| 98 98 13 14 1 14 14 14 14 1 13 2 14 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/module.h> #include <net/caif/caif_layer.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfctrl.h> #include <net/caif/cfmuxl.h> #include <net/caif/cffrml.h> #include <net/caif/cfserl.h> #include <net/caif/cfsrvl.h> #include <net/caif/caif_dev.h> #define container_obj(layr) container_of(layr, struct cfcnfg, layer) /* Information about CAIF physical interfaces held by Config Module in order * to manage physical interfaces */ struct cfcnfg_phyinfo { struct list_head node; bool up; /* Pointer to the layer below the MUX (framing layer) */ struct cflayer *frm_layer; /* Pointer to the lowest actual physical layer */ struct cflayer *phy_layer; /* Unique identifier of the physical interface */ unsigned int id; /* Preference of the physical in interface */ enum cfcnfg_phy_preference pref; /* Information about the physical device */ struct dev_info dev_info; /* Interface index */ int ifindex; /* Protocol head room added for CAIF link layer */ int head_room; /* Use Start of frame checksum */ bool use_fcs; }; struct cfcnfg { struct cflayer layer; struct cflayer *ctrl; struct cflayer *mux; struct list_head phys; struct mutex lock; }; static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer); static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id); static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer); static void cfctrl_resp_func(void); static void cfctrl_enum_resp(void); struct cfcnfg *cfcnfg_create(void) { struct cfcnfg *this; struct cfctrl_rsp *resp; might_sleep(); /* Initiate this layer */ this = kzalloc(sizeof(struct cfcnfg), GFP_ATOMIC); if (!this) return NULL; this->mux = cfmuxl_create(); if (!this->mux) goto out_of_mem; this->ctrl = cfctrl_create(); if (!this->ctrl) goto out_of_mem; /* Initiate response functions */ resp = cfctrl_get_respfuncs(this->ctrl); resp->enum_rsp = cfctrl_enum_resp; resp->linkerror_ind = cfctrl_resp_func; resp->linkdestroy_rsp = cfcnfg_linkdestroy_rsp; resp->sleep_rsp = cfctrl_resp_func; resp->wake_rsp = cfctrl_resp_func; resp->restart_rsp = cfctrl_resp_func; resp->radioset_rsp = cfctrl_resp_func; resp->linksetup_rsp = cfcnfg_linkup_rsp; resp->reject_rsp = cfcnfg_reject_rsp; INIT_LIST_HEAD(&this->phys); cfmuxl_set_uplayer(this->mux, this->ctrl, 0); layer_set_dn(this->ctrl, this->mux); layer_set_up(this->ctrl, this); mutex_init(&this->lock); return this; out_of_mem: synchronize_rcu(); kfree(this->mux); kfree(this->ctrl); kfree(this); return NULL; } void cfcnfg_remove(struct cfcnfg *cfg) { might_sleep(); if (cfg) { synchronize_rcu(); kfree(cfg->mux); cfctrl_remove(cfg->ctrl); kfree(cfg); } } static void cfctrl_resp_func(void) { } static struct cfcnfg_phyinfo *cfcnfg_get_phyinfo_rcu(struct cfcnfg *cnfg, u8 phyid) { struct cfcnfg_phyinfo *phy; list_for_each_entry_rcu(phy, &cnfg->phys, node) if (phy->id == phyid) return phy; return NULL; } static void cfctrl_enum_resp(void) { } static struct dev_info *cfcnfg_get_phyid(struct cfcnfg *cnfg, enum cfcnfg_phy_preference phy_pref) { /* Try to match with specified preference */ struct cfcnfg_phyinfo *phy; list_for_each_entry_rcu(phy, &cnfg->phys, node) { if (phy->up && phy->pref == phy_pref && phy->frm_layer != NULL) return &phy->dev_info; } /* Otherwise just return something */ list_for_each_entry_rcu(phy, &cnfg->phys, node) if (phy->up) return &phy->dev_info; return NULL; } static int cfcnfg_get_id_from_ifi(struct cfcnfg *cnfg, int ifi) { struct cfcnfg_phyinfo *phy; list_for_each_entry_rcu(phy, &cnfg->phys, node) if (phy->ifindex == ifi && phy->up) return phy->id; return -ENODEV; } int caif_disconnect_client(struct net *net, struct cflayer *adap_layer) { u8 channel_id; struct cfcnfg *cfg = get_cfcnfg(net); caif_assert(adap_layer != NULL); cfctrl_cancel_req(cfg->ctrl, adap_layer); channel_id = adap_layer->id; if (channel_id != 0) { struct cflayer *servl; servl = cfmuxl_remove_uplayer(cfg->mux, channel_id); cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer); if (servl != NULL) layer_set_up(servl, NULL); } else pr_debug("nothing to disconnect\n"); /* Do RCU sync before initiating cleanup */ synchronize_rcu(); if (adap_layer->ctrlcmd != NULL) adap_layer->ctrlcmd(adap_layer, CAIF_CTRLCMD_DEINIT_RSP, 0); return 0; } EXPORT_SYMBOL(caif_disconnect_client); static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id) { } static const int protohead[CFCTRL_SRV_MASK] = { [CFCTRL_SRV_VEI] = 4, [CFCTRL_SRV_DATAGRAM] = 7, [CFCTRL_SRV_UTIL] = 4, [CFCTRL_SRV_RFM] = 3, [CFCTRL_SRV_DBG] = 3, }; static int caif_connect_req_to_link_param(struct cfcnfg *cnfg, struct caif_connect_request *s, struct cfctrl_link_param *l) { struct dev_info *dev_info; enum cfcnfg_phy_preference pref; int res; memset(l, 0, sizeof(*l)); /* In caif protocol low value is high priority */ l->priority = CAIF_PRIO_MAX - s->priority + 1; if (s->ifindex != 0) { res = cfcnfg_get_id_from_ifi(cnfg, s->ifindex); if (res < 0) return res; l->phyid = res; } else { switch (s->link_selector) { case CAIF_LINK_HIGH_BANDW: pref = CFPHYPREF_HIGH_BW; break; case CAIF_LINK_LOW_LATENCY: pref = CFPHYPREF_LOW_LAT; break; default: return -EINVAL; } dev_info = cfcnfg_get_phyid(cnfg, pref); if (dev_info == NULL) return -ENODEV; l->phyid = dev_info->id; } switch (s->protocol) { case CAIFPROTO_AT: l->linktype = CFCTRL_SRV_VEI; l->endpoint = (s->sockaddr.u.at.type >> 2) & 0x3; l->chtype = s->sockaddr.u.at.type & 0x3; break; case CAIFPROTO_DATAGRAM: l->linktype = CFCTRL_SRV_DATAGRAM; l->chtype = 0x00; l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; break; case CAIFPROTO_DATAGRAM_LOOP: l->linktype = CFCTRL_SRV_DATAGRAM; l->chtype = 0x03; l->endpoint = 0x00; l->u.datagram.connid = s->sockaddr.u.dgm.connection_id; break; case CAIFPROTO_RFM: l->linktype = CFCTRL_SRV_RFM; l->u.datagram.connid = s->sockaddr.u.rfm.connection_id; strscpy(l->u.rfm.volume, s->sockaddr.u.rfm.volume, sizeof(l->u.rfm.volume)); break; case CAIFPROTO_UTIL: l->linktype = CFCTRL_SRV_UTIL; l->endpoint = 0x00; l->chtype = 0x00; strscpy(l->u.utility.name, s->sockaddr.u.util.service, sizeof(l->u.utility.name)); caif_assert(sizeof(l->u.utility.name) > 10); l->u.utility.paramlen = s->param.size; if (l->u.utility.paramlen > sizeof(l->u.utility.params)) l->u.utility.paramlen = sizeof(l->u.utility.params); memcpy(l->u.utility.params, s->param.data, l->u.utility.paramlen); break; case CAIFPROTO_DEBUG: l->linktype = CFCTRL_SRV_DBG; l->endpoint = s->sockaddr.u.dbg.service; l->chtype = s->sockaddr.u.dbg.type; break; default: return -EINVAL; } return 0; } int caif_connect_client(struct net *net, struct caif_connect_request *conn_req, struct cflayer *adap_layer, int *ifindex, int *proto_head, int *proto_tail) { struct cflayer *frml; struct cfcnfg_phyinfo *phy; int err; struct cfctrl_link_param param; struct cfcnfg *cfg = get_cfcnfg(net); rcu_read_lock(); err = caif_connect_req_to_link_param(cfg, conn_req, ¶m); if (err) goto unlock; phy = cfcnfg_get_phyinfo_rcu(cfg, param.phyid); if (!phy) { err = -ENODEV; goto unlock; } err = -EINVAL; if (adap_layer == NULL) { pr_err("adap_layer is zero\n"); goto unlock; } if (adap_layer->receive == NULL) { pr_err("adap_layer->receive is NULL\n"); goto unlock; } if (adap_layer->ctrlcmd == NULL) { pr_err("adap_layer->ctrlcmd == NULL\n"); goto unlock; } err = -ENODEV; frml = phy->frm_layer; if (frml == NULL) { pr_err("Specified PHY type does not exist!\n"); goto unlock; } caif_assert(param.phyid == phy->id); caif_assert(phy->frm_layer->id == param.phyid); caif_assert(phy->phy_layer->id == param.phyid); *ifindex = phy->ifindex; *proto_tail = 2; *proto_head = protohead[param.linktype] + phy->head_room; rcu_read_unlock(); /* FIXME: ENUMERATE INITIALLY WHEN ACTIVATING PHYSICAL INTERFACE */ cfctrl_enum_req(cfg->ctrl, param.phyid); return cfctrl_linkup_request(cfg->ctrl, ¶m, adap_layer); unlock: rcu_read_unlock(); return err; } EXPORT_SYMBOL(caif_connect_client); static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer) { if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL) adapt_layer->ctrlcmd(adapt_layer, CAIF_CTRLCMD_INIT_FAIL_RSP, 0); } static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer) { struct cfcnfg *cnfg = container_obj(layer); struct cflayer *servicel = NULL; struct cfcnfg_phyinfo *phyinfo; struct net_device *netdev; if (channel_id == 0) { pr_warn("received channel_id zero\n"); if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL) adapt_layer->ctrlcmd(adapt_layer, CAIF_CTRLCMD_INIT_FAIL_RSP, 0); return; } rcu_read_lock(); if (adapt_layer == NULL) { pr_debug("link setup response but no client exist, send linkdown back\n"); cfctrl_linkdown_req(cnfg->ctrl, channel_id, NULL); goto unlock; } caif_assert(cnfg != NULL); caif_assert(phyid != 0); phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phyid); if (phyinfo == NULL) { pr_err("ERROR: Link Layer Device disappeared while connecting\n"); goto unlock; } caif_assert(phyinfo != NULL); caif_assert(phyinfo->id == phyid); caif_assert(phyinfo->phy_layer != NULL); caif_assert(phyinfo->phy_layer->id == phyid); adapt_layer->id = channel_id; switch (serv) { case CFCTRL_SRV_VEI: servicel = cfvei_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DATAGRAM: servicel = cfdgml_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_RFM: netdev = phyinfo->dev_info.dev; servicel = cfrfml_create(channel_id, &phyinfo->dev_info, netdev->mtu); break; case CFCTRL_SRV_UTIL: servicel = cfutill_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_VIDEO: servicel = cfvidl_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DBG: servicel = cfdbgl_create(channel_id, &phyinfo->dev_info); break; default: pr_err("Protocol error. Link setup response - unknown channel type\n"); goto unlock; } if (!servicel) goto unlock; layer_set_dn(servicel, cnfg->mux); cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id); layer_set_up(servicel, adapt_layer); layer_set_dn(adapt_layer, servicel); rcu_read_unlock(); servicel->ctrlcmd(servicel, CAIF_CTRLCMD_INIT_RSP, 0); return; unlock: rcu_read_unlock(); } int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, struct cflayer *link_support, bool fcs, int head_room) { struct cflayer *frml; struct cfcnfg_phyinfo *phyinfo = NULL; int i, res = 0; u8 phyid; mutex_lock(&cnfg->lock); /* CAIF protocol allow maximum 6 link-layers */ for (i = 0; i < 7; i++) { phyid = (dev->ifindex + i) & 0x7; if (phyid == 0) continue; if (cfcnfg_get_phyinfo_rcu(cnfg, phyid) == NULL) goto got_phyid; } pr_warn("Too many CAIF Link Layers (max 6)\n"); res = -EEXIST; goto out; got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); if (!phyinfo) { res = -ENOMEM; goto out; } phy_layer->id = phyid; phyinfo->pref = pref; phyinfo->id = phyid; phyinfo->dev_info.id = phyid; phyinfo->dev_info.dev = dev; phyinfo->phy_layer = phy_layer; phyinfo->ifindex = dev->ifindex; phyinfo->head_room = head_room; phyinfo->use_fcs = fcs; frml = cffrml_create(phyid, fcs); if (!frml) { res = -ENOMEM; goto out_err; } phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux); if (link_support != NULL) { link_support->id = phyid; layer_set_dn(frml, link_support); layer_set_up(link_support, frml); layer_set_dn(link_support, phy_layer); layer_set_up(phy_layer, link_support); } else { layer_set_dn(frml, phy_layer); layer_set_up(phy_layer, frml); } list_add_rcu(&phyinfo->node, &cnfg->phys); out: mutex_unlock(&cnfg->lock); return res; out_err: kfree(phyinfo); mutex_unlock(&cnfg->lock); return res; } EXPORT_SYMBOL(cfcnfg_add_phy_layer); int cfcnfg_set_phy_state(struct cfcnfg *cnfg, struct cflayer *phy_layer, bool up) { struct cfcnfg_phyinfo *phyinfo; rcu_read_lock(); phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phy_layer->id); if (phyinfo == NULL) { rcu_read_unlock(); return -ENODEV; } if (phyinfo->up == up) { rcu_read_unlock(); return 0; } phyinfo->up = up; if (up) { cffrml_hold(phyinfo->frm_layer); cfmuxl_set_dnlayer(cnfg->mux, phyinfo->frm_layer, phy_layer->id); } else { cfmuxl_remove_dnlayer(cnfg->mux, phy_layer->id); cffrml_put(phyinfo->frm_layer); } rcu_read_unlock(); return 0; } EXPORT_SYMBOL(cfcnfg_set_phy_state); int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer) { struct cflayer *frml, *frml_dn; u16 phyid; struct cfcnfg_phyinfo *phyinfo; might_sleep(); mutex_lock(&cnfg->lock); phyid = phy_layer->id; phyinfo = cfcnfg_get_phyinfo_rcu(cnfg, phyid); if (phyinfo == NULL) { mutex_unlock(&cnfg->lock); return 0; } caif_assert(phyid == phyinfo->id); caif_assert(phy_layer == phyinfo->phy_layer); caif_assert(phy_layer->id == phyid); caif_assert(phyinfo->frm_layer->id == phyid); list_del_rcu(&phyinfo->node); synchronize_rcu(); /* Fail if reference count is not zero */ if (cffrml_refcnt_read(phyinfo->frm_layer) != 0) { pr_info("Wait for device inuse\n"); list_add_rcu(&phyinfo->node, &cnfg->phys); mutex_unlock(&cnfg->lock); return -EAGAIN; } frml = phyinfo->frm_layer; frml_dn = frml->dn; cffrml_set_uplayer(frml, NULL); cffrml_set_dnlayer(frml, NULL); if (phy_layer != frml_dn) { layer_set_up(frml_dn, NULL); layer_set_dn(frml_dn, NULL); } layer_set_up(phy_layer, NULL); if (phyinfo->phy_layer != frml_dn) kfree(frml_dn); cffrml_free(frml); kfree(phyinfo); mutex_unlock(&cnfg->lock); return 0; } EXPORT_SYMBOL(cfcnfg_del_phy_layer); |
| 4 4 2 4 4 2 2 2 2 2 2 2 2 3 3 3 3 3 3 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv4/xfrm4_protocol.c */ #include <linux/init.h> #include <linux/mutex.h> #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; static DEFINE_MUTEX(xfrm6_protocol_mutex); static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_handlers; case IPPROTO_AH: return &ah6_handlers; case IPPROTO_COMP: return &ipcomp6_handlers; } return NULL; } #define for_each_protocol_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(protocol); if (!head) return 0; for_each_protocol_rcu(*proto_handlers(protocol), handler) if ((ret = handler->cb_handler(skb, err)) <= 0) return ret; return 0; } int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(nexthdr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); if (!head) goto out; if (!skb_dst(skb)) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); int flags = RT6_LOOKUP_F_HAS_SADDR; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowlabel = ip6_flowinfo(ip6h), .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; dst = ip6_route_input_lookup(dev_net(skb->dev), skb->dev, &fl6, skb, flags); if (dst->error) goto drop; skb_dst_set(skb, dst); } for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; out: icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } EXPORT_SYMBOL(xfrm6_rcv_encap); static int xfrm6_esp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(esp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(esp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ah_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ah6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ah6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ipcomp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ipcomp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ipcomp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol esp6_protocol = { .handler = xfrm6_esp_rcv, .err_handler = xfrm6_esp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ah6_protocol = { .handler = xfrm6_ah_rcv, .err_handler = xfrm6_ah_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ipcomp6_protocol = { .handler = xfrm6_ipcomp_rcv, .err_handler = xfrm6_ipcomp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct xfrm_input_afinfo xfrm6_input_afinfo = { .family = AF_INET6, .callback = xfrm6_rcv_cb, }; static inline const struct inet6_protocol *netproto(unsigned char protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_protocol; case IPPROTO_AH: return &ah6_protocol; case IPPROTO_COMP: return &ipcomp6_protocol; } return NULL; } int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; bool add_netproto = false; int ret = -EEXIST; int priority = handler->priority; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) add_netproto = true; for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t->priority < priority) break; if (t->priority == priority) goto err; } handler->next = *pprev; rcu_assign_pointer(*pprev, handler); ret = 0; err: mutex_unlock(&xfrm6_protocol_mutex); if (add_netproto) { if (inet6_add_protocol(netproto(protocol), protocol)) { pr_err("%s: can't add protocol\n", __func__); ret = -EAGAIN; } } return ret; } EXPORT_SYMBOL(xfrm6_protocol_register); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; int ret = -ENOENT; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) { if (inet6_del_protocol(netproto(protocol), protocol) < 0) { pr_err("%s: can't remove protocol\n", __func__); ret = -EAGAIN; } } mutex_unlock(&xfrm6_protocol_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_protocol_deregister); int __init xfrm6_protocol_init(void) { return xfrm_input_register_afinfo(&xfrm6_input_afinfo); } void xfrm6_protocol_fini(void) { xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); } |
| 10 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xt_mark - Netfilter module to match NFMARK value * * (C) 1999-2001 Marc Boucher <marc@mbsi.ca> * Copyright © CC Computer Consultants GmbH, 2007 - 2008 * Jan Engelhardt <jengelh@medozas.de> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/xt_mark.h> #include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("Xtables: packet mark operations"); MODULE_ALIAS("ipt_mark"); MODULE_ALIAS("ip6t_mark"); MODULE_ALIAS("ipt_MARK"); MODULE_ALIAS("ip6t_MARK"); MODULE_ALIAS("arpt_MARK"); static unsigned int mark_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_mark_tginfo2 *info = par->targinfo; skb->mark = (skb->mark & ~info->mask) ^ info->mark; return XT_CONTINUE; } static bool mark_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_mark_mtinfo1 *info = par->matchinfo; return ((skb->mark & info->mask) == info->mark) ^ info->invert; } static struct xt_target mark_tg_reg[] __read_mostly = { { .name = "MARK", .revision = 2, .family = NFPROTO_IPV4, .target = mark_tg, .targetsize = sizeof(struct xt_mark_tginfo2), .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP_NF_ARPTABLES) { .name = "MARK", .revision = 2, .family = NFPROTO_ARP, .target = mark_tg, .targetsize = sizeof(struct xt_mark_tginfo2), .me = THIS_MODULE, }, #endif #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "MARK", .revision = 2, .family = NFPROTO_IPV6, .target = mark_tg, .targetsize = sizeof(struct xt_mark_tginfo2), .me = THIS_MODULE, }, #endif }; static struct xt_match mark_mt_reg __read_mostly = { .name = "mark", .revision = 1, .family = NFPROTO_UNSPEC, .match = mark_mt, .matchsize = sizeof(struct xt_mark_mtinfo1), .me = THIS_MODULE, }; static int __init mark_mt_init(void) { int ret; ret = xt_register_targets(mark_tg_reg, ARRAY_SIZE(mark_tg_reg)); if (ret < 0) return ret; ret = xt_register_match(&mark_mt_reg); if (ret < 0) { xt_unregister_targets(mark_tg_reg, ARRAY_SIZE(mark_tg_reg)); return ret; } return 0; } static void __exit mark_mt_exit(void) { xt_unregister_match(&mark_mt_reg); xt_unregister_targets(mark_tg_reg, ARRAY_SIZE(mark_tg_reg)); } module_init(mark_mt_init); module_exit(mark_mt_exit); |
| 106 105 2 2 3 3 63 3 30 3 4 1 3 1 2 31 32 10 10 32 32 32 32 1 1 31 32 1 1 62 61 5 3 58 58 10 8 10 10 10 10 10 10 32 32 1 31 8 26 11 11 11 2 9 1 2 2 2 2 2 11 9 2 2 2 16 16 16 5 11 9 2 11 16 7 7 7 7 7 16 4 3 10 10 3 3 1 2 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * To speed up listener socket lookup, create an array to store all sockets * listening on the same port. This allows a decision to be made after finding * the first socket. An optional BPF program can also be configured for * selecting the socket index from the array of available sockets. */ #include <net/ip.h> #include <net/sock_reuseport.h> #include <linux/bpf.h> #include <linux/idr.h> #include <linux/filter.h> #include <linux/rcupdate.h> #define INIT_SOCKS 128 DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); void reuseport_has_conns_set(struct sock *sk) { struct sock_reuseport *reuse; if (!rcu_access_pointer(sk->sk_reuseport_cb)) return; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (likely(reuse)) reuse->has_conns = 1; spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_has_conns_set); static void __reuseport_get_incoming_cpu(struct sock_reuseport *reuse) { /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu + 1); } static void __reuseport_put_incoming_cpu(struct sock_reuseport *reuse) { /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu - 1); } static void reuseport_get_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) { if (sk->sk_incoming_cpu >= 0) __reuseport_get_incoming_cpu(reuse); } static void reuseport_put_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) { if (sk->sk_incoming_cpu >= 0) __reuseport_put_incoming_cpu(reuse); } void reuseport_update_incoming_cpu(struct sock *sk, int val) { struct sock_reuseport *reuse; int old_sk_incoming_cpu; if (unlikely(!rcu_access_pointer(sk->sk_reuseport_cb))) { /* Paired with REAE_ONCE() in sk_incoming_cpu_update() * and compute_score(). */ WRITE_ONCE(sk->sk_incoming_cpu, val); return; } spin_lock_bh(&reuseport_lock); /* This must be done under reuseport_lock to avoid a race with * reuseport_grow(), which accesses sk->sk_incoming_cpu without * lock_sock() when detaching a shutdown()ed sk. * * Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ old_sk_incoming_cpu = sk->sk_incoming_cpu; WRITE_ONCE(sk->sk_incoming_cpu, val); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk. */ if (!reuse) goto out; if (old_sk_incoming_cpu < 0 && val >= 0) __reuseport_get_incoming_cpu(reuse); else if (old_sk_incoming_cpu >= 0 && val < 0) __reuseport_put_incoming_cpu(reuse); out: spin_unlock_bh(&reuseport_lock); } static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) { int left, right; if (!closed) { left = 0; right = reuse->num_socks; } else { left = reuse->max_socks - reuse->num_closed_socks; right = reuse->max_socks; } for (; left < right; left++) if (reuse->socks[left] == sk) return left; return -1; } static void __reuseport_add_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->num_socks] = sk; /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ smp_wmb(); reuse->num_socks++; reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, false); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; reuseport_put_incoming_cpu(sk, reuse); return true; } static void __reuseport_add_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, true); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); reuseport_put_incoming_cpu(sk, reuse); return true; } static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { struct sock_reuseport *reuse; reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC); if (!reuse) return NULL; reuse->max_socks = max_socks; RCU_INIT_POINTER(reuse->prog, NULL); return reuse; } int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; int id, ret = 0; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); /* Allocation attempts can occur concurrently via the setsockopt path * and the bind/hash path. Nothing to do when we lose the race. */ reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { if (reuse->num_closed_socks) { /* sk was shutdown()ed before */ ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); goto out; } /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. */ if (bind_inany) reuse->bind_inany = bind_inany; goto out; } reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { ret = -ENOMEM; goto out; } id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); ret = id; goto out; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; reuseport_get_incoming_cpu(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: spin_unlock_bh(&reuseport_lock); return ret; } EXPORT_SYMBOL(reuseport_alloc); static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) { struct sock_reuseport *more_reuse; u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; if (more_socks_size > U16_MAX) { if (reuse->num_closed_socks) { /* Make room by removing a closed sk. * The child has already been migrated. * Only reqsk left at this point. */ struct sock *sk; sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); __reuseport_detach_closed_sock(sk, reuse); return reuse; } return NULL; } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; more_reuse->incoming_cpu = reuse->incoming_cpu; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); memcpy(more_reuse->socks + (more_reuse->max_socks - more_reuse->num_closed_socks), reuse->socks + (reuse->max_socks - reuse->num_closed_socks), reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); /* Note: we use kfree_rcu here instead of reuseport_free_rcu so * that reuse and more_reuse can temporarily share a reference * to prog. */ kfree_rcu(reuse, rcu); return more_reuse; } static void reuseport_free_rcu(struct rcu_head *head) { struct sock_reuseport *reuse; reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); ida_free(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. * @sk2: Socket belonging to the existing reuseport group. * @bind_inany: Whether or not the group is bound to a local INANY address. * * May return ENOMEM and not add socket to group under memory pressure. */ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) { struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2, bind_inany); if (err) return err; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (old_reuse && old_reuse->num_closed_socks) { /* sk was shutdown()ed before */ int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); spin_unlock_bh(&reuseport_lock); return err; } if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); return -ENOMEM; } } __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); if (old_reuse) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } EXPORT_SYMBOL(reuseport_add_sock); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany) { if (old_reuse == reuse) { /* If sk was in the same reuseport group, just pop sk out of * the closed section and push sk into the listening section. */ __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, old_reuse); return 0; } if (!reuse) { /* In bind()/listen() path, we cannot carry over the eBPF prog * for the shutdown()ed socket. In setsockopt() path, we should * not change the eBPF prog of listening sockets by attaching a * prog to the shutdown()ed socket. Thus, we will allocate a new * reuseport group and detach sk from the old group. */ int id; reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) return -ENOMEM; id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); return id; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; } else { /* Move sk from the old group to the new one if * - all the other listeners in the old group were close()d or * shutdown()ed, and then sk2 has listen()ed on the same port * OR * - sk listen()ed without bind() (or with autobind), was * shutdown()ed, and then listen()s on another port which * sk2 listen()s on. */ if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) return -ENOMEM; } } __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk */ if (!reuse) goto out; /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * * Other bpf map types that work with reuseport, like sockmap, * don't need an explicit callback from here. They override sk * unhash/close ops to remove the sk from the map before we * get to this point. */ bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); if (!__reuseport_detach_closed_sock(sk, reuse)) __reuseport_detach_sock(sk, reuse); if (reuse->num_socks + reuse->num_closed_socks == 0) call_rcu(&reuse->rcu, reuseport_free_rcu); out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); void reuseport_stop_listen_sock(struct sock *sk) { if (sk->sk_protocol == IPPROTO_TCP) { struct sock_reuseport *reuse; struct bpf_prog *prog; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) || (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. */ bpf_sk_reuseport_detach(sk); __reuseport_detach_sock(sk, reuse); __reuseport_add_closed_sock(sk, reuse); spin_unlock_bh(&reuseport_lock); return; } spin_unlock_bh(&reuseport_lock); } /* Not capable to do migration, detach immediately */ reuseport_detach_sock(sk); } EXPORT_SYMBOL(reuseport_stop_listen_sock); static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) { struct sk_buff *nskb = NULL; u32 index; if (skb_shared(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return NULL; skb = nskb; } /* temporarily advance data past protocol header */ if (!pskb_pull(skb, hdr_len)) { kfree_skb(nskb); return NULL; } index = bpf_prog_run_save_cb(prog, skb); __skb_push(skb, hdr_len); consume_skb(nskb); if (index >= socks) return NULL; return reuse->socks[index]; } static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, u32 hash, u16 num_socks) { struct sock *first_valid_sk = NULL; int i, j; i = j = reciprocal_scale(hash, num_socks); do { struct sock *sk = reuse->socks[i]; if (sk->sk_state != TCP_ESTABLISHED) { /* Paired with WRITE_ONCE() in __reuseport_(get|put)_incoming_cpu(). */ if (!READ_ONCE(reuse->incoming_cpu)) return sk; /* Paired with WRITE_ONCE() in reuseport_update_incoming_cpu(). */ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) return sk; if (!first_valid_sk) first_valid_sk = sk; } i++; if (i >= num_socks) i = 0; } while (i != j); return first_valid_sk; } /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. * @hash: When no BPF filter is available, use this hash to select. * @skb: skb to run through BPF filter. * @hdr_len: BPF filter expects skb data pointer at payload data. If * the skb does not yet point at the payload, this parameter represents * how far the pointer needs to advance to reach the payload. * Returns a socket that should receive the packet (or NULL on error). */ struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len) { struct sock_reuseport *reuse; struct bpf_prog *prog; struct sock *sk2 = NULL; u16 socks; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); /* if memory allocation failed or add call is not yet complete */ if (!reuse) goto out; prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ if (!sk2) sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: rcu_read_unlock(); return sk2; } EXPORT_SYMBOL(reuseport_select_sock); /** * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. * @sk: close()ed or shutdown()ed socket in the group. * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or * NEW_SYN_RECV request socket during 3WHS. * @skb: skb to run through BPF filter. * Returns a socket (with sk_refcnt +1) that should accept the child socket * (or NULL on error). */ struct sock *reuseport_migrate_sock(struct sock *sk, struct sock *migrating_sk, struct sk_buff *skb) { struct sock_reuseport *reuse; struct sock *nsk = NULL; bool allocated = false; struct bpf_prog *prog; u16 socks; u32 hash; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (!reuse) goto out; socks = READ_ONCE(reuse->num_socks); if (unlikely(!socks)) goto failure; /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); hash = migrating_sk->sk_hash; prog = rcu_dereference(reuse->prog); if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req)) goto select_by_hash; goto failure; } if (!skb) { skb = alloc_skb(0, GFP_ATOMIC); if (!skb) goto failure; allocated = true; } nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); if (allocated) kfree_skb(skb); select_by_hash: if (!nsk) nsk = reuseport_select_sock_by_hash(reuse, hash, socks); if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) { nsk = NULL; goto failure; } out: rcu_read_unlock(); return nsk; failure: __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); goto out; } EXPORT_SYMBOL(reuseport_migrate_sock); int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; if (sk_unhashed(sk)) { int err; if (!sk->sk_reuseport) return -EINVAL; err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { /* The socket wasn't bound with SO_REUSEPORT */ return -EINVAL; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); rcu_assign_pointer(reuse->prog, prog); spin_unlock_bh(&reuseport_lock); sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_attach_prog); int reuseport_detach_prog(struct sock *sk) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuse must be checked after acquiring the reuseport_lock * because reuseport_grow() can detach a closed sk. */ if (!reuse) { spin_unlock_bh(&reuseport_lock); return sk->sk_reuseport ? -ENOENT : -EINVAL; } if (sk_unhashed(sk) && reuse->num_closed_socks) { spin_unlock_bh(&reuseport_lock); return -ENOENT; } old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); if (!old_prog) return -ENOENT; sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_detach_prog); |
| 14 66 66 8 1 4 1 2 13 32 31 45 72 13 92 15 20 240 128 122 34 34 20 34 60 84 84 11 25 26 15 15 317 219 216 54 165 28 27 28 28 28 6 22 28 27 27 28 28 28 1 28 28 28 28 28 28 28 28 7 28 28 41 41 41 7 7 7 7 7 7 7 7 7 5 4 7 5 14 2 16 16 16 34 34 34 28 19 28 28 27 28 28 28 28 28 28 33 34 34 16 28 28 28 27 28 22 8 5 7 31 23 7 44 42 44 29 29 70 60 55 60 66 66 24 66 75 75 126 59 77 127 127 60 77 22 110 128 6 6 1 6 6 75 16 15 45 66 51 60 22 27 22 27 34 34 34 34 9 28 20 28 21 28 28 28 28 28 28 2 45 20 28 28 5 45 28 28 28 21 28 17 28 45 45 28 28 20 20 45 45 45 28 45 27 34 33 34 20 34 34 34 34 34 34 45 45 45 34 9 9 9 28 1 28 28 28 12 24 34 34 34 12 24 34 34 34 42 7 36 36 35 6 32 13 23 35 2 36 35 35 35 35 35 4 4 1 1 3 16 16 10 16 16 3 16 22 22 22 22 2 2 16 16 16 16 75 75 75 75 75 75 75 75 30 30 75 75 75 75 16 66 66 74 75 16 16 16 16 16 16 6 16 16 16 16 15 16 6 7 7 18 17 3 16 16 1 8 9 14 1 9 14 2 6 6 4 11 11 8 3 7 1 6 6 6 4 1 4 3 10 2 8 3 3 5 1 2 2 2 2 2 5 1 2 2 2 1 2 2 2 2 2 2 2 2 2 8 8 8 8 2 6 8 8 1 1 1 1 1 1 7 7 1 7 3 4 2 2 3 4 5 1 12 2 1 9 1 1 1 1 1 5 3 1 1 62 62 62 14 5 9 14 245 245 1 245 228 21 21 3 10 1 5 2 8 4 4 23 20 23 8 15 100 77 15 5 2 66 66 17 70 69 70 70 70 70 70 70 66 6 11 14 20 7 72 168 1 72 155 158 91 158 66 158 44 25 25 24 25 25 25 13 17 3 3 3 1 3 39 39 4 37 2 24 22 4 1 4 39 39 39 26 1 26 2 26 26 1 1 1 38 39 39 26 17 24 17 24 26 37 4 4 22 39 7 32 40 37 27 40 36 25 35 19 23 34 2 33 2 4 1 3 7 7 8 7 1 3 6 1 6 7 20 20 3 20 20 20 20 20 11 10 25 5 3 19 15 2 11 66 66 66 66 66 45 66 66 66 26 64 66 66 66 65 66 45 15 60 60 60 60 59 2 37 24 60 15 45 60 60 61 1 60 60 59 6 6 6 6 9 9 9 9 9 9 9 9 9 9 9 9 8 11 119 2 2 2 130 10 1 120 120 118 120 7 7 2 5 5 5 5 13 129 129 141 143 11 114 6 2604 2601 2600 2603 1 1 1038 1043 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 | /* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "cgroup-internal.h" #include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/hashtable.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) /* let's not notify more than 100 times per second */ #define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0) /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); #if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP) EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif DEFINE_SPINLOCK(trace_cgroup_path_lock); char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; static bool cgroup_debug __read_mostly; /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */ static DEFINE_SPINLOCK(cgroup_idr_lock); /* * Protects cgroup_file->kn for !self csses. It synchronizes notifications * against file removal/re-creation across css hiding. */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required"); /* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_destroy_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, struct cgroup_subsys *cgroup_subsys[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of cgroup subsystem names */ #define SUBSYS(_x) [_x ## _cgrp_id] = #_x, static const char *cgroup_subsys_name[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ #define SUBSYS(_x) \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key); #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key, static struct static_key_true *cgroup_subsys_enabled_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key, static struct static_key_true *cgroup_subsys_on_dfl_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); /* the default hierarchy */ struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ bool cgrp_dfl_visible; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; /* some controllers can be threaded on the default hierarchy */ static u16 cgrp_dfl_threaded_ss_mask; /* The list of hierarchy roots */ LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); /* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */ static u64 css_serial_nr_next = 1; /* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS); /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = { .ns.count = REFCOUNT_INIT(2), .user_ns = &init_user_ns, .ns.ops = &cgroupns_operations, .ns.inum = PROC_CGROUP_INIT_INO, .root_cset = &init_css_set, }; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_base_files[]; static struct cftype cgroup_psi_files[]; /* cgroup optional features */ enum cgroup_opt_features { #ifdef CONFIG_PSI OPT_FEATURE_PRESSURE, #endif OPT_FEATURE_COUNT }; static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = { #ifdef CONFIG_PSI "pressure", #endif }; static u16 cgroup_feature_disable_mask __read_mostly; static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); #ifdef CONFIG_DEBUG_CGROUP_REF #define CGROUP_REF_FN_ATTRS noinline #define CGROUP_REF_EXPORT(fn) EXPORT_SYMBOL_GPL(fn); #include <linux/cgroup_refcnt.h> #endif /** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ bool cgroup_ssid_enabled(int ssid) { if (!CGROUP_HAS_SUBSYS_CONFIG) return false; return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. */ bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { int ret; idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; } static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { void *ret; spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret; } static void cgroup_idr_remove(struct idr *idr, int id) { spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock); } static bool cgroup_has_tasks(struct cgroup *cgrp) { return cgrp->nr_populated_csets; } static bool cgroup_is_threaded(struct cgroup *cgrp) { return cgrp->dom_cgrp != cgrp; } /* can @cgrp host both domain and threaded children? */ static bool cgroup_is_mixable(struct cgroup *cgrp) { /* * Root isn't under domain level resource control exempting it from * the no-internal-process constraint, so it can serve as a thread * root and a parent of resource domains at the same time. */ return !cgroup_parent(cgrp); } /* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return true; /* domain roots can't be nested under threaded */ if (cgroup_is_threaded(cgrp)) return false; /* can only have either domain or threaded children */ if (cgrp->nr_populated_domain_children) return false; /* and no domain controllers can be enabled */ if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return false; return true; } /* is @cgrp root of a threaded subtree? */ static bool cgroup_is_thread_root(struct cgroup *cgrp) { /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) return false; /* a domain w/ threaded children is a thread root */ if (cgrp->nr_threaded_children) return true; /* * A domain which has tasks and explicit threaded controllers * enabled is a thread root. */ if (cgroup_has_tasks(cgrp) && (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) return true; return false; } /* a domain which isn't connected to the root w/o brekage can't be used */ static bool cgroup_is_valid_domain(struct cgroup *cgrp) { /* the cgroup itself can be a thread root */ if (cgroup_is_threaded(cgrp)) return false; /* but the ancestors can't be unless mixable */ while ((cgrp = cgroup_parent(cgrp))) { if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) return false; if (cgroup_is_threaded(cgrp)) return false; } return true; } /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; if (parent) { u16 ss_mask = parent->subtree_control; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask; } /* subsystems enabled on a cgroup */ static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); if (parent) { u16 ss_mask = parent->subtree_ss_mask; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } return cgrp->root->subsys_mask; } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (CGROUP_HAS_SUBSYS_CONFIG && ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; } /** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); if (!ss) return &cgrp->self; /* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; } return cgroup_css(cgrp, ss); } /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; do { css = cgroup_css(cgrp, ss); if (css) return css; cgrp = cgroup_parent(cgrp); } while (cgrp); return init_css_set.subsys[ss->id]; } /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; rcu_read_lock(); do { css = cgroup_css(cgrp, ss); if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp); css = init_css_set.subsys[ss->id]; css_get(css); out_unlock: rcu_read_unlock(); return css; } EXPORT_SYMBOL_GPL(cgroup_get_e_css); static void cgroup_get_live(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); cgroup_get(cgrp); } /** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */ int __cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks; return count; } /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */ int cgroup_task_count(const struct cgroup *cgrp) { int count; spin_lock_irq(&css_set_lock); count = __cgroup_task_count(cgrp); spin_unlock_irq(&css_set_lock); return count; } static struct cgroup *kn_priv(struct kernfs_node *kn) { struct kernfs_node *parent; /* * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. * Therefore it is always safe to dereference this pointer outside of a * RCU section. */ parent = rcu_dereference_check(kn->__parent, kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); return parent->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); /* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self; } EXPORT_SYMBOL_GPL(of_css); /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_mutex. */ #define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_HAS_SUBSYS_CONFIG) { \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ { #define while_each_subsys_mask() \ } \ } \ } while (false) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* * The following field is re-initialized when this cset gets linked * in cgroup_init(). However, let's initialize the field * statically too so that the default cgroup can be accessed safely * early during boot. */ .dfl_cgrp = &cgrp_dfl_root.cgrp, }; static int css_set_count = 1; /* 1 for init_css_set */ static bool css_set_threaded(struct css_set *cset) { return cset->dom_cset != cset; } /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { lockdep_assert_held(&css_set_lock); return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); } /** * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->nr_populated_* accordingly. The * count is propagated towards root so that a given cgroup's * nr_populated_children is zero iff none of its descendants contain any * tasks. * * @cgrp's interface file "cgroup.populated" is zero if both * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and * 1 otherwise. When the sum changes from or to zero, userland is notified * that the content of the interface file has changed. This can be used to * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { struct cgroup *child = NULL; int adj = populated ? 1 : -1; lockdep_assert_held(&css_set_lock); do { bool was_populated = cgroup_is_populated(cgrp); if (!child) { cgrp->nr_populated_csets += adj; } else { if (cgroup_is_threaded(child)) cgrp->nr_populated_threaded_children += adj; else cgrp->nr_populated_domain_children += adj; } if (was_populated == cgroup_is_populated(cgrp)) break; cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); cgroup_file_notify(&cgrp->events_file); child = cgrp; cgrp = cgroup_parent(cgrp); } while (cgrp); } /** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) cgroup_update_populated(link->cgrp, populated); } /* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */ static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task) { struct css_task_iter *it, *pos; list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) css_task_iter_skip(it, task); } /** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { lockdep_assert_held(&css_set_lock); if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true); if (from_cset) { WARN_ON_ONCE(list_empty(&task->cg_list)); css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); } if (to_cset) { /* * We are synchronized through cgroup_threadgroup_rwsem * against PF_EXITING setting such that we can't race * against cgroup_exit()/cgroup_free() dropping the css_set. */ WARN_ON_ONCE(task->flags & PF_EXITING); cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } } /* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state **css) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; } void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&css_set_lock); if (!refcount_dec_and_test(&cset->refcount)) return; WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); } if (css_set_threaded(cset)) { list_del(&cset->threaded_csets_node); put_css_set_locked(cset->dom_cset); } kfree_rcu(cset, rcu_head); } /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2; /* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; /* @cset's domain should match the default cgroup's */ if (cgroup_on_dfl(new_cgrp)) new_dfl_cgrp = new_cgrp; else new_dfl_cgrp = old_cset->dfl_cgrp; if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) return false; /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; } /** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state **template) { struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; } static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } } /** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */ static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; } /** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp; link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; /* * Always add links to the tail of the lists so that the lists are * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); if (cgroup_parent(cgrp)) cgroup_get_live(cgrp); } /** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */ static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } refcount_set(&cset->refcount, 1); cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->dying_tasks); INIT_LIST_HEAD(&cset->task_iters); INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_src_preload_node); INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid]; list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); } spin_unlock_irq(&css_set_lock); /* * If @cset should be threaded, look up the matching dom_cset and * link them up. We first fully initialize @cset then look for the * dom_cset. It's simpler this way and safe as @cset is guaranteed * to stay empty until we return. */ if (cgroup_is_threaded(cset->dfl_cgrp)) { struct css_set *dcset; dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); if (!dcset) { put_css_set(cset); return NULL; } spin_lock_irq(&css_set_lock); cset->dom_cset = dcset; list_add_tail(&cset->threaded_csets_node, &dcset->threaded_csets); spin_unlock_irq(&css_set_lock); } return cset; } struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv; return root_cgrp->root; } void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) { bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS; /* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */ if (favor && !favoring) { rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); root->flags |= CGRP_ROOT_FAVOR_DYNMODS; } else if (!favor && favoring) { rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; } } static int cgroup_init_root_id(struct cgroup_root *root) { int id; lockdep_assert_held(&cgroup_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; } static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } void cgroup_free_root(struct cgroup_root *root) { kfree_rcu(root, rcu); } static void cgroup_destroy_root(struct cgroup_root *root) { struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; trace_cgroup_destroy_root(root); cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); /* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } spin_unlock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&root->root_list)); list_del_rcu(&root->root_list); cgroup_root_count--; if (!have_favordynmods) cgroup_favor_dynmods(root, false); cgroup_exit_root_id(root); cgroup_unlock(); cgroup_rstat_exit(cgrp); kernfs_destroy_root(root->kf_root); cgroup_free_root(root); } /* * Returned cgroup is without refcount but it's valid as long as cset pins it. */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { struct cgroup *res_cgroup = NULL; if (cset == &init_css_set) { res_cgroup = &root->cgrp; } else if (root == &cgrp_dfl_root) { res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res_cgroup = c; break; } } } /* * If cgroup_mutex is not held, the cgrp_cset_link will be freed * before we remove the cgroup root from the root_list. Consequently, * when accessing a cgroup root, the cset_link may have already been * freed, resulting in a NULL res_cgroup. However, by holding the * cgroup_mutex, we ensure that res_cgroup can't be NULL. * If we don't hold cgroup_mutex in the caller, we must do the NULL * check. */ return res_cgroup; } /* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */ static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { struct cgroup *res = NULL; struct css_set *cset; lockdep_assert_held(&css_set_lock); rcu_read_lock(); cset = current->nsproxy->cgroup_ns->root_cset; res = __cset_cgroup_from_root(cset, root); rcu_read_unlock(); /* * The namespace_sem is held by current, so the root cgroup can't * be umounted. Therefore, we can ensure that the res is non-NULL. */ WARN_ON_ONCE(!res); return res; } /* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */ static struct cgroup *current_cgns_cgroup_dfl(void) { struct css_set *cset; if (current->nsproxy) { cset = current->nsproxy->cgroup_ns->root_cset; return __cset_cgroup_from_root(cset, &cgrp_dfl_root); } else { /* * NOTE: This function may be called from bpf_cgroup_from_id() * on a task which has already passed exit_task_namespaces() and * nsproxy == NULL. Fall back to cgrp_dfl_root which will make all * cgroups visible for lookups. */ return &cgrp_dfl_root.cgrp; } } /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with css_set_lock held to prevent task's groups from being modified. * Must be called with either cgroup_mutex or rcu read lock to prevent the * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { /* * No need to lock the task - since we hold css_set_lock the * task can't change groups. */ return cset_cgroup_from_root(task_css_set(task), root); } /* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { struct cgroup_subsys *ss = cft->ss; if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : ""; snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); } else { strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); } return buf; } /** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */ static umode_t cgroup_file_mode(const struct cftype *cft) { umode_t mode = 0; if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO; if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; } return mode; } /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); cur_ss_mask |= cgrp_dfl_implicit_ss_mask; while (true) { u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; } return cur_ss_mask; } /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn); cgroup_unlock(); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); } /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn); /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn); if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else cgroup_lock(); if (!cgroup_is_dead(cgrp)) return cgrp; cgroup_kn_unlock(kn); return NULL; } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); timer_delete_sync(&cfile->notify_timer); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } /** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) return; css->flags &= ~CSS_VISIBLE; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); if (cgroup_psi_enabled()) cgroup_addrm_files(css, cgrp, cgroup_psi_files, false); } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, false); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); } } /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */ static int css_populate_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; if (css->flags & CSS_VISIBLE) return 0; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { ret = cgroup_addrm_files(css, cgrp, cgroup_base_files, true); if (ret < 0) return ret; if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(css, cgrp, cgroup_psi_files, true); if (ret < 0) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); return ret; } } } else { ret = cgroup_addrm_files(css, cgrp, cgroup1_base_files, true); if (ret < 0) return ret; } } else { list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } } css->flags |= CSS_VISIBLE; return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret; } int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; /* * Collect ssid's that need to be disabled from default * hierarchy. */ if (ss->root == &cgrp_dfl_root) dfl_disable_ss_mask |= 1 << ssid; } while_each_subsys_mask(); if (dfl_disable_ss_mask) { struct cgroup *scgrp = &cgrp_dfl_root.cgrp; /* * Controllers from default hierarchy that need to be rebound * are all disabled together in one go. */ cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset, *cset_pos; struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); if (src_root != &cgrp_dfl_root) { /* disable from the source */ src_root->subsys_mask &= ~(1 << ssid); WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; spin_lock_irq(&css_set_lock); css->cgroup = dcgrp; WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); /* * all css_sets of scgrp together in same order to dcgrp, * patch in-flight iterators to preserve correct iteration. * since the iterator is always advanced right away and * finished when it->cset_pos meets it->cset_head, so only * update it->cset_head is enough here. */ list_for_each_entry(it, &cset->task_iters, iters_node) if (it->cset_head == &scgrp->e_csets[ss->id]) it->cset_head = &dcgrp->e_csets[ss->id]; } spin_unlock_irq(&css_set_lock); if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret); if (ss->bind) ss->bind(css); } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; } int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM; spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); if (len == -E2BIG) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len; } enum cgroup2_param { Opt_nsdelegate, Opt_favordynmods, Opt_memory_localevents, Opt_memory_recursiveprot, Opt_memory_hugetlb_accounting, Opt_pids_localevents, nr__cgroup2_params }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("favordynmods", Opt_favordynmods), fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting), fsparam_flag("pids_localevents", Opt_pids_localevents), {} }; static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_nsdelegate: ctx->flags |= CGRP_ROOT_NS_DELEGATE; return 0; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; case Opt_memory_recursiveprot: ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; return 0; case Opt_memory_hugetlb_accounting: ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; return 0; case Opt_pids_localevents: ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; return 0; } return -EINVAL; } struct cgroup_of_peak *of_peak(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; return &ctx->peak; } static void apply_cgroup_root_flags(unsigned int root_flags) { if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { if (root_flags & CGRP_ROOT_NS_DELEGATE) cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; else cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; cgroup_favor_dynmods(&cgrp_dfl_root, root_flags & CGRP_ROOT_FAVOR_DYNMODS); if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS; } } static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) seq_puts(seq, ",memory_recursiveprot"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) seq_puts(seq, ",memory_hugetlb_accounting"); if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) seq_puts(seq, ",pids_localevents"); return 0; } static int cgroup_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); apply_cgroup_root_flags(ctx->flags); return 0; } static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; int ssid; INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; INIT_LIST_HEAD(&cgrp->rstat_css_list); prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } void init_cgroup_root(struct cgroup_fs_context *ctx) { struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); /* DYNMODS must be modified through cgroup_favor_dynmods() */ root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; if (ctx->release_agent) strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); if (ctx->name) strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret; lockdep_assert_held(&cgroup_mutex); ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out; /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; ret = cgroup_init_root_id(root); if (ret) goto cancel_ref; kf_sops = root == &cgrp_dfl_root ? &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | KERNFS_ROOT_SUPPORT_USER_XATTR | KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = kernfs_root_to_node(root->kf_root); WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); root_cgrp->ancestors[0] = root_cgrp; ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; ret = cgroup_rstat_init(root_cgrp); if (ret) goto destroy_root; ret = rebind_subsystems(root, ss_mask); if (ret) goto exit_stats; if (root == &cgrp_dfl_root) { ret = cgroup_bpf_inherit(root_cgrp); WARN_ON_ONCE(ret); } trace_cgroup_setup_root(root); /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++; /* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); ret = 0; goto out; exit_stats: cgroup_rstat_exit(root_cgrp); destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL; exit_root_id: cgroup_exit_root_id(root); cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt); out: free_cgrp_cset_links(&tmp_links); return ret; } int cgroup_do_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; ctx->kfc.root = ctx->root->kf_root; if (fc->fs_type == &cgroup2_fs_type) ctx->kfc.magic = CGROUP2_SUPER_MAGIC; else ctx->kfc.magic = CGROUP_SUPER_MAGIC; ret = kernfs_get_tree(fc); /* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; cgroup_lock(); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); cgroup_unlock(); nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); if (IS_ERR(nsdentry)) { deactivate_locked_super(sb); ret = PTR_ERR(nsdentry); nsdentry = NULL; } fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) cgroup_put(&ctx->root->cgrp); return ret; } /* * Destroy a cgroup filesystem context. */ static void cgroup_fs_context_free(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); kfree(ctx->name); kfree(ctx->release_agent); put_cgroup_ns(ctx->ns); kernfs_free_fs_context(fc); kfree(ctx); } static int cgroup_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; WRITE_ONCE(cgrp_dfl_visible, true); cgroup_get_live(&cgrp_dfl_root.cgrp); ctx->root = &cgrp_dfl_root; ret = cgroup_do_get_tree(fc); if (!ret) apply_cgroup_root_flags(ctx->flags); return ret; } static const struct fs_context_operations cgroup_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup2_parse_param, .get_tree = cgroup_get_tree, .reconfigure = cgroup_reconfigure, }; static const struct fs_context_operations cgroup1_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup1_parse_param, .get_tree = cgroup1_get_tree, .reconfigure = cgroup1_reconfigure, }; /* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */ static int cgroup_init_fs_context(struct fs_context *fc) { struct cgroup_fs_context *ctx; ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; if (fc->fs_type == &cgroup2_fs_type) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; if (have_favordynmods) ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; } static void cgroup_kill_sb(struct super_block *sb) { struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); /* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && !percpu_ref_is_dying(&root->cgrp.self.refcnt)) percpu_ref_kill(&root->cgrp.self.refcnt); cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; #ifdef CONFIG_CPUSETS_V1 enum cpuset_param { Opt_cpuset_v2_mode, }; static const struct fs_parameter_spec cpuset_fs_parameters[] = { fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), {} }; static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cpuset_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; return 0; } return -EINVAL; } static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, .parse_param = cpuset_parse_param, }; /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ static int cpuset_init_fs_context(struct fs_context *fc) { char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); struct cgroup_fs_context *ctx; int err; err = cgroup_init_fs_context(fc); if (err) { kfree(agent); return err; } fc->ops = &cpuset_fs_context_ops; ctx = cgroup_fc2context(fc); ctx->subsys_mask = 1 << cpuset_cgrp_id; ctx->flags |= CGRP_ROOT_NOPREFIX; ctx->release_agent = agent; get_filesystem(&cgroup_fs_type); put_filesystem(fc->fs_type); fc->fs_type = &cgroup_fs_type; return 0; } static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, .parameters = cpuset_fs_parameters, .fs_flags = FS_USERNS_MOUNT, }; #endif int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); } int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { int ret; cgroup_lock(); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); cgroup_unlock(); return ret; } EXPORT_SYMBOL_GPL(cgroup_path_ns); /** * cgroup_attach_lock - Lock for ->attach() * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ void cgroup_attach_lock(bool lock_threadgroup) { cpus_read_lock(); if (lock_threadgroup) percpu_down_write(&cgroup_threadgroup_rwsem); } /** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ void cgroup_attach_unlock(bool lock_threadgroup) { if (lock_threadgroup) percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); } /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */ static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return; /* cgroup_threadgroup_rwsem protects racing against forks */ WARN_ON_ONCE(list_empty(&task->cg_list)); cset = task_css_set(task); if (!cset->mg_src_cgrp) return; mgctx->tset.nr_tasks++; list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_add_tail(&cset->mg_dst_cset->mg_node, &mgctx->tset.dst_csets); } /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list); if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; /* * This function may be called both before and * after cgroup_migrate_execute(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid]; return task; } cset = list_next_entry(cset, mg_node); task = NULL; } return NULL; } /** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; /* check that we can legitimately attach to the cgroup */ if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); } /* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); from_cset->nr_tasks--; /* * If the source or destination cgroup is frozen, * the task might require to change its state. */ cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, to_cset->dfl_cgrp); put_css_set_locked(from_cset); } } spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets; if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); } } while_each_subsys_mask(); } ret = 0; goto out_release_tset; out_cancel_attach: if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); } out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); /* * Re-initialize the cgroup_taskset structure in case it is reused * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() * iteration. */ tset->nr_tasks = 0; tset->csets = &tset->src_csets; return ret; } /** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { /* v1 doesn't have any restriction */ if (!cgroup_on_dfl(dst_cgrp)) return 0; /* verify @dst_cgrp can host resources */ if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) return -EOPNOTSUPP; /* * If @dst_cgrp is already or can become a thread root or is * threaded, it doesn't matter. */ if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) return 0; /* apply no-internal-process constraint */ if (dst_cgrp->subtree_control) return -EBUSY; return 0; } /** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_src_preload_node); put_css_set_locked(cset); } list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } spin_unlock_irq(&css_set_lock); } /** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx) { struct cgroup *src_cgrp; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); /* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return; if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) return -ENOMEM; WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); /* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; } src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_dst_preload_node)) list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); for_each_subsys(ss, ssid) if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) mgctx->ss_mask |= 1 << ssid; } return 0; } /** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx) { struct task_struct *task; /* * The following thread iteration should be inside an RCU critical * section to prevent tasks from being freed while taking the snapshot. * spin_lock_irq() implies RCU critical section here. */ spin_lock_irq(&css_set_lock); task = leader; do { cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); spin_unlock_irq(&css_set_lock); return cgroup_migrate_execute(mgctx); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret = 0; /* look up all src csets */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) ret = cgroup_migrate(leader, threadgroup, &mgctx); cgroup_migrate_finish(&mgctx); if (!ret) TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); return ret; } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL); /* * If we migrate a single thread, we don't care about threadgroup * stability. If the thread is `current`, it won't exit(2) under our * hands or change PID through exec(2). We exclude * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write * callers by cgroup_mutex. * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); *threadgroup_locked = pid || threadgroup; cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { tsk = ERR_PTR(-ESRCH); goto out_unlock_threadgroup; } } else { tsk = current; } if (threadgroup) tsk = tsk->group_leader; /* * kthreads may acquire PF_NO_SETAFFINITY during initialization. * If userland migrates such a kthread to a non-root cgroup, it can * become trapped in a cpuset, or RT kthread may be born in a * cgroup with no rt_runtime allocated. Just say no. */ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { tsk = ERR_PTR(-EINVAL); goto out_unlock_threadgroup; } get_task_struct(tsk); goto out_unlock_rcu; out_unlock_threadgroup: cgroup_attach_unlock(*threadgroup_locked); *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; /* release reference from cgroup_procs_write_start() */ put_task_struct(task); cgroup_attach_unlock(threadgroup_locked); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); } /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; } /* show controllers which are enabled for a given cgroup's children */ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0; } /** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; bool has_tasks; int ret; lockdep_assert_held(&cgroup_mutex); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; /* * As cgroup_update_dfl_csses() is only called by * cgroup_apply_control(). The csses associated with the * given cgrp will not be affected by changes made to * its subtree_control file. We can skip them. */ if (dsct == cgrp) continue; list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock); /* * We need to write-lock threadgroup_rwsem while migrating tasks. * However, if there are no source csets for @cgrp, changing its * controllers isn't gonna produce any task migrations and the * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(has_tasks); return ret; } /** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; restart: cgroup_lock(); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get_live(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); cgroup_unlock(); schedule(); finish_wait(&dsct->offline_waitq, &wait); cgroup_put(dsct); goto restart; } } } /** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; dsct->old_dom_cgrp = dsct->dom_cgrp; } } /** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */ static void cgroup_propagate_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); } } /** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; dsct->dom_cgrp = dsct->old_dom_cgrp; } } static bool css_visible(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; } /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); } WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } } return 0; } /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */ static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!css) continue; WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } } } /** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */ static int cgroup_apply_control(struct cgroup *cgrp) { int ret; cgroup_propagate_control(cgrp); ret = cgroup_apply_control_enable(cgrp); if (ret) return ret; /* * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ return cgroup_update_dfl_csses(cgrp); } /** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); } cgroup_apply_control_disable(cgrp); } static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) { u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; /* if nothing is getting enabled, nothing to worry about */ if (!enable) return 0; /* can @cgrp host any resources? */ if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) return -EOPNOTSUPP; /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return 0; if (domain_enable) { /* can't enable domain controllers inside a thread subtree */ if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return -EOPNOTSUPP; } else { /* * Threaded controllers can handle internal competitions * and are always allowed inside a (prospective) thread * subtree. */ if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return 0; } /* * Controllers can't be enabled for a cgroup with tasks to avoid * child cgroups competing against tasks. */ if (cgroup_has_tasks(cgrp)) return -EBUSY; return 0; } /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { u16 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret; /* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; } if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; } /* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } } if (!enable && !disable) { ret = 0; goto out_unlock; } ret = cgroup_vet_subtree_control_enable(cgrp, enable); if (ret) goto out_unlock; /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); if (ret) goto out_unlock; kernfs_activate(cgrp->kn); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } /** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; struct cgroup *dsct; struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); /* noop if already threaded */ if (cgroup_is_threaded(cgrp)) return 0; /* * If @cgroup is populated or has domain controllers enabled, it * can't be switched. While the below cgroup_can_be_thread_root() * test can catch the same conditions, that's only when @parent is * not mixable, so let's check it explicitly. */ if (cgroup_is_populated(cgrp) || cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return -EOPNOTSUPP; /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP; /* * The following shouldn't cause actual migrations and should * always succeed. */ cgroup_save_control(cgrp); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) if (dsct == cgrp || cgroup_is_threaded(dsct)) dsct->dom_cgrp = dom_cgrp; ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; cgroup_finalize_control(cgrp, ret); return ret; } static int cgroup_type_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; if (cgroup_is_threaded(cgrp)) seq_puts(seq, "threaded\n"); else if (!cgroup_is_valid_domain(cgrp)) seq_puts(seq, "domain invalid\n"); else if (cgroup_is_thread_root(cgrp)) seq_puts(seq, "domain threaded\n"); else seq_puts(seq, "domain\n"); return 0; } static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int ret; /* only switching to threaded mode is supported */ if (strcmp(strstrip(buf), "threaded")) return -EINVAL; /* drain dying csses before we re-apply (threaded) subtree control */ cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; /* threaded can only be enabled */ ret = cgroup_enable_threaded(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_max_descendants_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int descendants = READ_ONCE(cgrp->max_descendants); if (descendants == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", descendants); return 0; } static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int descendants; ssize_t ret; buf = strstrip(buf); if (!strcmp(buf, "max")) { descendants = INT_MAX; } else { ret = kstrtoint(buf, 0, &descendants); if (ret) return ret; } if (descendants < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_descendants = descendants; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_max_depth_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int depth = READ_ONCE(cgrp->max_depth); if (depth == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", depth); return 0; } static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int depth; buf = strstrip(buf); if (!strcmp(buf, "max")) { depth = INT_MAX; } else { ret = kstrtoint(buf, 0, &depth); if (ret) return ret; } if (depth < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_depth = depth; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_events_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags)); return 0; } static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; struct cgroup_subsys_state *css; int dying_cnt[CGROUP_SUBSYS_COUNT]; int ssid; seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants); /* * Show the number of live and dying csses associated with each of * non-inhibited cgroup subsystems that is bound to cgroup v2. * * Without proper lock protection, racing is possible. So the * numbers may not be consistent when that happens. */ rcu_read_lock(); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { dying_cnt[ssid] = -1; if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) || (cgroup_subsys[ssid]->root != &cgrp_dfl_root)) continue; css = rcu_dereference_raw(cgroup->subsys[ssid]); dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid]; seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name, css ? (css->nr_descendants + 1) : 0); } seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { if (dying_cnt[ssid] >= 0) seq_printf(seq, "nr_dying_subsys_%s %d\n", cgroup_subsys[ssid]->name, dying_cnt[ssid]); } rcu_read_unlock(); return 0; } #ifdef CONFIG_CGROUP_SCHED /** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; rcu_read_lock(); css = cgroup_css(cgrp, ss); if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock(); return css; } static int cgroup_extra_stat_show(struct seq_file *seq, int ssid) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_extra_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_extra_stat_show(seq, css); css_put(css); return ret; } static int cgroup_local_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid) { struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_local_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_local_stat_show(seq, css); css_put(css); return ret; } #endif static int cpu_stat_show(struct seq_file *seq, void *v) { int ret = 0; cgroup_base_stat_cputime_show(seq); #ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cpu_cgrp_id); #endif return ret; } static int cpu_local_stat_show(struct seq_file *seq, void *v) { struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; #ifdef CONFIG_CGROUP_SCHED ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id); #endif return ret; } #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; cgroup_get(cgrp); cgroup_kn_unlock(of->kn); /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { cgroup_put(cgrp); return -EBUSY; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); } smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; } static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_CPU); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IRQ); } static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IRQ); } #endif static int cgroup_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); seq_printf(seq, "%d\n", psi->enabled); return 0; } static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret; int enable; struct cgroup *cgrp; struct psi_group *psi; ret = kstrtoint(strstrip(buf), 0, &enable); if (ret) return ret; if (enable < 0 || enable > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; psi = cgroup_psi(cgrp); if (psi->enabled != enable) { int i; /* show or hide {cpu,memory,io,irq}.pressure files */ for (i = 0; i < NR_PSI_RESOURCES; i++) cgroup_file_show(&cgrp->psi_files[i], enable); psi->enabled = enable; if (enable) psi_cgroup_restart(psi); } cgroup_kn_unlock(of->kn); return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { struct cgroup_file_ctx *ctx = of->priv; return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) { if (static_branch_likely(&psi_disabled)) return false; return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } #else /* CONFIG_PSI */ bool cgroup_psi_enabled(void) { return false; } #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "%d\n", cgrp->freezer.freeze); return 0; } static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int freeze; ret = kstrtoint(strstrip(buf), 0, &freeze); if (ret) return ret; if (freeze < 0 || freeze > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgroup_freeze(cgrp, freeze); cgroup_kn_unlock(of->kn); return nbytes; } static void __cgroup_kill(struct cgroup *cgrp) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); cgrp->kill_seq++; spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); while ((task = css_task_iter_next(&it))) { /* Ignore kernel threads here. */ if (task->flags & PF_KTHREAD) continue; /* Skip tasks that are already dying. */ if (__fatal_signal_pending(task)) continue; send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); } static void cgroup_kill(struct cgroup *cgrp) { struct cgroup_subsys_state *css; struct cgroup *dsct; lockdep_assert_held(&cgroup_mutex); cgroup_for_each_live_descendant_pre(dsct, css, cgrp) __cgroup_kill(dsct); } static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret = 0; int kill; struct cgroup *cgrp; ret = kstrtoint(strstrip(buf), 0, &kill); if (ret) return ret; if (kill != 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; /* * Killing is a process directed operation, i.e. the whole thread-group * is taken down so act like we do for cgroup.procs and only make this * writable in non-threaded cgroups. */ if (cgroup_is_threaded(cgrp)) ret = -EOPNOTSUPP; else cgroup_kill(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); of->priv = ctx; if (!cft->open) return 0; ret = cft->open(of); if (ret) { put_cgroup_ns(ctx->ns); kfree(ctx); } return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; if (!nbytes) return 0; /* * If namespaces are delegation boundaries, disallow writes to * files in an non-init namespace root from inside the namespace * except for the files explicitly marked delegatable - * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control. */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) return cft->write(of, buf, nbytes, off); /* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock(); if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; } return ret ?: nbytes; } static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); return kernfs_generic_poll(of, pt); } static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { return seq_cft(seq)->seq_next(seq, v, ppos); } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { if (seq_cft(seq)->seq_stop) seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m); if (cft->seq_show) return cft->seq_show(m, arg); if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0; } static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show, }; static void cgroup_file_notify_timer(struct timer_list *timer) { cgroup_file_notify(container_of(timer, struct cgroup_file, notify_timer)); } static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), current_fsuid(), current_fsgid(), 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); } return 0; } /** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */ static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { struct cftype *cft, *cft_end = NULL; int ret = 0; lockdep_assert_held(&cgroup_mutex); restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret; } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0; lockdep_assert_held(&cgroup_mutex); /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; } if (is_add && !ret) kernfs_activate(root->kn); return ret; } static void cgroup_exit_cftypes(struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL; /* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | __CFTYPE_ADDED); } } static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; int ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops; WARN_ON(cft->ss || cft->kf_ops); if (cft->flags & __CFTYPE_ADDED) { ret = -EBUSY; break; } if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops; /* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { ret = -ENOMEM; break; } kf_ops->atomic_write_len = cft->max_write_len; } cft->kf_ops = kf_ops; cft->ss = ss; cft->flags |= __CFTYPE_ADDED; } if (ret) cgroup_exit_cftypes(cfts); return ret; } static void cgroup_rm_cftypes_locked(struct cftype *cfts) { lockdep_assert_held(&cgroup_mutex); list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts); } /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */ int cgroup_rm_cftypes(struct cftype *cfts) { if (!cfts || cfts[0].name[0] == '\0') return 0; if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT; cgroup_lock(); cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return 0; } /** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { int ret; if (!cgroup_ssid_enabled(ss->id)) return 0; if (!cfts || cfts[0].name[0] == '\0') return 0; ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret; cgroup_lock(); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return ret; } /** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */ void cgroup_file_notify(struct cgroup_file *cfile) { unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); if (cfile->kn) { unsigned long last = cfile->notified_at; unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; if (time_in_range(jiffies, last, next)) { timer_reduce(&cfile->notify_timer, next); } else { kernfs_notify(cfile->kn); cfile->notified_at = jiffies; } } spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); } /** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */ void cgroup_file_show(struct cgroup_file *cfile, bool show) { struct kernfs_node *kn; spin_lock_irq(&cgroup_file_kn_lock); kn = cfile->kn; kernfs_get(kn); spin_unlock_irq(&cgroup_file_kn_lock); if (kn) kernfs_show(kn, show); kernfs_put(kn); } /** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling, lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; } /* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL; } /** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; } return NULL; } EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct rightmost descendant as long as @pos * is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; cgroup_assert_mutex_or_rcu_locked(); do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; } static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last; do { last = pos; pos = css_next_child(NULL, pos); } while (pos); return last; } /** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @cgroup are accessible and @pos is a descendant of @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ return pos->parent; } /** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */ bool css_has_online_children(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *child; bool ret = false; rcu_read_lock(); css_for_each_child(child, css) { if (child->flags & CSS_ONLINE) { ret = true; break; } } rcu_read_unlock(); return ret; } static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) { struct list_head *l; struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* find the next threaded cset */ if (it->tcset_pos) { l = it->tcset_pos->next; if (l != it->tcset_head) { it->tcset_pos = l; return container_of(l, struct css_set, threaded_csets_node); } it->tcset_pos = NULL; } /* find the next cset */ l = it->cset_pos; l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; return NULL; } if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; } it->cset_pos = l; /* initialize threaded css_set walking */ if (it->flags & CSS_TASK_ITER_THREADED) { if (it->cur_dcset) put_css_set_locked(it->cur_dcset); it->cur_dcset = cset; get_css_set(cset); it->tcset_head = &cset->threaded_csets; it->tcset_pos = &cset->threaded_csets; } return cset; } /** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set and find first non-empty tasks list*/ while ((cset = css_task_iter_next_css_set(it))) { if (!list_empty(&cset->tasks)) { it->cur_tasks_head = &cset->tasks; break; } else if (!list_empty(&cset->mg_tasks)) { it->cur_tasks_head = &cset->mg_tasks; break; } else if (!list_empty(&cset->dying_tasks)) { it->cur_tasks_head = &cset->dying_tasks; break; } } if (!cset) { it->task_pos = NULL; return; } it->task_pos = it->cur_tasks_head->next; /* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters); } static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task) { lockdep_assert_held(&css_set_lock); if (it->task_pos == &task->cg_list) { it->task_pos = it->task_pos->next; it->flags |= CSS_TASK_ITER_SKIPPED; } } static void css_task_iter_advance(struct css_task_iter *it) { struct task_struct *task; lockdep_assert_held(&css_set_lock); repeat: if (it->task_pos) { /* * Advance iterator to find next entry. We go through cset * tasks, mg_tasks and dying_tasks, when consumed we move onto * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next; if (it->task_pos == &it->cur_cset->tasks) { it->cur_tasks_head = &it->cur_cset->mg_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->mg_tasks) { it->cur_tasks_head = &it->cur_cset->dying_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it); } if (!it->task_pos) return; task = list_entry(it->task_pos, struct task_struct, cg_list); if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ if (!thread_group_leader(task)) goto repeat; /* and dying leaders w/o live member threads */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; } } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { unsigned long irqflags; memset(it, 0, sizeof(*it)); spin_lock_irqsave(&css_set_lock, irqflags); it->ss = css->ss; it->flags = flags; if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links; it->cset_head = it->cset_pos; css_task_iter_advance(it); spin_unlock_irqrestore(&css_set_lock, irqflags); } /** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { unsigned long irqflags; if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } spin_lock_irqsave(&css_set_lock, irqflags); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); } spin_unlock_irqrestore(&css_set_lock, irqflags); return it->cur_task; } /** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) { unsigned long irqflags; if (it->cur_cset) { spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irqrestore(&css_set_lock, irqflags); } if (it->cur_dcset) put_css_set(it->cur_dcset); if (it->cur_task) put_task_struct(it->cur_task); } static void cgroup_procs_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; if (ctx->procs.started) css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags) { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_file_ctx *ctx = of->priv; struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); css_task_iter_start(&cgrp->self, iter_flags, it); ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); } else return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { struct cgroup *cgrp = seq_css(s)->cgroup; /* * All processes of a threaded subtree belong to the domain cgroup * of the subtree. Only threads can be distributed across the * subtree. Reject reads on cgroup.procs in the subtree proper. * They're always empty anyway. */ if (cgroup_is_threaded(cgrp)) return ERR_PTR(-EOPNOTSUPP); return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED); } static int cgroup_procs_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", task_pid_vnr(v)); return 0; } static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) { int ret; struct inode *inode; lockdep_assert_held(&cgroup_mutex); inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (!inode) return -ENOMEM; ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); iput(inode); return ret; } static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns) { struct cgroup *com_cgrp = src_cgrp; int ret; lockdep_assert_held(&cgroup_mutex); /* find the common ancestor */ while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) com_cgrp = cgroup_parent(com_cgrp); /* %current should be authorized to migrate to the common ancestor */ ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret; /* * If namespaces are delegation boundaries, %current must be able * to see both source and destination cgroups from its namespace. */ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) return -ENOENT; return 0; } static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns) { int ret = 0; ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret; ret = cgroup_migrate_vet_dst(dst_cgrp); if (ret) return ret; if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) ret = -EOPNOTSUPP; return ret; } static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; ssize_t ret; bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* find the source cgroup */ spin_lock_irq(&css_set_lock); src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); /* * Process and thread migrations follow same delegation rule. Check * permissions using the credentials from file open to protect against * inherited fd attacks. */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup, ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); return ret; } static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, true) ?: nbytes; } static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) { return __cgroup_procs_start(s, pos, 0); } static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, false) ?: nbytes; } /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { { .name = "cgroup.type", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_type_show, .write = cgroup_type_write, }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { .name = "cgroup.threads", .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_threads_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { .name = "cgroup.max.descendants", .seq_show = cgroup_max_descendants_show, .write = cgroup_max_descendants_write, }, { .name = "cgroup.max.depth", .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, { .name = "cgroup.freeze", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_freeze_show, .write = cgroup_freeze_write, }, { .name = "cgroup.kill", .flags = CFTYPE_NOT_ON_ROOT, .write = cgroup_kill_write, }, { .name = "cpu.stat", .seq_show = cpu_stat_show, }, { .name = "cpu.stat.local", .seq_show = cpu_local_stat_show, }, { } /* terminate */ }; static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #ifdef CONFIG_IRQ_TIME_ACCOUNTING { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #endif { .name = "cgroup.pressure", .seq_show = cgroup_pressure_show, .write = cgroup_pressure_write, }, #endif /* CONFIG_PSI */ { } /* terminate */ }; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_rwork_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */ static void css_free_rwork_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); if (ss) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id; ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); if (!cgroup_on_dfl(cgrp)) cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); bpf_cgrp_storage_free(cgrp); if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); psi_cgroup_free(cgrp); cgroup_rstat_exit(cgrp); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } } } static void css_release_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; cgroup_lock(); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); if (ss) { struct cgroup *parent_cgrp; /* css release path */ if (!list_empty(&css->rstat_css_node)) { cgroup_rstat_flush(cgrp); list_del_rcu(&css->rstat_css_node); } cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); cgrp->nr_dying_subsys[ss->id]--; /* * When a css is released and ready to be freed, its * nr_descendants must be zero. However, the corresponding * cgrp->nr_dying_subsys[ss->id] may not be 0 if a subsystem * is activated and deactivated multiple times with one or * more of its previous activation leaving behind dying csses. */ WARN_ON_ONCE(css->nr_descendants); parent_cgrp = cgroup_parent(cgrp); while (parent_cgrp) { parent_cgrp->nr_dying_subsys[ss->id]--; parent_cgrp = cgroup_parent(parent_cgrp); } } else { struct cgroup *tcgrp; /* cgroup release path */ TRACE_CGROUP_PATH(release, cgrp); cgroup_rstat_flush(cgrp); spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); } cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { lockdep_assert_held(&cgroup_mutex); cgroup_get_live(cgrp); memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); INIT_LIST_HEAD(&css->rstat_css_node); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); } if (ss->css_rstat_flush) list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); BUG_ON(cgroup_css(cgrp, ss)); } /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); if (css->parent) { atomic_inc(&css->parent->online_cnt); while ((css = css->parent)) css->nr_descendants++; } } return ret; } /* if the CSS is online, invoke ->css_offline() on it and mark it offline */ static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) return; if (ss->css_offline) ss->css_offline(css); css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); css->cgroup->nr_dying_subsys[ss->id]++; /* * Parent css and cgroup cannot be freed until after the freeing * of child css, see css_free_rwork_fn(). */ while ((css = css->parent)) { css->nr_descendants--; css->cgroup->nr_dying_subsys[ss->id]++; } } /** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err; lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); if (!css) css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css; init_and_link_css(css, ss, cgrp); err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); err = online_css(css); if (err) goto err_list_del; return css; err_list_del: list_del_rcu(&css->sibling); err_free_css: list_del_rcu(&css->rstat_css_node); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); return ERR_PTR(err); } /* * The returned cgroup is fully initialized including its control mask, but * it doesn't have the control mask applied. */ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; struct kernfs_node *kn; int level = parent->level + 1; int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; ret = cgroup_rstat_init(cgrp); if (ret) goto out_cancel_ref; /* create the directory */ kn = kernfs_create_dir_ns(parent->kn, name, mode, current_fsuid(), current_fsgid(), cgrp, NULL); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_stat_exit; } cgrp->kn = kn; init_cgroup_housekeeping(cgrp); cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; ret = psi_cgroup_alloc(cgrp); if (ret) goto out_kernfs_remove; if (cgrp->root == &cgrp_dfl_root) { ret = cgroup_bpf_inherit(cgrp); if (ret) goto out_psi_free; } /* * New cgroup inherits effective freeze counter, and * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be * attached to the child cgroup, it will become frozen. * At this point the new cgroup is unpopulated, so we can * consider it frozen immediately. */ set_bit(CGRP_FREEZE, &cgrp->flags); set_bit(CGRP_FROZEN, &cgrp->flags); } spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestors[tcgrp->level] = tcgrp; if (tcgrp != cgrp) { tcgrp->nr_descendants++; /* * If the new cgroup is frozen, all ancestor cgroups * get a new frozen descendant, but their state can't * change because of this. */ if (cgrp->freezer.e_freeze) tcgrp->freezer.nr_frozen_descendants++; } } spin_unlock_irq(&css_set_lock); if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); cgrp->self.serial_nr = css_serial_nr_next++; /* allocation complete, commit to creation */ list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); cgroup_propagate_control(cgrp); return cgrp; out_psi_free: psi_cgroup_free(cgrp); out_kernfs_remove: kernfs_remove(cgrp->kn); out_stat_exit: cgroup_rstat_exit(cgrp); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); } static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { struct cgroup *cgroup; int ret = false; int level = 0; lockdep_assert_held(&cgroup_mutex); for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail; if (level >= cgroup->max_depth) goto fail; level++; } ret = true; fail: return ret; } int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL; parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; if (!cgroup_check_hierarchy_limits(parent)) { ret = -EAGAIN; goto out_unlock; } cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } /* * This extra ref will be put in css_free_rwork_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(cgrp->kn); ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; out_destroy: cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; } /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); cgroup_lock(); do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); cgroup_unlock(); } /* css kill confirmation processing requires process context, bounce */ static void css_killed_ref_fn(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } } /** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */ static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) return; /* * Call css_killed(), if defined, before setting the CSS_DYING flag */ if (css->ss->css_killed) css->ss->css_killed(css); css->flags |= CSS_DYING; /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive * until after ->css_offline(). */ css_get(css); /* * cgroup core guarantees that, by the time ->css_offline() is * invoked, no new css reference will be given out via * css_tryget_online(). We can't simply call percpu_ref_kill() and * proceed to offlining css's because percpu_ref_kill() doesn't * guarantee that the ref is seen as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } /** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_kn_lock_live(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; spin_lock_irq(&css_set_lock); for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); if (cgrp->root == &cgrp_dfl_root) cgroup_bpf_offline(cgrp); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; }; int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; ret = cgroup_destroy_locked(cgrp); if (!ret) TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { struct cgroup_subsys_state *css; pr_debug("Initializing cgroup subsys %s\n", ss->name); cgroup_lock(); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); /* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF; if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); BUG_ON(online_css(css)); cgroup_unlock(); } /** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */ int __init cgroup_init_early(void) { static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i; ctx.root = &cgrp_dfl_root; init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss, true); } return 0; } /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */ int __init cgroup_init(void) { struct cgroup_subsys *ss; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); cgroup_rstat_boot(); get_user_ns(init_cgroup_ns.user_ns); cgroup_lock(); /* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); cgroup_unlock(); for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id]; css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); } list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]); /* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (!cgroup_ssid_enabled(ssid)) continue; if (cgroup1_ssid_disabled(ssid)) pr_info("Disabling %s control group subsystem in v1 mounts\n", ss->legacy_name); cgrp_dfl_root.subsys_mask |= 1 << ss->id; /* implicit controllers must be threaded too */ WARN_ON(ss->implicit_on_dfl && !ss->threaded); if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->threaded) cgrp_dfl_threaded_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } if (ss->bind) ss->bind(init_css_set.subsys[ssid]); cgroup_lock(); css_populate_dir(init_css_set.subsys[ssid]); cgroup_unlock(); } /* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); #ifdef CONFIG_CPUSETS_V1 WARN_ON(register_filesystem(&cpuset_fs_type)); #endif return 0; } static int __init cgroup_wq_init(void) { /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); return 0; } core_initcall(cgroup_wq_init); void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); kernfs_put(kn); } /* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */ struct cgroup *cgroup_get_from_id(u64 id) { struct kernfs_node *kn; struct cgroup *cgrp, *root_cgrp; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return ERR_PTR(-ENOENT); if (kernfs_type(kn) != KERNFS_DIR) { kernfs_put(kn); return ERR_PTR(-ENOENT); } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL; rcu_read_unlock(); kernfs_put(kn); if (!cgrp) return ERR_PTR(-ENOENT); root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_id); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; int retval; struct cgroup_root *root; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; cgrp = task_cgroup_from_root(tsk, root); /* The root has already been unmounted. */ if (!cgrp) continue; seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock; seq_puts(m, buf); } else { seq_puts(m, "/"); } if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); } retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); rcu_read_unlock(); kfree(buf); out: return retval; } /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); } /** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); return css->cgroup; } /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } /** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) { int ret; struct cgroup *dst_cgrp = NULL; struct css_set *cset; struct super_block *sb; if (kargs->flags & CLONE_INTO_CGROUP) cgroup_lock(); cgroup_threadgroup_change_begin(current); spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); if (kargs->cgrp) kargs->kill_seq = kargs->cgrp->kill_seq; else kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { kargs->cset = cset; return 0; } CLASS(fd_raw, f)(kargs->cgroup); if (fd_empty(f)) { ret = -EBADF; goto err; } sb = fd_file(f)->f_path.dentry->d_sb; dst_cgrp = cgroup_get_from_file(fd_file(f)); if (IS_ERR(dst_cgrp)) { ret = PTR_ERR(dst_cgrp); dst_cgrp = NULL; goto err; } if (cgroup_is_dead(dst_cgrp)) { ret = -ENODEV; goto err; } /* * Verify that we the target cgroup is writable for us. This is * usually done by the vfs layer but since we're not going through * the vfs layer here we need to do it "manually". */ ret = cgroup_may_write(dst_cgrp, sb); if (ret) goto err; /* * Spawning a task directly into a cgroup works by passing a file * descriptor to the target cgroup directory. This can even be an O_PATH * file descriptor. But it can never be a cgroup.procs file descriptor. * This was done on purpose so spawning into a cgroup could be * conceptualized as an atomic * * fd = openat(dfd_cgroup, "cgroup.procs", ...); * write(fd, <child-pid>, ...); * * sequence, i.e. it's a shorthand for the caller opening and writing * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us * to always use the caller's credentials. */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); if (ret) goto err; kargs->cset = find_css_set(cset, dst_cgrp); if (!kargs->cset) { ret = -ENOMEM; goto err; } put_css_set(cset); kargs->cgrp = dst_cgrp; return ret; err: cgroup_threadgroup_change_end(current); cgroup_unlock(); if (dst_cgrp) cgroup_put(dst_cgrp); put_css_set(cset); if (kargs->cset) put_css_set(kargs->cset); return ret; } /** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset; cgroup_threadgroup_change_end(current); if (cset) { put_css_set(cset); kargs->cset = NULL; } if (kargs->flags & CLONE_INTO_CGROUP) { cgroup_unlock(); if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; } } } /** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i, j, ret; ret = cgroup_css_set_fork(kargs); if (ret) return ret; do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask(); return 0; out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); } cgroup_css_set_put_fork(kargs); return ret; } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); cgroup_css_set_put_fork(kargs); } /** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; struct css_set *cset; int i; cset = kargs->cset; kargs->cset = NULL; spin_lock_irq(&css_set_lock); /* init tasks are special, only link regular threads */ if (likely(child->pid)) { if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; cgrp_kill_seq = kargs->cgrp->kill_seq; } else { cgrp_flags = cset->dfl_cgrp->flags; cgrp_kill_seq = cset->dfl_cgrp->kill_seq; } WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } else { put_css_set(cset); cset = NULL; } if (!(child->flags & PF_KTHREAD)) { if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { /* * If the cgroup has to be frozen, the new task has * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to * get the task into the frozen state. */ spin_lock(&child->sighand->siglock); WARN_ON_ONCE(child->frozen); child->jobctl |= JOBCTL_TRAP_FREEZE; spin_unlock(&child->sighand->siglock); /* * Calling cgroup_update_frozen() isn't required here, * because it will be called anyway a bit later from * do_freezer_trap(). So we avoid cgroup's transient * switch from the frozen state and back. */ } /* * If the cgroup is to be killed notice it now and take the * child down right after we finished preparing it for * userspace. */ kill = kargs->kill_seq != cgrp_kill_seq; } spin_unlock_irq(&css_set_lock); /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); /* Make the new cset the root_cset of the new cgroup namespace. */ if (kargs->flags & CLONE_NEWCGROUP) { struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; get_css_set(cset); child->nsproxy->cgroup_ns->root_cset = cset; put_css_set(rcset); } /* Cgroup has to be killed so take down child immediately. */ if (unlikely(kill)) do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID); cgroup_css_set_put_fork(kargs); } /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */ void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; int i; spin_lock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); cset->nr_tasks--; /* matches the signal->live check in css_task_iter_advance() */ if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); if (dl_task(tsk)) dec_dl_tasks_cs(tsk); WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) cgroup_update_frozen(task_dfl_cgroup(tsk)); spin_unlock_irq(&css_set_lock); /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask(); } void cgroup_release(struct task_struct *task) { struct cgroup_subsys *ss; int ssid; do_each_subsys_mask(ss, ssid, have_release_callback) { ss->release(task); } while_each_subsys_mask(); if (!list_empty(&task->cg_list)) { spin_lock_irq(&css_set_lock); css_set_skip_task_iters(task_css_set(task), task); list_del_init(&task->cg_list); spin_unlock_irq(&css_set_lock); } } void cgroup_free(struct task_struct *task) { struct css_set *cset = task_css_set(task); put_css_set(cset); } static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; static_branch_disable(cgroup_subsys_enabled_key[i]); pr_info("Disabling %s control group subsystem\n", ss->name); } for (i = 0; i < OPT_FEATURE_COUNT; i++) { if (strcmp(token, cgroup_opt_feature_names[i])) continue; cgroup_feature_disable_mask |= 1 << i; pr_info("Disabling %s control group feature\n", cgroup_opt_feature_names[i]); break; } } return 1; } __setup("cgroup_disable=", cgroup_disable); void __init __weak enable_debug_cgroup(void) { } static int __init enable_cgroup_debug(char *str) { cgroup_debug = true; enable_debug_cgroup(); return 1; } __setup("cgroup_debug", enable_cgroup_debug); static int __init cgroup_favordynmods_setup(char *str) { return (kstrtobool(str, &have_favordynmods) == 0); } __setup("cgroup_favordynmods=", cgroup_favordynmods_setup); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); /* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT); rcu_read_unlock(); return css; } /** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); return idr_find(&ss->css_idr, id); } /** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); if (!kn) goto out; if (kernfs_type(kn) != KERNFS_DIR) { cgrp = ERR_PTR(-ENOTDIR); goto out_kernfs; } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); rcu_read_unlock(); out_kernfs: kernfs_put(kn); out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF); return cgroup_v1v2_get_from_file(fd_file(f)); } /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) { u64 v = 1; while (power--) v *= 10; return v; } /** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) { s64 whole, frac = 0; int fstart = 0, fend = 0, flen; if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) return -EINVAL; if (frac < 0) return -EINVAL; flen = fend > fstart ? fend - fstart : 0; if (flen < dec_shift) frac *= power_of_ten(dec_shift - flen); else frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift)); *v = whole * power_of_ten(dec_shift) + frac; return 0; } /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { struct cgroup *cgroup; rcu_read_lock(); /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) { cgroup = &cgrp_dfl_root.cgrp; cgroup_get(cgroup); goto out; } while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { cgroup = cset->dfl_cgrp; break; } cpu_relax(); } out: skcd->cgroup = cgroup; cgroup_bpf_get(cgroup); rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); /* * We might be cloning a socket which is left in an empty * cgroup and the cgroup might have already been rmdir'd. * Don't use cgroup_get_live(). */ cgroup_get(cgrp); cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); cgroup_bpf_put(cgrp); cgroup_put(cgrp); } #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) { struct cftype *cft; ssize_t ret = 0; for (cft = files; cft && cft->name[0] != '\0'; cft++) { if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) continue; if (prefix) ret += snprintf(buf + ret, size - ret, "%s.", prefix); ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); if (WARN_ON(ret >= size)) break; } return ret; } static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct cgroup_subsys *ss; int ssid; ssize_t ret = 0; ret = show_delegatable_files(cgroup_base_files, buf + ret, PAGE_SIZE - ret, NULL); if (cgroup_psi_enabled()) ret += show_delegatable_files(cgroup_psi_files, buf + ret, PAGE_SIZE - ret, NULL); for_each_subsys(ss, ssid) ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, PAGE_SIZE - ret, cgroup_subsys_name[ssid]); return ret; } static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "nsdelegate\n" "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n" "memory_hugetlb_accounting\n" "pids_localevents\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, &cgroup_features_attr.attr, NULL, }; static const struct attribute_group cgroup_sysfs_attr_group = { .attrs = cgroup_sysfs_attrs, .name = "cgroup", }; static int __init cgroup_sysfs_init(void) { return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); } subsys_initcall(cgroup_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BLK_INTEGRITY_H #define _LINUX_BLK_INTEGRITY_H #include <linux/blk-mq.h> #include <linux/bio-integrity.h> struct request; enum blk_integrity_flags { BLK_INTEGRITY_NOVERIFY = 1 << 0, BLK_INTEGRITY_NOGENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, BLK_INTEGRITY_REF_TAG = 1 << 3, BLK_INTEGRITY_STACKED = 1 << 4, }; const char *blk_integrity_profile_name(struct blk_integrity *bi); bool queue_limits_stack_integrity(struct queue_limits *t, struct queue_limits *b); static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, struct block_device *bdev) { return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits); } #ifdef CONFIG_BLK_DEV_INTEGRITY int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes); static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return q->limits.integrity.tuple_size; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { if (!blk_integrity_queue_supports_integrity(disk->queue)) return NULL; return &disk->queue->limits.integrity; } static inline struct blk_integrity * bdev_get_integrity(struct block_device *bdev) { return blk_get_integrity(bdev->bd_disk); } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return q->limits.max_integrity_segments; } /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device * @sectors: Size of the bio in 512-byte sectors * * Description: The block layer calculates everything in 512 byte * sectors but integrity metadata is done in terms of the data integrity * interval size of the storage device. Convert the block layer sectors * to the appropriate number of integrity intervals. */ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; } /* * Return the current bvec that contains the integrity data. bip_iter may be * advanced to iterate over the integrity data. */ static inline struct bio_vec rq_integrity_vec(struct request *rq) { return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec, rq->bio->bi_integrity->bip_iter); } #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *b) { return 0; } static inline int blk_rq_map_integrity_sg(struct request *q, struct scatterlist *s) { return 0; } static inline int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes) { return -EINVAL; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return 0; } static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline int blk_integrity_rq(struct request *rq) { return 0; } static inline struct bio_vec rq_integrity_vec(struct request *rq) { /* the optimizer will remove all calls to this function */ return (struct bio_vec){ }; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #endif /* _LINUX_BLK_INTEGRITY_H */ |
| 1 2 1 1 1 1 14 14 14 14 14 14 22 22 22 4 16 3 21 12 16 8 2 16 16 4 12 1 7 2 10 10 6 6 6 7 7 6 2141 2121 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2007-2012 Siemens AG * * Written by: * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Sergey Lapin <slapin@ossfans.org> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/netdevice.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/ieee802154.h> #include <net/nl802154.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/cfg802154.h> #include "ieee802154_i.h" #include "driver-ops.h" int mac802154_wpan_update_llsec(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; int rc = 0; if (ops->llsec) { struct ieee802154_llsec_params params; int changed = 0; params.pan_id = wpan_dev->pan_id; changed |= IEEE802154_LLSEC_PARAM_PAN_ID; params.hwaddr = wpan_dev->extended_addr; changed |= IEEE802154_LLSEC_PARAM_HWADDR; rc = ops->llsec->set_params(dev, ¶ms, changed); } return rc; } static int mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct sockaddr_ieee802154 *sa = (struct sockaddr_ieee802154 *)&ifr->ifr_addr; int err = -ENOIOCTLCMD; if (cmd != SIOCGIFADDR && cmd != SIOCSIFADDR) return err; rtnl_lock(); switch (cmd) { case SIOCGIFADDR: { u16 pan_id, short_addr; pan_id = le16_to_cpu(wpan_dev->pan_id); short_addr = le16_to_cpu(wpan_dev->short_addr); if (pan_id == IEEE802154_PANID_BROADCAST || short_addr == IEEE802154_ADDR_BROADCAST) { err = -EADDRNOTAVAIL; break; } sa->family = AF_IEEE802154; sa->addr.addr_type = IEEE802154_ADDR_SHORT; sa->addr.pan_id = pan_id; sa->addr.short_addr = short_addr; err = 0; break; } case SIOCSIFADDR: if (netif_running(dev)) { rtnl_unlock(); return -EBUSY; } dev_warn(&dev->dev, "Using DEBUGing ioctl SIOCSIFADDR isn't recommended!\n"); if (sa->family != AF_IEEE802154 || sa->addr.addr_type != IEEE802154_ADDR_SHORT || sa->addr.pan_id == IEEE802154_PANID_BROADCAST || sa->addr.short_addr == IEEE802154_ADDR_BROADCAST || sa->addr.short_addr == IEEE802154_ADDR_UNDEF) { err = -EINVAL; break; } wpan_dev->pan_id = cpu_to_le16(sa->addr.pan_id); wpan_dev->short_addr = cpu_to_le16(sa->addr.short_addr); err = mac802154_wpan_update_llsec(dev); break; } rtnl_unlock(); return err; } static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct sockaddr *addr = p; __le64 extended_addr; if (netif_running(dev)) return -EBUSY; /* lowpan need to be down for update * SLAAC address after ifup */ if (sdata->wpan_dev.lowpan_dev) { if (netif_running(sdata->wpan_dev.lowpan_dev)) return -EBUSY; } ieee802154_be64_to_le64(&extended_addr, addr->sa_data); if (!ieee802154_is_valid_extended_unicast_addr(extended_addr)) return -EINVAL; dev_addr_set(dev, addr->sa_data); sdata->wpan_dev.extended_addr = extended_addr; /* update lowpan interface mac address when * wpan mac has been changed */ if (sdata->wpan_dev.lowpan_dev) dev_addr_set(sdata->wpan_dev.lowpan_dev, dev->dev_addr); return mac802154_wpan_update_llsec(dev); } static int ieee802154_setup_hw(struct ieee802154_sub_if_data *sdata) { struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; sdata->required_filtering = sdata->iface_default_filtering; if (local->hw.flags & IEEE802154_HW_AFILT) { local->addr_filt.pan_id = wpan_dev->pan_id; local->addr_filt.ieee_addr = wpan_dev->extended_addr; local->addr_filt.short_addr = wpan_dev->short_addr; } if (local->hw.flags & IEEE802154_HW_LBT) { ret = drv_set_lbt_mode(local, wpan_dev->lbt); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { ret = drv_set_csma_params(local, wpan_dev->min_be, wpan_dev->max_be, wpan_dev->csma_retries); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) { ret = drv_set_max_frame_retries(local, wpan_dev->frame_retries); if (ret < 0) return ret; } return 0; } static int mac802154_slave_open(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; int res; ASSERT_RTNL(); set_bit(SDATA_STATE_RUNNING, &sdata->state); if (!local->open_count) { res = ieee802154_setup_hw(sdata); if (res) goto err; res = drv_start(local, sdata->required_filtering, &local->addr_filt); if (res) goto err; } local->open_count++; netif_start_queue(dev); return 0; err: /* might already be clear but that doesn't matter */ clear_bit(SDATA_STATE_RUNNING, &sdata->state); return res; } static int ieee802154_check_mac_settings(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct ieee802154_sub_if_data *nsdata) { struct wpan_dev *nwpan_dev = &nsdata->wpan_dev; struct wpan_dev *wpan_dev = &sdata->wpan_dev; ASSERT_RTNL(); if (sdata->iface_default_filtering != nsdata->iface_default_filtering) return -EBUSY; if (local->hw.flags & IEEE802154_HW_AFILT) { if (wpan_dev->pan_id != nwpan_dev->pan_id || wpan_dev->short_addr != nwpan_dev->short_addr || wpan_dev->extended_addr != nwpan_dev->extended_addr) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { if (wpan_dev->min_be != nwpan_dev->min_be || wpan_dev->max_be != nwpan_dev->max_be || wpan_dev->csma_retries != nwpan_dev->csma_retries) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) { if (wpan_dev->frame_retries != nwpan_dev->frame_retries) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_LBT) { if (wpan_dev->lbt != nwpan_dev->lbt) return -EBUSY; } return 0; } static int ieee802154_check_concurrent_iface(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype iftype) { struct ieee802154_local *local = sdata->local; struct ieee802154_sub_if_data *nsdata; /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee802154_sdata_running(nsdata)) { int ret; /* TODO currently we don't support multiple node/coord * types we need to run skb_clone at rx path. Check if * there exist really an use case if we need to support * multiple node/coord types at the same time. */ if (sdata->wpan_dev.iftype != NL802154_IFTYPE_MONITOR && nsdata->wpan_dev.iftype != NL802154_IFTYPE_MONITOR) return -EBUSY; /* check all phy mac sublayer settings are the same. * We have only one phy, different values makes trouble. */ ret = ieee802154_check_mac_settings(local, sdata, nsdata); if (ret < 0) return ret; } } return 0; } static int mac802154_wpan_open(struct net_device *dev) { int rc; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; rc = ieee802154_check_concurrent_iface(sdata, wpan_dev->iftype); if (rc < 0) return rc; return mac802154_slave_open(dev); } static int mac802154_slave_close(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; ASSERT_RTNL(); if (mac802154_is_scanning(local)) mac802154_abort_scan_locked(local, sdata); if (mac802154_is_beaconing(local)) mac802154_stop_beacons_locked(local, sdata); netif_stop_queue(dev); local->open_count--; clear_bit(SDATA_STATE_RUNNING, &sdata->state); if (!local->open_count) ieee802154_stop_device(local); return 0; } static int mac802154_set_header_security(struct ieee802154_sub_if_data *sdata, struct ieee802154_hdr *hdr, const struct ieee802154_mac_cb *cb) { struct ieee802154_llsec_params params; u8 level; mac802154_llsec_get_params(&sdata->sec, ¶ms); if (!params.enabled && cb->secen_override && cb->secen) return -EINVAL; if (!params.enabled || (cb->secen_override && !cb->secen) || !params.out_level) return 0; if (cb->seclevel_override && !cb->seclevel) return -EINVAL; level = cb->seclevel_override ? cb->seclevel : params.out_level; hdr->fc.security_enabled = 1; hdr->sec.level = level; hdr->sec.key_id_mode = params.out_key.mode; if (params.out_key.mode == IEEE802154_SCF_KEY_SHORT_INDEX) hdr->sec.short_src = params.out_key.short_source; else if (params.out_key.mode == IEEE802154_SCF_KEY_HW_INDEX) hdr->sec.extended_src = params.out_key.extended_source; hdr->sec.key_id = params.out_key.id; return 0; } static int ieee802154_header_create(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, const struct ieee802154_addr *saddr, unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_mac_cb *cb = mac_cb(skb); int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); hdr.fc.type = cb->type; hdr.fc.security_enabled = cb->secen; hdr.fc.ack_request = cb->ackreq; hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; if (mac802154_set_header_security(sdata, &hdr, cb) < 0) return -EINVAL; if (!saddr) { if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { hdr.source.mode = IEEE802154_ADDR_LONG; hdr.source.extended_addr = wpan_dev->extended_addr; } else { hdr.source.mode = IEEE802154_ADDR_SHORT; hdr.source.short_addr = wpan_dev->short_addr; } hdr.source.pan_id = wpan_dev->pan_id; } else { hdr.source = *(const struct ieee802154_addr *)saddr; } hdr.dest = *(const struct ieee802154_addr *)daddr; hlen = ieee802154_hdr_push(skb, &hdr); if (hlen < 0) return -EINVAL; skb_reset_mac_header(skb); skb->mac_len = hlen; if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; } static const struct wpan_dev_header_ops ieee802154_header_ops = { .create = ieee802154_header_create, }; /* This header create functionality assumes a 8 byte array for * source and destination pointer at maximum. To adapt this for * the 802.15.4 dataframe header we use extended address handling * here only and intra pan connection. fc fields are mostly fallback * handling. For provide dev_hard_header for dgram sockets. */ static int mac802154_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_mac_cb cb = { }; int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); hdr.fc.type = IEEE802154_FC_TYPE_DATA; hdr.fc.ack_request = wpan_dev->ackreq; hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; /* TODO currently a workaround to give zero cb block to set * security parameters defaults according MIB. */ if (mac802154_set_header_security(sdata, &hdr, &cb) < 0) return -EINVAL; hdr.dest.pan_id = wpan_dev->pan_id; hdr.dest.mode = IEEE802154_ADDR_LONG; ieee802154_be64_to_le64(&hdr.dest.extended_addr, daddr); hdr.source.pan_id = hdr.dest.pan_id; hdr.source.mode = IEEE802154_ADDR_LONG; if (!saddr) hdr.source.extended_addr = wpan_dev->extended_addr; else ieee802154_be64_to_le64(&hdr.source.extended_addr, saddr); hlen = ieee802154_hdr_push(skb, &hdr); if (hlen < 0) return -EINVAL; skb_reset_mac_header(skb); skb->mac_len = hlen; if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; } static int mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) { struct ieee802154_hdr hdr; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) { pr_debug("malformed packet\n"); return 0; } if (hdr.source.mode == IEEE802154_ADDR_LONG) { ieee802154_le64_to_be64(haddr, &hdr.source.extended_addr); return IEEE802154_EXTENDED_ADDR_LEN; } return 0; } static const struct header_ops mac802154_header_ops = { .create = mac802154_header_create, .parse = mac802154_header_parse, }; static const struct net_device_ops mac802154_wpan_ops = { .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = ieee802154_subif_start_xmit, .ndo_do_ioctl = mac802154_wpan_ioctl, .ndo_set_mac_address = mac802154_wpan_mac_addr, }; static const struct net_device_ops mac802154_monitor_ops = { .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = ieee802154_monitor_start_xmit, }; static void mac802154_wpan_free(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); mac802154_llsec_destroy(&sdata->sec); } static void ieee802154_if_setup(struct net_device *dev) { dev->addr_len = IEEE802154_EXTENDED_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_EXTENDED_ADDR_LEN); /* Let hard_header_len set to IEEE802154_MIN_HEADER_LEN. AF_PACKET * will not send frames without any payload, but ack frames * has no payload, so substract one that we can send a 3 bytes * frame. The xmit callback assumes at least a hard header where two * bytes fc and sequence field are set. */ dev->hard_header_len = IEEE802154_MIN_HEADER_LEN - 1; /* The auth_tag header is for security and places in private payload * room of mac frame which stucks between payload and FCS field. */ dev->needed_tailroom = IEEE802154_MAX_AUTH_TAG_LEN + IEEE802154_FCS_LEN; /* The mtu size is the payload without mac header in this case. * We have a dynamic length header with a minimum header length * which is hard_header_len. In this case we let mtu to the size * of maximum payload which is IEEE802154_MTU - IEEE802154_FCS_LEN - * hard_header_len. The FCS which is set by hardware or ndo_start_xmit * and the minimum mac header which can be evaluated inside driver * layer. The rest of mac header will be part of payload if greater * than hard_header_len. */ dev->mtu = IEEE802154_MTU - IEEE802154_FCS_LEN - dev->hard_header_len; dev->tx_queue_len = 300; dev->flags = IFF_NOARP | IFF_BROADCAST; } static int ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; u8 tmp; /* set some type-dependent values */ sdata->wpan_dev.iftype = type; get_random_bytes(&tmp, sizeof(tmp)); atomic_set(&wpan_dev->bsn, tmp); get_random_bytes(&tmp, sizeof(tmp)); atomic_set(&wpan_dev->dsn, tmp); /* defaults per 802.15.4-2011 */ wpan_dev->min_be = 3; wpan_dev->max_be = 5; wpan_dev->csma_retries = 4; wpan_dev->frame_retries = 3; wpan_dev->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); switch (type) { case NL802154_IFTYPE_COORD: case NL802154_IFTYPE_NODE: ieee802154_be64_to_le64(&wpan_dev->extended_addr, sdata->dev->dev_addr); sdata->dev->header_ops = &mac802154_header_ops; sdata->dev->needs_free_netdev = true; sdata->dev->priv_destructor = mac802154_wpan_free; sdata->dev->netdev_ops = &mac802154_wpan_ops; sdata->dev->ml_priv = &mac802154_mlme_wpan; sdata->iface_default_filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; wpan_dev->header_ops = &ieee802154_header_ops; mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); ret = mac802154_wpan_update_llsec(sdata->dev); if (ret < 0) return ret; break; case NL802154_IFTYPE_MONITOR: sdata->dev->needs_free_netdev = true; sdata->dev->netdev_ops = &mac802154_monitor_ops; sdata->iface_default_filtering = IEEE802154_FILTERING_NONE; break; default: BUG(); } return 0; } struct net_device * ieee802154_if_add(struct ieee802154_local *local, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { u8 addr[IEEE802154_EXTENDED_ADDR_LEN]; struct net_device *ndev = NULL; struct ieee802154_sub_if_data *sdata = NULL; int ret; ASSERT_RTNL(); ndev = alloc_netdev(sizeof(*sdata), name, name_assign_type, ieee802154_if_setup); if (!ndev) return ERR_PTR(-ENOMEM); ndev->needed_headroom = local->hw.extra_tx_headroom + IEEE802154_MAX_HEADER_LEN; ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) goto err; ieee802154_le64_to_be64(ndev->perm_addr, &local->hw.phy->perm_extended_addr); switch (type) { case NL802154_IFTYPE_COORD: case NL802154_IFTYPE_NODE: ndev->type = ARPHRD_IEEE802154; if (ieee802154_is_valid_extended_unicast_addr(extended_addr)) { ieee802154_le64_to_be64(addr, &extended_addr); dev_addr_set(ndev, addr); } else { dev_addr_set(ndev, ndev->perm_addr); } break; case NL802154_IFTYPE_MONITOR: ndev->type = ARPHRD_IEEE802154_MONITOR; break; default: ret = -EINVAL; goto err; } /* TODO check this */ SET_NETDEV_DEV(ndev, &local->phy->dev); dev_net_set(ndev, wpan_phy_net(local->hw.phy)); sdata = netdev_priv(ndev); ndev->ieee802154_ptr = &sdata->wpan_dev; memcpy(sdata->name, ndev->name, IFNAMSIZ); sdata->dev = ndev; sdata->wpan_dev.wpan_phy = local->hw.phy; sdata->local = local; INIT_LIST_HEAD(&sdata->wpan_dev.list); /* setup type-dependent data */ ret = ieee802154_setup_sdata(sdata, type); if (ret) goto err; ret = register_netdevice(ndev); if (ret < 0) goto err; mutex_lock(&local->iflist_mtx); list_add_tail_rcu(&sdata->list, &local->interfaces); mutex_unlock(&local->iflist_mtx); return ndev; err: free_netdev(ndev); return ERR_PTR(ret); } void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) { ASSERT_RTNL(); mutex_lock(&sdata->local->iflist_mtx); if (list_empty(&sdata->local->interfaces)) { mutex_unlock(&sdata->local->iflist_mtx); return; } list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); synchronize_rcu(); unregister_netdevice(sdata->dev); } void ieee802154_remove_interfaces(struct ieee802154_local *local) { struct ieee802154_sub_if_data *sdata, *tmp; mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); unregister_netdevice(sdata->dev); } mutex_unlock(&local->iflist_mtx); } static int netdev_notify(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ieee802154_sub_if_data *sdata; if (state != NETDEV_CHANGENAME) return NOTIFY_DONE; if (!dev->ieee802154_ptr || !dev->ieee802154_ptr->wpan_phy) return NOTIFY_DONE; if (dev->ieee802154_ptr->wpan_phy->privid != mac802154_wpan_phy_privid) return NOTIFY_DONE; sdata = IEEE802154_DEV_TO_SUB_IF(dev); memcpy(sdata->name, dev->name, IFNAMSIZ); return NOTIFY_OK; } static struct notifier_block mac802154_netdev_notifier = { .notifier_call = netdev_notify, }; int ieee802154_iface_init(void) { return register_netdevice_notifier(&mac802154_netdev_notifier); } void ieee802154_iface_exit(void) { unregister_netdevice_notifier(&mac802154_netdev_notifier); } |
| 98 98 3 3 3 3 3 3 3 3 3 3 3 3 1 3 3 3 6 6 2 5 5 6 6 3 6 5 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 | // SPDX-License-Identifier: GPL-2.0-only /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * SMC statistics netlink routines * * Copyright IBM Corp. 2021 * * Author(s): Guvenc Gulce */ #include <linux/init.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/ctype.h> #include <linux/smc.h> #include <net/genetlink.h> #include <net/sock.h> #include "smc_netlink.h" #include "smc_stats.h" int smc_stats_init(struct net *net) { net->smc.fback_rsn = kzalloc(sizeof(*net->smc.fback_rsn), GFP_KERNEL); if (!net->smc.fback_rsn) goto err_fback; net->smc.smc_stats = alloc_percpu(struct smc_stats); if (!net->smc.smc_stats) goto err_stats; mutex_init(&net->smc.mutex_fback_rsn); return 0; err_stats: kfree(net->smc.fback_rsn); err_fback: return -ENOMEM; } void smc_stats_exit(struct net *net) { kfree(net->smc.fback_rsn); if (net->smc.smc_stats) free_percpu(net->smc.smc_stats); } static int smc_nl_fill_stats_rmb_data(struct sk_buff *skb, struct smc_stats *stats, int tech, int type) { struct smc_stats_rmbcnt *stats_rmb_cnt; struct nlattr *attrs; if (type == SMC_NLA_STATS_T_TX_RMB_STATS) stats_rmb_cnt = &stats->smc[tech].rmb_tx; else stats_rmb_cnt = &stats->smc[tech].rmb_rx; attrs = nla_nest_start(skb, type); if (!attrs) goto errout; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_REUSE_CNT, stats_rmb_cnt->reuse_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT, stats_rmb_cnt->buf_size_small_peer_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_CNT, stats_rmb_cnt->buf_size_small_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_PEER_CNT, stats_rmb_cnt->buf_full_peer_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_CNT, stats_rmb_cnt->buf_full_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_ALLOC_CNT, stats_rmb_cnt->alloc_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_DGRADE_CNT, stats_rmb_cnt->dgrade_cnt, SMC_NLA_STATS_RMB_PAD)) goto errattr; nla_nest_end(skb, attrs); return 0; errattr: nla_nest_cancel(skb, attrs); errout: return -EMSGSIZE; } static int smc_nl_fill_stats_bufsize_data(struct sk_buff *skb, struct smc_stats *stats, int tech, int type) { struct smc_stats_memsize *stats_pload; struct nlattr *attrs; if (type == SMC_NLA_STATS_T_TXPLOAD_SIZE) stats_pload = &stats->smc[tech].tx_pd; else if (type == SMC_NLA_STATS_T_RXPLOAD_SIZE) stats_pload = &stats->smc[tech].rx_pd; else if (type == SMC_NLA_STATS_T_TX_RMB_SIZE) stats_pload = &stats->smc[tech].tx_rmbsize; else if (type == SMC_NLA_STATS_T_RX_RMB_SIZE) stats_pload = &stats->smc[tech].rx_rmbsize; else goto errout; attrs = nla_nest_start(skb, type); if (!attrs) goto errout; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_8K, stats_pload->buf[SMC_BUF_8K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_16K, stats_pload->buf[SMC_BUF_16K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_32K, stats_pload->buf[SMC_BUF_32K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_64K, stats_pload->buf[SMC_BUF_64K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_128K, stats_pload->buf[SMC_BUF_128K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_256K, stats_pload->buf[SMC_BUF_256K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_512K, stats_pload->buf[SMC_BUF_512K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_1024K, stats_pload->buf[SMC_BUF_1024K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_G_1024K, stats_pload->buf[SMC_BUF_G_1024K], SMC_NLA_STATS_PLOAD_PAD)) goto errattr; nla_nest_end(skb, attrs); return 0; errattr: nla_nest_cancel(skb, attrs); errout: return -EMSGSIZE; } static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, struct smc_stats *stats, int tech) { struct smc_stats_tech *smc_tech; struct nlattr *attrs; smc_tech = &stats->smc[tech]; if (tech == SMC_TYPE_D) attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCD_TECH); else attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCR_TECH); if (!attrs) goto errout; if (smc_nl_fill_stats_rmb_data(skb, stats, tech, SMC_NLA_STATS_T_TX_RMB_STATS)) goto errattr; if (smc_nl_fill_stats_rmb_data(skb, stats, tech, SMC_NLA_STATS_T_RX_RMB_STATS)) goto errattr; if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, SMC_NLA_STATS_T_TXPLOAD_SIZE)) goto errattr; if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, SMC_NLA_STATS_T_RXPLOAD_SIZE)) goto errattr; if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, SMC_NLA_STATS_T_TX_RMB_SIZE)) goto errattr; if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, SMC_NLA_STATS_T_RX_RMB_SIZE)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V1_SUCC, smc_tech->clnt_v1_succ_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V2_SUCC, smc_tech->clnt_v2_succ_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V1_SUCC, smc_tech->srv_v1_succ_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V2_SUCC, smc_tech->srv_v2_succ_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_BYTES, smc_tech->rx_bytes, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_BYTES, smc_tech->tx_bytes, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_uint(skb, SMC_NLA_STATS_T_RX_RMB_USAGE, smc_tech->rx_rmbuse)) goto errattr; if (nla_put_uint(skb, SMC_NLA_STATS_T_TX_RMB_USAGE, smc_tech->tx_rmbuse)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, smc_tech->rx_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_CNT, smc_tech->tx_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT, 0, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT, smc_tech->cork_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_NDLY_CNT, smc_tech->ndly_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SPLICE_CNT, smc_tech->splice_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_URG_DATA_CNT, smc_tech->urg_data_cnt, SMC_NLA_STATS_PAD)) goto errattr; nla_nest_end(skb, attrs); return 0; errattr: nla_nest_cancel(skb, attrs); errout: return -EMSGSIZE; } int smc_nl_get_stats(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct net *net = sock_net(skb->sk); struct smc_stats *stats; struct nlattr *attrs; int cpu, i, size; void *nlh; u64 *src; u64 *sum; if (cb_ctx->pos[0]) goto errmsg; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_STATS); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_STATS); if (!attrs) goto errnest; stats = kzalloc(sizeof(*stats), GFP_KERNEL); if (!stats) goto erralloc; size = sizeof(*stats) / sizeof(u64); for_each_possible_cpu(cpu) { src = (u64 *)per_cpu_ptr(net->smc.smc_stats, cpu); sum = (u64 *)stats; for (i = 0; i < size; i++) *(sum++) += *(src++); } if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_D)) goto errattr; if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_R)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_CLNT_HS_ERR_CNT, stats->clnt_hshake_err_cnt, SMC_NLA_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_SRV_HS_ERR_CNT, stats->srv_hshake_err_cnt, SMC_NLA_STATS_PAD)) goto errattr; nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); cb_ctx->pos[0] = 1; kfree(stats); return skb->len; errattr: kfree(stats); erralloc: nla_nest_cancel(skb, attrs); errnest: genlmsg_cancel(skb, nlh); errmsg: return skb->len; } static int smc_nl_get_fback_details(struct sk_buff *skb, struct netlink_callback *cb, int pos, bool is_srv) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct net *net = sock_net(skb->sk); int cnt_reported = cb_ctx->pos[2]; struct smc_stats_fback *trgt_arr; struct nlattr *attrs; int rc = 0; void *nlh; if (is_srv) trgt_arr = &net->smc.fback_rsn->srv[0]; else trgt_arr = &net->smc.fback_rsn->clnt[0]; if (!trgt_arr[pos].fback_code) return -ENODATA; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_FBACK_STATS); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_FBACK_STATS); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_FBACK_STATS_TYPE, is_srv)) goto errattr; if (!cnt_reported) { if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_SRV_CNT, net->smc.fback_rsn->srv_fback_cnt, SMC_NLA_FBACK_STATS_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_CLNT_CNT, net->smc.fback_rsn->clnt_fback_cnt, SMC_NLA_FBACK_STATS_PAD)) goto errattr; cnt_reported = 1; } if (nla_put_u32(skb, SMC_NLA_FBACK_STATS_RSN_CODE, trgt_arr[pos].fback_code)) goto errattr; if (nla_put_u16(skb, SMC_NLA_FBACK_STATS_RSN_CNT, trgt_arr[pos].count)) goto errattr; cb_ctx->pos[2] = cnt_reported; nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return rc; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct net *net = sock_net(skb->sk); int rc_srv = 0, rc_clnt = 0, k; int skip_serv = cb_ctx->pos[1]; int snum = cb_ctx->pos[0]; bool is_srv = true; mutex_lock(&net->smc.mutex_fback_rsn); for (k = 0; k < SMC_MAX_FBACK_RSN_CNT; k++) { if (k < snum) continue; if (!skip_serv) { rc_srv = smc_nl_get_fback_details(skb, cb, k, is_srv); if (rc_srv && rc_srv != -ENODATA) break; } else { skip_serv = 0; } rc_clnt = smc_nl_get_fback_details(skb, cb, k, !is_srv); if (rc_clnt && rc_clnt != -ENODATA) { skip_serv = 1; break; } if (rc_clnt == -ENODATA && rc_srv == -ENODATA) break; } mutex_unlock(&net->smc.mutex_fback_rsn); cb_ctx->pos[1] = skip_serv; cb_ctx->pos[0] = k; return skb->len; } |
