osdmap.c 26.7 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 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72

char *ceph_osdmap_state_str(char *str, int len, int state)
{
	int flag = 0;

	if (!len)
		goto done;

	*str = '\0';
	if (state) {
		if (state & CEPH_OSD_EXISTS) {
			snprintf(str, len, "exists");
			flag = 1;
		}
		if (state & CEPH_OSD_UP) {
			snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""),
				 "up");
			flag = 1;
		}
	} else {
		snprintf(str, len, "doesn't exist");
	}
done:
	return str;
}

/* maps */

static int calc_bits_of(unsigned t)
{
	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)
{
	pi->pg_num_mask = (1 << calc_bits_of(le32_to_cpu(pi->v.pg_num)-1)) - 1;
	pi->pgp_num_mask =
		(1 << calc_bits_of(le32_to_cpu(pi->v.pgp_num)-1)) - 1;
	pi->lpg_num_mask =
		(1 << calc_bits_of(le32_to_cpu(pi->v.lpg_num)-1)) - 1;
	pi->lpgp_num_mask =
		(1 << calc_bits_of(le32_to_cpu(pi->v.lpgp_num)-1)) - 1;
}

/*
 * 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);
73
	b->item_weight = ceph_decode_32(p);
S
Sage Weil 已提交
74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91
	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++) {
92 93
		b->item_weights[j] = ceph_decode_32(p);
		b->sum_weights[j] = ceph_decode_32(p);
S
Sage Weil 已提交
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110
	}
	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++)
111
		b->node_weights[j] = ceph_decode_32(p);
S
Sage Weil 已提交
112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
	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++) {
130 131
		b->item_weights[j] = ceph_decode_32(p);
		b->straws[j] = ceph_decode_32(p);
S
Sage Weil 已提交
132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
	}
	return 0;
bad:
	return -EINVAL;
}

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;

	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);

	ceph_decode_need(p, end, 4*sizeof(u32), bad);
154
	magic = ceph_decode_32(p);
S
Sage Weil 已提交
155 156 157 158 159
	if (magic != CRUSH_MAGIC) {
		pr_err("crush_decode magic %x != current %x\n",
		       (unsigned)magic, (unsigned)CRUSH_MAGIC);
		goto bad;
	}
160 161 162
	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
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205

	c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS);
	if (c->device_parents == NULL)
		goto badmem;
	c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS);
	if (c->bucket_parents == NULL)
		goto badmem;

	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:
206
			err = -EINVAL;
S
Sage Weil 已提交
207 208 209 210 211 212 213 214
			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);
215 216
		b->id = ceph_decode_32(p);
		b->type = ceph_decode_16(p);
217 218
		b->alg = ceph_decode_8(p);
		b->hash = ceph_decode_8(p);
219 220
		b->weight = ceph_decode_32(p);
		b->size = ceph_decode_32(p);
S
Sage Weil 已提交
221 222 223 224 225 226 227 228 229 230 231 232 233 234

		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++)
235
			b->items[j] = ceph_decode_32(p);
S
Sage Weil 已提交
236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284

		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
285
		err = -EINVAL;
S
Sage Weil 已提交
286 287 288 289 290 291 292 293 294 295 296 297 298
		if (yes > ULONG_MAX / sizeof(struct crush_rule_step))
			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++) {
299 300 301
			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
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
		}
	}

	/* ignore trailing name maps. */

	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);
}

/*
319 320
 * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
 * to a set of osds)
S
Sage Weil 已提交
321
 */
322 323 324 325 326 327 328 329 330 331 332 333
static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
{
	u64 a = *(u64 *)&l;
	u64 b = *(u64 *)&r;

	if (a < b)
		return -1;
	if (a > b)
		return 1;
	return 0;
}

334 335
static int __insert_pg_mapping(struct ceph_pg_mapping *new,
			       struct rb_root *root)
S
Sage Weil 已提交
336 337 338 339
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_pg_mapping *pg = NULL;
340
	int c;
S
Sage Weil 已提交
341 342 343 344

