osdmap.c 32.7 KB
Newer Older
S
Sage Weil 已提交
1

2
#include <linux/ceph/ceph_debug.h>
3

4
#include <linux/module.h>
5
#include <linux/slab.h>
S
Sage Weil 已提交
6 7
#include <asm/div64.h>

8 9 10 11 12
#include <linux/ceph/libceph.h>
#include <linux/ceph/osdmap.h>
#include <linux/ceph/decode.h>
#include <linux/crush/hash.h>
#include <linux/crush/mapper.h>
S
Sage Weil 已提交
13 14 15 16

char *ceph_osdmap_state_str(char *str, int len, int state)
{
	if (!len)
17
		return str;
S
Sage Weil 已提交
18

19 20 21 22 23 24 25
	if ((state & CEPH_OSD_EXISTS) && (state & CEPH_OSD_UP))
		snprintf(str, len, "exists, up");
	else if (state & CEPH_OSD_EXISTS)
		snprintf(str, len, "exists");
	else if (state & CEPH_OSD_UP)
		snprintf(str, len, "up");
	else
S
Sage Weil 已提交
26
		snprintf(str, len, "doesn't exist");
27

S
Sage Weil 已提交
28 29 30 31 32
	return str;
}

/* maps */

33
static int calc_bits_of(unsigned int t)
S
Sage Weil 已提交
34 35 36 37 38 39 40 41 42 43 44 45 46 47
{
	int b = 0;
	while (t) {
		t = t >> 1;
		b++;
	}
	return b;
}

/*
 * the foo_mask is the smallest value 2^n-1 that is >= foo.
 */
static void calc_pg_masks(struct ceph_pg_pool_info *pi)
{
48 49
	pi->pg_num_mask = (1 << calc_bits_of(pi->pg_num-1)) - 1;
	pi->pgp_num_mask = (1 << calc_bits_of(pi->pgp_num-1)) - 1;
S
Sage Weil 已提交
50 51 52 53 54 55 56 57 58 59
}

/*
 * decode crush map
 */
static int crush_decode_uniform_bucket(void **p, void *end,
				       struct crush_bucket_uniform *b)
{
	dout("crush_decode_uniform_bucket %p to %p\n", *p, end);
	ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad);
60
	b->item_weight = ceph_decode_32(p);
S
Sage Weil 已提交
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78
	return 0;
bad:
	return -EINVAL;
}

static int crush_decode_list_bucket(void **p, void *end,
				    struct crush_bucket_list *b)
{
	int j;
	dout("crush_decode_list_bucket %p to %p\n", *p, end);
	b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
	if (b->item_weights == NULL)
		return -ENOMEM;
	b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
	if (b->sum_weights == NULL)
		return -ENOMEM;
	ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad);
	for (j = 0; j < b->h.size; j++) {
79 80
		b->item_weights[j] = ceph_decode_32(p);
		b->sum_weights[j] = ceph_decode_32(p);
S
Sage Weil 已提交
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97
	}
	return 0;
bad:
	return -EINVAL;
}

static int crush_decode_tree_bucket(void **p, void *end,
				    struct crush_bucket_tree *b)
{
	int j;
	dout("crush_decode_tree_bucket %p to %p\n", *p, end);
	ceph_decode_32_safe(p, end, b->num_nodes, bad);
	b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS);
	if (b->node_weights == NULL)
		return -ENOMEM;
	ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad);
	for (j = 0; j < b->num_nodes; j++)
98
		b->node_weights[j] = ceph_decode_32(p);
S
Sage Weil 已提交
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
	return 0;
bad:
	return -EINVAL;
}

static int crush_decode_straw_bucket(void **p, void *end,
				     struct crush_bucket_straw *b)
{
	int j;
	dout("crush_decode_straw_bucket %p to %p\n", *p, end);
	b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
	if (b->item_weights == NULL)
		return -ENOMEM;
	b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS);
	if (b->straws == NULL)
		return -ENOMEM;
	ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad);
	for (j = 0; j < b->h.size; j++) {
117 118
		b->item_weights[j] = ceph_decode_32(p);
		b->straws[j] = ceph_decode_32(p);
S
Sage Weil 已提交
119 120 121 122 123 124
	}
	return 0;
bad:
	return -EINVAL;
}

S
Sage Weil 已提交
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
static int skip_name_map(void **p, void *end)
{
        int len;
        ceph_decode_32_safe(p, end, len ,bad);
        while (len--) {
                int strlen;
                *p += sizeof(u32);
                ceph_decode_32_safe(p, end, strlen, bad);
                *p += strlen;
}
        return 0;
bad:
        return -EINVAL;
}

S
Sage Weil 已提交
140 141 142 143 144 145 146 147
static struct crush_map *crush_decode(void *pbyval, void *end)
{
	struct crush_map *c;
	int err = -EINVAL;
	int i, j;
	void **p = &pbyval;
	void *start = pbyval;
	u32 magic;
S
Sage Weil 已提交
148
	u32 num_name_maps;
S
Sage Weil 已提交
149 150 151 152 153 154 155

	dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p));

	c = kzalloc(sizeof(*c), GFP_NOFS);
	if (c == NULL)
		return ERR_PTR(-ENOMEM);

S
Sage Weil 已提交
156 157 158 159
        /* set tunables to default values */
        c->choose_local_tries = 2;
        c->choose_local_fallback_tries = 5;
        c->choose_total_tries = 19;
160
	c->chooseleaf_descend_once = 0;
S
Sage Weil 已提交
161

S
Sage Weil 已提交
162
	ceph_decode_need(p, end, 4*sizeof(u32), bad);
163
	magic = ceph_decode_32(p);
S
Sage Weil 已提交
164 165
	if (magic != CRUSH_MAGIC) {
		pr_err("crush_decode magic %x != current %x\n",
166
		       (unsigned int)magic, (unsigned int)CRUSH_MAGIC);
S
Sage Weil 已提交
167 168
		goto bad;
	}
169 170 171
	c->max_buckets = ceph_decode_32(p);
	c->max_rules = ceph_decode_32(p);
	c->max_devices = ceph_decode_32(p);
S
Sage Weil 已提交
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

	c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS);
	if (c->buckets == NULL)
		goto badmem;
	c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS);
	if (c->rules == NULL)
		goto badmem;