| 42 42 42 42 42 16 16 7 7 16 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_array(n, sizeof(struct probe), GFP_KERNEL); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL); struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 16 17 17 17 17 16 17 17 16 17 10 17 16 17 16 17 6 7 7 16 17 10 10 10 7 17 17 9 9 7 6 7 7 7 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Virtio ring implementation. * * Copyright 2007 Rusty Russell IBM Corporation */ #include <linux/virtio.h> #include <linux/virtio_ring.h> #include <linux/virtio_config.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/hrtimer.h> #include <linux/dma-mapping.h> #include <linux/kmsan.h> #include <linux/spinlock.h> #include <xen/xen.h> #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ #define BAD_RING(_vq, fmt, args...) \ do { \ dev_err(&(_vq)->vq.vdev->dev, \ "%s:"fmt, (_vq)->vq.name, ##args); \ BUG(); \ } while (0) /* Caller is supposed to guarantee no reentry. */ #define START_USE(_vq) \ do { \ if ((_vq)->in_use) \ panic("%s:in_use = %i\n", \ (_vq)->vq.name, (_vq)->in_use); \ (_vq)->in_use = __LINE__; \ } while (0) #define END_USE(_vq) \ do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0) #define LAST_ADD_TIME_UPDATE(_vq) \ do { \ ktime_t now = ktime_get(); \ \ /* No kick or get, with .1 second between? Warn. */ \ if ((_vq)->last_add_time_valid) \ WARN_ON(ktime_to_ms(ktime_sub(now, \ (_vq)->last_add_time)) > 100); \ (_vq)->last_add_time = now; \ (_vq)->last_add_time_valid = true; \ } while (0) #define LAST_ADD_TIME_CHECK(_vq) \ do { \ if ((_vq)->last_add_time_valid) { \ WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), \ (_vq)->last_add_time)) > 100); \ } \ } while (0) #define LAST_ADD_TIME_INVALID(_vq) \ ((_vq)->last_add_time_valid = false) #else #define BAD_RING(_vq, fmt, args...) \ do { \ dev_err(&_vq->vq.vdev->dev, \ "%s:"fmt, (_vq)->vq.name, ##args); \ (_vq)->broken = true; \ } while (0) #define START_USE(vq) #define END_USE(vq) #define LAST_ADD_TIME_UPDATE(vq) #define LAST_ADD_TIME_CHECK(vq) #define LAST_ADD_TIME_INVALID(vq) #endif struct vring_desc_state_split { void *data; /* Data for callback. */ /* Indirect desc table and extra table, if any. These two will be * allocated together. So we won't stress more to the memory allocator. */ struct vring_desc *indir_desc; }; struct vring_desc_state_packed { void *data; /* Data for callback. */ /* Indirect desc table and extra table, if any. These two will be * allocated together. So we won't stress more to the memory allocator. */ struct vring_packed_desc *indir_desc; u16 num; /* Descriptor list length. */ u16 last; /* The last desc state in a list. */ }; struct vring_desc_extra { dma_addr_t addr; /* Descriptor DMA addr. */ u32 len; /* Descriptor length. */ u16 flags; /* Descriptor flags. */ u16 next; /* The next desc state in a list. */ }; struct vring_virtqueue_split { /* Actual memory layout for this queue. */ struct vring vring; /* Last written value to avail->flags */ u16 avail_flags_shadow; /* * Last written value to avail->idx in * guest byte order. */ u16 avail_idx_shadow; /* Per-descriptor state. */ struct vring_desc_state_split *desc_state; struct vring_desc_extra *desc_extra; /* DMA address and size information */ dma_addr_t queue_dma_addr; size_t queue_size_in_bytes; /* * The parameters for creating vrings are reserved for creating new * vring. */ u32 vring_align; bool may_reduce_num; }; struct vring_virtqueue_packed { /* Actual memory layout for this queue. */ struct { unsigned int num; struct vring_packed_desc *desc; struct vring_packed_desc_event *driver; struct vring_packed_desc_event *device; } vring; /* Driver ring wrap counter. */ bool avail_wrap_counter; /* Avail used flags. */ u16 avail_used_flags; /* Index of the next avail descriptor. */ u16 next_avail_idx; /* * Last written value to driver->flags in * guest byte order. */ u16 event_flags_shadow; /* Per-descriptor state. */ struct vring_desc_state_packed *desc_state; struct vring_desc_extra *desc_extra; /* DMA address and size information */ dma_addr_t ring_dma_addr; dma_addr_t driver_event_dma_addr; dma_addr_t device_event_dma_addr; size_t ring_size_in_bytes; size_t event_size_in_bytes; }; struct vring_virtqueue { struct virtqueue vq; /* Is this a packed ring? */ bool packed_ring; /* Is DMA API used? */ bool use_dma_api; /* Can we use weak barriers? */ bool weak_barriers; /* Other side has made a mess, don't try any more. */ bool broken; /* Host supports indirect buffers */ bool indirect; /* Host publishes avail event idx */ bool event; /* Head of free buffer list. */ unsigned int free_head; /* Number we've added since last sync. */ unsigned int num_added; /* Last used index we've seen. * for split ring, it just contains last used index * for packed ring: * bits up to VRING_PACKED_EVENT_F_WRAP_CTR include the last used index. * bits from VRING_PACKED_EVENT_F_WRAP_CTR include the used wrap counter. */ u16 last_used_idx; /* Hint for event idx: already triggered no need to disable. */ bool event_triggered; union { /* Available for split ring */ struct vring_virtqueue_split split; /* Available for packed ring */ struct vring_virtqueue_packed packed; }; /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); /* DMA, allocation, and size information */ bool we_own_ring; /* Device used for doing DMA */ struct device *dma_dev; #ifdef DEBUG /* They're supposed to lock for us. */ unsigned int in_use; /* Figure out if their kicks are too delayed. */ bool last_add_time_valid; ktime_t last_add_time; #endif }; static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num); static void vring_free(struct virtqueue *_vq); /* * Helpers. */ #define to_vvq(_vq) container_of_const(_vq, struct vring_virtqueue, vq) static bool virtqueue_use_indirect(const struct vring_virtqueue *vq, unsigned int total_sg) { /* * If the host supports indirect descriptor tables, and we have multiple * buffers, then go indirect. FIXME: tune this threshold */ return (vq->indirect && total_sg > 1 && vq->vq.num_free); } /* * Modern virtio devices have feature bits to specify whether they need a * quirk and bypass the IOMMU. If not there, just use the DMA API. * * If there, the interaction between virtio and DMA API is messy. * * On most systems with virtio, physical addresses match bus addresses, * and it doesn't particularly matter whether we use the DMA API. * * On some systems, including Xen and any system with a physical device * that speaks virtio behind a physical IOMMU, we must use the DMA API * for virtio DMA to work at all. * * On other systems, including SPARC and PPC64, virtio-pci devices are * enumerated as though they are behind an IOMMU, but the virtio host * ignores the IOMMU, so we must either pretend that the IOMMU isn't * there or somehow map everything as the identity. * * For the time being, we preserve historic behavior and bypass the DMA * API. * * TODO: install a per-device DMA ops structure that does the right thing * taking into account all the above quirks, and use the DMA API * unconditionally on data path. */ static bool vring_use_dma_api(const struct virtio_device *vdev) { if (!virtio_has_dma_quirk(vdev)) return true; /* Otherwise, we are left to guess. */ /* * In theory, it's possible to have a buggy QEMU-supposed * emulated Q35 IOMMU and Xen enabled at the same time. On * such a configuration, virtio has never worked and will * not work without an even larger kludge. Instead, enable * the DMA API if we're a Xen guest, which at least allows * all of the sensible Xen configurations to work correctly. */ if (xen_domain()) return true; return false; } static bool vring_need_unmap_buffer(const struct vring_virtqueue *vring, const struct vring_desc_extra *extra) { return vring->use_dma_api && (extra->addr != DMA_MAPPING_ERROR); } size_t virtio_max_dma_size(const struct virtio_device *vdev) { size_t max_segment_size = SIZE_MAX; if (vring_use_dma_api(vdev)) max_segment_size = dma_max_mapping_size(vdev->dev.parent); return max_segment_size; } EXPORT_SYMBOL_GPL(virtio_max_dma_size); static void *vring_alloc_queue(struct virtio_device *vdev, size_t size, dma_addr_t *dma_handle, gfp_t flag, struct device *dma_dev) { if (vring_use_dma_api(vdev)) { return dma_alloc_coherent(dma_dev, size, dma_handle, flag); } else { void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag); if (queue) { phys_addr_t phys_addr = virt_to_phys(queue); *dma_handle = (dma_addr_t)phys_addr; /* * Sanity check: make sure we dind't truncate * the address. The only arches I can find that * have 64-bit phys_addr_t but 32-bit dma_addr_t * are certain non-highmem MIPS and x86 * configurations, but these configurations * should never allocate physical pages above 32 * bits, so this is fine. Just in case, throw a * warning and abort if we end up with an * unrepresentable address. */ if (WARN_ON_ONCE(*dma_handle != phys_addr)) { free_pages_exact(queue, PAGE_ALIGN(size)); return NULL; } } return queue; } } static void vring_free_queue(struct virtio_device *vdev, size_t size, void *queue, dma_addr_t dma_handle, struct device *dma_dev) { if (vring_use_dma_api(vdev)) dma_free_coherent(dma_dev, size, queue, dma_handle); else free_pages_exact(queue, PAGE_ALIGN(size)); } /* * The DMA ops on various arches are rather gnarly right now, and * making all of the arch DMA ops work on the vring device itself * is a mess. */ static struct device *vring_dma_dev(const struct vring_virtqueue *vq) { return vq->dma_dev; } /* Map one sg entry. */ static int vring_map_one_sg(const struct vring_virtqueue *vq, struct scatterlist *sg, enum dma_data_direction direction, dma_addr_t *addr, u32 *len, bool premapped) { if (premapped) { *addr = sg_dma_address(sg); *len = sg_dma_len(sg); return 0; } *len = sg->length; if (!vq->use_dma_api) { /* * If DMA is not used, KMSAN doesn't know that the scatterlist * is initialized by the hardware. Explicitly check/unpoison it * depending on the direction. */ kmsan_handle_dma(sg_page(sg), sg->offset, sg->length, direction); *addr = (dma_addr_t)sg_phys(sg); return 0; } /* * We can't use dma_map_sg, because we don't use scatterlists in * the way it expects (we don't guarantee that the scatterlist * will exist for the lifetime of the mapping). */ *addr = dma_map_page(vring_dma_dev(vq), sg_page(sg), sg->offset, sg->length, direction); if (dma_mapping_error(vring_dma_dev(vq), *addr)) return -ENOMEM; return 0; } static dma_addr_t vring_map_single(const struct vring_virtqueue *vq, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (!vq->use_dma_api) return (dma_addr_t)virt_to_phys(cpu_addr); return dma_map_single(vring_dma_dev(vq), cpu_addr, size, direction); } static int vring_mapping_error(const struct vring_virtqueue *vq, dma_addr_t addr) { if (!vq->use_dma_api) return 0; return dma_mapping_error(vring_dma_dev(vq), addr); } static void virtqueue_init(struct vring_virtqueue *vq, u32 num) { vq->vq.num_free = num; if (vq->packed_ring) vq->last_used_idx = 0 | (1 << VRING_PACKED_EVENT_F_WRAP_CTR); else vq->last_used_idx = 0; vq->event_triggered = false; vq->num_added = 0; #ifdef DEBUG vq->in_use = false; vq->last_add_time_valid = false; #endif } /* * Split ring specific functions - *_split(). */ static unsigned int vring_unmap_one_split(const struct vring_virtqueue *vq, struct vring_desc_extra *extra) { u16 flags; flags = extra->flags; if (flags & VRING_DESC_F_INDIRECT) { if (!vq->use_dma_api) goto out; dma_unmap_single(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } else { if (!vring_need_unmap_buffer(vq, extra)) goto out; dma_unmap_page(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } out: return extra->next; } static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq, unsigned int total_sg, gfp_t gfp) { struct vring_desc_extra *extra; struct vring_desc *desc; unsigned int i, size; /* * We require lowmem mappings for the descriptors because * otherwise virt_to_phys will give us bogus addresses in the * virtqueue. */ gfp &= ~__GFP_HIGHMEM; size = sizeof(*desc) * total_sg + sizeof(*extra) * total_sg; desc = kmalloc(size, gfp); if (!desc) return NULL; extra = (struct vring_desc_extra *)&desc[total_sg]; for (i = 0; i < total_sg; i++) extra[i].next = i + 1; return desc; } static inline unsigned int virtqueue_add_desc_split(struct virtqueue *vq, struct vring_desc *desc, struct vring_desc_extra *extra, unsigned int i, dma_addr_t addr, unsigned int len, u16 flags, bool premapped) { u16 next; desc[i].flags = cpu_to_virtio16(vq->vdev, flags); desc[i].addr = cpu_to_virtio64(vq->vdev, addr); desc[i].len = cpu_to_virtio32(vq->vdev, len); extra[i].addr = premapped ? DMA_MAPPING_ERROR : addr; extra[i].len = len; extra[i].flags = flags; next = extra[i].next; desc[i].next = cpu_to_virtio16(vq->vdev, next); return next; } static inline int virtqueue_add_split(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, void *ctx, bool premapped, gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); struct vring_desc_extra *extra; struct scatterlist *sg; struct vring_desc *desc; unsigned int i, n, avail, descs_used, prev, err_idx; int head; bool indirect; START_USE(vq); BUG_ON(data == NULL); BUG_ON(ctx && vq->indirect); if (unlikely(vq->broken)) { END_USE(vq); return -EIO; } LAST_ADD_TIME_UPDATE(vq); BUG_ON(total_sg == 0); head = vq->free_head; if (virtqueue_use_indirect(vq, total_sg)) desc = alloc_indirect_split(_vq, total_sg, gfp); else { desc = NULL; WARN_ON_ONCE(total_sg > vq->split.vring.num && !vq->indirect); } if (desc) { /* Use a single buffer which doesn't continue */ indirect = true; /* Set up rest to use this indirect table. */ i = 0; descs_used = 1; extra = (struct vring_desc_extra *)&desc[total_sg]; } else { indirect = false; desc = vq->split.vring.desc; extra = vq->split.desc_extra; i = head; descs_used = total_sg; } if (unlikely(vq->vq.num_free < descs_used)) { pr_debug("Can't add buf len %i - avail = %i\n", descs_used, vq->vq.num_free); /* FIXME: for historical reasons, we force a notify here if * there are outgoing parts to the buffer. Presumably the * host should service the ring ASAP. */ if (out_sgs) vq->notify(&vq->vq); if (indirect) kfree(desc); END_USE(vq); return -ENOSPC; } for (n = 0; n < out_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { dma_addr_t addr; u32 len; if (vring_map_one_sg(vq, sg, DMA_TO_DEVICE, &addr, &len, premapped)) goto unmap_release; prev = i; /* Note that we trust indirect descriptor * table since it use stream DMA mapping. */ i = virtqueue_add_desc_split(_vq, desc, extra, i, addr, len, VRING_DESC_F_NEXT, premapped); } } for (; n < (out_sgs + in_sgs); n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { dma_addr_t addr; u32 len; if (vring_map_one_sg(vq, sg, DMA_FROM_DEVICE, &addr, &len, premapped)) goto unmap_release; prev = i; /* Note that we trust indirect descriptor * table since it use stream DMA mapping. */ i = virtqueue_add_desc_split(_vq, desc, extra, i, addr, len, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE, premapped); } } /* Last one doesn't continue. */ desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT); if (!indirect && vring_need_unmap_buffer(vq, &extra[prev])) vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &= ~VRING_DESC_F_NEXT; if (indirect) { /* Now that the indirect table is filled in, map it. */ dma_addr_t addr = vring_map_single( vq, desc, total_sg * sizeof(struct vring_desc), DMA_TO_DEVICE); if (vring_mapping_error(vq, addr)) goto unmap_release; virtqueue_add_desc_split(_vq, vq->split.vring.desc, vq->split.desc_extra, head, addr, total_sg * sizeof(struct vring_desc), VRING_DESC_F_INDIRECT, false); } /* We're using some buffers from the free list. */ vq->vq.num_free -= descs_used; /* Update free pointer */ if (indirect) vq->free_head = vq->split.desc_extra[head].next; else vq->free_head = i; /* Store token and indirect buffer state. */ vq->split.desc_state[head].data = data; if (indirect) vq->split.desc_state[head].indir_desc = desc; else vq->split.desc_state[head].indir_desc = ctx; /* Put entry in available array (but don't update avail->idx until they * do sync). */ avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1); vq->split.vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head); /* Descriptors and available array need to be set before we expose the * new available array entries. */ virtio_wmb(vq->weak_barriers); vq->split.avail_idx_shadow++; vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->split.avail_idx_shadow); vq->num_added++; pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); /* This is very unlikely, but theoretically possible. Kick * just in case. */ if (unlikely(vq->num_added == (1 << 16) - 1)) virtqueue_kick(_vq); return 0; unmap_release: err_idx = i; if (indirect) i = 0; else i = head; for (n = 0; n < total_sg; n++) { if (i == err_idx) break; i = vring_unmap_one_split(vq, &extra[i]); } if (indirect) kfree(desc); END_USE(vq); return -ENOMEM; } static bool virtqueue_kick_prepare_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 new, old; bool needs_kick; START_USE(vq); /* We need to expose available array entries before checking avail * event. */ virtio_mb(vq->weak_barriers); old = vq->split.avail_idx_shadow - vq->num_added; new = vq->split.avail_idx_shadow; vq->num_added = 0; LAST_ADD_TIME_CHECK(vq); LAST_ADD_TIME_INVALID(vq); if (vq->event) { needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->split.vring)), new, old); } else { needs_kick = !(vq->split.vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY)); } END_USE(vq); return needs_kick; } static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head, void **ctx) { struct vring_desc_extra *extra; unsigned int i, j; __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT); /* Clear data ptr. */ vq->split.desc_state[head].data = NULL; extra = vq->split.desc_extra; /* Put back on free list: unmap first-level descriptors and find end */ i = head; while (vq->split.vring.desc[i].flags & nextflag) { vring_unmap_one_split(vq, &extra[i]); i = vq->split.desc_extra[i].next; vq->vq.num_free++; } vring_unmap_one_split(vq, &extra[i]); vq->split.desc_extra[i].next = vq->free_head; vq->free_head = head; /* Plus final descriptor */ vq->vq.num_free++; if (vq->indirect) { struct vring_desc *indir_desc = vq->split.desc_state[head].indir_desc; u32 len, num; /* Free the indirect table, if any, now that it's unmapped. */ if (!indir_desc) return; len = vq->split.desc_extra[head].len; BUG_ON(!(vq->split.desc_extra[head].flags & VRING_DESC_F_INDIRECT)); BUG_ON(len == 0 || len % sizeof(struct vring_desc)); num = len / sizeof(struct vring_desc); extra = (struct vring_desc_extra *)&indir_desc[num]; if (vq->use_dma_api) { for (j = 0; j < num; j++) vring_unmap_one_split(vq, &extra[j]); } kfree(indir_desc); vq->split.desc_state[head].indir_desc = NULL; } else if (ctx) { *ctx = vq->split.desc_state[head].indir_desc; } } static bool more_used_split(const struct vring_virtqueue *vq) { return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->split.vring.used->idx); } static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq, unsigned int *len, void **ctx) { struct vring_virtqueue *vq = to_vvq(_vq); void *ret; unsigned int i; u16 last_used; START_USE(vq); if (unlikely(vq->broken)) { END_USE(vq); return NULL; } if (!more_used_split(vq)) { pr_debug("No more buffers in queue\n"); END_USE(vq); return NULL; } /* Only get used array entries after they have been exposed by host. */ virtio_rmb(vq->weak_barriers); last_used = (vq->last_used_idx & (vq->split.vring.num - 1)); i = virtio32_to_cpu(_vq->vdev, vq->split.vring.used->ring[last_used].id); *len = virtio32_to_cpu(_vq->vdev, vq->split.vring.used->ring[last_used].len); if (unlikely(i >= vq->split.vring.num)) { BAD_RING(vq, "id %u out of range\n", i); return NULL; } if (unlikely(!vq->split.desc_state[i].data)) { BAD_RING(vq, "id %u is not a head!\n", i); return NULL; } /* detach_buf_split clears data, so grab it now. */ ret = vq->split.desc_state[i].data; detach_buf_split(vq, i, ctx); vq->last_used_idx++; /* If we expect an interrupt for the next entry, tell host * by writing event index and flush out the write before * the read in the next get_buf call. */ if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) virtio_store_mb(vq->weak_barriers, &vring_used_event(&vq->split.vring), cpu_to_virtio16(_vq->vdev, vq->last_used_idx)); LAST_ADD_TIME_INVALID(vq); END_USE(vq); return ret; } static void virtqueue_disable_cb_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; /* * If device triggered an event already it won't trigger one again: * no need to disable. */ if (vq->event_triggered) return; if (vq->event) /* TODO: this is a hack. Figure out a cleaner value to write. */ vring_used_event(&vq->split.vring) = 0x0; else vq->split.vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->split.avail_flags_shadow); } } static unsigned int virtqueue_enable_cb_prepare_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 last_used_idx; START_USE(vq); /* We optimistically turn back on interrupts, then check if there was * more to do. */ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always do both to keep code simple. */ if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; if (!vq->event) vq->split.vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->split.avail_flags_shadow); } vring_used_event(&vq->split.vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx); END_USE(vq); return last_used_idx; } static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned int last_used_idx) { struct vring_virtqueue *vq = to_vvq(_vq); return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx); } static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 bufs; START_USE(vq); /* We optimistically turn back on interrupts, then check if there was * more to do. */ /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always update the event index to keep code simple. */ if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; if (!vq->event) vq->split.vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->split.avail_flags_shadow); } /* TODO: tune this threshold */ bufs = (u16)(vq->split.avail_idx_shadow - vq->last_used_idx) * 3 / 4; virtio_store_mb(vq->weak_barriers, &vring_used_event(&vq->split.vring), cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs)); if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx) - vq->last_used_idx) > bufs)) { END_USE(vq); return false; } END_USE(vq); return true; } static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); unsigned int i; void *buf; START_USE(vq); for (i = 0; i < vq->split.vring.num; i++) { if (!vq->split.desc_state[i].data) continue; /* detach_buf_split clears data, so grab it now. */ buf = vq->split.desc_state[i].data; detach_buf_split(vq, i, NULL); vq->split.avail_idx_shadow--; vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->split.avail_idx_shadow); END_USE(vq); return buf; } /* That should have freed everything. */ BUG_ON(vq->vq.num_free != vq->split.vring.num); END_USE(vq); return NULL; } static void virtqueue_vring_init_split(struct vring_virtqueue_split *vring_split, struct vring_virtqueue *vq) { struct virtio_device *vdev; vdev = vq->vq.vdev; vring_split->avail_flags_shadow = 0; vring_split->avail_idx_shadow = 0; /* No callback? Tell other side not to bother us. */ if (!vq->vq.callback) { vring_split->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; if (!vq->event) vring_split->vring.avail->flags = cpu_to_virtio16(vdev, vring_split->avail_flags_shadow); } } static void virtqueue_reinit_split(struct vring_virtqueue *vq) { int num; num = vq->split.vring.num; vq->split.vring.avail->flags = 0; vq->split.vring.avail->idx = 0; /* reset avail event */ vq->split.vring.avail->ring[num] = 0; vq->split.vring.used->flags = 0; vq->split.vring.used->idx = 0; /* reset used event */ *(__virtio16 *)&(vq->split.vring.used->ring[num]) = 0; virtqueue_init(vq, num); virtqueue_vring_init_split(&vq->split, vq); } static void virtqueue_vring_attach_split(struct vring_virtqueue *vq, struct vring_virtqueue_split *vring_split) { vq->split = *vring_split; /* Put everything in free lists. */ vq->free_head = 0; } static int vring_alloc_state_extra_split(struct vring_virtqueue_split *vring_split) { struct vring_desc_state_split *state; struct vring_desc_extra *extra; u32 num = vring_split->vring.num; state = kmalloc_array(num, sizeof(struct vring_desc_state_split), GFP_KERNEL); if (!state) goto err_state; extra = vring_alloc_desc_extra(num); if (!extra) goto err_extra; memset(state, 0, num * sizeof(struct vring_desc_state_split)); vring_split->desc_state = state; vring_split->desc_extra = extra; return 0; err_extra: kfree(state); err_state: return -ENOMEM; } static void vring_free_split(struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, struct device *dma_dev) { vring_free_queue(vdev, vring_split->queue_size_in_bytes, vring_split->vring.desc, vring_split->queue_dma_addr, dma_dev); kfree(vring_split->desc_state); kfree(vring_split->desc_extra); } static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, u32 num, unsigned int vring_align, bool may_reduce_num, struct device *dma_dev) { void *queue = NULL; dma_addr_t dma_addr; /* We assume num is a power of 2. */ if (!is_power_of_2(num)) { dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num); return -EINVAL; } /* TODO: allocate each queue chunk individually */ for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) { queue = vring_alloc_queue(vdev, vring_size(num, vring_align), &dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (queue) break; if (!may_reduce_num) return -ENOMEM; } if (!num) return -ENOMEM; if (!queue) { /* Try to get a single page. You are my only hope! */ queue = vring_alloc_queue(vdev, vring_size(num, vring_align), &dma_addr, GFP_KERNEL | __GFP_ZERO, dma_dev); } if (!queue) return -ENOMEM; vring_init(&vring_split->vring, num, queue, vring_align); vring_split->queue_dma_addr = dma_addr; vring_split->queue_size_in_bytes = vring_size(num, vring_align); vring_split->vring_align = vring_align; vring_split->may_reduce_num = may_reduce_num; return 0; } static struct virtqueue *__vring_new_virtqueue_split(unsigned int index, struct vring_virtqueue_split *vring_split, struct virtio_device *vdev, bool weak_barriers, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue *vq; int err; vq = kmalloc(sizeof(*vq), GFP_KERNEL); if (!vq) return NULL; vq->packed_ring = false; vq->vq.callback = callback; vq->vq.vdev = vdev; vq->vq.name = name; vq->vq.index = index; vq->vq.reset = false; vq->we_own_ring = false; vq->notify = notify; vq->weak_barriers = weak_barriers; #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION vq->broken = true; #else vq->broken = false; #endif vq->dma_dev = dma_dev; vq->use_dma_api = vring_use_dma_api(vdev); vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) && !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) vq->weak_barriers = false; err = vring_alloc_state_extra_split(vring_split); if (err) { kfree(vq); return NULL; } virtqueue_vring_init_split(vring_split, vq); virtqueue_init(vq, vring_split->vring.num); virtqueue_vring_attach_split(vq, vring_split); spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); spin_unlock(&vdev->vqs_list_lock); return &vq->vq; } static struct virtqueue *vring_create_virtqueue_split( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue_split vring_split = {}; struct virtqueue *vq; int err; err = vring_alloc_queue_split(&vring_split, vdev, num, vring_align, may_reduce_num, dma_dev); if (err) return NULL; vq = __vring_new_virtqueue_split(index, &vring_split, vdev, weak_barriers, context, notify, callback, name, dma_dev); if (!vq) { vring_free_split(&vring_split, vdev, dma_dev); return NULL; } to_vvq(vq)->we_own_ring = true; return vq; } static int virtqueue_resize_split(struct virtqueue *_vq, u32 num) { struct vring_virtqueue_split vring_split = {}; struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = _vq->vdev; int err; err = vring_alloc_queue_split(&vring_split, vdev, num, vq->split.vring_align, vq->split.may_reduce_num, vring_dma_dev(vq)); if (err) goto err; err = vring_alloc_state_extra_split(&vring_split); if (err) goto err_state_extra; vring_free(&vq->vq); virtqueue_vring_init_split(&vring_split, vq); virtqueue_init(vq, vring_split.vring.num); virtqueue_vring_attach_split(vq, &vring_split); return 0; err_state_extra: vring_free_split(&vring_split, vdev, vring_dma_dev(vq)); err: virtqueue_reinit_split(vq); return -ENOMEM; } /* * Packed ring specific functions - *_packed(). */ static bool packed_used_wrap_counter(u16 last_used_idx) { return !!(last_used_idx & (1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } static u16 packed_last_used(u16 last_used_idx) { return last_used_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, const struct vring_desc_extra *extra) { u16 flags; flags = extra->flags; if (flags & VRING_DESC_F_INDIRECT) { if (!vq->use_dma_api) return; dma_unmap_single(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } else { if (!vring_need_unmap_buffer(vq, extra)) return; dma_unmap_page(vring_dma_dev(vq), extra->addr, extra->len, (flags & VRING_DESC_F_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } } static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg, gfp_t gfp) { struct vring_desc_extra *extra; struct vring_packed_desc *desc; int i, size; /* * We require lowmem mappings for the descriptors because * otherwise virt_to_phys will give us bogus addresses in the * virtqueue. */ gfp &= ~__GFP_HIGHMEM; size = (sizeof(*desc) + sizeof(*extra)) * total_sg; desc = kmalloc(size, gfp); if (!desc) return NULL; extra = (struct vring_desc_extra *)&desc[total_sg]; for (i = 0; i < total_sg; i++) extra[i].next = i + 1; return desc; } static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, bool premapped, gfp_t gfp) { struct vring_desc_extra *extra; struct vring_packed_desc *desc; struct scatterlist *sg; unsigned int i, n, err_idx, len; u16 head, id; dma_addr_t addr; head = vq->packed.next_avail_idx; desc = alloc_indirect_packed(total_sg, gfp); if (!desc) return -ENOMEM; extra = (struct vring_desc_extra *)&desc[total_sg]; if (unlikely(vq->vq.num_free < 1)) { pr_debug("Can't add buf len 1 - avail = 0\n"); kfree(desc); END_USE(vq); return -ENOSPC; } i = 0; id = vq->free_head; BUG_ON(id == vq->packed.vring.num); for (n = 0; n < out_sgs + in_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { if (vring_map_one_sg(vq, sg, n < out_sgs ? DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr, &len, premapped)) goto unmap_release; desc[i].flags = cpu_to_le16(n < out_sgs ? 0 : VRING_DESC_F_WRITE); desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(len); if (unlikely(vq->use_dma_api)) { extra[i].addr = premapped ? DMA_MAPPING_ERROR : addr; extra[i].len = len; extra[i].flags = n < out_sgs ? 0 : VRING_DESC_F_WRITE; } i++; } } /* Now that the indirect table is filled in, map it. */ addr = vring_map_single(vq, desc, total_sg * sizeof(struct vring_packed_desc), DMA_TO_DEVICE); if (vring_mapping_error(vq, addr)) goto unmap_release; vq->packed.vring.desc[head].addr = cpu_to_le64(addr); vq->packed.vring.desc[head].len = cpu_to_le32(total_sg * sizeof(struct vring_packed_desc)); vq->packed.vring.desc[head].id = cpu_to_le16(id); if (vq->use_dma_api) { vq->packed.desc_extra[id].addr = addr; vq->packed.desc_extra[id].len = total_sg * sizeof(struct vring_packed_desc); vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT | vq->packed.avail_used_flags; } /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising * the list are made available. */ virtio_wmb(vq->weak_barriers); vq->packed.vring.desc[head].flags = cpu_to_le16(VRING_DESC_F_INDIRECT | vq->packed.avail_used_flags); /* We're using some buffers from the free list. */ vq->vq.num_free -= 1; /* Update free pointer */ n = head + 1; if (n >= vq->packed.vring.num) { n = 0; vq->packed.avail_wrap_counter ^= 1; vq->packed.avail_used_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } vq->packed.next_avail_idx = n; vq->free_head = vq->packed.desc_extra[id].next; /* Store token and indirect buffer state. */ vq->packed.desc_state[id].num = 1; vq->packed.desc_state[id].data = data; vq->packed.desc_state[id].indir_desc = desc; vq->packed.desc_state[id].last = id; vq->num_added += 1; pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); return 0; unmap_release: err_idx = i; for (i = 0; i < err_idx; i++) vring_unmap_extra_packed(vq, &extra[i]); kfree(desc); END_USE(vq); return -ENOMEM; } static inline int virtqueue_add_packed(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, void *ctx, bool premapped, gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); struct vring_packed_desc *desc; struct scatterlist *sg; unsigned int i, n, c, descs_used, err_idx, len; __le16 head_flags, flags; u16 head, id, prev, curr, avail_used_flags; int err; START_USE(vq); BUG_ON(data == NULL); BUG_ON(ctx && vq->indirect); if (unlikely(vq->broken)) { END_USE(vq); return -EIO; } LAST_ADD_TIME_UPDATE(vq); BUG_ON(total_sg == 0); if (virtqueue_use_indirect(vq, total_sg)) { err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs, in_sgs, data, premapped, gfp); if (err != -ENOMEM) { END_USE(vq); return err; } /* fall back on direct */ } head = vq->packed.next_avail_idx; avail_used_flags = vq->packed.avail_used_flags; WARN_ON_ONCE(total_sg > vq->packed.vring.num && !vq->indirect); desc = vq->packed.vring.desc; i = head; descs_used = total_sg; if (unlikely(vq->vq.num_free < descs_used)) { pr_debug("Can't add buf len %i - avail = %i\n", descs_used, vq->vq.num_free); END_USE(vq); return -ENOSPC; } id = vq->free_head; BUG_ON(id == vq->packed.vring.num); curr = id; c = 0; for (n = 0; n < out_sgs + in_sgs; n++) { for (sg = sgs[n]; sg; sg = sg_next(sg)) { dma_addr_t addr; if (vring_map_one_sg(vq, sg, n < out_sgs ? DMA_TO_DEVICE : DMA_FROM_DEVICE, &addr, &len, premapped)) goto unmap_release; flags = cpu_to_le16(vq->packed.avail_used_flags | (++c == total_sg ? 0 : VRING_DESC_F_NEXT) | (n < out_sgs ? 0 : VRING_DESC_F_WRITE)); if (i == head) head_flags = flags; else desc[i].flags = flags; desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(len); desc[i].id = cpu_to_le16(id); if (unlikely(vq->use_dma_api)) { vq->packed.desc_extra[curr].addr = premapped ? DMA_MAPPING_ERROR : addr; vq->packed.desc_extra[curr].len = len; vq->packed.desc_extra[curr].flags = le16_to_cpu(flags); } prev = curr; curr = vq->packed.desc_extra[curr].next; if ((unlikely(++i >= vq->packed.vring.num))) { i = 0; vq->packed.avail_used_flags ^= 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } } } if (i <= head) vq->packed.avail_wrap_counter ^= 1; /* We're using some buffers from the free list. */ vq->vq.num_free -= descs_used; /* Update free pointer */ vq->packed.next_avail_idx = i; vq->free_head = curr; /* Store token. */ vq->packed.desc_state[id].num = descs_used; vq->packed.desc_state[id].data = data; vq->packed.desc_state[id].indir_desc = ctx; vq->packed.desc_state[id].last = prev; /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising * the list are made available. */ virtio_wmb(vq->weak_barriers); vq->packed.vring.desc[head].flags = head_flags; vq->num_added += descs_used; pr_debug("Added buffer head %i to %p\n", head, vq); END_USE(vq); return 0; unmap_release: err_idx = i; i = head; curr = vq->free_head; vq->packed.avail_used_flags = avail_used_flags; for (n = 0; n < total_sg; n++) { if (i == err_idx) break; vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; i++; if (i >= vq->packed.vring.num) i = 0; } END_USE(vq); return -EIO; } static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 new, old, off_wrap, flags, wrap_counter, event_idx; bool needs_kick; union { struct { __le16 off_wrap; __le16 flags; }; u32 u32; } snapshot; START_USE(vq); /* * We need to expose the new flags value before checking notification * suppressions. */ virtio_mb(vq->weak_barriers); old = vq->packed.next_avail_idx - vq->num_added; new = vq->packed.next_avail_idx; vq->num_added = 0; snapshot.u32 = *(u32 *)vq->packed.vring.device; flags = le16_to_cpu(snapshot.flags); LAST_ADD_TIME_CHECK(vq); LAST_ADD_TIME_INVALID(vq); if (flags != VRING_PACKED_EVENT_FLAG_DESC) { needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE); goto out; } off_wrap = le16_to_cpu(snapshot.off_wrap); wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR; event_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR); if (wrap_counter != vq->packed.avail_wrap_counter) event_idx -= vq->packed.vring.num; needs_kick = vring_need_event(event_idx, new, old); out: END_USE(vq); return needs_kick; } static void detach_buf_packed(struct vring_virtqueue *vq, unsigned int id, void **ctx) { struct vring_desc_state_packed *state = NULL; struct vring_packed_desc *desc; unsigned int i, curr; state = &vq->packed.desc_state[id]; /* Clear data ptr. */ state->data = NULL; vq->packed.desc_extra[state->last].next = vq->free_head; vq->free_head = id; vq->vq.num_free += state->num; if (unlikely(vq->use_dma_api)) { curr = id; for (i = 0; i < state->num; i++) { vring_unmap_extra_packed(vq, &vq->packed.desc_extra[curr]); curr = vq->packed.desc_extra[curr].next; } } if (vq->indirect) { struct vring_desc_extra *extra; u32 len, num; /* Free the indirect table, if any, now that it's unmapped. */ desc = state->indir_desc; if (!desc) return; if (vq->use_dma_api) { len = vq->packed.desc_extra[id].len; num = len / sizeof(struct vring_packed_desc); extra = (struct vring_desc_extra *)&desc[num]; for (i = 0; i < num; i++) vring_unmap_extra_packed(vq, &extra[i]); } kfree(desc); state->indir_desc = NULL; } else if (ctx) { *ctx = state->indir_desc; } } static inline bool is_used_desc_packed(const struct vring_virtqueue *vq, u16 idx, bool used_wrap_counter) { bool avail, used; u16 flags; flags = le16_to_cpu(vq->packed.vring.desc[idx].flags); avail = !!(flags & (1 << VRING_PACKED_DESC_F_AVAIL)); used = !!(flags & (1 << VRING_PACKED_DESC_F_USED)); return avail == used && used == used_wrap_counter; } static bool more_used_packed(const struct vring_virtqueue *vq) { u16 last_used; u16 last_used_idx; bool used_wrap_counter; last_used_idx = READ_ONCE(vq->last_used_idx); last_used = packed_last_used(last_used_idx); used_wrap_counter = packed_used_wrap_counter(last_used_idx); return is_used_desc_packed(vq, last_used, used_wrap_counter); } static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, unsigned int *len, void **ctx) { struct vring_virtqueue *vq = to_vvq(_vq); u16 last_used, id, last_used_idx; bool used_wrap_counter; void *ret; START_USE(vq); if (unlikely(vq->broken)) { END_USE(vq); return NULL; } if (!more_used_packed(vq)) { pr_debug("No more buffers in queue\n"); END_USE(vq); return NULL; } /* Only get used elements after they have been exposed by host. */ virtio_rmb(vq->weak_barriers); last_used_idx = READ_ONCE(vq->last_used_idx); used_wrap_counter = packed_used_wrap_counter(last_used_idx); last_used = packed_last_used(last_used_idx); id = le16_to_cpu(vq->packed.vring.desc[last_used].id); *len = le32_to_cpu(vq->packed.vring.desc[last_used].len); if (unlikely(id >= vq->packed.vring.num)) { BAD_RING(vq, "id %u out of range\n", id); return NULL; } if (unlikely(!vq->packed.desc_state[id].data)) { BAD_RING(vq, "id %u is not a head!\n", id); return NULL; } /* detach_buf_packed clears data, so grab it now. */ ret = vq->packed.desc_state[id].data; detach_buf_packed(vq, id, ctx); last_used += vq->packed.desc_state[id].num; if (unlikely(last_used >= vq->packed.vring.num)) { last_used -= vq->packed.vring.num; used_wrap_counter ^= 1; } last_used = (last_used | (used_wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR)); WRITE_ONCE(vq->last_used_idx, last_used); /* * If we expect an interrupt for the next entry, tell host * by writing event index and flush out the write before * the read in the next get_buf call. */ if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DESC) virtio_store_mb(vq->weak_barriers, &vq->packed.vring.driver->off_wrap, cpu_to_le16(vq->last_used_idx)); LAST_ADD_TIME_INVALID(vq); END_USE(vq); return ret; } static void virtqueue_disable_cb_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; /* * If device triggered an event already it won't trigger one again: * no need to disable. */ if (vq->event_triggered) return; vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } } static unsigned int virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); START_USE(vq); /* * We optimistically turn back on interrupts, then check if there was * more to do. */ if (vq->event) { vq->packed.vring.driver->off_wrap = cpu_to_le16(vq->last_used_idx); /* * We need to update event offset and event wrap * counter first before updating event flags. */ virtio_wmb(vq->weak_barriers); } if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = vq->event ? VRING_PACKED_EVENT_FLAG_DESC : VRING_PACKED_EVENT_FLAG_ENABLE; vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } END_USE(vq); return vq->last_used_idx; } static bool virtqueue_poll_packed(struct virtqueue *_vq, u16 off_wrap) { struct vring_virtqueue *vq = to_vvq(_vq); bool wrap_counter; u16 used_idx; wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR; used_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR); return is_used_desc_packed(vq, used_idx, wrap_counter); } static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 used_idx, wrap_counter, last_used_idx; u16 bufs; START_USE(vq); /* * We optimistically turn back on interrupts, then check if there was * more to do. */ if (vq->event) { /* TODO: tune this threshold */ bufs = (vq->packed.vring.num - vq->vq.num_free) * 3 / 4; last_used_idx = READ_ONCE(vq->last_used_idx); wrap_counter = packed_used_wrap_counter(last_used_idx); used_idx = packed_last_used(last_used_idx) + bufs; if (used_idx >= vq->packed.vring.num) { used_idx -= vq->packed.vring.num; wrap_counter ^= 1; } vq->packed.vring.driver->off_wrap = cpu_to_le16(used_idx | (wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR)); /* * We need to update event offset and event wrap * counter first before updating event flags. */ virtio_wmb(vq->weak_barriers); } if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = vq->event ? VRING_PACKED_EVENT_FLAG_DESC : VRING_PACKED_EVENT_FLAG_ENABLE; vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } /* * We need to update event suppression structure first * before re-checking for more used buffers. */ virtio_mb(vq->weak_barriers); last_used_idx = READ_ONCE(vq->last_used_idx); wrap_counter = packed_used_wrap_counter(last_used_idx); used_idx = packed_last_used(last_used_idx); if (is_used_desc_packed(vq, used_idx, wrap_counter)) { END_USE(vq); return false; } END_USE(vq); return true; } static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); unsigned int i; void *buf; START_USE(vq); for (i = 0; i < vq->packed.vring.num; i++) { if (!vq->packed.desc_state[i].data) continue; /* detach_buf clears data, so grab it now. */ buf = vq->packed.desc_state[i].data; detach_buf_packed(vq, i, NULL); END_USE(vq); return buf; } /* That should have freed everything. */ BUG_ON(vq->vq.num_free != vq->packed.vring.num); END_USE(vq); return NULL; } static struct vring_desc_extra *vring_alloc_desc_extra(unsigned int num) { struct vring_desc_extra *desc_extra; unsigned int i; desc_extra = kmalloc_array(num, sizeof(struct vring_desc_extra), GFP_KERNEL); if (!desc_extra) return NULL; memset(desc_extra, 0, num * sizeof(struct vring_desc_extra)); for (i = 0; i < num - 1; i++) desc_extra[i].next = i + 1; return desc_extra; } static void vring_free_packed(struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, struct device *dma_dev) { if (vring_packed->vring.desc) vring_free_queue(vdev, vring_packed->ring_size_in_bytes, vring_packed->vring.desc, vring_packed->ring_dma_addr, dma_dev); if (vring_packed->vring.driver) vring_free_queue(vdev, vring_packed->event_size_in_bytes, vring_packed->vring.driver, vring_packed->driver_event_dma_addr, dma_dev); if (vring_packed->vring.device) vring_free_queue(vdev, vring_packed->event_size_in_bytes, vring_packed->vring.device, vring_packed->device_event_dma_addr, dma_dev); kfree(vring_packed->desc_state); kfree(vring_packed->desc_extra); } static int vring_alloc_queue_packed(struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, u32 num, struct device *dma_dev) { struct vring_packed_desc *ring; struct vring_packed_desc_event *driver, *device; dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr; size_t ring_size_in_bytes, event_size_in_bytes; ring_size_in_bytes = num * sizeof(struct vring_packed_desc); ring = vring_alloc_queue(vdev, ring_size_in_bytes, &ring_dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (!ring) goto err; vring_packed->vring.desc = ring; vring_packed->ring_dma_addr = ring_dma_addr; vring_packed->ring_size_in_bytes = ring_size_in_bytes; event_size_in_bytes = sizeof(struct vring_packed_desc_event); driver = vring_alloc_queue(vdev, event_size_in_bytes, &driver_event_dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (!driver) goto err; vring_packed->vring.driver = driver; vring_packed->event_size_in_bytes = event_size_in_bytes; vring_packed->driver_event_dma_addr = driver_event_dma_addr; device = vring_alloc_queue(vdev, event_size_in_bytes, &device_event_dma_addr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, dma_dev); if (!device) goto err; vring_packed->vring.device = device; vring_packed->device_event_dma_addr = device_event_dma_addr; vring_packed->vring.num = num; return 0; err: vring_free_packed(vring_packed, vdev, dma_dev); return -ENOMEM; } static int vring_alloc_state_extra_packed(struct vring_virtqueue_packed *vring_packed) { struct vring_desc_state_packed *state; struct vring_desc_extra *extra; u32 num = vring_packed->vring.num; state = kmalloc_array(num, sizeof(struct vring_desc_state_packed), GFP_KERNEL); if (!state) goto err_desc_state; memset(state, 0, num * sizeof(struct vring_desc_state_packed)); extra = vring_alloc_desc_extra(num); if (!extra) goto err_desc_extra; vring_packed->desc_state = state; vring_packed->desc_extra = extra; return 0; err_desc_extra: kfree(state); err_desc_state: return -ENOMEM; } static void virtqueue_vring_init_packed(struct vring_virtqueue_packed *vring_packed, bool callback) { vring_packed->next_avail_idx = 0; vring_packed->avail_wrap_counter = 1; vring_packed->event_flags_shadow = 0; vring_packed->avail_used_flags = 1 << VRING_PACKED_DESC_F_AVAIL; /* No callback? Tell other side not to bother us. */ if (!callback) { vring_packed->event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; vring_packed->vring.driver->flags = cpu_to_le16(vring_packed->event_flags_shadow); } } static void virtqueue_vring_attach_packed(struct vring_virtqueue *vq, struct vring_virtqueue_packed *vring_packed) { vq->packed = *vring_packed; /* Put everything in free lists. */ vq->free_head = 0; } static void virtqueue_reinit_packed(struct vring_virtqueue *vq) { memset(vq->packed.vring.device, 0, vq->packed.event_size_in_bytes); memset(vq->packed.vring.driver, 0, vq->packed.event_size_in_bytes); /* we need to reset the desc.flags. For more, see is_used_desc_packed() */ memset(vq->packed.vring.desc, 0, vq->packed.ring_size_in_bytes); virtqueue_init(vq, vq->packed.vring.num); virtqueue_vring_init_packed(&vq->packed, !!vq->vq.callback); } static struct virtqueue *__vring_new_virtqueue_packed(unsigned int index, struct vring_virtqueue_packed *vring_packed, struct virtio_device *vdev, bool weak_barriers, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue *vq; int err; vq = kmalloc(sizeof(*vq), GFP_KERNEL); if (!vq) return NULL; vq->vq.callback = callback; vq->vq.vdev = vdev; vq->vq.name = name; vq->vq.index = index; vq->vq.reset = false; vq->we_own_ring = false; vq->notify = notify; vq->weak_barriers = weak_barriers; #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION vq->broken = true; #else vq->broken = false; #endif vq->packed_ring = true; vq->dma_dev = dma_dev; vq->use_dma_api = vring_use_dma_api(vdev); vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) && !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) vq->weak_barriers = false; err = vring_alloc_state_extra_packed(vring_packed); if (err) { kfree(vq); return NULL; } virtqueue_vring_init_packed(vring_packed, !!callback); virtqueue_init(vq, vring_packed->vring.num); virtqueue_vring_attach_packed(vq, vring_packed); spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); spin_unlock(&vdev->vqs_list_lock); return &vq->vq; } static struct virtqueue *vring_create_virtqueue_packed( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { struct vring_virtqueue_packed vring_packed = {}; struct virtqueue *vq; if (vring_alloc_queue_packed(&vring_packed, vdev, num, dma_dev)) return NULL; vq = __vring_new_virtqueue_packed(index, &vring_packed, vdev, weak_barriers, context, notify, callback, name, dma_dev); if (!vq) { vring_free_packed(&vring_packed, vdev, dma_dev); return NULL; } to_vvq(vq)->we_own_ring = true; return vq; } static int virtqueue_resize_packed(struct virtqueue *_vq, u32 num) { struct vring_virtqueue_packed vring_packed = {}; struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = _vq->vdev; int err; if (vring_alloc_queue_packed(&vring_packed, vdev, num, vring_dma_dev(vq))) goto err_ring; err = vring_alloc_state_extra_packed(&vring_packed); if (err) goto err_state_extra; vring_free(&vq->vq); virtqueue_vring_init_packed(&vring_packed, !!vq->vq.callback); virtqueue_init(vq, vring_packed.vring.num); virtqueue_vring_attach_packed(vq, &vring_packed); return 0; err_state_extra: vring_free_packed(&vring_packed, vdev, vring_dma_dev(vq)); err_ring: virtqueue_reinit_packed(vq); return -ENOMEM; } static int virtqueue_disable_and_recycle(struct virtqueue *_vq, void (*recycle)(struct virtqueue *vq, void *buf)) { struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = vq->vq.vdev; void *buf; int err; if (!vq->we_own_ring) return -EPERM; if (!vdev->config->disable_vq_and_reset) return -ENOENT; if (!vdev->config->enable_vq_after_reset) return -ENOENT; err = vdev->config->disable_vq_and_reset(_vq); if (err) return err; while ((buf = virtqueue_detach_unused_buf(_vq)) != NULL) recycle(_vq, buf); return 0; } static int virtqueue_enable_after_reset(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); struct virtio_device *vdev = vq->vq.vdev; if (vdev->config->enable_vq_after_reset(_vq)) return -EBUSY; return 0; } /* * Generic functions and exported symbols. */ static inline int virtqueue_add(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int total_sg, unsigned int out_sgs, unsigned int in_sgs, void *data, void *ctx, bool premapped, gfp_t gfp) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_add_packed(_vq, sgs, total_sg, out_sgs, in_sgs, data, ctx, premapped, gfp) : virtqueue_add_split(_vq, sgs, total_sg, out_sgs, in_sgs, data, ctx, premapped, gfp); } /** * virtqueue_add_sgs - expose buffers to other end * @_vq: the struct virtqueue we're talking about. * @sgs: array of terminated scatterlists. * @out_sgs: the number of scatterlists readable by other side * @in_sgs: the number of scatterlists which are writable (after readable ones) * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_sgs(struct virtqueue *_vq, struct scatterlist *sgs[], unsigned int out_sgs, unsigned int in_sgs, void *data, gfp_t gfp) { unsigned int i, total_sg = 0; /* Count them first. */ for (i = 0; i < out_sgs + in_sgs; i++) { struct scatterlist *sg; for (sg = sgs[i]; sg; sg = sg_next(sg)) total_sg++; } return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, NULL, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_sgs); /** * virtqueue_add_outbuf - expose output buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg readable by other side * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_outbuf(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_outbuf); /** * virtqueue_add_outbuf_premapped - expose output buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg readable by other side * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Return: * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_outbuf_premapped(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, true, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_outbuf_premapped); /** * virtqueue_add_inbuf - expose input buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg writable by other side * @data: the token identifying the buffer. * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_inbuf(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf); /** * virtqueue_add_inbuf_ctx - expose input buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg writable by other side * @data: the token identifying the buffer. * @ctx: extra context for the token * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_inbuf_ctx(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, void *ctx, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, false, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx); /** * virtqueue_add_inbuf_premapped - expose input buffers to other end * @vq: the struct virtqueue we're talking about. * @sg: scatterlist (must be well-formed and terminated!) * @num: the number of entries in @sg writable by other side * @data: the token identifying the buffer. * @ctx: extra context for the token * @gfp: how to do memory allocations (if necessary). * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Return: * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO). */ int virtqueue_add_inbuf_premapped(struct virtqueue *vq, struct scatterlist *sg, unsigned int num, void *data, void *ctx, gfp_t gfp) { return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, true, gfp); } EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_premapped); /** * virtqueue_dma_dev - get the dma dev * @_vq: the struct virtqueue we're talking about. * * Returns the dma dev. That can been used for dma api. */ struct device *virtqueue_dma_dev(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->use_dma_api) return vring_dma_dev(vq); else return NULL; } EXPORT_SYMBOL_GPL(virtqueue_dma_dev); /** * virtqueue_kick_prepare - first half of split virtqueue_kick call. * @_vq: the struct virtqueue * * Instead of virtqueue_kick(), you can do: * if (virtqueue_kick_prepare(vq)) * virtqueue_notify(vq); * * This is sometimes useful because the virtqueue_kick_prepare() needs * to be serialized, but the actual virtqueue_notify() call does not. */ bool virtqueue_kick_prepare(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_kick_prepare_packed(_vq) : virtqueue_kick_prepare_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_kick_prepare); /** * virtqueue_notify - second half of split virtqueue_kick call. * @_vq: the struct virtqueue * * This does not need to be serialized. * * Returns false if host notify failed or queue is broken, otherwise true. */ bool virtqueue_notify(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (unlikely(vq->broken)) return false; /* Prod other side to tell it about changes. */ if (!vq->notify(_vq)) { vq->broken = true; return false; } return true; } EXPORT_SYMBOL_GPL(virtqueue_notify); /** * virtqueue_kick - update after add_buf * @vq: the struct virtqueue * * After one or more virtqueue_add_* calls, invoke this to kick * the other side. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). * * Returns false if kick failed, otherwise true. */ bool virtqueue_kick(struct virtqueue *vq) { if (virtqueue_kick_prepare(vq)) return virtqueue_notify(vq); return true; } EXPORT_SYMBOL_GPL(virtqueue_kick); /** * virtqueue_get_buf_ctx - get the next used buffer * @_vq: the struct virtqueue we're talking about. * @len: the length written into the buffer * @ctx: extra context for the token * * If the device wrote data into the buffer, @len will be set to the * amount written. This means you don't need to clear the buffer * beforehand to ensure there's no data leakage in the case of short * writes. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). * * Returns NULL if there are no used buffers, or the "data" token * handed to virtqueue_add_*(). */ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len, void **ctx) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) : virtqueue_get_buf_ctx_split(_vq, len, ctx); } EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx); void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) { return virtqueue_get_buf_ctx(_vq, len, NULL); } EXPORT_SYMBOL_GPL(virtqueue_get_buf); /** * virtqueue_disable_cb - disable callbacks * @_vq: the struct virtqueue we're talking about. * * Note that this is not necessarily synchronous, hence unreliable and only * useful as an optimization. * * Unlike other operations, this need not be serialized. */ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->packed_ring) virtqueue_disable_cb_packed(_vq); else virtqueue_disable_cb_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_disable_cb); /** * virtqueue_enable_cb_prepare - restart callbacks after disable_cb * @_vq: the struct virtqueue we're talking about. * * This re-enables callbacks; it returns current queue state * in an opaque unsigned value. This value should be later tested by * virtqueue_poll, to detect a possible race between the driver checking for * more work, and enabling callbacks. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). */ unsigned int virtqueue_enable_cb_prepare(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->event_triggered) vq->event_triggered = false; return vq->packed_ring ? virtqueue_enable_cb_prepare_packed(_vq) : virtqueue_enable_cb_prepare_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare); /** * virtqueue_poll - query pending used buffers * @_vq: the struct virtqueue we're talking about. * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare). * * Returns "true" if there are pending used buffers in the queue. * * This does not need to be serialized. */ bool virtqueue_poll(struct virtqueue *_vq, unsigned int last_used_idx) { struct vring_virtqueue *vq = to_vvq(_vq); if (unlikely(vq->broken)) return false; virtio_mb(vq->weak_barriers); return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) : virtqueue_poll_split(_vq, last_used_idx); } EXPORT_SYMBOL_GPL(virtqueue_poll); /** * virtqueue_enable_cb - restart callbacks after disable_cb. * @_vq: the struct virtqueue we're talking about. * * This re-enables callbacks; it returns "false" if there are pending * buffers in the queue, to detect a possible race between the driver * checking for more work, and enabling callbacks. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). */ bool virtqueue_enable_cb(struct virtqueue *_vq) { unsigned int last_used_idx = virtqueue_enable_cb_prepare(_vq); return !virtqueue_poll(_vq, last_used_idx); } EXPORT_SYMBOL_GPL(virtqueue_enable_cb); /** * virtqueue_enable_cb_delayed - restart callbacks after disable_cb. * @_vq: the struct virtqueue we're talking about. * * This re-enables callbacks but hints to the other side to delay * interrupts until most of the available buffers have been processed; * it returns "false" if there are many pending buffers in the queue, * to detect a possible race between the driver checking for more work, * and enabling callbacks. * * Caller must ensure we don't call this with other virtqueue * operations at the same time (except where noted). */ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->event_triggered) data_race(vq->event_triggered = false); return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) : virtqueue_enable_cb_delayed_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed); /** * virtqueue_detach_unused_buf - detach first unused buffer * @_vq: the struct virtqueue we're talking about. * * Returns NULL or the "data" token handed to virtqueue_add_*(). * This is not valid on an active queue; it is useful for device * shutdown or the reset queue. */ void *virtqueue_detach_unused_buf(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? virtqueue_detach_unused_buf_packed(_vq) : virtqueue_detach_unused_buf_split(_vq); } EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf); static inline bool more_used(const struct vring_virtqueue *vq) { return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq); } /** * vring_interrupt - notify a virtqueue on an interrupt * @irq: the IRQ number (ignored) * @_vq: the struct virtqueue to notify * * Calls the callback function of @_vq to process the virtqueue * notification. */ irqreturn_t vring_interrupt(int irq, void *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (!more_used(vq)) { pr_debug("virtqueue interrupt with no work for %p\n", vq); return IRQ_NONE; } if (unlikely(vq->broken)) { #ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION dev_warn_once(&vq->vq.vdev->dev, "virtio vring IRQ raised before DRIVER_OK"); return IRQ_NONE; #else return IRQ_HANDLED; #endif } /* Just a hint for performance: so it's ok that this can be racy! */ if (vq->event) data_race(vq->event_triggered = true); pr_debug("virtqueue callback for %p (%p)\n", vq, vq->vq.callback); if (vq->vq.callback) vq->vq.callback(&vq->vq); return IRQ_HANDLED; } EXPORT_SYMBOL_GPL(vring_interrupt); struct virtqueue *vring_create_virtqueue( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name) { if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) return vring_create_virtqueue_packed(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, vdev->dev.parent); return vring_create_virtqueue_split(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, vdev->dev.parent); } EXPORT_SYMBOL_GPL(vring_create_virtqueue); struct virtqueue *vring_create_virtqueue_dma( unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool may_reduce_num, bool context, bool (*notify)(struct virtqueue *), void (*callback)(struct virtqueue *), const char *name, struct device *dma_dev) { if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) return vring_create_virtqueue_packed(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, dma_dev); return vring_create_virtqueue_split(index, num, vring_align, vdev, weak_barriers, may_reduce_num, context, notify, callback, name, dma_dev); } EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); /** * virtqueue_resize - resize the vring of vq * @_vq: the struct virtqueue we're talking about. * @num: new ring num * @recycle: callback to recycle unused buffers * @recycle_done: callback to be invoked when recycle for all unused buffers done * * When it is really necessary to create a new vring, it will set the current vq * into the reset state. Then call the passed callback to recycle the buffer * that is no longer used. Only after the new vring is successfully created, the * old vring will be released. * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error. * 0: success. * -ENOMEM: Failed to allocate a new ring, fall back to the original ring size. * vq can still work normally * -EBUSY: Failed to sync with device, vq may not work properly * -ENOENT: Transport or device not supported * -E2BIG/-EINVAL: num error * -EPERM: Operation not permitted * */ int virtqueue_resize(struct virtqueue *_vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf), void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); int err; if (num > vq->vq.num_max) return -E2BIG; if (!num) return -EINVAL; if ((vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num) == num) return 0; err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; if (recycle_done) recycle_done(_vq); if (vq->packed_ring) err = virtqueue_resize_packed(_vq, num); else err = virtqueue_resize_split(_vq, num); return virtqueue_enable_after_reset(_vq); } EXPORT_SYMBOL_GPL(virtqueue_resize); /** * virtqueue_reset - detach and recycle all unused buffers * @_vq: the struct virtqueue we're talking about. * @recycle: callback to recycle unused buffers * @recycle_done: callback to be invoked when recycle for all unused buffers done * * Caller must ensure we don't call this with other virtqueue operations * at the same time (except where noted). * * Returns zero or a negative error. * 0: success. * -EBUSY: Failed to sync with device, vq may not work properly * -ENOENT: Transport or device not supported * -EPERM: Operation not permitted */ int virtqueue_reset(struct virtqueue *_vq, void (*recycle)(struct virtqueue *vq, void *buf), void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); int err; err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; if (recycle_done) recycle_done(_vq); if (vq->packed_ring) virtqueue_reinit_packed(vq); else virtqueue_reinit_split(vq); return virtqueue_enable_after_reset(_vq); } EXPORT_SYMBOL_GPL(virtqueue_reset); struct virtqueue *vring_new_virtqueue(unsigned int index, unsigned int num, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, bool context, void *pages, bool (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), const char *name) { struct vring_virtqueue_split vring_split = {}; if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) { struct vring_virtqueue_packed vring_packed = {}; vring_packed.vring.num = num; vring_packed.vring.desc = pages; return __vring_new_virtqueue_packed(index, &vring_packed, vdev, weak_barriers, context, notify, callback, name, vdev->dev.parent); } vring_init(&vring_split.vring, num, pages, vring_align); return __vring_new_virtqueue_split(index, &vring_split, vdev, weak_barriers, context, notify, callback, name, vdev->dev.parent); } EXPORT_SYMBOL_GPL(vring_new_virtqueue); static void vring_free(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); if (vq->we_own_ring) { if (vq->packed_ring) { vring_free_queue(vq->vq.vdev, vq->packed.ring_size_in_bytes, vq->packed.vring.desc, vq->packed.ring_dma_addr, vring_dma_dev(vq)); vring_free_queue(vq->vq.vdev, vq->packed.event_size_in_bytes, vq->packed.vring.driver, vq->packed.driver_event_dma_addr, vring_dma_dev(vq)); vring_free_queue(vq->vq.vdev, vq->packed.event_size_in_bytes, vq->packed.vring.device, vq->packed.device_event_dma_addr, vring_dma_dev(vq)); kfree(vq->packed.desc_state); kfree(vq->packed.desc_extra); } else { vring_free_queue(vq->vq.vdev, vq->split.queue_size_in_bytes, vq->split.vring.desc, vq->split.queue_dma_addr, vring_dma_dev(vq)); } } if (!vq->packed_ring) { kfree(vq->split.desc_state); kfree(vq->split.desc_extra); } } void vring_del_virtqueue(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); spin_lock(&vq->vq.vdev->vqs_list_lock); list_del(&_vq->list); spin_unlock(&vq->vq.vdev->vqs_list_lock); vring_free(_vq); kfree(vq); } EXPORT_SYMBOL_GPL(vring_del_virtqueue); u32 vring_notification_data(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); u16 next; if (vq->packed_ring) next = (vq->packed.next_avail_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR))) | vq->packed.avail_wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR; else next = vq->split.avail_idx_shadow; return next << 16 | _vq->index; } EXPORT_SYMBOL_GPL(vring_notification_data); /* Manipulates transport-specific feature bits. */ void vring_transport_features(struct virtio_device *vdev) { unsigned int i; for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) { switch (i) { case VIRTIO_RING_F_INDIRECT_DESC: break; case VIRTIO_RING_F_EVENT_IDX: break; case VIRTIO_F_VERSION_1: break; case VIRTIO_F_ACCESS_PLATFORM: break; case VIRTIO_F_RING_PACKED: break; case VIRTIO_F_ORDER_PLATFORM: break; case VIRTIO_F_NOTIFICATION_DATA: break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); } } } EXPORT_SYMBOL_GPL(vring_transport_features); /** * virtqueue_get_vring_size - return the size of the virtqueue's vring * @_vq: the struct virtqueue containing the vring of interest. * * Returns the size of the vring. This is mainly used for boasting to * userspace. Unlike other operations, this need not be serialized. */ unsigned int virtqueue_get_vring_size(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num; } EXPORT_SYMBOL_GPL(virtqueue_get_vring_size); /* * This function should only be called by the core, not directly by the driver. */ void __virtqueue_break(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, true); } EXPORT_SYMBOL_GPL(__virtqueue_break); /* * This function should only be called by the core, not directly by the driver. */ void __virtqueue_unbreak(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, false); } EXPORT_SYMBOL_GPL(__virtqueue_unbreak); bool virtqueue_is_broken(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); return READ_ONCE(vq->broken); } EXPORT_SYMBOL_GPL(virtqueue_is_broken); /* * This should prevent the device from being used, allowing drivers to * recover. You may need to grab appropriate locks to flush. */ void virtio_break_device(struct virtio_device *dev) { struct virtqueue *_vq; spin_lock(&dev->vqs_list_lock); list_for_each_entry(_vq, &dev->vqs, list) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, true); } spin_unlock(&dev->vqs_list_lock); } EXPORT_SYMBOL_GPL(virtio_break_device); /* * This should allow the device to be used by the driver. You may * need to grab appropriate locks to flush the write to * vq->broken. This should only be used in some specific case e.g * (probing and restoring). This function should only be called by the * core, not directly by the driver. */ void __virtio_unbreak_device(struct virtio_device *dev) { struct virtqueue *_vq; spin_lock(&dev->vqs_list_lock); list_for_each_entry(_vq, &dev->vqs, list) { struct vring_virtqueue *vq = to_vvq(_vq); /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ WRITE_ONCE(vq->broken, false); } spin_unlock(&dev->vqs_list_lock); } EXPORT_SYMBOL_GPL(__virtio_unbreak_device); dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); if (vq->packed_ring) return vq->packed.ring_dma_addr; return vq->split.queue_dma_addr; } EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr); dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); if (vq->packed_ring) return vq->packed.driver_event_dma_addr; return vq->split.queue_dma_addr + ((char *)vq->split.vring.avail - (char *)vq->split.vring.desc); } EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr); dma_addr_t virtqueue_get_used_addr(const struct virtqueue *_vq) { const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); if (vq->packed_ring) return vq->packed.device_event_dma_addr; return vq->split.queue_dma_addr + ((char *)vq->split.vring.used - (char *)vq->split.vring.desc); } EXPORT_SYMBOL_GPL(virtqueue_get_used_addr); /* Only available for split ring */ const struct vring *virtqueue_get_vring(const struct virtqueue *vq) { return &to_vvq(vq)->split.vring; } EXPORT_SYMBOL_GPL(virtqueue_get_vring); /** * virtqueue_dma_map_single_attrs - map DMA for _vq * @_vq: the struct virtqueue we're talking about. * @ptr: the pointer of the buffer to do dma * @size: the size of the buffer to do dma * @dir: DMA direction * @attrs: DMA Attrs * * The caller calls this to do dma mapping in advance. The DMA address can be * passed to this _vq when it is in pre-mapped mode. * * return DMA address. Caller should check that by virtqueue_dma_mapping_error(). */ dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) { kmsan_handle_dma(virt_to_page(ptr), offset_in_page(ptr), size, dir); return (dma_addr_t)virt_to_phys(ptr); } return dma_map_single_attrs(vring_dma_dev(vq), ptr, size, dir, attrs); } EXPORT_SYMBOL_GPL(virtqueue_dma_map_single_attrs); /** * virtqueue_dma_unmap_single_attrs - unmap DMA for _vq * @_vq: the struct virtqueue we're talking about. * @addr: the dma address to unmap * @size: the size of the buffer * @dir: DMA direction * @attrs: DMA Attrs * * Unmap the address that is mapped by the virtqueue_dma_map_* APIs. * */ void virtqueue_dma_unmap_single_attrs(struct virtqueue *_vq, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) return; dma_unmap_single_attrs(vring_dma_dev(vq), addr, size, dir, attrs); } EXPORT_SYMBOL_GPL(virtqueue_dma_unmap_single_attrs); /** * virtqueue_dma_mapping_error - check dma address * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * * Returns 0 means dma valid. Other means invalid dma address. */ int virtqueue_dma_mapping_error(struct virtqueue *_vq, dma_addr_t addr) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) return 0; return dma_mapping_error(vring_dma_dev(vq), addr); } EXPORT_SYMBOL_GPL(virtqueue_dma_mapping_error); /** * virtqueue_dma_need_sync - check a dma address needs sync * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * * Check if the dma address mapped by the virtqueue_dma_map_* APIs needs to be * synchronized * * return bool */ bool virtqueue_dma_need_sync(struct virtqueue *_vq, dma_addr_t addr) { struct vring_virtqueue *vq = to_vvq(_vq); if (!vq->use_dma_api) return false; return dma_need_sync(vring_dma_dev(vq), addr); } EXPORT_SYMBOL_GPL(virtqueue_dma_need_sync); /** * virtqueue_dma_sync_single_range_for_cpu - dma sync for cpu * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * @offset: DMA address offset * @size: buf size for sync * @dir: DMA direction * * Before calling this function, use virtqueue_dma_need_sync() to confirm that * the DMA address really needs to be synchronized * */ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir) { struct vring_virtqueue *vq = to_vvq(_vq); struct device *dev = vring_dma_dev(vq); if (!vq->use_dma_api) return; dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu); /** * virtqueue_dma_sync_single_range_for_device - dma sync for device * @_vq: the struct virtqueue we're talking about. * @addr: DMA address * @offset: DMA address offset * @size: buf size for sync * @dir: DMA direction * * Before calling this function, use virtqueue_dma_need_sync() to confirm that * the DMA address really needs to be synchronized */ void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir) { struct vring_virtqueue *vq = to_vvq(_vq); struct device *dev = vring_dma_dev(vq); if (!vq->use_dma_api) return; dma_sync_single_range_for_device(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device); MODULE_DESCRIPTION("Virtio ring implementation"); MODULE_LICENSE("GPL"); |
| 4 4 4 3 74 12 59 42 5 53 1 9 3 1 2 15 1 15 2 231 26 88 67 67 67 67 67 67 67 67 67 67 67 67 67 6 3 10 9 4 17 12 12 3 8 10 1 3 5 4 1 1 1 1 5 1 6 174 6 22 5 144 1 4 5 5 5 4 5 4 1 1 1 1 1 1 1 1 1 1 48 48 31 31 39 39 1 2 2 36 4 31 31 14 26 2 31 35 35 22 11 25 9 27 17 2 2 6 6 6 6 1 9 8 9 9 9 9 27 8 9 9 9 9 9 9 9 9 9 9 9 9 9 9 1 1 1 7 2 4 4 4 39 39 39 125 125 38 39 87 2 54 9 48 31 32 1 8 8 8 41 40 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Wireless utility functions * * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH * Copyright (C) 2018-2023, 2025 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> #include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" const struct ieee80211_rate * ieee80211_get_response_rate(struct ieee80211_supported_band *sband, u32 basic_rates, int bitrate) { struct ieee80211_rate *result = &sband->bitrates[0]; int i; for (i = 0; i < sband->n_bitrates; i++) { if (!(basic_rates & BIT(i))) continue; if (sband->bitrates[i].bitrate > bitrate) continue; result = &sband->bitrates[i]; } return result; } EXPORT_SYMBOL(ieee80211_get_response_rate); u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband) { struct ieee80211_rate *bitrates; u32 mandatory_rates = 0; enum ieee80211_rate_flags mandatory_flag; int i; if (WARN_ON(!sband)) return 1; if (sband->band == NL80211_BAND_2GHZ) mandatory_flag = IEEE80211_RATE_MANDATORY_B; else mandatory_flag = IEEE80211_RATE_MANDATORY_A; bitrates = sband->bitrates; for (i = 0; i < sband->n_bitrates; i++) if (bitrates[i].flags & mandatory_flag) mandatory_rates |= BIT(i); return mandatory_rates; } EXPORT_SYMBOL(ieee80211_mandatory_rates); u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) { /* see 802.11 17.3.8.3.2 and Annex J * there are overlapping channel numbers in 5GHz and 2GHz bands */ if (chan <= 0) return 0; /* not supported */ switch (band) { case NL80211_BAND_2GHZ: case NL80211_BAND_LC: if (chan == 14) return MHZ_TO_KHZ(2484); else if (chan < 14) return MHZ_TO_KHZ(2407 + chan * 5); break; case NL80211_BAND_5GHZ: if (chan >= 182 && chan <= 196) return MHZ_TO_KHZ(4000 + chan * 5); else return MHZ_TO_KHZ(5000 + chan * 5); break; case NL80211_BAND_6GHZ: /* see 802.11ax D6.1 27.3.23.2 */ if (chan == 2) return MHZ_TO_KHZ(5935); if (chan <= 233) return MHZ_TO_KHZ(5950 + chan * 5); break; case NL80211_BAND_60GHZ: if (chan < 7) return MHZ_TO_KHZ(56160 + chan * 2160); break; case NL80211_BAND_S1GHZ: return 902000 + chan * 500; default: ; } return 0; /* not supported */ } EXPORT_SYMBOL(ieee80211_channel_to_freq_khz); enum nl80211_chan_width ieee80211_s1g_channel_width(const struct ieee80211_channel *chan) { if (WARN_ON(!chan || chan->band != NL80211_BAND_S1GHZ)) return NL80211_CHAN_WIDTH_20_NOHT; /*S1G defines a single allowed channel width per channel. * Extract that width here. */ if (chan->flags & IEEE80211_CHAN_1MHZ) return NL80211_CHAN_WIDTH_1; else if (chan->flags & IEEE80211_CHAN_2MHZ) return NL80211_CHAN_WIDTH_2; else if (chan->flags & IEEE80211_CHAN_4MHZ) return NL80211_CHAN_WIDTH_4; else if (chan->flags & IEEE80211_CHAN_8MHZ) return NL80211_CHAN_WIDTH_8; else if (chan->flags & IEEE80211_CHAN_16MHZ) return NL80211_CHAN_WIDTH_16; pr_err("unknown channel width for channel at %dKHz?\n", ieee80211_channel_to_khz(chan)); return NL80211_CHAN_WIDTH_1; } EXPORT_SYMBOL(ieee80211_s1g_channel_width); int ieee80211_freq_khz_to_channel(u32 freq) { /* TODO: just handle MHz for now */ freq = KHZ_TO_MHZ(freq); /* see 802.11 17.3.8.3.2 and Annex J */ if (freq == 2484) return 14; else if (freq < 2484) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; else if (freq < 5925) return (freq - 5000) / 5; else if (freq == 5935) return 2; else if (freq <= 45000) /* DMG band lower limit */ /* see 802.11ax D6.1 27.3.22.2 */ return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else return 0; } EXPORT_SYMBOL(ieee80211_freq_khz_to_channel); struct ieee80211_channel *ieee80211_get_channel_khz(struct wiphy *wiphy, u32 freq) { enum nl80211_band band; struct ieee80211_supported_band *sband; int i; for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels; i++) { struct ieee80211_channel *chan = &sband->channels[i]; if (ieee80211_channel_to_khz(chan) == freq) return chan; } } return NULL; } EXPORT_SYMBOL(ieee80211_get_channel_khz); static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) { int i, want; switch (sband->band) { case NL80211_BAND_5GHZ: case NL80211_BAND_6GHZ: want = 3; for (i = 0; i < sband->n_bitrates; i++) { if (sband->bitrates[i].bitrate == 60 || sband->bitrates[i].bitrate == 120 || sband->bitrates[i].bitrate == 240) { sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_A; want--; } } WARN_ON(want); break; case NL80211_BAND_2GHZ: case NL80211_BAND_LC: want = 7; for (i = 0; i < sband->n_bitrates; i++) { switch (sband->bitrates[i].bitrate) { case 10: case 20: case 55: case 110: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; want--; break; case 60: case 120: case 240: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; fallthrough; default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; break; } } WARN_ON(want != 0 && want != 3); break; case NL80211_BAND_60GHZ: /* check for mandatory HT MCS 1..4 */ WARN_ON(!sband->ht_cap.ht_supported); WARN_ON((sband->ht_cap.mcs.rx_mask[0] & 0x1e) != 0x1e); break; case NL80211_BAND_S1GHZ: /* Figure 9-589bd: 3 means unsupported, so != 3 means at least * mandatory is ok. */ WARN_ON((sband->s1g_cap.nss_mcs[0] & 0x3) == 0x3); break; case NUM_NL80211_BANDS: default: WARN_ON(1); break; } } void ieee80211_set_bitrate_flags(struct wiphy *wiphy) { enum nl80211_band band; for (band = 0; band < NUM_NL80211_BANDS; band++) if (wiphy->bands[band]) set_mandatory_flags_band(wiphy->bands[band]); } bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher) { int i; for (i = 0; i < wiphy->n_cipher_suites; i++) if (cipher == wiphy->cipher_suites[i]) return true; return false; } static bool cfg80211_igtk_cipher_supported(struct cfg80211_registered_device *rdev) { struct wiphy *wiphy = &rdev->wiphy; int i; for (i = 0; i < wiphy->n_cipher_suites; i++) { switch (wiphy->cipher_suites[i]) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: return true; } } return false; } bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, int key_idx, bool pairwise) { int max_key_idx; if (pairwise) max_key_idx = 3; else if (wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; else if (cfg80211_igtk_cipher_supported(rdev)) max_key_idx = 5; else max_key_idx = 3; if (key_idx < 0 || key_idx > max_key_idx) return false; return true; } int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { if (!cfg80211_valid_key_idx(rdev, key_idx, pairwise)) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) return -EINVAL; if (pairwise && !mac_addr) return -EINVAL; switch (params->cipher) { case WLAN_CIPHER_SUITE_TKIP: /* Extended Key ID can only be used with CCMP/GCMP ciphers */ if ((pairwise && key_idx) || params->mode != NL80211_KEY_RX_TX) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: /* IEEE802.11-2016 allows only 0 and - when supporting * Extended Key ID - 1 as index for pairwise keys. * @NL80211_KEY_NO_TX is only allowed for pairwise keys when * the driver supports Extended Key ID. * @NL80211_KEY_SET_TX can't be set when installing and * validating a key. */ if ((params->mode == NL80211_KEY_NO_TX && !pairwise) || params->mode == NL80211_KEY_SET_TX) return -EINVAL; if (wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) { if (pairwise && (key_idx < 0 || key_idx > 1)) return -EINVAL; } else if (pairwise && key_idx) { return -EINVAL; } break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: /* Disallow BIP (group-only) cipher as pairwise cipher */ if (pairwise) return -EINVAL; if (key_idx < 4) return -EINVAL; break; case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: if (key_idx > 3) return -EINVAL; break; default: break; } switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: if (params->key_len != WLAN_KEY_LEN_WEP40) return -EINVAL; break; case WLAN_CIPHER_SUITE_TKIP: if (params->key_len != WLAN_KEY_LEN_TKIP) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: if (params->key_len != WLAN_KEY_LEN_CCMP) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP_256: if (params->key_len != WLAN_KEY_LEN_CCMP_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_GCMP: if (params->key_len != WLAN_KEY_LEN_GCMP) return -EINVAL; break; case WLAN_CIPHER_SUITE_GCMP_256: if (params->key_len != WLAN_KEY_LEN_GCMP_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_WEP104: if (params->key_len != WLAN_KEY_LEN_WEP104) return -EINVAL; break; case WLAN_CIPHER_SUITE_AES_CMAC: if (params->key_len != WLAN_KEY_LEN_AES_CMAC) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (params->key_len != WLAN_KEY_LEN_BIP_CMAC_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_128) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_256) return -EINVAL; break; default: /* * We don't know anything about this algorithm, * allow using it -- but the driver must check * all parameters! We still check below whether * or not the driver supports this algorithm, * of course. */ break; } if (params->seq) { switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: /* These ciphers do not use key sequence */ return -EINVAL; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->seq_len != 6) return -EINVAL; break; } } if (!cfg80211_supported_cipher_suite(&rdev->wiphy, params->cipher)) return -EINVAL; return 0; } unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc) { unsigned int hdrlen = 24; if (ieee80211_is_ext(fc)) { hdrlen = 4; goto out; } if (ieee80211_is_data(fc)) { if (ieee80211_has_a4(fc)) hdrlen = 30; if (ieee80211_is_data_qos(fc)) { hdrlen += IEEE80211_QOS_CTL_LEN; if (ieee80211_has_order(fc)) hdrlen += IEEE80211_HT_CTL_LEN; } goto out; } if (ieee80211_is_mgmt(fc)) { if (ieee80211_has_order(fc)) hdrlen += IEEE80211_HT_CTL_LEN; goto out; } if (ieee80211_is_ctl(fc)) { /* * ACK and CTS are 10 bytes, all others 16. To see how * to get this condition consider * subtype mask: 0b0000000011110000 (0x00F0) * ACK subtype: 0b0000000011010000 (0x00D0) * CTS subtype: 0b0000000011000000 (0x00C0) * bits that matter: ^^^ (0x00E0) * value of those: 0b0000000011000000 (0x00C0) */ if ((fc & cpu_to_le16(0x00E0)) == cpu_to_le16(0x00C0)) hdrlen = 10; else hdrlen = 16; } out: return hdrlen; } EXPORT_SYMBOL(ieee80211_hdrlen); unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) { const struct ieee80211_hdr *hdr = (const struct ieee80211_hdr *)skb->data; unsigned int hdrlen; if (unlikely(skb->len < 10)) return 0; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (unlikely(hdrlen > skb->len)) return 0; return hdrlen; } EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); static unsigned int __ieee80211_get_mesh_hdrlen(u8 flags) { int ae = flags & MESH_FLAGS_AE; /* 802.11-2012, 8.2.4.7.3 */ switch (ae) { default: case 0: return 6; case MESH_FLAGS_AE_A4: return 12; case MESH_FLAGS_AE_A5_A6: return 18; } } unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) { return __ieee80211_get_mesh_hdrlen(meshhdr->flags); } EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); bool ieee80211_get_8023_tunnel_proto(const void *hdr, __be16 *proto) { const __be16 *hdr_proto = hdr + ETH_ALEN; if (!(ether_addr_equal(hdr, rfc1042_header) && *hdr_proto != htons(ETH_P_AARP) && *hdr_proto != htons(ETH_P_IPX)) && !ether_addr_equal(hdr, bridge_tunnel_header)) return false; *proto = *hdr_proto; return true; } EXPORT_SYMBOL(ieee80211_get_8023_tunnel_proto); int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb) { const void *mesh_addr; struct { struct ethhdr eth; u8 flags; } payload; int hdrlen; int ret; ret = skb_copy_bits(skb, 0, &payload, sizeof(payload)); if (ret) return ret; hdrlen = sizeof(payload.eth) + __ieee80211_get_mesh_hdrlen(payload.flags); if (likely(pskb_may_pull(skb, hdrlen + 8) && ieee80211_get_8023_tunnel_proto(skb->data + hdrlen, &payload.eth.h_proto))) hdrlen += ETH_ALEN + 2; else if (!pskb_may_pull(skb, hdrlen)) return -EINVAL; else payload.eth.h_proto = htons(skb->len - hdrlen); mesh_addr = skb->data + sizeof(payload.eth) + ETH_ALEN; switch (payload.flags & MESH_FLAGS_AE) { case MESH_FLAGS_AE_A4: memcpy(&payload.eth.h_source, mesh_addr, ETH_ALEN); break; case MESH_FLAGS_AE_A5_A6: memcpy(&payload.eth, mesh_addr, 2 * ETH_ALEN); break; default: break; } pskb_pull(skb, hdrlen - sizeof(payload.eth)); memcpy(skb->data, &payload.eth, sizeof(payload.eth)); return 0; } EXPORT_SYMBOL(ieee80211_strip_8023_mesh_hdr); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, u8 data_offset, bool is_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { u8 hdr[ETH_ALEN] __aligned(2); __be16 proto; } payload; struct ethhdr tmp; u16 hdrlen; if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return -1; hdrlen = ieee80211_hdrlen(hdr->frame_control) + data_offset; if (skb->len < hdrlen) return -1; /* convert IEEE 802.11 header + possible LLC headers into Ethernet * header * IEEE 802.11 address fields: * ToDS FromDS Addr1 Addr2 Addr3 Addr4 * 0 0 DA SA BSSID n/a * 0 1 DA BSSID SA n/a * 1 0 BSSID SA DA n/a * 1 1 RA TA DA SA */ memcpy(tmp.h_dest, ieee80211_get_DA(hdr), ETH_ALEN); memcpy(tmp.h_source, ieee80211_get_SA(hdr), ETH_ALEN); switch (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) { case cpu_to_le16(IEEE80211_FCTL_TODS): if (unlikely(iftype != NL80211_IFTYPE_AP && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_P2P_GO)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_STATION)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_FROMDS): if ((iftype != NL80211_IFTYPE_STATION && iftype != NL80211_IFTYPE_P2P_CLIENT && iftype != NL80211_IFTYPE_MESH_POINT) || (is_multicast_ether_addr(tmp.h_dest) && ether_addr_equal(tmp.h_source, addr))) return -1; break; case cpu_to_le16(0): if (iftype != NL80211_IFTYPE_ADHOC && iftype != NL80211_IFTYPE_STATION && iftype != NL80211_IFTYPE_OCB) return -1; break; } if (likely(!is_amsdu && iftype != NL80211_IFTYPE_MESH_POINT && skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)) == 0 && ieee80211_get_8023_tunnel_proto(&payload, &tmp.h_proto))) { /* remove RFC1042 or Bridge-Tunnel encapsulation */ hdrlen += ETH_ALEN + 2; skb_postpull_rcsum(skb, &payload, ETH_ALEN + 2); } else { tmp.h_proto = htons(skb->len - hdrlen); } pskb_pull(skb, hdrlen); if (!ehdr) ehdr = skb_push(skb, sizeof(struct ethhdr)); memcpy(ehdr, &tmp, sizeof(tmp)); return 0; } EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr); static void __frame_add_frag(struct sk_buff *skb, struct page *page, void *ptr, int len, int size) { struct skb_shared_info *sh = skb_shinfo(skb); int page_offset; get_page(page); page_offset = ptr - page_address(page); skb_add_rx_frag(skb, sh->nr_frags, page, page_offset, len, size); } static void __ieee80211_amsdu_copy_frag(struct sk_buff *skb, struct sk_buff *frame, int offset, int len) { struct skb_shared_info *sh = skb_shinfo(skb); const skb_frag_t *frag = &sh->frags[0]; struct page *frag_page; void *frag_ptr; int frag_len, frag_size; int head_size = skb->len - skb->data_len; int cur_len; frag_page = virt_to_head_page(skb->head); frag_ptr = skb->data; frag_size = head_size; while (offset >= frag_size) { offset -= frag_size; frag_page = skb_frag_page(frag); frag_ptr = skb_frag_address(frag); frag_size = skb_frag_size(frag); frag++; } frag_ptr += offset; frag_len = frag_size - offset; cur_len = min(len, frag_len); __frame_add_frag(frame, frag_page, frag_ptr, cur_len, frag_size); len -= cur_len; while (len > 0) { frag_len = skb_frag_size(frag); cur_len = min(len, frag_len); __frame_add_frag(frame, skb_frag_page(frag), skb_frag_address(frag), cur_len, frag_len); len -= cur_len; frag++; } } static struct sk_buff * __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen, int offset, int len, bool reuse_frag, int min_len) { struct sk_buff *frame; int cur_len = len; if (skb->len - offset < len) return NULL; /* * When reusing fragments, copy some data to the head to simplify * ethernet header handling and speed up protocol header processing * in the stack later. */ if (reuse_frag) cur_len = min_t(int, len, min_len); /* * Allocate and reserve two bytes more for payload * alignment since sizeof(struct ethhdr) is 14. */ frame = dev_alloc_skb(hlen + sizeof(struct ethhdr) + 2 + cur_len); if (!frame) return NULL; frame->priority = skb->priority; skb_reserve(frame, hlen + sizeof(struct ethhdr) + 2); skb_copy_bits(skb, offset, skb_put(frame, cur_len), cur_len); len -= cur_len; if (!len) return frame; offset += cur_len; __ieee80211_amsdu_copy_frag(skb, frame, offset, len); return frame; } static u16 ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type) { __le16 *field_le = field; __be16 *field_be = field; u16 len; if (hdr_type >= 2) len = le16_to_cpu(*field_le); else len = be16_to_cpu(*field_be); if (hdr_type) len += __ieee80211_get_mesh_hdrlen(mesh_flags); return len; } bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) { int offset = 0, subframe_len, padding; for (offset = 0; offset < skb->len; offset += subframe_len + padding) { int remaining = skb->len - offset; struct { __be16 len; u8 mesh_flags; } hdr; u16 len; if (sizeof(hdr) > remaining) return false; if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0) return false; len = ieee80211_amsdu_subframe_length(&hdr.len, hdr.mesh_flags, mesh_hdr); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; if (subframe_len > remaining) return false; } return true; } EXPORT_SYMBOL(ieee80211_is_valid_amsdu); void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, const u8 *addr, enum nl80211_iftype iftype, const unsigned int extra_headroom, const u8 *check_da, const u8 *check_sa, u8 mesh_control) { unsigned int hlen = ALIGN(extra_headroom, 4); struct sk_buff *frame = NULL; int offset = 0; struct { struct ethhdr eth; uint8_t flags; } hdr; bool reuse_frag = skb->head_frag && !skb_has_frag_list(skb); bool reuse_skb = false; bool last = false; int copy_len = sizeof(hdr.eth); if (iftype == NL80211_IFTYPE_MESH_POINT) copy_len = sizeof(hdr); while (!last) { int remaining = skb->len - offset; unsigned int subframe_len; int len, mesh_len = 0; u8 padding; if (copy_len > remaining) goto purge; skb_copy_bits(skb, offset, &hdr, copy_len); if (iftype == NL80211_IFTYPE_MESH_POINT) mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags); len = ieee80211_amsdu_subframe_length(&hdr.eth.h_proto, hdr.flags, mesh_control); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; /* the last MSDU has no padding */ if (subframe_len > remaining) goto purge; /* mitigate A-MSDU aggregation injection attacks */ if (ether_addr_equal(hdr.eth.h_dest, rfc1042_header)) goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; /* FIXME: should we really accept multicast DA? */ if ((check_da && !is_multicast_ether_addr(hdr.eth.h_dest) && !ether_addr_equal(check_da, hdr.eth.h_dest)) || (check_sa && !ether_addr_equal(check_sa, hdr.eth.h_source))) { offset += len + padding; continue; } /* reuse skb for the last subframe */ if (!skb_is_nonlinear(skb) && !reuse_frag && last) { skb_pull(skb, offset); frame = skb; reuse_skb = true; } else { frame = __ieee80211_amsdu_copy(skb, hlen, offset, len, reuse_frag, 32 + mesh_len); if (!frame) goto purge; offset += len + padding; } skb_reset_network_header(frame); frame->dev = skb->dev; frame->priority = skb->priority; if (likely(iftype != NL80211_IFTYPE_MESH_POINT && ieee80211_get_8023_tunnel_proto(frame->data, &hdr.eth.h_proto))) skb_pull(frame, ETH_ALEN + 2); memcpy(skb_push(frame, sizeof(hdr.eth)), &hdr.eth, sizeof(hdr.eth)); __skb_queue_tail(list, frame); } if (!reuse_skb) dev_kfree_skb(skb); return; purge: __skb_queue_purge(list); dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_amsdu_to_8023s); /* Given a data frame determine the 802.1p/1d tag to use. */ unsigned int cfg80211_classify8021d(struct sk_buff *skb, struct cfg80211_qos_map *qos_map) { unsigned int dscp; unsigned char vlan_priority; unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ if (skb->priority >= 256 && skb->priority <= 263) { ret = skb->priority - 256; goto out; } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; if (vlan_priority > 0) { ret = vlan_priority; goto out; } } switch (skb->protocol) { case htons(ETH_P_IP): dscp = ipv4_get_dsfield(ip_hdr(skb)) & 0xfc; break; case htons(ETH_P_IPV6): dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc; break; case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): { struct mpls_label mpls_tmp, *mpls; mpls = skb_header_pointer(skb, sizeof(struct ethhdr), sizeof(*mpls), &mpls_tmp); if (!mpls) return 0; ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ return 7; default: return 0; } if (qos_map) { unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { if (tmp_dscp == qos_map->dscp_exception[i].dscp) { ret = qos_map->dscp_exception[i].up; goto out; } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && tmp_dscp <= qos_map->up[i].high) { ret = i; goto out; } } } /* The default mapping as defined Section 2.3 in RFC8325: The three * Most Significant Bits (MSBs) of the DSCP are used as the * corresponding L2 markings. */ ret = dscp >> 5; /* Handle specific DSCP values for which the default mapping (as * described above) doesn't adhere to the intended usage of the DSCP * value. See section 4 in RFC8325. Specifically, for the following * Diffserv Service Classes no update is needed: * - Standard: DF * - Low Priority Data: CS1 * - Multimedia Conferencing: AF41, AF42, AF43 * - Network Control Traffic: CS7 * - Real-Time Interactive: CS4 * - Signaling: CS5 */ switch (dscp >> 2) { case 10: case 12: case 14: /* High throughput data: AF11, AF12, AF13 */ ret = 0; break; case 16: /* Operations, Administration, and Maintenance and Provisioning: * CS2 */ ret = 0; break; case 18: case 20: case 22: /* Low latency data: AF21, AF22, AF23 */ ret = 3; break; case 24: /* Broadcasting video: CS3 */ ret = 4; break; case 26: case 28: case 30: /* Multimedia Streaming: AF31, AF32, AF33 */ ret = 4; break; case 44: /* Voice Admit: VA */ ret = 6; break; case 46: /* Telephony traffic: EF */ ret = 6; break; case 48: /* Network Control Traffic: CS6 */ ret = 7; break; } out: return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); const struct element *ieee80211_bss_get_elem(struct cfg80211_bss *bss, u8 id) { const struct cfg80211_bss_ies *ies; ies = rcu_dereference(bss->ies); if (!ies) return NULL; return cfg80211_find_elem(id, ies->data, ies->len); } EXPORT_SYMBOL(ieee80211_bss_get_elem); void cfg80211_upload_connect_keys(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct net_device *dev = wdev->netdev; int i; if (!wdev->connect_keys) return; for (i = 0; i < 4; i++) { if (!wdev->connect_keys->params[i].cipher) continue; if (rdev_add_key(rdev, dev, -1, i, false, NULL, &wdev->connect_keys->params[i])) { netdev_err(dev, "failed to set key %d\n", i); continue; } if (wdev->connect_keys->def == i && rdev_set_default_key(rdev, dev, -1, i, true, true)) { netdev_err(dev, "failed to set defkey %d\n", i); continue; } } kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; } void cfg80211_process_wdev_events(struct wireless_dev *wdev) { struct cfg80211_event *ev; unsigned long flags; spin_lock_irqsave(&wdev->event_lock, flags); while (!list_empty(&wdev->event_list)) { ev = list_first_entry(&wdev->event_list, struct cfg80211_event, list); list_del(&ev->list); spin_unlock_irqrestore(&wdev->event_lock, flags); switch (ev->type) { case EVENT_CONNECT_RESULT: __cfg80211_connect_result( wdev->netdev, &ev->cr, ev->cr.status == WLAN_STATUS_SUCCESS); break; case EVENT_ROAMED: __cfg80211_roamed(wdev, &ev->rm); break; case EVENT_DISCONNECTED: __cfg80211_disconnected(wdev->netdev, ev->dc.ie, ev->dc.ie_len, ev->dc.reason, !ev->dc.locally_generated); break; case EVENT_IBSS_JOINED: __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, ev->ij.channel); break; case EVENT_STOPPED: cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; case EVENT_PORT_AUTHORIZED: __cfg80211_port_authorized(wdev, ev->pa.peer_addr, ev->pa.td_bitmap, ev->pa.td_bitmap_len); break; } kfree(ev); spin_lock_irqsave(&wdev->event_lock, flags); } spin_unlock_irqrestore(&wdev->event_lock, flags); } void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; lockdep_assert_held(&rdev->wiphy.mtx); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_process_wdev_events(wdev); } int cfg80211_change_iface(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype ntype, struct vif_params *params) { int err; enum nl80211_iftype otype = dev->ieee80211_ptr->iftype; lockdep_assert_held(&rdev->wiphy.mtx); /* don't support changing VLANs, you just re-create them */ if (otype == NL80211_IFTYPE_AP_VLAN) return -EOPNOTSUPP; /* cannot change into P2P device or NAN */ if (ntype == NL80211_IFTYPE_P2P_DEVICE || ntype == NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!rdev->ops->change_virtual_intf || !(rdev->wiphy.interface_modes & (1 << ntype))) return -EOPNOTSUPP; if (ntype != otype) { /* if it's part of a bridge, reject changing type to station/ibss */ if (netif_is_bridge_port(dev) && (ntype == NL80211_IFTYPE_ADHOC || ntype == NL80211_IFTYPE_STATION || ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; dev->ieee80211_ptr->use_4addr = false; rdev_set_qos_map(rdev, dev, NULL); switch (otype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev, -1, true); break; case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, false); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, true); break; case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; case NL80211_IFTYPE_OCB: cfg80211_leave_ocb(rdev, dev); break; default: break; } cfg80211_process_rdev_events(rdev); cfg80211_mlme_purge_registrations(dev->ieee80211_ptr); memset(&dev->ieee80211_ptr->u, 0, sizeof(dev->ieee80211_ptr->u)); memset(&dev->ieee80211_ptr->links, 0, sizeof(dev->ieee80211_ptr->links)); } err = rdev_change_virtual_intf(rdev, dev, ntype, params); WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype); if (!err && params && params->use_4addr != -1) dev->ieee80211_ptr->use_4addr = params->use_4addr; if (!err) { dev->priv_flags &= ~IFF_DONT_BRIDGE; switch (ntype) { case NL80211_IFTYPE_STATION: if (dev->ieee80211_ptr->use_4addr) break; fallthrough; case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_ADHOC: dev->priv_flags |= IFF_DONT_BRIDGE; break; case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MESH_POINT: /* bridging OK */ break; case NL80211_IFTYPE_MONITOR: /* monitor can't bridge anyway */ break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: /* not happening */ break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_NAN: WARN_ON(1); break; } } if (!err && ntype != otype && netif_running(dev)) { cfg80211_update_iface_num(rdev, ntype, 1); cfg80211_update_iface_num(rdev, otype, -1); } return err; } static u32 cfg80211_calculate_bitrate_ht(struct rate_info *rate) { int modulation, streams, bitrate; /* the formula below does only work for MCS values smaller than 32 */ if (WARN_ON_ONCE(rate->mcs >= 32)) return 0; modulation = rate->mcs & 7; streams = (rate->mcs >> 3) + 1; bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000; if (modulation < 4) bitrate *= (modulation + 1); else if (modulation == 4) bitrate *= (modulation + 2); else bitrate *= (modulation + 3); bitrate *= streams; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; } static u32 cfg80211_calculate_bitrate_dmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { /* control PHY */ [0] = 275, /* SC PHY */ [1] = 3850, [2] = 7700, [3] = 9625, [4] = 11550, [5] = 12512, /* 1251.25 mbps */ [6] = 15400, [7] = 19250, [8] = 23100, [9] = 25025, [10] = 30800, [11] = 38500, [12] = 46200, /* OFDM PHY */ [13] = 6930, [14] = 8662, /* 866.25 mbps */ [15] = 13860, [16] = 17325, [17] = 20790, [18] = 27720, [19] = 34650, [20] = 41580, [21] = 45045, [22] = 51975, [23] = 62370, [24] = 67568, /* 6756.75 mbps */ /* LP-SC PHY */ [25] = 6260, [26] = 8340, [27] = 11120, [28] = 12510, [29] = 16680, [30] = 22240, [31] = 25030, }; if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) return 0; return __mcs2bitrate[rate->mcs]; } static u32 cfg80211_calculate_bitrate_extended_sc_dmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { [6 - 6] = 26950, /* MCS 9.1 : 2695.0 mbps */ [7 - 6] = 50050, /* MCS 12.1 */ [8 - 6] = 53900, [9 - 6] = 57750, [10 - 6] = 63900, [11 - 6] = 75075, [12 - 6] = 80850, }; /* Extended SC MCS not defined for base MCS below 6 or above 12 */ if (WARN_ON_ONCE(rate->mcs < 6 || rate->mcs > 12)) return 0; return __mcs2bitrate[rate->mcs - 6]; } static u32 cfg80211_calculate_bitrate_edmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { /* control PHY */ [0] = 275, /* SC PHY */ [1] = 3850, [2] = 7700, [3] = 9625, [4] = 11550, [5] = 12512, /* 1251.25 mbps */ [6] = 13475, [7] = 15400, [8] = 19250, [9] = 23100, [10] = 25025, [11] = 26950, [12] = 30800, [13] = 38500, [14] = 46200, [15] = 50050, [16] = 53900, [17] = 57750, [18] = 69300, [19] = 75075, [20] = 80850, }; if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) return 0; return __mcs2bitrate[rate->mcs] * rate->n_bonded_ch; } static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) { static const u32 base[4][12] = { { 6500000, 13000000, 19500000, 26000000, 39000000, 52000000, 58500000, 65000000, 78000000, /* not in the spec, but some devices use this: */ 86700000, 97500000, 108300000, }, { 13500000, 27000000, 40500000, 54000000, 81000000, 108000000, 121500000, 135000000, 162000000, 180000000, 202500000, 225000000, }, { 29300000, 58500000, 87800000, 117000000, 175500000, 234000000, 263300000, 292500000, 351000000, 390000000, 438800000, 487500000, }, { 58500000, 117000000, 175500000, 234000000, 351000000, 468000000, 526500000, 585000000, 702000000, 780000000, 877500000, 975000000, }, }; u32 bitrate; int idx; if (rate->mcs > 11) goto warn; switch (rate->bw) { case RATE_INFO_BW_160: idx = 3; break; case RATE_INFO_BW_80: idx = 2; break; case RATE_INFO_BW_40: idx = 1; break; case RATE_INFO_BW_5: case RATE_INFO_BW_10: default: goto warn; case RATE_INFO_BW_20: idx = 0; } bitrate = base[idx][rate->mcs]; bitrate *= rate->nss; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; warn: WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", rate->bw, rate->mcs, rate->nss); return 0; } static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) { #define SCALE 6144 u32 mcs_divisors[14] = { 102399, /* 16.666666... */ 51201, /* 8.333333... */ 34134, /* 5.555555... */ 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ 6828, /* 1.111111... */ 6144, /* 1.000000... */ 5690, /* 0.926106... */ 5120, /* 0.833333... */ }; u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; u32 rates_996[3] = { 480388888, 453700000, 408333333 }; u32 rates_484[3] = { 229411111, 216666666, 195000000 }; u32 rates_242[3] = { 114711111, 108333333, 97500000 }; u32 rates_106[3] = { 40000000, 37777777, 34000000 }; u32 rates_52[3] = { 18820000, 17777777, 16000000 }; u32 rates_26[3] = { 9411111, 8888888, 8000000 }; u64 tmp; u32 result; if (WARN_ON_ONCE(rate->mcs > 13)) return 0; if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2)) return 0; if (WARN_ON_ONCE(rate->he_ru_alloc > NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) return 0; if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; if (rate->bw == RATE_INFO_BW_160 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) result = rates_996[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) result = rates_484[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_20 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242)) result = rates_242[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106) result = rates_106[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52) result = rates_52[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26) result = rates_26[rate->he_gi]; else { WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", rate->bw, rate->he_ru_alloc); return 0; } /* now scale to the appropriate MCS */ tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); result = tmp; /* and take NSS, DCM into account */ result = (result * rate->nss) / 8; if (rate->he_dcm) result /= 2; return result / 10000; } static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) { #define SCALE 6144 static const u32 mcs_divisors[16] = { 102399, /* 16.666666... */ 51201, /* 8.333333... */ 34134, /* 5.555555... */ 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ 6828, /* 1.111111... */ 6144, /* 1.000000... */ 5690, /* 0.926106... */ 5120, /* 0.833333... */ 409600, /* 66.666666... */ 204800, /* 33.333333... */ }; static const u32 rates_996[3] = { 480388888, 453700000, 408333333 }; static const u32 rates_484[3] = { 229411111, 216666666, 195000000 }; static const u32 rates_242[3] = { 114711111, 108333333, 97500000 }; static const u32 rates_106[3] = { 40000000, 37777777, 34000000 }; static const u32 rates_52[3] = { 18820000, 17777777, 16000000 }; static const u32 rates_26[3] = { 9411111, 8888888, 8000000 }; u64 tmp; u32 result; if (WARN_ON_ONCE(rate->mcs > 15)) return 0; if (WARN_ON_ONCE(rate->eht_gi > NL80211_RATE_INFO_EHT_GI_3_2)) return 0; if (WARN_ON_ONCE(rate->eht_ru_alloc > NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) return 0; if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; /* Bandwidth checks for MCS 14 */ if (rate->mcs == 14) { if ((rate->bw != RATE_INFO_BW_EHT_RU && rate->bw != RATE_INFO_BW_80 && rate->bw != RATE_INFO_BW_160 && rate->bw != RATE_INFO_BW_320) || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_996 && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_2x996 && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) { WARN(1, "invalid EHT BW for MCS 14: bw:%d, ru:%d\n", rate->bw, rate->eht_ru_alloc); return 0; } } if (rate->bw == RATE_INFO_BW_320 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) result = 4 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484) result = 3 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996) result = 3 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484) result = 2 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_160 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996)) result = 2 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242) result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484) result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996)) result = rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484P242) result = rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484)) result = rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_20 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_242)) result = rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106P26) result = rates_106[rate->eht_gi] + rates_26[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106) result = rates_106[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52P26) result = rates_52[rate->eht_gi] + rates_26[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52) result = rates_52[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_26) result = rates_26[rate->eht_gi]; else { WARN(1, "invalid EHT MCS: bw:%d, ru:%d\n", rate->bw, rate->eht_ru_alloc); return 0; } /* now scale to the appropriate MCS */ tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); /* and take NSS */ tmp *= rate->nss; do_div(tmp, 8); result = tmp; return result / 10000; } static u32 cfg80211_calculate_bitrate_s1g(struct rate_info *rate) { /* For 1, 2, 4, 8 and 16 MHz channels */ static const u32 base[5][11] = { { 300000, 600000, 900000, 1200000, 1800000, 2400000, 2700000, 3000000, 3600000, 4000000, /* MCS 10 supported in 1 MHz only */ 150000, }, { 650000, 1300000, 1950000, 2600000, 3900000, 5200000, 5850000, 6500000, 7800000, /* MCS 9 not valid */ }, { 1350000, 2700000, 4050000, 5400000, 8100000, 10800000, 12150000, 13500000, 16200000, 18000000, }, { 2925000, 5850000, 8775000, 11700000, 17550000, 23400000, 26325000, 29250000, 35100000, 39000000, }, { 8580000, 11700000, 17550000, 23400000, 35100000, 46800000, 52650000, 58500000, 70200000, 78000000, }, }; u32 bitrate; /* default is 1 MHz index */ int idx = 0; if (rate->mcs >= 11) goto warn; switch (rate->bw) { case RATE_INFO_BW_16: idx = 4; break; case RATE_INFO_BW_8: idx = 3; break; case RATE_INFO_BW_4: idx = 2; break; case RATE_INFO_BW_2: idx = 1; break; case RATE_INFO_BW_1: idx = 0; break; case RATE_INFO_BW_5: case RATE_INFO_BW_10: case RATE_INFO_BW_20: case RATE_INFO_BW_40: case RATE_INFO_BW_80: case RATE_INFO_BW_160: default: goto warn; } bitrate = base[idx][rate->mcs]; bitrate *= rate->nss; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; warn: WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", rate->bw, rate->mcs, rate->nss); return 0; } u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) return cfg80211_calculate_bitrate_ht(rate); if (rate->flags & RATE_INFO_FLAGS_DMG) return cfg80211_calculate_bitrate_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EXTENDED_SC_DMG) return cfg80211_calculate_bitrate_extended_sc_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EDMG) return cfg80211_calculate_bitrate_edmg(rate); if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) return cfg80211_calculate_bitrate_vht(rate); if (rate->flags & RATE_INFO_FLAGS_HE_MCS) return cfg80211_calculate_bitrate_he(rate); if (rate->flags & RATE_INFO_FLAGS_EHT_MCS) return cfg80211_calculate_bitrate_eht(rate); if (rate->flags & RATE_INFO_FLAGS_S1G_MCS) return cfg80211_calculate_bitrate_s1g(rate); return rate->legacy; } EXPORT_SYMBOL(cfg80211_calculate_bitrate); int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, enum ieee80211_p2p_attr_id attr, u8 *buf, unsigned int bufsize) { u8 *out = buf; u16 attr_remaining = 0; bool desired_attr = false; u16 desired_len = 0; while (len > 0) { unsigned int iedatalen; unsigned int copy; const u8 *iedata; if (len < 2) return -EILSEQ; iedatalen = ies[1]; if (iedatalen + 2 > len) return -EILSEQ; if (ies[0] != WLAN_EID_VENDOR_SPECIFIC) goto cont; if (iedatalen < 4) goto cont; iedata = ies + 2; /* check WFA OUI, P2P subtype */ if (iedata[0] != 0x50 || iedata[1] != 0x6f || iedata[2] != 0x9a || iedata[3] != 0x09) goto cont; iedatalen -= 4; iedata += 4; /* check attribute continuation into this IE */ copy = min_t(unsigned int, attr_remaining, iedatalen); if (copy && desired_attr) { desired_len += copy; if (out) { memcpy(out, iedata, min(bufsize, copy)); out += min(bufsize, copy); bufsize -= min(bufsize, copy); } if (copy == attr_remaining) return desired_len; } attr_remaining -= copy; if (attr_remaining) goto cont; iedatalen -= copy; iedata += copy; while (iedatalen > 0) { u16 attr_len; /* P2P attribute ID & size must fit */ if (iedatalen < 3) return -EILSEQ; desired_attr = iedata[0] == attr; attr_len = get_unaligned_le16(iedata + 1); iedatalen -= 3; iedata += 3; copy = min_t(unsigned int, attr_len, iedatalen); if (desired_attr) { desired_len += copy; if (out) { memcpy(out, iedata, min(bufsize, copy)); out += min(bufsize, copy); bufsize -= min(bufsize, copy); } if (copy == attr_len) return desired_len; } iedata += copy; iedatalen -= copy; attr_remaining = attr_len - copy; } cont: len -= ies[1] + 2; ies += ies[1] + 2; } if (attr_remaining && desired_attr) return -EILSEQ; return -ENOENT; } EXPORT_SYMBOL(cfg80211_get_p2p_attr); static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext) { int i; /* Make sure array values are legal */ if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION)) return false; i = 0; while (i < n_ids) { if (ids[i] == WLAN_EID_EXTENSION) { if (id_ext && (ids[i + 1] == id)) return true; i += 2; continue; } if (ids[i] == id && !id_ext) return true; i++; } return false; } static size_t skip_ie(const u8 *ies, size_t ielen, size_t pos) { /* we assume a validly formed IEs buffer */ u8 len = ies[pos + 1]; pos += 2 + len; /* the IE itself must have 255 bytes for fragments to follow */ if (len < 255) return pos; while (pos < ielen && ies[pos] == WLAN_EID_FRAGMENT) { len = ies[pos + 1]; pos += 2 + len; } return pos; } size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, const u8 *after_ric, int n_after_ric, size_t offset) { size_t pos = offset; while (pos < ielen) { u8 ext = 0; if (ies[pos] == WLAN_EID_EXTENSION) ext = 2; if ((pos + ext) >= ielen) break; if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext], ies[pos] == WLAN_EID_EXTENSION)) break; if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { pos = skip_ie(ies, ielen, pos); while (pos < ielen) { if (ies[pos] == WLAN_EID_EXTENSION) ext = 2; else ext = 0; if ((pos + ext) >= ielen) break; if (!ieee80211_id_in_list(after_ric, n_after_ric, ies[pos + ext], ext == 2)) pos = skip_ie(ies, ielen, pos); else break; } } else { pos = skip_ie(ies, ielen, pos); } } return pos; } EXPORT_SYMBOL(ieee80211_ie_split_ric); void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos, u8 frag_id) { unsigned int elem_len; if (!len_pos) return; elem_len = skb->data + skb->len - len_pos - 1; while (elem_len > 255) { /* this one is 255 */ *len_pos = 255; /* remaining data gets smaller */ elem_len -= 255; /* make space for the fragment ID/len in SKB */ skb_put(skb, 2); /* shift back the remaining data to place fragment ID/len */ memmove(len_pos + 255 + 3, len_pos + 255 + 1, elem_len); /* place the fragment ID */ len_pos += 255 + 1; *len_pos = frag_id; /* and point to fragment length to update later */ len_pos++; } *len_pos = elem_len; } EXPORT_SYMBOL(ieee80211_fragment_element); bool ieee80211_operating_class_to_band(u8 operating_class, enum nl80211_band *band) { switch (operating_class) { case 112: case 115 ... 127: case 128 ... 130: *band = NL80211_BAND_5GHZ; return true; case 131 ... 135: case 137: *band = NL80211_BAND_6GHZ; return true; case 81: case 82: case 83: case 84: *band = NL80211_BAND_2GHZ; return true; case 180: *band = NL80211_BAND_60GHZ; return true; } return false; } EXPORT_SYMBOL(ieee80211_operating_class_to_band); bool ieee80211_operating_class_to_chandef(u8 operating_class, struct ieee80211_channel *chan, struct cfg80211_chan_def *chandef) { u32 control_freq, offset = 0; enum nl80211_band band; if (!ieee80211_operating_class_to_band(operating_class, &band) || !chan || band != chan->band) return false; control_freq = chan->center_freq; chandef->chan = chan; if (control_freq >= 5955) offset = control_freq - 5955; else if (control_freq >= 5745) offset = control_freq - 5745; else if (control_freq >= 5180) offset = control_freq - 5180; offset /= 20; switch (operating_class) { case 81: /* 2 GHz band; 20 MHz; channels 1..13 */ case 82: /* 2 GHz band; 20 MHz; channel 14 */ case 115: /* 5 GHz band; 20 MHz; channels 36,40,44,48 */ case 118: /* 5 GHz band; 20 MHz; channels 52,56,60,64 */ case 121: /* 5 GHz band; 20 MHz; channels 100..144 */ case 124: /* 5 GHz band; 20 MHz; channels 149,153,157,161 */ case 125: /* 5 GHz band; 20 MHz; channels 149..177 */ case 131: /* 6 GHz band; 20 MHz; channels 1..233*/ case 136: /* 6 GHz band; 20 MHz; channel 2 */ chandef->center_freq1 = control_freq; chandef->width = NL80211_CHAN_WIDTH_20; return true; case 83: /* 2 GHz band; 40 MHz; channels 1..9 */ case 116: /* 5 GHz band; 40 MHz; channels 36,44 */ case 119: /* 5 GHz band; 40 MHz; channels 52,60 */ case 122: /* 5 GHz band; 40 MHz; channels 100,108,116,124,132,140 */ case 126: /* 5 GHz band; 40 MHz; channels 149,157,165,173 */ chandef->center_freq1 = control_freq + 10; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 84: /* 2 GHz band; 40 MHz; channels 5..13 */ case 117: /* 5 GHz band; 40 MHz; channels 40,48 */ case 120: /* 5 GHz band; 40 MHz; channels 56,64 */ case 123: /* 5 GHz band; 40 MHz; channels 104,112,120,128,136,144 */ case 127: /* 5 GHz band; 40 MHz; channels 153,161,169,177 */ chandef->center_freq1 = control_freq - 10; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 132: /* 6 GHz band; 40 MHz; channels 1,5,..,229*/ chandef->center_freq1 = control_freq + 10 - (offset & 1) * 20; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 128: /* 5 GHz band; 80 MHz; channels 36..64,100..144,149..177 */ case 133: /* 6 GHz band; 80 MHz; channels 1,5,..,229 */ chandef->center_freq1 = control_freq + 30 - (offset & 3) * 20; chandef->width = NL80211_CHAN_WIDTH_80; return true; case 129: /* 5 GHz band; 160 MHz; channels 36..64,100..144,149..177 */ case 134: /* 6 GHz band; 160 MHz; channels 1,5,..,229 */ chandef->center_freq1 = control_freq + 70 - (offset & 7) * 20; chandef->width = NL80211_CHAN_WIDTH_160; return true; case 130: /* 5 GHz band; 80+80 MHz; channels 36..64,100..144,149..177 */ case 135: /* 6 GHz band; 80+80 MHz; channels 1,5,..,229 */ /* The center_freq2 of 80+80 MHz is unknown */ case 137: /* 6 GHz band; 320 MHz; channels 1,5,..,229 */ /* 320-1 or 320-2 channelization is unknown */ default: return false; } } EXPORT_SYMBOL(ieee80211_operating_class_to_chandef); bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { u8 vht_opclass; u32 freq = chandef->center_freq1; if (freq >= 2412 && freq <= 2472) { if (chandef->width > NL80211_CHAN_WIDTH_40) return false; /* 2.407 GHz, channels 1..13 */ if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 83; /* HT40+ */ else *op_class = 84; /* HT40- */ } else { *op_class = 81; } return true; } if (freq == 2484) { /* channel 14 is only for IEEE 802.11b */ if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT) return false; *op_class = 82; /* channel 14 */ return true; } switch (chandef->width) { case NL80211_CHAN_WIDTH_80: vht_opclass = 128; break; case NL80211_CHAN_WIDTH_160: vht_opclass = 129; break; case NL80211_CHAN_WIDTH_80P80: vht_opclass = 130; break; case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_5: return false; /* unsupported for now */ default: vht_opclass = 0; break; } /* 5 GHz, channels 36..48 */ if (freq >= 5180 && freq <= 5240) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 116; else *op_class = 117; } else { *op_class = 115; } return true; } /* 5 GHz, channels 52..64 */ if (freq >= 5260 && freq <= 5320) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 119; else *op_class = 120; } else { *op_class = 118; } return true; } /* 5 GHz, channels 100..144 */ if (freq >= 5500 && freq <= 5720) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 122; else *op_class = 123; } else { *op_class = 121; } return true; } /* 5 GHz, channels 149..169 */ if (freq >= 5745 && freq <= 5845) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 126; else *op_class = 127; } else if (freq <= 5805) { *op_class = 124; } else { *op_class = 125; } return true; } /* 56.16 GHz, channel 1..4 */ if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 6) { if (chandef->width >= NL80211_CHAN_WIDTH_40) return false; *op_class = 180; return true; } /* not supported yet */ return false; } EXPORT_SYMBOL(ieee80211_chandef_to_operating_class); static int cfg80211_wdev_bi(struct wireless_dev *wdev) { switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: WARN_ON(wdev->valid_links); return wdev->links[0].ap.beacon_interval; case NL80211_IFTYPE_MESH_POINT: return wdev->u.mesh.beacon_interval; case NL80211_IFTYPE_ADHOC: return wdev->u.ibss.beacon_interval; default: break; } return 0; } static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, u32 *beacon_int_gcd, bool *beacon_int_different, int radio_idx) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; *beacon_int_gcd = 0; *beacon_int_different = false; rdev = wiphy_to_rdev(wiphy); list_for_each_entry(wdev, &wiphy->wdev_list, list) { int wdev_bi; /* this feature isn't supported with MLO */ if (wdev->valid_links) continue; /* skip wdevs not active on the given wiphy radio */ if (radio_idx >= 0 && !(rdev_get_radio_mask(rdev, wdev->netdev) & BIT(radio_idx))) continue; wdev_bi = cfg80211_wdev_bi(wdev); if (!wdev_bi) continue; if (!*beacon_int_gcd) { *beacon_int_gcd = wdev_bi; continue; } if (wdev_bi == *beacon_int_gcd) continue; *beacon_int_different = true; *beacon_int_gcd = gcd(*beacon_int_gcd, wdev_bi); } if (new_beacon_int && *beacon_int_gcd != new_beacon_int) { if (*beacon_int_gcd) *beacon_int_different = true; *beacon_int_gcd = gcd(*beacon_int_gcd, new_beacon_int); } } int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, u32 beacon_int) { /* * This is just a basic pre-condition check; if interface combinations * are possible the driver must already be checking those with a call * to cfg80211_check_combinations(), in which case we'll validate more * through the cfg80211_calculate_bi_data() call and code in * cfg80211_iter_combinations(). */ if (beacon_int < 10 || beacon_int > 10000) return -EINVAL; return 0; } int cfg80211_iter_combinations(struct wiphy *wiphy, struct iface_combination_params *params, void (*iter)(const struct ieee80211_iface_combination *c, void *data), void *data) { const struct wiphy_radio *radio = NULL; const struct ieee80211_iface_combination *c, *cs; const struct ieee80211_regdomain *regdom; enum nl80211_dfs_regions region = 0; int i, j, n, iftype; int num_interfaces = 0; u32 used_iftypes = 0; u32 beacon_int_gcd; bool beacon_int_different; if (params->radio_idx >= 0) radio = &wiphy->radio[params->radio_idx]; /* * This is a bit strange, since the iteration used to rely only on * the data given by the driver, but here it now relies on context, * in form of the currently operating interfaces. * This is OK for all current users, and saves us from having to * push the GCD calculations into all the drivers. * In the future, this should probably rely more on data that's in * cfg80211 already - the only thing not would appear to be any new * interfaces (while being brought up) and channel/radar data. */ cfg80211_calculate_bi_data(wiphy, params->new_beacon_int, &beacon_int_gcd, &beacon_int_different, params->radio_idx); if (params->radar_detect) { rcu_read_lock(); regdom = rcu_dereference(cfg80211_regdomain); if (regdom) region = regdom->dfs_region; rcu_read_unlock(); } for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } if (radio) { cs = radio->iface_combinations; n = radio->n_iface_combinations; } else { cs = wiphy->iface_combinations; n = wiphy->n_iface_combinations; } for (i = 0; i < n; i++) { struct ieee80211_iface_limit *limits; u32 all_iftypes = 0; c = &cs[i]; if (num_interfaces > c->max_interfaces) continue; if (params->num_different_channels > c->num_different_channels) continue; limits = kmemdup_array(c->limits, c->n_limits, sizeof(*limits), GFP_KERNEL); if (!limits) return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < params->iftype_num[iftype]) goto cont; limits[j].max -= params->iftype_num[iftype]; } } if (params->radar_detect != (c->radar_detect_widths & params->radar_detect)) goto cont; if (params->radar_detect && c->radar_detect_regions && !(c->radar_detect_regions & BIT(region))) goto cont; /* Finally check that all iftypes that we're currently * using are actually part of this combination. If they * aren't then we can't use this combination and have * to continue to the next. */ if ((all_iftypes & used_iftypes) != used_iftypes) goto cont; if (beacon_int_gcd) { if (c->beacon_int_min_gcd && beacon_int_gcd < c->beacon_int_min_gcd) goto cont; if (!c->beacon_int_min_gcd && beacon_int_different) goto cont; } /* This combination covered all interface types and * supported the requested numbers, so we're good. */ (*iter)(c, data); cont: kfree(limits); } return 0; } EXPORT_SYMBOL(cfg80211_iter_combinations); static void cfg80211_iter_sum_ifcombs(const struct ieee80211_iface_combination *c, void *data) { int *num = data; (*num)++; } int cfg80211_check_combinations(struct wiphy *wiphy, struct iface_combination_params *params) { int err, num = 0; err = cfg80211_iter_combinations(wiphy, params, cfg80211_iter_sum_ifcombs, &num); if (err) return err; if (num == 0) return -EBUSY; return 0; } EXPORT_SYMBOL(cfg80211_check_combinations); int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, const u8 *rates, unsigned int n_rates, u32 *mask) { int i, j; if (!sband) return -EINVAL; if (n_rates == 0 || n_rates > NL80211_MAX_SUPP_RATES) return -EINVAL; *mask = 0; for (i = 0; i < n_rates; i++) { int rate = (rates[i] & 0x7f) * 5; bool found = false; for (j = 0; j < sband->n_bitrates; j++) { if (sband->bitrates[j].bitrate == rate) { found = true; *mask |= BIT(j); break; } } if (!found) return -EINVAL; } /* * mask must have at least one bit set here since we * didn't accept a 0-length rates array nor allowed * entries in the array that didn't exist */ return 0; } unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy) { enum nl80211_band band; unsigned int n_channels = 0; for (band = 0; band < NUM_NL80211_BANDS; band++) if (wiphy->bands[band]) n_channels += wiphy->bands[band]->n_channels; return n_channels; } EXPORT_SYMBOL(ieee80211_get_num_supported_channels); int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; wdev = dev->ieee80211_ptr; if (!wdev) return -EOPNOTSUPP; rdev = wiphy_to_rdev(wdev->wiphy); if (!rdev->ops->get_station) return -EOPNOTSUPP; memset(sinfo, 0, sizeof(*sinfo)); guard(wiphy)(&rdev->wiphy); return rdev_get_station(rdev, dev, mac_addr, sinfo); } EXPORT_SYMBOL(cfg80211_get_station); void cfg80211_free_nan_func(struct cfg80211_nan_func *f) { int i; if (!f) return; kfree(f->serv_spec_info); kfree(f->srf_bf); kfree(f->srf_macs); for (i = 0; i < f->num_rx_filters; i++) kfree(f->rx_filters[i].filter); for (i = 0; i < f->num_tx_filters; i++) kfree(f->tx_filters[i].filter); kfree(f->rx_filters); kfree(f->tx_filters); kfree(f); } EXPORT_SYMBOL(cfg80211_free_nan_func); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz) { u32 start_freq_khz, end_freq_khz; start_freq_khz = center_freq_khz - (bw_khz / 2); end_freq_khz = center_freq_khz + (bw_khz / 2); if (start_freq_khz >= freq_range->start_freq_khz && end_freq_khz <= freq_range->end_freq_khz) return true; return false; } int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp) { sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1, sizeof(*(sinfo->pertid)), gfp); if (!sinfo->pertid) return -ENOMEM; return 0; } EXPORT_SYMBOL(cfg80211_sinfo_alloc_tid_stats); /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; EXPORT_SYMBOL(rfc1042_header); /* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; EXPORT_SYMBOL(bridge_tunnel_header); /* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ struct iapp_layer2_update { u8 da[ETH_ALEN]; /* broadcast */ u8 sa[ETH_ALEN]; /* STA addr */ __be16 len; /* 6 */ u8 dsap; /* 0 */ u8 ssap; /* 0 */ u8 control; u8 xid_info[3]; } __packed; void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr) { struct iapp_layer2_update *msg; struct sk_buff *skb; /* Send Level 2 Update Frame to update forwarding tables in layer 2 * bridge devices */ skb = dev_alloc_skb(sizeof(*msg)); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ eth_broadcast_addr(msg->da); ether_addr_copy(msg->sa, addr); msg->len = htons(6); msg->dsap = 0; msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ msg->control = 0xaf; /* XID response lsb.1111F101. * F=0 (no poll command; unsolicited frame) */ msg->xid_info[0] = 0x81; /* XID format identifier */ msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ skb->dev = dev; skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); netif_rx(skb); } EXPORT_SYMBOL(cfg80211_send_layer2_update); int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, enum ieee80211_vht_chanwidth bw, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss) { u16 map = le16_to_cpu(cap->supp_mcs.rx_mcs_map); int ext_nss_bw; int supp_width; int i, mcs_encoding; if (map == 0xffff) return 0; if (WARN_ON(mcs > 9 || max_vht_nss > 8)) return 0; if (mcs <= 7) mcs_encoding = 0; else if (mcs == 8) mcs_encoding = 1; else mcs_encoding = 2; if (!max_vht_nss) { /* find max_vht_nss for the given MCS */ for (i = 7; i >= 0; i--) { int supp = (map >> (2 * i)) & 3; if (supp == 3) continue; if (supp >= mcs_encoding) { max_vht_nss = i + 1; break; } } } if (!(cap->supp_mcs.tx_mcs_map & cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) return max_vht_nss; ext_nss_bw = le32_get_bits(cap->vht_cap_info, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); supp_width = le32_get_bits(cap->vht_cap_info, IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); /* if not capable, treat ext_nss_bw as 0 */ if (!ext_nss_bw_capable) ext_nss_bw = 0; /* This is invalid */ if (supp_width == 3) return 0; /* This is an invalid combination so pretend nothing is supported */ if (supp_width == 2 && (ext_nss_bw == 1 || ext_nss_bw == 2)) return 0; /* * Cover all the special cases according to IEEE 802.11-2016 * Table 9-250. All other cases are either factor of 1 or not * valid/supported. */ switch (bw) { case IEEE80211_VHT_CHANWIDTH_USE_HT: case IEEE80211_VHT_CHANWIDTH_80MHZ: if ((supp_width == 1 || supp_width == 2) && ext_nss_bw == 3) return 2 * max_vht_nss; break; case IEEE80211_VHT_CHANWIDTH_160MHZ: if (supp_width == 0 && (ext_nss_bw == 1 || ext_nss_bw == 2)) return max_vht_nss / 2; if (supp_width == 0 && ext_nss_bw == 3) return (3 * max_vht_nss) / 4; if (supp_width == 1 && ext_nss_bw == 3) return 2 * max_vht_nss; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: if (supp_width == 0 && ext_nss_bw == 1) return 0; /* not possible */ if (supp_width == 0 && ext_nss_bw == 2) return max_vht_nss / 2; if (supp_width == 0 && ext_nss_bw == 3) return (3 * max_vht_nss) / 4; if (supp_width == 1 && ext_nss_bw == 0) return 0; /* not possible */ if (supp_width == 1 && ext_nss_bw == 1) return max_vht_nss / 2; if (supp_width == 1 && ext_nss_bw == 2) return (3 * max_vht_nss) / 4; break; } /* not covered or invalid combination received */ return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif) { bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; switch (check_swif) { case 0: if (is_vlan && is_4addr) return wiphy->flags & WIPHY_FLAG_4ADDR_AP; return wiphy->interface_modes & BIT(iftype); case 1: if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) return wiphy->flags & WIPHY_FLAG_4ADDR_AP; return wiphy->software_iftypes & BIT(iftype); default: break; } return false; } EXPORT_SYMBOL(cfg80211_iftype_allowed); void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); lockdep_assert_wiphy(wdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, wdev->netdev, link_id, true); break; default: /* per-link not relevant */ break; } rdev_del_intf_link(rdev, wdev, link_id); wdev->valid_links &= ~BIT(link_id); eth_zero_addr(wdev->links[link_id].addr); } void cfg80211_remove_links(struct wireless_dev *wdev) { unsigned int link_id; /* * links are controlled by upper layers (userspace/cfg) * only for AP mode, so only remove them here for AP */ if (wdev->iftype != NL80211_IFTYPE_AP) return; if (wdev->valid_links) { for_each_valid_link(wdev, link_id) cfg80211_remove_link(wdev, link_id); } } int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { cfg80211_remove_links(wdev); return rdev_del_virtual_intf(rdev, wdev); } const struct wiphy_iftype_ext_capab * cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type) { int i; for (i = 0; i < wiphy->num_iftype_ext_capab; i++) { if (wiphy->iftype_ext_capab[i].iftype == type) return &wiphy->iftype_ext_capab[i]; } return NULL; } EXPORT_SYMBOL(cfg80211_get_iftype_ext_capa); static bool ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, u32 freq, u32 width) { const struct wiphy_radio_freq_range *r; int i; for (i = 0; i < radio->n_freq_range; i++) { r = &radio->freq_range[i]; if (freq - width / 2 >= r->start_freq && freq + width / 2 <= r->end_freq) return true; } return false; } bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, const struct cfg80211_chan_def *chandef) { u32 freq, width; freq = ieee80211_chandef_to_khz(chandef); width = cfg80211_chandef_get_width(chandef); if (!ieee80211_radio_freq_range_valid(radio, freq, width)) return false; freq = MHZ_TO_KHZ(chandef->center_freq2); if (freq && !ieee80211_radio_freq_range_valid(radio, freq, width)) return false; return true; } EXPORT_SYMBOL(cfg80211_radio_chandef_valid); bool cfg80211_wdev_channel_allowed(struct wireless_dev *wdev, struct ieee80211_channel *chan) { struct wiphy *wiphy = wdev->wiphy; const struct wiphy_radio *radio; struct cfg80211_chan_def chandef; u32 radio_mask; int i; radio_mask = wdev->radio_mask; if (!wiphy->n_radio || radio_mask == BIT(wiphy->n_radio) - 1) return true; cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); for (i = 0; i < wiphy->n_radio; i++) { if (!(radio_mask & BIT(i))) continue; radio = &wiphy->radio[i]; if (!cfg80211_radio_chandef_valid(radio, &chandef)) continue; return true; } return false; } EXPORT_SYMBOL(cfg80211_wdev_channel_allowed); |
| 13 1 1 1 5 5 5 5 5 5 5 13 13 13 3 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 | // SPDX-License-Identifier: GPL-2.0-or-later /* * X.25 Packet Layer release 002 * * This is ALPHA test software. This code may break your machine, * randomly fail to work with new releases, misbehave and/or generally * screw up. It might even work. * * This code REQUIRES 2.1.15 or higher * * History * X.25 001 Jonathan Naylor Started coding. * X.25 002 Jonathan Naylor New timer architecture. * mar/20/00 Daniela Squassoni Disabling/enabling of facilities * negotiation. * 2000-09-04 Henner Eisen dev_hold() / dev_put() for x25_neigh. */ #define pr_fmt(fmt) "X25: " fmt #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/uaccess.h> #include <linux/init.h> #include <net/x25.h> LIST_HEAD(x25_neigh_list); DEFINE_RWLOCK(x25_neigh_list_lock); static void x25_t20timer_expiry(struct timer_list *); static void x25_transmit_restart_confirmation(struct x25_neigh *nb); static void x25_transmit_restart_request(struct x25_neigh *nb); /* * Linux set/reset timer routines */ static inline void x25_start_t20timer(struct x25_neigh *nb) { mod_timer(&nb->t20timer, jiffies + nb->t20); } static void x25_t20timer_expiry(struct timer_list *t) { struct x25_neigh *nb = from_timer(nb, t, t20timer); x25_transmit_restart_request(nb); x25_start_t20timer(nb); } static inline void x25_stop_t20timer(struct x25_neigh *nb) { timer_delete(&nb->t20timer); } /* * This handles all restart and diagnostic frames. */ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb, unsigned short frametype) { struct sk_buff *skbn; switch (frametype) { case X25_RESTART_REQUEST: switch (nb->state) { case X25_LINK_STATE_0: /* This can happen when the x25 module just gets loaded * and doesn't know layer 2 has already connected */ nb->state = X25_LINK_STATE_3; x25_transmit_restart_confirmation(nb); break; case X25_LINK_STATE_2: x25_stop_t20timer(nb); nb->state = X25_LINK_STATE_3; break; case X25_LINK_STATE_3: /* clear existing virtual calls */ x25_kill_by_neigh(nb); x25_transmit_restart_confirmation(nb); break; } break; case X25_RESTART_CONFIRMATION: switch (nb->state) { case X25_LINK_STATE_2: x25_stop_t20timer(nb); nb->state = X25_LINK_STATE_3; break; case X25_LINK_STATE_3: /* clear existing virtual calls */ x25_kill_by_neigh(nb); x25_transmit_restart_request(nb); nb->state = X25_LINK_STATE_2; x25_start_t20timer(nb); break; } break; case X25_DIAGNOSTIC: if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 4)) break; pr_warn("diagnostic #%d - %02X %02X %02X\n", skb->data[3], skb->data[4], skb->data[5], skb->data[6]); break; default: pr_warn("received unknown %02X with LCI 000\n", frametype); break; } if (nb->state == X25_LINK_STATE_3) while ((skbn = skb_dequeue(&nb->queue)) != NULL) x25_send_frame(skbn, nb); } /* * This routine is called when a Restart Request is needed */ static void x25_transmit_restart_request(struct x25_neigh *nb) { unsigned char *dptr; int len = X25_MAX_L2_LEN + X25_STD_MIN_LEN + 2; struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC); if (!skb) return; skb_reserve(skb, X25_MAX_L2_LEN); dptr = skb_put(skb, X25_STD_MIN_LEN + 2); *dptr++ = nb->extended ? X25_GFI_EXTSEQ : X25_GFI_STDSEQ; *dptr++ = 0x00; *dptr++ = X25_RESTART_REQUEST; *dptr++ = 0x00; *dptr++ = 0; skb->sk = NULL; x25_send_frame(skb, nb); } /* * This routine is called when a Restart Confirmation is needed */ static void x25_transmit_restart_confirmation(struct x25_neigh *nb) { unsigned char *dptr; int len = X25_MAX_L2_LEN + X25_STD_MIN_LEN; struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC); if (!skb) return; skb_reserve(skb, X25_MAX_L2_LEN); dptr = skb_put(skb, X25_STD_MIN_LEN); *dptr++ = nb->extended ? X25_GFI_EXTSEQ : X25_GFI_STDSEQ; *dptr++ = 0x00; *dptr++ = X25_RESTART_CONFIRMATION; skb->sk = NULL; x25_send_frame(skb, nb); } /* * This routine is called when a Clear Request is needed outside of the context * of a connected socket. */ void x25_transmit_clear_request(struct x25_neigh *nb, unsigned int lci, unsigned char cause) { unsigned char *dptr; int len = X25_MAX_L2_LEN + X25_STD_MIN_LEN + 2; struct sk_buff *skb = alloc_skb(len, GFP_ATOMIC); if (!skb) return; skb_reserve(skb, X25_MAX_L2_LEN); dptr = skb_put(skb, X25_STD_MIN_LEN + 2); *dptr++ = ((lci >> 8) & 0x0F) | (nb->extended ? X25_GFI_EXTSEQ : X25_GFI_STDSEQ); *dptr++ = (lci >> 0) & 0xFF; *dptr++ = X25_CLEAR_REQUEST; *dptr++ = cause; *dptr++ = 0x00; skb->sk = NULL; x25_send_frame(skb, nb); } void x25_transmit_link(struct sk_buff *skb, struct x25_neigh *nb) { switch (nb->state) { case X25_LINK_STATE_0: skb_queue_tail(&nb->queue, skb); nb->state = X25_LINK_STATE_1; x25_establish_link(nb); break; case X25_LINK_STATE_1: case X25_LINK_STATE_2: skb_queue_tail(&nb->queue, skb); break; case X25_LINK_STATE_3: x25_send_frame(skb, nb); break; } } /* * Called when the link layer has become established. */ void x25_link_established(struct x25_neigh *nb) { switch (nb->state) { case X25_LINK_STATE_0: case X25_LINK_STATE_1: x25_transmit_restart_request(nb); nb->state = X25_LINK_STATE_2; x25_start_t20timer(nb); break; } } /* * Called when the link layer has terminated, or an establishment * request has failed. */ void x25_link_terminated(struct x25_neigh *nb) { nb->state = X25_LINK_STATE_0; skb_queue_purge(&nb->queue); x25_stop_t20timer(nb); /* Out of order: clear existing virtual calls (X.25 03/93 4.6.3) */ x25_kill_by_neigh(nb); } /* * Add a new device. */ void x25_link_device_up(struct net_device *dev) { struct x25_neigh *nb = kmalloc(sizeof(*nb), GFP_ATOMIC); if (!nb) return; skb_queue_head_init(&nb->queue); timer_setup(&nb->t20timer, x25_t20timer_expiry, 0); dev_hold(dev); nb->dev = dev; nb->state = X25_LINK_STATE_0; nb->extended = 0; /* * Enables negotiation */ nb->global_facil_mask = X25_MASK_REVERSE | X25_MASK_THROUGHPUT | X25_MASK_PACKET_SIZE | X25_MASK_WINDOW_SIZE; nb->t20 = sysctl_x25_restart_request_timeout; refcount_set(&nb->refcnt, 1); write_lock_bh(&x25_neigh_list_lock); list_add(&nb->node, &x25_neigh_list); write_unlock_bh(&x25_neigh_list_lock); } /** * __x25_remove_neigh - remove neighbour from x25_neigh_list * @nb: - neigh to remove * * Remove neighbour from x25_neigh_list. If it was there. * Caller must hold x25_neigh_list_lock. */ static void __x25_remove_neigh(struct x25_neigh *nb) { if (nb->node.next) { list_del(&nb->node); x25_neigh_put(nb); } } /* * A device has been removed, remove its links. */ void x25_link_device_down(struct net_device *dev) { struct x25_neigh *nb; struct list_head *entry, *tmp; write_lock_bh(&x25_neigh_list_lock); list_for_each_safe(entry, tmp, &x25_neigh_list) { nb = list_entry(entry, struct x25_neigh, node); if (nb->dev == dev) { __x25_remove_neigh(nb); dev_put(dev); } } write_unlock_bh(&x25_neigh_list_lock); } /* * Given a device, return the neighbour address. */ struct x25_neigh *x25_get_neigh(struct net_device *dev) { struct x25_neigh *nb, *use = NULL; read_lock_bh(&x25_neigh_list_lock); list_for_each_entry(nb, &x25_neigh_list, node) { if (nb->dev == dev) { use = nb; break; } } if (use) x25_neigh_hold(use); read_unlock_bh(&x25_neigh_list_lock); return use; } /* * Handle the ioctls that control the subscription functions. */ int x25_subscr_ioctl(unsigned int cmd, void __user *arg) { struct x25_subscrip_struct x25_subscr; struct x25_neigh *nb; struct net_device *dev; int rc = -EINVAL; if (cmd != SIOCX25GSUBSCRIP && cmd != SIOCX25SSUBSCRIP) goto out; rc = -EFAULT; if (copy_from_user(&x25_subscr, arg, sizeof(x25_subscr))) goto out; rc = -EINVAL; if ((dev = x25_dev_get(x25_subscr.device)) == NULL) goto out; if ((nb = x25_get_neigh(dev)) == NULL) goto out_dev_put; dev_put(dev); if (cmd == SIOCX25GSUBSCRIP) { read_lock_bh(&x25_neigh_list_lock); x25_subscr.extended = nb->extended; x25_subscr.global_facil_mask = nb->global_facil_mask; read_unlock_bh(&x25_neigh_list_lock); rc = copy_to_user(arg, &x25_subscr, sizeof(x25_subscr)) ? -EFAULT : 0; } else { rc = -EINVAL; if (!(x25_subscr.extended && x25_subscr.extended != 1)) { rc = 0; write_lock_bh(&x25_neigh_list_lock); nb->extended = x25_subscr.extended; nb->global_facil_mask = x25_subscr.global_facil_mask; write_unlock_bh(&x25_neigh_list_lock); } } x25_neigh_put(nb); out: return rc; out_dev_put: dev_put(dev); goto out; } /* * Release all memory associated with X.25 neighbour structures. */ void __exit x25_link_free(void) { struct x25_neigh *nb; struct list_head *entry, *tmp; write_lock_bh(&x25_neigh_list_lock); list_for_each_safe(entry, tmp, &x25_neigh_list) { struct net_device *dev; nb = list_entry(entry, struct x25_neigh, node); dev = nb->dev; __x25_remove_neigh(nb); dev_put(dev); } write_unlock_bh(&x25_neigh_list_lock); } |
