Blame view
block/genhd.c
42.8 KB
1da177e4c
|
1 2 3 |
/* * gendisk handling */ |
1da177e4c
|
4 5 6 |
#include <linux/module.h> #include <linux/fs.h> #include <linux/genhd.h> |
b446b60e4
|
7 |
#include <linux/kdev_t.h> |
1da177e4c
|
8 9 10 11 |
#include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/init.h> #include <linux/spinlock.h> |
f500975a3
|
12 |
#include <linux/proc_fs.h> |
1da177e4c
|
13 14 15 16 |
#include <linux/seq_file.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/kobj_map.h> |
58383af62
|
17 |
#include <linux/mutex.h> |
bcce3de1b
|
18 |
#include <linux/idr.h> |
77ea887e4
|
19 |
#include <linux/log2.h> |
1da177e4c
|
20 |
|
ff88972c8
|
21 |
#include "blk.h" |
edfaa7c36
|
22 |
static DEFINE_MUTEX(block_class_lock); |
edfaa7c36
|
23 |
struct kobject *block_depr; |
1da177e4c
|
24 |
|
bcce3de1b
|
25 26 27 28 29 30 31 32 |
/* for extended dynamic devt allocation, currently only one major is used */ #define MAX_EXT_DEVT (1 << MINORBITS) /* For extended devt allocation. ext_devt_mutex prevents look up * results from going away underneath its user. */ static DEFINE_MUTEX(ext_devt_mutex); static DEFINE_IDR(ext_devt_idr); |
1826eadfc
|
33 |
static struct device_type disk_type; |
77ea887e4
|
34 35 36 |
static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); |
e71bf0d0e
|
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
/** * disk_get_part - get partition * @disk: disk to look partition from * @partno: partition number * * Look for partition @partno from @disk. If found, increment * reference count and return it. * * CONTEXT: * Don't care. * * RETURNS: * Pointer to the found partition on success, NULL if not found. */ struct hd_struct *disk_get_part(struct gendisk *disk, int partno) { |
540eed563
|
53 54 |
struct hd_struct *part = NULL; struct disk_part_tbl *ptbl; |
e71bf0d0e
|
55 |
|
540eed563
|
56 |
if (unlikely(partno < 0)) |
e71bf0d0e
|
57 |
return NULL; |
540eed563
|
58 |
|
e71bf0d0e
|
59 |
rcu_read_lock(); |
540eed563
|
60 61 62 63 64 65 66 |
ptbl = rcu_dereference(disk->part_tbl); if (likely(partno < ptbl->len)) { part = rcu_dereference(ptbl->part[partno]); if (part) get_device(part_to_dev(part)); } |
e71bf0d0e
|
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
rcu_read_unlock(); return part; } EXPORT_SYMBOL_GPL(disk_get_part); /** * disk_part_iter_init - initialize partition iterator * @piter: iterator to initialize * @disk: disk to iterate over * @flags: DISK_PITER_* flags * * Initialize @piter so that it iterates over partitions of @disk. * * CONTEXT: * Don't care. */ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk, unsigned int flags) { |
540eed563
|
87 88 89 90 |
struct disk_part_tbl *ptbl; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); |
e71bf0d0e
|
91 92 93 94 |
piter->disk = disk; piter->part = NULL; if (flags & DISK_PITER_REVERSE) |
540eed563
|
95 |
piter->idx = ptbl->len - 1; |
71982a409
|
96 |
else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) |
e71bf0d0e
|
97 |
piter->idx = 0; |
b5d0b9df0
|
98 99 |
else piter->idx = 1; |
e71bf0d0e
|
100 101 |
piter->flags = flags; |
540eed563
|
102 103 |
rcu_read_unlock(); |
e71bf0d0e
|
104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
} EXPORT_SYMBOL_GPL(disk_part_iter_init); /** * disk_part_iter_next - proceed iterator to the next partition and return it * @piter: iterator of interest * * Proceed @piter to the next partition and return it. * * CONTEXT: * Don't care. */ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) { |
540eed563
|
118 |
struct disk_part_tbl *ptbl; |
e71bf0d0e
|
119 120 121 122 123 |
int inc, end; /* put the last partition */ disk_put_part(piter->part); piter->part = NULL; |
540eed563
|
124 |
/* get part_tbl */ |
e71bf0d0e
|
125 |
rcu_read_lock(); |
540eed563
|
126 |
ptbl = rcu_dereference(piter->disk->part_tbl); |
e71bf0d0e
|
127 128 129 130 |
/* determine iteration parameters */ if (piter->flags & DISK_PITER_REVERSE) { inc = -1; |
71982a409
|
131 132 |
if (piter->flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) |
b5d0b9df0
|
133 134 135 |
end = -1; else end = 0; |
e71bf0d0e
|
136 137 |
} else { inc = 1; |
540eed563
|
138 |
end = ptbl->len; |
e71bf0d0e
|
139 140 141 142 143 |
} /* iterate to the next partition */ for (; piter->idx != end; piter->idx += inc) { struct hd_struct *part; |
540eed563
|
144 |
part = rcu_dereference(ptbl->part[piter->idx]); |
e71bf0d0e
|
145 146 |
if (!part) continue; |
71982a409
|
147 148 149 150 |
if (!part->nr_sects && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) |
e71bf0d0e
|
151 |
continue; |
ed9e19823
|
152 |
get_device(part_to_dev(part)); |
e71bf0d0e
|
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 |
piter->part = part; piter->idx += inc; break; } rcu_read_unlock(); return piter->part; } EXPORT_SYMBOL_GPL(disk_part_iter_next); /** * disk_part_iter_exit - finish up partition iteration * @piter: iter of interest * * Called when iteration is over. Cleans up @piter. * * CONTEXT: * Don't care. */ void disk_part_iter_exit(struct disk_part_iter *piter) { disk_put_part(piter->part); piter->part = NULL; } EXPORT_SYMBOL_GPL(disk_part_iter_exit); |
a6f23657d
|
179 180 181 182 183 |
static inline int sector_in_part(struct hd_struct *part, sector_t sector) { return part->start_sect <= sector && sector < part->start_sect + part->nr_sects; } |
e71bf0d0e
|
184 185 186 187 188 189 190 191 192 193 194 195 196 |
/** * disk_map_sector_rcu - map sector to partition * @disk: gendisk of interest * @sector: sector to map * * Find out which partition @sector maps to on @disk. This is * primarily used for stats accounting. * * CONTEXT: * RCU read locked. The returned partition pointer is valid only * while preemption is disabled. * * RETURNS: |
074a7aca7
|
197 |
* Found partition on success, part0 is returned if no partition matches |
e71bf0d0e
|
198 199 200 |
*/ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { |
540eed563
|
201 |
struct disk_part_tbl *ptbl; |
a6f23657d
|
202 |
struct hd_struct *part; |
e71bf0d0e
|
203 |
int i; |
540eed563
|
204 |
ptbl = rcu_dereference(disk->part_tbl); |
a6f23657d
|
205 206 207 |
part = rcu_dereference(ptbl->last_lookup); if (part && sector_in_part(part, sector)) return part; |
540eed563
|
208 |
for (i = 1; i < ptbl->len; i++) { |
a6f23657d
|
209 |
part = rcu_dereference(ptbl->part[i]); |
e71bf0d0e
|
210 |
|
a6f23657d
|
211 212 |
if (part && sector_in_part(part, sector)) { rcu_assign_pointer(ptbl->last_lookup, part); |
e71bf0d0e
|
213 |
return part; |
a6f23657d
|
214 |
} |
e71bf0d0e
|
215 |
} |
074a7aca7
|
216 |
return &disk->part0; |
e71bf0d0e
|
217 218 |
} EXPORT_SYMBOL_GPL(disk_map_sector_rcu); |
1da177e4c
|
219 220 221 222 223 224 225 226 |
