Merge tag 'ceph-for-4.8-rc1' of git://github.com/ceph/ceph-client

Pull Ceph updates from Ilya Dryomov:
 "The highlights are:

   - RADOS namespace support in libceph and CephFS (Zheng Yan and
     myself).  The stopgaps added in 4.5 to deny access to inodes in
     namespaces are removed and CEPH_FEATURE_FS_FILE_LAYOUT_V2 feature
     bit is now fully supported

   - A large rework of the MDS cap flushing code (Zheng Yan)

   - Handle some of ->d_revalidate() in RCU mode (Jeff Layton).  We were
     overly pessimistic before, bailing at the first sight of LOOKUP_RCU

  On top of that we've got a few CephFS bug fixes, a couple of cleanups
  and Arnd's workaround for a weird genksyms issue"

* tag 'ceph-for-4.8-rc1' of git://github.com/ceph/ceph-client: (34 commits)
  ceph: fix symbol versioning for ceph_monc_do_statfs
  ceph: Correctly return NXIO errors from ceph_llseek
  ceph: Mark the file cache as unreclaimable
  ceph: optimize cap flush waiting
  ceph: cleanup ceph_flush_snaps()
  ceph: kick cap flushes before sending other cap message
  ceph: introduce an inode flag to indicates if snapflush is needed
  ceph: avoid sending duplicated cap flush message
  ceph: unify cap flush and snapcap flush
  ceph: use list instead of rbtree to track cap flushes
  ceph: update types of some local varibles
  ceph: include 'follows' of pending snapflush in cap reconnect message
  ceph: update cap reconnect message to version 3
  ceph: mount non-default filesystem by name
  libceph: fsmap.user subscription support
  ceph: handle LOOKUP_RCU in ceph_d_revalidate
  ceph: allow dentry_lease_is_valid to work under RCU walk
  ceph: clear d_fsinfo pointer under d_lock
  ceph: remove ceph_mdsc_lease_release
  ceph: don't use ->d_time
  ...

1 files changed, 32 insertions, 8 deletions

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 99bdef66213a..dd3a6dbf71eb 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -446,7 +446,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_symlink = NULL;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
-	ci->i_pool_ns_len = 0;
+	RCU_INIT_POINTER(ci->i_layout.pool_ns, NULL);
 
 	ci->i_fragtree = RB_ROOT;
 	mutex_init(&ci->i_fragtree_mutex);
@@ -468,7 +468,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	INIT_LIST_HEAD(&ci->i_dirty_item);
 	INIT_LIST_HEAD(&ci->i_flushing_item);
 	ci->i_prealloc_cap_flush = NULL;
-	ci->i_cap_flush_tree = RB_ROOT;
+	INIT_LIST_HEAD(&ci->i_cap_flush_list);
 	init_waitqueue_head(&ci->i_cap_wq);
 	ci->i_hold_caps_min = 0;
 	ci->i_hold_caps_max = 0;
@@ -477,7 +477,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_head_snapc = NULL;
 	ci->i_snap_caps = 0;
 
-	for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
+	for (i = 0; i < CEPH_FILE_MODE_BITS; i++)
 		ci->i_nr_by_mode[i] = 0;
 
 	mutex_init(&ci->i_truncate_mutex);
@@ -570,6 +570,8 @@ void ceph_destroy_inode(struct inode *inode)
 	if (ci->i_xattrs.prealloc_blob)
 		ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
+	ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
+
 	call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 
@@ -583,6 +585,14 @@ int ceph_drop_inode(struct inode *inode)
 	return 1;
 }
 
+void ceph_evict_inode(struct inode *inode)
+{
+	/* wait unsafe sync writes */
+	ceph_sync_write_wait(inode);
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+}
+
 static inline blkcnt_t calc_inode_blocks(u64 size)
 {
 	return (size + (1<<9) - 1) >> 9;
@@ -733,6 +743,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	int issued = 0, implemented, new_issued;
 	struct timespec mtime, atime, ctime;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_string *pool_ns = NULL;
 	struct ceph_cap *new_cap = NULL;
 	int err = 0;
 	bool wake = false;
@@ -760,6 +771,10 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 			       iinfo->xattr_len);
 	}
 
+	if (iinfo->pool_ns_len > 0)
+		pool_ns = ceph_find_or_create_string(iinfo->pool_ns_data,
+						     iinfo->pool_ns_len);
+
 	spin_lock(&ci->i_ceph_lock);
 
 	/*
@@ -814,10 +829,18 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 
 	if (new_version ||
 	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
-		if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool)
+		s64 old_pool = ci->i_layout.pool_id;
+		struct ceph_string *old_ns;
+
+		ceph_file_layout_from_legacy(&ci->i_layout, &info->layout);
+		old_ns = rcu_dereference_protected(ci->i_layout.pool_ns,
+					lockdep_is_held(&ci->i_ceph_lock));
+		rcu_assign_pointer(ci->i_layout.pool_ns, pool_ns);
+
+		if (ci->i_layout.pool_id != old_pool || pool_ns != old_ns)
 			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
-		ci->i_layout = info->layout;
-		ci->i_pool_ns_len = iinfo->pool_ns_len;
+
+		pool_ns = old_ns;
 
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
@@ -985,6 +1008,7 @@ out:
 		ceph_put_cap(mdsc, new_cap);
 	if (xattr_blob)
 		ceph_buffer_put(xattr_blob);
+	ceph_put_string(pool_ns);
 	return err;
 }
 
@@ -1018,7 +1042,7 @@ static void update_dentry_lease(struct dentry *dentry,
 		goto out_unlock;
 
 	if (di->lease_gen == session->s_cap_gen &&
-	    time_before(ttl, dentry->d_time))
+	    time_before(ttl, di->time))
 		goto out_unlock;  /* we already have a newer lease. */
 
 	if (di->lease_session && di->lease_session != session)
@@ -1032,7 +1056,7 @@ static void update_dentry_lease(struct dentry *dentry,
 	di->lease_seq = le32_to_cpu(lease->seq);
 	di->lease_renew_after = half_ttl;
 	di->lease_renew_from = 0;
-	dentry->d_time = ttl;
+	di->time = ttl;
 out_unlock:
 	spin_unlock(&dentry->d_lock);
 	return;