int evtype); int __snd_seq_deliver_single_event(struct snd_seq_client *dest, struct snd_seq_client_port *dest_port, struct snd_seq_event *event, int atomic, int hop); /* only for OSS sequencer */ int snd_seq_kernel_client_ioctl(int clientid, unsigned int cmd, void *arg); extern int seq_client_load[15]; /* for internal use between kernel sequencer clients */ struct snd_seq_client *snd_seq_kernel_client_get(int client); void snd_seq_kernel_client_put(struct snd_seq_client *cptr); static inline bool snd_seq_client_is_ump(struct snd_seq_client *c) { return c->midi_version != SNDRV_SEQ_CLIENT_LEGACY_MIDI; } static inline bool snd_seq_client_is_midi2(struct snd_seq_client *c) { return c->midi_version == SNDRV_SEQ_CLIENT_UMP_MIDI_2_0; } #endif |
| 26 20 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/net.h> #include <linux/uio.h> #include <net/sock.h> #include <linux/nospec.h> #include "rsrc.h" #define IO_NOTIF_UBUF_FLAGS (SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN) #define IO_NOTIF_SPLICE_BATCH 32 struct io_notif_data { struct file *file; struct ubuf_info uarg; struct io_notif_data *next; struct io_notif_data *head; unsigned account_pages; bool zc_report; bool zc_used; bool zc_copied; }; struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx); void io_tx_ubuf_complete(struct sk_buff *skb, struct ubuf_info *uarg, bool success); static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif) { return io_kiocb_to_cmd(notif, struct io_notif_data); } static inline void io_notif_flush(struct io_kiocb *notif) __must_hold(¬if->ctx->uring_lock) { struct io_notif_data *nd = io_notif_to_data(notif); io_tx_ubuf_complete(NULL, &nd->uarg, true); } static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len) { struct io_ring_ctx *ctx = notif->ctx; struct io_notif_data *nd = io_notif_to_data(notif); unsigned nr_pages = (len >> PAGE_SHIFT) + 2; int ret; if (ctx->user) { ret = __io_account_mem(ctx->user, nr_pages); if (ret) return ret; nd->account_pages += nr_pages; } return 0; } |
| 3 3 3 3 3 3 3 3 3 1 3 3 1 1 1 1 1 3 3 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include <linux/phy.h> #include <linux/phylib_stubs.h> struct linkstate_req_info { struct ethnl_req_info base; }; struct linkstate_reply_data { struct ethnl_reply_data base; int link; int sqi; int sqi_max; struct ethtool_link_ext_stats link_stats; bool link_ext_state_provided; struct ethtool_link_ext_state_info ethtool_link_ext_state_info; }; #define LINKSTATE_REPDATA(__reply_base) \ container_of(__reply_base, struct linkstate_reply_data, base) const struct nla_policy ethnl_linkstate_get_policy[] = { [ETHTOOL_A_LINKSTATE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int linkstate_get_sqi(struct phy_device *phydev) { int ret; if (!phydev) return -EOPNOTSUPP; mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi) ret = -EOPNOTSUPP; else if (!phydev->link) ret = -ENETDOWN; else ret = phydev->drv->get_sqi(phydev); mutex_unlock(&phydev->lock); return ret; } static int linkstate_get_sqi_max(struct phy_device *phydev) { int ret; if (!phydev) return -EOPNOTSUPP; mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi_max) ret = -EOPNOTSUPP; else if (!phydev->link) ret = -ENETDOWN; else ret = phydev->drv->get_sqi_max(phydev); mutex_unlock(&phydev->lock); return ret; }; static bool linkstate_sqi_critical_error(int sqi) { return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN; } static bool linkstate_sqi_valid(struct linkstate_reply_data *data) { return data->sqi >= 0 && data->sqi_max >= 0 && data->sqi <= data->sqi_max; } static int linkstate_get_link_ext_state(struct net_device *dev, struct linkstate_reply_data *data) { int err; if (!dev->ethtool_ops->get_link_ext_state) return -EOPNOTSUPP; err = dev->ethtool_ops->get_link_ext_state(dev, &data->ethtool_link_ext_state_info); if (err) return err; data->link_ext_state_provided = true; return 0; } static int linkstate_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_LINKSTATE_HEADER, info->extack); if (IS_ERR(phydev)) { ret = PTR_ERR(phydev); goto out; } ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->link = __ethtool_get_link(dev); ret = linkstate_get_sqi(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; ret = linkstate_get_sqi_max(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; if (dev->flags & IFF_UP) { ret = linkstate_get_link_ext_state(dev, data); if (ret < 0 && ret != -EOPNOTSUPP && ret != -ENODATA) goto out; } ethtool_stats_init((u64 *)&data->link_stats, sizeof(data->link_stats) / 8); if (req_base->flags & ETHTOOL_FLAG_STATS) { if (phydev) phy_ethtool_get_link_ext_stats(phydev, &data->link_stats); if (dev->ethtool_ops->get_link_ext_stats) dev->ethtool_ops->get_link_ext_stats(dev, &data->link_stats); } ret = 0; out: ethnl_ops_complete(dev); return ret; } static int linkstate_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); int len; len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + 0; if (linkstate_sqi_valid(data)) { len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */ len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */ } if (data->link_ext_state_provided) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */ if (data->ethtool_link_ext_state_info.__link_ext_substate) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */ if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) len += nla_total_size(sizeof(u32)); return len; } static int linkstate_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); if (data->link >= 0 && nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) return -EMSGSIZE; if (linkstate_sqi_valid(data)) { if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) return -EMSGSIZE; } if (data->link_ext_state_provided) { if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE, data->ethtool_link_ext_state_info.link_ext_state)) return -EMSGSIZE; if (data->ethtool_link_ext_state_info.__link_ext_substate && nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, data->ethtool_link_ext_state_info.__link_ext_substate)) return -EMSGSIZE; } if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, data->link_stats.link_down_events)) return -EMSGSIZE; return 0; } const struct ethnl_request_ops ethnl_linkstate_request_ops = { .request_cmd = ETHTOOL_MSG_LINKSTATE_GET, .reply_cmd = ETHTOOL_MSG_LINKSTATE_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKSTATE_HEADER, .req_info_size = sizeof(struct linkstate_req_info), .reply_data_size = sizeof(struct linkstate_reply_data), .prepare_data = linkstate_prepare_data, .reply_size = linkstate_reply_size, .fill_reply = linkstate_fill_reply, }; |
| 209 128 207 148 149 209 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | #include <linux/dcache.h> #include "internal.h" unsigned name_to_int(const struct qstr *qstr) { const char *name = qstr->name; int len = qstr->len; unsigned n = 0; if (len > 1 && *name == '0') goto out; do { unsigned c = *name++ - '0'; if (c > 9) goto out; if (n >= (~0U-9)/10) goto out; n *= 10; n += c; } while (--len > 0); return n; out: return ~0U; } |
| 15 46 39 56 24 24 5 5 173 72 175 1 1 44 44 41 44 35 35 35 12 12 12 5 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_err_rcv_t encap_err_rcv; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck, u16 ipcb_flags); void udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck, u16 ip6cb_flags); void udp_tunnel_sock_release(struct socket *sock); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, int oif, __be32 *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 tos, struct dst_cache *dst_cache); struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, const unsigned long *flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif #if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add); void udp_tunnel_update_gro_rcv(struct sock *sk, bool add); #else static inline void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add) {} static inline void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) {} #endif static inline void udp_tunnel_cleanup_gro(struct sock *sk) { udp_tunnel_update_gro_rcv(sk, false); udp_tunnel_update_gro_lookup(sock_net(sk), sk, false); } static inline void udp_tunnel_encap_enable(struct sock *sk) { if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) return; #if IS_ENABLED(CONFIG_IPV6) if (READ_ONCE(sk->sk_family) == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(0), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(1), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(2), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); void (*assert_locked)(struct net_device *dev); void (*lock)(struct net_device *dev); void (*unlock)(struct net_device *dev); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) { udp_tunnel_nic_ops->assert_locked(dev); udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } } static inline void udp_tunnel_nic_assert_locked(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->assert_locked(dev); } static inline void udp_tunnel_nic_lock(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->lock(dev); } static inline void udp_tunnel_nic_unlock(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->unlock(dev); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { size_t ret; if (!udp_tunnel_nic_ops) return 0; udp_tunnel_nic_ops->lock(dev); ret = udp_tunnel_nic_ops->dump_size(dev, table); udp_tunnel_nic_ops->unlock(dev); return ret; } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { int ret; if (!udp_tunnel_nic_ops) return 0; udp_tunnel_nic_ops->lock(dev); ret = udp_tunnel_nic_ops->dump_write(dev, table, skb); udp_tunnel_nic_ops->unlock(dev); return ret; } static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; udp_tunnel_nic_assert_locked(dev); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; udp_tunnel_nic_assert_locked(dev); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } #endif |
| 11 11 10 10 11 17 17 | 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 | /* * linux/fs/nls/nls_cp857.c * * Charset cp857 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7, 0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x0131, 0x00c4, 0x00c5, /* 0x90*/ 0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9, 0x0130, 0x00d6, 0x00dc, 0x00f8, 0x00a3, 0x00d8, 0x015e, 0x015f, /* 0xa0*/ 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x011e, 0x011f, 0x00bf, 0x00ae, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x00c1, 0x00c2, 0x00c0, 0x00a9, 0x2563, 0x2551, 0x2557, 0x255d, 0x00a2, 0x00a5, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x00e3, 0x00c3, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4, /* 0xd0*/ 0x00ba, 0x00aa, 0x00ca, 0x00cb, 0x00c8, 0x0000, 0x00cd, 0x00ce, 0x00cf, 0x2518, 0x250c, 0x2588, 0x2584, 0x00a6, 0x00cc, 0x2580, /* 0xe0*/ 0x00d3, 0x00df, 0x00d4, 0x00d2, 0x00f5, 0x00d5, 0x00b5, 0x0000, 0x00d7, 0x00da, 0x00db, 0x00d9, 0x00ec, 0x00ff, 0x00af, 0x00b4, /* 0xf0*/ 0x00ad, 0x00b1, 0x0000, 0x00be, 0x00b6, 0x00a7, 0x00f7, 0x00b8, 0x00b0, 0x00a8, 0x00b7, 0x00b9, 0x00b3, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0xad, 0xbd, 0x9c, 0xcf, 0xbe, 0xdd, 0xf5, /* 0xa0-0xa7 */ 0xf9, 0xb8, 0xd1, 0xae, 0xaa, 0xf0, 0xa9, 0xee, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0xfc, 0xef, 0xe6, 0xf4, 0xfa, /* 0xb0-0xb7 */ 0xf7, 0xfb, 0xd0, 0xaf, 0xac, 0xab, 0xf3, 0xa8, /* 0xb8-0xbf */ 0xb7, 0xb5, 0xb6, 0xc7, 0x8e, 0x8f, 0x92, 0x80, /* 0xc0-0xc7 */ 0xd4, 0x90, 0xd2, 0xd3, 0xde, 0xd6, 0xd7, 0xd8, /* 0xc8-0xcf */ 0x00, 0xa5, 0xe3, 0xe0, 0xe2, 0xe5, 0x99, 0xe8, /* 0xd0-0xd7 */ 0x9d, 0xeb, 0xe9, 0xea, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x85, 0xa0, 0x83, 0xc6, 0x84, 0x86, 0x91, 0x87, /* 0xe0-0xe7 */ 0x8a, 0x82, 0x88, 0x89, 0xec, 0xa1, 0x8c, 0x8b, /* 0xe8-0xef */ 0x00, 0xa4, 0x95, 0xa2, 0x93, 0xe4, 0x94, 0xf6, /* 0xf0-0xf7 */ 0x9b, 0x97, 0xa3, 0x96, 0x81, 0x00, 0x00, 0xed, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa6, 0xa7, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x98, 0x8d, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x9e, 0x9f, /* 0x58-0x5f */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0x00, 0x00, 0xc9, 0x00, 0x00, 0xbb, /* 0x50-0x57 */ 0x00, 0x00, 0xc8, 0x00, 0x00, 0xbc, 0x00, 0x00, /* 0x58-0x5f */ 0xcc, 0x00, 0x00, 0xb9, 0x00, 0x00, 0xcb, 0x00, /* 0x60-0x67 */ 0x00, 0xca, 0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x84, 0x86, /* 0x88-0x8f */ 0x82, 0x91, 0x91, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x69, 0x94, 0x81, 0x9b, 0x9c, 0x9b, 0x9f, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa4, 0xa7, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xa0, 0x83, 0x85, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc6, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0x88, 0x89, 0x8a, 0x00, 0xa1, 0x8c, /* 0xd0-0xd7 */ 0x8b, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xec, 0xdf, /* 0xd8-0xdf */ 0xa2, 0xe1, 0x93, 0x95, 0xe4, 0xe4, 0xe6, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xa3, 0x96, 0x97, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0x00, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0xb6, 0x8e, 0xb7, 0x8f, 0x80, /* 0x80-0x87 */ 0xd2, 0xd3, 0xd4, 0xd8, 0xd7, 0x49, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x92, 0x92, 0xe2, 0x99, 0xe3, 0xea, 0xeb, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9d, 0x9c, 0x9d, 0x9e, 0x9e, /* 0x98-0x9f */ 0xb5, 0xd6, 0xe0, 0xe9, 0xa5, 0xa5, 0xa6, 0xa6, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc7, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0x00, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe5, 0xe5, 0x00, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xde, 0x00, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0x00, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp857", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp857(void) { return register_nls(&table); } static void __exit exit_nls_cp857(void) { unregister_nls(&table); } module_init(init_nls_cp857) module_exit(exit_nls_cp857) MODULE_DESCRIPTION("NLS Codepage 857 (Turkish)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 77 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi_bus.h - ACPI Bus Driver ($Revision: 22 $) * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef __ACPI_BUS_H__ #define __ACPI_BUS_H__ #include <linux/completion.h> #include <linux/container_of.h> #include <linux/device.h> #include <linux/kobject.h> #include <linux/mutex.h> #include <linux/property.h> #include <linux/types.h> struct acpi_handle_list { u32 count; acpi_handle *handles; }; /* acpi_utils.h */ acpi_status acpi_extract_package(union acpi_object *package, struct acpi_buffer *format, struct acpi_buffer *buffer); acpi_status acpi_evaluate_integer(acpi_handle handle, acpi_string pathname, struct acpi_object_list *arguments, unsigned long long *data); bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname, struct acpi_object_list *arguments, struct acpi_handle_list *list); bool acpi_handle_list_equal(struct acpi_handle_list *list1, struct acpi_handle_list *list2); void acpi_handle_list_replace(struct acpi_handle_list *dst, struct acpi_handle_list *src); void acpi_handle_list_free(struct acpi_handle_list *list); bool acpi_device_dep(acpi_handle target, acpi_handle match); acpi_status acpi_evaluate_ost(acpi_handle handle, u32 source_event, u32 status_code, struct acpi_buffer *status_buf); bool acpi_has_method(acpi_handle handle, char *name); acpi_status acpi_execute_simple_method(acpi_handle handle, char *method, u64 arg); acpi_status acpi_evaluate_ej0(acpi_handle handle); acpi_status acpi_evaluate_lck(acpi_handle handle, int lock); acpi_status acpi_evaluate_reg(acpi_handle handle, u8 space_id, u32 function); bool acpi_ata_match(acpi_handle handle); bool acpi_bay_match(acpi_handle handle); bool acpi_dock_match(acpi_handle handle); bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs); union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4); #ifdef CONFIG_ACPI bool acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld); static inline union acpi_object * acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4, acpi_object_type type) { union acpi_object *obj; obj = acpi_evaluate_dsm(handle, guid, rev, func, argv4); if (obj && obj->type != type) { ACPI_FREE(obj); obj = NULL; } return obj; } #endif #define ACPI_INIT_DSM_ARGV4(cnt, eles) \ { \ .package.type = ACPI_TYPE_PACKAGE, \ .package.count = (cnt), \ .package.elements = (eles) \ } bool acpi_dev_found(const char *hid); bool acpi_dev_present(const char *hid, const char *uid, s64 hrv); bool acpi_reduced_hardware(void); #ifdef CONFIG_ACPI struct proc_dir_entry; #define ACPI_BUS_FILE_ROOT "acpi" extern struct proc_dir_entry *acpi_root_dir; enum acpi_bus_device_type { ACPI_BUS_TYPE_DEVICE = 0, ACPI_BUS_TYPE_POWER, ACPI_BUS_TYPE_PROCESSOR, ACPI_BUS_TYPE_THERMAL, ACPI_BUS_TYPE_POWER_BUTTON, ACPI_BUS_TYPE_SLEEP_BUTTON, ACPI_BUS_TYPE_ECDT_EC, ACPI_BUS_DEVICE_TYPE_COUNT }; struct acpi_driver; struct acpi_device; /* * ACPI Scan Handler * ----------------- */ struct acpi_hotplug_profile { struct kobject kobj; int (*scan_dependent)(struct acpi_device *adev); void (*notify_online)(struct acpi_device *adev); bool enabled:1; bool demand_offline:1; }; static inline struct acpi_hotplug_profile *to_acpi_hotplug_profile( struct kobject *kobj) { return container_of(kobj, struct acpi_hotplug_profile, kobj); } struct acpi_scan_handler { struct list_head list_node; const struct acpi_device_id *ids; bool (*match)(const char *idstr, const struct acpi_device_id **matchid); int (*attach)(struct acpi_device *dev, const struct acpi_device_id *id); void (*detach)(struct acpi_device *dev); void (*post_eject)(struct acpi_device *dev); void (*bind)(struct device *phys_dev); void (*unbind)(struct device *phys_dev); struct acpi_hotplug_profile hotplug; }; /* * ACPI Hotplug Context * -------------------- */ typedef int (*acpi_hp_notify) (struct acpi_device *, u32); typedef void (*acpi_hp_uevent) (struct acpi_device *, u32); typedef void (*acpi_hp_fixup) (struct acpi_device *); struct acpi_hotplug_context { struct acpi_device *self; acpi_hp_notify notify; acpi_hp_uevent uevent; acpi_hp_fixup fixup; }; /* * ACPI Driver * ----------- */ typedef int (*acpi_op_add) (struct acpi_device * device); typedef void (*acpi_op_remove) (struct acpi_device *device); typedef void (*acpi_op_notify) (struct acpi_device * device, u32 event); struct acpi_device_ops { acpi_op_add add; acpi_op_remove remove; acpi_op_notify notify; }; #define ACPI_DRIVER_ALL_NOTIFY_EVENTS 0x1 /* system AND device events */ struct acpi_driver { char name[80]; char class[80]; const struct acpi_device_id *ids; /* Supported Hardware IDs */ unsigned int flags; struct acpi_device_ops ops; struct device_driver drv; }; /* * ACPI Device * ----------- */ /* Status (_STA) */ struct acpi_device_status { u32 present:1; u32 enabled:1; u32 show_in_ui:1; u32 functional:1; u32 battery_present:1; u32 reserved:27; }; /* Flags */ struct acpi_device_flags { u32 dynamic_status:1; u32 removable:1; u32 ejectable:1; u32 power_manageable:1; u32 match_driver:1; u32 initialized:1; u32 visited:1; u32 hotplug_notify:1; u32 is_dock_station:1; u32 of_compatible_ok:1; u32 coherent_dma:1; u32 cca_seen:1; u32 enumeration_by_parent:1; u32 honor_deps:1; u32 reserved:18; }; /* File System */ struct acpi_device_dir { struct proc_dir_entry *entry; }; #define acpi_device_dir(d) ((d)->dir.entry) /* Plug and Play */ #define MAX_ACPI_DEVICE_NAME_LEN 40 #define MAX_ACPI_CLASS_NAME_LEN 20 typedef char acpi_bus_id[8]; typedef u64 acpi_bus_address; typedef char acpi_device_name[MAX_ACPI_DEVICE_NAME_LEN]; typedef char acpi_device_class[MAX_ACPI_CLASS_NAME_LEN]; struct acpi_hardware_id { struct list_head list; const char *id; }; struct acpi_pnp_type { u32 hardware_id:1; u32 bus_address:1; u32 platform_id:1; u32 backlight:1; u32 reserved:28; }; struct acpi_device_pnp { acpi_bus_id bus_id; /* Object name */ int instance_no; /* Instance number of this object */ struct acpi_pnp_type type; /* ID type */ acpi_bus_address bus_address; /* _ADR */ char *unique_id; /* _UID */ struct list_head ids; /* _HID and _CIDs */ acpi_device_name device_name; /* Driver-determined */ acpi_device_class device_class; /* " */ }; #define acpi_device_bid(d) ((d)->pnp.bus_id) #define acpi_device_adr(d) ((d)->pnp.bus_address) const char *acpi_device_hid(struct acpi_device *device); #define acpi_device_uid(d) ((d)->pnp.unique_id) #define acpi_device_name(d) ((d)->pnp.device_name) #define acpi_device_class(d) ((d)->pnp.device_class) /* Power Management */ struct acpi_device_power_flags { u32 explicit_get:1; /* _PSC present? */ u32 power_resources:1; /* Power resources */ u32 inrush_current:1; /* Serialize Dx->D0 */ u32 power_removed:1; /* Optimize Dx->D0 */ u32 ignore_parent:1; /* Power is independent of parent power state */ u32 dsw_present:1; /* _DSW present? */ u32 reserved:26; }; struct acpi_device_power_state { struct list_head resources; /* Power resources referenced */ struct { u8 valid:1; u8 explicit_set:1; /* _PSx present? */ u8 reserved:6; } flags; int power; /* % Power (compared to D0) */ int latency; /* Dx->D0 time (microseconds) */ }; struct acpi_device_power { int state; /* Current state */ struct acpi_device_power_flags flags; struct acpi_device_power_state states[ACPI_D_STATE_COUNT]; /* Power states (D0-D3Cold) */ u8 state_for_enumeration; /* Deepest power state for enumeration */ }; struct acpi_dep_data { struct list_head node; acpi_handle supplier; acpi_handle consumer; bool honor_dep; bool met; bool free_when_met; }; /* Performance Management */ struct acpi_device_perf_flags { u8 reserved:8; }; struct acpi_device_perf_state { struct { u8 valid:1; u8 reserved:7; } flags; u8 power; /* % Power (compared to P0) */ u8 performance; /* % Performance ( " ) */ int latency; /* Px->P0 time (microseconds) */ }; struct acpi_device_perf { int state; struct acpi_device_perf_flags flags; int state_count; struct acpi_device_perf_state *states; }; /* Wakeup Management */ struct acpi_device_wakeup_flags { u8 valid:1; /* Can successfully enable wakeup? */ u8 notifier_present:1; /* Wake-up notify handler has been installed */ }; struct acpi_device_wakeup_context { void (*func)(struct acpi_device_wakeup_context *context); struct device *dev; }; struct acpi_device_wakeup { acpi_handle gpe_device; u64 gpe_number; u64 sleep_state; struct list_head resources; struct acpi_device_wakeup_flags flags; struct acpi_device_wakeup_context context; struct wakeup_source *ws; int prepare_count; int enable_count; }; struct acpi_device_physical_node { struct list_head node; struct device *dev; unsigned int node_id; bool put_online:1; }; struct acpi_device_properties { struct list_head list; const guid_t *guid; union acpi_object *properties; void **bufs; }; /* ACPI Device Specific Data (_DSD) */ struct acpi_device_data { const union acpi_object *pointer; struct list_head properties; const union acpi_object *of_compatible; struct list_head subnodes; }; struct acpi_gpio_mapping; #define ACPI_DEVICE_SWNODE_ROOT 0 /* * The maximum expected number of CSI-2 data lanes. * * This number is not expected to ever have to be equal to or greater than the * number of bits in an unsigned long variable, but if it needs to be increased * above that limit, code will need to be adjusted accordingly. */ #define ACPI_DEVICE_CSI2_DATA_LANES 8 #define ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH 8 enum acpi_device_swnode_dev_props { ACPI_DEVICE_SWNODE_DEV_ROTATION, ACPI_DEVICE_SWNODE_DEV_CLOCK_FREQUENCY, ACPI_DEVICE_SWNODE_DEV_LED_MAX_MICROAMP, ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_MICROAMP, ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_TIMEOUT_US, ACPI_DEVICE_SWNODE_DEV_NUM_OF, ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES }; enum acpi_device_swnode_port_props { ACPI_DEVICE_SWNODE_PORT_REG, ACPI_DEVICE_SWNODE_PORT_NUM_OF, ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES }; enum acpi_device_swnode_ep_props { ACPI_DEVICE_SWNODE_EP_REMOTE_EP, ACPI_DEVICE_SWNODE_EP_BUS_TYPE, ACPI_DEVICE_SWNODE_EP_REG, ACPI_DEVICE_SWNODE_EP_CLOCK_LANES, ACPI_DEVICE_SWNODE_EP_DATA_LANES, ACPI_DEVICE_SWNODE_EP_LANE_POLARITIES, /* TX only */ ACPI_DEVICE_SWNODE_EP_LINK_FREQUENCIES, ACPI_DEVICE_SWNODE_EP_NUM_OF, ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES }; /* * Each device has a root software node plus two times as many nodes as the * number of CSI-2 ports. */ #define ACPI_DEVICE_SWNODE_PORT(port) (2 * (port) + 1) #define ACPI_DEVICE_SWNODE_EP(endpoint) \ (ACPI_DEVICE_SWNODE_PORT(endpoint) + 1) /** * struct acpi_device_software_node_port - MIPI DisCo for Imaging CSI-2 port * @port_name: Port name. * @data_lanes: "data-lanes" property values. * @lane_polarities: "lane-polarities" property values. * @link_frequencies: "link_frequencies" property values. * @port_nr: Port number. * @crs_crs2_local: _CRS CSI2 record present (i.e. this is a transmitter one). * @port_props: Port properties. * @ep_props: Endpoint properties. * @remote_ep: Reference to the remote endpoint. */ struct acpi_device_software_node_port { char port_name[ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH + 1]; u32 data_lanes[ACPI_DEVICE_CSI2_DATA_LANES]; u32 lane_polarities[ACPI_DEVICE_CSI2_DATA_LANES + 1 /* clock lane */]; u64 link_frequencies[ACPI_DEVICE_CSI2_DATA_LANES]; unsigned int port_nr; bool crs_csi2_local; struct property_entry port_props[ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES]; struct property_entry ep_props[ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES]; struct software_node_ref_args remote_ep[1]; }; /** * struct acpi_device_software_nodes - Software nodes for an ACPI device * @dev_props: Device properties. * @nodes: Software nodes for root as well as ports and endpoints. * @nodeprts: Array of software node pointers, for (un)registering them. * @ports: Information related to each port and endpoint within a port. * @num_ports: The number of ports. */ struct acpi_device_software_nodes { struct property_entry dev_props[ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES]; struct software_node *nodes; const struct software_node **nodeptrs; struct acpi_device_software_node_port *ports; unsigned int num_ports; }; /* Device */ struct acpi_device { u32 pld_crc; int device_type; acpi_handle handle; /* no handle for fixed hardware */ struct fwnode_handle fwnode; struct list_head wakeup_list; struct list_head del_list; struct acpi_device_status status; struct acpi_device_flags flags; struct acpi_device_pnp pnp; struct acpi_device_power power; struct acpi_device_wakeup wakeup; struct acpi_device_perf performance; struct acpi_device_dir dir; struct acpi_device_data data; struct acpi_scan_handler *handler; struct acpi_hotplug_context *hp; struct acpi_device_software_nodes *swnodes; const struct acpi_gpio_mapping *driver_gpios; void *driver_data; struct device dev; unsigned int physical_node_count; unsigned int dep_unmet; struct list_head physical_node_list; struct mutex physical_node_lock; void (*remove)(struct acpi_device *); }; /* Non-device subnode */ struct acpi_data_node { struct list_head sibling; const char *name; acpi_handle handle; struct fwnode_handle fwnode; struct fwnode_handle *parent; struct acpi_device_data data; struct kobject kobj; struct completion kobj_done; }; extern const struct fwnode_operations acpi_device_fwnode_ops; extern const struct fwnode_operations acpi_data_fwnode_ops; extern const struct fwnode_operations acpi_static_fwnode_ops; bool is_acpi_device_node(const struct fwnode_handle *fwnode); bool is_acpi_data_node(const struct fwnode_handle *fwnode); static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return (is_acpi_device_node(fwnode) || is_acpi_data_node(fwnode)); } #define to_acpi_device_node(__fwnode) \ ({ \ typeof(__fwnode) __to_acpi_device_node_fwnode = __fwnode; \ \ is_acpi_device_node(__to_acpi_device_node_fwnode) ? \ container_of(__to_acpi_device_node_fwnode, \ struct acpi_device, fwnode) : \ NULL; \ }) #define to_acpi_data_node(__fwnode) \ ({ \ typeof(__fwnode) __to_acpi_data_node_fwnode = __fwnode; \ \ is_acpi_data_node(__to_acpi_data_node_fwnode) ? \ container_of(__to_acpi_data_node_fwnode, \ struct acpi_data_node, fwnode) : \ NULL; \ }) static inline bool is_acpi_static_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_static_fwnode_ops; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return is_acpi_data_node(fwnode) ? (!strcmp(to_acpi_data_node(fwnode)->name, name)) : false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return &adev->fwnode; } static inline void *acpi_driver_data(struct acpi_device *d) { return d->driver_data; } #define to_acpi_device(d) container_of(d, struct acpi_device, dev) #define to_acpi_driver(d) container_of_const(d, struct acpi_driver, drv) static inline struct acpi_device *acpi_dev_parent(struct acpi_device *adev) { if (adev->dev.parent) return to_acpi_device(adev->dev.parent); return NULL; } static inline void acpi_set_device_status(struct acpi_device *adev, u32 sta) { *((u32 *)&adev->status) = sta; } static inline void acpi_set_hp_context(struct acpi_device *adev, struct acpi_hotplug_context *hp) { hp->self = adev; adev->hp = hp; } void acpi_initialize_hp_context(struct acpi_device *adev, struct acpi_hotplug_context *hp, acpi_hp_notify notify, acpi_hp_uevent uevent); /* acpi_device.dev.bus == &acpi_bus_type */ extern const struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); int acpi_dev_for_each_child(struct acpi_device *adev, int (*fn)(struct acpi_device *, void *), void *data); int acpi_dev_for_each_child_reverse(struct acpi_device *adev, int (*fn)(struct acpi_device *, void *), void *data); /* * Events * ------ */ struct acpi_bus_event { struct list_head node; acpi_device_class device_class; acpi_bus_id bus_id; u32 type; u32 data; }; extern struct kobject *acpi_kobj; extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int); void acpi_bus_private_data_handler(acpi_handle, void *); int acpi_bus_get_private_data(acpi_handle, void **); int acpi_bus_attach_private_data(acpi_handle, void *); void acpi_bus_detach_private_data(acpi_handle); int acpi_dev_install_notify_handler(struct acpi_device *adev, u32 handler_type, acpi_notify_handler handler, void *context); void acpi_dev_remove_notify_handler(struct acpi_device *adev, u32 handler_type, acpi_notify_handler handler); extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32); extern int register_acpi_notifier(struct notifier_block *); extern int unregister_acpi_notifier(struct notifier_block *); /* * External Functions */ acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); int acpi_bus_get_status(struct acpi_device *device); int acpi_bus_set_power(acpi_handle handle, int state); const char *acpi_power_state_string(int state); int acpi_device_set_power(struct acpi_device *device, int state); int acpi_bus_init_power(struct acpi_device *device); int acpi_device_fix_up_power(struct acpi_device *device); void acpi_device_fix_up_power_extended(struct acpi_device *adev); void acpi_device_fix_up_power_children(struct acpi_device *adev); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); void acpi_dev_power_up_children_with_adr(struct acpi_device *adev); u8 acpi_dev_power_state_for_wake(struct acpi_device *adev); int acpi_device_power_add_dependent(struct acpi_device *adev, struct device *dev); void acpi_device_power_remove_dependent(struct acpi_device *adev, struct device *dev); #ifdef CONFIG_PM bool acpi_bus_can_wakeup(acpi_handle handle); #else static inline bool acpi_bus_can_wakeup(acpi_handle handle) { return false; } #endif void acpi_scan_lock_acquire(void); void acpi_scan_lock_release(void); void acpi_lock_hp_context(void); void acpi_unlock_hp_context(void); int acpi_scan_add_handler(struct acpi_scan_handler *handler); /* * use a macro to avoid include chaining to get THIS_MODULE */ #define acpi_bus_register_driver(drv) \ __acpi_bus_register_driver(drv, THIS_MODULE) int __acpi_bus_register_driver(struct acpi_driver *driver, struct module *owner); void acpi_bus_unregister_driver(struct acpi_driver *driver); int acpi_bus_scan(acpi_handle handle); void acpi_bus_trim(struct acpi_device *start); acpi_status acpi_bus_get_ejd(acpi_handle handle, acpi_handle * ejd); int acpi_match_device_ids(struct acpi_device *device, const struct acpi_device_id *ids); void acpi_set_modalias(struct acpi_device *adev, const char *default_id, char *modalias, size_t len); static inline bool acpi_device_enumerated(struct acpi_device *adev) { return adev && adev->flags.initialized && adev->flags.visited; } /** * module_acpi_driver(acpi_driver) - Helper macro for registering an ACPI driver * @__acpi_driver: acpi_driver struct * * Helper macro for ACPI drivers which do not do anything special in module * init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() */ #define module_acpi_driver(__acpi_driver) \ module_driver(__acpi_driver, acpi_bus_register_driver, \ acpi_bus_unregister_driver) /* * Bind physical devices with ACPI devices */ struct acpi_bus_type { struct list_head list; const char *name; bool (*match)(struct device *dev); struct acpi_device * (*find_companion)(struct device *); void (*setup)(struct device *); }; int register_acpi_bus_type(struct acpi_bus_type *); int unregister_acpi_bus_type(struct acpi_bus_type *); int acpi_bind_one(struct device *dev, struct acpi_device *adev); int acpi_unbind_one(struct device *dev); enum acpi_bridge_type { ACPI_BRIDGE_TYPE_PCIE = 1, ACPI_BRIDGE_TYPE_CXL, }; struct acpi_pci_root { struct acpi_device * device; struct pci_bus *bus; u16 segment; int bridge_type; struct resource secondary; /* downstream bus range */ u32 osc_support_set; /* _OSC state of support bits */ u32 osc_control_set; /* _OSC state of control bits */ u32 osc_ext_support_set; /* _OSC state of extended support bits */ u32 osc_ext_control_set; /* _OSC state of extended control bits */ phys_addr_t mcfg_addr; }; /* helper */ struct iommu_ops; bool acpi_dma_supported(const struct acpi_device *adev); enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev); int acpi_iommu_fwspec_init(struct device *dev, u32 id, struct fwnode_handle *fwnode); int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map); int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id); static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return acpi_dma_configure_id(dev, attr, NULL); } struct acpi_device *acpi_find_child_device(struct acpi_device *parent, u64 address, bool check_children); struct acpi_device *acpi_find_child_by_adr(struct acpi_device *adev, acpi_bus_address adr); int acpi_is_root_bridge(acpi_handle); struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle); int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state); int acpi_disable_wakeup_device_power(struct acpi_device *dev); #ifdef CONFIG_X86 bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *status); bool acpi_quirk_skip_acpi_ac_and_battery(void); int acpi_install_cmos_rtc_space_handler(acpi_handle handle); void acpi_remove_cmos_rtc_space_handler(acpi_handle handle); int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip); #else static inline bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *status) { return false; } static inline bool acpi_quirk_skip_acpi_ac_and_battery(void) { return false; } static inline int acpi_install_cmos_rtc_space_handler(acpi_handle handle) { return 1; } static inline void acpi_remove_cmos_rtc_space_handler(acpi_handle handle) { } static inline int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) { *skip = false; return 0; } #endif #if IS_ENABLED(CONFIG_X86_ANDROID_TABLETS) bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev); bool acpi_quirk_skip_gpio_event_handlers(void); #else static inline bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev) { return false; } static inline bool acpi_quirk_skip_gpio_event_handlers(void) { return false; } #endif #ifdef CONFIG_PM void acpi_pm_wakeup_event(struct device *dev); acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev, void (*func)(struct acpi_device_wakeup_context *context)); acpi_status acpi_remove_pm_notifier(struct acpi_device *adev); bool acpi_pm_device_can_wakeup(struct device *dev); int acpi_pm_device_sleep_state(struct device *, int *, int); int acpi_pm_set_device_wakeup(struct device *dev, bool enable); #else static inline void acpi_pm_wakeup_event(struct device *dev) { } static inline acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev, void (*func)(struct acpi_device_wakeup_context *context)) { return AE_SUPPORT; } static inline acpi_status acpi_remove_pm_notifier(struct acpi_device *adev) { return AE_SUPPORT; } static inline bool acpi_pm_device_can_wakeup(struct device *dev) { return false; } static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m) { if (p) *p = ACPI_STATE_D0; return (m >= ACPI_STATE_D0 && m <= ACPI_STATE_D3_COLD) ? m : ACPI_STATE_D0; } static inline int acpi_pm_set_device_wakeup(struct device *dev, bool enable) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT bool acpi_sleep_state_supported(u8 sleep_state); #else static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; } #endif #ifdef CONFIG_ACPI_SLEEP u32 acpi_target_system_state(void); #else static inline u32 acpi_target_system_state(void) { return ACPI_STATE_S0; } #endif static inline bool acpi_device_power_manageable(struct acpi_device *adev) { return adev->flags.power_manageable; } static inline bool acpi_device_can_wakeup(struct acpi_device *adev) { return adev->wakeup.flags.valid; } static inline bool acpi_device_can_poweroff(struct acpi_device *adev) { return adev->power.states[ACPI_STATE_D3_COLD].flags.valid || ((acpi_gbl_FADT.header.revision < 6) && adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set); } int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer); static inline bool acpi_dev_hid_match(struct acpi_device *adev, const char *hid2) { const char *hid1 = acpi_device_hid(adev); return hid1 && hid2 && !strcmp(hid1, hid2); } static inline bool acpi_str_uid_match(struct acpi_device *adev, const char *uid2) { const char *uid1 = acpi_device_uid(adev); return uid1 && uid2 && !strcmp(uid1, uid2); } static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2) { u64 uid1; return !acpi_dev_uid_to_integer(adev, &uid1) && uid1 == uid2; } #define TYPE_ENTRY(type, x) \ const type: x, \ type: x #define ACPI_STR_TYPES(match) \ TYPE_ENTRY(unsigned char *, match), \ TYPE_ENTRY(signed char *, match), \ TYPE_ENTRY(char *, match), \ TYPE_ENTRY(void *, match) /** * acpi_dev_uid_match - Match device by supplied UID * @adev: ACPI device to match. * @uid2: Unique ID of the device. * * Matches UID in @adev with given @uid2. * * Returns: %true if matches, %false otherwise. */ #define acpi_dev_uid_match(adev, uid2) \ _Generic(uid2, \ /* Treat @uid2 as a string for acpi string types */ \ ACPI_STR_TYPES(acpi_str_uid_match), \ /* Treat as an integer otherwise */ \ default: acpi_int_uid_match)(adev, uid2) /** * acpi_dev_hid_uid_match - Match device by supplied HID and UID * @adev: ACPI device to match. * @hid2: Hardware ID of the device. * @uid2: Unique ID of the device, pass NULL to not check _UID. * * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2 * will be treated as a match. If user wants to validate @uid2, it should be * done before calling this function. * * Returns: %true if matches or @uid2 is NULL, %false otherwise. */ #define acpi_dev_hid_uid_match(adev, hid2, uid2) \ (acpi_dev_hid_match(adev, hid2) && \ /* Distinguish integer 0 from NULL @uid2 */ \ (_Generic(uid2, ACPI_STR_TYPES(!(uid2)), default: 0) || \ acpi_dev_uid_match(adev, uid2))) void acpi_dev_clear_dependencies(struct acpi_device *supplier); bool acpi_dev_ready_for_enumeration(const struct acpi_device *device); struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier, struct acpi_device *start); /** * for_each_acpi_consumer_dev - iterate over the consumer ACPI devices for a * given supplier * @supplier: Pointer to the supplier's ACPI device * @consumer: Pointer to &struct acpi_device to hold the consumer, initially NULL */ #define for_each_acpi_consumer_dev(supplier, consumer) \ for (consumer = acpi_dev_get_next_consumer_dev(supplier, NULL); \ consumer; \ consumer = acpi_dev_get_next_consumer_dev(supplier, consumer)) struct acpi_device * acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const char *uid, s64 hrv); struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); /** * for_each_acpi_dev_match - iterate over ACPI devices that matching the criteria * @adev: pointer to the matching ACPI device, NULL at the end of the loop * @hid: Hardware ID of the device. * @uid: Unique ID of the device, pass NULL to not check _UID * @hrv: Hardware Revision of the device, pass -1 to not check _HRV * * The caller is responsible for invoking acpi_dev_put() on the returned device. */ #define for_each_acpi_dev_match(adev, hid, uid, hrv) \ for (adev = acpi_dev_get_first_match_dev(hid, uid, hrv); \ adev; \ adev = acpi_dev_get_next_match_dev(adev, hid, uid, hrv)) static inline struct acpi_device *acpi_dev_get(struct acpi_device *adev) { return adev ? to_acpi_device(get_device(&adev->dev)) : NULL; } static inline void acpi_dev_put(struct acpi_device *adev) { if (adev) put_device(&adev->dev); } struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); struct acpi_device *acpi_get_acpi_dev(acpi_handle handle); static inline void acpi_put_acpi_dev(struct acpi_device *adev) { acpi_dev_put(adev); } int acpi_wait_for_acpi_ipmi(void); int acpi_scan_add_dep(acpi_handle handle, struct acpi_handle_list *dep_devices); u32 arch_acpi_add_auto_dep(acpi_handle handle); #else /* CONFIG_ACPI */ static inline int register_acpi_bus_type(void *bus) { return 0; } static inline int unregister_acpi_bus_type(void *bus) { return 0; } static inline int acpi_wait_for_acpi_ipmi(void) { return 0; } static inline const char *acpi_device_hid(struct acpi_device *device) { return ""; } static inline bool acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld) { return false; } #define for_each_acpi_consumer_dev(supplier, consumer) \ for (consumer = NULL; false && (supplier);) #define for_each_acpi_dev_match(adev, hid, uid, hrv) \ for (adev = NULL; false && (hid) && (uid) && (hrv); ) #endif /* CONFIG_ACPI */ #endif /*__ACPI_BUS_H__*/ |
| 10 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 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H #define _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H #ifndef __LITTLE_ENDIAN #define __LITTLE_ENDIAN 1234 #endif #ifndef __LITTLE_ENDIAN_BITFIELD #define __LITTLE_ENDIAN_BITFIELD #endif #include <linux/stddef.h> #include <linux/types.h> #include <linux/swab.h> #define __constant_htonl(x) ((__force __be32)___constant_swab32((x))) #define __constant_ntohl(x) ___constant_swab32((__force __be32)(x)) #define __constant_htons(x) ((__force __be16)___constant_swab16((x))) #define __constant_ntohs(x) ___constant_swab16((__force __be16)(x)) #define __constant_cpu_to_le64(x) ((__force __le64)(__u64)(x)) #define __constant_le64_to_cpu(x) ((__force __u64)(__le64)(x)) #define __constant_cpu_to_le32(x) ((__force __le32)(__u32)(x)) #define __constant_le32_to_cpu(x) ((__force __u32)(__le32)(x)) #define __constant_cpu_to_le16(x) ((__force __le16)(__u16)(x)) #define __constant_le16_to_cpu(x) ((__force __u16)(__le16)(x)) #define __constant_cpu_to_be64(x) ((__force __be64)___constant_swab64((x))) #define __constant_be64_to_cpu(x) ___constant_swab64((__force __u64)(__be64)(x)) #define __constant_cpu_to_be32(x) ((__force __be32)___constant_swab32((x))) #define __constant_be32_to_cpu(x) ___constant_swab32((__force __u32)(__be32)(x)) #define __constant_cpu_to_be16(x) ((__force __be16)___constant_swab16((x))) #define __constant_be16_to_cpu(x) ___constant_swab16((__force __u16)(__be16)(x)) #define __cpu_to_le64(x) ((__force __le64)(__u64)(x)) #define __le64_to_cpu(x) ((__force __u64)(__le64)(x)) #define __cpu_to_le32(x) ((__force __le32)(__u32)(x)) #define __le32_to_cpu(x) ((__force __u32)(__le32)(x)) #define __cpu_to_le16(x) ((__force __le16)(__u16)(x)) #define __le16_to_cpu(x) ((__force __u16)(__le16)(x)) #define __cpu_to_be64(x) ((__force __be64)__swab64((x))) #define __be64_to_cpu(x) __swab64((__force __u64)(__be64)(x)) #define __cpu_to_be32(x) ((__force __be32)__swab32((x))) #define __be32_to_cpu(x) __swab32((__force __u32)(__be32)(x)) #define __cpu_to_be16(x) ((__force __be16)__swab16((x))) #define __be16_to_cpu(x) __swab16((__force __u16)(__be16)(x)) static __always_inline __le64 __cpu_to_le64p(const __u64 *p) { return (__force __le64)*p; } static __always_inline __u64 __le64_to_cpup(const __le64 *p) { return (__force __u64)*p; } static __always_inline __le32 __cpu_to_le32p(const __u32 *p) { return (__force __le32)*p; } static __always_inline __u32 __le32_to_cpup(const __le32 *p) { return (__force __u32)*p; } static __always_inline __le16 __cpu_to_le16p(const __u16 *p) { return (__force __le16)*p; } static __always_inline __u16 __le16_to_cpup(const __le16 *p) { return (__force __u16)*p; } static __always_inline __be64 __cpu_to_be64p(const __u64 *p) { return (__force __be64)__swab64p(p); } static __always_inline __u64 __be64_to_cpup(const __be64 *p) { return __swab64p((__u64 *)p); } static __always_inline __be32 __cpu_to_be32p(const __u32 *p) { return (__force __be32)__swab32p(p); } static __always_inline __u32 __be32_to_cpup(const __be32 *p) { return __swab32p((__u32 *)p); } static __always_inline __be16 __cpu_to_be16p(const __u16 *p) { return (__force __be16)__swab16p(p); } static __always_inline __u16 __be16_to_cpup(const __be16 *p) { return __swab16p((__u16 *)p); } #define __cpu_to_le64s(x) do { (void)(x); } while (0) #define __le64_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_le32s(x) do { (void)(x); } while (0) #define __le32_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_le16s(x) do { (void)(x); } while (0) #define __le16_to_cpus(x) do { (void)(x); } while (0) #define __cpu_to_be64s(x) __swab64s((x)) #define __be64_to_cpus(x) __swab64s((x)) #define __cpu_to_be32s(x) __swab32s((x)) #define __be32_to_cpus(x) __swab32s((x)) #define __cpu_to_be16s(x) __swab16s((x)) #define __be16_to_cpus(x) __swab16s((x)) #endif /* _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H */ |
| 3 3 3 3 3 3 3 3 2 2 2 2 2 1 1 1 1 1 1 1 1 2 2 2 1 2 2 3 3 3 3 3 1 2 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * AirSpy SDR driver * * Copyright (C) 2014 Antti Palosaari <crope@iki.fi> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/usb.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #include <media/videobuf2-v4l2.h> #include <media/videobuf2-vmalloc.h> /* AirSpy USB API commands (from AirSpy Library) */ enum { CMD_INVALID = 0x00, CMD_RECEIVER_MODE = 0x01, CMD_SI5351C_WRITE = 0x02, CMD_SI5351C_READ = 0x03, CMD_R820T_WRITE = 0x04, CMD_R820T_READ = 0x05, CMD_SPIFLASH_ERASE = 0x06, CMD_SPIFLASH_WRITE = 0x07, CMD_SPIFLASH_READ = 0x08, CMD_BOARD_ID_READ = 0x09, CMD_VERSION_STRING_READ = 0x0a, CMD_BOARD_PARTID_SERIALNO_READ = 0x0b, CMD_SET_SAMPLE_RATE = 0x0c, CMD_SET_FREQ = 0x0d, CMD_SET_LNA_GAIN = 0x0e, CMD_SET_MIXER_GAIN = 0x0f, CMD_SET_VGA_GAIN = 0x10, CMD_SET_LNA_AGC = 0x11, CMD_SET_MIXER_AGC = 0x12, CMD_SET_PACKING = 0x13, }; /* * bEndpointAddress 0x81 EP 1 IN * Transfer Type Bulk * wMaxPacketSize 0x0200 1x 512 bytes */ #define MAX_BULK_BUFS (6) #define BULK_BUFFER_SIZE (128 * 512) static const struct v4l2_frequency_band bands[] = { { .tuner = 0, .type = V4L2_TUNER_ADC, .index = 0, .capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS, .rangelow = 20000000, .rangehigh = 20000000, }, }; static const struct v4l2_frequency_band bands_rf[] = { { .tuner = 1, .type = V4L2_TUNER_RF, .index = 0, .capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS, .rangelow = 24000000, .rangehigh = 1750000000, }, }; /* stream formats */ struct airspy_format { u32 pixelformat; u32 buffersize; }; /* format descriptions for capture and preview */ static struct airspy_format formats[] = { { .pixelformat = V4L2_SDR_FMT_RU12LE, .buffersize = BULK_BUFFER_SIZE, }, }; static const unsigned int NUM_FORMATS = ARRAY_SIZE(formats); /* intermediate buffers with raw data from the USB device */ struct airspy_frame_buf { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; struct airspy { #define POWER_ON 1 #define USB_STATE_URB_BUF 2 unsigned long flags; struct device *dev; struct usb_device *udev; struct video_device vdev; struct v4l2_device v4l2_dev; /* videobuf2 queue and queued buffers list */ struct vb2_queue vb_queue; struct list_head queued_bufs; spinlock_t queued_bufs_lock; /* Protects queued_bufs */ unsigned sequence; /* Buffer sequence counter */ unsigned int vb_full; /* vb is full and packets dropped */ /* Note if taking both locks v4l2_lock must always be locked first! */ struct mutex v4l2_lock; /* Protects everything else */ struct mutex vb_queue_lock; /* Protects vb_queue and capt_file */ struct urb *urb_list[MAX_BULK_BUFS]; int buf_num; unsigned long buf_size; u8 *buf_list[MAX_BULK_BUFS]; dma_addr_t dma_addr[MAX_BULK_BUFS]; int urbs_initialized; int urbs_submitted; /* USB control message buffer */ #define BUF_SIZE 128 u8 *buf; /* Current configuration */ unsigned int f_adc; unsigned int f_rf; u32 pixelformat; u32 buffersize; /* Controls */ struct v4l2_ctrl_handler hdl; struct v4l2_ctrl *lna_gain_auto; struct v4l2_ctrl *lna_gain; struct v4l2_ctrl *mixer_gain_auto; struct v4l2_ctrl *mixer_gain; struct v4l2_ctrl *if_gain; /* Sample rate calc */ unsigned long jiffies_next; unsigned int sample; unsigned int sample_measured; }; #define airspy_dbg_usb_control_msg(_dev, _r, _t, _v, _i, _b, _l) { \ char *_direction; \ if (_t & USB_DIR_IN) \ _direction = "<<<"; \ else \ _direction = ">>>"; \ dev_dbg(_dev, "%02x %02x %02x %02x %02x %02x %02x %02x %s %*ph\n", \ _t, _r, _v & 0xff, _v >> 8, _i & 0xff, _i >> 8, \ _l & 0xff, _l >> 8, _direction, _l, _b); \ } /* execute firmware command */ static int airspy_ctrl_msg(struct airspy *s, u8 request, u16 value, u16 index, u8 *data, u16 size) { int ret; unsigned int pipe; u8 requesttype; switch (request) { case CMD_RECEIVER_MODE: case CMD_SET_FREQ: pipe = usb_sndctrlpipe(s->udev, 0); requesttype = (USB_TYPE_VENDOR | USB_DIR_OUT); break; case CMD_BOARD_ID_READ: case CMD_VERSION_STRING_READ: case CMD_BOARD_PARTID_SERIALNO_READ: case CMD_SET_LNA_GAIN: case CMD_SET_MIXER_GAIN: case CMD_SET_VGA_GAIN: case CMD_SET_LNA_AGC: case CMD_SET_MIXER_AGC: pipe = usb_rcvctrlpipe(s->udev, 0); requesttype = (USB_TYPE_VENDOR | USB_DIR_IN); break; default: dev_err(s->dev, "Unknown command %02x\n", request); ret = -EINVAL; goto err; } /* write request */ if (!(requesttype & USB_DIR_IN)) memcpy(s->buf, data, size); ret = usb_control_msg(s->udev, pipe, request, requesttype, value, index, s->buf, size, 1000); airspy_dbg_usb_control_msg(s->dev, request, requesttype, value, index, s->buf, size); if (ret < 0) { dev_err(s->dev, "usb_control_msg() failed %d request %02x\n", ret, request); goto err; } /* read request */ if (requesttype & USB_DIR_IN) memcpy(data, s->buf, size); return 0; err: return ret; } /* Private functions */ static struct airspy_frame_buf *airspy_get_next_fill_buf(struct airspy *s) { unsigned long flags; struct airspy_frame_buf *buf = NULL; spin_lock_irqsave(&s->queued_bufs_lock, flags); if (list_empty(&s->queued_bufs)) goto leave; buf = list_entry(s->queued_bufs.next, struct airspy_frame_buf, list); list_del(&buf->list); leave: spin_unlock_irqrestore(&s->queued_bufs_lock, flags); return buf; } static unsigned int airspy_convert_stream(struct airspy *s, void *dst, void *src, unsigned int src_len) { unsigned int dst_len; if (s->pixelformat == V4L2_SDR_FMT_RU12LE) { memcpy(dst, src, src_len); dst_len = src_len; } else { dst_len = 0; } /* calculate sample rate and output it in 10 seconds intervals */ if (unlikely(time_is_before_jiffies(s->jiffies_next))) { #define MSECS 10000UL unsigned int msecs = jiffies_to_msecs(jiffies - s->jiffies_next + msecs_to_jiffies(MSECS)); unsigned int samples = s->sample - s->sample_measured; s->jiffies_next = jiffies + msecs_to_jiffies(MSECS); s->sample_measured = s->sample; dev_dbg(s->dev, "slen=%u samples=%u msecs=%u sample rate=%lu\n", src_len, samples, msecs, samples * 1000UL / msecs); } /* total number of samples */ s->sample += src_len / 2; return dst_len; } /* * This gets called for the bulk stream pipe. This is done in interrupt * time, so it has to be fast, not crash, and not stall. Neat. */ static void airspy_urb_complete(struct urb *urb) { struct airspy *s = urb->context; struct airspy_frame_buf *fbuf; dev_dbg_ratelimited(s->dev, "status=%d length=%d/%d errors=%d\n", urb->status, urb->actual_length, urb->transfer_buffer_length, urb->error_count); switch (urb->status) { case 0: /* success */ case -ETIMEDOUT: /* NAK */ break; case -ECONNRESET: /* kill */ case -ENOENT: case -ESHUTDOWN: return; default: /* error */ dev_err_ratelimited(s->dev, "URB failed %d\n", urb->status); break; } if (likely(urb->actual_length > 0)) { void *ptr; unsigned int len; /* get free framebuffer */ fbuf = airspy_get_next_fill_buf(s); if (unlikely(fbuf == NULL)) { s->vb_full++; dev_notice_ratelimited(s->dev, "video buffer is full, %d packets dropped\n", s->vb_full); goto skip; } /* fill framebuffer */ ptr = vb2_plane_vaddr(&fbuf->vb.vb2_buf, 0); len = airspy_convert_stream(s, ptr, urb->transfer_buffer, urb->actual_length); vb2_set_plane_payload(&fbuf->vb.vb2_buf, 0, len); fbuf->vb.vb2_buf.timestamp = ktime_get_ns(); fbuf->vb.sequence = s->sequence++; vb2_buffer_done(&fbuf->vb.vb2_buf, VB2_BUF_STATE_DONE); } skip: usb_submit_urb(urb, GFP_ATOMIC); } static int airspy_kill_urbs(struct airspy *s) { int i; for (i = s->urbs_submitted - 1; i >= 0; i--) { dev_dbg(s->dev, "kill urb=%d\n", i); /* stop the URB */ usb_kill_urb(s->urb_list[i]); } s->urbs_submitted = 0; return 0; } static int airspy_submit_urbs(struct airspy *s) { int i, ret; for (i = 0; i < s->urbs_initialized; i++) { dev_dbg(s->dev, "submit urb=%d\n", i); ret = usb_submit_urb(s->urb_list[i], GFP_ATOMIC); if (ret) { dev_err(s->dev, "Could not submit URB no. %d - get them all back\n", i); airspy_kill_urbs(s); return ret; } s->urbs_submitted++; } return 0; } static int airspy_free_stream_bufs(struct airspy *s) { if (test_bit(USB_STATE_URB_BUF, &s->flags)) { while (s->buf_num) { s->buf_num--; dev_dbg(s->dev, "free buf=%d\n", s->buf_num); usb_free_coherent(s->udev, s->buf_size, s->buf_list[s->buf_num], s->dma_addr[s->buf_num]); } } clear_bit(USB_STATE_URB_BUF, &s->flags); return 0; } static int airspy_alloc_stream_bufs(struct airspy *s) { s->buf_num = 0; s->buf_size = BULK_BUFFER_SIZE; dev_dbg(s->dev, "all in all I will use %u bytes for streaming\n", MAX_BULK_BUFS * BULK_BUFFER_SIZE); for (s->buf_num = 0; s->buf_num < MAX_BULK_BUFS; s->buf_num++) { s->buf_list[s->buf_num] = usb_alloc_coherent(s->udev, BULK_BUFFER_SIZE, GFP_ATOMIC, &s->dma_addr[s->buf_num]); if (!s->buf_list[s->buf_num]) { dev_dbg(s->dev, "alloc buf=%d failed\n", s->buf_num); airspy_free_stream_bufs(s); return -ENOMEM; } dev_dbg(s->dev, "alloc buf=%d %p (dma %llu)\n", s->buf_num, s->buf_list[s->buf_num], (long long)s->dma_addr[s->buf_num]); set_bit(USB_STATE_URB_BUF, &s->flags); } return 0; } static int airspy_free_urbs(struct airspy *s) { int i; airspy_kill_urbs(s); for (i = s->urbs_initialized - 1; i >= 0; i--) { if (s->urb_list[i]) { dev_dbg(s->dev, "free urb=%d\n", i); /* free the URBs */ usb_free_urb(s->urb_list[i]); } } s->urbs_initialized = 0; return 0; } static int airspy_alloc_urbs(struct airspy *s) { int i, j; /* allocate the URBs */ for (i = 0; i < MAX_BULK_BUFS; i++) { dev_dbg(s->dev, "alloc urb=%d\n", i); s->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC); if (!s->urb_list[i]) { for (j = 0; j < i; j++) { usb_free_urb(s->urb_list[j]); s->urb_list[j] = NULL; } s->urbs_initialized = 0; return -ENOMEM; } usb_fill_bulk_urb(s->urb_list[i], s->udev, usb_rcvbulkpipe(s->udev, 0x81), s->buf_list[i], BULK_BUFFER_SIZE, airspy_urb_complete, s); s->urb_list[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP; s->urb_list[i]->transfer_dma = s->dma_addr[i]; s->urbs_initialized++; } return 0; } /* Must be called with vb_queue_lock hold */ static void airspy_cleanup_queued_bufs(struct airspy *s) { unsigned long flags; dev_dbg(s->dev, "\n"); spin_lock_irqsave(&s->queued_bufs_lock, flags); while (!list_empty(&s->queued_bufs)) { struct airspy_frame_buf *buf; buf = list_entry(s->queued_bufs.next, struct airspy_frame_buf, list); list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); } spin_unlock_irqrestore(&s->queued_bufs_lock, flags); } /* The user yanked out the cable... */ static void airspy_disconnect(struct usb_interface *intf) { struct v4l2_device *v = usb_get_intfdata(intf); struct airspy *s = container_of(v, struct airspy, v4l2_dev); dev_dbg(s->dev, "\n"); mutex_lock(&s->vb_queue_lock); mutex_lock(&s->v4l2_lock); /* No need to keep the urbs around after disconnection */ s->udev = NULL; v4l2_device_disconnect(&s->v4l2_dev); video_unregister_device(&s->vdev); mutex_unlock(&s->v4l2_lock); mutex_unlock(&s->vb_queue_lock); v4l2_device_put(&s->v4l2_dev); } /* Videobuf2 operations */ static int airspy_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct airspy *s = vb2_get_drv_priv(vq); unsigned int q_num_bufs = vb2_get_num_buffers(vq); dev_dbg(s->dev, "nbuffers=%d\n", *nbuffers); /* Need at least 8 buffers */ if (q_num_bufs + *nbuffers < 8) *nbuffers = 8 - q_num_bufs; *nplanes = 1; sizes[0] = PAGE_ALIGN(s->buffersize); dev_dbg(s->dev, "nbuffers=%d sizes[0]=%d\n", *nbuffers, sizes[0]); return 0; } static void airspy_buf_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct airspy *s = vb2_get_drv_priv(vb->vb2_queue); struct airspy_frame_buf *buf = container_of(vbuf, struct airspy_frame_buf, vb); unsigned long flags; /* Check the device has not disconnected between prep and queuing */ if (unlikely(!s->udev)) { vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); return; } spin_lock_irqsave(&s->queued_bufs_lock, flags); list_add_tail(&buf->list, &s->queued_bufs); spin_unlock_irqrestore(&s->queued_bufs_lock, flags); } static int airspy_start_streaming(struct vb2_queue *vq, unsigned int count) { struct airspy *s = vb2_get_drv_priv(vq); int ret; dev_dbg(s->dev, "\n"); if (!s->udev) return -ENODEV; mutex_lock(&s->v4l2_lock); s->sequence = 0; set_bit(POWER_ON, &s->flags); ret = airspy_alloc_stream_bufs(s); if (ret) goto err_clear_bit; ret = airspy_alloc_urbs(s); if (ret) goto err_free_stream_bufs; ret = airspy_submit_urbs(s); if (ret) goto err_free_urbs; /* start hardware streaming */ ret = airspy_ctrl_msg(s, CMD_RECEIVER_MODE, 1, 0, NULL, 0); if (ret) goto err_kill_urbs; goto exit_mutex_unlock; err_kill_urbs: airspy_kill_urbs(s); err_free_urbs: airspy_free_urbs(s); err_free_stream_bufs: airspy_free_stream_bufs(s); err_clear_bit: clear_bit(POWER_ON, &s->flags); /* return all queued buffers to vb2 */ { struct airspy_frame_buf *buf, *tmp; list_for_each_entry_safe(buf, tmp, &s->queued_bufs, list) { list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } } exit_mutex_unlock: mutex_unlock(&s->v4l2_lock); return ret; } static void airspy_stop_streaming(struct vb2_queue *vq) { struct airspy *s = vb2_get_drv_priv(vq); dev_dbg(s->dev, "\n"); mutex_lock(&s->v4l2_lock); /* stop hardware streaming */ airspy_ctrl_msg(s, CMD_RECEIVER_MODE, 0, 0, NULL, 0); airspy_kill_urbs(s); airspy_free_urbs(s); airspy_free_stream_bufs(s); airspy_cleanup_queued_bufs(s); clear_bit(POWER_ON, &s->flags); mutex_unlock(&s->v4l2_lock); } static const struct vb2_ops airspy_vb2_ops = { .queue_setup = airspy_queue_setup, .buf_queue = airspy_buf_queue, .start_streaming = airspy_start_streaming, .stop_streaming = airspy_stop_streaming, }; static int airspy_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { struct airspy *s = video_drvdata(file); strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver)); strscpy(cap->card, s->vdev.name, sizeof(cap->card)); usb_make_path(s->udev, cap->bus_info, sizeof(cap->bus_info)); return 0; } static int airspy_enum_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { if (f->index >= NUM_FORMATS) return -EINVAL; f->pixelformat = formats[f->index].pixelformat; return 0; } static int airspy_g_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_format *f) { struct airspy *s = video_drvdata(file); f->fmt.sdr.pixelformat = s->pixelformat; f->fmt.sdr.buffersize = s->buffersize; return 0; } static int airspy_s_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_format *f) { struct airspy *s = video_drvdata(file); struct vb2_queue *q = &s->vb_queue; int i; if (vb2_is_busy(q)) return -EBUSY; for (i = 0; i < NUM_FORMATS; i++) { if (formats[i].pixelformat == f->fmt.sdr.pixelformat) { s->pixelformat = formats[i].pixelformat; s->buffersize = formats[i].buffersize; f->fmt.sdr.buffersize = formats[i].buffersize; return 0; } } s->pixelformat = formats[0].pixelformat; s->buffersize = formats[0].buffersize; f->fmt.sdr.pixelformat = formats[0].pixelformat; f->fmt.sdr.buffersize = formats[0].buffersize; return 0; } static int airspy_try_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_format *f) { int i; for (i = 0; i < NUM_FORMATS; i++) { if (formats[i].pixelformat == f->fmt.sdr.pixelformat) { f->fmt.sdr.buffersize = formats[i].buffersize; return 0; } } f->fmt.sdr.pixelformat = formats[0].pixelformat; f->fmt.sdr.buffersize = formats[0].buffersize; return 0; } static int airspy_s_tuner(struct file *file, void *priv, const struct v4l2_tuner *v) { int ret; if (v->index == 0) ret = 0; else if (v->index == 1) ret = 0; else ret = -EINVAL; return ret; } static int airspy_g_tuner(struct file *file, void *priv, struct v4l2_tuner *v) { int ret; if (v->index == 0) { strscpy(v->name, "AirSpy ADC", sizeof(v->name)); v->type = V4L2_TUNER_ADC; v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS; v->rangelow = bands[0].rangelow; v->rangehigh = bands[0].rangehigh; ret = 0; } else if (v->index == 1) { strscpy(v->name, "AirSpy RF", sizeof(v->name)); v->type = V4L2_TUNER_RF; v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS; v->rangelow = bands_rf[0].rangelow; v->rangehigh = bands_rf[0].rangehigh; ret = 0; } else { ret = -EINVAL; } return ret; } static int airspy_g_frequency(struct file *file, void *priv, struct v4l2_frequency *f) { struct airspy *s = video_drvdata(file); int ret; if (f->tuner == 0) { f->type = V4L2_TUNER_ADC; f->frequency = s->f_adc; dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc); ret = 0; } else if (f->tuner == 1) { f->type = V4L2_TUNER_RF; f->frequency = s->f_rf; dev_dbg(s->dev, "RF frequency=%u Hz\n", s->f_rf); ret = 0; } else { ret = -EINVAL; } return ret; } static int airspy_s_frequency(struct file *file, void *priv, const struct v4l2_frequency *f) { struct airspy *s = video_drvdata(file); int ret; u8 buf[4]; if (f->tuner == 0) { s->f_adc = clamp_t(unsigned int, f->frequency, bands[0].rangelow, bands[0].rangehigh); dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc); ret = 0; } else if (f->tuner == 1) { s->f_rf = clamp_t(unsigned int, f->frequency, bands_rf[0].rangelow, bands_rf[0].rangehigh); dev_dbg(s->dev, "RF frequency=%u Hz\n", s->f_rf); buf[0] = (s->f_rf >> 0) & 0xff; buf[1] = (s->f_rf >> 8) & 0xff; buf[2] = (s->f_rf >> 16) & 0xff; buf[3] = (s->f_rf >> 24) & 0xff; ret = airspy_ctrl_msg(s, CMD_SET_FREQ, 0, 0, buf, 4); } else { ret = -EINVAL; } return ret; } static int airspy_enum_freq_bands(struct file *file, void *priv, struct v4l2_frequency_band *band) { int ret; if (band->tuner == 0) { if (band->index >= ARRAY_SIZE(bands)) { ret = -EINVAL; } else { *band = bands[band->index]; ret = 0; } } else if (band->tuner == 1) { if (band->index >= ARRAY_SIZE(bands_rf)) { ret = -EINVAL; } else { *band = bands_rf[band->index]; ret = 0; } } else { ret = -EINVAL; } return ret; } static