	while (*p) {
		parent = *p;
		pg = rb_entry(parent, struct ceph_pg_mapping, node);
345 346
		c = pgid_cmp(new->pgid, pg->pgid);
		if (c < 0)
S
Sage Weil 已提交
347
			p = &(*p)->rb_left;
348
		else if (c > 0)
S
Sage Weil 已提交
349 350
			p = &(*p)->rb_right;
		else
351
			return -EEXIST;
S
Sage Weil 已提交
352 353 354 355
	}

	rb_link_node(&new->node, parent, p);
	rb_insert_color(&new->node, root);
356
	return 0;
S
Sage Weil 已提交
357 358
}

359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
						   struct ceph_pg pgid)
{
	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);
		if (c < 0)
			n = n->rb_left;
		else if (c > 0)
			n = n->rb_right;
		else
			return pg;
	}
	return NULL;
}

379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420
/*
 * 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;
}

static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
{
	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;
}

Y
Yehuda Sadeh 已提交
421 422 423 424 425 426 427 428 429 430 431 432
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;
}
433
EXPORT_SYMBOL(ceph_pg_poolid_by_name);
Y
Yehuda Sadeh 已提交
434

435 436 437 438 439 440 441
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);
}

S
Sage Weil 已提交
442
static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
443
{
S
Sage Weil 已提交
444 445
	unsigned n, m;

446 447
	ceph_decode_copy(p, &pi->v, sizeof(pi->v));
	calc_pg_masks(pi);
S
Sage Weil 已提交
448 449 450 451 452 453 454 455 456 457 458 459 460

	/* num_snaps * snap_info_t */
	n = le32_to_cpu(pi->v.num_snaps);
	while (n--) {
		ceph_decode_need(p, end, sizeof(u64) + 1 + sizeof(u64) +
				 sizeof(struct ceph_timespec), bad);
		*p += sizeof(u64) +       /* key */
			1 + sizeof(u64) + /* u8, snapid */
			sizeof(struct ceph_timespec);
		m = ceph_decode_32(p);    /* snap name */
		*p += m;
	}

461
	*p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
S
Sage Weil 已提交
462 463 464 465
	return 0;

bad:
	return -EINVAL;
466 467
}

468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559
static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
{
	struct ceph_pg_pool_info *pi;
	u32 num, len, pool;

	ceph_decode_32_safe(p, end, num, bad);
	dout(" %d pool names\n", num);
	while (num--) {
		ceph_decode_32_safe(p, end, pool, bad);
		ceph_decode_32_safe(p, end, len, bad);
		dout("  pool %d len %d\n", pool, len);
		pi = __lookup_pg_pool(&map->pg_pools, pool);
		if (pi) {
			kfree(pi->name);
			pi->name = kmalloc(len + 1, GFP_NOFS);
			if (pi->name) {
				memcpy(pi->name, *p, len);
				pi->name[len] = '\0';
				dout("  name is %s\n", pi->name);
			}
		}
		*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);
	}
	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);
}

/*
 * adjust max osd value.  reallocate arrays.
 */
static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
{
	u8 *state;
	struct ceph_entity_addr *addr;
	u32 *weight;

	state = kcalloc(max, sizeof(*state), GFP_NOFS);
	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
	if (state == NULL || addr == NULL || weight == NULL) {
		kfree(state);
		kfree(addr);
		kfree(weight);
		return -ENOMEM;
	}

	/* copy old? */
	if (map->osd_state) {
		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
		kfree(map->osd_state);
		kfree(map->osd_addr);
		kfree(map->osd_weight);
	}

	map->osd_state = state;
	map->osd_weight = weight;
	map->osd_addr = addr;
	map->max_osd = max;
	return 0;
}