/* * Can be deleted altogether. Later. * */ static struct blk_major_name { struct blk_major_name *next; int major; char name[16]; |
68eef3b47
|
227 |
} *major_names[BLKDEV_MAJOR_HASH_SIZE]; |
1da177e4c
|
228 229 |
/* index in the above - for now: assume no multimajor ranges */ |
e61eb2e93
|
230 |
static inline int major_to_index(unsigned major) |
1da177e4c
|
231 |
{ |
68eef3b47
|
232 |
return major % BLKDEV_MAJOR_HASH_SIZE; |
7170be5f5
|
233 |
} |
68eef3b47
|
234 |
#ifdef CONFIG_PROC_FS |
cf771cb5a
|
235 |
void blkdev_show(struct seq_file *seqf, off_t offset) |
7170be5f5
|
236 |
{ |
68eef3b47
|
237 |
struct blk_major_name *dp; |
7170be5f5
|
238 |
|
68eef3b47
|
239 |
if (offset < BLKDEV_MAJOR_HASH_SIZE) { |
edfaa7c36
|
240 |
mutex_lock(&block_class_lock); |
68eef3b47
|
241 |
for (dp = major_names[offset]; dp; dp = dp->next) |
cf771cb5a
|
242 243 |
seq_printf(seqf, "%3d %s ", dp->major, dp->name); |
edfaa7c36
|
244 |
mutex_unlock(&block_class_lock); |
1da177e4c
|
245 |
} |
1da177e4c
|
246 |
} |
68eef3b47
|
247 |
#endif /* CONFIG_PROC_FS */ |
1da177e4c
|
248 |
|
9e8c0bccd
|
249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 |
/** * register_blkdev - register a new block device * * @major: the requested major device number [1..255]. If @major=0, try to * allocate any unused major number. * @name: the name of the new block device as a zero terminated string * * The @name must be unique within the system. * * The return value depends on the @major input parameter. * - if a major device number was requested in range [1..255] then the * function returns zero on success, or a negative error code * - if any unused major number was requested with @major=0 parameter * then the return value is the allocated major number in range * [1..255] or a negative error code otherwise */ |
1da177e4c
|
265 266 267 268 |
int register_blkdev(unsigned int major, const char *name) { struct blk_major_name **n, *p; int index, ret = 0; |
edfaa7c36
|
269 |
mutex_lock(&block_class_lock); |
1da177e4c
|
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 |
/* temporary */ if (major == 0) { for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) { if (major_names[index] == NULL) break; } if (index == 0) { printk("register_blkdev: failed to get major for %s ", name); ret = -EBUSY; goto out; } major = index; ret = major; } p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL); if (p == NULL) { ret = -ENOMEM; goto out; } p->major = major; strlcpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); for (n = &major_names[index]; *n; n = &(*n)->next) { if ((*n)->major == major) break; } if (!*n) *n = p; else ret = -EBUSY; if (ret < 0) { printk("register_blkdev: cannot get major %d for %s ", major, name); kfree(p); } out: |
edfaa7c36
|
316 |
mutex_unlock(&block_class_lock); |
1da177e4c
|
317 318 319 320 |
return ret; } EXPORT_SYMBOL(register_blkdev); |
f4480240f
|
321 |
void unregister_blkdev(unsigned int major, const char *name) |
1da177e4c
|
322 323 324 325 |
{ struct blk_major_name **n; struct blk_major_name *p = NULL; int index = major_to_index(major); |
1da177e4c
|
326 |
|
edfaa7c36
|
327 |
mutex_lock(&block_class_lock); |
1da177e4c
|
328 329 330 |
for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; |
294462a5c
|
331 332 |
if (!*n || strcmp((*n)->name, name)) { WARN_ON(1); |
294462a5c
|
333 |
} else { |
1da177e4c
|
334 335 336 |
p = *n; *n = p->next; } |
edfaa7c36
|
337 |
mutex_unlock(&block_class_lock); |
1da177e4c
|
338 |
kfree(p); |
1da177e4c
|
339 340 341 342 343 |
} EXPORT_SYMBOL(unregister_blkdev); static struct kobj_map *bdev_map; |
bcce3de1b
|
344 |
/** |
870d66561
|
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 |
* blk_mangle_minor - scatter minor numbers apart * @minor: minor number to mangle * * Scatter consecutively allocated @minor number apart if MANGLE_DEVT * is enabled. Mangling twice gives the original value. * * RETURNS: * Mangled value. * * CONTEXT: * Don't care. */ static int blk_mangle_minor(int minor) { #ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT int i; for (i = 0; i < MINORBITS / 2; i++) { int low = minor & (1 << i); int high = minor & (1 << (MINORBITS - 1 - i)); int distance = MINORBITS - 1 - 2 * i; minor ^= low | high; /* clear both bits */ low <<= distance; /* swap the positions */ high >>= distance; minor |= low | high; /* and set */ } #endif return minor; } /** |
bcce3de1b
|
377 378 |
* blk_alloc_devt - allocate a dev_t for a partition * @part: partition to allocate dev_t for |
bcce3de1b
|
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 |
* @devt: out parameter for resulting dev_t * * Allocate a dev_t for block device. * * RETURNS: * 0 on success, allocated dev_t is returned in *@devt. -errno on * failure. * * CONTEXT: * Might sleep. */ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) { struct gendisk *disk = part_to_disk(part); int idx, rc; /* in consecutive minor range? */ if (part->partno < disk->minors) { *devt = MKDEV(disk->major, disk->first_minor + part->partno); return 0; } /* allocate ext devt */ do { if (!idr_pre_get(&ext_devt_idr, GFP_KERNEL)) return -ENOMEM; rc = idr_get_new(&ext_devt_idr, part, &idx); } while (rc == -EAGAIN); if (rc) return rc; if (idx > MAX_EXT_DEVT) { idr_remove(&ext_devt_idr, idx); return -EBUSY; } |
870d66561
|
415 |
*devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); |
bcce3de1b
|
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 |
return 0; } /** * blk_free_devt - free a dev_t * @devt: dev_t to free * * Free @devt which was allocated using blk_alloc_devt(). * * CONTEXT: * Might sleep. */ void blk_free_devt(dev_t devt) { might_sleep(); if (devt == MKDEV(0, 0)) return; if (MAJOR(devt) == BLOCK_EXT_MAJOR) { mutex_lock(&ext_devt_mutex); |
870d66561
|
437 |
idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); |
bcce3de1b
|
438 439 440 |
mutex_unlock(&ext_devt_mutex); } } |
1f0142905
|
441 442 443 444 445 446 447 448 449 450 451 |
static char *bdevt_str(dev_t devt, char *buf) { if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { char tbuf[BDEVT_SIZE]; snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); } else snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); return buf; } |
1da177e4c
|
452 453 454 455 456 |
/* * Register device numbers dev..(dev+range-1) * range must be nonzero * The hash chain is sorted on range, so that subranges can override. */ |
edfaa7c36
|
457 |
void blk_register_region(dev_t devt, unsigned long range, struct module *module, |
1da177e4c
|
458 459 460 |
struct kobject *(*probe)(dev_t, int *, void *), int (*lock)(dev_t, void *), void *data) { |
edfaa7c36
|
461 |
kobj_map(bdev_map, devt, range, module, probe, lock, data); |
1da177e4c
|
462 463 464 |
} EXPORT_SYMBOL(blk_register_region); |
