osdmap.c

#include <linux/ceph/ceph_debug.h>

#include <linux/module.h>
#include <linux/slab.h>
#include <asm/div64.h>

#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>

char *ceph_osdmap_state_str(char *str, int len, int state)
{
	if (!len)
		return str;

	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
		snprintf(str, len, "doesn't exist");

	return str;
}

/* maps */

static int calc_bits_of(unsigned int 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(pi->pg_num-1)) - 1;
	pi->pgp_num_mask = (1 << calc_bits_of(pi->pgp_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);
	b->item_weight = ceph_decode_32(p);
	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++) {
		b->item_weights[j] = ceph_decode_32(p);
		b->sum_weights[j] = ceph_decode_32(p);
	}
	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++)
		b->node_weights[j] = ceph_decode_32(p);
	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++) {
		b->item_weights[j] = ceph_decode_32(p);
		b->straws[j] = ceph_decode_32(p);
	}
	return 0;
bad:
	return -EINVAL;
}

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;
}

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;
	u32 num_name_maps;

	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);

        /* set tunables to default values */
        c->choose_local_tries = 2;
        c->choose_local_fallback_tries = 5;
        c->choose_total_tries = 19;
	c->chooseleaf_descend_once = 0;

	ceph_decode_need(p, end, 4*sizeof(u32), bad);
	magic = ceph_decode_32(p);
	if (magic != CRUSH_MAGIC) {
		pr_err("crush_decode magic %x != current %x\n",
		       (unsigned int)magic, (unsigned int)CRUSH_MAGIC);
		goto bad;
	}
	c->max_buckets = ceph_decode_32(p);
	c->max_rules = ceph_decode_32(p);
	c->max_devices = ceph_decode_32(p);

	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:
			err = -EINVAL;
			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);
		b->id = ceph_decode_32(p);
		b->type = ceph_decode_16(p);
		b->alg = ceph_decode_8(p);
		b->hash = ceph_decode_8(p);
		b->weight = ceph_decode_32(p);
		b->size = ceph_decode_32(p);

		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++)
			b->items[j] = ceph_decode_32(p);

		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
		err = -EINVAL;
		if (yes > (ULONG_MAX - sizeof(*r))
			  / 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++) {
			r->steps[j].op = ceph_decode_32(p);
			r->steps[j].arg1 = ceph_decode_32(p);
			r->steps[j].arg2 = ceph_decode_32(p);
		}
	}

	/* ignore trailing name maps. */
        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);

	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);

done:
	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);
}

/*
 * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
 * to a set of osds)
 */
static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
{
	if (l.pool < r.pool)
		return -1;
	if (l.pool > r.pool)
		return 1;
	if (l.seed < r.seed)
		return -1;
	if (l.seed > r.seed)
		return 1;
	return 0;
}

static int __insert_pg_mapping(struct ceph_pg_mapping *new,
			       struct rb_root *root)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct ceph_pg_mapping *pg = NULL;
	int c;

	dout("__insert_pg_mapping %llx %p\n", *(u64 *)&new->pgid, new);
	while (*p) {
		parent = *p;
		pg = rb_entry(parent, struct ceph_pg_mapping, node);
		c = pgid_cmp(new->pgid, pg->pgid);
		if (c < 0)
			p = &(*p)->rb_left;
		else if (c > 0)
			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_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 {
			dout("__lookup_pg_mapping %lld.%x got %p\n",
			     pgid.pool, pgid.seed, pg);
			return pg;
		}
	}
	return NULL;
}

static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid)
{
	struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid);

	if (pg) {
		dout("__remove_pg_mapping %lld.%x %p\n", pgid.pool, pgid.seed,
		     pg);
		rb_erase(&pg->node, root);
		kfree(pg);
		return 0;
	}
	dout("__remove_pg_mapping %lld.%x dne\n", pgid.pool, pgid.seed);
	return -ENOENT;
}

/*
 * 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, u64 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;
}

struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id)
{
	return __lookup_pg_pool(&map->pg_pools, id);
}

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);

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;
}
EXPORT_SYMBOL(ceph_pg_poolid_by_name);

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);
}

static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
{
	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;
	}
	if (cv > 9) {
		pr_warning("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv);
		return -EINVAL;
	}
	len = ceph_decode_32(p);
	ceph_decode_need(p, end, len, bad);
	pool_end = *p + len;