| 2 11 13 1 1 11 13 13 2 11 3 11 11 11 3 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/netfilter/xt_IDLETIMER.c * * Netfilter module to trigger a timer when packet matches. * After timer expires a kevent will be sent. * * Copyright (C) 2004, 2010 Nokia Corporation * Written by Timo Teras <ext-timo.teras@nokia.com> * * Converted to x_tables and reworked for upstream inclusion * by Luciano Coelho <luciano.coelho@nokia.com> * * Contact: Luciano Coelho <luciano.coelho@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/timer.h> #include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_IDLETIMER.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/workqueue.h> #include <linux/sysfs.h> struct idletimer_tg { struct list_head entry; struct alarm alarm; struct timer_list timer; struct work_struct work; struct kobject *kobj; struct device_attribute attr; unsigned int refcnt; u8 timer_type; }; static LIST_HEAD(idletimer_tg_list); static DEFINE_MUTEX(list_mutex); static struct kobject *idletimer_tg_kobj; static struct idletimer_tg *__idletimer_tg_find_by_label(const char *label) { struct idletimer_tg *entry; list_for_each_entry(entry, &idletimer_tg_list, entry) { if (!strcmp(label, entry->attr.attr.name)) return entry; } return NULL; } static ssize_t idletimer_tg_show(struct device *dev, struct device_attribute *attr, char *buf) { struct idletimer_tg *timer; unsigned long expires = 0; struct timespec64 ktimespec = {}; long time_diff = 0; mutex_lock(&list_mutex); timer = __idletimer_tg_find_by_label(attr->attr.name); if (timer) { if (timer->timer_type & XT_IDLETIMER_ALARM) { ktime_t expires_alarm = alarm_expires_remaining(&timer->alarm); ktimespec = ktime_to_timespec64(expires_alarm); time_diff = ktimespec.tv_sec; } else { expires = timer->timer.expires; time_diff = jiffies_to_msecs(expires - jiffies) / 1000; } } mutex_unlock(&list_mutex); if (time_after(expires, jiffies) || ktimespec.tv_sec > 0) return sysfs_emit(buf, "%ld\n", time_diff); return sysfs_emit(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) { struct idletimer_tg *timer = container_of(work, struct idletimer_tg, work); sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name); } static void idletimer_tg_expired(struct timer_list *t) { struct idletimer_tg *timer = from_timer(timer, t, timer); pr_debug("timer %s expired\n", timer->attr.attr.name); schedule_work(&timer->work); } static void idletimer_tg_alarmproc(struct alarm *alarm, ktime_t now) { struct idletimer_tg *timer = alarm->data; pr_debug("alarm %s expired\n", timer->attr.attr.name); schedule_work(&timer->work); } static int idletimer_check_sysfs_name(const char *name, unsigned int size) { int ret; ret = xt_check_proc_name(name, size); if (ret < 0) return ret; if (!strcmp(name, "power") || !strcmp(name, "subsystem") || !strcmp(name, "uevent")) return -EINVAL; return 0; } static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; info->timer = kzalloc(sizeof(*info->timer), GFP_KERNEL); if (!info->timer) { ret = -ENOMEM; goto out; } ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); if (ret < 0) goto out_free_timer; sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { ret = -ENOMEM; goto out_free_timer; } info->timer->attr.attr.mode = 0444; info->timer->attr.show = idletimer_tg_show; ret = sysfs_create_file(idletimer_tg_kobj, &info->timer->attr.attr); if (ret < 0) { pr_debug("couldn't add file to sysfs"); goto out_free_attr; } list_add(&info->timer->entry, &idletimer_tg_list); timer_setup(&info->timer->timer, idletimer_tg_expired, 0); info->timer->refcnt = 1; INIT_WORK(&info->timer->work, idletimer_tg_work); mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); return 0; out_free_attr: kfree(info->timer->attr.attr.name); out_free_timer: kfree(info->timer); out: return ret; } static int idletimer_tg_create_v1(struct idletimer_tg_info_v1 *info) { int ret; info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL); if (!info->timer) { ret = -ENOMEM; goto out; } ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); if (ret < 0) goto out_free_timer; sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { ret = -ENOMEM; goto out_free_timer; } info->timer->attr.attr.mode = 0444; info->timer->attr.show = idletimer_tg_show; ret = sysfs_create_file(idletimer_tg_kobj, &info->timer->attr.attr); if (ret < 0) { pr_debug("couldn't add file to sysfs"); goto out_free_attr; } /* notify userspace */ kobject_uevent(idletimer_tg_kobj,KOBJ_ADD); list_add(&info->timer->entry, &idletimer_tg_list); pr_debug("timer type value is %u", info->timer_type); info->timer->timer_type = info->timer_type; info->timer->refcnt = 1; INIT_WORK(&info->timer->work, idletimer_tg_work); if (info->timer->timer_type & XT_IDLETIMER_ALARM) { ktime_t tout; alarm_init(&info->timer->alarm, ALARM_BOOTTIME, idletimer_tg_alarmproc); info->timer->alarm.data = info->timer; tout = ktime_set(info->timeout, 0); alarm_start_relative(&info->timer->alarm, tout); } else { timer_setup(&info->timer->timer, idletimer_tg_expired, 0); mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); } return 0; out_free_attr: kfree(info->timer->attr.attr.name); out_free_timer: kfree(info->timer); out: return ret; } /* * The actual xt_tables plugin. */ static unsigned int idletimer_tg_target(struct sk_buff *skb, const struct xt_action_param *par) { const struct idletimer_tg_info *info = par->targinfo; pr_debug("resetting timer %s, timeout period %u\n", info->label, info->timeout); mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); return XT_CONTINUE; } /* * The actual xt_tables plugin. */ static unsigned int idletimer_tg_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct idletimer_tg_info_v1 *info = par->targinfo; pr_debug("resetting timer %s, timeout period %u\n", info->label, info->timeout); if (info->timer->timer_type & XT_IDLETIMER_ALARM) { ktime_t tout = ktime_set(info->timeout, 0); alarm_start_relative(&info->timer->alarm, tout); } else { mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); } return XT_CONTINUE; } static int idletimer_tg_helper(struct idletimer_tg_info *info) { if (info->timeout == 0) { pr_debug("timeout value is zero\n"); return -EINVAL; } if (info->timeout >= INT_MAX / 1000) { pr_debug("timeout value is too big\n"); return -EINVAL; } if (info->label[0] == '\0' || strnlen(info->label, MAX_IDLETIMER_LABEL_SIZE) == MAX_IDLETIMER_LABEL_SIZE) { pr_debug("label is empty or not nul-terminated\n"); return -EINVAL; } return 0; } static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) { struct idletimer_tg_info *info = par->targinfo; int ret; pr_debug("checkentry targinfo%s\n", info->label); ret = idletimer_tg_helper(info); if(ret < 0) { pr_debug("checkentry helper return invalid\n"); return -EINVAL; } mutex_lock(&list_mutex); info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { info->timer->refcnt++; mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); pr_debug("increased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); } else { ret = idletimer_tg_create(info); if (ret < 0) { pr_debug("failed to create timer\n"); mutex_unlock(&list_mutex); return ret; } } mutex_unlock(&list_mutex); return 0; } static int idletimer_tg_checkentry_v1(const struct xt_tgchk_param *par) { struct idletimer_tg_info_v1 *info = par->targinfo; int ret; pr_debug("checkentry targinfo%s\n", info->label); if (info->send_nl_msg) return -EOPNOTSUPP; ret = idletimer_tg_helper((struct idletimer_tg_info *)info); if(ret < 0) { pr_debug("checkentry helper return invalid\n"); return -EINVAL; } if (info->timer_type > XT_IDLETIMER_ALARM) { pr_debug("invalid value for timer type\n"); return -EINVAL; } mutex_lock(&list_mutex); info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { if (info->timer->timer_type != info->timer_type) { pr_debug("Adding/Replacing rule with same label and different timer type is not allowed\n"); mutex_unlock(&list_mutex); return -EINVAL; } info->timer->refcnt++; if (info->timer_type & XT_IDLETIMER_ALARM) { /* calculate remaining expiry time */ ktime_t tout = alarm_expires_remaining(&info->timer->alarm); struct timespec64 ktimespec = ktime_to_timespec64(tout); if (ktimespec.tv_sec > 0) { pr_debug("time_expiry_remaining %lld\n", ktimespec.tv_sec); alarm_start_relative(&info->timer->alarm, tout); } } else { mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); } pr_debug("increased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); } else { ret = idletimer_tg_create_v1(info); if (ret < 0) { pr_debug("failed to create timer\n"); mutex_unlock(&list_mutex); return ret; } } mutex_unlock(&list_mutex); return 0; } static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) { const struct idletimer_tg_info *info = par->targinfo; pr_debug("destroy targinfo %s\n", info->label); mutex_lock(&list_mutex); if (--info->timer->refcnt > 0) { pr_debug("decreased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); mutex_unlock(&list_mutex); return; } pr_debug("deleting timer %s\n", info->label); list_del(&info->timer->entry); mutex_unlock(&list_mutex); timer_shutdown_sync(&info->timer->timer); cancel_work_sync(&info->timer->work); sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); kfree(info->timer->attr.attr.name); kfree(info->timer); } static void idletimer_tg_destroy_v1(const struct xt_tgdtor_param *par) { const struct idletimer_tg_info_v1 *info = par->targinfo; pr_debug("destroy targinfo %s\n", info->label); mutex_lock(&list_mutex); if (--info->timer->refcnt > 0) { pr_debug("decreased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); mutex_unlock(&list_mutex); return; } pr_debug("deleting timer %s\n", info->label); list_del(&info->timer->entry); mutex_unlock(&list_mutex); if (info->timer->timer_type & XT_IDLETIMER_ALARM) { alarm_cancel(&info->timer->alarm); } else { timer_shutdown_sync(&info->timer->timer); } cancel_work_sync(&info->timer->work); sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); kfree(info->timer->attr.attr.name); kfree(info->timer); } static struct xt_target idletimer_tg[] __read_mostly = { { .name = "IDLETIMER", .family = NFPROTO_IPV4, .target = idletimer_tg_target, .targetsize = sizeof(struct idletimer_tg_info), .usersize = offsetof(struct idletimer_tg_info, timer), .checkentry = idletimer_tg_checkentry, .destroy = idletimer_tg_destroy, .me = THIS_MODULE, }, { .name = "IDLETIMER", .family = NFPROTO_IPV4, .revision = 1, .target = idletimer_tg_target_v1, .targetsize = sizeof(struct idletimer_tg_info_v1), .usersize = offsetof(struct idletimer_tg_info_v1, timer), .checkentry = idletimer_tg_checkentry_v1, .destroy = idletimer_tg_destroy_v1, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "IDLETIMER", .family = NFPROTO_IPV6, .target = idletimer_tg_target, .targetsize = sizeof(struct idletimer_tg_info), .usersize = offsetof(struct idletimer_tg_info, timer), .checkentry = idletimer_tg_checkentry, .destroy = idletimer_tg_destroy, .me = THIS_MODULE, }, { .name = "IDLETIMER", .family = NFPROTO_IPV6, .revision = 1, .target = idletimer_tg_target_v1, .targetsize = sizeof(struct idletimer_tg_info_v1), .usersize = offsetof(struct idletimer_tg_info_v1, timer), .checkentry = idletimer_tg_checkentry_v1, .destroy = idletimer_tg_destroy_v1, .me = THIS_MODULE, }, #endif }; static struct class *idletimer_tg_class; static struct device *idletimer_tg_device; static int __init idletimer_tg_init(void) { int err; idletimer_tg_class = class_create("xt_idletimer"); err = PTR_ERR(idletimer_tg_class); if (IS_ERR(idletimer_tg_class)) { pr_debug("couldn't register device class\n"); goto out; } idletimer_tg_device = device_create(idletimer_tg_class, NULL, MKDEV(0, 0), NULL, "timers"); err = PTR_ERR(idletimer_tg_device); if (IS_ERR(idletimer_tg_device)) { pr_debug("couldn't register system device\n"); goto out_class; } idletimer_tg_kobj = &idletimer_tg_device->kobj; err = xt_register_targets(idletimer_tg, ARRAY_SIZE(idletimer_tg)); if (err < 0) { pr_debug("couldn't register xt target\n"); goto out_dev; } return 0; out_dev: device_destroy(idletimer_tg_class, MKDEV(0, 0)); out_class: class_destroy(idletimer_tg_class); out: return err; } static void __exit idletimer_tg_exit(void) { xt_unregister_targets(idletimer_tg, ARRAY_SIZE(idletimer_tg)); device_destroy(idletimer_tg_class, MKDEV(0, 0)); class_destroy(idletimer_tg_class); } module_init(idletimer_tg_init); module_exit(idletimer_tg_exit); MODULE_AUTHOR("Timo Teras <ext-timo.teras@nokia.com>"); MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); MODULE_DESCRIPTION("Xtables: idle time monitor"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("ipt_IDLETIMER"); MODULE_ALIAS("ip6t_IDLETIMER"); |
| 31 105 104 7 105 105 104 7 7 840 104 104 104 38 66 103 104 104 103 19 92 103 103 104 104 92 93 31 105 35 71 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 IBM Corporation * * Author: Mimi Zohar <zohar@us.ibm.com> * * File: ima_api.c * Implements must_appraise_or_measure, collect_measurement, * appraise_measurement, store_measurement and store_template. */ #include <linux/slab.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/evm.h> #include <linux/fsverity.h> #include "ima.h" /* * ima_free_template_entry - free an existing template entry */ void ima_free_template_entry(struct ima_template_entry *entry) { int i; for (i = 0; i < entry->template_desc->num_fields; i++) kfree(entry->template_data[i].data); kfree(entry->digests); kfree(entry); } /* * ima_alloc_init_template - create and initialize a new template entry */ int ima_alloc_init_template(struct ima_event_data *event_data, struct ima_template_entry **entry, struct ima_template_desc *desc) { struct ima_template_desc *template_desc; struct tpm_digest *digests; int i, result = 0; if (desc) template_desc = desc; else template_desc = ima_template_desc_current(); *entry = kzalloc(struct_size(*entry, template_data, template_desc->num_fields), GFP_NOFS); if (!*entry) return -ENOMEM; digests = kcalloc(NR_BANKS(ima_tpm_chip) + ima_extra_slots, sizeof(*digests), GFP_NOFS); if (!digests) { kfree(*entry); *entry = NULL; return -ENOMEM; } (*entry)->digests = digests; (*entry)->template_desc = template_desc; for (i = 0; i < template_desc->num_fields; i++) { const struct ima_template_field *field = template_desc->fields[i]; u32 len; result = field->field_init(event_data, &((*entry)->template_data[i])); if (result != 0) goto out; len = (*entry)->template_data[i].len; (*entry)->template_data_len += sizeof(len); (*entry)->template_data_len += len; } return 0; out: ima_free_template_entry(*entry); *entry = NULL; return result; } /* * ima_store_template - store ima template measurements * * Calculate the hash of a template entry, add the template entry * to an ordered list of measurement entries maintained inside the kernel, * and also update the aggregate integrity value (maintained inside the * configured TPM PCR) over the hashes of the current list of measurement * entries. * * Applications retrieve the current kernel-held measurement list through * the securityfs entries in /sys/kernel/security/ima. The signed aggregate * TPM PCR (called quote) can be retrieved using a TPM user space library * and is used to validate the measurement list. * * Returns 0 on success, error code otherwise */ int ima_store_template(struct ima_template_entry *entry, int violation, struct inode *inode, const unsigned char *filename, int pcr) { static const char op[] = "add_template_measure"; static const char audit_cause[] = "hashing_error"; char *template_name = entry->template_desc->name; int result; if (!violation) { result = ima_calc_field_array_hash(&entry->template_data[0], entry); if (result < 0) { integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, template_name, op, audit_cause, result, 0); return result; } } entry->pcr = pcr; result = ima_add_template_entry(entry, violation, op, inode, filename); return result; } /* * ima_add_violation - add violation to measurement list. * * Violations are flagged in the measurement list with zero hash values. * By extending the PCR with 0xFF's instead of with zeroes, the PCR * value is invalidated. */ void ima_add_violation(struct file *file, const unsigned char *filename, struct ima_iint_cache *iint, const char *op, const char *cause) { struct ima_template_entry *entry; struct inode *inode = file_inode(file); struct ima_event_data event_data = { .iint = iint, .file = file, .filename = filename, .violation = cause }; int violation = 1; int result; /* can overflow, only indicator */ atomic_long_inc(&ima_htable.violations); result = ima_alloc_init_template(&event_data, &entry, NULL); if (result < 0) { result = -ENOMEM; goto err_out; } result = ima_store_template(entry, violation, inode, filename, CONFIG_IMA_MEASURE_PCR_IDX); if (result < 0) ima_free_template_entry(entry); err_out: integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename, op, cause, result, 0); } /** * ima_get_action - appraise & measure decision based on policy. * @idmap: idmap of the mount the inode was found from * @inode: pointer to the inode associated with the object being validated * @cred: pointer to credentials structure to validate * @prop: properties of the task being validated * @mask: contains the permission mask (MAY_READ, MAY_WRITE, MAY_EXEC, * MAY_APPEND) * @func: caller identifier * @pcr: pointer filled in if matched measure policy sets pcr= * @template_desc: pointer filled in if matched measure policy sets template= * @func_data: func specific data, may be NULL * @allowed_algos: allowlist of hash algorithms for the IMA xattr * * The policy is defined in terms of keypairs: * subj=, obj=, type=, func=, mask=, fsmagic= * subj,obj, and type: are LSM specific. * func: FILE_CHECK | BPRM_CHECK | CREDS_CHECK | MMAP_CHECK | MODULE_CHECK * | KEXEC_CMDLINE | KEY_CHECK | CRITICAL_DATA | SETXATTR_CHECK * | MMAP_CHECK_REQPROT * mask: contains the permission mask * fsmagic: hex value * * Returns IMA_MEASURE, IMA_APPRAISE mask. * */ int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, struct lsm_prop *prop, int mask, enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, const char *func_data, unsigned int *allowed_algos) { int flags = IMA_MEASURE | IMA_AUDIT | IMA_APPRAISE | IMA_HASH; flags &= ima_policy_flag; return ima_match_policy(idmap, inode, cred, prop, func, mask, flags, pcr, template_desc, func_data, allowed_algos); } static bool ima_get_verity_digest(struct ima_iint_cache *iint, struct inode *inode, struct ima_max_digest_data *hash) { enum hash_algo alg; int digest_len; /* * On failure, 'measure' policy rules will result in a file data * hash containing 0's. */ digest_len = fsverity_get_digest(inode, hash->digest, NULL, &alg); if (digest_len == 0) return false; /* * Unlike in the case of actually calculating the file hash, in * the fsverity case regardless of the hash algorithm, return * the verity digest to be included in the measurement list. A * mismatch between the verity algorithm and the xattr signature * algorithm, if one exists, will be detected later. */ hash->hdr.algo = alg; hash->hdr.length = digest_len; return true; } /* * ima_collect_measurement - collect file measurement * * Calculate the file hash, if it doesn't already exist, * storing the measurement and i_version in the iint. * * Must be called with iint->mutex held. * * Return 0 on success, error code otherwise */ int ima_collect_measurement(struct ima_iint_cache *iint, struct file *file, void *buf, loff_t size, enum hash_algo algo, struct modsig *modsig) { const char *audit_cause = "failed"; struct inode *inode = file_inode(file); struct inode *real_inode = d_real_inode(file_dentry(file)); struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); struct name_snapshot filename; struct kstat stat; int result = 0; int length; void *tmpbuf; u64 i_version = 0; /* * Always collect the modsig, because IMA might have already collected * the file digest without collecting the modsig in a previous * measurement rule. */ if (modsig) ima_collect_modsig(modsig, buf, size); if (iint->flags & IMA_COLLECTED) goto out; /* * Detecting file change is based on i_version. On filesystems * which do not support i_version, support was originally limited * to an initial measurement/appraisal/audit, but was modified to * assume the file changed. */ result = vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT); if (!result && (stat.result_mask & STATX_CHANGE_COOKIE)) i_version = stat.change_cookie; hash.hdr.algo = algo; hash.hdr.length = hash_digest_size[algo]; /* Initialize hash digest to 0's in case of failure */ memset(&hash.digest, 0, sizeof(hash.digest)); if (iint->flags & IMA_VERITY_REQUIRED) { if (!ima_get_verity_digest(iint, inode, &hash)) { audit_cause = "no-verity-digest"; result = -ENODATA; } } else if (buf) { result = ima_calc_buffer_hash(buf, size, hash_hdr); } else { result = ima_calc_file_hash(file, hash_hdr); } if (result && result != -EBADF && result != -EINVAL) goto out; length = sizeof(hash.hdr) + hash.hdr.length; tmpbuf = krealloc(iint->ima_hash, length, GFP_NOFS); if (!tmpbuf) { result = -ENOMEM; goto out; } iint->ima_hash = tmpbuf; memcpy(iint->ima_hash, &hash, length); if (real_inode == inode) iint->real_inode.version = i_version; else integrity_inode_attrs_store(&iint->real_inode, i_version, real_inode); /* Possibly temporary failure due to type of read (eg. O_DIRECT) */ if (!result) iint->flags |= IMA_COLLECTED; out: if (result) { if (file->f_flags & O_DIRECT) audit_cause = "failed(directio)"; take_dentry_name_snapshot(&filename, file->f_path.dentry); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename.name.name, "collect_data", audit_cause, result, 0); release_dentry_name_snapshot(&filename); } return result; } /* * ima_store_measurement - store file measurement * * Create an "ima" template and then store the template by calling * ima_store_template. * * We only get here if the inode has not already been measured, * but the measurement could already exist: * - multiple copies of the same file on either the same or * different filesystems. * - the inode was previously flushed as well as the iint info, * containing the hashing info. * * Must be called with iint->mutex held. */ void ima_store_measurement(struct ima_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig, int pcr, struct ima_template_desc *template_desc) { static const char op[] = "add_template_measure"; static const char audit_cause[] = "ENOMEM"; int result = -ENOMEM; struct inode *inode = file_inode(file); struct ima_template_entry *entry; struct ima_event_data event_data = { .iint = iint, .file = file, .filename = filename, .xattr_value = xattr_value, .xattr_len = xattr_len, .modsig = modsig }; int violation = 0; /* * We still need to store the measurement in the case of MODSIG because * we only have its contents to put in the list at the time of * appraisal, but a file measurement from earlier might already exist in * the measurement list. */ if (iint->measured_pcrs & (0x1 << pcr) && !modsig) return; result = ima_alloc_init_template(&event_data, &entry, template_desc); if (result < 0) { integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename, op, audit_cause, result, 0); return; } result = ima_store_template(entry, violation, inode, filename, pcr); if ((!result || result == -EEXIST) && !(file->f_flags & O_DIRECT)) { iint->flags |= IMA_MEASURED; iint->measured_pcrs |= (0x1 << pcr); } if (result < 0) ima_free_template_entry(entry); } void ima_audit_measurement(struct ima_iint_cache *iint, const unsigned char *filename) { struct audit_buffer *ab; char *hash; const char *algo_name = hash_algo_name[iint->ima_hash->algo]; int i; if (iint->flags & IMA_AUDITED) return; hash = kzalloc((iint->ima_hash->length * 2) + 1, GFP_KERNEL); if (!hash) return; for (i = 0; i < iint->ima_hash->length; i++) hex_byte_pack(hash + (i * 2), iint->ima_hash->digest[i]); hash[i * 2] = '\0'; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_INTEGRITY_RULE); if (!ab) goto out; audit_log_format(ab, "file="); audit_log_untrustedstring(ab, filename); audit_log_format(ab, " hash=\"%s:%s\"", algo_name, hash); audit_log_task_info(ab); audit_log_end(ab); iint->flags |= IMA_AUDITED; out: kfree(hash); return; } /* * ima_d_path - return a pointer to the full pathname * * Attempt to return a pointer to the full pathname for use in the * IMA measurement list, IMA audit records, and auditing logs. * * On failure, return a pointer to a copy of the filename, not dname. * Returning a pointer to dname, could result in using the pointer * after the memory has been freed. */ const char *ima_d_path(const struct path *path, char **pathbuf, char *namebuf) { struct name_snapshot filename; char *pathname = NULL; *pathbuf = __getname(); if (*pathbuf) { pathname = d_absolute_path(path, *pathbuf, PATH_MAX); if (IS_ERR(pathname)) { __putname(*pathbuf); *pathbuf = NULL; pathname = NULL; } } if (!pathname) { take_dentry_name_snapshot(&filename, path->dentry); strscpy(namebuf, filename.name.name, NAME_MAX); release_dentry_name_snapshot(&filename); pathname = namebuf; } return pathname; } |
| 23 23 12 16 16 12 23 23 12 16 16 12 25 32 32 19 20 19 7 32 3 20 13 11 32 7 10 16 25 25 25 25 25 3 23 23 32 32 23 23 26 26 27 21 1 1 1 18 17 2 19 19 19 21 21 32 32 32 32 32 3 3 5 7 26 2 24 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_sfb.c Stochastic Fair Blue * * Copyright (c) 2008-2011 Juliusz Chroboczek <jch@pps.jussieu.fr> * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> * * W. Feng, D. Kandlur, D. Saha, K. Shin. Blue: * A New Class of Active Queue Management Algorithms. * U. Michigan CSE-TR-387-99, April 1999. * * http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/siphash.h> #include <net/ip.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/inet_ecn.h> /* * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level) * This implementation uses L = 8 and N = 16 * This permits us to split one 32bit hash (provided per packet by rxhash or * external classifier) into 8 subhashes of 4 bits. */ #define SFB_BUCKET_SHIFT 4 #define SFB_NUMBUCKETS (1 << SFB_BUCKET_SHIFT) /* N bins per Level */ #define SFB_BUCKET_MASK (SFB_NUMBUCKETS - 1) #define SFB_LEVELS (32 / SFB_BUCKET_SHIFT) /* L */ /* SFB algo uses a virtual queue, named "bin" */ struct sfb_bucket { u16 qlen; /* length of virtual queue */ u16 p_mark; /* marking probability */ }; /* We use a double buffering right before hash change * (Section 4.4 of SFB reference : moving hash functions) */ struct sfb_bins { siphash_key_t perturbation; /* siphash key */ struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; }; struct sfb_sched_data { struct Qdisc *qdisc; struct tcf_proto __rcu *filter_list; struct tcf_block *block; unsigned long rehash_interval; unsigned long warmup_time; /* double buffering warmup time in jiffies */ u32 max; u32 bin_size; /* maximum queue length per bin */ u32 increment; /* d1 */ u32 decrement; /* d2 */ u32 limit; /* HARD maximal queue length */ u32 penalty_rate; u32 penalty_burst; u32 tokens_avail; unsigned long rehash_time; unsigned long token_time; u8 slot; /* current active bins (0 or 1) */ bool double_buffering; struct sfb_bins bins[2]; struct { u32 earlydrop; u32 penaltydrop; u32 bucketdrop; u32 queuedrop; u32 childdrop; /* drops in child qdisc */ u32 marked; /* ECN mark */ } stats; }; /* * Each queued skb might be hashed on one or two bins * We store in skb_cb the two hash values. * (A zero value means double buffering was not used) */ struct sfb_skb_cb { u32 hashes[2]; }; static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct sfb_skb_cb)); return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data; } /* * If using 'internal' SFB flow classifier, hash comes from skb rxhash * If using external classifier, hash comes from the classid. */ static u32 sfb_hash(const struct sk_buff *skb, u32 slot) { return sfb_skb_cb(skb)->hashes[slot]; } /* Probabilities are coded as Q0.16 fixed-point values, * with 0xFFFF representing 65535/65536 (almost 1.0) * Addition and subtraction are saturating in [0, 65535] */ static u32 prob_plus(u32 p1, u32 p2) { u32 res = p1 + p2; return min_t(u32, res, SFB_MAX_PROB); } static u32 prob_minus(u32 p1, u32 p2) { return p1 > p2 ? p1 - p2 : 0; } static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) { int i; struct sfb_bucket *b = &q->bins[slot].bins[0][0]; for (i = 0; i < SFB_LEVELS; i++) { u32 hash = sfbhash & SFB_BUCKET_MASK; sfbhash >>= SFB_BUCKET_SHIFT; if (b[hash].qlen < 0xFFFF) b[hash].qlen++; b += SFB_NUMBUCKETS; /* next level */ } } static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q) { u32 sfbhash; sfbhash = cb->hashes[0]; if (sfbhash) increment_one_qlen(sfbhash, 0, q); sfbhash = cb->hashes[1]; if (sfbhash) increment_one_qlen(sfbhash, 1, q); } static void decrement_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) { int i; struct sfb_bucket *b = &q->bins[slot].bins[0][0]; for (i = 0; i < SFB_LEVELS; i++) { u32 hash = sfbhash & SFB_BUCKET_MASK; sfbhash >>= SFB_BUCKET_SHIFT; if (b[hash].qlen > 0) b[hash].qlen--; b += SFB_NUMBUCKETS; /* next level */ } } static void decrement_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) { u32 sfbhash; sfbhash = sfb_hash(skb, 0); if (sfbhash) decrement_one_qlen(sfbhash, 0, q); sfbhash = sfb_hash(skb, 1); if (sfbhash) decrement_one_qlen(sfbhash, 1, q); } static void decrement_prob(struct sfb_bucket *b, struct sfb_sched_data *q) { b->p_mark = prob_minus(b->p_mark, q->decrement); } static void increment_prob(struct sfb_bucket *b, struct sfb_sched_data *q) { b->p_mark = prob_plus(b->p_mark, q->increment); } static void sfb_zero_all_buckets(struct sfb_sched_data *q) { memset(&q->bins, 0, sizeof(q->bins)); } /* * compute max qlen, max p_mark, and avg p_mark */ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_data *q) { int i; u32 qlen = 0, prob = 0, totalpm = 0; const struct sfb_bucket *b = &q->bins[q->slot].bins[0][0]; for (i = 0; i < SFB_LEVELS * SFB_NUMBUCKETS; i++) { if (qlen < b->qlen) qlen = b->qlen; totalpm += b->p_mark; if (prob < b->p_mark) prob = b->p_mark; b++; } *prob_r = prob; *avgpm_r = totalpm / (SFB_LEVELS * SFB_NUMBUCKETS); return qlen; } static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { get_random_bytes(&q->bins[slot].perturbation, sizeof(q->bins[slot].perturbation)); } static void sfb_swap_slot(struct sfb_sched_data *q) { sfb_init_perturbation(q->slot, q); q->slot ^= 1; q->double_buffering = false; } /* Non elastic flows are allowed to use part of the bandwidth, expressed * in "penalty_rate" packets per second, with "penalty_burst" burst */ static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q) { if (q->penalty_rate == 0 || q->penalty_burst == 0) return true; if (q->tokens_avail < 1) { unsigned long age = min(10UL * HZ, jiffies - q->token_time); q->tokens_avail = (age * q->penalty_rate) / HZ; if (q->tokens_avail > q->penalty_burst) q->tokens_avail = q->penalty_burst; q->token_time = jiffies; if (q->tokens_avail < 1) return true; } q->tokens_avail--; return false; } static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, int *qerr, u32 *salt) { struct tcf_result res; int result; result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return false; } #endif *salt = TC_H_MIN(res.classid); return true; } return false; } static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct sfb_sched_data *q = qdisc_priv(sch); unsigned int len = qdisc_pkt_len(skb); struct Qdisc *child = q->qdisc; struct tcf_proto *fl; struct sfb_skb_cb cb; int i; u32 p_min = ~0; u32 minqlen = ~0; u32 r, sfbhash; u32 slot = q->slot; int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (unlikely(sch->q.qlen >= q->limit)) { qdisc_qstats_overlimit(sch); q->stats.queuedrop++; goto drop; } if (q->rehash_interval > 0) { unsigned long limit = q->rehash_time + q->rehash_interval; if (unlikely(time_after(jiffies, limit))) { sfb_swap_slot(q); q->rehash_time = jiffies; } else if (unlikely(!q->double_buffering && q->warmup_time > 0 && time_after(jiffies, limit - q->warmup_time))) { q->double_buffering = true; } } fl = rcu_dereference_bh(q->filter_list); if (fl) { u32 salt; /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation); } else { sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); } if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; for (i = 0; i < SFB_LEVELS; i++) { u32 hash = sfbhash & SFB_BUCKET_MASK; struct sfb_bucket *b = &q->bins[slot].bins[i][hash]; sfbhash >>= SFB_BUCKET_SHIFT; if (b->qlen == 0) decrement_prob(b, q); else if (b->qlen >= q->bin_size) increment_prob(b, q); if (minqlen > b->qlen) minqlen = b->qlen; if (p_min > b->p_mark) p_min = b->p_mark; } slot ^= 1; sfb_skb_cb(skb)->hashes[slot] = 0; if (unlikely(minqlen >= q->max)) { qdisc_qstats_overlimit(sch); q->stats.bucketdrop++; goto drop; } if (unlikely(p_min >= SFB_MAX_PROB)) { /* Inelastic flow */ if (q->double_buffering) { sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; for (i = 0; i < SFB_LEVELS; i++) { u32 hash = sfbhash & SFB_BUCKET_MASK; struct sfb_bucket *b = &q->bins[slot].bins[i][hash]; sfbhash >>= SFB_BUCKET_SHIFT; if (b->qlen == 0) decrement_prob(b, q); else if (b->qlen >= q->bin_size) increment_prob(b, q); } } if (sfb_rate_limit(skb, q)) { qdisc_qstats_overlimit(sch); q->stats.penaltydrop++; goto drop; } goto enqueue; } r = get_random_u16() & SFB_MAX_PROB; reason = SKB_DROP_REASON_QDISC_CONGESTED; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { /* If we're marking that many packets, then either * this flow is unresponsive, or we're badly congested. * In either case, we want to start dropping packets. */ if (r < (p_min - SFB_MAX_PROB / 2) * 2) { q->stats.earlydrop++; goto drop; } } if (INET_ECN_set_ce(skb)) { q->stats.marked++; } else { q->stats.earlydrop++; goto drop; } } enqueue: memcpy(&cb, sfb_skb_cb(skb), sizeof(cb)); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { sch->qstats.backlog += len; sch->q.qlen++; increment_qlen(&cb, q); } else if (net_xmit_drop_count(ret)) { q->stats.childdrop++; qdisc_qstats_drop(sch); } return ret; drop: qdisc_drop_reason(skb, sch, to_free, reason); return NET_XMIT_CN; other_drop: if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); kfree_skb(skb); return ret; } static struct sk_buff *sfb_dequeue(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; struct sk_buff *skb; skb = child->dequeue(q->qdisc); if (skb) { qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; decrement_qlen(skb, q); } return skb; } static struct sk_buff *sfb_peek(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; return child->ops->peek(child); } /* No sfb_drop -- impossible since the child doesn't return the dropped skb. */ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); if (likely(q->qdisc)) qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); sfb_init_perturbation(0, q); } static void sfb_destroy(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); qdisc_put(q->qdisc); } static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { [TCA_SFB_PARMS] = { .len = sizeof(struct tc_sfb_qopt) }, }; static const struct tc_sfb_qopt sfb_default_ops = { .rehash_interval = 600 * MSEC_PER_SEC, .warmup_time = 60 * MSEC_PER_SEC, .limit = 0, .max = 25, .bin_size = 20, .increment = (SFB_MAX_PROB + 500) / 1000, /* 0.1 % */ .decrement = (SFB_MAX_PROB + 3000) / 6000, .penalty_rate = 10, .penalty_burst = 20, }; static int sfb_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); struct Qdisc *child, *old; struct nlattr *tb[TCA_SFB_MAX + 1]; const struct tc_sfb_qopt *ctl = &sfb_default_ops; u32 limit; int err; if (opt) { err = nla_parse_nested_deprecated(tb, TCA_SFB_MAX, opt, sfb_policy, NULL); if (err < 0) return -EINVAL; if (tb[TCA_SFB_PARMS] == NULL) return -EINVAL; ctl = nla_data(tb[TCA_SFB_PARMS]); } limit = ctl->limit; if (limit == 0) limit = qdisc_dev(sch)->tx_queue_len; child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit, extack); if (IS_ERR(child)) return PTR_ERR(child); if (child != &noop_qdisc) qdisc_hash_add(child, true); sch_tree_lock(sch); qdisc_purge_queue(q->qdisc); old = q->qdisc; q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); q->warmup_time = msecs_to_jiffies(ctl->warmup_time); q->rehash_time = jiffies; q->limit = limit; q->increment = ctl->increment; q->decrement = ctl->decrement; q->max = ctl->max; q->bin_size = ctl->bin_size; q->penalty_rate = ctl->penalty_rate; q->penalty_burst = ctl->penalty_burst; q->tokens_avail = ctl->penalty_burst; q->token_time = jiffies; q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); sfb_init_perturbation(0, q); sfb_init_perturbation(1, q); sch_tree_unlock(sch); qdisc_put(old); return 0; } static int sfb_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); int err; err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; q->qdisc = &noop_qdisc; return sfb_change(sch, opt, extack); } static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) { struct sfb_sched_data *q = qdisc_priv(sch); struct nlattr *opts; struct tc_sfb_qopt opt = { .rehash_interval = jiffies_to_msecs(q->rehash_interval), .warmup_time = jiffies_to_msecs(q->warmup_time), .limit = q->limit, .max = q->max, .bin_size = q->bin_size, .increment = q->increment, .decrement = q->decrement, .penalty_rate = q->penalty_rate, .penalty_burst = q->penalty_burst, }; sch->qstats.backlog = q->qdisc->qstats.backlog; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -EMSGSIZE; } static int sfb_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct sfb_sched_data *q = qdisc_priv(sch); struct tc_sfb_xstats st = { .earlydrop = q->stats.earlydrop, .penaltydrop = q->stats.penaltydrop, .bucketdrop = q->stats.bucketdrop, .queuedrop = q->stats.queuedrop, .childdrop = q->stats.childdrop, .marked = q->stats.marked, }; st.maxqlen = sfb_compute_qlen(&st.maxprob, &st.avgprob, q); return gnet_stats_copy_app(d, &st, sizeof(st)); } static int sfb_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { return -ENOSYS; } static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); if (new == NULL) new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->qdisc); return 0; } static struct Qdisc *sfb_leaf(struct Qdisc *sch, unsigned long arg) { struct sfb_sched_data *q = qdisc_priv(sch); return q->qdisc; } static unsigned long sfb_find(struct Qdisc *sch, u32 classid) { return 1; } static void sfb_unbind(struct Qdisc *sch, unsigned long arg) { } static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg, struct netlink_ext_ack *extack) { return -ENOSYS; } static int sfb_delete(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { return -ENOSYS; } static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { tc_qdisc_stats_dump(sch, 1, walker); } } static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); if (cl) return NULL; return q->block; } static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { return 0; } static const struct Qdisc_class_ops sfb_class_ops = { .graft = sfb_graft, .leaf = sfb_leaf, .find = sfb_find, .change = sfb_change_class, .delete = sfb_delete, .walk = sfb_walk, .tcf_block = sfb_tcf_block, .bind_tcf = sfb_bind, .unbind_tcf = sfb_unbind, .dump = sfb_dump_class, }; static struct Qdisc_ops sfb_qdisc_ops __read_mostly = { .id = "sfb", .priv_size = sizeof(struct sfb_sched_data), .cl_ops = &sfb_class_ops, .enqueue = sfb_enqueue, .dequeue = sfb_dequeue, .peek = sfb_peek, .init = sfb_init, .reset = sfb_reset, .destroy = sfb_destroy, .change = sfb_change, .dump = sfb_dump, .dump_stats = sfb_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("sfb"); static int __init sfb_module_init(void) { return register_qdisc(&sfb_qdisc_ops); } static void __exit sfb_module_exit(void) { unregister_qdisc(&sfb_qdisc_ops); } module_init(sfb_module_init) module_exit(sfb_module_exit) MODULE_DESCRIPTION("Stochastic Fair Blue queue discipline"); MODULE_AUTHOR("Juliusz Chroboczek"); MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); |
| 9 9 9 9 9 9 9 9 1 9 2 9 9 2 9 9 5 8 8 8 8 11 5 2 3 5 3 3 1 11 11 3 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * PRNG: Pseudo Random Number Generator * Based on NIST Recommended PRNG From ANSI X9.31 Appendix A.2.4 using * AES 128 cipher * * (C) Neil Horman <nhorman@tuxdriver.com> */ #include <crypto/internal/cipher.h> #include <crypto/internal/rng.h> #include <linux/err.h> #include <linux/init.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/string.h> #define DEFAULT_PRNG_KEY "0123456789abcdef" #define DEFAULT_PRNG_KSZ 16 #define DEFAULT_BLK_SZ 16 #define DEFAULT_V_SEED "zaybxcwdveuftgsh" /* * Flags for the prng_context flags field */ #define PRNG_FIXED_SIZE 0x1 #define PRNG_NEED_RESET 0x2 /* * Note: DT is our counter value * I is our intermediate value * V is our seed vector * See http://csrc.nist.gov/groups/STM/cavp/documents/rng/931rngext.pdf * for implementation details */ struct prng_context { spinlock_t prng_lock; unsigned char rand_data[DEFAULT_BLK_SZ]; unsigned char last_rand_data[DEFAULT_BLK_SZ]; unsigned char DT[DEFAULT_BLK_SZ]; unsigned char I[DEFAULT_BLK_SZ]; unsigned char V[DEFAULT_BLK_SZ]; u32 rand_data_valid; struct crypto_cipher *tfm; u32 flags; }; static int dbg; static void hexdump(char *note, unsigned char *buf, unsigned int len) { if (dbg) { printk(KERN_CRIT "%s", note); print_hex_dump(KERN_CONT, "", DUMP_PREFIX_OFFSET, 16, 1, buf, len, false); } } #define dbgprint(format, args...) do {\ if (dbg)\ printk(format, ##args);\ } while (0) static void xor_vectors(unsigned char *in1, unsigned char *in2, unsigned char *out, unsigned int size) { int i; for (i = 0; i < size; i++) out[i] = in1[i] ^ in2[i]; } /* * Returns DEFAULT_BLK_SZ bytes of random data per call * returns 0 if generation succeeded, <0 if something went wrong */ static int _get_more_prng_bytes(struct prng_context *ctx, int cont_test) { int i; unsigned char tmp[DEFAULT_BLK_SZ]; unsigned char *output = NULL; dbgprint(KERN_CRIT "Calling _get_more_prng_bytes for context %p\n", ctx); hexdump("Input DT: ", ctx->DT, DEFAULT_BLK_SZ); hexdump("Input I: ", ctx->I, DEFAULT_BLK_SZ); hexdump("Input V: ", ctx->V, DEFAULT_BLK_SZ); /* * This algorithm is a 3 stage state machine */ for (i = 0; i < 3; i++) { switch (i) { case 0: /* * Start by encrypting the counter value * This gives us an intermediate value I */ memcpy(tmp, ctx->DT, DEFAULT_BLK_SZ); output = ctx->I; hexdump("tmp stage 0: ", tmp, DEFAULT_BLK_SZ); break; case 1: /* * Next xor I with our secret vector V * encrypt that result to obtain our * pseudo random data which we output */ xor_vectors(ctx->I, ctx->V, tmp, DEFAULT_BLK_SZ); hexdump("tmp stage 1: ", tmp, DEFAULT_BLK_SZ); output = ctx->rand_data; break; case 2: /* * First check that we didn't produce the same * random data that we did last time around through this */ if (!memcmp(ctx->rand_data, ctx->last_rand_data, DEFAULT_BLK_SZ)) { if (cont_test) { panic("cprng %p Failed repetition check!\n", ctx); } printk(KERN_ERR "ctx %p Failed repetition check!\n", ctx); ctx->flags |= PRNG_NEED_RESET; return -EINVAL; } memcpy(ctx->last_rand_data, ctx->rand_data, DEFAULT_BLK_SZ); /* * Lastly xor the random data with I * and encrypt that to obtain a new secret vector V */ xor_vectors(ctx->rand_data, ctx->I, tmp, DEFAULT_BLK_SZ); output = ctx->V; hexdump("tmp stage 2: ", tmp, DEFAULT_BLK_SZ); break; } /* do the encryption */ crypto_cipher_encrypt_one(ctx->tfm, output, tmp); } /* * Now update our DT value */ for (i = DEFAULT_BLK_SZ - 1; i >= 0; i--) { ctx->DT[i] += 1; if (ctx->DT[i] != 0) break; } dbgprint("Returning new block for context %p\n", ctx); ctx->rand_data_valid = 0; hexdump("Output DT: ", ctx->DT, DEFAULT_BLK_SZ); hexdump("Output I: ", ctx->I, DEFAULT_BLK_SZ); hexdump("Output V: ", ctx->V, DEFAULT_BLK_SZ); hexdump("New Random Data: ", ctx->rand_data, DEFAULT_BLK_SZ); return 0; } /* Our exported functions */ static int get_prng_bytes(char *buf, size_t nbytes, struct prng_context *ctx, int do_cont_test) { unsigned char *ptr = buf; unsigned int byte_count = (unsigned int)nbytes; int err; spin_lock_bh(&ctx->prng_lock); err = -EINVAL; if (ctx->flags & PRNG_NEED_RESET) goto done; /* * If the FIXED_SIZE flag is on, only return whole blocks of * pseudo random data */ err = -EINVAL; if (ctx->flags & PRNG_FIXED_SIZE) { if (nbytes < DEFAULT_BLK_SZ) goto done; byte_count = DEFAULT_BLK_SZ; } /* * Return 0 in case of success as mandated by the kernel * crypto API interface definition. */ err = 0; dbgprint(KERN_CRIT "getting %d random bytes for context %p\n", byte_count, ctx); remainder: if (ctx->rand_data_valid == DEFAULT_BLK_SZ) { if (_get_more_prng_bytes(ctx, do_cont_test) < 0) { memset(buf, 0, nbytes); err = -EINVAL; goto done; } } /* * Copy any data less than an entire block */ if (byte_count < DEFAULT_BLK_SZ) { empty_rbuf: while (ctx->rand_data_valid < DEFAULT_BLK_SZ) { *ptr = ctx->rand_data[ctx->rand_data_valid]; ptr++; byte_count--; ctx->rand_data_valid++; if (byte_count == 0) goto done; } } /* * Now copy whole blocks */ for (; byte_count >= DEFAULT_BLK_SZ; byte_count -= DEFAULT_BLK_SZ) { if (ctx->rand_data_valid == DEFAULT_BLK_SZ) { if (_get_more_prng_bytes(ctx, do_cont_test) < 0) { memset(buf, 0, nbytes); err = -EINVAL; goto done; } } if (ctx->rand_data_valid > 0) goto empty_rbuf; memcpy(ptr, ctx->rand_data, DEFAULT_BLK_SZ); ctx->rand_data_valid += DEFAULT_BLK_SZ; ptr += DEFAULT_BLK_SZ; } /* * Now go back and get any remaining partial block */ if (byte_count) goto remainder; done: spin_unlock_bh(&ctx->prng_lock); dbgprint(KERN_CRIT "returning %d from get_prng_bytes in context %p\n", err, ctx); return err; } static void free_prng_context(struct prng_context *ctx) { crypto_free_cipher(ctx->tfm); } static int reset_prng_context(struct prng_context *ctx, const unsigned char *key, size_t klen, const unsigned char *V, const unsigned char *DT) { int ret; const unsigned char *prng_key; spin_lock_bh(&ctx->prng_lock); ctx->flags |= PRNG_NEED_RESET; prng_key = (key != NULL) ? key : (unsigned char *)DEFAULT_PRNG_KEY; if (!key) klen = DEFAULT_PRNG_KSZ; if (V) memcpy(ctx->V, V, DEFAULT_BLK_SZ); else memcpy(ctx->V, DEFAULT_V_SEED, DEFAULT_BLK_SZ); if (DT) memcpy(ctx->DT, DT, DEFAULT_BLK_SZ); else memset(ctx->DT, 0, DEFAULT_BLK_SZ); memset(ctx->rand_data, 0, DEFAULT_BLK_SZ); memset(ctx->last_rand_data, 0, DEFAULT_BLK_SZ); ctx->rand_data_valid = DEFAULT_BLK_SZ; ret = crypto_cipher_setkey(ctx->tfm, prng_key, klen); if (ret) { dbgprint(KERN_CRIT "PRNG: setkey() failed flags=%x\n", crypto_cipher_get_flags(ctx->tfm)); goto out; } ret = 0; ctx->flags &= ~PRNG_NEED_RESET; out: spin_unlock_bh(&ctx->prng_lock); return ret; } static int cprng_init(struct crypto_tfm *tfm) { struct prng_context *ctx = crypto_tfm_ctx(tfm); spin_lock_init(&ctx->prng_lock); ctx->tfm = crypto_alloc_cipher("aes", 0, 0); if (IS_ERR(ctx->tfm)) { dbgprint(KERN_CRIT "Failed to alloc tfm for context %p\n", ctx); return PTR_ERR(ctx->tfm); } if (reset_prng_context(ctx, NULL, DEFAULT_PRNG_KSZ, NULL, NULL) < 0) return -EINVAL; /* * after allocation, we should always force the user to reset * so they don't inadvertently use the insecure default values * without specifying them intentially */ ctx->flags |= PRNG_NEED_RESET; return 0; } static void cprng_exit(struct crypto_tfm *tfm) { free_prng_context(crypto_tfm_ctx(tfm)); } static int cprng_get_random(struct crypto_rng *tfm, const u8 *src, unsigned int slen, u8 *rdata, unsigned int dlen) { struct prng_context *prng = crypto_rng_ctx(tfm); return get_prng_bytes(rdata, dlen, prng, 0); } /* * This is the cprng_registered reset method the seed value is * interpreted as the tuple { V KEY DT} * V and KEY are required during reset, and DT is optional, detected * as being present by testing the length of the seed */ static int cprng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) { struct prng_context *prng = crypto_rng_ctx(tfm); const u8 *key = seed + DEFAULT_BLK_SZ; const u8 *dt = NULL; if (slen < DEFAULT_PRNG_KSZ + DEFAULT_BLK_SZ) return -EINVAL; if (slen >= (2 * DEFAULT_BLK_SZ + DEFAULT_PRNG_KSZ)) dt = key + DEFAULT_PRNG_KSZ; reset_prng_context(prng, key, DEFAULT_PRNG_KSZ, seed, dt); if (prng->flags & PRNG_NEED_RESET) return -EINVAL; return 0; } #ifdef CONFIG_CRYPTO_FIPS static int fips_cprng_get_random(struct crypto_rng *tfm, const u8 *src, unsigned int slen, u8 *rdata, unsigned int dlen) { struct prng_context *prng = crypto_rng_ctx(tfm); return get_prng_bytes(rdata, dlen, prng, 1); } static int fips_cprng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) { u8 rdata[DEFAULT_BLK_SZ]; const u8 *key = seed + DEFAULT_BLK_SZ; int rc; struct prng_context *prng = crypto_rng_ctx(tfm); if (slen < DEFAULT_PRNG_KSZ + DEFAULT_BLK_SZ) return -EINVAL; /* fips strictly requires seed != key */ if (!memcmp(seed, key, DEFAULT_PRNG_KSZ)) return -EINVAL; rc = cprng_reset(tfm, seed, slen); if (!rc) goto out; /* this primes our continuity test */ rc = get_prng_bytes(rdata, DEFAULT_BLK_SZ, prng, 0); prng->rand_data_valid = DEFAULT_BLK_SZ; out: return rc; } #endif static struct rng_alg rng_algs[] = { { .generate = cprng_get_random, .seed = cprng_reset, .seedsize = DEFAULT_PRNG_KSZ + 2 * DEFAULT_BLK_SZ, .base = { .cra_name = "stdrng", .cra_driver_name = "ansi_cprng", .cra_priority = 100, .cra_ctxsize = sizeof(struct prng_context), .cra_module = THIS_MODULE, .cra_init = cprng_init, .cra_exit = cprng_exit, } #ifdef CONFIG_CRYPTO_FIPS }, { .generate = fips_cprng_get_random, .seed = fips_cprng_reset, .seedsize = DEFAULT_PRNG_KSZ + 2 * DEFAULT_BLK_SZ, .base = { .cra_name = "fips(ansi_cprng)", .cra_driver_name = "fips_ansi_cprng", .cra_priority = 300, .cra_ctxsize = sizeof(struct prng_context), .cra_module = THIS_MODULE, .cra_init = cprng_init, .cra_exit = cprng_exit, } #endif } }; /* Module initalization */ static int __init prng_mod_init(void) { return crypto_register_rngs(rng_algs, ARRAY_SIZE(rng_algs)); } static void __exit prng_mod_fini(void) { crypto_unregister_rngs(rng_algs, ARRAY_SIZE(rng_algs)); } MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Software Pseudo Random Number Generator"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); module_param(dbg, int, 0); MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)"); subsys_initcall(prng_mod_init); module_exit(prng_mod_fini); MODULE_ALIAS_CRYPTO("stdrng"); MODULE_ALIAS_CRYPTO("ansi_cprng"); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 38 38 38 38 38 38 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * HT handling * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018 - 2024 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "wme.h" /** * DOC: TX A-MPDU aggregation * * Aggregation on the TX side requires setting the hardware flag * %IEEE80211_HW_AMPDU_AGGREGATION. The driver will then be handed * packets with a flag indicating A-MPDU aggregation. The driver * or device is responsible for actually aggregating the frames, * as well as deciding how many and which to aggregate. * * When TX aggregation is started by some subsystem (usually the rate * control algorithm would be appropriate) by calling the * ieee80211_start_tx_ba_session() function, the driver will be * notified via its @ampdu_action function, with the * %IEEE80211_AMPDU_TX_START action. * * In response to that, the driver is later required to call the * ieee80211_start_tx_ba_cb_irqsafe() function, which will really * start the aggregation session after the peer has also responded. * If the peer responds negatively, the session will be stopped * again right away. Note that it is possible for the aggregation * session to be stopped before the driver has indicated that it * is done setting it up, in which case it must not indicate the * setup completion. * * Also note that, since we also need to wait for a response from * the peer, the driver is notified of the completion of the * handshake by the %IEEE80211_AMPDU_TX_OPERATIONAL action to the * @ampdu_action callback. * * Similarly, when the aggregation session is stopped by the peer * or something calling ieee80211_stop_tx_ba_session(), the driver's * @ampdu_action function will be called with the action * %IEEE80211_AMPDU_TX_STOP. In this case, the call must not fail, * and the driver must later call ieee80211_stop_tx_ba_cb_irqsafe(). * Note that the sta can get destroyed before the BA tear down is * complete. */ static void ieee80211_send_addba_request(struct sta_info *sta, u16 tid, u8 dialog_token, u16 start_seq_num, u16 agg_size, u16 timeout) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u16 capab; skb = dev_alloc_skb(sizeof(*mgmt) + 2 + sizeof(struct ieee80211_addba_ext_ie) + local->hw.extra_tx_headroom); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); mgmt = ieee80211_mgmt_ba(skb, sta->sta.addr, sdata); skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_req)); mgmt->u.action.category = WLAN_CATEGORY_BACK; mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ; mgmt->u.action.u.addba_req.dialog_token = dialog_token; capab = IEEE80211_ADDBA_PARAM_AMSDU_MASK; capab |= IEEE80211_ADDBA_PARAM_POLICY_MASK; capab |= u16_encode_bits(tid, IEEE80211_ADDBA_PARAM_TID_MASK); capab |= u16_encode_bits(agg_size, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK); mgmt->u.action.u.addba_req.capab = cpu_to_le16(capab); mgmt->u.action.u.addba_req.timeout = cpu_to_le16(timeout); mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4); if (sta->sta.deflink.he_cap.has_he) ieee80211_add_addbaext(skb, 0, agg_size); ieee80211_tx_skb_tid(sdata, skb, tid, -1); } void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_bar *bar; u16 bar_control = 0; skb = dev_alloc_skb(sizeof(*bar) + local->hw.extra_tx_headroom); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); bar = skb_put_zero(skb, sizeof(*bar)); bar->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); memcpy(bar->ra, ra, ETH_ALEN); memcpy(bar->ta, sdata->vif.addr, ETH_ALEN); bar_control |= (u16)IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL; bar_control |= (u16)IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA; bar_control |= (u16)(tid << IEEE80211_BAR_CTRL_TID_INFO_SHIFT); bar->control = cpu_to_le16(bar_control); bar->start_seq_num = cpu_to_le16(ssn); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_REQ_TX_STATUS; ieee80211_tx_skb_tid(sdata, skb, tid, -1); } EXPORT_SYMBOL(ieee80211_send_bar); void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) { lockdep_assert_wiphy(sta->local->hw.wiphy); lockdep_assert_held(&sta->lock); rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], tid_tx); } /* * When multiple aggregation sessions on multiple stations * are being created/destroyed simultaneously, we need to * refcount the global queue stop caused by that in order * to not get into a situation where one of the aggregation * setup or teardown re-enables queues before the other is * ready to handle that. * * These two functions take care of this issue by keeping * a global "agg_queue_stop" refcount. */ static void __acquires(agg_queue) ieee80211_stop_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; /* we do refcounting here, so don't use the queue reason refcounting */ if (atomic_inc_return(&sdata->local->agg_queue_stop[queue]) == 1) ieee80211_stop_queue_by_reason( &sdata->local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION, false); __acquire(agg_queue); } static void __releases(agg_queue) ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; if (atomic_dec_return(&sdata->local->agg_queue_stop[queue]) == 0) ieee80211_wake_queue_by_reason( &sdata->local->hw, queue, IEEE80211_QUEUE_STOP_REASON_AGGREGATION, false); __release(agg_queue); } static void ieee80211_agg_stop_txq(struct sta_info *sta, int tid) { struct ieee80211_txq *txq = sta->sta.txq[tid]; struct ieee80211_sub_if_data *sdata; struct fq *fq; struct txq_info *txqi; if (!txq) return; txqi = to_txq_info(txq); sdata = vif_to_sdata(txq->vif); fq = &sdata->local->fq; /* Lock here to protect against further seqno updates on dequeue */ spin_lock_bh(&fq->lock); set_bit(IEEE80211_TXQ_STOP, &txqi->flags); spin_unlock_bh(&fq->lock); } static void ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) { struct ieee80211_txq *txq = sta->sta.txq[tid]; struct txq_info *txqi; lockdep_assert_wiphy(sta->local->hw.wiphy); if (!txq) return; txqi = to_txq_info(txq); if (enable) set_bit(IEEE80211_TXQ_AMPDU, &txqi->flags); else clear_bit(IEEE80211_TXQ_AMPDU, &txqi->flags); clear_bit(IEEE80211_TXQ_STOP, &txqi->flags); local_bh_disable(); rcu_read_lock(); schedule_and_wake_txq(sta->sdata->local, txqi); rcu_read_unlock(); local_bh_enable(); } /* * splice packets from the STA's pending to the local pending, * requires a call to ieee80211_agg_splice_finish later */ static void __acquires(agg_queue) ieee80211_agg_splice_packets(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx, u16 tid) { struct ieee80211_local *local = sdata->local; int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; unsigned long flags; ieee80211_stop_queue_agg(sdata, tid); if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates from the pending queue\n", tid)) return; if (!skb_queue_empty(&tid_tx->pending)) { spin_lock_irqsave(&local->queue_stop_reason_lock, flags); /* copy over remaining packets */ skb_queue_splice_tail_init(&tid_tx->pending, &local->pending[queue]); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } } static void __releases(agg_queue) ieee80211_agg_splice_finish(struct ieee80211_sub_if_data *sdata, u16 tid) { ieee80211_wake_queue_agg(sdata, tid); } static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; lockdep_assert_wiphy(sta->local->hw.wiphy); lockdep_assert_held(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* * When we get here, the TX path will not be lockless any more wrt. * aggregation, since the OPERATIONAL bit has long been cleared. * Thus it will block on getting the lock, if it occurs. So if we * stop the queue now, we will not get any more packets, and any * that might be being processed will wait for us here, thereby * guaranteeing that no packets go to the tid_tx pending queue any * more. */ ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); /* future packets must not find the tid_tx struct any more */ ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sta->sdata, tid); kfree_rcu(tid_tx, rcu_head); } int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_agg_stop_reason reason) { struct ieee80211_local *local = sta->local; struct tid_ampdu_tx *tid_tx; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .tid = tid, .buf_size = 0, .amsdu = false, .timeout = 0, .ssn = 0, }; int ret; lockdep_assert_wiphy(sta->local->hw.wiphy); switch (reason) { case AGG_STOP_DECLINED: case AGG_STOP_LOCAL_REQUEST: case AGG_STOP_PEER_REQUEST: params.action = IEEE80211_AMPDU_TX_STOP_CONT; break; case AGG_STOP_DESTROY_STA: params.action = IEEE80211_AMPDU_TX_STOP_FLUSH; break; default: WARN_ON_ONCE(1); return -EINVAL; } spin_lock_bh(&sta->lock); /* free struct pending for start, if present */ tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; kfree(tid_tx); sta->ampdu_mlme.tid_start_tx[tid] = NULL; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) { spin_unlock_bh(&sta->lock); return -ENOENT; } /* * if we're already stopping ignore any new requests to stop * unless we're destroying it in which case notify the driver */ if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { spin_unlock_bh(&sta->lock); if (reason != AGG_STOP_DESTROY_STA) return -EALREADY; params.action = IEEE80211_AMPDU_TX_STOP_FLUSH_CONT; ret = drv_ampdu_action(local, sta->sdata, ¶ms); WARN_ON_ONCE(ret); return 0; } if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { /* not even started yet! */ ieee80211_assign_tid_tx(sta, tid, NULL); spin_unlock_bh(&sta->lock); kfree_rcu(tid_tx, rcu_head); return 0; } set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); ieee80211_agg_stop_txq(sta, tid); spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", sta->sta.addr, tid); timer_delete_sync(&tid_tx->addba_resp_timer); timer_delete_sync(&tid_tx->session_timer); /* * After this packets are no longer handed right through * to the driver but are put onto tid_tx->pending instead, * with locking to ensure proper access. */ clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); /* * There might be a few packets being processed right now (on * another CPU) that have already gotten past the aggregation * check when it was still OPERATIONAL and consequently have * IEEE80211_TX_CTL_AMPDU set. In that case, this code might * call into the driver at the same time or even before the * TX paths calls into it, which could confuse the driver. * * Wait for all currently running TX paths to finish before * telling the driver. New packets will not go through since * the aggregation session is no longer OPERATIONAL. */ if (!local->in_reconfig) synchronize_net(); tid_tx->stop_initiator = reason == AGG_STOP_PEER_REQUEST ? WLAN_BACK_RECIPIENT : WLAN_BACK_INITIATOR; tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST; ret = drv_ampdu_action(local, sta->sdata, ¶ms); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { /* * We may have pending packets get stuck in this case... * Not bothering with a workaround for now. */ } /* * In the case of AGG_STOP_DESTROY_STA, the driver won't * necessarily call ieee80211_stop_tx_ba_cb(), so this may * seem like we can leave the tid_tx data pending forever. * This is true, in a way, but "forever" is only until the * station struct is actually destroyed. In the meantime, * leaving it around ensures that we don't transmit packets * to the driver on this TID which might confuse it. */ return 0; } /* * After sending add Block Ack request we activated a timer until * add Block Ack response will arrive from the recipient. * If this timer expires sta_addba_resp_timer_expired will be executed. */ static void sta_addba_resp_timer_expired(struct timer_list *t) { struct tid_ampdu_tx *tid_tx = from_timer(tid_tx, t, addba_resp_timer); struct sta_info *sta = tid_tx->sta; u8 tid = tid_tx->tid; /* check if the TID waits for addBA response */ if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { ht_dbg(sta->sdata, "timer expired on %pM tid %d not expecting addBA response\n", sta->sta.addr, tid); return; } ht_dbg(sta->sdata, "addBA response timer expired on %pM tid %d\n", sta->sta.addr, tid); ieee80211_stop_tx_ba_session(&sta->sta, tid); } static void ieee80211_send_addba_with_timeout(struct sta_info *sta, struct tid_ampdu_tx *tid_tx) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sta->local; u8 tid = tid_tx->tid; u16 buf_size; if (WARN_ON_ONCE(test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state) || test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state))) return; lockdep_assert_wiphy(sta->local->hw.wiphy); /* activate the timer for the recipient's addBA response */ mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL); ht_dbg(sdata, "activated addBA response timer on %pM tid %d\n", sta->sta.addr, tid); spin_lock_bh(&sta->lock); sta->ampdu_mlme.last_addba_req_time[tid] = jiffies; sta->ampdu_mlme.addba_req_num[tid]++; spin_unlock_bh(&sta->lock); if (sta->sta.valid_links || sta->sta.deflink.eht_cap.has_eht || ieee80211_hw_check(&local->hw, STRICT)) { buf_size = local->hw.max_tx_aggregation_subframes; } else if (sta->sta.deflink.he_cap.has_he) { buf_size = min_t(u16, local->hw.max_tx_aggregation_subframes, IEEE80211_MAX_AMPDU_BUF_HE); } else { /* * We really should use what the driver told us it will * transmit as the maximum, but certain APs (e.g. the * LinkSys WRT120N with FW v1.0.07 build 002 Jun 18 2012) * will crash when we use a lower number. */ buf_size = IEEE80211_MAX_AMPDU_BUF_HT; } /* send AddBA request */ ieee80211_send_addba_request(sta, tid, tid_tx->dialog_token, tid_tx->ssn, buf_size, tid_tx->timeout); WARN_ON(test_and_set_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)); } void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_START, .tid = tid, .buf_size = 0, .amsdu = false, .timeout = 0, }; int ret; tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* * Start queuing up packets for this aggregation session. * We're going to release them once the driver is OK with * that. */ clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); /* * Make sure no packets are being processed. This ensures that * we have a valid starting sequence number and that in-flight * packets have been flushed out and no packets for this TID * will go into the driver during the ampdu_action call. */ synchronize_net(); params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); tid_tx->ssn = params.ssn; if (ret == IEEE80211_AMPDU_TX_START_DELAY_ADDBA) { return; } else if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) { /* * We didn't send the request yet, so don't need to check * here if we already got a response, just mark as driver * ready immediately. */ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state); } else if (ret) { ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", sta->sta.addr, tid); spin_lock_bh(&sta->lock); ieee80211_agg_splice_packets(sdata, tid_tx, tid); ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sdata, tid); spin_unlock_bh(&sta->lock); ieee80211_agg_start_txq(sta, tid, false); kfree_rcu(tid_tx, rcu_head); return; } ieee80211_send_addba_with_timeout(sta, tid_tx); } void ieee80211_refresh_tx_agg_session_timer(struct ieee80211_sta *pubsta, u16 tid) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct tid_ampdu_tx *tid_tx; if (WARN_ON_ONCE(tid >= IEEE80211_NUM_TIDS)) return; tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); if (!tid_tx) return; tid_tx->last_tx = jiffies; } EXPORT_SYMBOL(ieee80211_refresh_tx_agg_session_timer); /* * After accepting the AddBA Response we activated a timer, * resetting it after each frame that we send. */ static void sta_tx_agg_session_timer_expired(struct timer_list *t) { struct tid_ampdu_tx *tid_tx = from_timer(tid_tx, t, session_timer); struct sta_info *sta = tid_tx->sta; u8 tid = tid_tx->tid; unsigned long timeout; if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { return; } timeout = tid_tx->last_tx + TU_TO_JIFFIES(tid_tx->timeout); if (time_is_after_jiffies(timeout)) { mod_timer(&tid_tx->session_timer, timeout); return; } ht_dbg(sta->sdata, "tx session timer expired on %pM tid %d\n", sta->sta.addr, tid); ieee80211_stop_tx_ba_session(&sta->sta, tid); } int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, u16 timeout) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; int ret = 0; trace_api_start_tx_ba_session(pubsta, tid); if (WARN(sta->reserved_tid == tid, "Requested to start BA session on reserved tid=%d", tid)) return -EINVAL; if (!pubsta->valid_links && !pubsta->deflink.ht_cap.ht_supported && !pubsta->deflink.vht_cap.vht_supported && !pubsta->deflink.he_cap.has_he && !pubsta->deflink.eht_cap.has_eht) return -EINVAL; if (WARN_ON_ONCE(!local->ops->ampdu_action)) return -EINVAL; if ((tid >= IEEE80211_NUM_TIDS) || !ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION) || ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW)) return -EINVAL; if (WARN_ON(tid >= IEEE80211_FIRST_TSPEC_TSID)) return -EINVAL; ht_dbg(sdata, "Open BA session requested for %pM tid %u\n", pubsta->addr, tid); if (sdata->vif.type != NL80211_IFTYPE_STATION && sdata->vif.type != NL80211_IFTYPE_MESH_POINT && sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_AP && sdata->vif.type != NL80211_IFTYPE_ADHOC) return -EINVAL; if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { ht_dbg(sdata, "BA sessions blocked - Denying BA session request %pM tid %d\n", sta->sta.addr, tid); return -EINVAL; } if (test_sta_flag(sta, WLAN_STA_MFP) && !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { ht_dbg(sdata, "MFP STA not authorized - deny BA session request %pM tid %d\n", sta->sta.addr, tid); return -EINVAL; } /* * 802.11n-2009 11.5.1.1: If the initiating STA is an HT STA, is a * member of an IBSS, and has no other existing Block Ack agreement * with the recipient STA, then the initiating STA shall transmit a * Probe Request frame to the recipient STA and shall not transmit an * ADDBA Request frame unless it receives a Probe Response frame * from the recipient within dot11ADDBAFailureTimeout. * * The probe request mechanism for ADDBA is currently not implemented, * but we only build up Block Ack session with HT STAs. This information * is set when we receive a bss info from a probe response or a beacon. */ if (sta->sdata->vif.type == NL80211_IFTYPE_ADHOC && !sta->sta.deflink.ht_cap.ht_supported) { ht_dbg(sdata, "BA request denied - IBSS STA %pM does not advertise HT support\n", pubsta->addr); return -EINVAL; } spin_lock_bh(&sta->lock); /* we have tried too many times, receiver does not want A-MPDU */ if (sta->ampdu_mlme.addba_req_num[tid] > HT_AGG_MAX_RETRIES) { ret = -EBUSY; goto err_unlock_sta; } /* * if we have tried more than HT_AGG_BURST_RETRIES times we * will spread our requests in time to avoid stalling connection * for too long */ if (sta->ampdu_mlme.addba_req_num[tid] > HT_AGG_BURST_RETRIES && time_before(jiffies, sta->ampdu_mlme.last_addba_req_time[tid] + HT_AGG_RETRIES_PERIOD)) { ht_dbg(sdata, "BA request denied - %d failed requests on %pM tid %u\n", sta->ampdu_mlme.addba_req_num[tid], sta->sta.addr, tid); ret = -EBUSY; goto err_unlock_sta; } tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* check if the TID is not in aggregation flow already */ if (tid_tx || sta->ampdu_mlme.tid_start_tx[tid]) { ht_dbg(sdata, "BA request denied - session is not idle on %pM tid %u\n", sta->sta.addr, tid); ret = -EAGAIN; goto err_unlock_sta; } /* prepare A-MPDU MLME for Tx aggregation */ tid_tx = kzalloc(sizeof(struct tid_ampdu_tx), GFP_ATOMIC); if (!tid_tx) { ret = -ENOMEM; goto err_unlock_sta; } skb_queue_head_init(&tid_tx->pending); __set_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); tid_tx->timeout = timeout; tid_tx->sta = sta; tid_tx->tid = tid; /* response timer */ timer_setup(&tid_tx->addba_resp_timer, sta_addba_resp_timer_expired, 0); /* tx timer */ timer_setup(&tid_tx->session_timer, sta_tx_agg_session_timer_expired, TIMER_DEFERRABLE); /* assign a dialog token */ sta->ampdu_mlme.dialog_token_allocator++; tid_tx->dialog_token = sta->ampdu_mlme.dialog_token_allocator; /* * Finally, assign it to the start array; the work item will * collect it and move it to the normal array. */ sta->ampdu_mlme.tid_start_tx[tid] = tid_tx; wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); /* this flow continues off the work */ err_unlock_sta: spin_unlock_bh(&sta->lock); return ret; } EXPORT_SYMBOL(ieee80211_start_tx_ba_session); static void ieee80211_agg_tx_operational(struct ieee80211_local *local, struct sta_info *sta, u16 tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_OPERATIONAL, .tid = tid, .timeout = 0, .ssn = 0, }; lockdep_assert_wiphy(sta->local->hw.wiphy); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); params.buf_size = tid_tx->buf_size; params.amsdu = tid_tx->amsdu; ht_dbg(sta->sdata, "Aggregation is on for %pM tid %d\n", sta->sta.addr, tid); drv_ampdu_action(local, sta->sdata, ¶ms); /* * synchronize with TX path, while splicing the TX path * should block so it won't put more packets onto pending. */ spin_lock_bh(&sta->lock); ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); /* * Now mark as operational. This will be visible * in the TX path, and lets it go lock-free in * the common case. */ set_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); ieee80211_agg_splice_finish(sta->sdata, tid); spin_unlock_bh(&sta->lock); ieee80211_agg_start_txq(sta, tid, true); } void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(sta->local->hw.wiphy); if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state))) return; if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state) || test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) return; if (!test_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)) { ieee80211_send_addba_with_timeout(sta, tid_tx); /* RESPONSE_RECEIVED state would trigger the flow again */ return; } if (test_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); } static struct tid_ampdu_tx * ieee80211_lookup_tid_tx(struct ieee80211_sub_if_data *sdata, const u8 *ra, u16 tid, struct sta_info **sta) { struct tid_ampdu_tx *tid_tx; if (tid >= IEEE80211_NUM_TIDS) { ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", tid, IEEE80211_NUM_TIDS); return NULL; } *sta = sta_info_get_bss(sdata, ra); if (!*sta) { ht_dbg(sdata, "Could not find station: %pM\n", ra); return NULL; } tid_tx = rcu_dereference((*sta)->ampdu_mlme.tid_tx[tid]); if (WARN_ON(!tid_tx)) ht_dbg(sdata, "addBA was not requested!\n"); return tid_tx; } void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct tid_ampdu_tx *tid_tx; trace_api_start_tx_ba_cb(sdata, ra, tid); rcu_read_lock(); tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta); if (!tid_tx) goto out; set_bit(HT_AGG_STATE_START_CB, &tid_tx->state); wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); out: rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe); int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; int ret = 0; trace_api_stop_tx_ba_session(pubsta, tid); if (!local->ops->ampdu_action) return -EINVAL; if (tid >= IEEE80211_NUM_TIDS) return -EINVAL; spin_lock_bh(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) { ret = -ENOENT; goto unlock; } WARN(sta->reserved_tid == tid, "Requested to stop BA session on reserved tid=%d", tid); if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { /* already in progress stopping it */ ret = 0; goto unlock; } set_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state); wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); unlock: spin_unlock_bh(&sta->lock); return ret; } EXPORT_SYMBOL(ieee80211_stop_tx_ba_session); void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, struct tid_ampdu_tx *tid_tx) { struct ieee80211_sub_if_data *sdata = sta->sdata; bool send_delba = false; bool start_txq = false; ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", sta->sta.addr, tid); spin_lock_bh(&sta->lock); if (!test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { ht_dbg(sdata, "unexpected callback to A-MPDU stop for %pM tid %d\n", sta->sta.addr, tid); goto unlock_sta; } if (tid_tx->stop_initiator == WLAN_BACK_INITIATOR && tid_tx->tx_stop) send_delba = true; ieee80211_remove_tid_tx(sta, tid); start_txq = true; unlock_sta: spin_unlock_bh(&sta->lock); if (start_txq) ieee80211_agg_start_txq(sta, tid, false); if (send_delba) ieee80211_send_delba(sdata, sta->sta.addr, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); } void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct tid_ampdu_tx *tid_tx; trace_api_stop_tx_ba_cb(sdata, ra, tid); rcu_read_lock(); tid_tx = ieee80211_lookup_tid_tx(sdata, ra, tid, &sta); if (!tid_tx) goto out; set_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state); wiphy_work_queue(local->hw.wiphy, &sta->ampdu_mlme.work); out: rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb_irqsafe); void ieee80211_process_addba_resp(struct ieee80211_local *local, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len) { struct tid_ampdu_tx *tid_tx; struct ieee80211_txq *txq; u16 capab, tid, buf_size; bool amsdu; lockdep_assert_wiphy(sta->local->hw.wiphy); capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK; tid = u16_get_bits(capab, IEEE80211_ADDBA_PARAM_TID_MASK); buf_size = u16_get_bits(capab, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK); ieee80211_retrieve_addba_ext_data(sta, mgmt->u.action.u.addba_resp.variable, len - offsetof(typeof(*mgmt), u.action.u.addba_resp.variable), &buf_size); buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes); txq = sta->sta.txq[tid]; if (!amsdu && txq) set_bit(IEEE80211_TXQ_NO_AMSDU, &to_txq_info(txq)->flags); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); if (!tid_tx) return; if (mgmt->u.action.u.addba_resp.dialog_token != tid_tx->dialog_token) { ht_dbg(sta->sdata, "wrong addBA response token, %pM tid %d\n", sta->sta.addr, tid); return; } timer_delete_sync(&tid_tx->addba_resp_timer); ht_dbg(sta->sdata, "switched off addBA timer for %pM tid %d\n", sta->sta.addr, tid); /* * addba_resp_timer may have fired before we got here, and * caused WANT_STOP to be set. If the stop then was already * processed further, STOPPING might be set. */ if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) || test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { ht_dbg(sta->sdata, "got addBA resp for %pM tid %d but we already gave up\n", sta->sta.addr, tid); return; } /* * IEEE 802.11-2007 7.3.1.14: * In an ADDBA Response frame, when the Status Code field * is set to 0, the Buffer Size subfield is set to a value * of at least 1. */ if (le16_to_cpu(mgmt->u.action.u.addba_resp.status) == WLAN_STATUS_SUCCESS && buf_size) { if (test_and_set_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { /* ignore duplicate response */ return; } tid_tx->buf_size = buf_size; tid_tx->amsdu = amsdu; if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); sta->ampdu_mlme.addba_req_num[tid] = 0; tid_tx->timeout = le16_to_cpu(mgmt->u.action.u.addba_resp.timeout); if (tid_tx->timeout) { mod_timer(&tid_tx->session_timer, TU_TO_EXP_TIME(tid_tx->timeout)); tid_tx->last_tx = jiffies; } } else { __ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_DECLINED); } } |
| 66 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * AEAD: Authenticated Encryption with Associated Data * * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_AEAD_H #define _CRYPTO_INTERNAL_AEAD_H #include <crypto/aead.h> #include <crypto/algapi.h> #include <linux/stddef.h> #include <linux/types.h> struct rtattr; struct aead_instance { void (*free)(struct aead_instance *inst); union { struct { char head[offsetof(struct aead_alg, base)]; struct crypto_instance base; } s; struct aead_alg alg; }; }; struct crypto_aead_spawn { struct crypto_spawn base; }; struct aead_queue { struct crypto_queue base; }; static inline void *crypto_aead_ctx(struct crypto_aead *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void *crypto_aead_ctx_dma(struct crypto_aead *tfm) { return crypto_tfm_ctx_dma(&tfm->base); } static inline struct crypto_instance *aead_crypto_instance( struct aead_instance *inst) { return container_of(&inst->alg.base, struct crypto_instance, alg); } static inline struct aead_instance *aead_instance(struct crypto_instance *inst) { return container_of(&inst->alg, struct aead_instance, alg.base); } static inline struct aead_instance *aead_alg_instance(struct crypto_aead *aead) { return aead_instance(crypto_tfm_alg_instance(&aead->base)); } static inline void *aead_instance_ctx(struct aead_instance *inst) { return crypto_instance_ctx(aead_crypto_instance(inst)); } static inline void *aead_request_ctx(struct aead_request *req) { return req->__ctx; } static inline void *aead_request_ctx_dma(struct aead_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(aead_request_ctx(req), align); } static inline void aead_request_complete(struct aead_request *req, int err) { crypto_request_complete(&req->base, err); } static inline u32 aead_request_flags(struct aead_request *req) { return req->base.flags; } static inline struct aead_request *aead_request_cast( struct crypto_async_request *req) { return container_of(req, struct aead_request, base); } int crypto_grab_aead(struct crypto_aead_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_aead(struct crypto_aead_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct aead_alg *crypto_spawn_aead_alg( struct crypto_aead_spawn *spawn) { return container_of(spawn->base.alg, struct aead_alg, base); } static inline struct crypto_aead *crypto_spawn_aead( struct crypto_aead_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline void crypto_aead_set_reqsize(struct crypto_aead *aead, unsigned int reqsize) { aead->reqsize = reqsize; } static inline void crypto_aead_set_reqsize_dma(struct crypto_aead *aead, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); aead->reqsize = reqsize; } static inline void aead_init_queue(struct aead_queue *queue, unsigned int max_qlen) { crypto_init_queue(&queue->base, max_qlen); } static inline unsigned int crypto_aead_alg_chunksize(struct aead_alg *alg) { return alg->chunksize; } /** * crypto_aead_chunksize() - obtain chunk size * @tfm: cipher handle * * The block size is set to one for ciphers such as CCM. However, * you still need to provide incremental updates in multiples of * the underlying block size as the IV does not have sub-block * granularity. This is known in this API as the chunk size. * * Return: chunk size in bytes */ static inline unsigned int crypto_aead_chunksize(struct crypto_aead *tfm) { return crypto_aead_alg_chunksize(crypto_aead_alg(tfm)); } int crypto_register_aead(struct aead_alg *alg); void crypto_unregister_aead(struct aead_alg *alg); int crypto_register_aeads(struct aead_alg *algs, int count); void crypto_unregister_aeads(struct aead_alg *algs, int count); int aead_register_instance(struct crypto_template *tmpl, struct aead_instance *inst); #endif /* _CRYPTO_INTERNAL_AEAD_H */ |
| 692 409 416 414 415 416 415 2 2 2 2 2 174 174 174 173 3 171 162 16 173 173 173 173 300 301 88 4 236 193 125 297 3 1 300 4 297 297 297 3 300 298 300 301 300 247 161 136 161 102 130 152 14 249 250 219 189 186 2 8 1 8 5 248 250 166 166 251 8 296 297 246 158 17 17 17 17 17 16 1 17 55 55 28 433 54 412 151 85 77 10 10 324 410 312 45 350 171 131 397 365 115 363 480 410 370 13 4 27 25 3 11 15 27 371 20 356 496 378 448 91 420 14 14 14 14 14 57 97 29 13 3 42 7 7 7 46 174 174 24 2 9 13 2 23 524 500 155 32 1 8 15 11 423 17 404 2 10 10 3 7 435 113 265 4 91 91 91 353 353 59 4 57 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2002, 2004 * Copyright (c) 2001 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * Copyright (c) 2002-2003 Intel Corp. * * This file is part of the SCTP kernel implementation * * SCTP over IPv6. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Le Yanqun <yanqun.le@nokia.com> * Hui Huang <hui.huang@nokia.com> * La Monte H.P. Yarroll <piggy@acm.org> * Sridhar Samudrala <sri@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * * Based on: * linux/net/ipv6/tcp_ipv6.c */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/init.h> #include <linux/ipsec.h> #include <linux/slab.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/seq_file.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/sctp/sctp.h> #include <net/udp_tunnel.h> #include <linux/uaccess.h> static inline int sctp_v6_addr_match_len(union sctp_addr *s1, union sctp_addr *s2); static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, __be16 port); static int sctp_v6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2); /* Event handler for inet6 address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same * time and thus corrupt the list. * The reader side is protected with RCU. */ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct sctp_sockaddr_entry *addr = NULL; struct sctp_sockaddr_entry *temp; struct net *net = dev_net(ifa->idev->dev); int found = 0; switch (ev) { case NETDEV_UP: addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; spin_lock_bh(&net->sctp.local_addr_lock); list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list); sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW); spin_unlock_bh(&net->sctp.local_addr_lock); } break; case NETDEV_DOWN: spin_lock_bh(&net->sctp.local_addr_lock); list_for_each_entry_safe(addr, temp, &net->sctp.local_addr_list, list) { if (addr->a.sa.sa_family == AF_INET6 && ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr) && addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { found = 1; addr->valid = 0; list_del_rcu(&addr->list); sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); break; } } spin_unlock_bh(&net->sctp.local_addr_lock); if (found) kfree_rcu(addr, rcu); break; } return NOTIFY_DONE; } static struct notifier_block sctp_inet6addr_notifier = { .notifier_call = sctp_inet6addr_event, }; static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, __u8 type, __u8 code, __u32 info) { struct sctp_association *asoc = t->asoc; struct sock *sk = asoc->base.sk; int err = 0; switch (type) { case ICMPV6_PKT_TOOBIG: if (ip6_sk_accept_pmtu(sk)) sctp_icmp_frag_needed(sk, asoc, t, info); return; case ICMPV6_PARAMPROB: if (ICMPV6_UNK_NEXTHDR == code) { sctp_icmp_proto_unreachable(sk, asoc, t); return; } break; case NDISC_REDIRECT: sctp_icmp_redirect(sk, t, skb); return; default: break; } icmpv6_err_convert(type, code, &err); if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { sk->sk_err = err; sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } } /* ICMP error handler. */ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct sctp_transport *transport; struct sctp_association *asoc; __u16 saveip, savesctp; struct sock *sk; /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; skb_reset_network_header(skb); skb_set_transport_header(skb, offset); sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport); /* Put back, the original pointers. */ skb->network_header = saveip; skb->transport_header = savesctp; if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } sctp_v6_err_handle(transport, skb, type, code, ntohl(info)); sctp_err_finish(sk, transport); return 0; } int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sctp_association *asoc; struct sctp_transport *t; struct icmp6hdr *hdr; __u32 info = 0; skb->transport_header += sizeof(struct udphdr); sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &t); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } skb->transport_header -= sizeof(struct udphdr); hdr = (struct icmp6hdr *)(skb_network_header(skb) - sizeof(struct icmp6hdr)); if (hdr->icmp6_type == NDISC_REDIRECT) { /* can't be handled without outer ip6hdr known, leave it to udpv6_err */ sctp_err_finish(sk, t); return 0; } if (hdr->icmp6_type == ICMPV6_PKT_TOOBIG) info = ntohl(hdr->icmp6_mtu); sctp_v6_err_handle(t, skb, hdr->icmp6_type, hdr->icmp6_code, info); sctp_err_finish(sk, t); return 1; } static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) { struct dst_entry *dst = dst_clone(t->dst); struct flowi6 *fl6 = &t->fl.u.ip6; struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); __u8 tclass = np->tclass; __be32 label; pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, skb->len, &fl6->saddr, &fl6->daddr); if (t->dscp & SCTP_DSCP_SET_MASK) tclass = t->dscp & SCTP_DSCP_VAL_MASK; if (INET_ECN_is_capable(tclass)) IP6_ECN_flow_xmit(sk, fl6->flowlabel); if (!(t->param_flags & SPP_PMTUD_ENABLE)) skb->ignore_df = 1; SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); if (!t->encap_port || !sctp_sk(sk)->udp_port) { int res; skb_dst_set(skb, dst); rcu_read_lock(); res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); return res; } if (skb_is_gso(skb)) skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; skb->encapsulation = 1; skb_reset_inner_mac_header(skb); skb_reset_inner_transport_header(skb); skb_set_inner_ipproto(skb, IPPROTO_SCTP); label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6); return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, &fl6->daddr, tclass, ip6_dst_hoplimit(dst), label, sctp_sk(sk)->udp_port, t->encap_port, false); } /* Returns the dst cache entry for the given source and destination ip * addresses. */ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct flowi *fl, struct sock *sk) { struct sctp_association *asoc = t->asoc; struct dst_entry *dst = NULL; struct flowi _fl; struct flowi6 *fl6 = &_fl.u.ip6; struct sctp_bind_addr *bp; struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; struct in6_addr *final_p, final; enum sctp_scope scope; __u8 matchlen = 0; memset(&_fl, 0, sizeof(_fl)); fl6->daddr = daddr->v6.sin6_addr; fl6->fl6_dport = daddr->v6.sin6_port; fl6->flowi6_proto = IPPROTO_SCTP; if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) fl6->flowi6_oif = daddr->v6.sin6_scope_id; else if (asoc) fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if; if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK) fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK); if (inet6_test_bit(SNDFLOW, sk) && (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) goto out; fl6_sock_release(flowlabel); } pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr); if (asoc) fl6->fl6_sport = htons(asoc->base.bind_addr.port); if (saddr) { fl6->saddr = saddr->v6.sin6_addr; if (!fl6->fl6_sport) fl6->fl6_sport = saddr->v6.sin6_port; pr_debug("src=%pI6 - ", &fl6->saddr); } rcu_read_lock(); final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!asoc || saddr) { t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); goto out; } bp = &asoc->base.bind_addr; scope = sctp_scope(daddr); /* ip6_dst_lookup has filled in the fl6->saddr for us. Check * to see if we can use it. */ if (!IS_ERR(dst)) { /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ sctp_v6_to_addr(&dst_saddr, &fl6->saddr, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid || laddr->state == SCTP_ADDR_DEL || (laddr->state != SCTP_ADDR_SRC && !asoc->src_out_of_asoc_ok)) continue; /* Do not compare against v4 addrs */ if ((laddr->a.sa.sa_family == AF_INET6) && (sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) { rcu_read_unlock(); t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); goto out; } } rcu_read_unlock(); /* None of the bound addresses match the source address of the * dst. So release it. */ dst_release(dst); dst = NULL; } /* Walk through the bind address list and try to get the * best source address for a given destination. */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { struct dst_entry *bdst; __u8 bmatchlen; if (!laddr->valid || laddr->state != SCTP_ADDR_SRC || laddr->a.sa.sa_family != AF_INET6 || scope > sctp_scope(&laddr->a)) continue; fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(bdst)) continue; if (ipv6_chk_addr(dev_net(bdst->dev), &laddr->a.v6.sin6_addr, bdst->dev, 1)) { if (!IS_ERR_OR_NULL(dst)) dst_release(dst); dst = bdst; t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); break; } bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); if (matchlen > bmatchlen) { dst_release(bdst); continue; } if (!IS_ERR_OR_NULL(dst)) dst_release(dst); dst = bdst; matchlen = bmatchlen; t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); } rcu_read_unlock(); out: if (!IS_ERR_OR_NULL(dst)) { struct rt6_info *rt; rt = dst_rt6_info(dst); t->dst_cookie = rt6_get_cookie(rt); pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n", &rt->rt6i_dst.addr, rt->rt6i_dst.plen, &fl->u.ip6.saddr); } else { t->dst = NULL; pr_debug("no route\n"); } } /* Returns the number of consecutive initial bits that match in the 2 ipv6 * addresses. */ static inline int sctp_v6_addr_match_len(union sctp_addr *s1, union sctp_addr *s2) { return ipv6_addr_diff(&s1->v6.sin6_addr, &s2->v6.sin6_addr); } /* Fills in the source address(saddr) based on the destination address(daddr) * and asoc's bind address list. */ static void sctp_v6_get_saddr(struct sctp_sock *sk, struct sctp_transport *t, struct flowi *fl) { struct flowi6 *fl6 = &fl->u.ip6; union sctp_addr *saddr = &t->saddr; pr_debug("%s: asoc:%p dst:%p\n", __func__, t->asoc, t->dst); if (t->dst) { saddr->v6.sin6_family = AF_INET6; saddr->v6.sin6_addr = fl6->saddr; } } /* Make a copy of all potential local addresses. */ static void sctp_v6_copy_addrlist(struct list_head *addrlist, struct net_device *dev) { struct inet6_dev *in6_dev; struct inet6_ifaddr *ifp; struct sctp_sockaddr_entry *addr; rcu_read_lock(); if ((in6_dev = __in6_dev_get(dev)) == NULL) { rcu_read_unlock(); return; } read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { /* Add the address to the local list. */ addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; addr->a.v6.sin6_addr = ifp->addr; addr->a.v6.sin6_scope_id = dev->ifindex; addr->valid = 1; INIT_LIST_HEAD(&addr->list); list_add_tail(&addr->list, addrlist); } } read_unlock_bh(&in6_dev->lock); rcu_read_unlock(); } /* Copy over any ip options */ static void sctp_v6_copy_ip_options(struct sock *sk, struct sock *newsk) { struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct ipv6_txoptions *opt; newnp = inet6_sk(newsk); rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); if (!opt) pr_err("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newnp->opt, opt); rcu_read_unlock(); } /* Account for the IP options */ static int sctp_v6_ip_options_len(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt; int len = 0; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) len = opt->opt_flen + opt->opt_nflen; rcu_read_unlock(); return len; } /* Initialize a sockaddr_storage from in incoming skb. */ static void sctp_v6_from_skb(union sctp_addr *addr, struct sk_buff *skb, int is_saddr) { /* Always called on head skb, so this is safe */ struct sctphdr *sh = sctp_hdr(skb); struct sockaddr_in6 *sa = &addr->v6; addr->v6.sin6_family = AF_INET6; addr->v6.sin6_flowinfo = 0; /* FIXME */ addr->v6.sin6_scope_id = ((struct inet6_skb_parm *)skb->cb)->iif; if (is_saddr) { sa->sin6_port = sh->source; sa->sin6_addr = ipv6_hdr(skb)->saddr; } else { sa->sin6_port = sh->dest; sa->sin6_addr = ipv6_hdr(skb)->daddr; } } /* Initialize an sctp_addr from a socket. */ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = 0; addr->v6.sin6_addr = sk->sk_v6_rcv_saddr; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { if (addr->sa.sa_family == AF_INET) { sk->sk_v6_rcv_saddr.s6_addr32[0] = 0; sk->sk_v6_rcv_saddr.s6_addr32[1] = 0; sk->sk_v6_rcv_saddr.s6_addr32[2] = htonl(0x0000ffff); sk->sk_v6_rcv_saddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; } else { sk->sk_v6_rcv_saddr = addr->v6.sin6_addr; } } /* Initialize sk->sk_daddr from sctp_addr. */ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { if (addr->sa.sa_family == AF_INET) { sk->sk_v6_daddr.s6_addr32[0] = 0; sk->sk_v6_daddr.s6_addr32[1] = 0; sk->sk_v6_daddr.s6_addr32[2] = htonl(0x0000ffff); sk->sk_v6_daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; } else { sk->sk_v6_daddr = addr->v6.sin6_addr; } } /* Initialize a sctp_addr from an address parameter. */ static bool sctp_v6_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param)) return false; addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; /* BUG */ addr->v6.sin6_addr = param->v6.addr; addr->v6.sin6_scope_id = iif; return true; } /* Initialize an address parameter from a sctp_addr and return the length * of the address parameter. */ static int sctp_v6_to_addr_param(const union sctp_addr *addr, union sctp_addr_param *param) { int length = sizeof(struct sctp_ipv6addr_param); param->v6.param_hdr.type = SCTP_PARAM_IPV6_ADDRESS; param->v6.param_hdr.length = htons(length); param->v6.addr = addr->v6.sin6_addr; return length; } /* Initialize a sctp_addr from struct in6_addr. */ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, __be16 port) { addr->sa.sa_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; addr->v6.sin6_addr = *saddr; addr->v6.sin6_scope_id = 0; } static int __sctp_v6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2) { if (addr1->sa.sa_family != addr2->sa.sa_family) { if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET6 && ipv6_addr_v4mapped(&addr2->v6.sin6_addr) && addr2->v6.sin6_addr.s6_addr32[3] == addr1->v4.sin_addr.s_addr) return 1; if (addr2->sa.sa_family == AF_INET && addr1->sa.sa_family == AF_INET6 && ipv6_addr_v4mapped(&addr1->v6.sin6_addr) && addr1->v6.sin6_addr.s6_addr32[3] == addr2->v4.sin_addr.s_addr) return 1; return 0; } if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) && addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id) return 0; return 1; } /* Compare addresses exactly. * v4-mapped-v6 is also in consideration. */ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2) { return __sctp_v6_cmp_addr(addr1, addr2) && addr1->v6.sin6_port == addr2->v6.sin6_port; } /* Initialize addr struct to INADDR_ANY. */ static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port) { memset(addr, 0x00, sizeof(union sctp_addr)); addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; } /* Is this a wildcard address? */ static int sctp_v6_is_any(const union sctp_addr *addr) { return ipv6_addr_any(&addr->v6.sin6_addr); } /* Should this be available for binding? */ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) { const struct in6_addr *in6 = (const struct in6_addr *)&addr->v6.sin6_addr; struct sock *sk = &sp->inet.sk; struct net *net = sock_net(sk); struct net_device *dev = NULL; int type, res, bound_dev_if; type = ipv6_addr_type(in6); if (IPV6_ADDR_ANY == type) return 1; if (type == IPV6_ADDR_MAPPED) { if (sp && ipv6_only_sock(sctp_opt2sk(sp))) return 0; sctp_v6_map_v4(addr); return sctp_get_af_specific(AF_INET)->available(addr, sp); } if (!(type & IPV6_ADDR_UNICAST)) return 0; rcu_read_lock(); bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if) { res = 0; dev = dev_get_by_index_rcu(net, bound_dev_if); if (!dev) goto out; } res = ipv6_can_nonlocal_bind(net, &sp->inet) || ipv6_chk_addr(net, in6, dev, 0); out: rcu_read_unlock(); return res; } /* This function checks if the address is a valid address to be used for * SCTP. * * Output: * Return 0 - If the address is a non-unicast or an illegal address. * Return 1 - If the address is a unicast. */ static int sctp_v6_addr_valid(union sctp_addr *addr, struct sctp_sock *sp, const struct sk_buff *skb) { int ret = ipv6_addr_type(&addr->v6.sin6_addr); /* Support v4-mapped-v6 address. */ if (ret == IPV6_ADDR_MAPPED) { /* Note: This routine is used in input, so v4-mapped-v6 * are disallowed here when there is no sctp_sock. */ if (sp && ipv6_only_sock(sctp_opt2sk(sp))) return 0; sctp_v6_map_v4(addr); return sctp_get_af_specific(AF_INET)->addr_valid(addr, sp, skb); } /* Is this a non-unicast address */ if (!(ret & IPV6_ADDR_UNICAST)) return 0; return 1; } /* What is the scope of 'addr'? */ static enum sctp_scope sctp_v6_scope(union sctp_addr *addr) { enum sctp_scope retval; int v6scope; /* The IPv6 scope is really a set of bit fields. * See IFA_* in <net/if_inet6.h>. Map to a generic SCTP scope. */ v6scope = ipv6_addr_scope(&addr->v6.sin6_addr); switch (v6scope) { case IFA_HOST: retval = SCTP_SCOPE_LOOPBACK; break; case IFA_LINK: retval = SCTP_SCOPE_LINK; break; case IFA_SITE: retval = SCTP_SCOPE_PRIVATE; break; default: retval = SCTP_SCOPE_GLOBAL; break; } return retval; } /* Create and initialize a new sk for the socket to be returned by accept(). */ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct sctp_association *asoc, bool kern) { struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); if (!newsk) goto out; sock_init_data(NULL, newsk); sctp_copy_sock(newsk, sk, asoc); sock_reset_flag(sk, SOCK_ZAPPED); newsctp6sk = (struct sctp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newsctp6sk->inet6; sctp_sk(newsk)->v4mapped = sctp_sk(sk)->v4mapped; newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; sctp_v6_copy_ip_options(sk, newsk); /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() * and getpeername(). */ sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk); newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr; if (newsk->sk_prot->init(newsk)) { sk_common_release(newsk); newsk = NULL; } out: return newsk; } /* Format a sockaddr for return to user space. This makes sure the return is * AF_INET or AF_INET6 depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. */ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { if (sp->v4mapped) { if (addr->sa.sa_family == AF_INET) sctp_v4_map_v6(addr); } else { if (addr->sa.sa_family == AF_INET6 && ipv6_addr_v4mapped(&addr->v6.sin6_addr)) sctp_v6_map_v4(addr); } if (addr->sa.sa_family == AF_INET) { memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); } return sizeof(struct sockaddr_in6); } /* Where did this skb come from? */ static int sctp_v6_skb_iif(const struct sk_buff *skb) { return inet6_iif(skb); } static int sctp_v6_skb_sdif(const struct sk_buff *skb) { return inet6_sdif(skb); } /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v6_is_ce(const struct sk_buff *skb) { return *((__u32 *)(ipv6_hdr(skb))) & (__force __u32)htonl(1 << 20); } /* Dump the v6 addr to the seq file. */ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) { seq_printf(seq, "%pI6 ", &addr->v6.sin6_addr); } static void sctp_v6_ecn_capable(struct sock *sk) { inet6_sk(sk)->tclass |= INET_ECN_ECT_0; } /* Initialize a PF_INET msgname from a ulpevent. */ static void sctp_inet6_event_msgname(struct sctp_ulpevent *event, char *msgname, int *addrlen) { union sctp_addr *addr; struct sctp_association *asoc; union sctp_addr *paddr; if (!msgname) return; addr = (union sctp_addr *)msgname; asoc = event->asoc; paddr = &asoc->peer.primary_addr; if (paddr->sa.sa_family == AF_INET) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = htons(asoc->peer.port); addr->v4.sin_addr = paddr->v4.sin_addr; } else { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_flowinfo = 0; if (ipv6_addr_type(&paddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) addr->v6.sin6_scope_id = paddr->v6.sin6_scope_id; else addr->v6.sin6_scope_id = 0; addr->v6.sin6_port = htons(asoc->peer.port); addr->v6.sin6_addr = paddr->v6.sin6_addr; } *addrlen = sctp_v6_addr_to_user(sctp_sk(asoc->base.sk), addr); } /* Initialize a msg_name from an inbound skb. */ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname, int *addr_len) { union sctp_addr *addr; struct sctphdr *sh; if (!msgname) return; addr = (union sctp_addr *)msgname; sh = sctp_hdr(skb); if (ip_hdr(skb)->version == 4) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = sh->source; addr->v4.sin_addr.s_addr = ip_hdr(skb)->saddr; } else { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_flowinfo = 0; addr->v6.sin6_port = sh->source; addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb); else addr->v6.sin6_scope_id = 0; } *addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr); } /* Do we support this AF? */ static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp) { switch (family) { case AF_INET6: return 1; /* v4-mapped-v6 addresses */ case AF_INET: if (!ipv6_only_sock(sctp_opt2sk(sp))) return 1; fallthrough; default: return 0; } } /* Address matching with wildcards allowed. This extra level * of indirection lets us choose whether a PF_INET6 should * disallow any v4 addresses if we so choose. */ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2, struct sctp_sock *opt) { struct sock *sk = sctp_opt2sk(opt); struct sctp_af *af1, *af2; af1 = sctp_get_af_specific(addr1->sa.sa_family); af2 = sctp_get_af_specific(addr2->sa.sa_family); if (!af1 || !af2) return 0; /* If the socket is IPv6 only, v4 addrs will not match */ if (ipv6_only_sock(sk) && af1 != af2) return 0; /* Today, wildcard AF_INET/AF_INET6. */ if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1; if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET) return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr; return __sctp_v6_cmp_addr(addr1, addr2); } /* Verify that the provided sockaddr looks bindable. Common verification, * has already been taken care of. */ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) { struct sctp_af *af; /* ASSERT: address family has already been verified. */ if (addr->sa.sa_family != AF_INET6) af = sctp_get_af_specific(addr->sa.sa_family); else { int type = ipv6_addr_type(&addr->v6.sin6_addr); struct net_device *dev; if (type & IPV6_ADDR_LINKLOCAL) { struct net *net; if (!addr->v6.sin6_scope_id) return 0; net = sock_net(&opt->inet.sk); rcu_read_lock(); dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id); if (!dev || !(ipv6_can_nonlocal_bind(net, &opt->inet) || ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0))) { rcu_read_unlock(); return 0; } rcu_read_unlock(); } af = opt->pf->af; } return af->available(addr, opt); } /* Verify that the provided sockaddr looks sendable. Common verification, * has already been taken care of. */ static int sctp_inet6_send_verify(struct sctp_sock *opt, union sctp_addr *addr) { struct sctp_af *af = NULL; /* ASSERT: address family has already been verified. */ if (addr->sa.sa_family != AF_INET6) af = sctp_get_af_specific(addr->sa.sa_family); else { int type = ipv6_addr_type(&addr->v6.sin6_addr); struct net_device *dev; if (type & IPV6_ADDR_LINKLOCAL) { if (!addr->v6.sin6_scope_id) return 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(&opt->inet.sk), addr->v6.sin6_scope_id); rcu_read_unlock(); if (!dev) return 0; } af = opt->pf->af; } return af != NULL; } /* Fill in Supported Address Type information for INIT and INIT-ACK * chunks. Note: In the future, we may want to look at sock options * to determine whether a PF_INET6 socket really wants to have IPV4 * addresses. * Returns number of addresses supported. */ static int sctp_inet6_supported_addrs(const struct sctp_sock *opt, __be16 *types) { types[0] = SCTP_PARAM_IPV6_ADDRESS; if (!opt || !ipv6_only_sock(sctp_opt2sk(opt))) { types[1] = SCTP_PARAM_IPV4_ADDRESS; return 2; } return 1; } /* Handle SCTP_I_WANT_MAPPED_V4_ADDR for getpeername() and getsockname() */ static int sctp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { int rc; rc = inet6_getname(sock, uaddr, peer); if (rc < 0) return rc; rc = sctp_v6_addr_to_user(sctp_sk(sock->sk), (union sctp_addr *)uaddr); return rc; } static const struct proto_ops inet6_seqpacket_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = sctp_inet_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = sctp_getname, .poll = sctp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .listen = sctp_inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw sctpv6_seqpacket_protosw = { .type = SOCK_SEQPACKET, .protocol = IPPROTO_SCTP, .prot = &sctpv6_prot, .ops = &inet6_seqpacket_ops, .flags = SCTP_PROTOSW_FLAG }; static struct inet_protosw sctpv6_stream_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_SCTP, .prot = &sctpv6_prot, .ops = &inet6_seqpacket_ops, .flags = SCTP_PROTOSW_FLAG, }; static int sctp6_rcv(struct sk_buff *skb) { SCTP_INPUT_CB(skb)->encap_port = 0; return sctp_rcv(skb) ? -1 : 0; } static const struct inet6_protocol sctpv6_protocol = { .handler = sctp6_rcv, .err_handler = sctp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; static struct sctp_af sctp_af_inet6 = { .sa_family = AF_INET6, .sctp_xmit = sctp_v6_xmit, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .get_dst = sctp_v6_get_dst, .get_saddr = sctp_v6_get_saddr, .copy_addrlist = sctp_v6_copy_addrlist, .from_skb = sctp_v6_from_skb, .from_sk = sctp_v6_from_sk, .from_addr_param = sctp_v6_from_addr_param, .to_addr_param = sctp_v6_to_addr_param, .cmp_addr = sctp_v6_cmp_addr, .scope = sctp_v6_scope, .addr_valid = sctp_v6_addr_valid, .inaddr_any = sctp_v6_inaddr_any, .is_any = sctp_v6_is_any, .available = sctp_v6_available, .skb_iif = sctp_v6_skb_iif, .skb_sdif = sctp_v6_skb_sdif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, .ecn_capable = sctp_v6_ecn_capable, .net_header_len = sizeof(struct ipv6hdr), .sockaddr_len = sizeof(struct sockaddr_in6), .ip_options_len = sctp_v6_ip_options_len, }; static struct sctp_pf sctp_pf_inet6 = { .event_msgname = sctp_inet6_event_msgname, .skb_msgname = sctp_inet6_skb_msgname, .af_supported = sctp_inet6_af_supported, .cmp_addr = sctp_inet6_cmp_addr, .bind_verify = sctp_inet6_bind_verify, .send_verify = sctp_inet6_send_verify, .supported_addrs = sctp_inet6_supported_addrs, .create_accept_sk = sctp_v6_create_accept_sk, .addr_to_user = sctp_v6_addr_to_user, .to_sk_saddr = sctp_v6_to_sk_saddr, .to_sk_daddr = sctp_v6_to_sk_daddr, .copy_ip_options = sctp_v6_copy_ip_options, .af = &sctp_af_inet6, }; /* Initialize IPv6 support and register with socket layer. */ void sctp_v6_pf_init(void) { /* Register the SCTP specific PF_INET6 functions. */ sctp_register_pf(&sctp_pf_inet6, PF_INET6); /* Register the SCTP specific AF_INET6 functions. */ sctp_register_af(&sctp_af_inet6); } void sctp_v6_pf_exit(void) { list_del(&sctp_af_inet6.list); } /* Initialize IPv6 support and register with socket layer. */ int sctp_v6_protosw_init(void) { int rc; rc = proto_register(&sctpv6_prot, 1); if (rc) return rc; /* Add SCTPv6(UDP and TCP style) to inetsw6 linked list. */ inet6_register_protosw(&sctpv6_seqpacket_protosw); inet6_register_protosw(&sctpv6_stream_protosw); return 0; } void sctp_v6_protosw_exit(void) { inet6_unregister_protosw(&sctpv6_seqpacket_protosw); inet6_unregister_protosw(&sctpv6_stream_protosw); proto_unregister(&sctpv6_prot); } /* Register with inet6 layer. */ int sctp_v6_add_protocol(void) { /* Register notifier for inet6 address additions/deletions. */ register_inet6addr_notifier(&sctp_inet6addr_notifier); if (inet6_add_protocol(&sctpv6_protocol, IPPROTO_SCTP) < 0) return -EAGAIN; return 0; } /* Unregister with inet6 layer. */ void sctp_v6_del_protocol(void) { inet6_del_protocol(&sctpv6_protocol, IPPROTO_SCTP); unregister_inet6addr_notifier(&sctp_inet6addr_notifier); } |
| 2 2 1 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* LRW: as defined by Cyril Guyot in * http://grouper.ieee.org/groups/1619/email/pdf00017.pdf * * Copyright (c) 2006 Rik Snel <rsnel@cube.dyndns.org> * * Based on ecb.c * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ /* This implementation is checked against the test vectors in the above * document and by a test vector provided by Ken Buchanan at * https://www.mail-archive.com/stds-p1619@listserv.ieee.org/msg00173.html * * The test vectors are included in the testing module tcrypt.[ch] */ #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <crypto/b128ops.h> #include <crypto/gf128mul.h> #define LRW_BLOCK_SIZE 16 struct lrw_tfm_ctx { struct crypto_skcipher *child; /* * optimizes multiplying a random (non incrementing, as at the * start of a new sector) value with key2, we could also have * used 4k optimization tables or no optimization at all. In the * latter case we would have to store key2 here */ struct gf128mul_64k *table; /* * stores: * key2*{ 0,0,...0,0,0,0,1 }, key2*{ 0,0,...0,0,0,1,1 }, * key2*{ 0,0,...0,0,1,1,1 }, key2*{ 0,0,...0,1,1,1,1 } * key2*{ 0,0,...1,1,1,1,1 }, etc * needed for optimized multiplication of incrementing values * with key2 */ be128 mulinc[128]; }; struct lrw_request_ctx { be128 t; struct skcipher_request subreq; }; static inline void lrw_setbit128_bbe(void *b, int bit) { __set_bit(bit ^ (0x80 - #ifdef __BIG_ENDIAN BITS_PER_LONG #else BITS_PER_BYTE #endif ), b); } static int lrw_setkey(struct crypto_skcipher *parent, const u8 *key, unsigned int keylen) { struct lrw_tfm_ctx *ctx = crypto_skcipher_ctx(parent); struct crypto_skcipher *child = ctx->child; int err, bsize = LRW_BLOCK_SIZE; const u8 *tweak = key + keylen - bsize; be128 tmp = { 0 }; int i; crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) & CRYPTO_TFM_REQ_MASK); err = crypto_skcipher_setkey(child, key, keylen - bsize); if (err) return err; if (ctx->table) gf128mul_free_64k(ctx->table); /* initialize multiplication table for Key2 */ ctx->table = gf128mul_init_64k_bbe((be128 *)tweak); if (!ctx->table) return -ENOMEM; /* initialize optimization table */ for (i = 0; i < 128; i++) { lrw_setbit128_bbe(&tmp, i); ctx->mulinc[i] = tmp; gf128mul_64k_bbe(&ctx->mulinc[i], ctx->table); } return 0; } /* * Returns the number of trailing '1' bits in the words of the counter, which is * represented by 4 32-bit words, arranged from least to most significant. * At the same time, increments the counter by one. * * For example: * * u32 counter[4] = { 0xFFFFFFFF, 0x1, 0x0, 0x0 }; * int i = lrw_next_index(&counter); * // i == 33, counter == { 0x0, 0x2, 0x0, 0x0 } */ static int lrw_next_index(u32 *counter) { int i, res = 0; for (i = 0; i < 4; i++) { if (counter[i] + 1 != 0) return res + ffz(counter[i]++); counter[i] = 0; res += 32; } /* * If we get here, then x == 128 and we are incrementing the counter * from all ones to all zeros. This means we must return index 127, i.e. * the one corresponding to key2*{ 1,...,1 }. */ return 127; } /* * We compute the tweak masks twice (both before and after the ECB encryption or * decryption) to avoid having to allocate a temporary buffer and/or make * mutliple calls to the 'ecb(..)' instance, which usually would be slower than * just doing the lrw_next_index() calls again. */ static int lrw_xor_tweak(struct skcipher_request *req, bool second_pass) { const int bs = LRW_BLOCK_SIZE; struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); const struct lrw_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); struct lrw_request_ctx *rctx = skcipher_request_ctx(req); be128 t = rctx->t; struct skcipher_walk w; __be32 *iv; u32 counter[4]; int err; if (second_pass) { req = &rctx->subreq; /* set to our TFM to enforce correct alignment: */ skcipher_request_set_tfm(req, tfm); } err = skcipher_walk_virt(&w, req, false); if (err) return err; iv = (__be32 *)w.iv; counter[0] = be32_to_cpu(iv[3]); counter[1] = be32_to_cpu(iv[2]); counter[2] = be32_to_cpu(iv[1]); counter[3] = be32_to_cpu(iv[0]); while (w.nbytes) { unsigned int avail = w.nbytes; const be128 *wsrc; be128 *wdst; wsrc = w.src.virt.addr; wdst = w.dst.virt.addr; do { be128_xor(wdst++, &t, wsrc++); /* T <- I*Key2, using the optimization * discussed in the specification */ be128_xor(&t, &t, &ctx->mulinc[lrw_next_index(counter)]); } while ((avail -= bs) >= bs); if (second_pass && w.nbytes == w.total) { iv[0] = cpu_to_be32(counter[3]); iv[1] = cpu_to_be32(counter[2]); iv[2] = cpu_to_be32(counter[1]); iv[3] = cpu_to_be32(counter[0]); } err = skcipher_walk_done(&w, avail); } return err; } static int lrw_xor_tweak_pre(struct skcipher_request *req) { return lrw_xor_tweak(req, false); } static int lrw_xor_tweak_post(struct skcipher_request *req) { return lrw_xor_tweak(req, true); } static void lrw_crypt_done(void *data, int err) { struct skcipher_request *req = data; if (!err) { struct lrw_request_ctx *rctx = skcipher_request_ctx(req); rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; err = lrw_xor_tweak_post(req); } skcipher_request_complete(req, err); } static void lrw_init_crypt(struct skcipher_request *req) { const struct lrw_tfm_ctx *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); struct lrw_request_ctx *rctx = skcipher_request_ctx(req); struct skcipher_request *subreq = &rctx->subreq; skcipher_request_set_tfm(subreq, ctx->child); skcipher_request_set_callback(subreq, req->base.flags, lrw_crypt_done, req); /* pass req->iv as IV (will be used by xor_tweak, ECB will ignore it) */ skcipher_request_set_crypt(subreq, req->dst, req->dst, req->cryptlen, req->iv); /* calculate first value of T */ memcpy(&rctx->t, req->iv, sizeof(rctx->t)); /* T <- I*Key2 */ gf128mul_64k_bbe(&rctx->t, ctx->table); } static int lrw_encrypt(struct skcipher_request *req) { struct lrw_request_ctx *rctx = skcipher_request_ctx(req); struct skcipher_request *subreq = &rctx->subreq; lrw_init_crypt(req); return lrw_xor_tweak_pre(req) ?: crypto_skcipher_encrypt(subreq) ?: lrw_xor_tweak_post(req); } static int lrw_decrypt(struct skcipher_request *req) { struct lrw_request_ctx *rctx = skcipher_request_ctx(req); struct skcipher_request *subreq = &rctx->subreq; lrw_init_crypt(req); return lrw_xor_tweak_pre(req) ?: crypto_skcipher_decrypt(subreq) ?: lrw_xor_tweak_post(req); } static int lrw_init_tfm(struct crypto_skcipher *tfm) { struct skcipher_instance *inst = skcipher_alg_instance(tfm); struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst); struct lrw_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); struct crypto_skcipher *cipher; cipher = crypto_spawn_skcipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; crypto_skcipher_set_reqsize(tfm, crypto_skcipher_reqsize(cipher) + sizeof(struct lrw_request_ctx)); return 0; } static void lrw_exit_tfm(struct crypto_skcipher *tfm) { struct lrw_tfm_ctx *ctx = crypto_skcipher_ctx(tfm); if (ctx->table) gf128mul_free_64k(ctx->table); crypto_free_skcipher(ctx->child); } static void lrw_free_instance(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); } static int lrw_create(struct crypto_template *tmpl, struct rtattr **tb) { struct crypto_skcipher_spawn *spawn; struct skcipher_alg_common *alg; struct skcipher_instance *inst; const char *cipher_name; char ecb_name[CRYPTO_MAX_ALG_NAME]; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask); if (err) return err; cipher_name = crypto_attr_alg_name(tb[1]); if (IS_ERR(cipher_name)) return PTR_ERR(cipher_name); inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = skcipher_instance_ctx(inst); err = crypto_grab_skcipher(spawn, skcipher_crypto_instance(inst), cipher_name, 0, mask); if (err == -ENOENT) { err = -ENAMETOOLONG; if (snprintf(ecb_name, CRYPTO_MAX_ALG_NAME, "ecb(%s)", cipher_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; err = crypto_grab_skcipher(spawn, skcipher_crypto_instance(inst), ecb_name, 0, mask); } if (err) goto err_free_inst; alg = crypto_spawn_skcipher_alg_common(spawn); err = -EINVAL; if (alg->base.cra_blocksize != LRW_BLOCK_SIZE) goto err_free_inst; if (alg->ivsize) goto err_free_inst; err = crypto_inst_setname(skcipher_crypto_instance(inst), "lrw", &alg->base); if (err) goto err_free_inst; err = -EINVAL; cipher_name = alg->base.cra_name; /* Alas we screwed up the naming so we have to mangle the * cipher name. */ if (!strncmp(cipher_name, "ecb(", 4)) { int len; len = strscpy(ecb_name, cipher_name + 4, sizeof(ecb_name)); if (len < 2) goto err_free_inst; if (ecb_name[len - 1] != ')') goto err_free_inst; ecb_name[len - 1] = 0; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "lrw(%s)", ecb_name) >= CRYPTO_MAX_ALG_NAME) { err = -ENAMETOOLONG; goto err_free_inst; } } else goto err_free_inst; inst->alg.base.cra_priority = alg->base.cra_priority; inst->alg.base.cra_blocksize = LRW_BLOCK_SIZE; inst->alg.base.cra_alignmask = alg->base.cra_alignmask | (__alignof__(be128) - 1); inst->alg.ivsize = LRW_BLOCK_SIZE; inst->alg.min_keysize = alg->min_keysize + LRW_BLOCK_SIZE; inst->alg.max_keysize = alg->max_keysize + LRW_BLOCK_SIZE; inst->alg.base.cra_ctxsize = sizeof(struct lrw_tfm_ctx); inst->alg.init = lrw_init_tfm; inst->alg.exit = lrw_exit_tfm; inst->alg.setkey = lrw_setkey; inst->alg.encrypt = lrw_encrypt; inst->alg.decrypt = lrw_decrypt; inst->free = lrw_free_instance; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: lrw_free_instance(inst); } return err; } static struct crypto_template lrw_tmpl = { .name = "lrw", .create = lrw_create, .module = THIS_MODULE, }; static int __init lrw_module_init(void) { return crypto_register_template(&lrw_tmpl); } static void __exit lrw_module_exit(void) { crypto_unregister_template(&lrw_tmpl); } subsys_initcall(lrw_module_init); module_exit(lrw_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("LRW block cipher mode"); MODULE_ALIAS_CRYPTO("lrw"); MODULE_SOFTDEP("pre: ecb"); |
| 6 6 6 12 15 15 1 15 15 1 15 15 15 15 13 15 15 15 15 13 13 15 15 7 10 12 15 15 13 13 6 13 18 4 15 15 15 14 4 2 2 1 1 1 3 1 2 2 2 27 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/sort.h> #include <linux/delay.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> #include <linux/fs_parser.h> #include <trace/events/cgroup.h> /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls * Expiring in the middle is a performance problem not a correctness one. * 1 sec should be enough. */ #define CGROUP_PIDLIST_DESTROY_DELAY HZ /* Controllers blocked by the commandline in v1 */ static u16 cgroup_no_v1_mask; /* disable named v1 mounts */ static bool cgroup_no_v1_named; /* * pidlist destructions need to be flushed on cgroup destruction. Use a * separate workqueue as flush domain. */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; /* protects cgroup_subsys->release_agent_path */ static DEFINE_SPINLOCK(release_agent_path_lock); bool cgroup1_ssid_disabled(int ssid) { return cgroup_no_v1_mask & (1 << ssid); } static bool cgroup1_subsys_absent(struct cgroup_subsys *ss) { /* Check also dfl_cftypes for file-less controllers, i.e. perf_event */ return ss->legacy_cftypes == NULL && ss->dfl_cftypes; } /** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached * * Return: %0 on success or a negative errno code on failure */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; cgroup_lock(); cgroup_attach_lock(true); for_each_root(root) { struct cgroup *from_cgrp; spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } cgroup_attach_unlock(true); cgroup_unlock(); return retval; } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /** * cgroup_transfer_tasks - move tasks from one cgroup to another * @to: cgroup to which the tasks will be moved * @from: cgroup in which the tasks currently reside * * Locking rules between cgroup_post_fork() and the migration path * guarantee that, if a task is forking while being migrated, the new child * is guaranteed to be either visible in the source cgroup after the * parent's migration is complete or put into the target cgroup. No task * can slip out of migration through forking. * * Return: %0 on success or a negative errno code on failure */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { DEFINE_CGROUP_MGCTX(mgctx); struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ret; if (cgroup_on_dfl(to)) return -EINVAL; ret = cgroup_migrate_vet_dst(to); if (ret) return ret; cgroup_lock(); cgroup_attach_lock(true); /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &mgctx); spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_err; /* * Migrate tasks one-by-one until @from is empty. This fails iff * ->can_attach() fails. */ do { css_task_iter_start(&from->self, 0, &it); do { task = css_task_iter_next(&it); } while (task && (task->flags & PF_EXITING)); if (task) get_task_struct(task); css_task_iter_end(&it); if (task) { ret = cgroup_migrate(task, false, &mgctx); if (!ret) TRACE_CGROUP_PATH(transfer_tasks, to, task, false); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(true); cgroup_unlock(); return ret; } /* * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), * but we cannot guarantee that the information we produce is correct * unless we produce it entirely atomically. * */ /* which pidlist file are we talking about? */ enum cgroup_filetype { CGROUP_FILE_PROCS, CGROUP_FILE_TASKS, }; /* * A pidlist is a list of pids that virtually represents the contents of one * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, * a pair (one each for procs, tasks) for each pid namespace that's relevant * to the cgroup. */ struct cgroup_pidlist { /* * used to find which pidlist is wanted. doesn't change as long as * this particular list stays in the list. */ struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* each of these stored in a list by its cgroup */ struct list_head links; /* pointer to the cgroup we belong to, for list removal purposes */ struct cgroup *owner; /* for delayed destruction */ struct delayed_work destroy_dwork; }; /* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */ void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) { struct cgroup_pidlist *l, *tmp_l; mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); mutex_unlock(&cgrp->pidlist_mutex); flush_workqueue(cgroup_pidlist_destroy_wq); BUG_ON(!list_empty(&cgrp->pidlists)); } static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, destroy_dwork); struct cgroup_pidlist *tofree = NULL; mutex_lock(&l->owner->pidlist_mutex); /* * Destroy iff we didn't get queued again. The state won't change * as destroy_dwork can only be queued while locked. */ if (!delayed_work_pending(dwork)) { list_del(&l->links); kvfree(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); } /* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * Returns the number of unique elements. */ static int pidlist_uniq(pid_t *list, int length) { int src, dest = 1; /* * we presume the 0th element is unique, so i starts at 1. trivial * edge cases first; no work needs to be done for either */ if (length == 0 || length == 1) return length; /* src and dest walk down the list; dest counts unique elements */ for (src = 1; src < length; src++) { /* find next unique element */ while (list[src] == list[src-1]) { src++; if (src == length) goto after; } /* dest always points to where the next unique element goes */ list[dest] = list[src]; dest++; } after: return dest; } /* * The two pid files - task and cgroup.procs - guaranteed that the result * is sorted, which forced this whole pidlist fiasco. As pid order is * different per namespace, each namespace needs differently sorted list, * making it impossible to use, for example, single rbtree of member tasks * sorted by task pointer. As pidlists can be fairly large, allocating one * per open file is dangerous, so cgroup had to implement shared pool of * pidlists keyed by cgroup and namespace. */ static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; } static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ struct pid_namespace *ns = task_active_pid_ns(current); lockdep_assert_held(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) if (l->key.type == type && l->key.ns == ns) return l; return NULL; } /* * find the appropriate pidlist for our purpose (given procs vs tasks) * returns with the lock on that pidlist already held, and takes care * of the use count, or returns NULL with no locks held if we're out of * memory. */ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); l = cgroup_pidlist_find(cgrp, type); if (l) return l; /* entry not found; create a new one */ l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); if (!l) return l; INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); l->key.type = type; /* don't need task_nsproxy() if we're looking at ourself */ l->key.ns = get_pid_ns(task_active_pid_ns(current)); l->owner = cgrp; list_add(&l->links, &cgrp->pidlists); return l; } /* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, struct cgroup_pidlist **lp) { pid_t *array; int length; int pid, n = 0; /* used for populating the array */ struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); /* * If cgroup gets more users after we read count, we won't have * enough space - tough. This race is indistinguishable to the * caller from the case that the additional cgroup users didn't * show up until sometime later on. */ length = cgroup_task_count(cgrp); array = kvmalloc_array(length, sizeof(pid_t), GFP_KERNEL); if (!array) return -ENOMEM; /* now, populate the array */ css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ if (type == CGROUP_FILE_PROCS) pid = task_tgid_vnr(tsk); else pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } css_task_iter_end(&it); length = n; /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ sort(array, length, sizeof(pid_t), cmppid, NULL); length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { kvfree(array); return -ENOMEM; } /* store array, freeing old if necessary */ kvfree(l->list); l->list = array; l->length = length; *lp = l; return 0; } /* * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid * in the cgroup->l->list array. */ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to * one more than the last pid shown (or 0 on the first call or * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; int index = 0, pid = *pos; int *iter, ret; mutex_lock(&cgrp->pidlist_mutex); /* * !NULL @ctx->procs1.pidlist indicates that this isn't the first * start() after open. If the matching pidlist is around, we can use * that. Look for it. Note that @ctx->procs1.pidlist can't be used * directly. It could already have been destroyed. */ if (ctx->procs1.pidlist) ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ if (!ctx->procs1.pidlist) { ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } l = ctx->procs1.pidlist; if (pid) { int end = l->length; while (index < end) { int mid = (index + end) / 2; if (l->list[mid] == pid) { index = mid; break; } else if (l->list[mid] < pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ iter = l->list + index; *pos = *iter; return iter; } static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); } static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done */ p++; if (p >= end) { (*pos)++; return NULL; } else { *pos = *p; return p; } } static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; } static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct cgroup *cgrp; struct task_struct *task; const struct cred *cred, *tcred; ssize_t ret; bool locked; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* * Even if we're attaching all tasks in the thread group, we only need * to check permissions on one of them. Check permissions using the * credentials from file open to protect against inherited fd attacks. */ cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid)) ret = -EACCES; put_cred(tcred); if (ret) goto out_finish; ret = cgroup_attach_task(cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, locked); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, true); } static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, false); } static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ ctx = of->priv; if ((ctx->ns->user_ns != &init_user_ns) || !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) return -EPERM; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); strscpy(cgrp->root->release_agent_path, strstrip(buf), sizeof(cgrp->root->release_agent_path)); spin_unlock(&release_agent_path_lock); cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_release_agent_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; spin_lock(&release_agent_path_lock); seq_puts(seq, cgrp->root->release_agent_path); spin_unlock(&release_agent_path_lock); seq_putc(seq, '\n'); return 0; } static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; } static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); } static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; } static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); } static int cgroup_clone_children_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; } /* cgroup core interface files for the legacy hierarchies */ struct cftype cgroup1_base_files[] = { { .name = "cgroup.procs", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup1_procs_write, }, { .name = "cgroup.clone_children", .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, { .name = "cgroup.sane_behavior", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_sane_behavior_show, }, { .name = "tasks", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, .write = cgroup1_tasks_write, }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, { .name = "release_agent", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write = cgroup_release_agent_write, .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; /* Display information about each subsystem and each hierarchy */ int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; bool cgrp_v1_visible = false; int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); /* * Grab the subsystems state racily. No need to add avenue to * cgroup_mutex contention. */ for_each_subsys(ss, i) { if (cgroup1_subsys_absent(ss)) continue; cgrp_v1_visible |= ss->root != &cgrp_dfl_root; seq_printf(m, "%s\t%d\t%d\t%d\n", ss->legacy_name, ss->root->hierarchy_id, atomic_read(&ss->root->nr_cgrps), cgroup_ssid_enabled(i)); } if (cgrp_dfl_visible && !cgrp_v1_visible) pr_info_once("/proc/cgroups lists only v1 controllers, use cgroup.controllers of root cgroup for v2 info\n"); return 0; } /** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into * @dentry: A dentry entry belonging to the cgroup for which stats have * been requested. * * Build and fill cgroupstats so that taskstats can export it to user * space. * * Return: %0 on success or a negative errno code on failure */ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; /* it should be kernfs_node belonging to cgroupfs and is a directory */ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || kernfs_type(kn) != KERNFS_DIR) return -EINVAL; /* * We aren't being called from kernfs and there's no guarantee on * @kn->priv's validity. For this and css_tryget_online_from_dir(), * @kn->priv is RCU safe. Let's do the RCU dancing. */ rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) { rcu_read_unlock(); return -ENOENT; } rcu_read_unlock(); css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { switch (READ_ONCE(tsk->__state)) { case TASK_RUNNING: stats->nr_running++; break; case TASK_INTERRUPTIBLE: stats->nr_sleeping++; break; case TASK_UNINTERRUPTIBLE: stats->nr_uninterruptible++; break; case TASK_STOPPED: stats->nr_stopped++; break; default: if (tsk->in_iowait) stats->nr_io_wait++; break; } } css_task_iter_end(&it); cgroup_put(cgrp); return 0; } void cgroup1_check_for_release(struct cgroup *cgrp) { if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) schedule_work(&cgrp->release_agent_work); } /* * Notify userspace when a cgroup is released, by running the * configured release agent with the name of the cgroup (path * relative to the root of cgroup file system) as the argument. * * Most likely, this user command will try to rmdir this cgroup. * * This races with the possibility that some other task will be * attached to this cgroup before it is removed, or that some other * user task will 'mkdir' a child cgroup of this cgroup. That's ok. * The presumed 'rmdir' will fail quietly if this cgroup is no longer * unused, and this cgroup will be reprieved from its death sentence, * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which * means only wait until the task is successfully execve()'d. The * separate release agent task is forked by call_usermodehelper(), * then control in this thread returns here, without waiting for the * release agent task. We don't bother to wait because the caller of * this routine has no use for the exit status of the release agent * task, so no sense holding our caller up for that. */ void cgroup1_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); char *pathbuf, *agentbuf; char *argv[3], *envp[3]; int ret; /* snoop agent path and exit early if empty */ if (!cgrp->root->release_agent_path[0]) return; /* prepare argument buffers */ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf || !agentbuf) goto out_free; spin_lock(&release_agent_path_lock); strscpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX); spin_unlock(&release_agent_path_lock); if (!agentbuf[0]) goto out_free; ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); if (ret < 0) goto out_free; argv[0] = agentbuf; argv[1] = pathbuf; argv[2] = NULL; /* minimal command environment */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); out_free: kfree(agentbuf); kfree(pathbuf); } /* * cgroup_rename - Only allow simple rename of directories in place. */ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name_str) { struct cgroup *cgrp = kn->priv; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(new_name_str, '\n')) return -EINVAL; if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (rcu_access_pointer(kn->__parent) != new_parent) return -EIO; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. kernfs_rename() doesn't require active_ref * protection. Break them before grabbing cgroup_mutex. */ kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); cgroup_lock(); ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) TRACE_CGROUP_PATH(rename, cgrp); cgroup_unlock(); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); return ret; } static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_show_option(seq, ss->legacy_name, NULL); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) seq_puts(seq, ",cpuset_v2_mode"); if (root->flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_show_option(seq, "release_agent", root->release_agent_path); spin_unlock(&release_agent_path_lock); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_show_option(seq, "name", root->name); return 0; } enum cgroup1_param { Opt_all, Opt_clone_children, Opt_cpuset_v2_mode, Opt_name, Opt_none, Opt_noprefix, Opt_release_agent, Opt_xattr, Opt_favordynmods, Opt_nofavordynmods, }; const struct fs_parameter_spec cgroup1_fs_parameters[] = { fsparam_flag ("all", Opt_all), fsparam_flag ("clone_children", Opt_clone_children), fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), fsparam_string("name", Opt_name), fsparam_flag ("none", Opt_none), fsparam_flag ("noprefix", Opt_noprefix), fsparam_string("release_agent", Opt_release_agent), fsparam_flag ("xattr", Opt_xattr), fsparam_flag ("favordynmods", Opt_favordynmods), fsparam_flag ("nofavordynmods", Opt_nofavordynmods), {} }; int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_subsys *ss; struct fs_parse_result result; int opt, i; opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { int ret; ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name) || cgroup1_subsys_absent(ss)) continue; if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) return invalfc(fc, "Disabled controller '%s'", param->key); ctx->subsys_mask |= (1 << i); return 0; } return invalfc(fc, "Unknown subsys name '%s'", param->key); } if (opt < 0) return opt; switch (opt) { case Opt_none: /* Explicitly have no subsystems */ ctx->none = true; break; case Opt_all: ctx->all_ss = true; break; case Opt_noprefix: ctx->flags |= CGRP_ROOT_NOPREFIX; break; case Opt_clone_children: ctx->cpuset_clone_children = true; break; case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; break; case Opt_xattr: ctx->flags |= CGRP_ROOT_XATTR; break; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; break; case Opt_nofavordynmods: ctx->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; break; case Opt_release_agent: /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; case Opt_name: /* blocked by boot param? */ if (cgroup_no_v1_named) return -ENOENT; /* Can't specify an empty name */ if (!param->size) return invalfc(fc, "Empty name"); if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) return invalfc(fc, "Name too long"); /* Must match [\w.-]+ */ for (i = 0; i < param->size; i++) { char c = param->string[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return invalfc(fc, "Invalid name"); } /* Specifying two names is forbidden */ if (ctx->name) return invalfc(fc, "name respecified"); ctx->name = param->string; param->string = NULL; break; } return 0; } static int check_cgroupfs_options(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); u16 mask = U16_MAX; u16 enabled = 0; struct cgroup_subsys *ss; int i; #ifdef CONFIG_CPUSETS mask = ~((u16)1 << cpuset_cgrp_id); #endif for_each_subsys(ss, i) if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i) && !cgroup1_subsys_absent(ss)) enabled |= 1 << i; ctx->subsys_mask &= enabled; /* * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) ctx->all_ss = true; if (ctx->all_ss) { /* Mutually exclusive option 'all' + subsystem name */ if (ctx->subsys_mask) return invalfc(fc, "subsys name conflicts with all"); /* 'all' => select all the subsystems */ ctx->subsys_mask = enabled; } /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!ctx->subsys_mask && !ctx->name) return invalfc(fc, "Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) return invalfc(fc, "noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ if (ctx->subsys_mask && ctx->none) return invalfc(fc, "none used incorrectly"); return 0; } int cgroup1_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); int ret = 0; u16 added_mask, removed_mask; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = check_cgroupfs_options(fc); if (ret) goto out_unlock; if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = ctx->subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~ctx->subsys_mask; /* Don't allow flags or name to change at remount */ if ((ctx->flags ^ root->flags) || (ctx->name && strcmp(ctx->name, root->name))) { errorfc(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (!list_empty(&root->cgrp.self.children)) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (ctx->release_agent) { spin_lock(&release_agent_path_lock); strcpy(root->release_agent_path, ctx->release_agent); spin_unlock(&release_agent_path_lock); } trace_cgroup_remount(root); out_unlock: cgroup_unlock(); return ret; } struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { .rename = cgroup1_rename, .show_options = cgroup1_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; /* * The guts of cgroup1 mount - find or create cgroup_root to use. * Called with cgroup_mutex held; returns 0 on success, -E... on * error and positive - in case when the candidate is busy dying. * On success it stashes a reference to cgroup_root into given * cgroup_fs_context; that reference is *NOT* counting towards the * cgroup_root refcount. */ static int cgroup1_root_to_use(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; struct cgroup_subsys *ss; int i, ret; /* First find the desired set of subsystems */ ret = check_cgroupfs_options(fc); if (ret) return ret; /* * Destruction of cgroup root is asynchronous, so subsystems may * still be dying after the previous unmount. Let's drain the * dying subsystems. We just need to ensure that the ones * unmounted previously finish dying and don't care about new ones * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { if (!(ctx->subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) return 1; /* restart */ cgroup_put(&ss->root->cgrp); } for_each_root(root) { bool name_match = false; if (root == &cgrp_dfl_root) continue; /* * If we asked for a name then it must match. Also, if * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ if (ctx->name) { if (strcmp(ctx->name, root->name)) continue; name_match = true; } /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ if ((ctx->subsys_mask || ctx->none) && (ctx->subsys_mask != root->subsys_mask)) { if (!name_match) continue; return -EBUSY; } if (root->flags ^ ctx->flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); ctx->root = root; return 0; } /* * No such thing, create a new one. name= matching without subsys * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ if (!ctx->subsys_mask && !ctx->none) return invalfc(fc, "No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ if (ctx->ns != &init_cgroup_ns) return -EPERM; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return -ENOMEM; ctx->root = root; init_cgroup_root(ctx); ret = cgroup_setup_root(root, ctx->subsys_mask); if (!ret) cgroup_favor_dynmods(root, ctx->flags & CGRP_ROOT_FAVOR_DYNMODS); else cgroup_free_root(root); return ret; } int cgroup1_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; /* Check if the caller has permission to mount. */ if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); ret = cgroup1_root_to_use(fc); if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) ret = 1; /* restart */ cgroup_unlock(); if (!ret) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { fc_drop_locked(fc); ret = 1; } if (unlikely(ret > 0)) { msleep(10); return restart_syscall(); } return ret; } /** * task_get_cgroup1 - Acquires the associated cgroup of a task within a * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its * hierarchy ID. * @tsk: The target task * @hierarchy_id: The ID of a cgroup1 hierarchy * * On success, the cgroup is returned. On failure, ERR_PTR is returned. * We limit it to cgroup1 only. */ struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id) { struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup_root *root; unsigned long flags; rcu_read_lock(); for_each_root(root) { /* cgroup1 only*/ if (root == &cgrp_dfl_root) continue; if (root->hierarchy_id != hierarchy_id) continue; spin_lock_irqsave(&css_set_lock, flags); cgrp = task_cgroup_from_root(tsk, root); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); spin_unlock_irqrestore(&css_set_lock, flags); break; } rcu_read_unlock(); return cgrp; } static int __init cgroup1_wq_init(void) { /* * Used to destroy pidlists and separate to serve as flush domain. * Cap @max_active to 1 too. */ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", 0, 1); BUG_ON(!cgroup_pidlist_destroy_wq); return 0; } core_initcall(cgroup1_wq_init); static int __init cgroup_no_v1(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "all")) { cgroup_no_v1_mask = U16_MAX; continue; } if (!strcmp(token, "named")) { cgroup_no_v1_named = true; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_no_v1_mask |= 1 << i; break; } } return 1; } __setup("cgroup_no_v1=", cgroup_no_v1); |
