#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/mon_client.h>
#include <linux/ceph/libceph.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);
/*
* Decode a monmap blob (e.g., during mount).
*/
struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
{
struct ceph_monmap *m = NULL;
int i, err = -EINVAL;
struct ceph_fsid fsid;
u32 epoch, num_mon;
u16 version;
u32 len;
ceph_decode_32_safe(&p, end, len, bad);
ceph_decode_need(&p, end, len, bad);
dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p));
ceph_decode_16_safe(&p, end, version, bad);
ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
ceph_decode_copy(&p, &fsid, sizeof(fsid));
epoch = ceph_decode_32(&p);
num_mon = ceph_decode_32(&p);
ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad);
if (num_mon >= CEPH_MAX_MON)
goto bad;
m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS);
if (m == NULL)
return ERR_PTR(-ENOMEM);
m->fsid = fsid;
m->epoch = epoch;
m->num_mon = num_mon;
ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0]));
for (i = 0; i < num_mon; i++)
ceph_decode_addr(&m->mon_inst[i].addr);
dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
m->num_mon);
for (i = 0; i < m->num_mon; i++)
dout("monmap_decode mon%d is %s\n", i,
ceph_pr_addr(&m->mon_inst[i].addr.in_addr));
return m;
bad:
dout("monmap_decode failed with %d\n", err);
kfree(m);
return ERR_PTR(err);
}
/*
* 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 (memcmp(addr, &m->mon_inst[i].addr, sizeof(*addr)) == 0)
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_con_revoke(monc->con, 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)
{
if (monc->con) {
dout("__close_session closing mon%d\n", monc->cur_mon);
ceph_con_revoke(monc->con, monc->m_auth);
ceph_con_close(monc->con);
monc->cur_mon = -1;
monc->pending_auth = 0;