ceph: add helper function that forcibly reconnects to ceph cluster.

It closes mds sessions, drop all caps and invalidates page caches,
then use new entity address to reconnect to the cluster.

After reconnect, all dirty data/metadata are dropped, file locks
get lost sliently. Open files continue to work because client will
try renewing caps on later read/write.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index df4bea231017a2e1df77a4d739eec60022f90fee..ed4d20a54af736892c129d8c82910f31e3bf39b0 100644 (file)
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1394,9 +1394,12 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
                struct ceph_cap_flush *cf;
                struct ceph_mds_client *mdsc = fsc->mdsc;
 
-               if (ci->i_wrbuffer_ref > 0 &&
-                   READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
-                       invalidate = true;
+               if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+                       if (inode->i_data.nrpages > 0)
+                               invalidate = true;
+                       if (ci->i_wrbuffer_ref > 0)
+                               mapping_set_error(&inode->i_data, -EIO);
+               }
 
                while (!list_empty(&ci->i_cap_flush_list)) {
                        cf = list_first_entry(&ci->i_cap_flush_list,
@@ -4369,7 +4372,12 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
                session = __ceph_lookup_mds_session(mdsc, mds);
                if (!session)
                        continue;
+
+               if (session->s_state == CEPH_MDS_SESSION_REJECTED)
+                       __unregister_session(mdsc, session);
+               __wake_requests(mdsc, &session->s_waiting);
                mutex_unlock(&mdsc->mutex);
+
                mutex_lock(&session->s_mutex);
                __close_session(mdsc, session);
                if (session->s_state == CEPH_MDS_SESSION_CLOSING) {
@@ -4378,6 +4386,7 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
                }
                mutex_unlock(&session->s_mutex);
                ceph_put_mds_session(session);
+
                mutex_lock(&mdsc->mutex);
                kick_requests(mdsc, mds);
        }

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index ab4868c7308ecc9011fd76bf06307244658f2580..a95dd13bb628c4324c3853be7ab7800e43115205 100644 (file)
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -829,7 +829,6 @@ static void ceph_umount_begin(struct super_block *sb)
        fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
        ceph_osdc_abort_requests(&fsc->client->osdc, -EIO);
        ceph_mdsc_force_umount(fsc->mdsc);
-       return;
 }
 
 static int ceph_remount(struct super_block *sb, int *flags, char *data)
@@ -1152,6 +1151,31 @@ static struct file_system_type ceph_fs_type = {
 };
 MODULE_ALIAS_FS("ceph");
 
+int ceph_force_reconnect(struct super_block *sb)
+{
+       struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+       int err = 0;
+
+       ceph_umount_begin(sb);
+
+       /* Make sure all page caches get invalidated.
+        * see remove_session_caps_cb() */
+       flush_workqueue(fsc->inode_wq);
+
+       /* In case that we were blacklisted. This also reset
+        * all mon/osd connections */
+       ceph_reset_client_addr(fsc->client);
+
+       ceph_osdc_clear_abort_err(&fsc->client->osdc);
+       fsc->mount_state = CEPH_MOUNT_MOUNTED;
+
+       if (sb->s_root) {
+               err = __ceph_do_getattr(d_inode(sb->s_root), NULL,
+                                       CEPH_STAT_CAP_INODE, true);
+       }
+       return err;
+}
+
 static int __init init_ceph(void)
 {
        int ret = init_caches();

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1452f62445c33d878fb2958063c65753520fa262..7af7f2ba8da54a2fa0cd6d830fdf11feb0f5cd33 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -846,7 +846,8 @@ static inline int default_congestion_kb(void)
 }
 
 
-
+/* super.c */
+extern int ceph_force_reconnect(struct super_block *sb);
 /* snap.c */
 struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
                                               u64 ino);