1/* 2 * Copyright (c) 2012 Mellanox Technologies. All rights reserved. 3 * 4 * This software is available to you under a choice of one of two 5 * licenses. You may choose to be licensed under the terms of the GNU 6 * General Public License (GPL) Version 2, available from the file 7 * COPYING in the main directory of this source tree, or the 8 * OpenIB.org BSD license below: 9 * 10 * Redistribution and use in source and binary forms, with or 11 * without modification, are permitted provided that the following 12 * conditions are met: 13 * 14 * - Redistributions of source code must retain the above 15 * copyright notice, this list of conditions and the following 16 * disclaimer. 17 * 18 * - Redistributions in binary form must reproduce the above 19 * copyright notice, this list of conditions and the following 20 * disclaimer in the documentation and/or other materials 21 * provided with the distribution. 22 * 23 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 24 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 25 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND 26 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS 27 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN 28 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN 29 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 30 * SOFTWARE. 31 */ 32 33#include <rdma/ib_mad.h> 34 35#include <linux/mlx4/cmd.h> 36#include <linux/rbtree.h> 37#include <linux/idr.h> 38#include <rdma/ib_cm.h> 39 40#include "mlx4_ib.h" 41 42#define CM_CLEANUP_CACHE_TIMEOUT (30 * HZ) 43 44struct id_map_entry { 45 struct rb_node node; 46 47 u32 sl_cm_id; 48 u32 pv_cm_id; 49 int slave_id; 50 int scheduled_delete; 51 struct mlx4_ib_dev *dev; 52 53 struct list_head list; 54 struct delayed_work timeout; 55}; 56 57struct rej_tmout_entry { 58 int slave; 59 u32 rem_pv_cm_id; 60 struct delayed_work timeout; 61 struct xarray *xa_rej_tmout; 62}; 63 64struct cm_generic_msg { 65 struct ib_mad_hdr hdr; 66 67 __be32 local_comm_id; 68 __be32 remote_comm_id; 69 unsigned char unused[2]; 70 __be16 rej_reason; 71}; 72 73struct cm_sidr_generic_msg { 74 struct ib_mad_hdr hdr; 75 __be32 request_id; 76}; 77 78struct cm_req_msg { 79 unsigned char unused[0x60]; 80 union ib_gid primary_path_sgid; 81}; 82 83 84static void set_local_comm_id(struct ib_mad *mad, u32 cm_id) 85{ 86 if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { 87 struct cm_sidr_generic_msg *msg = 88 (struct cm_sidr_generic_msg *)mad; 89 msg->request_id = cpu_to_be32(cm_id); 90 } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { 91 pr_err("trying to set local_comm_id in SIDR_REP\n"); 92 return; 93 } else { 94 struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; 95 msg->local_comm_id = cpu_to_be32(cm_id); 96 } 97} 98 99static u32 get_local_comm_id(struct ib_mad *mad) 100{ 101 if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { 102 struct cm_sidr_generic_msg *msg = 103 (struct cm_sidr_generic_msg *)mad; 104 return be32_to_cpu(msg->request_id); 105 } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { 106 pr_err("trying to set local_comm_id in SIDR_REP\n"); 107 return -1; 108 } else { 109 struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; 110 return be32_to_cpu(msg->local_comm_id); 111 } 112} 113 114static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id) 115{ 116 if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { 117 struct cm_sidr_generic_msg *msg = 118 (struct cm_sidr_generic_msg *)mad; 119 msg->request_id = cpu_to_be32(cm_id); 120 } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { 