osdmap.c 22.1 KB
Newer Older
S
Sage Weil 已提交
1 2 3 4 5 6 7 8 9 10 11 12 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

#include <asm/div64.h>

#include "super.h"
#include "osdmap.h"
#include "crush/hash.h"
#include "crush/mapper.h"
#include "decode.h"
#include "ceph_debug.h"

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);
70
	b->item_weight = ceph_decode_32(p);
S
Sage Weil 已提交
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
	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++) {
89 90
		b->item_weights[j] = ceph_decode_32(p);
		b->sum_weights[j] = ceph_decode_32(p);
S
Sage Weil 已提交
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107
	}
	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++)
108
		b->node_weights[j] = ceph_decode_32(p);
S
Sage Weil 已提交
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
	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++) {
127 128
		b->item_weights[j] = ceph_decode_32(p);
		b->straws[j] = ceph_decode_32(p);
S
Sage Weil 已提交
129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
	}
	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);
151
	magic = ceph_decode_32(p);
S
Sage Weil 已提交
152 153 154 155 156
	if (magic != CRUSH_MAGIC) {
		pr_err("crush_decode magic %x != current %x\n",
		       (unsigned)magic, (unsigned)CRUSH_MAGIC);
		goto bad;
	}
157 158 159
	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
160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202

	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:
203
			err = -EINVAL;
S
Sage Weil 已提交
204 205 206 207 208 209 210 211
			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);
212 213
		b->id = ceph_decode_32(p);
		b->type = ceph_decode_16(p);
214 215
		b->alg = ceph_decode_8(p);
		b->hash = ceph_decode_8(p);
216 217
		b->weight = ceph_decode_32(p);
		b->size = ceph_decode_32(p);
S
Sage Weil 已提交
218 219 220 221 222 223 224 225 226 227 228 229 230 231

		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++)
232
			b->items[j] = ceph_decode_32(p);
S
Sage Weil 已提交
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281

		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
282
		err = -EINVAL;
S
Sage Weil 已提交
283 284 285 286 287 288 289 290 291 292 293 294 295
		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++) {
296 297 298
			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
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
		}
	}

	/* 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);
}


/*
 * 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))
		rb_erase(rb_first(&map->pg_temp), &map->pg_temp);
	kfree(map->osd_state);
	kfree(map->osd_weight);
	kfree(map->pg_pool);
	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;
}

/*
 * Insert a new pg_temp mapping
 */
372 373 374 375 376 377 378 379 380 381 382 383
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;
}

384 385
static int __insert_pg_mapping(struct ceph_pg_mapping *new,
			       struct rb_root *root)
S
Sage Weil 已提交
386 387 388 389
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_pg_mapping *pg = NULL;
390
	int c;
S
Sage Weil 已提交
391 392 393 394

	while (*p) {
		parent = *p;
		pg = rb_entry(parent, struct ceph_pg_mapping, node);
395 396
		c = pgid_cmp(new->pgid, pg->pgid);
		if (c < 0)
S
Sage Weil 已提交
397
			p = &(*p)->rb_left;
398
		else if (c > 0)
S
Sage Weil 已提交
399 400
			p = &(*p)->rb_right;
		else
401
			return -EEXIST;
S
Sage Weil 已提交
402 403 404 405
	}

	rb_link_node(&new->node, parent, p);
	rb_insert_color(&new->node, root);
406
	return 0;
S
Sage Weil 已提交
407 408 409 410 411 412 413 414 415 416
}

/*
 * decode a full map.
 */
struct ceph_osdmap *osdmap_decode(void **p, void *end)
{
	struct ceph_osdmap *map;
	u16 version;
	u32 len, max, i;
417
	u8 ev;
S
Sage Weil 已提交
418 419 420 421 422 423 424 425 426 427 428 429 430 431
	int err = -EINVAL;
	void *start = *p;

	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);

	ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad);
	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
432
	map->epoch = ceph_decode_32(p);
S
Sage Weil 已提交
433 434 435
	ceph_decode_copy(p, &map->created, sizeof(map->created));
	ceph_decode_copy(p, &map->modified, sizeof(map->modified));