edfaa7c36
|
465 |
void blk_unregister_region(dev_t devt, unsigned long range) |
1da177e4c
|
466 |
{ |
edfaa7c36
|
467 |
kobj_unmap(bdev_map, devt, range); |
1da177e4c
|
468 469 470 |
} EXPORT_SYMBOL(blk_unregister_region); |
cf771cb5a
|
471 |
static struct kobject *exact_match(dev_t devt, int *partno, void *data) |
1da177e4c
|
472 473 |
{ struct gendisk *p = data; |
edfaa7c36
|
474 |
|
ed9e19823
|
475 |
return &disk_to_dev(p)->kobj; |
1da177e4c
|
476 |
} |
edfaa7c36
|
477 |
static int exact_lock(dev_t devt, void *data) |
1da177e4c
|
478 479 480 481 482 483 484 |
{ struct gendisk *p = data; if (!get_disk(p)) return -1; return 0; } |
4752bc309
|
485 |
static void register_disk(struct gendisk *disk) |
d2bf1b672
|
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 |
{ struct device *ddev = disk_to_dev(disk); struct block_device *bdev; struct disk_part_iter piter; struct hd_struct *part; int err; ddev->parent = disk->driverfs_dev; dev_set_name(ddev, disk->disk_name); /* delay uevents, until we scanned partition table */ dev_set_uevent_suppress(ddev, 1); if (device_add(ddev)) return; if (!sysfs_deprecated) { err = sysfs_create_link(block_depr, &ddev->kobj, kobject_name(&ddev->kobj)); if (err) { device_del(ddev); return; } } disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); /* No minors to use for partitions */ |
d27769ec3
|
514 |
if (!disk_part_scan_enabled(disk)) |
d2bf1b672
|
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 |
goto exit; /* No such device (e.g., media were just removed) */ if (!get_capacity(disk)) goto exit; bdev = bdget_disk(disk, 0); if (!bdev) goto exit; bdev->bd_invalidated = 1; err = blkdev_get(bdev, FMODE_READ, NULL); if (err < 0) goto exit; blkdev_put(bdev, FMODE_READ); exit: /* announce disk after possible partitions are created */ dev_set_uevent_suppress(ddev, 0); kobject_uevent(&ddev->kobj, KOBJ_ADD); /* announce possible partitions */ disk_part_iter_init(&piter, disk, 0); while ((part = disk_part_iter_next(&piter))) kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD); disk_part_iter_exit(&piter); } |
1da177e4c
|
542 543 544 545 546 547 |
/** * add_disk - add partitioning information to kernel list * @disk: per-device partitioning information * * This function registers the partitioning information in @disk * with the kernel. |
3e1a7ff8a
|
548 549 |
* * FIXME: error handling |
1da177e4c
|
550 551 552 |
*/ void add_disk(struct gendisk *disk) { |
cf0ca9fe5
|
553 |
struct backing_dev_info *bdi; |
3e1a7ff8a
|
554 |
dev_t devt; |
6ffeea77f
|
555 |
int retval; |
cf0ca9fe5
|
556 |
|
3e1a7ff8a
|
557 558 559 560 561 562 |
/* minors == 0 indicates to use ext devt from part0 and should * be accompanied with EXT_DEVT flag. Make sure all * parameters make sense. */ WARN_ON(disk->minors && !(disk->major || disk->first_minor)); WARN_ON(!disk->minors && !(disk->flags & GENHD_FL_EXT_DEVT)); |
1da177e4c
|
563 |
disk->flags |= GENHD_FL_UP; |
3e1a7ff8a
|
564 565 566 567 568 569 570 571 572 573 574 575 576 |
retval = blk_alloc_devt(&disk->part0, &devt); if (retval) { WARN_ON(1); return; } disk_to_dev(disk)->devt = devt; /* ->major and ->first_minor aren't supposed to be * dereferenced from here on, but set them just in case. */ disk->major = MAJOR(devt); disk->first_minor = MINOR(devt); |
9f5e48655
|
577 |
/* Register BDI before referencing it from bdev */ |
01ea50638
|
578 579 |
bdi = &disk->queue->backing_dev_info; bdi_register_dev(bdi, disk_devt(disk)); |
f331c0296
|
580 581 |
blk_register_region(disk_devt(disk), disk->minors, NULL, exact_match, exact_lock, disk); |
1da177e4c
|
582 583 |
register_disk(disk); blk_register_queue(disk); |
cf0ca9fe5
|
584 |
|
523e1d399
|
585 586 587 588 |
/* * Take an extra ref on queue which will be put on disk_release() * so that it sticks around as long as @disk is there. */ |
09ac46c42
|
589 |
WARN_ON_ONCE(!blk_get_queue(disk->queue)); |
523e1d399
|
590 |
|
ed9e19823
|
591 592 |
retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj, "bdi"); |
6ffeea77f
|
593 |
WARN_ON(retval); |
1da177e4c
|
594 |
|
77ea887e4
|
595 |
disk_add_events(disk); |
1da177e4c
|
596 |
} |
1da177e4c
|
597 |
EXPORT_SYMBOL(add_disk); |
1da177e4c
|
598 |
|
d2bf1b672
|
599 |
void del_gendisk(struct gendisk *disk) |
1da177e4c
|
600 |
{ |
d2bf1b672
|
601 602 |
struct disk_part_iter piter; struct hd_struct *part; |
77ea887e4
|
603 |
disk_del_events(disk); |
d2bf1b672
|
604 605 606 607 608 609 610 611 612 613 614 615 616 |
/* invalidate stuff */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE); while ((part = disk_part_iter_next(&piter))) { invalidate_partition(disk, part->partno); delete_partition(disk, part->partno); } disk_part_iter_exit(&piter); invalidate_partition(disk, 0); blk_free_devt(disk_to_dev(disk)->devt); set_capacity(disk, 0); disk->flags &= ~GENHD_FL_UP; |
ed9e19823
|
617 |
sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); |
cf0ca9fe5
|
618 |
bdi_unregister(&disk->queue->backing_dev_info); |
1da177e4c
|
619 |
blk_unregister_queue(disk); |
f331c0296
|
620 |
blk_unregister_region(disk_devt(disk), disk->minors); |
d2bf1b672
|
621 622 623 624 625 626 627 628 629 630 |
part_stat_set_all(&disk->part0, 0); disk->part0.stamp = 0; kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); disk->driverfs_dev = NULL; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); device_del(disk_to_dev(disk)); |
1da177e4c
|
631 |
} |
d2bf1b672
|
632 |
EXPORT_SYMBOL(del_gendisk); |
1da177e4c
|
633 |
|
1da177e4c
|
634 635 |
/** * get_gendisk - get partitioning information for a given device |
710027a48
|
636 |
* @devt: device to get partitioning information for |
496aa8a98
|
637 |
* @partno: returned partition index |
1da177e4c
|
638 639 |
* * This function gets the structure containing partitioning |
710027a48
|
640 |
* information for the given device @devt. |
1da177e4c
|
641 |
*/ |
cf771cb5a
|
642 |
struct gendisk *get_gendisk(dev_t devt, int *partno) |
1da177e4c
|
643 |
{ |
bcce3de1b
|
644 645 646 647 648 649 650 651 652 653 654 655 |
struct gendisk *disk = NULL; if (MAJOR(devt) != BLOCK_EXT_MAJOR) { struct kobject *kobj; kobj = kobj_lookup(bdev_map, devt, partno); if (kobj) disk = dev_to_disk(kobj_to_dev(kobj)); } else { struct hd_struct *part; mutex_lock(&ext_devt_mutex); |
870d66561
|
656 |
part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); |
bcce3de1b
|
657 658 659 660 661 662 |
if (part && get_disk(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } mutex_unlock(&ext_devt_mutex); } |
edfaa7c36
|
663 |
|
bcce3de1b
|
664 |
return disk; |
1da177e4c
|
665 |
} |
b6ac23af2
|
666 |
EXPORT_SYMBOL(get_gendisk); |
1da177e4c
|
667 |
|
f331c0296
|
668 669 670 671 672 673 674 675 676 677 678 679 680 |