	/* buckets */
	for (i = 0; i < c->max_buckets; i++) {
		int size = 0;
		u32 alg;
		struct crush_bucket *b;

		ceph_decode_32_safe(p, end, alg, bad);
		if (alg == 0) {
			c->buckets[i] = NULL;
			continue;
		}
		dout("crush_decode bucket %d off %x %p to %p\n",
		     i, (int)(*p-start), *p, end);

		switch (alg) {
		case CRUSH_BUCKET_UNIFORM:
			size = sizeof(struct crush_bucket_uniform);
			break;
		case CRUSH_BUCKET_LIST:
			size = sizeof(struct crush_bucket_list);
			break;
		case CRUSH_BUCKET_TREE:
			size = sizeof(struct crush_bucket_tree);
			break;
		case CRUSH_BUCKET_STRAW:
			size = sizeof(struct crush_bucket_straw);
			break;
		default:
208
			err = -EINVAL;
S
Sage Weil 已提交
209 210 211 212 213 214 215 216
			goto bad;
		}
		BUG_ON(size == 0);
		b = c->buckets[i] = kzalloc(size, GFP_NOFS);
		if (b == NULL)
			goto badmem;

		ceph_decode_need(p, end, 4*sizeof(u32), bad);
217 218
		b->id = ceph_decode_32(p);
		b->type = ceph_decode_16(p);
219 220
		b->alg = ceph_decode_8(p);
		b->hash = ceph_decode_8(p);
221 222
		b->weight = ceph_decode_32(p);
		b->size = ceph_decode_32(p);
S
Sage Weil 已提交
223 224 225 226 227 228 229 230 231 232 233 234 235 236

		dout("crush_decode bucket size %d off %x %p to %p\n",
		     b->size, (int)(*p-start), *p, end);

		b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS);
		if (b->items == NULL)
			goto badmem;
		b->perm = kcalloc(b->size, sizeof(u32), GFP_NOFS);
		if (b->perm == NULL)
			goto badmem;
		b->perm_n = 0;

		ceph_decode_need(p, end, b->size*sizeof(u32), bad);
		for (j = 0; j < b->size; j++)
237
			b->items[j] = ceph_decode_32(p);
S
Sage Weil 已提交
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

		switch (b->alg) {
		case CRUSH_BUCKET_UNIFORM:
			err = crush_decode_uniform_bucket(p, end,
				  (struct crush_bucket_uniform *)b);
			if (err < 0)
				goto bad;
			break;
		case CRUSH_BUCKET_LIST:
			err = crush_decode_list_bucket(p, end,
			       (struct crush_bucket_list *)b);
			if (err < 0)
				goto bad;
			break;
		case CRUSH_BUCKET_TREE:
			err = crush_decode_tree_bucket(p, end,
				(struct crush_bucket_tree *)b);
			if (err < 0)
				goto bad;
			break;
		case CRUSH_BUCKET_STRAW:
			err = crush_decode_straw_bucket(p, end,
				(struct crush_bucket_straw *)b);
			if (err < 0)
				goto bad;
			break;
		}
	}

	/* rules */
	dout("rule vec is %p\n", c->rules);
	for (i = 0; i < c->max_rules; i++) {
		u32 yes;
		struct crush_rule *r;

		ceph_decode_32_safe(p, end, yes, bad);
		if (!yes) {
			dout("crush_decode NO rule %d off %x %p to %p\n",
			     i, (int)(*p-start), *p, end);
			c->rules[i] = NULL;
			continue;
		}

		dout("crush_decode rule %d off %x %p to %p\n",
		     i, (int)(*p-start), *p, end);

		/* len */
		ceph_decode_32_safe(p, end, yes, bad);
#if BITS_PER_LONG == 32
287
		err = -EINVAL;
288 289
		if (yes > (ULONG_MAX - sizeof(*r))
			  / sizeof(struct crush_rule_step))
S
Sage Weil 已提交
290 291 292 293 294 295 296 297 298 299 300 301
			goto bad;
#endif
		r = c->rules[i] = kmalloc(sizeof(*r) +
					  yes*sizeof(struct crush_rule_step),
					  GFP_NOFS);
		if (r == NULL)
			goto badmem;
		dout(" rule %d is at %p\n", i, r);
		r->len = yes;
		ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */
		ceph_decode_need(p, end, r->len*3*sizeof(u32), bad);
		for (j = 0; j < r->len; j++) {
302 303 304
			r->steps[j].op = ceph_decode_32(p);
			r->steps[j].arg1 = ceph_decode_32(p);
			r->steps[j].arg2 = ceph_decode_32(p);
S
Sage Weil 已提交
305 306 307 308
		}
	}

	/* ignore trailing name maps. */
S
Sage Weil 已提交
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
        for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) {
                err = skip_name_map(p, end);
                if (err < 0)
                        goto done;
        }

        /* tunables */
        ceph_decode_need(p, end, 3*sizeof(u32), done);
        c->choose_local_tries = ceph_decode_32(p);
        c->choose_local_fallback_tries =  ceph_decode_32(p);
        c->choose_total_tries = ceph_decode_32(p);
        dout("crush decode tunable choose_local_tries = %d",
             c->choose_local_tries);
        dout("crush decode tunable choose_local_fallback_tries = %d",
             c->choose_local_fallback_tries);
        dout("crush decode tunable choose_total_tries = %d",
             c->choose_total_tries);
S
Sage Weil 已提交
326

327 328 329 330 331
	ceph_decode_need(p, end, sizeof(u32), done);
	c->chooseleaf_descend_once = ceph_decode_32(p);
	dout("crush decode tunable chooseleaf_descend_once = %d",
	     c->chooseleaf_descend_once);

S
Sage Weil 已提交
332
done:
S
Sage Weil 已提交
333 334 335 336 337 338 339 340 341 342 343 344
	dout("crush_decode success\n");
	return c;

badmem:
	err = -ENOMEM;
bad:
	dout("crush_decode fail %d\n", err);
	crush_destroy(c);
	return ERR_PTR(err);
}