436
	map->num_pools = ceph_decode_32(p);
S
Sage Weil 已提交
437 438 439 440 441 442 443 444
	map->pg_pool = kcalloc(map->num_pools, sizeof(*map->pg_pool),
			       GFP_NOFS);
	if (!map->pg_pool) {
		err = -ENOMEM;
		goto bad;
	}
	ceph_decode_32_safe(p, end, max, bad);
	while (max--) {
445
		ceph_decode_need(p, end, 4+1+sizeof(map->pg_pool->v), bad);
446
		i = ceph_decode_32(p);
S
Sage Weil 已提交
447 448
		if (i >= map->num_pools)
			goto bad;
449
		ev = ceph_decode_8(p); /* encoding version */
S
Sage Weil 已提交
450 451 452 453 454 455 456 457 458 459
		ceph_decode_copy(p, &map->pg_pool[i].v,
				 sizeof(map->pg_pool->v));
		calc_pg_masks(&map->pg_pool[i]);
		p += le32_to_cpu(map->pg_pool[i].v.num_snaps) * sizeof(u64);
		p += le32_to_cpu(map->pg_pool[i].v.num_removed_snap_intervals)
			* sizeof(u64) * 2;
	}

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

460
	max = ceph_decode_32(p);
S
Sage Weil 已提交
461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477

	/* (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++)
478
		map->osd_weight[i] = ceph_decode_32(p);
S
Sage Weil 已提交
479 480 481

	*p += 4; /* skip length field (should match max) */
	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
482 483
	for (i = 0; i < map->max_osd; i++)
		ceph_decode_addr(&map->osd_addr[i]);
S
Sage Weil 已提交
484 485 486 487 488

	/* pg_temp */
	ceph_decode_32_safe(p, end, len, bad);
	for (i = 0; i < len; i++) {
		int n, j;
489
		struct ceph_pg pgid;
S
Sage Weil 已提交
490 491 492
		struct ceph_pg_mapping *pg;

		ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad);
493
		ceph_decode_copy(p, &pgid, sizeof(pgid));
494
		n = ceph_decode_32(p);
S
Sage Weil 已提交
495
		ceph_decode_need(p, end, n * sizeof(u32), bad);
496
		err = -ENOMEM;
S
Sage Weil 已提交
497
		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
498
		if (!pg)
S
Sage Weil 已提交
499 500 501 502
			goto bad;
		pg->pgid = pgid;
		pg->len = n;
		for (j = 0; j < n; j++)
503
			pg->osds[j] = ceph_decode_32(p);
S
Sage Weil 已提交
504

505 506 507
		err = __insert_pg_mapping(pg, &map->pg_temp);
		if (err)
			goto bad;
508
		dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len);
S
Sage Weil 已提交
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
	}

	/* 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;
	__s32 new_flags, max;
	void *start = *p;
	int err = -EINVAL;
	u16 version;
	struct rb_node *rbp;

	ceph_decode_16_safe(p, end, version, bad);

	ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32),
			 bad);
	ceph_decode_copy(p, &fsid, sizeof(fsid));
559
	epoch = ceph_decode_32(p);
S
Sage Weil 已提交
560 561
	BUG_ON(epoch != map->epoch+1);
	ceph_decode_copy(p, &modified, sizeof(modified));
562
	new_flags = ceph_decode_32(p);
S
Sage Weil 已提交
563 564 565 566 567 568

	/* 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);
569
		return osdmap_decode(p, min(*p+len, end));
S
Sage Weil 已提交
570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588
	}

	/* 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))
			return ERR_PTR(PTR_ERR(newcrush));
	}

	/* new flags? */
	if (new_flags >= 0)
		map->flags = new_flags;

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

	/* new max? */
589
	max = ceph_decode_32(p);
S
Sage Weil 已提交
590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607
	if (max >= 0) {
		err = osdmap_set_max_osd(map, max);
		if (err < 0)
			goto bad;
	}

	map->epoch++;
	map->modified = map->modified;
	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--) {
608 609
		__u8 ev;