	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);

	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;
	}

	/* skip removed_snaps */
	num = ceph_decode_32(p);
	*p += num * (8 + 8);

	*p += 8;  /* skip auid */
	pi->flags = ceph_decode_64(p);
	*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;
	}

	/* ignore the rest */

	*p = pool_end;
	calc_pg_masks(pi);
	return 0;

bad:
	return -EINVAL;
}

static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
{
	struct ceph_pg_pool_info *pi;
	u32 num, len;
	u64 pool;

	ceph_decode_32_safe(p, end, num, bad);
	dout(" %d pool names\n", num);
	while (num--) {
		ceph_decode_64_safe(p, end, pool, bad);
		ceph_decode_32_safe(p, end, len, bad);
		dout("  pool %llu len %d\n", pool, len);
		ceph_decode_need(p, end, len, bad);
		pi = __lookup_pg_pool(&map->pg_pools, pool);
		if (pi) {
			char *name = kstrndup(*p, len, GFP_NOFS);

			if (!name)
				return -ENOMEM;
			kfree(pi->name);
			pi->name = name;
			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, (re)allocate arrays.
 *
 * The new elements are properly initialized.
 */
static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
{
	u8 *state;
	u32 *weight;
	struct ceph_entity_addr *addr;
	int i;

	state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS);
	weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS);
	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
	if (!state || !weight || !addr) {
		kfree(state);
		kfree(weight);
		kfree(addr);

		return -ENOMEM;
	}

	for (i = map->max_osd; i < max; i++) {
		state[i] = 0;
		weight[i] = CEPH_OSD_OUT;
		memset(addr + i, 0, sizeof(*addr));
	}

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

	map->max_osd = max;

	return 0;
}

#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;
}

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);
}

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;
			pg->len = len;
			for (i = 0; i < len; i++)
				pg->osds[i] = ceph_decode_32(p);

			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);
}

/*
 * decode a full map.
 */
static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
{
	u8 struct_v;
	u32 epoch = 0;
	void *start = *p;
	u32 max;
	u32 len, i;
	int err;

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

	err = get_osdmap_client_data_v(p, end, "full", &struct_v);
	if (err)
		goto bad;

	/* fsid, epoch, created, modified */
	ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) +
			 sizeof(map->created) + sizeof(map->modified), e_inval);
	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
	epoch = map->epoch = ceph_decode_32(p);
	ceph_decode_copy(p, &map->created, sizeof(map->created));
	ceph_decode_copy(p, &map->modified, sizeof(map->modified));

	/* pools */
	err = decode_pools(p, end, map);
	if (err)
		goto bad;

	/* pool_name */
	err = decode_pool_names(p, end, map);
	if (err)
		goto bad;

	ceph_decode_32_safe(p, end, map->pool_max, e_inval);

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

	/* max_osd */
	ceph_decode_32_safe(p, end, max, e_inval);

	/* (re)alloc osd arrays */
	err = osdmap_set_max_osd(map, max);
	if (err)
		goto bad;

	/* osd_state, osd_weight, osd_addrs->client_addr */
	ceph_decode_need(p, end, 3*sizeof(u32) +
			 map->max_osd*(1 + sizeof(*map->osd_weight) +
				       sizeof(*map->osd_addr)), e_inval);

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

	ceph_decode_copy(p, map->osd_state, map->max_osd);

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

	for (i = 0; i < map->max_osd; i++)
		map->osd_weight[i] = ceph_decode_32(p);

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

	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
	for (i = 0; i < map->max_osd; i++)
		ceph_decode_addr(&map->osd_addr[i]);

	/* pg_temp */
	err = decode_pg_temp(p, end, map);
	if (err)
		goto bad;

	/* crush */
	ceph_decode_32_safe(p, end, len, e_inval);
	map->crush = crush_decode(*p, min(*p + len, end));
	if (IS_ERR(map->crush)) {
		err = PTR_ERR(map->crush);
		map->crush = NULL;
		goto bad;
	}
	*p += len;

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

	dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
	return 0;

e_inval:
	err = -EINVAL;
bad:
	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);
	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;
	mutex_init(&map->crush_scratch_mutex);

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

	return map;
}

/*
 * 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;
	s32 len;
	u64 pool;
	__s64 new_pool_max;
	__s32 new_flags, max;
	void *start = *p;
	int err;
	u8 struct_v;

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