osdmap.c

	/* new_weight */
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		u32 osd, off;
		ceph_decode_need(p, end, sizeof(u32)*2, bad);
		osd = ceph_decode_32(p);
		off = ceph_decode_32(p);
		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 */
	ceph_decode_32_safe(p, end, len, bad);
	while (len--) {
		struct ceph_pg_mapping *pg;
		int j;
		struct ceph_pg pgid;
		u32 pglen;

		err = ceph_decode_pgid(p, end, &pgid);
		if (err)
			goto bad;
		ceph_decode_need(p, end, sizeof(u32), bad);
		pglen = ceph_decode_32(p);
		if (pglen) {
			ceph_decode_need(p, end, pglen*sizeof(u32), bad);

			/* removing existing (if any) */
			(void) __remove_pg_mapping(&map->pg_temp, pgid);

			/* insert */
			err = -EINVAL;
			if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
				goto bad;
			err = -ENOMEM;
			pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
			if (!pg)
				goto bad;
			pg->pgid = pgid;
			pg->len = pglen;
			for (j = 0; j < pglen; j++)
				pg->osds[j] = ceph_decode_32(p);
			err = __insert_pg_mapping(pg, &map->pg_temp);
			if (err) {
				kfree(pg);
				goto bad;
			}
			dout(" added pg_temp %lld.%x len %d\n", pgid.pool,
			     pgid.seed, pglen);
		} else {
			/* remove */
			__remove_pg_mapping(&map->pg_temp, pgid);
		}
	}

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

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

bad:
	pr_err("corrupt inc 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);
	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.
 */
int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
				   u64 off, u64 len,
				   u64 *ono,
				   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;
	u64 t, su_offset;

	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, len,
	     osize, su);
	if (su == 0 || sc == 0)
		goto invalid;
	su_per_object = osize / su;
	if (su_per_object == 0)
		goto invalid;
	dout("osize %u / su %u = su_per_object %u\n", osize, su,
	     su_per_object);

	if ((su & ~PAGE_MASK) != 0)
		goto invalid;

	/* 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;

	*ono = objsetno * sc + stripepos;
	dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono);

	/* *oxoff = *off % layout->fl_stripe_unit;  # offset in su */
	t = off;
	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 (len) or
	 * the remainder of the current stripe being written to.
	 */
	*oxlen = min_t(u64, len, su - su_offset);

	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
	return 0;

invalid:
	dout(" invalid layout\n");
	*ono = 0;
	*oxoff = 0;
	*oxlen = 0;
	return -EINVAL;
}
EXPORT_SYMBOL(ceph_calc_file_object_mapping);

/*
 * Calculate mapping of a (oloc, oid) pair to a PG.  Should only be
 * called with target's (oloc, oid), since tiering isn't taken into
 * account.
 */
int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
			struct ceph_object_locator *oloc,
			struct ceph_object_id *oid,
			struct ceph_pg *pg_out)
{
	struct ceph_pg_pool_info *pi;

	pi = __lookup_pg_pool(&osdmap->pg_pools, oloc->pool);
	if (!pi)
		return -EIO;

	pg_out->pool = oloc->pool;
	pg_out->seed = ceph_str_hash(pi->object_hash, oid->name,
				     oid->name_len);

	dout("%s '%.*s' pgid %llu.%x\n", __func__, oid->name_len, oid->name,
	     pg_out->pool, pg_out->seed);
	return 0;
}
EXPORT_SYMBOL(ceph_oloc_oid_to_pg);

static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
		    int *result, int result_max,
		    const __u32 *weight, int weight_max)
{
	int r;

	BUG_ON(result_max > CEPH_PG_MAX_SIZE);

	mutex_lock(&map->crush_scratch_mutex);
	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
			  weight, weight_max, map->crush_scratch_ary);
	mutex_unlock(&map->crush_scratch_mutex);

	return r;
}

/*
 * Calculate raw osd vector for the given pgid.  Return pointer to osd
 * array, or NULL on failure.
 */
static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
			int *osds, int *num)
{
	struct ceph_pg_mapping *pg;
	struct ceph_pg_pool_info *pool;
	int ruleno;
	int r;
	u32 pps;

	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
	if (!pool)
		return NULL;

	/* pg_temp? */
	pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
				    pool->pg_num_mask);
	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
	if (pg) {
		*num = pg->len;
		return pg->osds;
	}

	/* crush */
	ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
				 pool->type, pool->size);
	if (ruleno < 0) {
		pr_err("no crush rule pool %lld ruleset %d type %d size %d\n",
		       pgid.pool, pool->crush_ruleset, pool->type,
		       pool->size);
		return NULL;
	}

	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
		/* hash pool id and seed sothat pool PGs do not overlap */
		pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
				     ceph_stable_mod(pgid.seed, pool->pgp_num,
						     pool->pgp_num_mask),
				     pgid.pool);
	} else {
		/*
		 * legacy ehavior: add ps and pool together.  this is
		 * not a great approach because the PGs from each pool
		 * will overlap on top of each other: 0.5 == 1.4 ==
		 * 2.3 == ...
		 */
		pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
				      pool->pgp_num_mask) +
			(unsigned)pgid.pool;
	}
	r = do_crush(osdmap, ruleno, pps, osds, min_t(int, pool->size, *num),
		     osdmap->osd_weight, osdmap->max_osd);
	if (r < 0) {
		pr_err("error %d from crush rule: pool %lld ruleset %d type %d"
		       " size %d\n", r, pgid.pool, pool->crush_ruleset,
		       pool->type, pool->size);
		return NULL;
	}
	*num = r;
	return osds;
}

/*
 * 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;
}

/*
 * Return primary osd for given pgid, or -1 if none.
 */
int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
{
	int rawosds[CEPH_PG_MAX_SIZE], *osds;
	int i, num = CEPH_PG_MAX_SIZE;

	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];
	return -1;
}
EXPORT_SYMBOL(ceph_calc_pg_primary);