S
Sage Weil 已提交
610 611 612 613 614 615 616 617 618 619 620 621 622 623 624
		ceph_decode_32_safe(p, end, pool, bad);
		if (pool >= map->num_pools) {
			void *pg_pool = kcalloc(pool + 1,
						sizeof(*map->pg_pool),
						GFP_NOFS);
			if (!pg_pool) {
				err = -ENOMEM;
				goto bad;
			}
			memcpy(pg_pool, map->pg_pool,
			       map->num_pools * sizeof(*map->pg_pool));
			kfree(map->pg_pool);
			map->pg_pool = pg_pool;
			map->num_pools = pool+1;
		}
625 626
		ceph_decode_need(p, end, 1 + sizeof(map->pg_pool->v), bad);
		ev = ceph_decode_8(p);  /* encoding version */
S
Sage Weil 已提交
627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643
		ceph_decode_copy(p, &map->pg_pool[pool].v,
				 sizeof(map->pg_pool->v));
		calc_pg_masks(&map->pg_pool[pool]);
	}

	/* old_pool (ignore) */
	ceph_decode_32_safe(p, end, len, bad);
	*p += len * sizeof(u32);

	/* 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);
644
		ceph_decode_addr(&addr);
S
Sage Weil 已提交
645 646 647 648 649 650 651 652 653 654 655 656
		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;
	}

	/* new_down */
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		u32 osd;
		ceph_decode_32_safe(p, end, osd, bad);
		(*p)++;  /* clean flag */
657
		pr_info("osd%d down\n", osd);
S
Sage Weil 已提交
658 659 660 661 662 663 664 665 666
		if (osd < map->max_osd)
			map->osd_state[osd] &= ~CEPH_OSD_UP;
	}

	/* new_weight */
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		u32 osd, off;
		ceph_decode_need(p, end, sizeof(u32)*2, bad);
667 668
		osd = ceph_decode_32(p);
		off = ceph_decode_32(p);
S
Sage Weil 已提交
669 670 671 672 673 674 675 676 677 678 679 680 681
		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;
682
		struct ceph_pg pgid;
S
Sage Weil 已提交
683 684
		u32 pglen;
		ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
685
		ceph_decode_copy(p, &pgid, sizeof(pgid));
686
		pglen = ceph_decode_32(p);
S
Sage Weil 已提交
687 688

		/* remove any? */
689 690
		while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping,
						node)->pgid, pgid) <= 0) {
S
Sage Weil 已提交
691 692 693
			struct rb_node *cur = rbp;
			rbp = rb_next(rbp);
			dout(" removed pg_temp %llx\n",
694 695
			     *(u64 *)&rb_entry(cur, struct ceph_pg_mapping,
					       node)->pgid);
S
Sage Weil 已提交
696 697 698 699 700 701 702 703 704 705 706 707 708
			rb_erase(cur, &map->pg_temp);
		}

		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;
709
			for (j = 0; j < pglen; j++)
710
				pg->osds[j] = ceph_decode_32(p);
711 712 713
			err = __insert_pg_mapping(pg, &map->pg_temp);
			if (err)
				goto bad;
714 715
			dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid,
			     pglen);
S
Sage Weil 已提交
716 717 718 719 720 721
		}
	}
	while (rbp) {
		struct rb_node *cur = rbp;
		rbp = rb_next(rbp);
		dout(" removed pg_temp %llx\n",
722 723
		     *(u64 *)&rb_entry(cur, struct ceph_pg_mapping,
				       node)->pgid);
S
Sage Weil 已提交
724 725 726 727 728 729 730 731 732 733
		rb_erase(cur, &map->pg_temp);
	}

	/* 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);
734 735 736
	print_hex_dump(KERN_DEBUG, "osdmap: ",
		       DUMP_PREFIX_OFFSET, 16, 1,
		       start, end - start, true);
S
Sage Weil 已提交
737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
	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,
755
				   u64 *ono,
S
Sage Weil 已提交
756 757 758 759 760 761 762
				   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;
763
	u64 t, su_offset;
S
Sage Weil 已提交
764 765 766

	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, *plen,
	     osize, su);
767
	su_per_object = osize / su;
S
Sage Weil 已提交
768 769 770 771 772 773 774 775 776 777 778 779 780 781
	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;

782 783 784 785
	*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
786
	t = off;
787 788 789 790 791 792 793 794 795
	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
796 797 798 799 800 801 802 803 804 805 806 807 808 809 810
	*plen = *oxlen;

	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
}

/*
 * 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;
811
	struct ceph_pg pgid;
S
Sage Weil 已提交
812 813 814
	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;
815
	unsigned ps;
S
Sage Weil 已提交
816