S
Sage Weil 已提交
560 561 562 563 564 565 566 567
/*
 * decode a full map.
 */
struct ceph_osdmap *osdmap_decode(void **p, void *end)
{
	struct ceph_osdmap *map;
	u16 version;
	u32 len, max, i;
568
	u8 ev;
S
Sage Weil 已提交
569 570
	int err = -EINVAL;
	void *start = *p;
571
	struct ceph_pg_pool_info *pi;
S
Sage Weil 已提交
572 573 574 575 576 577 578 579 580

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

	map = kzalloc(sizeof(*map), GFP_NOFS);
	if (map == NULL)
		return ERR_PTR(-ENOMEM);
	map->pg_temp = RB_ROOT;

	ceph_decode_16_safe(p, end, version, bad);
S
Sage Weil 已提交
581 582 583 584 585
	if (version > CEPH_OSDMAP_VERSION) {
		pr_warning("got unknown v %d > %d of osdmap\n", version,
			   CEPH_OSDMAP_VERSION);
		goto bad;
	}
S
Sage Weil 已提交
586 587 588

	ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad);
	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
589
	map->epoch = ceph_decode_32(p);
S
Sage Weil 已提交
590 591 592 593 594
	ceph_decode_copy(p, &map->created, sizeof(map->created));
	ceph_decode_copy(p, &map->modified, sizeof(map->modified));

	ceph_decode_32_safe(p, end, max, bad);
	while (max--) {
595
		ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
596
		pi = kzalloc(sizeof(*pi), GFP_NOFS);
597
		if (!pi)
S
Sage Weil 已提交
598
			goto bad;
599
		pi->id = ceph_decode_32(p);
600
		ev = ceph_decode_8(p); /* encoding version */
S
Sage Weil 已提交
601 602 603
		if (ev > CEPH_PG_POOL_VERSION) {
			pr_warning("got unknown v %d > %d of ceph_pg_pool\n",
				   ev, CEPH_PG_POOL_VERSION);
D
Dan Carpenter 已提交
604
			kfree(pi);
S
Sage Weil 已提交
605 606
			goto bad;
		}
S
Sage Weil 已提交
607
		err = __decode_pool(p, end, pi);
608 609
		if (err < 0) {
			kfree(pi);
S
Sage Weil 已提交
610
			goto bad;
611
		}
612
		__insert_pg_pool(&map->pg_pools, pi);
S
Sage Weil 已提交
613
	}
614 615 616 617

	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
		goto bad;

618
	ceph_decode_32_safe(p, end, map->pool_max, bad);
S
Sage Weil 已提交
619 620 621

	ceph_decode_32_safe(p, end, map->flags, bad);

622
	max = ceph_decode_32(p);
S
Sage Weil 已提交
623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639

	/* (re)alloc osd arrays */
	err = osdmap_set_max_osd(map, max);
	if (err < 0)
		goto bad;
	dout("osdmap_decode max_osd = %d\n", map->max_osd);

	/* osds */
	err = -EINVAL;
	ceph_decode_need(p, end, 3*sizeof(u32) +
			 map->max_osd*(1 + sizeof(*map->osd_weight) +
				       sizeof(*map->osd_addr)), bad);
	*p += 4; /* skip length field (should match max) */
	ceph_decode_copy(p, map->osd_state, map->max_osd);

	*p += 4; /* skip length field (should match max) */
	for (i = 0; i < map->max_osd; i++)
640
		map->osd_weight[i] = ceph_decode_32(p);
S
Sage Weil 已提交
641 642 643

	*p += 4; /* skip length field (should match max) */
	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
644 645
	for (i = 0; i < map->max_osd; i++)
		ceph_decode_addr(&map->osd_addr[i]);
S
Sage Weil 已提交
646 647 648 649 650

	/* pg_temp */
	ceph_decode_32_safe(p, end, len, bad);
	for (i = 0; i < len; i++) {
		int n, j;
651
		struct ceph_pg pgid;
S
Sage Weil 已提交
652 653 654
		struct ceph_pg_mapping *pg;

		ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad);
655
		ceph_decode_copy(p, &pgid, sizeof(pgid));
656
		n = ceph_decode_32(p);
S
Sage Weil 已提交
657
		ceph_decode_need(p, end, n * sizeof(u32), bad);
658
		err = -ENOMEM;
S
Sage Weil 已提交
659
		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
660
		if (!pg)
S
Sage Weil 已提交
661 662 663 664
			goto bad;
		pg->pgid = pgid;
		pg->len = n;
		for (j = 0; j < n; j++)
665
			pg->osds[j] = ceph_decode_32(p);
S
Sage Weil 已提交
666

667 668 669
		err = __insert_pg_mapping(pg, &map->pg_temp);
		if (err)
			goto bad;
670
		dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len);
S
Sage Weil 已提交
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
	}

	/* crush */
	ceph_decode_32_safe(p, end, len, bad);
	dout("osdmap_decode crush len %d from off 0x%x\n", len,
	     (int)(*p - start));
	ceph_decode_need(p, end, len, bad);
	map->crush = crush_decode(*p, end);
	*p += len;
	if (IS_ERR(map->crush)) {
		err = PTR_ERR(map->crush);
		map->crush = NULL;
		goto bad;
	}

	/* ignore the rest of the map */
	*p = end;

	dout("osdmap_decode done %p %p\n", *p, end);
	return map;

bad:
	dout("osdmap_decode fail\n");
	ceph_osdmap_destroy(map);
	return ERR_PTR(err);
}

/*
 * 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;
	u32 len, pool;
710
	__s32 new_pool_max, new_flags, max;
S
Sage Weil 已提交
711 712 713 714 715 716
	void *start = *p;
	int err = -EINVAL;
	u16 version;
	struct rb_node *rbp;

	ceph_decode_16_safe(p, end, version, bad);
S
Sage Weil 已提交
717 718 719 720 721
	if (version > CEPH_OSDMAP_INC_VERSION) {
		pr_warning("got unknown v %d > %d of inc osdmap\n", version,
			   CEPH_OSDMAP_INC_VERSION);
		goto bad;
	}
S
Sage Weil 已提交
722 723 724 725

	ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32),
			 bad);
	ceph_decode_copy(p, &fsid, sizeof(fsid));
726
	epoch = ceph_decode_32(p);
S
Sage Weil 已提交
727 728
	BUG_ON(epoch != map->epoch+1);
	ceph_decode_copy(p, &modified, sizeof(modified));
729
	new_pool_max = ceph_decode_32(p);
730
	new_flags = ceph_decode_32(p);
S
Sage Weil 已提交
731 732 733 734 735 736

	/* full map? */
	ceph_decode_32_safe(p, end, len, bad);
	if (len > 0) {
		dout("apply_incremental full map len %d, %p to %p\n",
		     len, *p, end);
737
		return osdmap_decode(p, min(*p+len, end));
S
Sage Weil 已提交
738 739 740 741 742 743 744 745 746
	}

	/* new crush? */
	ceph_decode_32_safe(p, end, len, bad);
	if (len > 0) {
		dout("apply_incremental new crush map len %d, %p to %p\n",
		     len, *p, end);
		newcrush = crush_decode(*p, min(*p+len, end));
		if (IS_ERR(newcrush))
J
Julia Lawall 已提交
747
			return ERR_CAST(newcrush);
S
Sage Weil 已提交
748
		*p += len;
S
Sage Weil 已提交
749 750 751 752 753
	}

	/* new flags? */
	if (new_flags >= 0)
		map->flags = new_flags;
754 755
	if (new_pool_max >= 0)
		map->pool_max = new_pool_max;
S
Sage Weil 已提交
756 757 758 759

	ceph_decode_need(p, end, 5*sizeof(u32), bad);

	/* new max? */
760
	max = ceph_decode_32(p);
S
Sage Weil 已提交
761 762 763 764 765 766 767
	if (max >= 0) {
		err = osdmap_set_max_osd(map, max);
		if (err < 0)
			goto bad;
	}

	map->epoch++;
768
	map->modified = modified;
S
Sage Weil 已提交
769 770 771 772 773 774 775 776 777 778
	if (newcrush) {
		if (map->crush)
			crush_destroy(map->crush);
		map->crush = newcrush;
		newcrush = NULL;
	}