/*
345
 * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
346
 * to a set of osds) and primary_temp (explicit primary setting)
S
Sage Weil 已提交
347
 */
348
static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
349
{
350 351 352 353 354
	if (l.pool < r.pool)
		return -1;
	if (l.pool > r.pool)
		return 1;
	if (l.seed < r.seed)
355
		return -1;
356
	if (l.seed > r.seed)
357 358 359 360
		return 1;
	return 0;
}

361 362
static int __insert_pg_mapping(struct ceph_pg_mapping *new,
			       struct rb_root *root)
S
Sage Weil 已提交
363 364 365 366
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_pg_mapping *pg = NULL;
367
	int c;
S
Sage Weil 已提交
368

S
Sage Weil 已提交
369
	dout("__insert_pg_mapping %llx %p\n", *(u64 *)&new->pgid, new);
S
Sage Weil 已提交
370 371 372
	while (*p) {
		parent = *p;
		pg = rb_entry(parent, struct ceph_pg_mapping, node);
373 374
		c = pgid_cmp(new->pgid, pg->pgid);
		if (c < 0)
S
Sage Weil 已提交
375
			p = &(*p)->rb_left;
376
		else if (c > 0)
S
Sage Weil 已提交
377 378
			p = &(*p)->rb_right;
		else
379
			return -EEXIST;
S
Sage Weil 已提交
380 381 382 383
	}

	rb_link_node(&new->node, parent, p);
	rb_insert_color(&new->node, root);
384
	return 0;
S
Sage Weil 已提交
385 386
}

387
static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
388
						   struct ceph_pg pgid)
389 390 391 392 393 394 395 396
{
	struct rb_node *n = root->rb_node;
	struct ceph_pg_mapping *pg;
	int c;

	while (n) {
		pg = rb_entry(n, struct ceph_pg_mapping, node);
		c = pgid_cmp(pgid, pg->pgid);
S
Sage Weil 已提交
397
		if (c < 0) {
398
			n = n->rb_left;
S
Sage Weil 已提交
399
		} else if (c > 0) {
400
			n = n->rb_right;
S
Sage Weil 已提交
401
		} else {
402 403
			dout("__lookup_pg_mapping %lld.%x got %p\n",
			     pgid.pool, pgid.seed, pg);
404
			return pg;
S
Sage Weil 已提交
405
		}
406 407 408 409
	}
	return NULL;
}

410
static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid)
S
Sage Weil 已提交
411 412 413 414
{
	struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid);

	if (pg) {
415 416
		dout("__remove_pg_mapping %lld.%x %p\n", pgid.pool, pgid.seed,
		     pg);
S
Sage Weil 已提交
417 418 419 420
		rb_erase(&pg->node, root);
		kfree(pg);
		return 0;
	}
421
	dout("__remove_pg_mapping %lld.%x dne\n", pgid.pool, pgid.seed);
S
Sage Weil 已提交
422 423 424
	return -ENOENT;
}

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
/*
 * rbtree of pg pool info
 */
static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_pg_pool_info *pi = NULL;

	while (*p) {
		parent = *p;
		pi = rb_entry(parent, struct ceph_pg_pool_info, node);
		if (new->id < pi->id)
			p = &(*p)->rb_left;
		else if (new->id > pi->id)
			p = &(*p)->rb_right;
		else
			return -EEXIST;
	}

	rb_link_node(&new->node, parent, p);
	rb_insert_color(&new->node, root);
	return 0;
}

450
static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id)
451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466
{
	struct ceph_pg_pool_info *pi;
	struct rb_node *n = root->rb_node;

	while (n) {
		pi = rb_entry(n, struct ceph_pg_pool_info, node);
		if (id < pi->id)
			n = n->rb_left;
		else if (id > pi->id)
			n = n->rb_right;
		else
			return pi;
	}
	return NULL;
}

I
Ilya Dryomov 已提交
467 468 469 470 471
struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id)
{
	return __lookup_pg_pool(&map->pg_pools, id);
}

472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487
const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id)
{
	struct ceph_pg_pool_info *pi;

	if (id == CEPH_NOPOOL)
		return NULL;

	if (WARN_ON_ONCE(id > (u64) INT_MAX))
		return NULL;

	pi = __lookup_pg_pool(&map->pg_pools, (int) id);

	return pi ? pi->name : NULL;
}
EXPORT_SYMBOL(ceph_pg_pool_name_by_id);

Y
Yehuda Sadeh 已提交
488 489 490 491 492 493 494 495 496 497 498 499
int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
{
	struct rb_node *rbp;

	for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) {
		struct ceph_pg_pool_info *pi =
			rb_entry(rbp, struct ceph_pg_pool_info, node);
		if (pi->name && strcmp(pi->name, name) == 0)
			return pi->id;
	}
	return -ENOENT;
}
500
EXPORT_SYMBOL(ceph_pg_poolid_by_name);
Y
Yehuda Sadeh 已提交
501

502 503 504 505 506 507 508
static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
{
	rb_erase(&pi->node, root);
	kfree(pi->name);
	kfree(pi);
}

509
static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
510
{
511 512 513 514 515 516 517 518 519 520 521
	u8 ev, cv;
	unsigned len, num;
	void *pool_end;

	ceph_decode_need(p, end, 2 + 4, bad);
	ev = ceph_decode_8(p);  /* encoding version */
	cv = ceph_decode_8(p); /* compat version */
	if (ev < 5) {
		pr_warning("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv);
		return -EINVAL;
	}
522 523
	if (cv > 9) {
		pr_warning("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv);
524 525 526 527 528
		return -EINVAL;
	}
	len = ceph_decode_32(p);
	ceph_decode_need(p, end, len, bad);
	pool_end = *p + len;
S
Sage Weil 已提交
529

530 531 532 533
	pi->type = ceph_decode_8(p);
	pi->size = ceph_decode_8(p);
	pi->crush_ruleset = ceph_decode_8(p);
	pi->object_hash = ceph_decode_8(p);
S
Sage Weil 已提交
534

535 536 537 538 539 540 541 542 543 544 545 546 547 548
	pi->pg_num = ceph_decode_32(p);
	pi->pgp_num = ceph_decode_32(p);