/** * bdget_disk - do bdget() by gendisk and partition number * @disk: gendisk of interest * @partno: partition number * * Find partition @partno from @disk, do bdget() on it. * * CONTEXT: * Don't care. * * RETURNS: * Resulting block_device on success, NULL on failure. */ |
aeb3d3a81
|
681 |
struct block_device *bdget_disk(struct gendisk *disk, int partno) |
f331c0296
|
682 |
{ |
548b10eb2
|
683 684 |
struct hd_struct *part; struct block_device *bdev = NULL; |
f331c0296
|
685 |
|
548b10eb2
|
686 |
part = disk_get_part(disk, partno); |
2bbedcb4c
|
687 |
if (part) |
548b10eb2
|
688 689 |
bdev = bdget(part_devt(part)); disk_put_part(part); |
f331c0296
|
690 |
|
548b10eb2
|
691 |
return bdev; |
f331c0296
|
692 693 |
} EXPORT_SYMBOL(bdget_disk); |
dd2a345f8
|
694 |
/* |
5c6f35c5e
|
695 696 697 698 699 700 |
* print a full list of all partitions - intended for places where the root * filesystem can't be mounted and thus to give the victim some idea of what * went wrong */ void __init printk_all_partitions(void) { |
def4e38dd
|
701 702 703 704 705 706 |
struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); |
e71bf0d0e
|
707 708 |
struct disk_part_iter piter; struct hd_struct *part; |
1f0142905
|
709 710 |
char name_buf[BDEVNAME_SIZE]; char devt_buf[BDEVT_SIZE]; |
b5af921ec
|
711 |
u8 uuid[PARTITION_META_INFO_UUIDLTH * 2 + 1]; |
def4e38dd
|
712 713 714 |
/* * Don't show empty devices or things that have been |
25985edce
|
715 |
* suppressed |
def4e38dd
|
716 717 718 719 720 721 722 723 724 725 |
*/ if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)) continue; /* * Note, unlike /proc/partitions, I am showing the * numbers in hex - the same format as the root= * option takes. */ |
074a7aca7
|
726 727 728 |
disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) { bool is_part0 = part == &disk->part0; |
def4e38dd
|
729 |
|
b5af921ec
|
730 731 732 733 734 |
uuid[0] = 0; if (part->info) part_unpack_uuid(part->info->uuid, uuid); printk("%s%s %10llu %s %s", is_part0 ? "" : " ", |
1f0142905
|
735 |
bdevt_str(part_devt(part), devt_buf), |
f331c0296
|
736 |
(unsigned long long)part->nr_sects >> 1, |
b5af921ec
|
737 |
disk_name(disk, part->partno, name_buf), uuid); |
074a7aca7
|
738 739 740 741 742 743 744 745 746 747 748 749 750 |
if (is_part0) { if (disk->driverfs_dev != NULL && disk->driverfs_dev->driver != NULL) printk(" driver: %s ", disk->driverfs_dev->driver->name); else printk(" (driver?) "); } else printk(" "); } |
e71bf0d0e
|
751 |
disk_part_iter_exit(&piter); |
def4e38dd
|
752 753 |
} class_dev_iter_exit(&iter); |
dd2a345f8
|
754 |
} |
1da177e4c
|
755 756 |
#ifdef CONFIG_PROC_FS /* iterator */ |
def4e38dd
|
757 |
static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos) |
68c4d4a78
|
758 |
{ |
def4e38dd
|
759 760 761 |
loff_t skip = *pos; struct class_dev_iter *iter; struct device *dev; |
68c4d4a78
|
762 |
|
aeb3d3a81
|
763 |
iter = kmalloc(sizeof(*iter), GFP_KERNEL); |
def4e38dd
|
764 765 766 767 768 769 770 771 772 773 774 775 |
if (!iter) return ERR_PTR(-ENOMEM); seqf->private = iter; class_dev_iter_init(iter, &block_class, NULL, &disk_type); do { dev = class_dev_iter_next(iter); if (!dev) return NULL; } while (skip--); return dev_to_disk(dev); |
68c4d4a78
|
776 |
} |
def4e38dd
|
777 |
static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos) |
1da177e4c
|
778 |
{ |
edfaa7c36
|
779 |
struct device *dev; |
1da177e4c
|
780 |
|
def4e38dd
|
781 782 |
(*pos)++; dev = class_dev_iter_next(seqf->private); |
2ac3cee52
|
783 |
if (dev) |
68c4d4a78
|
784 |
return dev_to_disk(dev); |
2ac3cee52
|
785 |
|
1da177e4c
|
786 787 |
return NULL; } |
def4e38dd
|
788 |
static void disk_seqf_stop(struct seq_file *seqf, void *v) |
27f302519
|
789 |
{ |
def4e38dd
|
790 |
struct class_dev_iter *iter = seqf->private; |
27f302519
|
791 |
|
def4e38dd
|
792 793 794 795 |
/* stop is called even after start failed :-( */ if (iter) { class_dev_iter_exit(iter); kfree(iter); |
5c0ef6d02
|
796 |
} |
1da177e4c
|
797 |
} |
def4e38dd
|
798 |
static void *show_partition_start(struct seq_file *seqf, loff_t *pos) |
1da177e4c
|
799 |
{ |
def4e38dd
|
800 801 802 |
static void *p; p = disk_seqf_start(seqf, pos); |
b9f985b6e
|
803 |
if (!IS_ERR_OR_NULL(p) && !*pos) |
def4e38dd
|
804 805 806 807 |
seq_puts(seqf, "major minor #blocks name "); return p; |
1da177e4c
|
808 |
} |
cf771cb5a
|
809 |
static int show_partition(struct seq_file *seqf, void *v) |
1da177e4c
|
810 811 |
{ struct gendisk *sgp = v; |
e71bf0d0e
|
812 813 |
struct disk_part_iter piter; struct hd_struct *part; |
1da177e4c
|
814 |
char buf[BDEVNAME_SIZE]; |
1da177e4c
|
815 |
/* Don't show non-partitionable removeable devices or empty devices */ |
d27769ec3
|
816 |
if (!get_capacity(sgp) || (!disk_max_parts(sgp) && |
f331c0296
|
817 |
(sgp->flags & GENHD_FL_REMOVABLE))) |
1da177e4c
|
818 819 820 821 822 |
return 0; if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) return 0; /* show the full disk and all non-0 size partitions of it */ |
074a7aca7
|
823 |
disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0); |
e71bf0d0e
|
824 |
while ((part = disk_part_iter_next(&piter))) |
1f0142905
|
825 826 |
seq_printf(seqf, "%4d %7d %10llu %s ", |
f331c0296
|
827 828 829 |
MAJOR(part_devt(part)), MINOR(part_devt(part)), (unsigned long long)part->nr_sects >> 1, disk_name(sgp, part->partno, buf)); |
e71bf0d0e
|
830 |
disk_part_iter_exit(&piter); |
1da177e4c
|
831 832 833 |
return 0; } |
f500975a3
|
834 |
static const struct seq_operations partitions_op = { |
def4e38dd
|
835 836 837 |
.start = show_partition_start, .next = disk_seqf_next, .stop = disk_seqf_stop, |
edfaa7c36
|
838 |
.show = show_partition |
1da177e4c
|
839 |
}; |
f500975a3
|
840 841 842 843 844 845 846 847 848 849 850 851 |
static int partitions_open(struct inode *inode, struct file *file) { return seq_open(file, &partitions_op); } static const struct file_operations proc_partitions_operations = { .open = partitions_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
1da177e4c
|
852 |
#endif |
cf771cb5a
|
853 |
static struct kobject *base_probe(dev_t devt, int *partno, void *data) |
1da177e4c
|
854 |
{ |
edfaa7c36
|
855 |
if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0) |
1da177e4c
|
856 |
/* Make old-style 2.4 aliases work */ |
edfaa7c36
|
857 |
request_module("block-major-%d", MAJOR(devt)); |
1da177e4c
|
858 859 860 861 862 |
return NULL; } static int __init genhd_device_init(void) { |
e105b8bfc
|
863 864 865 866 |
int error; block_class.dev_kobj = sysfs_dev_block_kobj; error = class_register(&block_class); |
ee27a558a
|
867 868 |
if (unlikely(error)) return error; |
edfaa7c36
|
869 |
bdev_map = kobj_map_init(base_probe, &block_class_lock); |
1da177e4c
|
870 |
blk_dev_init(); |
edfaa7c36