	/* new_pool */
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
779
		__u8 ev;
780
		struct ceph_pg_pool_info *pi;
781

S
Sage Weil 已提交
782
		ceph_decode_32_safe(p, end, pool, bad);
783
		ceph_decode_need(p, end, 1 + sizeof(pi->v), bad);
784
		ev = ceph_decode_8(p);  /* encoding version */
S
Sage Weil 已提交
785 786 787 788 789
		if (ev > CEPH_PG_POOL_VERSION) {
			pr_warning("got unknown v %d > %d of ceph_pg_pool\n",
				   ev, CEPH_PG_POOL_VERSION);
			goto bad;
		}
790 791
		pi = __lookup_pg_pool(&map->pg_pools, pool);
		if (!pi) {
792
			pi = kzalloc(sizeof(*pi), GFP_NOFS);
793 794 795 796 797 798 799
			if (!pi) {
				err = -ENOMEM;
				goto bad;
			}
			pi->id = pool;
			__insert_pg_pool(&map->pg_pools, pi);
		}
S
Sage Weil 已提交
800 801 802
		err = __decode_pool(p, end, pi);
		if (err < 0)
			goto bad;
S
Sage Weil 已提交
803
	}
804 805
	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
		goto bad;
S
Sage Weil 已提交
806

807
	/* old_pool */
S
Sage Weil 已提交
808
	ceph_decode_32_safe(p, end, len, bad);
809 810 811 812 813
	while (len--) {
		struct ceph_pg_pool_info *pi;

		ceph_decode_32_safe(p, end, pool, bad);
		pi = __lookup_pg_pool(&map->pg_pools, pool);
814 815
		if (pi)
			__remove_pg_pool(&map->pg_pools, pi);
816
	}
S
Sage Weil 已提交
817 818 819 820 821 822 823 824 825

	/* new_up */
	err = -EINVAL;
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		u32 osd;
		struct ceph_entity_addr addr;
		ceph_decode_32_safe(p, end, osd, bad);
		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad);
826
		ceph_decode_addr(&addr);
S
Sage Weil 已提交
827 828 829 830 831 832
		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;
	}

833
	/* new_state */
S
Sage Weil 已提交
834 835 836
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		u32 osd;
837
		u8 xorstate;
S
Sage Weil 已提交
838
		ceph_decode_32_safe(p, end, osd, bad);
839
		xorstate = **(u8 **)p;
S
Sage Weil 已提交
840
		(*p)++;  /* clean flag */
841 842 843 844
		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
845
		if (osd < map->max_osd)
846
			map->osd_state[osd] ^= xorstate;
S
Sage Weil 已提交
847 848 849 850 851 852 853
	}

	/* new_weight */
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		u32 osd, off;
		ceph_decode_need(p, end, sizeof(u32)*2, bad);
854 855
		osd = ceph_decode_32(p);
		off = ceph_decode_32(p);
S
Sage Weil 已提交
856 857 858 859 860 861 862 863 864 865 866 867 868
		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 */
	rbp = rb_first(&map->pg_temp);
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		struct ceph_pg_mapping *pg;
		int j;
869
		struct ceph_pg pgid;
S
Sage Weil 已提交
870 871
		u32 pglen;
		ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
872
		ceph_decode_copy(p, &pgid, sizeof(pgid));
873
		pglen = ceph_decode_32(p);
S
Sage Weil 已提交
874 875

		/* remove any? */
876 877
		while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping,
						node)->pgid, pgid) <= 0) {
878 879
			struct ceph_pg_mapping *cur =
				rb_entry(rbp, struct ceph_pg_mapping, node);
S
Sage Weil 已提交
880

