osdmap.c 38.5 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);

332 333 334 335 336
	ceph_decode_need(p, end, sizeof(u8), done);
	c->chooseleaf_vary_r = ceph_decode_8(p);
	dout("crush decode tunable chooseleaf_vary_r = %d",
	     c->chooseleaf_vary_r);

S
Sage Weil 已提交
337
done:
S
Sage Weil 已提交
338 339 340 341 342 343 344 345 346 347 348 349
	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);
}

/*
350
 * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
351
 * to a set of osds) and primary_temp (explicit primary setting)
S
Sage Weil 已提交
352
 */
353
static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
354
{
355 356 357 358 359
	if (l.pool < r.pool)
		return -1;
	if (l.pool > r.pool)
		return 1;
	if (l.seed < r.seed)
360
		return -1;
361
	if (l.seed > r.seed)
362 363 364 365
		return 1;
	return 0;
}

366 367
static int __insert_pg_mapping(struct ceph_pg_mapping *new,
			       struct rb_root *root)
S
Sage Weil 已提交
368 369 370 371
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_pg_mapping *pg = NULL;
372
	int c;
S
Sage Weil 已提交
373

S
Sage Weil 已提交
374
	dout("__insert_pg_mapping %llx %p\n", *(u64 *)&new->pgid, new);
S
Sage Weil 已提交
375 376 377
	while (*p) {
		parent = *p;
		pg = rb_entry(parent, struct ceph_pg_mapping, node);
378 379
		c = pgid_cmp(new->pgid, pg->pgid);
		if (c < 0)
S
Sage Weil 已提交
380
			p = &(*p)->rb_left;
381
		else if (c > 0)
S
Sage Weil 已提交
382 383
			p = &(*p)->rb_right;
		else
384
			return -EEXIST;
S
Sage Weil 已提交
385 386 387 388
	}

	rb_link_node(&new->node, parent, p);
	rb_insert_color(&new->node, root);
389
	return 0;
S
Sage Weil 已提交
390 391
}

392
static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
393
						   struct ceph_pg pgid)
394 395 396 397 398 399 400 401
{
	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
402
		if (c < 0) {
403
			n = n->rb_left;
S
Sage Weil 已提交
404
		} else if (c > 0) {
405
			n = n->rb_right;
S
Sage Weil 已提交
406
		} else {
407 408
			dout("__lookup_pg_mapping %lld.%x got %p\n",
			     pgid.pool, pgid.seed, pg);
409
			return pg;
S
Sage Weil 已提交
410
		}
411 412 413 414
	}
	return NULL;
}

415
static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid)
S
Sage Weil 已提交
416 417 418 419
{
	struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid);

	if (pg) {
420 421
		dout("__remove_pg_mapping %lld.%x %p\n", pgid.pool, pgid.seed,
		     pg);
S
Sage Weil 已提交
422 423 424 425
		rb_erase(&pg->node, root);
		kfree(pg);
		return 0;
	}
426
	dout("__remove_pg_mapping %lld.%x dne\n", pgid.pool, pgid.seed);
S
Sage Weil 已提交
427 428 429
	return -ENOENT;
}

430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
/*
 * 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;
}

455
static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id)
456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
{
	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
472 473 474 475 476
struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id)
{
	return __lookup_pg_pool(&map->pg_pools, id);
}

477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492
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
493 494 495 496 497 498 499 500 501 502 503 504
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;
}
505
EXPORT_SYMBOL(ceph_pg_poolid_by_name);
Y
Yehuda Sadeh 已提交
506

507 508 509 510 511 512 513
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);
}

514
static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
515
{
516 517 518 519 520 521 522 523 524 525 526
	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;
	}
527 528
	if (cv > 9) {
		pr_warning("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv);
529 530 531 532 533
		return -EINVAL;
	}
	len = ceph_decode_32(p);
	ceph_decode_need(p, end, len, bad);
	pool_end = *p + len;
S
Sage Weil 已提交
534

535 536 537 538
	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
539

540 541 542 543 544 545 546 547 548 549 550 551 552 553
	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
554 555
	}

556
	/* skip removed_snaps */
557 558 559 560 561
	num = ceph_decode_32(p);
	*p += num * (8 + 8);

