Merge tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The two main items are support for disabling automatic rbd exclusive
  lock transfers from myself and the long awaited -ENOSPC handling
  series from Jeff.

  The former will allow rbd users to take advantage of exclusive lock's
  built-in blacklist/break-lock functionality while staying in control
  of who owns the lock. With the latter in place, we will abort
  filesystem writes on -ENOSPC instead of having them block
  indefinitely.

  Beyond that we've got the usual pile of filesystem fixes from Zheng,
  some refcount_t conversion patches from Elena and a patch for an
  ancient open() flags handling bug from Alexander"

* tag 'ceph-for-4.12-rc1' of git://github.com/ceph/ceph-client: (31 commits)
  ceph: fix memory leak in __ceph_setxattr()
  ceph: fix file open flags on ppc64
  ceph: choose readdir frag based on previous readdir reply
  rbd: exclusive map option
  rbd: return ResponseMessage result from rbd_handle_request_lock()
  rbd: kill rbd_is_lock_supported()
  rbd: support updating the lock cookie without releasing the lock
  rbd: store lock cookie
  rbd: ignore unlock errors
  rbd: fix error handling around rbd_init_disk()
  rbd: move rbd_unregister_watch() call into rbd_dev_image_release()
  rbd: move rbd_dev_destroy() call out of rbd_dev_image_release()
  ceph: when seeing write errors on an inode, switch to sync writes
  Revert "ceph: SetPageError() for writeback pages if writepages fails"
  ceph: handle epoch barriers in cap messages
  libceph: add an epoch_barrier field to struct ceph_osd_client
  libceph: abort already submitted but abortable requests when map or pool goes full
  libceph: allow requests to return immediately on full conditions if caller wishes
  libceph: remove req->r_replay_version
  ceph: make seeky readdir more efficient
  ...

1 files changed, 37 insertions, 7 deletions

diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 5454e2327a5f..1a748cf88535 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -22,11 +22,11 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
 	int i;
 
 	/* special case for one mds */
-	if (1 == m->m_max_mds && m->m_info[0].state > 0)
+	if (1 == m->m_num_mds && m->m_info[0].state > 0)
 		return 0;
 
 	/* count */
-	for (i = 0; i < m->m_max_mds; i++)
+	for (i = 0; i < m->m_num_mds; i++)
 		if (m->m_info[i].state > 0)
 			n++;
 	if (n == 0)
@@ -135,8 +135,9 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 	m->m_session_autoclose = ceph_decode_32(p);
 	m->m_max_file_size = ceph_decode_64(p);
 	m->m_max_mds = ceph_decode_32(p);
+	m->m_num_mds = m->m_max_mds;
 
-	m->m_info = kcalloc(m->m_max_mds, sizeof(*m->m_info), GFP_NOFS);
+	m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS);
 	if (m->m_info == NULL)
 		goto nomem;
 
@@ -207,9 +208,20 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		     ceph_pr_addr(&addr.in_addr),
 		     ceph_mds_state_name(state));
 
-		if (mds < 0 || mds >= m->m_max_mds || state <= 0)
+		if (mds < 0 || state <= 0)
 			continue;
 
+		if (mds >= m->m_num_mds) {
+			int new_num = max(mds + 1, m->m_num_mds * 2);
+			void *new_m_info = krealloc(m->m_info,
+						new_num * sizeof(*m->m_info),
+						GFP_NOFS | __GFP_ZERO);
+			if (!new_m_info)
+				goto nomem;
+			m->m_info = new_m_info;
+			m->m_num_mds = new_num;
+		}
+
 		info = &m->m_info[mds];
 		info->global_id = global_id;
 		info->state = state;
@@ -229,6 +241,14 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 			info->export_targets = NULL;
 		}
 	}
+	if (m->m_num_mds > m->m_max_mds) {
+		/* find max up mds */
+		for (i = m->m_num_mds; i >= m->m_max_mds; i--) {
+			if (i == 0 || m->m_info[i-1].state > 0)
+				break;
+		}
+		m->m_num_mds = i;
+	}
 
 	/* pg_pools */
 	ceph_decode_32_safe(p, end, n, bad);
@@ -270,12 +290,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 
 		for (i = 0; i < n; i++) {
 			s32 mds = ceph_decode_32(p);
-			if (mds >= 0 && mds < m->m_max_mds) {
+			if (mds >= 0 && mds < m->m_num_mds) {
 				if (m->m_info[mds].laggy)
 					num_laggy++;
 			}
 		}
 		m->m_num_laggy = num_laggy;
+
+		if (n > m->m_num_mds) {
+			void *new_m_info = krealloc(m->m_info,
+						    n * sizeof(*m->m_info),
+						    GFP_NOFS | __GFP_ZERO);
+			if (!new_m_info)
+				goto nomem;
+			m->m_info = new_m_info;
+		}
+		m->m_num_mds = n;
 	}
 
 	/* inc */
@@ -341,7 +371,7 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
 {
 	int i;
 
-	for (i = 0; i < m->m_max_mds; i++)
+	for (i = 0; i < m->m_num_mds; i++)
 		kfree(m->m_info[i].export_targets);
 	kfree(m->m_info);
 	kfree(m->m_data_pg_pools);
@@ -357,7 +387,7 @@ bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m)
 		return false;
 	if (m->m_num_laggy > 0)
 		return false;
-	for (i = 0; i < m->m_max_mds; i++) {
+	for (i = 0; i < m->m_num_mds; i++) {
 		if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE)
 			nr_active++;
 	}