|
871 |
|
561ec68e4
|
872 |
register_blkdev(BLOCK_EXT_MAJOR, "blkext"); |
edfaa7c36
|
873 |
/* create top-level block dir */ |
e52eec13c
|
874 875 |
if (!sysfs_deprecated) block_depr = kobject_create_and_add("block", NULL); |
830d3cfb1
|
876 |
return 0; |
1da177e4c
|
877 878 879 |
} subsys_initcall(genhd_device_init); |
edfaa7c36
|
880 881 |
static ssize_t disk_range_show(struct device *dev, struct device_attribute *attr, char *buf) |
1da177e4c
|
882 |
{ |
edfaa7c36
|
883 |
struct gendisk *disk = dev_to_disk(dev); |
1da177e4c
|
884 |
|
edfaa7c36
|
885 886 |
return sprintf(buf, "%d ", disk->minors); |
1da177e4c
|
887 |
} |
1f0142905
|
888 889 890 891 |
static ssize_t disk_ext_range_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); |
b5d0b9df0
|
892 893 |
return sprintf(buf, "%d ", disk_max_parts(disk)); |
1f0142905
|
894 |
} |
edfaa7c36
|
895 896 |
static ssize_t disk_removable_show(struct device *dev, struct device_attribute *attr, char *buf) |
a7fd67062
|
897 |
{ |
edfaa7c36
|
898 |
struct gendisk *disk = dev_to_disk(dev); |
a7fd67062
|
899 |
|
edfaa7c36
|
900 901 902 |
return sprintf(buf, "%d ", (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0)); |
a7fd67062
|
903 |
} |
1c9ce5276
|
904 905 906 907 |
static ssize_t disk_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); |
b7db9956e
|
908 909 |
return sprintf(buf, "%d ", get_disk_ro(disk) ? 1 : 0); |
1c9ce5276
|
910 |
} |
edfaa7c36
|
911 912 |
static ssize_t disk_capability_show(struct device *dev, struct device_attribute *attr, char *buf) |
86ce18d7b
|
913 |
{ |
edfaa7c36
|
914 915 916 917 |
struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%x ", disk->flags); |
86ce18d7b
|
918 |
} |
edfaa7c36
|
919 |
|
c72758f33
|
920 921 922 923 924 925 926 927 928 |
static ssize_t disk_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d ", queue_alignment_offset(disk->queue)); } |
86b372814
|
929 930 931 932 933 |
static ssize_t disk_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); |
dd3d145d4
|
934 935 |
return sprintf(buf, "%d ", queue_discard_alignment(disk->queue)); |
86b372814
|
936 |
} |
edfaa7c36
|
937 |
static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL); |
1f0142905
|
938 |
static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL); |
edfaa7c36
|
939 |
static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL); |
1c9ce5276
|
940 |
static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL); |
e56105214
|
941 |
static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); |
c72758f33
|
942 |
static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); |
86b372814
|
943 944 |
static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show, NULL); |
edfaa7c36
|
945 |
static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); |
074a7aca7
|
946 |
static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); |
316d315bf
|
947 |
static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); |
c17bb4951
|
948 |
#ifdef CONFIG_FAIL_MAKE_REQUEST |
edfaa7c36
|
949 |
static struct device_attribute dev_attr_fail = |
eddb2e26b
|
950 |
__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); |
c17bb4951
|
951 |
#endif |
581d4e28d
|
952 953 954 955 956 |
#ifdef CONFIG_FAIL_IO_TIMEOUT static struct device_attribute dev_attr_fail_timeout = __ATTR(io-timeout-fail, S_IRUGO|S_IWUSR, part_timeout_show, part_timeout_store); #endif |
edfaa7c36
|
957 958 959 |
static struct attribute *disk_attrs[] = { &dev_attr_range.attr, |
1f0142905
|
960 |
&dev_attr_ext_range.attr, |
edfaa7c36
|
961 |
&dev_attr_removable.attr, |
1c9ce5276
|
962 |
&dev_attr_ro.attr, |
edfaa7c36
|
963 |
&dev_attr_size.attr, |
c72758f33
|
964 |
&dev_attr_alignment_offset.attr, |
86b372814
|
965 |
&dev_attr_discard_alignment.attr, |
edfaa7c36
|
966 967 |
&dev_attr_capability.attr, &dev_attr_stat.attr, |
316d315bf
|
968 |
&dev_attr_inflight.attr, |
edfaa7c36
|
969 970 971 |
#ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif |
581d4e28d
|
972 973 974 |
#ifdef CONFIG_FAIL_IO_TIMEOUT &dev_attr_fail_timeout.attr, #endif |
edfaa7c36
|
975 976 977 978 979 980 |
NULL }; static struct attribute_group disk_attr_group = { .attrs = disk_attrs, }; |
a4dbd6740
|
981 |
static const struct attribute_group *disk_attr_groups[] = { |
edfaa7c36
|
982 983 |
&disk_attr_group, NULL |
1da177e4c
|
984 |
}; |
540eed563
|
985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 |
/** * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way * @disk: disk to replace part_tbl for * @new_ptbl: new part_tbl to install * * Replace disk->part_tbl with @new_ptbl in RCU-safe way. The * original ptbl is freed using RCU callback. * * LOCKING: * Matching bd_mutx locked. */ static void disk_replace_part_tbl(struct gendisk *disk, struct disk_part_tbl *new_ptbl) { struct disk_part_tbl *old_ptbl = disk->part_tbl; rcu_assign_pointer(disk->part_tbl, new_ptbl); |
a6f23657d
|
1002 1003 1004 |
if (old_ptbl) { rcu_assign_pointer(old_ptbl->last_lookup, NULL); |
57bdfbf9e
|
1005 |
kfree_rcu(old_ptbl, rcu_head); |
a6f23657d
|
1006 |
} |
540eed563
|
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 |
} /** * disk_expand_part_tbl - expand disk->part_tbl * @disk: disk to expand part_tbl for * @partno: expand such that this partno can fit in * * Expand disk->part_tbl such that @partno can fit in. disk->part_tbl * uses RCU to allow unlocked dereferencing for stats and other stuff. * * LOCKING: * Matching bd_mutex locked, might sleep. * * RETURNS: * 0 on success, -errno on failure. */ int disk_expand_part_tbl(struct gendisk *disk, int partno) { struct disk_part_tbl *old_ptbl = disk->part_tbl; struct disk_part_tbl *new_ptbl; int len = old_ptbl ? old_ptbl->len : 0; int target = partno + 1; size_t size; int i; /* disk_max_parts() is zero during initialization, ignore if so */ if (disk_max_parts(disk) && target > disk_max_parts(disk)) return -EINVAL; if (target <= len) return 0; size = sizeof(*new_ptbl) + target * sizeof(new_ptbl->part[0]); new_ptbl = kzalloc_node(size, GFP_KERNEL, disk->node_id); if (!new_ptbl) return -ENOMEM; |
540eed563
|
1043 1044 1045 1046 1047 1048 1049 1050 |
new_ptbl->len = target; for (i = 0; i < len; i++) rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]); disk_replace_part_tbl(disk, new_ptbl); return 0; } |
edfaa7c36
|
1051 |
static void disk_release(struct device *dev) |
1da177e4c
|
1052 |
{ |
edfaa7c36
|
1053 |
struct gendisk *disk = dev_to_disk(dev); |
77ea887e4
|
1054 |
disk_release_events(disk); |
1da177e4c
|
1055 |
kfree(disk->random); |
540eed563
|
1056 |
disk_replace_part_tbl(disk, NULL); |
074a7aca7
|
1057 |
free_part_stats(&disk->part0); |
6d1d8050b
|
1058 |
free_part_info(&disk->part0); |
523e1d399
|
1059 1060 |
if (disk->queue) blk_put_queue(disk->queue); |