	*p += 4 + 4;  /* skip lpg* */
	*p += 4;      /* skip last_change */
	*p += 8 + 4;  /* skip snap_seq, snap_epoch */

	/* skip snaps */
	num = ceph_decode_32(p);
	while (num--) {
		*p += 8;  /* snapid key */
		*p += 1 + 1; /* versions */
		len = ceph_decode_32(p);
		*p += len;
S
Sage Weil 已提交
549 550
	}

551
	/* skip removed_snaps */
552 553 554 555 556
	num = ceph_decode_32(p);
	*p += num * (8 + 8);

	*p += 8;  /* skip auid */
	pi->flags = ceph_decode_64(p);
557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
	*p += 4;  /* skip crash_replay_interval */

	if (ev >= 7)
		*p += 1;  /* skip min_size */

	if (ev >= 8)
		*p += 8 + 8;  /* skip quota_max_* */

	if (ev >= 9) {
		/* skip tiers */
		num = ceph_decode_32(p);
		*p += num * 8;

		*p += 8;  /* skip tier_of */
		*p += 1;  /* skip cache_mode */

		pi->read_tier = ceph_decode_64(p);
		pi->write_tier = ceph_decode_64(p);
	} else {
		pi->read_tier = -1;
		pi->write_tier = -1;
	}
579 580 581 582 583

	/* ignore the rest */

	*p = pool_end;
	calc_pg_masks(pi);
S
Sage Weil 已提交
584 585 586 587
	return 0;

bad:
	return -EINVAL;
588 589
}

590
static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
591 592
{
	struct ceph_pg_pool_info *pi;
593 594
	u32 num, len;
	u64 pool;
595 596 597 598

	ceph_decode_32_safe(p, end, num, bad);
	dout(" %d pool names\n", num);
	while (num--) {
599
		ceph_decode_64_safe(p, end, pool, bad);
600
		ceph_decode_32_safe(p, end, len, bad);
601
		dout("  pool %llu len %d\n", pool, len);
602
		ceph_decode_need(p, end, len, bad);
603 604
		pi = __lookup_pg_pool(&map->pg_pools, pool);
		if (pi) {
605 606 607 608
			char *name = kstrndup(*p, len, GFP_NOFS);

			if (!name)
				return -ENOMEM;
609
			kfree(pi->name);
610 611
			pi->name = name;
			dout("  name is %s\n", pi->name);
612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635
		}
		*p += len;
	}
	return 0;

bad:
	return -EINVAL;
}

/*
 * osd map
 */
void ceph_osdmap_destroy(struct ceph_osdmap *map)
{
	dout("osdmap_destroy %p\n", map);
	if (map->crush)
		crush_destroy(map->crush);
	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
		struct ceph_pg_mapping *pg =
			rb_entry(rb_first(&map->pg_temp),
				 struct ceph_pg_mapping, node);
		rb_erase(&pg->node, &map->pg_temp);
		kfree(pg);
	}
636 637 638 639 640 641 642
	while (!RB_EMPTY_ROOT(&map->primary_temp)) {
		struct ceph_pg_mapping *pg =
			rb_entry(rb_first(&map->primary_temp),
				 struct ceph_pg_mapping, node);
		rb_erase(&pg->node, &map->primary_temp);
		kfree(pg);
	}
643 644 645 646 647 648 649 650 651 652 653 654 655
	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
		struct ceph_pg_pool_info *pi =
			rb_entry(rb_first(&map->pg_pools),
				 struct ceph_pg_pool_info, node);
		__remove_pg_pool(&map->pg_pools, pi);
	}
	kfree(map->osd_state);
	kfree(map->osd_weight);
	kfree(map->osd_addr);
	kfree(map);
}

/*
656 657 658
 * Adjust max_osd value, (re)allocate arrays.
 *
 * The new elements are properly initialized.
659 660 661 662 663
 */
static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
{
	u8 *state;
	u32 *weight;
664 665
	struct ceph_entity_addr *addr;
	int i;
666

667 668 669 670
	state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS);
	weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS);
	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
	if (!state || !weight || !addr) {
671 672
		kfree(state);
		kfree(weight);
673 674
		kfree(addr);

675 676 677
		return -ENOMEM;
	}

678 679 680 681
	for (i = map->max_osd; i < max; i++) {
		state[i] = 0;
		weight[i] = CEPH_OSD_OUT;
		memset(addr + i, 0, sizeof(*addr));
682 683 684 685 686
	}

	map->osd_state = state;
	map->osd_weight = weight;
	map->osd_addr = addr;
687

688
	map->max_osd = max;
689

690 691 692
	return 0;
}

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
#define OSDMAP_WRAPPER_COMPAT_VER	7
#define OSDMAP_CLIENT_DATA_COMPAT_VER	1

/*
 * Return 0 or error.  On success, *v is set to 0 for old (v6) osdmaps,
 * to struct_v of the client_data section for new (v7 and above)
 * osdmaps.
 */
static int get_osdmap_client_data_v(void **p, void *end,
				    const char *prefix, u8 *v)
{
	u8 struct_v;

	ceph_decode_8_safe(p, end, struct_v, e_inval);
	if (struct_v >= 7) {
		u8 struct_compat;

		ceph_decode_8_safe(p, end, struct_compat, e_inval);
		if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) {
			pr_warning("got v %d cv %d > %d of %s ceph_osdmap\n",
				   struct_v, struct_compat,
				   OSDMAP_WRAPPER_COMPAT_VER, prefix);
			return -EINVAL;
		}
		*p += 4; /* ignore wrapper struct_len */

		ceph_decode_8_safe(p, end, struct_v, e_inval);
		ceph_decode_8_safe(p, end, struct_compat, e_inval);
		if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) {
			pr_warning("got v %d cv %d > %d of %s ceph_osdmap client data\n",
				   struct_v, struct_compat,
				   OSDMAP_CLIENT_DATA_COMPAT_VER, prefix);
			return -EINVAL;
		}
		*p += 4; /* ignore client data struct_len */
	} else {
		u16 version;

		*p -= 1;
		ceph_decode_16_safe(p, end, version, e_inval);
		if (version < 6) {
			pr_warning("got v %d < 6 of %s ceph_osdmap\n", version,
				   prefix);
			return -EINVAL;
		}