| 50 50 51 51 60 3 60 3 1 34 19 1 15 9 30 4 56 43 16 5 6 49 45 21 15 49 35 24 50 12 2 50 2 14 14 1 10 2 1 61 61 61 61 60 61 40 13 1 1 3 4 20 2 20 6 98 98 98 98 60 57 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 | // SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The IP fragmentation functionality. * * Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * Alan Cox : Split from ip.c , see ip_input.c for history. * David S. Miller : Begin massive cleanup... * Andi Kleen : Add sysctls. * xxxx : Overlapfrag bug. * Ultima : ip_expire() kernel panic. * Bill Hawes : Frag accounting and evictor fixes. * John McDonald : 0 length frag bug. * Alexey Kuznetsov: SMP races, threading, cleanup. * Patrick McHardy : LRU queue of frag heads for evictor. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/compiler.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/jiffies.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/netdevice.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/slab.h> #include <net/route.h> #include <net/dst.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_frag.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/inet.h> #include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> #include <net/l3mdev.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c * as well. Or notify me, at least. --ANK */ static const char ip_frag_cache_name[] = "ip4-frags"; /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; unsigned int rid; struct inet_peer *peer; }; static u8 ip4_frag_ecn(u8 tos) { return 1 << (tos & INET_ECN_MASK); } static struct inet_frags ip4_frags; static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev, int *refs); static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); const struct frag_v4_compare_key *key = a; struct net *net = q->fqdir->net; struct inet_peer *p = NULL; q->key.v4 = *key; qp->ecn = 0; if (q->fqdir->max_dist) { rcu_read_lock(); p = inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif); if (p && !refcount_inc_not_zero(&p->refcnt)) p = NULL; rcu_read_unlock(); } qp->peer = p; } static void ip4_frag_free(struct inet_frag_queue *q) { struct ipq *qp; qp = container_of(q, struct ipq, q); if (qp->peer) inet_putpeer(qp->peer); } static bool frag_expire_skip_icmp(u32 user) { return user == IP_DEFRAG_AF_PACKET || ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN, __IP_DEFRAG_CONNTRACK_IN_END) || ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN, __IP_DEFRAG_CONNTRACK_BRIDGE_IN); } /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ static void ip_expire(struct timer_list *t) { enum skb_drop_reason reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; struct inet_frag_queue *frag = from_timer(frag, t, timer); const struct iphdr *iph; struct sk_buff *head = NULL; struct net *net; struct ipq *qp; int refs = 1; qp = container_of(frag, struct ipq, q); net = qp->q.fqdir->net; rcu_read_lock(); /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(qp->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&qp->q.lock); if (qp->q.flags & INET_FRAG_COMPLETE) goto out; qp->q.flags |= INET_FRAG_DROP; inet_frag_kill(&qp->q, &refs); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); if (!(qp->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&qp->q); if (!head) goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); reason = ip_route_input_noref(head, iph->daddr, iph->saddr, ip4h_dscp(iph), head->dev); if (reason) goto out; /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; if (frag_expire_skip_icmp(qp->q.key.v4.user) && (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out; spin_unlock(&qp->q.lock); icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); goto out_rcu_unlock; out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); kfree_skb_reason(head, reason); inet_frag_putn(&qp->q, refs); } /* Find the correct entry in the "incomplete datagrams" queue for * this IP datagram, and create new one, if nothing is found. */ static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user, int vif) { struct frag_v4_compare_key key = { .saddr = iph->saddr, .daddr = iph->daddr, .user = user, .vif = vif, .id = iph->id, .protocol = iph->protocol, }; struct inet_frag_queue *q; q = inet_frag_find(net->ipv4.fqdir, &key); if (!q) return NULL; return container_of(q, struct ipq, q); } /* Is the fragment too far ahead to be part of ipq? */ static int ip_frag_too_far(struct ipq *qp) { struct inet_peer *peer = qp->peer; unsigned int max = qp->q.fqdir->max_dist; unsigned int start, end; int rc; if (!peer || !max) return 0; start = qp->rid; end = atomic_inc_return(&peer->rid); qp->rid = end; rc = qp->q.fragments_tail && (end - start) > max; if (rc) __IP_INC_STATS(qp->q.fqdir->net, IPSTATS_MIB_REASMFAILS); return rc; } static int ip_frag_reinit(struct ipq *qp) { unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) { refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, SKB_DROP_REASON_FRAG_TOO_FAR); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; qp->iif = 0; qp->ecn = 0; return 0; } /* Add new segment to existing queue. */ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb, int *refs) { struct net *net = qp->q.fqdir->net; int ihl, end, flags, offset; struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; int err = -ENOENT; SKB_DR(reason); u8 ecn; /* If reassembly is already done, @skb must be a duplicate frag. */ if (qp->q.flags & INET_FRAG_COMPLETE) { SKB_DR_SET(reason, DUP_FRAG); goto err; } if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && unlikely(err = ip_frag_reinit(qp))) { inet_frag_kill(&qp->q, refs); goto err; } ecn = ip4_frag_ecn(ip_hdr(skb)->tos); offset = ntohs(ip_hdr(skb)->frag_off); flags = offset & ~IP_OFFSET; offset &= IP_OFFSET; offset <<= 3; /* offset is in 8-byte chunks */ ihl = ip_hdrlen(skb); /* Determine the position of this fragment. */ end = offset + skb->len - skb_network_offset(skb) - ihl; err = -EINVAL; /* Is this the final fragment? */ if ((flags & IP_MF) == 0) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { if (end&7) { end &= ~7; if (skb->ip_summed != CHECKSUM_UNNECESSARY) skb->ip_summed = CHECKSUM_NONE; } if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) goto discard_qp; qp->q.len = end; } } if (end == offset) goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); prev_tail = qp->q.fragments_tail; err = inet_frag_queue_insert(&qp->q, skb, offset, end); if (err) goto insert_error; if (dev) qp->iif = dev->ifindex; qp->q.stamp = skb->tstamp; qp->q.tstamp_type = skb->tstamp_type; qp->q.meat += skb->len; qp->ecn |= ecn; add_frag_mem_limit(qp->q.fqdir, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; fragsize = skb->len + ihl; if (fragsize > qp->q.max_size) qp->q.max_size = fragsize; if (ip_hdr(skb)->frag_off & htons(IP_DF) && fragsize > qp->max_df_size) qp->max_df_size = fragsize; if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev, refs); skb->_skb_refdst = orefdst; if (err) inet_frag_kill(&qp->q, refs); return err; } skb_dst_drop(skb); skb_orphan(skb); return -EINPROGRESS; insert_error: if (err == IPFRAG_DUP) { SKB_DR_SET(reason, DUP_FRAG); err = -EINVAL; goto err; } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q, refs); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb_reason(skb, reason); return err; } static bool ip_frag_coalesce_ok(const struct ipq *qp) { return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER; } /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev, int *refs) { struct net *net = qp->q.fqdir->net; struct iphdr *iph; void *reasm_data; int len, err; u8 ecn; inet_frag_kill(&qp->q, refs); ecn = ip_frag_ecn_table[qp->ecn]; if (unlikely(ecn == 0xff)) { err = -EINVAL; goto out_fail; } /* Make the one we just received the head. */ reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); if (!reasm_data) goto out_nomem; len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; inet_frag_reasm_finish(&qp->q, skb, reasm_data, ip_frag_coalesce_ok(qp)); skb->dev = dev; IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; /* When we set IP_DF on a refragmented skb we must also force a * call to ip_fragment to avoid forwarding a DF-skb of size s while * original sender only sent fragments of size f (where f < s). * * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest * frag seen to avoid sending tiny DF-fragments in case skb was built * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; } ip_send_check(iph); __IP_INC_STATS(net, IPSTATS_MIB_REASMOKS); qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; return 0; out_nomem: net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp); err = -ENOMEM; goto out_fail; out_oversize: net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr); out_fail: __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); return err; } /* Process an incoming IP datagram fragment. */ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; int vif = l3mdev_master_ifindex_rcu(dev); struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ rcu_read_lock(); qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { int ret, refs = 0; spin_lock(&qp->q.lock); ret = ip_frag_queue(qp, skb, &refs); spin_unlock(&qp->q.lock); rcu_read_unlock(); inet_frag_putn(&qp->q, refs); return ret; } rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -ENOMEM; } EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct iphdr iph; int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; netoff = skb_network_offset(skb); if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { kfree_skb(skb); return NULL; } if (pskb_trim_rcsum(skb, netoff + len)) { kfree_skb(skb); return NULL; } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; skb_clear_hash(skb); } } return skb; } EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL static int dist_min; static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "ipfrag_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "ipfrag_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ipfrag_max_dist", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &dist_min, }, }; /* secret interval has been deprecated */ static int ip4_frags_secret_interval_unused; static struct ctl_table ip4_frags_ctl_table[] = { { .procname = "ipfrag_secret_interval", .data = &ip4_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; static int __net_init ip4_frags_ns_ctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = ip4_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); if (!table) goto err_alloc; } table[0].data = &net->ipv4.fqdir->high_thresh; table[0].extra1 = &net->ipv4.fqdir->low_thresh; table[1].data = &net->ipv4.fqdir->low_thresh; table[1].extra2 = &net->ipv4.fqdir->high_thresh; table[2].data = &net->ipv4.fqdir->timeout; table[3].data = &net->ipv4.fqdir->max_dist; hdr = register_net_sysctl_sz(net, "net/ipv4", table, ARRAY_SIZE(ip4_frags_ns_ctl_table)); if (!hdr) goto err_reg; net->ipv4.frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { const struct ctl_table *table; table = net->ipv4.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.frags_hdr); kfree(table); } static void __init ip4_frags_ctl_register(void) { register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table); } #else static int ip4_frags_ns_ctl_register(struct net *net) { return 0; } static void ip4_frags_ns_ctl_unregister(struct net *net) { } static void __init ip4_frags_ctl_register(void) { } #endif static int __net_init ipv4_frags_init_net(struct net *net) { int res; res = fqdir_init(&net->ipv4.fqdir, &ip4_frags, net); if (res < 0) return res; /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for * the real memory usage, by measuring both the size of frag * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) * and the SKB's truesize. * * A 64K fragment consumes 129736 bytes (44*2944)+200 * (1500 truesize == 2944, sizeof(struct ipq) == 200) * * We will commit 4MB at one time. Should we cross that limit * we will prune down to 3MB, making room for approx 8 big 64K * fragments 8x128k. */ net->ipv4.fqdir->high_thresh = 4 * 1024 * 1024; net->ipv4.fqdir->low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival * by TTL. */ net->ipv4.fqdir->timeout = IP_FRAG_TIME; net->ipv4.fqdir->max_dist = 64; res = ip4_frags_ns_ctl_register(net); if (res < 0) fqdir_exit(net->ipv4.fqdir); return res; } static void __net_exit ipv4_frags_pre_exit_net(struct net *net) { fqdir_pre_exit(net->ipv4.fqdir); } static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); fqdir_exit(net->ipv4.fqdir); } static struct pernet_operations ip4_frags_ops = { .init = ipv4_frags_init_net, .pre_exit = ipv4_frags_pre_exit_net, .exit = ipv4_frags_exit_net, }; static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); } static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v4, sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); } static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v4_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static const struct rhashtable_params ip4_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .key_offset = offsetof(struct inet_frag_queue, key), .key_len = sizeof(struct frag_v4_compare_key), .hashfn = ip4_key_hashfn, .obj_hashfn = ip4_obj_hashfn, .obj_cmpfn = ip4_obj_cmpfn, .automatic_shrinking = true, }; void __init ipfrag_init(void) { ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; ip4_frags.qsize = sizeof(struct ipq); ip4_frags.frag_expire = ip_expire; ip4_frags.frags_cache_name = ip_frag_cache_name; ip4_frags.rhash_params = ip4_rhash_params; if (inet_frags_init(&ip4_frags)) panic("IP: failed to allocate ip4_frags cache\n"); ip4_frags_ctl_register(); register_pernet_subsys(&ip4_frags_ops); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2007-2017 Nicira, Inc. */ #ifndef FLOW_H #define FLOW_H 1 #include <linux/cache.h> #include <linux/kernel.h> #include <linux/netlink.h> #include <linux/openvswitch.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/if_ether.h> #include <linux/in6.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/cpumask.h> #include <net/inet_ecn.h> #include <net/ip_tunnels.h> #include <net/dst_metadata.h> #include <net/nsh.h> struct sk_buff; enum sw_flow_mac_proto { MAC_PROTO_NONE = 0, MAC_PROTO_ETHERNET, }; #define SW_FLOW_KEY_INVALID 0x80 #define MPLS_LABEL_DEPTH 3 /* Bit definitions for IPv6 Extension Header pseudo-field. */ enum ofp12_ipv6exthdr_flags { OFPIEH12_NONEXT = 1 << 0, /* "No next header" encountered. */ OFPIEH12_ESP = 1 << 1, /* Encrypted Sec Payload header present. */ OFPIEH12_AUTH = 1 << 2, /* Authentication header present. */ OFPIEH12_DEST = 1 << 3, /* 1 or 2 dest headers present. */ OFPIEH12_FRAG = 1 << 4, /* Fragment header present. */ OFPIEH12_ROUTER = 1 << 5, /* Router header present. */ OFPIEH12_HOP = 1 << 6, /* Hop-by-hop header present. */ OFPIEH12_UNREP = 1 << 7, /* Unexpected repeats encountered. */ OFPIEH12_UNSEQ = 1 << 8 /* Unexpected sequencing encountered. */ }; /* Store options at the end of the array if they are less than the * maximum size. This allows us to get the benefits of variable length * matching for small options. */ #define TUN_METADATA_OFFSET(opt_len) \ (sizeof_field(struct sw_flow_key, tun_opts) - opt_len) #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) struct ovs_tunnel_info { struct metadata_dst *tun_dst; }; struct vlan_head { __be16 tpid; /* Vlan type. Generally 802.1q or 802.1ad.*/ __be16 tci; /* 0 if no VLAN, VLAN_CFI_MASK set otherwise. */ }; #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ sizeof_field(struct sw_flow_key, recirc_id)) struct ovs_key_nsh { struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; }; struct sw_flow_key { u8 tun_opts[IP_TUNNEL_OPTS_MAX]; u8 tun_opts_len; struct ip_tunnel_key tun_key; /* Encapsulating tunnel key. */ struct { u32 priority; /* Packet QoS priority. */ u32 skb_mark; /* SKB mark. */ u16 in_port; /* Input switch port (or DP_MAX_PORTS). */ } __packed phy; /* Safe when right after 'tun_key'. */ u8 mac_proto; /* MAC layer protocol (e.g. Ethernet). */ u8 tun_proto; /* Protocol of encapsulating tunnel. */ u32 ovs_flow_hash; /* Datapath computed hash value. */ u32 recirc_id; /* Recirculation ID. */ struct { u8 src[ETH_ALEN]; /* Ethernet source address. */ u8 dst[ETH_ALEN]; /* Ethernet destination address. */ struct vlan_head vlan; struct vlan_head cvlan; __be16 type; /* Ethernet frame type. */ } eth; /* Filling a hole of two bytes. */ u8 ct_state; u8 ct_orig_proto; /* CT original direction tuple IP * protocol. */ union { struct { u8 proto; /* IP protocol or lower 8 bits of ARP opcode. */ u8 tos; /* IP ToS. */ u8 ttl; /* IP TTL/hop limit. */ u8 frag; /* One of OVS_FRAG_TYPE_*. */ } ip; }; u16 ct_zone; /* Conntrack zone. */ struct { __be16 src; /* TCP/UDP/SCTP source port. */ __be16 dst; /* TCP/UDP/SCTP destination port. */ __be16 flags; /* TCP flags. */ } tp; union { struct { struct { __be32 src; /* IP source address. */ __be32 dst; /* IP destination address. */ } addr; union { struct { __be32 src; __be32 dst; } ct_orig; /* Conntrack original direction fields. */ struct { u8 sha[ETH_ALEN]; /* ARP source hardware address. */ u8 tha[ETH_ALEN]; /* ARP target hardware address. */ } arp; }; } ipv4; struct { struct { struct in6_addr src; /* IPv6 source address. */ struct in6_addr dst; /* IPv6 destination address. */ } addr; __be32 label; /* IPv6 flow label. */ u16 exthdrs; /* IPv6 extension header flags */ union { struct { struct in6_addr src; struct in6_addr dst; } ct_orig; /* Conntrack original direction fields. */ struct { struct in6_addr target; /* ND target address. */ u8 sll[ETH_ALEN]; /* ND source link layer address. */ u8 tll[ETH_ALEN]; /* ND target link layer address. */ } nd; }; } ipv6; struct { u32 num_labels_mask; /* labels present bitmap of effective length MPLS_LABEL_DEPTH */ __be32 lse[MPLS_LABEL_DEPTH]; /* label stack entry */ } mpls; struct ovs_key_nsh nsh; /* network service header */ }; struct { /* Connection tracking fields not packed above. */ struct { __be16 src; /* CT orig tuple tp src port. */ __be16 dst; /* CT orig tuple tp dst port. */ } orig_tp; u32 mark; struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ static inline bool sw_flow_key_is_nd(const struct sw_flow_key *key) { return key->eth.type == htons(ETH_P_IPV6) && key->ip.proto == NEXTHDR_ICMP && key->tp.dst == 0 && (key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)); } struct sw_flow_key_range { unsigned short int start; unsigned short int end; }; struct sw_flow_mask { int ref_count; struct rcu_head rcu; struct sw_flow_key_range range; struct sw_flow_key key; }; struct sw_flow_match { struct sw_flow_key *key; struct sw_flow_key_range range; struct sw_flow_mask *mask; }; #define MAX_UFID_LENGTH 16 /* 128 bits */ struct sw_flow_id { u32 ufid_len; union { u32 ufid[MAX_UFID_LENGTH / 4]; struct sw_flow_key *unmasked_key; }; }; struct sw_flow_actions { struct rcu_head rcu; size_t orig_len; /* From flow_cmd_new netlink actions size */ u32 actions_len; struct nlattr actions[]; }; struct sw_flow_stats { u64 packet_count; /* Number of packets matched. */ u64 byte_count; /* Number of bytes matched. */ unsigned long used; /* Last used time (in jiffies). */ spinlock_t lock; /* Lock for atomic stats update. */ __be16 tcp_flags; /* Union of seen TCP flags. */ }; struct sw_flow { struct rcu_head rcu; struct { struct hlist_node node[2]; u32 hash; } flow_table, ufid_table; int stats_last_writer; /* CPU id of the last writer on * 'stats[0]'. */ struct sw_flow_key key; struct sw_flow_id id; struct cpumask *cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one * is allocated at flow creation time, * the rest are allocated on demand * while holding the 'stats[0].lock'. */ }; struct arp_eth_header { __be16 ar_hrd; /* format of hardware address */ __be16 ar_pro; /* format of protocol address */ unsigned char ar_hln; /* length of hardware address */ unsigned char ar_pln; /* length of protocol address */ __be16 ar_op; /* ARP opcode (command) */ /* Ethernet+IPv4 specific members. */ unsigned char ar_sha[ETH_ALEN]; /* sender hardware address */ unsigned char ar_sip[4]; /* sender IP address */ unsigned char ar_tha[ETH_ALEN]; /* target hardware address */ unsigned char ar_tip[4]; /* target IP address */ } __packed; static inline u8 ovs_key_mac_proto(const struct sw_flow_key *key) { return key->mac_proto & ~SW_FLOW_KEY_INVALID; } static inline u16 __ovs_mac_header_len(u8 mac_proto) { return mac_proto == MAC_PROTO_ETHERNET ? ETH_HLEN : 0; } static inline u16 ovs_mac_header_len(const struct sw_flow_key *key) { return __ovs_mac_header_len(ovs_key_mac_proto(key)); } static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid) { return sfid->ufid_len; } static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid) { return !ovs_identifier_is_ufid(sfid); } void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags, const struct sk_buff *); void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *, unsigned long *used, __be16 *tcp_flags); void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key); int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key); /* Extract key from packet coming from userspace. */ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, struct sk_buff *skb, struct sw_flow_key *key, bool log); #endif /* flow.h */ |
| 8 8 5 1 3 4 2 24 18 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * Serpent Cipher Algorithm. * * Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no> */ #include <crypto/algapi.h> #include <linux/init.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/unaligned.h> #include <linux/types.h> #include <crypto/serpent.h> /* Key is padded to the maximum of 256 bits before round key generation. * Any key length <= 256 bits (32 bytes) is allowed by the algorithm. */ #define PHI 0x9e3779b9UL #define keyiter(a, b, c, d, i, j) \ ({ b ^= d; b ^= c; b ^= a; b ^= PHI ^ i; b = rol32(b, 11); k[j] = b; }) #define loadkeys(x0, x1, x2, x3, i) \ ({ x0 = k[i]; x1 = k[i+1]; x2 = k[i+2]; x3 = k[i+3]; }) #define storekeys(x0, x1, x2, x3, i) \ ({ k[i] = x0; k[i+1] = x1; k[i+2] = x2; k[i+3] = x3; }) #define store_and_load_keys(x0, x1, x2, x3, s, l) \ ({ storekeys(x0, x1, x2, x3, s); loadkeys(x0, x1, x2, x3, l); }) #define K(x0, x1, x2, x3, i) ({ \ x3 ^= k[4*(i)+3]; x2 ^= k[4*(i)+2]; \ x1 ^= k[4*(i)+1]; x0 ^= k[4*(i)+0]; \ }) #define LK(x0, x1, x2, x3, x4, i) ({ \ x0 = rol32(x0, 13);\ x2 = rol32(x2, 3); x1 ^= x0; x4 = x0 << 3; \ x3 ^= x2; x1 ^= x2; \ x1 = rol32(x1, 1); x3 ^= x4; \ x3 = rol32(x3, 7); x4 = x1; \ x0 ^= x1; x4 <<= 7; x2 ^= x3; \ x0 ^= x3; x2 ^= x4; x3 ^= k[4*i+3]; \ x1 ^= k[4*i+1]; x0 = rol32(x0, 5); x2 = rol32(x2, 22);\ x0 ^= k[4*i+0]; x2 ^= k[4*i+2]; \ }) #define KL(x0, x1, x2, x3, x4, i) ({ \ x0 ^= k[4*i+0]; x1 ^= k[4*i+1]; x2 ^= k[4*i+2]; \ x3 ^= k[4*i+3]; x0 = ror32(x0, 5); x2 = ror32(x2, 22);\ x4 = x1; x2 ^= x3; x0 ^= x3; \ x4 <<= 7; x0 ^= x1; x1 = ror32(x1, 1); \ x2 ^= x4; x3 = ror32(x3, 7); x4 = x0 << 3; \ x1 ^= x0; x3 ^= x4; x0 = ror32(x0, 13);\ x1 ^= x2; x3 ^= x2; x2 = ror32(x2, 3); \ }) #define S0(x0, x1, x2, x3, x4) ({ \ x4 = x3; \ x3 |= x0; x0 ^= x4; x4 ^= x2; \ x4 = ~x4; x3 ^= x1; x1 &= x0; \ x1 ^= x4; x2 ^= x0; x0 ^= x3; \ x4 |= x0; x0 ^= x2; x2 &= x1; \ x3 ^= x2; x1 = ~x1; x2 ^= x4; \ x1 ^= x2; \ }) #define S1(x0, x1, x2, x3, x4) ({ \ x4 = x1; \ x1 ^= x0; x0 ^= x3; x3 = ~x3; \ x4 &= x1; x0 |= x1; x3 ^= x2; \ x0 ^= x3; x1 ^= x3; x3 ^= x4; \ x1 |= x4; x4 ^= x2; x2 &= x0; \ x2 ^= x1; x1 |= x0; x0 = ~x0; \ x0 ^= x2; x4 ^= x1; \ }) #define S2(x0, x1, x2, x3, x4) ({ \ x3 = ~x3; \ x1 ^= x0; x4 = x0; x0 &= x2; \ x0 ^= x3; x3 |= x4; x2 ^= x1; \ x3 ^= x1; x1 &= x0; x0 ^= x2; \ x2 &= x3; x3 |= x1; x0 = ~x0; \ x3 ^= x0; x4 ^= x0; x0 ^= x2; \ x1 |= x2; \ }) #define S3(x0, x1, x2, x3, x4) ({ \ x4 = x1; \ x1 ^= x3; x3 |= x0; x4 &= x0; \ x0 ^= x2; x2 ^= x1; x1 &= x3; \ x2 ^= x3; x0 |= x4; x4 ^= x3; \ x1 ^= x0; x0 &= x3; x3 &= x4; \ x3 ^= x2; x4 |= x1; x2 &= x1; \ x4 ^= x3; x0 ^= x3; x3 ^= x2; \ }) #define S4(x0, x1, x2, x3, x4) ({ \ x4 = x3; \ x3 &= x0; x0 ^= x4; \ x3 ^= x2; x2 |= x4; x0 ^= x1; \ x4 ^= x3; x2 |= x0; \ x2 ^= x1; x1 &= x0; \ x1 ^= x4; x4 &= x2; x2 ^= x3; \ x4 ^= x0; x3 |= x1; x1 = ~x1; \ x3 ^= x0; \ }) #define S5(x0, x1, x2, x3, x4) ({ \ x4 = x1; x1 |= x0; \ x2 ^= x1; x3 = ~x3; x4 ^= x0; \ x0 ^= x2; x1 &= x4; x4 |= x3; \ x4 ^= x0; x0 &= x3; x1 ^= x3; \ x3 ^= x2; x0 ^= x1; x2 &= x4; \ x1 ^= x2; x2 &= x0; \ x3 ^= x2; \ }) #define S6(x0, x1, x2, x3, x4) ({ \ x4 = x1; \ x3 ^= x0; x1 ^= x2; x2 ^= x0; \ x0 &= x3; x1 |= x3; x4 = ~x4; \ x0 ^= x1; x1 ^= x2; \ x3 ^= x4; x4 ^= x0; x2 &= x0; \ x4 ^= x1; x2 ^= x3; x3 &= x1; \ x3 ^= x0; x1 ^= x2; \ }) #define S7(x0, x1, x2, x3, x4) ({ \ x1 = ~x1; \ x4 = x1; x0 = ~x0; x1 &= x2; \ x1 ^= x3; x3 |= x4; x4 ^= x2; \ x2 ^= x3; x3 ^= x0; x0 |= x1; \ x2 &= x0; x0 ^= x4; x4 ^= x3; \ x3 &= x0; x4 ^= x1; \ x2 ^= x4; x3 ^= x1; x4 |= x0; \ x4 ^= x1; \ }) #define SI0(x0, x1, x2, x3, x4) ({ \ x4 = x3; x1 ^= x0; \ x3 |= x1; x4 ^= x1; x0 = ~x0; \ x2 ^= x3; x3 ^= x0; x0 &= x1; \ x0 ^= x2; x2 &= x3; x3 ^= x4; \ x2 ^= x3; x1 ^= x3; x3 &= x0; \ x1 ^= x0; x0 ^= x2; x4 ^= x3; \ }) #define SI1(x0, x1, x2, x3, x4) ({ \ x1 ^= x3; x4 = x0; \ x0 ^= x2; x2 = ~x2; x4 |= x1; \ x4 ^= x3; x3 &= x1; x1 ^= x2; \ x2 &= x4; x4 ^= x1; x1 |= x3; \ x3 ^= x0; x2 ^= x0; x0 |= x4; \ x2 ^= x4; x1 ^= x0; \ x4 ^= x1; \ }) #define SI2(x0, x1, x2, x3, x4) ({ \ x2 ^= x1; x4 = x3; x3 = ~x3; \ x3 |= x2; x2 ^= x4; x4 ^= x0; \ x3 ^= x1; x1 |= x2; x2 ^= x0; \ x1 ^= x4; x4 |= x3; x2 ^= x3; \ x4 ^= x2; x2 &= x1; \ x2 ^= x3; x3 ^= x4; x4 ^= x0; \ }) #define SI3(x0, x1, x2, x3, x4) ({ \ x2 ^= x1; \ x4 = x1; x1 &= x2; \ x1 ^= x0; x0 |= x4; x4 ^= x3; \ x0 ^= x3; x3 |= x1; x1 ^= x2; \ x1 ^= x3; x0 ^= x2; x2 ^= x3; \ x3 &= x1; x1 ^= x0; x0 &= x2; \ x4 ^= x3; x3 ^= x0; x0 ^= x1; \ }) #define SI4(x0, x1, x2, x3, x4) ({ \ x2 ^= x3; x4 = x0; x0 &= x1; \ x0 ^= x2; x2 |= x3; x4 = ~x4; \ x1 ^= x0; x0 ^= x2; x2 &= x4; \ x2 ^= x0; x0 |= x4; \ x0 ^= x3; x3 &= x2; \ x4 ^= x3; x3 ^= x1; x1 &= x0; \ x4 ^= x1; x0 ^= x3; \ }) #define SI5(x0, x1, x2, x3, x4) ({ \ x4 = x1; x1 |= x2; \ x2 ^= x4; x1 ^= x3; x3 &= x4; \ x2 ^= x3; x3 |= x0; x0 = ~x0; \ x3 ^= x2; x2 |= x0; x4 ^= x1; \ x2 ^= x4; x4 &= x0; x0 ^= x1; \ x1 ^= x3; x0 &= x2; x2 ^= x3; \ x0 ^= x2; x2 ^= x4; x4 ^= x3; \ }) #define SI6(x0, x1, x2, x3, x4) ({ \ x0 ^= x2; \ x4 = x0; x0 &= x3; x2 ^= x3; \ x0 ^= x2; x3 ^= x1; x2 |= x4; \ x2 ^= x3; x3 &= x0; x0 = ~x0; \ x3 ^= x1; x1 &= x2; x4 ^= x0; \ x3 ^= x4; x4 ^= x2; x0 ^= x1; \ x2 ^= x0; \ }) #define SI7(x0, x1, x2, x3, x4) ({ \ x4 = x3; x3 &= x0; x0 ^= x2; \ x2 |= x4; x4 ^= x1; x0 = ~x0; \ x1 |= x3; x4 ^= x0; x0 &= x2; \ x0 ^= x1; x1 &= x2; x3 ^= x2; \ x4 ^= x3; x2 &= x3; x3 |= x0; \ x1 ^= x4; x3 ^= x4; x4 &= x0; \ x4 ^= x2; \ }) /* * both gcc and clang have misoptimized this function in the past, * producing horrible object code from spilling temporary variables * on the stack. Forcing this part out of line avoids that. */ static noinline void __serpent_setkey_sbox(u32 r0, u32 r1, u32 r2, u32 r3, u32 r4, u32 *k) { k += 100; S3(r3, r4, r0, r1, r2); store_and_load_keys(r1, r2, r4, r3, 28, 24); S4(r1, r2, r4, r3, r0); store_and_load_keys(r2, r4, r3, r0, 24, 20); S5(r2, r4, r3, r0, r1); store_and_load_keys(r1, r2, r4, r0, 20, 16); S6(r1, r2, r4, r0, r3); store_and_load_keys(r4, r3, r2, r0, 16, 12); S7(r4, r3, r2, r0, r1); store_and_load_keys(r1, r2, r0, r4, 12, 8); S0(r1, r2, r0, r4, r3); store_and_load_keys(r0, r2, r4, r1, 8, 4); S1(r0, r2, r4, r1, r3); store_and_load_keys(r3, r4, r1, r0, 4, 0); S2(r3, r4, r1, r0, r2); store_and_load_keys(r2, r4, r3, r0, 0, -4); S3(r2, r4, r3, r0, r1); store_and_load_keys(r0, r1, r4, r2, -4, -8); S4(r0, r1, r4, r2, r3); store_and_load_keys(r1, r4, r2, r3, -8, -12); S5(r1, r4, r2, r3, r0); store_and_load_keys(r0, r1, r4, r3, -12, -16); S6(r0, r1, r4, r3, r2); store_and_load_keys(r4, r2, r1, r3, -16, -20); S7(r4, r2, r1, r3, r0); store_and_load_keys(r0, r1, r3, r4, -20, -24); S0(r0, r1, r3, r4, r2); store_and_load_keys(r3, r1, r4, r0, -24, -28); k -= 50; S1(r3, r1, r4, r0, r2); store_and_load_keys(r2, r4, r0, r3, 22, 18); S2(r2, r4, r0, r3, r1); store_and_load_keys(r1, r4, r2, r3, 18, 14); S3(r1, r4, r2, r3, r0); store_and_load_keys(r3, r0, r4, r1, 14, 10); S4(r3, r0, r4, r1, r2); store_and_load_keys(r0, r4, r1, r2, 10, 6); S5(r0, r4, r1, r2, r3); store_and_load_keys(r3, r0, r4, r2, 6, 2); S6(r3, r0, r4, r2, r1); store_and_load_keys(r4, r1, r0, r2, 2, -2); S7(r4, r1, r0, r2, r3); store_and_load_keys(r3, r0, r2, r4, -2, -6); S0(r3, r0, r2, r4, r1); store_and_load_keys(r2, r0, r4, r3, -6, -10); S1(r2, r0, r4, r3, r1); store_and_load_keys(r1, r4, r3, r2, -10, -14); S2(r1, r4, r3, r2, r0); store_and_load_keys(r0, r4, r1, r2, -14, -18); S3(r0, r4, r1, r2, r3); store_and_load_keys(r2, r3, r4, r0, -18, -22); k -= 50; S4(r2, r3, r4, r0, r1); store_and_load_keys(r3, r4, r0, r1, 28, 24); S5(r3, r4, r0, r1, r2); store_and_load_keys(r2, r3, r4, r1, 24, 20); S6(r2, r3, r4, r1, r0); store_and_load_keys(r4, r0, r3, r1, 20, 16); S7(r4, r0, r3, r1, r2); store_and_load_keys(r2, r3, r1, r4, 16, 12); S0(r2, r3, r1, r4, r0); store_and_load_keys(r1, r3, r4, r2, 12, 8); S1(r1, r3, r4, r2, r0); store_and_load_keys(r0, r4, r2, r1, 8, 4); S2(r0, r4, r2, r1, r3); store_and_load_keys(r3, r4, r0, r1, 4, 0); S3(r3, r4, r0, r1, r2); storekeys(r1, r2, r4, r3, 0); } int __serpent_setkey(struct serpent_ctx *ctx, const u8 *key, unsigned int keylen) { u32 *k = ctx->expkey; u8 *k8 = (u8 *)k; u32 r0, r1, r2, r3, r4; __le32 *lk; int i; /* Copy key, add padding */ for (i = 0; i < keylen; ++i) k8[i] = key[i]; if (i < SERPENT_MAX_KEY_SIZE) k8[i++] = 1; while (i < SERPENT_MAX_KEY_SIZE) k8[i++] = 0; lk = (__le32 *)k; k[0] = le32_to_cpu(lk[0]); k[1] = le32_to_cpu(lk[1]); k[2] = le32_to_cpu(lk[2]); k[3] = le32_to_cpu(lk[3]); k[4] = le32_to_cpu(lk[4]); k[5] = le32_to_cpu(lk[5]); k[6] = le32_to_cpu(lk[6]); k[7] = le32_to_cpu(lk[7]); /* Expand key using polynomial */ r0 = k[3]; r1 = k[4]; r2 = k[5]; r3 = k[6]; r4 = k[7]; keyiter(k[0], r0, r4, r2, 0, 0); keyiter(k[1], r1, r0, r3, 1, 1); keyiter(k[2], r2, r1, r4, 2, 2); keyiter(k[3], r3, r2, r0, 3, 3); keyiter(k[4], r4, r3, r1, 4, 4); keyiter(k[5], r0, r4, r2, 5, 5); keyiter(k[6], r1, r0, r3, 6, 6); keyiter(k[7], r2, r1, r4, 7, 7); keyiter(k[0], r3, r2, r0, 8, 8); keyiter(k[1], r4, r3, r1, 9, 9); keyiter(k[2], r0, r4, r2, 10, 10); keyiter(k[3], r1, r0, r3, 11, 11); keyiter(k[4], r2, r1, r4, 12, 12); keyiter(k[5], r3, r2, r0, 13, 13); keyiter(k[6], r4, r3, r1, 14, 14); keyiter(k[7], r0, r4, r2, 15, 15); keyiter(k[8], r1, r0, r3, 16, 16); keyiter(k[9], r2, r1, r4, 17, 17); keyiter(k[10], r3, r2, r0, 18, 18); keyiter(k[11], r4, r3, r1, 19, 19); keyiter(k[12], r0, r4, r2, 20, 20); keyiter(k[13], r1, r0, r3, 21, 21); keyiter(k[14], r2, r1, r4, 22, 22); keyiter(k[15], r3, r2, r0, 23, 23); keyiter(k[16], r4, r3, r1, 24, 24); keyiter(k[17], r0, r4, r2, 25, 25); keyiter(k[18], r1, r0, r3, 26, 26); keyiter(k[19], r2, r1, r4, 27, 27); keyiter(k[20], r3, r2, r0, 28, 28); keyiter(k[21], r4, r3, r1, 29, 29); keyiter(k[22], r0, r4, r2, 30, 30); keyiter(k[23], r1, r0, r3, 31, 31); k += 50; keyiter(k[-26], r2, r1, r4, 32, -18); keyiter(k[-25], r3, r2, r0, 33, -17); keyiter(k[-24], r4, r3, r1, 34, -16); keyiter(k[-23], r0, r4, r2, 35, -15); keyiter(k[-22], r1, r0, r3, 36, -14); keyiter(k[-21], r2, r1, r4, 37, -13); keyiter(k[-20], r3, r2, r0, 38, -12); keyiter(k[-19], r4, r3, r1, 39, -11); keyiter(k[-18], r0, r4, r2, 40, -10); keyiter(k[-17], r1, r0, r3, 41, -9); keyiter(k[-16], r2, r1, r4, 42, -8); keyiter(k[-15], r3, r2, r0, 43, -7); keyiter(k[-14], r4, r3, r1, 44, -6); keyiter(k[-13], r0, r4, r2, 45, -5); keyiter(k[-12], r1, r0, r3, 46, -4); keyiter(k[-11], r2, r1, r4, 47, -3); keyiter(k[-10], r3, r2, r0, 48, -2); keyiter(k[-9], r4, r3, r1, 49, -1); keyiter(k[-8], r0, r4, r2, 50, 0); keyiter(k[-7], r1, r0, r3, 51, 1); keyiter(k[-6], r2, r1, r4, 52, 2); keyiter(k[-5], r3, r2, r0, 53, 3); keyiter(k[-4], r4, r3, r1, 54, 4); keyiter(k[-3], r0, r4, r2, 55, 5); keyiter(k[-2], r1, r0, r3, 56, 6); keyiter(k[-1], r2, r1, r4, 57, 7); keyiter(k[0], r3, r2, r0, 58, 8); keyiter(k[1], r4, r3, r1, 59, 9); keyiter(k[2], r0, r4, r2, 60, 10); keyiter(k[3], r1, r0, r3, 61, 11); keyiter(k[4], r2, r1, r4, 62, 12); keyiter(k[5], r3, r2, r0, 63, 13); keyiter(k[6], r4, r3, r1, 64, 14); keyiter(k[7], r0, r4, r2, 65, 15); keyiter(k[8], r1, r0, r3, 66, 16); keyiter(k[9], r2, r1, r4, 67, 17); keyiter(k[10], r3, r2, r0, 68, 18); keyiter(k[11], r4, r3, r1, 69, 19); keyiter(k[12], r0, r4, r2, 70, 20); keyiter(k[13], r1, r0, r3, 71, 21); keyiter(k[14], r2, r1, r4, 72, 22); keyiter(k[15], r3, r2, r0, 73, 23); keyiter(k[16], r4, r3, r1, 74, 24); keyiter(k[17], r0, r4, r2, 75, 25); keyiter(k[18], r1, r0, r3, 76, 26); keyiter(k[19], r2, r1, r4, 77, 27); keyiter(k[20], r3, r2, r0, 78, 28); keyiter(k[21], r4, r3, r1, 79, 29); keyiter(k[22], r0, r4, r2, 80, 30); keyiter(k[23], r1, r0, r3, 81, 31); k += 50; keyiter(k[-26], r2, r1, r4, 82, -18); keyiter(k[-25], r3, r2, r0, 83, -17); keyiter(k[-24], r4, r3, r1, 84, -16); keyiter(k[-23], r0, r4, r2, 85, -15); keyiter(k[-22], r1, r0, r3, 86, -14); keyiter(k[-21], r2, r1, r4, 87, -13); keyiter(k[-20], r3, r2, r0, 88, -12); keyiter(k[-19], r4, r3, r1, 89, -11); keyiter(k[-18], r0, r4, r2, 90, -10); keyiter(k[-17], r1, r0, r3, 91, -9); keyiter(k[-16], r2, r1, r4, 92, -8); keyiter(k[-15], r3, r2, r0, 93, -7); keyiter(k[-14], r4, r3, r1, 94, -6); keyiter(k[-13], r0, r4, r2, 95, -5); keyiter(k[-12], r1, r0, r3, 96, -4); keyiter(k[-11], r2, r1, r4, 97, -3); keyiter(k[-10], r3, r2, r0, 98, -2); keyiter(k[-9], r4, r3, r1, 99, -1); keyiter(k[-8], r0, r4, r2, 100, 0); keyiter(k[-7], r1, r0, r3, 101, 1); keyiter(k[-6], r2, r1, r4, 102, 2); keyiter(k[-5], r3, r2, r0, 103, 3); keyiter(k[-4], r4, r3, r1, 104, 4); keyiter(k[-3], r0, r4, r2, 105, 5); keyiter(k[-2], r1, r0, r3, 106, 6); keyiter(k[-1], r2, r1, r4, 107, 7); keyiter(k[0], r3, r2, r0, 108, 8); keyiter(k[1], r4, r3, r1, 109, 9); keyiter(k[2], r0, r4, r2, 110, 10); keyiter(k[3], r1, r0, r3, 111, 11); keyiter(k[4], r2, r1, r4, 112, 12); keyiter(k[5], r3, r2, r0, 113, 13); keyiter(k[6], r4, r3, r1, 114, 14); keyiter(k[7], r0, r4, r2, 115, 15); keyiter(k[8], r1, r0, r3, 116, 16); keyiter(k[9], r2, r1, r4, 117, 17); keyiter(k[10], r3, r2, r0, 118, 18); keyiter(k[11], r4, r3, r1, 119, 19); keyiter(k[12], r0, r4, r2, 120, 20); keyiter(k[13], r1, r0, r3, 121, 21); keyiter(k[14], r2, r1, r4, 122, 22); keyiter(k[15], r3, r2, r0, 123, 23); keyiter(k[16], r4, r3, r1, 124, 24); keyiter(k[17], r0, r4, r2, 125, 25); keyiter(k[18], r1, r0, r3, 126, 26); keyiter(k[19], r2, r1, r4, 127, 27); keyiter(k[20], r3, r2, r0, 128, 28); keyiter(k[21], r4, r3, r1, 129, 29); keyiter(k[22], r0, r4, r2, 130, 30); keyiter(k[23], r1, r0, r3, 131, 31); /* Apply S-boxes */ __serpent_setkey_sbox(r0, r1, r2, r3, r4, ctx->expkey); return 0; } EXPORT_SYMBOL_GPL(__serpent_setkey); int serpent_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen) { return __serpent_setkey(crypto_tfm_ctx(tfm), key, keylen); } EXPORT_SYMBOL_GPL(serpent_setkey); void __serpent_encrypt(const void *c, u8 *dst, const u8 *src) { const struct serpent_ctx *ctx = c; const u32 *k = ctx->expkey; u32 r0, r1, r2, r3, r4; r0 = get_unaligned_le32(src); r1 = get_unaligned_le32(src + 4); r2 = get_unaligned_le32(src + 8); r3 = get_unaligned_le32(src + 12); K(r0, r1, r2, r3, 0); S0(r0, r1, r2, r3, r4); LK(r2, r1, r3, r0, r4, 1); S1(r2, r1, r3, r0, r4); LK(r4, r3, r0, r2, r1, 2); S2(r4, r3, r0, r2, r1); LK(r1, r3, r4, r2, r0, 3); S3(r1, r3, r4, r2, r0); LK(r2, r0, r3, r1, r4, 4); S4(r2, r0, r3, r1, r4); LK(r0, r3, r1, r4, r2, 5); S5(r0, r3, r1, r4, r2); LK(r2, r0, r3, r4, r1, 6); S6(r2, r0, r3, r4, r1); LK(r3, r1, r0, r4, r2, 7); S7(r3, r1, r0, r4, r2); LK(r2, r0, r4, r3, r1, 8); S0(r2, r0, r4, r3, r1); LK(r4, r0, r3, r2, r1, 9); S1(r4, r0, r3, r2, r1); LK(r1, r3, r2, r4, r0, 10); S2(r1, r3, r2, r4, r0); LK(r0, r3, r1, r4, r2, 11); S3(r0, r3, r1, r4, r2); LK(r4, r2, r3, r0, r1, 12); S4(r4, r2, r3, r0, r1); LK(r2, r3, r0, r1, r4, 13); S5(r2, r3, r0, r1, r4); LK(r4, r2, r3, r1, r0, 14); S6(r4, r2, r3, r1, r0); LK(r3, r0, r2, r1, r4, 15); S7(r3, r0, r2, r1, r4); LK(r4, r2, r1, r3, r0, 16); S0(r4, r2, r1, r3, r0); LK(r1, r2, r3, r4, r0, 17); S1(r1, r2, r3, r4, r0); LK(r0, r3, r4, r1, r2, 18); S2(r0, r3, r4, r1, r2); LK(r2, r3, r0, r1, r4, 19); S3(r2, r3, r0, r1, r4); LK(r1, r4, r3, r2, r0, 20); S4(r1, r4, r3, r2, r0); LK(r4, r3, r2, r0, r1, 21); S5(r4, r3, r2, r0, r1); LK(r1, r4, r3, r0, r2, 22); S6(r1, r4, r3, r0, r2); LK(r3, r2, r4, r0, r1, 23); S7(r3, r2, r4, r0, r1); LK(r1, r4, r0, r3, r2, 24); S0(r1, r4, r0, r3, r2); LK(r0, r4, r3, r1, r2, 25); S1(r0, r4, r3, r1, r2); LK(r2, r3, r1, r0, r4, 26); S2(r2, r3, r1, r0, r4); LK(r4, r3, r2, r0, r1, 27); S3(r4, r3, r2, r0, r1); LK(r0, r1, r3, r4, r2, 28); S4(r0, r1, r3, r4, r2); LK(r1, r3, r4, r2, r0, 29); S5(r1, r3, r4, r2, r0); LK(r0, r1, r3, r2, r4, 30); S6(r0, r1, r3, r2, r4); LK(r3, r4, r1, r2, r0, 31); S7(r3, r4, r1, r2, r0); K(r0, r1, r2, r3, 32); put_unaligned_le32(r0, dst); put_unaligned_le32(r1, dst + 4); put_unaligned_le32(r2, dst + 8); put_unaligned_le32(r3, dst + 12); } EXPORT_SYMBOL_GPL(__serpent_encrypt); static void serpent_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct serpent_ctx *ctx = crypto_tfm_ctx(tfm); __serpent_encrypt(ctx, dst, src); } void __serpent_decrypt(const void *c, u8 *dst, const u8 *src) { const struct serpent_ctx *ctx = c; const u32 *k = ctx->expkey; u32 r0, r1, r2, r3, r4; r0 = get_unaligned_le32(src); r1 = get_unaligned_le32(src + 4); r2 = get_unaligned_le32(src + 8); r3 = get_unaligned_le32(src + 12); K(r0, r1, r2, r3, 32); SI7(r0, r1, r2, r3, r4); KL(r1, r3, r0, r4, r2, 31); SI6(r1, r3, r0, r4, r2); KL(r0, r2, r4, r1, r3, 30); SI5(r0, r2, r4, r1, r3); KL(r2, r3, r0, r4, r1, 29); SI4(r2, r3, r0, r4, r1); KL(r2, r0, r1, r4, r3, 28); SI3(r2, r0, r1, r4, r3); KL(r1, r2, r3, r4, r0, 27); SI2(r1, r2, r3, r4, r0); KL(r2, r0, r4, r3, r1, 26); SI1(r2, r0, r4, r3, r1); KL(r1, r0, r4, r3, r2, 25); SI0(r1, r0, r4, r3, r2); KL(r4, r2, r0, r1, r3, 24); SI7(r4, r2, r0, r1, r3); KL(r2, r1, r4, r3, r0, 23); SI6(r2, r1, r4, r3, r0); KL(r4, r0, r3, r2, r1, 22); SI5(r4, r0, r3, r2, r1); KL(r0, r1, r4, r3, r2, 21); SI4(r0, r1, r4, r3, r2); KL(r0, r4, r2, r3, r1, 20); SI3(r0, r4, r2, r3, r1); KL(r2, r0, r1, r3, r4, 19); SI2(r2, r0, r1, r3, r4); KL(r0, r4, r3, r1, r2, 18); SI1(r0, r4, r3, r1, r2); KL(r2, r4, r3, r1, r0, 17); SI0(r2, r4, r3, r1, r0); KL(r3, r0, r4, r2, r1, 16); SI7(r3, r0, r4, r2, r1); KL(r0, r2, r3, r1, r4, 15); SI6(r0, r2, r3, r1, r4); KL(r3, r4, r1, r0, r2, 14); SI5(r3, r4, r1, r0, r2); KL(r4, r2, r3, r1, r0, 13); SI4(r4, r2, r3, r1, r0); KL(r4, r3, r0, r1, r2, 12); SI3(r4, r3, r0, r1, r2); KL(r0, r4, r2, r1, r3, 11); SI2(r0, r4, r2, r1, r3); KL(r4, r3, r1, r2, r0, 10); SI1(r4, r3, r1, r2, r0); KL(r0, r3, r1, r2, r4, 9); SI0(r0, r3, r1, r2, r4); KL(r1, r4, r3, r0, r2, 8); SI7(r1, r4, r3, r0, r2); KL(r4, r0, r1, r2, r3, 7); SI6(r4, r0, r1, r2, r3); KL(r1, r3, r2, r4, r0, 6); SI5(r1, r3, r2, r4, r0); KL(r3, r0, r1, r2, r4, 5); SI4(r3, r0, r1, r2, r4); KL(r3, r1, r4, r2, r0, 4); SI3(r3, r1, r4, r2, r0); KL(r4, r3, r0, r2, r1, 3); SI2(r4, r3, r0, r2, r1); KL(r3, r1, r2, r0, r4, 2); SI1(r3, r1, r2, r0, r4); KL(r4, r1, r2, r0, r3, 1); SI0(r4, r1, r2, r0, r3); K(r2, r3, r1, r4, 0); put_unaligned_le32(r2, dst); put_unaligned_le32(r3, dst + 4); put_unaligned_le32(r1, dst + 8); put_unaligned_le32(r4, dst + 12); } EXPORT_SYMBOL_GPL(__serpent_decrypt); static void serpent_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { struct serpent_ctx *ctx = crypto_tfm_ctx(tfm); __serpent_decrypt(ctx, dst, src); } static struct crypto_alg srp_alg = { .cra_name = "serpent", .cra_driver_name = "serpent-generic", .cra_priority = 100, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = SERPENT_MIN_KEY_SIZE, .cia_max_keysize = SERPENT_MAX_KEY_SIZE, .cia_setkey = serpent_setkey, .cia_encrypt = serpent_encrypt, .cia_decrypt = serpent_decrypt } } }; static int __init serpent_mod_init(void) { return crypto_register_alg(&srp_alg); } static void __exit serpent_mod_fini(void) { crypto_unregister_alg(&srp_alg); } subsys_initcall(serpent_mod_init); module_exit(serpent_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent Cipher Algorithm"); MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>"); MODULE_ALIAS_CRYPTO("serpent"); MODULE_ALIAS_CRYPTO("serpent-generic"); |
| 113 189 239 2 175 16 129 1 5 1 1 1 5 8 2 1 1 31 143 144 132 132 279 280 50 75 1 53 143 1 17 4 36 105 137 199 201 151 168 6 2 6 8 202 1 313 4 40 12 11 27 15 69 69 83 13 99 155 6 14 188 5 39 18 171 4 4 171 355 34 32 65 418 35 71 110 4 5 6 4 44 125 2 4 2 158 9 4 98 121 17 3 25 117 4 264 60 161 153 153 153 272 59 167 7 30 28 18 29 25 122 64 7 248 6 375 24 450 7 129 18 5 1 68 4 61 3 36 37 5 5 1 1 361 540 467 360 541 2 70 75 151 418 38 20 1 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the TCP module. * * Version: @(#)tcp.h 1.0.5 05/23/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _TCP_H #define _TCP_H #define FASTRETRANS_DEBUG 1 #include <linux/list.h> #include <linux/tcp.h> #include <linux/bug.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> #include <linux/bits.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/tcp_ao.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> #include <net/xfrm.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); DECLARE_PER_CPU(u32, tcp_tw_isn); void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE) /* * Never offer a window over 32767 without using window scaling. Some * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW 32767U /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U /* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ #define TCP_PROBE_INTERVAL 600 /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS 16U /* Maximal number of window scale according to RFC1323 */ #define TCP_MAX_WSCALE 14U /* urg_data states */ #define TCP_URG_VALID 0x0100 #define TCP_URG_NOTYET 0x0200 #define TCP_URG_READ 0x0400 #define TCP_RETR1 3 /* * This is how many retries it does before it * tries to figure out if the gateway is * down. Minimal RFC value is 3; it corresponds * to ~3sec-8min depending on RTO. */ #define TCP_RETR2 15 /* * This should take at least * 90 minutes to time out. * RFC1122 says that the limit is 100 sec. * 15 is ~13-30min depending on RTO. */ #define TCP_SYN_RETRIES 6 /* This is how many retries are done * when active opening a connection. * RFC1122 says the minimum retry MUST * be at least 180secs. Nevertheless * this value is corresponding to * 63secs of retransmission with the * current initial RTO. */ #define TCP_SYNACK_RETRIES 5 /* This is how may retries are done * when passive opening a connection. * This is corresponding to 31secs of * retransmission with the current * initial RTO. */ #define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ #define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN /* BSD style FIN_WAIT2 deadlock breaker. * It used to be 3min, new value is 60sec, * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) #else #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif #define TCP_RTO_MAX_SEC 120 #define TCP_RTO_MAX ((unsigned)(TCP_RTO_MAX_SEC * HZ)) #define TCP_RTO_MIN ((unsigned)(HZ / 5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the * initial data transmission if no * valid RTT sample has been acquired, * most likely due to retrans in 3WHS. */ #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes * for local resources. */ #define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */ #define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */ #define TCP_KEEPALIVE_INTVL (75*HZ) #define MAX_TCP_KEEPIDLE 32767 #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 /* Ensure that TCP PAWS checks are relaxed after ~2147 seconds * to avoid overflows. This assumes a clock smaller than 1 Mhz. * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz. */ #define TCP_PAWS_WRAP (INT_MAX / USEC_PER_SEC) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN * to provide reliability equal to one * provided by timewait state. */ #define TCP_PAWS_WINDOW 1 /* Replay window for per-host * timestamps. It must be less than * minimal timewait lifetime. */ /* * TCP option */ #define TCPOPT_NOP 1 /* Padding */ #define TCPOPT_EOL 0 /* End of options */ #define TCPOPT_MSS 2 /* Segment size negotiating */ #define TCPOPT_WINDOW 3 /* Window scaling */ #define TCPOPT_SACK_PERM 4 /* SACK Permitted */ #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ #define TCPOPT_AO 29 /* Authentication Option (RFC5925) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 /* * TCP option lengths */ #define TCPOLEN_MSS 4 #define TCPOLEN_WINDOW 3 #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 #define TCPOLEN_WSCALE_ALIGNED 4 #define TCPOLEN_SACKPERM_ALIGNED 4 #define TCPOLEN_SACK_BASE 2 #define TCPOLEN_SACK_BASE_ALIGNED 4 #define TCPOLEN_SACK_PERBLOCK 8 #define TCPOLEN_MD5SIG_ALIGNED 20 #define TCPOLEN_MSS_ALIGNED 4 #define TCPOLEN_EXP_SMC_BASE_ALIGNED 8 /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */ #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ /* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 #define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD 0x200 /* Force enable TFO on all listeners, i.e., not requiring the * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 0x400 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { if (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). */ static inline bool before(__u32 seq1, __u32 seq2) { return (__s32)(seq1-seq2) < 0; } #define after(seq2, seq1) before(seq1, seq2) /* is s2<=s1<=s3 ? */ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) { return seq3 - seq2 >= seq1 - seq2; } static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); if (!skb_zcopy_pure(skb)) sk_mem_uncharge(sk, skb->truesize); else sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb))); __kfree_skb(skb); } void sk_forced_mem_schedule(struct sock *sk, int size); bool tcp_check_oom(const struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) void tcp_tasklet_init(void); int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); void tcp_remove_empty_skb(struct sock *sk); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); void tcp_splice_eof(struct socket *sock); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); int tcp_wmem_schedule(struct sock *sk, int copy); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule); static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { /* How many ACKs S/ACKing new data have we sent? */ const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ icsk->icsk_ack.ato = TCP_ATO_MIN; } else icsk->icsk_ack.quick -= pkts; } } #define TCP_ECN_MODE_RFC3168 BIT(0) #define TCP_ECN_QUEUE_CWR BIT(1) #define TCP_ECN_DEMAND_CWR BIT(2) #define TCP_ECN_SEEN BIT(3) #define TCP_ECN_MODE_ACCECN BIT(4) #define TCP_ECN_DISABLED 0 #define TCP_ECN_MODE_PENDING (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) #define TCP_ECN_MODE_ANY (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp) { return tp->ecn_flags & TCP_ECN_MODE_ANY; } static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp) { return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168; } static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp) { return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN; } static inline bool tcp_ecn_disabled(const struct tcp_sock *tp) { return !tcp_ecn_mode_any(tp); } static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp) { return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING; } static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode) { tp->ecn_flags &= ~TCP_ECN_MODE_ANY; tp->ecn_flags |= mode; } enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, TCP_TW_SYN = 3, TCP_TW_ACK_OOW = 4 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th, u32 *tw_isn, enum skb_drop_reason *drop_reason); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race, enum skb_drop_reason *drop_reason); enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); bool tcp_bpf_bypass_getsockopt(int level, int optname); int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss); void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); #endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); /* * BPF SKB-less helpers */ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, int mss, u32 tsoff); #if IS_ENABLED(CONFIG_BPF) struct bpf_tcp_req_attrs { u32 rcv_tsval; u32 rcv_tsecr; u16 mss; u8 rcv_wscale; u8 snd_wscale; u8 ecn_ok; u8 wscale_ok; u8 sack_ok; u8 tstamp_ok; u8 usec_ts_ok; u8 reserved[3]; }; #endif #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE 2 #define TCP_SYNCOOKIE_PERIOD (60 * HZ) #define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) * It is racy as we do not hold a lock, but race is very minor. */ static inline void tcp_synq_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(tcp_sk_rw(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, * then we're under synflood. However, we have to use * 'last_overflow - HZ' as lower bound. That's because a concurrent * tcp_synq_overflow() could update .ts_recent_stamp after we read * jiffies but before we store .ts_recent_stamp into last_overflow, * which could lead to rejecting a valid syncookie. */ return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } /* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ static inline u64 tcp_ns_to_ts(bool usec_ts, u64 val) { if (usec_ts) return div_u64(val, NSEC_PER_USEC); return div_u64(val, NSEC_PER_MSEC); } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst) { return READ_ONCE(net->ipv4.sysctl_tcp_ecn) || dst_feature(dst, RTAX_FEATURE_ECN); } #if IS_ENABLED(CONFIG_BPF) static inline bool cookie_bpf_ok(struct sk_buff *skb) { return skb->sk; } struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb); #else static inline bool cookie_bpf_ok(struct sk_buff *skb) { return false; } static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk, struct sk_buff *skb) { return NULL; } #endif /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); enum tcp_queue { TCP_FRAG_IN_WRITE_QUEUE, TCP_FRAG_IN_RTX_QUEUE, }; int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto); void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); static inline void tcp_cleanup_skb(struct sk_buff *skb) { skb_dst_drop(skb); secpath_reset(skb); } static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); __skb_queue_tail(&sk->sk_receive_queue, skb); } /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) __sock_put(sk); if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1) __sock_put(sk); inet_csk_clear_xmit_timers(sk); } unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { int cutoff; /* When peer uses tiny windows, there is no use in packetizing * to sub-MSS pieces for the sake of SWS or making sure there * are enough packets in the pipe for fast recovery. * * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; if (cutoff && pktsize > cutoff) return max_t(int, cutoff, 68U - tp->tcp_header_len); else return pktsize; } /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor, bool noack, u32 *copied_seq); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); void tcp_read_done(struct sock *sk, size_t len); void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); static inline unsigned int tcp_rto_max(const struct sock *sk) { return READ_ONCE(inet_csk(sk)->icsk_rto_max); } static inline void tcp_bound_rto(struct sock *sk) { inet_csk(sk)->icsk_rto = min(inet_csk(sk)->icsk_rto, tcp_rto_max(sk)); } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { /* mptcp hooks are only on the slow path */ if (sk_is_mptcp((struct sock *)tp)) return; tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); } static inline void tcp_fast_path_on(struct tcp_sock *tp) { __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); } static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) tcp_fast_path_on(tp); } u32 tcp_delack_max(const struct sock *sk); /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(const struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min); if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); return rto_min; } static inline u32 tcp_rto_min_us(const struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) { return dst_metric_locked(dst, RTAX_CC_ALGO); } /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_receive_window(const struct tcp_sock *tp) { s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt; if (win < 0) win = 0; return (u32) win; } /* Choose a new window, without checks for shrinking, and without * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); /* TCP uses 32bit jiffies to save some space. * Note that this is different from tcp_time_stamp, which * historically has been the same until linux-4.13. */ #define tcp_jiffies32 ((u32)jiffies) /* * Deliver a 32bit value for TCP timestamp option (RFC 7323) * It is no longer tied to jiffies, but to 1 ms clock. * Note: double check if you want to use tcp_jiffies32 instead of this. */ #define TCP_TS_HZ 1000 static inline u64 tcp_clock_ns(void) { return ktime_get_ns(); } static inline u64 tcp_clock_us(void) { return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } static inline u64 tcp_clock_ms(void) { return div_u64(tcp_clock_ns(), NSEC_PER_MSEC); } /* TCP Timestamp included in TS option (RFC 1323) can either use ms * or usec resolution. Each socket carries a flag to select one or other * resolution, as the route attribute could change anytime. * Each flow must stick to initial resolution. */ static inline u32 tcp_clock_ts(bool usec_ts) { return usec_ts ? tcp_clock_us() : tcp_clock_ms(); } static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp) { return div_u64(tp->tcp_mstamp, USEC_PER_MSEC); } static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) { if (tp->tcp_usec_ts) return tp->tcp_mstamp; return tcp_time_stamp_ms(tp); } void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { return max_t(s64, t1 - t0, 0); } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } /* Provide skb TSval in usec or ms unit */ static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb) { if (usec_ts) return tcp_skb_timestamp_us(skb); return div_u64(skb->skb_mstamp_ns, NSEC_PER_MSEC); } static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw) { return tcp_clock_ts(tcptw->tw_sk.tw_usec_ts) + tcptw->tw_ts_offset; } static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) { return tcp_clock_ts(treq->req_usec_ts) + treq->ts_off; } #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) #define TCPHDR_FIN BIT(0) #define TCPHDR_SYN BIT(1) #define TCPHDR_RST BIT(2) #define TCPHDR_PSH BIT(3) #define TCPHDR_ACK BIT(4) #define TCPHDR_URG BIT(5) #define TCPHDR_ECE BIT(6) #define TCPHDR_CWR BIT(7) #define TCPHDR_AE BIT(8) #define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \ TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \ TCPHDR_FLAGS_MASK) #define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) /* State flags for sacked in struct tcp_skb_cb */ enum tcp_skb_cb_sacked_flags { TCPCB_SACKED_ACKED = (1 << 0), /* SKB ACK'd by a SACK block */ TCPCB_SACKED_RETRANS = (1 << 1), /* SKB retransmitted */ TCPCB_LOST = (1 << 2), /* SKB is lost */ TCPCB_TAGBITS = (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS | TCPCB_LOST), /* All tag bits */ TCPCB_REPAIRED = (1 << 4), /* SKB repaired (no skb_mstamp_ns) */ TCPCB_EVER_RETRANS = (1 << 7), /* Ever retransmitted frame */ TCPCB_RETRANS = (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS | TCPCB_REPAIRED), }; /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. * This is 44 bytes if IPV6 is enabled. * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { /* Note : * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; __u16 tcp_flags; /* TCP header flags (tcp[12-13])*/ __u8 sacked; /* State flags for SACK. */ __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ #define TSTAMP_ACK_SK 0x1 #define TSTAMP_ACK_BPF 0x2 __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ unused:4; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { #define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1) /* There is space for up to 24 bytes */ __u32 is_app_limited:1, /* cwnd not fully used? */ delivered_ce:20, unused:11; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ u64 first_tx_mstamp; /* when we reached the "delivered" count */ u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] */ static inline int tcp_v6_iif(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->header.h6.iif; } static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags)) return TCP_SKB_CB(skb)->header.h6.iif; #endif return 0; } extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); void tcp_v6_early_demux(struct sk_buff *skb); #endif /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) return TCP_SKB_CB(skb)->header.h4.iif; #endif return 0; } /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_segs; } static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs = segs; } static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs += segs; } /* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_size; } static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { return likely(!TCP_SKB_CB(skb)->eor); } static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && skb_pure_zcopy_same(to, from) && skb_frags_readable(to) == skb_frags_readable(from)); } static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, const struct sk_buff *from) { return likely(mptcp_skb_can_collapse(to, from) && !skb_cmp_decrypted(to, from)); } /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ }; /* * Interface for adding new TCP congestion control handlers */ #define TCP_CA_NAME_MAX 16 #define TCP_CA_MAX 128 #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; u32 in_flight; }; /* A rate sample measures the number of (original/retransmitted) data * packets delivered "delivered" over an interval of time "interval_us". * The tcp_rate.c code fills in the rate sample, and congestion * control modules that define a cong_control function to run at the end * of ACK processing can optionally chose to consult this sample when * setting cwnd and pacing rate. * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ s32 delivered_ce; /* number of packets delivered w/ CE marks*/ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { /* fast path fields are put first to fill one cache line */ /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); /* do new cwnd calculation (required) */ void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); /* override sysctl_tcp_min_tso_segs */ u32 (*min_tso_segs)(struct sock *sk); /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ u32 (*sndbuf_expand)(struct sock *sk); /* control/slow paths put last */ /* get info for inet_diag (optional) */ size_t (*get_info)(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; struct list_head list; u32 key; u32 flags; /* initialize private data (optional) */ void (*init)(struct sock *sk); /* cleanup private data (optional) */ void (*release)(struct sock *sk); } ____cacheline_aligned_in_smp; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); int tcp_update_congestion_control(struct tcp_congestion_ops *type, struct tcp_congestion_ops *old_type); int tcp_validate_congestion_control(struct tcp_congestion_ops *ca); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(struct net *net, const char *name); void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer) { return NULL; } #endif static inline bool tcp_ca_needs_ecn(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cwnd_event) icsk->icsk_ca_ops->cwnd_event(sk, event); } /* From tcp_cong.c */ void tcp_set_ca_state(struct sock *sk, const u8 ca_state); /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs); void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK */ static inline int tcp_is_sack(const struct tcp_sock *tp) { return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) { return !tcp_is_sack(tp); } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; } /* This determines how many packets are "in the network" to the best * of our knowledge. In many cases it is conservative, but where * detailed information is available from the receiver (via SACK * blocks etc.) we can make more aggressive calculations. * * Use this for decisions involving congestion control, use just * tp->packets_out to determine if the send queue is empty or not. * * Read this equation as: * * "Packets sent once on transmission queue" MINUS * "Packets left network, but not honestly ACKed yet" PLUS * "Packets fast retransmitted" */ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } #define TCP_INFINITE_SSTHRESH 0x7fffffff static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) { return tp->snd_cwnd; } static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) { WARN_ON_ONCE((int)val <= 0); tp->snd_cwnd = val; } static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; } static inline bool tcp_in_cwnd_reduction(const struct sock *sk) { return (TCPF_CA_CWR | TCPF_CA_Recovery) & (1 << inet_csk(sk)->icsk_ca_state); } /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tcp_in_cwnd_reduction(sk)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, ((tcp_snd_cwnd(tp) >> 1) + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) void tcp_enter_cwr(struct sock *sk); __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. */ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) { return 3; } /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { return tp->snd_una + tp->snd_wnd; } /* We follow the spirit of RFC2861 to validate cwnd but implement a more * flexible approach. The RFC suggests cwnd should not be raised unless * it was fully used previously. And that's exactly what we do in * congestion avoidance mode. But in slow start we allow cwnd to grow * as long as the application has used half the cwnd. * Example : * cwnd is 10 (IW10), but application sends 9 frames. * We allow cwnd to reach 18 when all frames are ACKed. * This check is safe because it's as aggressive as slow start which already * risks 100% overshoot. The advantage is that we discourage application to * either send more filler packets or data to artificially blow up the cwnd * usage, and allow application-limited process to probe bw more aggressively. */ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tp->is_cwnd_limited) return true; /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; return false; } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static inline bool tcp_needs_internal_pacing(const struct sock *sk) { return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } /* Estimates in how many jiffies next packet for this flow can be sent. * Scheduling a retransmit timer too early would be silly. */ static inline unsigned long tcp_pacing_delay(const struct sock *sk) { s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache; return delay > 0 ? nsecs_to_jiffies(delay) : 0; } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, bool pace_delay) { if (pace_delay) when += tcp_pacing_delay(sk); inet_csk_reset_xmit_timer(sk, what, when, tcp_rto_max(sk)); } /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) */ static inline unsigned long tcp_probe0_base(const struct sock *sk) { return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); } /* Variant of inet_csk_rto_backoff() used for zero window probes */ static inline unsigned long tcp_probe0_when(const struct sock *sk, unsigned long max_when) { u8 backoff = min_t(u8, ilog2(TCP_RTO_MAX / TCP_RTO_MIN) + 1, inet_csk(sk)->icsk_backoff); u64 when = (u64)tcp_probe0_base(sk) << backoff; return (unsigned long)min_t(u64, when, max_when); } static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, tcp_probe0_base(sk), true); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } /* * Calculate(/check) TCP checksum */ static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __skb_checksum_complete(skb); } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; rx_opt->num_sacks = 0; } void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); s32 delta; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } /* Determine a window scaling and initial window to offer. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int __tcp_win_from_space(u8 scaling_ratio, int space) { s64 scaled_space = (s64)space * scaling_ratio; return scaled_space >> TCP_RMEM_TO_WIN_SCALE; } static inline int tcp_win_from_space(const struct sock *sk, int space) { return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space); } /* inverse of __tcp_win_from_space() */ static inline int __tcp_space_from_win(u8 scaling_ratio, int win) { u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE; do_div(val, scaling_ratio); return val; } static inline int tcp_space_from_win(const struct sock *sk, int win) { return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } /* Assume a 50% default for skb->len/skb->truesize ratio. * This may be adjusted later in tcp_measure_rcv_mss(). */ #define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1)) static inline void tcp_scaling_ratio_init(struct sock *sk) { tcp_sk(sk)->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; } /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { int unused_mem = sk_unused_reserved_mem(sk); struct tcp_sock *tp = tcp_sk(sk); tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); if (unused_mem) tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, tcp_win_from_space(sk, unused_mem)); } static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) { __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); } void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small * len/truesize ratio. */ static inline bool tcp_rmem_pressure(const struct sock *sk) { int rcvbuf, threshold; if (tcp_under_memory_pressure(sk)) return true; rcvbuf = READ_ONCE(sk->sk_rcvbuf); threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } static inline bool tcp_epollin_ready(const struct sock *sk, int target) { const struct tcp_sock *tp = tcp_sk(sk); int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); if (avail <= 0) return false; return (avail >= target) || tcp_rmem_pressure(sk) || (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss); } extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() * and do_tcp_setsockopt(). */ val = READ_ONCE(tp->keepalive_intvl); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ val = READ_ONCE(tp->keepalive_time); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() * and do_tcp_setsockopt(). */ val = READ_ONCE(tp->keepalive_probes); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) { int fin_timeout = tcp_sk(sk)->linger2 ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) fin_timeout = (rto << 2) - (rto >> 1); return fin_timeout; } static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, int paws_win) { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_WRAP))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, * then following tcp messages have valid values. Ignore 0 value, * or else 'negative' tsval might forbid us to accept their packets. */ if (!rx_opt->ts_recent) return true; return false; } static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, int rst) { if (tcp_paws_check(rx_opt, 0)) return false; /* RST segments are not recommended to carry timestamp, and, if they do, it is recommended to ignore PAWS because "their cleanup function should take precedence over timestamps." Certainly, it is mistake. It is necessary to understand the reasons of this constraint to relax it: if peer reboots, clock may go out-of-sync and half-open connections will not be reset. Actually, the problem would be not existing if all the implementations followed draft about maintaining clock via reboots. Linux-2.2 DOES NOT! However, we can relax time bounds for RST segments to MSL. */ if (rst && !time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1); TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1); } /* from STCP */ static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp) { tp->lost_skb_hint = NULL; } static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { tcp_clear_retrans_hints_partial(tp); tp->retransmit_skb_hint = NULL; } #define tcp_md5_addr tcp_ao_addr /* - key database */ struct tcp_md5sig_key { struct hlist_node node; u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; struct rcu_head rcu; }; /* - sock block */ struct tcp_md5sig_info { struct hlist_head head; struct rcu_head rcu; }; /* - pseudo header */ struct tcp4_pseudohdr { __be32 saddr; __be32 daddr; __u8 pad; __u8 protocol; __be16 len; }; struct tcp6_pseudohdr { struct in6_addr saddr; struct in6_addr daddr; __be32 len; __be32 protocol; /* including padding */ }; union tcp_md5sum_block { struct tcp4_pseudohdr ip4; #if IS_ENABLED(CONFIG_IPV6) struct tcp6_pseudohdr ip6; #endif }; /* * struct tcp_sigpool - per-CPU pool of ahash_requests * @scratch: per-CPU temporary area, that can be used between * tcp_sigpool_start() and tcp_sigpool_end() to perform * crypto request * @req: pre-allocated ahash request */ struct tcp_sigpool { void *scratch; struct ahash_request *req; }; int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size); void tcp_sigpool_get(unsigned int id); void tcp_sigpool_release(unsigned int id); int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, const struct sk_buff *skb, unsigned int header_len); /** * tcp_sigpool_start - disable bh and start using tcp_sigpool_ahash * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() * @c: returned tcp_sigpool for usage (uninitialized on failure) * * Returns: 0 on success, error otherwise. */ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); /** * tcp_sigpool_end - enable bh and stop using tcp_sigpool * @c: tcp_sigpool context that was returned by tcp_sigpool_start() */ void tcp_sigpool_end(struct tcp_sigpool *c); size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); /* - functions */ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, struct tcp_md5sig_key *key); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags); void tcp_clear_md5_list(struct sock *sk); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family, false); } static inline struct tcp_md5sig_key * tcp_md5_do_lookup_any_l3index(const struct sock *sk, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; return __tcp_md5_do_lookup(sk, 0, addr, family, true); } #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { return NULL; } static inline struct tcp_md5sig_key * tcp_md5_do_lookup_any_l3index(const struct sock *sk, const union tcp_md5_addr *addr, int family) { return NULL; } #define tcp_twsk_md5_key(twsk) NULL #endif int tcp_md5_alloc_sigpool(void); void tcp_md5_release_sigpool(void); void tcp_md5_add_sigpool(void); extern int tcp_md5_sigpool_id; int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) #define TCP_FASTOPEN_KEY_MAX 2 #define TCP_FASTOPEN_KEY_BUF_LENGTH \ (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; int num; struct rcu_head rcu; }; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Caller needs to wrap with rcu_read_(un)lock() */ static inline struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); if (!ctx) ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); return ctx; } static inline bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, const struct tcp_fastopen_cookie *orig) { if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && orig->len == foc->len && !memcmp(orig->val, foc->val, foc->len)) return true; return false; } static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { return ctx->num; } /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ enum tcp_chrono { TCP_CHRONO_UNSPEC, TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */ TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */ TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */ __TCP_CHRONO_MAX, }; void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses * the same memory storage than skb->destructor/_skb_refdst */ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) { skb->destructor = NULL; skb->_skb_refdst = 0UL; } #define tcp_skb_tsorted_save(skb) { \ unsigned long _save = skb->_skb_refdst; \ skb->_skb_refdst = 0UL; #define tcp_skb_tsorted_restore(skb) \ skb->_skb_refdst = _save; \ } void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) { return skb_rb_first(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) { return skb_rb_last(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); } #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, const struct sk_buff *skb) { return skb_queue_is_last(&sk->sk_write_queue, skb); } /** * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue * @sk: socket * * Since the write queue can have a temporary empty skb in it, * we must not use "return skb_queue_empty(&sk->sk_write_queue)" */ static inline bool tcp_write_queue_empty(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) { return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); } static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) { return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); /* Queue it, remembering where we must start sending. */ if (sk->sk_write_queue.next == skb) tcp_chrono_start(sk, TCP_CHRONO_BUSY); } /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); } static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } static inline void tcp_write_collapse_fence(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb) TCP_SKB_CB(skb)->eor = 1; } static inline void tcp_push_pending_frames(struct sock *sk) { if (tcp_send_head(sk)) { struct tcp_sock *tp = tcp_sk(sk); __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); } } /* Start sequence of the skb just after the highest skb with SACKed * bit, valid only if sacked_out > 0 or when the caller has ensured * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { if (!tp->sacked_out) return tp->snd_una; if (tp->highest_sack == NULL) return tp->snd_nxt; return TCP_SKB_CB(tp->highest_sack)->seq; } static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { tcp_sk(sk)->highest_sack = skb_rb_next(skb); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) { return tcp_sk(sk)->highest_sack; } static inline void tcp_highest_sack_reset(struct sock *sk) { tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk); } /* Called when old skb is about to be deleted and replaced by new skb */ static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { if (old == tcp_highest_sack(sk)) tcp_sk(sk)->highest_sack = new; } /* This helper checks if socket has IP_TRANSPARENT set */ static inline bool inet_sk_transparent(const struct sock *sk) { switch (sk->sk_state) { case TCP_TIME_WAIT: return inet_twsk(sk)->tw_transparent; case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } return inet_test_bit(TRANSPARENT, sk); } /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) { return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); } /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, TCP_SEQ_STATE_ESTABLISHED, }; void *tcp_seq_start(struct seq_file *seq, loff_t *pos); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { sa_family_t family; }; struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; int bucket, offset, sbucket, num; loff_t last_pos; }; extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); #ifdef CONFIG_INET void tcp_gro_complete(struct sk_buff *skb); #else static inline void tcp_gro_complete(struct sk_buff *skb) { } #endif void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); u32 val; val = READ_ONCE(tp->notsent_lowat); return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); int (*md5_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); #endif #ifdef CONFIG_TCP_AO int (*ao_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, struct sock *addr_sk, int sndid, int rcvid); int (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key, const struct sock *sk, __be32 sisn, __be32 disn, bool send); int (*calc_ao_hash)(char *location, struct tcp_ao_key *ao, const struct sock *sk, const struct sk_buff *skb, const u8 *tkey, int hash_offset, u32 sne); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); #endif #ifdef CONFIG_TCP_AO struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, struct request_sock *req, int sndid, int rcvid); int (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk); int (*ao_synack_hash)(char *ao_hash, struct tcp_ao_key *mkt, struct request_sock *req, const struct sk_buff *skb, int hash_offset, u32 sne); #endif #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; #if IS_ENABLED(CONFIG_IPV6) extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #endif #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { tcp_synq_overflow(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; } #endif struct tcp_key { union { struct { struct tcp_ao_key *ao_key; char *traffic_key; u32 sne; u8 rcv_next; }; struct tcp_md5sig_key *md5_key; }; enum { TCP_KEY_NONE = 0, TCP_KEY_MD5, TCP_KEY_AO, } type; }; static inline void tcp_get_current_key(const struct sock *sk, struct tcp_key *out) { #if defined(CONFIG_TCP_AO) || defined(CONFIG_TCP_MD5SIG) const struct tcp_sock *tp = tcp_sk(sk); #endif #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key)) { struct tcp_ao_info *ao; ao = rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held(sk)); if (ao) { out->ao_key = READ_ONCE(ao->current_key); out->type = TCP_KEY_AO; return; } } #endif #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { out->md5_key = tp->af_specific->md5_lookup(sk, sk); if (out->md5_key) { out->type = TCP_KEY_MD5; return; } } #endif out->type = TCP_KEY_NONE; } static inline bool tcp_key_is_md5(const struct tcp_key *key) { if (static_branch_tcp_md5()) return key->type == TCP_KEY_MD5; return false; } static inline bool tcp_key_is_ao(const struct tcp_key *key) { if (static_branch_tcp_ao()) return key->type == TCP_KEY_AO; return false; } int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); /* tcp_plb.c */ /* * Scaling factor for fractions in PLB. For example, tcp_plb_update_state * expects cong_ratio which represents fraction of traffic that experienced * congestion over a single RTT. In order to avoid floating point operations, * this fraction should be mapped to (1 << TCP_PLB_SCALE) and passed in. */ #define TCP_PLB_SCALE 8 /* State for PLB (Protective Load Balancing) for a single TCP connection. */ struct tcp_plb_state { u8 consec_cong_rounds:5, /* consecutive congested rounds */ unused:3; u32 pause_until; /* jiffies32 when PLB can resume rerouting */ }; static inline void tcp_plb_init(const struct sock *sk, struct tcp_plb_state *plb) { plb->consec_cong_rounds = 0; plb->pause_until = 0; } void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, const int cong_ratio); void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str) { WARN_ONCE(cond, "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n", str, tcp_snd_cwnd(tcp_sk(sk)), tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, tcp_sk(sk)->tlp_high_seq, sk->sk_state, inet_csk(sk)->icsk_ca_state, tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, inet_csk(sk)->icsk_pmtu_cookie); } /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; if (likely(skb)) { u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } else { tcp_warn_once(sk, 1, "rtx queue empty: "); return jiffies_to_usecs(rto); } } /* * Save and compile IPv4 options, return a pointer to it */ static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, struct sk_buff *skb) { const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct ip_options_rcu *dopt = NULL; if (opt->optlen) { int opt_size = sizeof(*dopt) + opt->optlen; dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) { kfree(dopt); dopt = NULL; } } return dopt; } /* locally generated TCP pure ACKs have skb->truesize == 2 * (check tcp_send_ack() in net/ipv4/tcp_output.c ) * This is much faster than dissecting the packet to find out. * (Think of GRE encapsulations, IPv4, IPv6, ...) */ static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) { return skb->truesize == 2; } static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) { skb->truesize = 2; } static inline int tcp_inq(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int answ; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { answ = 0; } else if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { answ = tp->rcv_nxt - tp->copied_seq; /* Subtract 1, if FIN was received */ if (answ && sock_flag(sk, SOCK_DONE)) answ--; } else { answ = tp->urg_seq - tp->copied_seq; } return answ; } int tcp_peek_len(struct socket *sock); static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); /* We update these fields while other threads might * read them from tcp_get_info() */ WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in); if (skb->len > tcp_hdrlen(skb)) WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in); } /* * TCP listen path runs lockless. * We forced "struct sock" to be const qualified to make sure * we don't modify one of its field by mistake. * Here, we increment sk_drops which is an atomic_t, so we can safely * make sock writable again. */ static inline void tcp_listendrop(const struct sock *sk) { atomic_inc(&((struct sock *)sk)->sk_drops); __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); } enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); /* * Interface for adding Upper Level Protocols over TCP */ #define TCP_ULP_NAME_MAX 16 #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) struct tcp_ulp_ops { struct list_head list; /* initialize ulp */ int (*init)(struct sock *sk); /* update ulp */ void (*update)(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin); size_t (*get_info_size)(const struct sock *sk, bool net_admin); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); char name[TCP_ULP_NAME_MAX]; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) #ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_SYSCALL int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #ifdef CONFIG_BPF_STREAM_PARSER struct strparser; int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, sk_read_actor_t recv_actor); #endif /* CONFIG_BPF_STREAM_PARSER */ #endif /* CONFIG_BPF_SYSCALL */ #ifdef CONFIG_INET void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); #else static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) { } #endif int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { } #endif #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { skops->skb = skb; skops->skb_data_end = skb->data + end_offset; } #else static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { } #endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF * program loaded). */ #ifdef CONFIG_BPF static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { struct bpf_sock_ops_kern sock_ops; int ret; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; sock_ops.is_locked_tcp_sock = 1; sock_owned_by_me(sk); } sock_ops.sk = sk; sock_ops.op = op; if (nargs > 0) memcpy(sock_ops.args, args, nargs * sizeof(*args)); ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); if (ret == 0) ret = sock_ops.reply; else ret = -1; return ret; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { u32 args[2] = {arg1, arg2}; return tcp_call_bpf(sk, op, 2, args); } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { u32 args[3] = {arg1, arg2, arg3}; return tcp_call_bpf(sk, op, 3, args); } #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { return -EPERM; } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { return -EPERM; } #endif static inline u32 tcp_timeout_init(struct sock *sk) { int timeout; timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL); if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { int rwnd; rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL); if (rwnd < 0) rwnd = 0; return rwnd; } static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) void clean_acked_data_enable(struct tcp_sock *tp, void (*cad)(struct sock *sk, u32 ack_seq)); void clean_acked_data_disable(struct tcp_sock *tp); void clean_acked_data_flush(void); #endif DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static inline void tcp_add_tx_delay(struct sk_buff *skb, const struct tcp_sock *tp) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; } /* Compute Earliest Departure Time for some control packets * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. */ static inline u64 tcp_transmit_time(const struct sock *sk) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) { u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; } return 0; } static inline int tcp_parse_auth_options(const struct tcphdr *th, const u8 **md5_hash, const struct tcp_ao_hdr **aoh) { const u8 *md5_tmp, *ao_tmp; int ret; ret = tcp_do_parse_auth_options(th, &md5_tmp, &ao_tmp); if (ret) return ret; if (md5_hash) *md5_hash = md5_tmp; if (aoh) { if (!ao_tmp) *aoh = NULL; else *aoh = (struct tcp_ao_hdr *)(ao_tmp - 2); } return 0; } static inline bool tcp_ao_required(struct sock *sk, const void *saddr, int family, int l3index, bool stat_inc) { #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; struct tcp_ao_key *ao_key; if (!static_branch_unlikely(&tcp_ao_needed.key)) return false; ao_info = rcu_dereference_check(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk)); if (!ao_info) return false; ao_key = tcp_ao_do_lookup(sk, l3index, saddr, family, -1, -1); if (ao_info->ao_required || ao_key) { if (stat_inc) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOREQUIRED); atomic64_inc(&ao_info->counters.ao_required); } return true; } #endif return false; } enum skb_drop_reason tcp_inbound_hash(struct sock *sk, const struct request_sock *req, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif); #endif /* _TCP_H */ |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/libnvdimm.h> #include "rxe.h" #include "rxe_loc.h" /* Return a random 8 bit key value that is * different than the last_key. Set last_key to -1 * if this is the first key for an MR or MW */ u8 rxe_get_next_key(u32 last_key) { u8 key; do { get_random_bytes(&key, 1); } while (key == last_key); return key; } int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length) { switch (mr->ibmr.type) { case IB_MR_TYPE_DMA: return 0; case IB_MR_TYPE_USER: case IB_MR_TYPE_MEM_REG: if (iova < mr->ibmr.iova || iova + length > mr->ibmr.iova + mr->ibmr.length) { rxe_dbg_mr(mr, "iova/length out of range\n"); return -EINVAL; } return 0; default: rxe_dbg_mr(mr, "mr type not supported\n"); return -EINVAL; } } void rxe_mr_init(int access, struct rxe_mr *mr) { u32 key = mr->elem.index << 8 | rxe_get_next_key(-1); /* set ibmr->l/rkey and also copy into private l/rkey * for user MRs these will always be the same * for cases where caller 'owns' the key portion * they may be different until REG_MR WQE is executed. */ mr->lkey = mr->ibmr.lkey = key; mr->rkey = mr->ibmr.rkey = key; mr->access = access; mr->ibmr.page_size = PAGE_SIZE; mr->page_mask = PAGE_MASK; mr->page_shift = PAGE_SHIFT; mr->state = RXE_MR_STATE_INVALID; } void rxe_mr_init_dma(int access, struct rxe_mr *mr) { rxe_mr_init(access, mr); mr->state = RXE_MR_STATE_VALID; mr->ibmr.type = IB_MR_TYPE_DMA; } static unsigned long rxe_mr_iova_to_index(struct rxe_mr *mr, u64 iova) { return (iova >> mr->page_shift) - (mr->ibmr.iova >> mr->page_shift); } static unsigned long rxe_mr_iova_to_page_offset(struct rxe_mr *mr, u64 iova) { return iova & (mr_page_size(mr) - 1); } static bool is_pmem_page(struct page *pg) { unsigned long paddr = page_to_phys(pg); return REGION_INTERSECTS == region_intersects(paddr, PAGE_SIZE, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY); } static int rxe_mr_fill_pages_from_sgt(struct rxe_mr *mr, struct sg_table *sgt) { XA_STATE(xas, &mr->page_list, 0); struct sg_page_iter sg_iter; struct page *page; bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); __sg_page_iter_start(&sg_iter, sgt->sgl, sgt->orig_nents, 0); if (!__sg_page_iter_next(&sg_iter)) return 0; do { xas_lock(&xas); while (true) { page = sg_page_iter_page(&sg_iter); if (persistent && !is_pmem_page(page)) { rxe_dbg_mr(mr, "Page can't be persistent\n"); xas_set_err(&xas, -EINVAL); break; } xas_store(&xas, page); if (xas_error(&xas)) break; xas_next(&xas); if (!__sg_page_iter_next(&sg_iter)) break; } xas_unlock(&xas); } while (xas_nomem(&xas, GFP_KERNEL)); return xas_error(&xas); } int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, int access, struct rxe_mr *mr) { struct ib_umem *umem; int err; rxe_mr_init(access, mr); xa_init(&mr->page_list); umem = ib_umem_get(&rxe->ib_dev, start, length, access); if (IS_ERR(umem)) { rxe_dbg_mr(mr, "Unable to pin memory region err = %d\n", (int)PTR_ERR(umem)); return PTR_ERR(umem); } err = rxe_mr_fill_pages_from_sgt(mr, &umem->sgt_append.sgt); if (err) { ib_umem_release(umem); return err; } mr->umem = umem; mr->ibmr.type = IB_MR_TYPE_USER; mr->state = RXE_MR_STATE_VALID; return 0; } static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf) { XA_STATE(xas, &mr->page_list, 0); int i = 0; int err; xa_init(&mr->page_list); do { xas_lock(&xas); while (i != num_buf) { xas_store(&xas, XA_ZERO_ENTRY); if (xas_error(&xas)) break; xas_next(&xas); i++; } xas_unlock(&xas); } while (xas_nomem(&xas, GFP_KERNEL)); err = xas_error(&xas); if (err) return err; mr->num_buf = num_buf; return 0; } int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr) { int err; /* always allow remote access for FMRs */ rxe_mr_init(RXE_ACCESS_REMOTE, mr); err = rxe_mr_alloc(mr, max_pages); if (err) goto err1; mr->state = RXE_MR_STATE_FREE; mr->ibmr.type = IB_MR_TYPE_MEM_REG; return 0; err1: return err; } static int rxe_set_page(struct ib_mr *ibmr, u64 dma_addr) { struct rxe_mr *mr = to_rmr(ibmr); struct page *page = ib_virt_dma_to_page(dma_addr); bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); int err; if (persistent && !is_pmem_page(page)) { rxe_dbg_mr(mr, "Page cannot be persistent\n"); return -EINVAL; } if (unlikely(mr->nbuf == mr->num_buf)) return -ENOMEM; err = xa_err(xa_store(&mr->page_list, mr->nbuf, page, GFP_KERNEL)); if (err) return err; mr->nbuf++; return 0; } int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset) { struct rxe_mr *mr = to_rmr(ibmr); unsigned int page_size = mr_page_size(mr); mr->nbuf = 0; mr->page_shift = ilog2(page_size); mr->page_mask = ~((u64)page_size - 1); mr->page_offset = mr->ibmr.iova & (page_size - 1); return ib_sg_to_pages(ibmr, sgl, sg_nents, sg_offset, rxe_set_page); } static int rxe_mr_copy_xarray(struct rxe_mr *mr, u64 iova, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { unsigned int page_offset = rxe_mr_iova_to_page_offset(mr, iova); unsigned long index = rxe_mr_iova_to_index(mr, iova); unsigned int bytes; struct page *page; void *va; while (length) { page = xa_load(&mr->page_list, index); if (!page) return -EFAULT; bytes = min_t(unsigned int, length, mr_page_size(mr) - page_offset); va = kmap_local_page(page); if (dir == RXE_FROM_MR_OBJ) memcpy(addr, va + page_offset, bytes); else memcpy(va + page_offset, addr, bytes); kunmap_local(va); page_offset = 0; addr += bytes; length -= bytes; index++; } return 0; } static void rxe_mr_copy_dma(struct rxe_mr *mr, u64 dma_addr, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { unsigned int page_offset = dma_addr & (PAGE_SIZE - 1); unsigned int bytes; struct page *page; u8 *va; while (length) { page = ib_virt_dma_to_page(dma_addr); bytes = min_t(unsigned int, length, PAGE_SIZE - page_offset); va = kmap_local_page(page); if (dir == RXE_TO_MR_OBJ) memcpy(va + page_offset, addr, bytes); else memcpy(addr, va + page_offset, bytes); kunmap_local(va); page_offset = 0; dma_addr += bytes; addr += bytes; length -= bytes; } } int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { int err; if (length == 0) return 0; if (WARN_ON(!mr)) return -EINVAL; if (mr->ibmr.type == IB_MR_TYPE_DMA) { rxe_mr_copy_dma(mr, iova, addr, length, dir); return 0; } err = mr_check_range(mr, iova, length); if (unlikely(err)) { rxe_dbg_mr(mr, "iova out of range\n"); return err; } if (is_odp_mr(mr)) return rxe_odp_mr_copy(mr, iova, addr, length, dir); else return rxe_mr_copy_xarray(mr, iova, addr, length, dir); } /* copy data in or out of a wqe, i.e. sg list * under the control of a dma descriptor */ int copy_data( struct rxe_pd *pd, int access, struct rxe_dma_info *dma, void *addr, int length, enum rxe_mr_copy_dir dir) { int bytes; struct rxe_sge *sge = &dma->sge[dma->cur_sge]; int offset = dma->sge_offset; int resid = dma->resid; struct rxe_mr *mr = NULL; u64 iova; int err; if (length == 0) return 0; if (length > resid) { err = -EINVAL; goto err2; } if (sge->length && (offset < sge->length)) { mr = lookup_mr(pd, access, sge->lkey, RXE_LOOKUP_LOCAL); if (!mr) { err = -EINVAL; goto err1; } } while (length > 0) { bytes = length; if (offset >= sge->length) { if (mr) { rxe_put(mr); mr = NULL; } sge++; dma->cur_sge++; offset = 0; if (dma->cur_sge >= dma->num_sge) { err = -ENOSPC; goto err2; } if (sge->length) { mr = lookup_mr(pd, access, sge->lkey, RXE_LOOKUP_LOCAL); if (!mr) { err = -EINVAL; goto err1; } } else { continue; } } if (bytes > sge->length - offset) bytes = sge->length - offset; if (bytes > 0) { iova = sge->addr + offset; err = rxe_mr_copy(mr, iova, addr, bytes, dir); if (err) goto err2; offset += bytes; resid -= bytes; length -= bytes; addr += bytes; } } dma->sge_offset = offset; dma->resid = resid; if (mr) rxe_put(mr); return 0; err2: if (mr) rxe_put(mr); err1: return err; } int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length) { unsigned int page_offset; unsigned long index; struct page *page; unsigned int bytes; int err; u8 *va; /* mr must be valid even if length is zero */ if (WARN_ON(!mr)) return -EINVAL; if (length == 0) return 0; if (mr->ibmr.type == IB_MR_TYPE_DMA) return -EFAULT; err = mr_check_range(mr, iova, length); if (err) return err; while (length > 0) { index = rxe_mr_iova_to_index(mr, iova); page = xa_load(&mr->page_list, index); page_offset = rxe_mr_iova_to_page_offset(mr, iova); if (!page) return -EFAULT; bytes = min_t(unsigned int, length, mr_page_size(mr) - page_offset); va = kmap_local_page(page); arch_wb_cache_pmem(va + page_offset, bytes); kunmap_local(va); length -= bytes; iova += bytes; page_offset = 0; } return 0; } /* Guarantee atomicity of atomic operations at the machine level. */ DEFINE_SPINLOCK(atomic_ops_lock); int rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, u64 compare, u64 swap_add, u64 *orig_val) { unsigned int page_offset; struct page *page; u64 value; u64 *va; if (unlikely(mr->state != RXE_MR_STATE_VALID)) { rxe_dbg_mr(mr, "mr not in valid state\n"); return RESPST_ERR_RKEY_VIOLATION; } if (mr->ibmr.type == IB_MR_TYPE_DMA) { page_offset = iova & (PAGE_SIZE - 1); page = ib_virt_dma_to_page(iova); } else { unsigned long index; int err; err = mr_check_range(mr, iova, sizeof(value)); if (err) { rxe_dbg_mr(mr, "iova out of range\n"); return RESPST_ERR_RKEY_VIOLATION; } page_offset = rxe_mr_iova_to_page_offset(mr, iova); index = rxe_mr_iova_to_index(mr, iova); page = xa_load(&mr->page_list, index); if (!page) return RESPST_ERR_RKEY_VIOLATION; } if (unlikely(page_offset & 0x7)) { rxe_dbg_mr(mr, "iova not aligned\n"); return RESPST_ERR_MISALIGNED_ATOMIC; } va = kmap_local_page(page); spin_lock_bh(&atomic_ops_lock); value = *orig_val = va[page_offset >> 3]; if (opcode == IB_OPCODE_RC_COMPARE_SWAP) { if (value == compare) va[page_offset >> 3] = swap_add; } else { value += swap_add; va[page_offset >> 3] = value; } spin_unlock_bh(&atomic_ops_lock); kunmap_local(va); return 0; } #if defined CONFIG_64BIT /* only implemented or called for 64 bit architectures */ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) { unsigned int page_offset; struct page *page; u64 *va; /* ODP is not supported right now. WIP. */ if (is_odp_mr(mr)) return RESPST_ERR_UNSUPPORTED_OPCODE; /* See IBA oA19-28 */ if (unlikely(mr->state != RXE_MR_STATE_VALID)) { rxe_dbg_mr(mr, "mr not in valid state\n"); return RESPST_ERR_RKEY_VIOLATION; } if (mr->ibmr.type == IB_MR_TYPE_DMA) { page_offset = iova & (PAGE_SIZE - 1); page = ib_virt_dma_to_page(iova); } else { unsigned long index; int err; /* See IBA oA19-28 */ err = mr_check_range(mr, iova, sizeof(value)); if (unlikely(err)) { rxe_dbg_mr(mr, "iova out of range\n"); return RESPST_ERR_RKEY_VIOLATION; } page_offset = rxe_mr_iova_to_page_offset(mr, iova); index = rxe_mr_iova_to_index(mr, iova); page = xa_load(&mr->page_list, index); if (!page) return RESPST_ERR_RKEY_VIOLATION; } /* See IBA A19.4.2 */ if (unlikely(page_offset & 0x7)) { rxe_dbg_mr(mr, "misaligned address\n"); return RESPST_ERR_MISALIGNED_ATOMIC; } va = kmap_local_page(page); /* Do atomic write after all prior operations have completed */ smp_store_release(&va[page_offset >> 3], value); kunmap_local(va); return 0; } #else int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) { return RESPST_ERR_UNSUPPORTED_OPCODE; } #endif int advance_dma_data(struct rxe_dma_info *dma, unsigned int length) { struct rxe_sge *sge = &dma->sge[dma->cur_sge]; int offset = dma->sge_offset; int resid = dma->resid; while (length) { unsigned int bytes; if (offset >= sge->length) { sge++; dma->cur_sge++; offset = 0; if (dma->cur_sge >= dma->num_sge) return -ENOSPC; } bytes = length; if (bytes > sge->length - offset) bytes = sge->length - offset; offset += bytes; resid -= bytes; length -= bytes; } dma->sge_offset = offset; dma->resid = resid; return 0; } struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, enum rxe_mr_lookup_type type) { struct rxe_mr *mr; struct rxe_dev *rxe = to_rdev(pd->ibpd.device); int index = key >> 8; mr = rxe_pool_get_index(&rxe->mr_pool, index); if (!mr) return NULL; if (unlikely((type == RXE_LOOKUP_LOCAL && mr->lkey != key) || (type == RXE_LOOKUP_REMOTE && mr->rkey != key) || mr_pd(mr) != pd || ((access & mr->access) != access) || mr->state != RXE_MR_STATE_VALID)) { rxe_put(mr); mr = NULL; } return mr; } int rxe_invalidate_mr(struct rxe_qp *qp, u32 key) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct rxe_mr *mr; int remote; int ret; mr = rxe_pool_get_index(&rxe->mr_pool, key >> 8); if (!mr) { rxe_dbg_qp(qp, "No MR for key %#x\n", key); ret = -EINVAL; goto err; } remote = mr->access & RXE_ACCESS_REMOTE; if (remote ? (key != mr->rkey) : (key != mr->lkey)) { rxe_dbg_mr(mr, "wr key (%#x) doesn't match mr key (%#x)\n", key, (remote ? mr->rkey : mr->lkey)); ret = -EINVAL; goto err_drop_ref; } if (atomic_read(&mr->num_mw) > 0) { rxe_dbg_mr(mr, "Attempt to invalidate an MR while bound to MWs\n"); ret = -EINVAL; goto err_drop_ref; } if (unlikely(mr->ibmr.type != IB_MR_TYPE_MEM_REG)) { rxe_dbg_mr(mr, "Type (%d) is wrong\n", mr->ibmr.type); ret = -EINVAL; goto err_drop_ref; } mr->state = RXE_MR_STATE_FREE; ret = 0; err_drop_ref: rxe_put(mr); err: return ret; } /* user can (re)register fast MR by executing a REG_MR WQE. * user is expected to hold a reference on the ib mr until the * WQE completes. * Once a fast MR is created this is the only way to change the * private keys. It is the responsibility of the user to maintain * the ib mr keys in sync with rxe mr keys. */ int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe) { struct rxe_mr *mr = to_rmr(wqe->wr.wr.reg.mr); u32 key = wqe->wr.wr.reg.key; u32 access = wqe->wr.wr.reg.access; /* user can only register MR in free state */ if (unlikely(mr->state != RXE_MR_STATE_FREE)) { rxe_dbg_mr(mr, "mr->lkey = 0x%x not free\n", mr->lkey); return -EINVAL; } /* user can only register mr with qp in same protection domain */ if (unlikely(qp->ibqp.pd != mr->ibmr.pd)) { rxe_dbg_mr(mr, "qp->pd and mr->pd don't match\n"); return -EINVAL; } /* user is only allowed to change key portion of l/rkey */ if (unlikely((mr->lkey & ~0xff) != (key & ~0xff))) { rxe_dbg_mr(mr, "key = 0x%x has wrong index mr->lkey = 0x%x\n", key, mr->lkey); return -EINVAL; } mr->access = access; mr->lkey = key; mr->rkey = key; mr->ibmr.iova = wqe->wr.wr.reg.mr->iova; mr->state = RXE_MR_STATE_VALID; return 0; } void rxe_mr_cleanup(struct rxe_pool_elem *elem) { struct rxe_mr *mr = container_of(elem, typeof(*mr), elem); rxe_put(mr_pd(mr)); ib_umem_release(mr->umem); if (mr->ibmr.type != IB_MR_TYPE_DMA) xa_destroy(&mr->page_list); } |
| 78 77 1 1 1 1 1 1 1 135 59 | 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-or-later /* * Bridge per vlan tunnel port dst_metadata handling code * * Authors: * Roopa Prabhu <roopa@cumulusnetworks.com> */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/switchdev.h> #include <net/dst_metadata.h> #include "br_private.h" #include "br_private_tunnel.h" static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct net_bridge_vlan *vle = ptr; __be64 tunid = *(__be64 *)arg->key; return vle->tinfo.tunnel_id != tunid; } static const struct rhashtable_params br_vlan_tunnel_rht_params = { .head_offset = offsetof(struct net_bridge_vlan, tnode), .key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id), .key_len = sizeof(__be64), .nelem_hint = 3, .obj_cmpfn = br_vlan_tunid_cmp, .automatic_shrinking = true, }; static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, __be64 tunnel_id) { return rhashtable_lookup_fast(tbl, &tunnel_id, br_vlan_tunnel_rht_params); } static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) { struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); WRITE_ONCE(vlan->tinfo.tunnel_id, 0); RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); dst_release(&tdst->dst); } void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); vlan_tunnel_info_release(vlan); } static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err; if (metadata) return -EEXIST; __set_bit(IP_TUNNEL_KEY_BIT, flags); metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, key, 0); if (!metadata) return -EINVAL; metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); WRITE_ONCE(vlan->tinfo.tunnel_id, key); err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); if (err) goto out; return 0; out: vlan_tunnel_info_release(vlan); return err; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_tunnel_info_add(const struct net_bridge_port *port, u16 vid, u32 tun_id) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; ASSERT_RTNL(); vg = nbp_vlan_group(port); vlan = br_vlan_find(vg, vid); if (!vlan) return -EINVAL; return __vlan_tunnel_info_add(vg, vlan, tun_id); } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_tunnel_info_delete(const struct net_bridge_port *port, u16 vid) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); vg = nbp_vlan_group(port); v = br_vlan_find(vg, vid); if (!v) return -ENOENT; vlan_tunnel_info_del(vg, v); return 0; } static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) vlan_tunnel_info_del(vg, vlan); } void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = nbp_vlan_group(port); __vlan_tunnel_info_flush(vg); } int vlan_tunnel_init(struct net_bridge_vlan_group *vg) { return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params); } void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg) { rhashtable_destroy(&vg->tunnel_hash); } void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_port *p, struct net_bridge_vlan_group *vg) { struct ip_tunnel_info *tinfo = skb_tunnel_info(skb); struct net_bridge_vlan *vlan; if (!vg || !tinfo) return; /* if already tagged, ignore */ if (skb_vlan_tagged(skb)) return; /* lookup vid, given tunnel id */ vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id); if (!vlan) return; skb_dst_drop(skb); __vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid); } int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tunnel_dst; __be64 tunnel_id; int err; if (!vlan) return 0; tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0; skb_dst_drop(skb); err = skb_vlan_pop(skb); if (err) return err; if (BR_INPUT_SKB_CB(skb)->backup_nhid) { __set_bit(IP_TUNNEL_KEY_BIT, flags); tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, tunnel_id, 0); if (!tunnel_dst) return -ENOMEM; tunnel_dst->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; tunnel_dst->u.tun_info.key.nhid = BR_INPUT_SKB_CB(skb)->backup_nhid; skb_dst_set(skb, &tunnel_dst->dst); return 0; } tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) skb_dst_set(skb, &tunnel_dst->dst); return 0; } |
| 5 4 27 4 20 1 2 20 2 2 1 5 5 2 2 26 20 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_count.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_zones.h> struct nft_connlimit { struct nf_conncount_list *list; u32 limit; bool invert; }; static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct nft_set_ext *ext) { const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; const struct nf_conntrack_tuple *tuple_ptr; struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int count; tuple_ptr = &tuple; ct = nf_ct_get(pkt->skb, &ctinfo); if (ct != NULL) { tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; zone = nf_ct_zone(ct); } else if (!nf_ct_get_tuplepr(pkt->skb, skb_network_offset(pkt->skb), nft_pf(pkt), nft_net(pkt), &tuple)) { regs->verdict.code = NF_DROP; return; } if (nf_conncount_add(nft_net(pkt), priv->list, tuple_ptr, zone)) { regs->verdict.code = NF_DROP; return; } count = priv->list->count; if ((count > priv->limit) ^ priv->invert) { regs->verdict.code = NFT_BREAK; return; } } static int nft_connlimit_do_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_connlimit *priv) { bool invert = false; u32 flags, limit; int err; if (!tb[NFTA_CONNLIMIT_COUNT]) return -EINVAL; limit = ntohl(nla_get_be32(tb[NFTA_CONNLIMIT_COUNT])); if (tb[NFTA_CONNLIMIT_FLAGS]) { flags = ntohl(nla_get_be32(tb[NFTA_CONNLIMIT_FLAGS])); if (flags & ~NFT_CONNLIMIT_F_INV) return -EOPNOTSUPP; if (flags & NFT_CONNLIMIT_F_INV) invert = true; } priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT); if (!priv->list) return -ENOMEM; nf_conncount_list_init(priv->list); priv->limit = limit; priv->invert = invert; err = nf_ct_netns_get(ctx->net, ctx->family); if (err < 0) goto err_netns; return 0; err_netns: kfree(priv->list); return err; } static void nft_connlimit_do_destroy(const struct nft_ctx *ctx, struct nft_connlimit *priv) { nf_ct_netns_put(ctx->net, ctx->family); nf_conncount_cache_free(priv->list); kfree(priv->list); } static int nft_connlimit_do_dump(struct sk_buff *skb, struct nft_connlimit *priv) { if (nla_put_be32(skb, NFTA_CONNLIMIT_COUNT, htonl(priv->limit))) goto nla_put_failure; if (priv->invert && nla_put_be32(skb, NFTA_CONNLIMIT_FLAGS, htonl(NFT_CONNLIMIT_F_INV))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static inline void nft_connlimit_obj_eval(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_connlimit *priv = nft_obj_data(obj); nft_connlimit_do_eval(priv, regs, pkt, NULL); } static int nft_connlimit_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { struct nft_connlimit *priv = nft_obj_data(obj); return nft_connlimit_do_init(ctx, tb, priv); } static void nft_connlimit_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { struct nft_connlimit *priv = nft_obj_data(obj); nft_connlimit_do_destroy(ctx, priv); } static int nft_connlimit_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { struct nft_connlimit *priv = nft_obj_data(obj); return nft_connlimit_do_dump(skb, priv); } static const struct nla_policy nft_connlimit_policy[NFTA_CONNLIMIT_MAX + 1] = { [NFTA_CONNLIMIT_COUNT] = { .type = NLA_U32 }, [NFTA_CONNLIMIT_FLAGS] = { .type = NLA_U32 }, }; static struct nft_object_type nft_connlimit_obj_type; static const struct nft_object_ops nft_connlimit_obj_ops = { .type = &nft_connlimit_obj_type, .size = sizeof(struct nft_connlimit), .eval = nft_connlimit_obj_eval, .init = nft_connlimit_obj_init, .destroy = nft_connlimit_obj_destroy, .dump = nft_connlimit_obj_dump, }; static struct nft_object_type nft_connlimit_obj_type __read_mostly = { .type = NFT_OBJECT_CONNLIMIT, .ops = &nft_connlimit_obj_ops, .maxattr = NFTA_CONNLIMIT_MAX, .policy = nft_connlimit_policy, .owner = THIS_MODULE, }; static void nft_connlimit_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_connlimit *priv = nft_expr_priv(expr); nft_connlimit_do_eval(priv, regs, pkt, NULL); } static int nft_connlimit_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_connlimit *priv = nft_expr_priv(expr); return nft_connlimit_do_dump(skb, priv); } static int nft_connlimit_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_connlimit *priv = nft_expr_priv(expr); return nft_connlimit_do_init(ctx, tb, priv); } static void nft_connlimit_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); nft_connlimit_do_destroy(ctx, priv); } static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_connlimit *priv_dst = nft_expr_priv(dst); struct nft_connlimit *priv_src = nft_expr_priv(src); priv_dst->list = kmalloc(sizeof(*priv_dst->list), gfp); if (!priv_dst->list) return -ENOMEM; nf_conncount_list_init(priv_dst->list); priv_dst->limit = priv_src->limit; priv_dst->invert = priv_src->invert; return 0; } static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); nf_conncount_cache_free(priv->list); kfree(priv->list); } static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); bool ret; local_bh_disable(); ret = nf_conncount_gc_list(net, priv->list); local_bh_enable(); return ret; } static struct nft_expr_type nft_connlimit_type; static const struct nft_expr_ops nft_connlimit_ops = { .type = &nft_connlimit_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_connlimit)), .eval = nft_connlimit_eval, .init = nft_connlimit_init, .destroy = nft_connlimit_destroy, .clone = nft_connlimit_clone, .destroy_clone = nft_connlimit_destroy_clone, .dump = nft_connlimit_dump, .gc = nft_connlimit_gc, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_connlimit_type __read_mostly = { .name = "connlimit", .ops = &nft_connlimit_ops, .policy = nft_connlimit_policy, .maxattr = NFTA_CONNLIMIT_MAX, .flags = NFT_EXPR_STATEFUL | NFT_EXPR_GC, .owner = THIS_MODULE, }; static int __init nft_connlimit_module_init(void) { int err; err = nft_register_obj(&nft_connlimit_obj_type); if (err < 0) return err; err = nft_register_expr(&nft_connlimit_type); if (err < 0) goto err1; return 0; err1: nft_unregister_obj(&nft_connlimit_obj_type); return err; } static void __exit nft_connlimit_module_exit(void) { nft_unregister_expr(&nft_connlimit_type); nft_unregister_obj(&nft_connlimit_obj_type); } module_init(nft_connlimit_module_init); module_exit(nft_connlimit_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso"); MODULE_ALIAS_NFT_EXPR("connlimit"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CONNLIMIT); MODULE_DESCRIPTION("nftables connlimit rule support"); |
| 8 41 9 8 48 48 5 43 48 48 15 1 14 12 2 9 5 11 3 12 2 11 3 11 3 10 4 12 2 14 14 56 51 51 5 5 17 19 16 1 16 16 16 14 3 48 48 24 24 25 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2013 Cisco Systems, Inc, 2013. * * Author: Vijay Subramanian <vijaynsu@cisco.com> * Author: Mythili Prabhu <mysuryan@cisco.com> * * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no> * University of Oslo, Norway. * * References: * RFC 8033: https://tools.ietf.org/html/rfc8033 */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> #include <net/pie.h> /* private data for the Qdisc */ struct pie_sched_data { struct pie_vars vars; struct pie_params params; struct pie_stats stats; struct timer_list adapt_timer; struct Qdisc *sch; }; bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, struct pie_vars *vars, u32 backlog, u32 packet_size) { u64 rnd; u64 local_prob = vars->prob; u32 mtu = psched_mtu(qdisc_dev(sch)); /* If there is still burst allowance left skip random early drop */ if (vars->burst_time > 0) return false; /* If current delay is less than half of target, and * if drop prob is low already, disable early_drop */ if ((vars->qdelay < params->target / 2) && (vars->prob < MAX_PROB / 5)) return false; /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early, * similar to min_th in RED */ if (backlog < 2 * mtu) return false; /* If bytemode is turned on, use packet size to compute new * probablity. Smaller packets will have lower drop prob in this case */ if (params->bytemode && packet_size <= mtu) local_prob = (u64)packet_size * div_u64(local_prob, mtu); else local_prob = vars->prob; if (local_prob == 0) vars->accu_prob = 0; else vars->accu_prob += local_prob; if (vars->accu_prob < (MAX_PROB / 100) * 85) return false; if (vars->accu_prob >= (MAX_PROB / 2) * 17) return true; get_random_bytes(&rnd, 8); if ((rnd >> BITS_PER_BYTE) < local_prob) { vars->accu_prob = 0; return true; } return false; } EXPORT_SYMBOL_GPL(pie_drop_early); static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { enum skb_drop_reason reason = SKB_DROP_REASON_QDISC_OVERLIMIT; struct pie_sched_data *q = qdisc_priv(sch); bool enqueue = false; if (unlikely(qdisc_qlen(sch) >= sch->limit)) { q->stats.overlimit++; goto out; } reason = SKB_DROP_REASON_QDISC_CONGESTED; if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog, skb->len)) { enqueue = true; } else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) && INET_ECN_set_ce(skb)) { /* If packet is ecn capable, mark it if drop probability * is lower than 10%, else drop it. */ q->stats.ecn_mark++; enqueue = true; } /* we can enqueue the packet */ if (enqueue) { /* Set enqueue time only when dq_rate_estimator is disabled. */ if (!q->params.dq_rate_estimator) pie_set_enqueue_time(skb); q->stats.packets_in++; if (qdisc_qlen(sch) > q->stats.maxq) q->stats.maxq = qdisc_qlen(sch); return qdisc_enqueue_tail(skb, sch); } out: q->stats.dropped++; q->vars.accu_prob = 0; return qdisc_drop_reason(skb, sch, to_free, reason); } static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { [TCA_PIE_TARGET] = {.type = NLA_U32}, [TCA_PIE_LIMIT] = {.type = NLA_U32}, [TCA_PIE_TUPDATE] = {.type = NLA_U32}, [TCA_PIE_ALPHA] = {.type = NLA_U32}, [TCA_PIE_BETA] = {.type = NLA_U32}, [TCA_PIE_ECN] = {.type = NLA_U32}, [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, }; static int pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy, NULL); if (err < 0) return err; sch_tree_lock(sch); /* convert from microseconds to pschedtime */ if (tb[TCA_PIE_TARGET]) { /* target is in us */ u32 target = nla_get_u32(tb[TCA_PIE_TARGET]); /* convert to pschedtime */ WRITE_ONCE(q->params.target, PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC)); } /* tupdate is in jiffies */ if (tb[TCA_PIE_TUPDATE]) WRITE_ONCE(q->params.tupdate, usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]))); if (tb[TCA_PIE_LIMIT]) { u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]); WRITE_ONCE(q->params.limit, limit); WRITE_ONCE(sch->limit, limit); } if (tb[TCA_PIE_ALPHA]) WRITE_ONCE(q->params.alpha, nla_get_u32(tb[TCA_PIE_ALPHA])); if (tb[TCA_PIE_BETA]) WRITE_ONCE(q->params.beta, nla_get_u32(tb[TCA_PIE_BETA])); if (tb[TCA_PIE_ECN]) WRITE_ONCE(q->params.ecn, nla_get_u32(tb[TCA_PIE_ECN])); if (tb[TCA_PIE_BYTEMODE]) WRITE_ONCE(q->params.bytemode, nla_get_u32(tb[TCA_PIE_BYTEMODE])); if (tb[TCA_PIE_DQ_RATE_ESTIMATOR]) WRITE_ONCE(q->params.dq_rate_estimator, nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); rtnl_qdisc_drop(skb, sch); } qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; } void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, struct pie_vars *vars, u32 backlog) { psched_time_t now = psched_get_time(); u32 dtime = 0; /* If dq_rate_estimator is disabled, calculate qdelay using the * packet timestamp. */ if (!params->dq_rate_estimator) { vars->qdelay = now - pie_get_enqueue_time(skb); if (vars->dq_tstamp != DTIME_INVALID) dtime = now - vars->dq_tstamp; vars->dq_tstamp = now; if (backlog == 0) vars->qdelay = 0; if (dtime == 0) return; goto burst_allowance_reduction; } /* If current queue is about 10 packets or more and dq_count is unset * we have enough packets to calculate the drain rate. Save * current time as dq_tstamp and start measurement cycle. */ if (backlog >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) { vars->dq_tstamp = psched_get_time(); vars->dq_count = 0; } /* Calculate the average drain rate from this value. If queue length * has receded to a small value viz., <= QUEUE_THRESHOLD bytes, reset * the dq_count to -1 as we don't have enough packets to calculate the * drain rate anymore. The following if block is entered only when we * have a substantial queue built up (QUEUE_THRESHOLD bytes or more) * and we calculate the drain rate for the threshold here. dq_count is * in bytes, time difference in psched_time, hence rate is in * bytes/psched_time. */ if (vars->dq_count != DQCOUNT_INVALID) { vars->dq_count += skb->len; if (vars->dq_count >= QUEUE_THRESHOLD) { u32 count = vars->dq_count << PIE_SCALE; dtime = now - vars->dq_tstamp; if (dtime == 0) return; count = count / dtime; if (vars->avg_dq_rate == 0) vars->avg_dq_rate = count; else vars->avg_dq_rate = (vars->avg_dq_rate - (vars->avg_dq_rate >> 3)) + (count >> 3); /* If the queue has receded below the threshold, we hold * on to the last drain rate calculated, else we reset * dq_count to 0 to re-enter the if block when the next * packet is dequeued */ if (backlog < QUEUE_THRESHOLD) { vars->dq_count = DQCOUNT_INVALID; } else { vars->dq_count = 0; vars->dq_tstamp = psched_get_time(); } goto burst_allowance_reduction; } } return; burst_allowance_reduction: if (vars->burst_time > 0) { if (vars->burst_time > dtime) vars->burst_time -= dtime; else vars->burst_time = 0; } } EXPORT_SYMBOL_GPL(pie_process_dequeue); void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, u32 backlog) { psched_time_t qdelay = 0; /* in pschedtime */ psched_time_t qdelay_old = 0; /* in pschedtime */ s64 delta = 0; /* determines the change in probability */ u64 oldprob; u64 alpha, beta; u32 power; bool update_prob = true; if (params->dq_rate_estimator) { qdelay_old = vars->qdelay; vars->qdelay_old = vars->qdelay; if (vars->avg_dq_rate > 0) qdelay = (backlog << PIE_SCALE) / vars->avg_dq_rate; else qdelay = 0; } else { qdelay = vars->qdelay; qdelay_old = vars->qdelay_old; } /* If qdelay is zero and backlog is not, it means backlog is very small, * so we do not update probability in this round. */ if (qdelay == 0 && backlog != 0) update_prob = false; /* In the algorithm, alpha and beta are between 0 and 2 with typical * value for alpha as 0.125. In this implementation, we use values 0-32 * passed from user space to represent this. Also, alpha and beta have * unit of HZ and need to be scaled before they can used to update * probability. alpha/beta are updated locally below by scaling down * by 16 to come to 0-2 range. */ alpha = ((u64)params->alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; beta = ((u64)params->beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; /* We scale alpha and beta differently depending on how heavy the * congestion is. Please see RFC 8033 for details. */ if (vars->prob < MAX_PROB / 10) { alpha >>= 1; beta >>= 1; power = 100; while (vars->prob < div_u64(MAX_PROB, power) && power <= 1000000) { alpha >>= 2; beta >>= 2; power *= 10; } } /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ delta += alpha * (qdelay - params->target); delta += beta * (qdelay - qdelay_old); oldprob = vars->prob; /* to ensure we increase probability in steps of no more than 2% */ if (delta > (s64)(MAX_PROB / (100 / 2)) && vars->prob >= MAX_PROB / 10) delta = (MAX_PROB / 100) * 2; /* Non-linear drop: * Tune drop probability to increase quickly for high delays(>= 250ms) * 250ms is derived through experiments and provides error protection */ if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) delta += MAX_PROB / (100 / 2); vars->prob += delta; if (delta > 0) { /* prevent overflow */ if (vars->prob < oldprob) { vars->prob = MAX_PROB; /* Prevent normalization error. If probability is at * maximum value already, we normalize it here, and * skip the check to do a non-linear drop in the next * section. */ update_prob = false; } } else { /* prevent underflow */ if (vars->prob > oldprob) vars->prob = 0; } /* Non-linear drop in probability: Reduce drop probability quickly if * delay is 0 for 2 consecutive Tupdate periods. */ if (qdelay == 0 && qdelay_old == 0 && update_prob) /* Reduce drop probability to 98.4% */ vars->prob -= vars->prob / 64; vars->qdelay = qdelay; vars->backlog_old = backlog; /* We restart the measurement cycle if the following conditions are met * 1. If the delay has been low for 2 consecutive Tupdate periods * 2. Calculated drop probability is zero * 3. If average dq_rate_estimator is enabled, we have at least one * estimate for the avg_dq_rate ie., is a non-zero value */ if ((vars->qdelay < params->target / 2) && (vars->qdelay_old < params->target / 2) && vars->prob == 0 && (!params->dq_rate_estimator || vars->avg_dq_rate > 0)) { pie_vars_init(vars); } if (!params->dq_rate_estimator) vars->qdelay_old = qdelay; } EXPORT_SYMBOL_GPL(pie_calculate_probability); static void pie_timer(struct timer_list *t) { struct pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock; rcu_read_lock(); root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); /* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */ if (q->params.tupdate) mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); spin_unlock(root_lock); rcu_read_unlock(); } static int pie_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct pie_sched_data *q = qdisc_priv(sch); pie_params_init(&q->params); pie_vars_init(&q->vars); sch->limit = q->params.limit; q->sch = sch; timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { int err = pie_change(sch, opt, extack); if (err) return err; } mod_timer(&q->adapt_timer, jiffies + HZ / 2); return 0; } static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) { struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *opts; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; /* convert target from pschedtime to us */ if (nla_put_u32(skb, TCA_PIE_TARGET, ((u32)PSCHED_TICKS2NS(READ_ONCE(q->params.target))) / NSEC_PER_USEC) || nla_put_u32(skb, TCA_PIE_LIMIT, READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(READ_ONCE(q->params.tupdate))) || nla_put_u32(skb, TCA_PIE_ALPHA, READ_ONCE(q->params.alpha)) || nla_put_u32(skb, TCA_PIE_BETA, READ_ONCE(q->params.beta)) || nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) || nla_put_u32(skb, TCA_PIE_BYTEMODE, READ_ONCE(q->params.bytemode)) || nla_put_u32(skb, TCA_PIE_DQ_RATE_ESTIMATOR, READ_ONCE(q->params.dq_rate_estimator))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -1; } static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { .prob = q->vars.prob << BITS_PER_BYTE, .delay = ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) / NSEC_PER_USEC, .packets_in = q->stats.packets_in, .overlimit = q->stats.overlimit, .maxq = q->stats.maxq, .dropped = q->stats.dropped, .ecn_mark = q->stats.ecn_mark, }; /* avg_dq_rate is only valid if dq_rate_estimator is enabled */ st.dq_rate_estimating = q->params.dq_rate_estimator; /* unscale and return dq_rate in bytes per sec */ if (q->params.dq_rate_estimator) st.avg_dq_rate = q->vars.avg_dq_rate * (PSCHED_TICKS_PER_SEC) >> PIE_SCALE; return gnet_stats_copy_app(d, &st, sizeof(st)); } static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = qdisc_dequeue_head(sch); if (!skb) return NULL; pie_process_dequeue(skb, &q->params, &q->vars, sch->qstats.backlog); return skb; } static void pie_reset(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); pie_vars_init(&q->vars); } static void pie_destroy(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); q->params.tupdate = 0; timer_delete_sync(&q->adapt_timer); } static struct Qdisc_ops pie_qdisc_ops __read_mostly = { .id = "pie", .priv_size = sizeof(struct pie_sched_data), .enqueue = pie_qdisc_enqueue, .dequeue = pie_qdisc_dequeue, .peek = qdisc_peek_dequeued, .init = pie_init, .destroy = pie_destroy, .reset = pie_reset, .change = pie_change, .dump = pie_dump, .dump_stats = pie_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("pie"); static int __init pie_module_init(void) { return register_qdisc(&pie_qdisc_ops); } static void __exit pie_module_exit(void) { unregister_qdisc(&pie_qdisc_ops); } module_init(pie_module_init); module_exit(pie_module_exit); MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler"); MODULE_AUTHOR("Vijay Subramanian"); MODULE_AUTHOR("Mythili Prabhu"); MODULE_LICENSE("GPL"); |