const struct v4l2_ioctl_ops airspy_ioctl_ops = { .vidioc_querycap = airspy_querycap, .vidioc_enum_fmt_sdr_cap = airspy_enum_fmt_sdr_cap, .vidioc_g_fmt_sdr_cap = airspy_g_fmt_sdr_cap, .vidioc_s_fmt_sdr_cap = airspy_s_fmt_sdr_cap, .vidioc_try_fmt_sdr_cap = airspy_try_fmt_sdr_cap, .vidioc_reqbufs = vb2_ioctl_reqbufs, .vidioc_create_bufs = vb2_ioctl_create_bufs, .vidioc_prepare_buf = vb2_ioctl_prepare_buf, .vidioc_querybuf = vb2_ioctl_querybuf, .vidioc_qbuf = vb2_ioctl_qbuf, .vidioc_dqbuf = vb2_ioctl_dqbuf, .vidioc_streamon = vb2_ioctl_streamon, .vidioc_streamoff = vb2_ioctl_streamoff, .vidioc_g_tuner = airspy_g_tuner, .vidioc_s_tuner = airspy_s_tuner, .vidioc_g_frequency = airspy_g_frequency, .vidioc_s_frequency = airspy_s_frequency, .vidioc_enum_freq_bands = airspy_enum_freq_bands, .vidioc_subscribe_event = v4l2_ctrl_subscribe_event, .vidioc_unsubscribe_event = v4l2_event_unsubscribe, .vidioc_log_status = v4l2_ctrl_log_status, }; static const struct v4l2_file_operations airspy_fops = { .owner = THIS_MODULE, .open = v4l2_fh_open, .release = vb2_fop_release, .read = vb2_fop_read, .poll = vb2_fop_poll, .mmap = vb2_fop_mmap, .unlocked_ioctl = video_ioctl2, }; static const struct video_device airspy_template = { .name = "AirSpy SDR", .release = video_device_release_empty, .fops = &airspy_fops, .ioctl_ops = &airspy_ioctl_ops, }; static void airspy_video_release(struct v4l2_device *v) { struct airspy *s = container_of(v, struct airspy, v4l2_dev); v4l2_ctrl_handler_free(&s->hdl); v4l2_device_unregister(&s->v4l2_dev); kfree(s->buf); kfree(s); } static int airspy_set_lna_gain(struct airspy *s) { int ret; u8 u8tmp; dev_dbg(s->dev, "lna auto=%d->%d val=%d->%d\n", s->lna_gain_auto->cur.val, s->lna_gain_auto->val, s->lna_gain->cur.val, s->lna_gain->val); ret = airspy_ctrl_msg(s, CMD_SET_LNA_AGC, 0, s->lna_gain_auto->val, &u8tmp, 1); if (ret) goto err; if (s->lna_gain_auto->val == false) { ret = airspy_ctrl_msg(s, CMD_SET_LNA_GAIN, 0, s->lna_gain->val, &u8tmp, 1); if (ret) goto err; } err: if (ret) dev_dbg(s->dev, "failed=%d\n", ret); return ret; } static int airspy_set_mixer_gain(struct airspy *s) { int ret; u8 u8tmp; dev_dbg(s->dev, "mixer auto=%d->%d val=%d->%d\n", s->mixer_gain_auto->cur.val, s->mixer_gain_auto->val, s->mixer_gain->cur.val, s->mixer_gain->val); ret = airspy_ctrl_msg(s, CMD_SET_MIXER_AGC, 0, s->mixer_gain_auto->val, &u8tmp, 1); if (ret) goto err; if (s->mixer_gain_auto->val == false) { ret = airspy_ctrl_msg(s, CMD_SET_MIXER_GAIN, 0, s->mixer_gain->val, &u8tmp, 1); if (ret) goto err; } err: if (ret) dev_dbg(s->dev, "failed=%d\n", ret); return ret; } static int airspy_set_if_gain(struct airspy *s) { int ret; u8 u8tmp; dev_dbg(s->dev, "val=%d->%d\n", s->if_gain->cur.val, s->if_gain->val); ret = airspy_ctrl_msg(s, CMD_SET_VGA_GAIN, 0, s->if_gain->val, &u8tmp, 1); if (ret) dev_dbg(s->dev, "failed=%d\n", ret); return ret; } static int airspy_s_ctrl(struct v4l2_ctrl *ctrl) { struct airspy *s = container_of(ctrl->handler, struct airspy, hdl); int ret; switch (ctrl->id) { case V4L2_CID_RF_TUNER_LNA_GAIN_AUTO: case V4L2_CID_RF_TUNER_LNA_GAIN: ret = airspy_set_lna_gain(s); break; case V4L2_CID_RF_TUNER_MIXER_GAIN_AUTO: case V4L2_CID_RF_TUNER_MIXER_GAIN: ret = airspy_set_mixer_gain(s); break; case V4L2_CID_RF_TUNER_IF_GAIN: ret = airspy_set_if_gain(s); break; default: dev_dbg(s->dev, "unknown ctrl: id=%d name=%s\n", ctrl->id, ctrl->name); ret = -EINVAL; } return ret; } static const struct v4l2_ctrl_ops airspy_ctrl_ops = { .s_ctrl = airspy_s_ctrl, }; static int airspy_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct airspy *s; int ret; u8 u8tmp, *buf; buf = NULL; ret = -ENOMEM; s = kzalloc(sizeof(struct airspy), GFP_KERNEL); if (s == NULL) { dev_err(&intf->dev, "Could not allocate memory for state\n"); return -ENOMEM; } s->buf = kzalloc(BUF_SIZE, GFP_KERNEL); if (!s->buf) goto err_free_mem; buf = kzalloc(BUF_SIZE, GFP_KERNEL); if (!buf) goto err_free_mem; mutex_init(&s->v4l2_lock); mutex_init(&s->vb_queue_lock); spin_lock_init(&s->queued_bufs_lock); INIT_LIST_HEAD(&s->queued_bufs); s->dev = &intf->dev; s->udev = interface_to_usbdev(intf); s->f_adc = bands[0].rangelow; s->f_rf = bands_rf[0].rangelow; s->pixelformat = formats[0].pixelformat; s->buffersize = formats[0].buffersize; /* Detect device */ ret = airspy_ctrl_msg(s, CMD_BOARD_ID_READ, 0, 0, &u8tmp, 1); if (ret == 0) ret = airspy_ctrl_msg(s, CMD_VERSION_STRING_READ, 0, 0, buf, BUF_SIZE); if (ret) { dev_err(s->dev, "Could not detect board\n"); goto err_free_mem; } buf[BUF_SIZE - 1] = '\0'; dev_info(s->dev, "Board ID: %02x\n", u8tmp); dev_info(s->dev, "Firmware version: %s\n", buf); /* Init videobuf2 queue structure */ s->vb_queue.type = V4L2_BUF_TYPE_SDR_CAPTURE; s->vb_queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_READ; s->vb_queue.drv_priv = s; s->vb_queue.buf_struct_size = sizeof(struct airspy_frame_buf); s->vb_queue.ops = &airspy_vb2_ops; s->vb_queue.mem_ops = &vb2_vmalloc_memops; s->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; s->vb_queue.lock = &s->vb_queue_lock; ret = vb2_queue_init(&s->vb_queue); if (ret) { dev_err(s->dev, "Could not initialize vb2 queue\n"); goto err_free_mem; } /* Init video_device structure */ s->vdev = airspy_template; s->vdev.queue = &s->vb_queue; video_set_drvdata(&s->vdev, s); /* Register the v4l2_device structure */ s->v4l2_dev.release = airspy_video_release; ret = v4l2_device_register(&intf->dev, &s->v4l2_dev); if (ret) { dev_err(s->dev, "Failed to register v4l2-device (%d)\n", ret); goto err_free_mem; } /* Register controls */ v4l2_ctrl_handler_init(&s->hdl, 5); s->lna_gain_auto = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_LNA_GAIN_AUTO, 0, 1, 1, 0); s->lna_gain = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_LNA_GAIN, 0, 14, 1, 8); v4l2_ctrl_auto_cluster(2, &s->lna_gain_auto, 0, false); s->mixer_gain_auto = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_MIXER_GAIN_AUTO, 0, 1, 1, 0); s->mixer_gain = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_MIXER_GAIN, 0, 15, 1, 8); v4l2_ctrl_auto_cluster(2, &s->mixer_gain_auto, 0, false); s->if_gain = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_IF_GAIN, 0, 15, 1, 0); if (s->hdl.error) { ret = s->hdl.error; dev_err(s->dev, "Could not initialize controls\n"); goto err_free_controls; } v4l2_ctrl_handler_setup(&s->hdl); s->v4l2_dev.ctrl_handler = &s->hdl; s->vdev.v4l2_dev = &s->v4l2_dev; s->vdev.lock = &s->v4l2_lock; s->vdev.device_caps = V4L2_CAP_SDR_CAPTURE | V4L2_CAP_STREAMING | V4L2_CAP_READWRITE | V4L2_CAP_TUNER; ret = video_register_device(&s->vdev, VFL_TYPE_SDR, -1); if (ret) { dev_err(s->dev, "Failed to register as video device (%d)\n", ret); goto err_free_controls; } /* Free buf if success*/ kfree(buf); dev_info(s->dev, "Registered as %s\n", video_device_node_name(&s->vdev)); dev_notice(s->dev, "SDR API is still slightly experimental and functionality changes may follow\n"); return 0; err_free_controls: v4l2_ctrl_handler_free(&s->hdl); v4l2_device_unregister(&s->v4l2_dev); err_free_mem: kfree(buf); kfree(s->buf); kfree(s); return ret; } /* USB device ID list */ static const struct usb_device_id airspy_id_table[] = { { USB_DEVICE(0x1d50, 0x60a1) }, /* AirSpy */ { } }; MODULE_DEVICE_TABLE(usb, airspy_id_table); /* USB subsystem interface */ static struct usb_driver airspy_driver = { .name = KBUILD_MODNAME, .probe = airspy_probe, .disconnect = airspy_disconnect, .id_table = airspy_id_table, }; module_usb_driver(airspy_driver); MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>"); MODULE_DESCRIPTION("AirSpy SDR"); MODULE_LICENSE("GPL"); |
| 75 21 25 33 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/pagemap.h> #include <linux/blkdev.h> #include "../blk.h" /* * add_gd_partition adds a partitions details to the devices partition * description. */ struct parsed_partitions { struct gendisk *disk; char name[BDEVNAME_SIZE]; struct { sector_t from; sector_t size; int flags; bool has_info; struct partition_meta_info info; } *parts; int next; int limit; bool access_beyond_eod; char *pp_buf; }; typedef struct { struct folio *v; } Sector; void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p); static inline void put_dev_sector(Sector p) { folio_put(p.v); } static inline void put_partition(struct parsed_partitions *p, int n, sector_t from, sector_t size) { if (n < p->limit) { char tmp[1 + BDEVNAME_SIZE + 10 + 1]; p->parts[n].from = from; p->parts[n].size = size; snprintf(tmp, sizeof(tmp), " %s%d", p->name, n); strlcat(p->pp_buf, tmp, PAGE_SIZE); } } /* detection routines go here in alphabetical order: */ int adfspart_check_ADFS(struct parsed_partitions *state); int adfspart_check_CUMANA(struct parsed_partitions *state); int adfspart_check_EESOX(struct parsed_partitions *state); int adfspart_check_ICS(struct parsed_partitions *state); int adfspart_check_POWERTEC(struct parsed_partitions *state); int aix_partition(struct parsed_partitions *state); int amiga_partition(struct parsed_partitions *state); int atari_partition(struct parsed_partitions *state); int cmdline_partition(struct parsed_partitions *state); int efi_partition(struct parsed_partitions *state); int ibm_partition(struct parsed_partitions *); int karma_partition(struct parsed_partitions *state); int ldm_partition(struct parsed_partitions *state); int mac_partition(struct parsed_partitions *state); int msdos_partition(struct parsed_partitions *state); int of_partition(struct parsed_partitions *state); int osf_partition(struct parsed_partitions *state); int sgi_partition(struct parsed_partitions *state); int sun_partition(struct parsed_partitions *state); int sysv68_partition(struct parsed_partitions *state); int ultrix_partition(struct parsed_partitions *state); |
| 1 9 1 2 3 1 1 1 1 8 8 8 8 8 8 8 8 1 1 1 1 1 1 1 1 1 1 1 9 9 9 8 1 8 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 9 9 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8 9 11 11 11 9 9 9 9 9 1 1 1 9 9 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8 8 8 8 8 8 8 8 8 9 9 9 9 8 9 1 1 1 1 9 9 9 9 9 9 9 3 3 3 3 3 3 9 9 9 9 11 11 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/if_vlan.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/netdevice.h> #include <net/addrconf.h> #include <rdma/ib_cache.h> #include "core_priv.h" struct ib_pkey_cache { int table_len; u16 table[] __counted_by(table_len); }; struct ib_update_work { struct work_struct work; struct ib_event event; bool enforce_security; }; union ib_gid zgid; EXPORT_SYMBOL(zgid); enum gid_attr_find_mask { GID_ATTR_FIND_MASK_GID = 1UL << 0, GID_ATTR_FIND_MASK_NETDEV = 1UL << 1, GID_ATTR_FIND_MASK_DEFAULT = 1UL << 2, GID_ATTR_FIND_MASK_GID_TYPE = 1UL << 3, }; enum gid_table_entry_state { GID_TABLE_ENTRY_INVALID = 1, GID_TABLE_ENTRY_VALID = 2, /* * Indicates that entry is pending to be removed, there may * be active users of this GID entry. * When last user of the GID entry releases reference to it, * GID entry is detached from the table. */ GID_TABLE_ENTRY_PENDING_DEL = 3, }; struct roce_gid_ndev_storage { struct rcu_head rcu_head; struct net_device *ndev; }; struct ib_gid_table_entry { struct kref kref; struct work_struct del_work; struct ib_gid_attr attr; void *context; /* Store the ndev pointer to release reference later on in * call_rcu context because by that time gid_table_entry * and attr might be already freed. So keep a copy of it. * ndev_storage is freed by rcu callback. */ struct roce_gid_ndev_storage *ndev_storage; enum gid_table_entry_state state; }; struct ib_gid_table { int sz; /* In RoCE, adding a GID to the table requires: * (a) Find if this GID is already exists. * (b) Find a free space. * (c) Write the new GID * * Delete requires different set of operations: * (a) Find the GID * (b) Delete it. * **/ /* Any writer to data_vec must hold this lock and the write side of * rwlock. Readers must hold only rwlock. All writers must be in a * sleepable context. */ struct mutex lock; /* rwlock protects data_vec[ix]->state and entry pointer. */ rwlock_t rwlock; struct ib_gid_table_entry **data_vec; /* bit field, each bit indicates the index of default GID */ u32 default_gid_indices; }; static void dispatch_gid_change_event(struct ib_device *ib_dev, u32 port) { struct ib_event event; event.device = ib_dev; event.element.port_num = port; event.event = IB_EVENT_GID_CHANGE; ib_dispatch_event_clients(&event); } static const char * const gid_type_str[] = { /* IB/RoCE v1 value is set for IB_GID_TYPE_IB and IB_GID_TYPE_ROCE for * user space compatibility reasons. */ [IB_GID_TYPE_IB] = "IB/RoCE v1", [IB_GID_TYPE_ROCE] = "IB/RoCE v1", [IB_GID_TYPE_ROCE_UDP_ENCAP] = "RoCE v2", }; const char *ib_cache_gid_type_str(enum ib_gid_type gid_type) { if (gid_type < ARRAY_SIZE(gid_type_str) && gid_type_str[gid_type]) return gid_type_str[gid_type]; return "Invalid GID type"; } EXPORT_SYMBOL(ib_cache_gid_type_str); /** rdma_is_zero_gid - Check if given GID is zero or not. * @gid: GID to check * Returns true if given GID is zero, returns false otherwise. */ bool rdma_is_zero_gid(const union ib_gid *gid) { return !memcmp(gid, &zgid, sizeof(*gid)); } EXPORT_SYMBOL(rdma_is_zero_gid); /** is_gid_index_default - Check if a given index belongs to * reserved default GIDs or not. * @table: GID table pointer * @index: Index to check in GID table * Returns true if index is one of the reserved default GID index otherwise * returns false. */ static bool is_gid_index_default(const struct ib_gid_table *table, unsigned int index) { return index < 32 && (BIT(index) & table->default_gid_indices); } int ib_cache_gid_parse_type_str(const char *buf) { unsigned int i; size_t len; int err = -EINVAL; len = strlen(buf); if (len == 0) return -EINVAL; if (buf[len - 1] == '\n') len--; for (i = 0; i < ARRAY_SIZE(gid_type_str); ++i) if (gid_type_str[i] && !strncmp(buf, gid_type_str[i], len) && len == strlen(gid_type_str[i])) { err = i; break; } return err; } EXPORT_SYMBOL(ib_cache_gid_parse_type_str); static struct ib_gid_table *rdma_gid_table(struct ib_device *device, u32 port) { return device->port_data[port].cache.gid; } static bool is_gid_entry_free(const struct ib_gid_table_entry *entry) { return !entry; } static bool is_gid_entry_valid(const struct ib_gid_table_entry *entry) { return entry && entry->state == GID_TABLE_ENTRY_VALID; } static void schedule_free_gid(struct kref *kref) { struct ib_gid_table_entry *entry = container_of(kref, struct ib_gid_table_entry, kref); queue_work(ib_wq, &entry->del_work); } static void put_gid_ndev(struct rcu_head *head) { struct roce_gid_ndev_storage *storage = container_of(head, struct roce_gid_ndev_storage, rcu_head); WARN_ON(!storage->ndev); /* At this point its safe to release netdev reference, * as all callers working on gid_attr->ndev are done * using this netdev. */ dev_put(storage->ndev); kfree(storage); } static void free_gid_entry_locked(struct ib_gid_table_entry *entry) { struct ib_device *device = entry->attr.device; u32 port_num = entry->attr.port_num; struct ib_gid_table *table = rdma_gid_table(device, port_num); dev_dbg(&device->dev, "%s port=%u index=%u gid %pI6\n", __func__, port_num, entry->attr.index, entry->attr.gid.raw); write_lock_irq(&table->rwlock); /* * The only way to avoid overwriting NULL in table is * by comparing if it is same entry in table or not! * If new entry in table is added by the time we free here, * don't overwrite the table entry. */ if (entry == table->data_vec[entry->attr.index]) table->data_vec[entry->attr.index] = NULL; /* Now this index is ready to be allocated */ write_unlock_irq(&table->rwlock); if (entry->ndev_storage) call_rcu(&entry->ndev_storage->rcu_head, put_gid_ndev); kfree(entry); } static void free_gid_entry(struct kref *kref) { struct ib_gid_table_entry *entry = container_of(kref, struct ib_gid_table_entry, kref); free_gid_entry_locked(entry); } /** * free_gid_work - Release reference to the GID entry * @work: Work structure to refer to GID entry which needs to be * deleted. * * free_gid_work() frees the entry from the HCA's hardware table * if provider supports it. It releases reference to netdevice. */ static void free_gid_work(struct work_struct *work) { struct ib_gid_table_entry *entry = container_of(work, struct ib_gid_table_entry, del_work); struct ib_device *device = entry->attr.device; u32 port_num = entry->attr.port_num; struct ib_gid_table *table = rdma_gid_table(device, port_num); mutex_lock(&table->lock); free_gid_entry_locked(entry); mutex_unlock(&table->lock); } static struct ib_gid_table_entry * alloc_gid_entry(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry; struct net_device *ndev; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return NULL; ndev = rcu_dereference_protected(attr->ndev, 1); if (ndev) { entry->ndev_storage = kzalloc(sizeof(*entry->ndev_storage), GFP_KERNEL); if (!entry->ndev_storage) { kfree(entry); return NULL; } dev_hold(ndev); entry->ndev_storage->ndev = ndev; } kref_init(&entry->kref); memcpy(&entry->attr, attr, sizeof(*attr)); INIT_WORK(&entry->del_work, free_gid_work); entry->state = GID_TABLE_ENTRY_INVALID; return entry; } static void store_gid_entry(struct ib_gid_table *table, struct ib_gid_table_entry *entry) { entry->state = GID_TABLE_ENTRY_VALID; dev_dbg(&entry->attr.device->dev, "%s port=%u index=%u gid %pI6\n", __func__, entry->attr.port_num, entry->attr.index, entry->attr.gid.raw); lockdep_assert_held(&table->lock); write_lock_irq(&table->rwlock); table->data_vec[entry->attr.index] = entry; write_unlock_irq(&table->rwlock); } static void get_gid_entry(struct ib_gid_table_entry *entry) { kref_get(&entry->kref); } static void put_gid_entry(struct ib_gid_table_entry *entry) { kref_put(&entry->kref, schedule_free_gid); } static void put_gid_entry_locked(struct ib_gid_table_entry *entry) { kref_put(&entry->kref, free_gid_entry); } static int add_roce_gid(struct ib_gid_table_entry *entry) { const struct ib_gid_attr *attr = &entry->attr; int ret; if (!attr->ndev) { dev_err(&attr->device->dev, "%s NULL netdev port=%u index=%u\n", __func__, attr->port_num, attr->index); return -EINVAL; } if (rdma_cap_roce_gid_table(attr->device, attr->port_num)) { ret = attr->device->ops.add_gid(attr, &entry->context); if (ret) { dev_err(&attr->device->dev, "%s GID add failed port=%u index=%u\n", __func__, attr->port_num, attr->index); return ret; } } return 0; } /** * del_gid - Delete GID table entry * * @ib_dev: IB device whose GID entry to be deleted * @port: Port number of the IB device * @table: GID table of the IB device for a port * @ix: GID entry index to delete * */ static void del_gid(struct ib_device *ib_dev, u32 port, struct ib_gid_table *table, int ix) { struct roce_gid_ndev_storage *ndev_storage; struct ib_gid_table_entry *entry; lockdep_assert_held(&table->lock); dev_dbg(&ib_dev->dev, "%s port=%u index=%d gid %pI6\n", __func__, port, ix, table->data_vec[ix]->attr.gid.raw); write_lock_irq(&table->rwlock); entry = table->data_vec[ix]; entry->state = GID_TABLE_ENTRY_PENDING_DEL; /* * For non RoCE protocol, GID entry slot is ready to use. */ if (!rdma_protocol_roce(ib_dev, port)) table->data_vec[ix] = NULL; write_unlock_irq(&table->rwlock); if (rdma_cap_roce_gid_table(ib_dev, port)) ib_dev->ops.del_gid(&entry->attr, &entry->context); ndev_storage = entry->ndev_storage; if (ndev_storage) { entry->ndev_storage = NULL; rcu_assign_pointer(entry->attr.ndev, NULL); call_rcu(&ndev_storage->rcu_head, put_gid_ndev); } put_gid_entry_locked(entry); } /** * add_modify_gid - Add or modify GID table entry * * @table: GID table in which GID to be added or modified * @attr: Attributes of the GID * * Returns 0 on success or appropriate error code. It accepts zero * GID addition for non RoCE ports for HCA's who report them as valid * GID. However such zero GIDs are not added to the cache. */ static int add_modify_gid(struct ib_gid_table *table, const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry; int ret = 0; /* * Invalidate any old entry in the table to make it safe to write to * this index. */ if (is_gid_entry_valid(table->data_vec[attr->index])) del_gid(attr->device, attr->port_num, table, attr->index); /* * Some HCA's report multiple GID entries with only one valid GID, and * leave other unused entries as the zero GID. Convert zero GIDs to * empty table entries instead of storing them. */ if (rdma_is_zero_gid(&attr->gid)) return 0; entry = alloc_gid_entry(attr); if (!entry) return -ENOMEM; if (rdma_protocol_roce(attr->device, attr->port_num)) { ret = add_roce_gid(entry); if (ret) goto done; } store_gid_entry(table, entry); return 0; done: put_gid_entry(entry); return ret; } /* rwlock should be read locked, or lock should be held */ static int find_gid(struct ib_gid_table *table, const union ib_gid *gid, const struct ib_gid_attr *val, bool default_gid, unsigned long mask, int *pempty) { int i = 0; int found = -1; int empty = pempty ? -1 : 0; while (i < table->sz && (found < 0 || empty < 0)) { struct ib_gid_table_entry *data = table->data_vec[i]; struct ib_gid_attr *attr; int curr_index = i; i++; /* find_gid() is used during GID addition where it is expected * to return a free entry slot which is not duplicate. * Free entry slot is requested and returned if pempty is set, * so lookup free slot only if requested. */ if (pempty && empty < 0) { if (is_gid_entry_free(data) && default_gid == is_gid_index_default(table, curr_index)) { /* * Found an invalid (free) entry; allocate it. * If default GID is requested, then our * found slot must be one of the DEFAULT * reserved slots or we fail. * This ensures that only DEFAULT reserved * slots are used for default property GIDs. */ empty = curr_index; } } /* * Additionally find_gid() is used to find valid entry during * lookup operation; so ignore the entries which are marked as * pending for removal and the entries which are marked as * invalid. */ if (!is_gid_entry_valid(data)) continue; if (found >= 0) continue; attr = &data->attr; if (mask & GID_ATTR_FIND_MASK_GID_TYPE && attr->gid_type != val->gid_type) continue; if (mask & GID_ATTR_FIND_MASK_GID && memcmp(gid, &data->attr.gid, sizeof(*gid))) continue; if (mask & GID_ATTR_FIND_MASK_NETDEV && attr->ndev != val->ndev) continue; if (mask & GID_ATTR_FIND_MASK_DEFAULT && is_gid_index_default(table, curr_index) != default_gid) continue; found = curr_index; } if (pempty) *pempty = empty; return found; } static void make_default_gid(struct net_device *dev, union ib_gid *gid) { gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); addrconf_ifid_eui48(&gid->raw[8], dev); } static int __ib_cache_gid_add(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr, unsigned long mask, bool default_gid) { struct ib_gid_table *table; int ret = 0; int empty; int ix; /* Do not allow adding zero GID in support of * IB spec version 1.3 section 4.1.1 point (6) and * section 12.7.10 and section 12.7.20 */ if (rdma_is_zero_gid(gid)) return -EINVAL; table = rdma_gid_table(ib_dev, port); mutex_lock(&table->lock); ix = find_gid(table, gid, attr, default_gid, mask, &empty); if (ix >= 0) goto out_unlock; if (empty < 0) { ret = -ENOSPC; goto out_unlock; } attr->device = ib_dev; attr->index = empty; attr->port_num = port; attr->gid = *gid; ret = add_modify_gid(table, attr); if (!ret) dispatch_gid_change_event(ib_dev, port); out_unlock: mutex_unlock(&table->lock); if (ret) pr_warn_ratelimited("%s: unable to add gid %pI6 error=%d\n", __func__, gid->raw, ret); return ret; } int ib_cache_gid_add(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr) { unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE | GID_ATTR_FIND_MASK_NETDEV; return __ib_cache_gid_add(ib_dev, port, gid, attr, mask, false); } static int _ib_cache_gid_del(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr, unsigned long mask, bool default_gid) { struct ib_gid_table *table; int ret = 0; int ix; table = rdma_gid_table(ib_dev, port); mutex_lock(&table->lock); ix = find_gid(table, gid, attr, default_gid, mask, NULL); if (ix < 0) { ret = -EINVAL; goto out_unlock; } del_gid(ib_dev, port, table, ix); dispatch_gid_change_event(ib_dev, port); out_unlock: mutex_unlock(&table->lock); if (ret) pr_debug("%s: can't delete gid %pI6 error=%d\n", __func__, gid->raw, ret); return ret; } int ib_cache_gid_del(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr) { unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE | GID_ATTR_FIND_MASK_DEFAULT | GID_ATTR_FIND_MASK_NETDEV; return _ib_cache_gid_del(ib_dev, port, gid, attr, mask, false); } int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct ib_gid_table *table; int ix; bool deleted = false; table = rdma_gid_table(ib_dev, port); mutex_lock(&table->lock); for (ix = 0; ix < table->sz; ix++) { if (is_gid_entry_valid(table->data_vec[ix]) && table->data_vec[ix]->attr.ndev == ndev) { del_gid(ib_dev, port, table, ix); deleted = true; } } mutex_unlock(&table->lock); if (deleted) dispatch_gid_change_event(ib_dev, port); return 0; } /** * rdma_find_gid_by_port - Returns the GID entry attributes when it finds * a valid GID entry for given search parameters. It searches for the specified * GID value in the local software cache. * @ib_dev: The device to query. * @gid: The GID value to search for. * @gid_type: The GID type to search for. * @port: The port number of the device where the GID value should be searched. * @ndev: In RoCE, the net device of the device. NULL means ignore. * * Returns sgid attributes if the GID is found with valid reference or * returns ERR_PTR for the error. * The caller must invoke rdma_put_gid_attr() to release the reference. */ const struct ib_gid_attr * rdma_find_gid_by_port(struct ib_device *ib_dev, const union ib_gid *gid, enum ib_gid_type gid_type, u32 port, struct net_device *ndev) { int local_index; struct ib_gid_table *table; unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE; struct ib_gid_attr val = {.ndev = ndev, .gid_type = gid_type}; const struct ib_gid_attr *attr; unsigned long flags; if (!rdma_is_port_valid(ib_dev, port)) return ERR_PTR(-ENOENT); table = rdma_gid_table(ib_dev, port); if (ndev) mask |= GID_ATTR_FIND_MASK_NETDEV; read_lock_irqsave(&table->rwlock, flags); local_index = find_gid(table, gid, &val, false, mask, NULL); if (local_index >= 0) { get_gid_entry(table->data_vec[local_index]); attr = &table->data_vec[local_index]->attr; read_unlock_irqrestore(&table->rwlock, flags); return attr; } read_unlock_irqrestore(&table->rwlock, flags); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL(rdma_find_gid_by_port); /** * rdma_find_gid_by_filter - Returns the GID table attribute where a * specified GID value occurs * @ib_dev: The device to query. * @gid: The GID value to search for. * @port: The port number of the device where the GID value could be * searched. * @filter: The filter function is executed on any matching GID in the table. * If the filter function returns true, the corresponding index is returned, * otherwise, we continue searching the GID table. It's guaranteed that * while filter is executed, ndev field is valid and the structure won't * change. filter is executed in an atomic context. filter must not be NULL. * @context: Private data to pass into the call-back. * * rdma_find_gid_by_filter() searches for the specified GID value * of which the filter function returns true in the port's GID table. * */ const struct ib_gid_attr *rdma_find_gid_by_filter( struct ib_device *ib_dev, const union ib_gid *gid, u32 port, bool (*filter)(const union ib_gid *gid, const struct ib_gid_attr *, void *), void *context) { const struct ib_gid_attr *res = ERR_PTR(-ENOENT); struct ib_gid_table *table; unsigned long flags; unsigned int i; if (!rdma_is_port_valid(ib_dev, port)) return ERR_PTR(-EINVAL); table = rdma_gid_table(ib_dev, port); read_lock_irqsave(&table->rwlock, flags); for (i = 0; i < table->sz; i++) { struct ib_gid_table_entry *entry = table->data_vec[i]; if (!is_gid_entry_valid(entry)) continue; if (memcmp(gid, &entry->attr.gid, sizeof(*gid))) continue; if (filter(gid, &entry->attr, context)) { get_gid_entry(entry); res = &entry->attr; break; } } read_unlock_irqrestore(&table->rwlock, flags); return res; } static struct ib_gid_table *alloc_gid_table(int sz) { struct ib_gid_table *table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) return NULL; table->data_vec = kcalloc(sz, sizeof(*table->data_vec), GFP_KERNEL); if (!table->data_vec) goto err_free_table; mutex_init(&table->lock); table->sz = sz; rwlock_init(&table->rwlock); return table; err_free_table: kfree(table); return NULL; } static void release_gid_table(struct ib_device *device, struct ib_gid_table *table) { int i; if (!table) return; for (i = 0; i < table->sz; i++) { if (is_gid_entry_free(table->data_vec[i])) continue; WARN_ONCE(true, "GID entry ref leak for dev %s index %d ref=%u\n", dev_name(&device->dev), i, kref_read(&table->data_vec[i]->kref)); } mutex_destroy(&table->lock); kfree(table->data_vec); kfree(table); } static void cleanup_gid_table_port(struct ib_device *ib_dev, u32 port, struct ib_gid_table *table) { int i; if (!table) return; mutex_lock(&table->lock); for (i = 0; i < table->sz; ++i) { if (is_gid_entry_valid(table->data_vec[i])) del_gid(ib_dev, port, table, i); } mutex_unlock(&table->lock); } void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u32 port, struct net_device *ndev, unsigned long gid_type_mask, enum ib_cache_gid_default_mode mode) { union ib_gid gid = { }; struct ib_gid_attr gid_attr; unsigned int gid_type; unsigned long mask; mask = GID_ATTR_FIND_MASK_GID_TYPE | GID_ATTR_FIND_MASK_DEFAULT | GID_ATTR_FIND_MASK_NETDEV; memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; for (gid_type = 0; gid_type < IB_GID_TYPE_SIZE; ++gid_type) { if (1UL << gid_type & ~gid_type_mask) continue; gid_attr.gid_type = gid_type; if (mode == IB_CACHE_GID_DEFAULT_MODE_SET) { make_default_gid(ndev, &gid); __ib_cache_gid_add(ib_dev, port, &gid, &gid_attr, mask, true); } else if (mode == IB_CACHE_GID_DEFAULT_MODE_DELETE) { _ib_cache_gid_del(ib_dev, port, &gid, &gid_attr, mask, true); } } } static void gid_table_reserve_default(struct ib_device *ib_dev, u32 port, struct ib_gid_table *table) { unsigned int i; unsigned long roce_gid_type_mask; unsigned int num_default_gids; roce_gid_type_mask = roce_gid_type_mask_support(ib_dev, port); num_default_gids = hweight_long(roce_gid_type_mask); /* Reserve starting indices for default GIDs */ for (i = 0; i < num_default_gids && i < table->sz; i++) table->default_gid_indices |= BIT(i); } static void gid_table_release_one(struct ib_device *ib_dev) { u32 p; rdma_for_each_port (ib_dev, p) { release_gid_table(ib_dev, ib_dev->port_data[p].cache.gid); ib_dev->port_data[p].cache.gid = NULL; } } static int _gid_table_setup_one(struct ib_device *ib_dev) { struct ib_gid_table *table; u32 rdma_port; rdma_for_each_port (ib_dev, rdma_port) { table = alloc_gid_table( ib_dev->port_data[rdma_port].immutable.gid_tbl_len); if (!table) goto rollback_table_setup; gid_table_reserve_default(ib_dev, rdma_port, table); ib_dev->port_data[rdma_port].cache.gid = table; } return 0; rollback_table_setup: gid_table_release_one(ib_dev); return -ENOMEM; } static void gid_table_cleanup_one(struct ib_device *ib_dev) { u32 p; rdma_for_each_port (ib_dev, p) cleanup_gid_table_port(ib_dev, p, ib_dev->port_data[p].cache.gid); } static int gid_table_setup_one(struct ib_device *ib_dev) { int err; err = _gid_table_setup_one(ib_dev); if (err) return err; rdma_roce_rescan_device(ib_dev); return err; } /** * rdma_query_gid - Read the GID content from the GID software cache * @device: Device to query the GID * @port_num: Port number of the device * @index: Index of the GID table entry to read * @gid: Pointer to GID where to store the entry's GID * * rdma_query_gid() only reads the GID entry content for requested device, * port and index. It reads for IB, RoCE and iWarp link layers. It doesn't * hold any reference to the GID table entry in the HCA or software cache. * * Returns 0 on success