		/* old osdmap enconding */
		struct_v = 0;
	}

	*v = struct_v;
	return 0;

e_inval:
	return -EINVAL;
}

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
static int __decode_pools(void **p, void *end, struct ceph_osdmap *map,
			  bool incremental)
{
	u32 n;

	ceph_decode_32_safe(p, end, n, e_inval);
	while (n--) {
		struct ceph_pg_pool_info *pi;
		u64 pool;
		int ret;

		ceph_decode_64_safe(p, end, pool, e_inval);

		pi = __lookup_pg_pool(&map->pg_pools, pool);
		if (!incremental || !pi) {
			pi = kzalloc(sizeof(*pi), GFP_NOFS);
			if (!pi)
				return -ENOMEM;

			pi->id = pool;

			ret = __insert_pg_pool(&map->pg_pools, pi);
			if (ret) {
				kfree(pi);
				return ret;
			}
		}

		ret = decode_pool(p, end, pi);
		if (ret)
			return ret;
	}

	return 0;

e_inval:
	return -EINVAL;
}

static int decode_pools(void **p, void *end, struct ceph_osdmap *map)
{
	return __decode_pools(p, end, map, false);
}

static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map)
{
	return __decode_pools(p, end, map, true);
}

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
static int __decode_pg_temp(void **p, void *end, struct ceph_osdmap *map,
			    bool incremental)
{
	u32 n;

	ceph_decode_32_safe(p, end, n, e_inval);
	while (n--) {
		struct ceph_pg pgid;
		u32 len, i;
		int ret;

		ret = ceph_decode_pgid(p, end, &pgid);
		if (ret)
			return ret;

		ceph_decode_32_safe(p, end, len, e_inval);

		ret = __remove_pg_mapping(&map->pg_temp, pgid);
		BUG_ON(!incremental && ret != -ENOENT);

		if (!incremental || len > 0) {
			struct ceph_pg_mapping *pg;

			ceph_decode_need(p, end, len*sizeof(u32), e_inval);

			if (len > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
				return -EINVAL;

			pg = kzalloc(sizeof(*pg) + len*sizeof(u32), GFP_NOFS);
			if (!pg)
				return -ENOMEM;

			pg->pgid = pgid;
832
			pg->pg_temp.len = len;
833
			for (i = 0; i < len; i++)
834
				pg->pg_temp.osds[i] = ceph_decode_32(p);
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

			ret = __insert_pg_mapping(pg, &map->pg_temp);
			if (ret) {
				kfree(pg);
				return ret;
			}
		}
	}

	return 0;

e_inval:
	return -EINVAL;
}

static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map)
{
	return __decode_pg_temp(p, end, map, false);
}

static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map)
{
	return __decode_pg_temp(p, end, map, true);
}

I
Ilya Dryomov 已提交
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
static int __decode_primary_temp(void **p, void *end, struct ceph_osdmap *map,
				 bool incremental)
{
	u32 n;

	ceph_decode_32_safe(p, end, n, e_inval);
	while (n--) {
		struct ceph_pg pgid;
		u32 osd;
		int ret;

		ret = ceph_decode_pgid(p, end, &pgid);
		if (ret)
			return ret;

		ceph_decode_32_safe(p, end, osd, e_inval);

		ret = __remove_pg_mapping(&map->primary_temp, pgid);
		BUG_ON(!incremental && ret != -ENOENT);

		if (!incremental || osd != (u32)-1) {
			struct ceph_pg_mapping *pg;

			pg = kzalloc(sizeof(*pg), GFP_NOFS);
			if (!pg)
				return -ENOMEM;

			pg->pgid = pgid;
			pg->primary_temp.osd = osd;

			ret = __insert_pg_mapping(pg, &map->primary_temp);
			if (ret) {
				kfree(pg);
				return ret;
			}
		}
	}

	return 0;

e_inval:
	return -EINVAL;
}

static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map)
{
	return __decode_primary_temp(p, end, map, false);
}

static int decode_new_primary_temp(void **p, void *end,
				   struct ceph_osdmap *map)
{
	return __decode_primary_temp(p, end, map, true);
}

S
Sage Weil 已提交
915 916 917
/*
 * decode a full map.
 */
918
static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
S
Sage Weil 已提交
919
{
920
	u8 struct_v;
921
	u32 epoch = 0;
S
Sage Weil 已提交
922
	void *start = *p;
923 924
	u32 max;
	u32 len, i;
925
	int err;
S
Sage Weil 已提交
926

927
	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
S
Sage Weil 已提交
928

929 930 931
	err = get_osdmap_client_data_v(p, end, "full", &struct_v);
	if (err)
		goto bad;
S
Sage Weil 已提交
932

933 934 935
	/* fsid, epoch, created, modified */
	ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) +
			 sizeof(map->created) + sizeof(map->modified), e_inval);
S
Sage Weil 已提交
936
	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
937
	epoch = map->epoch = ceph_decode_32(p);
S
Sage Weil 已提交
938 939 940
	ceph_decode_copy(p, &map->created, sizeof(map->created));
	ceph_decode_copy(p, &map->modified, sizeof(map->modified));

941 942 943 944
	/* pools */
	err = decode_pools(p, end, map);
	if (err)
		goto bad;
945

946 947
	/* pool_name */
	err = decode_pool_names(p, end, map);
948
	if (err)
949
		goto bad;
950

951
	ceph_decode_32_safe(p, end, map->pool_max, e_inval);
S
Sage Weil 已提交
952

953
	ceph_decode_32_safe(p, end, map->flags, e_inval);
S
Sage Weil 已提交
954

955 956
	/* max_osd */
	ceph_decode_32_safe(p, end, max, e_inval);
S
Sage Weil 已提交
957 958 959

	/* (re)alloc osd arrays */
	err = osdmap_set_max_osd(map, max);
960
	if (err)
S
Sage Weil 已提交
961 962
		goto bad;

963
	/* osd_state, osd_weight, osd_addrs->client_addr */
S
Sage Weil 已提交
964 965
	ceph_decode_need(p, end, 3*sizeof(u32) +
			 map->max_osd*(1 + sizeof(*map->osd_weight) +
966 967
				       sizeof(*map->osd_addr)), e_inval);