1da177e4c
|
1061 1062 |
kfree(disk); } |
edfaa7c36
|
1063 1064 |
struct class block_class = { .name = "block", |
1da177e4c
|
1065 |
}; |
2c9ede55e
|
1066 |
static char *block_devnode(struct device *dev, umode_t *mode) |
b03f38b68
|
1067 1068 |
{ struct gendisk *disk = dev_to_disk(dev); |
e454cea20
|
1069 1070 |
if (disk->devnode) return disk->devnode(disk, mode); |
b03f38b68
|
1071 1072 |
return NULL; } |
1826eadfc
|
1073 |
static struct device_type disk_type = { |
edfaa7c36
|
1074 1075 1076 |
.name = "disk", .groups = disk_attr_groups, .release = disk_release, |
e454cea20
|
1077 |
.devnode = block_devnode, |
1da177e4c
|
1078 |
}; |
a6e2ba887
|
1079 |
#ifdef CONFIG_PROC_FS |
cf771cb5a
|
1080 1081 1082 1083 1084 1085 1086 1087 |
/* * aggregate disk stat collector. Uses the same stats that the sysfs * entries do, above, but makes them available through one seq_file. * * The output looks suspiciously like /proc/partitions with a bunch of * extra fields. */ static int diskstats_show(struct seq_file *seqf, void *v) |
1da177e4c
|
1088 1089 |
{ struct gendisk *gp = v; |
e71bf0d0e
|
1090 1091 |
struct disk_part_iter piter; struct hd_struct *hd; |
1da177e4c
|
1092 |
char buf[BDEVNAME_SIZE]; |
c99590591
|
1093 |
int cpu; |
1da177e4c
|
1094 1095 |
/* |
ed9e19823
|
1096 |
if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next) |
cf771cb5a
|
1097 |
seq_puts(seqf, "major minor name" |
1da177e4c
|
1098 1099 1100 1101 1102 1103 |
" rio rmerge rsect ruse wio wmerge " "wsect wuse running use aveq" " "); */ |
9f5e48655
|
1104 |
|
71982a409
|
1105 |
disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0); |
e71bf0d0e
|
1106 |
while ((hd = disk_part_iter_next(&piter))) { |
074a7aca7
|
1107 |
cpu = part_stat_lock(); |
c99590591
|
1108 |
part_round_stats(cpu, hd); |
074a7aca7
|
1109 |
part_stat_unlock(); |
f95fe9cfb
|
1110 1111 1112 |
seq_printf(seqf, "%4d %7d %s %lu %lu %lu " "%u %lu %lu %lu %u %u %u %u ", |
f331c0296
|
1113 1114 |
MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), |
53f22956e
|
1115 1116 |
part_stat_read(hd, ios[READ]), part_stat_read(hd, merges[READ]), |
f95fe9cfb
|
1117 |
part_stat_read(hd, sectors[READ]), |
53f22956e
|
1118 1119 1120 |
jiffies_to_msecs(part_stat_read(hd, ticks[READ])), part_stat_read(hd, ios[WRITE]), part_stat_read(hd, merges[WRITE]), |
f95fe9cfb
|
1121 |
part_stat_read(hd, sectors[WRITE]), |
53f22956e
|
1122 |
jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])), |
316d315bf
|
1123 |
part_in_flight(hd), |
28f39d553
|
1124 1125 1126 |
jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); |
1da177e4c
|
1127 |
} |
e71bf0d0e
|
1128 |
disk_part_iter_exit(&piter); |
9f5e48655
|
1129 |
|
1da177e4c
|
1130 1131 |
return 0; } |
31d85ab28
|
1132 |
static const struct seq_operations diskstats_op = { |
def4e38dd
|
1133 1134 1135 |
.start = disk_seqf_start, .next = disk_seqf_next, .stop = disk_seqf_stop, |
1da177e4c
|
1136 1137 |
.show = diskstats_show }; |
f500975a3
|
1138 |
|
31d85ab28
|
1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 |
static int diskstats_open(struct inode *inode, struct file *file) { return seq_open(file, &diskstats_op); } static const struct file_operations proc_diskstats_operations = { .open = diskstats_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
f500975a3
|
1150 1151 |
static int __init proc_genhd_init(void) { |
31d85ab28
|
1152 |
proc_create("diskstats", 0, NULL, &proc_diskstats_operations); |
f500975a3
|
1153 1154 1155 1156 |
proc_create("partitions", 0, NULL, &proc_partitions_operations); return 0; } module_init(proc_genhd_init); |
a6e2ba887
|
1157 |
#endif /* CONFIG_PROC_FS */ |
1da177e4c
|
1158 |
|
cf771cb5a
|
1159 |
dev_t blk_lookup_devt(const char *name, int partno) |
a142be856
|
1160 |
{ |
def4e38dd
|
1161 1162 1163 |
dev_t devt = MKDEV(0, 0); struct class_dev_iter iter; struct device *dev; |
a142be856
|
1164 |
|
def4e38dd
|
1165 1166 |
class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { |
a142be856
|
1167 |
struct gendisk *disk = dev_to_disk(dev); |
548b10eb2
|
1168 |
struct hd_struct *part; |
a142be856
|
1169 |
|
3ada8b7e9
|
1170 |
if (strcmp(dev_name(dev), name)) |
f331c0296
|
1171 |
continue; |
f331c0296
|
1172 |
|
41b8c853a
|
1173 1174 1175 1176 1177 1178 1179 1180 |
if (partno < disk->minors) { /* We need to return the right devno, even * if the partition doesn't exist yet. */ devt = MKDEV(MAJOR(dev->devt), MINOR(dev->devt) + partno); break; } |
548b10eb2
|
1181 |
part = disk_get_part(disk, partno); |
2bbedcb4c
|
1182 |
if (part) { |
f331c0296
|
1183 |
devt = part_devt(part); |
e71bf0d0e
|
1184 |
disk_put_part(part); |
548b10eb2
|
1185 |
break; |
def4e38dd
|
1186 |
} |
548b10eb2
|
1187 |
disk_put_part(part); |
5c0ef6d02
|
1188 |
} |
def4e38dd
|
1189 |
class_dev_iter_exit(&iter); |
edfaa7c36
|
1190 1191 |
return devt; } |
edfaa7c36
|
1192 |
EXPORT_SYMBOL(blk_lookup_devt); |
1da177e4c
|
1193 1194 |
struct gendisk *alloc_disk(int minors) { |
1946089a1
|
1195 1196 |
return alloc_disk_node(minors, -1); } |
689d6fac4
|
1197 |
EXPORT_SYMBOL(alloc_disk); |
1946089a1
|
1198 1199 1200 1201 |
struct gendisk *alloc_disk_node(int minors, int node_id) { struct gendisk *disk; |
94f6030ca
|
1202 1203 |
disk = kmalloc_node(sizeof(struct gendisk), GFP_KERNEL | __GFP_ZERO, node_id); |
1da177e4c
|
1204 |
if (disk) { |
074a7aca7
|
1205 |
if (!init_part_stats(&disk->part0)) { |
1da177e4c
|
1206 1207 1208 |
kfree(disk); return NULL; } |
bf91db18a
|
1209 |
disk->node_id = node_id; |
540eed563
|
1210 1211 |
if (disk_expand_part_tbl(disk, 0)) { free_part_stats(&disk->part0); |
b5d0b9df0
|
1212 1213 |
kfree(disk); return NULL; |
1da177e4c
|
1214 |
} |
540eed563
|
1215 |
disk->part_tbl->part[0] = &disk->part0; |
6c23a9681
|
1216 1217 |
hd_ref_init(&disk->part0); |
b5d0b9df0
|
1218 |
|
1da177e4c
|
1219 |
disk->minors = minors; |
1da177e4c
|
1220 |
rand_initialize_disk(disk); |
ed9e19823
|
1221 1222 1223 |
disk_to_dev(disk)->class = &block_class; disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); |
1da177e4c
|
1224 1225 1226 |
} return disk; } |
1946089a1
|
1227 |
EXPORT_SYMBOL(alloc_disk_node); |
1da177e4c
|
1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 |
struct kobject *get_disk(struct gendisk *disk) { struct module *owner; struct kobject *kobj; if (!disk->fops) return NULL; owner = disk->fops->owner; if (owner && !try_module_get(owner)) return NULL; |
ed9e19823
|
1239 |
kobj = kobject_get(&disk_to_dev(disk)->kobj); |
1da177e4c
|
1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 |
if (kobj == NULL) { module_put(owner); return NULL; } return kobj; } EXPORT_SYMBOL(get_disk); void put_disk(struct gendisk *disk) { if (disk) |
ed9e19823
|
1253 |
kobject_put(&disk_to_dev(disk)->kobj); |