or appropriate error code. * */ int rdma_query_gid(struct ib_device *device, u32 port_num, int index, union ib_gid *gid) { struct ib_gid_table *table; unsigned long flags; int res; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); if (index < 0 || index >= table->sz) { res = -EINVAL; goto done; } if (!is_gid_entry_valid(table->data_vec[index])) { res = -ENOENT; goto done; } memcpy(gid, &table->data_vec[index]->attr.gid, sizeof(*gid)); res = 0; done: read_unlock_irqrestore(&table->rwlock, flags); return res; } EXPORT_SYMBOL(rdma_query_gid); /** * rdma_read_gid_hw_context - Read the HW GID context from GID attribute * @attr: Potinter to the GID attribute * * rdma_read_gid_hw_context() reads the drivers GID HW context corresponding * to the SGID attr. Callers are required to already be holding the reference * to an existing GID entry. * * Returns the HW GID context * */ void *rdma_read_gid_hw_context(const struct ib_gid_attr *attr) { return container_of(attr, struct ib_gid_table_entry, attr)->context; } EXPORT_SYMBOL(rdma_read_gid_hw_context); /** * rdma_find_gid - Returns SGID attributes if the matching GID is found. * @device: The device to query. * @gid: The GID value to search for. * @gid_type: The GID type to search for. * @ndev: In RoCE, the net device of the device. NULL means ignore. * * rdma_find_gid() searches for the specified GID value in the software cache. * * Returns GID attributes if a valid GID is found or returns ERR_PTR for the * error. The caller must invoke rdma_put_gid_attr() to release the reference. * */ const struct ib_gid_attr *rdma_find_gid(struct ib_device *device, const union ib_gid *gid, enum ib_gid_type gid_type, struct net_device *ndev) { unsigned long mask = GID_ATTR_FIND_MASK_GID | GID_ATTR_FIND_MASK_GID_TYPE; struct ib_gid_attr gid_attr_val = {.ndev = ndev, .gid_type = gid_type}; u32 p; if (ndev) mask |= GID_ATTR_FIND_MASK_NETDEV; rdma_for_each_port(device, p) { struct ib_gid_table *table; unsigned long flags; int index; table = device->port_data[p].cache.gid; read_lock_irqsave(&table->rwlock, flags); index = find_gid(table, gid, &gid_attr_val, false, mask, NULL); if (index >= 0) { const struct ib_gid_attr *attr; get_gid_entry(table->data_vec[index]); attr = &table->data_vec[index]->attr; read_unlock_irqrestore(&table->rwlock, flags); return attr; } read_unlock_irqrestore(&table->rwlock, flags); } return ERR_PTR(-ENOENT); } EXPORT_SYMBOL(rdma_find_gid); int ib_get_cached_pkey(struct ib_device *device, u32 port_num, int index, u16 *pkey) { struct ib_pkey_cache *cache; unsigned long flags; int ret = 0; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); cache = device->port_data[port_num].cache.pkey; if (!cache || index < 0 || index >= cache->table_len) ret = -EINVAL; else *pkey = cache->table[index]; read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_get_cached_pkey); void ib_get_cached_subnet_prefix(struct ib_device *device, u32 port_num, u64 *sn_pfx) { unsigned long flags; read_lock_irqsave(&device->cache_lock, flags); *sn_pfx = device->port_data[port_num].cache.subnet_prefix; read_unlock_irqrestore(&device->cache_lock, flags); } EXPORT_SYMBOL(ib_get_cached_subnet_prefix); int ib_find_cached_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index) { struct ib_pkey_cache *cache; unsigned long flags; int i; int ret = -ENOENT; int partial_ix = -1; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); cache = device->port_data[port_num].cache.pkey; if (!cache) { ret = -EINVAL; goto err; } *index = -1; for (i = 0; i < cache->table_len; ++i) if ((cache->table[i] & 0x7fff) == (pkey & 0x7fff)) { if (cache->table[i] & 0x8000) { *index = i; ret = 0; break; } else { partial_ix = i; } } if (ret && partial_ix >= 0) { *index = partial_ix; ret = 0; } err: read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_find_cached_pkey); int ib_get_cached_lmc(struct ib_device *device, u32 port_num, u8 *lmc) { unsigned long flags; int ret = 0; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); *lmc = device->port_data[port_num].cache.lmc; read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_get_cached_lmc); int ib_get_cached_port_state(struct ib_device *device, u32 port_num, enum ib_port_state *port_state) { unsigned long flags; int ret = 0; if (!rdma_is_port_valid(device, port_num)) return -EINVAL; read_lock_irqsave(&device->cache_lock, flags); *port_state = device->port_data[port_num].cache.port_state; read_unlock_irqrestore(&device->cache_lock, flags); return ret; } EXPORT_SYMBOL(ib_get_cached_port_state); /** * rdma_get_gid_attr - Returns GID attributes for a port of a device * at a requested gid_index, if a valid GID entry exists. * @device: The device to query. * @port_num: The port number on the device where the GID value * is to be queried. * @index: Index of the GID table entry whose attributes are to * be queried. * * rdma_get_gid_attr() acquires reference count of gid attributes from the * cached GID table. Caller must invoke rdma_put_gid_attr() to release * reference to gid attribute regardless of link layer. * * Returns pointer to valid gid attribute or ERR_PTR for the appropriate error * code. */ const struct ib_gid_attr * rdma_get_gid_attr(struct ib_device *device, u32 port_num, int index) { const struct ib_gid_attr *attr = ERR_PTR(-ENODATA); struct ib_gid_table *table; unsigned long flags; if (!rdma_is_port_valid(device, port_num)) return ERR_PTR(-EINVAL); table = rdma_gid_table(device, port_num); if (index < 0 || index >= table->sz) return ERR_PTR(-EINVAL); read_lock_irqsave(&table->rwlock, flags); if (!is_gid_entry_valid(table->data_vec[index])) goto done; get_gid_entry(table->data_vec[index]); attr = &table->data_vec[index]->attr; done: read_unlock_irqrestore(&table->rwlock, flags); return attr; } EXPORT_SYMBOL(rdma_get_gid_attr); /** * rdma_query_gid_table - Reads GID table entries of all the ports of a device up to max_entries. * @device: The device to query. * @entries: Entries where GID entries are returned. * @max_entries: Maximum number of entries that can be returned. * Entries array must be allocated to hold max_entries number of entries. * * Returns number of entries on success or appropriate error code. */ ssize_t rdma_query_gid_table(struct ib_device *device, struct ib_uverbs_gid_entry *entries, size_t max_entries) { const struct ib_gid_attr *gid_attr; ssize_t num_entries = 0, ret; struct ib_gid_table *table; u32 port_num, i; struct net_device *ndev; unsigned long flags; rdma_for_each_port(device, port_num) { table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); for (i = 0; i < table->sz; i++) { if (!is_gid_entry_valid(table->data_vec[i])) continue; if (num_entries >= max_entries) { ret = -EINVAL; goto err; } gid_attr = &table->data_vec[i]->attr; memcpy(&entries->gid, &gid_attr->gid, sizeof(gid_attr->gid)); entries->gid_index = gid_attr->index; entries->port_num = gid_attr->port_num; entries->gid_type = gid_attr->gid_type; ndev = rcu_dereference_protected( gid_attr->ndev, lockdep_is_held(&table->rwlock)); if (ndev) entries->netdev_ifindex = ndev->ifindex; num_entries++; entries++; } read_unlock_irqrestore(&table->rwlock, flags); } return num_entries; err: read_unlock_irqrestore(&table->rwlock, flags); return ret; } EXPORT_SYMBOL(rdma_query_gid_table); /** * rdma_put_gid_attr - Release reference to the GID attribute * @attr: Pointer to the GID attribute whose reference * needs to be released. * * rdma_put_gid_attr() must be used to release reference whose * reference is acquired using rdma_get_gid_attr() or any APIs * which returns a pointer to the ib_gid_attr regardless of link layer * of IB or RoCE. * */ void rdma_put_gid_attr(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry = container_of(attr, struct ib_gid_table_entry, attr); put_gid_entry(entry); } EXPORT_SYMBOL(rdma_put_gid_attr); /** * rdma_hold_gid_attr - Get reference to existing GID attribute * * @attr: Pointer to the GID attribute whose reference * needs to be taken. * * Increase the reference count to a GID attribute to keep it from being * freed. Callers are required to already be holding a reference to attribute. * */ void rdma_hold_gid_attr(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry = container_of(attr, struct ib_gid_table_entry, attr); get_gid_entry(entry); } EXPORT_SYMBOL(rdma_hold_gid_attr); /** * rdma_read_gid_attr_ndev_rcu - Read GID attribute netdevice * which must be in UP state. * * @attr:Pointer to the GID attribute * * Returns pointer to netdevice if the netdevice was attached to GID and * netdevice is in UP state. Caller must hold RCU lock as this API * reads the netdev flags which can change while netdevice migrates to * different net namespace. Returns ERR_PTR with error code otherwise. * */ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr) { struct ib_gid_table_entry *entry = container_of(attr, struct ib_gid_table_entry, attr); struct ib_device *device = entry->attr.device; struct net_device *ndev = ERR_PTR(-EINVAL); u32 port_num = entry->attr.port_num; struct ib_gid_table *table; unsigned long flags; bool valid; table = rdma_gid_table(device, port_num); read_lock_irqsave(&table->rwlock, flags); valid = is_gid_entry_valid(table->data_vec[attr->index]); if (valid) { ndev = rcu_dereference(attr->ndev); if (!ndev) ndev = ERR_PTR(-ENODEV); } read_unlock_irqrestore(&table->rwlock, flags); return ndev; } EXPORT_SYMBOL(rdma_read_gid_attr_ndev_rcu); static int get_lower_dev_vlan(struct net_device *lower_dev, struct netdev_nested_priv *priv) { u16 *vlan_id = (u16 *)priv->data; if (is_vlan_dev(lower_dev)) *vlan_id = vlan_dev_vlan_id(lower_dev); /* We are interested only in first level vlan device, so * always return 1 to stop iterating over next level devices. */ return 1; } /** * rdma_read_gid_l2_fields - Read the vlan ID and source MAC address * of a GID entry. * * @attr: GID attribute pointer whose L2 fields to be read * @vlan_id: Pointer to vlan id to fill up if the GID entry has * vlan id. It is optional. * @smac: Pointer to smac to fill up for a GID entry. It is optional. * * rdma_read_gid_l2_fields() returns 0 on success and returns vlan id * (if gid entry has vlan) and source MAC, or returns error. */ int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, u16 *vlan_id, u8 *smac) { struct netdev_nested_priv priv = { .data = (void *)vlan_id, }; struct net_device *ndev; rcu_read_lock(); ndev = rcu_dereference(attr->ndev); if (!ndev) { rcu_read_unlock(); return -ENODEV; } if (smac) ether_addr_copy(smac, ndev->dev_addr); if (vlan_id) { *vlan_id = 0xffff; if (is_vlan_dev(ndev)) { *vlan_id = vlan_dev_vlan_id(ndev); } else { /* If the netdev is upper device and if it's lower * device is vlan device, consider vlan id of * the lower vlan device for this gid entry. */ netdev_walk_all_lower_dev_rcu(attr->ndev, get_lower_dev_vlan, &priv); } } rcu_read_unlock(); return 0; } EXPORT_SYMBOL(rdma_read_gid_l2_fields); static int config_non_roce_gid_cache(struct ib_device *device, u32 port, struct ib_port_attr *tprops) { struct ib_gid_attr gid_attr = {}; struct ib_gid_table *table; int ret = 0; int i; gid_attr.device = device; gid_attr.port_num = port; table = rdma_gid_table(device, port); mutex_lock(&table->lock); for (i = 0; i < tprops->gid_tbl_len; ++i) { if (!device->ops.query_gid) continue; ret = device->ops.query_gid(device, port, i, &gid_attr.gid); if (ret) { dev_warn(&device->dev, "query_gid failed (%d) for index %d\n", ret, i); goto err; } if (rdma_protocol_iwarp(device, port)) { struct net_device *ndev; ndev = ib_device_get_netdev(device, port); if (!ndev) continue; RCU_INIT_POINTER(gid_attr.ndev, ndev); dev_put(ndev); } gid_attr.index = i; tprops->subnet_prefix = be64_to_cpu(gid_attr.gid.global.subnet_prefix); add_modify_gid(table, &gid_attr); } err: mutex_unlock(&table->lock); return ret; } static int ib_cache_update(struct ib_device *device, u32 port, bool update_gids, bool update_pkeys, bool enforce_security) { struct ib_port_attr *tprops = NULL; struct ib_pkey_cache *pkey_cache = NULL; struct ib_pkey_cache *old_pkey_cache = NULL; int i; int ret; if (!rdma_is_port_valid(device, port)) return -EINVAL; tprops = kmalloc(sizeof *tprops, GFP_KERNEL); if (!tprops) return -ENOMEM; ret = ib_query_port(device, port, tprops); if (ret) { dev_warn(&device->dev, "ib_query_port failed (%d)\n", ret); goto err; } if (!rdma_protocol_roce(device, port) && update_gids) { ret = config_non_roce_gid_cache(device, port, tprops); if (ret) goto err; } update_pkeys &= !!tprops->pkey_tbl_len; if (update_pkeys) { pkey_cache = kmalloc(struct_size(pkey_cache, table, tprops->pkey_tbl_len), GFP_KERNEL); if (!pkey_cache) { ret = -ENOMEM; goto err; } pkey_cache->table_len = tprops->pkey_tbl_len; for (i = 0; i < pkey_cache->table_len; ++i) { ret = ib_query_pkey(device, port, i, pkey_cache->table + i); if (ret) { dev_warn(&device->dev, "ib_query_pkey failed (%d) for index %d\n", ret, i); goto err; } } } write_lock_irq(&device->cache_lock); if (update_pkeys) { old_pkey_cache = device->port_data[port].cache.pkey; device->port_data[port].cache.pkey = pkey_cache; } device->port_data[port].cache.lmc = tprops->lmc; if (device->port_data[port].cache.port_state != IB_PORT_NOP && device->port_data[port].cache.port_state != tprops->state) ibdev_info(device, "Port: %d Link %s\n", port, ib_port_state_to_str(tprops->state)); device->port_data[port].cache.port_state = tprops->state; device->port_data[port].cache.subnet_prefix = tprops->subnet_prefix; write_unlock_irq(&device->cache_lock); if (enforce_security) ib_security_cache_change(device, port, tprops->subnet_prefix); kfree(old_pkey_cache); kfree(tprops); return 0; err: kfree(pkey_cache); kfree(tprops); return ret; } static void ib_cache_event_task(struct work_struct *_work) { struct ib_update_work *work = container_of(_work, struct ib_update_work, work); int ret; /* Before distributing the cache update event, first sync * the cache. */ ret = ib_cache_update(work->event.device, work->event.element.port_num, work->event.event == IB_EVENT_GID_CHANGE, work->event.event == IB_EVENT_PKEY_CHANGE, work->enforce_security); /* GID event is notified already for individual GID entries by * dispatch_gid_change_event(). Hence, notifiy for rest of the * events. */ if (!ret && work->event.event != IB_EVENT_GID_CHANGE) ib_dispatch_event_clients(&work->event); kfree(work); } static void ib_generic_event_task(struct work_struct *_work) { struct ib_update_work *work = container_of(_work, struct ib_update_work, work); ib_dispatch_event_clients(&work->event); kfree(work); } static bool is_cache_update_event(const struct ib_event *event) { return (event->event == IB_EVENT_PORT_ERR || event->event == IB_EVENT_PORT_ACTIVE || event->event == IB_EVENT_LID_CHANGE || event->event == IB_EVENT_PKEY_CHANGE || event->event == IB_EVENT_CLIENT_REREGISTER || event->event == IB_EVENT_GID_CHANGE); } /** * ib_dispatch_event - Dispatch an asynchronous event * @event:Event to dispatch * * Low-level drivers must call ib_dispatch_event() to dispatch the * event to all registered event handlers when an asynchronous event * occurs. */ void ib_dispatch_event(const struct ib_event *event) { struct ib_update_work *work; work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) return; if (is_cache_update_event(event)) INIT_WORK(&work->work, ib_cache_event_task); else INIT_WORK(&work->work, ib_generic_event_task); work->event = *event; if (event->event == IB_EVENT_PKEY_CHANGE || event->event == IB_EVENT_GID_CHANGE) work->enforce_security = true; queue_work(ib_wq, &work->work); } EXPORT_SYMBOL(ib_dispatch_event); int ib_cache_setup_one(struct ib_device *device) { u32 p; int err; err = gid_table_setup_one(device); if (err) return err; rdma_for_each_port (device, p) { err = ib_cache_update(device, p, true, true, true); if (err) { gid_table_cleanup_one(device); return err; } } return 0; } void ib_cache_release_one(struct ib_device *device) { u32 p; /* * The release function frees all the cache elements. * This function should be called as part of freeing * all the device's resources when the cache could no * longer be accessed. */ rdma_for_each_port (device, p) kfree(device->port_data[p].cache.pkey); gid_table_release_one(device); } void ib_cache_cleanup_one(struct ib_device *device) { /* The cleanup function waits for all in-progress workqueue * elements and cleans up the GID cache. This function should be * called after the device was removed from the devices list and * all clients were removed, so the cache exists but is * non-functional and shouldn't be updated anymore. */ flush_workqueue(ib_wq); gid_table_cleanup_one(device); /* * Flush the wq second time for any pending GID delete work. */ flush_workqueue(ib_wq); } |
| 6 5 1251 1136 1253 1252 1254 1171 1251 1170 495 495 495 169 494 363 236 509 50 381 382 7 11 131 131 29 25 11 11 11 1 11 1 25 25 25 25 25 156 1 12 5 5 5 5 48 85 50 146 145 1 498 497 491 491 491 489 477 478 1 476 497 498 498 491 497 26 41 41 41 41 41 41 41 40 40 40 40 40 40 32 32 32 32 32 2 2 2 31 52 1 1 1 49 4 41 49 49 49 49 22 22 22 52 52 50 52 52 24 24 24 24 24 24 2 2 22 52 128 80 54 130 18 18 18 18 18 18 1 1 1 1 1 1 1 1 1 18 2 16 16 16 16 16 6 6 10 12 12 12 12 12 12 12 2 2 2 12 12 12 12 12 12 12 16 16 12 16 4 4 4 4 4 3 3 2 3 1 1 1 1 2 2 2 6 6 6 5 5 4 4 6 12 12 12 12 11 11 10 10 5 5 7 1 7 2 6 6 7 9 12 16 19 19 7 4 19 4 4 15 15 15 15 15 2 2 2 14 9 6 6 6 5 2 15 19 7 7 1 7 7 7 7 7 7 7 7 7 7 7 7 7 7 13 13 13 1 1 1 1 1 1 1 1 1 1 1 1 13 13 13 3 10 1 13 6 4 13 13 10 13 13 129 131 4 4 4 3 4 1 4 4 4 76 1 77 77 78 77 20 20 24 20 20 20 20 20 20 20 20 20 20 58 4 54 1 1 1 1 1 1 1 52 54 54 54 49 54 53 54 54 17 17 37 36 53 53 16 18 3 3 18 17 18 15 18 18 18 1 18 18 37 37 34 37 3 36 35 37 37 37 1 37 37 37 54 53 54 17 54 660 662 78 660 636 636 636 738 608 739 1059 839 822 739 1059 1059 440 18 47 48 48 30 18 47 5 5 2 5 1 5 5 5 5 1 5 5 2 3 3 3 5 5 5 5 5 5 47 29 29 29 48 48 19 19 19 31 31 31 31 58 40 19 58 57 59 48 48 48 48 48 48 5 48 48 48 48 5 48 48 48 48 30 48 48 48 48 48 48 11 47 48 48 48 48 48 48 48 47 29 16 16 3 13 16 52 38 14 39 51 67 67 67 67 67 67 30 67 67 66 66 65 12 65 65 65 39 39 26 25 25 19 13 13 19 12 19 48 47 18 47 48 46 28 14 14 28 48 18 18 12 10 2 2 48 48 48 48 48 48 47 48 48 48 48 18 12 7 6 1 7 47 47 1 47 18 46 6 47 47 47 47 47 47 45 36 55 19 61 49 61 53 54 13 47 21 21 21 21 21 4 4 21 21 92 92 92 92 92 91 19 19 19 19 19 19 76 92 76 75 76 91 12 12 12 18 18 18 18 18 14 14 1 17 12 17 14 5 2 17 16 17 12 17 14 17 1 17 17 17 13 13 13 13 13 13 13 13 10 13 10 13 1 13 1 13 8 13 9 4 13 13 13 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2009 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/shrinker.h> #include <linux/mm_inline.h> #include <linux/swapops.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/mm_types.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/migrate.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/page_owner.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/compat.h> #include <linux/pgalloc_tag.h> #include <linux/pagewalk.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/thp.h> /* * By default, transparent hugepage support is disabled in order to avoid * risking an increased memory footprint for applications that are not * guaranteed to benefit from it. When transparent hugepage support is * enabled, it is for all mappings, and khugepaged scans all mappings. * Defrag is invoked by khugepaged hugepage allocations and by page faults * for all hugepage allocations. */ unsigned long transparent_hugepage_flags __read_mostly = #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS (1<<TRANSPARENT_HUGEPAGE_FLAG)| #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)| #endif (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)| (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); static struct shrinker *deferred_split_shrinker; static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc); static bool split_underused_thp = true; static atomic_t huge_zero_refcount; struct folio *huge_zero_folio __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; unsigned long huge_anon_orders_always __read_mostly; unsigned long huge_anon_orders_madvise __read_mostly; unsigned long huge_anon_orders_inherit __read_mostly; static bool anon_orders_configured __initdata; static inline bool file_thp_enabled(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) return false; if (!vma->vm_file) return false; inode = file_inode(vma->vm_file); return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, enum tva_type type, unsigned long orders) { const bool smaps = type == TVA_SMAPS; const bool in_pf = type == TVA_PAGEFAULT; const bool forced_collapse = type == TVA_FORCED_COLLAPSE; unsigned long supported_orders; /* Check the intersection of requested and supported orders. */ if (vma_is_anonymous(vma)) supported_orders = THP_ORDERS_ALL_ANON; else if (vma_is_special_huge(vma)) supported_orders = THP_ORDERS_ALL_SPECIAL; else supported_orders = THP_ORDERS_ALL_FILE_DEFAULT; orders &= supported_orders; if (!orders) return 0; if (!vma->vm_mm) /* vdso */ return 0; if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags, forced_collapse)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ if (vma_is_dax(vma)) return in_pf ? orders : 0; /* * khugepaged special VMA and hugetlb VMA. * Must be checked after dax since some dax mappings may have * VM_MIXEDMAP set. */ if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED)) return 0; /* * Check alignment for file vma and size for both file and anon vma by * filtering out the unsuitable orders. * * Skip the check for page fault. Huge fault does the check in fault * handlers. */ if (!in_pf) { int order = highest_order(orders); unsigned long addr; while (orders) { addr = vma->vm_end - (PAGE_SIZE << order); if (thp_vma_suitable_order(vma, addr, order)) break; order = next_order(&orders, order); } if (!orders) return 0; } /* * Enabled via shmem mount options or sysfs settings. * Must be done before hugepage flags check since shmem has its * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) return orders & shmem_allowable_huge_orders(file_inode(vma->vm_file), vma, vma->vm_pgoff, 0, forced_collapse); if (!vma_is_anonymous(vma)) { /* * Enforce THP collapse requirements as necessary. Anonymous vmas * were already handled in thp_vma_allowable_orders(). */ if (!forced_collapse && (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) && !hugepage_global_always()))) return 0; /* * Trust that ->huge_fault() handlers know what they are doing * in fault path. */ if (((in_pf || smaps)) && vma->vm_ops->huge_fault) return orders; /* Only regular file is valid in collapse path */ if (((!in_pf || smaps)) && file_thp_enabled(vma)) return orders; return 0; } if (vma_is_temporary_stack(vma)) return 0; /* * THPeligible bit of smaps should show 1 for proper VMAs even * though anon_vma is not initialized yet. * * Allow page fault since anon_vma may be not initialized until * the first page fault. */ if (!vma->anon_vma) return (smaps || in_pf) ? orders : 0; return orders; } static bool get_huge_zero_folio(void) { struct folio *zero_folio; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) return true; zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO | __GFP_ZEROTAGS) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_folio) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); return false; } /* Ensure zero folio won't have large_rmappable flag set. */ folio_clear_large_rmappable(zero_folio); preempt_disable(); if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) { preempt_enable(); folio_put(zero_folio); goto retry; } WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); count_vm_event(THP_ZERO_PAGE_ALLOC); return true; } static void put_huge_zero_folio(void) { /* * Counter should never go to zero here. Only shrinker can put * last reference. */ BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) return huge_zero_folio; if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm)) return READ_ONCE(huge_zero_folio); if (!get_huge_zero_folio()) return NULL; if (mm_flags_test_and_set(MMF_HUGE_ZERO_FOLIO, mm)) put_huge_zero_folio(); return READ_ONCE(huge_zero_folio); } void mm_put_huge_zero_folio(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) return; if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm)) put_huge_zero_folio(); } static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink, struct shrink_control *sc) { /* we can free zero page only if last reference remains */ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; } static unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink, struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct folio *zero_folio = xchg(&huge_zero_folio, NULL); BUG_ON(zero_folio == NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); folio_put(zero_folio); return HPAGE_PMD_NR; } return 0; } static struct shrinker *huge_zero_folio_shrinker; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags)) output = "[always] madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags)) output = "always [madvise] never"; else output = "always madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { ssize_t ret = count; if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else ret = -EINVAL; if (ret > 0) { int err = start_stop_khugepaged(); if (err) ret = err; } return ret; } static struct kobj_attribute enabled_attr = __ATTR_RW(enabled); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { return sysfs_emit(buf, "%d\n", !!test_bit(flag, &transparent_hugepage_flags)); } ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) { unsigned long value; int ret; ret = kstrtoul(buf, 10, &value); if (ret < 0) return ret; if (value > 1) return -EINVAL; if (value) set_bit(flag, &transparent_hugepage_flags); else clear_bit(flag, &transparent_hugepage_flags); return count; } static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) output = "[always] defer defer+madvise madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) output = "always [defer] defer+madvise madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) output = "always defer [defer+madvise] madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) output = "always defer defer+madvise [madvise] never"; else output = "always defer defer+madvise madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "defer+madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "defer")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); } else return -EINVAL; return count; } static struct kobj_attribute defrag_attr = __ATTR_RW(defrag); static ssize_t use_zero_page_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static ssize_t use_zero_page_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page); static ssize_t hpage_pmd_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE); } static struct kobj_attribute hpage_pmd_size_attr = __ATTR_RO(hpage_pmd_size); static ssize_t split_underused_thp_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", split_underused_thp); } static ssize_t split_underused_thp_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err = kstrtobool(buf, &split_underused_thp); if (err < 0) return err; return count; } static struct kobj_attribute split_underused_thp_attr = __ATTR( shrink_underused, 0644, split_underused_thp_show, split_underused_thp_store); static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, &use_zero_page_attr.attr, &hpage_pmd_size_attr.attr, #ifdef CONFIG_SHMEM &shmem_enabled_attr.attr, #endif &split_underused_thp_attr.attr, NULL, }; static const struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; static void hugepage_exit_sysfs(struct kobject *hugepage_kobj); static void thpsize_release(struct kobject *kobj); static DEFINE_SPINLOCK(huge_anon_orders_lock); static LIST_HEAD(thpsize_list); static ssize_t anon_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { int order = to_thpsize(kobj)->order; const char *output; if (test_bit(order, &huge_anon_orders_always)) output = "[always] inherit madvise never"; else if (test_bit(order, &huge_anon_orders_inherit)) output = "always [inherit] madvise never"; else if (test_bit(order, &huge_anon_orders_madvise)) output = "always inherit [madvise] never"; else output = "always inherit madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t anon_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int order = to_thpsize(kobj)->order; ssize_t ret = count; if (sysfs_streq(buf, "always")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_inherit); clear_bit(order, &huge_anon_orders_madvise); set_bit(order, &huge_anon_orders_always); spin_unlock(&huge_anon_orders_lock); } else if (sysfs_streq(buf, "inherit")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_always); clear_bit(order, &huge_anon_orders_madvise); set_bit(order, &huge_anon_orders_inherit); spin_unlock(&huge_anon_orders_lock); } else if (sysfs_streq(buf, "madvise")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_always); clear_bit(order, &huge_anon_orders_inherit); set_bit(order, &huge_anon_orders_madvise); spin_unlock(&huge_anon_orders_lock); } else if (sysfs_streq(buf, "never")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_always); clear_bit(order, &huge_anon_orders_inherit); clear_bit(order, &huge_anon_orders_madvise); spin_unlock(&huge_anon_orders_lock); } else ret = -EINVAL; if (ret > 0) { int err; err = start_stop_khugepaged(); if (err) ret = err; } return ret; } static struct kobj_attribute anon_enabled_attr = __ATTR(enabled, 0644, anon_enabled_show, anon_enabled_store); static struct attribute *anon_ctrl_attrs[] = { &anon_enabled_attr.attr, NULL, }; static const struct attribute_group anon_ctrl_attr_grp = { .attrs = anon_ctrl_attrs, }; static struct attribute *file_ctrl_attrs[] = { #ifdef CONFIG_SHMEM &thpsize_shmem_enabled_attr.attr, #endif NULL, }; static const struct attribute_group file_ctrl_attr_grp = { .attrs = file_ctrl_attrs, }; static struct attribute *any_ctrl_attrs[] = { NULL, }; static const struct attribute_group any_ctrl_attr_grp = { .attrs = any_ctrl_attrs, }; static const struct kobj_type thpsize_ktype = { .release = &thpsize_release, .sysfs_ops = &kobj_sysfs_ops, }; DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}}; static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item) { unsigned long sum = 0; int cpu; for_each_possible_cpu(cpu) { struct mthp_stat *this = &per_cpu(mthp_stats, cpu); sum += this->stats[order][item]; } return sum; } #define DEFINE_MTHP_STAT_ATTR(_name, _index) \ static ssize_t _name##_show(struct kobject *kobj, \ struct kobj_attribute *attr, char *buf) \ { \ int order = to_thpsize(kobj)->order; \ \ return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index)); \ } \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT); DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN); DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK); DEFINE_MTHP_STAT_ATTR(swpin_fallback_charge, MTHP_STAT_SWPIN_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); #ifdef CONFIG_SHMEM DEFINE_MTHP_STAT_ATTR(shmem_alloc, MTHP_STAT_SHMEM_ALLOC); DEFINE_MTHP_STAT_ATTR(shmem_fallback, MTHP_STAT_SHMEM_FALLBACK); DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE); #endif DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT); DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED); DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED); DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON); DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED); static struct attribute *anon_stats_attrs[] = { &anon_fault_alloc_attr.attr, &anon_fault_fallback_attr.attr, &anon_fault_fallback_charge_attr.attr, #ifndef CONFIG_SHMEM &zswpout_attr.attr, &swpin_attr.attr, &swpin_fallback_attr.attr, &swpin_fallback_charge_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif &split_deferred_attr.attr, &nr_anon_attr.attr, &nr_anon_partially_mapped_attr.attr, NULL, }; static struct attribute_group anon_stats_attr_grp = { .name = "stats", .attrs = anon_stats_attrs, }; static struct attribute *file_stats_attrs[] = { #ifdef CONFIG_SHMEM &shmem_alloc_attr.attr, &shmem_fallback_attr.attr, &shmem_fallback_charge_attr.attr, #endif NULL, }; static struct attribute_group file_stats_attr_grp = { .name = "stats", .attrs = file_stats_attrs, }; static struct attribute *any_stats_attrs[] = { #ifdef CONFIG_SHMEM &zswpout_attr.attr, &swpin_attr.attr, &swpin_fallback_attr.attr, &swpin_fallback_charge_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif &split_attr.attr, &split_failed_attr.attr, NULL, }; static struct attribute_group any_stats_attr_grp = { .name = "stats", .attrs = any_stats_attrs, }; static int sysfs_add_group(struct kobject *kobj, const struct attribute_group *grp) { int ret = -ENOENT; /* * If the group is named, try to merge first, assuming the subdirectory * was already created. This avoids the warning emitted by * sysfs_create_group() if the directory already exists. */ if (grp->name) ret = sysfs_merge_group(kobj, grp); if (ret) ret = sysfs_create_group(kobj, grp); return ret; } static struct thpsize *thpsize_create(int order, struct kobject *parent) { unsigned long size = (PAGE_SIZE << order) / SZ_1K; struct thpsize *thpsize; int ret = -ENOMEM; thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL); if (!thpsize) goto err; thpsize->order = order; ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent, "hugepages-%lukB", size); if (ret) { kfree(thpsize); goto err; } ret = sysfs_add_group(&thpsize->kobj, &any_ctrl_attr_grp); if (ret) goto err_put; ret = sysfs_add_group(&thpsize->kobj, &any_stats_attr_grp); if (ret) goto err_put; if (BIT(order) & THP_ORDERS_ALL_ANON) { ret = sysfs_add_group(&thpsize->kobj, &anon_ctrl_attr_grp); if (ret) goto err_put; ret = sysfs_add_group(&thpsize->kobj, &anon_stats_attr_grp); if (ret) goto err_put; } if (BIT(order) & THP_ORDERS_ALL_FILE_DEFAULT) { ret = sysfs_add_group(&thpsize->kobj, &file_ctrl_attr_grp); if (ret) goto err_put; ret = sysfs_add_group(&thpsize->kobj, &file_stats_attr_grp); if (ret) goto err_put; } return thpsize; err_put: kobject_put(&thpsize->kobj); err: return ERR_PTR(ret); } static void thpsize_release(struct kobject *kobj) { kfree(to_thpsize(kobj)); } static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; struct thpsize *thpsize; unsigned long orders; int order; /* * Default to setting PMD-sized THP to inherit the global setting and * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time * constant so we have to do this here. */ if (!anon_orders_configured) huge_anon_orders_inherit = BIT(PMD_ORDER); *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); if (unlikely(!