968 969 970
	if (ceph_decode_32(p) != map->max_osd)
		goto e_inval;

S
Sage Weil 已提交
971 972
	ceph_decode_copy(p, map->osd_state, map->max_osd);

973 974 975
	if (ceph_decode_32(p) != map->max_osd)
		goto e_inval;

S
Sage Weil 已提交
976
	for (i = 0; i < map->max_osd; i++)
977
		map->osd_weight[i] = ceph_decode_32(p);
S
Sage Weil 已提交
978

979 980 981
	if (ceph_decode_32(p) != map->max_osd)
		goto e_inval;

S
Sage Weil 已提交
982
	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
983 984
	for (i = 0; i < map->max_osd; i++)
		ceph_decode_addr(&map->osd_addr[i]);
S
Sage Weil 已提交
985 986

	/* pg_temp */
987 988 989
	err = decode_pg_temp(p, end, map);
	if (err)
		goto bad;
S
Sage Weil 已提交
990

I
Ilya Dryomov 已提交
991 992 993 994 995 996 997
	/* primary_temp */
	if (struct_v >= 1) {
		err = decode_primary_temp(p, end, map);
		if (err)
			goto bad;
	}

S
Sage Weil 已提交
998
	/* crush */
999
	ceph_decode_32_safe(p, end, len, e_inval);
1000
	map->crush = crush_decode(*p, min(*p + len, end));
S
Sage Weil 已提交
1001 1002 1003 1004 1005
	if (IS_ERR(map->crush)) {
		err = PTR_ERR(map->crush);
		map->crush = NULL;
		goto bad;
	}
1006
	*p += len;
S
Sage Weil 已提交
1007

1008
	/* ignore the rest */
S
Sage Weil 已提交
1009 1010
	*p = end;

1011
	dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
1012
	return 0;
S
Sage Weil 已提交
1013

1014 1015
e_inval:
	err = -EINVAL;
S
Sage Weil 已提交
1016
bad:
1017 1018 1019 1020 1021
	pr_err("corrupt full osdmap (%d) epoch %d off %d (%p of %p-%p)\n",
	       err, epoch, (int)(*p - start), *p, start, end);
	print_hex_dump(KERN_DEBUG, "osdmap: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       start, end - start, true);
1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037
	return err;
}

/*
 * Allocate and decode a full map.
 */
struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
{
	struct ceph_osdmap *map;
	int ret;

	map = kzalloc(sizeof(*map), GFP_NOFS);
	if (!map)
		return ERR_PTR(-ENOMEM);

	map->pg_temp = RB_ROOT;
1038
	map->primary_temp = RB_ROOT;
1039 1040 1041 1042 1043 1044 1045 1046 1047
	mutex_init(&map->crush_scratch_mutex);

	ret = osdmap_decode(p, end, map);
	if (ret) {
		ceph_osdmap_destroy(map);
		return ERR_PTR(ret);
	}

	return map;
S
Sage Weil 已提交
1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
}

/*
 * decode and apply an incremental map update.
 */
struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
					     struct ceph_osdmap *map,
					     struct ceph_messenger *msgr)
{
	struct crush_map *newcrush = NULL;
	struct ceph_fsid fsid;
	u32 epoch = 0;
	struct ceph_timespec modified;
1061 1062 1063 1064
	s32 len;
	u64 pool;
	__s64 new_pool_max;
	__s32 new_flags, max;
S
Sage Weil 已提交
1065
	void *start = *p;
1066
	int err;
1067
	u8 struct_v;
S
Sage Weil 已提交
1068

1069 1070
	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));

1071 1072 1073
	err = get_osdmap_client_data_v(p, end, "inc", &struct_v);
	if (err)
		goto bad;
S
Sage Weil 已提交
1074

1075 1076 1077
	/* fsid, epoch, modified, new_pool_max, new_flags */
	ceph_decode_need(p, end, sizeof(fsid) + sizeof(u32) + sizeof(modified) +
			 sizeof(u64) + sizeof(u32), e_inval);
S
Sage Weil 已提交
1078
	ceph_decode_copy(p, &fsid, sizeof(fsid));
1079
	epoch = ceph_decode_32(p);
S
Sage Weil 已提交
1080 1081
	BUG_ON(epoch != map->epoch+1);
	ceph_decode_copy(p, &modified, sizeof(modified));
1082
	new_pool_max = ceph_decode_64(p);
1083
	new_flags = ceph_decode_32(p);
S
Sage Weil 已提交
1084 1085

	/* full map? */
1086
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1087 1088 1089
	if (len > 0) {
		dout("apply_incremental full map len %d, %p to %p\n",
		     len, *p, end);
1090
		return ceph_osdmap_decode(p, min(*p+len, end));
S
Sage Weil 已提交
1091 1092 1093
	}

	/* new crush? */
1094
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1095 1096
	if (len > 0) {
		newcrush = crush_decode(*p, min(*p+len, end));
1097 1098 1099 1100 1101
		if (IS_ERR(newcrush)) {
			err = PTR_ERR(newcrush);
			newcrush = NULL;
			goto bad;
		}
S
Sage Weil 已提交
1102
		*p += len;
S
Sage Weil 已提交
1103 1104 1105 1106 1107
	}

	/* new flags? */
	if (new_flags >= 0)
		map->flags = new_flags;
1108 1109
	if (new_pool_max >= 0)
		map->pool_max = new_pool_max;
S
Sage Weil 已提交
1110 1111

	/* new max? */
1112
	ceph_decode_32_safe(p, end, max, e_inval);
S
Sage Weil 已提交
1113 1114
	if (max >= 0) {
		err = osdmap_set_max_osd(map, max);
1115
		if (err)
S
Sage Weil 已提交
1116 1117 1118 1119
			goto bad;
	}

	map->epoch++;
1120
	map->modified = modified;
S
Sage Weil 已提交
1121 1122 1123 1124 1125 1126 1127
	if (newcrush) {
		if (map->crush)
			crush_destroy(map->crush);
		map->crush = newcrush;
		newcrush = NULL;
	}