| 63 60 8 8 8 8 4 4 63 63 4 4 4 4 4 7 7 7 7 1 6 7 7 7 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 3 4 4 4 4 4 4 4 3 4 4 4 4 4 4 4 4 4 59 59 59 1 1 1 59 58 56 8 40 45 59 1 59 55 8 38 37 37 38 38 38 38 38 36 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH * Copyright 2018-2020, 2022-2024 Intel Corporation */ #include <crypto/utils.h> #include <linux/if_ether.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/export.h> #include <net/mac80211.h> #include <linux/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "debugfs_key.h" #include "aes_ccm.h" #include "aes_cmac.h" #include "aes_gmac.h" #include "aes_gcm.h" /** * DOC: Key handling basics * * Key handling in mac80211 is done based on per-interface (sub_if_data) * keys and per-station keys. Since each station belongs to an interface, * each station key also belongs to that interface. * * Hardware acceleration is done on a best-effort basis for algorithms * that are implemented in software, for each key the hardware is asked * to enable that key for offloading but if it cannot do that the key is * simply kept for software encryption (unless it is for an algorithm * that isn't implemented in software). * There is currently no way of knowing whether a key is handled in SW * or HW except by looking into debugfs. * * All key management is internally protected by a mutex. Within all * other parts of mac80211, key references are, just as STA structure * references, protected by RCU. Note, however, that some things are * unprotected, namely the key->sta dereferences within the hardware * acceleration functions. This means that sta_info_destroy() must * remove the key which waits for an RCU grace period. */ static const u8 bcast_addr[ETH_ALEN] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static void update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) { struct ieee80211_sub_if_data *vlan; if (sdata->vif.type != NL80211_IFTYPE_AP) return; /* crypto_tx_tailroom_needed_cnt is protected by this */ lockdep_assert_wiphy(sdata->local->hw.wiphy); rcu_read_lock(); list_for_each_entry_rcu(vlan, &sdata->u.ap.vlans, u.vlan.list) vlan->crypto_tx_tailroom_needed_cnt += delta; rcu_read_unlock(); } static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) { /* * When this count is zero, SKB resizing for allocating tailroom * for IV or MMIC is skipped. But, this check has created two race * cases in xmit path while transiting from zero count to one: * * 1. SKB resize was skipped because no key was added but just before * the xmit key is added and SW encryption kicks off. * * 2. SKB resize was skipped because all the keys were hw planted but * just before xmit one of the key is deleted and SW encryption kicks * off. * * In both the above case SW encryption will find not enough space for * tailroom and exits with WARN_ON. (See WARN_ONs at wpa.c) * * Solution has been explained at * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net */ lockdep_assert_wiphy(sdata->local->hw.wiphy); update_vlan_tailroom_need_count(sdata, 1); if (!sdata->crypto_tx_tailroom_needed_cnt++) { /* * Flush all XMIT packets currently using HW encryption or no * encryption at all if the count transition is from 0 -> 1. */ synchronize_net(); } } static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta) { lockdep_assert_wiphy(sdata->local->hw.wiphy); WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta); update_vlan_tailroom_need_count(sdata, -delta); sdata->crypto_tx_tailroom_needed_cnt -= delta; } static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata = key->sdata; struct sta_info *sta; int ret = -EOPNOTSUPP; might_sleep(); lockdep_assert_wiphy(key->local->hw.wiphy); if (key->flags & KEY_FLAG_TAINTED) { /* If we get here, it's during resume and the key is * tainted so shouldn't be used/programmed any more. * However, its flags may still indicate that it was * programmed into the device (since we're in resume) * so clear that flag now to avoid trying to remove * it again later. */ if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; return -EINVAL; } if (!key->local->ops->set_key) goto out_unsupported; sta = key->sta; /* * If this is a per-STA GTK, check if it * is supported; if not, return. */ if (sta && !(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE) && !ieee80211_hw_check(&key->local->hw, SUPPORTS_PER_STA_GTK)) goto out_unsupported; if (sta && !sta->uploaded) goto out_unsupported; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* * The driver doesn't know anything about VLAN interfaces. * Hence, don't send GTKs for VLAN interfaces to the driver. */ if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { ret = 1; goto out_unsupported; } } if (key->conf.link_id >= 0 && sdata->vif.active_links && !(sdata->vif.active_links & BIT(key->conf.link_id))) return 0; ret = drv_set_key(key->local, SET_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); if (!ret) { key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; if (!(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) decrease_tailroom_need_count(sdata, 1); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)); WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_MIC_SPACE) && (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)); return 0; } if (ret != -ENOSPC && ret != -EOPNOTSUPP && ret != 1) sdata_err(sdata, "failed to set key (%d, %pM) to hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); out_unsupported: switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: /* all of these we can do in software - if driver can */ if (ret == 1) return 0; if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) return -EINVAL; return 0; default: return -EINVAL; } } static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; struct sta_info *sta; int ret; might_sleep(); if (!key || !key->local->ops->set_key) return; if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) return; sta = key->sta; sdata = key->sdata; lockdep_assert_wiphy(key->local->hw.wiphy); if (key->conf.link_id >= 0 && sdata->vif.active_links && !(sdata->vif.active_links & BIT(key->conf.link_id))) return; if (!(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; ret = drv_set_key(key->local, DISABLE_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); if (ret) sdata_err(sdata, "failed to remove key (%d, %pM) from hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); } static int _ieee80211_set_tx_key(struct ieee80211_key *key, bool force) { struct sta_info *sta = key->sta; struct ieee80211_local *local = key->local; lockdep_assert_wiphy(local->hw.wiphy); set_sta_flag(sta, WLAN_STA_USES_ENCRYPTION); sta->ptk_idx = key->conf.keyidx; if (force || !ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_check_fast_xmit(sta); return 0; } int ieee80211_set_tx_key(struct ieee80211_key *key) { return _ieee80211_set_tx_key(key, false); } static void ieee80211_pairwise_rekey(struct ieee80211_key *old, struct ieee80211_key *new) { struct ieee80211_local *local = new->local; struct sta_info *sta = new->sta; int i; lockdep_assert_wiphy(local->hw.wiphy); if (new->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX) { /* Extended Key ID key install, initial one or rekey */ if (sta->ptk_idx != INVALID_PTK_KEYIDX && !ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) { /* Aggregation Sessions with Extended Key ID must not * mix MPDUs with different keyIDs within one A-MPDU. * Tear down running Tx aggregation sessions and block * new Rx/Tx aggregation requests during rekey to * ensure there are no A-MPDUs when the driver is not * supporting A-MPDU key borders. (Blocking Tx only * would be sufficient but WLAN_STA_BLOCK_BA gets the * job done for the few ms we need it.) */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); for (i = 0; i < IEEE80211_NUM_TIDS; i++) __ieee80211_stop_tx_ba_session(sta, i, AGG_STOP_LOCAL_REQUEST); } } else if (old) { /* Rekey without Extended Key ID. * Aggregation sessions are OK when running on SW crypto. * A broken remote STA may cause issues not observed with HW * crypto, though. */ if (!(old->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) return; /* Stop Tx till we are on the new key */ old->flags |= KEY_FLAG_TAINTED; ieee80211_clear_fast_xmit(sta); if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION)) { set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_LOCAL_REQUEST); } if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0)) { pr_warn_ratelimited("Rekeying PTK for STA %pM but driver can't safely do that.", sta->sta.addr); /* Flushing the driver queues *may* help prevent * the clear text leaks and freezes. */ ieee80211_flush_queues(local, old->sdata, false); } } } static void __ieee80211_set_default_key(struct ieee80211_link_data *link, int idx, bool uni, bool multi) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_key *key = NULL; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (idx >= 0 && idx < NUM_DEFAULT_KEYS) { key = wiphy_dereference(sdata->local->hw.wiphy, sdata->keys[idx]); if (!key) key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); } if (uni) { rcu_assign_pointer(sdata->default_unicast_key, key); ieee80211_check_fast_xmit_iface(sdata); if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) drv_set_default_unicast_key(sdata->local, sdata, idx); } if (multi) rcu_assign_pointer(link->default_multicast_key, key); ieee80211_debugfs_key_update_default(sdata); } void ieee80211_set_default_key(struct ieee80211_link_data *link, int idx, bool uni, bool multi) { lockdep_assert_wiphy(link->sdata->local->hw.wiphy); __ieee80211_set_default_key(link, idx, uni, multi); } static void __ieee80211_set_default_mgmt_key(struct ieee80211_link_data *link, int idx) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_key *key = NULL; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (idx >= NUM_DEFAULT_KEYS && idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); rcu_assign_pointer(link->default_mgmt_key, key); ieee80211_debugfs_key_update_default(sdata); } void ieee80211_set_default_mgmt_key(struct ieee80211_link_data *link, int idx) { lockdep_assert_wiphy(link->sdata->local->hw.wiphy); __ieee80211_set_default_mgmt_key(link, idx); } static void __ieee80211_set_default_beacon_key(struct ieee80211_link_data *link, int idx) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_key *key = NULL; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS && idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS) key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); rcu_assign_pointer(link->default_beacon_key, key); ieee80211_debugfs_key_update_default(sdata); } void ieee80211_set_default_beacon_key(struct ieee80211_link_data *link, int idx) { lockdep_assert_wiphy(link->sdata->local->hw.wiphy); __ieee80211_set_default_beacon_key(link, idx); } static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct sta_info *sta, bool pairwise, struct ieee80211_key *old, struct ieee80211_key *new) { struct link_sta_info *link_sta = sta ? &sta->deflink : NULL; int link_id; int idx; int ret = 0; bool defunikey, defmultikey, defmgmtkey, defbeaconkey; bool is_wep; lockdep_assert_wiphy(sdata->local->hw.wiphy); /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) return 0; if (new) { idx = new->conf.keyidx; is_wep = new->conf.cipher == WLAN_CIPHER_SUITE_WEP40 || new->conf.cipher == WLAN_CIPHER_SUITE_WEP104; link_id = new->conf.link_id; } else { idx = old->conf.keyidx; is_wep = old->conf.cipher == WLAN_CIPHER_SUITE_WEP40 || old->conf.cipher == WLAN_CIPHER_SUITE_WEP104; link_id = old->conf.link_id; } if (WARN(old && old->conf.link_id != link_id, "old link ID %d doesn't match new link ID %d\n", old->conf.link_id, link_id)) return -EINVAL; if (link_id >= 0) { if (!link) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return -ENOLINK; } if (sta) { link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&sta->local->hw.wiphy->mtx)); if (!link_sta) return -ENOLINK; } } else { link = &sdata->deflink; } if ((is_wep || pairwise) && idx >= NUM_DEFAULT_KEYS) return -EINVAL; WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); if (new && sta && pairwise) { /* Unicast rekey needs special handling. With Extended Key ID * old is still NULL for the first rekey. */ ieee80211_pairwise_rekey(old, new); } if (old) { if (old->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) { ieee80211_key_disable_hw_accel(old); if (new) ret = ieee80211_key_enable_hw_accel(new); } } else { if (!new->local->wowlan) ret = ieee80211_key_enable_hw_accel(new); else new->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; } if (ret) return ret; if (new) list_add_tail_rcu(&new->list, &sdata->key_list); if (sta) { if (pairwise) { rcu_assign_pointer(sta->ptk[idx], new); if (new && !(new->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX)) _ieee80211_set_tx_key(new, true); } else { rcu_assign_pointer(link_sta->gtk[idx], new); } /* Only needed for transition from no key -> key. * Still triggers unnecessary when using Extended Key ID * and installing the second key ID the first time. */ if (new && !old) ieee80211_check_fast_rx(sta); } else { defunikey = old && old == wiphy_dereference(sdata->local->hw.wiphy, sdata->default_unicast_key); defmultikey = old && old == wiphy_dereference(sdata->local->hw.wiphy, link->default_multicast_key); defmgmtkey = old && old == wiphy_dereference(sdata->local->hw.wiphy, link->default_mgmt_key); defbeaconkey = old && old == wiphy_dereference(sdata->local->hw.wiphy, link->default_beacon_key); if (defunikey && !new) __ieee80211_set_default_key(link, -1, true, false); if (defmultikey && !new) __ieee80211_set_default_key(link, -1, false, true); if (defmgmtkey && !new) __ieee80211_set_default_mgmt_key(link, -1); if (defbeaconkey && !new) __ieee80211_set_default_beacon_key(link, -1); if (is_wep || pairwise) rcu_assign_pointer(sdata->keys[idx], new); else rcu_assign_pointer(link->gtk[idx], new); if (defunikey && new) __ieee80211_set_default_key(link, new->conf.keyidx, true, false); if (defmultikey && new) __ieee80211_set_default_key(link, new->conf.keyidx, false, true); if (defmgmtkey && new) __ieee80211_set_default_mgmt_key(link, new->conf.keyidx); if (defbeaconkey && new) __ieee80211_set_default_beacon_key(link, new->conf.keyidx); } if (old) list_del_rcu(&old->list); return 0; } struct ieee80211_key * ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, const u8 *key_data, size_t seq_len, const u8 *seq) { struct ieee80211_key *key; int i, j, err; if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS)) return ERR_PTR(-EINVAL); key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL); if (!key) return ERR_PTR(-ENOMEM); /* * Default to software encryption; we'll later upload the * key to the hardware if possible. */ key->conf.flags = 0; key->flags = 0; key->conf.link_id = -1; key->conf.cipher = cipher; key->conf.keyidx = idx; key->conf.keylen = key_len; switch (cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: key->conf.iv_len = IEEE80211_WEP_IV_LEN; key->conf.icv_len = IEEE80211_WEP_ICV_LEN; break; case WLAN_CIPHER_SUITE_TKIP: key->conf.iv_len = IEEE80211_TKIP_IV_LEN; key->conf.icv_len = IEEE80211_TKIP_ICV_LEN; if (seq) { for (i = 0; i < IEEE80211_NUM_TIDS; i++) { key->u.tkip.rx[i].iv32 = get_unaligned_le32(&seq[2]); key->u.tkip.rx[i].iv16 = get_unaligned_le16(seq); } } spin_lock_init(&key->u.tkip.txlock); break; case WLAN_CIPHER_SUITE_CCMP: key->conf.iv_len = IEEE80211_CCMP_HDR_LEN; key->conf.icv_len = IEEE80211_CCMP_MIC_LEN; if (seq) { for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < IEEE80211_CCMP_PN_LEN; j++) key->u.ccmp.rx_pn[i][j] = seq[IEEE80211_CCMP_PN_LEN - j - 1]; } /* * Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt( key_data, key_len, IEEE80211_CCMP_MIC_LEN); if (IS_ERR(key->u.ccmp.tfm)) { err = PTR_ERR(key->u.ccmp.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_CCMP_256: key->conf.iv_len = IEEE80211_CCMP_256_HDR_LEN; key->conf.icv_len = IEEE80211_CCMP_256_MIC_LEN; for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < IEEE80211_CCMP_256_PN_LEN; j++) key->u.ccmp.rx_pn[i][j] = seq[IEEE80211_CCMP_256_PN_LEN - j - 1]; /* Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.ccmp.tfm = ieee80211_aes_key_setup_encrypt( key_data, key_len, IEEE80211_CCMP_256_MIC_LEN); if (IS_ERR(key->u.ccmp.tfm)) { err = PTR_ERR(key->u.ccmp.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->conf.iv_len = 0; if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) key->conf.icv_len = sizeof(struct ieee80211_mmie); else key->conf.icv_len = sizeof(struct ieee80211_mmie_16); if (seq) for (j = 0; j < IEEE80211_CMAC_PN_LEN; j++) key->u.aes_cmac.rx_pn[j] = seq[IEEE80211_CMAC_PN_LEN - j - 1]; /* * Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.aes_cmac.tfm = ieee80211_aes_cmac_key_setup(key_data, key_len); if (IS_ERR(key->u.aes_cmac.tfm)) { err = PTR_ERR(key->u.aes_cmac.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: key->conf.iv_len = 0; key->conf.icv_len = sizeof(struct ieee80211_mmie_16); if (seq) for (j = 0; j < IEEE80211_GMAC_PN_LEN; j++) key->u.aes_gmac.rx_pn[j] = seq[IEEE80211_GMAC_PN_LEN - j - 1]; /* Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.aes_gmac.tfm = ieee80211_aes_gmac_key_setup(key_data, key_len); if (IS_ERR(key->u.aes_gmac.tfm)) { err = PTR_ERR(key->u.aes_gmac.tfm); kfree(key); return ERR_PTR(err); } break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: key->conf.iv_len = IEEE80211_GCMP_HDR_LEN; key->conf.icv_len = IEEE80211_GCMP_MIC_LEN; for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < IEEE80211_GCMP_PN_LEN; j++) key->u.gcmp.rx_pn[i][j] = seq[IEEE80211_GCMP_PN_LEN - j - 1]; /* Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. */ key->u.gcmp.tfm = ieee80211_aes_gcm_key_setup_encrypt(key_data, key_len); if (IS_ERR(key->u.gcmp.tfm)) { err = PTR_ERR(key->u.gcmp.tfm); kfree(key); return ERR_PTR(err); } break; } memcpy(key->conf.key, key_data, key_len); INIT_LIST_HEAD(&key->list); return key; } static void ieee80211_key_free_common(struct ieee80211_key *key) { switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: ieee80211_aes_key_free(key->u.ccmp.tfm); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: ieee80211_aes_gmac_key_free(key->u.aes_gmac.tfm); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: ieee80211_aes_gcm_key_free(key->u.gcmp.tfm); break; } kfree_sensitive(key); } static void __ieee80211_key_destroy(struct ieee80211_key *key, bool delay_tailroom) { if (key->local) { struct ieee80211_sub_if_data *sdata = key->sdata; ieee80211_debugfs_key_remove(key); if (delay_tailroom) { /* see ieee80211_delayed_tailroom_dec */ sdata->crypto_tx_tailroom_pending_dec++; wiphy_delayed_work_queue(sdata->local->hw.wiphy, &sdata->dec_tailroom_needed_wk, HZ / 2); } else { decrease_tailroom_need_count(sdata, 1); } } ieee80211_key_free_common(key); } static void ieee80211_key_destroy(struct ieee80211_key *key, bool delay_tailroom) { if (!key) return; /* * Synchronize so the TX path and rcu key iterators * can no longer be using this key before we free/remove it. */ synchronize_net(); __ieee80211_key_destroy(key, delay_tailroom); } void ieee80211_key_free_unused(struct ieee80211_key *key) { if (!key) return; WARN_ON(key->sdata || key->local); ieee80211_key_free_common(key); } static bool ieee80211_key_identical(struct ieee80211_sub_if_data *sdata, struct ieee80211_key *old, struct ieee80211_key *new) { u8 tkip_old[WLAN_KEY_LEN_TKIP], tkip_new[WLAN_KEY_LEN_TKIP]; u8 *tk_old, *tk_new; if (!old || new->conf.keylen != old->conf.keylen) return false; tk_old = old->conf.key; tk_new = new->conf.key; /* * In station mode, don't compare the TX MIC key, as it's never used * and offloaded rekeying may not care to send it to the host. This * is the case in iwlwifi, for example. */ if (sdata->vif.type == NL80211_IFTYPE_STATION && new->conf.cipher == WLAN_CIPHER_SUITE_TKIP && new->conf.keylen == WLAN_KEY_LEN_TKIP && !(new->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { memcpy(tkip_old, tk_old, WLAN_KEY_LEN_TKIP); memcpy(tkip_new, tk_new, WLAN_KEY_LEN_TKIP); memset(tkip_old + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8); memset(tkip_new + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY, 0, 8); tk_old = tkip_old; tk_new = tkip_new; } return !crypto_memneq(tk_old, tk_new, new->conf.keylen); } int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_link_data *link, struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = link->sdata; static atomic_t key_color = ATOMIC_INIT(0); struct ieee80211_key *old_key = NULL; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; /* * We want to delay tailroom updates only for station - in that * case it helps roaming speed, but in other cases it hurts and * can cause warnings to appear. */ bool delay_tailroom = sdata->vif.type == NL80211_IFTYPE_STATION; int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (sta && pairwise) { struct ieee80211_key *alt_key; old_key = wiphy_dereference(sdata->local->hw.wiphy, sta->ptk[idx]); alt_key = wiphy_dereference(sdata->local->hw.wiphy, sta->ptk[idx ^ 1]); /* The rekey code assumes that the old and new key are using * the same cipher. Enforce the assumption for pairwise keys. */ if ((alt_key && alt_key->conf.cipher != key->conf.cipher) || (old_key && old_key->conf.cipher != key->conf.cipher)) { ret = -EOPNOTSUPP; goto out; } } else if (sta) { struct link_sta_info *link_sta = &sta->deflink; int link_id = key->conf.link_id; if (link_id >= 0) { link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&sta->local->hw.wiphy->mtx)); if (!link_sta) { ret = -ENOLINK; goto out; } } old_key = wiphy_dereference(sdata->local->hw.wiphy, link_sta->gtk[idx]); } else { if (idx < NUM_DEFAULT_KEYS) old_key = wiphy_dereference(sdata->local->hw.wiphy, sdata->keys[idx]); if (!old_key) old_key = wiphy_dereference(sdata->local->hw.wiphy, link->gtk[idx]); } /* Non-pairwise keys must also not switch the cipher on rekey */ if (!pairwise) { if (old_key && old_key->conf.cipher != key->conf.cipher) { ret = -EOPNOTSUPP; goto out; } } /* * Silently accept key re-installation without really installing the * new version of the key to avoid nonce reuse or replay issues. */ if (ieee80211_key_identical(sdata, old_key, key)) { ret = -EALREADY; goto out; } key->local = sdata->local; key->sdata = sdata; key->sta = sta; /* * Assign a unique ID to every key so we can easily prevent mixed * key and fragment cache attacks. */ key->color = atomic_inc_return(&key_color); /* keep this flag for easier access later */ if (sta && sta->sta.spp_amsdu) key->conf.flags |= IEEE80211_KEY_FLAG_SPP_AMSDU; increment_tailroom_need_count(sdata); ret = ieee80211_key_replace(sdata, link, sta, pairwise, old_key, key); if (!ret) { ieee80211_debugfs_key_add(key); ieee80211_key_destroy(old_key, delay_tailroom); } else { ieee80211_key_free(key, delay_tailroom); } key = NULL; out: ieee80211_key_free_unused(key); return ret; } void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom) { if (!key) return; /* * Replace key with nothingness if it was ever used. */ if (key->sdata) ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); ieee80211_key_destroy(key, delay_tailroom); } void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) { struct ieee80211_key *key; struct ieee80211_sub_if_data *vlan; lockdep_assert_wiphy(sdata->local->hw.wiphy); sdata->crypto_tx_tailroom_needed_cnt = 0; sdata->crypto_tx_tailroom_pending_dec = 0; if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->crypto_tx_tailroom_needed_cnt = 0; vlan->crypto_tx_tailroom_pending_dec = 0; } } if (ieee80211_sdata_running(sdata)) { list_for_each_entry(key, &sdata->key_list, list) { increment_tailroom_need_count(sdata); ieee80211_key_enable_hw_accel(key); } } } static void ieee80211_key_iter(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_key *key, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { /* skip keys of station in removal process */ if (key->sta && key->sta->removed) return; if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) return; iter(hw, vif, key->sta ? &key->sta->sta : NULL, &key->conf, iter_data); } void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_key *key, *tmp; struct ieee80211_sub_if_data *sdata; lockdep_assert_wiphy(hw->wiphy); if (vif) { sdata = vif_to_sdata(vif); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) ieee80211_key_iter(hw, vif, key, iter, iter_data); } else { list_for_each_entry(sdata, &local->interfaces, list) list_for_each_entry_safe(key, tmp, &sdata->key_list, list) ieee80211_key_iter(hw, &sdata->vif, key, iter, iter_data); } } EXPORT_SYMBOL(ieee80211_iter_keys); static void _ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, struct ieee80211_sub_if_data *sdata, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { struct ieee80211_key *key; list_for_each_entry_rcu(key, &sdata->key_list, list) ieee80211_key_iter(hw, &sdata->vif, key, iter, iter_data); } void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; if (vif) { sdata = vif_to_sdata(vif); _ieee80211_iter_keys_rcu(hw, sdata, iter, iter_data); } else { list_for_each_entry_rcu(sdata, &local->interfaces, list) _ieee80211_iter_keys_rcu(hw, sdata, iter, iter_data); } } EXPORT_SYMBOL(ieee80211_iter_keys_rcu); static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, struct list_head *keys) { struct ieee80211_key *key, *tmp; decrease_tailroom_need_count(sdata, sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); ieee80211_debugfs_key_remove_beacon_default(sdata); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); list_add_tail(&key->list, keys); } ieee80211_debugfs_key_update_default(sdata); } void ieee80211_remove_link_keys(struct ieee80211_link_data *link, struct list_head *keys) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_key *key, *tmp; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { if (key->conf.link_id != link->link_id) continue; ieee80211_key_replace(key->sdata, link, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); list_add_tail(&key->list, keys); } } void ieee80211_free_key_list(struct ieee80211_local *local, struct list_head *keys) { struct ieee80211_key *key, *tmp; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry_safe(key, tmp, keys, list) __ieee80211_key_destroy(key, false); } void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, bool force_synchronize) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *vlan; struct ieee80211_sub_if_data *master; struct ieee80211_key *key, *tmp; LIST_HEAD(keys); wiphy_delayed_work_cancel(local->hw.wiphy, &sdata->dec_tailroom_needed_wk); lockdep_assert_wiphy(local->hw.wiphy); ieee80211_free_keys_iface(sdata, &keys); if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) ieee80211_free_keys_iface(vlan, &keys); } if (!list_empty(&keys) || force_synchronize) synchronize_net(); list_for_each_entry_safe(key, tmp, &keys, list) __ieee80211_key_destroy(key, false); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { if (sdata->bss) { master = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt != master->crypto_tx_tailroom_needed_cnt); } } else { WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || sdata->crypto_tx_tailroom_pending_dec); } if (sdata->vif.type == NL80211_IFTYPE_AP) { list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || vlan->crypto_tx_tailroom_pending_dec); } } void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta) { struct ieee80211_key *key; int i; lockdep_assert_wiphy(local->hw.wiphy); for (i = 0; i < ARRAY_SIZE(sta->deflink.gtk); i++) { key = wiphy_dereference(local->hw.wiphy, sta->deflink.gtk[i]); if (!key) continue; ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); __ieee80211_key_destroy(key, key->sdata->vif.type == NL80211_IFTYPE_STATION); } for (i = 0; i < NUM_DEFAULT_KEYS; i++) { key = wiphy_dereference(local->hw.wiphy, sta->ptk[i]); if (!key) continue; ieee80211_key_replace(key->sdata, NULL, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); __ieee80211_key_destroy(key, key->sdata->vif.type == NL80211_IFTYPE_STATION); } } void ieee80211_delayed_tailroom_dec(struct wiphy *wiphy, struct wiphy_work *wk) { struct ieee80211_sub_if_data *sdata; sdata = container_of(wk, struct ieee80211_sub_if_data, dec_tailroom_needed_wk.work); /* * The reason for the delayed tailroom needed decrementing is to * make roaming faster: during roaming, all keys are first deleted * and then new keys are installed. The first new key causes the * crypto_tx_tailroom_needed_cnt to go from 0 to 1, which invokes * the cost of synchronize_net() (which can be slow). Avoid this * by deferring the crypto_tx_tailroom_needed_cnt decrementing on * key removal for a while, so if we roam the value is larger than * zero and no 0->1 transition happens. * * The cost is that if the AP switching was from an AP with keys * to one without, we still allocate tailroom while it would no * longer be needed. However, in the typical (fast) roaming case * within an ESS this usually won't happen. */ decrease_tailroom_need_count(sdata, sdata->crypto_tx_tailroom_pending_dec); sdata->crypto_tx_tailroom_pending_dec = 0; } void ieee80211_gtk_rekey_notify(struct ieee80211_vif *vif, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); trace_api_gtk_rekey_notify(sdata, bssid, replay_ctr); cfg80211_gtk_rekey_notify(sdata->dev, bssid, replay_ctr, gfp); } EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_notify); void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq) { struct ieee80211_key *key; const u8 *pn; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: if (WARN_ON(tid < 0 || tid >= IEEE80211_NUM_TIDS)) return; seq->tkip.iv32 = key->u.tkip.rx[tid].iv32; seq->tkip.iv16 = key->u.tkip.rx[tid].iv16; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.ccmp.rx_pn[tid]; memcpy(seq->ccmp.pn, pn, IEEE80211_CCMP_PN_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_cmac.rx_pn; memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_gmac.rx_pn; memcpy(seq->aes_gmac.pn, pn, IEEE80211_GMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.gcmp.rx_pn[tid]; memcpy(seq->gcmp.pn, pn, IEEE80211_GCMP_PN_LEN); break; } } EXPORT_SYMBOL(ieee80211_get_key_rx_seq); void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq) { struct ieee80211_key *key; u8 *pn; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: if (WARN_ON(tid < 0 || tid >= IEEE80211_NUM_TIDS)) return; key->u.tkip.rx[tid].iv32 = seq->tkip.iv32; key->u.tkip.rx[tid].iv16 = seq->tkip.iv16; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.ccmp.rx_pn[tid]; memcpy(pn, seq->ccmp.pn, IEEE80211_CCMP_PN_LEN); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_cmac.rx_pn; memcpy(pn, seq->aes_cmac.pn, IEEE80211_CMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (WARN_ON(tid != 0)) return; pn = key->u.aes_gmac.rx_pn; memcpy(pn, seq->aes_gmac.pn, IEEE80211_GMAC_PN_LEN); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.gcmp.rx_pn[tid]; memcpy(pn, seq->gcmp.pn, IEEE80211_GCMP_PN_LEN); break; default: WARN_ON(1); break; } } EXPORT_SYMBOL_GPL(ieee80211_set_key_rx_seq); void ieee80211_remove_key(struct ieee80211_key_conf *keyconf) { struct ieee80211_key *key; key = container_of(keyconf, struct ieee80211_key, conf); lockdep_assert_wiphy(key->local->hw.wiphy); /* * if key was uploaded, we assume the driver will/has remove(d) * it, so adjust bookkeeping accordingly */ if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) { key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; if (!(key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE | IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(key->sdata); } ieee80211_key_free(key, false); } EXPORT_SYMBOL_GPL(ieee80211_remove_key); struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, struct ieee80211_key_conf *keyconf, int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; int err; struct ieee80211_link_data *link_data = link_id < 0 ? &sdata->deflink : sdata_dereference(sdata->link[link_id], sdata); if (WARN_ON(!link_data)) return ERR_PTR(-EINVAL); if (WARN_ON(!local->wowlan)) return ERR_PTR(-EINVAL); if (WARN_ON(vif->type != NL80211_IFTYPE_STATION)) return ERR_PTR(-EINVAL); key = ieee80211_key_alloc(keyconf->cipher, keyconf->keyidx, keyconf->keylen, keyconf->key, 0, NULL); if (IS_ERR(key)) return ERR_CAST(key); if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; key->conf.link_id = link_data->link_id; err = ieee80211_key_link(key, link_data, NULL); if (err) return ERR_PTR(err); return &key->conf; } EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_add); void ieee80211_key_mic_failure(struct ieee80211_key_conf *keyconf) { struct ieee80211_key *key; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->u.aes_cmac.icverrors++; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: key->u.aes_gmac.icverrors++; break; default: /* ignore the others for now, we don't keep counters now */ break; } } EXPORT_SYMBOL_GPL(ieee80211_key_mic_failure); void ieee80211_key_replay(struct ieee80211_key_conf *keyconf) { struct ieee80211_key *key; key = container_of(keyconf, struct ieee80211_key, conf); switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: key->u.ccmp.replays++; break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: key->u.aes_cmac.replays++; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: key->u.aes_gmac.replays++; break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: key->u.gcmp.replays++; break; } } EXPORT_SYMBOL_GPL(ieee80211_key_replay); int ieee80211_key_switch_links(struct ieee80211_sub_if_data *sdata, unsigned long del_links_mask, unsigned long add_links_mask) { struct ieee80211_key *key; int ret; list_for_each_entry(key, &sdata->key_list, list) { if (key->conf.link_id < 0 || !(del_links_mask & BIT(key->conf.link_id))) continue; /* shouldn't happen for per-link keys */ WARN_ON(key->sta); ieee80211_key_disable_hw_accel(key); } list_for_each_entry(key, &sdata->key_list, list) { if (key->conf.link_id < 0 || !(add_links_mask & BIT(key->conf.link_id))) continue; /* shouldn't happen for per-link keys */ WARN_ON(key->sta); ret = ieee80211_key_enable_hw_accel(key); if (ret) return ret; } return 0; } |
| 91 90 91 91 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine (KVM) Hypervisor * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ #include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/percpu.h> #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/vmalloc.h> #include <linux/reboot.h> #include <linux/debugfs.h> #include <linux/highmem.h> #include <linux/file.h> #include <linux/syscore_ops.h> #include <linux/cpu.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/cpumask.h> #include <linux/smp.h> #include <linux/anon_inodes.h> #include <linux/profile.h> #include <linux/kvm_para.h> #include <linux/pagemap.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/compat.h> #include <linux/srcu.h> #include <linux/hugetlb.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/bsearch.h> #include <linux/io.h> #include <linux/lockdep.h> #include <linux/kthread.h> #include <linux/suspend.h> #include <asm/processor.h> #include <asm/ioctl.h> #include <linux/uaccess.h> #include "coalesced_mmio.h" #include "async_pf.h" #include "kvm_mm.h" #include "vfio.h" #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> #include <linux/kvm_dirty_ring.h> /* Worst case buffer size needed for holding an integer. */ #define ITOA_MAX_LEN 12 MODULE_AUTHOR("Qumranet"); MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor"); MODULE_LICENSE("GPL"); /* Architectures should define their poll value according to the halt latency */ unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; module_param(halt_poll_ns, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns); /* Default doubles per-vcpu halt_poll_ns. */ unsigned int halt_poll_ns_grow = 2; module_param(halt_poll_ns_grow, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow); /* The start value to grow halt_poll_ns from */ unsigned int halt_poll_ns_grow_start = 10000; /* 10us */ module_param(halt_poll_ns_grow_start, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start); /* Default halves per-vcpu halt_poll_ns. */ unsigned int halt_poll_ns_shrink = 2; module_param(halt_poll_ns_shrink, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); /* * Allow direct access (from KVM or the CPU) without MMU notifier protection * to unpinned pages. */ static bool allow_unsafe_mappings; module_param(allow_unsafe_mappings, bool, 0444); /* * Ordering of locks: * * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ DEFINE_MUTEX(kvm_lock); LIST_HEAD(vm_list); static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); static struct dentry *kvm_debugfs_dir; static const struct file_operations stat_fops_per_vm; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #define KVM_COMPAT(c) .compat_ioctl = (c) #else /* * For architectures that don't implement a compat infrastructure, * adopt a double line of defense: * - Prevent a compat task from opening /dev/kvm * - If the open has been done by a 64bit task, and the KVM fd * passed to a compat task, let the ioctls fail. */ static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { return -EINVAL; } static int kvm_no_compat_open(struct inode *inode, struct file *file) { return is_compat_task() ? -ENODEV : 0; } #define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ .open = kvm_no_compat_open #endif static int kvm_enable_virtualization(void); static void kvm_disable_virtualization(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { } /* * Switches to specified vcpu, until a matching vcpu_put() */ void vcpu_load(struct kvm_vcpu *vcpu) { int cpu = get_cpu(); __this_cpu_write(kvm_running_vcpu, vcpu); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); } EXPORT_SYMBOL_GPL(vcpu_load); void vcpu_put(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); __this_cpu_write(kvm_running_vcpu, NULL); preempt_enable(); } EXPORT_SYMBOL_GPL(vcpu_put); /* TODO: merge with kvm_arch_vcpu_should_kick */ static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req) { int mode = kvm_vcpu_exiting_guest_mode(vcpu); /* * We need to wait for the VCPU to reenable interrupts and get out of * READING_SHADOW_PAGE_TABLES mode. */ if (req & KVM_REQUEST_WAIT) return mode != OUTSIDE_GUEST_MODE; /* * Need to kick a running VCPU, but otherwise there is nothing to do. */ return mode == IN_GUEST_MODE; } static void ack_kick(void *_completed) { } static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) { if (cpumask_empty(cpus)) return false; smp_call_function_many(cpus, ack_kick, NULL, wait); return true; } static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req, struct cpumask *tmp, int current_cpu) { int cpu; if (likely(!(req & KVM_REQUEST_NO_ACTION))) __kvm_make_request(req, vcpu); if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) return; /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_request_needs_ipi(), which could result in sending an IPI * to the previous pCPU. But, that's OK because the purpose of the IPI * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES * after this point is also OK, as the requirement is only that KVM wait * for vCPUs that were reading SPTEs _before_ any changes were * finalized. See kvm_vcpu_kick() for more details on handling requests. */ if (kvm_request_needs_ipi(vcpu, req)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != -1 && cpu != current_cpu) __cpumask_set_cpu(cpu, tmp); } } bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap) { struct kvm_vcpu *vcpu; struct cpumask *cpus; int i, me; bool called; me = get_cpu(); cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); cpumask_clear(cpus); for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { vcpu = kvm_get_vcpu(kvm, i); if (!vcpu) continue; kvm_make_vcpu_request(vcpu, req, cpus, me); } called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { struct kvm_vcpu *vcpu; struct cpumask *cpus; unsigned long i; bool called; int me; me = get_cpu(); cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); cpumask_clear(cpus); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_vcpu_request(vcpu, req, cpus, me); called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); void kvm_flush_remote_tlbs(struct kvm *kvm) { ++kvm->stat.generic.remote_tlb_flush_requests; /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. * - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest * and smp_mb in walk_shadow_page_lockless_begin/end. * - powerpc: smp_mb in kvmppc_prepare_to_enter. * * There is already an smp_mb__after_atomic() before * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that * barrier here. */ if (!kvm_arch_flush_remote_tlbs(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages)) return; /* * Fall back to a flushing entire TLBs if the architecture range-based * TLB invalidation is unsupported or can't be performed for whatever * reason. */ kvm_flush_remote_tlbs(kvm); } void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot) { /* * All current use cases for flushing the TLBs for a specific memslot * are related to dirty logging, and many do the TLB flush out of * mmu_lock. The interaction between the various operations on memslot * must be serialized by slots_locks to ensure the TLB flush from one * operation is observed by any other operation on the same memslot. */ lockdep_assert_held(&kvm->slots_lock); kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); } static void kvm_flush_shadow_all(struct kvm *kvm) { kvm_arch_flush_shadow_all(kvm); kvm_arch_guest_memory_reclaimed(kvm); } #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) { void *page; gfp_flags |= mc->gfp_zero; if (mc->kmem_cache) return kmem_cache_alloc(mc->kmem_cache, gfp_flags); page = (void *)__get_free_page(gfp_flags); if (page && mc->init_value) memset64(page, mc->init_value, PAGE_SIZE / sizeof(u64)); return page; } int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min) { gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT; void *obj; if (mc->nobjs >= min) return 0; if (unlikely(!mc->objects)) { if (WARN_ON_ONCE(!capacity)) return -EIO; /* * Custom init values can be used only for page allocations, * and obviously conflict with __GFP_ZERO. */ if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero))) return -EIO; mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp); if (!mc->objects) return -ENOMEM; mc->capacity = capacity; } /* It is illegal to request a different capacity across topups. */ if (WARN_ON_ONCE(mc->capacity != capacity)) return -EIO; while (mc->nobjs < mc->capacity) { obj = mmu_memory_cache_alloc_obj(mc, gfp); if (!obj) return mc->nobjs >= min ? 0 : -ENOMEM; mc->objects[mc->nobjs++] = obj; } return 0; } int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) { return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min); } int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc) { return mc->nobjs; } void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) { while (mc->nobjs) { if (mc->kmem_cache) kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]); else free_page((unsigned long)mc->objects[--mc->nobjs]); } kvfree(mc->objects); mc->objects = NULL; mc->capacity = 0; } void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { void *p; if (WARN_ON(!mc->nobjs)) p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT); else p = mc->objects[--mc->nobjs]; BUG_ON(!p); return p; } #endif static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { mutex_init(&vcpu->mutex); vcpu->cpu = -1; vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; rwlock_init(&vcpu->pid_lock); #ifndef __KVM_HAVE_ARCH_WQP rcuwait_init(&vcpu->wait); #endif kvm_async_pf_vcpu_init(vcpu); kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); vcpu->last_used_slot = NULL; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", task_pid_nr(current), id); } static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_arch_vcpu_destroy(vcpu); kvm_dirty_ring_free(&vcpu->dirty_ring); /* * No need for rcu_read_lock as VCPU_RUN is the only place that changes * the vcpu->pid pointer, and at destruction time all file descriptors * are already gone. */ put_pid(vcpu->pid); free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } void kvm_destroy_vcpus(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_vcpu_destroy(vcpu); xa_erase(&kvm->vcpu_array, i); /* * Assert that the vCPU isn't visible in any way, to ensure KVM * doesn't trigger a use-after-free if destroying vCPUs results * in VM-wide request, e.g. to flush remote TLBs when tearing * down MMUs, or to mark the VM dead if a KVM_BUG_ON() fires. */ WARN_ON_ONCE(xa_load(&kvm->vcpu_array, i) || kvm_get_vcpu(kvm, i)); } atomic_set(&kvm->online_vcpus, 0); } EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); } typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm); struct kvm_mmu_notifier_range { /* * 64-bit addresses, as KVM notifiers can operate on host virtual * addresses (unsigned long) and guest physical addresses (64-bit). */ u64 start; u64 end; union kvm_mmu_notifier_arg arg; gfn_handler_t handler; on_lock_fn_t on_lock; bool flush_on_ret; bool may_block; bool lockless; }; /* * The inner-most helper returns a tuple containing the return value from the * arch- and action-specific handler, plus a flag indicating whether or not at * least one memslot was found, i.e. if the handler found guest memory. * * Note, most notifiers are averse to booleans, so even though KVM tracks the * return from arch code as a bool, outer helpers will cast it to an int. :-( */ typedef struct kvm_mmu_notifier_return { bool ret; bool found_memslot; } kvm_mn_ret_t; /* * Use a dedicated stub instead of NULL to indicate that there is no callback * function/handler. The compiler technically can't guarantee that a real * function will have a non-zero address, and so it will generate code to * check for !NULL, whereas comparing against a stub will be elided at compile * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9). */ static void kvm_null_fn(void) { } #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) /* Iterate over each memslot intersecting [start, last] (inclusive) range */ #define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ node; \ node = interval_tree_iter_next(node, start, last)) \ static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm, const struct kvm_mmu_notifier_range *range) { struct kvm_mmu_notifier_return r = { .ret = false, .found_memslot = false, }; struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; int i, idx; if (WARN_ON_ONCE(range->end <= range->start)) return r; /* A null handler is allowed if and only if on_lock() is provided. */ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && IS_KVM_NULL_FN(range->handler))) return r; /* on_lock will never be called for lockless walks */ if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock))) return r; idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct interval_tree_node *node; slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_hva_range(node, slots, range->start, range->end - 1) { unsigned long hva_start, hva_end; slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); hva_start = max_t(unsigned long, range->start, slot->userspace_addr); hva_end = min_t(unsigned long, range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); /* * To optimize for the likely case where the address * range is covered by zero or one memslots, don't * bother making these conditional (to avoid writes on * the second or later invocation of the handler). */ gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; /* * HVA-based notifications aren't relevant to private * mappings as they don't have a userspace mapping. */ gfn_range.attr_filter = KVM_FILTER_SHARED; /* * {gfn(page) | page intersects with [hva_start, hva_end)} = * {gfn_start, gfn_start+1, ..., gfn_end-1}. */ gfn_range.start = hva_to_gfn_memslot(hva_start, slot); gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot); gfn_range.slot = slot; gfn_range.lockless = range->lockless; if (!r.found_memslot) { r.found_memslot = true; if (!range->lockless) { KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) range->on_lock(kvm); if (IS_KVM_NULL_FN(range->handler)) goto mmu_unlock; } } r.ret |= range->handler(kvm, &gfn_range); } } if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); mmu_unlock: if (r.found_memslot && !range->lockless) KVM_MMU_UNLOCK(kvm); srcu_read_unlock(&kvm->srcu, idx); return r; } static __always_inline int kvm_age_hva_range(struct mmu_notifier *mn, unsigned long start, unsigned long end, gfn_handler_t handler, bool flush_on_ret) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .handler = handler, .on_lock = (void *)kvm_null_fn, .flush_on_ret = flush_on_ret, .may_block = false, .lockless = IS_ENABLED(CONFIG_KVM_MMU_LOCKLESS_AGING), }; return kvm_handle_hva_range(kvm, &range).ret; } static __always_inline int kvm_age_hva_range_no_flush(struct mmu_notifier *mn, unsigned long start, unsigned long end, gfn_handler_t handler) { return kvm_age_hva_range(mn, start, end, handler, false); } void kvm_mmu_invalidate_begin(struct kvm *kvm) { lockdep_assert_held_write(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ kvm->mmu_invalidate_in_progress++; if (likely(kvm->mmu_invalidate_in_progress == 1)) { kvm->mmu_invalidate_range_start = INVALID_GPA; kvm->mmu_invalidate_range_end = INVALID_GPA; } } void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end) { lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress); if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) { kvm->mmu_invalidate_range_start = start; kvm->mmu_invalidate_range_end = end; } else { /* * Fully tracking multiple concurrent ranges has diminishing * returns. Keep things simple and just find the minimal range * which includes the current and new ranges. As there won't be * enough information to subtract a range after its invalidate * completes, any ranges invalidated concurrently will * accumulate and persist until all outstanding invalidates * complete. */ kvm->mmu_invalidate_range_start = min(kvm->mmu_invalidate_range_start, start); kvm->mmu_invalidate_range_end = max(kvm->mmu_invalidate_range_end, end); } } bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_unmap_gfn_range(kvm, range); } static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = kvm_mmu_unmap_gfn_range, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; trace_kvm_unmap_hva_range(range->start, range->end); /* * Prevent memslot modification between range_start() and range_end() * so that conditionally locking provides the same result in both * functions. Without that guarantee, the mmu_invalidate_in_progress * adjustments will be imbalanced. * * Pairs with the decrement in range_end(). */ spin_lock(&kvm->mn_invalidate_lock); kvm->mn_active_invalidate_count++; spin_unlock(&kvm->mn_invalidate_lock); /* * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e. * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring * each cache's lock. There are relatively few caches in existence at * any given time, and the caches themselves can check for hva overlap, * i.e. don't need to rely on memslot overlap checks for performance. * Because this runs without holding mmu_lock, the pfn caches must use * mn_active_invalidate_count (see above) instead of * mmu_invalidate_in_progress. */ gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end); /* * If one or more memslots were found and thus zapped, notify arch code * that guest memory has been reclaimed. This needs to be done *after* * dropping mmu_lock, as x86's reclaim path is slooooow. */ if (kvm_handle_hva_range(kvm, &hva_range).found_memslot) kvm_arch_guest_memory_reclaimed(kvm); return 0; } void kvm_mmu_invalidate_end(struct kvm *kvm) { lockdep_assert_held_write(&kvm->mmu_lock); /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have * been freed. */ kvm->mmu_invalidate_seq++; smp_wmb(); /* * The above sequence increase must be visible before the * below count decrease, which is ensured by the smp_wmb above * in conjunction with the smp_rmb in mmu_invalidate_retry(). */ kvm->mmu_invalidate_in_progress--; KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm); /* * Assert that at least one range was added between start() and end(). * Not adding a range isn't fatal, but it is a KVM bug. */ WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA); } static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = (void *)kvm_null_fn, .on_lock = kvm_mmu_invalidate_end, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; bool wake; kvm_handle_hva_range(kvm, &hva_range); /* Pairs with the increment in range_start(). */ spin_lock(&kvm->mn_invalidate_lock); if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count)) --kvm->mn_active_invalidate_count; wake = !kvm->mn_active_invalidate_count; spin_unlock(&kvm->mn_invalidate_lock); /* * There can only be one waiter, since the wait happens under * slots_lock. */ if (wake) rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); } static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { trace_kvm_age_hva(start, end); return kvm_age_hva_range(mn, start, end, kvm_age_gfn, !IS_ENABLED(CONFIG_KVM_ELIDE_TLB_FLUSH_IF_YOUNG)); } static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { trace_kvm_age_hva(start, end); /* * Even though we do not flush TLB, this will still adversely * affect performance on pre-Haswell Intel EPT, where there is * no EPT Access Bit to clear so that we have to tear down EPT * tables instead. If we find this unacceptable, we can always * add a parameter to kvm_age_hva so that it effectively doesn't * do anything on clear_young. * * Also note that currently we never issue secondary TLB flushes * from clear_young, leaving this job up to the regular system * cadence. If we find this inaccurate, we might come up with a * more sophisticated heuristic later. */ return kvm_age_hva_range_no_flush(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { trace_kvm_test_age_hva(address); return kvm_age_hva_range_no_flush(mn, address, address + 1, kvm_test_age_gfn); } static void kvm_mmu_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int idx; idx = srcu_read_lock(&kvm->srcu); kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, .clear_young = kvm_mmu_notifier_clear_young, .test_young = kvm_mmu_notifier_test_young, .release = kvm_mmu_notifier_release, }; static int kvm_init_mmu_notifier(struct kvm *kvm) { kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } #else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */ static int kvm_init_mmu_notifier(struct kvm *kvm) { return 0; } #endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */ #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_pm_notifier_call(struct notifier_block *bl, unsigned long state, void *unused) { struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); return kvm_arch_pm_notifier(kvm, state); } static void kvm_init_pm_notifier(struct kvm *kvm) { kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; /* Suspend KVM before we suspend ftrace, RCU, etc. */ kvm->pm_notifier.priority = INT_MAX; register_pm_notifier(&kvm->pm_notifier); } static void kvm_destroy_pm_notifier(struct kvm *kvm) { unregister_pm_notifier(&kvm->pm_notifier); } #else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_init_pm_notifier(struct kvm *kvm) { } static void kvm_destroy_pm_notifier(struct kvm *kvm) { } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) return; vfree(memslot->dirty_bitmap); memslot->dirty_bitmap = NULL; } /* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { if (slot->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(slot); kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { struct hlist_node *idnode; struct kvm_memory_slot *memslot; int bkt; /* * The same memslot objects live in both active and inactive sets, * arbitrarily free using index '1' so the second invocation of this * function isn't operating over a structure with dangling pointers * (even though this function isn't actually touching them). */ if (!slots->node_idx) return; hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot); } static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) { switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { case KVM_STATS_TYPE_INSTANT: return 0444; case KVM_STATS_TYPE_CUMULATIVE: case KVM_STATS_TYPE_PEAK: default: return 0644; } } static void kvm_destroy_vm_debugfs(struct kvm *kvm) { int i; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; if (IS_ERR(kvm->debugfs_dentry)) return; debugfs_remove_recursive(kvm->debugfs_dentry); if (kvm->debugfs_stat_data) { for (i = 0; i < kvm_debugfs_num_entries; i++) kfree(kvm->debugfs_stat_data[i]); kfree(kvm->debugfs_stat_data); } } static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) { static DEFINE_MUTEX(kvm_debugfs_lock); struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; const struct _kvm_stats_desc *pdesc; int i, ret = -ENOMEM; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; if (!debugfs_initialized()) return 0; snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname); mutex_lock(&kvm_debugfs_lock); dent = debugfs_lookup(dir_name, kvm_debugfs_dir); if (dent) { pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name); dput(dent); mutex_unlock(&kvm_debugfs_lock); return 0; } dent = debugfs_create_dir(dir_name, kvm_debugfs_dir); mutex_unlock(&kvm_debugfs_lock); if (IS_ERR(dent)) return 0; kvm->debugfs_dentry = dent; kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), GFP_KERNEL_ACCOUNT); if (!kvm->debugfs_stat_data) goto out_err; for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { pdesc = &kvm_vm_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) goto out_err; stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VM; kvm->debugfs_stat_data[i] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { pdesc = &kvm_vcpu_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) goto out_err; stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VCPU; kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } kvm_arch_create_vm_debugfs(kvm); return 0; out_err: kvm_destroy_vm_debugfs(kvm); return ret; } /* * Called just after removing the VM from the vm_list, but before doing any * other destruction. */ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) { } /* * Called after per-vm debugfs created. When called kvm->debugfs_dentry should * be setup already, so we can create arch-specific debugfs entries under it. * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so * a per-arch destroy interface is not needed. */ void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) { } static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) { struct kvm *kvm = kvm_arch_alloc_vm(); struct kvm_memslots *slots; int r, i, j; if (!kvm) return ERR_PTR(-ENOMEM); KVM_MMU_LOCK_INIT(kvm); mmgrab(current->mm); kvm->mm = current->mm; kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); mutex_init(&kvm->slots_arch_lock); spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_init(&kvm->mem_attr_array); #endif INIT_LIST_HEAD(&kvm->gpc_list); spin_lock_init(&kvm->gpc_lock); INIT_LIST_HEAD(&kvm->devices); kvm->max_vcpus = KVM_MAX_VCPUS; BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); /* * Force subsequent debugfs file creations to fail if the VM directory * is not created (by kvm_create_vm_debugfs()). */ kvm->debugfs_dentry = ERR_PTR(-ENOENT); snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d", task_pid_nr(current)); r = -ENOMEM; if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) goto out_err_no_irq_srcu; r = kvm_init_irq_routing(kvm); if (r) goto out_err_no_irq_routing; refcount_set(&kvm->users_count, 1); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { for (j = 0; j < 2; j++) { slots = &kvm->__memslots[i][j]; atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); slots->hva_tree = RB_ROOT_CACHED; slots->gfn_tree = RB_ROOT; hash_init(slots->id_hash); slots->node_idx = j; /* Generations must be different for each address space. */ slots->generation = i; } rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); } r = -ENOMEM; for (i = 0; i < KVM_NR_BUSES; i++) { rcu_assign_pointer(kvm->buses[i], kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT)); if (!kvm->buses[i]) goto out_err_no_arch_destroy_vm; } r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; r = kvm_enable_virtualization(); if (r) goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif r = kvm_init_mmu_notifier(kvm); if (r) goto out_err_no_mmu_notifier; r = kvm_coalesced_mmio_init(kvm); if (r < 0) goto out_no_coalesced_mmio; r = kvm_create_vm_debugfs(kvm, fdname); if (r) goto out_err_no_debugfs; mutex_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); mutex_unlock(&kvm_lock); preempt_notifier_inc(); kvm_init_pm_notifier(kvm); return kvm; out_err_no_debugfs: kvm_coalesced_mmio_free(kvm); out_no_coalesced_mmio: #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif out_err_no_mmu_notifier: kvm_disable_virtualization(); out_err_no_disable: kvm_arch_destroy_vm(kvm); out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); kvm_free_irq_routing(kvm); out_err_no_irq_routing: cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); out_err_no_srcu: kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); } static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; /* * We do not need to take the kvm->lock here, because nobody else * has a reference to the struct kvm at this point and therefore * cannot access the devices list anyhow. * * The device list is generally managed as an rculist, but list_del() * is used intentionally here. If a bug in KVM introduced a reader that * was not backed by a reference on the kvm struct, the hope is that * it'd consume the poisoned forward pointer instead of suffering a * use-after-free, even though this cannot be guaranteed. */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); } } static void kvm_destroy_vm(struct kvm *kvm) { int i; struct mm_struct *mm = kvm->mm; kvm_destroy_pm_notifier(kvm); kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); mutex_lock(&kvm_lock); list_del(&kvm->vm_list); mutex_unlock(&kvm_lock); kvm_arch_pre_destroy_vm(kvm); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { struct kvm_io_bus *bus = kvm_get_bus(kvm, i); if (bus) kvm_io_bus_destroy(bus); kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); /* * At this point, pending calls to invalidate_range_start() * have completed but no more MMU notifiers will run, so * mn_active_invalidate_count may remain unbalanced. * No threads can be waiting in kvm_swap_active_memslots() as the * last reference on KVM has been dropped, but freeing * memslots would deadlock without this manual intervention. * * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU * notifier between a start() and end(), then there shouldn't be any * in-progress invalidations. */ WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); if (kvm->mn_active_invalidate_count) kvm->mn_active_invalidate_count = 0; else WARN_ON(kvm->mmu_invalidate_in_progress); #else kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { kvm_free_memslots(kvm, &kvm->__memslots[i][0]); kvm_free_memslots(kvm, &kvm->__memslots[i][1]); } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_destroy(&kvm->mem_attr_array); #endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); kvm_disable_virtualization(); mmdrop(mm); } void kvm_get_kvm(struct kvm *kvm) { refcount_inc(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm); /* * Make sure the vm is not during destruction, which is a safe version of * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise. */ bool kvm_get_kvm_safe(struct kvm *kvm) { return refcount_inc_not_zero(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); void kvm_put_kvm(struct kvm *kvm) { if (refcount_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm); } EXPORT_SYMBOL_GPL(kvm_put_kvm); /* * Used to put a reference that was taken on behalf of an object associated * with a user-visible file descriptor, e.g. a vcpu or device, if installation * of the new file descriptor fails and the reference cannot be transferred to * its final owner. In such cases, the caller is still actively using @kvm and * will fail miserably if the refcount unexpectedly hits zero. */ void kvm_put_kvm_no_destroy(struct kvm *kvm) { WARN_ON(refcount_dec_and_test(&kvm->users_count)); } EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy); static int kvm_vm_release(struct inode *inode, struct file *filp) { struct kvm *kvm = filp->private_data; kvm_irqfd_release(kvm); kvm_put_kvm(kvm); return 0; } /* * Allocation size is twice as large as the actual dirty bitmap size. * See kvm_vm_ioctl_get_dirty_log() why this is needed. */ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot); memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; return 0; } static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { struct kvm_memslots *active = __kvm_memslots(kvm, as_id); int node_idx_inactive = active->node_idx ^ 1; return &kvm->__memslots[as_id][node_idx_inactive]; } /* * Helper to get the address space ID when one of memslot pointers may be NULL. * This also serves as a sanity that at least one of the pointers is non-NULL, * and that their address space IDs don't diverge. */ static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, struct kvm_memory_slot *b) { if (WARN_ON_ONCE(!a && !b)) return 0; if (!a) return b->as_id; if (!b) return a->as_id; WARN_ON_ONCE(a->as_id != b->as_id); return a->as_id; } static void kvm_insert_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *slot) { struct rb_root *gfn_tree = &slots->gfn_tree; struct rb_node **node, *parent; int idx = slots->node_idx; parent = NULL; for (node = &gfn_tree->rb_node; *node; ) { struct kvm_memory_slot *tmp; tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); parent = *node; if (slot->base_gfn < tmp->base_gfn) node = &(*node)->rb_left; else if (slot->base_gfn > tmp->base_gfn) node = &(*node)->rb_right; else BUG(); } rb_link_node(&slot->gfn_node[idx], parent, node); rb_insert_color(&slot->gfn_node[idx], gfn_tree); } static void kvm_erase_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *slot) { rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); } static void kvm_replace_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int idx = slots->node_idx; WARN_ON_ONCE(old->base_gfn != new->base_gfn); rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], &slots->gfn_tree); } /* * Replace @old with @new in the inactive memslots. * * With NULL @old this simply adds @new. * With NULL @new this simply removes @old. * * If @new is non-NULL its hva_node[slots_idx] range has to be set * appropriately. */ static void kvm_replace_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int as_id = kvm_memslots_get_as_id(old, new); struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); int idx = slots->node_idx; if (old) { hash_del(&old->id_node[idx]); interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); if ((long)old == atomic_long_read(&slots->last_used_slot)) atomic_long_set(&slots->last_used_slot, (long)new); if (!new) { kvm_erase_gfn_node(slots, old); return; } } /* * Initialize @new's hva range. Do this even when replacing an @old * slot, kvm_copy_memslot() deliberately does not touch node data. */ new->hva_node[idx].start = new->userspace_addr; new->hva_node[idx].last = new->userspace_addr + (new->npages << PAGE_SHIFT) - 1; /* * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), * hva_node needs to be swapped with remove+insert even though hva can't * change when replacing an existing slot. */ hash_add(slots->id_hash, &new->id_node[idx], new->id); interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); /* * If the memslot gfn is unchanged, rb_replace_node() can be used to * switch the node in the gfn tree instead of removing the old and * inserting the new as two separate operations. Replacement is a * single O(1) operation versus two O(log(n)) operations for * remove+insert. */ if (old && old->base_gfn == new->base_gfn) { kvm_replace_gfn_node(slots, old, new); } else { if (old) kvm_erase_gfn_node(slots, old); kvm_insert_gfn_node(slots, new); } } /* * Flags that do not access any of the extra space of struct * kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS * only allows these. */ #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) static int check_memory_region_flags(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; if (kvm_arch_has_private_mem(kvm)) valid_flags |= KVM_MEM_GUEST_MEMFD; /* Dirty logging private memory is not currently supported. */ if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ if (kvm_arch_has_readonly_mem(kvm) && !(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; if (mem->flags & ~valid_flags) return -EINVAL; return 0; } static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); /* Grab the generation from the activate memslots. */ u64 gen = __kvm_memslots(kvm, as_id)->generation; WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; /* * Do not store the new memslots while there are invalidations in * progress, otherwise the locking in invalidate_range_start and * invalidate_range_end will be unbalanced. */ spin_lock(&kvm->mn_invalidate_lock); prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait); while (kvm->mn_active_invalidate_count) { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&kvm->mn_invalidate_lock); schedule(); spin_lock(&kvm->mn_invalidate_lock); } finish_rcuwait(&kvm->mn_memslots_update_rcuwait); rcu_assign_pointer(kvm->memslots[as_id], slots); spin_unlock(&kvm->mn_invalidate_lock); /* * Acquired in kvm_set_memslot. Must be released before synchronize * SRCU below in order to avoid deadlock with another thread * acquiring the slots_arch_lock in an srcu critical section. */ mutex_unlock(&kvm->slots_arch_lock); synchronize_srcu_expedited(&kvm->srcu); /* * Increment the new memslot generation a second time, dropping the * update in-progress flag and incrementing the generation based on * the number of address spaces. This provides a unique and easily * identifiable generation number while the memslots are in flux. */ gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; /* * Generations must be unique even across address spaces. We do not need * a global counter for that, instead the generation space is evenly split * across address spaces. For example, with two address spaces, address * space 0 will use generations 0, 2, 4, ... while address space 1 will * use generations 1, 3, 5, ... */ gen += kvm_arch_nr_memslot_as_ids(kvm); kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; } static int kvm_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { int r; /* * If dirty logging is disabled, nullify the bitmap; the old bitmap * will be freed on "commit". If logging is enabled in both old and * new, reuse the existing bitmap. If logging is enabled only in the * new and KVM isn't using a ring buffer, allocate and initialize a * new bitmap. */ if (change != KVM_MR_DELETE) { if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) new->dirty_bitmap = NULL; else if (old && old->dirty_bitmap) new->dirty_bitmap = old->dirty_bitmap; else if (kvm_use_dirty_bitmap(kvm)) { r = kvm_alloc_dirty_bitmap(new); if (r) return r; if (kvm_dirty_log_manual_protect_and_init_set(kvm)) bitmap_set(new->dirty_bitmap, 0, new->npages); } } r = kvm_arch_prepare_memory_region(kvm, old, new, change); /* Free the bitmap on failure if it was allocated above. */ if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) kvm_destroy_dirty_bitmap(new); return r; } static void kvm_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { int old_flags = old ? old->flags : 0; int new_flags = new ? new->flags : 0; /* * Update the total number of memslot pages before calling the arch * hook so that architectures can consume the result directly. */ if (change == KVM_MR_DELETE) kvm->nr_memslot_pages -= old->npages; else if (change == KVM_MR_CREATE) kvm->nr_memslot_pages += new->npages; if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) { int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1; atomic_set(&kvm->nr_memslots_dirty_logging, atomic_read(&kvm->nr_memslots_dirty_logging) + change); } kvm_arch_commit_memory_region(kvm, old, new, change); switch (change) { case KVM_MR_CREATE: /* Nothing more to do. */ break; case KVM_MR_DELETE: /* Free the old memslot and all its metadata. */ kvm_free_memslot(kvm, old); break; case KVM_MR_MOVE: case KVM_MR_FLAGS_ONLY: /* * Free the dirty bitmap as needed; the below check encompasses * both the flags and whether a ring buffer is being used) */ if (old->dirty_bitmap && !new->dirty_bitmap) kvm_destroy_dirty_bitmap(old); /* * The final quirk. Free the detached, old slot, but only its * memory, not any metadata. Metadata, including arch specific * data, may be reused by @new. */ kfree(old); break; default: BUG(); } } /* * Activate @new, which must be installed in the inactive slots by the caller, * by swapping the active slots and then propagating @new to @old once @old is * unreachable and can be safely modified. * * With NULL @old this simply adds @new to @active (while swapping the sets). * With NULL @new this simply removes @old from @active and frees it * (while also swapping the sets). */ static void kvm_activate_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int as_id = kvm_memslots_get_as_id(old, new); kvm_swap_active_memslots(kvm, as_id); /* Propagate the new memslot to the now inactive memslots. */ kvm_replace_memslot(kvm, old, new); } static void kvm_copy_memslot(struct kvm_memory_slot *dest, const struct kvm_memory_slot *src) { dest->base_gfn = src->base_gfn; dest->npages = src->npages; dest->dirty_bitmap = src->dirty_bitmap; dest->arch = src->arch; dest->userspace_addr = src->userspace_addr; dest->flags = src->flags; dest->id = src->id; dest->as_id = src->as_id; } static void kvm_invalidate_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *invalid_slot) { /* * Mark the current slot INVALID. As with all memslot modifications, * this must be done on an unreachable slot to avoid modifying the * current slot in the active tree. */ kvm_copy_memslot(invalid_slot, old); invalid_slot->flags |= KVM_MEMSLOT_INVALID; kvm_replace_memslot(kvm, old, invalid_slot); /* * Activate the slot that is now marked INVALID, but don't propagate * the slot to the now inactive slots. The slot is either going to be * deleted or recreated as a new slot. */ kvm_swap_active_memslots(kvm, old->as_id); /* * From this point no new shadow pages pointing to a deleted, or moved, * memslot will be created. Validation of sp->gfn happens in: * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, old); kvm_arch_guest_memory_reclaimed(kvm); /* Was released by kvm_swap_active_memslots(), reacquire. */ mutex_lock(&kvm->slots_arch_lock); /* * Copy the arch-specific field of the newly-installed slot back to the * old slot as the arch data could have changed between releasing * slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock * above. Writers are required to retrieve memslots *after* acquiring * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. */ old->arch = invalid_slot->arch; } static void kvm_create_memslot(struct kvm *kvm, struct kvm_memory_slot *new) { /* Add the new memslot to the inactive set and activate. */ kvm_replace_memslot(kvm, NULL, new); kvm_activate_memslot(kvm, NULL, new); } static void kvm_delete_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *invalid_slot) { /* * Remove the old memslot (in the inactive memslots) by passing NULL as * the "new" slot, and for the invalid version in the active slots. */ kvm_replace_memslot(kvm, old, NULL); kvm_activate_memslot(kvm, invalid_slot, NULL); } static void kvm_move_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, struct kvm_memory_slot *invalid_slot) { /* * Replace the old memslot in the inactive slots, and then swap slots * and replace the current INVALID with the new as well. */ kvm_replace_memslot(kvm, old, new); kvm_activate_memslot(kvm, invalid_slot, new); } static void kvm_update_flags_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { /* * Similar to the MOVE case, but the slot doesn't need to be zapped as * an intermediate step. Instead, the old memslot is simply replaced * with a new, updated copy in both memslot sets. */ kvm_replace_memslot(kvm, old, new); kvm_activate_memslot(kvm, old, new); } static int kvm_set_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { struct kvm_memory_slot *invalid_slot; int r; /* * Released in kvm_swap_active_memslots(). * * Must be held from before the current memslots are copied until after * the new memslots are installed with rcu_assign_pointer, then * released before the synchronize srcu in kvm_swap_active_memslots(). * * When modifying memslots outside of the slots_lock, must be held * before reading the pointer to the current memslots until after all * changes to those memslots are complete. * * These rules ensure that installing new memslots does not lose * changes made to the previous memslots. */ mutex_lock(&kvm->slots_arch_lock); /* * Invalidate the old slot if it's being deleted or moved. This is * done prior to actually deleting/moving the memslot to allow vCPUs to * continue running by ensuring there are no mappings or shadow pages * for the memslot when it is deleted/moved. Without pre-invalidation * (and without a lock), a window would exist between effecting the * delete/move and committing the changes in arch code where KVM or a * guest could access a non-existent memslot. * * Modifications are done on a temporary, unreachable slot. The old * slot needs to be preserved in case a later step fails and the * invalidation needs to be reverted. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); if (!invalid_slot) { mutex_unlock(&kvm->slots_arch_lock); return -ENOMEM; } kvm_invalidate_memslot(kvm, old, invalid_slot); } r = kvm_prepare_memory_region(kvm, old, new, change); if (r) { /* * For DELETE/MOVE, revert the above INVALID change. No * modifications required since the original slot was preserved * in the inactive slots. Changing the active memslots also * release slots_arch_lock. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { kvm_activate_memslot(kvm, invalid_slot, old); kfree(invalid_slot); } else { mutex_unlock(&kvm->slots_arch_lock); } return r; } /* * For DELETE and MOVE, the working slot is now active as the INVALID * version of the old slot. MOVE is particularly special as it reuses * the old slot and returns a copy of the old slot (in working_slot). * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the * old slot is detached but otherwise preserved. */ if (change == KVM_MR_CREATE) kvm_create_memslot(kvm, new); else if (change == KVM_MR_DELETE) kvm_delete_memslot(kvm, old, invalid_slot); else if (change == KVM_MR_MOVE) kvm_move_memslot(kvm, old, new, invalid_slot); else if (change == KVM_MR_FLAGS_ONLY) kvm_update_flags_memslot(kvm, old, new); else BUG(); /* Free the temporary INVALID slot used for DELETE and MOVE. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) kfree(invalid_slot); /* * No need to refresh new->arch, changes after dropping slots_arch_lock * will directly hit the final, active memslot. Architectures are * responsible for knowing that new->arch may be stale. */ kvm_commit_memory_region(kvm, old, new, change); return 0; } static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, gfn_t start, gfn_t end) { struct kvm_memslot_iter iter; kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { if (iter.slot->id != id) return true; } return false; } static int kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { struct kvm_memory_slot *old, *new; struct kvm_memslots *slots; enum kvm_mr_change change; unsigned long npages; gfn_t base_gfn; int as_id, id; int r; lockdep_assert_held(&kvm->slots_lock); r = check_memory_region_flags(kvm, mem); if (r) return r; as_id = mem->slot >> 16; id = (u16)mem->slot; /* General sanity checks */ if ((mem->memory_size & (PAGE_SIZE - 1)) || (mem->memory_size != (unsigned long)mem->memory_size)) return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; if (mem->flags & KVM_MEM_GUEST_MEMFD && (mem->guest_memfd_offset & (PAGE_SIZE - 1) || mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset)) return -EINVAL; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM) return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; /* * The size of userspace-defined memory regions is restricted in order * to play nice with dirty bitmap operations, which are indexed with an * "unsigned int". KVM's internal memory regions don't support dirty * logging, and so are exempt. */ if (id < KVM_USER_MEM_SLOTS && (mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) return -EINVAL; slots = __kvm_memslots(kvm, as_id); /* * Note, the old memslot (and the pointer itself!) may be invalidated * and/or destroyed by kvm_set_memslot(). */ old = id_to_memslot(slots, id); if (!mem->memory_size) { if (!old || !old->npages) return -EINVAL; if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) return -EIO; return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); } base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); npages = (mem->memory_size >> PAGE_SHIFT); if (!old || !old->npages) { change = KVM_MR_CREATE; /* * To simplify KVM internals, the total number of pages across * all memslots must fit in an unsigned long. */ if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) return -EINVAL; } else { /* Modify an existing slot. */ /* Private memslots are immutable, they can only be deleted. */ if (mem->flags & KVM_MEM_GUEST_MEMFD) return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) return -EINVAL; if (base_gfn != old->base_gfn) change = KVM_MR_MOVE; else if (mem->flags != old->flags) change = KVM_MR_FLAGS_ONLY; else /* Nothing to change. */ return 0; } if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) return -EEXIST; /* Allocate a slot that will persist in the memslot. */ new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (!new) return -ENOMEM; new->as_id = as_id; new->id = id; new->base_gfn = base_gfn; new->npages = npages; new->flags = mem->flags; new->userspace_addr = mem->userspace_addr; if (mem->flags & KVM_MEM_GUEST_MEMFD) { r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset); if (r) goto out; } r = kvm_set_memslot(kvm, old, new, change); if (r) goto out_unbind; return 0; out_unbind: if (mem->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(new); out: kfree(new); return r; } int kvm_set_internal_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { if (WARN_ON_ONCE(mem->slot < KVM_USER_MEM_SLOTS)) return -EINVAL; if (WARN_ON_ONCE(mem->flags)) return -EINVAL; return kvm_set_memory_region(kvm, mem); } EXPORT_SYMBOL_GPL(kvm_set_internal_memslot); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region2 *mem) { if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; guard(mutex)(&kvm->slots_lock); return kvm_set_memory_region(kvm, mem); } #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT /** * kvm_get_dirty_log - get a snapshot of dirty pages * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * @is_dirty: set to '1' if any dirty pages were found * @memslot: set to the associated memslot, always valid on success */ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot) { struct kvm_memslots *slots; int i, as_id, id; unsigned long n; unsigned long any = 0; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; *memslot = NULL; *is_dirty = 0; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); *memslot = id_to_memslot(slots, id); if (!(*memslot) || !(*memslot)->dirty_bitmap) return -ENOENT; kvm_arch_sync_dirty_log(kvm, *memslot); n = kvm_dirty_bitmap_bytes(*memslot); for (i = 0; !any && i < n/sizeof(long); ++i) any = (*memslot)->dirty_bitmap[i]; if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n)) return -EFAULT; if (any) *is_dirty = 1; return 0; } EXPORT_SYMBOL_GPL(kvm_get_dirty_log); #else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ /** * kvm_get_dirty_log_protect - get a snapshot of dirty pages * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * * We need to keep it in mind that VCPU threads can write to the bitmap * concurrently. So, to avoid losing track of dirty pages we keep the * following order: * * 1. Take a snapshot of the bit and clear it if needed. * 2. Write protect the corresponding page. * 3. Copy the snapshot to the userspace. * 4. Upon return caller flushes TLB's if needed. * * Between 2 and 4, the guest may write to the page using the remaining TLB * entry. This is not a problem because the page is reported dirty using * the snapshot taken before and step 4 ensures that writes done after * exiting to userspace will be logged for the next call. * */ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i, as_id, id; unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; bool flush; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap) return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; kvm_arch_sync_dirty_log(kvm, memslot); n = kvm_dirty_bitmap_bytes(memslot); flush = false; if (kvm->manual_dirty_log_protect) { /* * Unlike kvm_get_dirty_log, we always return false in *flush, * because no flush is needed until KVM_CLEAR_DIRTY_LOG. There * is some code duplication between this function and * kvm_get_dirty_log, but hopefully all architecture * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log * can be eliminated. */ dirty_bitmap_buffer = dirty_bitmap; } else { dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); memset(dirty_bitmap_buffer, 0, n); KVM_MMU_LOCK(kvm); for (i = 0; i < n / sizeof(long); i++) { unsigned long mask; gfn_t offset; if (!dirty_bitmap[i]) continue; flush = true; mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; offset = i * BITS_PER_LONG; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } KVM_MMU_UNLOCK(kvm); } if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) return -EFAULT; return 0; } /** * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot * @kvm: kvm instance * @log: slot id and address to which we copy the log * * Steps 1-4 below provide general overview of dirty page logging. See * kvm_get_dirty_log_protect() function description for additional details. * * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we * always flush the TLB (step 4) even if previous step failed and the dirty * bitmap may be corrupt. Regardless of previous outcome the KVM logging API * does not preclude user space subsequent dirty log read. Flushing TLB ensures * writes will be marked dirty for next log read. * * 1. Take a snapshot of the bit and clear it if needed. * 2. Write protect the corresponding page. * 3. Copy the snapshot to the userspace. * 4. Flush TLB's if needed. */ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { int r; mutex_lock(&kvm->slots_lock); r = kvm_get_dirty_log_protect(kvm, log); mutex_unlock(&kvm->slots_lock); return r; } /** * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address from which to fetch the bitmap of dirty pages */ static int kvm_clear_dirty_log_protect(struct kvm *kvm, struct kvm_clear_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int as_id, id; gfn_t offset; unsigned long i, n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; bool flush; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; if (log->first_page & 63) return -EINVAL; slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap) return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; n = ALIGN(log->num_pages, BITS_PER_LONG) / 8; if (log->first_page > memslot->npages || log->num_pages > memslot->npages - log->first_page || (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) return -EINVAL; kvm_arch_sync_dirty_log(kvm, memslot); flush = false; dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) return -EFAULT; KVM_MMU_LOCK(kvm); for (offset = log->first_page, i = offset / BITS_PER_LONG, n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--; i++, offset += BITS_PER_LONG) { unsigned long mask = *dirty_bitmap_buffer++; atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i]; if (!mask) continue; mask &= atomic_long_fetch_andnot(mask, p); /* * mask contains the bits that really have been cleared. This * never includes any bits beyond the length of the memslot (if * the length is not aligned to 64 pages), therefore it is not * a problem if userspace sets them in log->dirty_bitmap. */ if (mask) { flush = true; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } } KVM_MMU_UNLOCK(kvm); if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); return 0; } static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) { int r; mutex_lock(&kvm->slots_lock); r = kvm_clear_dirty_log_protect(kvm, log); mutex_unlock(&kvm->slots_lock); return r; } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES static u64 kvm_supported_mem_attributes(struct kvm *kvm) { if (!kvm || kvm_arch_has_private_mem(kvm)) return KVM_MEMORY_ATTRIBUTE_PRIVATE; return 0; } /* * Returns true if _all_ gfns in the range [@start, @end) have attributes * such that the bits in @mask match @attrs. */ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long mask, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); unsigned long index; void *entry; mask &= kvm_supported_mem_attributes(kvm); if (attrs & ~mask) return false; if (end == start + 1) return (kvm_get_memory_attributes(kvm, start) & mask) == attrs; guard(rcu)(); if (!attrs) return !xas_find(&xas, end - 1); for (index = start; index < end; index++) { do { entry = xas_next(&xas); } while (xas_retry(&xas, entry)); if (xas.xa_index != index || (xa_to_value(entry) & mask) != attrs) return false; } return true; } static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, struct kvm_mmu_notifier_range *range) { struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; struct kvm_memslot_iter iter; bool found_memslot = false; bool ret = false; int i; gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; /* * If/when KVM supports more attributes beyond private .vs shared, this * _could_ set KVM_FILTER_{SHARED,PRIVATE} appropriately if the entire target * range already has the desired private vs. shared state (it's unclear * if that is a net win). For now, KVM reaches this point if and only * if the private flag is being toggled, i.e. all mappings are in play. */ for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) { slot = iter.slot; gfn_range.slot = slot; gfn_range.start = max(range->start, slot->base_gfn); gfn_range.end = min(range->end, slot->base_gfn + slot->npages); if (gfn_range.start >= gfn_range.end) continue; if (!found_memslot) { found_memslot = true; KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) range->on_lock(kvm); } ret |= range->handler(kvm, &gfn_range); } } if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (found_memslot) KVM_MMU_UNLOCK(kvm); } static bool kvm_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { /* * Unconditionally add the range to the invalidation set, regardless of * whether or not the arch callback actually needs to zap SPTEs. E.g. * if KVM supports RWX attributes in the future and the attributes are * going from R=>RW, zapping isn't strictly necessary. Unconditionally * adding the range allows KVM to require that MMU invalidations add at * least one range between begin() and end(), e.g. allows KVM to detect * bugs where the add() is missed. Relaxing the rule *might* be safe, * but it's not obvious that allowing new mappings while the attributes * are in flux is desirable or worth the complexity. */ kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_arch_pre_set_memory_attributes(kvm, range); } /* Set @attributes for the gfn range [@start, @end). */ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long attributes) { struct kvm_mmu_notifier_range pre_set_range = { .start = start, .end = end, .arg.attributes = attributes, .handler = kvm_pre_set_memory_attributes, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, .may_block = true, }; struct kvm_mmu_notifier_range post_set_range = { .start = start, .end = end, .arg.attributes = attributes, .handler = kvm_arch_post_set_memory_attributes, .on_lock = kvm_mmu_invalidate_end, .may_block = true, }; unsigned long i; void *entry; int r = 0; entry = attributes ? xa_mk_value(attributes) : NULL; mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range as the desired attributes. */ if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) goto out_unlock; /* * Reserve memory ahead of time to avoid having to deal with failures * partway through setting the new attributes. */ for (i = start; i < end; i++) { r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); if (r) goto out_unlock; } kvm_handle_gfn_range(kvm, &pre_set_range); for (i = start; i < end; i++) { r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, GFP_KERNEL_ACCOUNT)); KVM_BUG_ON(r, kvm); } kvm_handle_gfn_range(kvm, &post_set_range); out_unlock: mutex_unlock(&kvm->slots_lock); return r; } static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, struct kvm_memory_attributes *attrs) { gfn_t start, end; /* flags is currently not used. */ if (attrs->flags) return -EINVAL; if (attrs->attributes & ~kvm_supported_mem_attributes(kvm)) return -EINVAL; if (attrs->size == 0 || attrs->address + attrs->size < attrs->address) return -EINVAL; if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size)) return -EINVAL; start = attrs->address >> PAGE_SHIFT; end = (attrs->address + attrs->size) >> PAGE_SHIFT; /* * xarray tracks data using "unsigned long", and as a result so does * KVM. For simplicity, supports generic attributes only on 64-bit * architectures. */ BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long)); return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); } EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); u64 gen = slots->generation; struct kvm_memory_slot *slot; /* * This also protects against using a memslot from a different address space, * since different address spaces have different generation numbers. */ if (unlikely(gen != vcpu->last_used_slot_gen)) { vcpu->last_used_slot = NULL; vcpu->last_used_slot_gen = gen; } slot = try_get_memslot(vcpu->last_used_slot, gfn); if (slot) return slot; /* * Fall back to searching all memslots. We purposely use * search_memslots() instead of __gfn_to_memslot() to avoid * thrashing the VM-wide last_used_slot in kvm_memslots. */ slot = search_memslots(slots, gfn, false); if (slot) { vcpu->last_used_slot = slot; return slot; } return NULL; } bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr, size; size = PAGE_SIZE; addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL); if (kvm_is_error_hva(addr)) return PAGE_SIZE; mmap_read_lock(current->mm); vma = find_vma(current->mm, addr); if (!vma) goto out; size = vma_kernel_pagesize(vma); out: mmap_read_unlock(current->mm); return size; } static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return KVM_HVA_ERR_BAD; if (memslot_is_readonly(slot) && write) return KVM_HVA_ERR_RO_BAD; if (nr_pages) *nr_pages = slot->npages - (gfn - slot->base_gfn); return __gfn_to_hva_memslot(slot, gfn); } static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages) { return __gfn_to_hva_many(slot, gfn, nr_pages, true); } unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return gfn_to_hva_many(slot, gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva_memslot); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva); /* * Return the hva of a @gfn and the R/W attribute if possible. * * @slot: the kvm_memory_slot which contains @gfn * @gfn: the gfn to be translated * @writable: used to return the read/write attribute of the @slot if the hva * is valid and @writable is not NULL */ unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable) { unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); if (!kvm_is_error_hva(hva) && writable) *writable = !memslot_is_readonly(slot); return hva; } unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return gfn_to_hva_memslot_prot(slot, gfn, writable); } unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return gfn_to_hva_memslot_prot(slot, gfn, writable); } static bool kvm_is_ad_tracked_page(struct page *page) { /* * Per page-flags.h, pages tagged PG_reserved "should in general not be * touched (e.g. set dirty) except by its owner". */ return !PageReserved(page); } static void kvm_set_page_dirty(struct page *page) { if (kvm_is_ad_tracked_page(page)) SetPageDirty(page); } static void kvm_set_page_accessed(struct page *page) { if (kvm_is_ad_tracked_page(page)) mark_page_accessed(page); } void kvm_release_page_clean(struct page *page) { if (!page) return; kvm_set_page_accessed(page); put_page(page); } EXPORT_SYMBOL_GPL(kvm_release_page_clean); void kvm_release_page_dirty(struct page *page) { if (!page) return; kvm_set_page_dirty(page); kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); static kvm_pfn_t kvm_resolve_pfn(struct kvm_follow_pfn *kfp, struct page *page, struct follow_pfnmap_args *map, bool writable) { kvm_pfn_t pfn; WARN_ON_ONCE(!!page == !!map); if (kfp->map_writable) *kfp->map_writable = writable; if (map) pfn = map->pfn; else pfn = page_to_pfn(page); *kfp->refcounted_page = page; return pfn; } /* * The fast path to get the writable pfn which will be stored in @pfn, * true indicates success, otherwise false is returned. */ static bool hva_to_pfn_fast(struct kvm_follow_pfn *kfp, kvm_pfn_t *pfn) { struct page *page; bool r; /* * Try the fast-only path when the caller wants to pin/get the page for * writing. If the caller only wants to read the page, KVM must go * down the full, slow path in order to avoid racing an operation that * breaks Copy-on-Write (CoW), e.g. so that KVM doesn't end up pointing * at the old, read-only page while mm/ points at a new, writable page. */ if (!((kfp->flags & FOLL_WRITE) || kfp->map_writable)) return false; if (kfp->pin) r = pin_user_pages_fast(kfp->hva, 1, FOLL_WRITE, &page) == 1; else r = get_user_page_fast_only(kfp->hva, FOLL_WRITE, &page); if (r) { *pfn = kvm_resolve_pfn(kfp, page, NULL, true); return true; } return false; } /* * The slow path to get the pfn of the specified host virtual address, * 1 indicates success, -errno is returned if error is detected. */ static int hva_to_pfn_slow(struct kvm_follow_pfn *kfp, kvm_pfn_t *pfn) { /* * When a VCPU accesses a page that is not mapped into the secondary * MMU, we lookup the page using GUP to map it, so the guest VCPU can * make progress. We always want to honor NUMA hinting faults in that * case, because GUP usage corresponds to memory accesses from the VCPU. * Otherwise, we'd not trigger NUMA hinting faults once a page is * mapped into the secondary MMU and gets accessed by a VCPU. * * Note that get_user_page_fast_only() and FOLL_WRITE for now * implicitly honor NUMA hinting faults and don't need this flag. */ unsigned int flags = FOLL_HWPOISON | FOLL_HONOR_NUMA_FAULT | kfp->flags; struct page *page, *wpage; int npages; if (kfp->pin) npages = pin_user_pages_unlocked(kfp->hva, 1, &page, flags); else npages = get_user_pages_unlocked(kfp->hva, 1, &page, flags); if (npages != 1) return npages; /* * Pinning is mutually exclusive with opportunistically mapping a read * fault as writable, as KVM should never pin pages when mapping memory * into the guest (pinning is only for direct accesses from KVM). */ if (WARN_ON_ONCE(kfp->map_writable && kfp->pin)) goto out; /* map read fault as writable if possible */ if (!(flags & FOLL_WRITE) && kfp->map_writable && get_user_page_fast_only(kfp->hva, FOLL_WRITE, &wpage)) { put_page(page); page = wpage; flags |= FOLL_WRITE; } out: *pfn = kvm_resolve_pfn(kfp, page, NULL, flags & FOLL_WRITE); return npages; } static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) { if (unlikely(!(vma->vm_flags & VM_READ))) return false; if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE)))) return false; return true; } static int hva_to_pfn_remapped(struct vm_area_struct *vma, struct kvm_follow_pfn *kfp, kvm_pfn_t *p_pfn) { struct follow_pfnmap_args args = { .vma = vma, .address = kfp->hva }; bool write_fault = kfp->flags & FOLL_WRITE; int r; /* * Remapped memory cannot be pinned in any meaningful sense. Bail if * the caller wants to pin the page, i.e. access the page outside of * MMU notifier protection, and unsafe umappings are disallowed. */ if (kfp->pin && !allow_unsafe_mappings) return -EINVAL; r = follow_pfnmap_start(&args); if (r) { /* * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does * not call the fault handler, so do it here. */ bool unlocked = false; r = fixup_user_fault(current->mm, kfp->hva, (write_fault ? FAULT_FLAG_WRITE : 0), &unlocked); if (unlocked) return -EAGAIN; if (r) return r; r = follow_pfnmap_start(&args); if (r) return r; } if (write_fault && !args.writable) { *p_pfn = KVM_PFN_ERR_RO_FAULT; goto out; } *p_pfn = kvm_resolve_pfn(kfp, NULL, &args, args.writable); out: follow_pfnmap_end(&args); return r; } kvm_pfn_t hva_to_pfn(struct kvm_follow_pfn *kfp) { struct vm_area_struct *vma; kvm_pfn_t pfn; int npages, r; might_sleep(); if (WARN_ON_ONCE(!kfp->refcounted_page)) return KVM_PFN_ERR_FAULT; if (hva_to_pfn_fast(kfp, &pfn)) return pfn; npages = hva_to_pfn_slow(kfp, &pfn); if (npages == 1) return pfn; if (npages == -EINTR || npages == -EAGAIN) return KVM_PFN_ERR_SIGPENDING; if (npages == -EHWPOISON) return KVM_PFN_ERR_HWPOISON; mmap_read_lock(current->mm); retry: vma = vma_lookup(current->mm, kfp->hva); if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { r = hva_to_pfn_remapped(vma, kfp, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) pfn = KVM_PFN_ERR_FAULT; } else { if ((kfp->flags & FOLL_NOWAIT) && vma_is_valid(vma, kfp->flags & FOLL_WRITE)) pfn = KVM_PFN_ERR_NEEDS_IO; else pfn = KVM_PFN_ERR_FAULT; } mmap_read_unlock(current->mm); return pfn; } static kvm_pfn_t kvm_follow_pfn(struct kvm_follow_pfn *kfp) { kfp->hva = __gfn_to_hva_many(kfp->slot, kfp->gfn, NULL, kfp->flags & FOLL_WRITE); if (kfp->hva == KVM_HVA_ERR_RO_BAD) return KVM_PFN_ERR_RO_FAULT; if (kvm_is_error_hva(kfp->hva)) return KVM_PFN_NOSLOT; if (memslot_is_readonly(kfp->slot) && kfp->map_writable) { *kfp->map_writable = false; kfp->map_writable = NULL; } return hva_to_pfn(kfp); } kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, unsigned int foll, bool *writable, struct page **refcounted_page) { struct kvm_follow_pfn kfp = { .slot = slot, .gfn = gfn, .flags = foll, .map_writable = writable, .refcounted_page = refcounted_page, }; if (WARN_ON_ONCE(!writable || !refcounted_page)) return KVM_PFN_ERR_FAULT; *writable = false; *refcounted_page = NULL; return kvm_follow_pfn(&kfp); } EXPORT_SYMBOL_GPL(__kvm_faultin_pfn); int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages) { unsigned long addr; gfn_t entry = 0; addr = gfn_to_hva_many(slot, gfn, &entry); if (kvm_is_error_hva(addr)) return -1; if (entry < nr_pages) return 0; return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages); } EXPORT_SYMBOL_GPL(kvm_prefetch_pages); /* * Don't use this API unless you are absolutely, positively certain that KVM * needs to get a struct page, e.g. to pin the page for firmware DMA. * * FIXME: Users of this API likely need to FOLL_PIN the page, not just elevate * its refcount. */ struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write) { struct page *refcounted_page = NULL; struct kvm_follow_pfn kfp = { .slot = gfn_to_memslot(kvm, gfn), .gfn = gfn, .flags = write ? FOLL_WRITE : 0, .refcounted_page = &refcounted_page, }; (void)kvm_follow_pfn(&kfp); return refcounted_page; } EXPORT_SYMBOL_GPL(__gfn_to_page); int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, bool writable) { struct kvm_follow_pfn kfp = { .slot = gfn_to_memslot(vcpu->kvm, gfn), .gfn = gfn, .flags = writable ? FOLL_WRITE : 0, .refcounted_page = &map->pinned_page, .pin = true, }; map->pinned_page = NULL; map->page = NULL; map->hva = NULL; map->gfn = gfn; map->writable = writable; map->pfn = kvm_follow_pfn(&kfp); if (is_error_noslot_pfn(map->pfn)) return -EINVAL; if (pfn_valid(map->pfn)) { map->page = pfn_to_page(map->pfn); map->hva = kmap(map->page); #ifdef CONFIG_HAS_IOMEM } else { map->hva = memremap(pfn_to_hpa(map->pfn), PAGE_SIZE, MEMREMAP_WB); #endif } return map->hva ? 0 : -EFAULT; } EXPORT_SYMBOL_GPL(__kvm_vcpu_map); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map) { if (!map->hva) return; if (map->page) kunmap(map->page); #ifdef CONFIG_HAS_IOMEM else memunmap(map->hva); #endif if (map->writable) kvm_vcpu_mark_page_dirty(vcpu, map->gfn); if (map->pinned_page) { if (map->writable) kvm_set_page_dirty(map->pinned_page); kvm_set_page_accessed(map->pinned_page); unpin_user_page(map->pinned_page); } map->hva = NULL; map->page = NULL; map->pinned_page = NULL; } EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) return PAGE_SIZE - offset; else return len; } /* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, int len) { int r; unsigned long addr; if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) return -EFAULT; addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return __kvm_read_guest_page(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_page); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, int len) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return __kvm_read_guest_page(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_read_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest); static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, unsigned long len) { int r; unsigned long addr; if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) return -EFAULT; addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; return 0; } int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); int offset = offset_in_page(gpa); return __kvm_read_guest_atomic(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); /* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */ static int __kvm_write_guest_page(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn, const void *data, int offset, int len) { int r; unsigned long addr; if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) return -EFAULT; addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; mark_page_dirty_in_slot(kvm, memslot, gfn); return 0; } int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_page); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest); static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { int offset = offset_in_page(gpa); gfn_t start_gfn = gpa >> PAGE_SHIFT; gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; gfn_t nr_pages_needed = end_gfn - start_gfn + 1; gfn_t nr_pages_avail; /* Update ghc->generation before performing any error checks. */ ghc->generation = slots->generation; if (start_gfn > end_gfn) { ghc->hva = KVM_HVA_ERR_BAD; return -EINVAL; } /* * If the requested region crosses two memslots, we still * verify that the entire region is valid here. */ for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) { ghc->memslot = __gfn_to_memslot(slots, start_gfn); ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); if (kvm_is_error_hva(ghc->hva)) return -EFAULT; } /* Use the slow path for cross page reads and writes. */ if (nr_pages_needed == 1) ghc->hva += offset; else ghc->memslot = NULL; ghc->gpa = gpa; ghc->len = len; return 0; } int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len); } EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; gpa_t gpa = ghc->gpa + offset; if (WARN_ON_ONCE(len + offset > ghc->len)) return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) return -EFAULT; } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; if (unlikely(!ghc->memslot)) return kvm_write_guest(kvm, gpa, data, len); r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT); return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_cached); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; gpa_t gpa = ghc->gpa + offset; if (WARN_ON_ONCE(len + offset > ghc->len)) return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) return -EFAULT; } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; if (unlikely(!ghc->memslot)) return kvm_read_guest(kvm, gpa, data, len); r = __copy_from_user(data, (void __user *)ghc->hva + offset, len); if (r) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_cached); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) { const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); #ifdef CONFIG_HAVE_KVM_DIRTY_RING if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm)) return; WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm)); #endif if (memslot && kvm_slot_dirty_track_enabled(memslot)) { unsigned long rel_gfn = gfn - memslot->base_gfn; u32 slot = (memslot->as_id << 16) | memslot->id; if (kvm->dirty_ring_size && vcpu) kvm_dirty_ring_push(vcpu, slot, rel_gfn); else if (memslot->dirty_bitmap) set_bit_le(rel_gfn, memslot->dirty_bitmap); } } EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = gfn_to_memslot(kvm, gfn); mark_page_dirty_in_slot(kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(mark_page_dirty); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); void kvm_sigset_activate(struct kvm_vcpu *vcpu) { if (!vcpu->sigset_active) return; /* * This does a lockless modification of ->real_blocked, which is fine * because, only current can change ->real_blocked and all readers of * ->real_blocked don't care as long ->real_blocked is always a subset * of ->blocked. */ sigprocmask(SIG_SETMASK, &vcpu->sigset, ¤t->real_blocked); } void kvm_sigset_deactivate(struct kvm_vcpu *vcpu) { if (!vcpu->sigset_active) return; sigprocmask(SIG_SETMASK, ¤t->real_blocked, NULL); sigemptyset(¤t->real_blocked); } static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) { unsigned int old, val, grow, grow_start; old = val = vcpu->halt_poll_ns; grow_start = READ_ONCE(halt_poll_ns_grow_start); grow = READ_ONCE(halt_poll_ns_grow); if (!grow) goto out; val *= grow; if (val < grow_start) val = grow_start; vcpu->halt_poll_ns = val; out: trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; if (val < grow_start) val = 0; vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) { int ret = -EINTR; int idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_arch_vcpu_runnable(vcpu)) goto out; if (kvm_cpu_has_pending_timer(vcpu)) goto out; if (signal_pending(current)) goto out; if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) goto out; ret = 0; out: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } /* * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is * pending. This is mostly used when halting a vCPU, but may also be used * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. */ bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool waited = false; vcpu->stat.generic.blocking = 1; preempt_disable(); kvm_arch_vcpu_blocking(vcpu); prepare_to_rcuwait(wait); preempt_enable(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; waited = true; schedule(); } preempt_disable(); finish_rcuwait(wait); kvm_arch_vcpu_unblocking(vcpu); preempt_enable(); vcpu->stat.generic.blocking = 0; return waited; } static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, ktime_t end, bool success) { struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic; u64 poll_ns = ktime_to_ns(ktime_sub(end, start)); ++vcpu->stat.generic.halt_attempted_poll; if (success) { ++vcpu->stat.generic.halt_successful_poll; if (!vcpu_valid_wakeup(vcpu)) ++vcpu->stat.generic.halt_poll_invalid; stats->halt_poll_success_ns += poll_ns; KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns); } else { stats->halt_poll_fail_ns += poll_ns; KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns); } } static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; if (kvm->override_halt_poll_ns) { /* * Ensure kvm->max_halt_poll_ns is not read before * kvm->override_halt_poll_ns. * * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL. */ smp_rmb(); return READ_ONCE(kvm->max_halt_poll_ns); } return READ_ONCE(halt_poll_ns); } /* * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt * polling is enabled, busy wait for a short time before blocking to avoid the * expensive block+unblock sequence if a wake event arrives soon after the vCPU * is halted. */ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); ktime_t start, cur, poll_end; bool waited = false; bool do_halt_poll; u64 halt_ns; if (vcpu->halt_poll_ns > max_halt_poll_ns) vcpu->halt_poll_ns = max_halt_poll_ns; do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; start = cur = poll_end = ktime_get(); if (do_halt_poll) { ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); do { if (kvm_vcpu_check_block(vcpu) < 0) goto out; cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); } waited = kvm_vcpu_block(vcpu); cur = ktime_get(); if (waited) { vcpu->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(poll_end); KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist, ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: /* The total time the vCPU was "halted", including polling time. */ halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); /* * Note, halt-polling is considered successful so long as the vCPU was * never actually scheduled out, i.e. even if the wake event arrived * after of the halt-polling loop itself, but before the full wait. */ if (do_halt_poll) update_halt_poll_stats(vcpu, start, poll_end, !waited); if (halt_poll_allowed) { /* Recompute the max halt poll time in case it changed. */ max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); } else if (max_halt_poll_ns) { if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && halt_ns > max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ else if (vcpu->halt_poll_ns < max_halt_poll_ns && halt_ns < max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.generic.halt_wakeup; return true; } return false; } EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); #ifndef CONFIG_S390 /* * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; me = get_cpu(); /* * The only state change done outside the vcpu mutex is IN_GUEST_MODE * to EXITING_GUEST_MODE. Therefore the moderately expensive "should * kick" check does not need atomic operations if kvm_vcpu_kick is used * within the vCPU thread itself. */ if (vcpu == __this_cpu_read(kvm_running_vcpu)) { if (vcpu->mode == IN_GUEST_MODE) WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE); goto out; } /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_arch_vcpu_should_kick(), which could result in sending an * IPI to the previous pCPU. But, that's ok because the purpose of the * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the * vCPU also requires it to leave IN_GUEST_MODE. */ if (kvm_arch_vcpu_should_kick(vcpu)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); } out: put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); #endif /* !CONFIG_S390 */ int kvm_vcpu_yield_to(struct kvm_vcpu *target) { struct task_struct *task = NULL; int ret; if (!read_trylock(&target->pid_lock)) return 0; if (target->pid) task = get_pid_task(target->pid, PIDTYPE_PID); read_unlock(&target->pid_lock); if (!task) return 0; ret = yield_to(task, 1); put_task_struct(task); return ret; } EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); /* * Helper that checks whether a VCPU is eligible for directed yield. * Most eligible candidate to yield is decided by following heuristics: * * (a) VCPU which has not done pl-exit or cpu relax intercepted recently * (preempted lock holder), indicated by @in_spin_loop. * Set at the beginning and cleared at the end of interception/PLE handler. * * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get * chance last time (mostly it has become eligible now since we have probably * yielded to lockholder in last iteration. This is done by toggling * @dy_eligible each time a VCPU checked for eligibility.) * * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding * to preempted lock-holder could result in wrong VCPU selection and CPU * burning. Giving priority for a potential lock-holder increases lock * progress. * * Since algorithm is based on heuristics, accessing another VCPU data without * locking does not harm. It may result in trying to yield to same VCPU, fail * and continue with next VCPU and so on. */ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) { #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT bool eligible; eligible = !vcpu->spin_loop.in_spin_loop || vcpu->spin_loop.dy_eligible; if (vcpu->spin_loop.in_spin_loop) kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible); return eligible; #else return true; #endif } /* * Unlike kvm_arch_vcpu_runnable, this function is called outside * a vcpu_load/vcpu_put pair. However, for most architectures * kvm_arch_vcpu_runnable does not require vcpu_load. */ bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { return kvm_arch_vcpu_runnable(vcpu); } static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) { if (kvm_arch_dy_runnable(vcpu)) return true; #ifdef CONFIG_KVM_ASYNC_PF if (!list_empty_careful(&vcpu->async_pf.done)) return true; #endif return false; } /* * By default, simply query the target vCPU's current mode when checking if a * vCPU was preempted in kernel mode. All architectures except x86 (or more * specifical, except VMX) allow querying whether or not a vCPU is in kernel * mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel() * directly for cross-vCPU checks is functionally correct and accurate. */ bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) { return kvm_arch_vcpu_in_kernel(vcpu); } bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; } void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { int nr_vcpus, start, i, idx, yielded; struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int try = 3; nr_vcpus = atomic_read(&kvm->online_vcpus); if (nr_vcpus < 2) return; /* Pairs with the smp_wmb() in kvm_vm_ioctl_create_vcpu(). */ smp_rmb(); kvm_vcpu_set_in_spin_loop(me, true); /* * The current vCPU ("me") is spinning in kernel mode, i.e. is likely * waiting for a resource to become available. Attempt to yield to a * vCPU that is runnable, but not currently running, e.g. because the * vCPU was preempted by a higher priority task. With luck, the vCPU * that was preempted is holding a lock or some other resource that the * current vCPU is waiting to acquire, and yielding to the other vCPU * will allow it to make forward progress and release the lock (or kick * the spinning vCPU, etc). * * Since KVM has no insight into what exactly the guest is doing, * approximate a round-robin selection by iterating over all vCPUs, * starting at the last boosted vCPU. I.e. if N=kvm->last_boosted_vcpu, * iterate over vCPU[N+1]..vCPU[N-1], wrapping as needed. * * Note, this is inherently racy, e.g. if multiple vCPUs are spinning, * they may all try to yield to the same vCPU(s). But as above, this * is all best effort due to KVM's lack of visibility into the guest. */ start = READ_ONCE(kvm->last_boosted_vcpu) + 1; for (i = 0; i < nr_vcpus; i++) { idx = (start + i) % nr_vcpus; if (idx == me->vcpu_idx) continue; vcpu = xa_load(&kvm->vcpu_array, idx); if (!READ_ONCE(vcpu->ready)) continue; if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; /* * Treat the target vCPU as being in-kernel if it has a pending * interrupt, as the vCPU trying to yield may be spinning * waiting on IPI delivery, i.e. the target vCPU is in-kernel * for the purposes of directed yield. */ if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && !kvm_arch_vcpu_preempted_in_kernel(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0 && !--try) { break; } } kvm_vcpu_set_in_spin_loop(me, false); /* Ensure vcpu is not eligible during next spinloop */ kvm_vcpu_set_dy_eligible(me, false); } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { #ifdef CONFIG_HAVE_KVM_DIRTY_RING return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + kvm->dirty_ring_size / PAGE_SIZE); #else return false; #endif } static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; struct page *page; if (vmf->pgoff == 0) page = virt_to_page(vcpu->run); #ifdef CONFIG_X86 else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET) page = virt_to_page(vcpu->arch.pio_data); #endif #ifdef CONFIG_KVM_MMIO else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff)) page = kvm_dirty_ring_get_page( &vcpu->dirty_ring, vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET); else return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct kvm_vcpu_vm_ops = { .fault = kvm_vcpu_fault, }; static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { struct kvm_vcpu *vcpu = file->private_data; unsigned long pages = vma_pages(vma); if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED))) return -EINVAL; vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, .llseek = noop_llseek, KVM_COMPAT(kvm_vcpu_compat_ioctl), }; /* * Allocates an inode for the vcpu. */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { char name[8 + 1 + ITOA_MAX_LEN + 1]; snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id); return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS static int vcpu_get_pid(void *data, u64 *val) { struct kvm_vcpu *vcpu = data; read_lock(&vcpu->pid_lock); *val = pid_nr(vcpu->pid); read_unlock(&vcpu->pid_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n"); static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { struct dentry *debugfs_dentry; char dir_name[ITOA_MAX_LEN * 2]; if (!debugfs_initialized()) return; snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); debugfs_dentry = debugfs_create_dir(dir_name, vcpu->kvm->debugfs_dentry); debugfs_create_file("pid", 0444, debugfs_dentry, vcpu, &vcpu_get_pid_fops); kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry); } #endif /* * Creates some virtual cpus. Good luck creating more than one. */ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) { int r; struct kvm_vcpu *vcpu; struct page *page; /* * KVM tracks vCPU IDs as 'int', be kind to userspace and reject * too-large values instead of silently truncating. * * Ensure KVM_MAX_VCPU_IDS isn't pushed above INT_MAX without first * changing the storage type (at the very least, IDs should be tracked * as unsigned ints). */ BUILD_BUG_ON(KVM_MAX_VCPU_IDS > INT_MAX); if (id >= KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&kvm->lock); if (kvm->created_vcpus >= kvm->max_vcpus) { mutex_unlock(&kvm->lock); return -EINVAL; } r = kvm_arch_vcpu_precreate(kvm, id); if (r) { mutex_unlock(&kvm->lock); return r; } kvm->created_vcpus++; mutex_unlock(&kvm->lock); vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vcpu) { r = -ENOMEM; goto vcpu_decrement; } BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) { r = -ENOMEM; goto vcpu_free; } vcpu->run = page_address(page); kvm_vcpu_init(vcpu, kvm, id); r = kvm_arch_vcpu_create(vcpu); if (r) goto vcpu_free_run_page; if (kvm->dirty_ring_size) { r = kvm_dirty_ring_alloc(&vcpu->dirty_ring, id, kvm->dirty_ring_size); if (r) goto arch_vcpu_destroy; } mutex_lock(&kvm->lock); if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; goto unlock_vcpu_destroy; } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); WARN_ON_ONCE(r == -EBUSY); if (r) goto unlock_vcpu_destroy; /* * Now it's all set up, let userspace reach it. Grab the vCPU's mutex * so that userspace can't invoke vCPU ioctl()s until the vCPU is fully * visible (per online_vcpus), e.g. so that KVM doesn't get tricked * into a NULL-pointer dereference because KVM thinks the _current_ * vCPU doesn't exist. As a bonus, taking vcpu->mutex ensures lockdep * knows it's taken *inside* kvm->lock. */ mutex_lock(&vcpu->mutex); kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) goto kvm_put_xa_erase; /* * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); mutex_unlock(&vcpu->mutex); mutex_unlock(&kvm->lock); kvm_arch_vcpu_postcreate(vcpu); kvm_create_vcpu_debugfs(vcpu); return r; kvm_put_xa_erase: mutex_unlock(&vcpu->mutex); kvm_put_kvm_no_destroy(kvm); xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); arch_vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); vcpu_free_run_page: free_page((unsigned long)vcpu->run); vcpu_free: kmem_cache_free(kvm_vcpu_cache, vcpu); vcpu_decrement: mutex_lock(&kvm->lock); kvm->created_vcpus--; mutex_unlock(&kvm->lock); return r; } static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) { if (sigset) { sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP)); vcpu->sigset_active = 1; vcpu->sigset = *sigset; } else vcpu->sigset_active = 0; return 0; } static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset) { struct kvm_vcpu *vcpu = file->private_data; return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header, &kvm_vcpu_stats_desc[0], &vcpu->stat, sizeof(vcpu->stat), user_buffer, size, offset); } static int kvm_vcpu_stats_release(struct inode *inode, struct file *file) { struct kvm_vcpu *vcpu = file->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static const struct file_operations kvm_vcpu_stats_fops = { .owner = THIS_MODULE, .read = kvm_vcpu_stats_read, .release = kvm_vcpu_stats_release, .llseek = noop_llseek, }; static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) { int fd; struct file *file; char name[15 + ITOA_MAX_LEN + 1]; snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile_fmode(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY, FMODE_PREAD); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } kvm_get_kvm(vcpu->kvm); fd_install(fd, file); return fd; } #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range) { int idx; long r; u64 full_size; if (range->flags) return -EINVAL; if (!PAGE_ALIGNED(range->gpa) || !PAGE_ALIGNED(range->size) || range->gpa + range->size <= range->gpa) return -EINVAL; vcpu_load(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); full_size = range->size; do { if (signal_pending(current)) { r = -EINTR; break; } r = kvm_arch_vcpu_pre_fault_memory(vcpu, range); if (WARN_ON_ONCE(r == 0 || r == -EIO)) break; if (r < 0) break; range->size -= r; range->gpa += r; cond_resched(); } while (range->size); srcu_read_unlock(&vcpu->kvm->srcu, idx); vcpu_put(vcpu); /* Return success if at least one page was mapped successfully. */ return full_size == range->size ? r : 0; } #endif static int kvm_wait_for_vcpu_online(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; /* * In practice, this happy path will always be taken, as a well-behaved * VMM will never invoke a vCPU ioctl() before KVM_CREATE_VCPU returns. */ if (likely(vcpu->vcpu_idx < atomic_read(&kvm->online_vcpus))) return 0; /* * Acquire and release the vCPU's mutex to wait for vCPU creation to * complete (kvm_vm_ioctl_create_vcpu() holds the mutex until the vCPU * is fully online). */ if (mutex_lock_killable(&vcpu->mutex)) return -EINTR; mutex_unlock(&vcpu->mutex); if (WARN_ON_ONCE(!kvm_get_vcpu(kvm, vcpu->vcpu_idx))) return -EIO; return 0; } static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) return -EINVAL; /* * Wait for the vCPU to be online before handling the ioctl(), as KVM * assumes the vCPU is reachable via vcpu_array, i.e. may dereference * a NULL pointer if userspace invokes an ioctl() before KVM is ready. */ r = kvm_wait_for_vcpu_online(vcpu); if (r) return r; /* * Some architectures have vcpu ioctls that are asynchronous to vcpu * execution; mutex_lock() would break them. */ r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg); if (r != -ENOIOCTLCMD) return r; if (mutex_lock_killable(&vcpu->mutex)) return -EINTR; switch (ioctl) { case KVM_RUN: { struct pid *oldpid; r = -EINVAL; if (arg) goto out; /* * Note, vcpu->pid is primarily protected by vcpu->mutex. The * dedicated r/w lock allows other tasks, e.g. other vCPUs, to * read vcpu->pid while this vCPU is in KVM_RUN, e.g. to yield * directly to this vCPU */ oldpid = vcpu->pid; if (unlikely(oldpid != task_pid(current))) { /* The thread running this VCPU changed. */ struct pid *newpid; r = kvm_arch_vcpu_run_pid_change(vcpu); if (r) break; newpid = get_task_pid(current, PIDTYPE_PID); write_lock(&vcpu->pid_lock); vcpu->pid = newpid; write_unlock(&vcpu->pid_lock); put_pid(oldpid); } vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe); r = kvm_arch_vcpu_ioctl_run(vcpu); vcpu->wants_to_run = false; trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; } case KVM_GET_REGS: { struct kvm_regs *kvm_regs; r = -ENOMEM; kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); if (!kvm_regs) goto out; r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs); if (r) goto out_free1; r = -EFAULT; if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs))) goto out_free1; r = 0; out_free1: kfree(kvm_regs); break; } case KVM_SET_REGS: { struct kvm_regs *kvm_regs; kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); if (IS_ERR(kvm_regs)) { r = PTR_ERR(kvm_regs); goto out; } r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs); kfree(kvm_regs); break; } case KVM_GET_SREGS: { kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL); r = -ENOMEM; if (!kvm_sregs) goto out; r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs))) goto out; r = 0; break; } case KVM_SET_SREGS: { kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs)); if (IS_ERR(kvm_sregs)) { r = PTR_ERR(kvm_sregs); kvm_sregs = NULL; goto out; } r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs); break; } case KVM_GET_MP_STATE: { struct kvm_mp_state mp_state; r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &mp_state, sizeof(mp_state))) goto out; r = 0; break; } case KVM_SET_MP_STATE: { struct kvm_mp_state mp_state; r = -EFAULT; if (copy_from_user(&mp_state, argp, sizeof(mp_state))) goto out; r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state); break; } case KVM_TRANSLATE: { struct kvm_translation tr; r = -EFAULT; if (copy_from_user(&tr, argp, sizeof(tr))) goto out; r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &tr, sizeof(tr))) goto out; r = 0; break; } case KVM_SET_GUEST_DEBUG: { struct kvm_guest_debug dbg; r = -EFAULT; if (copy_from_user(&dbg, argp, sizeof(dbg))) goto out; r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); break; } case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset, *p; p = NULL; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof(kvm_sigmask))) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof(sigset)) goto out; r = -EFAULT; if (copy_from_user(&sigset, sigmask_arg->sigset, sizeof(sigset))) goto out; p = &sigset; } r = kvm_vcpu_ioctl_set_sigmask(vcpu, p); break; } case KVM_GET_FPU: { fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL); r = -ENOMEM; if (!fpu) goto out; r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu))) goto out; r = 0; break; } case KVM_SET_FPU: { fpu = memdup_user(argp, sizeof(*fpu)); if (IS_ERR(fpu)) { r = PTR_ERR(fpu); fpu = NULL; goto out; } r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); break; } case KVM_GET_STATS_FD: { r = kvm_vcpu_ioctl_get_stats_fd(vcpu); break; } #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY case KVM_PRE_FAULT_MEMORY: { struct kvm_pre_fault_memory range; r = -EFAULT; if (copy_from_user(&range, argp, sizeof(range))) break; r = kvm_vcpu_pre_fault_memory(vcpu, &range); /* Pass back leftover range. */ if (copy_to_user(argp, &range, sizeof(range))) r = -EFAULT; break; } #endif default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: mutex_unlock(&vcpu->mutex); kfree(fpu); kfree(kvm_sregs); return r; } #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = compat_ptr(arg); int r; if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof(kvm_sigmask))) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof(compat_sigset_t)) goto out; r = -EFAULT; if (get_compat_sigset(&sigset, (compat_sigset_t __user *)sigmask_arg->sigset)) goto out; r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); } else r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL); break; } default: r = kvm_vcpu_ioctl(filp, ioctl, arg); } out: return r; } #endif static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma) { struct kvm_device *dev = filp->private_data; if (dev->ops->mmap) return dev->ops->mmap(dev, vma); return -ENODEV; } static int kvm_device_ioctl_attr(struct kvm_device *dev, int (*accessor)(struct kvm_device *dev, struct kvm_device_attr *attr), unsigned long arg) { struct kvm_device_attr attr; if (!accessor) return -EPERM; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) return -EFAULT; return accessor(dev, &attr); } static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_device *dev = filp->private_data; if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); case KVM_GET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg); case KVM_HAS_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg); default: if (dev->ops->ioctl) return dev->ops->ioctl(dev, ioctl, arg); return -ENOTTY; } } static int kvm_device_release(struct inode *inode, struct file *filp) { struct kvm_device *dev = filp->private_data; struct kvm *kvm = dev->kvm; if (dev->ops->release) { mutex_lock(&kvm->lock); list_del_rcu(&dev->vm_node); synchronize_rcu(); dev->ops->release(dev); mutex_unlock(&kvm->lock); } kvm_put_kvm(kvm); return 0; } static struct file_operations kvm_device_fops = { .unlocked_ioctl = kvm_device_ioctl, .release = kvm_device_release, KVM_COMPAT(kvm_device_ioctl), .mmap = kvm_device_mmap, }; struct kvm_device *kvm_device_from_filp(struct file *filp) { if (filp->f_op != &kvm_device_fops) return NULL; return filp->private_data; } static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { #ifdef CONFIG_KVM_MPIC [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, #endif }; int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) { if (type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENOSPC; if (kvm_device_ops_table[type] != NULL) return -EEXIST; kvm_device_ops_table[type] = ops; return 0; } void kvm_unregister_device_ops(u32 type) { if (kvm_device_ops_table[type] != NULL) kvm_device_ops_table[type] = NULL; } static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { const struct kvm_device_ops *ops; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type; int ret; if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENODEV; type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table)); ops = kvm_device_ops_table[type]; if (ops == NULL) return -ENODEV; if (test) return 0; dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; dev->ops = ops; dev->kvm = kvm; mutex_lock(&kvm->lock); ret = ops->create(dev, type); if (ret < 0) { mutex_unlock(&kvm->lock); kfree(dev); return ret; } list_add_rcu(&dev->vm_node, &kvm->devices); mutex_unlock(&kvm->lock); if (ops->init) ops->init(dev); kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del_rcu(&dev->vm_node); synchronize_rcu(); if (ops->release) ops->release(dev); mutex_unlock(&kvm->lock); if (ops->destroy) ops->destroy(dev); return ret; } cd->fd = ret; return 0; } static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: case KVM_CAP_USER_MEMORY2: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: case KVM_CAP_INTERNAL_ERROR_DATA: #ifdef CONFIG_HAVE_KVM_MSI case KVM_CAP_SIGNAL_MSI: #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQFD: #endif case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_HALT_POLL: return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: return KVM_COALESCED_MMIO_PAGE_OFFSET; case KVM_CAP_COALESCED_PIO: return 1; #endif #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: return KVM_DIRTY_LOG_MANUAL_CAPS; #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif #if KVM_MAX_NR_ADDRESS_SPACES > 1 case KVM_CAP_MULTI_ADDRESS_SPACE: if (kvm) return kvm_arch_nr_memslot_as_ids(kvm); return KVM_MAX_NR_ADDRESS_SPACES; #endif case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; case KVM_CAP_DIRTY_LOG_RING: #ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; #endif case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: #ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; #endif #ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: #endif case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: case KVM_CAP_DEVICE_CTRL: return 1; #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_CAP_MEMORY_ATTRIBUTES: return kvm_supported_mem_attributes(kvm); #endif #ifdef CONFIG_KVM_PRIVATE_MEM case KVM_CAP_GUEST_MEMFD: return !kvm || kvm_arch_has_private_mem(kvm); #endif default: break; } return kvm_vm_ioctl_check_extension(kvm, arg); } static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) { int r; if (!KVM_DIRTY_LOG_PAGE_OFFSET) return -EINVAL; /* the size should be power of 2 */ if (!size || (size & (size - 1))) return -EINVAL; /* Should be bigger to keep the reserved entries, or a page */ if (size < kvm_dirty_ring_get_rsvd_entries() * sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE) return -EINVAL; if (size > KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn)) return -E2BIG; /* We only allow it to set once */ if (kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->lock); if (kvm->created_vcpus) { /* We don't allow to change this value after vcpu created */ r = -EINVAL; } else { kvm->dirty_ring_size = size; r = 0; } mutex_unlock(&kvm->lock); return r; } static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; int cleared = 0; if (!kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->slots_lock); kvm_for_each_vcpu(i, vcpu, kvm) cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring); mutex_unlock(&kvm->slots_lock); if (cleared) kvm_flush_remote_tlbs(kvm); return cleared; } int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { return -EINVAL; } bool kvm_are_all_memslots_empty(struct kvm *kvm) { int i; lockdep_assert_held(&kvm->slots_lock); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) return false; } return true; } EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty); static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) { switch (cap->cap) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: { u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE; if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE) allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS; if (cap->flags || (cap->args[0] & ~allowed_options)) return -EINVAL; kvm->manual_dirty_log_protect = cap->args[0]; return 0; } #endif case KVM_CAP_HALT_POLL: { if (cap->flags || cap->args[0] != (unsigned int)cap->args[0]) return -EINVAL; kvm->max_halt_poll_ns = cap->args[0]; /* * Ensure kvm->override_halt_poll_ns does not become visible * before kvm->max_halt_poll_ns. * * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns(). */ smp_wmb(); kvm->override_halt_poll_ns = true; return 0; } case KVM_CAP_DIRTY_LOG_RING: case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) return -EINVAL; return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: { int r = -EINVAL; if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) || !kvm->dirty_ring_size || cap->flags) return r; mutex_lock(&kvm->slots_lock); /* * For simplicity, allow enabling ring+bitmap if and only if * there are no memslots, e.g. to ensure all memslots allocate * a bitmap after the capability is enabled. */ if (kvm_are_all_memslots_empty(kvm)) { kvm->dirty_ring_with_bitmap = true; r = 0; } mutex_unlock(&kvm->slots_lock); return r; } default: return kvm_vm_ioctl_enable_cap(kvm, cap); } } static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset) { struct kvm *kvm = file->private_data; return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header, &kvm_vm_stats_desc[0], &kvm->stat, sizeof(kvm->stat), user_buffer, size, offset); } static int kvm_vm_stats_release(struct inode *inode, struct file *file) { struct kvm *kvm = file->private_data; kvm_put_kvm(kvm); return 0; } static const struct file_operations kvm_vm_stats_fops = { .owner = THIS_MODULE, .read = kvm_vm_stats_read, .release = kvm_vm_stats_release, .llseek = noop_llseek, }; static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) { int fd; struct file *file; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile_fmode("kvm-vm-stats", &kvm_vm_stats_fops, kvm, O_RDONLY, FMODE_PREAD); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } kvm_get_kvm(kvm); fd_install(fd, file); return fd; } #define SANITY_CHECK_MEM_REGION_FIELD(field) \ do { \ BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \ offsetof(struct kvm_userspace_memory_region2, field)); \ BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \ sizeof_field(struct kvm_userspace_memory_region2, field)); \ } while (0) static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r; if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: r = kvm_vm_ioctl_create_vcpu(kvm, arg); break; case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) goto out; r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap); break; } case KVM_SET_USER_MEMORY_REGION2: case KVM_SET_USER_MEMORY_REGION: { struct kvm_userspace_memory_region2 mem; unsigned long size; if (ioctl == KVM_SET_USER_MEMORY_REGION) { /* * Fields beyond struct kvm_userspace_memory_region shouldn't be * accessed, but avoid leaking kernel memory in case of a bug. */ memset(&mem, 0, sizeof(mem)); size = sizeof(struct kvm_userspace_memory_region); } else { size = sizeof(struct kvm_userspace_memory_region2); } /* Ensure the common parts of the two structs are identical. */ SANITY_CHECK_MEM_REGION_FIELD(slot); SANITY_CHECK_MEM_REGION_FIELD(flags); SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr); SANITY_CHECK_MEM_REGION_FIELD(memory_size); SANITY_CHECK_MEM_REGION_FIELD(userspace_addr); r = -EFAULT; if (copy_from_user(&mem, argp, size)) goto out; r = -EINVAL; if (ioctl == KVM_SET_USER_MEMORY_REGION && (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS)) goto out; r = kvm_vm_ioctl_set_memory_region(kvm, &mem); break; } case KVM_GET_DIRTY_LOG: { struct kvm_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { struct kvm_clear_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); break; } #endif #ifdef CONFIG_KVM_MMIO case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); break; } case KVM_UNREGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); break; } #endif case KVM_IRQFD: { struct kvm_irqfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_irqfd(kvm, &data); break; } case KVM_IOEVENTFD: { struct kvm_ioeventfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_ioeventfd(kvm, &data); break; } #ifdef CONFIG_HAVE_KVM_MSI case KVM_SIGNAL_MSI: { struct kvm_msi msi; r = -EFAULT; if (copy_from_user(&msi, argp, sizeof(msi))) goto out; r = kvm_send_userspace_msi(kvm, &msi); break; } #endif #ifdef __KVM_HAVE_IRQ_LINE case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof(irq_event))) goto out; r = kvm_vm_ioctl_irq_line(kvm, &irq_event, ioctl == KVM_IRQ_LINE_STATUS); if (r) goto out; r = -EFAULT; if (ioctl == KVM_IRQ_LINE_STATUS) { if (copy_to_user(argp, &irq_event, sizeof(irq_event))) goto out; } r = 0; break; } #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_SET_GSI_ROUTING: { struct kvm_irq_routing routing; struct kvm_irq_routing __user *urouting; struct kvm_irq_routing_entry *entries = NULL; r = -EFAULT; if (copy_from_user(&routing, argp, sizeof(routing))) goto out; r = -EINVAL; if (!kvm_arch_can_set_irq_routing(kvm)) goto out; if (routing.nr > KVM_MAX_IRQ_ROUTES) goto out; if (routing.flags) goto out; if (routing.nr) { urouting = argp; entries = vmemdup_array_user(urouting->entries, routing.nr, sizeof(*entries)); if (IS_ERR(entries)) { r = PTR_ERR(entries); goto out; } } r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); kvfree(entries); break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_SET_MEMORY_ATTRIBUTES: { struct kvm_memory_attributes attrs; r = -EFAULT; if (copy_from_user(&attrs, argp, sizeof(attrs))) goto out; r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); break; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; r = -EFAULT; if (copy_from_user(&cd, argp, sizeof(cd))) goto out; r = kvm_ioctl_create_device(kvm, &cd); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &cd, sizeof(cd))) goto out; r = 0; break; } case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(kvm, arg); break; case KVM_RESET_DIRTY_RINGS: r = kvm_vm_ioctl_reset_dirty_pages(kvm); break; case KVM_GET_STATS_FD: r = kvm_vm_ioctl_get_stats_fd(kvm); break; #ifdef CONFIG_KVM_PRIVATE_MEM case KVM_CREATE_GUEST_MEMFD: { struct kvm_create_guest_memfd guest_memfd; r = -EFAULT; if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd))) goto out; r = kvm_gmem_create(kvm, &guest_memfd); break; } #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } out: return r; } #ifdef CONFIG_KVM_COMPAT struct compat_kvm_dirty_log { __u32 slot; __u32 padding1; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; struct compat_kvm_clear_dirty_log { __u32 slot; __u32 num_pages; __u64 first_page; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -ENOTTY; } static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; int r; if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); if (r != -ENOTTY) return r; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { struct compat_kvm_clear_dirty_log compat_log; struct kvm_clear_dirty_log log; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) return -EFAULT; log.slot = compat_log.slot; log.num_pages = compat_log.num_pages; log.first_page = compat_log.first_page; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); break; } #endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) return -EFAULT; log.slot = compat_log.slot; log.padding1 = compat_log.padding1; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } default: r = kvm_vm_ioctl(filp, ioctl, arg); } return r; } #endif static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_vm_compat_ioctl), }; bool file_is_kvm(struct file *file) { return file && file->f_op == &kvm_vm_fops; } EXPORT_SYMBOL_GPL(file_is_kvm); static int kvm_dev_ioctl_create_vm(unsigned long type) { char fdname[ITOA_MAX_LEN + 1]; int r, fd; struct kvm *kvm; struct file *file; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; snprintf(fdname, sizeof(fdname), "%d", fd); kvm = kvm_create_vm(type, fdname); if (IS_ERR(kvm)) { r = PTR_ERR(kvm); goto put_fd; } file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { r = PTR_ERR(file); goto put_kvm; } /* * Don't call kvm_put_kvm anymore at this point; file->f_op is * already set, with ->release() being kvm_vm_release(). In error * cases it will be called by the final fput(file) and will take * care of doing kvm_put_kvm(kvm). */ kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); fd_install(fd, file); return fd; put_kvm: kvm_put_kvm(kvm); put_fd: put_unused_fd(fd); return r; } static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { int r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: if (arg) goto out; r = KVM_API_VERSION; break; case KVM_CREATE_VM: r = kvm_dev_ioctl_create_vm(arg); break; case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(NULL, arg); break; case KVM_GET_VCPU_MMAP_SIZE: if (arg) goto out; r = PAGE_SIZE; /* struct kvm_run */ #ifdef CONFIG_X86 r += PAGE_SIZE; /* pio data page */ #endif #ifdef CONFIG_KVM_MMIO r += PAGE_SIZE; /* coalesced mmio ring page */ #endif break; default: return kvm_arch_dev_ioctl(filp, ioctl, arg); } out: return r; } static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_dev_ioctl), }; static struct miscdevice kvm_dev = { KVM_MINOR, "kvm", &kvm_chardev_ops, }; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING static bool enable_virt_at_load = true; module_param(enable_virt_at_load, bool, 0444); __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); static DEFINE_PER_CPU(bool, virtualization_enabled); static DEFINE_MUTEX(kvm_usage_lock); static int kvm_usage_count; __weak void kvm_arch_enable_virtualization(void) { } __weak void kvm_arch_disable_virtualization(void) { } static int kvm_enable_virtualization_cpu(void) { if (__this_cpu_read(virtualization_enabled)) return 0; if (kvm_arch_enable_virtualization_cpu()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; } __this_cpu_write(virtualization_enabled, true); return 0; } static int kvm_online_cpu(unsigned int cpu) { /* * Abort the CPU online process if hardware virtualization cannot * be enabled. Otherwise running VMs would encounter unrecoverable * errors when scheduled to this CPU. */ return kvm_enable_virtualization_cpu(); } static void kvm_disable_virtualization_cpu(void *ign) { if (!