*hugepage_kobj)) { pr_err("failed to create transparent hugepage kobject\n"); return -ENOMEM; } err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); if (err) { pr_err("failed to register transparent hugepage group\n"); goto delete_obj; } err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); if (err) { pr_err("failed to register transparent hugepage group\n"); goto remove_hp_group; } orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT; order = highest_order(orders); while (orders) { thpsize = thpsize_create(order, *hugepage_kobj); if (IS_ERR(thpsize)) { pr_err("failed to create thpsize for order %d\n", order); err = PTR_ERR(thpsize); goto remove_all; } list_add(&thpsize->node, &thpsize_list); order = next_order(&orders, order); } return 0; remove_all: hugepage_exit_sysfs(*hugepage_kobj); return err; remove_hp_group: sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group); delete_obj: kobject_put(*hugepage_kobj); return err; } static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj) { struct thpsize *thpsize, *tmp; list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) { list_del(&thpsize->node); kobject_put(&thpsize->kobj); } sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group); sysfs_remove_group(hugepage_kobj, &hugepage_attr_group); kobject_put(hugepage_kobj); } #else static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj) { return 0; } static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) { } #endif /* CONFIG_SYSFS */ static int __init thp_shrinker_init(void) { deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | SHRINKER_NONSLAB, "thp-deferred_split"); if (!deferred_split_shrinker) return -ENOMEM; deferred_split_shrinker->count_objects = deferred_split_count; deferred_split_shrinker->scan_objects = deferred_split_scan; shrinker_register(deferred_split_shrinker); if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) { /* * Bump the reference of the huge_zero_folio and do not * initialize the shrinker. * * huge_zero_folio will always be NULL on failure. We assume * that get_huge_zero_folio() will most likely not fail as * thp_shrinker_init() is invoked early on during boot. */ if (!get_huge_zero_folio()) pr_warn("Allocating persistent huge zero folio failed\n"); return 0; } huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero"); if (!huge_zero_folio_shrinker) { shrinker_free(deferred_split_shrinker); return -ENOMEM; } huge_zero_folio_shrinker->count_objects = shrink_huge_zero_folio_count; huge_zero_folio_shrinker->scan_objects = shrink_huge_zero_folio_scan; shrinker_register(huge_zero_folio_shrinker); return 0; } static void __init thp_shrinker_exit(void) { shrinker_free(huge_zero_folio_shrinker); shrinker_free(deferred_split_shrinker); } static int __init hugepage_init(void) { int err; struct kobject *hugepage_kobj; if (!has_transparent_hugepage()) { transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED; return -EINVAL; } /* * hugepages can't be allocated by the buddy allocator */ MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER); err = hugepage_init_sysfs(&hugepage_kobj); if (err) goto err_sysfs; err = khugepaged_init(); if (err) goto err_slab; err = thp_shrinker_init(); if (err) goto err_shrinker; /* * By default disable transparent hugepages on smaller systems, * where the extra memory used could hurt more than TLB overhead * is likely to save. The admin can still enable it through /sys. */ if (totalram_pages() < MB_TO_PAGES(512)) { transparent_hugepage_flags = 0; return 0; } err = start_stop_khugepaged(); if (err) goto err_khugepaged; return 0; err_khugepaged: thp_shrinker_exit(); err_shrinker: khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); err_sysfs: return err; } subsys_initcall(hugepage_init); static int __init setup_transparent_hugepage(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "always")) { set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } else if (!strcmp(str, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } else if (!strcmp(str, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } out: if (!ret) pr_warn("transparent_hugepage= cannot parse, ignored\n"); return ret; } __setup("transparent_hugepage=", setup_transparent_hugepage); static char str_dup[PAGE_SIZE] __initdata; static int __init setup_thp_anon(char *str) { char *token, *range, *policy, *subtoken; unsigned long always, inherit, madvise; char *start_size, *end_size; int start, end, nr; char *p; if (!str || strlen(str) + 1 > PAGE_SIZE) goto err; strscpy(str_dup, str); always = huge_anon_orders_always; madvise = huge_anon_orders_madvise; inherit = huge_anon_orders_inherit; p = str_dup; while ((token = strsep(&p, ";")) != NULL) { range = strsep(&token, ":"); policy = token; if (!policy) goto err; while ((subtoken = strsep(&range, ",")) != NULL) { if (strchr(subtoken, '-')) { start_size = strsep(&subtoken, "-"); end_size = subtoken; start = get_order_from_str(start_size, THP_ORDERS_ALL_ANON); end = get_order_from_str(end_size, THP_ORDERS_ALL_ANON); } else { start_size = end_size = subtoken; start = end = get_order_from_str(subtoken, THP_ORDERS_ALL_ANON); } if (start == -EINVAL) { pr_err("invalid size %s in thp_anon boot parameter\n", start_size); goto err; } if (end == -EINVAL) { pr_err("invalid size %s in thp_anon boot parameter\n", end_size); goto err; } if (start < 0 || end < 0 || start > end) goto err; nr = end - start + 1; if (!strcmp(policy, "always")) { bitmap_set(&always, start, nr); bitmap_clear(&inherit, start, nr); bitmap_clear(&madvise, start, nr); } else if (!strcmp(policy, "madvise")) { bitmap_set(&madvise, start, nr); bitmap_clear(&inherit, start, nr); bitmap_clear(&always, start, nr); } else if (!strcmp(policy, "inherit")) { bitmap_set(&inherit, start, nr); bitmap_clear(&madvise, start, nr); bitmap_clear(&always, start, nr); } else if (!strcmp(policy, "never")) { bitmap_clear(&inherit, start, nr); bitmap_clear(&madvise, start, nr); bitmap_clear(&always, start, nr); } else { pr_err("invalid policy %s in thp_anon boot parameter\n", policy); goto err; } } } huge_anon_orders_always = always; huge_anon_orders_madvise = madvise; huge_anon_orders_inherit = inherit; anon_orders_configured = true; return 1; err: pr_warn("thp_anon=%s: error parsing string, ignoring setting\n", str); return 0; } __setup("thp_anon=", setup_thp_anon); pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pmd = pmd_mkwrite(pmd, vma); return pmd; } #ifdef CONFIG_MEMCG static inline struct deferred_split *get_deferred_split_queue(struct folio *folio) { struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = NODE_DATA(folio_nid(folio)); if (memcg) return &memcg->deferred_split_queue; else return &pgdat->deferred_split_queue; } #else static inline struct deferred_split *get_deferred_split_queue(struct folio *folio) { struct pglist_data *pgdat = NODE_DATA(folio_nid(folio)); return &pgdat->deferred_split_queue; } #endif static inline bool is_transparent_hugepage(const struct folio *folio) { if (!folio_test_large(folio)) return false; return is_huge_zero_folio(folio) || folio_test_large_rmappable(folio); } static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, loff_t off, unsigned long flags, unsigned long size, vm_flags_t vm_flags) { loff_t off_end = off + len; loff_t off_align = round_up(off, size); unsigned long len_pad, ret, off_sub; if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) return 0; if (off_end <= off_align || (off_end - off_align) < size) return 0; len_pad = len + size; if (len_pad < len || (off + len_pad) < off) return 0; ret = mm_get_unmapped_area_vmflags(current->mm, filp, addr, len_pad, off >> PAGE_SHIFT, flags, vm_flags); /* * The failure might be due to length padding. The caller will retry * without the padding. */ if (IS_ERR_VALUE(ret)) return 0; /* * Do not try to align to THP boundary if allocation at the address * hint succeeds. */ if (ret == addr) return addr; off_sub = (off - ret) & (size - 1); if (mm_flags_test(MMF_TOPDOWN, current->mm) && !off_sub) return ret + size; ret += off_sub; return ret; } unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long ret; loff_t off = (loff_t)pgoff << PAGE_SHIFT; ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags); if (ret) return ret; return mm_get_unmapped_area_vmflags(current->mm, filp, addr, len, pgoff, flags, vm_flags); } unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, unsigned long addr) { gfp_t gfp = vma_thp_gfp_mask(vma); const int order = HPAGE_PMD_ORDER; struct folio *folio; folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK); if (unlikely(!folio)) { count_vm_event(THP_FAULT_FALLBACK); count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); return NULL; } VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); return NULL; } folio_throttle_swaprate(folio, gfp); /* * When a folio is not zeroed during allocation (__GFP_ZERO not used) * or user folios require special handling, folio_zero_user() is used to * make sure that the page corresponding to the faulting address will be * hot in the cache after zeroing. */ if (user_alloc_needs_zeroing()) folio_zero_user(folio, addr); /* * The memory barrier inside __folio_mark_uptodate makes sure that * folio_zero_user writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); return folio; } static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd, struct vm_area_struct *vma, unsigned long haddr) { pmd_t entry; entry = folio_mk_pmd(folio, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); set_pmd_at(vma->vm_mm, haddr, pmd, entry); update_mmu_cache_pmd(vma, haddr, pmd); add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); count_vm_event(THP_FAULT_ALLOC); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) { unsigned long haddr = vmf->address & HPAGE_PMD_MASK; struct vm_area_struct *vma = vmf->vma; struct folio *folio; pgtable_t pgtable; vm_fault_t ret = 0; folio = vma_alloc_anon_folio_pmd(vma, vmf->address); if (unlikely(!folio)) return VM_FAULT_FALLBACK; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) { ret = VM_FAULT_OOM; goto release; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); folio_put(folio); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); deferred_split_folio(folio, false); spin_unlock(vmf->ptl); } return 0; unlock_release: spin_unlock(vmf->ptl); release: if (pgtable) pte_free(vma->vm_mm, pgtable); folio_put(folio); return ret; } /* * always: directly stall for all thp allocations * defer: wake kswapd and fail if not immediately available * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise * fail if not immediately available * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately * available * never: never stall for any thp allocation */ gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) { const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE); /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : __GFP_KSWAPD_RECLAIM); /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); return GFP_TRANSHUGE_LIGHT; } /* Caller must hold page table lock. */ static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, struct folio *zero_folio) { pmd_t entry; entry = folio_mk_pmd(zero_folio, vma->vm_page_prot); entry = pmd_mkspecial(entry); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); mm_inc_nr_ptes(mm); } vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return VM_FAULT_FALLBACK; ret = vmf_anon_prepare(vmf); if (ret) return ret; khugepaged_enter_vma(vma, vma->vm_flags); if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct folio *zero_folio; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) return VM_FAULT_OOM; zero_folio = mm_get_huge_zero_folio(vma->vm_mm); if (unlikely(!zero_folio)) { pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_folio(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_folio); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); } } else { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); } return ret; } return __do_huge_pmd_anonymous_page(vmf); } struct folio_or_pfn { union { struct folio *folio; unsigned long pfn; }; bool is_folio; }; static vm_fault_t insert_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, struct folio_or_pfn fop, pgprot_t prot, bool write) { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable = NULL; spinlock_t *ptl; pmd_t entry; if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (arch_needs_pgtable_deposit()) { pgtable = pte_alloc_one(vma->vm_mm); if (!pgtable) return VM_FAULT_OOM; } ptl = pmd_lock(mm, pmd); if (!pmd_none(*pmd)) { const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) : fop.pfn; if (write) { if (pmd_pfn(*pmd) != pfn) { WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); goto out_unlock; } entry = pmd_mkyoung(*pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) update_mmu_cache_pmd(vma, addr, pmd); } goto out_unlock; } if (fop.is_folio) { entry = folio_mk_pmd(fop.folio, vma->vm_page_prot); if (is_huge_zero_folio(fop.folio)) { entry = pmd_mkspecial(entry); } else { folio_get(fop.folio); folio_add_file_rmap_pmd(fop.folio, &fop.folio->page, vma); add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PMD_NR); } } else { entry = pmd_mkhuge(pfn_pmd(fop.pfn, prot)); entry = pmd_mkspecial(entry); } if (write) { entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); } if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); out_unlock: spin_unlock(ptl); if (pgtable) pte_free(mm, pgtable); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @write: whether it's a write fault * * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, bool write) { unsigned long addr = vmf->address & PMD_MASK; struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; struct folio_or_pfn fop = { .pfn = pfn, }; /* * If we had pmd_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); pfnmap_setup_cachemode_pfn(pfn, &pgprot); return insert_pmd(vma, addr, vmf->pmd, fop, pgprot, write); } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, bool write) { struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address & PMD_MASK; struct folio_or_pfn fop = { .folio = folio, .is_folio = true, }; if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER)) return VM_FAULT_SIGBUS; return insert_pmd(vma, addr, vmf->pmd, fop, vma->vm_page_prot, write); } EXPORT_SYMBOL_GPL(vmf_insert_folio_pmd); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pud = pud_mkwrite(pud); return pud; } static vm_fault_t insert_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, struct folio_or_pfn fop, pgprot_t prot, bool write) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; pud_t entry; if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; ptl = pud_lock(mm, pud); if (!pud_none(*pud)) { const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) : fop.pfn; if (write) { if (WARN_ON_ONCE(pud_pfn(*pud) != pfn)) goto out_unlock; entry = pud_mkyoung(*pud); entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); if (pudp_set_access_flags(vma, addr, pud, entry, 1)) update_mmu_cache_pud(vma, addr, pud); } goto out_unlock; } if (fop.is_folio) { entry = folio_mk_pud(fop.folio, vma->vm_page_prot); folio_get(fop.folio); folio_add_file_rmap_pud(fop.folio, &fop.folio->page, vma); add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PUD_NR); } else { entry = pud_mkhuge(pfn_pud(fop.pfn, prot)); entry = pud_mkspecial(entry); } if (write) { entry = pud_mkyoung(pud_mkdirty(entry)); entry = maybe_pud_mkwrite(entry, vma); } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); out_unlock: spin_unlock(ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @write: whether it's a write fault * * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, bool write) { unsigned long addr = vmf->address & PUD_MASK; struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; struct folio_or_pfn fop = { .pfn = pfn, }; /* * If we had pud_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); pfnmap_setup_cachemode_pfn(pfn, &pgprot); return insert_pud(vma, addr, vmf->pud, fop, pgprot, write); } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); /** * vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry * @vmf: Structure describing the fault * @folio: folio to insert * @write: whether it's a write fault * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, bool write) { struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address & PUD_MASK; struct folio_or_pfn fop = { .folio = folio, .is_folio = true, }; if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER)) return VM_FAULT_SIGBUS; return insert_pud(vma, addr, vmf->pud, fop, vma->vm_page_prot, write); } EXPORT_SYMBOL_GPL(vmf_insert_folio_pud); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write) { pmd_t _pmd; _pmd = pmd_mkyoung(*pmd); if (write) _pmd = pmd_mkdirty(_pmd); if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, pmd, _pmd, write)) update_mmu_cache_pmd(vma, addr, pmd); } int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; struct folio *src_folio; pmd_t pmd; pgtable_t pgtable = NULL; int ret = -ENOMEM; pmd = pmdp_get_lockless(src_pmd); if (unlikely(pmd_present(pmd) && pmd_special(pmd) && !is_huge_zero_pmd(pmd))) { dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); /* * No need to recheck the pmd, it can't change with write * mmap lock held here. * * Meanwhile, making sure it's not a CoW VMA with writable * mapping, otherwise it means either the anon page wrongly * applied special bit, or we made the PRIVATE mapping be * able to wrongly write to the backend MMIO. */ VM_WARN_ON_ONCE(is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd)); goto set_pmd; } /* Skip if can be re-fill on fault */ if (!vma_is_anonymous(dst_vma)) return 0; pgtable = pte_alloc_one(dst_mm); if (unlikely(!pgtable)) goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pmd = *src_pmd; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely(is_swap_pmd(pmd))) { swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); if (!is_readable_migration_entry(entry)) { entry = make_readable_migration_entry( swp_offset(entry)); pmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*src_pmd)) pmd = pmd_swp_mksoft_dirty(pmd); if (pmd_swp_uffd_wp(*src_pmd)) pmd = pmd_swp_mkuffd_wp(pmd); set_pmd_at(src_mm, addr, src_pmd, pmd); } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); if (!userfaultfd_wp(dst_vma)) pmd = pmd_swp_clear_uffd_wp(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; goto out_unlock; } #endif if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } /* * When page table lock is held, the huge zero pmd should not be * under splitting since we don't split the page itself, only pmd to * a page table. */ if (is_huge_zero_pmd(pmd)) { /* * mm_get_huge_zero_folio() will never allocate a new * folio here, since we already have a zero page to * copy. It just takes a reference. */ mm_get_huge_zero_folio(dst_mm); goto out_zero_page; } src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); src_folio = page_folio(src_page); folio_get(src_folio); if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, dst_vma, src_vma))) { /* Page maybe pinned: split and retry the fault on PTEs. */ folio_put(src_folio); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); __split_huge_pmd(src_vma, src_pmd, addr, false); return -EAGAIN; } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); out_zero_page: mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); if (!userfaultfd_wp(dst_vma)) pmd = pmd_clear_uffd_wp(pmd); pmd = pmd_wrprotect(pmd); set_pmd: pmd = pmd_mkold(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; out_unlock: spin_unlock(src_ptl); spin_unlock(dst_ptl); out: return ret; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write) { pud_t _pud; _pud = pud_mkyoung(*pud); if (write) _pud = pud_mkdirty(_pud); if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, pud, _pud, write)) update_mmu_cache_pud(vma, addr, pud); } int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma) { spinlock_t *dst_ptl, *src_ptl; pud_t pud; int ret; dst_ptl = pud_lock(dst_mm, dst_pud); src_ptl = pud_lockptr(src_mm, src_pud); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pud = *src_pud; if (unlikely(!pud_trans_huge(pud))) goto out_unlock; /* * TODO: once we support anonymous pages, use * folio_try_dup_anon_rmap_*() and split if duplicating fails. */ if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) { pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_wrprotect(pud); } pud = pud_mkold(pud); set_pud_at(dst_mm, addr, dst_pud, pud); ret = 0; out_unlock: spin_unlock(src_ptl); spin_unlock(dst_ptl); return ret; } void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); if (unlikely(!pud_same(*vmf->pud, orig_pud))) goto unlock; touch_pud(vmf->vma, vmf->address, vmf->pud, write); unlock: spin_unlock(vmf->ptl); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ void huge_pmd_set_accessed(struct vm_fault *vmf) { bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) goto unlock; touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); unlock: spin_unlock(vmf->ptl); } static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf) { unsigned long haddr = vmf->address & HPAGE_PMD_MASK; struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; struct folio *folio; vm_fault_t ret = 0; folio = vma_alloc_anon_folio_pmd(vma, vmf->address); if (unlikely(!folio)) return VM_FAULT_FALLBACK; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) goto release; ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; (void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd); map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); goto unlock; release: folio_put(folio); unlock: spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); return ret; } vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); if (is_huge_zero_pmd(orig_pmd)) { vm_fault_t ret = do_huge_zero_wp_pmd(vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; /* Fallback to splitting PMD if THP cannot be allocated */ goto fallback; } spin_lock(vmf->ptl); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { spin_unlock(vmf->ptl); return 0; } page = pmd_page(orig_pmd); folio = page_folio(page); VM_BUG_ON_PAGE(!PageHead(page), page); /* Early check when only holding the PT lock. */ if (PageAnonExclusive(page)) goto reuse; if (!folio_trylock(folio)) { folio_get(folio); spin_unlock(vmf->ptl); folio_lock(folio); spin_lock(vmf->ptl); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { spin_unlock(vmf->ptl); folio_unlock(folio); folio_put(folio); return 0; } folio_put(folio); } /* Recheck after temporarily dropping the PT lock. */ if (PageAnonExclusive(page)) { folio_unlock(folio); goto reuse; } /* * See do_wp_page(): we can only reuse the folio exclusively if * there are no additional references. Note that we always drain * the LRU cache immediately after adding a THP. */ if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio) * folio_nr_pages(folio)) goto unlock_fallback; if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_ref_count(folio) == 1) { pmd_t entry; folio_move_anon_rmap(folio, vma); SetPageAnonExclusive(page); folio_unlock(folio); reuse: if (unlikely(unshare)) { spin_unlock(vmf->ptl); return 0; } entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); return 0; } unlock_fallback: folio_unlock(folio); spin_unlock(vmf->ptl); fallback: __split_huge_pmd(vma, vmf->pmd, vmf->address, false); return VM_FAULT_FALLBACK; } static inline bool can_change_pmd_writable(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { struct page *page; if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE))) return false; /* Don't touch entries that are not even readable (NUMA hinting). */ if (pmd_protnone(pmd)) return false; /* Do we need write faults for softdirty tracking? */ if (pmd_needs_soft_dirty_wp(vma, pmd)) return false; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_huge_pmd_wp(vma, pmd)) return false; if (!(vma->vm_flags & VM_SHARED)) { /* See can_change_pte_writable(). */ page = vm_normal_page_pmd(vma, addr, pmd); return page && PageAnon(page) && PageAnonExclusive(page); } /* See can_change_pte_writable(). */ return pmd_dirty(pmd); } /* NUMA hinting page fault entry point for trans huge pmds */ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; int nid = NUMA_NO_NODE; int target_nid, last_cpupid; pmd_t pmd, old_pmd; bool writable = false; int flags = 0; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); old_pmd = pmdp_get(vmf->pmd); if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) { spin_unlock(vmf->ptl); return 0; } pmd = pmd_modify(old_pmd, vma->vm_page_prot); /* * Detect now whether the PMD could be writable; this information * is only valid while holding the PT lock. */ writable = pmd_write(pmd); if (!writable && vma_wants_manual_pte_write_upgrade(vma) && can_change_pmd_writable(vma, vmf->address, pmd)) writable = true; folio = vm_normal_folio_pmd(vma, haddr, pmd); if (!folio) goto out_map; nid = folio_nid(folio); target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable, &last_cpupid); if (target_nid == NUMA_NO_NODE) goto out_map; if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { flags |= TNF_MIGRATE_FAIL; goto out_map; } /* The folio is isolated and isolation code holds a folio reference. */ spin_unlock(vmf->ptl); writable = false; if (!migrate_misplaced_folio(folio, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); return 0; } flags |= TNF_MIGRATE_FAIL; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) { spin_unlock(vmf->ptl); return 0; } out_map: /* Restore the PMD */ pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot); pmd = pmd_mkyoung(pmd); if (writable) pmd = pmd_mkwrite(pmd, vma); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); return 0; } /* * Return true if we do MADV_FREE successfully on entire pmd page. * Otherwise, return false. */ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next) { spinlock_t *ptl; pmd_t orig_pmd; struct folio *folio; struct mm_struct *mm = tlb->mm; bool ret = false; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) goto out_unlocked; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto out; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); goto out; } folio = pmd_folio(orig_pmd); /* * If other processes are mapping this folio, we couldn't discard * the folio unless they all do MADV_FREE so let's skip the folio. */ if (folio_maybe_mapped_shared(folio)) goto out; if (!folio_trylock(folio)) goto out; /* * If user want to discard part-pages of THP, split it so MADV_FREE * will deactivate only them. */ if (next - addr != HPAGE_PMD_SIZE) { folio_get(folio); spin_unlock(ptl); split_folio(folio); folio_unlock(folio); folio_put(folio); goto out_unlocked; } if (folio_test_dirty(folio)) folio_clear_dirty(folio); folio_unlock(folio); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_mark_lazyfree(folio); ret = true; out: spin_unlock(ptl); out_unlocked: return ret; } static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, pmd); pte_free(mm, pgtable); mm_dec_nr_ptes(mm); } int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { pmd_t orig_pmd; spinlock_t *ptl; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; /* * For architectures like ppc64 we look at deposited pgtable * when calling pmdp_huge_get_and_clear. So do the * pgtable_trans_huge_withdraw after finishing pmdp related * operations. */ orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd, tlb->fullmm); arch_check_zapped_pmd(vma, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); if (!vma_is_dax(vma) && vma_is_special_huge(vma)) { if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else if (is_huge_zero_pmd(orig_pmd)) { if (!vma_is_dax(vma) || arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else { struct folio *folio = NULL; int flush_needed = 1; if (pmd_present(orig_pmd)) { struct page *page = pmd_page(orig_pmd); folio = page_folio(page); folio_remove_rmap_pmd(folio, page, vma); WARN_ON_ONCE(folio_mapcount(folio) < 0); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { swp_entry_t entry; VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); folio = pfn_swap_entry_folio(entry); flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); if (folio_test_anon(folio)) { zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); } else { if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PMD_NR); /* * Use flush_needed to indicate whether the PMD entry * is present, instead of checking pmd_present() again. */ if (flush_needed && pmd_young(orig_pmd) && likely(vma_has_recency(vma))) folio_mark_accessed(folio); } spin_unlock(ptl); if (flush_needed) tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE); } return 1; } #ifndef pmd_move_must_withdraw static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, spinlock_t *old_pmd_ptl, struct vm_area_struct *vma) { /* * With split pmd lock we also need to move preallocated * PTE page table if new_pmd is on different PMD page table. * * We also don't deposit and withdraw tables for file pages. */ return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); } #endif