	*p += 8;  /* skip auid */
	pi->flags = ceph_decode_64(p);
562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583
	*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;
	}
584 585 586 587 588

	/* ignore the rest */

	*p = pool_end;
	calc_pg_masks(pi);
S
Sage Weil 已提交
589 590 591 592
	return 0;

bad:
	return -EINVAL;
593 594
}

595
static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
596 597
{
	struct ceph_pg_pool_info *pi;
598 599
	u32 num, len;
	u64 pool;
600 601 602 603

	ceph_decode_32_safe(p, end, num, bad);
	dout(" %d pool names\n", num);
	while (num--) {
604
		ceph_decode_64_safe(p, end, pool, bad);
605
		ceph_decode_32_safe(p, end, len, bad);
606
		dout("  pool %llu len %d\n", pool, len);
607
		ceph_decode_need(p, end, len, bad);
608 609
		pi = __lookup_pg_pool(&map->pg_pools, pool);
		if (pi) {
610 611 612 613
			char *name = kstrndup(*p, len, GFP_NOFS);

			if (!name)
				return -ENOMEM;
614
			kfree(pi->name);
615 616
			pi->name = name;
			dout("  name is %s\n", pi->name);
617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640
		}
		*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);
	}
641 642 643 644 645 646 647
	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);
	}
648 649 650 651 652 653 654 655 656
	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);
657
	kfree(map->osd_primary_affinity);
658 659 660 661
	kfree(map);
}

/*
662 663 664
 * Adjust max_osd value, (re)allocate arrays.
 *
 * The new elements are properly initialized.
665 666 667 668 669
 */
static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
{
	u8 *state;
	u32 *weight;
670 671
	struct ceph_entity_addr *addr;
	int i;
672

673
	state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS);
674 675 676 677
	if (!state)
		return -ENOMEM;
	map->osd_state = state;

678
	weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS);
679 680 681
	if (!weight)
		return -ENOMEM;
	map->osd_weight = weight;
682

683 684
	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
	if (!addr)
685
		return -ENOMEM;
686
	map->osd_addr = addr;
687

688
	for (i = map->max_osd; i < max; i++) {
689 690 691
		map->osd_state[i] = 0;
		map->osd_weight[i] = CEPH_OSD_OUT;
		memset(map->osd_addr + i, 0, sizeof(*map->osd_addr));
692 693
	}

694 695 696 697 698 699 700
	if (map->osd_primary_affinity) {
		u32 *affinity;

		affinity = krealloc(map->osd_primary_affinity,
				    max*sizeof(*affinity), GFP_NOFS);
		if (!affinity)
			return -ENOMEM;
701
		map->osd_primary_affinity = affinity;
702 703

		for (i = map->max_osd; i < max; i++)
704 705
			map->osd_primary_affinity[i] =
			    CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
706 707
	}

708
	map->max_osd = max;
709

710 711 712
	return 0;
}

713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769
#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;
}

770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818
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);
}

819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
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;
852
			pg->pg_temp.len = len;
853
			for (i = 0; i < len; i++)
854
				pg->pg_temp.osds[i] = ceph_decode_32(p);
855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879

			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
880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934
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);
}

935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
{
	BUG_ON(osd >= map->max_osd);

	if (!map->osd_primary_affinity)
		return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;

	return map->osd_primary_affinity[osd];
}

static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff)
{
	BUG_ON(osd >= map->max_osd);

	if (!map->osd_primary_affinity) {
		int i;

		map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32),
						    GFP_NOFS);
		if (!map->osd_primary_affinity)
			return -ENOMEM;

		for (i = 0; i < map->max_osd; i++)
			map->osd_primary_affinity[i] =
			    CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
	}

	map->osd_primary_affinity[osd] = aff;

	return 0;
}

967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
static int decode_primary_affinity(void **p, void *end,
				   struct ceph_osdmap *map)
{
	u32 len, i;

	ceph_decode_32_safe(p, end, len, e_inval);
	if (len == 0) {
		kfree(map->osd_primary_affinity);
		map->osd_primary_affinity = NULL;
		return 0;
	}
	if (len != map->max_osd)
		goto e_inval;

	ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval);

	for (i = 0; i < map->max_osd; i++) {
		int ret;

		ret = set_primary_affinity(map, i, ceph_decode_32(p));
		if (ret)
			return ret;
	}

	return 0;

e_inval:
	return -EINVAL;
}

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

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

		ceph_decode_32_safe(p, end, osd, e_inval);
		ceph_decode_32_safe(p, end, aff, e_inval);

		ret = set_primary_affinity(map, osd, aff);
		if (ret)
			return ret;
1013 1014

		pr_info("osd%d primary-affinity 0x%x\n", osd, aff);
1015 1016 1017 1018 1019 1020 1021 1022
	}

	return 0;

e_inval:
	return -EINVAL;
}

S
Sage Weil 已提交
1023 1024 1025
/*
 * decode a full map.
 */
1026
static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
S
Sage Weil 已提交
1027
{
1028
	u8 struct_v;
1029
	u32 epoch = 0;
S
Sage Weil 已提交
1030
	void *start = *p;
1031 1032
	u32 max;
	u32 len, i;
1033
	int err;
S
Sage Weil 已提交
1034

1035
	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
S
Sage Weil 已提交
1036

1037 1038 1039
	err = get_osdmap_client_data_v(p, end, "full", &struct_v);
	if (err)
		goto bad;
S
Sage Weil 已提交
1040

1041 1042 1043
	/* 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
1044
	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
1045
	epoch = map->epoch = ceph_decode_32(p);
S
Sage Weil 已提交
1046 1047 1048
	ceph_decode_copy(p, &map->created, sizeof(map->created));
	ceph_decode_copy(p, &map->modified, sizeof(map->modified));

1049 1050 1051 1052
	/* pools */
	err = decode_pools(p, end, map);
	if (err)
		goto bad;
1053

1054 1055
	/* pool_name */
	err = decode_pool_names(p, end, map);
1056
	if (err)
1057
		goto bad;
1058

1059
	ceph_decode_32_safe(p, end, map->pool_max, e_inval);
S
Sage Weil 已提交
1060

1061
	ceph_decode_32_safe(p, end, map->flags, e_inval);
S
Sage Weil 已提交
1062

1063 1064
	/* max_osd */
	ceph_decode_32_safe(p, end, max, e_inval);
S
Sage Weil 已提交
1065 1066 1067

	/* (re)alloc osd arrays */
	err = osdmap_set_max_osd(map, max);
1068
	if (err)
S
Sage Weil 已提交
1069 1070
		goto bad;

1071
	/* osd_state, osd_weight, osd_addrs->client_addr */
S
Sage Weil 已提交
1072 1073
	ceph_decode_need(p, end, 3*sizeof(u32) +
			 map->max_osd*(1 + sizeof(*map->osd_weight) +
1074 1075
				       sizeof(*map->osd_addr)), e_inval);

1076 1077 1078
	if (ceph_decode_32(p) != map->max_osd)
		goto e_inval;

S
Sage Weil 已提交
1079 1080
	ceph_decode_copy(p, map->osd_state, map->max_osd);

1081 1082 1083
	if (ceph_decode_32(p) != map->max_osd)
		goto e_inval;

S
Sage Weil 已提交
1084
	for (i = 0; i < map->max_osd; i++)
1085
		map->osd_weight[i] = ceph_decode_32(p);
S
Sage Weil 已提交
1086

1087 1088 1089
	if (ceph_decode_32(p) != map->max_osd)
		goto e_inval;

S
Sage Weil 已提交
1090
	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
1091 1092
	for (i = 0; i < map->max_osd; i++)
		ceph_decode_addr(&map->osd_addr[i]);
S
Sage Weil 已提交
1093 1094

	/* pg_temp */
1095 1096 1097
	err = decode_pg_temp(p, end, map);
	if (err)
		goto bad;
S
Sage Weil 已提交
1098

I
Ilya Dryomov 已提交
1099 1100 1101 1102 1103 1104 1105
	/* primary_temp */
	if (struct_v >= 1) {
		err = decode_primary_temp(p, end, map);
		if (err)
			goto bad;
	}

1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116
	/* primary_affinity */
	if (struct_v >= 2) {
		err = decode_primary_affinity(p, end, map);
		if (err)
			goto bad;
	} else {
		/* XXX can this happen? */
		kfree(map->osd_primary_affinity);
		map->osd_primary_affinity = NULL;
	}