121 pr_err("trying to set remote_comm_id in SIDR_REQ\n"); 122 return; 123 } else { 124 struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; 125 msg->remote_comm_id = cpu_to_be32(cm_id); 126 } 127} 128 129static u32 get_remote_comm_id(struct ib_mad *mad) 130{ 131 if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { 132 struct cm_sidr_generic_msg *msg = 133 (struct cm_sidr_generic_msg *)mad; 134 return be32_to_cpu(msg->request_id); 135 } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { 136 pr_err("trying to set remote_comm_id in SIDR_REQ\n"); 137 return -1; 138 } else { 139 struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; 140 return be32_to_cpu(msg->remote_comm_id); 141 } 142} 143 144static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad) 145{ 146 struct cm_req_msg *msg = (struct cm_req_msg *)mad; 147 148 return msg->primary_path_sgid; 149} 150 151/* Lock should be taken before called */ 152static struct id_map_entry * 153id_map_find_by_sl_id(struct ib_device *ibdev, u32 slave_id, u32 sl_cm_id) 154{ 155 struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map; 156 struct rb_node *node = sl_id_map->rb_node; 157 158 while (node) { 159 struct id_map_entry *id_map_entry = 160 rb_entry(node, struct id_map_entry, node); 161 162 if (id_map_entry->sl_cm_id > sl_cm_id) 163 node = node->rb_left; 164 else if (id_map_entry->sl_cm_id < sl_cm_id) 165 node = node->rb_right; 166 else if (id_map_entry->slave_id > slave_id) 167 node = node->rb_left; 168 else if (id_map_entry->slave_id < slave_id) 169 node = node->rb_right; 170 else 171 return id_map_entry; 172 } 173 return NULL; 174} 175 176static void id_map_ent_timeout(struct work_struct *work) 177{ 178 struct delayed_work *delay = to_delayed_work(work); 179 struct id_map_entry *ent = container_of(delay, struct id_map_entry, timeout); 180 struct id_map_entry *found_ent; 181 struct mlx4_ib_dev *dev = ent->dev; 182 struct mlx4_ib_sriov *sriov = &dev->sriov; 183 struct rb_root *sl_id_map = &sriov->sl_id_map; 184 185 spin_lock(&sriov->id_map_lock); 186 if (!xa_erase(&sriov->pv_id_table, ent->pv_cm_id)) 187 goto out; 188 found_ent = id_map_find_by_sl_id(&dev->ib_dev, ent->slave_id, ent->sl_cm_id); 189 if (found_ent && found_ent == ent) 190 rb_erase(&found_ent->node, sl_id_map); 191 192out: 193 list_del(&ent->list); 194 spin_unlock(&sriov->id_map_lock); 195 kfree(ent); 196} 197 198static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new) 199{ 200 struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map; 201 struct rb_node **link = &sl_id_map->rb_node, *parent = NULL; 202 struct id_map_entry *ent; 203 int slave_id = new->slave_id; 204 int sl_cm_id = new->sl_cm_id; 205 206 ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id); 207 if (ent) { 208 pr_debug("overriding existing sl_id_map entry (cm_id = %x)\n", 209 sl_cm_id); 210 211 rb_replace_node(&ent->node, &new->node, sl_id_map); 212 return; 213 } 214 215 /* Go to the bottom of the tree */ 216 while (*link) { 217 parent = *link; 218 ent = rb_entry(parent, struct id_map_entry, node); 219 220 if (ent->sl_cm_id > sl_cm_id || (ent->sl_cm_id == sl_cm_id && ent->slave_id > slave_id)) 221 link = &(*link)->rb_left; 222 else 223 link = &(*link)->rb_right; 224 } 225 226 rb_link_node(&new->node, parent, link); 227 rb_insert_color(&new->node, sl_id_map); 228} 229 230static struct id_map_entry * 231id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id) 232{ 233 int ret; 234 struct id_map_entry *ent; 235 struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov; 236 237 ent = kmalloc(sizeof (struct id_map_entry), GFP_KERNEL); 238 if (!ent) 239 return ERR_PTR(-ENOMEM); 240 241 ent->sl_cm_id = sl_cm_id; 242 ent->slave_id = slave_id; 243 ent->scheduled_delete = 0; 244 ent->dev = to_mdev(ibdev); 245 INIT_DELAYED_WORK(&ent->timeout, id_map_ent_timeout); 246 247 ret = xa_alloc_cyclic(&sriov->pv_id_table, &ent->pv_cm_id, ent, 248 xa_limit_32b, &sriov->pv_id_next, GFP_KERNEL); 249 if (ret >= 0) { 250 spin_lock(&sriov->id_map_lock); 251 sl_id_map_add(ibdev, ent); 252 list_add_tail(&ent->list, &sriov->cm_list); 253 spin_unlock(&sriov->id_map_lock); 254 return ent; 255 } 256 257 /*error flow*/ 258 kfree(ent); 259 mlx4_ib_warn(ibdev, "Allocation failed (err:0x%x)\n", ret); 260 return ERR_PTR(-ENOMEM); 261} 262 263static struct id_map_entry * 264id_map_get(struct ib_device *ibdev, int *pv_cm_id, int slave_id, int sl_cm_id) 265{ 266 struct id_map_entry *ent; 267 struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov; 268 269 spin_lock(&sriov->id_map_lock); 270 if (*pv_cm_id == -1) { 271 ent = id_map_find_by_sl_id(ibdev, slave_id, sl_cm_id); 272 if (ent) 273 *pv_cm_id = (int) ent->pv_cm_id; 274 } else 275 ent = xa_load(&sriov->pv_id_table, *pv_cm_id); 276 spin_unlock(&sriov->id_map_lock); 277 278 return ent; 279} 280 281static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id) 282{ 283 struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov; 284 unsigned long flags; 285 286 spin_lock(&sriov->id_map_lock); 287 spin_lock_irqsave(&sriov->going_down_lock, flags); 288 /*make sure that there is no schedule inside the scheduled work.*/ 289 if (!sriov->is_going_down && !id->scheduled_delete) { 290 id->scheduled_delete = 1; 291 schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT); 292 } else if (id->scheduled_delete) { 293 /* Adjust timeout if already scheduled */ 294 mod_delayed_work(system_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT); 295 } 296 spin_unlock_irqrestore(&sriov->going_down_lock, flags); 297 spin_unlock(&sriov->id_map_lock); 298} 299 300#define REJ_REASON(m) be16_to_cpu(((struct cm_generic_msg *)(m))->rej_reason) 301int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id, 302 struct ib_mad *mad) 303{ 304 struct id_map_entry *id; 305 u32 sl_cm_id; 306 int pv_cm_id = -1; 307 308 if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID || 309 mad->mad_hdr.attr_id == CM_REP_ATTR_ID || 310 mad->mad_hdr.attr_id == CM_MRA_ATTR_ID || 311 mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID || 312 (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID && REJ_REASON(mad) == IB_CM_REJ_TIMEOUT)) { 313 sl_cm_id = get_local_comm_id(mad); 314 id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id); 315 if (id) 316 goto cont; 317 id = id_map_alloc(ibdev, slave_id, sl_cm_id); 318 if (IS_ERR(id)) { 319 mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n", 320 __func__, slave_id, sl_cm_id); 321 return PTR_ERR(id); 322 } 323 } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID || 324 mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { 325 return 0; 326 } else { 327 sl_cm_id = get_local_comm_id(mad); 328 id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id); 329 } 330 331 if (!id) { 332 pr_debug("id{slave: %d, sl_cm_id: 0x%x} is NULL! attr_id: 0x%x\n", 333 slave_id, sl_cm_id, be16_to_cpu(mad->mad_hdr.attr_id)); 334 return -EINVAL; 335 } 336 337cont: 338 set_local_comm_id(mad, id->pv_cm_id); 339 340 if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID) 341 schedule_delayed(ibdev, id); 342 return 0; 343} 344 345static void rej_tmout_timeout(struct work_struct *work) 346{ 347 struct delayed_work *delay = to_delayed_work(work); 348 struct rej_tmout_entry *item = container_of(delay, struct rej_tmout_entry, timeout); 349 struct rej_tmout_entry *deleted; 350 351 deleted = xa_cmpxchg(item->xa_rej_tmout, item->rem_pv_cm_id, item, NULL, 0); 352 353 if (deleted != item) 354 pr_debug("deleted(%p) != item(%p)\n", deleted, item); 355 356 kfree(item); 357} 358 359static int alloc_rej_tmout(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id, int slave) 360{ 361 struct rej_tmout_entry *item; 362 struct rej_tmout_entry *old; 363 int ret = 0; 364 365 xa_lock(&sriov->xa_rej_tmout); 366 item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id); 367 368 if (item) { 369 if (xa_err(item)) 370 ret = xa_err(item); 371 else 372 /* If a retry, adjust delayed work */ 373 mod_delayed_work(system_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT); 374 goto err_or_exists; 375 } 376 xa_unlock(&sriov->xa_rej_tmout); 377 378 item = kmalloc(sizeof(*item), GFP_KERNEL); 379 if (!item) 380 return -ENOMEM; 381 382 INIT_DELAYED_WORK(&item->timeout, rej_tmout_timeout); 383 item->slave = slave; 384 item->rem_pv_cm_id = rem_pv_cm_id; 385 item->xa_rej_tmout = &sriov->xa_rej_tmout; 386 387 old = xa_cmpxchg(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id, NULL, item, GFP_KERNEL); 388 if (old) { 389 pr_debug( 390 "Non-null old entry (%p) or error (%d) when inserting\n", 391 old, xa_err(old)); 392 kfree(item); 393 return xa_err(old); 394 } 395 396 schedule_delayed_work(&item->timeout, CM_CLEANUP_CACHE_TIMEOUT); 397 398 return 0; 399 400err_or_exists: 401 xa_unlock(&sriov->xa_rej_tmout); 402 return ret; 403} 404 405static int lookup_rej_tmout_slave(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id) 406{ 407 struct rej_tmout_entry *item; 408 int slave; 409 410 xa_lock(&sriov->xa_rej_tmout); 411 item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id); 412 413 if (!item || xa_err(item)) { 414 pr_debug("Could not find slave. rem_pv_cm_id 0x%x error: %d\n", 415 rem_pv_cm_id, xa_err(item)); 416 slave = !item ? -ENOENT : xa_err(item); 417 } else { 418 slave = item->slave; 419 } 420 xa_unlock(&sriov->xa_rej_tmout); 421 422 return slave; 423} 424 425int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave, 426 struct ib_mad *mad) 427{ 428 struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov; 429 u32 rem_pv_cm_id = get_local_comm_id(mad); 430 u32 pv_cm_id; 431 struct id_map_entry *id; 432 int sts; 433 434 if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID || 435 mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { 436 union ib_gid gid; 437 438 if (!slave) 439 return 0; 440 441 gid = gid_from_req_msg(ibdev, mad); 442 *slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id); 443 if (*slave < 0) { 444 mlx4_ib_warn(ibdev, "failed matching slave_id by gid (0x%llx)\n", 445 be64_to_cpu(gid.global.interface_id)); 446 return -ENOENT; 447 } 448 449 sts = alloc_rej_tmout(sriov, rem_pv_cm_id, *slave); 450 if (sts) 451 /* Even if this fails, we pass on the REQ to the slave */ 452 pr_debug("Could not allocate rej_tmout entry. rem_pv_cm_id 0x%x slave %d status %d\n", 453 rem_pv_cm_id, *slave, sts); 454 455 return 0; 456 } 457 458 pv_cm_id = get_remote_comm_id(mad); 459 id = id_map_get(ibdev, (int *)&pv_cm_id, -1, -1); 460 461 if (!id) { 462 if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID && 463 REJ_REASON(mad) == IB_CM_REJ_TIMEOUT && slave) { 464 *slave = lookup_rej_tmout_slave(sriov, rem_pv_cm_id); 465 466 return (*slave < 0) ? *slave : 0; 467 } 468 pr_debug("Couldn't find