static pmd_t move_soft_dirty_pmd(pmd_t pmd) { #ifdef CONFIG_MEM_SOFT_DIRTY if (unlikely(is_pmd_migration_entry(pmd))) pmd = pmd_swp_mksoft_dirty(pmd); else if (pmd_present(pmd)) pmd = pmd_mksoft_dirty(pmd); #endif return pmd; } static pmd_t clear_uffd_wp_pmd(pmd_t pmd) { if (pmd_present(pmd)) pmd = pmd_clear_uffd_wp(pmd); else if (is_swap_pmd(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); return pmd; } bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { spinlock_t *old_ptl, *new_ptl; pmd_t pmd; struct mm_struct *mm = vma->vm_mm; bool force_flush = false; /* * The destination pmd shouldn't be established, free_pgtables() * should have released it; but move_page_tables() might have already * inserted a page table, if racing against shmem/file collapse. */ if (!pmd_none(*new_pmd)) { VM_BUG_ON(pmd_trans_huge(*new_pmd)); return false; } /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. */ old_ptl = __pmd_trans_huge_lock(old_pmd, vma); if (old_ptl) { new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); if (pmd_present(pmd)) force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); if (vma_has_uffd_without_event_remap(vma)) pmd = clear_uffd_wp_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); if (new_ptl != old_ptl) spin_unlock(new_ptl); spin_unlock(old_ptl); return true; } return false; } /* * Returns * - 0 if PMD could not be locked * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary * or if prot_numa but THP migration is not supported * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; pmd_t oldpmd, entry; bool prot_numa = cp_flags & MM_CP_PROT_NUMA; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; int ret = 1; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); if (prot_numa && !thp_migration_supported()) return 1; ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); struct folio *folio = pfn_swap_entry_folio(entry); pmd_t newpmd; VM_BUG_ON(!is_pmd_migration_entry(*pmd)); if (is_writable_migration_entry(entry)) { /* * A protection check is difficult so * just be safe and disable write */ if (folio_test_anon(folio)) entry = make_readable_exclusive_migration_entry(swp_offset(entry)); else entry = make_readable_migration_entry(swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); } else { newpmd = *pmd; } if (uffd_wp) newpmd = pmd_swp_mkuffd_wp(newpmd); else if (uffd_wp_resolve) newpmd = pmd_swp_clear_uffd_wp(newpmd); if (!pmd_same(*pmd, newpmd)) set_pmd_at(mm, addr, pmd, newpmd); goto unlock; } #endif if (prot_numa) { struct folio *folio; bool toptier; /* * Avoid trapping faults against the zero page. The read-only * data is likely to be read-cached on the local CPU and * local/remote hits to the zero page are not interesting. */ if (is_huge_zero_pmd(*pmd)) goto unlock; if (pmd_protnone(*pmd)) goto unlock; folio = pmd_folio(*pmd); toptier = node_is_toptier(folio_nid(folio)); /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && toptier) goto unlock; if (folio_use_access_time(folio)) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); } /* * In case prot_numa, we are under mmap_read_lock(mm). It's critical * to not clear pmd intermittently to avoid race with MADV_DONTNEED * which is also under mmap_read_lock(mm): * * CPU0: CPU1: * change_huge_pmd(prot_numa=1) * pmdp_huge_get_and_clear_notify() * madvise_dontneed() * zap_pmd_range() * pmd_trans_huge(*pmd) == 0 (without ptl) * // skip the pmd * set_pmd_at(); * // pmd is re-established * * The race makes MADV_DONTNEED miss the huge pmd and don't clear it * which may break userspace. * * pmdp_invalidate_ad() is required to make sure we don't miss * dirty/young flags set by hardware. */ oldpmd = pmdp_invalidate_ad(vma, addr, pmd); entry = pmd_modify(oldpmd, newprot); if (uffd_wp) entry = pmd_mkuffd_wp(entry); else if (uffd_wp_resolve) /* * Leave the write bit to be handled by PF interrupt * handler, then things like COW could be properly * handled. */ entry = pmd_clear_uffd_wp(entry); /* See change_pte_range(). */ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) && can_change_pmd_writable(vma, addr, entry)) entry = pmd_mkwrite(entry, vma); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); if (huge_pmd_needs_flush(oldpmd, entry)) tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE); unlock: spin_unlock(ptl); return ret; } /* * Returns: * * - 0: if pud leaf changed from under us * - 1: if pud can be skipped * - HPAGE_PUD_NR: if pud was successfully processed */ #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; pud_t oldpud, entry; spinlock_t *ptl; tlb_change_page_size(tlb, HPAGE_PUD_SIZE); /* NUMA balancing doesn't apply to dax */ if (cp_flags & MM_CP_PROT_NUMA) return 1; /* * Huge entries on userfault-wp only works with anonymous, while we * don't have anonymous PUDs yet. */ if (WARN_ON_ONCE(cp_flags & MM_CP_UFFD_WP_ALL)) return 1; ptl = __pud_trans_huge_lock(pudp, vma); if (!ptl) return 0; /* * Can't clear PUD or it can race with concurrent zapping. See * change_huge_pmd(). */ oldpud = pudp_invalidate(vma, addr, pudp); entry = pud_modify(oldpud, newprot); set_pud_at(mm, addr, pudp, entry); tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE); spin_unlock(ptl); return HPAGE_PUD_NR; } #endif #ifdef CONFIG_USERFAULTFD /* * The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by * the caller, but it must return after releasing the page_table_lock. * Just move the page from src_pmd to dst_pmd if possible. * Return zero if succeeded in moving the page, -EAGAIN if it needs to be * repeated by the caller, or other errors in case of failure. */ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr) { pmd_t _dst_pmd, src_pmdval; struct page *src_page; struct folio *src_folio; struct anon_vma *src_anon_vma; spinlock_t *src_ptl, *dst_ptl; pgtable_t src_pgtable; struct mmu_notifier_range range; int err = 0; src_pmdval = *src_pmd; src_ptl = pmd_lockptr(mm, src_pmd); lockdep_assert_held(src_ptl); vma_assert_locked(src_vma); vma_assert_locked(dst_vma); /* Sanity checks before the operation */ if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) || WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) { spin_unlock(src_ptl); return -EINVAL; } if (!pmd_trans_huge(src_pmdval)) { spin_unlock(src_ptl); if (is_pmd_migration_entry(src_pmdval)) { pmd_migration_entry_wait(mm, &src_pmdval); return -EAGAIN; } return -ENOENT; } src_page = pmd_page(src_pmdval); if (!is_huge_zero_pmd(src_pmdval)) { if (unlikely(!PageAnonExclusive(src_page))) { spin_unlock(src_ptl); return -EBUSY; } src_folio = page_folio(src_page); folio_get(src_folio); } else src_folio = NULL; spin_unlock(src_ptl); flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr, src_addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); if (src_folio) { folio_lock(src_folio); /* * split_huge_page walks the anon_vma chain without the page * lock. Serialize against it with the anon_vma lock, the page * lock is not enough. */ src_anon_vma = folio_get_anon_vma(src_folio); if (!src_anon_vma) { err = -EAGAIN; goto unlock_folio; } anon_vma_lock_write(src_anon_vma); } else src_anon_vma = NULL; dst_ptl = pmd_lockptr(mm, dst_pmd); double_pt_lock(src_ptl, dst_ptl); if (unlikely(!pmd_same(*src_pmd, src_pmdval) || !pmd_same(*dst_pmd, dst_pmdval))) { err = -EAGAIN; goto unlock_ptls; } if (src_folio) { if (folio_maybe_dma_pinned(src_folio) || !PageAnonExclusive(&src_folio->page)) { err = -EBUSY; goto unlock_ptls; } if (WARN_ON_ONCE(!folio_test_head(src_folio)) || WARN_ON_ONCE(!folio_test_anon(src_folio))) { err = -EBUSY; goto unlock_ptls; } src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { set_pmd_at(mm, src_addr, src_pmd, src_pmdval); err = -EBUSY; goto unlock_ptls; } folio_move_anon_rmap(src_folio, dst_vma); src_folio->index = linear_page_index(dst_vma, dst_addr); _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); } else { src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); _dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot); } set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd); pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable); unlock_ptls: double_pt_unlock(src_ptl, dst_ptl); if (src_anon_vma) { anon_vma_unlock_write(src_anon_vma); put_anon_vma(src_anon_vma); } unlock_folio: /* unblock rmap walks */ if (src_folio) folio_unlock(src_folio); mmu_notifier_invalidate_range_end(&range); if (src_folio) folio_put(src_folio); return err; } #endif /* CONFIG_USERFAULTFD */ /* * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. * * Note that if it returns page table lock pointer, this routine returns without * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { spinlock_t *ptl; ptl = pmd_lock(vma->vm_mm, pmd); if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd))) return ptl; spin_unlock(ptl); return NULL; } /* * Returns page table lock pointer if a given pud maps a thp, NULL otherwise. * * Note that if it returns page table lock pointer, this routine returns without * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { spinlock_t *ptl; ptl = pud_lock(vma->vm_mm, pud); if (likely(pud_trans_huge(*pud))) return ptl; spin_unlock(ptl); return NULL; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr) { spinlock_t *ptl; pud_t orig_pud; ptl = __pud_trans_huge_lock(pud, vma); if (!ptl) return 0; orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm); arch_check_zapped_pud(vma, orig_pud); tlb_remove_pud_tlb_entry(tlb, pud, addr); if (!vma_is_dax(vma) && vma_is_special_huge(vma)) { spin_unlock(ptl); /* No zero page support yet */ } else { struct page *page = NULL; struct folio *folio; /* No support for anonymous PUD pages or migration yet */ VM_WARN_ON_ONCE(vma_is_anonymous(vma) || !pud_present(orig_pud)); page = pud_page(orig_pud); folio = page_folio(page); folio_remove_rmap_pud(folio, page, vma); add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PUD_NR); spin_unlock(ptl); tlb_remove_page_size(tlb, page, HPAGE_PUD_SIZE); } return 1; } static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, unsigned long haddr) { struct folio *folio; struct page *page; pud_t old_pud; VM_BUG_ON(haddr & ~HPAGE_PUD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); VM_BUG_ON(!pud_trans_huge(*pud)); count_vm_event(THP_SPLIT_PUD); old_pud = pudp_huge_clear_flush(vma, haddr, pud); if (!vma_is_dax(vma)) return; page = pud_page(old_pud); folio = page_folio(page); if (!folio_test_dirty(folio) && pud_dirty(old_pud)) folio_mark_dirty(folio); if (!folio_test_referenced(folio) && pud_young(old_pud)) folio_set_referenced(folio); folio_remove_rmap_pud(folio, page, vma); folio_put(folio); add_mm_counter(vma->vm_mm, mm_counter_file(folio), -HPAGE_PUD_NR); } void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address) { spinlock_t *ptl; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address & HPAGE_PUD_MASK, (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE); mmu_notifier_invalidate_range_start(&range); ptl = pud_lock(vma->vm_mm, pud); if (unlikely(!pud_trans_huge(*pud))) goto out; __split_huge_pud_locked(vma, pud, range.start); out: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); } #else void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address) { } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd) { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable; pmd_t _pmd, old_pmd; unsigned long addr; pte_t *pte; int i; /* * Leave pmd empty until pte is filled note that it is fine to delay * notification until mmu_notifier_invalidate_range_end() as we are * replacing a zero pmd write protected page with a zero pte write * protected page. * * See Documentation/mm/mmu_notifier.rst */ old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte); for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry; entry = pfn_pte(my_zero_pfn(addr), vma->vm_page_prot); entry = pte_mkspecial(entry); if (pmd_uffd_wp(old_pmd)) entry = pte_mkuffd_wp(entry); VM_BUG_ON(!pte_none(ptep_get(pte))); set_pte_at(mm, addr, pte, entry); pte++; } pte_unmap(pte - 1); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); } static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, unsigned long haddr, bool freeze) { struct mm_struct *mm = vma->vm_mm; struct folio *folio; struct page *page; pgtable_t pgtable; pmd_t old_pmd, _pmd; bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; bool anon_exclusive = false, dirty = false; unsigned long addr; pte_t *pte; int i; VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)); count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it */ if (arch_needs_pgtable_deposit()) zap_deposited_table(mm, pmd); if (!vma_is_dax(vma) && vma_is_special_huge(vma)) return; if (unlikely(is_pmd_migration_entry(old_pmd))) { swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); folio = pfn_swap_entry_folio(entry); } else if (is_huge_zero_pmd(old_pmd)) { return; } else { page = pmd_page(old_pmd); folio = page_folio(page); if (!folio_test_dirty(folio) && pmd_dirty(old_pmd)) folio_mark_dirty(folio); if (!folio_test_referenced(folio) && pmd_young(old_pmd)) folio_set_referenced(folio); folio_remove_rmap_pmd(folio, page, vma); folio_put(folio); } add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR); return; } if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_arch_invalidate_secondary_tlbs() see comments below * inside __split_huge_pmd() ? * * We are going from a zero huge page write protected to zero * small page also write protected so it does not seems useful * to invalidate secondary mmu at this time. */ return __split_huge_zero_page_pmd(vma, haddr, pmd); } pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); if (PageAnon(page)) anon_exclusive = is_readable_exclusive_migration_entry(entry); young = is_migration_entry_young(entry); dirty = is_migration_entry_dirty(entry); soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { /* * Up to this point the pmd is present and huge and userland has * the whole access to the hugepage during the split (which * happens in place). If we overwrite the pmd with the not-huge * version pointing to the pte here (which of course we could if * all CPUs were bug free), userland could trigger a small page * size TLB miss on the small sized TLB while the hugepage TLB * entry is still established in the huge TLB. Some CPU doesn't * like that. See * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum * 383 on page 105. Intel should be safe but is also warns that * it's only safe if the permission and cache attributes of the * two entries loaded in the two TLB is identical (which should * be the case here). But it is generally safer to never allow * small and huge TLB entries for the same virtual address to be * loaded simultaneously. So instead of doing "pmd_populate(); * flush_pmd_tlb_range();" we first mark the current pmd * notpresent (atomically because here the pmd_trans_huge must * remain set at all times on the pmd until the split is * complete for this pmd), then we flush the SMP TLB and finally * we write the non-huge version of the pmd entry with * pmd_populate. */ old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); folio = page_folio(page); if (pmd_dirty(old_pmd)) { dirty = true; folio_set_dirty(folio); } write = pmd_write(old_pmd); young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); uffd_wp = pmd_uffd_wp(old_pmd); VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); /* * Without "freeze", we'll simply split the PMD, propagating the * PageAnonExclusive() flag for each PTE by setting it for * each subpage -- no need to (temporarily) clear. * * With "freeze" we want to replace mapped pages by * migration entries right away. This is only possible if we * managed to clear PageAnonExclusive() -- see * set_pmd_migration_entry(). * * In case we cannot clear PageAnonExclusive(), split the PMD * only and let try_to_migrate_one() fail later. * * See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ anon_exclusive = PageAnonExclusive(page); if (freeze && anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) freeze = false; if (!freeze) { rmap_t rmap_flags = RMAP_NONE; folio_ref_add(folio, HPAGE_PMD_NR - 1); if (anon_exclusive) rmap_flags |= RMAP_EXCLUSIVE; folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR, vma, haddr, rmap_flags); } } /* * Withdraw the table only after we mark the pmd entry invalid. * This's critical for some architectures (Power). */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte); /* * Note that NUMA hinting access restrictions are not transferred to * avoid any possibility of altering permissions across VMAs. */ if (freeze || pmd_migration) { for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry; swp_entry_t swp_entry; if (write) swp_entry = make_writable_migration_entry( page_to_pfn(page + i)); else if (anon_exclusive) swp_entry = make_readable_exclusive_migration_entry( page_to_pfn(page + i)); else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); if (young) swp_entry = make_migration_entry_young(swp_entry); if (dirty) swp_entry = make_migration_entry_dirty(swp_entry); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); if (uffd_wp) entry = pte_swp_mkuffd_wp(entry); VM_WARN_ON(!pte_none(ptep_get(pte + i))); set_pte_at(mm, addr, pte + i, entry); } } else { pte_t entry; entry = mk_pte(page, READ_ONCE(vma->vm_page_prot)); if (write) entry = pte_mkwrite(entry, vma); if (!young) entry = pte_mkold(entry); /* NOTE: this may set soft-dirty too on some archs */ if (dirty) entry = pte_mkdirty(entry); if (soft_dirty) entry = pte_mksoft_dirty(entry); if (uffd_wp) entry = pte_mkuffd_wp(entry); for (i = 0; i < HPAGE_PMD_NR; i++) VM_WARN_ON(!pte_none(ptep_get(pte + i))); set_ptes(mm, haddr, pte, entry, HPAGE_PMD_NR); } pte_unmap(pte); if (!pmd_migration) folio_remove_rmap_pmd(folio, page, vma); if (freeze) put_page(page); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); } void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze) { VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE)); if (pmd_trans_huge(*pmd) || is_pmd_migration_entry(*pmd)) __split_huge_pmd_locked(vma, pmd, address, freeze); } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze) { spinlock_t *ptl; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address & HPAGE_PMD_MASK, (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); ptl = pmd_lock(vma->vm_mm, pmd); split_huge_pmd_locked(vma, range.start, pmd, freeze); spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); } void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze) { pmd_t *pmd = mm_find_pmd(vma->vm_mm, address); if (!pmd) return; __split_huge_pmd(vma, pmd, address, freeze); } static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) { /* * If the new address isn't hpage aligned and it could previously * contain an hugepage: check if we need to split an huge pmd. */ if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) && range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE), ALIGN(address, HPAGE_PMD_SIZE))) split_huge_pmd_address(vma, address, false); } void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct vm_area_struct *next) { /* Check if we need to split start first. */ split_huge_pmd_if_needed(vma, start); /* Check if we need to split end next. */ split_huge_pmd_if_needed(vma, end); /* If we're incrementing next->vm_start, we might need to split it. */ if (next) split_huge_pmd_if_needed(next, end); } static void unmap_folio(struct folio *folio) { enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC | TTU_BATCH_FLUSH; VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (folio_test_pmd_mappable(folio)) ttu_flags |= TTU_SPLIT_HUGE_PMD; /* * Anon pages need migration entries to preserve them, but file * pages can simply be left unmapped, then faulted back on demand. * If that is ever changed (perhaps for mlock), update remap_page(). */ if (folio_test_anon(folio)) try_to_migrate(folio, ttu_flags); else try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); try_to_unmap_flush(); } static bool __discard_anon_folio_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio) { struct mm_struct *mm = vma->vm_mm; int ref_count, map_count; pmd_t orig_pmd = *pmdp; if (pmd_dirty(orig_pmd)) folio_set_dirty(folio); if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { folio_set_swapbacked(folio); return false; } orig_pmd = pmdp_huge_clear_flush(vma, addr, pmdp); /* * Syncing against concurrent GUP-fast: * - clear PMD; barrier; read refcount * - inc refcount; barrier; read PMD */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for folio refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * If the folio or its PMD is redirtied at this point, or if there * are unexpected references, we will give up to discard this folio * and remap it. * * The only folio refs must be one from isolation plus the rmap(s). */ if (pmd_dirty(orig_pmd)) folio_set_dirty(folio); if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { folio_set_swapbacked(folio); set_pmd_at(mm, addr, pmdp, orig_pmd); return false; } if (ref_count != map_count + 1) { set_pmd_at(mm, addr, pmdp, orig_pmd); return false; } folio_remove_rmap_pmd(folio, pmd_page(orig_pmd), vma); zap_deposited_table(mm, pmdp); add_mm_counter(mm, MM_ANONPAGES, -HPAGE_PMD_NR); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); return true; } bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_pmd_mappable(folio), folio); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_WARN_ON_ONCE(!IS_ALIGNED(addr, HPAGE_PMD_SIZE)); return __discard_anon_folio_pmd_locked(vma, addr, pmdp, folio); } static void remap_page(struct folio *folio, unsigned long nr, int flags) { int i = 0; /* If unmap_folio() uses try_to_migrate() on file, remove this check */ if (!folio_test_anon(folio)) return; for (;;) { remove_migration_ptes(folio, folio, RMP_LOCKED | flags); i += folio_nr_pages(folio); if (i >= nr) break; folio = folio_next(folio); } } static void lru_add_split_folio(struct folio *folio, struct folio *new_folio, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_FOLIO(folio_test_lru(new_folio), folio); lockdep_assert_held(&lruvec->lru_lock); if (list) { /* page reclaim is reclaiming a huge page */ VM_WARN_ON(folio_test_lru(folio)); folio_get(new_folio); list_add_tail(&new_folio->lru, list); } else { /* head is still on lru (and we have it frozen) */ VM_WARN_ON(!folio_test_lru(folio)); if (folio_test_unevictable(folio)) new_folio->mlock_count = 0; else list_add_tail(&new_folio->lru, &folio->lru); folio_set_lru(new_folio); } } /* Racy check whether the huge page can be split */ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { int extra_pins; /* Additional pins from page cache */ if (folio_test_anon(folio)) extra_pins = folio_test_swapcache(folio) ? folio_nr_pages(folio) : 0; else extra_pins = folio_nr_pages(folio); if (pextra_pins) *pextra_pins = extra_pins; return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - caller_pins; } static bool page_range_has_hwpoisoned(struct page *page, long nr_pages) { for (; nr_pages; page++, nr_pages--) if (PageHWPoison(page)) return true; return false; } /* * It splits @folio into @new_order folios and copies the @folio metadata to * all the resulting folios. */ static void __split_folio_to_order(struct folio *folio, int old_order, int new_order) { /* Scan poisoned pages when split a poisoned folio to large folios */ const bool handle_hwpoison = folio_test_has_hwpoisoned(folio) && new_order; long new_nr_pages = 1 << new_order; long nr_pages = 1 << old_order; long i; folio_clear_has_hwpoisoned(folio); /* Check first new_nr_pages since the loop below skips them */ if (handle_hwpoison && page_range_has_hwpoisoned(folio_page(folio, 0), new_nr_pages)) folio_set_has_hwpoisoned(folio); /* * Skip the first new_nr_pages, since the new folio from them have all * the flags from the original folio. */ for (i = new_nr_pages; i < nr_pages; i += new_nr_pages) { struct page *new_head = &folio->page + i; /* * Careful: new_folio is not a "real" folio before we cleared PageTail. * Don't pass it around before clear_compound_head(). */ struct folio *new_folio = (struct folio *)new_head; VM_BUG_ON_PAGE(atomic_read(&new_folio->_mapcount) != -1, new_head); /* * Clone page flags before unfreezing refcount. * * After successful get_page_unless_zero() might follow flags change, * for example lock_page() which set PG_waiters. * * Note that for mapped sub-pages of an anonymous THP, * PG_anon_exclusive has been cleared in unmap_folio() and is stored in * the migration entry instead from where remap_page() will restore it. * We can still have PG_anon_exclusive set on effectively unmapped and * unreferenced sub-pages of an anonymous THP: we can simply drop * PG_anon_exclusive (-> PG_mappedtodisk) for these here. */ new_folio->flags.f &= ~PAGE_FLAGS_CHECK_AT_PREP; new_folio->flags.f |= (folio->flags.f & ((1L << PG_referenced) | (1L << PG_swapbacked) | (1L << PG_swapcache) | (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | #ifdef CONFIG_ARCH_USES_PG_ARCH_2 (1L << PG_arch_2) | #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_3 (1L << PG_arch_3) | #endif (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); if (handle_hwpoison && page_range_has_hwpoisoned(new_head, new_nr_pages)) folio_set_has_hwpoisoned(new_folio); new_folio->mapping = folio->mapping; new_folio->index = folio->index + i; /* * page->private should not be set in tail pages. Fix up and warn once * if private is unexpectedly set. */ if (unlikely(new_folio->private)) { VM_WARN_ON_ONCE_PAGE(true, new_head); new_folio->private = NULL; } if (folio_test_swapcache(folio)) new_folio->swap.val = folio->swap.val + i; /* Page flags must be visible before we make the page non-compound. */ smp_wmb(); /* * Clear PageTail before unfreezing page refcount. * * After successful get_page_unless_zero() might follow put_page() * which needs correct compound_head(). */ clear_compound_head(new_head); if (new_order) { prep_compound_page(new_head, new_order); folio_set_large_rmappable(new_folio); } if (folio_test_young(folio)) folio_set_young(new_folio); if (folio_test_idle(folio)) folio_set_idle(new_folio); #ifdef CONFIG_MEMCG new_folio->memcg_data = folio->memcg_data; #endif folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio)); } if (new_order) folio_set_order(folio, new_order); else ClearPageCompound(&folio->page); } /* * It splits an unmapped @folio to lower order smaller folios in two ways. * @folio: the to-be-split folio * @new_order: the smallest order of the after split folios (since buddy * allocator like split generates folios with orders from @folio's * order - 1 to new_order). * @split_at: in buddy allocator like split, the folio containing @split_at * will be split until its order becomes @new_order. * @xas: xa_state pointing to folio->mapping->i_pages and locked by caller * @mapping: @folio->mapping * @uniform_split: if the split is uniform or not (buddy allocator like split) * * * 1. uniform split: the given @folio into multiple @new_order small folios, * where all small folios have the same order. This is done when * uniform_split is true. * 2. buddy allocator like (non-uniform) split: the given @folio is split into * half and one of the half (containing the given page) is split into half * until the given @page's order becomes @new_order. This is done when * uniform_split is false. * * The high level flow for these two methods are: * 1. uniform split: a single __split_folio_to_order() is called to split the * @folio into @new_order, then we traverse all the resulting folios one by * one in PFN ascending order and perform stats, unfreeze, adding to list, * and file mapping index operations. * 2. non-uniform split: in general, folio_order - @new_order calls to * __split_folio_to_order() are made in a for loop to split the @folio * to one lower order at a time. The resulting small folios are processed * like what is done during the traversal in 1, except the one containing * @page, which is split in next for loop. * * After splitting, the caller's folio reference will be transferred to the * folio containing @page. The caller needs to unlock and/or free after-split * folios if necessary. * * For !uniform_split, when -ENOMEM is returned, the original folio might be * split. The caller needs to check the input folio. */ static int __split_unmapped_folio(struct folio *folio, int new_order, struct page *split_at, struct xa_state *xas, struct address_space *mapping, bool uniform_split) { int order = folio_order(folio); int start_order = uniform_split ? new_order : order - 1; bool stop_split = false; struct folio *next; int split_order; int ret = 0; if (folio_test_anon(folio)) mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1); /* * split to new_order one order at a time. For uniform split, * folio is split to new_order directly. */ for (split_order = start_order; split_order >= new_order && !stop_split; split_order--) { struct folio *end_folio = folio_next(folio); int old_order = folio_order(folio); struct folio *new_folio; /* order-1 anonymous folio is not supported */ if (folio_test_anon(folio) && split_order == 1) continue; if (uniform_split && split_order != new_order) continue; if (mapping) { /* * uniform split has xas_split_alloc() called before * irq is disabled to allocate enough memory, whereas * non-uniform split can handle ENOMEM. */ if (uniform_split) xas_split(xas, folio, old_order); else { xas_set_order(xas, folio->index, split_order); xas_try_split(xas, folio, old_order); if (xas_error(xas)) { ret = xas_error(xas); stop_split = true; } } } if (!stop_split) { folio_split_memcg_refs(folio, old_order, split_order); split_page_owner(&folio->page, old_order, split_order); pgalloc_tag_split(folio, old_order, split_order); __split_folio_to_order(folio, old_order, split_order); } /* * Iterate through after-split folios and update folio stats. * But in buddy allocator like split, the folio * containing the specified page is skipped until its order * is new_order, since the folio will be worked on in next * iteration. */ for (new_folio = folio; new_folio != end_folio; new_folio = next) { next = folio_next(new_folio); /* * for buddy allocator like split, new_folio containing * @split_at page could be split again, thus do not * change stats yet. Wait until new_folio's order is * @new_order or stop_split is set to true by the above * xas_split() failure. */ if (new_folio == page_folio(split_at)) { folio = new_folio; if (split_order != new_order && !stop_split) continue; } if (folio_test_anon(new_folio)) mod_mthp_stat(folio_order(new_folio), MTHP_STAT_NR_ANON, 1); } } return ret; } bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, bool warns) { if (folio_test_anon(folio)) { /* order-1 is not supported for anonymous THP. */ VM_WARN_ONCE(warns && new_order == 1, "Cannot split to order-1 folio"); if (new_order == 1) return false; } else if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { /* * No split if the file system does not support large folio. * Note that we might still have THPs in such mappings due to * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping * does not actually support large folios properly. */ VM_WARN_ONCE(warns, "Cannot split file folio to non-0 order"); return false; } /* Only swapping a whole PMD-mapped folio is supported */ if (folio_test_swapcache(folio)) { VM_WARN_ONCE(warns, "Cannot split swapcache folio to non-0 order"); return false; } return true; } /* See comments in non_uniform_split_supported() */ bool uniform_split_supported(struct folio *folio, unsigned int new_order, bool warns) { if (folio_test_anon(folio)) { VM_WARN_ONCE(warns && new_order == 1, "Cannot split to order-1 folio"); if (new_order == 1) return false; } else if (new_order) { if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { VM_WARN_ONCE(warns, "Cannot split file folio to non-0 order"); return false; } } if (new_order && folio_test_swapcache(folio)) { VM_WARN_ONCE(warns, "Cannot split swapcache folio to non-0 order"); return false; } return true; } /* * __folio_split: split a folio at @split_at to a @new_order folio * @folio: folio to split * @new_order: the order of the new folio * @split_at: a page within the new folio * @lock_at: a page within @folio to be left locked to caller * @list: after-split folios will be put on it if non NULL * @uniform_split: perform uniform split or not (non-uniform split) * * It calls __split_unmapped_folio() to perform uniform and non-uniform split. * It is in charge of checking whether the split is supported or not and * preparing @folio for __split_unmapped_folio(). * * After splitting, the after-split folio containing @lock_at remains locked * and others are unlocked: * 1. for uniform split, @lock_at points to one of @folio's subpages; * 2. for buddy allocator like (non-uniform) split, @lock_at points to @folio. * * return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be * split but not to @new_order, the caller needs to check) */ static int __folio_split(struct folio *folio, unsigned int new_order, struct page *split_at, struct page *lock_at, struct list_head *list, bool uniform_split) { struct deferred_split *ds_queue = get_deferred_split_queue(folio); XA_STATE(xas, &folio->mapping->i_pages, folio->index); struct folio *end_folio = folio_next(folio); bool is_anon = folio_test_anon(folio); struct address_space *mapping = NULL; struct anon_vma *anon_vma = NULL; int order = folio_order(folio); struct folio *new_folio, *next; int nr_shmem_dropped = 0; int remap_flags = 0; int extra_pins, ret; pgoff_t end; bool is_hzp; VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); if (folio != page_folio(split_at) || folio != page_folio(lock_at)) return -EINVAL; /* * Folios that just got truncated cannot get split. Signal to the * caller that there was a race. * * TODO: this will also currently refuse shmem folios that are in the * swapcache. */ if (!is_anon && !folio->mapping) return -EBUSY; if (new_order >= folio_order(folio)) return -EINVAL; if (uniform_split && !uniform_split_supported(folio, new_order, true)) return -EINVAL; if (!uniform_split && !non_uniform_split_supported(folio, new_order, true)) return -EINVAL; is_hzp = is_huge_zero_folio(folio); if (is_hzp) { pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); return -EBUSY; } if (folio_test_writeback(folio)) return -EBUSY; if (is_anon) { /* * The caller does not necessarily hold an mmap_lock that would * prevent the anon_vma disappearing so we first we take a * reference to it and then lock the anon_vma for write. This * is similar to folio_lock_anon_vma_read except the write lock * is taken to serialise against parallel split or collapse * operations. */ anon_vma = folio_get_anon_vma(folio); if (!anon_vma) { ret = -EBUSY; goto out; } mapping = NULL; anon_vma_lock_write(anon_vma); } else { unsigned int min_order; gfp_t gfp; mapping = folio->mapping; min_order = mapping_min_folio_order(folio->mapping); if (new_order < min_order) { ret = -EINVAL; goto out; } gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); if (!filemap_release_folio(folio, gfp)) { ret = -EBUSY; goto out; } if (uniform_split) { xas_set_order(&xas, folio->index, new_order); xas_split_alloc(&xas, folio, folio_order(folio), gfp); if (xas_error(&xas)) { ret = xas_error(&xas); goto out; } } anon_vma = NULL; i_mmap_lock_read(mapping); /* *__split_unmapped_folio() may need to trim off pages beyond * EOF: but on 32-bit, i_size_read() takes an irq-unsafe * seqlock, which cannot be nested inside the page tree lock. * So note end now: i_size itself may be changed at any moment, * but folio lock is good enough to serialize the trimming. */ end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (shmem_mapping(mapping)) end = shmem_fallocend(mapping->host, end); } /* * Racy check if we can split the page, before unmap_folio() will * split PMDs */ if (!can_split_folio(folio, 1, &extra_pins)) { ret = -EAGAIN; goto out_unlock; } unmap_folio(folio); /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); if (mapping) { /* * Check if the folio is present in page cache. * We assume all tail are present too, if folio is there. */ xas_lock(&xas); xas_reset(&xas); if (xas_load(&xas) != folio) { ret = -EAGAIN; goto fail; } } /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); if (folio_ref_freeze(folio, 1 + extra_pins)) { struct swap_cluster_info *ci = NULL; struct lruvec *lruvec; int expected_refs; if (folio_order(folio) > 1 && !