__this_cpu_read(virtualization_enabled)) return; kvm_arch_disable_virtualization_cpu(); __this_cpu_write(virtualization_enabled, false); } static int kvm_offline_cpu(unsigned int cpu) { kvm_disable_virtualization_cpu(NULL); return 0; } static void kvm_shutdown(void) { /* * Disable hardware virtualization and set kvm_rebooting to indicate * that KVM has asynchronously disabled hardware virtualization, i.e. * that relevant errors and exceptions aren't entirely unexpected. * Some flavors of hardware virtualization need to be disabled before * transferring control to firmware (to perform shutdown/reboot), e.g. * on x86, virtualization can block INIT interrupts, which are used by * firmware to pull APs back under firmware control. Note, this path * is used for both shutdown and reboot scenarios, i.e. neither name is * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1); } static int kvm_suspend(void) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage * count is stable. Assert that kvm_usage_lock is not held to ensure * the system isn't suspended while KVM is enabling hardware. Hardware * enabling can be preempted, but the task cannot be frozen until it has * dropped all locks (userspace tasks are frozen via a fake signal). */ lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); kvm_disable_virtualization_cpu(NULL); return 0; } static void kvm_resume(void) { lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); WARN_ON_ONCE(kvm_enable_virtualization_cpu()); } static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, .shutdown = kvm_shutdown, }; static int kvm_enable_virtualization(void) { int r; guard(mutex)(&kvm_usage_lock); if (kvm_usage_count++) return 0; kvm_arch_enable_virtualization(); r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", kvm_online_cpu, kvm_offline_cpu); if (r) goto err_cpuhp; register_syscore_ops(&kvm_syscore_ops); /* * Undo virtualization enabling and bail if the system is going down. * If userspace initiated a forced reboot, e.g. reboot -f, then it's * possible for an in-flight operation to enable virtualization after * syscore_shutdown() is called, i.e. without kvm_shutdown() being * invoked. Note, this relies on system_state being set _before_ * kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked * or this CPU observes the impending shutdown. Which is why KVM uses * a syscore ops hook instead of registering a dedicated reboot * notifier (the latter runs before system_state is updated). */ if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART) { r = -EBUSY; goto err_rebooting; } return 0; err_rebooting: unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); err_cpuhp: kvm_arch_disable_virtualization(); --kvm_usage_count; return r; } static void kvm_disable_virtualization(void) { guard(mutex)(&kvm_usage_lock); if (--kvm_usage_count) return; unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); kvm_arch_disable_virtualization(); } static int kvm_init_virtualization(void) { if (enable_virt_at_load) return kvm_enable_virtualization(); return 0; } static void kvm_uninit_virtualization(void) { if (enable_virt_at_load) kvm_disable_virtualization(); } #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int kvm_enable_virtualization(void) { return 0; } static int kvm_init_virtualization(void) { return 0; } static void kvm_disable_virtualization(void) { } static void kvm_uninit_virtualization(void) { } #endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static void kvm_iodevice_destructor(struct kvm_io_device *dev) { if (dev->ops->destructor) dev->ops->destructor(dev); } static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; for (i = 0; i < bus->dev_count; i++) { struct kvm_io_device *pos = bus->range[i].dev; kvm_iodevice_destructor(pos); } kfree(bus); } static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1, const struct kvm_io_range *r2) { gpa_t addr1 = r1->addr; gpa_t addr2 = r2->addr; if (addr1 < addr2) return -1; /* If r2->len == 0, match the exact address. If r2->len != 0, * accept any overlapping write. Any order is acceptable for * overlapping ranges, because kvm_io_bus_get_first_dev ensures * we process all of them. */ if (r2->len) { addr1 += r1->len; addr2 += r2->len; } if (addr1 > addr2) return 1; return 0; } static int kvm_io_bus_sort_cmp(const void *p1, const void *p2) { return kvm_io_bus_cmp(p1, p2); } static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, gpa_t addr, int len) { struct kvm_io_range *range, key; int off; key = (struct kvm_io_range) { .addr = addr, .len = len, }; range = bsearch(&key, bus->range, bus->dev_count, sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp); if (range == NULL) return -ENOENT; off = range - bus->range; while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0) off--; return off; } static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, const void *val) { int idx; idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; } return -EOPNOTSUPP; } /* kvm_io_bus_write - called under kvm->slots_lock */ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { struct kvm_io_bus *bus; struct kvm_io_range range; int r; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_write_cookie - called under kvm->slots_lock */ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie) { struct kvm_io_bus *bus; struct kvm_io_range range; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; /* First try the device referenced by cookie. */ if ((cookie >= 0) && (cookie < bus->dev_count) && (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0)) if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len, val)) return cookie; /* * cookie contained garbage; fall back to search and return the * correct cookie value. */ return __kvm_io_bus_write(vcpu, bus, &range, val); } static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, void *val) { int idx; idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; } return -EOPNOTSUPP; } /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { struct kvm_io_bus *bus; struct kvm_io_range range; int r; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; r = __kvm_io_bus_read(vcpu, bus, &range, val); return r < 0 ? r : 0; } int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) { int i; struct kvm_io_bus *new_bus, *bus; struct kvm_io_range range; lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus) return -ENOMEM; /* exclude ioeventfd which is limited by maximum fd */ if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1), GFP_KERNEL_ACCOUNT); if (!new_bus) return -ENOMEM; range = (struct kvm_io_range) { .addr = addr, .len = len, .dev = dev, }; for (i = 0; i < bus->dev_count; i++) if (kvm_io_bus_cmp(&bus->range[i], &range) > 0) break; memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); new_bus->dev_count++; new_bus->range[i] = range; memcpy(new_bus->range + i + 1, bus->range + i, (bus->dev_count - i) * sizeof(struct kvm_io_range)); rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); return 0; } int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { int i; struct kvm_io_bus *new_bus, *bus; lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus) return 0; for (i = 0; i < bus->dev_count; i++) { if (bus->range[i].dev == dev) { break; } } if (i == bus->dev_count) return 0; new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1), GFP_KERNEL_ACCOUNT); if (new_bus) { memcpy(new_bus, bus, struct_size(bus, range, i)); new_bus->dev_count--; memcpy(new_bus->range + i, bus->range + i + 1, flex_array_size(new_bus, range, new_bus->dev_count - i)); } rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); /* * If NULL bus is installed, destroy the old bus, including all the * attached devices. Otherwise, destroy the caller's device only. */ if (!new_bus) { pr_err("kvm: failed to shrink bus, removing it completely\n"); kvm_io_bus_destroy(bus); return -ENOMEM; } kvm_iodevice_destructor(dev); kfree(bus); return 0; } struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr) { struct kvm_io_bus *bus; int dev_idx, srcu_idx; struct kvm_io_device *iodev = NULL; srcu_idx = srcu_read_lock(&kvm->srcu); bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); if (!bus) goto out_unlock; dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); if (dev_idx < 0) goto out_unlock; iodev = bus->range[dev_idx].dev; out_unlock: srcu_read_unlock(&kvm->srcu, srcu_idx); return iodev; } EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev); static int kvm_debugfs_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { int ret; struct kvm_stat_data *stat_data = inode->i_private; /* * The debugfs files are a reference to the kvm struct which * is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe * avoids the race between open and the removal of the debugfs directory. */ if (!kvm_get_kvm_safe(stat_data->kvm)) return -ENOENT; ret = simple_attr_open(inode, file, get, kvm_stats_debugfs_mode(stat_data->desc) & 0222 ? set : NULL, fmt); if (ret) kvm_put_kvm(stat_data->kvm); return ret; } static int kvm_debugfs_release(struct inode *inode, struct file *file) { struct kvm_stat_data *stat_data = inode->i_private; simple_attr_release(inode, file); kvm_put_kvm(stat_data->kvm); return 0; } static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { *val = *(u64 *)((void *)(&kvm->stat) + offset); return 0; } static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { *(u64 *)((void *)(&kvm->stat) + offset) = 0; return 0; } static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { unsigned long i; struct kvm_vcpu *vcpu; *val = 0; kvm_for_each_vcpu(i, vcpu, kvm) *val += *(u64 *)((void *)(&vcpu->stat) + offset); return 0; } static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) *(u64 *)((void *)(&vcpu->stat) + offset) = 0; return 0; } static int kvm_stat_data_get(void *data, u64 *val) { int r = -EFAULT; struct kvm_stat_data *stat_data = data; switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, stat_data->desc->desc.offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, stat_data->desc->desc.offset, val); break; } return r; } static int kvm_stat_data_clear(void *data, u64 val) { int r = -EFAULT; struct kvm_stat_data *stat_data = data; if (val) return -EINVAL; switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, stat_data->desc->desc.offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, stat_data->desc->desc.offset); break; } return r; } static int kvm_stat_data_open(struct inode *inode, struct file *file) { __simple_attr_check_format("%llu\n", 0ull); return kvm_debugfs_open(inode, file, kvm_stat_data_get, kvm_stat_data_clear, "%llu\n"); } static const struct file_operations stat_fops_per_vm = { .owner = THIS_MODULE, .open = kvm_stat_data_open, .release = kvm_debugfs_release, .read = simple_attr_read, .write = simple_attr_write, }; static int vm_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_get_stat_per_vm(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); return 0; } static int vm_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_clear_stat_per_vm(kvm, offset); } mutex_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n"); static int vcpu_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_get_stat_per_vcpu(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); return 0; } static int vcpu_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_clear_stat_per_vcpu(kvm, offset); } mutex_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n"); static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) { struct kobj_uevent_env *env; unsigned long long created, active; if (!kvm_dev.this_device || !kvm) return; mutex_lock(&kvm_lock); if (type == KVM_EVENT_CREATE_VM) { kvm_createvm_count++; kvm_active_vms++; } else if (type == KVM_EVENT_DESTROY_VM) { kvm_active_vms--; } created = kvm_createvm_count; active = kvm_active_vms; mutex_unlock(&kvm_lock); env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return; add_uevent_var(env, "CREATED=%llu", created); add_uevent_var(env, "COUNT=%llu", active); if (type == KVM_EVENT_CREATE_VM) { add_uevent_var(env, "EVENT=create"); kvm->userspace_pid = task_pid_nr(current); } else if (type == KVM_EVENT_DESTROY_VM) { add_uevent_var(env, "EVENT=destroy"); } add_uevent_var(env, "PID=%d", kvm->userspace_pid); if (!IS_ERR(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); if (p) { tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX); if (!IS_ERR(tmp)) add_uevent_var(env, "STATS_PATH=%s", tmp); kfree(p); } } /* no need for checks, since we are adding at most only 5 keys */ env->envp[env->envp_idx++] = NULL; kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp); kfree(env); } static void kvm_init_debug(void) { const struct file_operations *fops; const struct _kvm_stats_desc *pdesc; int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { pdesc = &kvm_vm_stats_desc[i]; if (kvm_stats_debugfs_mode(pdesc) & 0222) fops = &vm_stat_fops; else fops = &vm_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, (void *)(long)pdesc->desc.offset, fops); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { pdesc = &kvm_vcpu_stats_desc[i]; if (kvm_stats_debugfs_mode(pdesc) & 0222) fops = &vcpu_stat_fops; else fops = &vcpu_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, (void *)(long)pdesc->desc.offset, fops); } } static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) { return container_of(pn, struct kvm_vcpu, preempt_notifier); } static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); WRITE_ONCE(vcpu->preempted, false); WRITE_ONCE(vcpu->ready, false); __this_cpu_write(kvm_running_vcpu, vcpu); kvm_arch_vcpu_load(vcpu, cpu); WRITE_ONCE(vcpu->scheduled_out, false); } static void kvm_sched_out(struct preempt_notifier *pn, struct task_struct *next) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); WRITE_ONCE(vcpu->scheduled_out, true); if (task_is_runnable(current) && vcpu->wants_to_run) { WRITE_ONCE(vcpu->preempted, true); WRITE_ONCE(vcpu->ready, true); } kvm_arch_vcpu_put(vcpu); __this_cpu_write(kvm_running_vcpu, NULL); } /** * kvm_get_running_vcpu - get the vcpu running on the current CPU. * * We can disable preemption locally around accessing the per-CPU variable, * and use the resolved vcpu pointer after enabling preemption again, * because even if the current thread is migrated to another CPU, reading * the per-CPU value later will give us the same value as we update the * per-CPU variable in the preempt notifier handlers. */ struct kvm_vcpu *kvm_get_running_vcpu(void) { struct kvm_vcpu *vcpu; preempt_disable(); vcpu = __this_cpu_read(kvm_running_vcpu); preempt_enable(); return vcpu; } EXPORT_SYMBOL_GPL(kvm_get_running_vcpu); /** * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. */ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) { return &kvm_running_vcpu; } #ifdef CONFIG_GUEST_PERF_EVENTS static unsigned int kvm_guest_state(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); unsigned int state; if (!kvm_arch_pmi_in_guest(vcpu)) return 0; state = PERF_GUEST_ACTIVE; if (!kvm_arch_vcpu_in_kernel(vcpu)) state |= PERF_GUEST_USER; return state; } static unsigned long kvm_guest_get_ip(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu))) return 0; return kvm_arch_vcpu_get_ip(vcpu); } static struct perf_guest_info_callbacks kvm_guest_cbs = { .state = kvm_guest_state, .get_ip = kvm_guest_get_ip, .handle_intel_pt_intr = NULL, }; void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)) { kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler; perf_register_guest_info_callbacks(&kvm_guest_cbs); } void kvm_unregister_perf_callbacks(void) { perf_unregister_guest_info_callbacks(&kvm_guest_cbs); } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) { int r; int cpu; /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); kvm_vcpu_cache = kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, SLAB_ACCOUNT, offsetof(struct kvm_vcpu, arch), offsetofend(struct kvm_vcpu, stats_id) - offsetof(struct kvm_vcpu, arch), NULL); if (!kvm_vcpu_cache) return -ENOMEM; for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), GFP_KERNEL, cpu_to_node(cpu))) { r = -ENOMEM; goto err_cpu_kick_mask; } } r = kvm_irqfd_init(); if (r) goto err_irqfd; r = kvm_async_pf_init(); if (r) goto err_async_pf; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; kvm_device_fops.owner = module; kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; kvm_init_debug(); r = kvm_vfio_ops_init(); if (WARN_ON_ONCE(r)) goto err_vfio; kvm_gmem_init(module); r = kvm_init_virtualization(); if (r) goto err_virt; /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! */ r = misc_register(&kvm_dev); if (r) { pr_err("kvm: misc device register failed\n"); goto err_register; } return 0; err_register: kvm_uninit_virtualization(); err_virt: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); err_async_pf: kvm_irqfd_exit(); err_irqfd: err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); return r; } EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { int cpu; /* * Note, unregistering /dev/kvm doesn't strictly need to come first, * fops_get(), a.k.a. try_module_get(), prevents acquiring references * to KVM while the module is being stopped. */ misc_deregister(&kvm_dev); kvm_uninit_virtualization(); debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * ARIA Cipher Algorithm. * * Documentation of ARIA can be found in RFC 5794. * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> * * Information for ARIA * http://210.104.33.10/ARIA/index-e.html (English) * http://seed.kisa.or.kr/ (Korean) * * Public domain version is distributed above. */ #include <crypto/aria.h> #include <linux/unaligned.h> static const u32 key_rc[20] = { 0x517cc1b7, 0x27220a94, 0xfe13abe8, 0xfa9a6ee0, 0x6db14acc, 0x9e21c820, 0xff28b1d5, 0xef5de2b0, 0xdb92371d, 0x2126e970, 0x03249775, 0x04e8c90e, 0x517cc1b7, 0x27220a94, 0xfe13abe8, 0xfa9a6ee0, 0x6db14acc, 0x9e21c820, 0xff28b1d5, 0xef5de2b0 }; static void aria_set_encrypt_key(struct aria_ctx *ctx, const u8 *in_key, unsigned int key_len) { u32 w0[4], w1[4], w2[4], w3[4]; u32 reg0, reg1, reg2, reg3; const u32 *ck; int rkidx = 0; ck = &key_rc[(key_len - 16) / 2]; w0[0] = get_unaligned_be32(&in_key[0]); w0[1] = get_unaligned_be32(&in_key[4]); w0[2] = get_unaligned_be32(&in_key[8]); w0[3] = get_unaligned_be32(&in_key[12]); reg0 = w0[0] ^ ck[0]; reg1 = w0[1] ^ ck[1]; reg2 = w0[2] ^ ck[2]; reg3 = w0[3] ^ ck[3]; aria_subst_diff_odd(®0, ®1, ®2, ®3); if (key_len > 16) { w1[0] = get_unaligned_be32(&in_key[16]); w1[1] = get_unaligned_be32(&in_key[20]); if (key_len > 24) { w1[2] = get_unaligned_be32(&in_key[24]); w1[3] = get_unaligned_be32(&in_key[28]); } else { w1[2] = 0; w1[3] = 0; } } else { w1[0] = 0; w1[1] = 0; w1[2] = 0; w1[3] = 0; } w1[0] ^= reg0; w1[1] ^= reg1; w1[2] ^= reg2; w1[3] ^= reg3; reg0 = w1[0]; reg1 = w1[1]; reg2 = w1[2]; reg3 = w1[3]; reg0 ^= ck[4]; reg1 ^= ck[5]; reg2 ^= ck[6]; reg3 ^= ck[7]; aria_subst_diff_even(®0, ®1, ®2, ®3); reg0 ^= w0[0]; reg1 ^= w0[1]; reg2 ^= w0[2]; reg3 ^= w0[3]; w2[0] = reg0; w2[1] = reg1; w2[2] = reg2; w2[3] = reg3; reg0 ^= ck[8]; reg1 ^= ck[9]; reg2 ^= ck[10]; reg3 ^= ck[11]; aria_subst_diff_odd(®0, ®1, ®2, ®3); w3[0] = reg0 ^ w1[0]; w3[1] = reg1 ^ w1[1]; w3[2] = reg2 ^ w1[2]; w3[3] = reg3 ^ w1[3]; aria_gsrk(ctx->enc_key[rkidx], w0, w1, 19); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w1, w2, 19); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w2, w3, 19); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w3, w0, 19); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w0, w1, 31); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w1, w2, 31); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w2, w3, 31); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w3, w0, 31); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w0, w1, 67); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w1, w2, 67); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w2, w3, 67); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w3, w0, 67); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w0, w1, 97); if (key_len > 16) { rkidx++; aria_gsrk(ctx->enc_key[rkidx], w1, w2, 97); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w2, w3, 97); if (key_len > 24) { rkidx++; aria_gsrk(ctx->enc_key[rkidx], w3, w0, 97); rkidx++; aria_gsrk(ctx->enc_key[rkidx], w0, w1, 109); } } } static void aria_set_decrypt_key(struct aria_ctx *ctx) { int i; for (i = 0; i < 4; i++) { ctx->dec_key[0][i] = ctx->enc_key[ctx->rounds][i]; ctx->dec_key[ctx->rounds][i] = ctx->enc_key[0][i]; } for (i = 1; i < ctx->rounds; i++) { ctx->dec_key[i][0] = aria_m(ctx->enc_key[ctx->rounds - i][0]); ctx->dec_key[i][1] = aria_m(ctx->enc_key[ctx->rounds - i][1]); ctx->dec_key[i][2] = aria_m(ctx->enc_key[ctx->rounds - i][2]); ctx->dec_key[i][3] = aria_m(ctx->enc_key[ctx->rounds - i][3]); aria_diff_word(&ctx->dec_key[i][0], &ctx->dec_key[i][1], &ctx->dec_key[i][2], &ctx->dec_key[i][3]); aria_diff_byte(&ctx->dec_key[i][1], &ctx->dec_key[i][2], &ctx->dec_key[i][3]); aria_diff_word(&ctx->dec_key[i][0], &ctx->dec_key[i][1], &ctx->dec_key[i][2], &ctx->dec_key[i][3]); } } int aria_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len) { struct aria_ctx *ctx = crypto_tfm_ctx(tfm); if (key_len != 16 && key_len != 24 && key_len != 32) return -EINVAL; BUILD_BUG_ON(sizeof(ctx->enc_key) != 272); BUILD_BUG_ON(sizeof(ctx->dec_key) != 272); BUILD_BUG_ON(sizeof(int) != sizeof(ctx->rounds)); ctx->key_length = key_len; ctx->rounds = (key_len + 32) / 4; aria_set_encrypt_key(ctx, in_key, key_len); aria_set_decrypt_key(ctx); return 0; } EXPORT_SYMBOL_GPL(aria_set_key); static void __aria_crypt(struct aria_ctx *ctx, u8 *out, const u8 *in, u32 key[][ARIA_RD_KEY_WORDS]) { u32 reg0, reg1, reg2, reg3; int rounds, rkidx = 0; rounds = ctx->rounds; reg0 = get_unaligned_be32(&in[0]); reg1 = get_unaligned_be32(&in[4]); reg2 = get_unaligned_be32(&in[8]); reg3 = get_unaligned_be32(&in[12]); aria_add_round_key(key[rkidx], ®0, ®1, ®2, ®3); rkidx++; aria_subst_diff_odd(®0, ®1, ®2, ®3); aria_add_round_key(key[rkidx], ®0, ®1, ®2, ®3); rkidx++; while ((rounds -= 2) > 0) { aria_subst_diff_even(®0, ®1, ®2, ®3); aria_add_round_key(key[rkidx], ®0, ®1, ®2, ®3); rkidx++; aria_subst_diff_odd(®0, ®1, ®2, ®3); aria_add_round_key(key[rkidx], ®0, ®1, ®2, ®3); rkidx++; } reg0 = key[rkidx][0] ^ make_u32((u8)(x1[get_u8(reg0, 0)]), (u8)(x2[get_u8(reg0, 1)] >> 8), (u8)(s1[get_u8(reg0, 2)]), (u8)(s2[get_u8(reg0, 3)])); reg1 = key[rkidx][1] ^ make_u32((u8)(x1[get_u8(reg1, 0)]), (u8)(x2[get_u8(reg1, 1)] >> 8), (u8)(s1[get_u8(reg1, 2)]), (u8)(s2[get_u8(reg1, 3)])); reg2 = key[rkidx][2] ^ make_u32((u8)(x1[get_u8(reg2, 0)]), (u8)(x2[get_u8(reg2, 1)] >> 8), (u8)(s1[get_u8(reg2, 2)]), (u8)(s2[get_u8(reg2, 3)])); reg3 = key[rkidx][3] ^ make_u32((u8)(x1[get_u8(reg3, 0)]), (u8)(x2[get_u8(reg3, 1)] >> 8), (u8)(s1[get_u8(reg3, 2)]), (u8)(s2[get_u8(reg3, 3)])); put_unaligned_be32(reg0, &out[0]); put_unaligned_be32(reg1, &out[4]); put_unaligned_be32(reg2, &out[8]); put_unaligned_be32(reg3, &out[12]); } void aria_encrypt(void *_ctx, u8 *out, const u8 *in) { struct aria_ctx *ctx = (struct aria_ctx *)_ctx; __aria_crypt(ctx, out, in, ctx->enc_key); } EXPORT_SYMBOL_GPL(aria_encrypt); void aria_decrypt(void *_ctx, u8 *out, const u8 *in) { struct aria_ctx *ctx = (struct aria_ctx *)_ctx; __aria_crypt(ctx, out, in, ctx->dec_key); } EXPORT_SYMBOL_GPL(aria_decrypt); static void __aria_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct aria_ctx *ctx = crypto_tfm_ctx(tfm); __aria_crypt(ctx, out, in, ctx->enc_key); } static void __aria_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { struct aria_ctx *ctx = crypto_tfm_ctx(tfm); __aria_crypt(ctx, out, in, ctx->dec_key); } static struct crypto_alg aria_alg = { .cra_name = "aria", .cra_driver_name = "aria-generic", .cra_priority = 100, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = ARIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct aria_ctx), .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = ARIA_MIN_KEY_SIZE, .cia_max_keysize = ARIA_MAX_KEY_SIZE, .cia_setkey = aria_set_key, .cia_encrypt = __aria_encrypt, .cia_decrypt = __aria_decrypt } } }; static int __init aria_init(void) { return crypto_register_alg(&aria_alg); } static void __exit aria_fini(void) { crypto_unregister_alg(&aria_alg); } subsys_initcall(aria_init); module_exit(aria_fini); MODULE_DESCRIPTION("ARIA Cipher Algorithm"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Taehee Yoo <ap420073@gmail.com>"); MODULE_ALIAS_CRYPTO("aria"); MODULE_ALIAS_CRYPTO("aria-generic"); |
| 5 1 1 2 3 1 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match the bridge port in and * out device for IP packets coming into contact with a bridge. */ /* (C) 2001-2003 Bart De Schuymer <bdschuym@pandora.be> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/if.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter/x_tables.h> #include <uapi/linux/netfilter/xt_physdev.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("Xtables: Bridge physical device match"); MODULE_ALIAS("ipt_physdev"); MODULE_ALIAS("ip6t_physdev"); static bool physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_physdev_info *info = par->matchinfo; const struct net_device *physdev; unsigned long ret; const char *indev, *outdev; /* Not a bridged IP packet or no info available yet: * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if * the destination device will be a bridge. */ if (!nf_bridge_info_exists(skb)) { /* Return MATCH if the invert flags of the used options are on */ if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && !(info->invert & XT_PHYSDEV_OP_BRIDGED)) return false; if ((info->bitmask & XT_PHYSDEV_OP_ISIN) && !(info->invert & XT_PHYSDEV_OP_ISIN)) return false; if ((info->bitmask & XT_PHYSDEV_OP_ISOUT) && !(info->invert & XT_PHYSDEV_OP_ISOUT)) return false; if ((info->bitmask & XT_PHYSDEV_OP_IN) && !(info->invert & XT_PHYSDEV_OP_IN)) return false; if ((info->bitmask & XT_PHYSDEV_OP_OUT) && !(info->invert & XT_PHYSDEV_OP_OUT)) return false; return true; } physdev = nf_bridge_get_physoutdev(skb); outdev = physdev ? physdev->name : NULL; /* This only makes sense in the FORWARD and POSTROUTING chains */ if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; physdev = nf_bridge_get_physindev(skb, xt_net(par)); indev = physdev ? physdev->name : NULL; if ((info->bitmask & XT_PHYSDEV_OP_ISIN && (!indev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) || (info->bitmask & XT_PHYSDEV_OP_ISOUT && (!outdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT)))) return false; if (!(info->bitmask & XT_PHYSDEV_OP_IN)) goto match_outdev; if (indev) { ret = ifname_compare_aligned(indev, info->physindev, info->in_mask); if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN)) return false; } match_outdev: if (!(info->bitmask & XT_PHYSDEV_OP_OUT)) return true; if (!outdev) return false; ret = ifname_compare_aligned(outdev, info->physoutdev, info->out_mask); return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT)); } static int physdev_mt_check(const struct xt_mtchk_param *par) { const struct xt_physdev_info *info = par->matchinfo; static bool brnf_probed __read_mostly; if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) return -EINVAL; if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && par->hook_mask & (1 << NF_INET_LOCAL_OUT)) { pr_info_ratelimited("--physdev-out and --physdev-is-out only supported in the FORWARD and POSTROUTING chains with bridged traffic\n"); return -EINVAL; } if (!brnf_probed) { brnf_probed = true; request_module("br_netfilter"); } return 0; } static struct xt_match physdev_mt_reg __read_mostly = { .name = "physdev", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = physdev_mt_check, .match = physdev_mt, .matchsize = sizeof(struct xt_physdev_info), .me = THIS_MODULE, }; static int __init physdev_mt_init(void) { return xt_register_match(&physdev_mt_reg); } static void __exit physdev_mt_exit(void) { xt_unregister_match(&physdev_mt_reg); } module_init(physdev_mt_init); module_exit(physdev_mt_exit); |
| 4 4 1204 3 211 1196 1206 1199 5 1202 1204 1204 1197 1197 1191 1200 1199 264 263 258 241 54 265 261 256 5 8 257 137 113 182 228 182 2 22 120 238 116 143 3 2 1 9 9 9 294 295 292 289 293 6 273 137 136 92 86 96 322 1 301 316 2 294 295 7 5 15 267 145 262 237 238 1 1 2 1 1 1 2 1 1 1 2 1 22 6 1 15 1 322 2 1 1 1 292 22 2 1 2 3 3 333 325 8 19 10 4 6 2 1 7 4 1 3 3 98 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <linux/poison.h> #include <net/ipv6.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); void *ip6t_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ip6t, IP6T); } EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip6_packet_match(const struct sk_buff *skb, const char *indev, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); if (NF_INVF(ip6info, IP6T_INV_SRCIP, ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, &ip6info->src)) || NF_INVF(ip6info, IP6T_INV_DSTIP, ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, &ip6info->dst))) return false; ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0)) return false; /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ if (ip6info->flags & IP6T_F_PROTO) { int protohdr; unsigned short _frag_off; protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); if (protohdr < 0) { if (_frag_off == 0) *hotdrop = true; return false; } *fragoff = _frag_off; if (ip6info->proto == protohdr) { if (ip6info->invflags & IP6T_INV_PROTO) return false; return true; } /* We need match for the '-p all', too! */ if ((ip6info->proto != 0) && !(ip6info->invflags & IP6T_INV_PROTO)) return false; } return true; } /* should be ip6 safe */ static bool ip6_checkentry(const struct ip6t_ip6 *ipv6) { if (ipv6->flags & ~IP6T_F_MASK) return false; if (ipv6->invflags & ~IP6T_INV_MASK) return false; return true; } static unsigned int ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline struct ip6t_entry * get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; return e->target_offset == sizeof(struct ip6t_entry) && memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP6_TRACE_COMMENT_RULE, NF_IP6_TRACE_COMMENT_RETURN, NF_IP6_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP6_TRACE_COMMENT_RULE] = "rule", [NF_IP6_TRACE_COMMENT_RETURN] = "return", [NF_IP6_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = LOGLEVEL_WARNING, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] : comments[NF_IP6_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ip6t_entry *e) { const struct ip6t_entry *root; const char *hookname, *chainname, *comment; const struct ip6t_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP6_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: e = ip6t_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ip6t_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ break; } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ip6t_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV6, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); } static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ip6t_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ip6t_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ip6t_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ip6t_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ip6t_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET6, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET6, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ip6t_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ip6t_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET6, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ip6t_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET6); #endif t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET6); #endif return ret; } static int get_entries(struct net *net, struct ip6t_get_entries __user *uptr, const int *len) { int ret; struct ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ip6t_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET6, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ip6t_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET6, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ip6t_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[]; }; static int compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ip6t_entry); *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ip6t_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ip6t_ip6 *ipv6, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ip6t_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ip6t_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ip6t_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ip6t_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ip6t_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ip6t_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ip6t_entry *iter0; struct ip6t_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET6); ret = xt_compat_init_offsets(AF_INET6, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. */ xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ip6t_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ip6t_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, int *len) { int ret; struct compat_ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET6); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET6); return ret; } #endif static int do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IP6T_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IP6T_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IP6T_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET6, rev.name, rev.revision, target, &ret), "ip6t_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ip6t_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ip6t_unregister_table(net, new_table); return ret; } void ip6t_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ip6t_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; static struct nf_sockopt_ops ip6t_sockopts = { .pf = PF_INET6, .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip6_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV6); } static void __net_exit ip6_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV6); } static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, }; static int __init ip6_tables_init(void) { int ret; ret = register_pernet_subsys(&ip6_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); err2: unregister_pernet_subsys(&ip6_tables_net_ops); err1: return ret; } static void __exit ip6_tables_fini(void) { nf_unregister_sockopt(&ip6t_sockopts); xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); unregister_pernet_subsys(&ip6_tables_net_ops); } EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); module_exit(ip6_tables_fini); |
| 21 21 21 21 50 30 21 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2007-2012 Siemens AG * * Written by: * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Sergey Lapin <slapin@ossfans.org> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/crc-ccitt.h> #include <linux/unaligned.h> #include <net/rtnetlink.h> #include <net/ieee802154_netdev.h> #include <net/mac802154.h> #include <net/cfg802154.h> #include "ieee802154_i.h" #include "driver-ops.h" void ieee802154_xmit_sync_worker(struct work_struct *work) { struct ieee802154_local *local = container_of(work, struct ieee802154_local, sync_tx_work); struct sk_buff *skb = local->tx_skb; struct net_device *dev = skb->dev; int res; res = drv_xmit_sync(local, skb); if (res) goto err_tx; DEV_STATS_INC(dev, tx_packets); DEV_STATS_ADD(dev, tx_bytes, skb->len); ieee802154_xmit_complete(&local->hw, skb, false); return; err_tx: /* Restart the netif queue on each sub_if_data object. */ ieee802154_release_queue(local); if (atomic_dec_and_test(&local->phy->ongoing_txs)) wake_up(&local->phy->sync_txq); kfree_skb(skb); netdev_dbg(dev, "transmission failed\n"); } static netdev_tx_t ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret; if (!(local->hw.flags & IEEE802154_HW_TX_OMIT_CKSUM)) { struct sk_buff *nskb; u16 crc; if (unlikely(skb_tailroom(skb) < IEEE802154_FCS_LEN)) { nskb = skb_copy_expand(skb, 0, IEEE802154_FCS_LEN, GFP_ATOMIC); if (likely(nskb)) { consume_skb(skb); skb = nskb; } else { goto err_free_skb; } } crc = crc_ccitt(0, skb->data, skb->len); put_unaligned_le16(crc, skb_put(skb, 2)); } /* Stop the netif queue on each sub_if_data object. */ ieee802154_hold_queue(local); atomic_inc(&local->phy->ongoing_txs); /* Drivers should preferably implement the async callback. In some rare * cases they only provide a sync callback which we will use as a * fallback. */ if (local->ops->xmit_async) { unsigned int len = skb->len; ret = drv_xmit_async(local, skb); if (ret) goto err_wake_netif_queue; DEV_STATS_INC(dev, tx_packets); DEV_STATS_ADD(dev, tx_bytes, len); } else { local->tx_skb = skb; queue_work(local->workqueue, &local->sync_tx_work); } return NETDEV_TX_OK; err_wake_netif_queue: ieee802154_release_queue(local); if (atomic_dec_and_test(&local->phy->ongoing_txs)) wake_up(&local->phy->sync_txq); err_free_skb: kfree_skb(skb); return NETDEV_TX_OK; } static int ieee802154_sync_queue(struct ieee802154_local *local) { int ret; ieee802154_hold_queue(local); ieee802154_disable_queue(local); wait_event(local->phy->sync_txq, !atomic_read(&local->phy->ongoing_txs)); ret = local->tx_result; ieee802154_release_queue(local); return ret; } int ieee802154_sync_and_hold_queue(struct ieee802154_local *local) { int ret; ieee802154_hold_queue(local); ret = ieee802154_sync_queue(local); set_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); return ret; } int ieee802154_mlme_op_pre(struct ieee802154_local *local) { return ieee802154_sync_and_hold_queue(local); } int ieee802154_mlme_tx_locked(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct sk_buff *skb) { /* Avoid possible calls to ->ndo_stop() when we asynchronously perform * MLME transmissions. */ ASSERT_RTNL(); /* Ensure the device was not stopped, otherwise error out */ if (!local->open_count) return -ENETDOWN; /* Warn if the ieee802154 core thinks MLME frames can be sent while the * net interface expects this cannot happen. */ if (WARN_ON_ONCE(!netif_running(sdata->dev))) return -ENETDOWN; ieee802154_tx(local, skb); return ieee802154_sync_queue(local); } int ieee802154_mlme_tx(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct sk_buff *skb) { int ret; rtnl_lock(); ret = ieee802154_mlme_tx_locked(local, sdata, skb); rtnl_unlock(); return ret; } void ieee802154_mlme_op_post(struct ieee802154_local *local) { ieee802154_release_queue(local); } int ieee802154_mlme_tx_one_locked(struct ieee802154_local *local, struct ieee802154_sub_if_data *sdata, struct sk_buff *skb) { int ret; ieee802154_mlme_op_pre(local); ret = ieee802154_mlme_tx_locked(local, sdata, skb); ieee802154_mlme_op_post(local); return ret; } static bool ieee802154_queue_is_stopped(struct ieee802154_local *local) { return test_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); } static netdev_tx_t ieee802154_hot_tx(struct ieee802154_local *local, struct sk_buff *skb) { /* Warn if the net interface tries to transmit frames while the * ieee802154 core assumes the queue is stopped. */ WARN_ON_ONCE(ieee802154_queue_is_stopped(local)); return ieee802154_tx(local, skb); } netdev_tx_t ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); skb->skb_iif = dev->ifindex; return ieee802154_hot_tx(sdata->local, skb); } netdev_tx_t ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int rc; /* TODO we should move it to wpan_dev_hard_header and dev_hard_header * functions. The reason is wireshark will show a mac header which is * with security fields but the payload is not encrypted. */ rc = mac802154_llsec_encrypt(&sdata->sec, skb); if (rc) { netdev_warn(dev, "encryption failed: %i\n", rc); kfree_skb(skb); return NETDEV_TX_OK; } skb->skb_iif = dev->ifindex; return ieee802154_hot_tx(sdata->local, skb); } |
| 49 1 48 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011 Florian Westphal <fw@strlen.de> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/route.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <linux/netfilter/xt_rpfilter.h> #include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_DESCRIPTION("Xtables: IPv6 reverse path filter match"); static bool rpfilter_addr_unicast(const struct in6_addr *addr) { int addr_type = ipv6_addr_type(addr); return addr_type & IPV6_ADDR_UNICAST; } static bool rpfilter_addr_linklocal(const struct in6_addr *addr) { int addr_type = ipv6_addr_type(addr); return addr_type & IPV6_ADDR_LINKLOCAL; } static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, const struct net_device *dev, u8 flags) { struct rt6_info *rt; struct ipv6hdr *iph = ipv6_hdr(skb); bool ret = false; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev), .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_proto = iph->nexthdr, .flowi6_uid = sock_net_uid(net, NULL), .daddr = iph->saddr, }; int lookup_flags; if (rpfilter_addr_unicast(&iph->daddr)) { memcpy(&fl6.saddr, &iph->daddr, sizeof(struct in6_addr)); lookup_flags = RT6_LOOKUP_F_HAS_SADDR; } else { lookup_flags = 0; } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; if (rpfilter_addr_linklocal(&iph->saddr)) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6.flowi6_oif = dev->ifindex; } else if ((flags & XT_RPFILTER_LOOSE) == 0) fl6.flowi6_oif = dev->ifindex; rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); if (rt->dst.error) goto out; if (rt->rt6i_flags & (RTF_REJECT|RTF_ANYCAST)) goto out; if (rt->rt6i_flags & RTF_LOCAL) { ret = flags & XT_RPFILTER_ACCEPT_LOCAL; goto out; } if (rt->rt6i_idev->dev == dev || l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex || (flags & XT_RPFILTER_LOOSE)) ret = true; out: ip6_rt_put(rt); return ret; } static bool rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info = par->matchinfo; int saddrtype; struct ipv6hdr *iph; bool invert = info->flags & XT_RPFILTER_INVERT; if (rpfilter_is_loopback(skb, xt_in(par))) return true ^ invert; iph = ipv6_hdr(skb); saddrtype = ipv6_addr_type(&iph->saddr); if (unlikely(saddrtype == IPV6_ADDR_ANY)) return true ^ invert; /* not routable: forward path will drop it */ return rpfilter_lookup_reverse6(xt_net(par), skb, xt_in(par), info->flags) ^ invert; } static int rpfilter_check(const struct xt_mtchk_param *par) { const struct xt_rpfilter_info *info = par->matchinfo; unsigned int options = ~XT_RPFILTER_OPTION_MASK; if (info->flags & options) { pr_info_ratelimited("unknown options\n"); return -EINVAL; } if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "raw") != 0) { pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n", par->table); return -EINVAL; } return 0; } static struct xt_match rpfilter_mt_reg __read_mostly = { .name = "rpfilter", .family = NFPROTO_IPV6, .checkentry = rpfilter_check, .match = rpfilter_mt, .matchsize = sizeof(struct xt_rpfilter_info), .hooks = (1 << NF_INET_PRE_ROUTING), .me = THIS_MODULE }; static int __init rpfilter_mt_init(void) { return xt_register_match(&rpfilter_mt_reg); } static void __exit rpfilter_mt_exit(void) { xt_unregister_match(&rpfilter_mt_reg); } module_init(rpfilter_mt_init); module_exit(rpfilter_mt_exit); |
| 514 511 514 531 70 3 10 10 10 3 3 3 96 118 10 40 40 149 151 151 151 7 4 4 1 7 2 5 4 2 4 3 1 2 2 2 2 22 3 1 1 17 17 17 4 1 12 16 16 16 11 5 1 3 12 16 16 16 4 11 11 1 10 7 10 16 37 37 37 37 35 31 7 22 5 2 3 2 185 460 176 382 60 62 61 62 56 9 622 622 21 21 622 3 18 21 21 505 504 19 19 19 505 506 20 504 514 495 513 498 71 71 16 63 63 2 622 584 622 588 83 83 9 75 621 622 1 511 512 955 958 957 958 625 627 626 627 6 622 623 622 624 624 40 2 6 2 4 4 1 2 2 2 2 2 1 1 6 6 2 2 1 734 735 490 734 58 2 512 512 28 482 49 49 49 48 48 48 714 715 715 702 53 714 1 1326 1326 581 584 584 502 500 502 16 501 98 62 34 6 3 35 21 1 9 20 20 17 9 7 13 7 9 9 42 3 41 41 3 39 39 4 36 35 25 6 26 6 6 33 28 10 12 19 28 28 51 18 20 16 11 50 50 17 16 29 12 23 7 2 2 17 7 9 36 36 36 1 35 35 17 26 35 28 6 6 6 31 515 515 55 55 4 6 50 10 45 35 20 18 18 11 7 15 15 15 7 14 1 8 3 2 8 37 1 37 7 35 6 12 14 5 29 4 4 7 5 4 16 2 1 1 1 15 17 3 1 17 17 1 28 2 1 25 3 20 20 4 14 4 17 11 6 3 7 7 1 4 5 2 1 1 1 2 2 8 8 1 1 6 2 4 4 4 2 70 44 26 26 1 8 18 8 1 4 7 5 5 26 351 343 9 9 1 9 358 358 359 213 65 2 4 145 98 97 2138 2136 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include "igmp_internal.h" #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/addrconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (timer_delete(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = get_random_u32_below(max_delay); im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = get_random_u32_below(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = get_random_u32_below(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (timer_delete(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); if (mr_ifc_count) { if (cmpxchg(&in_dev->mr_ifc_count, mr_ifc_count, mr_ifc_count - 1) != mr_ifc_count) goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = from_timer(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, const struct ip_mc_list *im, struct inet_fill_args *args) { struct ifa_cacheinfo ci; struct ifaddrmsg *ifm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = 32; ifm->ifa_flags = IFA_F_PERMANENT; ifm->ifa_scope = RT_SCOPE_UNIVERSE; ifm->ifa_index = dev->ifindex; ci.cstamp = (READ_ONCE(im->mca_cstamp) - INITIAL_JIFFIES) * 100UL / HZ; ci.tstamp = ci.cstamp; ci.ifa_prefered = INFINITY_LIFE_TIME; ci.ifa_valid = INFINITY_LIFE_TIME; if (nla_put_in_addr(skb, IFA_MULTICAST, im->multiaddr) < 0 || nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static void inet_ifmcaddr_notify(struct net_device *dev, const struct ip_mc_list *im, int event) { struct inet_fill_args fillargs = { .event = event, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(__be32)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) goto error; err = inet_fill_ifmcaddr(skb, dev, im, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); goto error; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MCADDR, NULL, GFP_KERNEL); return; error: rtnl_set_sk_err(net, RTNLGRP_IPV4_MCADDR, err); } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list __rcu **mc_hash; struct ip_mc_list *im; ASSERT_RTNL(); mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)addr, MC_HASH_SZ_LOG); for (im = rtnl_dereference(mc_hash[hash]); im; im = rtnl_dereference(im->next_hash)) { if (im->multiaddr == addr) break; } } else { for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) break; } } if (im) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } im = kzalloc(sizeof(*im), gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; im->mca_cstamp = jiffies; im->mca_tstamp = im->mca_cstamp; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); inet_ifmcaddr_notify(in_dev->dev, im, RTM_NEWMULTICAST); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); inet_ifmcaddr_notify(in_dev->dev, i, RTM_DELMULTICAST); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (timer_delete(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist_flex, flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen) { int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; msf_size = IP_MSFILTER_SIZE(copycount); if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_sockptr_offset(optval, offsetof(struct ip_msfilter, imsf_slist_flex), psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 281 169 1000 147 29 29 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_NULLS_H #define _LINUX_RCULIST_NULLS_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list_nulls.h> #include <linux/rcupdate.h> /** * hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_nulls_add_head_rcu() or * hlist_nulls_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_nulls_for_each_entry_rcu(). */ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * hlist_nulls_first_rcu - returns the first element of the hash list. * @head: the head of the list. */ #define hlist_nulls_first_rcu(head) \ (*((struct hlist_nulls_node __rcu __force **)&(head)->first)) /** * hlist_nulls_next_rcu - returns the element of the list after @node. * @node: element of the list. */ #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry(). */ static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_nulls, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; WRITE_ONCE(n->next, first); WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_nulls_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_nulls, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; !is_a_nulls(i); i = i->next) last = i; if (last) { WRITE_ONCE(n->next, last->next); n->pprev = &last->next; rcu_assign_pointer(hlist_nulls_next_rcu(last), n); } else { hlist_nulls_add_head_rcu(n, h); } } /* after that hlist_nulls_del will work */ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) { n->pprev = &n->next; n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); } /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. * * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] * [1] Documentation/memory-barriers.txt around line 1533 * [2] Documentation/RCU/rculist_nulls.rst around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) /** * hlist_nulls_for_each_entry_safe - * iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. */ #define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif |
| 143 7 1 15 15 1 10 10 23 29 6 3 29 479 3 6 1 1 1 1 2 1 25 11 9 6 7 7 7 10 10 7 121 104 38 68 380 381 376 372 13 380 89 89 89 89 2 13 13 89 68 42 141 10 11 11 10 10 1 1 2 8 10 10 10 6 5 10 10 10 2 8 11 11 7 6 6 11 11 9 9 7 10 10 57 57 57 48 23 9 9 171 31 34 3 3 3 1 12 147 12 27 380 4 13 406 407 2 18 13 267 380 311 350 1 3 3 351 8 393 10 409 136 29 108 1 7 135 7 3 13 15 1 14 13 15 26 15 15 6 73 78 7 7 126 24 126 125 2 141 142 142 142 125 24 142 125 24 142 139 7 140 126 24 141 142 1 74 70 141 141 79 71 71 71 7 64 21 21 1 8 5 7 21 8 8 8 2 3 6 37 38 34 37 19 1 20 37 37 11 4 4 4 4 11 12 12 43 12 7 366 365 38 38 16 25 9 44 15 30 45 29 38 10 29 2 29 7 3 29 29 29 29 3 9 12 27 26 1 4 9 31 31 15 31 13 1 12 1 11 9 5 1 4 171 31 166 184 4 3 2 5 171 5 135 4 31 166 29 146 7 28 28 164 2 3 141 2 1 2 1 21 164 31 181 187 187 4 2 58 6 8 45 48 25 25 37 3 34 39 39 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> #include <net/busy_poll.h> /* * LOCKING: * There are three level of locking required by epoll : * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) * 3) ep->lock (rwlock) * * The acquire order is the one listed above, from 1 to 3. * We need a rwlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need * a spinlock. During the event transfer loop (from kernel to * user space) we could end up sleeping due a copy_to_user(), so * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). * The epnested_mutex is acquired when inserting an epoll fd onto another * epoll fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two * simultaneous inserts (A into B and B into A) from racing and * constructing a cycle without either insert observing that it is * going to. * It is necessary to acquire multiple "ep->mtx"es at once in the * case when one epoll fd is added to another. In this case, we * always acquire the locks in the order of nesting (i.e. after * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired * before e2->mtx). Since we disallow cycles of epoll file * descriptors, this ensures that the mutexes are well-ordered. In * order to communicate this nesting to lockdep, when walking a tree * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global * mutex "epnested_mutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. * Events that require holding "epnested_mutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee * a better scalability. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) struct epoll_filefd { struct file *file; int fd; } __packed; /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct eppoll_entry *next; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* List header used to link this structure to the eventpoll ready list */ struct list_head rdllink; /* * Works together "struct eventpoll"->ovflist in keeping the * single linked chain of items. */ struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; /* * Protected by file->f_lock, true for to-be-released epitem already * removed from the "struct file" items list; together with * eventpoll->refcount orchestrates "struct eventpoll" disposal */ bool dying; /* List containing poll wait queues */ struct eppoll_entry *pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct hlist_node fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ rwlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; /* * usage count, used together with epitem->dying to * orchestrate the disposal of this struct */ refcount_t refcount; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; /* busy poll timeout */ u32 busy_poll_usecs; /* busy poll packet budget */ u16 busy_poll_budget; bool prefer_busy_poll; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* Used for cycles detection */ static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; /* Used to check for epoll file descriptor inclusion loops */ static struct eventpoll *inserting_into; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __ro_after_init; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __ro_after_init; /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epnested_mutex. */ struct epitems_head { struct hlist_head epitems; struct epitems_head *next; }; static struct epitems_head *tfile_check_list = EP_UNACTIVE_PTR; static struct kmem_cache *ephead_cache __ro_after_init; static inline void free_ephead(struct epitems_head *head) { if (head) kmem_cache_free(ephead_cache, head); } static void list_file(struct file *file) { struct epitems_head *head; head = container_of(file->f_ep, struct epitems_head, epitems); if (!head->next) { head->next = tfile_check_list; tfile_check_list = head; } } static void unlist_file(struct epitems_head *head) { struct epitems_head *to_free = head; struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems)); if (p) { struct epitem *epi= container_of(p, struct epitem, fllink); spin_lock(&epi->ffd.file->f_lock); if (!hlist_empty(&head->epitems)) to_free = NULL; head->next = NULL; spin_unlock(&epi->ffd.file->f_lock); } free_ephead(to_free); } #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, }; static void __init epoll_sysctls_init(void) { register_sysctl("fs/epoll", epoll_table); } #else #define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; static inline int is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Setup the structure that is used as key for the RB tree */ static inline void ep_set_ffd(struct epoll_filefd *ffd, struct file *file, int fd) { ffd->file = file; ffd->fd = fd; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_filefd *p1, struct epoll_filefd *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* Tells us if the item is currently linked */ static inline int ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /** * ep_events_available - Checks if ready events might be available. * * @ep: Pointer to the eventpoll context. * * Return: a value different than %zero if ready events are available, * or %zero otherwise. */ static inline int ep_events_available(struct eventpoll *ep) { return !list_empty_careful(&ep->rdllist) || READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL /** * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value * from the epoll instance ep is preferred, but if it is not set fallback to * the system-wide global via busy_loop_timeout. * * @start_time: The start time used to compute the remaining time until timeout. * @ep: Pointer to the eventpoll context. * * Return: true if the timeout has expired, false otherwise. */ static bool busy_loop_ep_timeout(unsigned long start_time, struct eventpoll *ep) { unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } else { return busy_loop_timeout(start_time); } } static bool ep_busy_loop_on(struct eventpoll *ep) { return !!READ_ONCE(ep->busy_poll_usecs) || READ_ONCE(ep->prefer_busy_poll) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static bool ep_busy_loop(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); u16 budget = READ_ONCE(ep->busy_poll_budget); bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (!budget) budget = BUSY_POLL_BUDGET; if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) return true; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ if (prefer_busy_poll) napi_resume_irqs(napi_id); ep->napi_id = 0; return false; } return false; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep = epi->ep; unsigned int napi_id; struct socket *sock; struct sock *sk; if (!ep_busy_loop_on(ep)) return; sock = sock_from_file(epi->ffd.file); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (!napi_id_valid(napi_id) || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct eventpoll *ep = file->private_data; void __user *uarg = (void __user *)arg; struct epoll_params epoll_params; switch (cmd) { case EPIOCSPARAMS: if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) return -EFAULT; /* pad byte must be zero */ if (epoll_params.__pad) return -EINVAL; if (epoll_params.busy_poll_usecs > S32_MAX) return -EINVAL; if (epoll_params.prefer_busy_poll > 1) return -EINVAL; if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && !capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); return 0; case EPIOCGPARAMS: memset(&epoll_params, 0, sizeof(epoll_params)); epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) return -EFAULT; return 0; default: return -ENOIOCTLCMD; } } static void ep_suspend_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_suspend_irqs(napi_id); } static void ep_resume_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_resume_irqs(napi_id); } #else static inline bool ep_busy_loop(struct eventpoll *ep) { return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } static void ep_suspend_napi_irqs(struct eventpoll *ep) { } static void ep_resume_napi_irqs(struct eventpoll *ep) { } #endif /* CONFIG_NET_RX_BUSY_POLL */ /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * If it is cleared by POLLFREE, it should be rcu-safe. * If we read NULL we need a barrier paired with * smp_store_release() in ep_poll_callback(), otherwise * we rely on whead->lock. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct eppoll_entry **p = &epi->pwqlist; struct eppoll_entry *pwq; while ((pwq = *p) != NULL) { *p = pwq->next; ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /* * ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) { /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ lockdep_assert_irqs_enabled(); write_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); write_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, struct list_head *txlist) { struct epitem *epi, *nepi; write_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { /* * We need to check if the item is already in the list. * During the "sproc" callback execution time, items are * queued into ->ovflist but the "txlist" might already * contain them, and the list_splice() below takes care of them. */ if (!ep_is_linked(epi)) { /* * ->ovflist is LIFO, so we have to reverse it in order * to keep in FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } /* * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after * releasing the lock, events will be queued in the normal way inside * ep->rdllist. */ WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); /* * Quickly re-inject items left on "txlist". */ list_splice(txlist, &ep->rdllist); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } write_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); } /* * Returns true if the event poll can be disposed */ static bool ep_refcount_dec_and_test(struct eventpoll *ep) { if (!refcount_dec_and_test(&ep->refcount)) return false; WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); return true; } static void ep_free(struct eventpoll *ep) { ep_resume_napi_irqs(ep); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); kfree(ep); } /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. * If the dying flag is set, do the removal only if force is true. * This prevents ep_clear_and_put() from dropping all the ep references * while running concurrently with eventpoll_release_file(). * Returns true if the eventpoll can be disposed. */ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; struct epitems_head *to_free; struct hlist_head *head; lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. */ ep_unregister_pollwait(ep, epi); /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); if (epi->dying && !force) { spin_unlock(&file->f_lock); return false; } to_free = NULL; head = file->f_ep; if (head->first == &epi->fllink && !epi->fllink.next) { /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, NULL); if (!is_file_epoll(file)) { struct epitems_head *v; v = container_of(head, struct epitems_head, epitems); if (!smp_load_acquire(&v->next)) to_free = v; } } hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); rb_erase_cached(&epi->rbn, &ep->rbr); write_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); return ep_refcount_dec_and_test(ep); } /* * ep_remove variant for callers owing an additional reference to the ep */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { WARN_ON_ONCE(__ep_remove(ep, epi, false)); } static void ep_clear_and_put(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; bool dispose; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); mutex_lock(&ep->mtx); /* * Walks through the whole tree by unregistering poll callbacks. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } /* * Walks through the whole tree and try to free each "struct epitem". * Note that ep_remove_safe() will not remove the epitem in case of a * racing eventpoll_release_file(); the latter will do the removal. * At this point we are sure no poll callbacks will be lingering around. * Since we still own a reference to the eventpoll struct, the loop can't * dispose it. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); ep_remove_safe(ep, epi); cond_resched(); } dispose = ep_refcount_dec_and_test(ep); mutex_unlock(&ep->mtx); if (dispose) ep_free(ep); } static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (!is_file_epoll(file)) return -EINVAL; switch (cmd) { case EPIOCSPARAMS: case EPIOCGPARAMS: ret = ep_eventpoll_bp_ioctl(file, cmd, arg); break; default: ret = -EINVAL; break; } return ret; } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_clear_and_put(ep); return 0; } static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth); static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; LIST_HEAD(txlist); struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; init_poll_funcptr(&pt, NULL); /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ mutex_lock_nested(&ep->mtx, depth); ep_start_scan(ep, &txlist); list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; break; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } /* * The ffd.file pointer may be in the process of being torn down due to * being closed, but we may not have finished eventpoll_release() yet. * * Normally, even with the atomic_long_inc_not_zero, the file may have * been free'd and then gotten re-allocated to something else (since * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). * * But for epoll, users hold the ep->mtx mutex, and as such any file in * the process of being free'd will block in eventpoll_release_file() * and thus the underlying file allocation will not be free'd, and the * file re-use cannot happen. * * For the same reason we can avoid a rcu_read_lock() around the * operation - 'ffd.file' cannot go away even if the refcount has * reached zero (but we must still not call out to ->poll() functions * etc). */ static struct file *epi_fget(const struct epitem *epi) { struct file *file; file = epi->ffd.file; if (!file_ref_get(&file->f_ref)) file = NULL; return file; } /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct file *file = epi_fget(epi); __poll_t res; /* * We could return EPOLLERR | EPOLLHUP or something, but let's * treat this more as "file doesn't exist, poll didn't happen". */ if (!file) return 0; pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); fput(file); return res & epi->event.events; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { return __ep_eventpoll_poll(file, wait, 0); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, .unlocked_ioctl = ep_eventpoll_ioctl, .compat_ioctl = compat_ptr_ioctl, }; /* * This is called from eventpoll_release() to unlink files from the eventpoll * interface. We need to have this facility to cleanup correctly files that are * closed without being removed from the eventpoll interface. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; bool dispose; /* * Use the 'dying' flag to prevent a concurrent ep_clear_and_put() from * touching the epitems list before eventpoll_release_file() can access * the ep->mtx. */ again: spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); epi->dying = true; spin_unlock(&file->f_lock); /* * ep access is safe as we still own a reference to the ep * struct */ ep = epi->ep; mutex_lock(&ep->mtx); dispose = __ep_remove(ep, epi, true); mutex_unlock(&ep->mtx); if (dispose) ep_free(ep); goto again; } spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) { struct eventpoll *ep; ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (unlikely(!ep)) return -ENOMEM; mutex_init(&ep->mtx); rwlock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = get_current_user(); refcount_set(&ep->refcount, 1); *pep = ep; return 0; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; struct epoll_filefd ffd; ep_set_ffd(&ffd, file, fd); for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ /* * Adds a new entry to the tail of the list in a lockless way, i.e. * multiple CPUs are allowed to call this function concurrently. * * Beware: it is necessary to prevent any other modifications of the * existing list until all changes are completed, in other words * concurrent list_add_tail_lockless() calls should be protected * with a read lock, where write lock acts as a barrier which * makes sure all list_add_tail_lockless() calls are fully * completed. * * Also an element can be locklessly added to the list only in one * direction i.e. either to the tail or to the head, otherwise * concurrent access will corrupt the list. * * Return: %false if element has been already added to the list, %true * otherwise. */ static inline bool list_add_tail_lockless(struct list_head *new, struct list_head *head) { struct list_head *prev; /* * This is simple 'new->next = head' operation, but cmpxchg() * is used in order to detect that same element has been just * added to the list from another CPU: the winner observes * new->next == new. */ if (!try_cmpxchg(&new->next, &new, head)) return false; /* * Initially ->next of a new element must be updated with the head * (we are inserting to the tail) and only then pointers are atomically * exchanged. XCHG guarantees memory ordering, thus ->next should be * updated before pointers are actually swapped and pointers are * swapped before prev->next is updated. */ prev = xchg(&head->prev, new); /* * It is safe to modify prev->next and new->prev, because a new element * is added only to the tail and new->next is updated before XCHG. */ prev->next = new; new->prev = prev; return true; } /* * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, * i.e. multiple CPUs are allowed to call this function concurrently. * * Return: %false if epi element has been already chained, %true otherwise. */ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; /* Fast preliminary check */ if (epi->next != EP_UNACTIVE_PTR) return false; /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; /* Atomically exchange tail */ epi->next = xchg(&ep->ovflist, epi); return true; } /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. * * This callback takes a read lock in order not to contend with concurrent * events from another file descriptor, thus all modifications to ->rdllist * or ->ovflist are lockless. Read lock is paired with the write lock from * ep_start/done_scan(), which stops all list modifications and guarantees * that lists state is seen correctly. * * Another thing worth to mention is that ep_poll_callback() can be called * concurrently for the same @epi from different CPUs if poll table was inited * with several wait queues entries. Plural wakeup from different CPUs of a * single wait queue is serialized by wq.lock, but the case when multiple wait * queues are used should be detected accordingly. This is detected using * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; read_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { if (chain_epi_lockless(epi)) ep_pm_stay_awake_rcu(epi); } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } if (sync) wake_up_sync(&ep->wq); else wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: read_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * If we race with ep_remove_wait_queue() it can miss * ->whead = NULL and do another remove_wait_queue() after * us, so we can't use __remove_wait_queue(). */ list_del_init(&wait->entry); /* * ->whead != NULL protects us from the race with * ep_clear_and_put() or ep_remove(), ep_remove_wait_queue() * takes whead->lock held by the caller. Once we nullify it, * nothing protects ep/epi or even wait. */ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt); struct epitem *epi = epq->epi; struct eppoll_entry *pwq; if (unlikely(!epi)) // an earlier allocation has failed return; pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL); if (unlikely(!pwq)) { epq->epi = NULL; return; } init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); pwq->next = epi->pwqlist; epi->pwqlist = pwq; } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate * from a single file of interest. For example, we allow 1000 paths of length * 1, to emanate from each file of interest. This essentially represents the * potential wakeup paths, which need to be limited in order to avoid massive * uncontrolled wakeup storms. The common use case should be a single ep which * is connected to n file sources. In this case each file source has 1 path * of length 1. Thus, the numbers below should be more than sufficient. These * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify * and delete can't add additional paths. Protected by the epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count[PATH_ARR_SIZE]; static int path_count_inc(int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(void) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) path_count[i] = 0; } static int reverse_path_check_proc(struct hlist_head *refs, int depth) { int error = 0; struct epitem *epi; if (depth > EP_MAX_NESTS) /* too deep nesting */ return -1; /* CTL_DEL can remove links here, but that can't increase our count */ hlist_for_each_entry_rcu(epi, refs, fllink) { struct hlist_head *refs = &epi->ep->refs; if (hlist_empty(refs)) error = path_count_inc(depth); else error = reverse_path_check_proc(refs, depth + 1); if (error != 0) break; } return error; } /** * reverse_path_check - The tfile_check_list is list of epitem_head, which have * links that are proposed to be newly added. We need to * make sure that those added links don't add too many * paths such that we will spend all our time waking up * eventpoll objects. * * Return: %zero if the proposed links don't create too many paths, * %-1 otherwise. */ static int reverse_path_check(void) { struct epitems_head *p; for (p = tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) { int error; path_count_init(); rcu_read_lock(); error = reverse_path_check_proc(&p->epitems, 0); rcu_read_unlock(); if (error) return error; } return 0; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } static int attach_epitem(struct file *file, struct epitem *epi) { struct epitems_head *to_free = NULL; struct hlist_head *head = NULL; struct eventpoll *ep = NULL; if (is_file_epoll(file)) ep = file->private_data; if (ep) { head = &ep->refs; } else if (!READ_ONCE(file->f_ep)) { allocate: to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL); if (!to_free) return -ENOMEM; head = &to_free->epitems; } spin_lock(&file->f_lock); if (!file->f_ep) { if (unlikely(!head)) { spin_unlock(&file->f_lock); goto allocate; } /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, head); to_free = NULL; } hlist_add_head_rcu(&epi->fllink, file->f_ep); spin_unlock(&file->f_lock); free_ephead(to_free); return 0; } /* * Must be called with "mtx" held. */ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, struct file *tfile, int fd, int full_check) { int error, pwake = 0; __poll_t revents; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; if (is_file_epoll(tfile)) tep = tfile->private_data; lockdep_assert_irqs_enabled(); if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return -ENOSPC; percpu_counter_inc(&ep->user->epoll_watches); if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) { percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } /* Item initialization follow here ... */ INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; epi->next = EP_UNACTIVE_PTR; if (tep) mutex_lock_nested(&tep->mtx, 1); /* Add the current item to the list of active epoll hook for this file */ if (unlikely(attach_epitem(tfile, epi) < 0)) { if (tep) mutex_unlock(&tep->mtx); kmem_cache_free(epi_cache, epi); percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } if (full_check && !tep) list_file(tfile); /* * Add the current item to the RB tree. All RB tree operations are * protected by "mtx", and ep_insert() is called with "mtx" held. */ ep_rbtree_insert(ep, epi); if (tep) mutex_unlock(&tep->mtx); /* * ep_remove_safe() calls in the later error paths can't lead to * ep_free() as the ep file itself still holds an ep reference. */ ep_get(ep); /* now check if we've created too many backpaths */ if (unlikely(full_check && reverse_path_check())) { ep_remove_safe(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { ep_remove_safe(ep, epi); return error; } } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* * We have to check if something went wrong during the poll wait queue * install process. Namely an allocation for a wait queue failed due * high memory pressure. */ if (unlikely(!epq.epi)) { ep_remove_safe(ep, epi); return -ENOMEM; } /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { write_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; LIST_HEAD(txlist); poll_table pt; int res = 0; /* * Always short-circuit for fatal signals to allow threads to make a * timely exit without the chance of finding more events available and * fetching repeatedly. */ if (fatal_signal_pending(current)) return -EINTR; init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); ep_start_scan(ep, &txlist); /* * We can loop without lock because we are passed a task private list. * Items cannot vanish during the loop we are holding ep->mtx. */ list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { struct wakeup_source *ws; __poll_t revents; if (res >= maxevents) break; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws * below). * * This could be rearranged to delay the deactivation of epi->ws * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, we are holding ep->mtx, * so no operations coming from userspace can change the item. */ revents = ep_item_poll(epi, &pt, 1); if (!revents) continue; events = epoll_put_uevent(revents, epi->event.data, events); if (!events) { list_add(&epi->rdllink, &txlist); ep_pm_stay_awake(epi); if (!res) res = -EFAULT; break; } res++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; else if (!(epi->event.events & EPOLLET)) { /* * If this file has been added with Level * Trigger mode, we need to insert back inside * the ready list, so that the next call to * epoll_wait() will check again the events * availability. At this point, no one can insert * into ep->rdllist besides us. The epoll_ctl() * callers are locked out by * ep_send_events() holding "mtx" and the * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { struct timespec64 now; if (ms < 0) return NULL; if (!ms) { to->tv_sec = 0; to->tv_nsec = 0; return to; } to->tv_sec = ms / MSEC_PER_SEC; to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); *to = timespec64_add_safe(now, *to); return to; } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } static int ep_try_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { int res; /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of * more luck. */ res = ep_send_events(ep, events, maxevents); if (res > 0) ep_suspend_napi_irqs(ep); return res; } static int ep_schedule_timeout(ktime_t *to) { if (to) return ktime_after(*to, ktime_get()); else return 1; } /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * timespec. If the timeout is zero, the function will not block, * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * * Return: the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout) { int res, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; *to = timespec64_to_ktime(*timeout); } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. */ timed_out = 1; } /* * This call is racy: We may or may not see events that are being added * to the ready list under the lock (e.g., in IRQ callbacks). For cases * with a non-zero timeout, this thread will check the ready list under * lock and will add to the wait queue. For cases with a zero * timeout, the user by definition should not care and will have to * recheck again. */ eavail = ep_events_available(ep); while (1) { if (eavail) { res = ep_try_send_events(ep, events, maxevents); if (res) return res; } if (timed_out) return 0; eavail = ep_busy_loop(ep); if (eavail) continue; if (signal_pending(current)) return -EINTR; /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; write_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); write_unlock_irq(&ep->lock); if (!eavail) timed_out = !ep_schedule_timeout(to) || !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = 1; if (!list_empty_careful(&wait.entry)) { write_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its * timeout expired before it could reacquire the lock. * Thus, when wait.entry is empty, it needs to harvest * events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); write_unlock_irq(&ep->lock); } } } /** * ep_loop_check_proc - verify that adding an epoll file inside another * epoll structure does not violate the constraints, in * terms of closed loops, or too deep chains (which can * result in excessive stack usage). * * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * * Return: %zero if adding the epoll @file inside current epoll * structure @ep does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check_proc(struct eventpoll *ep, int depth) { int error = 0; struct rb_node *rbp; struct epitem *epi; mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit->gen == loop_check_gen) continue; if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS) error = -1; else error = ep_loop_check_proc(ep_tovisit, depth + 1); if (error != 0) break; } else { /* * If we've reached a file that is not associated with * an ep, then we need to check if the newly added * links are going to add too many wakeup paths. We do * this by adding it to the tfile_check_list, if it's * not already there, and calling reverse_path_check() * during ep_insert(). */ list_file(epi->ffd.file); } } mutex_unlock(&ep->mtx); return error; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@to) * into another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ep: Pointer to the epoll we are inserting into. * @to: Pointer to the epoll to be inserted. * * Return: %zero if adding the epoll @to inside the epoll @from * does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to) { inserting_into = ep; return ep_loop_check_proc(to, 0); } static void clear_tfile_check_list(void) { rcu_read_lock(); while (tfile_check_list != EP_UNACTIVE_PTR) { struct epitems_head *head = tfile_check_list; tfile_check_list = head->next; unlist_file(head); } rcu_read_unlock(); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error, fd; struct eventpoll *ep = NULL; struct file *file; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC)); if (fd < 0) { error = fd; goto out_free_ep; } file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC)); if (IS_ERR(file)) { error = PTR_ERR(file); goto out_free_fd; } ep->file = file; fd_install(fd, file); return fd; out_free_fd: put_unused_fd(fd); out_free_ep: ep_clear_and_put(ep); return error; } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif static inline int epoll_mutex_lock(struct mutex *mutex, int depth, bool nonblock) { if (!nonblock) { mutex_lock_nested(mutex, depth); return 0; } if (mutex_trylock(mutex)) return 0; return -EAGAIN; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { int error; int full_check = 0; struct eventpoll *ep; struct epitem *epi; struct eventpoll *tep = NULL; CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; /* Get the "struct file *" for the target file */ CLASS(fd, tf)(fd); if (fd_empty(tf)) return -EBADF; /* The target file descriptor must support poll */ if (!file_can_poll(fd_file(tf))) return -EPERM; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * We have to check that the file structure underneath the file descriptor * the user passed to us _is_ an eventpoll file. And also we do not permit * adding an epoll file descriptor inside itself. */ error = -EINVAL; if (fd_file(f) == fd_file(tf) || !is_file_epoll(fd_file(f))) goto error_tgt_fput; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; if (op == EPOLL_CTL_ADD && (is_file_epoll(fd_file(tf)) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) goto error_tgt_fput; } /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* * When we insert an epoll file descriptor inside another epoll file * descriptor, there is the chance of creating closed loops, which are * better be handled here, than in more critical paths. While we are * checking for loops we also determine the list of files reachable * and hang them on the tfile_check_list, so we can check that we * haven't created too many possible wakeup paths. * * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when * the epoll file descriptor is attaching directly to a wakeup source, * unless the epoll file descriptor is nested. The purpose of taking the * 'epnested_mutex' on add is to prevent complex toplogies such as loops and * deep wakeup paths from forming in parallel through multiple * EPOLL_CTL_ADD operations. */ error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (READ_ONCE(fd_file(f)->f_ep) || ep->gen == loop_check_gen || is_file_epoll(fd_file(tf))) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; full_check = 1; if (is_file_epoll(fd_file(tf))) { tep = fd_file(tf)->private_data; error = -ELOOP; if (ep_loop_check(ep, tep) != 0) goto error_tgt_fput; } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; } } /* * Try to lookup the file inside our RB tree. Since we grabbed "mtx" * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ epi = ep_find(ep, fd_file(tf), fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(ep, epds, fd_file(tf), fd, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) { /* * The eventpoll itself is still alive: the refcount * can't go to zero here. */ ep_remove_safe(ep, epi); error = 0; } else { error = -ENOENT; } break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } mutex_unlock(&ep->mtx); error_tgt_fput: if (full_check) { clear_tfile_check_list(); loop_check_gen++; mutex_unlock(&epnested_mutex); } return error; } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } static int ep_check_params(struct file *file, struct epoll_event __user *evs, int maxevents) { /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(evs, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ if (!is_file_epoll(file)) return -EINVAL; return 0; } int epoll_sendevents(struct file *file, struct epoll_event __user *events, int maxevents) { struct eventpoll *ep; int ret; ret = ep_check_params(file, events, maxevents); if (unlikely(ret)) return ret; ep = file->private_data; /* * Racy call, but that's ok - it should get retried based on * poll readiness anyway. */ if (ep_events_available(ep)) return ep_try_send_events(ep, events, maxevents); return 0; } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to) { struct eventpoll *ep; int ret; /* Get the "struct file *" for the eventpoll file */ CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; ret = ep_check_params(fd_file(f), events, maxevents); if (unlikely(ret)) return ret; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* Time to fish for events ... */ return ep_poll(ep, events, maxevents, to); } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { struct timespec64 to; return do_epoll_wait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ static int do_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to, const sigset_t __user *sigmask, size_t sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, to); restore_saved_sigmask_unless(error == -EINTR); return error; } SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 to; return do_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #ifdef CONFIG_COMPAT static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 to; return do_compat_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_compat_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 19 84 44 41 113 25 1 4 4 2136 2140 472 472 326 307 154 192 113 | 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 | #include <linux/init.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/net_namespace.h> #include <net/netfilter/nf_tables.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter_arp.h> #include <net/netfilter/nf_tables_ipv4.h> #include <net/netfilter/nf_tables_ipv6.h> #ifdef CONFIG_NF_TABLES_IPV4 static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); nft_set_pktinfo_ipv4(&pkt); return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_ipv4 = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_IPV4, .hook_mask = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_LOCAL_IN] = nft_do_chain_ipv4, [NF_INET_LOCAL_OUT] = nft_do_chain_ipv4, [NF_INET_FORWARD] = nft_do_chain_ipv4, [NF_INET_PRE_ROUTING] = nft_do_chain_ipv4, [NF_INET_POST_ROUTING] = nft_do_chain_ipv4, }, }; static void nft_chain_filter_ipv4_init(void) { nft_register_chain_type(&nft_chain_filter_ipv4); } static void nft_chain_filter_ipv4_fini(void) { nft_unregister_chain_type(&nft_chain_filter_ipv4); } #else static inline void nft_chain_filter_ipv4_init(void) {} static inline void nft_chain_filter_ipv4_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV4 */ #ifdef CONFIG_NF_TABLES_ARP static unsigned int nft_do_chain_arp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); nft_set_pktinfo_unspec(&pkt); return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_arp = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_ARP, .owner = THIS_MODULE, .hook_mask = (1 << NF_ARP_IN) | (1 << NF_ARP_OUT), .hooks = { [NF_ARP_IN] = nft_do_chain_arp, [NF_ARP_OUT] = nft_do_chain_arp, }, }; static void nft_chain_filter_arp_init(void) { nft_register_chain_type(&nft_chain_filter_arp); } static void nft_chain_filter_arp_fini(void) { nft_unregister_chain_type(&nft_chain_filter_arp); } #else static inline void nft_chain_filter_arp_init(void) {} static inline void nft_chain_filter_arp_fini(void) {} #endif /* CONFIG_NF_TABLES_ARP */ #ifdef CONFIG_NF_TABLES_IPV6 static unsigned int nft_do_chain_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); nft_set_pktinfo_ipv6(&pkt); return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_ipv6 = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_IPV6, .hook_mask = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_LOCAL_IN] = nft_do_chain_ipv6, [NF_INET_LOCAL_OUT] = nft_do_chain_ipv6, [NF_INET_FORWARD] = nft_do_chain_ipv6, [NF_INET_PRE_ROUTING] = nft_do_chain_ipv6, [NF_INET_POST_ROUTING] = nft_do_chain_ipv6, }, }; static void nft_chain_filter_ipv6_init(void) { nft_register_chain_type(&nft_chain_filter_ipv6); } static void nft_chain_filter_ipv6_fini(void) { nft_unregister_chain_type(&nft_chain_filter_ipv6); } #else static inline void nft_chain_filter_ipv6_init(void) {} static inline void nft_chain_filter_ipv6_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ #ifdef CONFIG_NF_TABLES_INET static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (state->pf) { case NFPROTO_IPV4: nft_set_pktinfo_ipv4(&pkt); break; case NFPROTO_IPV6: nft_set_pktinfo_ipv6(&pkt); break; default: break; } return nft_do_chain(&pkt, priv); } static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_hook_state ingress_state = *state; struct nft_pktinfo pkt; switch (skb->protocol) { case htons(ETH_P_IP): /* Original hook is NFPROTO_NETDEV and NF_NETDEV_INGRESS. */ ingress_state.pf = NFPROTO_IPV4; ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); if (nft_set_pktinfo_ipv4_ingress(&pkt) < 0) return NF_DROP; break; case htons(ETH_P_IPV6): ingress_state.pf = NFPROTO_IPV6; ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); if (nft_set_pktinfo_ipv6_ingress(&pkt) < 0) return NF_DROP; break; default: return NF_ACCEPT; } return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_inet = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_INET, .hook_mask = (1 << NF_INET_INGRESS) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_INGRESS] = nft_do_chain_inet_ingress, [NF_INET_LOCAL_IN] = nft_do_chain_inet, [NF_INET_LOCAL_OUT] = nft_do_chain_inet, [NF_INET_FORWARD] = nft_do_chain_inet, [NF_INET_PRE_ROUTING] = nft_do_chain_inet, [NF_INET_POST_ROUTING] = nft_do_chain_inet, }, }; static void nft_chain_filter_inet_init(void) { nft_register_chain_type(&nft_chain_filter_inet); } static void nft_chain_filter_inet_fini(void) { nft_unregister_chain_type(&nft_chain_filter_inet); } #else static inline void nft_chain_filter_inet_init(void) {} static inline void nft_chain_filter_inet_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ #if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) static unsigned int nft_do_chain_bridge(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): nft_set_pktinfo_ipv6_validate(&pkt); break; default: nft_set_pktinfo_unspec(&pkt); break; } return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_bridge = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_BRIDGE, .hook_mask = (1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | (1 << NF_BR_LOCAL_OUT) | (1 << NF_BR_POST_ROUTING), .hooks = { [NF_BR_PRE_ROUTING] = nft_do_chain_bridge, [NF_BR_LOCAL_IN] = nft_do_chain_bridge, [NF_BR_FORWARD] = nft_do_chain_bridge, [NF_BR_LOCAL_OUT] = nft_do_chain_bridge, [NF_BR_POST_ROUTING] = nft_do_chain_bridge, }, }; static void nft_chain_filter_bridge_init(void) { nft_register_chain_type(&nft_chain_filter_bridge); } static void nft_chain_filter_bridge_fini(void) { nft_unregister_chain_type(&nft_chain_filter_bridge); } #else static inline void nft_chain_filter_bridge_init(void) {} static inline void nft_chain_filter_bridge_fini(void) {} #endif /* CONFIG_NF_TABLES_BRIDGE */ #ifdef CONFIG_NF_TABLES_NETDEV static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (skb->protocol) { case htons(ETH_P_IP): nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): nft_set_pktinfo_ipv6_validate(&pkt); break; default: nft_set_pktinfo_unspec(&pkt); break; } return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, .hook_mask = (1 << NF_NETDEV_INGRESS) | (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; static void nft_netdev_event(unsigned long event, struct net_device *dev, struct nft_base_chain *basechain) { struct nft_hook *hook; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; if (!(basechain->chain.table->flags & NFT_TABLE_F_DORMANT)) nf_unregister_net_hook(dev_net(dev), &hook->ops); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); break; } } static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_base_chain *basechain; struct nftables_pernet *nft_net; struct nft_chain *chain; struct nft_table *table; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(dev_net(dev)); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV && table->family != NFPROTO_INET) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) continue; basechain = nft_base_chain(chain); if (table->family == NFPROTO_INET && basechain->ops.hooknum != NF_INET_INGRESS) continue; nft_netdev_event(event, dev, basechain); } } mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nf_tables_netdev_notifier = { .notifier_call = nf_tables_netdev_event, }; static int nft_chain_filter_netdev_init(void) { int err; nft_register_chain_type(&nft_chain_filter_netdev); err = register_netdevice_notifier(&nf_tables_netdev_notifier); if (err) goto err_register_netdevice_notifier; return 0; err_register_netdevice_notifier: nft_unregister_chain_type(&nft_chain_filter_netdev); return err; } static void nft_chain_filter_netdev_fini(void) { nft_unregister_chain_type(&nft_chain_filter_netdev); unregister_netdevice_notifier(&nf_tables_netdev_notifier); } #else static inline int nft_chain_filter_netdev_init(void) { return 0; } static inline void nft_chain_filter_netdev_fini(void) {} #endif /* CONFIG_NF_TABLES_NETDEV */ int __init nft_chain_filter_init(void) { int err; err = nft_chain_filter_netdev_init(); if (err < 0) return err; nft_chain_filter_ipv4_init(); nft_chain_filter_ipv6_init(); nft_chain_filter_arp_init(); nft_chain_filter_inet_init(); nft_chain_filter_bridge_init(); return 0; } void nft_chain_filter_fini(void) { nft_chain_filter_bridge_fini(); nft_chain_filter_inet_fini(); nft_chain_filter_arp_fini(); nft_chain_filter_ipv6_fini(); nft_chain_filter_ipv4_fini(); nft_chain_filter_netdev_fini(); } |
| 4 1 4 10 10 1 4 4 4 5 11 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Stream Parser * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #include <linux/bpf.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/file.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/init.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> #include <net/strparser.h> #include <net/netns/generic.h> #include <net/sock.h> static struct workqueue_struct *strp_wq; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) { return (struct _strp_msg *)((void *)skb->cb + offsetof(struct sk_skb_cb, strp)); } /* Lower lock held */ static void strp_abort_strp(struct strparser *strp, int err) { /* Unrecoverable error in receive */ cancel_delayed_work(&strp->msg_timer_work); if (strp->stopped) return; strp->stopped = 1; if (strp->sk) { struct sock *sk = strp->sk; /* Report an error on the lower socket */ sk->sk_err = -err; sk_error_report(sk); } } static void strp_start_timer(struct strparser *strp, long timeo) { if (timeo && timeo != LONG_MAX) mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } /* Lower lock held */ static void strp_parser_err(struct strparser *strp, int err, read_descriptor_t *desc) { desc->error = err; kfree_skb(strp->skb_head); strp->skb_head = NULL; strp->cb.abort_parser(strp, err); } static inline int strp_peek_len(struct strparser *strp) { if (strp->sk) { struct socket *sock = strp->sk->sk_socket; return sock->ops->peek_len(sock); } /* If we don't have an associated socket there's nothing to peek. * Return int max to avoid stopping the strparser. */ return INT_MAX; } /* Lower socket lock held */ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len, size_t max_msg_size, long timeo) { struct strparser *strp = (struct strparser *)desc->arg.data; struct _strp_msg *stm; struct sk_buff *head, *skb; size_t eaten = 0, cand_len; ssize_t extra; int err; bool cloned_orig = false; if (strp->paused) return 0; head = strp->skb_head; if (head) { /* Message already in progress */ if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we * need to clone and pull since we can't deal with * offsets in the skbs for a message expect in the head. */ orig_skb = skb_clone(orig_skb, GFP_ATOMIC); if (!orig_skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; return 0; } if (!pskb_pull(orig_skb, orig_offset)) { STRP_STATS_INCR(strp->stats.mem_fail); kfree_skb(orig_skb); desc->error = -ENOMEM; return 0; } cloned_orig = true; orig_offset = 0; } if (!strp->skb_nextp) { /* We are going to append to the frags_list of head. * Need to unshare the frag_list. */ err = skb_unclone(head, GFP_ATOMIC); if (err) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = err; return 0; } if (unlikely(skb_shinfo(head)->frag_list)) { /* We can't append to an sk_buff that already * has a frag_list. We create a new head, point * the frag_list of that to the old head, and * then are able to use the old head->next for * appending to the message. */ if (WARN_ON(head->next)) { desc->error = -EINVAL; return 0; } skb = alloc_skb_for_msg(head); if (!skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; return 0; } strp->skb_nextp = &head->next; strp->skb_head = skb; head = skb; } else { strp->skb_nextp = &skb_shinfo(head)->frag_list; } } } while (eaten < orig_len) { /* Always clone since we will consume something */ skb = skb_clone(orig_skb, GFP_ATOMIC); if (!skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; break; } cand_len = orig_len - eaten; head = strp->skb_head; if (!head) { head = skb; strp->skb_head = head; /* Will set skb_nextp on next packet if needed */ strp->skb_nextp = NULL; stm = _strp_msg(head); memset(stm, 0, sizeof(*stm)); stm->strp.offset = orig_offset + eaten; } else { /* Unclone if we are appending to an skb that we * already share a frag_list with. */ if (skb_has_frag_list(skb)) { err = skb_unclone(skb, GFP_ATOMIC); if (err) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = err; break; } } stm = _strp_msg(head); *strp->skb_nextp = skb; strp->skb_nextp = &skb->next; head->data_len += skb->len; head->len += skb->len; head->truesize += skb->truesize; } if (!stm->strp.full_len) { ssize_t len; len = (*strp->cb.parse_msg)(strp, head); if (!len) { /* Need more header to determine length */ if (!stm->accum_len) { /* Start RX timer for new message */ strp_start_timer(strp, timeo); } stm->accum_len += cand_len; eaten += cand_len; STRP_STATS_INCR(strp->stats.need_more_hdr); WARN_ON(eaten != orig_len); break; } else if (len < 0) { if (len == -ESTRPIPE && stm->accum_len) { len = -ENODATA; strp->unrecov_intr = 1; } else { strp->interrupted = 1; } strp_parser_err(strp, len, desc); break; } else if (len > max_msg_size) { /* Message length exceeds maximum allowed */ STRP_STATS_INCR(strp->stats.msg_too_big); strp_parser_err(strp, -EMSGSIZE, desc); break; } else if (len <= (ssize_t)head->len - skb->len - stm->strp.offset) { /* Length must be into new skb (and also * greater than zero) */ STRP_STATS_INCR(strp->stats.bad_hdr_len); strp_parser_err(strp, -EPROTO, desc); break; } stm->strp.full_len = len; } extra = (ssize_t)(stm->accum_len + cand_len) - stm->strp.full_len; if (extra < 0) { /* Message not complete yet. */ if (stm->strp.full_len - stm->accum_len > strp_peek_len(strp)) { /* Don't have the whole message in the socket * buffer. Set strp->need_bytes to wait for * the rest of the message. Also, set "early * eaten" since we've already buffered the skb * but don't consume yet per strp_read_sock. */ if (!stm->accum_len) { /* Start RX timer for new message */ strp_start_timer(strp, timeo); } stm->accum_len += cand_len; eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; } stm->accum_len += cand_len; eaten += cand_len; WARN_ON(eaten != orig_len); break; } /* Positive extra indicates more bytes than needed for the * message */ WARN_ON(extra > cand_len); eaten += (cand_len - extra); /* Hurray, we have a new message! */ cancel_delayed_work(&strp->msg_timer_work); strp->skb_head = NULL; strp->need_bytes = 0; STRP_STATS_INCR(strp->stats.msgs); /* Give skb to upper layer */ strp->cb.rcv_msg(strp, head); if (unlikely(strp->paused)) { /* Upper layer paused strp */ break; } } if (cloned_orig) kfree_skb(orig_skb); STRP_STATS_ADD(strp->stats.bytes, eaten); return eaten; } int strp_process(struct strparser *strp, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len, size_t max_msg_size, long timeo) { read_descriptor_t desc; /* Dummy arg to strp_recv */ desc.arg.data = strp; return __strp_recv(&desc, orig_skb, orig_offset, orig_len, max_msg_size, timeo); } EXPORT_SYMBOL_GPL(strp_process); static int strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len) { struct strparser *strp = (struct strparser *)desc->arg.data; return __strp_recv(desc, orig_skb, orig_offset, orig_len, strp->sk->sk_rcvbuf, strp->sk->sk_rcvtimeo); } static int default_read_sock_done(struct strparser *strp, int err) { return err; } /* Called with lock held on lower socket */ static int strp_read_sock(struct strparser *strp) { struct socket *sock = strp->sk->sk_socket; read_descriptor_t desc; if (unlikely(!sock || !sock->ops)) return -EBUSY; if (unlikely(!strp->cb.read_sock && !sock->ops->read_sock)) return -EBUSY; desc.arg.data = strp; desc.error = 0; desc.count = 1; /* give more than one skb per call */ /* sk should be locked here, so okay to do read_sock */ if (strp->cb.read_sock) strp->cb.read_sock(strp, &desc, strp_recv); else sock->ops->read_sock(strp->sk, &desc, strp_recv); desc.error = strp->cb.read_sock_done(strp, desc.error); return desc.error; } /* Lower sock lock held */ void strp_data_ready(struct strparser *strp) { if (unlikely(strp->stopped) || strp->paused) return; /* This check is needed to synchronize with do_strp_work. * do_strp_work acquires a process lock (lock_sock) whereas * the lock held here is bh_lock_sock. The two locks can be * held by different threads at the same time, but bh_lock_sock * allows a thread in BH context to safely check if the process * lock is held. In this case, if the lock is held, queue work. */ if (sock_owned_by_user_nocheck(strp->sk)) { queue_work(strp_wq, &strp->work); return; } if (strp->need_bytes) { if (strp_peek_len(strp) < strp->need_bytes) return; } if (strp_read_sock(strp) == -ENOMEM) queue_work(strp_wq, &strp->work); } EXPORT_SYMBOL_GPL(strp_data_ready); static void do_strp_work(struct strparser *strp) { /* We need the read lock to synchronize with strp_data_ready. We * need the socket lock for calling strp_read_sock. */ strp->cb.lock(strp); if (unlikely(strp->stopped)) goto out; if (strp->paused) goto out; if (strp_read_sock(strp) == -ENOMEM) queue_work(strp_wq, &strp->work); out: strp->cb.unlock(strp); } static void strp_work(struct work_struct *w) { do_strp_work(container_of(w, struct strparser, work)); } static void strp_msg_timeout(struct work_struct *w) { struct strparser *strp = container_of(w, struct strparser, msg_timer_work.work); /* Message assembly timed out */ STRP_STATS_INCR(strp->stats.msg_timeouts); strp->cb.lock(strp); strp->cb.abort_parser(strp, -ETIMEDOUT); strp->cb.unlock(strp); } static void strp_sock_lock(struct strparser *strp) { lock_sock(strp->sk); } static void strp_sock_unlock(struct strparser *strp) { release_sock(strp->sk); } int strp_init(struct strparser *strp, struct sock *sk, const struct strp_callbacks *cb) { if (!cb || !cb->rcv_msg || !cb->parse_msg) return -EINVAL; /* The sk (sock) arg determines the mode of the stream parser. * * If the sock is set then the strparser is in receive callback mode. * The upper layer calls strp_data_ready to kick receive processing * and strparser calls the read_sock function on the socket to * get packets. * * If the sock is not set then the strparser is in general mode. * The upper layer calls strp_process for each skb to be parsed. */ if (!sk) { if (!cb->lock || !cb->unlock) return -EINVAL; } memset(strp, 0, sizeof(*strp)); strp->sk = sk; strp->cb.lock = cb->lock ? : strp_sock_lock; strp->cb.unlock = cb->unlock ? : strp_sock_unlock; strp->cb.rcv_msg = cb->rcv_msg; strp->cb.parse_msg = cb->parse_msg; strp->cb.read_sock = cb->read_sock; strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done; strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp; INIT_DELAYED_WORK(&strp->msg_timer_work, strp_msg_timeout); INIT_WORK(&strp->work, strp_work); return 0; } EXPORT_SYMBOL_GPL(strp_init); void strp_unpause(struct strparser *strp) { strp->paused = 0; /* Sync setting paused with RX work */ smp_mb(); queue_work(strp_wq, &strp->work); } EXPORT_SYMBOL_GPL(strp_unpause); /* strp must already be stopped so that strp_recv will no longer be called. * Note that strp_done is not called with the lower socket held. */ void strp_done(struct strparser *strp) { WARN_ON(!strp->stopped); cancel_delayed_work_sync(&strp->msg_timer_work); cancel_work_sync(&strp->work); if (strp->skb_head) { kfree_skb(strp->skb_head); strp->skb_head = NULL; } } EXPORT_SYMBOL_GPL(strp_done); void strp_stop(struct strparser *strp) { strp->stopped = 1; } EXPORT_SYMBOL_GPL(strp_stop); void strp_check_rcv(struct strparser *strp) { queue_work(strp_wq, &strp->work); } EXPORT_SYMBOL_GPL(strp_check_rcv); static int __init strp_dev_init(void) { BUILD_BUG_ON(sizeof(struct sk_skb_cb) > sizeof_field(struct sk_buff, cb)); strp_wq = create_singlethread_workqueue("kstrp"); if (unlikely(!strp_wq)) return -ENOMEM; return 0; } device_initcall(strp_dev_init); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2009 IBM Corporation * Author: Mimi Zohar <zohar@us.ibm.com> */ #ifndef _LINUX_INTEGRITY_H #define _LINUX_INTEGRITY_H #include <linux/fs.h> #include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_PASS_IMMUTABLE, INTEGRITY_FAIL, INTEGRITY_FAIL_IMMUTABLE, INTEGRITY_NOLABEL, INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, }; #ifdef CONFIG_INTEGRITY extern void __init integrity_load_keys(void); #else static inline void integrity_load_keys(void) { } #endif /* CONFIG_INTEGRITY */ /* An inode's attributes for detection of changes */ struct integrity_inode_attributes { u64 version; /* track inode changes */ unsigned long ino; dev_t dev; }; /* * On stacked filesystems the i_version alone is not enough to detect file data * or metadata change. Additional metadata is required. */ static inline void integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, u64 i_version, const struct inode *inode) { attrs->version = i_version; attrs->dev = inode->i_sb->s_dev; attrs->ino = inode->i_ino; } /* * On stacked filesystems detect whether the inode or its content has changed. */ static inline bool integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, const struct inode *inode) { return (inode->i_sb->s_dev != attrs->dev || inode->i_ino != attrs->ino || !inode_eq_iversion(inode, attrs->version)); } #endif /* _LINUX_INTEGRITY_H */ |
| 8 8 8 8 8 8 4 4 25 6 17 5 15 15 8 35 35 5 25 5 2 2 27 3 2 4 4 4 4 4 4 4 4 4 61 61 4 1 1 56 49 54 57 57 56 4 4 4 4 4 7 7 2 2 2 2 2 1 1 1 1 1 1 1 1 1 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 5 5 5 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 1 1 1 2 2 3 3 3 1 2 3 1 3 3 3 1 2 3 3 3 3 3 3 3 2 1 2 1 3 1 2 2 2 2 2 1 1 1 1 1 1 1 2 2 17 17 15 3 1 2 2 1 1 32 31 3 1 1 10 48 3 3 23 16 7 22 1 1 18 4 18 3 2 15 2 3 14 4 15 3 7 7 7 4 6 6 6 6 1 6 118 118 115 6 6 7 7 7 7 10 1 9 7 7 7 7 7 17 16 3 7 9 9 9 9 9 2 2 2 8 8 2 6 8 8 8 8 2 8 8 7 1 6 2 8 8 8 3 23 23 20 20 48 3 47 3 47 35 30 2 30 2 115 116 116 116 5 99 41 116 60 59 3 61 61 4 125 126 125 124 126 125 125 126 126 126 139 139 11 105 24 139 4 4 4 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 configuration hooks for cfg80211 * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> #include <linux/fips.h> #include <linux/if_ether.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wme.h" static struct ieee80211_link_data * ieee80211_link_or_deflink(struct ieee80211_sub_if_data *sdata, int link_id, bool require_valid) { struct ieee80211_link_data *link; if (link_id < 0) { /* * For keys, if sdata is not an MLD, we might not use * the return value at all (if it's not a pairwise key), * so in that case (require_valid==false) don't error. */ if (require_valid && ieee80211_vif_is_mld(&sdata->vif)) return ERR_PTR(-EINVAL); return &sdata->deflink; } link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return ERR_PTR(-ENOLINK); return link; } static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { bool mu_mimo_groups = false; bool mu_mimo_follow = false; if (params->vht_mumimo_groups) { u64 membership; BUILD_BUG_ON(sizeof(membership) != WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.position, params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN, WLAN_USER_POSITION_LEN); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MU_GROUPS); /* don't care about endianness - just check for 0 */ memcpy(&membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); mu_mimo_groups = membership != 0; } if (params->vht_mumimo_follow_addr) { mu_mimo_follow = is_valid_ether_addr(params->vht_mumimo_follow_addr); ether_addr_copy(sdata->u.mntr.mu_follow_addr, params->vht_mumimo_follow_addr); } sdata->vif.bss_conf.mu_mimo_owner = mu_mimo_groups || mu_mimo_follow; } static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *monitor_sdata; /* check flags first */ if (params->flags && ieee80211_sdata_running(sdata)) { u32 mask = MONITOR_FLAG_ACTIVE; /* * Prohibit MONITOR_FLAG_ACTIVE to be changed * while the interface is up. * Else we would need to add a lot of cruft * to update everything: * monitor and all fif_* counters * reconfigure hardware */ if ((params->flags & mask) != (sdata->u.mntr.flags & mask)) return -EBUSY; } /* also validate MU-MIMO change */ if (ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) monitor_sdata = sdata; else monitor_sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!monitor_sdata && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) return -EOPNOTSUPP; /* apply all changes now - no failures allowed */ if (monitor_sdata && (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) || ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR))) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { if (ieee80211_sdata_running(sdata)) { ieee80211_adjust_monitor_flags(sdata, -1); sdata->u.mntr.flags = params->flags; ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); } else { /* * Because the interface is down, ieee80211_do_stop * and ieee80211_do_open take care of "everything" * mentioned in the comment above. */ sdata->u.mntr.flags = params->flags; } } return 0; } static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata, struct cfg80211_mbssid_config *params, struct ieee80211_bss_conf *link_conf) { struct ieee80211_sub_if_data *tx_sdata; struct ieee80211_bss_conf *old; link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; link_conf->bssid_indicator = 0; if (sdata->vif.type != NL80211_IFTYPE_AP || !params->tx_wdev) return -EINVAL; old = sdata_dereference(link_conf->tx_bss_conf, sdata); if (old) return -EALREADY; tx_sdata = IEEE80211_WDEV_TO_SUB_IF(params->tx_wdev); if (!tx_sdata) return -EINVAL; if (tx_sdata == sdata) { rcu_assign_pointer(link_conf->tx_bss_conf, link_conf); } else { struct ieee80211_bss_conf *tx_bss_conf; tx_bss_conf = sdata_dereference(tx_sdata->vif.link_conf[params->tx_link_id], sdata); if (rcu_access_pointer(tx_bss_conf->tx_bss_conf) != tx_bss_conf) return -EINVAL; rcu_assign_pointer(link_conf->tx_bss_conf, tx_bss_conf); link_conf->nontransmitted = true; link_conf->bssid_index = params->index; } if (params->ema) link_conf->ema_ap = true; return 0; } static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, const char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct wireless_dev *wdev; struct ieee80211_sub_if_data *sdata; int err; err = ieee80211_if_add(local, name, name_assign_type, &wdev, type, params); if (err) return ERR_PTR(err); sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (type == NL80211_IFTYPE_MONITOR) { err = ieee80211_set_mon_options(sdata, params); if (err) { ieee80211_if_remove(sdata); return NULL; } } /* Let the driver know that an interface is going to be added. * Indicate so only for interface types that will be added to the * driver. */ switch (type) { case NL80211_IFTYPE_AP_VLAN: break; case NL80211_IFTYPE_MONITOR: if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) || !(params->flags & MONITOR_FLAG_ACTIVE)) break; fallthrough; default: drv_prep_add_interface(local, ieee80211_vif_type_p2p(&sdata->vif)); break; } return wdev; } static int ieee80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_if_remove(IEEE80211_WDEV_TO_SUB_IF(wdev)); return 0; } static int ieee80211_change_iface(struct wiphy *wiphy, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret; lockdep_assert_wiphy(local->hw.wiphy); ret = ieee80211_if_change_type(sdata, type); if (ret) return ret; if (type == NL80211_IFTYPE_AP_VLAN && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; if (params->use_4addr == ifmgd->use_4addr) return 0; /* FIXME: no support for 4-addr MLO yet */ if (ieee80211_vif_is_mld(&sdata->vif)) return -EOPNOTSUPP; sdata->u.mgd.use_4addr = params->use_4addr; if (!ifmgd->associated) return 0; sta = sta_info_get(sdata, sdata->deflink.u.mgd.bssid); if (sta) drv_sta_set_4addr(local, sdata, &sta->sta, params->use_4addr); if (params->use_4addr) ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { ret = ieee80211_set_mon_options(sdata, params); if (ret) return ret; } return 0; } static int ieee80211_start_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); ret = ieee80211_check_combinations(sdata, NULL, 0, 0, -1); if (ret < 0) return ret; return ieee80211_do_open(wdev, true); } static void ieee80211_stop_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_sdata_stop(IEEE80211_WDEV_TO_SUB_IF(wdev)); } static int ieee80211_start_nan(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); ret = ieee80211_check_combinations(sdata, NULL, 0, 0, -1); if (ret < 0) return ret; ret = ieee80211_do_open(wdev, true); if (ret) return ret; ret = drv_start_nan(sdata->local, sdata, conf); if (ret) ieee80211_sdata_stop(sdata); sdata->u.nan.conf = *conf; return ret; } static void ieee80211_stop_nan(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); drv_stop_nan(sdata->local, sdata); ieee80211_sdata_stop(sdata); } static int ieee80211_nan_change_conf(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_conf new_conf; int ret = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; new_conf = sdata->u.nan.conf; if (changes & CFG80211_NAN_CONF_CHANGED_PREF) new_conf.master_pref = conf->master_pref; if (changes & CFG80211_NAN_CONF_CHANGED_BANDS) new_conf.bands = conf->bands; ret = drv_nan_change_conf(sdata->local, sdata, &new_conf, changes); if (!ret) sdata->u.nan.conf = new_conf; return ret; } static int ieee80211_add_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; spin_lock_bh(&sdata->u.nan.func_lock); ret = idr_alloc(&sdata->u.nan.function_inst_ids, nan_func, 1, sdata->local->hw.max_nan_de_entries + 1, GFP_ATOMIC); spin_unlock_bh(&sdata->u.nan.func_lock); if (ret < 0) return ret; nan_func->instance_id = ret; WARN_ON(nan_func->instance_id == 0); ret = drv_add_nan_func(sdata->local, sdata, nan_func); if (ret) { spin_lock_bh(&sdata->u.nan.func_lock); idr_remove(&sdata->u.nan.function_inst_ids, nan_func->instance_id); spin_unlock_bh(&sdata->u.nan.func_lock); } return ret; } static struct cfg80211_nan_func * ieee80211_find_nan_func_by_cookie(struct ieee80211_sub_if_data *sdata, u64 cookie) { struct cfg80211_nan_func *func; int id; lockdep_assert_held(&sdata->u.nan.func_lock); idr_for_each_entry(&sdata->u.nan.function_inst_ids, func, id) { if (func->cookie == cookie) return func; } return NULL; } static void ieee80211_del_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_func *func; u8 instance_id = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN || !ieee80211_sdata_running(sdata)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = ieee80211_find_nan_func_by_cookie(sdata, cookie); if (func) instance_id = func->instance_id; spin_unlock_bh(&sdata->u.nan.func_lock); if (instance_id) drv_del_nan_func(sdata->local, sdata, instance_id); } static int ieee80211_set_noack_map(struct wiphy *wiphy, struct net_device *dev, u16 noack_map) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->noack_map = noack_map; ieee80211_check_fast_xmit_iface(sdata); return 0; } static int ieee80211_set_tx(struct ieee80211_sub_if_data *sdata, const u8 *mac_addr, u8 key_idx) { struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; struct sta_info *sta; int ret = -EINVAL; if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) return -EINVAL; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return -EINVAL; if (sta->ptk_idx == key_idx) return 0; key = wiphy_dereference(local->hw.wiphy, sta->ptk[key_idx]); if (key && key->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX) ret = ieee80211_set_tx_key(key); return ret; } static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, struct key_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); struct ieee80211_local *local = sdata->local; struct sta_info *sta = NULL; struct ieee80211_key *key; int err; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; if (IS_ERR(link)) return PTR_ERR(link); if (WARN_ON(pairwise && link_id >= 0)) return -EINVAL; if (pairwise && params->mode == NL80211_KEY_SET_TX) return ieee80211_set_tx(sdata, mac_addr, key_idx); /* reject WEP and TKIP keys if WEP failed to initialize */ switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_WEP104: if (link_id >= 0) return -EINVAL; if (WARN_ON_ONCE(fips_enabled)) return -EINVAL; break; default: break; } key = ieee80211_key_alloc(params->cipher, key_idx, params->key_len, params->key, params->seq_len, params->seq); if (IS_ERR(key)) return PTR_ERR(key); if (pairwise) { key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; key->conf.link_id = -1; } else { key->conf.link_id = link->link_id; } if (params->mode == NL80211_KEY_NO_TX) key->conf.flags |= IEEE80211_KEY_FLAG_NO_AUTO_TX; if (mac_addr) { sta = sta_info_get_bss(sdata, mac_addr); /* * The ASSOC test makes sure the driver is ready to * receive the key. When wpa_supplicant has roamed * using FT, it attempts to set the key before * association has completed, this rejects that attempt * so it will set the key again after association. * * TODO: accept the key if we have a station entry and * add it to the device after the station. */ if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) { ieee80211_key_free_unused(key); return -ENOENT; } } switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: /* no MFP (yet) */ break; case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH if (sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; #endif case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_OCB: /* shouldn't happen */ WARN_ON_ONCE(1); break; } err = ieee80211_key_link(key, link, sta); /* KRACK protection, shouldn't happen but just silently accept key */ if (err == -EALREADY) err = 0; return err; } static struct ieee80211_key * ieee80211_lookup_key(struct ieee80211_sub_if_data *sdata, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_local *local __maybe_unused = sdata->local; struct ieee80211_link_data *link = &sdata->deflink; struct ieee80211_key *key; if (link_id >= 0) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return NULL; } if (mac_addr) { struct sta_info *sta; struct link_sta_info *link_sta; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return NULL; if (link_id >= 0) { link_sta = rcu_dereference_check(sta->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); if (!link_sta) return NULL; } else { link_sta = &sta->deflink; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sta->ptk[key_idx]); if (!pairwise && key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS) return wiphy_dereference(local->hw.wiphy, link_sta->gtk[key_idx]); return NULL; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sdata->keys[key_idx]); key = wiphy_dereference(local->hw.wiphy, link->gtk[key_idx]); if (key) return key; /* or maybe it was a WEP key */ if (key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sdata->keys[key_idx]); return NULL; } static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; lockdep_assert_wiphy(local->hw.wiphy); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) return -ENOENT; ieee80211_key_free(key, sdata->vif.type == NL80211_IFTYPE_STATION); return 0; } static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params *params)) { struct ieee80211_sub_if_data *sdata; u8 seq[6] = {0}; struct key_params params; struct ieee80211_key *key; u64 pn64; u32 iv32; u16 iv16; int err = -ENOENT; struct ieee80211_key_seq kseq = {}; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) goto out; memset(¶ms, 0, sizeof(params)); params.cipher = key->conf.cipher; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: pn64 = atomic64_read(&key->conf.tx_pn); iv32 = TKIP_PN_TO_IV32(pn64); iv16 = TKIP_PN_TO_IV16(pn64); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); iv32 = kseq.tkip.iv32; iv16 = kseq.tkip.iv16; } seq[0] = iv16 & 0xff; seq[1] = (iv16 >> 8) & 0xff; seq[2] = iv32 & 0xff; seq[3] = (iv32 >> 8) & 0xff; seq[4] = (iv32 >> 16) & 0xff; seq[5] = (iv32 >> 24) & 0xff; params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_cmac)); fallthrough; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_gmac)); fallthrough; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), gcmp)); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); memcpy(seq, kseq.ccmp.pn, 6); } else { pn64 = atomic64_read(&key->conf.tx_pn); seq[0] = pn64; seq[1] = pn64 >> 8; seq[2] = pn64 >> 16; seq[3] = pn64 >> 24; seq[4] = pn64 >> 32; seq[5] = pn64 >> 40; } params.seq = seq; params.seq_len = 6; break; default: if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) break; if (WARN_ON(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) break; drv_get_key_seq(sdata->local, key, &kseq); params.seq = kseq.hw.seq; params.seq_len = kseq.hw.seq_len; break; } callback(cookie, ¶ms); err = 0; out: rcu_read_unlock(); return err; } static int ieee80211_config_default_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool uni, bool multi) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_key(link, key_idx, uni, multi); return 0; } static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_mgmt_key(link, key_idx); return 0; } static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_beacon_key(link, key_idx); return 0; } void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) { rinfo->flags = 0; if (rate->flags & IEEE80211_TX_RC_MCS) { rinfo->flags |= RATE_INFO_FLAGS_MCS; rinfo->mcs = rate->idx; } else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; rinfo->mcs = ieee80211_rate_get_vht_mcs(rate); rinfo->nss = ieee80211_rate_get_vht_nss(rate); } else { struct ieee80211_supported_band *sband; sband = ieee80211_get_sband(sta->sdata); WARN_ON_ONCE(sband && !sband->bitrates); if (sband && sband->bitrates) rinfo->legacy = sband->bitrates[rate->idx].bitrate; } if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_40; else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_160; else rinfo->bw = RATE_INFO_BW_20; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; } static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_by_idx(sdata, idx); if (sta) { ret = 0; memcpy(mac, sta->sta.addr, ETH_ALEN); sta_set_sinfo(sta, sinfo, true); } return ret; } static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev, int idx, struct survey_info *survey) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); return drv_get_survey(local, idx, survey); } static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, mac); if (sta) { ret = 0; sta_set_sinfo(sta, sinfo, true); } return ret; } static int ieee80211_set_monitor_channel(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; struct ieee80211_chan_req chanreq = { .oper = *chandef }; int ret; lockdep_assert_wiphy(local->hw.wiphy); sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { if (cfg80211_chandef_identical(&local->monitor_chanreq.oper, &chanreq.oper)) return 0; sdata = wiphy_dereference(wiphy, local->monitor_sdata); if (!sdata) goto done; } if (rcu_access_pointer(sdata->deflink.conf->chanctx_conf) && cfg80211_chandef_identical(&sdata->vif.bss_conf.chanreq.oper, &chanreq.oper)) return 0; ieee80211_link_release_channel(&sdata->deflink); ret = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (ret) return ret; done: local->monitor_chanreq = chanreq; return 0; } static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, const u8 *resp, size_t resp_len, const struct ieee80211_csa_settings *csa, const struct ieee80211_color_change_settings *cca, struct ieee80211_link_data *link) { struct probe_resp *new, *old; if (!resp || !resp_len) return 1; old = sdata_dereference(link->u.ap.probe_resp, sdata); new = kzalloc(sizeof(struct probe_resp) + resp_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = resp_len; memcpy(new->data, resp, resp_len); if (csa) memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * sizeof(new->cntdwn_counter_offsets[0])); else if (cca) new->cntdwn_counter_offsets[0] = cca->counter_offset_presp; rcu_assign_pointer(link->u.ap.probe_resp, new); if (old) kfree_rcu(old, rcu_head); return 0; } static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, struct cfg80211_fils_discovery *params, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf, u64 *changed) { struct fils_discovery_data *new, *old = NULL; struct ieee80211_fils_discovery *fd; if (!params->update) return 0; fd = &link_conf->fils_discovery; fd->min_interval = params->min_interval; fd->max_interval = params->max_interval; old = sdata_dereference(link->u.ap.fils_discovery, sdata); if (old) kfree_rcu(old, rcu_head); if (params->tmpl && params->tmpl_len) { new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = params->tmpl_len; memcpy(new->data, params->tmpl, params->tmpl_len); rcu_assign_pointer(link->u.ap.fils_discovery, new); } else { RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); } *changed |= BSS_CHANGED_FILS_DISCOVERY; return 0; } static int ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, struct cfg80211_unsol_bcast_probe_resp *params, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf, u64 *changed) { struct unsol_bcast_probe_resp_data *new, *old = NULL; if (!params->update) return 0; link_conf->unsol_bcast_probe_resp_interval = params->interval; old = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); if (old) kfree_rcu(old, rcu_head); if (params->tmpl && params->tmpl_len) { new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = params->tmpl_len; memcpy(new->data, params->tmpl, params->tmpl_len); rcu_assign_pointer(link->u.ap.unsol_bcast_probe_resp, new); } else { RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); } *changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; return 0; } static int ieee80211_set_ftm_responder_params( struct ieee80211_sub_if_data *sdata, const u8 *lci, size_t lci_len, const u8 *civicloc, size_t civicloc_len, struct ieee80211_bss_conf *link_conf) { struct ieee80211_ftm_responder_params *new, *old; u8 *pos; int len; if (!lci_len && !civicloc_len) return 0; old = link_conf->ftmr_params; len = lci_len + civicloc_len; new = kzalloc(sizeof(*new) + len, GFP_KERNEL); if (!new) return -ENOMEM; pos = (u8 *)(new + 1); if (lci_len) { new->lci_len = lci_len; new->lci = pos; memcpy(pos, lci, lci_len); pos += lci_len; } if (civicloc_len) { new->civicloc_len = civicloc_len; new->civicloc = pos; memcpy(pos, civicloc, civicloc_len); pos += civicloc_len; } link_conf->ftmr_params = new; kfree(old); return 0; } static int ieee80211_copy_mbssid_beacon(u8 *pos, struct cfg80211_mbssid_elems *dst, struct cfg80211_mbssid_elems *src) { int i, offset = 0; dst->cnt = src->cnt; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } return offset; } static int ieee80211_copy_rnr_beacon(u8 *pos, struct cfg80211_rnr_elems *dst, struct cfg80211_rnr_elems *src) { int i, offset = 0; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } dst->cnt = src->cnt; return offset; } static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct cfg80211_beacon_data *params, const struct ieee80211_csa_settings *csa, const struct ieee80211_color_change_settings *cca, u64 *changed) { struct cfg80211_mbssid_elems *mbssid = NULL; struct cfg80211_rnr_elems *rnr = NULL; struct beacon_data *new, *old; int new_head_len, new_tail_len; int size, err; u64 _changed = BSS_CHANGED_BEACON; struct ieee80211_bss_conf *link_conf = link->conf; old = sdata_dereference(link->u.ap.beacon, sdata); /* Need to have a beacon head if we don't have one yet */ if (!params->head && !old) return -EINVAL; /* new or old head? */ if (params->head) new_head_len = params->head_len; else new_head_len = old->head_len; /* new or old tail? */ if (params->tail || !old) /* params->tail_len will be zero for !params->tail */ new_tail_len = params->tail_len; else new_tail_len = old->tail_len; size = sizeof(*new) + new_head_len + new_tail_len; /* new or old multiple BSSID elements? */ if (params->mbssid_ies) { mbssid = params->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); if (params->rnr_ies) { rnr = params->rnr_ies; size += struct_size(new->rnr_ies, elem, rnr->cnt); } size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, mbssid->cnt); } else if (old && old->mbssid_ies) { mbssid = old->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); if (old && old->rnr_ies) { rnr = old->rnr_ies; size += struct_size(new->rnr_ies, elem, rnr->cnt); } size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, mbssid->cnt); } new = kzalloc(size, GFP_KERNEL); if (!new) return -ENOMEM; /* start filling the new info now */ /* * pointers go into the block we allocated, * memory is | beacon_data | head | tail | mbssid_ies | rnr_ies */ new->head = ((u8 *) new) + sizeof(*new); new->tail = new->head + new_head_len; new->head_len = new_head_len; new->tail_len = new_tail_len; /* copy in optional mbssid_ies */ if (mbssid) { u8 *pos = new->tail + new->tail_len; new->mbssid_ies = (void *)pos; pos += struct_size(new->mbssid_ies, elem, mbssid->cnt); pos += ieee80211_copy_mbssid_beacon(pos, new->mbssid_ies, mbssid); if (rnr) { new->rnr_ies = (void *)pos; pos += struct_size(new->rnr_ies, elem, rnr->cnt); ieee80211_copy_rnr_beacon(pos, new->rnr_ies, rnr); } /* update bssid_indicator */ link_conf->bssid_indicator = ilog2(__roundup_pow_of_two(mbssid->cnt + 1)); } if (csa) { new->cntdwn_current_counter = csa->count; memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * sizeof(new->cntdwn_counter_offsets[0])); } else if (cca) { new->cntdwn_current_counter = cca->count; new->cntdwn_counter_offsets[0] = cca->counter_offset_beacon; } /* copy in head */ if (params->head) memcpy(new->head, params->head, new_head_len); else memcpy(new->head, old->head, new_head_len); /* copy in optional tail */ if (params->tail) memcpy(new->tail, params->tail, new_tail_len); else if (old) memcpy(new->tail, old->tail, new_tail_len); err = ieee80211_set_probe_resp(sdata, params->probe_resp, params->probe_resp_len, csa, cca, link); if (err < 0) { kfree(new); return err; } if (err == 0) _changed |= BSS_CHANGED_AP_PROBE_RESP; if (params->ftm_responder != -1) { link_conf->ftm_responder = params->ftm_responder; err = ieee80211_set_ftm_responder_params(sdata, params->lci, params->lci_len, params->civicloc, params->civicloc_len, link_conf); if (err < 0) { kfree(new); return err; } _changed |= BSS_CHANGED_FTM_RESPONDER; } rcu_assign_pointer(link->u.ap.beacon, new); sdata->u.ap.active = true; if (old) kfree_rcu(old, rcu_head); *changed |= _changed; return 0; } static u8 ieee80211_num_beaconing_links(struct ieee80211_sub_if_data *sdata) { struct ieee80211_link_data *link; u8 link_id, num = 0; if (sdata->vif.type != NL80211_IFTYPE_AP && sdata->vif.type != NL80211_IFTYPE_P2P_GO) return num; if (!sdata->vif.valid_links) return num; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; if (sdata_dereference(link->u.ap.beacon, sdata)) num++; } return num; } static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct beacon_data *old; struct ieee80211_sub_if_data *vlan; u64 changed = BSS_CHANGED_BEACON_INT | BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_BEACON | BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | BSS_CHANGED_TWT; int i, err; int prev_beacon_int; unsigned int link_id = params->beacon.link_id; struct ieee80211_link_data *link; struct ieee80211_bss_conf *link_conf; struct ieee80211_chan_req chanreq = { .oper = params->chandef }; lockdep_assert_wiphy(local->hw.wiphy); link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return -ENOLINK; link_conf = link->conf; old = sdata_dereference(link->u.ap.beacon, sdata); if (old) return -EALREADY; link->smps_mode = IEEE80211_SMPS_OFF; link->needed_rx_chains = sdata->local->rx_chains; prev_beacon_int = link_conf->beacon_int; link_conf->beacon_int = params->beacon_interval; if (params->ht_cap) link_conf->ht_ldpc = params->ht_cap->cap_info & cpu_to_le16(IEEE80211_HT_CAP_LDPC_CODING); if (params->vht_cap) { link_conf->vht_ldpc = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC); link_conf->vht_su_beamformer = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE); link_conf->vht_su_beamformee = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE); link_conf->vht_mu_beamformer = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE); link_conf->vht_mu_beamformee = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE); } if (params->he_cap && params->he_oper) { link_conf->he_support = true; link_conf->htc_trig_based_pkt_ext = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK); link_conf->frame_time_rts_th = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); changed |= BSS_CHANGED_HE_OBSS_PD; if (params->beacon.he_bss_color.enabled) changed |= BSS_CHANGED_HE_BSS_COLOR; } if (params->he_cap) { link_conf->he_ldpc = params->he_cap->phy_cap_info[1] & IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD; link_conf->he_su_beamformer = params->he_cap->phy_cap_info[3] & IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER; link_conf->he_su_beamformee = params->he_cap->phy_cap_info[4] & IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE; link_conf->he_mu_beamformer = params->he_cap->phy_cap_info[4] & IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER; link_conf->he_full_ul_mumimo = params->he_cap->phy_cap_info[2] & IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO; } if (params->eht_cap) { if (!link_conf->he_support) return -EOPNOTSUPP; link_conf->eht_support = true; link_conf->eht_su_beamformer = params->eht_cap->fixed.phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER; link_conf->eht_su_beamformee = params->eht_cap->fixed.phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE; link_conf->eht_mu_beamformer = params->eht_cap->fixed.phy_cap_info[7] & (IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ); link_conf->eht_80mhz_full_bw_ul_mumimo = params->eht_cap->fixed.phy_cap_info[7] & (IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ); } else { link_conf->eht_su_beamformer = false; link_conf->eht_su_beamformee = false; link_conf->eht_mu_beamformer = false; } if (sdata->vif.type == NL80211_IFTYPE_AP && params->mbssid_config.tx_wdev) { err = ieee80211_set_ap_mbssid_options(sdata, ¶ms->mbssid_config, link_conf); if (err) return err; } err = ieee80211_link_use_channel(link, &chanreq, IEEE80211_CHANCTX_SHARED); if (!err) ieee80211_link_copy_chanctx_to_vlans(link, false); if (err) { link_conf->beacon_int = prev_beacon_int; return err; } /* * Apply control port protocol, this allows us to * not encrypt dynamic WEP control frames. */ sdata->control_port_protocol = params->crypto.control_port_ethertype; sdata->control_port_no_encrypt = params->crypto.control_port_no_encrypt; sdata->control_port_over_nl80211 = params->crypto.control_port_over_nl80211; sdata->control_port_no_preauth = params->crypto.control_port_no_preauth; list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->control_port_protocol = params->crypto.control_port_ethertype; vlan->control_port_no_encrypt = params->crypto.control_port_no_encrypt; vlan->control_port_over_nl80211 = params->crypto.control_port_over_nl80211; vlan->control_port_no_preauth = params->crypto.control_port_no_preauth; } link_conf->dtim_period = params->dtim_period; link_conf->enable_beacon = true; link_conf->allow_p2p_go_ps = sdata->vif.p2p; link_conf->twt_responder = params->twt_responder; link_conf->he_obss_pd = params->he_obss_pd; link_conf->he_bss_color = params->beacon.he_bss_color; sdata->vif.cfg.s1g = params->chandef.chan->band == NL80211_BAND_S1GHZ; sdata->vif.cfg.ssid_len = params->ssid_len; if (params->ssid_len) memcpy(sdata->vif.cfg.ssid, params->ssid, params->ssid_len); link_conf->hidden_ssid = (params->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE); memset(&link_conf->p2p_noa_attr, 0, sizeof(link_conf->p2p_noa_attr)); link_conf->p2p_noa_attr.oppps_ctwindow = params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; if (params->p2p_opp_ps) link_conf->p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; sdata->beacon_rate_set = false; if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) { for (i = 0; i < NUM_NL80211_BANDS; i++) { sdata->beacon_rateidx_mask[i] = params->beacon_rate.control[i].legacy; if (sdata->beacon_rateidx_mask[i]) sdata->beacon_rate_set = true; } } if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) link_conf->beacon_tx_rate = params->beacon_rate; err = ieee80211_assign_beacon(sdata, link, ¶ms->beacon, NULL, NULL, &changed); if (err < 0) goto error; err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, link, link_conf, &changed); if (err < 0) goto error; err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link, link_conf, &changed); if (err < 0) goto error; err = drv_start_ap(sdata->local, sdata, link_conf); if (err) { old = sdata_dereference(link->u.ap.beacon, sdata); if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(link->u.ap.beacon, NULL); if (ieee80211_num_beaconing_links(sdata) == 0) sdata->u.ap.active = false; goto error; } ieee80211_recalc_dtim(local, sdata); ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_SSID); ieee80211_link_info_change_notify(sdata, link, changed); if (ieee80211_num_beaconing_links(sdata) <= 1) netif_carrier_on(dev); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_on(vlan->dev); return 0; error: ieee80211_link_release_channel(link); return err; } static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_update *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct cfg80211_beacon_data *beacon = ¶ms->beacon; struct beacon_data *old; int err; struct ieee80211_bss_conf *link_conf; u64 changed = 0; lockdep_assert_wiphy(wiphy); link = sdata_dereference(sdata->link[beacon->link_id], sdata); if (!link) return -ENOLINK; link_conf = link->conf; /* don't allow changing the beacon while a countdown is in place - offset * of channel switch counter may change */ if (link_conf->csa_active || link_conf->color_change_active) return -EBUSY; old = sdata_dereference(link->u.ap.beacon, sdata); if (!old) return -ENOENT; err = ieee80211_assign_beacon(sdata, link, beacon, NULL, NULL, &changed); if (err < 0) return err; err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, link, link_conf, &changed); if (err < 0) return err; err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link, link_conf, &changed); if (err < 0) return err; if (beacon->he_bss_color_valid && beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) { link_conf->he_bss_color.enabled = beacon->he_bss_color.enabled; changed |= BSS_CHANGED_HE_BSS_COLOR; } ieee80211_link_info_change_notify(sdata, link, changed); return 0; } static void ieee80211_free_next_beacon(struct ieee80211_link_data *link) { if (!link->u.ap.next_beacon) return; kfree(link->u.ap.next_beacon->mbssid_ies); kfree(link->u.ap.next_beacon->rnr_ies); kfree(link->u.ap.next_beacon); link->u.ap.next_beacon = NULL; } static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_sub_if_data *vlan; struct ieee80211_local *local = sdata->local; struct beacon_data *old_beacon; struct probe_resp *old_probe_resp; struct fils_discovery_data *old_fils_discovery; struct unsol_bcast_probe_resp_data *old_unsol_bcast_probe_resp; struct cfg80211_chan_def chandef; struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct ieee80211_bss_conf *link_conf = link->conf; LIST_HEAD(keys); lockdep_assert_wiphy(local->hw.wiphy); old_beacon = sdata_dereference(link->u.ap.beacon, sdata); if (!old_beacon) return -ENOENT; old_probe_resp = sdata_dereference(link->u.ap.probe_resp, sdata); old_fils_discovery = sdata_dereference(link->u.ap.fils_discovery, sdata); old_unsol_bcast_probe_resp = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); /* abort any running channel switch or color change */ link_conf->csa_active = false; link_conf->color_change_active = false; ieee80211_vif_unblock_queues_csa(sdata); ieee80211_free_next_beacon(link); /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); if (ieee80211_num_beaconing_links(sdata) <= 1) { netif_carrier_off(dev); sdata->u.ap.active = false; } /* remove beacon and probe response */ RCU_INIT_POINTER(link->u.ap.beacon, NULL); RCU_INIT_POINTER(link->u.ap.probe_resp, NULL); RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); if (old_fils_discovery) kfree_rcu(old_fils_discovery, rcu_head); if (old_unsol_bcast_probe_resp) kfree_rcu(old_unsol_bcast_probe_resp, rcu_head); kfree(link_conf->ftmr_params); link_conf->ftmr_params = NULL; link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; link_conf->bssid_indicator = 0; __sta_info_flush(sdata, true, link_id, NULL); ieee80211_remove_link_keys(link, &keys); if (!list_empty(&keys)) { synchronize_net(); ieee80211_free_key_list(local, &keys); } ieee80211_stop_mbssid(sdata); RCU_INIT_POINTER(link_conf->tx_bss_conf, NULL); link_conf->enable_beacon = false; sdata->beacon_rate_set = false; sdata->vif.cfg.ssid_len = 0; clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_BEACON_ENABLED); if (sdata->wdev.links[link_id].cac_started) { chandef = link_conf->chanreq.oper; wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL, link_id); } drv_stop_ap(sdata->local, sdata, link_conf); /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf); ieee80211_link_copy_chanctx_to_vlans(link, true); ieee80211_link_release_channel(link); return 0; } static int sta_apply_auth_flags(struct ieee80211_local *local, struct sta_info *sta, u32 mask, u32 set) { int ret; if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && set & BIT(NL80211_STA_FLAG_AUTHENTICATED) && !test_sta_flag(sta, WLAN_STA_AUTH)) { ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && set & BIT(NL80211_STA_FLAG_ASSOCIATED) && !test_sta_flag(sta, WLAN_STA_ASSOC)) { /* * When peer becomes associated, init rate control as * well. Some drivers require rate control initialized * before drv_sta_state() is called. */ if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) rate_control_rate_init_all_links(sta); ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) ret = sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); else if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); else ret = 0; if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && !(set & BIT(NL80211_STA_FLAG_ASSOCIATED)) && test_sta_flag(sta, WLAN_STA_ASSOC)) { ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && !(set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) && test_sta_flag(sta, WLAN_STA_AUTH)) { ret = sta_info_move_state(sta, IEEE80211_STA_NONE); if (ret) return ret; } return 0; } static void sta_apply_mesh_params(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { #ifdef CONFIG_MAC80211_MESH struct ieee80211_sub_if_data *sdata = sta->sdata; u64 changed = 0; if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) { switch (params->plink_state) { case NL80211_PLINK_ESTAB: if (sta->mesh->plink_state != NL80211_PLINK_ESTAB) changed = mesh_plink_inc_estab_count(sdata); sta->mesh->plink_state = params->plink_state; sta->mesh->aid = params->peer_aid; ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, sdata->u.mesh.mshcfg.power_mode); ewma_mesh_tx_rate_avg_init(&sta->mesh->tx_rate_avg); /* init at low value */ ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, 10); break; case NL80211_PLINK_LISTEN: case NL80211_PLINK_BLOCKED: case NL80211_PLINK_OPN_SNT: case NL80211_PLINK_OPN_RCVD: case NL80211_PLINK_CNF_RCVD: case NL80211_PLINK_HOLDING: if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) changed = mesh_plink_dec_estab_count(sdata); sta->mesh->plink_state = params->plink_state; ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, NL80211_MESH_POWER_UNKNOWN); break; default: /* nothing */ break; } } switch (params->plink_action) { case NL80211_PLINK_ACTION_NO_ACTION: /* nothing */ break; case NL80211_PLINK_ACTION_OPEN: changed |= mesh_plink_open(sta); break; case NL80211_PLINK_ACTION_BLOCK: changed |= mesh_plink_block(sta); break; } if (params->local_pm) changed |= ieee80211_mps_set_sta_local_pm(sta, params->local_pm); ieee80211_mbss_info_change_notify(sdata, changed); #endif } enum sta_link_apply_mode { STA_LINK_MODE_NEW, STA_LINK_MODE_STA_MODIFY, STA_LINK_MODE_LINK_MODIFY, }; static int sta_link_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, enum sta_link_apply_mode mode, struct link_station_parameters *params) { struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata = sta->sdata; u32 link_id = params->link_id < 0 ? 0 : params->link_id; struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct link_sta_info *link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); bool changes = params->link_mac || params->txpwr_set || params->supported_rates_len || params->ht_capa || params->vht_capa || params->he_capa || params->eht_capa || params->opmode_notif_used; switch (mode) { case STA_LINK_MODE_NEW: if (!params->link_mac) return -EINVAL; break; case STA_LINK_MODE_LINK_MODIFY: break; case STA_LINK_MODE_STA_MODIFY: if (params->link_id >= 0) break; if (!changes) return 0; break; } if (!link || !link_sta) return -EINVAL; sband = ieee80211_get_link_sband(link); if (!sband) return -EINVAL; if (params->link_mac) { if (mode == STA_LINK_MODE_NEW) { memcpy(link_sta->addr, params->link_mac, ETH_ALEN); memcpy(link_sta->pub->addr, params->link_mac, ETH_ALEN); } else if (!ether_addr_equal(link_sta->addr, params->link_mac)) { return -EINVAL; } } if (params->txpwr_set) { int ret; link_sta->pub->txpwr.type = params->txpwr.type; if (params->txpwr.type == NL80211_TX_POWER_LIMITED) link_sta->pub->txpwr.power = params->txpwr.power; ret = drv_sta_set_txpwr(local, sdata, sta); if (ret) return ret; } if (params->supported_rates && params->supported_rates_len && !ieee80211_parse_bitrates(link->conf->chanreq.oper.width, sband, params->supported_rates, params->supported_rates_len, &link_sta->pub->supp_rates[sband->band])) return -EINVAL; if (params->ht_capa) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, params->ht_capa, link_sta); /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, NULL, link_sta); if (params->he_capa) ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, (void *)params->he_capa, params->he_capa_len, (void *)params->he_6ghz_capa, link_sta); if (params->he_capa && params->eht_capa) ieee80211_eht_cap_ie_to_sta_eht_cap(sdata, sband, (u8 *)params->he_capa, params->he_capa_len, params->eht_capa, params->eht_capa_len, link_sta); ieee80211_sta_init_nss(link_sta); if (params->opmode_notif_used) { /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it */ __ieee80211_vht_handle_opmode(sdata, link_sta, params->opmode_notif, sband->band); } return 0; } static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = sta->sdata; u32 mask, set; int ret = 0; mask = params->sta_flags_mask; set = params->sta_flags_set; if (ieee80211_vif_is_mesh(&sdata->vif)) { /* * In mesh mode, ASSOCIATED isn't part of the nl80211 * API but must follow AUTHENTICATED for driver state. */ if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) mask |= BIT(NL80211_STA_FLAG_ASSOCIATED); if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) set |= BIT(NL80211_STA_FLAG_ASSOCIATED); } else if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { /* * TDLS -- everything follows authorized, but * only becoming authorized is possible, not * going back */ if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) { set |= BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); mask |= BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); } } if (mask & BIT(NL80211_STA_FLAG_WME) && local->hw.queues >= IEEE80211_NUM_ACS) sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME); /* auth flags will be set later for TDLS, * and for unassociated stations that move to associated */ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !((mask & BIT(NL80211_STA_FLAG_ASSOCIATED)) && (set & BIT(NL80211_STA_FLAG_ASSOCIATED)))) { ret = sta_apply_auth_flags(local, sta, mask, set); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) set_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); else clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); } if (mask & BIT(NL80211_STA_FLAG_MFP)) { sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP)); if (set & BIT(NL80211_STA_FLAG_MFP)) set_sta_flag(sta, WLAN_STA_MFP); else clear_sta_flag(sta, WLAN_STA_MFP); } if (mask & BIT(NL80211_STA_FLAG_TDLS_PEER)) { if (set & BIT(NL80211_STA_FLAG_TDLS_PEER)) set_sta_flag(sta, WLAN_STA_TDLS_PEER); else clear_sta_flag(sta, WLAN_STA_TDLS_PEER); } if (mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) sta->sta.spp_amsdu = set & BIT(NL80211_STA_FLAG_SPP_AMSDU); /* mark TDLS channel switch support, if the AP allows it */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->deflink.u.mgd.tdls_chan_switch_prohibited && params->ext_capab_len >= 4 && params->ext_capab[3] & WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH) set_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH); if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->u.mgd.tdls_wider_bw_prohibited && ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) && params->ext_capab_len >= 8 && params->ext_capab[7] & WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED) set_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW); if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) { sta->sta.uapsd_queues = params->uapsd_queues; sta->sta.max_sp = params->max_sp; } ieee80211_sta_set_max_amsdu_subframes(sta, params->ext_capab, params->ext_capab_len); /* * cfg80211 validates this (1-2007) and allows setting the AID * only when creating a new station entry */ if (params->aid) sta->sta.aid = params->aid; /* * Some of the following updates would be racy if called on an * existing station, via ieee80211_change_station(). However, * all such changes are rejected by cfg80211 except for updates * changing the supported rates on an existing but not yet used * TDLS peer. */ if (params->listen_interval >= 0) sta->listen_interval = params->listen_interval; if (params->eml_cap_present) sta->sta.eml_cap = params->eml_cap; ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_STA_MODIFY, ¶ms->link_sta_params); if (ret) return ret; if (params->support_p2p_ps >= 0) sta->sta.support_p2p_ps = params->support_p2p_ps; if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); if (params->airtime_weight) sta->airtime_weight = params->airtime_weight; /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || set & BIT(NL80211_STA_FLAG_ASSOCIATED)) { ret = sta_apply_auth_flags(local, sta, mask, set); if (ret) return ret; } /* Mark the STA as MLO if MLD MAC address is available */ if (params->link_sta_params.mld_mac) sta->sta.mlo = true; return 0; } static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *sdata; int err; lockdep_assert_wiphy(local->hw.wiphy); if (params->vlan) { sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_AP) return -EINVAL; } else sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (ether_addr_equal(mac, sdata->vif.addr)) return -EINVAL; if (!is_valid_ether_addr(mac)) return -EINVAL; if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER) && sdata->vif.type == NL80211_IFTYPE_STATION && !sdata->u.mgd.associated) return -EINVAL; /* * If we have a link ID, it can be a non-MLO station on an AP MLD, * but we need to have a link_mac in that case as well, so use the * STA's MAC address in that case. */ if (params->link_sta_params.link_id >= 0) sta = sta_info_alloc_with_link(sdata, mac, params->link_sta_params.link_id, params->link_sta_params.link_mac ?: mac, GFP_KERNEL); else sta = sta_info_alloc(sdata, mac, GFP_KERNEL); if (!sta) return -ENOMEM; if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) sta->sta.tdls = true; /* Though the mutex is not needed here (since the station is not * visible yet), sta_apply_parameters (and inner functions) require * the mutex due to other paths. */ err = sta_apply_parameters(local, sta, params); if (err) { sta_info_free(local, sta); return err; } /* * for TDLS and for unassociated station, rate control should be * initialized only when rates are known and station is marked * authorized/associated */ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) && test_sta_flag(sta, WLAN_STA_ASSOC)) rate_control_rate_init_all_links(sta); return sta_info_insert(sta); } static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, struct station_del_parameters *params) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (params->mac) return sta_info_destroy_addr_bss(sdata, params->mac); sta_info_flush(sdata, params->link_id); return 0; } static int ieee80211_change_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *vlansdata; enum cfg80211_station_type statype; int err; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, mac); if (!sta) return -ENOENT; switch (sdata->vif.type) { case NL80211_IFTYPE_MESH_POINT: if (sdata->u.mesh.user_mpm) statype = CFG80211_STA_MESH_PEER_USER; else statype = CFG80211_STA_MESH_PEER_KERNEL; break; case NL80211_IFTYPE_ADHOC: statype = CFG80211_STA_IBSS; break; case NL80211_IFTYPE_STATION: if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { statype = CFG80211_STA_AP_STA; break; } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) statype = CFG80211_STA_TDLS_PEER_ACTIVE; else statype = CFG80211_STA_TDLS_PEER_SETUP; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: if (test_sta_flag(sta, WLAN_STA_ASSOC)) statype = CFG80211_STA_AP_CLIENT; else statype = CFG80211_STA_AP_CLIENT_UNASSOC; break; default: return -EOPNOTSUPP; } err = cfg80211_check_station_change(wiphy, params, statype); if (err) return err; if (params->vlan && params->vlan != sta->sdata->dev) { vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (params->vlan->ieee80211_ptr->use_4addr) { if (vlansdata->u.vlan.sta) return -EBUSY; rcu_assign_pointer(vlansdata->u.vlan.sta, sta); __ieee80211_check_fast_rx_iface(vlansdata); drv_sta_set_4addr(local, sta->sdata, &sta->sta, true); } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { ieee80211_vif_inc_num_mcast(sta->sdata); cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); } } err = sta_apply_parameters(local, sta, params); if (err) return err; if (sdata->vif.type == NL80211_IFTYPE_STATION && params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); } return 0; } #ifdef CONFIG_MAC80211_MESH static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); sta = sta_info_get(sdata, next_hop); if (!sta) { rcu_read_unlock(); return -ENOENT; } mpath = mesh_path_add(sdata, dst); if (IS_ERR(mpath)) { rcu_read_unlock(); return PTR_ERR(mpath); } mesh_path_fix_nexthop(mpath, sta); rcu_read_unlock(); return 0; } static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (dst) return mesh_path_del(sdata, dst); mesh_path_flush_by_iface(sdata); return 0; } static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); sta = sta_info_get(sdata, next_hop); if (!sta) { rcu_read_unlock(); return -ENOENT; } mpath = mesh_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } mesh_path_fix_nexthop(mpath, sta); rcu_read_unlock(); return 0; } static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, struct mpath_info *pinfo) { struct sta_info *next_hop_sta = rcu_dereference(mpath->next_hop); if (next_hop_sta) memcpy(next_hop, next_hop_sta->sta.addr, ETH_ALEN); else eth_zero_addr(next_hop); memset(pinfo, 0, sizeof(*pinfo)); pinfo->generation = mpath->sdata->u.mesh.mesh_paths_generation; pinfo->filled = MPATH_INFO_FRAME_QLEN | MPATH_INFO_SN | MPATH_INFO_METRIC | MPATH_INFO_EXPTIME | MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | MPATH_INFO_FLAGS | MPATH_INFO_HOP_COUNT | MPATH_INFO_PATH_CHANGE; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; pinfo->metric = mpath->metric; if (time_before(jiffies, mpath->exp_time)) pinfo->exptime = jiffies_to_msecs(mpath->exp_time - jiffies); pinfo->discovery_timeout = jiffies_to_msecs(mpath->discovery_timeout); pinfo->discovery_retries = mpath->discovery_retries; if (mpath->flags & MESH_PATH_ACTIVE) pinfo->flags |= NL80211_MPATH_FLAG_ACTIVE; if (mpath->flags & MESH_PATH_RESOLVING) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVING; if (mpath->flags & MESH_PATH_SN_VALID) pinfo->flags |= NL80211_MPATH_FLAG_SN_VALID; if (mpath->flags & MESH_PATH_FIXED) pinfo->flags |= NL80211_MPATH_FLAG_FIXED; if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; pinfo->hop_count = mpath->hop_count; pinfo->path_change_count = mpath->path_change_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mesh_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpath_set_pinfo(mpath, next_hop, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mesh_path_lookup_by_idx(sdata, idx); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpath_set_pinfo(mpath, next_hop, pinfo); rcu_read_unlock(); return 0; } static void mpp_set_pinfo(struct mesh_path *mpath, u8 *mpp, struct mpath_info *pinfo) { memset(pinfo, 0, sizeof(*pinfo)); memcpy(mpp, mpath->mpp, ETH_ALEN); pinfo->generation = mpath->sdata->u.mesh.mpp_paths_generation; } static int ieee80211_get_mpp(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mpp_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpp_set_pinfo(mpath, mpp, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_dump_mpp(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mpp_path_lookup_by_idx(sdata, idx); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpp_set_pinfo(mpath, mpp, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_get_mesh_config(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(conf, &(sdata->u.mesh.mshcfg), sizeof(struct mesh_config)); return 0; } static inline bool _chg_mesh_attr(enum nl80211_meshconf_params parm, u32 mask) { return (mask >> (parm-1)) & 0x1; } static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, const struct mesh_setup *setup) { u8 *new_ie; struct ieee80211_sub_if_data *sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); int i; /* allocate information elements */ new_ie = NULL; if (setup->ie_len) { new_ie = kmemdup(setup->ie, setup->ie_len, GFP_KERNEL); if (!new_ie) return -ENOMEM; } ifmsh->ie_len = setup->ie_len; ifmsh->ie = new_ie; /* now copy the rest of the setup parameters */ ifmsh->mesh_id_len = setup->mesh_id_len; memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); ifmsh->mesh_sp_id = setup->sync_method; ifmsh->mesh_pp_id = setup->path_sel_proto; ifmsh->mesh_pm_id = setup->path_metric; ifmsh->user_mpm = setup->user_mpm; ifmsh->mesh_auth_id = setup->auth_id; ifmsh->security = IEEE80211_MESH_SEC_NONE; ifmsh->userspace_handles_dfs = setup->userspace_handles_dfs; if (setup->is_authenticated) ifmsh->security |= IEEE80211_MESH_SEC_AUTHED; if (setup->is_secure) ifmsh->security |= IEEE80211_MESH_SEC_SECURED; /* mcast rate setting in Mesh Node */ memcpy(sdata->vif.bss_conf.mcast_rate, setup->mcast_rate, sizeof(setup->mcast_rate)); sdata->vif.bss_conf.basic_rates = setup->basic_rates; sdata->vif.bss_conf.beacon_int = setup->beacon_interval; sdata->vif.bss_conf.dtim_period = setup->dtim_period; sdata->beacon_rate_set = false; if (wiphy_ext_feature_isset(sdata->local->hw.wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) { for (i = 0; i < NUM_NL80211_BANDS; i++) { sdata->beacon_rateidx_mask[i] = setup->beacon_rate.control[i].legacy; if (sdata->beacon_rateidx_mask[i]) sdata->beacon_rate_set = true; } } return 0; } static int ieee80211_update_mesh_config(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { struct mesh_config *conf; struct ieee80211_sub_if_data *sdata; struct ieee80211_if_mesh *ifmsh; sdata = IEEE80211_DEV_TO_SUB_IF(dev); ifmsh = &sdata->u.mesh; /* Set the config options which we are interested in setting */ conf = &(sdata->u.mesh.mshcfg); if (_chg_mesh_attr(NL80211_MESHCONF_RETRY_TIMEOUT, mask)) conf->dot11MeshRetryTimeout = nconf->dot11MeshRetryTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_CONFIRM_TIMEOUT, mask)) conf->dot11MeshConfirmTimeout = nconf->dot11MeshConfirmTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HOLDING_TIMEOUT, mask)) conf->dot11MeshHoldingTimeout = nconf->dot11MeshHoldingTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_MAX_PEER_LINKS, mask)) conf->dot11MeshMaxPeerLinks = nconf->dot11MeshMaxPeerLinks; if (_chg_mesh_attr(NL80211_MESHCONF_MAX_RETRIES, mask)) conf->dot11MeshMaxRetries = nconf->dot11MeshMaxRetries; if (_chg_mesh_attr(NL80211_MESHCONF_TTL, mask)) conf->dot11MeshTTL = nconf->dot11MeshTTL; if (_chg_mesh_attr(NL80211_MESHCONF_ELEMENT_TTL, mask)) conf->element_ttl = nconf->element_ttl; if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) { if (ifmsh->user_mpm) return -EBUSY; conf->auto_open_plinks = nconf->auto_open_plinks; } if (_chg_mesh_attr(NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, mask)) conf->dot11MeshNbrOffsetMaxNeighbor = nconf->dot11MeshNbrOffsetMaxNeighbor; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, mask)) conf->dot11MeshHWMPmaxPREQretries = nconf->dot11MeshHWMPmaxPREQretries; if (_chg_mesh_attr(NL80211_MESHCONF_PATH_REFRESH_TIME, mask)) conf->path_refresh_time = nconf->path_refresh_time; if (_chg_mesh_attr(NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, mask)) conf->min_discovery_timeout = nconf->min_discovery_timeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, mask)) conf->dot11MeshHWMPactivePathTimeout = nconf->dot11MeshHWMPactivePathTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, mask)) conf->dot11MeshHWMPpreqMinInterval = nconf->dot11MeshHWMPpreqMinInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, mask)) conf->dot11MeshHWMPperrMinInterval = nconf->dot11MeshHWMPperrMinInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, mask)) conf->dot11MeshHWMPnetDiameterTraversalTime = nconf->dot11MeshHWMPnetDiameterTraversalTime; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOTMODE, mask)) { conf->dot11MeshHWMPRootMode = nconf->dot11MeshHWMPRootMode; ieee80211_mesh_root_setup(ifmsh); } if (_chg_mesh_attr(NL80211_MESHCONF_GATE_ANNOUNCEMENTS, mask)) { /* our current gate announcement implementation rides on root * announcements, so require this ifmsh to also be a root node * */ if (nconf->dot11MeshGateAnnouncementProtocol && !(conf->dot11MeshHWMPRootMode > IEEE80211_ROOTMODE_ROOT)) { conf->dot11MeshHWMPRootMode = IEEE80211_PROACTIVE_RANN; ieee80211_mesh_root_setup(ifmsh); } conf->dot11MeshGateAnnouncementProtocol = nconf->dot11MeshGateAnnouncementProtocol; } if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) conf->dot11MeshHWMPRannInterval = nconf->dot11MeshHWMPRannInterval; if (_chg_mesh_attr(NL80211_MESHCONF_FORWARDING, mask)) conf->dot11MeshForwarding = nconf->dot11MeshForwarding; if (_chg_mesh_attr(NL80211_MESHCONF_RSSI_THRESHOLD, mask)) { /* our RSSI threshold implementation is supported only for * devices that report signal in dBm. */ if (!ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM)) return -EOPNOTSUPP; conf->rssi_threshold = nconf->rssi_threshold; } if (_chg_mesh_attr(NL80211_MESHCONF_HT_OPMODE, mask)) { conf->ht_opmode = nconf->ht_opmode; sdata->vif.bss_conf.ht_operation_mode = nconf->ht_opmode; ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_HT); } if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, mask)) conf->dot11MeshHWMPactivePathToRootTimeout = nconf->dot11MeshHWMPactivePathToRootTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOT_INTERVAL, mask)) conf->dot11MeshHWMProotInterval = nconf->dot11MeshHWMProotInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, mask)) conf->dot11MeshHWMPconfirmationInterval = nconf->dot11MeshHWMPconfirmationInterval; if (_chg_mesh_attr(NL80211_MESHCONF_POWER_MODE, mask)) { conf->power_mode = nconf->power_mode; ieee80211_mps_local_status_update(sdata); } if (_chg_mesh_attr(NL80211_MESHCONF_AWAKE_WINDOW, mask)) conf->dot11MeshAwakeWindowDuration = nconf->dot11MeshAwakeWindowDuration; if (_chg_mesh_attr(NL80211_MESHCONF_PLINK_TIMEOUT, mask)) conf->plink_timeout = nconf->plink_timeout; if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_GATE, mask)) conf->dot11MeshConnectedToMeshGate = nconf->dot11MeshConnectedToMeshGate; if (_chg_mesh_attr(NL80211_MESHCONF_NOLEARN, mask)) conf->dot11MeshNolearn = nconf->dot11MeshNolearn; if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_AS, mask)) conf->dot11MeshConnectedToAuthServer = nconf->dot11MeshConnectedToAuthServer; ieee80211_mbss_info_change_notify(sdata, BSS_CHANGED_BEACON); return 0; } static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = setup->chandef }; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; int err; lockdep_assert_wiphy(sdata->local->hw.wiphy); memcpy(&ifmsh->mshcfg, conf, sizeof(struct mesh_config)); err = copy_mesh_setup(ifmsh, setup); if (err) return err; sdata->control_port_over_nl80211 = setup->control_port_over_nl80211; /* can mesh use other SMPS modes? */ sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = sdata->local->rx_chains; err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; return ieee80211_start_mesh(sdata); } static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); lockdep_assert_wiphy(sdata->local->hw.wiphy); ieee80211_stop_mesh(sdata); ieee80211_link_release_channel(&sdata->deflink); kfree(sdata->u.mesh.ie); return 0; } #endif static int ieee80211_change_bss(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct ieee80211_supported_band *sband; u64 changed = 0; link = ieee80211_link_or_deflink(sdata, params->link_id, true); if (IS_ERR(link)) return PTR_ERR(link); if (!sdata_dereference(link->u.ap.beacon, sdata)) return -ENOENT; sband = ieee80211_get_link_sband(link); if (!sband) return -EINVAL; if (params->basic_rates) { if (!ieee80211_parse_bitrates(link->conf->chanreq.oper.width, wiphy->bands[sband->band], params->basic_rates, params->basic_rates_len, &link->conf->basic_rates)) return -EINVAL; changed |= BSS_CHANGED_BASIC_RATES; ieee80211_check_rate_mask(link); } if (params->use_cts_prot >= 0) { link->conf->use_cts_prot = params->use_cts_prot; changed |= BSS_CHANGED_ERP_CTS_PROT; } if (params->use_short_preamble >= 0) { link->conf->use_short_preamble = params->use_short_preamble; changed |= BSS_CHANGED_ERP_PREAMBLE; } if (!link->conf->use_short_slot && (sband->band == NL80211_BAND_5GHZ || sband->band == NL80211_BAND_6GHZ)) { link->conf->use_short_slot = true; changed |= BSS_CHANGED_ERP_SLOT; } if (params->use_short_slot_time >= 0) { link->conf->use_short_slot = params->use_short_slot_time; changed |= BSS_CHANGED_ERP_SLOT; } if (params->ap_isolate >= 0) { if (params->ap_isolate) sdata->flags |= IEEE80211_SDATA_DONT_BRIDGE_PACKETS; else sdata->flags &= ~IEEE80211_SDATA_DONT_BRIDGE_PACKETS; ieee80211_check_fast_rx_iface(sdata); } if (params->ht_opmode >= 0) { link->conf->ht_operation_mode = (u16)params->ht_opmode; changed |= BSS_CHANGED_HT; } if (params->p2p_ctwindow >= 0) { link->conf->p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_CTWINDOW_MASK; link->conf->p2p_noa_attr.oppps_ctwindow |= params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; changed |= BSS_CHANGED_P2P_PS; } if (params->p2p_opp_ps > 0) { link->conf->p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } else if (params->p2p_opp_ps == 0) { link->conf->p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } ieee80211_link_info_change_notify(sdata, link, changed); return 0; } static int ieee80211_set_txq_params(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_txq_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, params->link_id, true); struct ieee80211_tx_queue_params p; if (!local->ops->conf_tx) return -EOPNOTSUPP; if (local->hw.queues < IEEE80211_NUM_ACS) return -EOPNOTSUPP; if (IS_ERR(link)) return PTR_ERR(link); memset(&p, 0, sizeof(p)); p.aifs = params->aifs; p.cw_max = params->cwmax; p.cw_min = params->cwmin; p.txop = params->txop; /* * Setting tx queue params disables u-apsd because it's only * called in master mode. */ p.uapsd = false; ieee80211_regulatory_limit_wmm_params(sdata, &p, params->ac); link->tx_conf[params->ac] = p; if (drv_conf_tx(local, link, params->ac, &p)) { wiphy_debug(local->hw.wiphy, "failed to set TX queue parameters for AC %d\n", params->ac); return -EINVAL; } ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_QOS); return 0; } #ifdef CONFIG_PM static int ieee80211_suspend(struct wiphy *wiphy, struct cfg80211_wowlan *wowlan) { return __ieee80211_suspend(wiphy_priv(wiphy), wowlan); } static int ieee80211_resume(struct wiphy *wiphy) { return __ieee80211_resume(wiphy_priv(wiphy)); } #else #define ieee80211_suspend NULL #define ieee80211_resume NULL #endif static int ieee80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *req) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_WDEV_TO_SUB_IF(req->wdev); switch (ieee80211_vif_type_p2p(&sdata->vif)) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_DEVICE: break; case NL80211_IFTYPE_P2P_GO: if (sdata->local->ops->hw_scan) break; /* * FIXME: implement NoA while scanning in software, * for now fall through to allow scanning only when * beaconing hasn't been configured yet */ fallthrough; case NL80211_IFTYPE_AP: /* * If the scan has been forced (and the driver supports * forcing), don't care about being beaconing already. * This will create problems to the attached stations (e.g. all * the frames sent while scanning on other channel will be * lost) */ if (sdata->deflink.u.ap.beacon && (!(wiphy->features & NL80211_FEATURE_AP_SCAN) || !(req->flags & NL80211_SCAN_FLAG_AP))) return -EOPNOTSUPP; break; case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } return ieee80211_request_scan(sdata, req); } static void ieee80211_abort_scan(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_scan_cancel(wiphy_priv(wiphy)); } static int ieee80211_sched_scan_start(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_sched_scan_request *req) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!sdata->local->ops->sched_scan_start) return -EOPNOTSUPP; return ieee80211_request_sched_scan_start(sdata, req); } static int ieee80211_sched_scan_stop(struct wiphy *wiphy, struct net_device *dev, u64 reqid) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->sched_scan_stop) return -EOPNOTSUPP; return ieee80211_request_sched_scan_stop(local); } static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_auth_request *req) { return ieee80211_mgd_auth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_deauth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_deauth_request *req) { return ieee80211_mgd_deauth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_disassoc_request *req) { return ieee80211_mgd_disassoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params) { return ieee80211_ibss_join(IEEE80211_DEV_TO_SUB_IF(dev), params); } static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev) { return ieee80211_ibss_leave(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_join_ocb(struct wiphy *wiphy, struct net_device *dev, struct ocb_setup *setup) { return ieee80211_ocb_join(IEEE80211_DEV_TO_SUB_IF(dev), setup); } static int ieee80211_leave_ocb(struct wiphy *wiphy, struct net_device *dev) { return ieee80211_ocb_leave(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev, int rate[NUM_NL80211_BANDS]) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(int) * NUM_NL80211_BANDS); if (ieee80211_sdata_running(sdata)) ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MCAST_RATE); return 0; } static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) { struct ieee80211_local *local = wiphy_priv(wiphy); int err; if (changed & WIPHY_PARAM_FRAG_THRESHOLD) { ieee80211_check_fast_xmit_all(local); err = drv_set_frag_threshold(local, wiphy->frag_threshold); if (err) { ieee80211_check_fast_xmit_all(local); return err; } } if ((changed & WIPHY_PARAM_COVERAGE_CLASS) || (changed & WIPHY_PARAM_DYN_ACK)) { s16 coverage_class; coverage_class = changed & WIPHY_PARAM_COVERAGE_CLASS ? wiphy->coverage_class : -1; err = drv_set_coverage_class(local, coverage_class); if (err) return err; } if (changed & WIPHY_PARAM_RTS_THRESHOLD) { err = drv_set_rts_threshold(local, wiphy->rts_threshold); if (err) return err; } if (changed & WIPHY_PARAM_RETRY_SHORT) { if (wiphy->retry_short > IEEE80211_MAX_TX_RETRY) return -EINVAL; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; } if (changed & WIPHY_PARAM_RETRY_LONG) { if (wiphy->retry_long > IEEE80211_MAX_TX_RETRY) return -EINVAL; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; } if (changed & (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS); if (changed & (WIPHY_PARAM_TXQ_LIMIT | WIPHY_PARAM_TXQ_MEMORY_LIMIT | WIPHY_PARAM_TXQ_QUANTUM)) ieee80211_txq_set_params(local); return 0; } static int ieee80211_set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, enum nl80211_tx_power_setting type, int mbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; enum nl80211_tx_power_setting txp_type = type; bool update_txp_type = false; bool has_monitor = false; int user_power_level; int old_power = local->user_power_level; lockdep_assert_wiphy(local->hw.wiphy); switch (type) { case NL80211_TX_POWER_AUTOMATIC: user_power_level = IEEE80211_UNSET_POWER_LEVEL; txp_type = NL80211_TX_POWER_LIMITED; break; case NL80211_TX_POWER_LIMITED: case NL80211_TX_POWER_FIXED: if (mbm < 0 || (mbm % 100)) return -EOPNOTSUPP; user_power_level = MBM_TO_DBM(mbm); break; default: return -EINVAL; } if (wdev) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) return -EOPNOTSUPP; sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) return -EOPNOTSUPP; } for (int link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) continue; link->user_power_level = user_power_level; if (txp_type != link->conf->txpower_type) { update_txp_type = true; link->conf->txpower_type = txp_type; } ieee80211_recalc_txpower(link, update_txp_type); } return 0; } local->user_power_level = user_power_level; list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { has_monitor = true; continue; } for (int link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) continue; link->user_power_level = local->user_power_level; if (txp_type != link->conf->txpower_type) update_txp_type = true; link->conf->txpower_type = txp_type; } } list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) continue; for (int link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) continue; ieee80211_recalc_txpower(link, update_txp_type); } } if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; sdata->vif.bss_conf.txpower_type = txp_type; ieee80211_recalc_txpower(&sdata->deflink, update_txp_type); } } if (local->emulate_chanctx && (old_power != local->user_power_level)) ieee80211_hw_conf_chan(local); return 0; } static int ieee80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id, int *dbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_link_data *link_data; if (local->ops->get_txpower && (sdata->flags & IEEE80211_SDATA_IN_DRIVER)) return drv_get_txpower(local, sdata, link_id, dbm); if (local->emulate_chanctx) { *dbm = local->hw.conf.power_level; } else { link_data = wiphy_dereference(wiphy, sdata->link[link_id]); if (link_data) *dbm = link_data->conf->txpower; else return -ENOLINK; } /* INT_MIN indicates no power level was set yet */ if (*dbm == INT_MIN) return -EINVAL; return 0; } static void ieee80211_rfkill_poll(struct wiphy *wiphy) { struct ieee80211_local *local = wiphy_priv(wiphy); drv_rfkill_poll(local); } #ifdef CONFIG_NL80211_TESTMODE static int ieee80211_testmode_cmd(struct wiphy *wiphy, struct wireless_dev *wdev, void *data, int len) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_vif *vif = NULL; if (!local->ops->testmode_cmd) return -EOPNOTSUPP; if (wdev) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->flags & IEEE80211_SDATA_IN_DRIVER) vif = &sdata->vif; } return local->ops->testmode_cmd(&local->hw, vif, data, len); } static int ieee80211_testmode_dump(struct wiphy *wiphy, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->testmode_dump) return -EOPNOTSUPP; return local->ops->testmode_dump(&local->hw, skb, cb, data, len); } #endif int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, enum ieee80211_smps_mode smps_mode) { const u8 *ap; enum ieee80211_smps_mode old_req; int err; struct sta_info *sta; bool tdls_peer_found = false; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) return -EINVAL; if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return 0; old_req = link->u.mgd.req_smps; link->u.mgd.req_smps = smps_mode; /* The driver indicated that EML is enabled for the interface, which * implies that SMPS flows towards the AP should be stopped. */ if (sdata->vif.driver_flags & IEEE80211_VIF_EML_ACTIVE) return 0; if (old_req == smps_mode && smps_mode != IEEE80211_SMPS_AUTOMATIC) return 0; /* * If not associated, or current association is not an HT * association, there's no need to do anything, just store * the new value until we associate. */ if (!sdata->u.mgd.associated || link->conf->chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; ap = sdata->vif.cfg.ap_addr; rcu_read_lock(); list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) continue; tdls_peer_found = true; break; } rcu_read_unlock(); if (smps_mode == IEEE80211_SMPS_AUTOMATIC) { if (tdls_peer_found || !sdata->u.mgd.powersave) smps_mode = IEEE80211_SMPS_OFF; else smps_mode = IEEE80211_SMPS_DYNAMIC; } /* send SM PS frame to AP */ err = ieee80211_send_smps_action(sdata, smps_mode, ap, ap, ieee80211_vif_is_mld(&sdata->vif) ? link->link_id : -1); if (err) link->u.mgd.req_smps = old_req; else if (smps_mode != IEEE80211_SMPS_OFF && tdls_peer_found) ieee80211_teardown_tdls_peers(link); return err; } static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); unsigned int link_id; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS)) return -EOPNOTSUPP; if (enabled == sdata->u.mgd.powersave && timeout == local->dynamic_ps_forced_timeout) return 0; sdata->u.mgd.powersave = enabled; local->dynamic_ps_forced_timeout = timeout; /* no change, but if automatic follow powersave */ for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; __ieee80211_request_smps_mgd(sdata, link, link->u.mgd.req_smps); } if (ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); ieee80211_check_fast_rx_iface(sdata); return 0; } static void ieee80211_set_cqm_rssi_link(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, s32 rssi_thold, u32 rssi_hyst, s32 rssi_low, s32 rssi_high) { struct ieee80211_bss_conf *conf; if (!link || !link->conf) return; conf = link->conf; if (rssi_thold && rssi_hyst && rssi_thold == conf->cqm_rssi_thold && rssi_hyst == conf->cqm_rssi_hyst) return; conf->cqm_rssi_thold = rssi_thold; conf->cqm_rssi_hyst = rssi_hyst; conf->cqm_rssi_low = rssi_low; conf->cqm_rssi_high = rssi_high; link->u.mgd.last_cqm_event_signal = 0; if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return; if (sdata->u.mgd.associated && (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_CQM); } static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; int link_id; if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER && !(vif->driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) return -EOPNOTSUPP; /* For MLD, handle CQM change on all the active links */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_set_cqm_rssi_link(sdata, link, rssi_thold, rssi_hyst, 0, 0); } return 0; } static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_low, s32 rssi_high) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; int link_id; if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER) return -EOPNOTSUPP; /* For MLD, handle CQM change on all the active links */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_set_cqm_rssi_link(sdata, link, 0, 0, rssi_low, rssi_high); } return 0; } static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, const u8 *addr, const struct cfg80211_bitrate_mask *mask) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); int i, ret; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; /* * If active validate the setting and reject it if it doesn't leave * at least one basic rate usable, since we really have to be able * to send something, and if we're an AP we have to be able to do * so at a basic rate so that all clients can receive it. */ if (rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) && sdata->vif.bss_conf.chanreq.oper.chan) { u32 basic_rates = sdata->vif.bss_conf.basic_rates; enum nl80211_band band; band = sdata->vif.bss_conf.chanreq.oper.chan->band; if (!(mask->control[band].legacy & basic_rates)) return -EINVAL; } if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { ret = drv_set_bitrate_mask(local, sdata, mask); if (ret) return ret; } for (i = 0; i < NUM_NL80211_BANDS; i++) { struct ieee80211_supported_band *sband = wiphy->bands[i]; int j; sdata->rc_rateidx_mask[i] = mask->control[i].legacy; memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs, sizeof(mask->control[i].ht_mcs)); memcpy(sdata->rc_rateidx_vht_mcs_mask[i], mask->control[i].vht_mcs, sizeof(mask->control[i].vht_mcs)); sdata->rc_has_mcs_mask[i] = false; sdata->rc_has_vht_mcs_mask[i] = false; if (!sband) continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) { sdata->rc_has_mcs_mask[i] = true; break; } } for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) { sdata->rc_has_vht_mcs_mask[i] = true; break; } } } return 0; } static int ieee80211_start_radar_detection(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms, int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = *chandef }; struct ieee80211_local *local = sdata->local; struct ieee80211_link_data *link_data; int err; lockdep_assert_wiphy(local->hw.wiphy); if (!list_empty(&local->roc_list) || local->scanning) return -EBUSY; link_data = sdata_dereference(sdata->link[link_id], sdata); if (!link_data) return -ENOLINK; /* whatever, but channel contexts should not complain about that one */ link_data->smps_mode = IEEE80211_SMPS_OFF; link_data->needed_rx_chains = local->rx_chains; err = ieee80211_link_use_channel(link_data, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; wiphy_delayed_work_queue(wiphy, &link_data->dfs_cac_timer_work, msecs_to_jiffies(cac_time_ms)); return 0; } static void ieee80211_end_cac(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_link_data *link_data; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { link_data = sdata_dereference(sdata->link[link_id], sdata); if (!link_data) continue; wiphy_delayed_work_cancel(wiphy, &link_data->dfs_cac_timer_work); if (sdata->wdev.links[link_id].cac_started) { ieee80211_link_release_channel(link_data); sdata->wdev.links[link_id].cac_started = false; } } } static struct cfg80211_beacon_data * cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) { struct cfg80211_beacon_data *new_beacon; u8 *pos; int len; len = beacon->head_len + beacon->tail_len + beacon->beacon_ies_len + beacon->proberesp_ies_len + beacon->assocresp_ies_len + beacon->probe_resp_len + beacon->lci_len + beacon->civicloc_len; if (beacon->mbssid_ies) len += ieee80211_get_mbssid_beacon_len(beacon->mbssid_ies, beacon->rnr_ies, beacon->mbssid_ies->cnt); new_beacon = kzalloc(sizeof(*new_beacon) + len, GFP_KERNEL); if (!new_beacon) return NULL; if (beacon->mbssid_ies && beacon->mbssid_ies->cnt) { new_beacon->mbssid_ies = kzalloc(struct_size(new_beacon->mbssid_ies, elem, beacon->mbssid_ies->cnt), GFP_KERNEL); if (!new_beacon->mbssid_ies) { kfree(new_beacon); return NULL; } if (beacon->rnr_ies && beacon->rnr_ies->cnt) { new_beacon->rnr_ies = kzalloc(struct_size(new_beacon->rnr_ies, elem, beacon->rnr_ies->cnt), GFP_KERNEL); if (!new_beacon->rnr_ies) { kfree(new_beacon->mbssid_ies); kfree(new_beacon); return NULL; } } } pos = (u8 *)(new_beacon + 1); if (beacon->head_len) { new_beacon->head_len = beacon->head_len; new_beacon->head = pos; memcpy(pos, beacon->head, beacon->head_len); pos += beacon->head_len; } if (beacon->tail_len) { new_beacon->tail_len = beacon->tail_len; new_beacon->tail = pos; memcpy(pos, beacon->tail, beacon->tail_len); pos += beacon->tail_len; } if (beacon->beacon_ies_len) { new_beacon->beacon_ies_len = beacon->beacon_ies_len; new_beacon->beacon_ies = pos; memcpy(pos, beacon->beacon_ies, beacon->beacon_ies_len); pos += beacon->beacon_ies_len; } if (beacon->proberesp_ies_len) { new_beacon->proberesp_ies_len = beacon->proberesp_ies_len; new_beacon->proberesp_ies = pos; memcpy(pos, beacon->proberesp_ies, beacon->proberesp_ies_len); pos += beacon->proberesp_ies_len; } if (beacon->assocresp_ies_len) { new_beacon->assocresp_ies_len = beacon->assocresp_ies_len; new_beacon->assocresp_ies = pos; memcpy(pos, beacon->assocresp_ies, beacon->assocresp_ies_len); pos += beacon->assocresp_ies_len; } if (beacon->probe_resp_len) { new_beacon->probe_resp_len = beacon->probe_resp_len; new_beacon->probe_resp = pos; memcpy(pos, beacon->probe_resp, beacon->probe_resp_len); pos += beacon->probe_resp_len; } if (beacon->mbssid_ies && beacon->mbssid_ies->cnt) { pos += ieee80211_copy_mbssid_beacon(pos, new_beacon->mbssid_ies, beacon->mbssid_ies); if (beacon->rnr_ies && beacon->rnr_ies->cnt) pos += ieee80211_copy_rnr_beacon(pos, new_beacon->rnr_ies, beacon->rnr_ies); } /* might copy -1, meaning no changes requested */ new_beacon->ftm_responder = beacon->ftm_responder; if (beacon->lci) { new_beacon->lci_len = beacon->lci_len; new_beacon->lci = pos; memcpy(pos, beacon->lci, beacon->lci_len); pos += beacon->lci_len; } if (beacon->civicloc) { new_beacon->civicloc_len = beacon->civicloc_len; new_beacon->civicloc = pos; memcpy(pos, beacon->civicloc, beacon->civicloc_len); pos += beacon->civicloc_len; } return new_beacon; } void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_bss_conf *tx_bss_conf; struct ieee80211_link_data *link_data; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return; rcu_read_lock(); link_data = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link_data)) { rcu_read_unlock(); return; } tx_bss_conf = rcu_dereference(link_data->conf->tx_bss_conf); if (tx_bss_conf == link_data->conf) { /* Trigger ieee80211_csa_finish() on the non-transmitting * interfaces when channel switch is received on * transmitting interface */ struct ieee80211_link_data *iter; for_each_sdata_link(local, iter) { if (iter->sdata == sdata || rcu_access_pointer(iter->conf->tx_bss_conf) != tx_bss_conf) continue; wiphy_work_queue(iter->sdata->local->hw.wiphy, &iter->csa.finalize_work); } } wiphy_work_queue(local->hw.wiphy, &link_data->csa.finalize_work); rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_csa_finish); void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; sdata_info(sdata, "channel switch failed, disconnecting\n"); wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work); } EXPORT_SYMBOL(ieee80211_channel_switch_disconnect); static int ieee80211_set_after_csa_beacon(struct ieee80211_link_data *link_data, u64 *changed) { struct ieee80211_sub_if_data *sdata = link_data->sdata; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: if (!link_data->u.ap.next_beacon) return -EINVAL; err = ieee80211_assign_beacon(sdata, link_data, link_data->u.ap.next_beacon, NULL, NULL, changed); ieee80211_free_next_beacon(link_data); if (err < 0) return err; break; case NL80211_IFTYPE_ADHOC: err = ieee80211_ibss_finish_csa(sdata, changed); if (err < 0) return err; break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: err = ieee80211_mesh_finish_csa(sdata, changed); if (err < 0) return err; break; #endif default: WARN_ON(1); return -EINVAL; } return 0; } static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) { struct ieee80211_sub_if_data *sdata = link_data->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_bss_conf *link_conf = link_data->conf; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); /* * using reservation isn't immediate as it may be deferred until later * with multi-vif. once reservation is complete it will re-schedule the * work with no reserved_chanctx so verify chandef to check if it * completed successfully */ if (link_data->reserved_chanctx) { /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their * reservations */ if (link_data->reserved_ready) return 0; return ieee80211_link_use_reserved_context(link_data); } if (!cfg80211_chandef_identical(&link_conf->chanreq.oper, &link_data->csa.chanreq.oper)) return -EINVAL; link_conf->csa_active = false; err = ieee80211_set_after_csa_beacon(link_data, &changed); if (err) return err; ieee80211_link_info_change_notify(sdata, link_data, changed); ieee80211_vif_unblock_queues_csa(sdata); err = drv_post_channel_switch(link_data); if (err) return err; cfg80211_ch_switch_notify(sdata->dev, &link_data->csa.chanreq.oper, link_data->link_id); return 0; } static void ieee80211_csa_finalize(struct ieee80211_link_data *link_data) { struct ieee80211_sub_if_data *sdata = link_data->sdata; if (__ieee80211_csa_finalize(link_data)) { sdata_info(sdata, "failed to finalize CSA on link %d, disconnecting\n", link_data->link_id); cfg80211_stop_iface(sdata->local->hw.wiphy, &sdata->wdev, GFP_KERNEL); } } void ieee80211_csa_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, csa.finalize_work); struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); /* AP might have been stopped while waiting for the lock. */ if (!link->conf->csa_active) return; if (!ieee80211_sdata_running(sdata)) return; ieee80211_csa_finalize(link); } static int ieee80211_set_csa_beacon(struct ieee80211_link_data *link_data, struct cfg80211_csa_settings *params, u64 *changed) { struct ieee80211_sub_if_data *sdata = link_data->sdata; struct ieee80211_csa_settings csa = {}; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: link_data->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_after); if (!link_data->u.ap.next_beacon) return -ENOMEM; /* * With a count of 0, we don't have to wait for any * TBTT before switching, so complete the CSA * immediately. In theory, with a count == 1 we * should delay the switch until just before the next * TBTT, but that would complicate things so we switch * immediately too. If we would delay the switch * until the next TBTT, we would have to set the probe * response here. * * TODO: A channel switch with count <= 1 without * sending a CSA action frame is kind of useless, * because the clients won't know we're changing * channels. The action frame must be implemented * either here or in the userspace. */ if (params->count <= 1) break; if ((params->n_counter_offsets_beacon > IEEE80211_MAX_CNTDWN_COUNTERS_NUM) || (params->n_counter_offsets_presp > IEEE80211_MAX_CNTDWN_COUNTERS_NUM)) { ieee80211_free_next_beacon(link_data); return -EINVAL; } csa.counter_offsets_beacon = params->counter_offsets_beacon; csa.counter_offsets_presp = params->counter_offsets_presp; csa.n_counter_offsets_beacon = params->n_counter_offsets_beacon; csa.n_counter_offsets_presp = params->n_counter_offsets_presp; csa.count = params->count; err = ieee80211_assign_beacon(sdata, link_data, ¶ms->beacon_csa, &csa, NULL, changed); if (err < 0) { ieee80211_free_next_beacon(link_data); return err; } break; case NL80211_IFTYPE_ADHOC: if (!sdata->vif.cfg.ibss_joined) return -EINVAL; if (params->chandef.width != sdata->u.ibss.chandef.width) return -EINVAL; switch (params->chandef.width) { case NL80211_CHAN_WIDTH_40: if (cfg80211_get_chandef_type(¶ms->chandef) != cfg80211_get_chandef_type(&sdata->u.ibss.chandef)) return -EINVAL; break; case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: break; default: return -EINVAL; } /* changes into another band are not supported */ if (sdata->u.ibss.chandef.chan->band != params->chandef.chan->band) return -EINVAL; /* see comments in the NL80211_IFTYPE_AP block */ if (params->count > 1) { err = ieee80211_ibss_csa_beacon(sdata, params, changed); if (err < 0) return err; } ieee80211_send_action_csa(sdata, params); break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; /* changes into another band are not supported */ if (sdata->vif.bss_conf.chanreq.oper.chan->band != params->chandef.chan->band) return -EINVAL; if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_NONE) { ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_INIT; if (!ifmsh->pre_value) ifmsh->pre_value = 1; else ifmsh->pre_value++; } /* see comments in the NL80211_IFTYPE_AP block */ if (params->count > 1) { err = ieee80211_mesh_csa_beacon(sdata, params, changed); if (err < 0) { ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE; return err; } } if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT) ieee80211_send_action_csa(sdata, params); break; } #endif default: return -EOPNOTSUPP; } return 0; } static void ieee80211_color_change_abort(struct ieee80211_link_data *link) { link->conf->color_change_active = false; ieee80211_free_next_beacon(link); cfg80211_color_change_aborted_notify(link->sdata->dev, link->link_id); } static int __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = params->chandef }; struct ieee80211_local *local = sdata->local; struct ieee80211_channel_switch ch_switch = { .link_id = params->link_id, }; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; struct ieee80211_bss_conf *link_conf; struct ieee80211_link_data *link_data; u64 changed = 0; u8 link_id = params->link_id; int err; lockdep_assert_wiphy(local->hw.wiphy); if (!list_empty(&local->roc_list) || local->scanning) return -EBUSY; if (sdata->wdev.links[link_id].cac_started) return -EBUSY; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return -EINVAL; link_data = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link_data) return -ENOLINK; link_conf = link_data->conf; if (chanreq.oper.punctured && !link_conf->eht_support) return -EINVAL; /* don't allow another channel switch if one is already active. */ if (link_conf->csa_active) return -EBUSY; conf = wiphy_dereference(wiphy, link_conf->chanctx_conf); if (!conf) { err = -EBUSY; goto out; } if (params->chandef.chan->freq_offset) { /* this may work, but is untested */ err = -EOPNOTSUPP; goto out; } chanctx = container_of(conf, struct ieee80211_chanctx, conf); ch_switch.timestamp = 0; ch_switch.device_timestamp = 0; ch_switch.block_tx = params->block_tx; ch_switch.chandef = chanreq.oper; ch_switch.count = params->count; err = drv_pre_channel_switch(sdata, &ch_switch); if (err) goto out; err = ieee80211_link_reserve_chanctx(link_data, &chanreq, chanctx->mode, params->radar_required); if (err) goto out; /* if reservation is invalid then this will fail */ err = ieee80211_check_combinations(sdata, NULL, chanctx->mode, 0, -1); if (err) { ieee80211_link_unreserve_chanctx(link_data); goto out; } /* if there is a color change in progress, abort it */ if (link_conf->color_change_active) ieee80211_color_change_abort(link_data); err = ieee80211_set_csa_beacon(link_data, params, &changed); if (err) { ieee80211_link_unreserve_chanctx(link_data); goto out; } link_data->csa.chanreq = chanreq; link_conf->csa_active = true; if (params->block_tx) ieee80211_vif_block_queues_csa(sdata); cfg80211_ch_switch_started_notify(sdata->dev, &link_data->csa.chanreq.oper, link_id, params->count, params->block_tx); if (changed) { ieee80211_link_info_change_notify(sdata, link_data, changed); drv_channel_switch_beacon(sdata, &link_data->csa.chanreq.oper); } else { /* if the beacon didn't change, we can finalize immediately */ ieee80211_csa_finalize(link_data); } out: return err; } int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); return __ieee80211_channel_switch(wiphy, dev, params); } u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local) { lockdep_assert_wiphy(local->hw.wiphy); local->roc_cookie_counter++; /* wow, you wrapped 64 bits ... more likely a bug */ if (WARN_ON(local->roc_cookie_counter == 0)) local->roc_cookie_counter++; return local->roc_cookie_counter; } int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb, u64 *cookie, gfp_t gfp) { unsigned long spin_flags; struct sk_buff *ack_skb; int id; ack_skb = skb_copy(skb, gfp); if (!ack_skb) return -ENOMEM; spin_lock_irqsave(&local->ack_status_lock, spin_flags); id = idr_alloc(&local->ack_status_frames, ack_skb, 1, 0x2000, GFP_ATOMIC); spin_unlock_irqrestore(&local->ack_status_lock, spin_flags); if (id < 0) { kfree_skb(ack_skb); return -ENOMEM; } IEEE80211_SKB_CB(skb)->status_data_idr = 1; IEEE80211_SKB_CB(skb)->status_data = id; *cookie = ieee80211_mgmt_tx_cookie(local); IEEE80211_SKB_CB(ack_skb)->ack.cookie = *cookie; return 0; } static void ieee80211_update_mgmt_frame_registrations(struct wiphy *wiphy, struct wireless_dev *wdev, struct mgmt_frame_regs *upd) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); u32 preq_mask = BIT(IEEE80211_STYPE_PROBE_REQ >> 4); u32 action_mask = BIT(IEEE80211_STYPE_ACTION >> 4); bool global_change, intf_change; global_change = (local->probe_req_reg != !!(upd->global_stypes & preq_mask)) || (local->rx_mcast_action_reg != !!(upd->global_mcast_stypes & action_mask)); local->probe_req_reg = upd->global_stypes & preq_mask; local->rx_mcast_action_reg = upd->global_mcast_stypes & action_mask; intf_change = (sdata->vif.probe_req_reg != !!(upd->interface_stypes & preq_mask)) || (sdata->vif.rx_mcast_action_reg != !!(upd->interface_mcast_stypes & action_mask)); sdata->vif.probe_req_reg = upd->interface_stypes & preq_mask; sdata->vif.rx_mcast_action_reg = upd->interface_mcast_stypes & action_mask; if (!local->open_count) return; if (intf_change && ieee80211_sdata_running(sdata)) drv_config_iface_filter(local, sdata, sdata->vif.probe_req_reg ? FIF_PROBE_REQ : 0, FIF_PROBE_REQ); if (global_change) ieee80211_configure_filter(local); } static int ieee80211_set_antenna(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant) { struct ieee80211_local *local = wiphy_priv(wiphy); int ret; if (local->started) return -EOPNOTSUPP; ret = drv_set_antenna(local, tx_ant, rx_ant); if (ret) return ret; local->rx_chains = hweight8(rx_ant); return 0; } static int ieee80211_get_antenna(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant) { struct ieee80211_local *local = wiphy_priv(wiphy); return drv_get_antenna(local, tx_ant, rx_ant); } static int ieee80211_set_rekey_data(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_gtk_rekey_data *data) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!local->ops->set_rekey_data) return -EOPNOTSUPP; drv_set_rekey_data(local, sdata, data); return 0; } static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_qos_hdr *nullfunc; struct sk_buff *skb; int size = sizeof(*nullfunc); __le16 fc; bool qos; struct ieee80211_tx_info *info; struct sta_info *sta; struct ieee80211_chanctx_conf *chanctx_conf; enum nl80211_band band; int ret; /* the lock is needed to assign the cookie later */ lockdep_assert_wiphy(local->hw.wiphy); rcu_read_lock(); sta = sta_info_get_bss(sdata, peer); if (!sta) { ret = -ENOLINK; goto unlock; } qos = sta->sta.wme; chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (WARN_ON(!chanctx_conf)) { ret = -EINVAL; goto unlock; } band = chanctx_conf->def.chan->band; if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | IEEE80211_FCTL_FROMDS); } else { size -= 2; fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | IEEE80211_FCTL_FROMDS); } skb = dev_alloc_skb(local->hw.extra_tx_headroom + size); if (!skb) { ret = -ENOMEM; goto unlock; } skb->dev = dev; skb_reserve(skb, local->hw.extra_tx_headroom); nullfunc = skb_put(skb, size); nullfunc->frame_control = fc; nullfunc->duration_id = 0; memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); nullfunc->seq_ctrl = 0; info = IEEE80211_SKB_CB(skb); info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_NL80211_FRAME_TX; info->band = band; skb_set_queue_mapping(skb, IEEE80211_AC_VO); skb->priority = 7; if (qos) nullfunc->qos_ctrl = cpu_to_le16(7); ret = ieee80211_attach_ack_skb(local, skb, cookie, GFP_ATOMIC); if (ret) { kfree_skb(skb); goto unlock; } local_bh_disable(); ieee80211_xmit(sdata, sta, skb); local_bh_enable(); ret = 0; unlock: rcu_read_unlock(); return ret; } static int ieee80211_cfg_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_link_data *link; int ret = -ENODATA; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (!link) { ret = -ENOLINK; goto out; } chanctx_conf = rcu_dereference(link->conf->chanctx_conf); if (chanctx_conf) { *chandef = link->conf->chanreq.oper; ret = 0; } else if (local->open_count > 0 && local->open_count == local->virt_monitors && sdata->vif.type == NL80211_IFTYPE_MONITOR) { *chandef = local->monitor_chanreq.oper; ret = 0; } out: rcu_read_unlock(); return ret; } #ifdef CONFIG_PM static void ieee80211_set_wakeup(struct wiphy *wiphy, bool enabled) { drv_set_wakeup(wiphy_priv(wiphy), enabled); } #endif static int ieee80211_set_qos_map(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_qos_map *qos_map) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct mac80211_qos_map *new_qos_map, *old_qos_map; if (qos_map) { new_qos_map = kzalloc(sizeof(*new_qos_map), GFP_KERNEL); if (!new_qos_map) return -ENOMEM; memcpy(&new_qos_map->qos_map, qos_map, sizeof(*qos_map)); } else { /* A NULL qos_map was passed to disable QoS mapping */ new_qos_map = NULL; } old_qos_map = sdata_dereference(sdata->qos_map, sdata); rcu_assign_pointer(sdata->qos_map, new_qos_map); if (old_qos_map) kfree_rcu(old_qos_map, rcu_head); return 0; } static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct ieee80211_chan_req chanreq = { .oper = *chandef }; int ret; u64 changed = 0; link = sdata_dereference(sdata->link[link_id], sdata); ret = ieee80211_link_change_chanreq(link, &chanreq, &changed); if (ret == 0) ieee80211_link_info_change_notify(sdata, link, changed); return ret; } static int ieee80211_add_tx_ts(struct wiphy *wiphy, struct net_device *dev, u8 tsid, const u8 *peer, u8 up, u16 admitted_time) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; int ac = ieee802_1d_to_ac[up]; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!(sdata->wmm_acm & BIT(up))) return -EINVAL; if (ifmgd->tx_tspec[ac].admitted_time) return -EBUSY; if (admitted_time) { ifmgd->tx_tspec[ac].admitted_time = 32 * admitted_time; ifmgd->tx_tspec[ac].tsid = tsid; ifmgd->tx_tspec[ac].up = up; } return 0; } static int ieee80211_del_tx_ts(struct wiphy *wiphy, struct net_device *dev, u8 tsid, const u8 *peer) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = wiphy_priv(wiphy); int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; /* skip unused entries */ if (!tx_tspec->admitted_time) continue; if (tx_tspec->tsid != tsid) continue; /* due to this new packets will be reassigned to non-ACM ACs */ tx_tspec->up = -1; /* Make sure that all packets have been sent to avoid to * restore the QoS params on packets that are still on the * queues. */ synchronize_net(); ieee80211_flush_queues(local, sdata, false); /* restore the normal QoS parameters * (unconditionally to avoid races) */ tx_tspec->action = TX_TSPEC_ACTION_STOP_DOWNGRADE; tx_tspec->downgraded = false; ieee80211_sta_handle_tspec_ac_params(sdata); /* finally clear all the data */ memset(tx_tspec, 0, sizeof(*tx_tspec)); return 0; } return -ENOENT; } void ieee80211_nan_func_terminated(struct ieee80211_vif *vif, u8 inst_id, enum nl80211_nan_func_term_reason reason, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct cfg80211_nan_func *func; u64 cookie; if (WARN_ON(vif->type != NL80211_IFTYPE_NAN)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = idr_find(&sdata->u.nan.function_inst_ids, inst_id); if (WARN_ON(!func)) { spin_unlock_bh(&sdata->u.nan.func_lock); return; } cookie = func->cookie; idr_remove(&sdata->u.nan.function_inst_ids, inst_id); spin_unlock_bh(&sdata->u.nan.func_lock); cfg80211_free_nan_func(func); cfg80211_nan_func_terminated(ieee80211_vif_to_wdev(vif), inst_id, reason, cookie, gfp); } EXPORT_SYMBOL(ieee80211_nan_func_terminated); void ieee80211_nan_func_match(struct ieee80211_vif *vif, struct cfg80211_nan_match_params *match, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct cfg80211_nan_func *func; if (WARN_ON(vif->type != NL80211_IFTYPE_NAN)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = idr_find(&sdata->u.nan.function_inst_ids, match->inst_id); if (WARN_ON(!func)) { spin_unlock_bh(&sdata->u.nan.func_lock); return; } match->cookie = func->cookie; spin_unlock_bh(&sdata->u.nan.func_lock); cfg80211_nan_match(ieee80211_vif_to_wdev(vif), match, gfp); } EXPORT_SYMBOL(ieee80211_nan_func_match); static int ieee80211_set_multicast_to_unicast(struct wiphy *wiphy, struct net_device *dev, const bool enabled) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->u.ap.multicast_to_unicast = enabled; return 0; } void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats, struct txq_info *txqi) { if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_BACKLOG_BYTES))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_BYTES); txqstats->backlog_bytes = txqi->tin.backlog_bytes; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS); txqstats->backlog_packets = txqi->tin.backlog_packets; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_FLOWS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_FLOWS); txqstats->flows = txqi->tin.flows; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_DROPS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_DROPS); txqstats->drops = txqi->cstats.drop_count; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_ECN_MARKS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_ECN_MARKS); txqstats->ecn_marks = txqi->cstats.ecn_mark; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_OVERLIMIT))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_OVERLIMIT); txqstats->overlimit = txqi->tin.overlimit; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_COLLISIONS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_COLLISIONS); txqstats->collisions = txqi->tin.collisions; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_TX_BYTES))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_TX_BYTES); txqstats->tx_bytes = txqi->tin.tx_bytes; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_TX_PACKETS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_TX_PACKETS); txqstats->tx_packets = txqi->tin.tx_packets; } } static int ieee80211_get_txq_stats(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_txq_stats *txqstats) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; int ret = 0; spin_lock_bh(&local->fq.lock); rcu_read_lock(); if (wdev) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (!sdata->vif.txq) { ret = 1; goto out; } ieee80211_fill_txq_stats(txqstats, to_txq_info(sdata->vif.txq)); } else { /* phy stats */ txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS) | BIT(NL80211_TXQ_STATS_BACKLOG_BYTES) | BIT(NL80211_TXQ_STATS_OVERLIMIT) | BIT(NL80211_TXQ_STATS_OVERMEMORY) | BIT(NL80211_TXQ_STATS_COLLISIONS) | BIT(NL80211_TXQ_STATS_MAX_FLOWS); txqstats->backlog_packets = local->fq.backlog; txqstats->backlog_bytes = local->fq.memory_usage; txqstats->overlimit = local->fq.overlimit; txqstats->overmemory = local->fq.overmemory; txqstats->collisions = local->fq.collisions; txqstats->max_flows = local->fq.flows_cnt; } out: rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); return ret; } static int ieee80211_get_ftm_responder_stats(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); return drv_get_ftm_responder_stats(local, sdata, ftm_stats); } static int ieee80211_start_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, struct cfg80211_pmsr_request *request) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(dev); return drv_start_pmsr(local, sdata, request); } static void ieee80211_abort_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, struct cfg80211_pmsr_request *request) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(dev); return drv_abort_pmsr(local, sdata, request); } static int ieee80211_set_tid_config(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_tid_config *tid_conf) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (!sdata->local->ops->set_tid_config) return -EOPNOTSUPP; if (!tid_conf->peer) return drv_set_tid_config(sdata->local, sdata, NULL, tid_conf); sta = sta_info_get_bss(sdata, tid_conf->peer); if (!sta) return -ENOENT; return drv_set_tid_config(sdata->local, sdata, &sta->sta, tid_conf); } static int ieee80211_reset_tid_config(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u8 tids) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (!sdata->local->ops->reset_tid_config) return -EOPNOTSUPP; if (!peer) return drv_reset_tid_config(sdata->local, sdata, NULL, tids); sta = sta_info_get_bss(sdata, peer); if (!sta) return -ENOENT; return drv_reset_tid_config(sdata->local, sdata, &sta->sta, tids); } static int ieee80211_set_sar_specs(struct wiphy *wiphy, struct cfg80211_sar_specs *sar) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->set_sar_specs) return -EOPNOTSUPP; return local->ops->set_sar_specs(&local->hw, sar); } static int ieee80211_set_after_color_change_beacon(struct ieee80211_link_data *link, u64 *changed) { struct ieee80211_sub_if_data *sdata = link->sdata; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: { int ret; if (!link->u.ap.next_beacon) return -EINVAL; ret = ieee80211_assign_beacon(sdata, link, link->u.ap.next_beacon, NULL, NULL, changed); ieee80211_free_next_beacon(link); if (ret < 0) return ret; break; } default: WARN_ON_ONCE(1); return -EINVAL; } return 0; } static int ieee80211_set_color_change_beacon(struct ieee80211_link_data *link, struct cfg80211_color_change_settings *params, u64 *changed) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_color_change_settings color_change = {}; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: link->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_next); if (!link->u.ap.next_beacon) return -ENOMEM; if (params->count <= 1) break; color_change.counter_offset_beacon = params->counter_offset_beacon; color_change.counter_offset_presp = params->counter_offset_presp; color_change.count = params->count; err = ieee80211_assign_beacon(sdata, link, ¶ms->beacon_color_change, NULL, &color_change, changed); if (err < 0) { ieee80211_free_next_beacon(link); return err; } break; default: return -EOPNOTSUPP; } return 0; } static void ieee80211_color_change_bss_config_notify(struct ieee80211_link_data *link, u8 color, int enable, u64 changed) { struct ieee80211_sub_if_data *sdata = link->sdata; lockdep_assert_wiphy(sdata->local->hw.wiphy); link->conf->he_bss_color.color = color; link->conf->he_bss_color.enabled = enable; changed |= BSS_CHANGED_HE_BSS_COLOR; ieee80211_link_info_change_notify(sdata, link, changed); if (!link->conf->nontransmitted && rcu_access_pointer(link->conf->tx_bss_conf)) { struct ieee80211_link_data *tmp; for_each_sdata_link(sdata->local, tmp) { if (tmp->sdata == sdata || rcu_access_pointer(tmp->conf->tx_bss_conf) != link->conf) continue; tmp->conf->he_bss_color.color = color; tmp->conf->he_bss_color.enabled = enable; ieee80211_link_info_change_notify(tmp->sdata, tmp, BSS_CHANGED_HE_BSS_COLOR); } } } static int ieee80211_color_change_finalize(struct ieee80211_link_data *link) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); link->conf->color_change_active = false; err = ieee80211_set_after_color_change_beacon(link, &changed); if (err) { cfg80211_color_change_aborted_notify(sdata->dev, link->link_id); return err; } ieee80211_color_change_bss_config_notify(link, link->conf->color_change_color, 1, changed); cfg80211_color_change_notify(sdata->dev, link->link_id); return 0; } void ieee80211_color_change_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, color_change_finalize_work); struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_bss_conf *link_conf = link->conf; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); /* AP might have been stopped while waiting for the lock. */ if (!link_conf->color_change_active) return; if (!ieee80211_sdata_running(sdata)) return; ieee80211_color_change_finalize(link); } void ieee80211_color_collision_detection_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, color_collision_detect_work.work); struct ieee80211_sub_if_data *sdata = link->sdata; cfg80211_obss_color_collision_notify(sdata->dev, link->color_bitmap, link->link_id); } void ieee80211_color_change_finish(struct ieee80211_vif *vif, u8 link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_link_data *link; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link)) { rcu_read_unlock(); return; } wiphy_work_queue(sdata->local->hw.wiphy, &link->color_change_finalize_work); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, u64 color_bitmap, u8 link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_link_data *link; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link)) { rcu_read_unlock(); return; } if (link->conf->color_change_active || link->conf->csa_active) { rcu_read_unlock(); return; } if (wiphy_delayed_work_pending(sdata->local->hw.wiphy, &link->color_collision_detect_work)) { rcu_read_unlock(); return; } link->color_bitmap = color_bitmap; /* queue the color collision detection event every 500 ms in order to * avoid sending too much netlink messages to userspace. */ wiphy_delayed_work_queue(sdata->local->hw.wiphy, &link->color_collision_detect_work, msecs_to_jiffies(500)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_obss_color_collision_notify); static int ieee80211_color_change(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_bss_conf *link_conf; struct ieee80211_link_data *link; u8 link_id = params->link_id; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return -EINVAL; link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) return -ENOLINK; link_conf = link->conf; if (link_conf->nontransmitted) return -EINVAL; /* don't allow another color change if one is already active or if csa * is active */ if (link_conf->color_change_active || link_conf->csa_active) { err = -EBUSY; goto out; } err = ieee80211_set_color_change_beacon(link, params, &changed); if (err) goto out; link_conf->color_change_active = true; link_conf->color_change_color = params->color; cfg80211_color_change_started_notify(sdata->dev, params->count, link_id); if (changed) ieee80211_color_change_bss_config_notify(link, 0, 0, changed); else /* if the beacon didn't change, we can finalize immediately */ ieee80211_color_change_finalize(link); out: return err; } static int ieee80211_set_radar_background(struct wiphy *wiphy, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->set_radar_background) return -EOPNOTSUPP; return local->ops->set_radar_background(&local->hw, chandef); } static int ieee80211_add_intf_link(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); lockdep_assert_wiphy(sdata->local->hw.wiphy); if (wdev->use_4addr) return -EOPNOTSUPP; return ieee80211_vif_set_links(sdata, wdev->valid_links, 0); } static void ieee80211_del_intf_link(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); u16 new_links = wdev->valid_links & ~BIT(link_id); lockdep_assert_wiphy(sdata->local->hw.wiphy); /* During the link teardown process, certain functions require the * link_id to remain in the valid_links bitmap. Therefore, instead * of removing the link_id from the bitmap, pass a masked value to * simulate as if link_id does not exist anymore. */ ieee80211_vif_set_links(sdata, new_links, 0); } static int ieee80211_add_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; int ret; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; if (!sta->sta.valid_links) return -EINVAL; if (sta->sta.valid_links & BIT(params->link_id)) return -EALREADY; ret = ieee80211_sta_allocate_link(sta, params->link_id); if (ret) return ret; ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_NEW, params); if (ret) { ieee80211_sta_free_link(sta, params->link_id); return ret; } if (test_sta_flag(sta, WLAN_STA_ASSOC)) { struct link_sta_info *link_sta; link_sta = sdata_dereference(sta->link[params->link_id], sdata); rate_control_rate_init(link_sta); } /* ieee80211_sta_activate_link frees the link upon failure */ return ieee80211_sta_activate_link(sta, params->link_id); } static int ieee80211_mod_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; if (!(sta->sta.valid_links & BIT(params->link_id))) return -EINVAL; return sta_link_apply_parameters(local, sta, STA_LINK_MODE_LINK_MODIFY, params); } static int ieee80211_del_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_del_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; if (!(sta->sta.valid_links & BIT(params->link_id))) return -EINVAL; /* must not create a STA without links */ if (sta->sta.valid_links == BIT(params->link_id)) return -EINVAL; ieee80211_sta_remove_link(sta, params->link_id); return 0; } static int ieee80211_set_hw_timestamp(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; if (!local->ops->set_hw_timestamp) return -EOPNOTSUPP; if (!check_sdata_in_driver(sdata)) return -EIO; return local->ops->set_hw_timestamp(&local->hw, &sdata->vif, hwts); } static int ieee80211_set_ttlm(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ttlm_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); lockdep_assert_wiphy(sdata->local->hw.wiphy); return ieee80211_req_neg_ttlm(sdata, params); } static int ieee80211_assoc_ml_reconf(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ml_reconf_req *req) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); lockdep_assert_wiphy(sdata->local->hw.wiphy); return ieee80211_mgd_assoc_ml_reconf(sdata, req); } static int ieee80211_set_epcs(struct wiphy *wiphy, struct net_device *dev, bool enable) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); return ieee80211_mgd_set_epcs(sdata, enable); } const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, .change_virtual_intf = ieee80211_change_iface, .start_p2p_device = ieee80211_start_p2p_device, .stop_p2p_device = ieee80211_stop_p2p_device, .add_key = ieee80211_add_key, .del_key = ieee80211_del_key, .get_key = ieee80211_get_key, .set_default_key = ieee80211_config_default_key, .set_default_mgmt_key = ieee80211_config_default_mgmt_key, .set_default_beacon_key = ieee80211_config_default_beacon_key, .start_ap = ieee80211_start_ap, .change_beacon = ieee80211_change_beacon, .stop_ap = ieee80211_stop_ap, .add_station = ieee80211_add_station, .del_station = ieee80211_del_station, .change_station = ieee80211_change_station, .get_station = ieee80211_get_station, .dump_station = ieee80211_dump_station, .dump_survey = ieee80211_dump_survey, #ifdef CONFIG_MAC80211_MESH .add_mpath = ieee80211_add_mpath, .del_mpath = ieee80211_del_mpath, .change_mpath = ieee80211_change_mpath, .get_mpath = ieee80211_get_mpath, .dump_mpath = ieee80211_dump_mpath, .get_mpp = ieee80211_get_mpp, .dump_mpp = ieee80211_dump_mpp, .update_mesh_config = ieee80211_update_mesh_config, .get_mesh_config = ieee80211_get_mesh_config, .join_mesh = ieee80211_join_mesh, .leave_mesh = ieee80211_leave_mesh, #endif .join_ocb = ieee80211_join_ocb, .leave_ocb = ieee80211_leave_ocb, .change_bss = ieee80211_change_bss, .inform_bss = ieee80211_inform_bss, .set_txq_params = ieee80211_set_txq_params, .set_monitor_channel = ieee80211_set_monitor_channel, .suspend = ieee80211_suspend, .resume = ieee80211_resume, .scan = ieee80211_scan, .abort_scan = ieee80211_abort_scan, .sched_scan_start = ieee80211_sched_scan_start, .sched_scan_stop = ieee80211_sched_scan_stop, .auth = ieee80211_auth, .assoc = ieee80211_assoc, .deauth = ieee80211_deauth, .disassoc = ieee80211_disassoc, .join_ibss = ieee80211_join_ibss, .leave_ibss = ieee80211_leave_ibss, .set_mcast_rate = ieee80211_set_mcast_rate, .set_wiphy_params = ieee80211_set_wiphy_params, .set_tx_power = ieee80211_set_tx_power, .get_tx_power = ieee80211_get_tx_power, .rfkill_poll = ieee80211_rfkill_poll, CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd) CFG80211_TESTMODE_DUMP(ieee80211_testmode_dump) .set_power_mgmt = ieee80211_set_power_mgmt, .set_bitrate_mask = ieee80211_set_bitrate_mask, .remain_on_channel = ieee80211_remain_on_channel, .cancel_remain_on_channel = ieee80211_cancel_remain_on_channel, .mgmt_tx = ieee80211_mgmt_tx, .mgmt_tx_cancel_wait = ieee80211_mgmt_tx_cancel_wait, .set_cqm_rssi_config = ieee80211_set_cqm_rssi_config, .set_cqm_rssi_range_config = ieee80211_set_cqm_rssi_range_config, .update_mgmt_frame_registrations = ieee80211_update_mgmt_frame_registrations, .set_antenna = ieee80211_set_antenna, .get_antenna = ieee80211_get_antenna, .set_rekey_data = ieee80211_set_rekey_data, .tdls_oper = ieee80211_tdls_oper, .tdls_mgmt = ieee80211_tdls_mgmt, .tdls_channel_switch = ieee80211_tdls_channel_switch, .tdls_cancel_channel_switch = ieee80211_tdls_cancel_channel_switch, .probe_client = ieee80211_probe_client, .set_noack_map = ieee80211_set_noack_map, #ifdef CONFIG_PM .set_wakeup = ieee80211_set_wakeup, #endif .get_channel = ieee80211_cfg_get_channel, .start_radar_detection = ieee80211_start_radar_detection, .end_cac = ieee80211_end_cac, .channel_switch = ieee80211_channel_switch, .set_qos_map = ieee80211_set_qos_map, .set_ap_chanwidth = ieee80211_set_ap_chanwidth, .add_tx_ts = ieee80211_add_tx_ts, .del_tx_ts = ieee80211_del_tx_ts, .start_nan = ieee80211_start_nan, .stop_nan = ieee80211_stop_nan, .nan_change_conf = ieee80211_nan_change_conf, .add_nan_func = ieee80211_add_nan_func, .del_nan_func = ieee80211_del_nan_func, .set_multicast_to_unicast = ieee80211_set_multicast_to_unicast, .tx_control_port = ieee80211_tx_control_port, .get_txq_stats = ieee80211_get_txq_stats, .get_ftm_responder_stats = ieee80211_get_ftm_responder_stats, .start_pmsr = ieee80211_start_pmsr, .abort_pmsr = ieee80211_abort_pmsr, .probe_mesh_link = ieee80211_probe_mesh_link, .set_tid_config = ieee80211_set_tid_config, .reset_tid_config = ieee80211_reset_tid_config, .set_sar_specs = ieee80211_set_sar_specs, .color_change = ieee80211_color_change, .set_radar_background = ieee80211_set_radar_background, .add_intf_link = ieee80211_add_intf_link, .del_intf_link = ieee80211_del_intf_link, .add_link_station = ieee80211_add_link_station, .mod_link_station = ieee80211_mod_link_station, .del_link_station = ieee80211_del_link_station, .set_hw_timestamp = ieee80211_set_hw_timestamp, .set_ttlm = ieee80211_set_ttlm, .get_radio_mask = ieee80211_get_radio_mask, .assoc_ml_reconf = ieee80211_assoc_ml_reconf, .set_epcs = ieee80211_set_epcs, }; |
| 2845 54 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/pagevec.h * * In many places it is efficient to batch an operation up against multiple * folios. A folio_batch is a container which is used for that. */ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H #include <linux/types.h> /* 31 pointers + header align the folio_batch structure to a power of two */ #define PAGEVEC_SIZE 31 struct folio; /** * struct folio_batch - A collection of folios. * * The folio_batch is used to amortise the cost of retrieving and * operating on a set of folios. The order of folios in the batch may be * significant (eg delete_from_page_cache_batch()). Some users of the * folio_batch store "exceptional" entries in it which can be removed * by calling folio_batch_remove_exceptionals(). */ struct folio_batch { unsigned char nr; unsigned char i; bool percpu_pvec_drained; struct folio *folios[PAGEVEC_SIZE]; }; /** * folio_batch_init() - Initialise a batch of folios * @fbatch: The folio batch. * * A freshly initialised folio_batch contains zero folios. */ static inline void folio_batch_init(struct folio_batch *fbatch) { fbatch->nr = 0; fbatch->i = 0; fbatch->percpu_pvec_drained = false; } static inline void folio_batch_reinit(struct folio_batch *fbatch) { fbatch->nr = 0; fbatch->i = 0; } static inline unsigned int folio_batch_count(struct folio_batch *fbatch) { return fbatch->nr; } static inline unsigned int folio_batch_space(struct folio_batch *fbatch) { return PAGEVEC_SIZE - fbatch->nr; } /** * folio_batch_add() - Add a folio to a batch. * @fbatch: The folio batch. * @folio: The folio to add. * * The folio is added to the end of the batch. * The batch must have previously been initialised using folio_batch_init(). * * Return: The number of slots still available. */ static inline unsigned folio_batch_add(struct folio_batch *fbatch, struct folio *folio) { fbatch->folios[fbatch->nr++] = folio; return folio_batch_space(fbatch); } /** * folio_batch_next - Return the next folio to process. * @fbatch: The folio batch being processed. * * Use this function to implement a queue of folios. * * Return: The next folio in the queue, or NULL if the queue is empty. */ static inline struct folio *folio_batch_next(struct folio_batch *fbatch) { if (fbatch->i == fbatch->nr) return NULL; return fbatch->folios[fbatch->i++]; } void __folio_batch_release(struct folio_batch *pvec); static inline void folio_batch_release(struct folio_batch *fbatch) { if (folio_batch_count(fbatch)) __folio_batch_release(fbatch); } void folio_batch_remove_exceptionals(struct folio_batch *fbatch); #endif /* _LINUX_PAGEVEC_H */ |
| 2 1 2 2 1 3 3 3 1 2 3 3 13 13 2 2 2 2 11 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Basic Transport Functions exploiting Infiniband API * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/socket.h> #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/reboot.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/smc.h> #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> #include "smc.h" #include "smc_clc.h" #include "smc_core.h" #include "smc_ib.h" #include "smc_wr.h" #include "smc_llc.h" #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" #include "smc_netlink.h" #include "smc_stats.h" #include "smc_tracepoint.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), .list = LIST_HEAD_INIT(smc_lgr_list.list), .num = 0, }; static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); static void smc_link_down_work(struct work_struct *work); /* return head of link group list and its lock for a given link group */ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr, spinlock_t **lgr_lock) { if (lgr->is_smcd) { *lgr_lock = &lgr->smcd->lgr_lock; return &lgr->smcd->lgr_list; } *lgr_lock = &smc_lgr_list.lock; return &smc_lgr_list.list; } static void smc_ibdev_cnt_inc(struct smc_link *lnk) { atomic_inc(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); } static void smc_ibdev_cnt_dec(struct smc_link *lnk) { atomic_dec(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); } static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { /* client link group creation always follows the server link group * creation. For client use a somewhat higher removal delay time, * otherwise there is a risk of out-of-sync link groups. */ if (!lgr->freeing) { mod_delayed_work(system_wq, &lgr->free_work, (!lgr->is_smcd && lgr->role == SMC_CLNT) ? SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV); } } /* Register connection's alert token in our lookup structure. * To use rbtrees we have to implement our own insert core. * Requires @conns_lock * @smc connection to register * Returns 0 on success, != otherwise. */ static void smc_lgr_add_alert_token(struct smc_connection *conn) { struct rb_node **link, *parent = NULL; u32 token = conn->alert_token_local; link = &conn->lgr->conns_all.rb_node; while (*link) { struct smc_connection *cur = rb_entry(*link, struct smc_connection, alert_node); parent = *link; if (cur->alert_token_local > token) link = &parent->rb_left; else link = &parent->rb_right; } /* Put the new node there */ rb_link_node(&conn->alert_node, parent, link); rb_insert_color(&conn->alert_node, &conn->lgr->conns_all); } /* assign an SMC-R link to the connection */ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) { enum smc_link_state expected = first ? SMC_LNK_ACTIVATING : SMC_LNK_ACTIVE; int i, j; /* do link balancing */ conn->lnk = NULL; /* reset conn->lnk first */ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &conn->lgr->lnk[i]; if (lnk->state != expected || lnk->link_is_asym) continue; if (conn->lgr->role == SMC_CLNT) { conn->lnk = lnk; /* temporary, SMC server assigns link*/ break; } if (conn->lgr->conns_num % 2) { for (j = i + 1; j < SMC_LINKS_PER_LGR_MAX; j++) { struct smc_link *lnk2; lnk2 = &conn->lgr->lnk[j]; if (lnk2->state == expected && !lnk2->link_is_asym) { conn->lnk = lnk2; break; } } } if (!conn->lnk) conn->lnk = lnk; break; } if (!conn->lnk) return SMC_CLC_DECL_NOACTLINK; atomic_inc(&conn->lnk->conn_cnt); return 0; } /* Register connection in link group by assigning an alert token * registered in a search tree. * Requires @conns_lock * Note that '0' is a reserved value and not assigned. */ static int smc_lgr_register_conn(struct smc_connection *conn, bool first) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); static atomic_t nexttoken = ATOMIC_INIT(0); int rc; if (!conn->lgr->is_smcd) { rc = smcr_lgr_conn_assign_link(conn, first); if (rc) { conn->lgr = NULL; return rc; } } /* find a new alert_token_local value not yet used by some connection * in this link group */ sock_hold(&smc->sk); /* sock_put in smc_lgr_unregister_conn() */ while (!conn->alert_token_local) { conn->alert_token_local = atomic_inc_return(&nexttoken); if (smc_lgr_find_conn(conn->alert_token_local, conn->lgr)) conn->alert_token_local = 0; } smc_lgr_add_alert_token(conn); conn->lgr->conns_num++; return 0; } /* Unregister connection and reset the alert token of the given connection< */ static void __smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_link_group *lgr = conn->lgr; rb_erase(&conn->alert_node, &lgr->conns_all); if (conn->lnk) atomic_dec(&conn->lnk->conn_cnt); lgr->conns_num--; conn->alert_token_local = 0; sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */ } /* Unregister connection from lgr */ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; if (!smc_conn_lgr_valid(conn)) return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); } write_unlock_bh(&lgr->conns_lock); } static void smc_lgr_buf_list_add(struct smc_link_group *lgr, bool is_rmb, struct list_head *buf_list, struct smc_buf_desc *buf_desc) { list_add(&buf_desc->list, buf_list); if (is_rmb) { lgr->alloc_rmbs += buf_desc->len; lgr->alloc_rmbs += lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; } else { lgr->alloc_sndbufs += buf_desc->len; } } static void smc_lgr_buf_list_del(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { list_del(&buf_desc->list); if (is_rmb) { lgr->alloc_rmbs -= buf_desc->len; lgr->alloc_rmbs -= lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; } else { lgr->alloc_sndbufs -= buf_desc->len; } } int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); char hostname[SMC_MAX_HOSTNAME_LEN + 1]; char smc_seid[SMC_MAX_EID_LEN + 1]; struct nlattr *attrs; u8 *seid = NULL; u8 *host = NULL; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_SYS_INFO); if (!nlh) goto errmsg; if (cb_ctx->pos[0]) goto errout; attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2)) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE)) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); hostname[SMC_MAX_HOSTNAME_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname)) goto errattr; } if (smc_ism_is_v2_capable()) { smc_ism_get_system_eid(&seid); memcpy(smc_seid, seid, SMC_MAX_EID_LEN); smc_seid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); cb_ctx->pos[0] = 1; return skb->len; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return skb->len; } /* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb, struct nlattr *v2_attrs) { char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_eid[SMC_MAX_EID_LEN + 1]; if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) goto errv2attr; memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); smc_host[SMC_MAX_HOSTNAME_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) goto errv2attr; memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); smc_eid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; errv2attr: nla_nest_cancel(skb, v2_attrs); return -EMSGSIZE; } static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *v2_attrs; v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); if (!v2_attrs) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_CONNS, lgr->max_conns)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_LINKS, lgr->max_links)) goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; errv2attr: nla_nest_cancel(skb, v2_attrs); errattr: return -EMSGSIZE; } static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) goto errout; if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id))) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_BUF_TYPE, lgr->buf_type)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_R_NET_COOKIE, lgr->net->net_cookie, SMC_NLA_LGR_R_PAD)) goto errattr; memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN); smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs)) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs)) goto errattr; if (lgr->smc_version > SMC_V1) { v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); if (!v2_attrs) goto errattr; if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) goto errattr; if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) goto errattr; } nla_nest_end(skb, attrs); return 0; errattr: nla_nest_cancel(skb, attrs); errout: return -EMSGSIZE; } static int smc_nl_fill_lgr_link(struct smc_link_group *lgr, struct smc_link *link, struct sk_buff *skb, struct netlink_callback *cb) { char smc_ibname[IB_DEVICE_NAME_MAX]; u8 smc_gid_target[41]; struct nlattr *attrs; u32 link_uid = 0; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LINK_SMCR); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT, atomic_read(&link->conn_cnt))) goto errattr; if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx)) goto errattr; snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname); if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname)) goto errattr; memcpy(&link_uid, link->link_uid, sizeof(link_uid)); if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid)) goto errattr; memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid)); if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid)) goto errattr; memset(smc_gid_target, 0, sizeof(smc_gid_target)); smc_gid_be16_convert(smc_gid_target, link->gid); if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target)) goto errattr; memset(smc_gid_target, 0, sizeof(smc_gid_target)); smc_gid_be16_convert(smc_gid_target, link->peer_gid); if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target)) goto errattr; nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static int smc_nl_handle_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb, bool list_links) { void *nlh; int i; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LGR_SMCR); if (!nlh) goto errmsg; if (smc_nl_fill_lgr(lgr, skb, cb)) goto errout; genlmsg_end(skb, nlh); if (!list_links) goto out; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_usable(&lgr->lnk[i])) continue; if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb)) goto errout; } out: return 0; errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, struct sk_buff *skb, struct netlink_callback *cb, bool list_links) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; int snum = cb_ctx->pos[0]; int num = 0; spin_lock_bh(&smc_lgr->lock); list_for_each_entry(lgr, &smc_lgr->list, list) { if (num < snum) goto next; if (smc_nl_handle_lgr(lgr, skb, cb, list_links)) goto errout; next: num++; } errout: spin_unlock_bh(&smc_lgr->lock); cb_ctx->pos[0] = num; } static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_pnet[SMC_MAX_PNETID_LEN + 1]; struct smcd_dev *smcd = lgr->smcd; struct smcd_gid smcd_gid; struct nlattr *attrs; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LGR_SMCD); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD); if (!attrs) goto errout; if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id))) goto errattr; smcd->ops->get_local_gid(smcd, &smcd_gid); if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, smcd_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID, smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID, lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs)) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs)) goto errattr; memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; if (lgr->smc_version > SMC_V1) { struct nlattr *v2_attrs; v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); if (!v2_attrs) goto errattr; if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; int snum = cb_ctx->pos[1]; int rc = 0, num = 0; spin_lock_bh(&dev->lgr_lock); list_for_each_entry(lgr, &dev->lgr_list, list) { if (!lgr->is_smcd) continue; if (num < snum) goto next; rc = smc_nl_fill_smcd_lgr(lgr, skb, cb); if (rc) goto errout; next: num++; } errout: spin_unlock_bh(&dev->lgr_lock); cb_ctx->pos[1] = num; return rc; } static int smc_nl_fill_smcd_dev(struct smcd_dev_list *dev_list, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smcd_dev *smcd_dev; int snum = cb_ctx->pos[0]; int rc = 0, num = 0; mutex_lock(&dev_list->mutex); list_for_each_entry(smcd_dev, &dev_list->list, list) { if (list_empty(&smcd_dev->lgr_list)) continue; if (num < snum) goto next; rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb); if (rc) goto errout; next: num++; } errout: mutex_unlock(&dev_list->mutex); cb_ctx->pos[0] = num; return rc; } int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = false; smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = true; smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb); return skb->len; } void smc_lgr_cleanup_early(struct smc_link_group *lgr) { spinlock_t *lgr_lock; if (!lgr) return; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); /* do not use this link group for new connections */ if (!list_empty(&lgr->list)) list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); __smc_lgr_terminate(lgr, true); } static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) { int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (smc_link_sendable(lnk)) lnk->state = SMC_LNK_INACTIVE; } wake_up_all(&lgr->llc_msg_waiter); wake_up_all(&lgr->llc_flow_waiter); } static void smc_lgr_free(struct smc_link_group *lgr); static void smc_lgr_free_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(to_delayed_work(work), struct smc_link_group, free_work); spinlock_t *lgr_lock; bool conns; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); if (lgr->freeing) { spin_unlock_bh(lgr_lock); return; } read_lock_bh(&lgr->conns_lock); conns = RB_EMPTY_ROOT(&lgr->conns_all); read_unlock_bh(&lgr->conns_lock); if (!conns) { /* number of lgr connections is no longer zero */ spin_unlock_bh(lgr_lock); return; } list_del_init(&lgr->list); /* remove from smc_lgr_list */ lgr->freeing = 1; /* this instance does the freeing, no new schedule */ spin_unlock_bh(lgr_lock); cancel_delayed_work(&lgr->free_work); if (!lgr->is_smcd && !lgr->terminating) smc_llc_send_link_delete_all(lgr, true, SMC_LLC_DEL_PROG_INIT_TERM); if (lgr->is_smcd && !lgr->terminating) smc_ism_signal_shutdown(lgr); if (!lgr->is_smcd) smcr_lgr_link_deactivate_all(lgr); smc_lgr_free(lgr); } static void smc_lgr_terminate_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(work, struct smc_link_group, terminate_work); __smc_lgr_terminate(lgr, true); } /* return next unique link id for the lgr */ static u8 smcr_next_link_id(struct smc_link_group *lgr) { u8 link_id; int i; while (1) { again: link_id = ++lgr->next_link_id; if (!link_id) /* skip zero as link_id */ link_id = ++lgr->next_link_id; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (smc_link_usable(&lgr->lnk[i]) && lgr->lnk[i].link_id == link_id) goto again; } break; } return link_id; } static void smcr_copy_dev_info_to_link(struct smc_link *link) { struct smc_ib_device *smcibdev = link->smcibdev; snprintf(link->ibname, sizeof(link->ibname), "%s", smcibdev->ibdev->name); link->ndev_ifidx = smcibdev->ndev_ifidx[link->ibport - 1]; } int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini) { struct smc_ib_device *smcibdev; u8 rndvec[3]; int rc; if (lgr->smc_version == SMC_V2) { lnk->smcibdev = ini->smcrv2.ib_dev_v2; lnk->ibport = ini->smcrv2.ib_port_v2; lnk->wr_rx_sge_cnt = lnk->smcibdev->ibdev->attrs.max_recv_sge < 2 ? 1 : 2; lnk->wr_rx_buflen = smc_link_shared_v2_rxbuf(lnk) ? SMC_WR_BUF_SIZE : SMC_WR_BUF_V2_SIZE; } else { lnk->smcibdev = ini->ib_dev; lnk->ibport = ini->ib_port; lnk->wr_rx_sge_cnt = 1; lnk->wr_rx_buflen = SMC_WR_BUF_SIZE; } get_device(&lnk->smcibdev->ibdev->dev); atomic_inc(&lnk->smcibdev->lnk_cnt); refcount_set(&lnk->refcnt, 1); /* link refcnt is set to 1 */ lnk->clearing = 0; lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */ lnk->link_idx = link_idx; lnk->wr_rx_id_compl = 0; smc_ibdev_cnt_inc(lnk); smcr_copy_dev_info_to_link(lnk); atomic_set(&lnk->conn_cnt, 0); smc_llc_link_set_uid(lnk); INIT_WORK(&lnk->link_down_wrk, smc_link_down_work); if (!lnk->smcibdev->initialized) { rc = (int)smc_ib_setup_per_ibdev(lnk->smcibdev); if (rc) goto out; } get_random_bytes(rndvec, sizeof(rndvec)); lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport, ini->vlan_id, lnk->gid, &lnk->sgid_index, lgr->smc_version == SMC_V2 ? &ini->smcrv2 : NULL); if (rc) goto out; rc = smc_llc_link_init(lnk); if (rc) goto out; rc = smc_wr_alloc_link_mem(lnk); if (rc) goto clear_llc_lnk; rc = smc_ib_create_protection_domain(lnk); if (rc) goto free_link_mem; rc = smc_ib_create_queue_pair(lnk); if (rc) goto dealloc_pd; rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; lnk->state = SMC_LNK_ACTIVATING; return 0; destroy_qp: smc_ib_destroy_queue_pair(lnk); dealloc_pd: smc_ib_dealloc_protection_domain(lnk); free_link_mem: smc_wr_free_link_mem(lnk); clear_llc_lnk: smc_llc_link_clear(lnk, false); out: smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; if (!atomic_dec_return(&smcibdev->lnk_cnt)) wake_up(&smcibdev->lnks_deleted); smc_lgr_put(lgr); /* lgr_hold above */ return rc; } /* create a new SMC link group */ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_link_group *lgr; struct list_head *lgr_list; struct smcd_dev *smcd; struct smc_link *lnk; spinlock_t *lgr_lock; u8 link_idx; int rc = 0; int i; if (ini->is_smcd && ini->vlan_id) { if (smc_ism_get_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id)) { rc = SMC_CLC_DECL_ISMVLANERR; goto out; } } lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = SMC_CLC_DECL_MEM; goto ism_put_vlan; } lgr->tx_wq = alloc_workqueue("smc_tx_wq-%*phN", 0, 0, SMC_LGR_ID_SIZE, &lgr->id); if (!lgr->tx_wq) { rc = -ENOMEM; goto free_lgr; } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; lgr->terminating = 0; lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ init_rwsem(&lgr->sndbufs_lock); init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); INIT_LIST_HEAD(&lgr->rmbs[i]); } lgr->next_link_id = 0; smc_lgr_list.num += SMC_LGR_NUM_INCR; memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE); INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work); INIT_WORK(&lgr->terminate_work, smc_lgr_terminate_work); lgr->conns_all = RB_ROOT; if (ini->is_smcd) { /* SMC-D specific settings */ smcd = ini->ism_dev[ini->ism_selected]; get_device(smcd->ops->get_dev(smcd)); lgr->peer_gid.gid = ini->ism_peer_gid[ini->ism_selected].gid; lgr->peer_gid.gid_ext = ini->ism_peer_gid[ini->ism_selected].gid_ext; lgr->smcd = ini->ism_dev[ini->ism_selected]; lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list; lgr_lock = &lgr->smcd->lgr_lock; lgr->smc_version = ini->smcd_version; lgr->peer_shutdown = 0; atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt); } else { /* SMC-R specific settings */ struct smc_ib_device *ibdev; int ibport; lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; lgr->smc_version = ini->smcr_version; memcpy(lgr->peer_systemid, ini->peer_systemid, SMC_SYSTEMID_LEN); if (lgr->smc_version == SMC_V2) { ibdev = ini->smcrv2.ib_dev_v2; ibport = ini->smcrv2.ib_port_v2; lgr->saddr = ini->smcrv2.saddr; lgr->uses_gateway = ini->smcrv2.uses_gateway; memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac, ETH_ALEN); lgr->max_conns = ini->max_conns; lgr->max_links = ini->max_links; } else { ibdev = ini->ib_dev; ibport = ini->ib_port; lgr->max_conns = SMC_CONN_PER_LGR_MAX; lgr->max_links = SMC_LINKS_ADD_LNK_MAX; } memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); rc = smc_wr_alloc_lgr_mem(lgr); if (rc) goto free_wq; smc_llc_lgr_init(lgr, smc); link_idx = SMC_SINGLE_LINK; lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); if (rc) { smc_wr_free_lgr_mem(lgr); goto free_wq; } lgr->net = smc_ib_net(lnk->smcibdev); lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; lgr->buf_type = lgr->net->smc.sysctl_smcr_buf_type; atomic_inc(&lgr_cnt); } smc->conn.lgr = lgr; spin_lock_bh(lgr_lock); list_add_tail(&lgr->list, lgr_list); spin_unlock_bh(lgr_lock); return 0; free_wq: destroy_workqueue(lgr->tx_wq); free_lgr: kfree(lgr); ism_put_vlan: if (ini->is_smcd && ini->vlan_id) smc_ism_put_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) rc = SMC_CLC_DECL_MEM; else rc = SMC_CLC_DECL_INTERR; } return rc; } static int smc_write_space(struct smc_connection *conn) { int buffer_len = conn->peer_rmbe_size; union smc_host_cursor prod; union smc_host_cursor cons; int space; smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); /* determine rx_buf space */ space = buffer_len - smc_curs_diff(buffer_len, &cons, &prod); return space; } static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, struct smc_wr_buf *wr_buf) { struct smc_connection *conn = &smc->conn; union smc_host_cursor cons, fin; int rc = 0; int diff; smc_curs_copy(&conn->tx_curs_sent, &conn->tx_curs_fin, conn); smc_curs_copy(&fin, &conn->local_tx_ctrl_fin, conn); /* set prod cursor to old state, enforce tx_rdma_writes() */ smc_curs_copy(&conn->local_tx_ctrl.prod, &fin, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); if (smc_curs_comp(conn->peer_rmbe_size, &cons, &fin) < 0) { /* cons cursor advanced more than fin, and prod was set * fin above, so now prod is smaller than cons. Fix that. */ diff = smc_curs_diff(conn->peer_rmbe_size, &fin, &cons); smc_curs_add(conn->sndbuf_desc->len, &conn->tx_curs_sent, diff); smc_curs_add(conn->sndbuf_desc->len, &conn->tx_curs_fin, diff); smp_mb__before_atomic(); atomic_add(diff, &conn->sndbuf_space); smp_mb__after_atomic(); smc_curs_add(conn->peer_rmbe_size, &conn->local_tx_ctrl.prod, diff); smc_curs_add(conn->peer_rmbe_size, &conn->local_tx_ctrl_fin, diff); } /* recalculate, value is used by tx_rdma_writes() */ atomic_set(&smc->conn.peer_rmbe_space, smc_write_space(conn)); if (smc->sk.sk_state != SMC_INIT && smc->sk.sk_state != SMC_CLOSED) { rc = smcr_cdc_msg_send_validation(conn, pend, wr_buf); if (!rc) { queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, 0); smc->sk.sk_data_ready(&smc->sk); } } else { smc_wr_tx_put_slot(conn->lnk, (struct smc_wr_tx_pend_priv *)pend); } return rc; } void smc_switch_link_and_count(struct smc_connection *conn, struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); /* link_hold in smc_conn_create() */ smcr_link_put(conn->lnk); conn->lnk = to_lnk; atomic_inc(&conn->lnk->conn_cnt); /* link_put in smc_conn_free() */ smcr_link_hold(conn->lnk); } struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err) { struct smc_link *to_lnk = NULL; struct smc_cdc_tx_pend *pend; struct smc_connection *conn; struct smc_wr_buf *wr_buf; struct smc_sock *smc; struct rb_node *node; int i, rc = 0; /* link is inactive, wake up tx waiters */ smc_wr_wakeup_tx_wait(from_lnk); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i]) || i == from_lnk->link_idx) continue; if (is_dev_err && from_lnk->smcibdev == lgr->lnk[i].smcibdev && from_lnk->ibport == lgr->lnk[i].ibport) { continue; } to_lnk = &lgr->lnk[i]; break; } if (!to_lnk || !smc_wr_tx_link_hold(to_lnk)) { smc_lgr_terminate_sched(lgr); return NULL; } again: read_lock_bh(&lgr->conns_lock); for (node = rb_first(&lgr->conns_all); node; node = rb_next(node)) { conn = rb_entry(node, struct smc_connection, alert_node); if (conn->lnk != from_lnk) continue; smc = container_of(conn, struct smc_sock, conn); /* conn->lnk not yet set in SMC_INIT state */ if (smc->sk.sk_state == SMC_INIT) continue; if (smc->sk.sk_state == SMC_CLOSED || smc->sk.sk_state == SMC_PEERCLOSEWAIT1 || smc->sk.sk_state == SMC_PEERCLOSEWAIT2 || smc->sk.sk_state == SMC_APPFINCLOSEWAIT || smc->sk.sk_state == SMC_APPCLOSEWAIT1 || smc->sk.sk_state == SMC_APPCLOSEWAIT2 || smc->sk.sk_state == SMC_PEERFINCLOSEWAIT || smc->sk.sk_state == SMC_PEERABORTWAIT || smc->sk.sk_state == SMC_PROCESSABORT) { spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); spin_unlock_bh(&conn->send_lock); continue; } sock_hold(&smc->sk); read_unlock_bh(&lgr->conns_lock); /* pre-fetch buffer outside of send_lock, might sleep */ rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend); if (rc) goto err_out; /* avoid race with smcr_tx_sndbuf_nonempty() */ spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); rc = smc_switch_cursor(smc, pend, wr_buf); spin_unlock_bh(&conn->send_lock); sock_put(&smc->sk); if (rc) goto err_out; goto again; } read_unlock_bh(&lgr->conns_lock); smc_wr_tx_link_put(to_lnk); return to_lnk; err_out: smcr_link_down_cond_sched(to_lnk); smc_wr_tx_link_put(to_lnk); return NULL; } static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { /* unregister rmb with peer */ rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (!rc) { /* protect against smc_llc_cli_rkey_exchange() */ down_read(&lgr->llc_conf_mutex); smc_llc_do_delete_rkey(lgr, buf_desc); buf_desc->is_conf_rkey = false; up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } } if (buf_desc->is_reg_err) { /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; down_write(lock); smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { /* memzero_explicit provides potential memory barrier semantics */ memzero_explicit(buf_desc->cpu_addr, buf_desc->len); WRITE_ONCE(buf_desc->used, 0); } } static void smcd_buf_detach(struct smc_connection *conn) { struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; if (!conn->sndbuf_desc) return; smc_ism_detach_dmb(smcd, peer_token); kfree(conn->sndbuf_desc); conn->sndbuf_desc = NULL; } static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); bool is_smcd = lgr->is_smcd; int bufsize; if (conn->sndbuf_desc) { bufsize = conn->sndbuf_desc->len; if (!is_smcd && conn->sndbuf_desc->is_vm) { smcr_buf_unuse(conn->sndbuf_desc, false, lgr); } else { memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize); WRITE_ONCE(conn->sndbuf_desc->used, 0); } SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize); } if (conn->rmb_desc) { bufsize = conn->rmb_desc->len; if (!is_smcd) { smcr_buf_unuse(conn->rmb_desc, true, lgr); } else { bufsize += sizeof(struct smcd_cdc_msg); memzero_explicit(conn->rmb_desc->cpu_addr, bufsize); WRITE_ONCE(conn->rmb_desc->used, 0); } SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize); } } /* remove a finished connection from its link group */ void smc_conn_free(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; if (!lgr || conn->freed) /* Connection has never been registered in a * link group, or has already been freed. */ return; conn->freed = 1; if (!smc_conn_lgr_valid(conn)) /* Connection has already unregistered from * link group. */ goto lgr_put; if (lgr->is_smcd) { if (!list_empty(&lgr->list)) smc_ism_unset_conn(conn); if (smc_ism_support_dmb_nocopy(lgr->smcd)) smcd_buf_detach(conn); tasklet_kill(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); if (current_work() != &conn->abort_work) cancel_work_sync(&conn->abort_work); } if (!list_empty(&lgr->list)) { smc_buf_unuse(conn, lgr); /* allow buffer reuse */ smc_lgr_unregister_conn(conn); } if (!lgr->conns_num) smc_lgr_schedule_free_work(lgr); lgr_put: if (!lgr->is_smcd) smcr_link_put(conn->lnk); /* link_hold in smc_conn_create() */ smc_lgr_put(lgr); /* lgr_hold in smc_conn_create() */ } /* unregister a link from a buf_desc */ static void smcr_buf_unmap_link(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link *lnk) { if (is_rmb || buf_desc->is_vm) buf_desc->is_reg_mr[lnk->link_idx] = false; if (!buf_desc->is_map_ib[lnk->link_idx]) return; if ((is_rmb || buf_desc->is_vm) && buf_desc->mr[lnk->link_idx]) { smc_ib_put_memory_region(buf_desc->mr[lnk->link_idx]); buf_desc->mr[lnk->link_idx] = NULL; } if (is_rmb) smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_FROM_DEVICE); else smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_TO_DEVICE); sg_free_table(&buf_desc->sgt[lnk->link_idx]); buf_desc->is_map_ib[lnk->link_idx] = false; } /* unmap all buffers of lgr for a deleted link */ static void smcr_buf_unmap_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_buf_desc *buf_desc, *bf; int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); up_write(&lgr->rmbs_lock); down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); up_write(&lgr->sndbufs_lock); } } static void smcr_rtoken_clear_link(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { lgr->rtokens[i][lnk->link_idx].rkey = 0; lgr->rtokens[i][lnk->link_idx].dma_addr = 0; } } static void __smcr_link_clear(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_ib_device *smcibdev; smc_wr_free_link_mem(lnk); smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; if (!atomic_dec_return(&smcibdev->lnk_cnt)) wake_up(&smcibdev->lnks_deleted); smc_lgr_put(lgr); /* lgr_hold in smcr_link_init() */ } /* must be called under lgr->llc_conf_mutex lock */ void smcr_link_clear(struct smc_link *lnk, bool log) { if (!lnk->lgr || lnk->clearing || lnk->state == SMC_LNK_UNUSED) return; lnk->clearing = 1; lnk->peer_qpn = 0; smc_llc_link_clear(lnk, log); smcr_buf_unmap_lgr(lnk); smcr_rtoken_clear_link(lnk); smc_ib_modify_qp_error(lnk); smc_wr_free_link(lnk); smc_ib_destroy_queue_pair(lnk); smc_ib_dealloc_protection_domain(lnk); smcr_link_put(lnk); /* theoretically last link_put */ } void smcr_link_hold(struct smc_link *lnk) { refcount_inc(&lnk->refcnt); } void smcr_link_put(struct smc_link *lnk) { if (refcount_dec_and_test(&lnk->refcnt)) __smcr_link_clear(lnk); } static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) smcr_buf_unmap_link(buf_desc, is_rmb, &lgr->lnk[i]); if (!buf_desc->is_vm && buf_desc->pages) __free_pages(buf_desc->pages, buf_desc->order); else if (buf_desc->is_vm && buf_desc->cpu_addr) vfree(buf_desc->cpu_addr); kfree(buf_desc); } static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb, struct smc_buf_desc *buf_desc) { if (is_dmb) { /* restore original buf len */ buf_desc->len += sizeof(struct smcd_cdc_msg); smc_ism_unregister_dmb(lgr->smcd, buf_desc); } else { kfree(buf_desc->cpu_addr); } kfree(buf_desc); } static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { if (lgr->is_smcd) smcd_buf_free(lgr, is_rmb, buf_desc); else smcr_buf_free(lgr, is_rmb, buf_desc); } static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf_desc; struct list_head *buf_list; int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { if (is_rmb) buf_list = &lgr->rmbs[i]; else buf_list = &lgr->sndbufs[i]; list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); smc_buf_free(lgr, is_rmb, buf_desc); } } } static void smc_lgr_free_bufs(struct smc_link_group *lgr) { /* free send buffers */ __smc_lgr_free_bufs(lgr, false); /* free rmbs */ __smc_lgr_free_bufs(lgr, true); } /* won't be freed until no one accesses to lgr anymore */ static void __smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); if (lgr->is_smcd) { if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { smc_wr_free_lgr_mem(lgr); if (!atomic_dec_return(&lgr_cnt)) wake_up(&lgrs_deleted); } kfree(lgr); } /* remove a link group */ static void smc_lgr_free(struct smc_link_group *lgr) { int i; if (!lgr->is_smcd) { down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state != SMC_LNK_UNUSED) smcr_link_clear(&lgr->lnk[i], false); } up_write(&lgr->llc_conf_mutex); smc_llc_lgr_clear(lgr); } destroy_workqueue(lgr->tx_wq); if (lgr->is_smcd) { smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); put_device(lgr->smcd->ops->get_dev(lgr->smcd)); } smc_lgr_put(lgr); /* theoretically last lgr_put */ } void smc_lgr_hold(struct smc_link_group *lgr) { refcount_inc(&lgr->refcnt); } void smc_lgr_put(struct smc_link_group *lgr) { if (refcount_dec_and_test(&lgr->refcnt)) __smc_lgr_free(lgr); } static void smc_sk_wake_ups(struct smc_sock *smc) { smc->sk.sk_write_space(&smc->sk); smc->sk.sk_data_ready(&smc->sk); smc->sk.sk_state_change(&smc->sk); } /* kill a connection */ static void smc_conn_kill(struct smc_connection *conn, bool soft) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); if (conn->lgr->is_smcd && conn->lgr->peer_shutdown) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; else smc_close_abort(conn); conn->killed = 1; smc->sk.sk_err = ECONNABORTED; smc_sk_wake_ups(smc); if (conn->lgr->is_smcd) { smc_ism_unset_conn(conn); if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) smcd_buf_detach(conn); if (soft) tasklet_kill(&conn->rx_tsklet); else tasklet_unlock_wait(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); } smc_lgr_unregister_conn(conn); smc_close_active_abort(smc); } static void smc_lgr_cleanup(struct smc_link_group *lgr) { if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); } else { u32 rsn = lgr->llc_termination_rsn; if (!rsn) rsn = SMC_LLC_DEL_PROG_INIT_TERM; smc_llc_send_link_delete_all(lgr, false, rsn); smcr_lgr_link_deactivate_all(lgr); } } /* terminate link group * @soft: true if link group shutdown can take its time * false if immediate link group shutdown is required */ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) { struct smc_connection *conn; struct smc_sock *smc; struct rb_node *node; if (lgr->terminating) return; /* lgr already terminating */ /* cancel free_work sync, will terminate when lgr->freeing is set */ cancel_delayed_work(&lgr->free_work); lgr->terminating = 1; /* kill remaining link group connections */ read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); while (node) { read_unlock_bh(&lgr->conns_lock); conn = rb_entry(node, struct smc_connection, alert_node); smc = container_of(conn, struct smc_sock, conn); sock_hold(&smc->sk); /* sock_put below */ lock_sock(&smc->sk); smc_conn_kill(conn, soft); release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold above */ read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); } read_unlock_bh(&lgr->conns_lock); smc_lgr_cleanup(lgr); smc_lgr_free(lgr); } /* unlink link group and schedule termination */ void smc_lgr_terminate_sched(struct smc_link_group *lgr) { spinlock_t *lgr_lock; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); if (list_empty(&lgr->list) || lgr->terminating || lgr->freeing) { spin_unlock_bh(lgr_lock); return; /* lgr already terminating */ } list_del_init(&lgr->list); lgr->freeing = 1; spin_unlock_bh(lgr_lock); schedule_work(&lgr->terminate_work); } /* Called when peer lgr shutdown (regularly or abnormally) is received */ void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, unsigned short vlan) { struct smc_link_group *lgr, *l; LIST_HEAD(lgr_free_list); /* run common cleanup function and build free list */ spin_lock_bh(&dev->lgr_lock); list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) { if ((!peer_gid->gid || (lgr->peer_gid.gid == peer_gid->gid && !smc_ism_is_emulated(dev) ? 1 : lgr->peer_gid.gid_ext == peer_gid->gid_ext)) && (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { if (peer_gid->gid) /* peer triggered termination */ lgr->peer_shutdown = 1; list_move(&lgr->list, &lgr_free_list); lgr->freeing = 1; } } spin_unlock_bh(&dev->lgr_lock); /* cancel the regular free workers and actually free lgrs */ list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { list_del_init(&lgr->list); schedule_work(&lgr->terminate_work); } } /* Called when an SMCD device is removed or the smc module is unloaded */ void smc_smcd_terminate_all(struct smcd_dev *smcd) { struct smc_link_group *lgr, *lg; LIST_HEAD(lgr_free_list); spin_lock_bh(&smcd->lgr_lock); list_splice_init(&smcd->lgr_list, &lgr_free_list); list_for_each_entry(lgr, &lgr_free_list, list) lgr->freeing = 1; spin_unlock_bh(&smcd->lgr_lock); list_for_each_entry_safe(lgr, lg, &lgr_free_list, list) { list_del_init(&lgr->list); __smc_lgr_terminate(lgr, false); } if (atomic_read(&smcd->lgr_cnt)) wait_event(smcd->lgrs_deleted, !atomic_read(&smcd->lgr_cnt)); } /* Called when an SMCR device is removed or the smc module is unloaded. * If smcibdev is given, all SMCR link groups using this device are terminated. * If smcibdev is NULL, all SMCR link groups are terminated. */ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev) { struct smc_link_group *lgr, *lg; LIST_HEAD(lgr_free_list); int i; spin_lock_bh(&smc_lgr_list.lock); if (!smcibdev) { list_splice_init(&smc_lgr_list.list, &lgr_free_list); list_for_each_entry(lgr, &lgr_free_list, list) lgr->freeing = 1; } else { list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) { for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].smcibdev == smcibdev) smcr_link_down_cond_sched(&lgr->lnk[i]); } } } spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_free_list, list) { list_del_init(&lgr->list); smc_llc_set_termination_rsn(lgr, SMC_LLC_DEL_OP_INIT_TERM); __smc_lgr_terminate(lgr, false); } if (smcibdev) { if (atomic_read(&smcibdev->lnk_cnt)) wait_event(smcibdev->lnks_deleted, !atomic_read(&smcibdev->lnk_cnt)); } else { if (atomic_read(&lgr_cnt)) wait_event(lgrs_deleted, !atomic_read(&lgr_cnt)); } } /* set new lgr type and clear all asymmetric link tagging */ void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type) { char *lgr_type = ""; int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) if (smc_link_usable(&lgr->lnk[i])) lgr->lnk[i].link_is_asym = false; if (lgr->type == new_type) return; lgr->type = new_type; switch (lgr->type) { case SMC_LGR_NONE: lgr_type = "NONE"; break; case SMC_LGR_SINGLE: lgr_type = "SINGLE"; break; case SMC_LGR_SYMMETRIC: lgr_type = "SYMMETRIC"; break; case SMC_LGR_ASYMMETRIC_PEER: lgr_type = "ASYMMETRIC_PEER"; break; case SMC_LGR_ASYMMETRIC_LOCAL: lgr_type = "ASYMMETRIC_LOCAL"; break; } pr_warn_ratelimited("smc: SMC-R lg %*phN net %llu state changed: " "%s, pnetid %.16s\n", SMC_LGR_ID_SIZE, &lgr->id, lgr->net->net_cookie, lgr_type, lgr->pnet_id); } /* set new lgr type and tag a link as asymmetric */ void smcr_lgr_set_type_asym(struct smc_link_group *lgr, enum smc_lgr_type new_type, int asym_lnk_idx) { smcr_lgr_set_type(lgr, new_type); lgr->lnk[asym_lnk_idx].link_is_asym = true; } /* abort connection, abort_work scheduled from tasklet context */ static void smc_conn_abort_work(struct work_struct *work) { struct smc_connection *conn = container_of(work, struct smc_connection, abort_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); lock_sock(&smc->sk); smc_conn_kill(conn, true); release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold done by schedulers of abort_work */ } void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { struct smc_link *link; if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN) || lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER || !rdma_dev_access_netns(smcibdev->ibdev, lgr->net)) continue; if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) continue; /* trigger local add link processing */ link = smc_llc_usable_link(lgr); if (link) smc_llc_add_link_local(link); } spin_unlock_bh(&smc_lgr_list.lock); } /* link is down - switch connections to alternate link, * must be called under lgr->llc_conf_mutex lock */ static void smcr_link_down(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_link *to_lnk; int del_link_id; if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list)) return; to_lnk = smc_switch_conns(lgr, lnk, true); if (!to_lnk) { /* no backup link available */ smcr_link_clear(lnk, true); return; } smcr_lgr_set_type(lgr, SMC_LGR_SINGLE); del_link_id = lnk->link_id; if (lgr->role == SMC_SERV) { /* trigger local delete link processing */ smc_llc_srv_delete_link_local(to_lnk, del_link_id); } else { if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ up_write(&lgr->llc_conf_mutex); wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); down_write(&lgr->llc_conf_mutex); } if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, SMC_LLC_REQ, true, SMC_LLC_DEL_LOST_PATH); smcr_link_clear(lnk, true); } wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } /* must be called under lgr->llc_conf_mutex lock */ void smcr_link_down_cond(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); smcr_link_down(lnk); } } /* will get the lgr->llc_conf_mutex lock */ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ if (!schedule_work(&lnk->link_down_wrk)) smcr_link_put(lnk); } } void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; int i; list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN)) continue; /* lgr is not affected */ if (list_empty(&lgr->list)) continue; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (smc_link_usable(lnk) && lnk->smcibdev == smcibdev && lnk->ibport == ibport) smcr_link_down_cond_sched(lnk); } } } static void smc_link_down_work(struct work_struct *work) { struct smc_link *link = container_of(work, struct smc_link, link_down_wrk); struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); out: smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, struct netdev_nested_priv *priv) { unsigned short *vlan_id = (unsigned short *)priv->data; if (is_vlan_dev(lower_dev)) { *vlan_id = vlan_dev_vlan_id(lower_dev); return 1; } return 0; } /* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); struct netdev_nested_priv priv; struct net_device *ndev; int rc = 0; ini->vlan_id = 0; if (!dst) { rc = -ENOTCONN; goto out; } if (!dst->dev) { rc = -ENODEV; goto out_rel; } ndev = dst->dev; if (is_vlan_dev(ndev)) { ini->vlan_id = vlan_dev_vlan_id(ndev); goto out_rel; } priv.data = (void *)&ini->vlan_id; rtnl_lock(); netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: dst_release(dst); out: return rc; } static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version, u8 peer_systemid[], u8 peer_gid[], u8 peer_mac_v1[], enum smc_lgr_role role, u32 clcqpn, struct net *net) { struct smc_link *lnk; int i; if (memcmp(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN) || lgr->role != role) return false; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { lnk = &lgr->lnk[i]; if (!smc_link_active(lnk)) continue; /* use verbs API to check netns, instead of lgr->net */ if (!rdma_dev_access_netns(lnk->smcibdev->ibdev, net)) return false; if ((lgr->role == SMC_SERV || lnk->peer_qpn == clcqpn) && !memcmp(lnk->peer_gid, peer_gid, SMC_GID_SIZE) && (smcr_version == SMC_V2 || !memcmp(lnk->peer_mac, peer_mac_v1, ETH_ALEN))) return true; } return false; } static bool smcd_lgr_match(struct smc_link_group *lgr, struct smcd_dev *smcismdev, struct smcd_gid *peer_gid) { if (lgr->peer_gid.gid != peer_gid->gid || lgr->smcd != smcismdev) return false; if (smc_ism_is_emulated(smcismdev) && lgr->peer_gid.gid_ext != peer_gid->gid_ext) return false; return true; } /* create a new SMC connection (and a new link group if necessary) */ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_connection *conn = &smc->conn; struct net *net = sock_net(&smc->sk); struct list_head *lgr_list; struct smc_link_group *lgr; enum smc_lgr_role role; spinlock_t *lgr_lock; int rc = 0; lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list : &smc_lgr_list.list; lgr_lock = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_lock : &smc_lgr_list.lock; ini->first_contact_local = 1; role = smc->listen_smc ? SMC_SERV : SMC_CLNT; if (role == SMC_CLNT && ini->first_contact_peer) /* create new link group as well */ goto create; /* determine if an existing link group can be reused */ spin_lock_bh(lgr_lock); list_for_each_entry(lgr, lgr_list, list) { write_lock_bh(&lgr->conns_lock); if ((ini->is_smcd ? smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], &ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->smcr_version, ini->peer_systemid, ini->peer_gid, ini->peer_mac, role, ini->ib_clcqpn, net)) && !lgr->sync_err && (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || (lgr->conns_num < lgr->max_conns && !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) { /* link group found */ ini->first_contact_local = 0; conn->lgr = lgr; rc = smc_lgr_register_conn(conn, false); write_unlock_bh(&lgr->conns_lock); if (!rc && delayed_work_pending(&lgr->free_work)) cancel_delayed_work(&lgr->free_work); break; } write_unlock_bh(&lgr->conns_lock); } spin_unlock_bh(lgr_lock); if (rc) return rc; if (role == SMC_CLNT && !ini->first_contact_peer && ini->first_contact_local) { /* Server reuses a link group, but Client wants to start * a new one * send out_of_sync decline, reason synchr. error */ return SMC_CLC_DECL_SYNCERR; } create: if (ini->first_contact_local) { rc = smc_lgr_create(smc, ini); if (rc) goto out; lgr = conn->lgr; write_lock_bh(&lgr->conns_lock); rc = smc_lgr_register_conn(conn, true); write_unlock_bh(&lgr->conns_lock); if (rc) { smc_lgr_cleanup_early(lgr); goto out; } } smc_lgr_hold(conn->lgr); /* lgr_put in smc_conn_free() */ if (!conn->lgr->is_smcd) smcr_link_hold(conn->lnk); /* link_put in smc_conn_free() */ conn->freed = 0; conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; conn->urg_state = SMC_URG_READ; init_waitqueue_head(&conn->cdc_pend_tx_wq); INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work); if (ini->is_smcd) { conn->rx_off = sizeof(struct smcd_cdc_msg); smcd_cdc_rx_init(conn); /* init tasklet for this conn */ } else { conn->rx_off = 0; } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif out: return rc; } #define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ #define SMCR_RMBE_SIZES 15 /* 0 -> 16KB, 1 -> 32KB, .. 15 -> 512MB */ /* convert the RMB size into the compressed notation (minimum 16K, see * SMCD/R_DMBE_SIZES. * In contrast to plain ilog2, this rounds towards the next power of 2, * so the socket application gets at least its desired sndbuf / rcvbuf size. */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { u8 compressed; if (size <= SMC_BUF_MIN_SIZE) return 0; size = (size - 1) >> 14; /* convert to 16K multiple */ compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); #ifdef CONFIG_ARCH_NO_SG_CHAIN if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14)); #endif return compressed; } /* convert the RMB size from compressed notation into integer */ int smc_uncompress_bufsize(u8 compressed) { u32 size; size = 0x00000001 << (((int)compressed) + 14); return (int)size; } /* try to reuse a sndbuf or rmb description slot for a certain * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { up_read(lock); return buf_slot; } } up_read(lock); return NULL; } /* one of the conditions for announcing a receiver's current window size is * that it "results in a minimum increase in the window size of 10% of the * receive buffer space" [RFC7609] */ static inline int smc_rmb_wnd_update_limit(int rmbe_size) { return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); } /* map an buf to a link */ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link *lnk) { int rc, i, nents, offset, buf_size, size, access_flags; struct scatterlist *sg; void *buf; if (buf_desc->is_map_ib[lnk->link_idx]) return 0; if (buf_desc->is_vm) { buf = buf_desc->cpu_addr; buf_size = buf_desc->len; offset = offset_in_page(buf_desc->cpu_addr); nents = PAGE_ALIGN(buf_size + offset) / PAGE_SIZE; } else { nents = 1; } rc = sg_alloc_table(&buf_desc->sgt[lnk->link_idx], nents, GFP_KERNEL); if (rc) return rc; if (buf_desc->is_vm) { /* virtually contiguous buffer */ for_each_sg(buf_desc->sgt[lnk->link_idx].sgl, sg, nents, i) { size = min_t(int, PAGE_SIZE - offset, buf_size); sg_set_page(sg, vmalloc_to_page(buf), size, offset); buf += size; buf_size -= size; offset = 0; } } else { /* physically contiguous buffer */ sg_set_buf(buf_desc->sgt[lnk->link_idx].sgl, buf_desc->cpu_addr, buf_desc->len); } /* map sg table to DMA address */ rc = smc_ib_buf_map_sg(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); /* SMC protocol depends on mapping to one DMA address only */ if (rc != nents) { rc = -EAGAIN; goto free_table; } buf_desc->is_dma_need_sync |= smc_ib_is_sg_need_sync(lnk, buf_desc) << lnk->link_idx; if (is_rmb || buf_desc->is_vm) { /* create a new memory region for the RMB or vzalloced sndbuf */ access_flags = is_rmb ? IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : IB_ACCESS_LOCAL_WRITE; rc = smc_ib_get_memory_region(lnk->roce_pd, access_flags, buf_desc, lnk->link_idx); if (rc) goto buf_unmap; smc_ib_sync_sg_for_device(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } buf_desc->is_map_ib[lnk->link_idx] = true; return 0; buf_unmap: smc_ib_buf_unmap_sg(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); free_table: sg_free_table(&buf_desc->sgt[lnk->link_idx]); return rc; } /* register a new buf on IB device, rmb or vzalloced sndbuf * must be called under lgr->llc_conf_mutex lock */ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) { if (list_empty(&link->lgr->list)) return -ENOLINK; if (!buf_desc->is_reg_mr[link->link_idx]) { /* register memory region for new buf */ if (buf_desc->is_vm) buf_desc->mr[link->link_idx]->iova = (uintptr_t)buf_desc->cpu_addr; if (smc_wr_reg_send(link, buf_desc->mr[link->link_idx])) { buf_desc->is_reg_err = true; return -EFAULT; } buf_desc->is_reg_mr[link->link_idx] = true; } return 0; } static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; rc = smcr_buf_map_link(buf_desc, is_rmb, lnk); if (rc) goto out; } out: up_write(lock); return rc; } /* map all used buffers of lgr for a new link */ int smcr_buf_map_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; int i, rc = 0; for (i = 0; i < SMC_RMBE_SIZES; i++) { rc = _smcr_buf_map_lgr(lnk, &lgr->rmbs_lock, &lgr->rmbs[i], true); if (rc) return rc; rc = _smcr_buf_map_lgr(lnk, &lgr->sndbufs_lock, &lgr->sndbufs[i], false); if (rc) return rc; } return 0; } /* register all used buffers of lgr for a new link, * must be called under lgr->llc_conf_mutex lock */ int smcr_buf_reg_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_buf_desc *buf_desc, *bf; int i, rc = 0; /* reg all RMBs for a new link */ down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { up_write(&lgr->rmbs_lock); return rc; } } } up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { up_write(&lgr->sndbufs_lock); return rc; } } } up_write(&lgr->sndbufs_lock); return rc; } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, int bufsize) { struct smc_buf_desc *buf_desc; /* try to alloc a new buffer */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return ERR_PTR(-ENOMEM); switch (lgr->buf_type) { case SMCR_PHYS_CONT_BUFS: case SMCR_MIXED_BUFS: buf_desc->order = get_order(bufsize); buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | __GFP_COMP | __GFP_NORETRY | __GFP_ZERO, buf_desc->order); if (buf_desc->pages) { buf_desc->cpu_addr = (void *)page_address(buf_desc->pages); buf_desc->len = bufsize; buf_desc->is_vm = false; break; } if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) goto out; fallthrough; // try virtually contiguous buf case SMCR_VIRT_CONT_BUFS: buf_desc->order = get_order(bufsize); buf_desc->cpu_addr = vzalloc(PAGE_SIZE << buf_desc->order); if (!buf_desc->cpu_addr) goto out; buf_desc->pages = NULL; buf_desc->len = bufsize; buf_desc->is_vm = true; break; } return buf_desc; out: kfree(buf_desc); return ERR_PTR(-EAGAIN); } /* map buf_desc on all usable links, * unused buffers stay mapped as long as the link is up */ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, struct smc_buf_desc *buf_desc, bool is_rmb) { int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (!smc_link_usable(lnk)) continue; if (smcr_buf_map_link(buf_desc, is_rmb, lnk)) { rc = -ENOMEM; goto out; } cnt++; } out: up_read(&lgr->llc_conf_mutex); if (!rc && !cnt) rc = -EINVAL; return rc; } static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) { struct smc_buf_desc *buf_desc; int rc; /* try to alloc a new DMB */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return ERR_PTR(-ENOMEM); if (is_dmb) { rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); if (rc) { kfree(buf_desc); if (rc == -ENOMEM) return ERR_PTR(-EAGAIN); if (rc == -ENOSPC) return ERR_PTR(-ENOSPC); return ERR_PTR(-EIO); } buf_desc->pages = virt_to_page(buf_desc->cpu_addr); /* CDC header stored in buf. So, pretend it was smaller */ buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg); } else { buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC); if (!buf_desc->cpu_addr) { kfree(buf_desc); return ERR_PTR(-EAGAIN); } buf_desc->len = bufsize; } return buf_desc; } static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) { struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ bufsize = smc->sk.sk_sndbuf / 2; for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; buf_list = &lgr->sndbufs[bufsize_comp]; } bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); break; /* found reusable slot */ } if (is_smcd) buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); else buf_desc = smcr_new_buf_create(lgr, bufsize); if (PTR_ERR(buf_desc) == -ENOMEM) break; if (IS_ERR(buf_desc)) { if (!is_dgraded) { is_dgraded = true; SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb); } continue; } SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); buf_desc->used = 1; down_write(lock); smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc); up_write(lock); break; /* found */ } if (IS_ERR(buf_desc)) return PTR_ERR(buf_desc); if (!is_smcd) { if (smcr_buf_map_usable_links(lgr, buf_desc, is_rmb)) { smcr_buf_unuse(buf_desc, is_rmb, lgr); return -ENOMEM; } } if (is_rmb) { conn->rmb_desc = buf_desc; conn->rmbe_size_comp = bufsize_comp; smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); if (is_smcd) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; } void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { if (!conn->sndbuf_desc->is_dma_need_sync) return; if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) { int i; if (!conn->rmb_desc->is_dma_need_sync) return; if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_cpu(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); } } /* create the send and receive buffer for an SMC socket; * receive buffers are called RMBs; * (even though the SMC protocol allows more than one RMB-element per RMB, * the Linux implementation uses just one RMB-element per RMB, i.e. uses an * extra RMB for every connection in a link group */ int smc_buf_create(struct smc_sock *smc, bool is_smcd) { int rc; /* create send buffer */ if (is_smcd && smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) goto create_rmb; rc = __smc_buf_create(smc, is_smcd, false); if (rc) return rc; create_rmb: /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); smc_lgr_buf_list_del(smc->conn.lgr, false, smc->conn.sndbuf_desc); up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } return rc; } int smcd_buf_attach(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; struct smc_buf_desc *buf_desc; int rc; buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return -ENOMEM; /* The ghost sndbuf_desc describes the same memory region as * peer RMB. Its lifecycle is consistent with the connection's * and it will be freed with the connections instead of the * link group. */ rc = smc_ism_attach_dmb(smcd, peer_token, buf_desc); if (rc) goto free; smc->sk.sk_sndbuf = buf_desc->len; buf_desc->cpu_addr = (u8 *)buf_desc->cpu_addr + sizeof(struct smcd_cdc_msg); buf_desc->len -= sizeof(struct smcd_cdc_msg); conn->sndbuf_desc = buf_desc; conn->sndbuf_desc->used = 1; atomic_set(&conn->sndbuf_space, conn->sndbuf_desc->len); return 0; free: kfree(buf_desc); return rc; } static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr) { int i; for_each_clear_bit(i, lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX) { if (!test_and_set_bit(i, lgr->rtokens_used_mask)) return i; } return -ENOSPC; } static int smc_rtoken_find_by_link(struct smc_link_group *lgr, int lnk_idx, u32 rkey) { int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (test_bit(i, lgr->rtokens_used_mask) && lgr->rtokens[i][lnk_idx].rkey == rkey) return i; } return -ENOENT; } /* set rtoken for a new link to an existing rmb */ void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new, __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey) { int rtok_idx; rtok_idx = smc_rtoken_find_by_link(lgr, link_idx, ntohl(nw_rkey_known)); if (rtok_idx == -ENOENT) return; lgr->rtokens[rtok_idx][link_idx_new].rkey = ntohl(nw_rkey); lgr->rtokens[rtok_idx][link_idx_new].dma_addr = be64_to_cpu(nw_vaddr); } /* set rtoken for a new link whose link_id is given */ void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id, __be64 nw_vaddr, __be32 nw_rkey) { u64 dma_addr = be64_to_cpu(nw_vaddr); u32 rkey = ntohl(nw_rkey); bool found = false; int link_idx; for (link_idx = 0; link_idx < SMC_LINKS_PER_LGR_MAX; link_idx++) { if (lgr->lnk[link_idx].link_id == link_id) { found = true; break; } } if (!found) return; lgr->rtokens[rtok_idx][link_idx].rkey = rkey; lgr->rtokens[rtok_idx][link_idx].dma_addr = dma_addr; } /* add a new rtoken from peer */ int smc_rtoken_add(struct smc_link *lnk, __be64 nw_vaddr, __be32 nw_rkey) { struct smc_link_group *lgr = smc_get_lgr(lnk); u64 dma_addr = be64_to_cpu(nw_vaddr); u32 rkey = ntohl(nw_rkey); int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (lgr->rtokens[i][lnk->link_idx].rkey == rkey && lgr->rtokens[i][lnk->link_idx].dma_addr == dma_addr && test_bit(i, lgr->rtokens_used_mask)) { /* already in list */ return i; } } i = smc_rmb_reserve_rtoken_idx(lgr); if (i < 0) return i; lgr->rtokens[i][lnk->link_idx].rkey = rkey; lgr->rtokens[i][lnk->link_idx].dma_addr = dma_addr; return i; } /* delete an rtoken from all links */ int smc_rtoken_delete(struct smc_link *lnk, __be32 nw_rkey) { struct smc_link_group *lgr = smc_get_lgr(lnk); u32 rkey = ntohl(nw_rkey); int i, j; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (lgr->rtokens[i][lnk->link_idx].rkey == rkey && test_bit(i, lgr->rtokens_used_mask)) { for (j = 0; j < SMC_LINKS_PER_LGR_MAX; j++) { lgr->rtokens[i][j].rkey = 0; lgr->rtokens[i][j].dma_addr = 0; } clear_bit(i, lgr->rtokens_used_mask); return 0; } } return -ENOENT; } /* save rkey and dma_addr received from peer during clc handshake */ int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *lnk, struct smc_clc_msg_accept_confirm *clc) { conn->rtoken_idx = smc_rtoken_add(lnk, clc->r0.rmb_dma_addr, clc->r0.rmb_rkey); if (conn->rtoken_idx < 0) return conn->rtoken_idx; return 0; } static void smc_core_going_away(void) { struct smc_ib_device *smcibdev; struct smcd_dev *smcd; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { int i; for (i = 0; i < SMC_MAX_PORTS; i++) set_bit(i, smcibdev->ports_going_away); } mutex_unlock(&smc_ib_devices.mutex); mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { smcd->going_away = 1; } mutex_unlock(&smcd_dev_list.mutex); } /* Clean up all SMC link groups */ static void smc_lgrs_shutdown(void) { struct smcd_dev *smcd; smc_core_going_away(); smc_smcr_terminate_all(NULL); mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) smc_smcd_terminate_all(smcd); mutex_unlock(&smcd_dev_list.mutex); } static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); smc_ib_unregister_client(); smc_ism_exit(); return 0; } static struct notifier_block smc_reboot_notifier = { .notifier_call = smc_core_reboot_event, }; int __init smc_core_init(void) { return register_reboot_notifier(&smc_reboot_notifier); } /* Called (from smc_exit) when module is removed */ void smc_core_exit(void) { unregister_reboot_notifier(&smc_reboot_notifier); smc_lgrs_shutdown(); } |
