1/* Copyright (c) 2013 Coraid, Inc. See COPYING for GPL terms. */ 2/* 3 * aoedev.c 4 * AoE device utility functions; maintains device list. 5 */ 6 7#include <linux/hdreg.h> 8#include <linux/blk-mq.h> 9#include <linux/netdevice.h> 10#include <linux/delay.h> 11#include <linux/slab.h> 12#include <linux/bitmap.h> 13#include <linux/kdev_t.h> 14#include <linux/moduleparam.h> 15#include <linux/string.h> 16#include "aoe.h" 17 18static void freetgt(struct aoedev *d, struct aoetgt *t); 19static void skbpoolfree(struct aoedev *d); 20 21static int aoe_dyndevs = 1; 22module_param(aoe_dyndevs, int, 0644); 23MODULE_PARM_DESC(aoe_dyndevs, "Use dynamic minor numbers for devices."); 24 25static struct aoedev *devlist; 26static DEFINE_SPINLOCK(devlist_lock); 27 28/* Because some systems will have one, many, or no 29 * - partitions, 30 * - slots per shelf, 31 * - or shelves, 32 * we need some flexibility in the way the minor numbers 33 * are allocated. So they are dynamic. 34 */ 35#define N_DEVS ((1U<<MINORBITS)/AOE_PARTITIONS) 36 37static DEFINE_SPINLOCK(used_minors_lock); 38static DECLARE_BITMAP(used_minors, N_DEVS); 39 40static int 41minor_get_dyn(ulong *sysminor) 42{ 43 ulong flags; 44 ulong n; 45 int error = 0; 46 47 spin_lock_irqsave(&used_minors_lock, flags); 48 n = find_first_zero_bit(used_minors, N_DEVS); 49 if (n < N_DEVS) 50 set_bit(n, used_minors); 51 else 52 error = -1; 53 spin_unlock_irqrestore(&used_minors_lock, flags); 54 55 *sysminor = n * AOE_PARTITIONS; 56 return error; 57} 58 59static int 60minor_get_static(ulong *sysminor, ulong aoemaj, int aoemin) 61{ 62 ulong flags; 63 ulong n; 64 int error = 0; 65 enum { 66 /* for backwards compatibility when !aoe_dyndevs, 67 * a static number of supported slots per shelf */ 68 NPERSHELF = 16, 69 }; 70 71 if (aoemin >= NPERSHELF) { 72 pr_err("aoe: %s %d slots per shelf\n", 73 "static minor device numbers support only", 74 NPERSHELF); 75 error = -1; 76 goto out; 77 } 78 79 n = aoemaj * NPERSHELF + aoemin; 80 if (n >= N_DEVS) { 81 pr_err("aoe: %s with e%ld.%d\n", 82 "cannot use static minor device numbers", 83 aoemaj, aoemin); 84 error = -1; 85 goto out; 86 } 87 88 spin_lock_irqsave(&used_minors_lock, flags); 89 if (test_bit(n, used_minors)) { 90 pr_err("aoe: %s %lu\n", 91 "existing device already has static minor number", 92 n); 93 error = -1; 94 } else 95 set_bit(n, used_minors); 96 spin_unlock_irqrestore(&used_minors_lock, flags); 97 *sysminor = n * AOE_PARTITIONS; 98out: 99 return error; 100} 101 102static int 103minor_get(ulong *sysminor, ulong aoemaj, int aoemin) 104{ 105 if (aoe_dyndevs) 106 return minor_get_dyn(sysminor); 107 else 108 return minor_get_static(sysminor, aoemaj, aoemin); 109} 110 111static void 112minor_free(ulong minor) 113{ 114 ulong flags; 115 116 minor /= AOE_PARTITIONS; 117 BUG_ON(minor >= N_DEVS); 118 119 spin_lock_irqsave(&used_minors_lock, flags); 120 BUG_ON(!test_bit(minor, used_minors)); 121 clear_bit(minor, used_minors); 122 spin_unlock_irqrestore(&used_minors_lock, flags); 123} 124 125/* 126 * Users who grab a pointer to the device with aoedev_by_aoeaddr 127 * automatically get a reference count and must be responsible 128 * for performing a aoedev_put. With the addition of async 129 * kthread processing I'm no longer confident that we can 130 * guarantee consistency in the face of device flushes. 