S
Sage Weil 已提交
881
			rbp = rb_next(rbp);
882 883 884
			dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
			rb_erase(&cur->node, &map->pg_temp);
			kfree(cur);
S
Sage Weil 已提交
885 886 887 888 889 890 891 892 893 894 895 896
		}

		if (pglen) {
			/* insert */
			ceph_decode_need(p, end, pglen*sizeof(u32), bad);
			pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
			if (!pg) {
				err = -ENOMEM;
				goto bad;
			}
			pg->pgid = pgid;
			pg->len = pglen;
897
			for (j = 0; j < pglen; j++)
898
				pg->osds[j] = ceph_decode_32(p);
899
			err = __insert_pg_mapping(pg, &map->pg_temp);
900 901
			if (err) {
				kfree(pg);
902
				goto bad;
903
			}
904 905
			dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid,
			     pglen);
S
Sage Weil 已提交
906 907 908
		}
	}
	while (rbp) {
909 910 911
		struct ceph_pg_mapping *cur =
			rb_entry(rbp, struct ceph_pg_mapping, node);

S
Sage Weil 已提交
912
		rbp = rb_next(rbp);
913 914 915
		dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
		rb_erase(&cur->node, &map->pg_temp);
		kfree(cur);
S
Sage Weil 已提交
916 917 918 919 920 921 922 923 924
	}

	/* ignore the rest */
	*p = end;
	return map;

bad:
	pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n",
	       epoch, (int)(*p - start), *p, start, end);
925 926 927
	print_hex_dump(KERN_DEBUG, "osdmap: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       start, end - start, true);
S
Sage Weil 已提交
928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945
	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.
 */
void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
				   u64 off, u64 *plen,
946
				   u64 *ono,
S
Sage Weil 已提交
947 948 949 950 951 952 953
				   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;
954
	u64 t, su_offset;
S
Sage Weil 已提交
955 956 957

	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, *plen,
	     osize, su);
958
	su_per_object = osize / su;
S
Sage Weil 已提交
959 960 961 962 963 964 965 966 967 968 969 970 971 972
	dout("osize %u / su %u = su_per_object %u\n", osize, su,
	     su_per_object);

	BUG_ON((su & ~PAGE_MASK) != 0);
	/* 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;

973 974 975 976
	*ono = objsetno * sc + stripepos;
	dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned)*ono);

	/* *oxoff = *off % layout->fl_stripe_unit;  # offset in su */
S
Sage Weil 已提交
977
	t = off;
978 979 980 981 982 983 984 985 986
	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
	 * object. This is the minimum of the full length requested (plen) or
	 * the remainder of the current stripe being written to.
	 */
	*oxlen = min_t(u64, *plen, su - su_offset);
S
Sage Weil 已提交
987 988 989 990
	*plen = *oxlen;

	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
}
991
EXPORT_SYMBOL(ceph_calc_file_object_mapping);
S
Sage Weil 已提交
992 993 994 995 996 997 998 999 1000 1001 1002

/*
 * calculate an object layout (i.e. pgid) from an oid,
 * file_layout, and osdmap
 */
int ceph_calc_object_layout(struct ceph_object_layout *ol,
			    const char *oid,
			    struct ceph_file_layout *fl,
			    struct ceph_osdmap *osdmap)
{
	unsigned num, num_mask;
1003
	struct ceph_pg pgid;
S
Sage Weil 已提交
1004 1005 1006
	s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred);
	int poolid = le32_to_cpu(fl->fl_pg_pool);
	struct ceph_pg_pool_info *pool;
1007
	unsigned ps;
S
Sage Weil 已提交
1008

1009
	BUG_ON(!osdmap);
S
Sage Weil 已提交
1010

1011 1012 1013
	pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
	if (!pool)
		return -EIO;
1014
	ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid));
S
Sage Weil 已提交
1015
	if (preferred >= 0) {
1016
		ps += preferred;
S
Sage Weil 已提交
1017 1018 1019 1020 1021 1022 1023
		num = le32_to_cpu(pool->v.lpg_num);
		num_mask = pool->lpg_num_mask;
	} else {
		num = le32_to_cpu(pool->v.pg_num);
		num_mask = pool->pg_num_mask;
	}