1da177e4c
|
1254 1255 1256 |
} EXPORT_SYMBOL(put_disk); |
e3264a4d7
|
1257 1258 1259 1260 1261 1262 1263 1264 1265 |
static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; char *envp[] = { event, NULL }; if (!ro) event[8] = '0'; kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp); } |
1da177e4c
|
1266 1267 |
void set_device_ro(struct block_device *bdev, int flag) { |
b7db9956e
|
1268 |
bdev->bd_part->policy = flag; |
1da177e4c
|
1269 1270 1271 1272 1273 1274 |
} EXPORT_SYMBOL(set_device_ro); void set_disk_ro(struct gendisk *disk, int flag) { |
e71bf0d0e
|
1275 1276 |
struct disk_part_iter piter; struct hd_struct *part; |
e3264a4d7
|
1277 1278 1279 1280 1281 1282 |
if (disk->part0.policy != flag) { set_disk_ro_uevent(disk, flag); disk->part0.policy = flag; } disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); |
e71bf0d0e
|
1283 1284 1285 |
while ((part = disk_part_iter_next(&piter))) part->policy = flag; disk_part_iter_exit(&piter); |
1da177e4c
|
1286 1287 1288 1289 1290 1291 1292 1293 |
} EXPORT_SYMBOL(set_disk_ro); int bdev_read_only(struct block_device *bdev) { if (!bdev) return 0; |
b7db9956e
|
1294 |
return bdev->bd_part->policy; |
1da177e4c
|
1295 1296 1297 |
} EXPORT_SYMBOL(bdev_read_only); |
cf771cb5a
|
1298 |
int invalidate_partition(struct gendisk *disk, int partno) |
1da177e4c
|
1299 1300 |
{ int res = 0; |
cf771cb5a
|
1301 |
struct block_device *bdev = bdget_disk(disk, partno); |
1da177e4c
|
1302 |
if (bdev) { |
2ef41634d
|
1303 |
fsync_bdev(bdev); |
93b270f76
|
1304 |
res = __invalidate_device(bdev, true); |
1da177e4c
|
1305 1306 1307 1308 1309 1310 |
bdput(bdev); } return res; } EXPORT_SYMBOL(invalidate_partition); |
77ea887e4
|
1311 1312 1313 1314 1315 1316 1317 1318 |
/* * Disk events - monitor disk events like media change and eject request. */ struct disk_events { struct list_head node; /* all disk_event's */ struct gendisk *disk; /* the associated disk */ spinlock_t lock; |
fdd514e16
|
1319 |
struct mutex block_mutex; /* protects blocking */ |
77ea887e4
|
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 |
int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ long poll_msecs; /* interval, -1 for default */ struct delayed_work dwork; }; static const char *disk_events_strs[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", }; static char *disk_uevents[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", }; /* list of all disk_events */ static DEFINE_MUTEX(disk_events_mutex); static LIST_HEAD(disk_events); /* disable in-kernel polling by default */ static unsigned long disk_events_dfl_poll_msecs = 0; static unsigned long disk_events_poll_jiffies(struct gendisk *disk) { struct disk_events *ev = disk->ev; long intv_msecs = 0; /* * If device-specific poll interval is set, always use it. If * the default is being used, poll iff there are events which * can't be monitored asynchronously. */ if (ev->poll_msecs >= 0) intv_msecs = ev->poll_msecs; else if (disk->events & ~disk->async_events) intv_msecs = disk_events_dfl_poll_msecs; return msecs_to_jiffies(intv_msecs); } |
c3af54afb
|
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 |
/** * disk_block_events - block and flush disk event checking * @disk: disk to block events for * * On return from this function, it is guaranteed that event checking * isn't in progress and won't happen until unblocked by * disk_unblock_events(). Events blocking is counted and the actual * unblocking happens after the matching number of unblocks are done. * * Note that this intentionally does not block event checking from * disk_clear_events(). * * CONTEXT: * Might sleep. */ void disk_block_events(struct gendisk *disk) |
77ea887e4
|
1378 1379 1380 1381 |
{ struct disk_events *ev = disk->ev; unsigned long flags; bool cancel; |
c3af54afb
|
1382 1383 |
if (!ev) return; |
fdd514e16
|
1384 1385 1386 1387 1388 |
/* * Outer mutex ensures that the first blocker completes canceling * the event work before further blockers are allowed to finish. */ mutex_lock(&ev->block_mutex); |
77ea887e4
|
1389 1390 1391 |
spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); |
c3af54afb
|
1392 1393 |
if (cancel) cancel_delayed_work_sync(&disk->ev->dwork); |
fdd514e16
|
1394 1395 |
mutex_unlock(&ev->block_mutex); |
77ea887e4
|
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 |
} static void __disk_unblock_events(struct gendisk *disk, bool check_now) { struct disk_events *ev = disk->ev; unsigned long intv; unsigned long flags; spin_lock_irqsave(&ev->lock, flags); if (WARN_ON_ONCE(ev->block <= 0)) goto out_unlock; if (--ev->block) goto out_unlock; /* * Not exactly a latency critical operation, set poll timer * slack to 25% and kick event check. */ intv = disk_events_poll_jiffies(disk); set_timer_slack(&ev->dwork.timer, intv / 4); if (check_now) queue_delayed_work(system_nrt_wq, &ev->dwork, 0); else if (intv) queue_delayed_work(system_nrt_wq, &ev->dwork, intv); out_unlock: spin_unlock_irqrestore(&ev->lock, flags); } /** |
77ea887e4
|
1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 |
* disk_unblock_events - unblock disk event checking * @disk: disk to unblock events for * * Undo disk_block_events(). When the block count reaches zero, it * starts events polling if configured. * * CONTEXT: * Don't care. Safe to call from irq context. */ void disk_unblock_events(struct gendisk *disk) { if (disk->ev) |
facc31ddc
|
1439 |
__disk_unblock_events(disk, false); |
77ea887e4
|
1440 1441 1442 |
} /** |
85ef06d1d
|
1443 1444 1445 |
* disk_flush_events - schedule immediate event checking and flushing * @disk: disk to check and flush events for * @mask: events to flush |
77ea887e4
|
1446 |
* |
85ef06d1d
|
1447 1448 1449 |
* Schedule immediate event checking on @disk if not blocked. Events in * @mask are scheduled to be cleared from the driver. Note that this * doesn't clear the events from @disk->ev. |
77ea887e4
|
1450 1451 |
* * CONTEXT: |
85ef06d1d
|
1452 |
* If @mask is non-zero must be called with bdev->bd_mutex held. |
77ea887e4
|
1453 |
*/ |
85ef06d1d
|
1454 |
void disk_flush_events(struct gendisk *disk, unsigned int mask) |
77ea887e4
|
1455 |
{ |
a9dce2a3b
|
1456 |
struct disk_events *ev = disk->ev; |
a9dce2a3b
|
1457 1458 1459 |
if (!ev) return; |
85ef06d1d
|
1460 1461 |
spin_lock_irq(&ev->lock); ev->clearing |= mask; |
a9dce2a3b
|
1462 1463 1464 |
if (!ev->block) { cancel_delayed_work(&ev->dwork); queue_delayed_work(system_nrt_wq, &ev->dwork, 0); |
77ea887e4
|
1465 |
} |
85ef06d1d
|
1466 |
spin_unlock_irq(&ev->lock); |
77ea887e4
|
1467 |
} |
77ea887e4
|
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 |