1128 1129 1130 1131
	/* new_pools */
	err = decode_new_pools(p, end, map);
	if (err)
		goto bad;
1132

1133 1134
	/* new_pool_names */
	err = decode_pool_names(p, end, map);
1135 1136
	if (err)
		goto bad;
S
Sage Weil 已提交
1137

1138
	/* old_pool */
1139
	ceph_decode_32_safe(p, end, len, e_inval);
1140 1141 1142
	while (len--) {
		struct ceph_pg_pool_info *pi;

1143
		ceph_decode_64_safe(p, end, pool, e_inval);
1144
		pi = __lookup_pg_pool(&map->pg_pools, pool);
1145 1146
		if (pi)
			__remove_pg_pool(&map->pg_pools, pi);
1147
	}
S
Sage Weil 已提交
1148 1149

	/* new_up */
1150
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1151 1152 1153
	while (len--) {
		u32 osd;
		struct ceph_entity_addr addr;
1154 1155
		ceph_decode_32_safe(p, end, osd, e_inval);
		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval);
1156
		ceph_decode_addr(&addr);
S
Sage Weil 已提交
1157 1158 1159 1160 1161 1162
		pr_info("osd%d up\n", osd);
		BUG_ON(osd >= map->max_osd);
		map->osd_state[osd] |= CEPH_OSD_UP;
		map->osd_addr[osd] = addr;
	}

1163
	/* new_state */
1164
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1165 1166
	while (len--) {
		u32 osd;
1167
		u8 xorstate;
1168
		ceph_decode_32_safe(p, end, osd, e_inval);
1169
		xorstate = **(u8 **)p;
S
Sage Weil 已提交
1170
		(*p)++;  /* clean flag */
1171 1172 1173 1174
		if (xorstate == 0)
			xorstate = CEPH_OSD_UP;
		if (xorstate & CEPH_OSD_UP)
			pr_info("osd%d down\n", osd);
S
Sage Weil 已提交
1175
		if (osd < map->max_osd)
1176
			map->osd_state[osd] ^= xorstate;
S
Sage Weil 已提交
1177 1178 1179
	}

	/* new_weight */
1180
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1181 1182
	while (len--) {
		u32 osd, off;
1183
		ceph_decode_need(p, end, sizeof(u32)*2, e_inval);
1184 1185
		osd = ceph_decode_32(p);
		off = ceph_decode_32(p);
S
Sage Weil 已提交
1186 1187 1188 1189 1190 1191 1192 1193
		pr_info("osd%d weight 0x%x %s\n", osd, off,
		     off == CEPH_OSD_IN ? "(in)" :
		     (off == CEPH_OSD_OUT ? "(out)" : ""));
		if (osd < map->max_osd)
			map->osd_weight[osd] = off;
	}

	/* new_pg_temp */
1194 1195 1196
	err = decode_new_pg_temp(p, end, map);
	if (err)
		goto bad;
S
Sage Weil 已提交
1197

I
Ilya Dryomov 已提交
1198 1199 1200 1201 1202 1203 1204
	/* new_primary_temp */
	if (struct_v >= 1) {
		err = decode_new_primary_temp(p, end, map);
		if (err)
			goto bad;
	}

S
Sage Weil 已提交
1205 1206
	/* ignore the rest */
	*p = end;
1207 1208

	dout("inc osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
S
Sage Weil 已提交
1209 1210
	return map;

1211 1212
e_inval:
	err = -EINVAL;
S
Sage Weil 已提交
1213
bad:
1214 1215
	pr_err("corrupt inc osdmap (%d) epoch %d off %d (%p of %p-%p)\n",
	       err, epoch, (int)(*p - start), *p, start, end);
1216 1217 1218
	print_hex_dump(KERN_DEBUG, "osdmap: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       start, end - start, true);
S
Sage Weil 已提交
1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234
	if (newcrush)
		crush_destroy(newcrush);
	return ERR_PTR(err);
}




/*
 * calculate file layout from given offset, length.
 * fill in correct oid, logical length, and object extent
 * offset, length.
 *
 * for now, we write only a single su, until we can
 * pass a stride back to the caller.
 */
S
Sage Weil 已提交
1235
int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
1236
				   u64 off, u64 len,
1237
				   u64 *ono,
S
Sage Weil 已提交
1238 1239 1240 1241 1242 1243 1244
				   u64 *oxoff, u64 *oxlen)
{
	u32 osize = le32_to_cpu(layout->fl_object_size);
	u32 su = le32_to_cpu(layout->fl_stripe_unit);
	u32 sc = le32_to_cpu(layout->fl_stripe_count);
	u32 bl, stripeno, stripepos, objsetno;
	u32 su_per_object;
1245
	u64 t, su_offset;
S
Sage Weil 已提交
1246

1247
	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, len,
S
Sage Weil 已提交
1248
	     osize, su);
S
Sage Weil 已提交
1249 1250
	if (su == 0 || sc == 0)
		goto invalid;
1251
	su_per_object = osize / su;
S
Sage Weil 已提交
1252 1253
	if (su_per_object == 0)
		goto invalid;
S
Sage Weil 已提交
1254 1255 1256
	dout("osize %u / su %u = su_per_object %u\n", osize, su,
	     su_per_object);

S
Sage Weil 已提交
1257 1258 1259
	if ((su & ~PAGE_MASK) != 0)
		goto invalid;

S
Sage Weil 已提交
1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
	/* bl = *off / su; */
	t = off;
	do_div(t, su);
	bl = t;
	dout("off %llu / su %u = bl %u\n", off, su, bl);

	stripeno = bl / sc;
	stripepos = bl % sc;
	objsetno = stripeno / su_per_object;

1270
	*ono = objsetno * sc + stripepos;
1271
	dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono);
1272 1273

	/* *oxoff = *off % layout->fl_stripe_unit;  # offset in su */
S
Sage Weil 已提交
1274
	t = off;
1275 1276 1277 1278 1279
	su_offset = do_div(t, su);
	*oxoff = su_offset + (stripeno % su_per_object) * su;