an entry for pv_cm_id 0x%x, attr_id 0x%x\n", 469 pv_cm_id, be16_to_cpu(mad->mad_hdr.attr_id)); 470 return -ENOENT; 471 } 472 473 if (slave) 474 *slave = id->slave_id; 475 set_remote_comm_id(mad, id->sl_cm_id); 476 477 if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID || 478 mad->mad_hdr.attr_id == CM_REJ_ATTR_ID) 479 schedule_delayed(ibdev, id); 480 481 return 0; 482} 483 484void mlx4_ib_cm_paravirt_init(struct mlx4_ib_dev *dev) 485{ 486 spin_lock_init(&dev->sriov.id_map_lock); 487 INIT_LIST_HEAD(&dev->sriov.cm_list); 488 dev->sriov.sl_id_map = RB_ROOT; 489 xa_init_flags(&dev->sriov.pv_id_table, XA_FLAGS_ALLOC); 490 xa_init(&dev->sriov.xa_rej_tmout); 491} 492 493static void rej_tmout_xa_cleanup(struct mlx4_ib_sriov *sriov, int slave) 494{ 495 struct rej_tmout_entry *item; 496 bool flush_needed = false; 497 unsigned long id; 498 int cnt = 0; 499 500 xa_lock(&sriov->xa_rej_tmout); 501 xa_for_each(&sriov->xa_rej_tmout, id, item) { 502 if (slave < 0 || slave == item->slave) { 503 mod_delayed_work(system_wq, &item->timeout, 0); 504 flush_needed = true; 505 ++cnt; 506 } 507 } 508 xa_unlock(&sriov->xa_rej_tmout); 509 510 if (flush_needed) { 511 flush_scheduled_work(); 512 pr_debug("Deleted %d entries in xarray for slave %d during cleanup\n", 513 cnt, slave); 514 } 515 516 if (slave < 0) 517 WARN_ON(!xa_empty(&sriov->xa_rej_tmout)); 518} 519 520/* slave = -1 ==> all slaves */ 521/* TBD -- call paravirt clean for single slave. Need for slave RESET event */ 522void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave) 523{ 524 struct mlx4_ib_sriov *sriov = &dev->sriov; 525 struct rb_root *sl_id_map = &sriov->sl_id_map; 526 struct list_head lh; 527 struct rb_node *nd; 528 int need_flush = 0; 529 struct id_map_entry *map, *tmp_map; 530 /* cancel all delayed work queue entries */ 531 INIT_LIST_HEAD(&lh); 532 spin_lock(&sriov->id_map_lock); 533 list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) { 534 if (slave < 0 || slave == map->slave_id) { 535 if (map->scheduled_delete) 536 need_flush |= !cancel_delayed_work(&map->timeout); 537 } 538 } 539 540 spin_unlock(&sriov->id_map_lock); 541 542 if (need_flush) 543 flush_scheduled_work(); /* make sure all timers were flushed */ 544 545 /* now, remove all leftover entries from databases*/ 546 spin_lock(&sriov->id_map_lock); 547 if (slave < 0) { 548 while (rb_first(sl_id_map)) { 549 struct id_map_entry *ent = 550 rb_entry(rb_first(sl_id_map), 551 struct id_map_entry, node); 552 553 rb_erase(&ent->node, sl_id_map); 554 xa_erase(&sriov->pv_id_table, ent->pv_cm_id); 555 } 556 list_splice_init(&dev->sriov.cm_list, &lh); 557 } else { 558 /* first, move nodes belonging to slave to db remove list */ 559 nd = rb_first(sl_id_map); 560 while (nd) { 561 struct id_map_entry *ent = 562 rb_entry(nd, struct id_map_entry, node); 563 nd = rb_next(nd); 564 if (ent->slave_id == slave) 565 list_move_tail(&ent->list, &lh); 566 } 567 /* remove those nodes from databases */ 568 list_for_each_entry_safe(map, tmp_map, &lh, list) { 569 rb_erase(&map->node, sl_id_map); 570 xa_erase(&sriov->pv_id_table, map->pv_cm_id); 571 } 572 573 /* add remaining nodes from cm_list */ 574 list_for_each_entry_safe(map, tmp_map, &dev->sriov.cm_list, list) { 575 if (slave == map->slave_id) 576 list_move_tail(&map->list, &lh); 577 } 578 } 579 580 spin_unlock(&sriov->id_map_lock); 581 582 /* free any map entries left behind due to cancel_delayed_work above */ 583 list_for_each_entry_safe(map, tmp_map, &lh, list) { 584 list_del(&map->list); 585 kfree(map); 586 } 587 588 rej_tmout_xa_cleanup(sriov, slave); 589} 590