/** * disk_clear_events - synchronously check, clear and return pending events * @disk: disk to fetch and clear events from * @mask: mask of events to be fetched and clearted * * Disk events are synchronously checked and pending events in @mask * are cleared and returned. This ignores the block count. * * CONTEXT: * Might sleep. */ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) { const struct block_device_operations *bdops = disk->fops; struct disk_events *ev = disk->ev; unsigned int pending; if (!ev) { /* for drivers still using the old ->media_changed method */ if ((mask & DISK_EVENT_MEDIA_CHANGE) && bdops->media_changed && bdops->media_changed(disk)) return DISK_EVENT_MEDIA_CHANGE; return 0; } /* tell the workfn about the events being cleared */ spin_lock_irq(&ev->lock); ev->clearing |= mask; spin_unlock_irq(&ev->lock); /* uncondtionally schedule event check and wait for it to finish */ |
c3af54afb
|
1500 |
disk_block_events(disk); |
77ea887e4
|
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 |
queue_delayed_work(system_nrt_wq, &ev->dwork, 0); flush_delayed_work(&ev->dwork); __disk_unblock_events(disk, false); /* then, fetch and clear pending events */ spin_lock_irq(&ev->lock); WARN_ON_ONCE(ev->clearing & mask); /* cleared by workfn */ pending = ev->pending & mask; ev->pending &= ~mask; spin_unlock_irq(&ev->lock); return pending; } static void disk_events_workfn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct disk_events *ev = container_of(dwork, struct disk_events, dwork); struct gendisk *disk = ev->disk; char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; unsigned int clearing = ev->clearing; unsigned int events; unsigned long intv; int nr_events = 0, i; /* check events */ events = disk->fops->check_events(disk, clearing); /* accumulate pending events and schedule next poll if necessary */ spin_lock_irq(&ev->lock); events &= ~ev->pending; ev->pending |= events; ev->clearing &= ~clearing; intv = disk_events_poll_jiffies(disk); if (!ev->block && intv) queue_delayed_work(system_nrt_wq, &ev->dwork, intv); spin_unlock_irq(&ev->lock); |
7c88a168d
|
1541 1542 1543 1544 1545 |
/* * Tell userland about new events. Only the events listed in * @disk->events are reported. Unlisted events are processed the * same internally but never get reported to userland. */ |
77ea887e4
|
1546 |
for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) |
7c88a168d
|
1547 |
if (events & disk->events & (1 << i)) |
77ea887e4
|
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 |
envp[nr_events++] = disk_uevents[i]; if (nr_events) kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); } /* * A disk events enabled device has the following sysfs nodes under * its /sys/block/X/ directory. * * events : list of all supported events * events_async : list of events which can be detected w/o polling * events_poll_msecs : polling interval, 0: disable, -1: system default */ static ssize_t __disk_events_show(unsigned int events, char *buf) { const char *delim = ""; ssize_t pos = 0; int i; for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) if (events & (1 << i)) { pos += sprintf(buf + pos, "%s%s", delim, disk_events_strs[i]); delim = " "; } if (pos) pos += sprintf(buf + pos, " "); return pos; } static ssize_t disk_events_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return __disk_events_show(disk->events, buf); } static ssize_t disk_events_async_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return __disk_events_show(disk->async_events, buf); } static ssize_t disk_events_poll_msecs_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%ld ", disk->ev->poll_msecs); } static ssize_t disk_events_poll_msecs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); long intv; if (!count || !sscanf(buf, "%ld", &intv)) return -EINVAL; if (intv < 0 && intv != -1) return -EINVAL; |
c3af54afb
|
1618 |
disk_block_events(disk); |
77ea887e4
|
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 |
disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); return count; } static const DEVICE_ATTR(events, S_IRUGO, disk_events_show, NULL); static const DEVICE_ATTR(events_async, S_IRUGO, disk_events_async_show, NULL); static const DEVICE_ATTR(events_poll_msecs, S_IRUGO|S_IWUSR, disk_events_poll_msecs_show, disk_events_poll_msecs_store); static const struct attribute *disk_events_attrs[] = { &dev_attr_events.attr, &dev_attr_events_async.attr, &dev_attr_events_poll_msecs.attr, NULL, }; /* * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to * /sys/module/block/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) { struct disk_events *ev; int ret; ret = param_set_ulong(val, kp); if (ret < 0) return ret; mutex_lock(&disk_events_mutex); list_for_each_entry(ev, &disk_events, node) |
85ef06d1d
|
1657 |
disk_flush_events(ev->disk, 0); |
77ea887e4
|
1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 |
mutex_unlock(&disk_events_mutex); return 0; } static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { .set = disk_events_set_dfl_poll_msecs, .get = param_get_ulong, }; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "block." module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, &disk_events_dfl_poll_msecs, 0644); /* * disk_{add|del|release}_events - initialize and destroy disk_events. */ static void disk_add_events(struct gendisk *disk) { struct disk_events *ev; |
75e3f3ee3
|
1681 |
if (!disk->fops->check_events) |
77ea887e4
|
1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 |
return; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { pr_warn("%s: failed to initialize events ", disk->disk_name); return; } if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) { pr_warn("%s: failed to create sysfs files for events ", disk->disk_name); kfree(ev); return; } disk->ev = ev; INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); |
fdd514e16
|
1705 |
mutex_init(&ev->block_mutex); |
77ea887e4
|
1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 |
ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); mutex_lock(&disk_events_mutex); list_add_tail(&ev->node, &disk_events); mutex_unlock(&disk_events_mutex); /* * Block count is initialized to 1 and the following initial * unblock kicks it into action. */ __disk_unblock_events(disk, true); } static void disk_del_events(struct gendisk *disk) { if (!disk->ev) return; |
c3af54afb
|
1725 |
disk_block_events(disk); |
77ea887e4
|
1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 |
mutex_lock(&disk_events_mutex); list_del_init(&disk->ev->node); mutex_unlock(&disk_events_mutex); sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs); } static void disk_release_events(struct gendisk *disk) { /* the block count should be 1 from disk_del_events() */ WARN_ON_ONCE(disk->ev && disk->ev->block != 1); kfree(disk->ev); } |