Release 4.14 net/ceph/osdmap.c

// SPDX-License-Identifier: GPL-2.0

#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, u32 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
68
73.91%
1
33.33%
Cong Ding
23
25.00%
1
33.33%
Ilya Dryomov
1
1.09%
1
33.33%
Total
92
100.00%
3
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 struct crush_choose_arg_map *alloc_choose_arg_map(void)
{
	struct crush_choose_arg_map *arg_map;

	arg_map = kzalloc(sizeof(*arg_map), GFP_NOIO);
	if (!arg_map)
		return NULL;

	RB_CLEAR_NODE(&arg_map->node);
	return arg_map;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
47
100.00%
1
100.00%
Total
47
100.00%
1
100.00%



static void free_choose_arg_map(struct crush_choose_arg_map *arg_map)
{
	if (arg_map) {
		int i, j;

		WARN_ON(!RB_EMPTY_NODE(&arg_map->node));

		for (i = 0; i < arg_map->size; i++) {
			struct crush_choose_arg *arg = &arg_map->args[i];

			for (j = 0; j < arg->weight_set_size; j++)
				kfree(arg->weight_set[j].weights);
			kfree(arg->weight_set);
			kfree(arg->ids);
		}
		kfree(arg_map->args);
		kfree(arg_map);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
117
100.00%
1
100.00%
Total
117
100.00%
1
100.00%

DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index,
		node);



void clear_choose_args(struct crush_map *c)
{
	while (!RB_EMPTY_ROOT(&c->choose_args)) {
		struct crush_choose_arg_map *arg_map =
		    rb_entry(rb_first(&c->choose_args),
			     struct crush_choose_arg_map, node);

		erase_choose_arg_map(&c->choose_args, arg_map);
		free_choose_arg_map(arg_map);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
59
100.00%
1
100.00%
Total
59
100.00%
1
100.00%



static u32 *decode_array_32_alloc(void **p, void *end, u32 *plen)
{
	u32 *a = NULL;
	u32 len;
	int ret;

	ceph_decode_32_safe(p, end, len, e_inval);
	if (len) {
		u32 i;

		a = kmalloc_array(len, sizeof(u32), GFP_NOIO);
		if (!a) {
			ret = -ENOMEM;
			goto fail;
		}

		ceph_decode_need(p, end, len * sizeof(u32), e_inval);
		for (i = 0; i < len; i++)
			a[i] = ceph_decode_32(p);
	}

	*plen = len;
	return a;

e_inval:
	ret = -EINVAL;
fail:
	kfree(a);
	return ERR_PTR(ret);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
148
100.00%
1
100.00%
Total
148
100.00%
1
100.00%

/*
 * Assumes @arg is zero-initialized.
 */


static int decode_choose_arg(void **p, void *end, struct crush_choose_arg *arg)
{
	int ret;

	ceph_decode_32_safe(p, end, arg->weight_set_size, e_inval);
	if (arg->weight_set_size) {
		u32 i;

		arg->weight_set = kmalloc_array(arg->weight_set_size,
						sizeof(*arg->weight_set),
						GFP_NOIO);
		if (!arg->weight_set)
			return -ENOMEM;

		for (i = 0; i < arg->weight_set_size; i++) {
			struct crush_weight_set *w = &arg->weight_set[i];

			w->weights = decode_array_32_alloc(p, end, &w->size);
			if (IS_ERR(w->weights)) {
				ret = PTR_ERR(w->weights);
				w->weights = NULL;
				return ret;
			}
		}
	}

	arg->ids = decode_array_32_alloc(p, end, &arg->ids_size);
	if (IS_ERR(arg->ids)) {
		ret = PTR_ERR(arg->ids);
		arg->ids = NULL;
		return ret;
	}

	return 0;

e_inval:
	return -EINVAL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
208
100.00%
1
100.00%
Total
208
100.00%
1
100.00%



static int decode_choose_args(void **p, void *end, struct crush_map *c)
{
	struct crush_choose_arg_map *arg_map = NULL;
	u32 num_choose_arg_maps, num_buckets;
	int ret;

	ceph_decode_32_safe(p, end, num_choose_arg_maps, e_inval);
	while (num_choose_arg_maps--) {
		arg_map = alloc_choose_arg_map();
		if (!arg_map) {
			ret = -ENOMEM;
			goto fail;
		}

		ceph_decode_64_safe(p, end, arg_map->choose_args_index,
				    e_inval);
		arg_map->size = c->max_buckets;
		arg_map->args = kcalloc(arg_map->size, sizeof(*arg_map->args),
					GFP_NOIO);
		if (!arg_map->args) {
			ret = -ENOMEM;
			goto fail;
		}

		ceph_decode_32_safe(p, end, num_buckets, e_inval);
		while (num_buckets--) {
			struct crush_choose_arg *arg;
			u32 bucket_index;

			ceph_decode_32_safe(p, end, bucket_index, e_inval);
			if (bucket_index >= arg_map->size)
				goto e_inval;

			arg = &arg_map->args[bucket_index];
			ret = decode_choose_arg(p, end, arg);
			if (ret)
				goto fail;

			if (arg->ids_size &&
			    arg->ids_size != c->buckets[bucket_index]->size)
				goto e_inval;
		}

		insert_choose_arg_map(&c->choose_args, arg_map);
	}

	return 0;

e_inval:
	ret = -EINVAL;
fail:
	free_choose_arg_map(arg_map);
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Ilya Dryomov
260
100.00%
2
100.00%
Total
260
100.00%
2
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;
	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);

	c->choose_args = RB_ROOT;

        /* 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:
			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 fail;
			break;
		case CRUSH_BUCKET_LIST:
			err = crush_decode_list_bucket(p, end,
			       (struct crush_bucket_list *)b);
			if (err < 0)
				goto fail;
			break;
		case CRUSH_BUCKET_TREE:
			err = crush_decode_tree_bucket(p, end,
				(struct crush_bucket_tree *)b);
			if (err < 0)
				goto fail;
			break;
		case CRUSH_BUCKET_STRAW:
			err = crush_decode_straw_bucket(p, end,
				(struct crush_bucket_straw *)b);
			if (err < 0)
				goto fail;
			break;
		case CRUSH_BUCKET_STRAW2:
			err = crush_decode_straw2_bucket(p, end,
				(struct crush_bucket_straw2 *)b);
			if (err < 0)
				goto fail;
			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
		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);
		}
	}

	ceph_decode_skip_map(p, end, 32, string, bad); /* type_map */
	ceph_decode_skip_map(p, end, 32, string, bad); /* name_map */
	ceph_decode_skip_map(p, end, 32, string, bad); /* rule_name_map */

        /* 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);

	if (*p != end) {
		/* class_map */
		ceph_decode_skip_map(p, end, 32, 32, bad);
		/* class_name */
		ceph_decode_skip_map(p, end, 32, string, bad);
		/* class_bucket */
		ceph_decode_skip_map_of_map(p,