131 * 132 * For the time being, we only bother to add extra references for 133 * frames sitting on the iocq. When the kthreads finish processing 134 * these frames, they will aoedev_put the device. 135 */ 136 137void 138aoedev_put(struct aoedev *d) 139{ 140 ulong flags; 141 142 spin_lock_irqsave(&devlist_lock, flags); 143 d->ref--; 144 spin_unlock_irqrestore(&devlist_lock, flags); 145} 146 147static void 148dummy_timer(struct timer_list *t) 149{ 150 struct aoedev *d; 151 152 d = from_timer(d, t, timer); 153 if (d->flags & DEVFL_TKILL) 154 return; 155 d->timer.expires = jiffies + HZ; 156 add_timer(&d->timer); 157} 158 159static void 160aoe_failip(struct aoedev *d) 161{ 162 struct request *rq; 163 struct aoe_req *req; 164 struct bio *bio; 165 166 aoe_failbuf(d, d->ip.buf); 167 rq = d->ip.rq; 168 if (rq == NULL) 169 return; 170 171 req = blk_mq_rq_to_pdu(rq); 172 while ((bio = d->ip.nxbio)) { 173 bio->bi_status = BLK_STS_IOERR; 174 d->ip.nxbio = bio->bi_next; 175 req->nr_bios--; 176 } 177 178 if (!req->nr_bios) 179 aoe_end_request(d, rq, 0); 180} 181 182static void 183downdev_frame(struct list_head *pos) 184{ 185 struct frame *f; 186 187 f = list_entry(pos, struct frame, head); 188 list_del(pos); 189 if (f->buf) { 190 f->buf->nframesout--; 191 aoe_failbuf(f->t->d, f->buf); 192 } 193 aoe_freetframe(f); 194} 195 196void 197aoedev_downdev(struct aoedev *d) 198{ 199 struct aoetgt *t, **tt, **te; 200 struct list_head *head, *pos, *nx; 201 int i; 202 203 d->flags &= ~DEVFL_UP; 204 205 /* clean out active and to-be-retransmitted buffers */ 206 for (i = 0; i < NFACTIVE; i++) { 207 head = &d->factive[i]; 208 list_for_each_safe(pos, nx, head) 209 downdev_frame(pos); 210 } 211 head = &d->rexmitq; 212 list_for_each_safe(pos, nx, head) 213 downdev_frame(pos); 214 215 /* reset window dressings */ 216 tt = d->targets; 217 te = tt + d->ntargets; 218 for (; tt < te && (t = *tt); tt++) { 219 aoecmd_wreset(t); 220 t->nout = 0; 221 } 222 223 /* clean out the in-process request (if any) */ 224 aoe_failip(d); 225 226 /* fast fail all pending I/O */ 227 if (d->blkq) { 228 /* UP is cleared, freeze+quiesce to insure all are errored */ 229 blk_mq_freeze_queue(d->blkq); 230 blk_mq_quiesce_queue(d->blkq); 231 blk_mq_unquiesce_queue(d->blkq); 232 blk_mq_unfreeze_queue(d->blkq); 233 } 234 235 if (d->gd) 236 set_capacity(d->gd, 0); 237} 238 239/* return whether the user asked for this particular 240 * device to be flushed 241 */ 242static int 243user_req(char *s, size_t slen, struct aoedev *d) 244{ 245 const char *p; 246 size_t lim; 247 248 if (!d->gd) 249 return 0; 250 p = kbasename(d->gd->disk_name); 251 lim = sizeof(d->gd->disk_name); 252 lim -= p - d->gd->disk_name; 253 if (slen < lim) 254 lim = slen; 255 256 return !strncmp(s, p, lim); 257} 258 259static void 260freedev(struct aoedev *d) 261{ 262 struct aoetgt **t, **e; 263 int freeing = 0; 264 unsigned long flags; 265 266 spin_lock_irqsave(&d->lock, flags); 267 if (d->flags & DEVFL_TKILL 268 && !