| 1 39 2 4 2 3 39 1 2 34 1 5 88 30 2 3 29 5 3 1 48 16 50 15 11 54 40 33 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/ematch.c Extended Match API * * Authors: Thomas Graf <tgraf@suug.ch> * * ========================================================================== * * An extended match (ematch) is a small classification tool not worth * writing a full classifier for. Ematches can be interconnected to form * a logic expression and get attached to classifiers to extend their * functionatlity. * * The userspace part transforms the logic expressions into an array * consisting of multiple sequences of interconnected ematches separated * by markers. Precedence is implemented by a special ematch kind * referencing a sequence beyond the marker of the current sequence * causing the current position in the sequence to be pushed onto a stack * to allow the current position to be overwritten by the position referenced * in the special ematch. Matching continues in the new sequence until a * marker is reached causing the position to be restored from the stack. * * Example: * A AND (B1 OR B2) AND C AND D * * ------->-PUSH------- * -->-- / -->-- \ -->-- * / \ / / \ \ / \ * +-------+-------+-------+-------+-------+--------+ * | A AND | B AND | C AND | D END | B1 OR | B2 END | * +-------+-------+-------+-------+-------+--------+ * \ / * --------<-POP--------- * * where B is a virtual ematch referencing to sequence starting with B1. * * ========================================================================== * * How to write an ematch in 60 seconds * ------------------------------------ * * 1) Provide a matcher function: * static int my_match(struct sk_buff *skb, struct tcf_ematch *m, * struct tcf_pkt_info *info) * { * struct mydata *d = (struct mydata *) m->data; * * if (...matching goes here...) * return 1; * else * return 0; * } * * 2) Fill out a struct tcf_ematch_ops: * static struct tcf_ematch_ops my_ops = { * .kind = unique id, * .datalen = sizeof(struct mydata), * .match = my_match, * .owner = THIS_MODULE, * }; * * 3) Register/Unregister your ematch: * static int __init init_my_ematch(void) * { * return tcf_em_register(&my_ops); * } * * static void __exit exit_my_ematch(void) * { * tcf_em_unregister(&my_ops); * } * * module_init(init_my_ematch); * module_exit(exit_my_ematch); * * 4) By now you should have two more seconds left, barely enough to * open up a beer to watch the compilation going. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/pkt_cls.h> static LIST_HEAD(ematch_ops); static DEFINE_RWLOCK(ematch_mod_lock); static struct tcf_ematch_ops *tcf_em_lookup(u16 kind) { struct tcf_ematch_ops *e = NULL; read_lock(&ematch_mod_lock); list_for_each_entry(e, &ematch_ops, link) { if (kind == e->kind) { if (!try_module_get(e->owner)) e = NULL; read_unlock(&ematch_mod_lock); return e; } } read_unlock(&ematch_mod_lock); return NULL; } /** * tcf_em_register - register an extended match * * @ops: ematch operations lookup table * * This function must be called by ematches to announce their presence. * The given @ops must have kind set to a unique identifier and the * callback match() must be implemented. All other callbacks are optional * and a fallback implementation is used instead. * * Returns -EEXISTS if an ematch of the same kind has already registered. */ int tcf_em_register(struct tcf_ematch_ops *ops) { int err = -EEXIST; struct tcf_ematch_ops *e; if (ops->match == NULL) return -EINVAL; write_lock(&ematch_mod_lock); list_for_each_entry(e, &ematch_ops, link) if (ops->kind == e->kind) goto errout; list_add_tail(&ops->link, &ematch_ops); err = 0; errout: write_unlock(&ematch_mod_lock); return err; } EXPORT_SYMBOL(tcf_em_register); /** * tcf_em_unregister - unregister and extended match * * @ops: ematch operations lookup table * * This function must be called by ematches to announce their disappearance * for examples when the module gets unloaded. The @ops parameter must be * the same as the one used for registration. * * Returns -ENOENT if no matching ematch was found. */ void tcf_em_unregister(struct tcf_ematch_ops *ops) { write_lock(&ematch_mod_lock); list_del(&ops->link); write_unlock(&ematch_mod_lock); } EXPORT_SYMBOL(tcf_em_unregister); static inline struct tcf_ematch *tcf_em_get_match(struct tcf_ematch_tree *tree, int index) { return &tree->matches[index]; } static int tcf_em_validate(struct tcf_proto *tp, struct tcf_ematch_tree_hdr *tree_hdr, struct tcf_ematch *em, struct nlattr *nla, int idx) { int err = -EINVAL; struct tcf_ematch_hdr *em_hdr = nla_data(nla); int data_len = nla_len(nla) - sizeof(*em_hdr); void *data = (void *) em_hdr + sizeof(*em_hdr); struct net *net = tp->chain->block->net; if (!TCF_EM_REL_VALID(em_hdr->flags)) goto errout; if (em_hdr->kind == TCF_EM_CONTAINER) { /* Special ematch called "container", carries an index * referencing an external ematch sequence. */ u32 ref; if (data_len < sizeof(ref)) goto errout; ref = *(u32 *) data; if (ref >= tree_hdr->nmatches) goto errout; /* We do not allow backward jumps to avoid loops and jumps * to our own position are of course illegal. */ if (ref <= idx) goto errout; em->data = ref; } else { /* Note: This lookup will increase the module refcnt * of the ematch module referenced. In case of a failure, * a destroy function is called by the underlying layer * which automatically releases the reference again, therefore * the module MUST not be given back under any circumstances * here. Be aware, the destroy function assumes that the * module is held if the ops field is non zero. */ em->ops = tcf_em_lookup(em_hdr->kind); if (em->ops == NULL) { err = -ENOENT; #ifdef CONFIG_MODULES __rtnl_unlock(); request_module("ematch-kind-%u", em_hdr->kind); rtnl_lock(); em->ops = tcf_em_lookup(em_hdr->kind); if (em->ops) { /* We dropped the RTNL mutex in order to * perform the module load. Tell the caller * to replay the request. */ module_put(em->ops->owner); em->ops = NULL; err = -EAGAIN; } #endif goto errout; } /* ematch module provides expected length of data, so we * can do a basic sanity check. */ if (em->ops->datalen && data_len < em->ops->datalen) goto errout; if (em->ops->change) { err = -EINVAL; if (em_hdr->flags & TCF_EM_SIMPLE) goto errout; err = em->ops->change(net, data, data_len, em); if (err < 0) goto errout; } else if (data_len > 0) { /* ematch module doesn't provide an own change * procedure and expects us to allocate and copy * the ematch data. * * TCF_EM_SIMPLE may be specified stating that the * data only consists of a u32 integer and the module * does not expected a memory reference but rather * the value carried. */ if (em_hdr->flags & TCF_EM_SIMPLE) { if (em->ops->datalen > 0) goto errout; if (data_len < sizeof(u32)) goto errout; em->data = *(u32 *) data; } else { void *v = kmemdup(data, data_len, GFP_KERNEL); if (v == NULL) { err = -ENOBUFS; goto errout; } em->data = (unsigned long) v; } em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; em->net = net; err = 0; errout: return err; } static const struct nla_policy em_policy[TCA_EMATCH_TREE_MAX + 1] = { [TCA_EMATCH_TREE_HDR] = { .len = sizeof(struct tcf_ematch_tree_hdr) }, [TCA_EMATCH_TREE_LIST] = { .type = NLA_NESTED }, }; /** * tcf_em_tree_validate - validate ematch config TLV and build ematch tree * * @tp: classifier kind handle * @nla: ematch tree configuration TLV * @tree: destination ematch tree variable to store the resulting * ematch tree. * * This function validates the given configuration TLV @nla and builds an * ematch tree in @tree. The resulting tree must later be copied into * the private classifier data using tcf_em_tree_change(). You MUST NOT * provide the ematch tree variable of the private classifier data directly, * the changes would not be locked properly. * * Returns a negative error code if the configuration TLV contains errors. */ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, struct tcf_ematch_tree *tree) { int idx, list_len, matches_len, err; struct nlattr *tb[TCA_EMATCH_TREE_MAX + 1]; struct nlattr *rt_match, *rt_hdr, *rt_list; struct tcf_ematch_tree_hdr *tree_hdr; struct tcf_ematch *em; memset(tree, 0, sizeof(*tree)); if (!nla) return 0; err = nla_parse_nested_deprecated(tb, TCA_EMATCH_TREE_MAX, nla, em_policy, NULL); if (err < 0) goto errout; err = -EINVAL; rt_hdr = tb[TCA_EMATCH_TREE_HDR]; rt_list = tb[TCA_EMATCH_TREE_LIST]; if (rt_hdr == NULL || rt_list == NULL) goto errout; tree_hdr = nla_data(rt_hdr); memcpy(&tree->hdr, tree_hdr, sizeof(*tree_hdr)); rt_match = nla_data(rt_list); list_len = nla_len(rt_list); matches_len = tree_hdr->nmatches * sizeof(*em); tree->matches = kzalloc(matches_len, GFP_KERNEL); if (tree->matches == NULL) goto errout; /* We do not use nla_parse_nested here because the maximum * number of attributes is unknown. This saves us the allocation * for a tb buffer which would serve no purpose at all. * * The array of rt attributes is parsed in the order as they are * provided, their type must be incremental from 1 to n. Even * if it does not serve any real purpose, a failure of sticking * to this policy will result in parsing failure. */ for (idx = 0; nla_ok(rt_match, list_len); idx++) { err = -EINVAL; if (rt_match->nla_type != (idx + 1)) goto errout_abort; if (idx >= tree_hdr->nmatches) goto errout_abort; if (nla_len(rt_match) < sizeof(struct tcf_ematch_hdr)) goto errout_abort; em = tcf_em_get_match(tree, idx); err = tcf_em_validate(tp, tree_hdr, em, rt_match, idx); if (err < 0) goto errout_abort; rt_match = nla_next(rt_match, &list_len); } /* Check if the number of matches provided by userspace actually * complies with the array of matches. The number was used for * the validation of references and a mismatch could lead to * undefined references during the matching process. */ if (idx != tree_hdr->nmatches) { err = -EINVAL; goto errout_abort; } err = 0; errout: return err; errout_abort: tcf_em_tree_destroy(tree); return err; } EXPORT_SYMBOL(tcf_em_tree_validate); /** * tcf_em_tree_destroy - destroy an ematch tree * * @tree: ematch tree to be deleted * * This functions destroys an ematch tree previously created by * tcf_em_tree_validate()/tcf_em_tree_change(). You must ensure that * the ematch tree is not in use before calling this function. */ void tcf_em_tree_destroy(struct tcf_ematch_tree *tree) { int i; if (tree->matches == NULL) return; for (i = 0; i < tree->hdr.nmatches; i++) { struct tcf_ematch *em = tcf_em_get_match(tree, i); if (em->ops) { if (em->ops->destroy) em->ops->destroy(em); else if (!tcf_em_is_simple(em)) kfree((void *) em->data); module_put(em->ops->owner); } } tree->hdr.nmatches = 0; kfree(tree->matches); tree->matches = NULL; } EXPORT_SYMBOL(tcf_em_tree_destroy); /** * tcf_em_tree_dump - dump ematch tree into a rtnl message * * @skb: skb holding the rtnl message * @tree: ematch tree to be dumped * @tlv: TLV type to be used to encapsulate the tree * * This function dumps a ematch tree into a rtnl message. It is valid to * call this function while the ematch tree is in use. * * Returns -1 if the skb tailroom is insufficient. */ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) { int i; u8 *tail; struct nlattr *top_start; struct nlattr *list_start; top_start = nla_nest_start_noflag(skb, tlv); if (top_start == NULL) goto nla_put_failure; if (nla_put(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr)) goto nla_put_failure; list_start = nla_nest_start_noflag(skb, TCA_EMATCH_TREE_LIST); if (list_start == NULL) goto nla_put_failure; tail = skb_tail_pointer(skb); for (i = 0; i < tree->hdr.nmatches; i++) { struct nlattr *match_start = (struct nlattr *)tail; struct tcf_ematch *em = tcf_em_get_match(tree, i); struct tcf_ematch_hdr em_hdr = { .kind = em->ops ? em->ops->kind : TCF_EM_CONTAINER, .matchid = em->matchid, .flags = em->flags }; if (nla_put(skb, i + 1, sizeof(em_hdr), &em_hdr)) goto nla_put_failure; if (em->ops && em->ops->dump) { if (em->ops->dump(skb, em) < 0) goto nla_put_failure; } else if (tcf_em_is_container(em) || tcf_em_is_simple(em)) { u32 u = em->data; nla_put_nohdr(skb, sizeof(u), &u); } else if (em->datalen > 0) nla_put_nohdr(skb, em->datalen, (void *) em->data); tail = skb_tail_pointer(skb); match_start->nla_len = tail - (u8 *)match_start; } nla_nest_end(skb, list_start); nla_nest_end(skb, top_start); return 0; nla_put_failure: return -1; } EXPORT_SYMBOL(tcf_em_tree_dump); static inline int tcf_em_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { int r = em->ops->match(skb, em, info); return tcf_em_is_inverted(em) ? !r : r; } /* Do not use this function directly, use tcf_em_tree_match instead */ int __tcf_em_tree_match(struct sk_buff *skb, struct tcf_ematch_tree *tree, struct tcf_pkt_info *info) { int stackp = 0, match_idx = 0, res = 0; struct tcf_ematch *cur_match; int stack[CONFIG_NET_EMATCH_STACK]; proceed: while (match_idx < tree->hdr.nmatches) { cur_match = tcf_em_get_match(tree, match_idx); if (tcf_em_is_container(cur_match)) { if (unlikely(stackp >= CONFIG_NET_EMATCH_STACK)) goto stack_overflow; stack[stackp++] = match_idx; match_idx = cur_match->data; goto proceed; } res = tcf_em_match(skb, cur_match, info); if (tcf_em_early_end(cur_match, res)) break; match_idx++; } pop_stack: if (stackp > 0) { match_idx = stack[--stackp]; cur_match = tcf_em_get_match(tree, match_idx); if (tcf_em_is_inverted(cur_match)) res = !res; if (tcf_em_early_end(cur_match, res)) { goto pop_stack; } else { match_idx++; goto proceed; } } return res; stack_overflow: net_warn_ratelimited("tc ematch: local stack overflow, increase NET_EMATCH_STACK\n"); return -1; } EXPORT_SYMBOL(__tcf_em_tree_match); |
| 42 42 19 41 42 42 42 42 42 42 42 42 42 19 19 19 19 19 41 42 19 19 | 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 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright (c) 2016-2020 INRIA, CMU and Microsoft Corporation */ #include <crypto/curve25519.h> #include <crypto/internal/kpp.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <asm/cpufeature.h> #include <asm/processor.h> static __always_inline u64 eq_mask(u64 a, u64 b) { u64 x = a ^ b; u64 minus_x = ~x + (u64)1U; u64 x_or_minus_x = x | minus_x; u64 xnx = x_or_minus_x >> (u32)63U; return xnx - (u64)1U; } static __always_inline u64 gte_mask(u64 a, u64 b) { u64 x = a; u64 y = b; u64 x_xor_y = x ^ y; u64 x_sub_y = x - y; u64 x_sub_y_xor_y = x_sub_y ^ y; u64 q = x_xor_y | x_sub_y_xor_y; u64 x_xor_q = x ^ q; u64 x_xor_q_ = x_xor_q >> (u32)63U; return x_xor_q_ - (u64)1U; } /* Computes the addition of four-element f1 with value in f2 * and returns the carry (if any) */ static inline u64 add_scalar(u64 *out, const u64 *f1, u64 f2) { u64 carry_r; asm volatile( /* Clear registers to propagate the carry bit */ " xor %%r8d, %%r8d;" " xor %%r9d, %%r9d;" " xor %%r10d, %%r10d;" " xor %%r11d, %%r11d;" " xor %k1, %k1;" /* Begin addition chain */ " addq 0(%3), %0;" " movq %0, 0(%2);" " adcxq 8(%3), %%r8;" " movq %%r8, 8(%2);" " adcxq 16(%3), %%r9;" " movq %%r9, 16(%2);" " adcxq 24(%3), %%r10;" " movq %%r10, 24(%2);" /* Return the carry bit in a register */ " adcx %%r11, %1;" : "+&r"(f2), "=&r"(carry_r) : "r"(out), "r"(f1) : "%r8", "%r9", "%r10", "%r11", "memory", "cc"); return carry_r; } /* Computes the field addition of two field elements */ static inline void fadd(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( /* Compute the raw addition of f1 + f2 */ " movq 0(%0), %%r8;" " addq 0(%2), %%r8;" " movq 8(%0), %%r9;" " adcxq 8(%2), %%r9;" " movq 16(%0), %%r10;" " adcxq 16(%2), %%r10;" " movq 24(%0), %%r11;" " adcxq 24(%2), %%r11;" /* Wrap the result back into the field */ /* Step 1: Compute carry*38 */ " mov $0, %%rax;" " mov $38, %0;" " cmovc %0, %%rax;" /* Step 2: Add carry*38 to the original sum */ " xor %%ecx, %%ecx;" " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %0, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" : "+&r"(f2) : "r"(out), "r"(f1) : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc"); } /* Computes the field subtraction of two field elements */ static inline void fsub(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( /* Compute the raw subtraction of f1-f2 */ " movq 0(%1), %%r8;" " subq 0(%2), %%r8;" " movq 8(%1), %%r9;" " sbbq 8(%2), %%r9;" " movq 16(%1), %%r10;" " sbbq 16(%2), %%r10;" " movq 24(%1), %%r11;" " sbbq 24(%2), %%r11;" /* Wrap the result back into the field */ /* Step 1: Compute carry*38 */ " mov $0, %%rax;" " mov $38, %%rcx;" " cmovc %%rcx, %%rax;" /* Step 2: Subtract carry*38 from the original difference */ " sub %%rax, %%r8;" " sbb $0, %%r9;" " sbb $0, %%r10;" " sbb $0, %%r11;" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rcx, %%rax;" " sub %%rax, %%r8;" /* Store the result */ " movq %%r8, 0(%0);" " movq %%r9, 8(%0);" " movq %%r10, 16(%0);" " movq %%r11, 24(%0);" : : "r"(out), "r"(f1), "r"(f2) : "%rax", "%rcx", "%r8", "%r9", "%r10", "%r11", "memory", "cc"); } /* Computes a field multiplication: out <- f1 * f2 * Uses the 8-element buffer tmp for intermediate results */ static inline void fmul(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) { asm volatile( /* Compute the raw multiplication: tmp <- src1 * src2 */ /* Compute src1[0] * src2 */ " movq 0(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 8(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%2), %%r8;" " movq %%r8, 8(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 16(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%2), %%r8;" " movq %%r8, 16(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 24(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%2), %%r8;" " movq %%r8, 24(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%2);" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%2);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%2);" /* Line up pointers */ " mov %2, %0;" " mov %3, %2;" /* Wrap the result back into the field */ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %k1, %k1;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %1, %%rax;" " adox %1, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %1, %%r9;" " movq %%r9, 8(%2);" " adcx %1, %%r10;" " movq %%r10, 16(%2);" " adcx %1, %%r11;" " movq %%r11, 24(%2);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%2);" : "+&r"(f1), "+&r"(f2), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "memory", "cc"); } /* Computes two field multiplications: * out[0] <- f1[0] * f2[0] * out[1] <- f1[1] * f2[1] * Uses the 16-element buffer tmp for intermediate results: */ static inline void fmul2(u64 *out, const u64 *f1, const u64 *f2, u64 *tmp) { asm volatile( /* Compute the raw multiplication tmp[0] <- f1[0] * f2[0] */ /* Compute src1[0] * src2 */ " movq 0(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 0(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 8(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 8(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 8(%2), %%r8;" " movq %%r8, 8(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 16(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 16(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 16(%2), %%r8;" " movq %%r8, 16(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 24(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 24(%0), %%rdx;" " mulxq 0(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 24(%2), %%r8;" " movq %%r8, 24(%2);" " mulxq 8(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 32(%2);" " mulxq 16(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 40(%2);" " mov $0, %%r8;" " mulxq 24(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 48(%2);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 56(%2);" /* Compute the raw multiplication tmp[1] <- f1[1] * f2[1] */ /* Compute src1[0] * src2 */ " movq 32(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " movq %%r8, 64(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " movq %%r10, 72(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" /* Compute src1[1] * src2 */ " movq 40(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 72(%2), %%r8;" " movq %%r8, 72(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 80(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[2] * src2 */ " movq 48(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 80(%2), %%r8;" " movq %%r8, 80(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 88(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " mov $0, %%r8;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" /* Compute src1[3] * src2 */ " movq 56(%0), %%rdx;" " mulxq 32(%1), %%r8, %%r9;" " xor %%r10d, %%r10d;" " adcxq 88(%2), %%r8;" " movq %%r8, 88(%2);" " mulxq 40(%1), %%r10, %%r11;" " adox %%r9, %%r10;" " adcx %%rbx, %%r10;" " movq %%r10, 96(%2);" " mulxq 48(%1), %%rbx, %%r13;" " adox %%r11, %%rbx;" " adcx %%r14, %%rbx;" " movq %%rbx, 104(%2);" " mov $0, %%r8;" " mulxq 56(%1), %%r14, %%rdx;" " adox %%r13, %%r14;" " adcx %%rax, %%r14;" " movq %%r14, 112(%2);" " mov $0, %%rax;" " adox %%rdx, %%rax;" " adcx %%r8, %%rax;" " movq %%rax, 120(%2);" /* Line up pointers */ " mov %2, %0;" " mov %3, %2;" /* Wrap the results back into the field */ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %k1, %k1;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %1, %%rax;" " adox %1, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %1, %%r9;" " movq %%r9, 8(%2);" " adcx %1, %%r10;" " movq %%r10, 16(%2);" " adcx %1, %%r11;" " movq %%r11, 24(%2);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%2);" /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 96(%0), %%r8, %%r13;" " xor %k1, %k1;" " adoxq 64(%0), %%r8;" " mulxq 104(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 72(%0), %%r9;" " mulxq 112(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 80(%0), %%r10;" " mulxq 120(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 88(%0), %%r11;" " adcx %1, %%rax;" " adox %1, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %1, %%r9;" " movq %%r9, 40(%2);" " adcx %1, %%r10;" " movq %%r10, 48(%2);" " adcx %1, %%r11;" " movq %%r11, 56(%2);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 32(%2);" : "+&r"(f1), "+&r"(f2), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "memory", "cc"); } /* Computes the field multiplication of four-element f1 with value in f2 * Requires f2 to be smaller than 2^17 */ static inline void fmul_scalar(u64 *out, const u64 *f1, u64 f2) { register u64 f2_r asm("rdx") = f2; asm volatile( /* Compute the raw multiplication of f1*f2 */ " mulxq 0(%2), %%r8, %%rcx;" /* f1[0]*f2 */ " mulxq 8(%2), %%r9, %%rbx;" /* f1[1]*f2 */ " add %%rcx, %%r9;" " mov $0, %%rcx;" " mulxq 16(%2), %%r10, %%r13;" /* f1[2]*f2 */ " adcx %%rbx, %%r10;" " mulxq 24(%2), %%r11, %%rax;" /* f1[3]*f2 */ " adcx %%r13, %%r11;" " adcx %%rcx, %%rax;" /* Wrap the result back into the field */ /* Step 1: Compute carry*38 */ " mov $38, %%rdx;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" : "+&r"(f2_r) : "r"(out), "r"(f1) : "%rax", "%rbx", "%rcx", "%r8", "%r9", "%r10", "%r11", "%r13", "memory", "cc"); } /* Computes p1 <- bit ? p2 : p1 in constant time */ static inline void cswap2(u64 bit, const u64 *p1, const u64 *p2) { asm volatile( /* Transfer bit into CF flag */ " add $18446744073709551615, %0;" /* cswap p1[0], p2[0] */ " movq 0(%1), %%r8;" " movq 0(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 0(%1);" " movq %%r9, 0(%2);" /* cswap p1[1], p2[1] */ " movq 8(%1), %%r8;" " movq 8(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 8(%1);" " movq %%r9, 8(%2);" /* cswap p1[2], p2[2] */ " movq 16(%1), %%r8;" " movq 16(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 16(%1);" " movq %%r9, 16(%2);" /* cswap p1[3], p2[3] */ " movq 24(%1), %%r8;" " movq 24(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 24(%1);" " movq %%r9, 24(%2);" /* cswap p1[4], p2[4] */ " movq 32(%1), %%r8;" " movq 32(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 32(%1);" " movq %%r9, 32(%2);" /* cswap p1[5], p2[5] */ " movq 40(%1), %%r8;" " movq 40(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 40(%1);" " movq %%r9, 40(%2);" /* cswap p1[6], p2[6] */ " movq 48(%1), %%r8;" " movq 48(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 48(%1);" " movq %%r9, 48(%2);" /* cswap p1[7], p2[7] */ " movq 56(%1), %%r8;" " movq 56(%2), %%r9;" " mov %%r8, %%r10;" " cmovc %%r9, %%r8;" " cmovc %%r10, %%r9;" " movq %%r8, 56(%1);" " movq %%r9, 56(%2);" : "+&r"(bit) : "r"(p1), "r"(p2) : "%r8", "%r9", "%r10", "memory", "cc"); } /* Computes the square of a field element: out <- f * f * Uses the 8-element buffer tmp for intermediate results */ static inline void fsqr(u64 *out, const u64 *f, u64 *tmp) { asm volatile( /* Compute the raw multiplication: tmp <- f * f */ /* Step 1: Compute all partial products */ " movq 0(%0), %%rdx;" /* f[0] */ " mulxq 8(%0), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 16(%0), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 24(%0), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 24(%0), %%rdx;" /* f[3] */ " mulxq 8(%0), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ " mulxq 16(%0), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ " movq 8(%0), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ " mulxq 16(%0), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" " adcx %%r9, %%r9;" " adox %%r15, %%rbx;" " adcx %%r10, %%r10;" " adox %%r15, %%r13;" " adcx %%r11, %%r11;" " adox %%r15, %%r14;" " adcx %%rbx, %%rbx;" " adcx %%r13, %%r13;" " adcx %%r14, %%r14;" /* Step 3: Compute intermediate squares */ " movq 0(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ " movq %%rax, 0(%1);" " add %%rcx, %%r8;" " movq %%r8, 8(%1);" " movq 8(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ " adcx %%rax, %%r9;" " movq %%r9, 16(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 24(%1);" " movq 16(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ " adcx %%rax, %%r11;" " movq %%r11, 32(%1);" " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%1);" " movq 24(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ " adcx %%rax, %%r13;" " movq %%r13, 48(%1);" " adcx %%rcx, %%r14;" " movq %%r14, 56(%1);" /* Line up pointers */ " mov %1, %0;" " mov %2, %1;" /* Wrap the result back into the field */ /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %%ecx, %%ecx;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %%rcx, %%rax;" " adox %%rcx, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" : "+&r"(f), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "%r15", "memory", "cc"); } /* Computes two field squarings: * out[0] <- f[0] * f[0] * out[1] <- f[1] * f[1] * Uses the 16-element buffer tmp for intermediate results */ static inline void fsqr2(u64 *out, const u64 *f, u64 *tmp) { asm volatile( /* Step 1: Compute all partial products */ " movq 0(%0), %%rdx;" /* f[0] */ " mulxq 8(%0), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 16(%0), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 24(%0), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 24(%0), %%rdx;" /* f[3] */ " mulxq 8(%0), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ " mulxq 16(%0), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ " movq 8(%0), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ " mulxq 16(%0), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" " adcx %%r9, %%r9;" " adox %%r15, %%rbx;" " adcx %%r10, %%r10;" " adox %%r15, %%r13;" " adcx %%r11, %%r11;" " adox %%r15, %%r14;" " adcx %%rbx, %%rbx;" " adcx %%r13, %%r13;" " adcx %%r14, %%r14;" /* Step 3: Compute intermediate squares */ " movq 0(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ " movq %%rax, 0(%1);" " add %%rcx, %%r8;" " movq %%r8, 8(%1);" " movq 8(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ " adcx %%rax, %%r9;" " movq %%r9, 16(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 24(%1);" " movq 16(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ " adcx %%rax, %%r11;" " movq %%r11, 32(%1);" " adcx %%rcx, %%rbx;" " movq %%rbx, 40(%1);" " movq 24(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ " adcx %%rax, %%r13;" " movq %%r13, 48(%1);" " adcx %%rcx, %%r14;" " movq %%r14, 56(%1);" /* Step 1: Compute all partial products */ " movq 32(%0), %%rdx;" /* f[0] */ " mulxq 40(%0), %%r8, %%r14;" " xor %%r15d, %%r15d;" /* f[1]*f[0] */ " mulxq 48(%0), %%r9, %%r10;" " adcx %%r14, %%r9;" /* f[2]*f[0] */ " mulxq 56(%0), %%rax, %%rcx;" " adcx %%rax, %%r10;" /* f[3]*f[0] */ " movq 56(%0), %%rdx;" /* f[3] */ " mulxq 40(%0), %%r11, %%rbx;" " adcx %%rcx, %%r11;" /* f[1]*f[3] */ " mulxq 48(%0), %%rax, %%r13;" " adcx %%rax, %%rbx;" /* f[2]*f[3] */ " movq 40(%0), %%rdx;" " adcx %%r15, %%r13;" /* f1 */ " mulxq 48(%0), %%rax, %%rcx;" " mov $0, %%r14;" /* f[2]*f[1] */ /* Step 2: Compute two parallel carry chains */ " xor %%r15d, %%r15d;" " adox %%rax, %%r10;" " adcx %%r8, %%r8;" " adox %%rcx, %%r11;" " adcx %%r9, %%r9;" " adox %%r15, %%rbx;" " adcx %%r10, %%r10;" " adox %%r15, %%r13;" " adcx %%r11, %%r11;" " adox %%r15, %%r14;" " adcx %%rbx, %%rbx;" " adcx %%r13, %%r13;" " adcx %%r14, %%r14;" /* Step 3: Compute intermediate squares */ " movq 32(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[0]^2 */ " movq %%rax, 64(%1);" " add %%rcx, %%r8;" " movq %%r8, 72(%1);" " movq 40(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[1]^2 */ " adcx %%rax, %%r9;" " movq %%r9, 80(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 88(%1);" " movq 48(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[2]^2 */ " adcx %%rax, %%r11;" " movq %%r11, 96(%1);" " adcx %%rcx, %%rbx;" " movq %%rbx, 104(%1);" " movq 56(%0), %%rdx;" " mulx %%rdx, %%rax, %%rcx;" /* f[3]^2 */ " adcx %%rax, %%r13;" " movq %%r13, 112(%1);" " adcx %%rcx, %%r14;" " movq %%r14, 120(%1);" /* Line up pointers */ " mov %1, %0;" " mov %2, %1;" /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 32(%0), %%r8, %%r13;" " xor %%ecx, %%ecx;" " adoxq 0(%0), %%r8;" " mulxq 40(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 8(%0), %%r9;" " mulxq 48(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 16(%0), %%r10;" " mulxq 56(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 24(%0), %%r11;" " adcx %%rcx, %%rax;" " adox %%rcx, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 8(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 16(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 24(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 0(%1);" /* Step 1: Compute dst + carry == tmp_hi * 38 + tmp_lo */ " mov $38, %%rdx;" " mulxq 96(%0), %%r8, %%r13;" " xor %%ecx, %%ecx;" " adoxq 64(%0), %%r8;" " mulxq 104(%0), %%r9, %%rbx;" " adcx %%r13, %%r9;" " adoxq 72(%0), %%r9;" " mulxq 112(%0), %%r10, %%r13;" " adcx %%rbx, %%r10;" " adoxq 80(%0), %%r10;" " mulxq 120(%0), %%r11, %%rax;" " adcx %%r13, %%r11;" " adoxq 88(%0), %%r11;" " adcx %%rcx, %%rax;" " adox %%rcx, %%rax;" " imul %%rdx, %%rax;" /* Step 2: Fold the carry back into dst */ " add %%rax, %%r8;" " adcx %%rcx, %%r9;" " movq %%r9, 40(%1);" " adcx %%rcx, %%r10;" " movq %%r10, 48(%1);" " adcx %%rcx, %%r11;" " movq %%r11, 56(%1);" /* Step 3: Fold the carry bit back in; guaranteed not to carry at this point */ " mov $0, %%rax;" " cmovc %%rdx, %%rax;" " add %%rax, %%r8;" " movq %%r8, 32(%1);" : "+&r"(f), "+&r"(tmp) : "r"(out) : "%rax", "%rbx", "%rcx", "%rdx", "%r8", "%r9", "%r10", "%r11", "%r13", "%r14", "%r15", "memory", "cc"); } static void point_add_and_double(u64 *q, u64 *p01_tmp1, u64 *tmp2) { u64 *nq = p01_tmp1; u64 *nq_p1 = p01_tmp1 + (u32)8U; u64 *tmp1 = p01_tmp1 + (u32)16U; u64 *x1 = q; u64 *x2 = nq; u64 *z2 = nq + (u32)4U; u64 *z3 = nq_p1 + (u32)4U; u64 *a = tmp1; u64 *b = tmp1 + (u32)4U; u64 *ab = tmp1; u64 *dc = tmp1 + (u32)8U; u64 *x3; u64 *z31; u64 *d0; u64 *c0; u64 *a1; u64 *b1; u64 *d; u64 *c; u64 *ab1; u64 *dc1; fadd(a, x2, z2); fsub(b, x2, z2); x3 = nq_p1; z31 = nq_p1 + (u32)4U; d0 = dc; c0 = dc + (u32)4U; fadd(c0, x3, z31); fsub(d0, x3, z31); fmul2(dc, dc, ab, tmp2); fadd(x3, d0, c0); fsub(z31, d0, c0); a1 = tmp1; b1 = tmp1 + (u32)4U; d = tmp1 + (u32)8U; c = tmp1 + (u32)12U; ab1 = tmp1; dc1 = tmp1 + (u32)8U; fsqr2(dc1, ab1, tmp2); fsqr2(nq_p1, nq_p1, tmp2); a1[0U] = c[0U]; a1[1U] = c[1U]; a1[2U] = c[2U]; a1[3U] = c[3U]; fsub(c, d, c); fmul_scalar(b1, c, (u64)121665U); fadd(b1, b1, d); fmul2(nq, dc1, ab1, tmp2); fmul(z3, z3, x1, tmp2); } static void point_double(u64 *nq, u64 *tmp1, u64 *tmp2) { u64 *x2 = nq; u64 *z2 = nq + (u32)4U; u64 *a = tmp1; u64 *b = tmp1 + (u32)4U; u64 *d = tmp1 + (u32)8U; u64 *c = tmp1 + (u32)12U; u64 *ab = tmp1; u64 *dc = tmp1 + (u32)8U; fadd(a, x2, z2); fsub(b, x2, z2); fsqr2(dc, ab, tmp2); a[0U] = c[0U]; a[1U] = c[1U]; a[2U] = c[2U]; a[3U] = c[3U]; fsub(c, d, c); fmul_scalar(b, c, (u64)121665U); fadd(b, b, d); fmul2(nq, dc, ab, tmp2); } static void montgomery_ladder(u64 *out, const u8 *key, u64 *init1) { u64 tmp2[16U] = { 0U }; u64 p01_tmp1_swap[33U] = { 0U }; u64 *p0 = p01_tmp1_swap; u64 *p01 = p01_tmp1_swap; u64 *p03 = p01; u64 *p11 = p01 + (u32)8U; u64 *x0; u64 *z0; u64 *p01_tmp1; u64 *p01_tmp11; u64 *nq10; u64 *nq_p11; u64 *swap1; u64 sw0; u64 *nq1; u64 *tmp1; memcpy(p11, init1, (u32)8U * sizeof(init1[0U])); x0 = p03; z0 = p03 + (u32)4U; x0[0U] = (u64)1U; x0[1U] = (u64)0U; x0[2U] = (u64)0U; x0[3U] = (u64)0U; z0[0U] = (u64)0U; z0[1U] = (u64)0U; z0[2U] = (u64)0U; z0[3U] = (u64)0U; p01_tmp1 = p01_tmp1_swap; p01_tmp11 = p01_tmp1_swap; nq10 = p01_tmp1_swap; nq_p11 = p01_tmp1_swap + (u32)8U; swap1 = p01_tmp1_swap + (u32)32U; cswap2((u64)1U, nq10, nq_p11); point_add_and_double(init1, p01_tmp11, tmp2); swap1[0U] = (u64)1U; { u32 i; for (i = (u32)0U; i < (u32)251U; i = i + (u32)1U) { u64 *p01_tmp12 = p01_tmp1_swap; u64 *swap2 = p01_tmp1_swap + (u32)32U; u64 *nq2 = p01_tmp12; u64 *nq_p12 = p01_tmp12 + (u32)8U; u64 bit = (u64)(key[((u32)253U - i) / (u32)8U] >> ((u32)253U - i) % (u32)8U & (u8)1U); u64 sw = swap2[0U] ^ bit; cswap2(sw, nq2, nq_p12); point_add_and_double(init1, p01_tmp12, tmp2); swap2[0U] = bit; } } sw0 = swap1[0U]; cswap2(sw0, nq10, nq_p11); nq1 = p01_tmp1; tmp1 = p01_tmp1 + (u32)16U; point_double(nq1, tmp1, tmp2); point_double(nq1, tmp1, tmp2); point_double(nq1, tmp1, tmp2); memcpy(out, p0, (u32)8U * sizeof(p0[0U])); memzero_explicit(tmp2, sizeof(tmp2)); memzero_explicit(p01_tmp1_swap, sizeof(p01_tmp1_swap)); } static void fsquare_times(u64 *o, const u64 *inp, u64 *tmp, u32 n1) { u32 i; fsqr(o, inp, tmp); for (i = (u32)0U; i < n1 - (u32)1U; i = i + (u32)1U) fsqr(o, o, tmp); } static void finv(u64 *o, const u64 *i, u64 *tmp) { u64 t1[16U] = { 0U }; u64 *a0 = t1; u64 *b = t1 + (u32)4U; u64 *c = t1 + (u32)8U; u64 *t00 = t1 + (u32)12U; u64 *tmp1 = tmp; u64 *a; u64 *t0; fsquare_times(a0, i, tmp1, (u32)1U); fsquare_times(t00, a0, tmp1, (u32)2U); fmul(b, t00, i, tmp); fmul(a0, b, a0, tmp); fsquare_times(t00, a0, tmp1, (u32)1U); fmul(b, t00, b, tmp); fsquare_times(t00, b, tmp1, (u32)5U); fmul(b, t00, b, tmp); fsquare_times(t00, b, tmp1, (u32)10U); fmul(c, t00, b, tmp); fsquare_times(t00, c, tmp1, (u32)20U); fmul(t00, t00, c, tmp); fsquare_times(t00, t00, tmp1, (u32)10U); fmul(b, t00, b, tmp); fsquare_times(t00, b, tmp1, (u32)50U); fmul(c, t00, b, tmp); fsquare_times(t00, c, tmp1, (u32)100U); fmul(t00, t00, c, tmp); fsquare_times(t00, t00, tmp1, (u32)50U); fmul(t00, t00, b, tmp); fsquare_times(t00, t00, tmp1, (u32)5U); a = t1; t0 = t1 + (u32)12U; fmul(o, t0, a, tmp); } static void store_felem(u64 *b, u64 *f) { u64 f30 = f[3U]; u64 top_bit0 = f30 >> (u32)63U; u64 f31; u64 top_bit; u64 f0; u64 f1; u64 f2; u64 f3; u64 m0; u64 m1; u64 m2; u64 m3; u64 mask; u64 f0_; u64 f1_; u64 f2_; u64 f3_; u64 o0; u64 o1; u64 o2; u64 o3; f[3U] = f30 & (u64)0x7fffffffffffffffU; add_scalar(f, f, (u64)19U * top_bit0); f31 = f[3U]; top_bit = f31 >> (u32)63U; f[3U] = f31 & (u64)0x7fffffffffffffffU; add_scalar(f, f, (u64)19U * top_bit); f0 = f[0U]; f1 = f[1U]; f2 = f[2U]; f3 = f[3U]; m0 = gte_mask(f0, (u64)0xffffffffffffffedU); m1 = eq_mask(f1, (u64)0xffffffffffffffffU); m2 = eq_mask(f2, (u64)0xffffffffffffffffU); m3 = eq_mask(f3, (u64)0x7fffffffffffffffU); mask = ((m0 & m1) & m2) & m3; f0_ = f0 - (mask & (u64)0xffffffffffffffedU); f1_ = f1 - (mask & (u64)0xffffffffffffffffU); f2_ = f2 - (mask & (u64)0xffffffffffffffffU); f3_ = f3 - (mask & (u64)0x7fffffffffffffffU); o0 = f0_; o1 = f1_; o2 = f2_; o3 = f3_; b[0U] = o0; b[1U] = o1; b[2U] = o2; b[3U] = o3; } static void encode_point(u8 *o, const u64 *i) { const u64 *x = i; const u64 *z = i + (u32)4U; u64 tmp[4U] = { 0U }; u64 tmp_w[16U] = { 0U }; finv(tmp, z, tmp_w); fmul(tmp, tmp, x, tmp_w); store_felem((u64 *)o, tmp); } static void curve25519_ever64(u8 *out, const u8 *priv, const u8 *pub) { u64 init1[8U] = { 0U }; u64 tmp[4U] = { 0U }; u64 tmp3; u64 *x; u64 *z; { u32 i; for (i = (u32)0U; i < (u32)4U; i = i + (u32)1U) { u64 *os = tmp; const u8 *bj = pub + i * (u32)8U; u64 u = *(u64 *)bj; u64 r = u; u64 x0 = r; os[i] = x0; } } tmp3 = tmp[3U]; tmp[3U] = tmp3 & (u64)0x7fffffffffffffffU; x = init1; z = init1 + (u32)4U; z[0U] = (u64)1U; z[1U] = (u64)0U; z[2U] = (u64)0U; z[3U] = (u64)0U; x[0U] = tmp[0U]; x[1U] = tmp[1U]; x[2U] = tmp[2U]; x[3U] = tmp[3U]; montgomery_ladder(init1, priv, init1); encode_point(out, init1); } /* The below constants were generated using this sage script: * * #!/usr/bin/env sage * import sys * from sage.all import * * def limbs(n): * n = int(n) * l = ((n >> 0) % 2^64, (n >> 64) % 2^64, (n >> 128) % 2^64, (n >> 192) % 2^64) * return "0x%016xULL, 0x%016xULL, 0x%016xULL, 0x%016xULL" % l * ec = EllipticCurve(GF(2^255 - 19), [0, 486662, 0, 1, 0]) * p_minus_s = (ec.lift_x(9) - ec.lift_x(1))[0] * print("static const u64 p_minus_s[] = { %s };\n" % limbs(p_minus_s)) * print("static const u64 table_ladder[] = {") * p = ec.lift_x(9) * for i in range(252): * l = (p[0] + p[2]) / (p[0] - p[2]) * print(("\t%s" + ("," if i != 251 else "")) % limbs(l)) * p = p * 2 * print("};") * */ static const u64 p_minus_s[] = { 0x816b1e0137d48290ULL, 0x440f6a51eb4d1207ULL, 0x52385f46dca2b71dULL, 0x215132111d8354cbULL }; static const u64 table_ladder[] = { 0xfffffffffffffff3ULL, 0xffffffffffffffffULL, 0xffffffffffffffffULL, 0x5fffffffffffffffULL, 0x6b8220f416aafe96ULL, 0x82ebeb2b4f566a34ULL, 0xd5a9a5b075a5950fULL, 0x5142b2cf4b2488f4ULL, 0x6aaebc750069680cULL, 0x89cf7820a0f99c41ULL, 0x2a58d9183b56d0f4ULL, 0x4b5aca80e36011a4ULL, 0x329132348c29745dULL, 0xf4a2e616e1642fd7ULL, 0x1e45bb03ff67bc34ULL, 0x306912d0f42a9b4aULL, 0xff886507e6af7154ULL, 0x04f50e13dfeec82fULL, 0xaa512fe82abab5ceULL, 0x174e251a68d5f222ULL, 0xcf96700d82028898ULL, 0x1743e3370a2c02c5ULL, 0x379eec98b4e86eaaULL, 0x0c59888a51e0482eULL, 0xfbcbf1d699b5d189ULL, 0xacaef0d58e9fdc84ULL, 0xc1c20d06231f7614ULL, 0x2938218da274f972ULL, 0xf6af49beff1d7f18ULL, 0xcc541c22387ac9c2ULL, 0x96fcc9ef4015c56bULL, 0x69c1627c690913a9ULL, 0x7a86fd2f4733db0eULL, 0xfdb8c4f29e087de9ULL, 0x095e4b1a8ea2a229ULL, 0x1ad7a7c829b37a79ULL, 0x342d89cad17ea0c0ULL, 0x67bedda6cced2051ULL, 0x19ca31bf2bb42f74ULL, 0x3df7b4c84980acbbULL, 0xa8c6444dc80ad883ULL, 0xb91e440366e3ab85ULL, 0xc215cda00164f6d8ULL, 0x3d867c6ef247e668ULL, 0xc7dd582bcc3e658cULL, 0xfd2c4748ee0e5528ULL, 0xa0fd9b95cc9f4f71ULL, 0x7529d871b0675ddfULL, 0xb8f568b42d3cbd78ULL, 0x1233011b91f3da82ULL, 0x2dce6ccd4a7c3b62ULL, 0x75e7fc8e9e498603ULL, 0x2f4f13f1fcd0b6ecULL, 0xf1a8ca1f29ff7a45ULL, 0xc249c1a72981e29bULL, 0x6ebe0dbb8c83b56aULL, 0x7114fa8d170bb222ULL, 0x65a2dcd5bf93935fULL, 0xbdc41f68b59c979aULL, 0x2f0eef79a2ce9289ULL, 0x42ecbf0c083c37ceULL, 0x2930bc09ec496322ULL, 0xf294b0c19cfeac0dULL, 0x3780aa4bedfabb80ULL, 0x56c17d3e7cead929ULL, 0xe7cb4beb2e5722c5ULL, 0x0ce931732dbfe15aULL, 0x41b883c7621052f8ULL, 0xdbf75ca0c3d25350ULL, 0x2936be086eb1e351ULL, 0xc936e03cb4a9b212ULL, 0x1d45bf82322225aaULL, 0xe81ab1036a024cc5ULL, 0xe212201c304c9a72ULL, 0xc5d73fba6832b1fcULL, 0x20ffdb5a4d839581ULL, 0xa283d367be5d0fadULL, 0x6c2b25ca8b164475ULL, 0x9d4935467caaf22eULL, 0x5166408eee85ff49ULL, 0x3c67baa2fab4e361ULL, 0xb3e433c67ef35cefULL, 0x5259729241159b1cULL, 0x6a621892d5b0ab33ULL, 0x20b74a387555cdcbULL, 0x532aa10e1208923fULL, 0xeaa17b7762281dd1ULL, 0x61ab3443f05c44bfULL, 0x257a6c422324def8ULL, 0x131c6c1017e3cf7fULL, 0x23758739f630a257ULL, 0x295a407a01a78580ULL, 0xf8c443246d5da8d9ULL, 0x19d775450c52fa5dULL, 0x2afcfc92731bf83dULL, 0x7d10c8e81b2b4700ULL, 0xc8e0271f70baa20bULL, 0x993748867ca63957ULL, 0x5412efb3cb7ed4bbULL, 0x3196d36173e62975ULL, 0xde5bcad141c7dffcULL, 0x47cc8cd2b395c848ULL, 0xa34cd942e11af3cbULL, 0x0256dbf2d04ecec2ULL, 0x875ab7e94b0e667fULL, 0xcad4dd83c0850d10ULL, 0x47f12e8f4e72c79fULL, 0x5f1a87bb8c85b19bULL, 0x7ae9d0b6437f51b8ULL, 0x12c7ce5518879065ULL, 0x2ade09fe5cf77aeeULL, 0x23a05a2f7d2c5627ULL, 0x5908e128f17c169aULL, 0xf77498dd8ad0852dULL, 0x74b4c4ceab102f64ULL, 0x183abadd10139845ULL, 0xb165ba8daa92aaacULL, 0xd5c5ef9599386705ULL, 0xbe2f8f0cf8fc40d1ULL, 0x2701e635ee204514ULL, 0x629fa80020156514ULL, 0xf223868764a8c1ceULL, 0x5b894fff0b3f060eULL, 0x60d9944cf708a3faULL, 0xaeea001a1c7a201fULL, 0xebf16a633ee2ce63ULL, 0x6f7709594c7a07e1ULL, 0x79b958150d0208cbULL, 0x24b55e5301d410e7ULL, 0xe3a34edff3fdc84dULL, 0xd88768e4904032d8ULL, 0x131384427b3aaeecULL, 0x8405e51286234f14ULL, 0x14dc4739adb4c529ULL, 0xb8a2b5b250634ffdULL, 0x2fe2a94ad8a7ff93ULL, 0xec5c57efe843faddULL, 0x2843ce40f0bb9918ULL, 0xa4b561d6cf3d6305ULL, 0x743629bde8fb777eULL, 0x343edd46bbaf738fULL, 0xed981828b101a651ULL, 0xa401760b882c797aULL, 0x1fc223e28dc88730ULL, 0x48604e91fc0fba0eULL, 0xb637f78f052c6fa4ULL, 0x91ccac3d09e9239cULL, 0x23f7eed4437a687cULL, 0x5173b1118d9bd800ULL, 0x29d641b63189d4a7ULL, 0xfdbf177988bbc586ULL, 0x2959894fcad81df5ULL, 0xaebc8ef3b4bbc899ULL, 0x4148995ab26992b9ULL, 0x24e20b0134f92cfbULL, 0x40d158894a05dee8ULL, 0x46b00b1185af76f6ULL, 0x26bac77873187a79ULL, 0x3dc0bf95ab8fff5fULL, 0x2a608bd8945524d7ULL, 0x26449588bd446302ULL, 0x7c4bc21c0388439cULL, 0x8e98a4f383bd11b2ULL, 0x26218d7bc9d876b9ULL, 0xe3081542997c178aULL, 0x3c2d29a86fb6606fULL, 0x5c217736fa279374ULL, 0x7dde05734afeb1faULL, 0x3bf10e3906d42babULL, 0xe4f7803e1980649cULL, 0xe6053bf89595bf7aULL, 0x394faf38da245530ULL, 0x7a8efb58896928f4ULL, 0xfbc778e9cc6a113cULL, 0x72670ce330af596fULL, 0x48f222a81d3d6cf7ULL, 0xf01fce410d72caa7ULL, 0x5a20ecc7213b5595ULL, 0x7bc21165c1fa1483ULL, 0x07f89ae31da8a741ULL, 0x05d2c2b4c6830ff9ULL, 0xd43e330fc6316293ULL, 0xa5a5590a96d3a904ULL, 0x705edb91a65333b6ULL, 0x048ee15e0bb9a5f7ULL, 0x3240cfca9e0aaf5dULL, 0x8f4b71ceedc4a40bULL, 0x621c0da3de544a6dULL, 0x92872836a08c4091ULL, 0xce8375b010c91445ULL, 0x8a72eb524f276394ULL, 0x2667fcfa7ec83635ULL, 0x7f4c173345e8752aULL, 0x061b47feee7079a5ULL, 0x25dd9afa9f86ff34ULL, 0x3780cef5425dc89cULL, 0x1a46035a513bb4e9ULL, 0x3e1ef379ac575adaULL, 0xc78c5f1c5fa24b50ULL, 0x321a967634fd9f22ULL, 0x946707b8826e27faULL, 0x3dca84d64c506fd0ULL, 0xc189218075e91436ULL, 0x6d9284169b3b8484ULL, 0x3a67e840383f2ddfULL, 0x33eec9a30c4f9b75ULL, 0x3ec7c86fa783ef47ULL, 0x26ec449fbac9fbc4ULL, 0x5c0f38cba09b9e7dULL, 0x81168cc762a3478cULL, 0x3e23b0d306fc121cULL, 0x5a238aa0a5efdcddULL, 0x1ba26121c4ea43ffULL, 0x36f8c77f7c8832b5ULL, 0x88fbea0b0adcf99aULL, 0x5ca9938ec25bebf9ULL, 0xd5436a5e51fccda0ULL, 0x1dbc4797c2cd893bULL, 0x19346a65d3224a08ULL, 0x0f5034e49b9af466ULL, 0xf23c3967a1e0b96eULL, 0xe58b08fa867a4d88ULL, 0xfb2fabc6a7341679ULL, 0x2a75381eb6026946ULL, 0xc80a3be4c19420acULL, 0x66b1f6c681f2b6dcULL, 0x7cf7036761e93388ULL, 0x25abbbd8a660a4c4ULL, 0x91ea12ba14fd5198ULL, 0x684950fc4a3cffa9ULL, 0xf826842130f5ad28ULL, 0x3ea988f75301a441ULL, 0xc978109a695f8c6fULL, 0x1746eb4a0530c3f3ULL, 0x444d6d77b4459995ULL, 0x75952b8c054e5cc7ULL, 0xa3703f7915f4d6aaULL, 0x66c346202f2647d8ULL, 0xd01469df811d644bULL, 0x77fea47d81a5d71fULL, 0xc5e9529ef57ca381ULL, 0x6eeeb4b9ce2f881aULL, 0xb6e91a28e8009bd6ULL, 0x4b80be3e9afc3fecULL, 0x7e3773c526aed2c5ULL, 0x1b4afcb453c9a49dULL, 0xa920bdd7baffb24dULL, 0x7c54699f122d400eULL, 0xef46c8e14fa94bc8ULL, 0xe0b074ce2952ed5eULL, 0xbea450e1dbd885d5ULL, 0x61b68649320f712cULL, 0x8a485f7309ccbdd1ULL, 0xbd06320d7d4d1a2dULL, 0x25232973322dbef4ULL, 0x445dc4758c17f770ULL, 0xdb0434177cc8933cULL, 0xed6fe82175ea059fULL, 0x1efebefdc053db34ULL, 0x4adbe867c65daf99ULL, 0x3acd71a2a90609dfULL, 0xe5e991856dd04050ULL, 0x1ec69b688157c23cULL, 0x697427f6885cfe4dULL, 0xd7be7b9b65e1a851ULL, 0xa03d28d522c536ddULL, 0x28399d658fd2b645ULL, 0x49e5b7e17c2641e1ULL, 0x6f8c3a98700457a4ULL, 0x5078f0a25ebb6778ULL, 0xd13c3ccbc382960fULL, 0x2e003258a7df84b1ULL, 0x8ad1f39be6296a1cULL, 0xc1eeaa652a5fbfb2ULL, 0x33ee0673fd26f3cbULL, 0x59256173a69d2cccULL, 0x41ea07aa4e18fc41ULL, 0xd9fc19527c87a51eULL, 0xbdaacb805831ca6fULL, 0x445b652dc916694fULL, 0xce92a3a7f2172315ULL, 0x1edc282de11b9964ULL, 0xa1823aafe04c314aULL, 0x790a2d94437cf586ULL, 0x71c447fb93f6e009ULL, 0x8922a56722845276ULL, 0xbf70903b204f5169ULL, 0x2f7a89891ba319feULL, 0x02a08eb577e2140cULL, 0xed9a4ed4427bdcf4ULL, 0x5253ec44e4323cd1ULL, 0x3e88363c14e9355bULL, 0xaa66c14277110b8cULL, 0x1ae0391610a23390ULL, 0x2030bd12c93fc2a2ULL, 0x3ee141579555c7abULL, 0x9214de3a6d6e7d41ULL, 0x3ccdd88607f17efeULL, 0x674f1288f8e11217ULL, 0x5682250f329f93d0ULL, 0x6cf00b136d2e396eULL, 0x6e4cf86f1014debfULL, 0x5930b1b5bfcc4e83ULL, 0x047069b48aba16b6ULL, 0x0d4ce4ab69b20793ULL, 0xb24db91a97d0fb9eULL, 0xcdfa50f54e00d01dULL, 0x221b1085368bddb5ULL, 0xe7e59468b1e3d8d2ULL, 0x53c56563bd122f93ULL, 0xeee8a903e0663f09ULL, 0x61efa662cbbe3d42ULL, 0x2cf8ddddde6eab2aULL, 0x9bf80ad51435f231ULL, 0x5deadacec9f04973ULL, 0x29275b5d41d29b27ULL, 0xcfde0f0895ebf14fULL, 0xb9aab96b054905a7ULL, 0xcae80dd9a1c420fdULL, 0x0a63bf2f1673bbc7ULL, 0x092f6e11958fbc8cULL, 0x672a81e804822fadULL, 0xcac8351560d52517ULL, 0x6f3f7722c8f192f8ULL, 0xf8ba90ccc2e894b7ULL, 0x2c7557a438ff9f0dULL, 0x894d1d855ae52359ULL, 0x68e122157b743d69ULL, 0xd87e5570cfb919f3ULL, 0x3f2cdecd95798db9ULL, 0x2121154710c0a2ceULL, 0x3c66a115246dc5b2ULL, 0xcbedc562294ecb72ULL, 0xba7143c36a280b16ULL, 0x9610c2efd4078b67ULL, 0x6144735d946a4b1eULL, 0x536f111ed75b3350ULL, 0x0211db8c2041d81bULL, 0xf93cb1000e10413cULL, 0x149dfd3c039e8876ULL, 0xd479dde46b63155bULL, 0xb66e15e93c837976ULL, 0xdafde43b1f13e038ULL, 0x5fafda1a2e4b0b35ULL, 0x3600bbdf17197581ULL, 0x3972050bbe3cd2c2ULL, 0x5938906dbdd5be86ULL, 0x34fce5e43f9b860fULL, 0x75a8a4cd42d14d02ULL, 0x828dabc53441df65ULL, 0x33dcabedd2e131d3ULL, 0x3ebad76fb814d25fULL, 0xd4906f566f70e10fULL, 0x5d12f7aa51690f5aULL, 0x45adb16e76cefcf2ULL, 0x01f768aead232999ULL, 0x2b6cc77b6248febdULL, 0x3cd30628ec3aaffdULL, 0xce1c0b80d4ef486aULL, 0x4c3bff2ea6f66c23ULL, 0x3f2ec4094aeaeb5fULL, 0x61b19b286e372ca7ULL, 0x5eefa966de2a701dULL, 0x23b20565de55e3efULL, 0xe301ca5279d58557ULL, 0x07b2d4ce27c2874fULL, 0xa532cd8a9dcf1d67ULL, 0x2a52fee23f2bff56ULL, 0x8624efb37cd8663dULL, 0xbbc7ac20ffbd7594ULL, 0x57b85e9c82d37445ULL, 0x7b3052cb86a6ec66ULL, 0x3482f0ad2525e91eULL, 0x2cb68043d28edca0ULL, 0xaf4f6d052e1b003aULL, 0x185f8c2529781b0aULL, 0xaa41de5bd80ce0d6ULL, 0x9407b2416853e9d6ULL, 0x563ec36e357f4c3aULL, 0x4cc4b8dd0e297bceULL, 0xa2fc1a52ffb8730eULL, 0x1811f16e67058e37ULL, 0x10f9a366cddf4ee1ULL, 0x72f4a0c4a0b9f099ULL, 0x8c16c06f663f4ea7ULL, 0x693b3af74e970fbaULL, 0x2102e7f1d69ec345ULL, 0x0ba53cbc968a8089ULL, 0xca3d9dc7fea15537ULL, 0x4c6824bb51536493ULL, 0xb9886314844006b1ULL, 0x40d2a72ab454cc60ULL, 0x5936a1b712570975ULL, 0x91b9d648debda657ULL, 0x3344094bb64330eaULL, 0x006ba10d12ee51d0ULL, 0x19228468f5de5d58ULL, 0x0eb12f4c38cc05b0ULL, 0xa1039f9dd5601990ULL, 0x4502d4ce4fff0e0bULL, 0xeb2054106837c189ULL, 0xd0f6544c6dd3b93cULL, 0x40727064c416d74fULL, 0x6e15c6114b502ef0ULL, 0x4df2a398cfb1a76bULL, 0x11256c7419f2f6b1ULL, 0x4a497962066e6043ULL, 0x705b3aab41355b44ULL, 0x365ef536d797b1d8ULL, 0x00076bd622ddf0dbULL, 0x3bbf33b0e0575a88ULL, 0x3777aa05c8e4ca4dULL, 0x392745c85578db5fULL, 0x6fda4149dbae5ae2ULL, 0xb1f0b00b8adc9867ULL, 0x09963437d36f1da3ULL, 0x7e824e90a5dc3853ULL, 0xccb5f6641f135cbdULL, 0x6736d86c87ce8fccULL, 0x625f3ce26604249fULL, 0xaf8ac8059502f63fULL, 0x0c05e70a2e351469ULL, 0x35292e9c764b6305ULL, 0x1a394360c7e23ac3ULL, 0xd5c6d53251183264ULL, 0x62065abd43c2b74fULL, 0xb5fbf5d03b973f9bULL, 0x13a3da3661206e5eULL, 0xc6bd5837725d94e5ULL, 0x18e30912205016c5ULL, 0x2088ce1570033c68ULL, 0x7fba1f495c837987ULL, 0x5a8c7423f2f9079dULL, 0x1735157b34023fc5ULL, 0xe4f9b49ad2fab351ULL, 0x6691ff72c878e33cULL, 0x122c2adedc5eff3eULL, 0xf8dd4bf1d8956cf4ULL, 0xeb86205d9e9e5bdaULL, 0x049b92b9d975c743ULL, 0xa5379730b0f6c05aULL, 0x72a0ffacc6f3a553ULL, 0xb0032c34b20dcd6dULL, 0x470e9dbc88d5164aULL, 0xb19cf10ca237c047ULL, 0xb65466711f6c81a2ULL, 0xb3321bd16dd80b43ULL, 0x48c14f600c5fbe8eULL, 0x66451c264aa6c803ULL, 0xb66e3904a4fa7da6ULL, 0xd45f19b0b3128395ULL, 0x31602627c3c9bc10ULL, 0x3120dc4832e4e10dULL, 0xeb20c46756c717f7ULL, 0x00f52e3f67280294ULL, 0x566d4fc14730c509ULL, 0x7e3a5d40fd837206ULL, 0xc1e926dc7159547aULL, 0x216730fba68d6095ULL, 0x22e8c3843f69cea7ULL, 0x33d074e8930e4b2bULL, 0xb6e4350e84d15816ULL, 0x5534c26ad6ba2365ULL, 0x7773c12f89f1f3f3ULL, 0x8cba404da57962aaULL, 0x5b9897a81999ce56ULL, 0x508e862f121692fcULL, 0x3a81907fa093c291ULL, 0x0dded0ff4725a510ULL, 0x10d8cc10673fc503ULL, 0x5b9d151c9f1f4e89ULL, 0x32a5c1d5cb09a44cULL, 0x1e0aa442b90541fbULL, 0x5f85eb7cc1b485dbULL, 0xbee595ce8a9df2e5ULL, 0x25e496c722422236ULL, 0x5edf3c46cd0fe5b9ULL, 0x34e75a7ed2a43388ULL, 0xe488de11d761e352ULL, 0x0e878a01a085545cULL, 0xba493c77e021bb04ULL, 0x2b4d1843c7df899aULL, 0x9ea37a487ae80d67ULL, 0x67a9958011e41794ULL, 0x4b58051a6697b065ULL, 0x47e33f7d8d6ba6d4ULL, 0xbb4da8d483ca46c1ULL, 0x68becaa181c2db0dULL, 0x8d8980e90b989aa5ULL, 0xf95eb14a2c93c99bULL, 0x51c6c7c4796e73a2ULL, 0x6e228363b5efb569ULL, 0xc6bbc0b02dd624c8ULL, 0x777eb47dec8170eeULL, 0x3cde15a004cfafa9ULL, 0x1dc6bc087160bf9bULL, 0x2e07e043eec34002ULL, 0x18e9fc677a68dc7fULL, 0xd8da03188bd15b9aULL, 0x48fbc3bb00568253ULL, 0x57547d4cfb654ce1ULL, 0xd3565b82a058e2adULL, 0xf63eaf0bbf154478ULL, 0x47531ef114dfbb18ULL, 0xe1ec630a4278c587ULL, 0x5507d546ca8e83f3ULL, 0x85e135c63adc0c2bULL, 0x0aa7efa85682844eULL, 0x72691ba8b3e1f615ULL, 0x32b4e9701fbe3ffaULL, 0x97b6d92e39bb7868ULL, 0x2cfe53dea02e39e8ULL, 0x687392cd85cd52b0ULL, 0x27ff66c910e29831ULL, 0x97134556a9832d06ULL, 0x269bb0360a84f8a0ULL, 0x706e55457643f85cULL, 0x3734a48c9b597d1bULL, 0x7aee91e8c6efa472ULL, 0x5cd6abc198a9d9e0ULL, 0x0e04de06cb3ce41aULL, 0xd8c6eb893402e138ULL, 0x904659bb686e3772ULL, 0x7215c371746ba8c8ULL, 0xfd12a97eeae4a2d9ULL, 0x9514b7516394f2c5ULL, 0x266fd5809208f294ULL, 0x5c847085619a26b9ULL, 0x52985410fed694eaULL, 0x3c905b934a2ed254ULL, 0x10bb47692d3be467ULL, 0x063b3d2d69e5e9e1ULL, 0x472726eedda57debULL, 0xefb6c4ae10f41891ULL, 0x2b1641917b307614ULL, 0x117c554fc4f45b7cULL, 0xc07cf3118f9d8812ULL, 0x01dbd82050017939ULL, 0xd7e803f4171b2827ULL, 0x1015e87487d225eaULL, 0xc58de3fed23acc4dULL, 0x50db91c294a7be2dULL, 0x0b94d43d1c9cf457ULL, 0x6b1640fa6e37524aULL, 0x692f346c5fda0d09ULL, 0x200b1c59fa4d3151ULL, 0xb8c46f760777a296ULL, 0x4b38395f3ffdfbcfULL, 0x18d25e00be54d671ULL, 0x60d50582bec8aba6ULL, 0x87ad8f263b78b982ULL, 0x50fdf64e9cda0432ULL, 0x90f567aac578dcf0ULL, 0xef1e9b0ef2a3133bULL, 0x0eebba9242d9de71ULL, 0x15473c9bf03101c7ULL, 0x7c77e8ae56b78095ULL, 0xb678e7666e6f078eULL, 0x2da0b9615348ba1fULL, 0x7cf931c1ff733f0bULL, 0x26b357f50a0a366cULL, 0xe9708cf42b87d732ULL, 0xc13aeea5f91cb2c0ULL, 0x35d90c991143bb4cULL, 0x47c1c404a9a0d9dcULL, 0x659e58451972d251ULL, 0x3875a8c473b38c31ULL, 0x1fbd9ed379561f24ULL, 0x11fabc6fd41ec28dULL, 0x7ef8dfe3cd2a2dcaULL, 0x72e73b5d8c404595ULL, 0x6135fa4954b72f27ULL, 0xccfc32a2de24b69cULL, 0x3f55698c1f095d88ULL, 0xbe3350ed5ac3f929ULL, 0x5e9bf806ca477eebULL, 0xe9ce8fb63c309f68ULL, 0x5376f63565e1f9f4ULL, 0xd1afcfb35a6393f1ULL, 0x6632a1ede5623506ULL, 0x0b7d6c390c2ded4cULL, 0x56cb3281df04cb1fULL, 0x66305a1249ecc3c7ULL, 0x5d588b60a38ca72aULL, 0xa6ecbf78e8e5f42dULL, 0x86eeb44b3c8a3eecULL, 0xec219c48fbd21604ULL, 0x1aaf1af517c36731ULL, 0xc306a2836769bde7ULL, 0x208280622b1e2adbULL, 0x8027f51ffbff94a6ULL, 0x76cfa1ce1124f26bULL, 0x18eb00562422abb6ULL, 0xf377c4d58f8c29c3ULL, 0x4dbbc207f531561aULL, 0x0253b7f082128a27ULL, 0x3d1f091cb62c17e0ULL, 0x4860e1abd64628a9ULL, 0x52d17436309d4253ULL, 0x356f97e13efae576ULL, 0xd351e11aa150535bULL, 0x3e6b45bb1dd878ccULL, 0x0c776128bed92c98ULL, 0x1d34ae93032885b8ULL, 0x4ba0488ca85ba4c3ULL, 0x985348c33c9ce6ceULL, 0x66124c6f97bda770ULL, 0x0f81a0290654124aULL, 0x9ed09ca6569b86fdULL, 0x811009fd18af9a2dULL, 0xff08d03f93d8c20aULL, 0x52a148199faef26bULL, 0x3e03f9dc2d8d1b73ULL, 0x4205801873961a70ULL, 0xc0d987f041a35970ULL, 0x07aa1f15a1c0d549ULL, 0xdfd46ce08cd27224ULL, 0x6d0a024f934e4239ULL, 0x808a7a6399897b59ULL, 0x0a4556e9e13d95a2ULL, 0xd21a991fe9c13045ULL, 0x9b0e8548fe7751b8ULL, 0x5da643cb4bf30035ULL, 0x77db28d63940f721ULL, 0xfc5eeb614adc9011ULL, 0x5229419ae8c411ebULL, 0x9ec3e7787d1dcf74ULL, 0x340d053e216e4cb5ULL, 0xcac7af39b48df2b4ULL, 0xc0faec2871a10a94ULL, 0x140a69245ca575edULL, 0x0cf1c37134273a4cULL, 0xc8ee306ac224b8a5ULL, 0x57eaee7ccb4930b0ULL, 0xa1e806bdaacbe74fULL, 0x7d9a62742eeb657dULL, 0x9eb6b6ef546c4830ULL, 0x885cca1fddb36e2eULL, 0xe6b9f383ef0d7105ULL, 0x58654fef9d2e0412ULL, 0xa905c4ffbe0e8e26ULL, 0x942de5df9b31816eULL, 0x497d723f802e88e1ULL, 0x30684dea602f408dULL, 0x21e5a278a3e6cb34ULL, 0xaefb6e6f5b151dc4ULL, 0xb30b8e049d77ca15ULL, 0x28c3c9cf53b98981ULL, 0x287fb721556cdd2aULL, 0x0d317ca897022274ULL, 0x7468c7423a543258ULL, 0x4a7f11464eb5642fULL, 0xa237a4774d193aa6ULL, 0xd865986ea92129a1ULL, 0x24c515ecf87c1a88ULL, 0x604003575f39f5ebULL, 0x47b9f189570a9b27ULL, 0x2b98cede465e4b78ULL, 0x026df551dbb85c20ULL, 0x74fcd91047e21901ULL, 0x13e2a90a23c1bfa3ULL, 0x0cb0074e478519f6ULL, 0x5ff1cbbe3af6cf44ULL, 0x67fe5438be812dbeULL, 0xd13cf64fa40f05b0ULL, 0x054dfb2f32283787ULL, 0x4173915b7f0d2aeaULL, 0x482f144f1f610d4eULL, 0xf6210201b47f8234ULL, 0x5d0ae1929e70b990ULL, 0xdcd7f455b049567cULL, 0x7e93d0f1f0916f01ULL, 0xdd79cbf18a7db4faULL, 0xbe8391bf6f74c62fULL, 0x027145d14b8291bdULL, 0x585a73ea2cbf1705ULL, 0x485ca03e928a0db2ULL, 0x10fc01a5742857e7ULL, 0x2f482edbd6d551a7ULL, 0x0f0433b5048fdb8aULL, 0x60da2e8dd7dc6247ULL, 0x88b4c9d38cd4819aULL, 0x13033ac001f66697ULL, 0x273b24fe3b367d75ULL, 0xc6e8f66a31b3b9d4ULL, 0x281514a494df49d5ULL, 0xd1726fdfc8b23da7ULL, 0x4b3ae7d103dee548ULL, 0xc6256e19ce4b9d7eULL, 0xff5c5cf186e3c61cULL, 0xacc63ca34b8ec145ULL, 0x74621888fee66574ULL, 0x956f409645290a1eULL, 0xef0bf8e3263a962eULL, 0xed6a50eb5ec2647bULL, 0x0694283a9dca7502ULL, 0x769b963643a2dcd1ULL, 0x42b7c8ea09fc5353ULL, 0x4f002aee13397eabULL, 0x63005e2c19b7d63aULL, 0xca6736da63023beaULL, 0x966c7f6db12a99b7ULL, 0xace09390c537c5e1ULL, 0x0b696063a1aa89eeULL, 0xebb03e97288c56e5ULL, 0x432a9f9f938c8be8ULL, 0xa6a5a93d5b717f71ULL, 0x1a5fb4c3e18f9d97ULL, 0x1c94e7ad1c60cdceULL, 0xee202a43fc02c4a0ULL, 0x8dafe4d867c46a20ULL, 0x0a10263c8ac27b58ULL, 0xd0dea9dfe4432a4aULL, 0x856af87bbe9277c5ULL, 0xce8472acc212c71aULL, 0x6f151b6d9bbb1e91ULL, 0x26776c527ceed56aULL, 0x7d211cb7fbf8faecULL, 0x37ae66a6fd4609ccULL, 0x1f81b702d2770c42ULL, 0x2fb0b057eac58392ULL, 0xe1dd89fe29744e9dULL, 0xc964f8eb17beb4f8ULL, 0x29571073c9a2d41eULL, 0xa948a18981c0e254ULL, 0x2df6369b65b22830ULL, 0xa33eb2d75fcfd3c6ULL, 0x078cd6ec4199a01fULL, 0x4a584a41ad900d2fULL, 0x32142b78e2c74c52ULL, 0x68c4e8338431c978ULL, 0x7f69ea9008689fc2ULL, 0x52f2c81e46a38265ULL, 0xfd78072d04a832fdULL, 0x8cd7d5fa25359e94ULL, 0x4de71b7454cc29d2ULL, 0x42eb60ad1eda6ac9ULL, 0x0aad37dfdbc09c3aULL, 0x81004b71e33cc191ULL, 0x44e6be345122803cULL, 0x03fe8388ba1920dbULL, 0xf5d57c32150db008ULL, 0x49c8c4281af60c29ULL, 0x21edb518de701aeeULL, 0x7fb63e418f06dc99ULL, 0xa4460d99c166d7b8ULL, 0x24dd5248ce520a83ULL, 0x5ec3ad712b928358ULL, 0x15022a5fbd17930fULL, 0xa4f64a77d82570e3ULL, 0x12bc8d6915783712ULL, 0x498194c0fc620abbULL, 0x38a2d9d255686c82ULL, 0x785c6bd9193e21f0ULL, 0xe4d5c81ab24a5484ULL, 0x56307860b2e20989ULL, 0x429d55f78b4d74c4ULL, 0x22f1834643350131ULL, 0x1e60c24598c71fffULL, 0x59f2f014979983efULL, 0x46a47d56eb494a44ULL, 0x3e22a854d636a18eULL, 0xb346e15274491c3bULL, 0x2ceafd4e5390cde7ULL, 0xba8a8538be0d6675ULL, 0x4b9074bb50818e23ULL, 0xcbdab89085d304c3ULL, 0x61a24fe0e56192c4ULL, 0xcb7615e6db525bcbULL, 0xdd7d8c35a567e4caULL, 0xe6b4153acafcdd69ULL, 0x2d668e097f3c9766ULL, 0xa57e7e265ce55ef0ULL, 0x5d9f4e527cd4b967ULL, 0xfbc83606492fd1e5ULL, 0x090d52beb7c3f7aeULL, 0x09b9515a1e7b4d7cULL, 0x1f266a2599da44c0ULL, 0xa1c49548e2c55504ULL, 0x7ef04287126f15ccULL, 0xfed1659dbd30ef15ULL, 0x8b4ab9eec4e0277bULL, 0x884d6236a5df3291ULL, 0x1fd96ea6bf5cf788ULL, 0x42a161981f190d9aULL, 0x61d849507e6052c1ULL, 0x9fe113bf285a2cd5ULL, 0x7c22d676dbad85d8ULL, 0x82e770ed2bfbd27dULL, 0x4c05b2ece996f5a5ULL, 0xcd40a9c2b0900150ULL, 0x5895319213d9bf64ULL, 0xe7cc5d703fea2e08ULL, 0xb50c491258e2188cULL, 0xcce30baa48205bf0ULL, 0x537c659ccfa32d62ULL, 0x37b6623a98cfc088ULL, 0xfe9bed1fa4d6aca4ULL, 0x04d29b8e56a8d1b0ULL, 0x725f71c40b519575ULL, 0x28c7f89cd0339ce6ULL, 0x8367b14469ddc18bULL, 0x883ada83a6a1652cULL, 0x585f1974034d6c17ULL, 0x89cfb266f1b19188ULL, 0xe63b4863e7c35217ULL, 0xd88c9da6b4c0526aULL, 0x3e035c9df0954635ULL, 0xdd9d5412fb45de9dULL, 0xdd684532e4cff40dULL, 0x4b5c999b151d671cULL, 0x2d8c2cc811e7f690ULL, 0x7f54be1d90055d40ULL, 0xa464c5df464aaf40ULL, 0x33979624f0e917beULL, 0x2c018dc527356b30ULL, 0xa5415024e330b3d4ULL, 0x73ff3d96691652d3ULL, 0x94ec42c4ef9b59f1ULL, 0x0747201618d08e5aULL, 0x4d6ca48aca411c53ULL, 0x66415f2fcfa66119ULL, 0x9c4dd40051e227ffULL, 0x59810bc09a02f7ebULL, 0x2a7eb171b3dc101dULL, 0x441c5ab99ffef68eULL, 0x32025c9b93b359eaULL, 0x5e8ce0a71e9d112fULL, 0xbfcccb92429503fdULL, 0xd271ba752f095d55ULL, 0x345ead5e972d091eULL, 0x18c8df11a83103baULL, 0x90cd949a9aed0f4cULL, 0xc5d1f4cb6660e37eULL, 0xb8cac52d56c52e0bULL, 0x6e42e400c5808e0dULL, 0xa3b46966eeaefd23ULL, 0x0c4f1f0be39ecdcaULL, 0x189dc8c9d683a51dULL, 0x51f27f054c09351bULL, 0x4c487ccd2a320682ULL, 0x587ea95bb3df1c96ULL, 0xc8ccf79e555cb8e8ULL, 0x547dc829a206d73dULL, 0xb822a6cd80c39b06ULL, 0xe96d54732000d4c6ULL, 0x28535b6f91463b4dULL, 0x228f4660e2486e1dULL, 0x98799538de8d3abfULL, 0x8cd8330045ebca6eULL, 0x79952a008221e738ULL, 0x4322e1a7535cd2bbULL, 0xb114c11819d1801cULL, 0x2016e4d84f3f5ec7ULL, 0xdd0e2df409260f4cULL, 0x5ec362c0ae5f7266ULL, 0xc0462b18b8b2b4eeULL, 0x7cc8d950274d1afbULL, 0xf25f7105436b02d2ULL, 0x43bbf8dcbff9ccd3ULL, 0xb6ad1767a039e9dfULL, 0xb0714da8f69d3583ULL, 0x5e55fa18b42931f5ULL, 0x4ed5558f33c60961ULL, 0x1fe37901c647a5ddULL, 0x593ddf1f8081d357ULL, 0x0249a4fd813fd7a6ULL, 0x69acca274e9caf61ULL, 0x047ba3ea330721c9ULL, 0x83423fc20e7e1ea0ULL, 0x1df4c0af01314a60ULL, 0x09a62dab89289527ULL, 0xa5b325a49cc6cb00ULL, 0xe94b5dc654b56cb6ULL, 0x3be28779adc994a0ULL, 0x4296e8f8ba3a4aadULL, 0x328689761e451eabULL, 0x2e4d598bff59594aULL, 0x49b96853d7a7084aULL, 0x4980a319601420a8ULL, 0x9565b9e12f552c42ULL, 0x8a5318db7100fe96ULL, 0x05c90b4d43add0d7ULL, 0x538b4cd66a5d4edaULL, 0xf4e94fc3e89f039fULL, 0x592c9af26f618045ULL, 0x08a36eb5fd4b9550ULL, 0x25fffaf6c2ed1419ULL, 0x34434459cc79d354ULL, 0xeeecbfb4b1d5476bULL, 0xddeb34a061615d99ULL, 0x5129cecceb64b773ULL, 0xee43215894993520ULL, 0x772f9c7cf14c0b3bULL, 0xd2e2fce306bedad5ULL, 0x715f42b546f06a97ULL, 0x434ecdceda5b5f1aULL, 0x0da17115a49741a9ULL, 0x680bd77c73edad2eULL, 0x487c02354edd9041ULL, 0xb8efeff3a70ed9c4ULL, 0x56a32aa3e857e302ULL, 0xdf3a68bd48a2a5a0ULL, 0x07f650b73176c444ULL, 0xe38b9b1626e0ccb1ULL, 0x79e053c18b09fb36ULL, 0x56d90319c9f94964ULL, 0x1ca941e7ac9ff5c4ULL, 0x49c4df29162fa0bbULL, 0x8488cf3282b33305ULL, 0x95dfda14cabb437dULL, 0x3391f78264d5ad86ULL, 0x729ae06ae2b5095dULL, 0xd58a58d73259a946ULL, 0xe9834262d13921edULL, 0x27fedafaa54bb592ULL, 0xa99dc5b829ad48bbULL, 0x5f025742499ee260ULL, 0x802c8ecd5d7513fdULL, 0x78ceb3ef3f6dd938ULL, 0xc342f44f8a135d94ULL, 0x7b9edb44828cdda3ULL, 0x9436d11a0537cfe7ULL, 0x5064b164ec1ab4c8ULL, 0x7020eccfd37eb2fcULL, 0x1f31ea3ed90d25fcULL, 0x1b930d7bdfa1bb34ULL, 0x5344467a48113044ULL, 0x70073170f25e6dfbULL, 0xe385dc1a50114cc8ULL, 0x2348698ac8fc4f00ULL, 0x2a77a55284dd40d8ULL, 0xfe06afe0c98c6ce4ULL, 0xc235df96dddfd6e4ULL, 0x1428d01e33bf1ed3ULL, 0x785768ec9300bdafULL, 0x9702e57a91deb63bULL, 0x61bdb8bfe5ce8b80ULL, 0x645b426f3d1d58acULL, 0x4804a82227a557bcULL, 0x8e57048ab44d2601ULL, 0x68d6501a4b3a6935ULL, 0xc39c9ec3f9e1c293ULL, 0x4172f257d4de63e2ULL, 0xd368b450330c6401ULL, 0x040d3017418f2391ULL, 0x2c34bb6090b7d90dULL, 0x16f649228fdfd51fULL, 0xbea6818e2b928ef5ULL, 0xe28ccf91cdc11e72ULL, 0x594aaa68e77a36cdULL, 0x313034806c7ffd0fULL, 0x8a9d27ac2249bd65ULL, 0x19a3b464018e9512ULL, 0xc26ccff352b37ec7ULL, 0x056f68341d797b21ULL, 0x5e79d6757efd2327ULL, 0xfabdbcb6553afe15ULL, 0xd3e7222c6eaf5a60ULL, 0x7046c76d4dae743bULL, 0x660be872b18d4a55ULL, 0x19992518574e1496ULL, 0xc103053a302bdcbbULL, 0x3ed8e9800b218e8eULL, 0x7b0b9239fa75e03eULL, 0xefe9fb684633c083ULL, 0x98a35fbe391a7793ULL, 0x6065510fe2d0fe34ULL, 0x55cb668548abad0cULL, 0xb4584548da87e527ULL, 0x2c43ecea0107c1ddULL, 0x526028809372de35ULL, 0x3415c56af9213b1fULL, 0x5bee1a4d017e98dbULL, 0x13f6b105b5cf709bULL, 0x5ff20e3482b29ab6ULL, 0x0aa29c75cc2e6c90ULL, 0xfc7d73ca3a70e206ULL, 0x899fc38fc4b5c515ULL, 0x250386b124ffc207ULL, 0x54ea28d5ae3d2b56ULL, 0x9913149dd6de60ceULL, 0x16694fc58f06d6c1ULL, 0x46b23975eb018fc7ULL, 0x470a6a0fb4b7b4e2ULL, 0x5d92475a8f7253deULL, 0xabeee5b52fbd3adbULL, 0x7fa20801a0806968ULL, 0x76f3faf19f7714d2ULL, 0xb3e840c12f4660c3ULL, 0x0fb4cd8df212744eULL, 0x4b065a251d3a2dd2ULL, 0x5cebde383d77cd4aULL, 0x6adf39df882c9cb1ULL, 0xa2dd242eb09af759ULL, 0x3147c0e50e5f6422ULL, 0x164ca5101d1350dbULL, 0xf8d13479c33fc962ULL, 0xe640ce4d13e5da08ULL, 0x4bdee0c45061f8baULL, 0xd7c46dc1a4edb1c9ULL, 0x5514d7b6437fd98aULL, 0x58942f6bb2a1c00bULL, 0x2dffb2ab1d70710eULL, 0xccdfcf2fc18b6d68ULL, 0xa8ebcba8b7806167ULL, 0x980697f95e2937e3ULL, 0x02fbba1cd0126e8cULL }; static void curve25519_ever64_base(u8 *out, const u8 *priv) { u64 swap = 1; int i, j, k; u64 tmp[16 + 32 + 4]; u64 *x1 = &tmp[0]; u64 *z1 = &tmp[4]; u64 *x2 = &tmp[8]; u64 *z2 = &tmp[12]; u64 *xz1 = &tmp[0]; u64 *xz2 = &tmp[8]; u64 *a = &tmp[0 + 16]; u64 *b = &tmp[4 + 16]; u64 *c = &tmp[8 + 16]; u64 *ab = &tmp[0 + 16]; u64 *abcd = &tmp[0 + 16]; u64 *ef = &tmp[16 + 16]; u64 *efgh = &tmp[16 + 16]; u64 *key = &tmp[0 + 16 + 32]; memcpy(key, priv, 32); ((u8 *)key)[0] &= 248; ((u8 *)key)[31] = (((u8 *)key)[31] & 127) | 64; x1[0] = 1, x1[1] = x1[2] = x1[3] = 0; z1[0] = 1, z1[1] = z1[2] = z1[3] = 0; z2[0] = 1, z2[1] = z2[2] = z2[3] = 0; memcpy(x2, p_minus_s, sizeof(p_minus_s)); j = 3; for (i = 0; i < 4; ++i) { while (j < (const int[]){ 64, 64, 64, 63 }[i]) { u64 bit = (key[i] >> j) & 1; k = (64 * i + j - 3); swap = swap ^ bit; cswap2(swap, xz1, xz2); swap = bit; fsub(b, x1, z1); fadd(a, x1, z1); fmul(c, &table_ladder[4 * k], b, ef); fsub(b, a, c); fadd(a, a, c); fsqr2(ab, ab, efgh); fmul2(xz1, xz2, ab, efgh); ++j; } j = 0; } point_double(xz1, abcd, efgh); point_double(xz1, abcd, efgh); point_double(xz1, abcd, efgh); encode_point(out, xz1); memzero_explicit(tmp, sizeof(tmp)); } static __ro_after_init DEFINE_STATIC_KEY_FALSE(curve25519_use_bmi2_adx); void curve25519_arch(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], const u8 basepoint[CURVE25519_KEY_SIZE]) { if (static_branch_likely(&curve25519_use_bmi2_adx)) curve25519_ever64(mypublic, secret, basepoint); else curve25519_generic(mypublic, secret, basepoint); } EXPORT_SYMBOL(curve25519_arch); void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE]) { if (static_branch_likely(&curve25519_use_bmi2_adx)) curve25519_ever64_base(pub, secret); else curve25519_generic(pub, secret, curve25519_base_point); } EXPORT_SYMBOL(curve25519_base_arch); static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf, unsigned int len) { u8 *secret = kpp_tfm_ctx(tfm); if (!len) curve25519_generate_secret(secret); else if (len == CURVE25519_KEY_SIZE && crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE)) memcpy(secret, buf, CURVE25519_KEY_SIZE); else return -EINVAL; return 0; } static int curve25519_generate_public_key(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); const u8 *secret = kpp_tfm_ctx(tfm); u8 buf[CURVE25519_KEY_SIZE]; int copied, nbytes; if (req->src) return -EINVAL; curve25519_base_arch(buf, secret); /* might want less than we've got */ nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len); copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, nbytes), buf, nbytes); if (copied != nbytes) return -EINVAL; return 0; } static int curve25519_compute_shared_secret(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); const u8 *secret = kpp_tfm_ctx(tfm); u8 public_key[CURVE25519_KEY_SIZE]; u8 buf[CURVE25519_KEY_SIZE]; int copied, nbytes; if (!req->src) return -EINVAL; copied = sg_copy_to_buffer(req->src, sg_nents_for_len(req->src, CURVE25519_KEY_SIZE), public_key, CURVE25519_KEY_SIZE); if (copied != CURVE25519_KEY_SIZE) return -EINVAL; curve25519_arch(buf, secret, public_key); /* might want less than we've got */ nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len); copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, nbytes), buf, nbytes); if (copied != nbytes) return -EINVAL; return 0; } static unsigned int curve25519_max_size(struct crypto_kpp *tfm) { return CURVE25519_KEY_SIZE; } static struct kpp_alg curve25519_alg = { .base.cra_name = "curve25519", .base.cra_driver_name = "curve25519-x86", .base.cra_priority = 200, .base.cra_module = THIS_MODULE, .base.cra_ctxsize = CURVE25519_KEY_SIZE, .set_secret = curve25519_set_secret, .generate_public_key = curve25519_generate_public_key, .compute_shared_secret = curve25519_compute_shared_secret, .max_size = curve25519_max_size, }; static int __init curve25519_mod_init(void) { if (boot_cpu_has(X86_FEATURE_BMI2) && boot_cpu_has(X86_FEATURE_ADX)) static_branch_enable(&curve25519_use_bmi2_adx); else return 0; return IS_REACHABLE(CONFIG_CRYPTO_KPP) ? crypto_register_kpp(&curve25519_alg) : 0; } static void __exit curve25519_mod_exit(void) { if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && static_branch_likely(&curve25519_use_bmi2_adx)) crypto_unregister_kpp(&curve25519_alg); } module_init(curve25519_mod_init); module_exit(curve25519_mod_exit); MODULE_ALIAS_CRYPTO("curve25519"); MODULE_ALIAS_CRYPTO("curve25519-x86"); MODULE_DESCRIPTION("Curve25519 algorithm, ADX optimized"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); |
| 7383 3842 7385 4530 3843 3847 4537 3842 7378 7375 7381 68 68 68 68 68 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> #include <trace/events/ipi.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 18 18 12 1 5 12 5 1 22 130 7 12 20 114 20 99 2 158 65 22 86 1 38 40 40 40 24 128 17 120 5 139 139 137 2 129 2 125 155 155 140 17 38 90 1 127 6 122 336 1 24 112 271 271 270 270 271 272 114 7 5 108 67 10 161 15 155 1 26 104 27 24 139 18 126 126 272 26 8 9 4 2 6 6 6 3 5 4 2 2 5 1 3 5 4 4 3 4 4 4 2 4 2 4 2 2 4 4 4 1 1 3 4 4 3 4 4 108 109 108 53 17 91 80 2 81 26 228 229 229 227 226 2 228 228 8 218 216 220 150 4 1 37 1 1 1 23 94 8 9 199 5 2 3 1 98 98 98 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Internet Control Message Protocol (ICMPv6) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on net/ipv4/icmp.c * * RFC 1885 */ /* * Changes: * * Andi Kleen : exception handling * Andi Kleen add rate limits. never reply to a icmp. * add more length checks and other fixes. * yoshfuji : ensure to sent parameter problem for * fragments. * YOSHIFUJI Hideaki @USAGI: added sysctl for icmp rate limit. * Randy Dunlap and * YOSHIFUJI Hideaki @USAGI: Per-interface statistics support * Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/netfilter.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/icmpv6.h> #include <net/ip.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> #include <net/ping.h> #include <net/protocol.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/seg6.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/inet_common.h> #include <net/dsfield.h> #include <net/l3mdev.h> #include <linux/uaccess.h> static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk); static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); struct net *net = dev_net_rcu(skb->dev); if (type == ICMPV6_PKT_TOOBIG) ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); if (!(type & ICMPV6_INFOMSG_MASK)) if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) ping_err(skb, offset, ntohl(info)); return 0; } static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; /* Called with BH disabled */ static struct sock *icmpv6_xmit_lock(struct net *net) { struct sock *sk; sk = this_cpu_read(ipv6_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an * outgoing ICMP6 packet. */ return NULL; } sock_net_set(sk, net); return sk; } static void icmpv6_xmit_unlock(struct sock *sk) { sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } /* * Figure out, may we reply to this packet with icmp error. * * We do not reply, if: * - it was icmp error message. * - it is truncated, so that it is known, that protocol is ICMPV6 * (i.e. in the middle of some exthdr) * * --ANK (980726) */ static bool is_ineligible(const struct sk_buff *skb) { int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; int len = skb->len - ptr; __u8 nexthdr = ipv6_hdr(skb)->nexthdr; __be16 frag_off; if (len < 0) return true; ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off); if (ptr < 0) return false; if (nexthdr == IPPROTO_ICMPV6) { u8 _type, *tp; tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); /* Based on RFC 8200, Section 4.5 Fragment Header, return * false if this is a fragment packet with no icmp header info. */ if (!tp && frag_off != 0) return false; else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; } static bool icmpv6_mask_allow(struct net *net, int type) { if (type > ICMPV6_MSG_MAX) return true; /* Limit if icmp type is set in ratemask. */ if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask)) return true; return false; } static bool icmpv6_global_allow(struct net *net, int type, bool *apply_ratelimit) { if (icmpv6_mask_allow(net, type)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } /* * Check the ICMP output rate limit */ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, struct flowi6 *fl6, bool apply_ratelimit) { struct net *net = sock_net(sk); struct dst_entry *dst; bool res = false; if (!apply_ratelimit) return true; /* * Look up the output route. * XXX: perhaps the expire for routing entries cloned by * this lookup should be more aggressive (not longer than timeout). */ dst = ip6_route_output(net, sk, fl6); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { res = true; } else { struct rt6_info *rt = dst_rt6_info(dst); int tmo = net->ipv6.sysctl.icmpv6_time; struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); rcu_read_lock(); peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr); res = inet_peer_xrlim_allow(peer, tmo); rcu_read_unlock(); } if (!res) __ICMP6_INC_STATS(net, ip6_dst_idev(dst), ICMP6_MIB_RATELIMITHOST); else icmp_global_consume(net); dst_release(dst); return res; } static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, struct flowi6 *fl6) { struct net *net = sock_net(sk); struct dst_entry *dst; bool res = false; dst = ip6_route_output(net, sk, fl6); if (!dst->error) { struct rt6_info *rt = dst_rt6_info(dst); struct in6_addr prefsrc; rt6_get_prefsrc(rt, &prefsrc); res = !ipv6_addr_any(&prefsrc); } dst_release(dst); return res; } /* * an inline helper for the "simple" if statement below * checks if parameter problem report is caused by an * unrecognized IPv6 option that has the Option Type * highest-order two bits set to 10 */ static bool opt_unrec(struct sk_buff *skb, __u32 offset) { u8 _optval, *op; offset += skb_network_offset(skb); op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval); if (!op) return true; return (*op & 0xC0) == 0x80; } void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; skb = skb_peek(&sk->sk_write_queue); if (!skb) return; icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); icmp6h->icmp6_cksum = 0; if (skb_queue_len(&sk->sk_write_queue) == 1) { skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, skb->csum); } else { __wsum tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); } tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, tmp_csum); } ip6_push_pending_frames(sk); } struct icmpv6_msg { struct sk_buff *skb; int offset; uint8_t type; }; static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct icmpv6_msg *msg = (struct icmpv6_msg *) from; struct sk_buff *org_skb = msg->skb; __wsum csum; csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (!(msg->type & ICMPV6_INFOMSG_MASK)) nf_ct_attach(skb, org_skb); return 0; } #if IS_ENABLED(CONFIG_IPV6_MIP6) static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); struct ipv6_destopt_hao *hao; int off; if (opt->dsthao) { off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); if (likely(off >= 0)) { hao = (struct ipv6_destopt_hao *) (skb_network_header(skb) + off); swap(iph->saddr, hao->addr); } } } #else static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, struct sock *sk, struct flowi6 *fl6) { struct dst_entry *dst, *dst2; struct flowi6 fl2; int err; err = ip6_dst_lookup(net, sk, &dst, fl6); if (err) return ERR_PTR(err); /* * We won't send icmp if the destination is known * anycast unless we need to treat anycast as unicast. */ if (!READ_ONCE(net->ipv6.sysctl.icmpv6_error_anycast_as_unicast) && ipv6_anycast_destination(dst, &fl6->daddr)) { net_dbg_ratelimited("icmp6_send: acast source\n"); dst_release(dst); return ERR_PTR(-EINVAL); } /* No need to clone since we're just using its address. */ dst2 = dst; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0); if (!IS_ERR(dst)) { if (dst != dst2) return dst; } else { if (PTR_ERR(dst) == -EPERM) dst = NULL; else return dst; } err = xfrm_decode_session_reverse(net, skb, flowi6_to_flowi(&fl2), AF_INET6); if (err) goto relookup_failed; err = ip6_dst_lookup(net, sk, &dst2, &fl2); if (err) goto relookup_failed; dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP); if (!IS_ERR(dst2)) { dst_release(dst); dst = dst2; } else { err = PTR_ERR(dst2); if (err == -EPERM) { dst_release(dst); return dst2; } else goto relookup_failed; } relookup_failed: if (dst) return dst; return ERR_PTR(err); } static struct net_device *icmp6_dev(const struct sk_buff *skb) { struct net_device *dev = skb->dev; /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so * get the real device index. Same is needed for replies to a link * local address on a device enslaved to an L3 master device */ if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), * and ip6_null_entry could be set to skb if no route is found. */ if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } return dev; } static int icmp6_iif(const struct sk_buff *skb) { return icmp6_dev(skb)->ifindex; } /* * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; bool apply_ratelimit = false; struct dst_entry *dst; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; struct ipcm6_cookie ipc6; int iif = 0; int addr_type = 0; int len; u32 mark; if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; if (!skb->dev) return; rcu_read_lock(); net = dev_net_rcu(skb->dev); mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules * i.e. RFC 1885 2.4(e) * Rule (e.1) is enforced by not using icmp6_send * in any code that processes icmp errors. */ addr_type = ipv6_addr_type(&hdr->daddr); if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) || ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr)) saddr = &hdr->daddr; /* * Dest addr check */ if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) { if (type != ICMPV6_PKT_TOOBIG && !(type == ICMPV6_PARAMPROB && code == ICMPV6_UNK_OPTION && (opt_unrec(skb, info)))) goto out; saddr = NULL; } addr_type = ipv6_addr_type(&hdr->saddr); /* * Source addr check */ if (__ipv6_addr_needs_scope_id(addr_type)) { iif = icmp6_iif(skb); } else { /* * The source device is used for looking up which routing table * to use for sending an ICMP error. */ iif = l3mdev_master_ifindex(skb->dev); } /* * Must not send error if the source does not uniquely * identify a single node (RFC2463 Section 2.4). * We check unspecified / multicast addresses here, * and anycast addresses will be checked later. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out; } /* * Never answer to a ICMP packet. */ if (is_ineligible(skb)) { net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out; } /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit */ if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type, &apply_ratelimit)) goto out_bh_enable; mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.daddr = hdr->saddr; if (force_saddr) saddr = force_saddr; if (saddr) { fl6.saddr = *saddr; } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) { /* select a more meaningful saddr from input if */ struct net_device *in_netdev; in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, &fl6.saddr); dev_put(in_netdev); } } fl6.flowi6_mark = mark; fl6.flowi6_oif = iif; fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; fl6.flowi6_uid = sock_net_uid(net, NULL); fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit)) goto out_unlock; tmp_hdr.icmp6_type = type; tmp_hdr.icmp6_code = code; tmp_hdr.icmp6_cksum = 0; tmp_hdr.icmp6_pointer = htonl(info); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); ipcm6_init_sk(&ipc6, sk); ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) goto out_unlock; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); msg.skb = skb; msg.offset = skb_network_offset(skb); msg.type = type; len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr)); if (len < 0) { net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out_dst_release; } idev = __in6_dev_get(skb->dev); if (ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); } out_dst_release: dst_release(dst); out_unlock: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); out: rcu_read_unlock(); } EXPORT_SYMBOL(icmp6_send); /* Slightly more convenient version of icmp6_send with drop reasons. */ void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos, enum skb_drop_reason reason) { icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb_reason(skb, reason); } /* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH * if sufficient data bytes are available * @nhs is the size of the tunnel header(s) : * Either an IPv4 header for SIT encap * an IPv4 header + GRE header for GRE encap */ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len) { struct in6_addr temp_saddr; struct rt6_info *rt; struct sk_buff *skb2; u32 info = 0; if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8)) return 1; /* RFC 4884 (partial) support for ICMP extensions */ if (data_len < 128 || (data_len & 7) || skb->len < data_len) data_len = 0; skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC); if (!skb2) return 1; skb_dst_drop(skb2); skb_pull(skb2, nhs); skb_reset_network_header(skb2); rt = rt6_lookup(dev_net_rcu(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, skb, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr); if (data_len) { /* RFC 4884 (partial) support : * insert 0 padding at the end, before the extensions */ __skb_push(skb2, nhs); skb_reset_network_header(skb2); memmove(skb2->data, skb2->data + nhs, data_len - nhs); memset(skb2->data + data_len - nhs, 0, nhs); /* RFC 4884 4.5 : Length is measured in 64-bit words, * and stored in reserved[0] */ info = (data_len/8) << 24; } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); kfree_skb(skb2); return 0; } EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach); static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = icmp6_hdr(skb); bool apply_ratelimit = false; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; struct dst_entry *dst; struct ipcm6_cookie ipc6; u32 mark = IP6_REPLY_MARK(net, skb->mark); SKB_DR(reason); bool acast; u8 type; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && net->ipv6.sysctl.icmpv6_echo_ignore_multicast) return reason; saddr = &ipv6_hdr(skb)->daddr; acast = ipv6_anycast_destination(skb_dst(skb), saddr); if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast) return reason; if (!ipv6_unicast_destination(skb) && !(net->ipv6.sysctl.anycast_src_echo_reply && acast)) saddr = NULL; if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) type = ICMPV6_EXT_ECHO_REPLY; else type = ICMPV6_ECHO_REPLY; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); tmp_hdr.icmp6_type = type; memset(&fl6, 0, sizeof(fl6)); if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES) fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; fl6.flowi6_oif = icmp6_iif(skb); fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); local_bh_disable(); sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) goto out; /* Check the ratelimit */ if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) || !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit)) goto out_dst_release; idev = __in6_dev_get(skb->dev); msg.skb = skb; msg.offset = 0; msg.type = type; ipcm6_init_sk(&ipc6, sk); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); ipc6.sockc.mark = mark; if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr)) goto out_dst_release; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); reason = SKB_CONSUMED; } out_dst_release: dst_release(dst); out: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); return reason; } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net_rcu(skb->dev); const struct inet6_protocol *ipprot; enum skb_drop_reason reason; int inner_offset; __be16 frag_off; u8 nexthdr; reason = pskb_may_pull_reason(skb, sizeof(struct ipv6hdr)); if (reason != SKB_NOT_DROPPED_YET) goto out; seg6_icmp_srh(skb, opt); nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { /* now skip over extension headers */ inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (inner_offset < 0) { SKB_DR_SET(reason, IPV6_BAD_EXTHDR); goto out; } } else { inner_offset = sizeof(struct ipv6hdr); } /* Checkin header including 8 bytes of inner protocol header. */ reason = pskb_may_pull_reason(skb, inner_offset + 8); if (reason != SKB_NOT_DROPPED_YET) goto out; /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed pmtu discovery. Corresponding argument (opt) to notifiers is already added. --ANK (980726) */ ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, opt, type, code, inner_offset, info); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); return SKB_CONSUMED; out: __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return reason; } /* * Handle icmp messages */ static int icmpv6_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct net *net = dev_net_rcu(skb->dev); struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; u8 type; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; } if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) goto drop_no_count; nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*hdr)); if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; } skb_set_network_header(skb, nh); } __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS); saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n", saddr, daddr); goto csum_error; } if (!pskb_pull(skb, sizeof(*hdr))) goto discard_it; hdr = icmp6_hdr(skb); type = hdr->icmp6_type; ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type); switch (type) { case ICMPV6_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all) reason = icmpv6_echo_reply(skb); break; case ICMPV6_EXT_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) reason = icmpv6_echo_reply(skb); break; case ICMPV6_ECHO_REPLY: case ICMPV6_EXT_ECHO_REPLY: ping_rcv(skb); return 0; case ICMPV6_PKT_TOOBIG: /* BUGGG_FUTURE: if packet contains rthdr, we cannot update standard destination cache. Seems, only "advanced" destination cache will allow to solve this problem --ANK (980726) */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto discard_it; hdr = icmp6_hdr(skb); /* to notify */ fallthrough; case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: reason = icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); break; case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: reason = ndisc_rcv(skb); break; case ICMPV6_MGM_QUERY: igmp6_event_query(skb); return 0; case ICMPV6_MGM_REPORT: igmp6_event_report(skb); return 0; case ICMPV6_MGM_REDUCTION: case ICMPV6_NI_QUERY: case ICMPV6_NI_REPLY: case ICMPV6_MLD2_REPORT: case ICMPV6_DHAAD_REQUEST: case ICMPV6_DHAAD_REPLY: case ICMPV6_MOBILE_PREFIX_SOL: case ICMPV6_MOBILE_PREFIX_ADV: break; default: /* informational */ if (type & ICMPV6_INFOMSG_MASK) break; net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n", saddr, daddr); /* * error of unknown type. * must pass to upper level */ reason = icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); } /* until the v6 path can be better sorted assume failure and * preserve the status quo behaviour for the rest of the paths to here */ if (reason) kfree_skb_reason(skb, reason); else consume_skb(skb); return 0; csum_error: reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS); discard_it: __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS); drop_no_count: kfree_skb_reason(skb, reason); return 0; } void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif) { memset(fl6, 0, sizeof(*fl6)); fl6->saddr = *saddr; fl6->daddr = *daddr; fl6->flowi6_proto = IPPROTO_ICMPV6; fl6->fl6_icmp_type = type; fl6->fl6_icmp_code = 0; fl6->flowi6_oif = oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } int __init icmpv6_init(void) { struct sock *sk; int err, i; for_each_possible_cpu(i) { err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, &init_net); if (err < 0) { pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); return err; } per_cpu(ipv6_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } err = -EAGAIN; if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) goto fail; err = inet6_register_icmp_sender(icmp6_send); if (err) goto sender_reg_err; return 0; sender_reg_err: inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); fail: pr_err("Failed to register ICMP6 protocol\n"); return err; } void icmpv6_cleanup(void) { inet6_unregister_icmp_sender(icmp6_send); inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); } static const struct icmp6_err { int err; int fatal; } tab_unreach[] = { { /* NOROUTE */ .err = ENETUNREACH, .fatal = 0, }, { /* ADM_PROHIBITED */ .err = EACCES, .fatal = 1, }, { /* Was NOT_NEIGHBOUR, now reserved */ .err = EHOSTUNREACH, .fatal = 0, }, { /* ADDR_UNREACH */ .err = EHOSTUNREACH, .fatal = 0, }, { /* PORT_UNREACH */ .err = ECONNREFUSED, .fatal = 1, }, { /* POLICY_FAIL */ .err = EACCES, .fatal = 1, }, { /* REJECT_ROUTE */ .err = EACCES, .fatal = 1, }, }; int icmpv6_err_convert(u8 type, u8 code, int *err) { int fatal = 0; *err = EPROTO; switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } break; case ICMPV6_PKT_TOOBIG: *err = EMSGSIZE; break; case ICMPV6_PARAMPROB: *err = EPROTO; fatal = 1; break; case ICMPV6_TIME_EXCEED: *err = EHOSTUNREACH; break; } return fatal; } EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL static struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "echo_ignore_all", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "echo_ignore_multicast", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "echo_ignore_anycast", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ratemask", .data = &init_net.ipv6.sysctl.icmpv6_ratemask_ptr, .maxlen = ICMPV6_MSG_MAX + 1, .mode = 0644, .proc_handler = proc_do_large_bitmap, }, { .procname = "error_anycast_as_unicast", .data = &init_net.ipv6.sysctl.icmpv6_error_anycast_as_unicast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_icmp_table_template, sizeof(ipv6_icmp_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.icmpv6_time; table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all; table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast; table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast; table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr; table[5].data = &net->ipv6.sysctl.icmpv6_error_anycast_as_unicast; } return table; } size_t ipv6_icmp_sysctl_table_size(void) { return ARRAY_SIZE(ipv6_icmp_table_template); } #endif |
| 7 7 7 12 7 7 7 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <linux/crc32c.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ __be32 s_head; /* blocknr of head of log, only uptodate * while the filesystem is clean */ /* 0x005C */ __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_fs_dev_wb_err: * * Records the errseq of the client fs's backing block device. */ errseq_t j_fs_dev_wb_err; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_transaction_overhead_buffers: * * Number of blocks each transaction needs for its own bookkeeping */ int j_transaction_overhead_buffers; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); /** * @j_bmap: * * Bmap function that should be used instead of the generic * VFS bmap function. */ int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* * We can support any known requested features iff the * superblock is not in version 1. Otherwise we fail to support any * extended sb features. */ static inline bool jbd2_format_support_feature(journal_t *j) { return j->j_superblock->s_header.h_blocktype != cpu_to_be32(JBD2_SUPERBLOCK_V1); } /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* Journal high priority write IO operation flags */ #define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on * clean and empty filesystem * logging area */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_handle(_gfp_flags) \ ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_inode(_gfp_flags) \ ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size); void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern void jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); void jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which * could be used to detect the client fs's metadata async write error. */ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); } static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { return jbd2_has_feature_csum2(journal) || jbd2_has_feature_csum3(journal); } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { return crc32c(crc, address, length); } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */ |
| 89 88 276 275 330 228 839 7 1573 698 214 427 1 1 4 11 273 33 280 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for inet_sock * * Authors: Many, reorganised here by * Arnaldo Carvalho de Melo <acme@mandriva.com> */ #ifndef _INET_SOCK_H #define _INET_SOCK_H #include <linux/bitops.h> #include <linux/string.h> #include <linux/types.h> #include <linux/jhash.h> #include <linux/netdevice.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/sock.h> #include <net/request_sock.h> #include <net/netns/hash.h> #include <net/tcp_states.h> #include <net/l3mdev.h> /** struct ip_options - IP Options * * @faddr - Saved first hop address * @nexthop - Saved nexthop address in LSRR and SSRR * @is_strictroute - Strict source route * @srr_is_hit - Packet destination addr was our one * @is_changed - IP checksum more not valid * @rr_needaddr - Need to record addr of outgoing dev * @ts_needtime - Need to record timestamp * @ts_needaddr - Need to record addr of outgoing dev */ struct ip_options { __be32 faddr; __be32 nexthop; unsigned char optlen; unsigned char srr; unsigned char rr; unsigned char ts; unsigned char is_strictroute:1, srr_is_hit:1, is_changed:1, rr_needaddr:1, ts_needtime:1, ts_needaddr:1; unsigned char router_alert; unsigned char cipso; unsigned char __pad2; unsigned char __data[]; }; struct ip_options_rcu { struct rcu_head rcu; struct ip_options opt; }; struct ip_options_data { struct ip_options_rcu opt; char data[40]; }; struct inet_request_sock { struct request_sock req; #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_rmt_addr req.__req_common.skc_daddr #define ir_num req.__req_common.skc_num #define ir_rmt_port req.__req_common.skc_dport #define ir_v6_rmt_addr req.__req_common.skc_v6_daddr #define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr #define ir_iif req.__req_common.skc_bound_dev_if #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state #define ireq_family req.__req_common.skc_family u16 snd_wscale : 4, rcv_wscale : 4, tstamp_ok : 1, sack_ok : 1, wscale_ok : 1, ecn_ok : 1, acked : 1, no_srccheck: 1, smc_ok : 1; u32 ir_mark; union { struct ip_options_rcu __rcu *ireq_opt; #if IS_ENABLED(CONFIG_IPV6) struct { struct ipv6_txoptions *ipv6_opt; struct sk_buff *pktopts; }; #endif }; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) { return (struct inet_request_sock *)sk; } static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { u32 mark = READ_ONCE(sk->sk_mark); if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; return mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!bound_dev_if && READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept)) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif return bound_dev_if; } static inline int inet_sk_bound_l3mdev(const struct sock *sk) { #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept)) return l3mdev_master_ifindex_by_index(net, sk->sk_bound_dev_if); #endif return 0; } static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, int dif, int sdif) { if (!bound_dev_if) return !sdif || l3mdev_accept; return bound_dev_if == dif || bound_dev_if == sdif; } static inline bool inet_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } struct inet_cork { unsigned int flags; __be32 addr; struct ip_options *opt; unsigned int fragsize; int length; /* Total length of all frames */ struct dst_entry *dst; u8 tx_flags; __u8 ttl; __s16 tos; u32 priority; __u16 gso_size; u32 ts_opt_id; u64 transmit_time; u32 mark; }; struct inet_cork_full { struct inet_cork base; struct flowi fl; }; struct ip_mc_socklist; struct ipv6_pinfo; struct rtable; /** struct inet_sock - representation of INET sockets * * @sk - ancestor class * @pinet6 - pointer to IPv6 control block * @inet_daddr - Foreign IPv4 addr * @inet_rcv_saddr - Bound local IPv4 addr * @inet_dport - Destination port * @inet_num - Local port * @inet_flags - various atomic flags * @inet_saddr - Sending source * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL * @uc_index - Unicast outgoing device index * @mc_index - Multicast device index * @mc_list - Group array * @cork - info to build ip hdr on each ip frag while socket is corked */ struct inet_sock { /* sk and pinet6 has to be the first two members of inet_sock */ struct sock sk; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ #define inet_daddr sk.__sk_common.skc_daddr #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport #define inet_num sk.__sk_common.skc_num unsigned long inet_flags; __be32 inet_saddr; __s16 uc_ttl; __be16 inet_sport; struct ip_options_rcu __rcu *inet_opt; atomic_t inet_id; __u8 tos; __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; __u8 rcv_tos; __u8 convert_csum; int uc_index; int mc_index; __be32 mc_addr; u32 local_port_range; /* high << 16 | low */ struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ #define IPCORK_TS_OPT_ID 2 /* ts_opt_id field is valid, overriding sk_tskey */ enum { INET_FLAGS_PKTINFO = 0, INET_FLAGS_TTL = 1, INET_FLAGS_TOS = 2, INET_FLAGS_RECVOPTS = 3, INET_FLAGS_RETOPTS = 4, INET_FLAGS_PASSSEC = 5, INET_FLAGS_ORIGDSTADDR = 6, INET_FLAGS_CHECKSUM = 7, INET_FLAGS_RECVFRAGSIZE = 8, INET_FLAGS_RECVERR = 9, INET_FLAGS_RECVERR_RFC4884 = 10, INET_FLAGS_FREEBIND = 11, INET_FLAGS_HDRINCL = 12, INET_FLAGS_MC_LOOP = 13, INET_FLAGS_MC_ALL = 14, INET_FLAGS_TRANSPARENT = 15, INET_FLAGS_IS_ICSK = 16, INET_FLAGS_NODEFRAG = 17, INET_FLAGS_BIND_ADDRESS_NO_PORT = 18, INET_FLAGS_DEFER_CONNECT = 19, INET_FLAGS_MC6_LOOP = 20, INET_FLAGS_RECVERR6_RFC4884 = 21, INET_FLAGS_MC6_ALL = 22, INET_FLAGS_AUTOFLOWLABEL_SET = 23, INET_FLAGS_AUTOFLOWLABEL = 24, INET_FLAGS_DONTFRAG = 25, INET_FLAGS_RECVERR6 = 26, INET_FLAGS_REPFLOW = 27, INET_FLAGS_RTALERT_ISOLATE = 28, INET_FLAGS_SNDFLOW = 29, INET_FLAGS_RTALERT = 30, }; /* cmsg flags for inet */ #define IP_CMSG_PKTINFO BIT(INET_FLAGS_PKTINFO) #define IP_CMSG_TTL BIT(INET_FLAGS_TTL) #define IP_CMSG_TOS BIT(INET_FLAGS_TOS) #define IP_CMSG_RECVOPTS BIT(INET_FLAGS_RECVOPTS) #define IP_CMSG_RETOPTS BIT(INET_FLAGS_RETOPTS) #define IP_CMSG_PASSSEC BIT(INET_FLAGS_PASSSEC) #define IP_CMSG_ORIGDSTADDR BIT(INET_FLAGS_ORIGDSTADDR) #define IP_CMSG_CHECKSUM BIT(INET_FLAGS_CHECKSUM) #define IP_CMSG_RECVFRAGSIZE BIT(INET_FLAGS_RECVFRAGSIZE) #define IP_CMSG_ALL (IP_CMSG_PKTINFO | IP_CMSG_TTL | \ IP_CMSG_TOS | IP_CMSG_RECVOPTS | \ IP_CMSG_RETOPTS | IP_CMSG_PASSSEC | \ IP_CMSG_ORIGDSTADDR | IP_CMSG_CHECKSUM | \ IP_CMSG_RECVFRAGSIZE) static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) { return READ_ONCE(inet->inet_flags) & IP_CMSG_ALL; } static inline dscp_t inet_sk_dscp(const struct inet_sock *inet) { return inet_dsfield_to_dscp(READ_ONCE(inet->tos)); } #define inet_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_set_bit(nr, sk) \ set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_clear_bit(nr, sk) \ clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket * * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ static inline struct sock *sk_to_full_sk(struct sock *sk) { #ifdef CONFIG_INET if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT) sk = NULL; #endif return sk; } /* sk_to_full_sk() variant with a const argument */ static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) { #ifdef CONFIG_INET if (sk && READ_ONCE(sk->sk_state) == TCP_NEW_SYN_RECV) sk = ((const struct request_sock *)sk)->rsk_listener; if (sk && READ_ONCE(sk->sk_state) == TCP_TIME_WAIT) sk = NULL; #endif return sk; } static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) { return sk_to_full_sk(skb->sk); } #define inet_sk(ptr) container_of_const(ptr, struct inet_sock, sk) static inline void __inet_sk_copy_descendant(struct sock *sk_to, const struct sock *sk_from, const int ancestor_size) { memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } int inet_sk_rebuild_header(struct sock *sk); /** * inet_sk_state_load - read sk->sk_state for lockless contexts * @sk: socket pointer * * Paired with inet_sk_state_store(). Used in places we don't hold socket lock: * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... */ static inline int inet_sk_state_load(const struct sock *sk) { /* state change might impact lockless readers. */ return smp_load_acquire(&sk->sk_state); } /** * inet_sk_state_store - update sk->sk_state * @sk: socket pointer * @newstate: new state * * Paired with inet_sk_state_load(). Should be used in contexts where * state change might impact lockless readers. */ void inet_sk_state_store(struct sock *sk, int newstate); void inet_sk_set_state(struct sock *sk, int state); static inline unsigned int __inet_ehashfn(const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport, u32 initval) { return jhash_3words((__force __u32) laddr, (__force __u32) faddr, ((__u32) lport) << 16 | (__force __u32)fport, initval); } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; if (inet_test_bit(TRANSPARENT, sk) || inet_test_bit(HDRINCL, sk)) flags |= FLOWI_FLAG_ANYSRC; return flags; } static inline void inet_inc_convert_csum(struct sock *sk) { inet_sk(sk)->convert_csum++; } static inline void inet_dec_convert_csum(struct sock *sk) { if (inet_sk(sk)->convert_csum > 0) inet_sk(sk)->convert_csum--; } static inline bool inet_get_convert_csum(struct sock *sk) { return !!inet_sk(sk)->convert_csum; } static inline bool inet_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } static inline bool inet_addr_valid_or_nonlocal(struct net *net, struct inet_sock *inet, __be32 addr, int addr_type) { return inet_can_nonlocal_bind(net, inet) || addr == htonl(INADDR_ANY) || addr_type == RTN_LOCAL || addr_type == RTN_MULTICAST || addr_type == RTN_BROADCAST; } #endif /* _INET_SOCK_H */ |
| 507 506 506 507 | 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/dax.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. * * Note that these are only respected if collapse was initiated by khugepaged. */ unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct khugepaged_mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t defrag_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_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR_RW(max_ptes_none); static ssize_t max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR_RW(max_ptes_swap); static ssize_t max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = KMEM_CACHE(khugepaged_mm_slot, 0); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } static bool hugepage_pmd_enabled(void) { /* * We cover the anon, shmem and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. * Shmem pmd-sized hugepages are also determined by its pmd-size control, * except when the global shmem_huge is set to SHMEM_HUGE_DENY. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_always)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_madvise)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled()) return true; return false; } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we return all * pagetables will be destroyed) until khugepaged has finished * working on the pagetables under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount = folio_mapcount(folio); if (!folio_test_anon(folio) || folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); if (folio_test_private(folio)) expected_refcount++; return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_maybe_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before folio_isolate_lru because the * folio can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static inline int check_pmd_state(pmd_t *pmd) { pmd_t pmde = pmdp_get_lockless(pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; return check_pmd_state(*pmd); } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { /* * Here the ptl is only used to check pte_same() in * do_swap_page(), so readonly version is enough. */ pte = pte_offset_map_ro_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. */ if (folio_maybe_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * @install_pmd: If a huge PMD should be installed * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) goto abort; /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) { spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) { flush_tlb_mm(mm); goto unlock; } } } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); pte_unmap_unlock(start_pte, ptl); if (ptl != pml) spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } unlock: if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool success = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); /* * The lock of new_folio is still held, we will be blocked in * the page fault path, which prevents the pte entries from * being set again. So even though the old empty PTE page may be * concurrently freed and a new PTE page is filled into the pmd * entry, it is still empty and can be removed. * * So here we only need to recheck if the state of pmd entry * still meets our requirements, rather than checking pmd_same() * like elsewhere. */ if (check_pmd_state(pmd) != SCAN_SUCCEED) goto drop_pml; ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); success = true; } if (ptl != pml) spin_unlock(ptl); drop_pml: spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (success) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; mapping_set_update(&xas, mapping); __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto rollback; } } while (1); for (index = start; index < end;) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } } nr_none++; index++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control 2 + nr_pages references to the folio: * - we hold a pin on it; * - nr_pages reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); index += folio_nr_pages(folio); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure i_writecount is up to date and the update to nr_thps * is visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { int i, nr_pages = folio_nr_pages(folio); while (index < folio->index) { clear_highpage(dst); index++; dst++; } for (i = 0; i < nr_pages; i++) { if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 2 + folio_nr_pages(folio)); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); mm = slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (hpage_collapse_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (hugepage_pmd_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; if (!hugepage_pmd_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 124 11 18 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #include <net/inet_common.h> enum linux_mptcp_mib_field { MPTCP_MIB_NUM = 0, MPTCP_MIB_MPCAPABLEPASSIVE, /* Received SYN with MP_CAPABLE */ MPTCP_MIB_MPCAPABLEACTIVE, /* Sent SYN with MP_CAPABLE */ MPTCP_MIB_MPCAPABLEACTIVEACK, /* Received SYN/ACK with MP_CAPABLE */ MPTCP_MIB_MPCAPABLEPASSIVEACK, /* Received third ACK with MP_CAPABLE */ MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK,/* Server-side fallback during 3-way handshake */ MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */ MPTCP_MIB_MPCAPABLEACTIVEDROP, /* Client-side fallback due to a MPC drop */ MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */ MPTCP_MIB_MPCAPABLEENDPATTEMPT, /* Prohibited MPC to port-based endp */ MPTCP_MIB_TOKENFALLBACKINIT, /* Could not init/allocate token */ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ MPTCP_MIB_JOINREJECTED, /* The PM rejected the JOIN request */ MPTCP_MIB_JOINSYNTX, /* Sending a SYN + MP_JOIN */ MPTCP_MIB_JOINSYNTXCREATSKERR, /* Not able to create a socket when sending a SYN + MP_JOIN */ MPTCP_MIB_JOINSYNTXBINDERR, /* Not able to bind() the address when sending a SYN + MP_JOIN */ MPTCP_MIB_JOINSYNTXCONNECTERR, /* Not able to connect() when sending a SYN + MP_JOIN */ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ MPTCP_MIB_DSSCORRUPTIONFALLBACK,/* DSS corruption detected, fallback */ MPTCP_MIB_DSSCORRUPTIONRESET, /* DSS corruption detected, MPJ subflow reset */ MPTCP_MIB_INFINITEMAPTX, /* Sent an infinite mapping */ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ MPTCP_MIB_DSSTCPMISMATCH, /* DSS-mapping did not map with TCP's sequence numbers */ MPTCP_MIB_DATACSUMERR, /* The data checksum fail */ MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */ MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */ MPTCP_MIB_OFOMERGE, /* Segments merged in OoO queue */ MPTCP_MIB_NODSSWINDOW, /* Segments not in MPTCP windows */ MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */ MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ MPTCP_MIB_ADDADDRTX, /* Sent ADD_ADDR with echo-flag=0 */ MPTCP_MIB_ADDADDRTXDROP, /* ADD_ADDR with echo-flag=0 not send due to * resource exhaustion */ MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ MPTCP_MIB_ECHOADDTX, /* Send ADD_ADDR with echo-flag=1 */ MPTCP_MIB_ECHOADDTXDROP, /* ADD_ADDR with echo-flag=1 not send due * to resource exhaustion */ MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */ MPTCP_MIB_ADDADDRDROP, /* Dropped incoming ADD_ADDR */ MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */ MPTCP_MIB_JOINPORTSYNACKRX, /* Received a SYNACK MP_JOIN with a different port-number */ MPTCP_MIB_JOINPORTACKRX, /* Received an ACK MP_JOIN with a different port-number */ MPTCP_MIB_MISMATCHPORTSYNRX, /* Received a SYN MP_JOIN with a mismatched port-number */ MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */ MPTCP_MIB_RMADDR, /* Received RM_ADDR */ MPTCP_MIB_RMADDRDROP, /* Dropped incoming RM_ADDR */ MPTCP_MIB_RMADDRTX, /* Sent RM_ADDR */ MPTCP_MIB_RMADDRTXDROP, /* RM_ADDR not sent due to resource exhaustion */ MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ MPTCP_MIB_MPFAILTX, /* Transmit a MP_FAIL */ MPTCP_MIB_MPFAILRX, /* Received a MP_FAIL */ MPTCP_MIB_MPFASTCLOSETX, /* Transmit a MP_FASTCLOSE */ MPTCP_MIB_MPFASTCLOSERX, /* Received a MP_FASTCLOSE */ MPTCP_MIB_MPRSTTX, /* Transmit a MP_RST */ MPTCP_MIB_MPRSTRX, /* Received a MP_RST */ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ MPTCP_MIB_SUBFLOWSTALE, /* Subflows entered 'stale' status */ MPTCP_MIB_SUBFLOWRECOVER, /* Subflows returned to active status after being stale */ MPTCP_MIB_SNDWNDSHARED, /* Subflow snd wnd is overridden by msk's one */ MPTCP_MIB_RCVWNDSHARED, /* Subflow rcv wnd is overridden by msk's one */ MPTCP_MIB_RCVWNDCONFLICTUPDATE, /* subflow rcv wnd is overridden by msk's one due to * conflict with another subflow while updating msk rcv wnd */ MPTCP_MIB_RCVWNDCONFLICT, /* Conflict with while updating msk rcv wnd */ MPTCP_MIB_CURRESTAB, /* Current established MPTCP connections */ MPTCP_MIB_BLACKHOLE, /* A blackhole has been detected */ __MPTCP_MIB_MAX }; #define LINUX_MIB_MPTCP_MAX __MPTCP_MIB_MAX struct mptcp_mib { unsigned long mibs[LINUX_MIB_MPTCP_MAX]; }; static inline void MPTCP_ADD_STATS(struct net *net, enum linux_mptcp_mib_field field, int val) { if (likely(net->mib.mptcp_statistics)) SNMP_ADD_STATS(net->mib.mptcp_statistics, field, val); } static inline void MPTCP_INC_STATS(struct net *net, enum linux_mptcp_mib_field field) { if (likely(net->mib.mptcp_statistics)) SNMP_INC_STATS(net->mib.mptcp_statistics, field); } static inline void __MPTCP_INC_STATS(struct net *net, enum linux_mptcp_mib_field field) { if (likely(net->mib.mptcp_statistics)) __SNMP_INC_STATS(net->mib.mptcp_statistics, field); } static inline void MPTCP_DEC_STATS(struct net *net, enum linux_mptcp_mib_field field) { if (likely(net->mib.mptcp_statistics)) SNMP_DEC_STATS(net->mib.mptcp_statistics, field); } bool mptcp_mib_alloc(struct net *net); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_LEGACY_H #define __X86_KERNEL_FPU_LEGACY_H #include <asm/fpu/types.h> extern unsigned int mxcsr_feature_mask; static inline void ldmxcsr(u32 mxcsr) { asm volatile("ldmxcsr %0" :: "m" (mxcsr)); } /* * Returns 0 on success or the trap number when the operation raises an * exception. */ #define user_insn(insn, output, input...) \ ({ \ int err; \ \ might_fault(); \ \ asm volatile(ASM_STAC "\n" \ "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn_err(insn, output, input...) \ ({ \ int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FPU_RESTORE) \ : output : input) static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); } static inline void fxrstor(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int fxrstor_safe(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void frstor(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int frstor_safe(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int frstor_from_user_sigframe(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); } #endif |
| 128 128 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | /* * Copyright (c) 2004 Topspin Communications. 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. */ #ifndef _CORE_PRIV_H #define _CORE_PRIV_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/cgroup_rdma.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <rdma/ib_verbs.h> #include <rdma/opa_addr.h> #include <rdma/ib_mad.h> #include <rdma/restrack.h> #include "mad_priv.h" #include "restrack.h" /* Total number of ports combined across all struct ib_devices's */ #define RDMA_MAX_PORTS 8192 struct pkey_index_qp_list { struct list_head pkey_index_list; u16 pkey_index; /* Lock to hold while iterating the qp_list. */ spinlock_t qp_list_lock; struct list_head qp_list; }; /** * struct rdma_dev_net - rdma net namespace metadata for a net * @nl_sock: Pointer to netlink socket * @net: Pointer to owner net namespace * @id: xarray id to identify the net namespace. */ struct rdma_dev_net { struct sock *nl_sock; possible_net_t net; u32 id; }; extern const struct attribute_group ib_dev_attr_group; extern bool ib_devices_shared_netns; extern unsigned int rdma_dev_net_id; static inline struct rdma_dev_net *rdma_net_to_dev_net(struct net *net) { return net_generic(net, rdma_dev_net_id); } int ib_device_rename(struct ib_device *ibdev, const char *name); int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim); typedef void (*roce_netdev_callback)(struct ib_device *device, u32 port, struct net_device *idev, void *cookie); typedef bool (*roce_netdev_filter)(struct ib_device *device, u32 port, struct net_device *idev, void *cookie); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); void ib_enum_roce_netdev(struct ib_device *ib_dev, roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie); void ib_enum_all_roce_netdevs(roce_netdev_filter filter, void *filter_cookie, roce_netdev_callback cb, void *cookie); typedef int (*nldev_callback)(struct ib_device *device, struct sk_buff *skb, struct netlink_callback *cb, unsigned int idx); int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb, struct netlink_callback *cb); struct ib_client_nl_info { struct sk_buff *nl_msg; struct device *cdev; u32 port; u64 abi; }; int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, struct ib_client_nl_info *res); enum ib_cache_gid_default_mode { IB_CACHE_GID_DEFAULT_MODE_SET, IB_CACHE_GID_DEFAULT_MODE_DELETE }; int ib_cache_gid_parse_type_str(const char *buf); const char *ib_cache_gid_type_str(enum ib_gid_type gid_type); 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); int ib_cache_gid_add(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr); int ib_cache_gid_del(struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *attr); int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev); int roce_gid_mgmt_init(void); void roce_gid_mgmt_cleanup(void); unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port); int ib_cache_setup_one(struct ib_device *device); void ib_cache_cleanup_one(struct ib_device *device); void ib_cache_release_one(struct ib_device *device); void ib_dispatch_event_clients(struct ib_event *event); #ifdef CONFIG_CGROUP_RDMA void ib_device_register_rdmacg(struct ib_device *device); void ib_device_unregister_rdmacg(struct ib_device *device); int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index); void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index); #else static inline void ib_device_register_rdmacg(struct ib_device *device) { } static inline void ib_device_unregister_rdmacg(struct ib_device *device) { } static inline int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index) { return 0; } static inline void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj, struct ib_device *device, enum rdmacg_resource_type resource_index) { } #endif static inline bool rdma_is_upper_dev_rcu(struct net_device *dev, struct net_device *upper) { return netdev_has_upper_dev_all_rcu(dev, upper); } int addr_init(void); void addr_cleanup(void); int ib_mad_init(void); void ib_mad_cleanup(void); int ib_sa_init(void); void ib_sa_cleanup(void); void rdma_nl_init(void); void rdma_nl_exit(void); int ib_nl_handle_resolve_resp(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); int ib_nl_handle_set_timeout(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); int ib_nl_handle_ip_res_resp(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); void ib_get_cached_subnet_prefix(struct ib_device *device, u32 port_num, u64 *sn_pfx); #ifdef CONFIG_SECURITY_INFINIBAND void ib_security_release_port_pkey_list(struct ib_device *device); void ib_security_cache_change(struct ib_device *device, u32 port_num, u64 subnet_prefix); int ib_security_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev); void ib_destroy_qp_security_begin(struct ib_qp_security *sec); void ib_destroy_qp_security_abort(struct ib_qp_security *sec); void ib_destroy_qp_security_end(struct ib_qp_security *sec); int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev); void ib_close_shared_qp_security(struct ib_qp_security *sec); int ib_mad_agent_security_setup(struct ib_mad_agent *agent, enum ib_qp_type qp_type); void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent); int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index); void ib_mad_agent_security_change(void); #else static inline void ib_security_release_port_pkey_list(struct ib_device *device) { } static inline void ib_security_cache_change(struct ib_device *device, u32 port_num, u64 subnet_prefix) { } static inline int ib_security_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata) { return qp->device->ops.modify_qp(qp->real_qp, qp_attr, qp_attr_mask, udata); } static inline int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) { return 0; } static inline void ib_destroy_qp_security_begin(struct ib_qp_security *sec) { } static inline void ib_destroy_qp_security_abort(struct ib_qp_security *sec) { } static inline void ib_destroy_qp_security_end(struct ib_qp_security *sec) { } static inline int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev) { return 0; } static inline void ib_close_shared_qp_security(struct ib_qp_security *sec) { } static inline int ib_mad_agent_security_setup(struct ib_mad_agent *agent, enum ib_qp_type qp_type) { return 0; } static inline void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent) { } static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index) { return 0; } static inline void ib_mad_agent_security_change(void) { } #endif struct ib_device *ib_device_get_by_index(const struct net *net, u32 index); /* RDMA device netlink */ void nldev_init(void); void nldev_exit(void); struct ib_qp *ib_create_qp_user(struct ib_device *dev, struct ib_pd *pd, struct ib_qp_init_attr *attr, struct ib_udata *udata, struct ib_uqp_object *uobj, const char *caller); void ib_qp_usecnt_inc(struct ib_qp *qp); void ib_qp_usecnt_dec(struct ib_qp *qp); struct rdma_dev_addr; int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, const union ib_gid *dgid, u8 *dmac, const struct ib_gid_attr *sgid_attr, int *hoplimit); void rdma_copy_src_l2_addr(struct rdma_dev_addr *dev_addr, const struct net_device *dev); struct sa_path_rec; int roce_resolve_route_from_path(struct sa_path_rec *rec, const struct ib_gid_attr *attr); struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr); void ib_free_port_attrs(struct ib_core_device *coredev); int ib_setup_port_attrs(struct ib_core_device *coredev); struct rdma_hw_stats *ib_get_hw_stats_port(struct ib_device *ibdev, u32 port_num); void ib_device_release_hw_stats(struct hw_stats_device_data *data); int ib_setup_device_attrs(struct ib_device *ibdev); int rdma_compatdev_set(u8 enable); int ib_port_register_client_groups(struct ib_device *ibdev, u32 port_num, const struct attribute_group **groups); void ib_port_unregister_client_groups(struct ib_device *ibdev, u32 port_num, const struct attribute_group **groups); int ib_device_set_netns_put(struct sk_buff *skb, struct ib_device *dev, u32 ns_fd); int rdma_nl_net_init(struct rdma_dev_net *rnet); void rdma_nl_net_exit(struct rdma_dev_net *rnet); struct rdma_umap_priv { struct vm_area_struct *vma; struct list_head list; struct rdma_user_mmap_entry *entry; }; void rdma_umap_priv_init(struct rdma_umap_priv *priv, struct vm_area_struct *vma, struct rdma_user_mmap_entry *entry); void ib_cq_pool_cleanup(struct ib_device *dev); bool rdma_nl_get_privileged_qkey(void); #endif /* _CORE_PRIV_H */ |
| 9 8 1 1 1 8 8 2 10 | 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 | // SPDX-License-Identifier: GPL-2.0 /* ATM ioctl handling */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ /* 2003 John Levon <levon@movementarian.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ #include <linux/module.h> #include <linux/kmod.h> #include <linux/net.h> /* struct socket, struct proto_ops */ #include <linux/atm.h> /* ATM stuff */ #include <linux/atmdev.h> #include <linux/atmclip.h> /* CLIP_*ENCAP */ #include <linux/atmarp.h> /* manifest constants */ #include <linux/capability.h> #include <linux/sonet.h> /* for ioctls */ #include <linux/atmsvc.h> #include <linux/atmmpc.h> #include <net/atmclip.h> #include <linux/atmlec.h> #include <linux/mutex.h> #include <asm/ioctls.h> #include <net/compat.h> #include "resources.h" #include "signaling.h" /* for WAITING and sigd_attach */ #include "common.h" static DEFINE_MUTEX(ioctl_mutex); static LIST_HEAD(ioctl_list); void register_atm_ioctl(struct atm_ioctl *ioctl) { mutex_lock(&ioctl_mutex); list_add_tail(&ioctl->list, &ioctl_list); mutex_unlock(&ioctl_mutex); } EXPORT_SYMBOL(register_atm_ioctl); void deregister_atm_ioctl(struct atm_ioctl *ioctl) { mutex_lock(&ioctl_mutex); list_del(&ioctl->list); mutex_unlock(&ioctl_mutex); } EXPORT_SYMBOL(deregister_atm_ioctl); static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg, int compat) { struct sock *sk = sock->sk; struct atm_vcc *vcc; int error; struct list_head *pos; void __user *argp = (void __user *)arg; void __user *buf; int __user *len; vcc = ATM_SD(sock); switch (cmd) { case SIOCOUTQ: if (sock->state != SS_CONNECTED || !test_bit(ATM_VF_READY, &vcc->flags)) { error = -EINVAL; goto done; } error = put_user(sk->sk_sndbuf - sk_wmem_alloc_get(sk), (int __user *)argp); goto done; case SIOCINQ: { struct sk_buff *skb; int amount; if (sock->state != SS_CONNECTED) { error = -EINVAL; goto done; } spin_lock_irq(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; spin_unlock_irq(&sk->sk_receive_queue.lock); error = put_user(amount, (int __user *)argp); goto done; } case ATM_SETSC: net_warn_ratelimited("ATM_SETSC is obsolete; used by %s:%d\n", current->comm, task_pid_nr(current)); error = 0; goto done; case ATMSIGD_CTRL: if (!capable(CAP_NET_ADMIN)) { error = -EPERM; goto done; } /* * The user/kernel protocol for exchanging signalling * info uses kernel pointers as opaque references, * so the holder of the file descriptor can scribble * on the kernel... so we should make sure that we * have the same privileges that /proc/kcore needs */ if (!capable(CAP_SYS_RAWIO)) { error = -EPERM; goto done; } #ifdef CONFIG_COMPAT /* WTF? I don't even want to _think_ about making this work for 32-bit userspace. TBH I don't really want to think about it at all. dwmw2. */ if (compat) { net_warn_ratelimited("32-bit task cannot be atmsigd\n"); error = -EINVAL; goto done; } #endif error = sigd_attach(vcc); if (!error) sock->state = SS_CONNECTED; goto done; case ATM_SETBACKEND: case ATM_NEWBACKENDIF: { atm_backend_t backend; error = get_user(backend, (atm_backend_t __user *)argp); if (error) goto done; switch (backend) { case ATM_BACKEND_PPP: request_module("pppoatm"); break; case ATM_BACKEND_BR2684: request_module("br2684"); break; } break; } case ATMMPC_CTRL: case ATMMPC_DATA: request_module("mpoa"); break; case ATMARPD_CTRL: request_module("clip"); break; case ATMLEC_CTRL: request_module("lec"); break; } error = -ENOIOCTLCMD; mutex_lock(&ioctl_mutex); list_for_each(pos, &ioctl_list) { struct atm_ioctl *ic = list_entry(pos, struct atm_ioctl, list); if (try_module_get(ic->owner)) { error = ic->ioctl(sock, cmd, arg); module_put(ic->owner); if (error != -ENOIOCTLCMD) break; } } mutex_unlock(&ioctl_mutex); if (error != -ENOIOCTLCMD) goto done; if (cmd == ATM_GETNAMES) { if (IS_ENABLED(CONFIG_COMPAT) && compat) { #ifdef CONFIG_COMPAT struct compat_atm_iobuf __user *ciobuf = argp; compat_uptr_t cbuf; len = &ciobuf->length; if (get_user(cbuf, &ciobuf->buffer)) return -EFAULT; buf = compat_ptr(cbuf); #endif } else { struct atm_iobuf __user *iobuf = argp; len = &iobuf->length; if (get_user(buf, &iobuf->buffer)) return -EFAULT; } error = atm_getnames(buf, len); } else { int number; if (IS_ENABLED(CONFIG_COMPAT) && compat) { #ifdef CONFIG_COMPAT struct compat_atmif_sioc __user *csioc = argp; compat_uptr_t carg; len = &csioc->length; if (get_user(carg, &csioc->arg)) return -EFAULT; buf = compat_ptr(carg); if (get_user(number, &csioc->number)) return -EFAULT; #endif } else { struct atmif_sioc __user *sioc = argp; len = &sioc->length; if (get_user(buf, &sioc->arg)) return -EFAULT; if (get_user(number, &sioc->number)) return -EFAULT; } error = atm_dev_ioctl(cmd, buf, len, number, compat); } done: return error; } int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return do_vcc_ioctl(sock, cmd, arg, 0); } #ifdef CONFIG_COMPAT /* * FIXME: * The compat_ioctl handling is duplicated, using both these conversion * routines and the compat argument to the actual handlers. Both * versions are somewhat incomplete and should be merged, e.g. by * moving the ioctl number translation into the actual handlers and * killing the conversion code. * * -arnd, November 2009 */ #define ATM_GETLINKRATE32 _IOW('a', ATMIOC_ITF+1, struct compat_atmif_sioc) #define ATM_GETNAMES32 _IOW('a', ATMIOC_ITF+3, struct compat_atm_iobuf) #define ATM_GETTYPE32 _IOW('a', ATMIOC_ITF+4, struct compat_atmif_sioc) #define ATM_GETESI32 _IOW('a', ATMIOC_ITF+5, struct compat_atmif_sioc) #define ATM_GETADDR32 _IOW('a', ATMIOC_ITF+6, struct compat_atmif_sioc) #define ATM_RSTADDR32 _IOW('a', ATMIOC_ITF+7, struct compat_atmif_sioc) #define ATM_ADDADDR32 _IOW('a', ATMIOC_ITF+8, struct compat_atmif_sioc) #define ATM_DELADDR32 _IOW('a', ATMIOC_ITF+9, struct compat_atmif_sioc) #define ATM_GETCIRANGE32 _IOW('a', ATMIOC_ITF+10, struct compat_atmif_sioc) #define ATM_SETCIRANGE32 _IOW('a', ATMIOC_ITF+11, struct compat_atmif_sioc) #define ATM_SETESI32 _IOW('a', ATMIOC_ITF+12, struct compat_atmif_sioc) #define ATM_SETESIF32 _IOW('a', ATMIOC_ITF+13, struct compat_atmif_sioc) #define ATM_GETSTAT32 _IOW('a', ATMIOC_SARCOM+0, struct compat_atmif_sioc) #define ATM_GETSTATZ32 _IOW('a', ATMIOC_SARCOM+1, struct compat_atmif_sioc) #define ATM_GETLOOP32 _IOW('a', ATMIOC_SARCOM+2, struct compat_atmif_sioc) #define ATM_SETLOOP32 _IOW('a', ATMIOC_SARCOM+3, struct compat_atmif_sioc) #define ATM_QUERYLOOP32 _IOW('a', ATMIOC_SARCOM+4, struct compat_atmif_sioc) static struct { unsigned int cmd32; unsigned int cmd; } atm_ioctl_map[] = { { ATM_GETLINKRATE32, ATM_GETLINKRATE }, { ATM_GETNAMES32, ATM_GETNAMES }, { ATM_GETTYPE32, ATM_GETTYPE }, { ATM_GETESI32, ATM_GETESI }, { ATM_GETADDR32, ATM_GETADDR }, { ATM_RSTADDR32, ATM_RSTADDR }, { ATM_ADDADDR32, ATM_ADDADDR }, { ATM_DELADDR32, ATM_DELADDR }, { ATM_GETCIRANGE32, ATM_GETCIRANGE }, { ATM_SETCIRANGE32, ATM_SETCIRANGE }, { ATM_SETESI32, ATM_SETESI }, { ATM_SETESIF32, ATM_SETESIF }, { ATM_GETSTAT32, ATM_GETSTAT }, { ATM_GETSTATZ32, ATM_GETSTATZ }, { ATM_GETLOOP32, ATM_GETLOOP }, { ATM_SETLOOP32, ATM_SETLOOP }, { ATM_QUERYLOOP32, ATM_QUERYLOOP }, }; #define NR_ATM_IOCTL ARRAY_SIZE(atm_ioctl_map) static int do_atm_iobuf(struct socket *sock, unsigned int cmd, unsigned long arg) { struct compat_atm_iobuf __user *iobuf32 = compat_ptr(arg); u32 data; if (get_user(data, &iobuf32->buffer)) return -EFAULT; return atm_getnames(&iobuf32->length, compat_ptr(data)); } static int do_atmif_sioc(struct socket *sock, unsigned int cmd, unsigned long arg) { struct compat_atmif_sioc __user *sioc32 = compat_ptr(arg); int number; u32 data; if (get_user(data, &sioc32->arg) || get_user(number, &sioc32->number)) return -EFAULT; return atm_dev_ioctl(cmd, compat_ptr(data), &sioc32->length, number, 0); } static int do_atm_ioctl(struct socket *sock, unsigned int cmd32, unsigned long arg) { int i; unsigned int cmd = 0; switch (cmd32) { case SONET_GETSTAT: case SONET_GETSTATZ: case SONET_GETDIAG: case SONET_SETDIAG: case SONET_CLRDIAG: case SONET_SETFRAMING: case SONET_GETFRAMING: case SONET_GETFRSENSE: return do_atmif_sioc(sock, cmd32, arg); } for (i = 0; i < NR_ATM_IOCTL; i++) { if (cmd32 == atm_ioctl_map[i].cmd32) { cmd = atm_ioctl_map[i].cmd; break; } } if (i == NR_ATM_IOCTL) return -EINVAL; switch (cmd) { case ATM_GETNAMES: return do_atm_iobuf(sock, cmd, arg); case ATM_GETLINKRATE: case ATM_GETTYPE: case ATM_GETESI: case ATM_GETADDR: case ATM_RSTADDR: case ATM_ADDADDR: case ATM_DELADDR: case ATM_GETCIRANGE: case ATM_SETCIRANGE: case ATM_SETESI: case ATM_SETESIF: case ATM_GETSTAT: case ATM_GETSTATZ: case ATM_GETLOOP: case ATM_SETLOOP: case ATM_QUERYLOOP: return do_atmif_sioc(sock, cmd, arg); } return -EINVAL; } int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int ret; ret = do_vcc_ioctl(sock, cmd, arg, 1); if (ret != -ENOIOCTLCMD) return ret; return do_atm_ioctl(sock, cmd, arg); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * DES & Triple DES EDE key verification helpers */ #ifndef __CRYPTO_INTERNAL_DES_H #define __CRYPTO_INTERNAL_DES_H #include <linux/crypto.h> #include <linux/fips.h> #include <crypto/des.h> #include <crypto/aead.h> #include <crypto/skcipher.h> /** * crypto_des_verify_key - Check whether a DES key is weak * @tfm: the crypto algo * @key: the key buffer * * Returns -EINVAL if the key is weak and the crypto TFM does not permit weak * keys. Otherwise, 0 is returned. * * It is the job of the caller to ensure that the size of the key equals * DES_KEY_SIZE. */ static inline int crypto_des_verify_key(struct crypto_tfm *tfm, const u8 *key) { struct des_ctx tmp; int err; err = des_expand_key(&tmp, key, DES_KEY_SIZE); if (err == -ENOKEY) { if (crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) err = -EINVAL; else err = 0; } memzero_explicit(&tmp, sizeof(tmp)); return err; } /* * RFC2451: * * For DES-EDE3, there is no known need to reject weak or * complementation keys. Any weakness is obviated by the use of * multiple keys. * * However, if the first two or last two independent 64-bit keys are * equal (k1 == k2 or k2 == k3), then the DES3 operation is simply the * same as DES. Implementers MUST reject keys that exhibit this * property. * */ static inline int des3_ede_verify_key(const u8 *key, unsigned int key_len, bool check_weak) { int ret = fips_enabled ? -EINVAL : -ENOKEY; u32 K[6]; memcpy(K, key, DES3_EDE_KEY_SIZE); if ((!((K[0] ^ K[2]) | (K[1] ^ K[3])) || !((K[2] ^ K[4]) | (K[3] ^ K[5]))) && (fips_enabled || check_weak)) goto bad; if ((!((K[0] ^ K[4]) | (K[1] ^ K[5]))) && fips_enabled) goto bad; ret = 0; bad: memzero_explicit(K, DES3_EDE_KEY_SIZE); return ret; } /** * crypto_des3_ede_verify_key - Check whether a DES3-EDE key is weak * @tfm: the crypto algo * @key: the key buffer * * Returns -EINVAL if the key is weak and the crypto TFM does not permit weak * keys or when running in FIPS mode. Otherwise, 0 is returned. Note that some * keys are rejected in FIPS mode even if weak keys are permitted by the TFM * flags. * * It is the job of the caller to ensure that the size of the key equals * DES3_EDE_KEY_SIZE. */ static inline int crypto_des3_ede_verify_key(struct crypto_tfm *tfm, const u8 *key) { return des3_ede_verify_key(key, DES3_EDE_KEY_SIZE, crypto_tfm_get_flags(tfm) & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); } static inline int verify_skcipher_des_key(struct crypto_skcipher *tfm, const u8 *key) { return crypto_des_verify_key(crypto_skcipher_tfm(tfm), key); } static inline int verify_skcipher_des3_key(struct crypto_skcipher *tfm, const u8 *key) { return crypto_des3_ede_verify_key(crypto_skcipher_tfm(tfm), key); } static inline int verify_aead_des_key(struct crypto_aead *tfm, const u8 *key, int keylen) { if (keylen != DES_KEY_SIZE) return -EINVAL; return crypto_des_verify_key(crypto_aead_tfm(tfm), key); } static inline int verify_aead_des3_key(struct crypto_aead *tfm, const u8 *key, int keylen) { if (keylen != DES3_EDE_KEY_SIZE) return -EINVAL; return crypto_des3_ede_verify_key(crypto_aead_tfm(tfm), key); } #endif /* __CRYPTO_INTERNAL_DES_H */ |
| 8 8 8 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match connection tracking information. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2005 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_state.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); MODULE_DESCRIPTION("ip[6]_tables connection tracking state match module"); MODULE_ALIAS("ipt_state"); MODULE_ALIAS("ip6t_state"); static bool state_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_state_info *sinfo = par->matchinfo; enum ip_conntrack_info ctinfo; unsigned int statebit; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct) statebit = XT_STATE_BIT(ctinfo); else if (ctinfo == IP_CT_UNTRACKED) statebit = XT_STATE_UNTRACKED; else statebit = XT_STATE_INVALID; return (sinfo->statemask & statebit); } static int state_mt_check(const struct xt_mtchk_param *par) { int ret; ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) pr_info_ratelimited("cannot load conntrack support for proto=%u\n", par->family); return ret; } static void state_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_netns_put(par->net, par->family); } static struct xt_match state_mt_reg __read_mostly = { .name = "state", .family = NFPROTO_UNSPEC, .checkentry = state_mt_check, .match = state_mt, .destroy = state_mt_destroy, .matchsize = sizeof(struct xt_state_info), .me = THIS_MODULE, }; static int __init state_mt_init(void) { return xt_register_match(&state_mt_reg); } static void __exit state_mt_exit(void) { xt_unregister_match(&state_mt_reg); } module_init(state_mt_init); module_exit(state_mt_exit); |
| 464 15009 14995 2301 18 2318 2318 2325 2319 8629 23 8614 15310 1447 14970 150 13252 13270 13277 410 2567 2178 2180 2183 8319 1449 11978 7262 7299 3 7265 15 4360 4369 4364 605 607 428 428 264 265 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * iw_table is the sysfs-set interleave weight table, a value of 0 denotes * system-default value should be used. A NULL iw_table also denotes that * system-default values should be used. Until the system-default table * is implemented, the system-default is always 1. * * iw_table is RCU protected */ static u8 __rcu *iw_table; static DEFINE_MUTEX(iw_table_lock); static u8 get_il_weight(int node) { u8 *table; u8 weight; rcu_read_lock(); table = rcu_dereference(iw_table); /* if no iw_table, use system default */ weight = table ? table[node] : 1; /* if value in iw_table is 0, use system default */ weight = weight ? weight : 1; rcu_read_unlock(); return weight; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); /** * nearest_node_nodemask - Find the node in @mask at the nearest distance * from @node. * * @node: a valid node ID to start the search from. * @mask: a pointer to a nodemask representing the allowed nodes. * * This function iterates over all nodes in @mask and calculates the * distance from the starting @node, then it returns the node ID that is * the closest to @node, or MAX_NUMNODES if no node is found. * * Note that @node must be a valid node ID usable with node_distance(), * providing an invalid node ID (e.g., NUMA_NO_NODE) may result in crashes * or unexpected behavior. */ int nearest_node_nodemask(int node, nodemask_t *mask) { int dist, n, min_dist = INT_MAX, min_node = MAX_NUMNODES; for_each_node_mask(n, *mask) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(nearest_node_nodemask); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed++; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_maybe_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_maybe_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table; unsigned int weight_total = 0; u8 weight; int nid; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); table = rcu_dereference(iw_table); /* calculate the total weight */ for_each_node_mask(nid, nodemask) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; weight_total += weight; } /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_frozen_pages_noprof( gfp | __GFP_THISNODE | __GFP_NORETRY, order, nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, ilx, nid); if (!page) return NULL; set_page_refcounted(page); return page_rmappable_folio(page); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_frozen_pages_noprof(gfp, order); if (page) set_page_refcounted(page); return page; } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *table, *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock(); /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1; weight_total += weights[node]; } /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct iw_node_attr *node_attr; u8 *new; u8 *old; u8 weight = 0; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "")) weight = 0; else if (kstrtou8(buf, 0, &weight)) return -EINVAL; new = kzalloc(nr_node_ids, GFP_KERNEL); if (!new) return -ENOMEM; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); if (old) memcpy(new, old, nr_node_ids); new[node_attr->nid] = weight; rcu_assign_pointer(iw_table, new); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); return count; } static struct iw_node_attr **node_attrs; static void sysfs_wi_node_release(struct iw_node_attr *node_attr, struct kobject *parent) { if (!node_attr) return; sysfs_remove_file(parent, &node_attr->kobj_attr.attr); kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); } static void sysfs_wi_release(struct kobject *wi_kobj) { int i; for (i = 0; i < nr_node_ids; i++) sysfs_wi_node_release(node_attrs[i], wi_kobj); kobject_put(wi_kobj); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = sysfs_wi_release, }; static int add_weight_node(int nid, struct kobject *wi_kobj) { struct iw_node_attr *node_attr; char *name; node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); if (!node_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(node_attr); return -ENOMEM; } sysfs_attr_init(&node_attr->kobj_attr.attr); node_attr->kobj_attr.attr.name = name; node_attr->kobj_attr.attr.mode = 0644; node_attr->kobj_attr.show = node_show; node_attr->kobj_attr.store = node_store; node_attr->nid = nid; if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); pr_err("failed to add attribute to weighted_interleave\n"); return -ENOMEM; } node_attrs[nid] = node_attr; return 0; } static int add_weighted_interleave_group(struct kobject *root_kobj) { struct kobject *wi_kobj; int nid, err; wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!wi_kobj) return -ENOMEM; err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, "weighted_interleave"); if (err) { kfree(wi_kobj); return err; } for_each_node_state(nid, N_POSSIBLE) { err = add_weight_node(nid, wi_kobj); if (err) { pr_err("failed to add sysfs [node%d]\n", nid); break; } } if (err) kobject_put(wi_kobj); return 0; } static void mempolicy_kobj_release(struct kobject *kobj) { u8 *old; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); rcu_assign_pointer(iw_table, NULL); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); kfree(node_attrs); kfree(kobj); } static const struct kobj_type mempolicy_ktype = { .release = mempolicy_kobj_release }; static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); if (!mempolicy_kobj) { err = -ENOMEM; goto err_out; } node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), GFP_KERNEL); if (!node_attrs) { err = -ENOMEM; goto mempol_out; } err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, "mempolicy"); if (err) goto node_out; err = add_weighted_interleave_group(mempolicy_kobj); if (err) { pr_err("mempolicy sysfs structure failed to initialize\n"); kobject_put(mempolicy_kobj); return err; } return err; node_out: kfree(node_attrs); mempol_out: kfree(mempolicy_kobj); err_out: pr_err("failed to add mempolicy kobject to the system\n"); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 12 2 12 1 1 6 1 4 2 5 20 20 3 3 2 12 4 5 9 6 6 2 27 5 17 5 22 22 1 25 3 38 10 28 2 9 9 27 27 93 1 2 2 5 48 48 42 43 41 41 4 40 31 31 5 27 25 3 27 32 32 2 29 29 9 9 2 7 23 23 4 13 9 7 4 10 10 31 27 4 31 12 12 27 24 2 2 2 25 25 1 132 146 3 143 120 108 5 2 5 108 94 44 1 123 12 117 18 6 66 63 43 91 2 11 2 75 21 92 62 1 61 52 44 3 42 5 3 44 42 115 3 98 16 107 6 102 11 104 8 110 3 105 9 87 26 107 5 109 4 113 107 58 48 7 103 10 100 8 3 18 24 3 16 8 8 8 6 8 2 94 23 101 16 27 120 109 123 119 4 61 61 2 58 29 28 28 21 13 13 1 6 5 18 18 17 11 280 326 4 2 3 2 2 4 2 3 1 3 2 5 4 3 298 73 232 9 54 216 1 8 229 32 123 94 94 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> #include <net/inet_dscp.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static const struct header_ops ipgre_header_ops; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6)) { unsigned int data_len = 0; if (type == ICMP_TIME_EXCEEDED) data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; } #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; ip_tunnel_flags_copy(flags, tpi->flags); itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); __set_bit(IP_TUNNEL_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_len + erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); info->options_len = sizeof(*md); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { const struct iphdr *tnl_params; if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; /* Special case for ipgre_header_parse(), which expects the * mac_header to point to the outer IP header. */ if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); ip_tunnel_flags_and(flags, tpi->flags, flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags); ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto err_free_skb; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); __set_bit(IP_TUNNEL_SEQ_BIT, flags); ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto err_free_skb; truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } __set_bit(IP_TUNNEL_SEQ_BIT, flags); gre_build_header(skb, 8, flags, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; if (!pskb_may_pull(skb, pull_len)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto free_skb; truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } } static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { __be16 i_flags, o_flags; int err; if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; i_flags = ip_tunnel_flags_to_be16(p->i_flags); o_flags = ip_tunnel_flags_to_be16(p->o_flags); if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } gre_flags_to_tnl_flags(p->i_flags, i_flags); gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); ip_tunnel_flags_from_be16(p->i_flags, i_flags); o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); ip_tunnel_flags_from_be16(p->o_flags, o_flags); return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph; struct gre_base_hdr *greh; iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4 = { .flowi4_oif = t->parms.link, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(&t->parms.iph)), .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_proto = IPPROTO_GRE, .saddr = t->parms.iph.saddr, .daddr = t->parms.iph.daddr, .fl4_gre_key = t->parms.o_key, }; struct rtable *rt; rt = ip_route_output_key(t->net, &fl4); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev-& |