S
Sage Weil 已提交
1117
	/* crush */
1118
	ceph_decode_32_safe(p, end, len, e_inval);
1119
	map->crush = crush_decode(*p, min(*p + len, end));
S
Sage Weil 已提交
1120 1121 1122 1123 1124
	if (IS_ERR(map->crush)) {
		err = PTR_ERR(map->crush);
		map->crush = NULL;
		goto bad;
	}
1125
	*p += len;
S
Sage Weil 已提交
1126

1127
	/* ignore the rest */
S
Sage Weil 已提交
1128 1129
	*p = end;

1130
	dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
1131
	return 0;
S
Sage Weil 已提交
1132

1133 1134
e_inval:
	err = -EINVAL;
S
Sage Weil 已提交
1135
bad:
1136 1137 1138 1139 1140
	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);
1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
	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;
1157
	map->primary_temp = RB_ROOT;
1158 1159 1160 1161 1162 1163 1164 1165 1166
	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
1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179
}

/*
 * 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;
1180 1181 1182 1183
	s32 len;
	u64 pool;
	__s64 new_pool_max;
	__s32 new_flags, max;
S
Sage Weil 已提交
1184
	void *start = *p;
1185
	int err;
1186
	u8 struct_v;
S
Sage Weil 已提交
1187

1188 1189
	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));

1190 1191 1192
	err = get_osdmap_client_data_v(p, end, "inc", &struct_v);
	if (err)
		goto bad;
S
Sage Weil 已提交
1193

1194 1195 1196
	/* 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
1197
	ceph_decode_copy(p, &fsid, sizeof(fsid));
1198
	epoch = ceph_decode_32(p);
S
Sage Weil 已提交
1199 1200
	BUG_ON(epoch != map->epoch+1);
	ceph_decode_copy(p, &modified, sizeof(modified));
1201
	new_pool_max = ceph_decode_64(p);
1202
	new_flags = ceph_decode_32(p);
S
Sage Weil 已提交
1203 1204

	/* full map? */
1205
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1206 1207 1208
	if (len > 0) {
		dout("apply_incremental full map len %d, %p to %p\n",
		     len, *p, end);
1209
		return ceph_osdmap_decode(p, min(*p+len, end));
S
Sage Weil 已提交
1210 1211 1212
	}

	/* new crush? */
1213
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1214 1215
	if (len > 0) {
		newcrush = crush_decode(*p, min(*p+len, end));
1216 1217 1218 1219 1220
		if (IS_ERR(newcrush)) {
			err = PTR_ERR(newcrush);
			newcrush = NULL;
			goto bad;
		}
S
Sage Weil 已提交
1221
		*p += len;
S
Sage Weil 已提交
1222 1223 1224 1225 1226
	}

	/* new flags? */
	if (new_flags >= 0)
		map->flags = new_flags;
1227 1228
	if (new_pool_max >= 0)
		map->pool_max = new_pool_max;
S
Sage Weil 已提交
1229 1230

	/* new max? */
1231
	ceph_decode_32_safe(p, end, max, e_inval);
S
Sage Weil 已提交
1232 1233
	if (max >= 0) {
		err = osdmap_set_max_osd(map, max);
1234
		if (err)
S
Sage Weil 已提交
1235 1236 1237 1238
			goto bad;
	}

	map->epoch++;
1239
	map->modified = modified;
S
Sage Weil 已提交
1240 1241 1242 1243 1244 1245 1246
	if (newcrush) {
		if (map->crush)
			crush_destroy(map->crush);
		map->crush = newcrush;
		newcrush = NULL;
	}

1247 1248 1249 1250
	/* new_pools */
	err = decode_new_pools(p, end, map);
	if (err)
		goto bad;
1251

1252 1253
	/* new_pool_names */
	err = decode_pool_names(p, end, map);
1254 1255
	if (err)
		goto bad;
S
Sage Weil 已提交
1256

1257
	/* old_pool */
1258
	ceph_decode_32_safe(p, end, len, e_inval);
1259 1260 1261
	while (len--) {
		struct ceph_pg_pool_info *pi;

