Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull ceph updates from Sage Weil:
 "The big item here is support for inline data for CephFS and for
  message signatures from Zheng.  There are also several bug fixes,
  including interrupted flock request handling, 0-length xattrs, mksnap,
  cached readdir results, and a message version compat field.  Finally
  there are several cleanups from Ilya, Dan, and Markus.

  Note that there is another series coming soon that fixes some bugs in
  the RBD 'lingering' requests, but it isn't quite ready yet"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (27 commits)
  ceph: fix setting empty extended attribute
  ceph: fix mksnap crash
  ceph: do_sync is never initialized
  libceph: fixup includes in pagelist.h
  ceph: support inline data feature
  ceph: flush inline version
  ceph: convert inline data to normal data before data write
  ceph: sync read inline data
  ceph: fetch inline data when getting Fcr cap refs
  ceph: use getattr request to fetch inline data
  ceph: add inline data to pagecache
  ceph: parse inline data in MClientReply and MClientCaps
  libceph: specify position of extent operation
  libceph: add CREATE osd operation support
  libceph: add SETXATTR/CMPXATTR osd operations support
  rbd: don't treat CEPH_OSD_OP_DELETE as extent op
  ceph: remove unused stringification macros
  libceph: require cephx message signature by default
  ceph: introduce global empty snap context
  ceph: message versioning fixes
  ...

1 files changed, 47 insertions, 12 deletions

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index a5593d51d035..f61a74115beb 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -387,8 +387,10 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ci->i_ceph_lock);
 
 	ci->i_version = 0;
+	ci->i_inline_version = 0;
 	ci->i_time_warp_seq = 0;
 	ci->i_ceph_flags = 0;
+	ci->i_ordered_count = 0;
 	atomic_set(&ci->i_release_count, 1);
 	atomic_set(&ci->i_complete_count, 0);
 	ci->i_symlink = NULL;
@@ -657,7 +659,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
  * Populate an inode based on info from mds.  May be called on new or
  * existing inodes.
  */
-static int fill_inode(struct inode *inode,
+static int fill_inode(struct inode *inode, struct page *locked_page,
 		      struct ceph_mds_reply_info_in *iinfo,
 		      struct ceph_mds_reply_dirfrag *dirinfo,
 		      struct ceph_mds_session *session,
@@ -675,6 +677,7 @@ static int fill_inode(struct inode *inode,
 	bool wake = false;
 	bool queue_trunc = false;
 	bool new_version = false;
+	bool fill_inline = false;
 
 	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
@@ -845,7 +848,8 @@ static int fill_inode(struct inode *inode,
 	    (issued & CEPH_CAP_FILE_EXCL) == 0 &&
 	    !__ceph_dir_is_complete(ci)) {
 		dout(" marking %p complete (empty)\n", inode);
-		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
+		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count),
+					ci->i_ordered_count);
 	}
 
 	/* were we issued a capability? */
@@ -873,8 +877,23 @@ static int fill_inode(struct inode *inode,
 			   ceph_vinop(inode));
 		__ceph_get_fmode(ci, cap_fmode);
 	}
+
+	if (iinfo->inline_version > 0 &&
+	    iinfo->inline_version >= ci->i_inline_version) {
+		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
+		ci->i_inline_version = iinfo->inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (locked_page ||
+		     (le32_to_cpu(info->cap.caps) & cache_caps)))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, locked_page,
+				      iinfo->inline_data, iinfo->inline_len);
+
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 
@@ -1062,7 +1081,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		struct inode *dir = req->r_locked_dir;
 
 		if (dir) {
-			err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
+			err = fill_inode(dir, NULL,
+					 &rinfo->diri, rinfo->dirfrag,
 					 session, req->r_request_started, -1,
 					 &req->r_caps_reservation);
 			if (err < 0)
@@ -1132,7 +1152,7 @@ retry_lookup:
 		}
 		req->r_target_inode = in;
 
-		err = fill_inode(in, &rinfo->targeti, NULL,
+		err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
 				session, req->r_request_started,
 				(!req->r_aborted && rinfo->head->result == 0) ?
 				req->r_fmode : -1,
@@ -1204,8 +1224,8 @@ retry_lookup:
 			ceph_invalidate_dentry_lease(dn);
 
 			/* d_move screws up sibling dentries' offsets */
-			ceph_dir_clear_complete(dir);
-			ceph_dir_clear_complete(olddir);
+			ceph_dir_clear_ordered(dir);
+			ceph_dir_clear_ordered(olddir);
 
 			dout("dn %p gets new offset %lld\n", req->r_old_dentry,
 			     ceph_dentry(req->r_old_dentry)->offset);
@@ -1217,6 +1237,7 @@ retry_lookup:
 		if (!rinfo->head->is_target) {
 			dout("fill_trace null dentry\n");
 			if (dn->d_inode) {
+				ceph_dir_clear_ordered(dir);
 				dout("d_delete %p\n", dn);
 				d_delete(dn);
 			} else {
@@ -1233,7 +1254,7 @@ retry_lookup:
 
 		/* attach proper inode */
 		if (!dn->d_inode) {
-			ceph_dir_clear_complete(dir);
+			ceph_dir_clear_ordered(dir);
 			ihold(in);
 			dn = splice_dentry(dn, in, &have_lease);
 			if (IS_ERR(dn)) {
@@ -1263,7 +1284,7 @@ retry_lookup:
 		BUG_ON(!dir);
 		BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR);
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
-		ceph_dir_clear_complete(dir);
+		ceph_dir_clear_ordered(dir);
 		ihold(in);
 		dn = splice_dentry(dn, in, NULL);
 		if (IS_ERR(dn)) {
@@ -1300,7 +1321,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 			dout("new_inode badness got %d\n", err);
 			continue;
 		}
-		rc = fill_inode(in, &rinfo->dir_in[i], NULL, session,
+		rc = fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
 				req->r_request_started, -1,
 				&req->r_caps_reservation);
 		if (rc < 0) {
@@ -1416,7 +1437,7 @@ retry_lookup:
 			}
 		}
 
-		if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
+		if (fill_inode(in, NULL, &rinfo->dir_in[i], NULL, session,
 			       req->r_request_started, -1,
 			       &req->r_caps_reservation) < 0) {
 			pr_err("fill_inode badness on %p\n", in);
@@ -1899,7 +1920,8 @@ out_put:
  * Verify that we have a lease on the given mask.  If not,
  * do a getattr against an mds.
  */
-int ceph_do_getattr(struct inode *inode, int mask, bool force)
+int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
+		      int mask, bool force)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1911,7 +1933,8 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
 		return 0;
 	}
 
-	dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
+	dout("do_getattr inode %p mask %s mode 0%o\n",
+	     inode, ceph_cap_string(mask), inode->i_mode);
 	if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
 		return 0;
 
@@ -1922,7 +1945,19 @@ int ceph_do_getattr(struct inode *inode, int mask, bool force)
 	ihold(inode);
 	req->r_num_caps = 1;
 	req->r_args.getattr.mask = cpu_to_le32(mask);
+	req->r_locked_page = locked_page;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	if (locked_page && err == 0) {
+		u64 inline_version = req->r_reply_info.targeti.inline_version;
+		if (inline_version == 0) {
+			/* the reply is supposed to contain inline data */
+			err = -EINVAL;
+		} else if (inline_version == CEPH_INLINE_NONE) {
+			err = -ENODATA;
+		} else {
+			err = req->r_reply_info.targeti.inline_len;
+		}
+	}
 	ceph_mdsc_put_request(req);
 	dout("do_getattr result=%d\n", err);
 	return err;