path: root/net/ceph/mon_client.c

// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>

#include <linux/module.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/sched.h>

#include <linux/ceph/ceph_features.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/libceph.h>
#include <linux/ceph/debugfs.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/auth.h>

/*
 * Interact with Ceph monitor cluster.  Handle requests for new map
 * versions, and periodically resend as needed.  Also implement
 * statfs() and umount().
 *
 * A small cluster of Ceph "monitors" are responsible for managing critical
 * cluster configuration and state information.  An odd number (e.g., 3, 5)
 * of cmon daemons use a modified version of the Paxos part-time parliament
 * algorithm to manage the MDS map (mds cluster membership), OSD map, and
 * list of clients who have mounted the file system.
 *
 * We maintain an open, active session with a monitor at all times in order to
 * receive timely MDSMap updates.  We periodically send a keepalive byte on the
 * TCP socket to ensure we detect a failure.  If the connection does break, we
 * randomly hunt for a new monitor.  Once the connection is reestablished, we
 * resend any outstanding requests.
 */

static const struct ceph_connection_operations mon_con_ops;

static int __validate_auth(struct ceph_mon_client *monc);

static int decode_mon_info(void **p, void *end, bool msgr2,
			   struct ceph_entity_addr *addr)
{
	void *mon_info_end;
	u32 struct_len;
	u8 struct_v;
	int ret;

	ret = ceph_start_decoding(p, end, 1, "mon_info_t", &struct_v,
				  &struct_len);
	if (ret)
		return ret;

	mon_info_end = *p + struct_len;
	ceph_decode_skip_string(p, end, e_inval);  /* skip mon name */
	ret = ceph_decode_entity_addrvec(p, end, msgr2, addr);
	if (ret)
		return ret;

	*p = mon_info_end;
	return 0;

e_inval:
	return -EINVAL;
}

/*
 * Decode a monmap blob (e.g., during mount).
 *
 * Assume MonMap v3 (i.e. encoding with MONNAMES and MONENC).
 */
static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
{
	struct ceph_monmap *monmap = NULL;
	struct ceph_fsid fsid;
	u32 struct_len;
	int blob_len;
	int num_mon;
	u8 struct_v;
	u32 epoch;
	int ret;
	int i;

	ceph_decode_32_safe(p, end, blob_len, e_inval);
	ceph_decode_need(p, end, blob_len, e_inval);

	ret = ceph_start_decoding(p, end, 6, "monmap", &struct_v, &struct_len);
	if (ret)
		goto fail;

	dout("%s struct_v %d\n", __func__, struct_v);
	ceph_decode_copy_safe(p, end, &fsid, sizeof(fsid), e_inval);
	ceph_decode_32_safe(p, end, epoch, e_inval);
	if (struct_v >= 6) {
		u32 feat_struct_len;
		u8 feat_struct_v;

		*p += sizeof(struct ceph_timespec);  /* skip last_changed */
		*p += sizeof(struct ceph_timespec);  /* skip created */

		ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
					  &feat_struct_v, &feat_struct_len);
		if (ret)
			goto fail;

		*p += feat_struct_len;  /* skip persistent_features */

		ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
					  &feat_struct_v, &feat_struct_len);
		if (ret)
			goto fail;

		*p += feat_struct_len;  /* skip optional_features */
	}
	ceph_decode_32_safe(p, end, num_mon, e_inval);

	dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
	     num_mon);
	if (num_mon > CEPH_MAX_MON)
		goto e_inval;

	monmap = kmalloc(struct_size(monmap, mon_inst, num_mon), GFP_NOIO);
	if (!monmap) {
		ret = -ENOMEM;
		goto fail;
	}
	monmap->fsid = fsid;
	monmap->epoch = epoch;
	monmap->num_mon = num_mon;

	/* legacy_mon_addr map or mon_info map */
	for (i = 0; i < num_mon; i++) {
		struct ceph_entity_inst *inst = &monmap->mon_inst[i];

		ceph_decode_skip_string(p, end, e_inval);  /* skip mon name */
		inst->name.type = CEPH_ENTITY_TYPE_MON;
		inst->name.num = cpu_to_le64(i);

		if (struct_v >= 6)
			ret = decode_mon_info(p, end, msgr2, &inst->addr);
		else
			ret = ceph_decode_entity_addr(p, end, &inst->addr);
		if (ret)
			goto fail;

		dout("%s mon%d addr %s\n", __func__, i,
		     ceph_pr_addr(&inst->addr));
	}

	return monmap;

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

/*
 * return true if *addr is included in the monmap.
 */
int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr)
{
	int i;

	for (i = 0; i < m->num_mon; i++) {
		if (ceph_addr_equal_no_type(addr, &m->mon_inst[i].addr))
			return 1;
	}

	return 0;
}

/*
 * Send an auth request.
 */
static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
{
	monc->pending_auth = 1;
	monc->m_auth->front.iov_len = len;
	monc->m_auth->hdr.front_len = cpu_to_le32(len);
	ceph_msg_revoke(monc->m_auth);
	ceph_msg_get(monc->m_auth);  /* keep our ref */
	ceph_con_send(&monc->con, monc->m_auth);
}

/*
 * Close monitor session, if any.
 */
static void __close_session(struct ceph_mon_client *monc)
{
	dout("__close_session closing mon%d\n", monc->cur_mon);
	ceph_msg_revoke(monc->m_auth);
	ceph_msg_revoke_incoming(monc->m_auth_reply);
	ceph_msg_revoke(monc->m_subscribe);
	ceph_msg_revoke_incoming(monc->m_subscribe_ack);
	ceph_con_close(&monc->con);

	monc->pending_auth = 0;
	ceph_auth_reset(monc->auth);
}

/*
 * Pick a new monitor at random and set cur_mon.  If we are repicking
 * (i.e. cur_mon is already set), be sure to pick a different one.
 */
static void