1024 1025 1026
	pgid.ps = cpu_to_le16(ps);
	pgid.preferred = cpu_to_le16(preferred);
	pgid.pool = fl->fl_pg_pool;
S
Sage Weil 已提交
1027
	if (preferred >= 0)
1028 1029
		dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps,
		     (int)preferred);
S
Sage Weil 已提交
1030
	else
1031
		dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps);
S
Sage Weil 已提交
1032

1033
	ol->ol_pgid = pgid;
S
Sage Weil 已提交
1034 1035 1036
	ol->ol_stripe_unit = fl->fl_object_stripe_unit;
	return 0;
}
1037
EXPORT_SYMBOL(ceph_calc_object_layout);
S
Sage Weil 已提交
1038 1039 1040 1041 1042

/*
 * Calculate raw osd vector for the given pgid.  Return pointer to osd
 * array, or NULL on failure.
 */
1043
static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
S
Sage Weil 已提交
1044 1045 1046 1047 1048
			int *osds, int *num)
{
	struct ceph_pg_mapping *pg;
	struct ceph_pg_pool_info *pool;
	int ruleno;
1049 1050
	unsigned poolid, ps, pps;
	int preferred;
S
Sage Weil 已提交
1051 1052

	/* pg_temp? */
1053 1054 1055 1056
	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
	if (pg) {
		*num = pg->len;
		return pg->osds;
S
Sage Weil 已提交
1057 1058 1059
	}

	/* crush */
1060 1061 1062 1063
	poolid = le32_to_cpu(pgid.pool);
	ps = le16_to_cpu(pgid.ps);
	preferred = (s16)le16_to_cpu(pgid.preferred);

1064 1065 1066 1067 1068
	/* don't forcefeed bad device ids to crush */
	if (preferred >= osdmap->max_osd ||
	    preferred >= osdmap->crush->max_devices)
		preferred = -1;

1069 1070
	pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
	if (!pool)
S
Sage Weil 已提交
1071 1072 1073 1074
		return NULL;
	ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset,
				 pool->v.type, pool->v.size);
	if (ruleno < 0) {
1075 1076 1077
		pr_err("no crush rule pool %d ruleset %d type %d size %d\n",
		       poolid, pool->v.crush_ruleset, pool->v.type,
		       pool->v.size);
S
Sage Weil 已提交
1078 1079 1080
		return NULL;
	}

1081 1082
	if (preferred >= 0)
		pps = ceph_stable_mod(ps,
S
Sage Weil 已提交
1083 1084 1085
				      le32_to_cpu(pool->v.lpgp_num),
				      pool->lpgp_num_mask);
	else
1086
		pps = ceph_stable_mod(ps,
S
Sage Weil 已提交
1087 1088
				      le32_to_cpu(pool->v.pgp_num),
				      pool->pgp_num_mask);
1089
	pps += poolid;
S
Sage Weil 已提交
1090 1091
	*num = crush_do_rule(osdmap->crush, ruleno, pps, osds,
			     min_t(int, pool->v.size, *num),
1092
			     preferred, osdmap->osd_weight);
S
Sage Weil 已提交
1093 1094 1095
	return osds;
}

1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116
/*
 * Return acting set for given pgid.
 */
int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
			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
1117 1118 1119
/*
 * Return primary osd for given pgid, or -1 if none.
 */
1120
int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
S
Sage Weil 已提交
1121
{
1122 1123
	int rawosds[CEPH_PG_MAX_SIZE], *osds;
	int i, num = CEPH_PG_MAX_SIZE;
S
Sage Weil 已提交
1124 1125 1126 1127 1128 1129 1130

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

	/* primary is first up osd */
	for (i = 0; i < num; i++)
1131
		if (ceph_osd_is_up(osdmap, osds[i]))
S
Sage Weil 已提交
1132 1133 1134
			return osds[i];
	return -1;
}
1135
EXPORT_SYMBOL(ceph_calc_pg_primary);