(d->flags & DEVFL_FREEING)) { 269 d->flags |= DEVFL_FREEING; 270 freeing = 1; 271 } 272 spin_unlock_irqrestore(&d->lock, flags); 273 if (!freeing) 274 return; 275 276 del_timer_sync(&d->timer); 277 if (d->gd) { 278 aoedisk_rm_debugfs(d); 279 del_gendisk(d->gd); 280 put_disk(d->gd); 281 blk_mq_free_tag_set(&d->tag_set); 282 blk_cleanup_queue(d->blkq); 283 } 284 t = d->targets; 285 e = t + d->ntargets; 286 for (; t < e && *t; t++) 287 freetgt(d, *t); 288 289 mempool_destroy(d->bufpool); 290 skbpoolfree(d); 291 minor_free(d->sysminor); 292 293 spin_lock_irqsave(&d->lock, flags); 294 d->flags |= DEVFL_FREED; 295 spin_unlock_irqrestore(&d->lock, flags); 296} 297 298enum flush_parms { 299 NOT_EXITING = 0, 300 EXITING = 1, 301}; 302 303static int 304flush(const char __user *str, size_t cnt, int exiting) 305{ 306 ulong flags; 307 struct aoedev *d, **dd; 308 char buf[16]; 309 int all = 0; 310 int specified = 0; /* flush a specific device */ 311 unsigned int skipflags; 312 313 skipflags = DEVFL_GDALLOC | DEVFL_NEWSIZE | DEVFL_TKILL; 314 315 if (!exiting && cnt >= 3) { 316 if (cnt > sizeof buf) 317 cnt = sizeof buf; 318 if (copy_from_user(buf, str, cnt)) 319 return -EFAULT; 320 all = !strncmp(buf, "all", 3); 321 if (!all) 322 specified = 1; 323 } 324 325 flush_scheduled_work(); 326 /* pass one: do aoedev_downdev, which might sleep */ 327restart1: 328 spin_lock_irqsave(&devlist_lock, flags); 329 for (d = devlist; d; d = d->next) { 330 spin_lock(&d->lock); 331 if (d->flags & DEVFL_TKILL) 332 goto cont; 333 334 if (exiting) { 335 /* unconditionally take each device down */ 336 } else if (specified) { 337 if (!user_req(buf, cnt, d)) 338 goto cont; 339 } else if ((!all && (d->flags & DEVFL_UP)) 340 || d->flags & skipflags 341 || d->nopen 342 || d->ref) 343 goto cont; 344 345 spin_unlock(&d->lock); 346 spin_unlock_irqrestore(&devlist_lock, flags); 347 aoedev_downdev(d); 348 d->flags |= DEVFL_TKILL; 349 goto restart1; 350cont: 351 spin_unlock(&d->lock); 352 } 353 spin_unlock_irqrestore(&devlist_lock, flags); 354 355 /* pass two: call freedev, which might sleep, 356 * for aoedevs marked with DEVFL_TKILL 357 */ 358restart2: 359 spin_lock_irqsave(&devlist_lock, flags); 360 for (d = devlist; d; d = d->next) { 361 spin_lock(&d->lock); 362 if (d->flags & DEVFL_TKILL 363 && !(d->flags & DEVFL_FREEING)) { 364 spin_unlock(&d->lock); 365 spin_unlock_irqrestore(&devlist_lock, flags); 366 freedev(d); 367 goto restart2; 368 } 369 spin_unlock(&d->lock); 370 } 371 372 /* pass three: remove aoedevs marked with DEVFL_FREED */ 373 for (dd = &devlist, d = *dd; d; d = *dd) { 374 struct aoedev *doomed = NULL; 375 376 spin_lock(&d->lock); 377 if (d->flags & DEVFL_FREED) { 378 *dd = d->next; 379 doomed = d; 380 } else { 381 dd = &d->next; 382 } 383 spin_unlock(&d->lock); 384 if (doomed) 385 kfree(doomed->targets); 386 kfree(doomed); 387 } 388 spin_unlock_irqrestore(&devlist_lock, flags); 389 390 return 0; 391} 392 393int 394aoedev_flush(const char __user *str, size_t cnt) 395{ 396 return flush(str, cnt, NOT_EXITING); 397} 398 399/* This has been confirmed