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } /* * Reinitialize page_deferred_list after removing the * page from the split_queue, otherwise a subsequent * split will see list corruption when checking the * page_deferred_list. */ list_del_init(&folio->_deferred_list); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { int nr = folio_nr_pages(folio); if (folio_test_pmd_mappable(folio) && new_order < HPAGE_PMD_ORDER) { if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } } } if (folio_test_swapcache(folio)) { if (mapping) { VM_WARN_ON_ONCE_FOLIO(mapping, folio); ret = -EINVAL; goto fail; } ci = swap_cluster_get_and_lock(folio); } /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ lruvec = folio_lruvec_lock(folio); ret = __split_unmapped_folio(folio, new_order, split_at, &xas, mapping, uniform_split); /* * Unfreeze after-split folios and put them back to the right * list. @folio should be kept frozon until page cache * entries are updated with all the other after-split folios * to prevent others seeing stale page cache entries. * As a result, new_folio starts from the next folio of * @folio. */ for (new_folio = folio_next(folio); new_folio != end_folio; new_folio = next) { unsigned long nr_pages = folio_nr_pages(new_folio); next = folio_next(new_folio); expected_refs = folio_expected_ref_count(new_folio) + 1; folio_ref_unfreeze(new_folio, expected_refs); lru_add_split_folio(folio, new_folio, lruvec, list); /* * Anonymous folio with swap cache. * NOTE: shmem in swap cache is not supported yet. */ if (ci) { __swap_cache_replace_folio(ci, folio, new_folio); continue; } /* Anonymous folio without swap cache */ if (!mapping) continue; /* Add the new folio to the page cache. */ if (new_folio->index < end) { __xa_store(&mapping->i_pages, new_folio->index, new_folio, 0); continue; } /* Drop folio beyond EOF: ->index >= end */ if (shmem_mapping(mapping)) nr_shmem_dropped += nr_pages; else if (folio_test_clear_dirty(new_folio)) folio_account_cleaned( new_folio, inode_to_wb(mapping->host)); __filemap_remove_folio(new_folio, NULL); folio_put_refs(new_folio, nr_pages); } /* * Unfreeze @folio only after all page cache entries, which * used to point to it, have been updated with new folios. * Otherwise, a parallel folio_try_get() can grab @folio * and its caller can see stale page cache entries. */ expected_refs = folio_expected_ref_count(folio) + 1; folio_ref_unfreeze(folio, expected_refs); unlock_page_lruvec(lruvec); if (ci) swap_cluster_unlock(ci); } else { spin_unlock(&ds_queue->split_queue_lock); ret = -EAGAIN; } fail: if (mapping) xas_unlock(&xas); local_irq_enable(); if (nr_shmem_dropped) shmem_uncharge(mapping->host, nr_shmem_dropped); if (!ret && is_anon) remap_flags = RMP_USE_SHARED_ZEROPAGE; remap_page(folio, 1 << order, remap_flags); /* * Unlock all after-split folios except the one containing * @lock_at page. If @folio is not split, it will be kept locked. */ for (new_folio = folio; new_folio != end_folio; new_folio = next) { next = folio_next(new_folio); if (new_folio == page_folio(lock_at)) continue; folio_unlock(new_folio); /* * Subpages may be freed if there wasn't any mapping * like if add_to_swap() is running on a lru page that * had its mapping zapped. And freeing these pages * requires taking the lru_lock so we do the put_page * of the tail pages after the split is complete. */ free_folio_and_swap_cache(new_folio); } out_unlock: if (anon_vma) { anon_vma_unlock_write(anon_vma); put_anon_vma(anon_vma); } if (mapping) i_mmap_unlock_read(mapping); out: xas_destroy(&xas); if (order == HPAGE_PMD_ORDER) count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); count_mthp_stat(order, !ret ? MTHP_STAT_SPLIT : MTHP_STAT_SPLIT_FAILED); return ret; } /* * This function splits a large folio into smaller folios of order @new_order. * @page can point to any page of the large folio to split. The split operation * does not change the position of @page. * * Prerequisites: * * 1) The caller must hold a reference on the @page's owning folio, also known * as the large folio. * * 2) The large folio must be locked. * * 3) The folio must not be pinned. Any unexpected folio references, including * GUP pins, will result in the folio not getting split; instead, the caller * will receive an -EAGAIN. * * 4) @new_order > 1, usually. Splitting to order-1 anonymous folios is not * supported for non-file-backed folios, because folio->_deferred_list, which * is used by partially mapped folios, is stored in subpage 2, but an order-1 * folio only has subpages 0 and 1. File-backed order-1 folios are supported, * since they do not use _deferred_list. * * After splitting, the caller's folio reference will be transferred to @page, * resulting in a raised refcount of @page after this call. The other pages may * be freed if they are not mapped. * * If @list is null, tail pages will be added to LRU list, otherwise, to @list. * * Pages in @new_order will inherit the mapping, flags, and so on from the * huge page. * * Returns 0 if the huge page was split successfully. * * Returns -EAGAIN if the folio has unexpected reference (e.g., GUP) or if * the folio was concurrently removed from the page cache. * * Returns -EBUSY when trying to split the huge zeropage, if the folio is * under writeback, if fs-specific folio metadata cannot currently be * released, or if some unexpected race happened (e.g., anon VMA disappeared, * truncation). * * Callers should ensure that the order respects the address space mapping * min-order if one is set for non-anonymous folios. * * Returns -EINVAL when trying to split to an order that is incompatible * with the folio. Splitting to order 0 is compatible with all folios. */ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) { struct folio *folio = page_folio(page); return __folio_split(folio, new_order, &folio->page, page, list, true); } /* * folio_split: split a folio at @split_at to a @new_order folio * @folio: folio to split * @new_order: the order of the new folio * @split_at: a page within the new folio * * return: 0: successful, <0 failed (if -ENOMEM is returned, @folio might be * split but not to @new_order, the caller needs to check) * * It has the same prerequisites and returns as * split_huge_page_to_list_to_order(). * * Split a folio at @split_at to a new_order folio, leave the * remaining subpages of the original folio as large as possible. For example, * in the case of splitting an order-9 folio at its third order-3 subpages to * an order-3 folio, there are 2^(9-3)=64 order-3 subpages in the order-9 folio. * After the split, there will be a group of folios with different orders and * the new folio containing @split_at is marked in bracket: * [order-4, {order-3}, order-3, order-5, order-6, order-7, order-8]. * * After split, folio is left locked for caller. */ int folio_split(struct folio *folio, unsigned int new_order, struct page *split_at, struct list_head *list) { return __folio_split(folio, new_order, split_at, &folio->page, list, false); } int min_order_for_split(struct folio *folio) { if (folio_test_anon(folio)) return 0; if (!folio->mapping) { if (folio_test_pmd_mappable(folio)) count_vm_event(THP_SPLIT_PAGE_FAILED); return -EBUSY; } return mapping_min_folio_order(folio->mapping); } int split_folio_to_list(struct folio *folio, struct list_head *list) { return split_huge_page_to_list_to_order(&folio->page, list, 0); } /* * __folio_unqueue_deferred_split() is not to be called directly: * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h * limits its calls to those folios which may have a _deferred_list for * queueing THP splits, and that list is (racily observed to be) non-empty. * * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is * zero: because even when split_queue_lock is held, a non-empty _deferred_list * might be in use on deferred_split_scan()'s unlocked on-stack list. * * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is * therefore important to unqueue deferred split before changing folio memcg. */ bool __folio_unqueue_deferred_split(struct folio *folio) { struct deferred_split *ds_queue; unsigned long flags; bool unqueued = false; WARN_ON_ONCE(folio_ref_count(folio)); WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio)); ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } list_del_init(&folio->_deferred_list); unqueued = true; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); return unqueued; /* useful for debug warnings */ } /* partially_mapped=false won't clear PG_partially_mapped folio flag */ void deferred_split_folio(struct folio *folio, bool partially_mapped) { struct deferred_split *ds_queue = get_deferred_split_queue(folio); #ifdef CONFIG_MEMCG struct mem_cgroup *memcg = folio_memcg(folio); #endif unsigned long flags; /* * Order 1 folios have no space for a deferred list, but we also * won't waste much memory by not adding them to the deferred list. */ if (folio_order(folio) <= 1) return; if (!partially_mapped && !split_underused_thp) return; /* * Exclude swapcache: originally to avoid a corrupt deferred split * queue. Nowadays that is fully prevented by memcg1_swapout(); * but if page reclaim is already handling the same folio, it is * unnecessary to handle it again in the shrinker, so excluding * swapcache here may still be a useful optimization. */ if (folio_test_swapcache(folio)) return; spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (partially_mapped) { if (!folio_test_partially_mapped(folio)) { folio_set_partially_mapped(folio); if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1); } } else { /* partially mapped folios cannot become non-partially mapped */ VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio); } if (list_empty(&folio->_deferred_list)) { list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG if (memcg) set_shrinker_bit(memcg, folio_nid(folio), deferred_split_shrinker->id); #endif } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; #ifdef CONFIG_MEMCG if (sc->memcg) ds_queue = &sc->memcg->deferred_split_queue; #endif return READ_ONCE(ds_queue->split_queue_len); } static bool thp_underused(struct folio *folio) { int num_zero_pages = 0, num_filled_pages = 0; int i; if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1) return false; if (folio_contain_hwpoisoned_page(folio)) return false; for (i = 0; i < folio_nr_pages(folio); i++) { if (pages_identical(folio_page(folio, i), ZERO_PAGE(0))) { if (++num_zero_pages > khugepaged_max_ptes_none) return true; } else { /* * Another path for early exit once the number * of non-zero filled pages exceeds threshold. */ if (++num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) return false; } } return false; } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list); struct folio *folio, *next, *prev = NULL; int split = 0, removed = 0; #ifdef CONFIG_MEMCG if (sc->memcg) ds_queue = &sc->memcg->deferred_split_queue; #endif spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_entry_safe(folio, next, &ds_queue->split_queue, _deferred_list) { if (folio_try_get(folio)) { list_move(&folio->_deferred_list, &list); } else { /* We lost race with folio_put() */ if (folio_test_partially_mapped(folio)) { folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } list_del_init(&folio->_deferred_list); ds_queue->split_queue_len--; } if (!--sc->nr_to_scan) break; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_entry_safe(folio, next, &list, _deferred_list) { bool did_split = false; bool underused = false; if (!folio_test_partially_mapped(folio)) { /* * See try_to_map_unused_to_zeropage(): we cannot * optimize zero-filled pages after splitting an * mlocked folio. */ if (folio_test_mlocked(folio)) goto next; underused = thp_underused(folio); if (!underused) goto next; } if (!folio_trylock(folio)) goto next; if (!split_folio(folio)) { did_split = true; if (underused) count_vm_event(THP_UNDERUSED_SPLIT_PAGE); split++; } folio_unlock(folio); next: /* * split_folio() removes folio from list on success. * Only add back to the queue if folio is partially mapped. * If thp_underused returns false, or if split_folio fails * in the case it was underused, then consider it used and * don't add it back to split_queue. */ if (did_split) { ; /* folio already removed from list */ } else if (!folio_test_partially_mapped(folio)) { list_del_init(&folio->_deferred_list); removed++; } else { /* * That unlocked list_del_init() above would be unsafe, * unless its folio is separated from any earlier folios * left on the list (which may be concurrently unqueued) * by one safe folio with refcount still raised. */ swap(folio, prev); } if (folio) folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); ds_queue->split_queue_len -= removed; spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); if (prev) folio_put(prev); /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. */ if (!split && list_empty(&ds_queue->split_queue)) return SHRINK_STOP; return split; } #ifdef CONFIG_DEBUG_FS static void split_huge_pages_all(void) { struct zone *zone; struct page *page; struct folio *folio; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; pr_debug("Split all THPs\n"); for_each_zone(zone) { if (!managed_zone(zone)) continue; max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { int nr_pages; page = pfn_to_online_page(pfn); if (!page || PageTail(page)) continue; folio = page_folio(page); if (!folio_try_get(folio)) continue; if (unlikely(page_folio(page) != folio)) goto next; if (zone != folio_zone(folio)) goto next; if (!folio_test_large(folio) || folio_test_hugetlb(folio) || !folio_test_lru(folio)) goto next; total++; folio_lock(folio); nr_pages = folio_nr_pages(folio); if (!split_folio(folio)) split++; pfn += nr_pages - 1; folio_unlock(folio); next: folio_put(folio); cond_resched(); } } pr_debug("%lu of %lu THP split\n", split, total); } static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) { return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || is_vm_hugetlb_page(vma); } static int split_huge_pages_pid(int pid, unsigned long vaddr_start, unsigned long vaddr_end, unsigned int new_order, long in_folio_offset) { int ret = 0; struct task_struct *task; struct mm_struct *mm; unsigned long total = 0, split = 0; unsigned long addr; vaddr_start &= PAGE_MASK; vaddr_end &= PAGE_MASK; task = find_get_task_by_vpid(pid); if (!task) { ret = -ESRCH; goto out; } /* Find the mm_struct */ mm = get_task_mm(task); put_task_struct(task); if (!mm) { ret = -EINVAL; goto out; } pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx], new_order: %u, in_folio_offset: %ld\n", pid, vaddr_start, vaddr_end, new_order, in_folio_offset); mmap_read_lock(mm); /* * always increase addr by PAGE_SIZE, since we could have a PTE page * table filled with PTE-mapped THPs, each of which is distinct. */ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { struct vm_area_struct *vma = vma_lookup(mm, addr); struct folio_walk fw; struct folio *folio; struct address_space *mapping; unsigned int target_order = new_order; if (!vma) break; /* skip special VMA and hugetlb VMA */ if (vma_not_suitable_for_thp_split(vma)) { addr = vma->vm_end; continue; } folio = folio_walk_start(&fw, vma, addr, 0); if (!folio) continue; if (!is_transparent_hugepage(folio)) goto next; if (!folio_test_anon(folio)) { mapping = folio->mapping; target_order = max(new_order, mapping_min_folio_order(mapping)); } if (target_order >= folio_order(folio)) goto next; total++; /* * For folios with private, split_huge_page_to_list_to_order() * will try to drop it before split and then check if the folio * can be split or not. So skip the check here. */ if (!folio_test_private(folio) && !can_split_folio(folio, 0, NULL)) goto next; if (!folio_trylock(folio)) goto next; folio_get(folio); folio_walk_end(&fw, vma); if (!folio_test_anon(folio) && folio->mapping != mapping) goto unlock; if (in_folio_offset < 0 || in_folio_offset >= folio_nr_pages(folio)) { if (!split_folio_to_order(folio, target_order)) split++; } else { struct page *split_at = folio_page(folio, in_folio_offset); if (!folio_split(folio, target_order, split_at, NULL)) split++; } unlock: folio_unlock(folio); folio_put(folio); cond_resched(); continue; next: folio_walk_end(&fw, vma); cond_resched(); } mmap_read_unlock(mm); mmput(mm); pr_debug("%lu of %lu THP split\n", split, total); out: return ret; } static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, pgoff_t off_end, unsigned int new_order, long in_folio_offset) { struct filename *file; struct file *candidate; struct address_space *mapping; int ret = -EINVAL; pgoff_t index; int nr_pages = 1; unsigned long total = 0, split = 0; unsigned int min_order; unsigned int target_order; file = getname_kernel(file_path); if (IS_ERR(file)) return ret; candidate = file_open_name(file, O_RDONLY, 0); if (IS_ERR(candidate)) goto out; pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx], new_order: %u, in_folio_offset: %ld\n", file_path, off_start, off_end, new_order, in_folio_offset); mapping = candidate->f_mapping; min_order = mapping_min_folio_order(mapping); target_order = max(new_order, min_order); for (index = off_start; index < off_end; index += nr_pages) { struct folio *folio = filemap_get_folio(mapping, index); nr_pages = 1; if (IS_ERR(folio)) continue; if (!folio_test_large(folio)) goto next; total++; nr_pages = folio_nr_pages(folio); if (target_order >= folio_order(folio)) goto next; if (!folio_trylock(folio)) goto next; if (folio->mapping != mapping) goto unlock; if (in_folio_offset < 0 || in_folio_offset >= nr_pages) { if (!split_folio_to_order(folio, target_order)) split++; } else { struct page *split_at = folio_page(folio, in_folio_offset); if (!folio_split(folio, target_order, split_at, NULL)) split++; } unlock: folio_unlock(folio); next: folio_put(folio); cond_resched(); } filp_close(candidate, NULL); ret = 0; pr_debug("%lu of %lu file-backed THP split\n", split, total); out: putname(file); return ret; } #define MAX_INPUT_BUF_SZ 255 static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, size_t count, loff_t *ppops) { static DEFINE_MUTEX(split_debug_mutex); ssize_t ret; /* * hold pid, start_vaddr, end_vaddr, new_order or * file_path, off_start, off_end, new_order */ char input_buf[MAX_INPUT_BUF_SZ]; int pid; unsigned long vaddr_start, vaddr_end; unsigned int new_order = 0; long in_folio_offset = -1; ret = mutex_lock_interruptible(&split_debug_mutex); if (ret) return ret; ret = -EFAULT; memset(input_buf, 0, MAX_INPUT_BUF_SZ); if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) goto out; input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; if (input_buf[0] == '/') { char *tok; char *tok_buf = input_buf; char file_path[MAX_INPUT_BUF_SZ]; pgoff_t off_start = 0, off_end = 0; size_t input_len = strlen(input_buf); tok = strsep(&tok_buf, ","); if (tok && tok_buf) { strscpy(file_path, tok); } else { ret = -EINVAL; goto out; } ret = sscanf(tok_buf, "0x%lx,0x%lx,%d,%ld", &off_start, &off_end, &new_order, &in_folio_offset); if (ret != 2 && ret != 3 && ret != 4) { ret = -EINVAL; goto out; } ret = split_huge_pages_in_file(file_path, off_start, off_end, new_order, in_folio_offset); if (!ret) ret = input_len; goto out; } ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d,%ld", &pid, &vaddr_start, &vaddr_end, &new_order, &in_folio_offset); if (ret == 1 && pid == 1) { split_huge_pages_all(); ret = strlen(input_buf); goto out; } else if (ret != 3 && ret != 4 && ret != 5) { ret = -EINVAL; goto out; } ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order, in_folio_offset); if (!ret) ret = strlen(input_buf); out: mutex_unlock(&split_debug_mutex); return ret; } static const struct file_operations split_huge_pages_fops = { .owner = THIS_MODULE, .write = split_huge_pages_write, }; static int __init split_huge_pages_debugfs(void) { debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); return 0; } late_initcall(split_huge_pages_debugfs); #endif #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { struct folio *folio = page_folio(page); struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; bool anon_exclusive; pmd_t pmdval; swp_entry_t entry; pmd_t pmdswp; if (!(pvmw->pmd && !pvmw->pte)) return 0; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); /* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page); if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) { set_pmd_at(mm, address, pvmw->pmd, pmdval); return -EBUSY; } if (pmd_dirty(pmdval)) folio_mark_dirty(folio); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); if (pmd_young(pmdval)) entry = make_migration_entry_young(entry); if (pmd_dirty(pmdval)) entry = make_migration_entry_dirty(entry); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); if (pmd_uffd_wp(pmdval)) pmdswp = pmd_swp_mkuffd_wp(pmdswp); set_pmd_at(mm, address, pvmw->pmd, pmdswp); folio_remove_rmap_pmd(folio, page, vma); folio_put(folio); trace_set_migration_pmd(address, pmd_val(pmdswp)); return 0; } void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { struct folio *folio = page_folio(new); struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; unsigned long haddr = address & HPAGE_PMD_MASK; pmd_t pmde; swp_entry_t entry; if (!(pvmw->pmd && !pvmw->pte)) return; entry = pmd_to_swp_entry(*pvmw->pmd); folio_get(folio); pmde = folio_mk_pmd(folio, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_writable_migration_entry(entry)) pmde = pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_mkuffd_wp(pmde); if (!is_migration_entry_young(entry)) pmde = pmd_mkold(pmde); /* NOTE: this may contain setting soft-dirty on some archs */ if (folio_test_dirty(folio) && is_migration_entry_dirty(entry)) pmde = pmd_mkdirty(pmde); if (folio_test_anon(folio)) { rmap_t rmap_flags = RMAP_NONE; if (!is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags); } else { folio_add_file_rmap_pmd(folio, new, vma); } VM_BUG_ON(pmd_write(pmde) && folio_test_anon(folio) && !PageAnonExclusive(new)); set_pmd_at(mm, haddr, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ update_mmu_cache_pmd(vma, address, pvmw->pmd); trace_remove_migration_pmd(address, pmd_val(pmde)); } #endif |
| 17 10 8 11 3 8 8 4 3 4 4 13 13 7 13 13 8 19 18 11 19 16 16 16 16 5 5 3 3 3 3 3 1 1 1 15 1 3 4 1 1 3 3 4 1 1 1 1 3 1 3 3 3 1 1 1 1 1 1 1 1 1 1 3 3 4 3 4 7 7 3 3 7 7 7 7 7 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #include <net/flow.h> #include <net/ip.h> #include "ipvlan.h" static u32 ipvlan_jhash_secret __read_mostly; void ipvlan_init_secret(void) { net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret)); } void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast) { if (likely(success)) { struct ipvl_pcpu_stats *pcptr; pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); u64_stats_inc(&pcptr->rx_pkts); u64_stats_add(&pcptr->rx_bytes, len); if (mcast) u64_stats_inc(&pcptr->rx_mcast); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->rx_errs); } } EXPORT_SYMBOL_GPL(ipvlan_count_rx); #if IS_ENABLED(CONFIG_IPV6) static u8 ipvlan_get_v6_hash(const void *iaddr) { const struct in6_addr *ip6_addr = iaddr; return __ipv6_addr_jhash(ip6_addr, ipvlan_jhash_secret) & IPVLAN_HASH_MASK; } #else static u8 ipvlan_get_v6_hash(const void *iaddr) { return 0; } #endif static u8 ipvlan_get_v4_hash(const void *iaddr) { const struct in_addr *ip4_addr = iaddr; return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) & IPVLAN_HASH_MASK; } static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr) { if (!is_v6 && addr->atype == IPVL_IPV4) { struct in_addr *i4addr = (struct in_addr *)iaddr; return addr->ip4addr.s_addr == i4addr->s_addr; #if IS_ENABLED(CONFIG_IPV6) } else if (is_v6 && addr->atype == IPVL_IPV6) { struct in6_addr *i6addr = (struct in6_addr *)iaddr; return ipv6_addr_equal(&addr->ip6addr, i6addr); #endif } return false; } static struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port, const void *iaddr, bool is_v6) { struct ipvl_addr *addr; u8 hash; hash = is_v6 ? ipvlan_get_v6_hash(iaddr) : ipvlan_get_v4_hash(iaddr); hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) if (addr_equal(is_v6, addr, iaddr)) return addr; return NULL; } void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr) { struct ipvl_port *port = ipvlan->port; u8 hash; hash = (addr->atype == IPVL_IPV6) ? ipvlan_get_v6_hash(&addr->ip6addr) : ipvlan_get_v4_hash(&addr->ip4addr); if (hlist_unhashed(&addr->hlnode)) hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]); } void ipvlan_ht_addr_del(struct ipvl_addr *addr) { hlist_del_init_rcu(&addr->hlnode); } struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6) { struct ipvl_addr *addr, *ret = NULL; rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) { if (addr_equal(is_v6, addr, iaddr)) { ret = addr; break; } } rcu_read_unlock(); return ret; } bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) { struct ipvl_dev *ipvlan; bool ret = false; rcu_read_lock(); list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) { if (ipvlan_find_addr(ipvlan, iaddr, is_v6)) { ret = true; break; } } rcu_read_unlock(); return ret; } void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) { void *lyr3h = NULL; switch (skb->protocol) { case htons(ETH_P_ARP): { struct arphdr *arph; if (unlikely(!pskb_may_pull(skb, arp_hdr_len(port->dev)))) return NULL; arph = arp_hdr(skb); *type = IPVL_ARP; lyr3h = arph; break; } case htons(ETH_P_IP): { u32 pktlen; struct iphdr *ip4h; if (unlikely(!pskb_may_pull(skb, sizeof(*ip4h)))) return NULL; ip4h = ip_hdr(skb); pktlen = skb_ip_totlen(skb); if (ip4h->ihl < 5 || ip4h->version != 4) return NULL; if (skb->len < pktlen || pktlen < (ip4h->ihl * 4)) return NULL; *type = IPVL_IPV4; lyr3h = ip4h; break; } #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct ipv6hdr *ip6h; if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h)))) return NULL; ip6h = ipv6_hdr(skb); if (ip6h->version != 6) return NULL; *type = IPVL_IPV6; lyr3h = ip6h; /* Only Neighbour Solicitation pkts need different treatment */ if (ipv6_addr_any(&ip6h->saddr) && ip6h->nexthdr == NEXTHDR_ICMP) { struct icmp6hdr *icmph; if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h) + sizeof(*icmph)))) return NULL; ip6h = ipv6_hdr(skb); icmph = (struct icmp6hdr *)(ip6h + 1); if (icmph->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) { /* Need to access the ipv6 address in body */ if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h) + sizeof(*icmph) + sizeof(struct in6_addr)))) return NULL; ip6h = ipv6_hdr(skb); icmph = (struct icmp6hdr *)(ip6h + 1); } *type = IPVL_ICMPV6; lyr3h = icmph; } break; } #endif default: return NULL; } return lyr3h; } unsigned int ipvlan_mac_hash(const unsigned char *addr) { u32 hash = jhash_1word(get_unaligned((u32 *)(addr + 2)), ipvlan_jhash_secret); return hash & IPVLAN_MAC_FILTER_MASK; } void ipvlan_process_multicast(struct work_struct *work) { struct ipvl_port *port = container_of(work, struct ipvl_port, wq); struct ethhdr *ethh; struct ipvl_dev *ipvlan; struct sk_buff *skb, *nskb; struct sk_buff_head list; unsigned int len; unsigned int mac_hash; int ret; u8 pkt_type; bool tx_pkt; __skb_queue_head_init(&list); spin_lock_bh(&port->backlog.lock); skb_queue_splice_tail_init(&port->backlog, &list); spin_unlock_bh(&port->backlog.lock); while ((skb = __skb_dequeue(&list)) != NULL) { struct net_device *dev = skb->dev; bool consumed = false; ethh = eth_hdr(skb); tx_pkt = IPVL_SKB_CB(skb)->tx_pkt; mac_hash = ipvlan_mac_hash(ethh->h_dest); if (ether_addr_equal(ethh->h_dest, port->dev->broadcast)) pkt_type = PACKET_BROADCAST; else pkt_type = PACKET_MULTICAST; rcu_read_lock(); list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) { if (tx_pkt && (ipvlan->dev == skb->dev)) continue; if (!test_bit(mac_hash, ipvlan->mac_filters)) continue; if (!