1262
		ceph_decode_64_safe(p, end, pool, e_inval);
1263
		pi = __lookup_pg_pool(&map->pg_pools, pool);
1264 1265
		if (pi)
			__remove_pg_pool(&map->pg_pools, pi);
1266
	}
S
Sage Weil 已提交
1267 1268

	/* new_up */
1269
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1270 1271 1272
	while (len--) {
		u32 osd;
		struct ceph_entity_addr addr;
1273 1274
		ceph_decode_32_safe(p, end, osd, e_inval);
		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval);
1275
		ceph_decode_addr(&addr);
S
Sage Weil 已提交
1276 1277 1278 1279 1280 1281
		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;
	}

1282
	/* new_state */
1283
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1284 1285
	while (len--) {
		u32 osd;
1286
		u8 xorstate;
1287
		ceph_decode_32_safe(p, end, osd, e_inval);
1288
		xorstate = **(u8 **)p;
S
Sage Weil 已提交
1289
		(*p)++;  /* clean flag */
1290 1291 1292 1293
		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
1294
		if (osd < map->max_osd)
1295
			map->osd_state[osd] ^= xorstate;
S
Sage Weil 已提交
1296 1297 1298
	}

	/* new_weight */
1299
	ceph_decode_32_safe(p, end, len, e_inval);
S
Sage Weil 已提交
1300 1301
	while (len--) {
		u32 osd, off;
1302
		ceph_decode_need(p, end, sizeof(u32)*2, e_inval);
1303 1304
		osd = ceph_decode_32(p);
		off = ceph_decode_32(p);
S
Sage Weil 已提交
1305 1306 1307 1308 1309 1310 1311 1312
		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 */
1313 1314 1315
	err = decode_new_pg_temp(p, end, map);
	if (err)
		goto bad;
S
Sage Weil 已提交
1316

I
Ilya Dryomov 已提交
1317 1318 1319 1320 1321 1322 1323
	/* new_primary_temp */
	if (struct_v >= 1) {
		err = decode_new_primary_temp(p, end, map);
		if (err)
			goto bad;
	}

1324 1325 1326 1327 1328 1329 1330
	/* new_primary_affinity */
	if (struct_v >= 2) {
		err = decode_new_primary_affinity(p, end, map);
		if (err)
			goto bad;
	}

S
Sage Weil 已提交
1331 1332
	/* ignore the rest */
	*p = end;
1333 1334

	dout("inc osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
S
Sage Weil 已提交
1335 1336
	return map;

1337 1338
e_inval:
	err = -EINVAL;
S
Sage Weil 已提交
1339
bad:
1340 1341
	pr_err("corrupt inc osdmap (%d) epoch %d off %d (%p of %p-%p)\n",
	       err, epoch, (int)(*p - start), *p, start, end);
1342 1343 1344
	print_hex_dump(KERN_DEBUG, "osdmap: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       start, end - start, true);
S
Sage Weil 已提交
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
	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
1361
int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
1362
				   u64 off, u64 len,
1363
				   u64 *ono,
S
Sage Weil 已提交
1364 1365 1366 1367 1368 1369 1370
				   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;
1371
	u64 t, su_offset;
S
Sage Weil 已提交
1372

1373
	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, len,
S
Sage Weil 已提交
1374
	     osize, su);
S
Sage Weil 已提交
1375 1376
	if (su == 0 || sc == 0)
		goto invalid;
1377
	su_per_object = osize / su;
S
Sage Weil 已提交
1378 1379
	if (su_per_object == 0)
		goto invalid;
S
Sage Weil 已提交
1380 1381 1382
	dout("osize %u / su %u = su_per_object %u\n", osize, su,
	     su_per_object);

S
Sage Weil 已提交
1383 1384 1385
	if ((su & ~PAGE_MASK) != 0)
		goto invalid;

S
Sage Weil 已提交
1386 1387 1388 1389 1390 1391 1392 1393 1394 1395
	/* 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;

1396
	*ono = objsetno * sc + stripepos;
1397
	dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono);
1398 1399

	/* *oxoff = *off % layout->fl_stripe_unit;  # offset in su */
S
Sage Weil 已提交
1400
	t = off;
1401 1402 1403 1404 1405
	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
1406
	 * object. This is the minimum of the full length requested (len) or
1407 1408
	 * the remainder of the current stripe being written to.
	 */
1409
	*oxlen = min_t(u64, len, su - su_offset);
S
Sage Weil 已提交
1410 1411