	/*
	 * Calculate the length of the extent being written to the selected
1280
	 * object. This is the minimum of the full length requested (len) or
1281 1282
	 * the remainder of the current stripe being written to.
	 */
1283
	*oxlen = min_t(u64, len, su - su_offset);
S
Sage Weil 已提交
1284 1285

	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
S
Sage Weil 已提交
1286 1287 1288 1289 1290 1291 1292 1293
	return 0;

invalid:
	dout(" invalid layout\n");
	*ono = 0;
	*oxoff = 0;
	*oxlen = 0;
	return -EINVAL;
S
Sage Weil 已提交
1294
}
1295
EXPORT_SYMBOL(ceph_calc_file_object_mapping);
S
Sage Weil 已提交
1296 1297

/*
1298 1299 1300
 * Calculate mapping of a (oloc, oid) pair to a PG.  Should only be
 * called with target's (oloc, oid), since tiering isn't taken into
 * account.
S
Sage Weil 已提交
1301
 */
1302 1303 1304 1305
int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
			struct ceph_object_locator *oloc,
			struct ceph_object_id *oid,
			struct ceph_pg *pg_out)
S
Sage Weil 已提交
1306
{
1307
	struct ceph_pg_pool_info *pi;
S
Sage Weil 已提交
1308

1309 1310
	pi = __lookup_pg_pool(&osdmap->pg_pools, oloc->pool);
	if (!pi)
1311
		return -EIO;
S
Sage Weil 已提交
1312

1313 1314 1315 1316 1317 1318
	pg_out->pool = oloc->pool;
	pg_out->seed = ceph_str_hash(pi->object_hash, oid->name,
				     oid->name_len);

	dout("%s '%.*s' pgid %llu.%x\n", __func__, oid->name_len, oid->name,
	     pg_out->pool, pg_out->seed);
S
Sage Weil 已提交
1319 1320
	return 0;
}
1321
EXPORT_SYMBOL(ceph_oloc_oid_to_pg);
S
Sage Weil 已提交
1322

1323 1324 1325
static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
		    int *result, int result_max,
		    const __u32 *weight, int weight_max)
1326
{
1327 1328 1329 1330 1331 1332 1333 1334
	int r;

	BUG_ON(result_max > CEPH_PG_MAX_SIZE);

	mutex_lock(&map->crush_scratch_mutex);
	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
			  weight, weight_max, map->crush_scratch_ary);
	mutex_unlock(&map->crush_scratch_mutex);
1335

1336
	return r;
1337 1338
}

S
Sage Weil 已提交
1339 1340 1341 1342
/*
 * Calculate raw osd vector for the given pgid.  Return pointer to osd
 * array, or NULL on failure.
 */
1343
static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
S
Sage Weil 已提交
1344 1345 1346 1347 1348
			int *osds, int *num)
{
	struct ceph_pg_mapping *pg;
	struct ceph_pg_pool_info *pool;
	int ruleno;
1349 1350
	int r;
	u32 pps;
S
Sage Weil 已提交
1351

1352
	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
1353 1354 1355
	if (!pool)
		return NULL;

S
Sage Weil 已提交
1356
	/* pg_temp? */
1357
	pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
1358
				    pool->pg_num_mask);
1359 1360
	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
	if (pg) {
1361 1362
		*num = pg->pg_temp.len;
		return pg->pg_temp.osds;
S
Sage Weil 已提交
1363 1364 1365
	}

	/* crush */
1366 1367
	ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
				 pool->type, pool->size);
S
Sage Weil 已提交
1368
	if (ruleno < 0) {
1369 1370
		pr_err("no crush rule pool %lld ruleset %d type %d size %d\n",
		       pgid.pool, pool->crush_ruleset, pool->type,
1371
		       pool->size);
S
Sage Weil 已提交
1372 1373 1374
		return NULL;
	}

1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391
	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
		/* hash pool id and seed sothat pool PGs do not overlap */
		pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
				     ceph_stable_mod(pgid.seed, pool->pgp_num,
						     pool->pgp_num_mask),
				     pgid.pool);
	} else {
		/*
		 * legacy ehavior: add ps and pool together.  this is
		 * not a great approach because the PGs from each pool
		 * will overlap on top of each other: 0.5 == 1.4 ==
		 * 2.3 == ...
		 */
		pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
				      pool->pgp_num_mask) +
			(unsigned)pgid.pool;
	}
1392 1393
	r = do_crush(osdmap, ruleno, pps, osds, min_t(int, pool->size, *num),
		     osdmap->osd_weight, osdmap->max_osd);
S
Sage Weil 已提交
1394
	if (r < 0) {
1395 1396
		pr_err("error %d from crush rule: pool %lld ruleset %d type %d"
		       " size %d\n", r, pgid.pool, pool->crush_ruleset,
1397
		       pool->type, pool->size);
S
Sage Weil 已提交
1398 1399 1400
		return NULL;
	}
	*num = r;
S
Sage Weil 已提交
1401 1402 1403
	return osds;
}

1404 1405 1406
/*
 * Return acting set for given pgid.
 */
1407
int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424
			int *acting)
{
	int rawosds[CEPH_PG_MAX_SIZE], *osds;
	int i, o, num = CEPH_PG_MAX_SIZE;

	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
	if (!osds)
		return -1;

	/* primary is first up osd */
	o = 0;
	for (i = 0; i < num; i++)
		if (ceph_osd_is_up(osdmap, osds[i]))
			acting[o++] = osds[i];
	return o;
}

S
Sage Weil 已提交
1425 1426 1427
/*
 * Return primary osd for given pgid, or -1 if none.
 */
1428
int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
S
Sage Weil 已提交
1429
{
1430 1431
	int rawosds[CEPH_PG_MAX_SIZE], *osds;
	int i, num = CEPH_PG_MAX_SIZE;
S
Sage Weil 已提交
1432 1433 1434 1435 1436 1437 1438

	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
	if (!osds)
		return -1;

	/* primary is first up osd */
	for (i = 0; i < num; i++)
1439
		if (ceph_osd_is_up(osdmap, osds[i]))
S
Sage Weil 已提交
1440 1441 1442
			return osds[i];
	return -1;
}
1443
EXPORT_SYMBOL(ceph_calc_pg_primary);