(ipvlan->dev->flags & IFF_UP)) continue; ret = NET_RX_DROP; len = skb->len + ETH_HLEN; nskb = skb_clone(skb, GFP_ATOMIC); local_bh_disable(); if (nskb) { consumed = true; nskb->pkt_type = pkt_type; nskb->dev = ipvlan->dev; if (tx_pkt) ret = dev_forward_skb(ipvlan->dev, nskb); else ret = netif_rx(nskb); } ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true); local_bh_enable(); } rcu_read_unlock(); if (tx_pkt) { /* If the packet originated here, send it out. */ skb->dev = port->dev; skb->pkt_type = pkt_type; dev_queue_xmit(skb); } else { if (consumed) consume_skb(skb); else kfree_skb(skb); } dev_put(dev); cond_resched(); } } static void ipvlan_skb_crossing_ns(struct sk_buff *skb, struct net_device *dev) { bool xnet = true; if (dev) xnet = !net_eq(dev_net(skb->dev), dev_net(dev)); skb_scrub_packet(skb, xnet); if (dev) skb->dev = dev; } static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb, bool local) { struct ipvl_dev *ipvlan = addr->master; struct net_device *dev = ipvlan->dev; unsigned int len; rx_handler_result_t ret = RX_HANDLER_CONSUMED; bool success = false; struct sk_buff *skb = *pskb; len = skb->len + ETH_HLEN; /* Only packets exchanged between two local slaves need to have * device-up check as well as skb-share check. */ if (local) { if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb(skb); goto out; } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto out; *pskb = skb; } if (local) { skb->pkt_type = PACKET_HOST; if (dev_forward_skb(ipvlan->dev, skb) == NET_RX_SUCCESS) success = true; } else { skb->dev = dev; ret = RX_HANDLER_ANOTHER; success = true; } out: ipvlan_count_rx(ipvlan, len, success, false); return ret; } struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, int addr_type, bool use_dest) { struct ipvl_addr *addr = NULL; switch (addr_type) { #if IS_ENABLED(CONFIG_IPV6) case IPVL_IPV6: { struct ipv6hdr *ip6h; struct in6_addr *i6addr; ip6h = (struct ipv6hdr *)lyr3h; i6addr = use_dest ? &ip6h->daddr : &ip6h->saddr; addr = ipvlan_ht_addr_lookup(port, i6addr, true); break; } case IPVL_ICMPV6: { struct nd_msg *ndmh; struct in6_addr *i6addr; /* Make sure that the NeighborSolicitation ICMPv6 packets * are handled to avoid DAD issue. */ ndmh = (struct nd_msg *)lyr3h; if (ndmh->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) { i6addr = &ndmh->target; addr = ipvlan_ht_addr_lookup(port, i6addr, true); } break; } #endif case IPVL_IPV4: { struct iphdr *ip4h; __be32 *i4addr; ip4h = (struct iphdr *)lyr3h; i4addr = use_dest ? &ip4h->daddr : &ip4h->saddr; addr = ipvlan_ht_addr_lookup(port, i4addr, false); break; } case IPVL_ARP: { struct arphdr *arph; unsigned char *arp_ptr; __be32 dip; arph = (struct arphdr *)lyr3h; arp_ptr = (unsigned char *)(arph + 1); if (use_dest) arp_ptr += (2 * port->dev->addr_len) + 4; else arp_ptr += port->dev->addr_len; memcpy(&dip, arp_ptr, 4); addr = ipvlan_ht_addr_lookup(port, &dip, false); break; } } return addr; } static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; const struct iphdr *ip4h; struct rtable *rt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, }; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) goto err; ip4h = ip_hdr(skb); fl4.daddr = ip4h->daddr; fl4.saddr = ip4h->saddr; fl4.flowi4_dscp = ip4h_dscp(ip4h); rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto err; } skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); err = ip_local_out(net, NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out; err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out: return ret; } #if IS_ENABLED(CONFIG_IPV6) static noinline_for_stack int ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowi6_flags = FLOWI_FLAG_ANYSRC, .flowlabel = ip6_flowinfo(ip6h), .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; struct dst_entry *dst; int err; dst = ip6_route_output(dev_net(dev), NULL, &fl6); err = dst->error; if (err) { dst_release(dst); return err; } skb_dst_set(skb, dst); return 0; } static int ipvlan_process_v6_outbound(struct sk_buff *skb) { struct net_device *dev = skb->dev; int err, ret = NET_XMIT_DROP; if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) { DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } err = ipvlan_route_v6_outbound(dev, skb); if (unlikely(err)) { DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return err; } memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); err = ip6_local_out(dev_net(dev), NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; return ret; } #else static int ipvlan_process_v6_outbound(struct sk_buff *skb) { return NET_XMIT_DROP; } #endif static int ipvlan_process_outbound(struct sk_buff *skb) { int ret = NET_XMIT_DROP; /* The ipvlan is a pseudo-L2 device, so the packets that we receive * will have L2; which need to discarded and processed further * in the net-ns of the main-device. */ if (skb_mac_header_was_set(skb)) { /* In this mode we dont care about * multicast and broadcast traffic */ struct ethhdr *ethh = eth_hdr(skb); if (is_multicast_ether_addr(ethh->h_dest)) { pr_debug_ratelimited( "Dropped {multi|broad}cast of type=[%x]\n", ntohs(skb->protocol)); kfree_skb(skb); goto out; } skb_pull(skb, sizeof(*ethh)); skb->mac_header = (typeof(skb->mac_header))~0U; skb_reset_network_header(skb); } if (skb->protocol == htons(ETH_P_IPV6)) ret = ipvlan_process_v6_outbound(skb); else if (skb->protocol == htons(ETH_P_IP)) ret = ipvlan_process_v4_outbound(skb); else { pr_warn_ratelimited("Dropped outbound packet type=%x\n", ntohs(skb->protocol)); kfree_skb(skb); } out: return ret; } static void ipvlan_multicast_enqueue(struct ipvl_port *port, struct sk_buff *skb, bool tx_pkt) { if (skb->protocol == htons(ETH_P_PAUSE)) { kfree_skb(skb); return; } /* Record that the deferred packet is from TX or RX path. By * looking at mac-addresses on packet will lead to erronus decisions. * (This would be true for a loopback-mode on master device or a * hair-pin mode of the switch.) */ IPVL_SKB_CB(skb)->tx_pkt = tx_pkt; spin_lock(&port->backlog.lock); if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) { dev_hold(skb->dev); __skb_queue_tail(&port->backlog, skb); spin_unlock(&port->backlog.lock); schedule_work(&port->wq); } else { spin_unlock(&port->backlog.lock); dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb(skb); } } static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); void *lyr3h; struct ipvl_addr *addr; int addr_type; lyr3h = ipvlan_get_L3_hdr(ipvlan->port, skb, &addr_type); if (!lyr3h) goto out; if (!ipvlan_is_vepa(ipvlan->port)) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) { if (ipvlan_is_private(ipvlan->port)) { consume_skb(skb); return NET_XMIT_DROP; } ipvlan_rcv_frame(addr, &skb, true); return NET_XMIT_SUCCESS; } } out: ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev); return ipvlan_process_outbound(skb); } static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); struct ethhdr *eth = skb_eth_hdr(skb); struct ipvl_addr *addr; void *lyr3h; int addr_type; if (!ipvlan_is_vepa(ipvlan->port) && ether_addr_equal(eth->h_dest, eth->h_source)) { lyr3h = ipvlan_get_L3_hdr(ipvlan->port, skb, &addr_type); if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) { if (ipvlan_is_private(ipvlan->port)) { consume_skb(skb); return NET_XMIT_DROP; } ipvlan_rcv_frame(addr, &skb, true); return NET_XMIT_SUCCESS; } } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return NET_XMIT_DROP; /* Packet definitely does not belong to any of the * virtual devices, but the dest is local. So forward * the skb for the main-dev. At the RX side we just return * RX_PASS for it to be processed further on the stack. */ dev_forward_skb(ipvlan->phy_dev, skb); return NET_XMIT_SUCCESS; } else if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); ipvlan_skb_crossing_ns(skb, NULL); ipvlan_multicast_enqueue(ipvlan->port, skb, true); return NET_XMIT_SUCCESS; } skb->dev = ipvlan->phy_dev; return dev_queue_xmit(skb); } int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rcu_bh(ipvlan->phy_dev); if (!port) goto out; if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) goto out; switch(port->mode) { case IPVLAN_MODE_L2: return ipvlan_xmit_mode_l2(skb, dev); case IPVLAN_MODE_L3: #ifdef CONFIG_IPVLAN_L3S case IPVLAN_MODE_L3S: #endif return ipvlan_xmit_mode_l3(skb, dev); } /* Should not reach here */ WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode); out: kfree_skb(skb); return NET_XMIT_DROP; } static bool ipvlan_external_frame(struct sk_buff *skb, struct ipvl_port *port) { struct ethhdr *eth = eth_hdr(skb); struct ipvl_addr *addr; void *lyr3h; int addr_type; if (ether_addr_equal(eth->h_source, skb->dev->dev_addr)) { lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); if (!lyr3h) return true; addr = ipvlan_addr_lookup(port, lyr3h, addr_type, false); if (addr) return false; } return true; } static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb, struct ipvl_port *port) { void *lyr3h; int addr_type; struct ipvl_addr *addr; struct sk_buff *skb = *pskb; rx_handler_result_t ret = RX_HANDLER_PASS; lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); if (!lyr3h) goto out; addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) ret = ipvlan_rcv_frame(addr, pskb, false); out: return ret; } static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, struct ipvl_port *port) { struct sk_buff *skb = *pskb; struct ethhdr *eth = eth_hdr(skb); rx_handler_result_t ret = RX_HANDLER_PASS; if (is_multicast_ether_addr(eth->h_dest)) { if (ipvlan_external_frame(skb, port)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); /* External frames are queued for device local * distribution, but a copy is given to master * straight away to avoid sending duplicates later * when work-queue processes this frame. This is * achieved by returning RX_HANDLER_PASS. */ if (nskb) { ipvlan_skb_crossing_ns(nskb, NULL); ipvlan_multicast_enqueue(port, nskb, false); } } } else { /* Perform like l3 mode for non-multicast packet */ ret = ipvlan_handle_mode_l3(pskb, port); } return ret; } rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct ipvl_port *port = ipvlan_port_get_rcu(skb->dev); if (!port) return RX_HANDLER_PASS; switch (port->mode) { case IPVLAN_MODE_L2: return ipvlan_handle_mode_l2(pskb, port); case IPVLAN_MODE_L3: return ipvlan_handle_mode_l3(pskb, port); #ifdef CONFIG_IPVLAN_L3S case IPVLAN_MODE_L3S: return RX_HANDLER_PASS; #endif } /* Should not reach here */ WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode); kfree_skb(skb); return RX_HANDLER_CONSUMED; } |
| 89 147 13 147 148 147 147 147 74 145 89 147 146 146 147 102 103 148 148 147 148 147 102 2 65 65 145 17 17 17 14 14 13 14 12 14 14 14 14 14 14 13 14 14 92 92 92 91 91 90 89 91 56 4 4 92 88 47 17 14 14 31 76 75 85 38 4 34 8 8 81 81 64 81 81 31 72 81 28 13 28 92 92 92 36 61 92 49 5 44 49 31 2 29 29 4 1 3 3 6 6 6 6 34 33 32 1 32 7 7 6 6 3 2 5 7 5 5 5 4 1 4 4 4 5 5 12 11 11 1 1 11 11 12 19 19 1 18 7 1 6 6 6 6 6 6 6 6 11 17 2 2 17 12 16 16 16 15 16 8 5 4 5 15 14 14 14 15 12 14 14 9 5 14 19 4 5 4 4 4 5 26 23 26 22 22 8 2 1 7 14 6 7 1 1 1 21 12 2 2 11 15 1 15 16 7 16 1 16 5 1 5 5 6 1 1 6 4 3 1 2 6 6 6 6 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * namei.c * * PURPOSE * Inode name handling routines for the OSTA-UDF(tm) filesystem. * * COPYRIGHT * (C) 1998-2004 Ben Fennema * (C) 1999-2000 Stelias Computing Inc * * HISTORY * * 12/12/98 blf Created. Split out the lookup code from dir.c * 04/19/99 blf link, mknod, symlink support */ #include "udfdecl.h" #include "udf_i.h" #include "udf_sb.h" #include <linux/string.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/crc-itu-t.h> #include <linux/exportfs.h> #include <linux/iversion.h> static inline int udf_match(int len1, const unsigned char *name1, int len2, const unsigned char *name2) { if (len1 != len2) return 0; return !memcmp(name1, name2, len1); } /** * udf_fiiter_find_entry - find entry in given directory. * * @dir: directory inode to search in * @child: qstr of the name * @iter: iter to use for searching * * This function searches in the directory @dir for a file name @child. When * found, @iter points to the position in the directory with given entry. * * Returns 0 on success, < 0 on error (including -ENOENT). */ static int udf_fiiter_find_entry(struct inode *dir, const struct qstr *child, struct udf_fileident_iter *iter) { int flen; unsigned char *fname = NULL; struct super_block *sb = dir->i_sb; int isdotdot = child->len == 2 && child->name[0] == '.' && child->name[1] == '.'; int ret; fname = kmalloc(UDF_NAME_LEN, GFP_KERNEL); if (!fname) return -ENOMEM; for (ret = udf_fiiter_init(iter, dir, 0); !ret && iter->pos < dir->i_size; ret = udf_fiiter_advance(iter)) { if (iter->fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) continue; } if (iter->fi.fileCharacteristics & FID_FILE_CHAR_HIDDEN) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) continue; } if ((iter->fi.fileCharacteristics & FID_FILE_CHAR_PARENT) && isdotdot) goto out_ok; if (!iter->fi.lengthFileIdent) continue; flen = udf_get_filename(sb, iter->name, iter->fi.lengthFileIdent, fname, UDF_NAME_LEN); if (flen < 0) { ret = flen; goto out_err; } if (udf_match(flen, fname, child->len, child->name)) goto out_ok; } if (!ret) ret = -ENOENT; out_err: udf_fiiter_release(iter); out_ok: kfree(fname); return ret; } static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct udf_fileident_iter iter; int err; if (dentry->d_name.len > UDF_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); err = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); if (err < 0 && err != -ENOENT) return ERR_PTR(err); if (err == 0) { struct kernel_lb_addr loc; loc = lelb_to_cpu(iter.fi.icb.extLocation); udf_fiiter_release(&iter); inode = udf_iget(dir->i_sb, &loc); } return d_splice_alias(inode, dentry); } static int udf_expand_dir_adinicb(struct inode *inode, udf_pblk_t *block) { udf_pblk_t newblock; struct buffer_head *dbh = NULL; struct kernel_lb_addr eloc; struct extent_position epos; uint8_t alloctype; struct udf_inode_info *iinfo = UDF_I(inode); struct udf_fileident_iter iter; uint8_t *impuse; int ret; if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) alloctype = ICBTAG_FLAG_AD_SHORT; else alloctype = ICBTAG_FLAG_AD_LONG; if (!inode->i_size) { iinfo->i_alloc_type = alloctype; mark_inode_dirty(inode); return 0; } /* alloc block, and copy data to it */ *block = udf_new_block(inode->i_sb, inode, iinfo->i_location.partitionReferenceNum, iinfo->i_location.logicalBlockNum, &ret); if (!(*block)) return ret; newblock = udf_get_pblock(inode->i_sb, *block, iinfo->i_location.partitionReferenceNum, 0); if (newblock == 0xffffffff) return -EFSCORRUPTED; dbh = sb_getblk(inode->i_sb, newblock); if (!dbh) return -ENOMEM; lock_buffer(dbh); memcpy(dbh->b_data, iinfo->i_data, inode->i_size); memset(dbh->b_data + inode->i_size, 0, inode->i_sb->s_blocksize - inode->i_size); set_buffer_uptodate(dbh); unlock_buffer(dbh); /* Drop inline data, add block instead */ iinfo->i_alloc_type = alloctype; memset(iinfo->i_data + iinfo->i_lenEAttr, 0, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; eloc.logicalBlockNum = *block; eloc.partitionReferenceNum = iinfo->i_location.partitionReferenceNum; iinfo->i_lenExtents = inode->i_size; epos.bh = NULL; epos.block = iinfo->i_location; epos.offset = udf_file_entry_alloc_offset(inode); ret = udf_add_aext(inode, &epos, &eloc, inode->i_size, 0); brelse(epos.bh); if (ret < 0) { brelse(dbh); udf_free_blocks(inode->i_sb, inode, &eloc, 0, 1); return ret; } mark_inode_dirty(inode); /* Now fixup tags in moved directory entries */ for (ret = udf_fiiter_init(&iter, inode, 0); !ret && iter.pos < inode->i_size; ret = udf_fiiter_advance(&iter)) { iter.fi.descTag.tagLocation = cpu_to_le32(*block); if (iter.fi.lengthOfImpUse != cpu_to_le16(0)) impuse = dbh->b_data + iter.pos + sizeof(struct fileIdentDesc); else impuse = NULL; udf_fiiter_write_fi(&iter, impuse); } brelse(dbh); /* * We don't expect the iteration to fail as the directory has been * already verified to be correct */ WARN_ON_ONCE(ret); udf_fiiter_release(&iter); return 0; } static int udf_fiiter_add_entry(struct inode *dir, struct dentry *dentry, struct udf_fileident_iter *iter) { struct udf_inode_info *dinfo = UDF_I(dir); int nfidlen, namelen = 0; int ret; int off, blksize = 1 << dir->i_blkbits; udf_pblk_t block; char name[UDF_NAME_LEN_CS0]; if (dentry) { namelen = udf_put_filename(dir->i_sb, dentry->d_name.name, dentry->d_name.len, name, UDF_NAME_LEN_CS0); if (!namelen) return -ENAMETOOLONG; } nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD); for (ret = udf_fiiter_init(iter, dir, 0); !ret && iter->pos < dir->i_size; ret = udf_fiiter_advance(iter)) { if (iter->fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { if (udf_dir_entry_len(&iter->fi) == nfidlen) { iter->fi.descTag.tagSerialNum = cpu_to_le16(1); iter->fi.fileVersionNum = cpu_to_le16(1); iter->fi.fileCharacteristics = 0; iter->fi.lengthFileIdent = namelen; iter->fi.lengthOfImpUse = cpu_to_le16(0); memcpy(iter->namebuf, name, namelen); iter->name = iter->namebuf; return 0; } } } if (ret) { udf_fiiter_release(iter); return ret; } if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && blksize - udf_ext0_offset(dir) - iter->pos < nfidlen) { udf_fiiter_release(iter); ret = udf_expand_dir_adinicb(dir, &block); if (ret) return ret; ret = udf_fiiter_init(iter, dir, dir->i_size); if (ret < 0) return ret; } /* Get blocknumber to use for entry tag */ if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { block = dinfo->i_location.logicalBlockNum; } else { block = iter->eloc.logicalBlockNum + ((iter->elen - 1) >> dir->i_blkbits); } off = iter->pos & (blksize - 1); if (!off) off = blksize; /* Entry fits into current block? */ if (blksize - udf_ext0_offset(dir) - off >= nfidlen) goto store_fi; ret = udf_fiiter_append_blk(iter); if (ret) { udf_fiiter_release(iter); return ret; } /* Entry will be completely in the new block? Update tag location... */ if (!(iter->pos & (blksize - 1))) block = iter->eloc.logicalBlockNum + ((iter->elen - 1) >> dir->i_blkbits); store_fi: memset(&iter->fi, 0, sizeof(struct fileIdentDesc)); if (UDF_SB(dir->i_sb)->s_udfrev >= 0x0200) udf_new_tag((char *)(&iter->fi), TAG_IDENT_FID, 3, 1, block, sizeof(struct tag)); else udf_new_tag((char *)(&iter->fi), TAG_IDENT_FID, 2, 1, block, sizeof(struct tag)); iter->fi.fileVersionNum = cpu_to_le16(1); iter->fi.lengthFileIdent = namelen; iter->fi.lengthOfImpUse = cpu_to_le16(0); memcpy(iter->namebuf, name, namelen); iter->name = iter->namebuf; dir->i_size += nfidlen; if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { dinfo->i_lenAlloc += nfidlen; } else { /* Truncate last extent to proper size */ udf_fiiter_update_elen(iter, iter->elen - (dinfo->i_lenExtents - dir->i_size)); } mark_inode_dirty(dir); return 0; } static void udf_fiiter_delete_entry(struct udf_fileident_iter *iter) { iter->fi.fileCharacteristics |= FID_FILE_CHAR_DELETED; if (UDF_QUERY_FLAG(iter->dir->i_sb, UDF_FLAG_STRICT)) memset(&iter->fi.icb, 0x00, sizeof(struct long_ad)); udf_fiiter_write_fi(iter, NULL); } static void udf_add_fid_counter(struct super_block *sb, bool dir, int val) { struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); if (!lvidiu) return; mutex_lock(&UDF_SB(sb)->s_alloc_mutex); if (dir) le32_add_cpu(&lvidiu->numDirs, val); else le32_add_cpu(&lvidiu->numFiles, val); udf_updated_lvid(sb); mutex_unlock(&UDF_SB(sb)->s_alloc_mutex); } static int udf_add_nondir(struct dentry *dentry, struct inode *inode) { struct udf_inode_info *iinfo = UDF_I(inode); struct inode *dir = d_inode(dentry->d_parent); struct udf_fileident_iter iter; int err; err = udf_fiiter_add_entry(dir, dentry, &iter); if (err) { inode_dec_link_count(inode); discard_new_inode(inode); return err; } iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); udf_fiiter_write_fi(&iter, NULL); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); udf_fiiter_release(&iter); udf_add_fid_counter(dir->i_sb, false, 1); d_instantiate_new(dentry, inode); return 0; } static int udf_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode = udf_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; mark_inode_dirty(inode); return udf_add_nondir(dentry, inode); } static int udf_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode = udf_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; mark_inode_dirty(inode); d_tmpfile(file, inode); unlock_new_inode(inode); return finish_open_simple(file, 0); } static int udf_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; if (!old_valid_dev(rdev)) return -EINVAL; inode = udf_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); init_special_inode(inode, mode, rdev); return udf_add_nondir(dentry, inode); } static struct dentry *udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; struct udf_fileident_iter iter; int err; struct udf_inode_info *dinfo = UDF_I(dir); struct udf_inode_info *iinfo; inode = udf_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) return ERR_CAST(inode); iinfo = UDF_I(inode); inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; err = udf_fiiter_add_entry(inode, NULL, &iter); if (err) { clear_nlink(inode); discard_new_inode(inode); return ERR_PTR(err); } set_nlink(inode, 2); iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(dinfo->i_location); *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(dinfo->i_unique & 0x00000000FFFFFFFFUL); iter.fi.fileCharacteristics = FID_FILE_CHAR_DIRECTORY | FID_FILE_CHAR_PARENT; udf_fiiter_write_fi(&iter, NULL); udf_fiiter_release(&iter); mark_inode_dirty(inode); err = udf_fiiter_add_entry(dir, dentry, &iter); if (err) { clear_nlink(inode); discard_new_inode(inode); return ERR_PTR(err); } iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); iter.fi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; udf_fiiter_write_fi(&iter, NULL); udf_fiiter_release(&iter); udf_add_fid_counter(dir->i_sb, true, 1); inc_nlink(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); d_instantiate_new(dentry, inode); return NULL; } static int empty_dir(struct inode *dir) { struct udf_fileident_iter iter; int ret; for (ret = udf_fiiter_init(&iter, dir, 0); !ret && iter.pos < dir->i_size; ret = udf_fiiter_advance(&iter)) { if (iter.fi.lengthFileIdent && !(iter.fi.fileCharacteristics & FID_FILE_CHAR_DELETED)) { udf_fiiter_release(&iter); return 0; } } udf_fiiter_release(&iter); return 1; } static int udf_rmdir(struct inode *dir, struct dentry *dentry) { int ret; struct inode *inode = d_inode(dentry); struct udf_fileident_iter iter; struct kernel_lb_addr tloc; ret = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); if (ret) goto out; ret = -EFSCORRUPTED; tloc = lelb_to_cpu(iter.fi.icb.extLocation); if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino) goto end_rmdir; ret = -ENOTEMPTY; if (!empty_dir(inode)) goto end_rmdir; udf_fiiter_delete_entry(&iter); if (inode->i_nlink != 2) udf_warn(inode->i_sb, "empty directory has nlink != 2 (%u)\n", inode->i_nlink); clear_nlink(inode); inode->i_size = 0; if (dir->i_nlink >= 3) inode_dec_link_count(dir); else udf_warn(inode->i_sb, "parent dir link count too low (%u)\n", dir->i_nlink); udf_add_fid_counter(dir->i_sb, true, -1); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); mark_inode_dirty(dir); ret = 0; end_rmdir: udf_fiiter_release(&iter); out: return ret; } static int udf_unlink(struct inode *dir, struct dentry *dentry) { int ret; struct inode *inode = d_inode(dentry); struct udf_fileident_iter iter; struct kernel_lb_addr tloc; ret = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); if (ret) goto out; ret = -EFSCORRUPTED; tloc = lelb_to_cpu(iter.fi.icb.extLocation); if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino) goto end_unlink; if (!inode->i_nlink) { udf_debug("Deleting nonexistent file (%lu), %u\n", inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } udf_fiiter_delete_entry(&iter); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); inode_dec_link_count(inode); udf_add_fid_counter(dir->i_sb, false, -1); inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); ret = 0; end_unlink: udf_fiiter_release(&iter); out: return ret; } static int udf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode; struct pathComponent *pc; const char *compstart; struct extent_position epos = {}; int eoffset, elen = 0; uint8_t *ea; int err; udf_pblk_t block; unsigned char *name = NULL; int namelen; struct udf_inode_info *iinfo; struct super_block *sb = dir->i_sb; name = kmalloc(UDF_NAME_LEN_CS0, GFP_KERNEL); if (!name) { err = -ENOMEM; goto out; } inode = udf_new_inode(dir, S_IFLNK | 0777); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out; } iinfo = UDF_I(inode); down_write(&iinfo->i_data_sem); inode->i_data.a_ops = &udf_symlink_aops; inode->i_op = &udf_symlink_inode_operations; inode_nohighmem(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { struct kernel_lb_addr eloc; uint32_t bsize; block = udf_new_block(sb, inode, iinfo->i_location.partitionReferenceNum, iinfo->i_location.logicalBlockNum, &err); if (!block) goto out_no_entry; epos.block = iinfo->i_location; epos.offset = udf_file_entry_alloc_offset(inode); epos.bh = NULL; eloc.logicalBlockNum = block; eloc.partitionReferenceNum = iinfo->i_location.partitionReferenceNum; bsize = sb->s_blocksize; iinfo->i_lenExtents = bsize; err = udf_add_aext(inode, &epos, &eloc, bsize, 0); brelse(epos.bh); if (err < 0) { udf_free_blocks(sb, inode, &eloc, 0, 1); goto out_no_entry; } block = udf_get_pblock(sb, block, iinfo->i_location.partitionReferenceNum, 0); epos.bh = sb_getblk(sb, block); if (unlikely(!epos.bh)) { err = -ENOMEM; udf_free_blocks(sb, inode, &eloc, 0, 1); goto out_no_entry; } lock_buffer(epos.bh); memset(epos.bh->b_data, 0x00, bsize); set_buffer_uptodate(epos.bh); unlock_buffer(epos.bh); mark_buffer_dirty_inode(epos.bh, inode); ea = epos.bh->b_data + udf_ext0_offset(inode); } else ea = iinfo->i_data + iinfo->i_lenEAttr; eoffset = sb->s_blocksize - udf_ext0_offset(inode); pc = (struct pathComponent *)ea; if (*symname == '/') { do { symname++; } while (*symname == '/'); pc->componentType = 1; pc->lengthComponentIdent = 0; pc->componentFileVersionNum = 0; elen += sizeof(struct pathComponent); } err = -ENAMETOOLONG; while (*symname) { if (elen + sizeof(struct pathComponent) > eoffset) goto out_no_entry; pc = (struct pathComponent *)(ea + elen); compstart = symname; do { symname++; } while (*symname && *symname != '/'); pc->componentType = 5; pc->lengthComponentIdent = 0; pc->componentFileVersionNum = 0; if (compstart[0] == '.') { if ((symname - compstart) == 1) pc->componentType = 4; else if ((symname - compstart) == 2 && compstart[1] == '.') pc->componentType = 3; } if (pc->componentType == 5) { namelen = udf_put_filename(sb, compstart, symname - compstart, name, UDF_NAME_LEN_CS0); if (!namelen) goto out_no_entry; if (elen + sizeof(struct pathComponent) + namelen > eoffset) goto out_no_entry; else pc->lengthComponentIdent = namelen; memcpy(pc->componentIdent, name, namelen); } elen += sizeof(struct pathComponent) + pc->lengthComponentIdent; if (*symname) { do { symname++; } while (*symname == '/'); } } brelse(epos.bh); inode->i_size = elen; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) iinfo->i_lenAlloc = inode->i_size; else udf_truncate_tail_extent(inode); mark_inode_dirty(inode); up_write(&iinfo->i_data_sem); err = udf_add_nondir(dentry, inode); out: kfree(name); return err; out_no_entry: up_write(&iinfo->i_data_sem); inode_dec_link_count(inode); discard_new_inode(inode); goto out; } static int udf_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); struct udf_fileident_iter iter; int err; err = udf_fiiter_add_entry(dir, dentry, &iter); if (err) return err; iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(UDF_I(inode)->i_location); if (UDF_SB(inode->i_sb)->s_lvid_bh) { *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(lvid_get_unique_id(inode->i_sb)); } udf_fiiter_write_fi(&iter, NULL); udf_fiiter_release(&iter); inc_nlink(inode); udf_add_fid_counter(dir->i_sb, false, 1); inode_set_ctime_current(inode); mark_inode_dirty(inode); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); ihold(inode); d_instantiate(dentry, inode); return 0; } /* Anybody can rename anything with this: the permission checks are left to the * higher-level routines. */ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct udf_fileident_iter oiter, niter, diriter; bool has_diriter = false, is_dir = false; int retval; struct kernel_lb_addr tloc; if (flags & ~RENAME_NOREPLACE) return -EINVAL; retval = udf_fiiter_find_entry(old_dir, &old_dentry->d_name, &oiter); if (retval) return retval; tloc = lelb_to_cpu(oiter.fi.icb.extLocation); if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) { retval = -ENOENT; goto out_oiter; } if (S_ISDIR(old_inode->i_mode)) { if (new_inode) { retval = -ENOTEMPTY; if (!empty_dir(new_inode)) goto out_oiter; retval = -EFSCORRUPTED; if (new_inode->i_nlink != 2) goto out_oiter; } retval = -EFSCORRUPTED; if (old_dir->i_nlink < 3) goto out_oiter; is_dir = true; } else if (new_inode) { retval = -EFSCORRUPTED; if (new_inode->i_nlink < 1) goto out_oiter; } if (is_dir && old_dir != new_dir) { retval = udf_fiiter_find_entry(old_inode, &dotdot_name, &diriter); if (retval == -ENOENT) { udf_err(old_inode->i_sb, "directory (ino %lu) has no '..' entry\n", old_inode->i_ino); retval = -EFSCORRUPTED; } if (retval) goto out_oiter; has_diriter = true; tloc = lelb_to_cpu(diriter.fi.icb.extLocation); if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) != old_dir->i_ino) { retval = -EFSCORRUPTED; udf_err(old_inode->i_sb, "directory (ino %lu) has parent entry pointing to another inode (%lu != %u)\n", old_inode->i_ino, old_dir->i_ino, udf_get_lb_pblock(old_inode->i_sb, &tloc, 0)); goto out_oiter; } } retval = udf_fiiter_find_entry(new_dir, &new_dentry->d_name, &niter); if (retval && retval != -ENOENT) goto out_oiter; /* Entry found but not passed by VFS? */ if (!retval && !new_inode) { retval = -EFSCORRUPTED; udf_fiiter_release(&niter); goto out_oiter; } /* Entry not found? Need to add one... */ if (retval) { udf_fiiter_release(&niter); retval = udf_fiiter_add_entry(new_dir, new_dentry, &niter); if (retval) goto out_oiter; } /* * Like most other Unix systems, set the ctime for inodes on a * rename. */ inode_set_ctime_current(old_inode); mark_inode_dirty(old_inode); /* * ok, that's it */ niter.fi.fileVersionNum = oiter.fi.fileVersionNum; niter.fi.fileCharacteristics = oiter.fi.fileCharacteristics; memcpy(&(niter.fi.icb), &(oiter.fi.icb), sizeof(oiter.fi.icb)); udf_fiiter_write_fi(&niter, NULL); udf_fiiter_release(&niter); /* * The old entry may have moved due to new entry allocation. Find it * again. */ udf_fiiter_release(&oiter); retval = udf_fiiter_find_entry(old_dir, &old_dentry->d_name, &oiter); if (retval) { udf_err(old_dir->i_sb, "failed to find renamed entry again in directory (ino %lu)\n", old_dir->i_ino); } else { udf_fiiter_delete_entry(&oiter); udf_fiiter_release(&oiter); } if (new_inode) { inode_set_ctime_current(new_inode); inode_dec_link_count(new_inode); udf_add_fid_counter(old_dir->i_sb, S_ISDIR(new_inode->i_mode), -1); } inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); mark_inode_dirty(old_dir); mark_inode_dirty(new_dir); if (has_diriter) { diriter.fi.icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location); udf_fiiter_write_fi(&diriter, NULL); udf_fiiter_release(&diriter); |