Release 4.11 net/ceph/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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
69
75.00%
1
50.00%
Cong Ding
23
25.00%
1
50.00%
Total
92
100.00%
2
100.00%

/* maps */



static int calc_bits_of(unsigned int t)
{
	int b = 0;
	while (t) {
		t = t >> 1;
		b++;
	}
	return b;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
32
96.97%
1
50.00%
Eric Dumazet
1
3.03%
1
50.00%
Total
33
100.00%
2
100.00%

/*
 * 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
49
100.00%
1
100.00%
Total
49
100.00%
1
100.00%

/*
 * 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
72
100.00%
2
100.00%
Total
72
100.00%
2
100.00%



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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
171
100.00%
2
100.00%
Total
171
100.00%
2
100.00%



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_8_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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
129
99.23%
2
66.67%
Ilya Dryomov
1
0.77%
1
33.33%
Total
130
100.00%
3
100.00%



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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
171
100.00%
2
100.00%
Total
171
100.00%
2
100.00%



static int crush_decode_straw2_bucket(void **p, void *end,
				      struct crush_bucket_straw2 *b)
{
	int j;
	dout("crush_decode_straw2_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;
	ceph_decode_need(p, end, b->h.size * sizeof(u32), bad);
	for (j = 0; j < b->h.size; j++)
		b->item_weights[j] = ceph_decode_32(p);
	return 0;
bad:
	return -EINVAL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
123
100.00%
1
100.00%
Total
123
100.00%
1
100.00%



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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
72
100.00%
1
100.00%
Total
72
100.00%
1
100.00%



static void crush_finalize(struct crush_map *c)
{
	__s32 b;

	/* Space for the array of pointers to per-bucket workspace */
	c->working_size = sizeof(struct crush_work) +
	    c->max_buckets * sizeof(struct crush_work_bucket *);

	for (b = 0; b < c->max_buckets; b++) {
		if (!c->buckets[b])
			continue;

		switch (c->buckets[b]->alg) {
		default:
			/*
                         * The base case, permutation variables and
                         * the pointer to the permutation array.
                         */
			c->working_size += sizeof(struct crush_work_bucket);
			break;
		}
		/* Every bucket has a permutation array. */
		c->working_size += c->buckets[b]->size * sizeof(__u32);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
109
100.00%
1
100.00%
Total
109
100.00%
1
100.00%



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;
		case CRUSH_BUCKET_STRAW2:
			size = sizeof(struct crush_bucket_straw2);
			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;

		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;
		case CRUSH_BUCKET_STRAW2:
			err = crush_decode_straw2_bucket(p, end,
				(struct crush_bucket_straw2 *)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\n",
             c->choose_local_tries);
        dout("crush decode tunable choose_local_fallback_tries = %d\n",
             c->choose_local_fallback_tries);
        dout("crush decode tunable choose_total_tries = %d\n",
             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\n",
	     c->chooseleaf_descend_once);

	ceph_decode_need(p, end, sizeof(u8), done);
	c->chooseleaf_vary_r = ceph_decode_8(p);
	dout("crush decode tunable chooseleaf_vary_r = %d\n",
	     c->chooseleaf_vary_r);

	/* skip straw_calc_version, allowed_bucket_algs */
	ceph_decode_need(p, end, sizeof(u8) + sizeof(u32), done);
	*p += sizeof(u8) + sizeof(u32);

	ceph_decode_need(p, end, sizeof(u8), done);
	c->chooseleaf_stable = ceph_decode_8(p);
	dout("crush decode tunable chooseleaf_stable = %d\n",
	     c->chooseleaf_stable);

done:
	crush_finalize(c);
	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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
1157
85.51%
5
38.46%
Ilya Dryomov
149
11.01%
5
38.46%
Jim Schutt
37
2.73%
1
7.69%
Xi Wang
8
0.59%
1
7.69%
Eric Dumazet
2
0.15%
1
7.69%
Total
1353
100.00%
13
100.00%



int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs)
{
	if (lhs->pool < rhs->pool)
		return -1;
	if (lhs->pool > rhs->pool)
		return 1;
	if (lhs->seed < rhs->seed)
		return -1;
	if (lhs->seed > rhs->seed)
		return 1;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
51
68.92%
3
75.00%
Ilya Dryomov
23
31.08%
1
25.00%
Total
74
100.00%
4
100.00%

/*
 * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
 * to a set of osds) and primary_temp (explicit primary setting)
 */


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 = ceph_pg_compare(&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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
160
98.16%
2
66.67%
Ilya Dryomov
3
1.84%
1
33.33%
Total
163
100.00%
3
100.00%



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 = ceph_pg_compare(&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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
115
97.46%
4
80.00%
Ilya Dryomov
3
2.54%
1
20.00%
Total
118
100.00%
5
100.00%



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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
83
100.00%
2
100.00%
Total
83
100.00%
2
100.00%

/*
 * 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
136
100.00%
4
100.00%
Total
136
100.00%
4
100.00%



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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Sage Weil
84
100.00%
2
100.00%
Total
84
100.00%
2
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
26
100.00%
1
100.00%
Total
26
100.00%
1
100.00%



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;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Alex Elder
68
100.00%
1
100.00%
Total
68
100.00%
1
100.00%


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