817
	BUG_ON(!osdmap);
S
Sage Weil 已提交
818 819 820
	if (poolid >= osdmap->num_pools)
		return -EIO;

821
	pool = &osdmap->pg_pool[poolid];
822
	ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid));
S
Sage Weil 已提交
823
	if (preferred >= 0) {
824
		ps += preferred;
S
Sage Weil 已提交
825 826 827 828 829 830 831
		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;
	}

832 833 834
	pgid.ps = cpu_to_le16(ps);
	pgid.preferred = cpu_to_le16(preferred);
	pgid.pool = fl->fl_pg_pool;
S
Sage Weil 已提交
835
	if (preferred >= 0)
836 837
		dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps,
		     (int)preferred);
S
Sage Weil 已提交
838
	else
839
		dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps);
S
Sage Weil 已提交
840

841
	ol->ol_pgid = pgid;
S
Sage Weil 已提交
842 843 844 845 846 847 848 849
	ol->ol_stripe_unit = fl->fl_object_stripe_unit;
	return 0;
}

/*
 * Calculate raw osd vector for the given pgid.  Return pointer to osd
 * array, or NULL on failure.
 */
850
static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
S
Sage Weil 已提交
851 852 853 854 855 856
			int *osds, int *num)
{
	struct rb_node *n = osdmap->pg_temp.rb_node;
	struct ceph_pg_mapping *pg;
	struct ceph_pg_pool_info *pool;
	int ruleno;
857 858 859
	unsigned poolid, ps, pps;
	int preferred;
	int c;
S
Sage Weil 已提交
860 861 862 863

	/* pg_temp? */
	while (n) {
		pg = rb_entry(n, struct ceph_pg_mapping, node);
864 865
		c = pgid_cmp(pgid, pg->pgid);
		if (c < 0)
S
Sage Weil 已提交
866
			n = n->rb_left;
867
		else if (c > 0)
S
Sage Weil 已提交
868 869 870 871 872 873 874 875
			n = n->rb_right;
		else {
			*num = pg->len;
			return pg->osds;
		}
	}

	/* crush */
876 877 878 879
	poolid = le32_to_cpu(pgid.pool);
	ps = le16_to_cpu(pgid.ps);
	preferred = (s16)le16_to_cpu(pgid.preferred);

880 881 882 883 884
	/* don't forcefeed bad device ids to crush */
	if (preferred >= osdmap->max_osd ||
	    preferred >= osdmap->crush->max_devices)
		preferred = -1;

885
	if (poolid >= osdmap->num_pools)
S
Sage Weil 已提交
886
		return NULL;
887
	pool = &osdmap->pg_pool[poolid];
S
Sage Weil 已提交
888 889 890 891
	ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset,
				 pool->v.type, pool->v.size);
	if (ruleno < 0) {
		pr_err("no crush rule pool %d type %d size %d\n",
892
		       poolid, pool->v.type, pool->v.size);
S
Sage Weil 已提交
893 894 895
		return NULL;
	}

896 897
	if (preferred >= 0)
		pps = ceph_stable_mod(ps,
S
Sage Weil 已提交
898 899 900
				      le32_to_cpu(pool->v.lpgp_num),
				      pool->lpgp_num_mask);
	else
901
		pps = ceph_stable_mod(ps,
S
Sage Weil 已提交
902 903
				      le32_to_cpu(pool->v.pgp_num),
				      pool->pgp_num_mask);
904
	pps += poolid;
S
Sage Weil 已提交
905 906
	*num = crush_do_rule(osdmap->crush, ruleno, pps, osds,
			     min_t(int, pool->v.size, *num),
907
			     preferred, osdmap->osd_weight);
S
Sage Weil 已提交
908 909 910 911 912 913
	return osds;
}

/*
 * Return primary osd for given pgid, or -1 if none.
 */
914
int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
S
Sage Weil 已提交
915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930
{
	int rawosds[10], *osds;
	int i, num = ARRAY_SIZE(rawosds);

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

	/* primary is first up osd */
	for (i = 0; i < num; i++)
		if (ceph_osd_is_up(osdmap, osds[i])) {
			return osds[i];
			break;
		}
	return -1;
}