	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
S
Sage Weil 已提交
1412 1413 1414 1415 1416 1417 1418 1419
	return 0;

invalid:
	dout(" invalid layout\n");
	*ono = 0;
	*oxoff = 0;
	*oxlen = 0;
	return -EINVAL;
S
Sage Weil 已提交
1420
}
1421
EXPORT_SYMBOL(ceph_calc_file_object_mapping);
S
Sage Weil 已提交
1422 1423

/*
1424 1425 1426
 * 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
1427
 */
1428 1429 1430 1431
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
1432
{
1433
	struct ceph_pg_pool_info *pi;
S
Sage Weil 已提交
1434

1435 1436
	pi = __lookup_pg_pool(&osdmap->pg_pools, oloc->pool);
	if (!pi)
1437
		return -EIO;
S
Sage Weil 已提交
1438

1439 1440 1441 1442 1443 1444
	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
1445 1446
	return 0;
}
1447
EXPORT_SYMBOL(ceph_oloc_oid_to_pg);
S
Sage Weil 已提交
1448

1449 1450 1451
static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
		    int *result, int result_max,
		    const __u32 *weight, int weight_max)
1452
{
1453 1454 1455 1456 1457 1458 1459 1460
	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);
1461

1462
	return r;
1463 1464
}

1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540
/*
 * Calculate raw (crush) set for given pgid.
 *
 * Return raw set length, or error.
 */
static int pg_to_raw_osds(struct ceph_osdmap *osdmap,
			  struct ceph_pg_pool_info *pool,
			  struct ceph_pg pgid, u32 pps, int *osds)
{
	int ruleno;
	int len;

	/* crush */
	ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
				 pool->type, pool->size);
	if (ruleno < 0) {
		pr_err("no crush rule: pool %lld ruleset %d type %d size %d\n",
		       pgid.pool, pool->crush_ruleset, pool->type,
		       pool->size);
		return -ENOENT;
	}

	len = do_crush(osdmap, ruleno, pps, osds,
		       min_t(int, pool->size, CEPH_PG_MAX_SIZE),
		       osdmap->osd_weight, osdmap->max_osd);
	if (len < 0) {
		pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n",
		       len, ruleno, pgid.pool, pool->crush_ruleset,
		       pool->type, pool->size);
		return len;
	}

	return len;
}

/*
 * Given raw set, calculate up set and up primary.
 *
 * Return up set length.  *primary is set to up primary osd id, or -1
 * if up set is empty.
 */
static int raw_to_up_osds(struct ceph_osdmap *osdmap,
			  struct ceph_pg_pool_info *pool,
			  int *osds, int len, int *primary)
{
	int up_primary = -1;
	int i;

	if (ceph_can_shift_osds(pool)) {
		int removed = 0;

		for (i = 0; i < len; i++) {
			if (ceph_osd_is_down(osdmap, osds[i])) {
				removed++;
				continue;
			}
			if (removed)
				osds[i - removed] = osds[i];
		}

		len -= removed;
		if (len > 0)
			up_primary = osds[0];
	} else {
		for (i = len - 1; i >= 0; i--) {
			if (ceph_osd_is_down(osdmap, osds[i]))
				osds[i] = CRUSH_ITEM_NONE;
			else
				up_primary = osds[i];
		}
	}

	*primary = up_primary;
	return len;
}

1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555
static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
				   struct ceph_pg_pool_info *pool,
				   int *osds, int len, int *primary)
{
	int i;
	int pos = -1;

	/*
	 * Do we have any non-default primary_affinity values for these
	 * osds?
	 */
	if (!osdmap->osd_primary_affinity)
		return;

	for (i = 0; i < len; i++) {
1556 1557 1558 1559
		int osd = osds[i];

		if (osd != CRUSH_ITEM_NONE &&
		    osdmap->osd_primary_affinity[osd] !=
1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572
					CEPH_OSD_DEFAULT_PRIMARY_AFFINITY) {
			break;
		}
	}
	if (i == len)
		return;