to occur once with Tms=3*1000 due to the 400 * driver changing link and not processing its transmit ring. The 401 * problem is hard enough to solve by returning an error that I'm 402 * still punting on "solving" this. 403 */ 404static void 405skbfree(struct sk_buff *skb) 406{ 407 enum { Sms = 250, Tms = 30 * 1000}; 408 int i = Tms / Sms; 409 410 if (skb == NULL) 411 return; 412 while (atomic_read(&skb_shinfo(skb)->dataref) != 1 && i-- > 0) 413 msleep(Sms); 414 if (i < 0) { 415 printk(KERN_ERR 416 "aoe: %s holds ref: %s\n", 417 skb->dev ? skb->dev->name : "netif", 418 "cannot free skb -- memory leaked."); 419 return; 420 } 421 skb->truesize -= skb->data_len; 422 skb_shinfo(skb)->nr_frags = skb->data_len = 0; 423 skb_trim(skb, 0); 424 dev_kfree_skb(skb); 425} 426 427static void 428skbpoolfree(struct aoedev *d) 429{ 430 struct sk_buff *skb, *tmp; 431 432 skb_queue_walk_safe(&d->skbpool, skb, tmp) 433 skbfree(skb); 434 435 __skb_queue_head_init(&d->skbpool); 436} 437 438/* find it or allocate it */ 439struct aoedev * 440aoedev_by_aoeaddr(ulong maj, int min, int do_alloc) 441{ 442 struct aoedev *d; 443 int i; 444 ulong flags; 445 ulong sysminor = 0; 446 447 spin_lock_irqsave(&devlist_lock, flags); 448 449 for (d=devlist; d; d=d->next) 450 if (d->aoemajor == maj && d->aoeminor == min) { 451 spin_lock(&d->lock); 452 if (d->flags & DEVFL_TKILL) { 453 spin_unlock(&d->lock); 454 d = NULL; 455 goto out; 456 } 457 d->ref++; 458 spin_unlock(&d->lock); 459 break; 460 } 461 if (d || !do_alloc || minor_get(&sysminor, maj, min) < 0) 462 goto out; 463 d = kcalloc(1, sizeof *d, GFP_ATOMIC); 464 if (!d) 465 goto out; 466 d->targets = kcalloc(NTARGETS, sizeof(*d->targets), GFP_ATOMIC); 467 if (!d->targets) { 468 kfree(d); 469 d = NULL; 470 goto out; 471 } 472 d->ntargets = NTARGETS; 473 INIT_WORK(&d->work, aoecmd_sleepwork); 474 spin_lock_init(&d->lock); 475 INIT_LIST_HEAD(&d->rq_list); 476 skb_queue_head_init(&d->skbpool); 477 timer_setup(&d->timer, dummy_timer, 0); 478 d->timer.expires = jiffies + HZ; 479 add_timer(&d->timer); 480 d->bufpool = NULL; /* defer to aoeblk_gdalloc */ 481 d->tgt = d->targets; 482 d->ref = 1; 483 for (i = 0; i < NFACTIVE; i++) 484 INIT_LIST_HEAD(&d->factive[i]); 485 INIT_LIST_HEAD(&d->rexmitq); 486 d->sysminor = sysminor; 487 d->aoemajor = maj; 488 d->aoeminor = min; 489 d->rttavg = RTTAVG_INIT; 490 d->rttdev = RTTDEV_INIT; 491 d->next = devlist; 492 devlist = d; 493 out: 494 spin_unlock_irqrestore(&devlist_lock, flags); 495 return d; 496} 497 498static void 499freetgt(struct aoedev *d, struct aoetgt *t) 500{ 501 struct frame *f; 502 struct list_head *pos, *nx, *head; 503 struct aoeif *ifp; 504 505 for (ifp = t->ifs; ifp < &t->ifs[NAOEIFS]; ++ifp) { 506 if (!ifp->nd) 507 break; 508 dev_put(ifp->nd); 509 } 510 511 head = &t->ffree; 512 list_for_each_safe(pos, nx, head) { 513 list_del(pos); 514 f = list_entry(pos, struct frame, head); 515 skbfree(f->skb); 516 kfree(f); 517 } 518 kfree(t); 519} 520 521void 522aoedev_exit(void) 523{ 524 flush_scheduled_work(); 525 flush(NULL, 0, EXITING); 526} 527 528int __init 529aoedev_init(void) 530{ 531 return 0; 532} 533