	/*
	 * Pick the primary.  Feed both the seed (for the pg) and the
	 * osd into the hash/rng so that a proportional fraction of an
	 * osd's pgs get rejected as primary.
	 */
	for (i = 0; i < len; i++) {
1573
		int osd = osds[i];
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
		u32 aff;

		if (osd == CRUSH_ITEM_NONE)
			continue;

		aff = osdmap->osd_primary_affinity[osd];
		if (aff < CEPH_OSD_MAX_PRIMARY_AFFINITY &&
		    (crush_hash32_2(CRUSH_HASH_RJENKINS1,
				    pps, osd) >> 16) >= aff) {
			/*
			 * We chose not to use this primary.  Note it
			 * anyway as a fallback in case we don't pick
			 * anyone else, but keep looking.
			 */
			if (pos < 0)
				pos = i;
		} else {
			pos = i;
			break;
		}
	}
	if (pos < 0)
		return;

	*primary = osds[pos];

	if (ceph_can_shift_osds(pool) && pos > 0) {
		/* move the new primary to the front */
		for (i = pos; i > 0; i--)
			osds[i] = osds[i - 1];
		osds[0] = *primary;
	}
}

1608
/*
1609
 * Given up set, apply pg_temp and primary_temp mappings.
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655
 *
 * Return acting set length.  *primary is set to acting primary osd id,
 * or -1 if acting set is empty.
 */
static int apply_temps(struct ceph_osdmap *osdmap,
		       struct ceph_pg_pool_info *pool, struct ceph_pg pgid,
		       int *osds, int len, int *primary)
{
	struct ceph_pg_mapping *pg;
	int temp_len;
	int temp_primary;
	int i;

	/* raw_pg -> pg */
	pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
				    pool->pg_num_mask);

	/* pg_temp? */
	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
	if (pg) {
		temp_len = 0;
		temp_primary = -1;

		for (i = 0; i < pg->pg_temp.len; i++) {
			if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) {
				if (ceph_can_shift_osds(pool))
					continue;
				else
					osds[temp_len++] = CRUSH_ITEM_NONE;
			} else {
				osds[temp_len++] = pg->pg_temp.osds[i];
			}
		}

		/* apply pg_temp's primary */
		for (i = 0; i < temp_len; i++) {
			if (osds[i] != CRUSH_ITEM_NONE) {
				temp_primary = osds[i];
				break;
			}
		}
	} else {
		temp_len = len;
		temp_primary = *primary;
	}

1656 1657 1658 1659 1660
	/* primary_temp? */
	pg = __lookup_pg_mapping(&osdmap->primary_temp, pgid);
	if (pg)
		temp_primary = pg->primary_temp.osd;

1661 1662 1663 1664
	*primary = temp_primary;
	return temp_len;
}

1665
/*
1666 1667
 * Calculate acting set for given pgid.
 *
1668 1669
 * Return acting set length, or error.  *primary is set to acting
 * primary osd id, or -1 if acting set is empty or on error.
1670
 */
1671
int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
1672
			int *osds, int *primary)
1673
{
1674 1675 1676
	struct ceph_pg_pool_info *pool;
	u32 pps;
	int len;
1677

1678
	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
1679 1680 1681 1682
	if (!pool) {
		*primary = -1;
		return -ENOENT;
	}
1683

1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702
	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
		/* hash pool id and seed so that 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 behavior: 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;
	}

	len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
1703 1704
	if (len < 0) {
		*primary = -1;
1705
		return len;
1706
	}
1707

1708
	len = raw_to_up_osds(osdmap, pool, osds, len, primary);
1709

1710 1711
	apply_primary_affinity(osdmap, pps, pool, osds, len, primary);

1712
	len = apply_temps(osdmap, pool, pgid, osds, len, primary);
1713 1714

	return len;
1715 1716
}

S
Sage Weil 已提交
1717 1718 1719
/*
 * Return primary osd for given pgid, or -1 if none.
 */
1720
int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
S
Sage Weil 已提交
1721
{
1722 1723
	int osds[CEPH_PG_MAX_SIZE];
	int primary;
S
Sage Weil 已提交
1724

1725
	ceph_calc_pg_acting(osdmap, pgid, osds, &primary);
S
Sage Weil 已提交
1726

1727
	return primary;
S
Sage Weil 已提交
1728
}
1729
EXPORT_SYMBOL(ceph_calc_pg_primary);