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

Pull Ceph updates from Sage Weil:
 "The biggest chunk is a series of patches from Ilya that add support
  for new Ceph osd and crush map features, including some new tunables,
  primary affinity, and the new encoding that is needed for erasure
  coding support.  This brings things into parity with the server side
  and the looming firefly release.  There is also support for allocation
  hints in RBD that help limit fragmentation on the server side.

  There is also a series of patches from Zheng fixing NFS reexport,
  directory fragmentation support, flock vs fnctl behavior, and some
  issues with clustered MDS.

  Finally, there are some miscellaneous fixes from Yunchuan Wen for
  fscache, Fabian Frederick for ACLs, and from me for fsync(dirfd)
  behavior"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (79 commits)
  ceph: skip invalid dentry during dcache readdir
  libceph: dump pool {read,write}_tier to debugfs
  libceph: output primary affinity values on osdmap updates
  ceph: flush cap release queue when trimming session caps
  ceph: don't grabs open file reference for aborted request
  ceph: drop extra open file reference in ceph_atomic_open()
  ceph: preallocate buffer for readdir reply
  libceph: enable PRIMARY_AFFINITY feature bit
  libceph: redo ceph_calc_pg_primary() in terms of ceph_calc_pg_acting()
  libceph: add support for osd primary affinity
  libceph: add support for primary_temp mappings
  libceph: return primary from ceph_calc_pg_acting()
  libceph: switch ceph_calc_pg_acting() to new helpers
  libceph: introduce apply_temps() helper
  libceph: introduce pg_to_raw_osds() and raw_to_up_osds() helpers
  libceph: ceph_can_shift_osds(pool) and pool type defines
  libceph: ceph_osd_{exists,is_up,is_down}(osd) definitions
  libceph: enable OSDMAP_ENC feature bit
  libceph: primary_affinity decode bits
  libceph: primary_affinity infrastructure
  ...

28 files changed, 1421 insertions, 635 deletions

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 34898d53395..4c95b503b09 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1654,7 +1654,7 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 	if (osd_req->r_result < 0)
 		obj_request->result = osd_req->r_result;
 
-	BUG_ON(osd_req->r_num_ops > 2);
+	rbd_assert(osd_req->r_num_ops <= CEPH_OSD_MAX_OP);
 
 	/*
 	 * We support a 64-bit length, but ultimately it has to be
@@ -1662,11 +1662,15 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 	 */
 	obj_request->xferred = osd_req->r_reply_op_len[0];
 	rbd_assert(obj_request->xferred < (u64)UINT_MAX);
+
 	opcode = osd_req->r_ops[0].op;
 	switch (opcode) {
 	case CEPH_OSD_OP_READ:
 		rbd_osd_read_callback(obj_request);
 		break;
+	case CEPH_OSD_OP_SETALLOCHINT:
+		rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE);
+		/* fall through */
 	case CEPH_OSD_OP_WRITE:
 		rbd_osd_write_callback(obj_request);
 		break;
@@ -1715,9 +1719,16 @@ static void rbd_osd_req_format_write(struct rbd_obj_request *obj_request)
 			snapc, CEPH_NOSNAP, &mtime);
 }
 
+/*
+ * Create an osd request.  A read request has one osd op (read).
+ * A write request has either one (watch) or two (hint+write) osd ops.
+ * (All rbd data writes are prefixed with an allocation hint op, but
+ * technically osd watch is a write request, hence this distinction.)
+ */
 static struct ceph_osd_request *rbd_osd_req_create(
 					struct rbd_device *rbd_dev,
 					bool write_request,
+					unsigned int num_ops,
 					struct rbd_obj_request *obj_request)
 {
 	struct ceph_snap_context *snapc = NULL;
@@ -1733,10 +1744,13 @@ static struct ceph_osd_request *rbd_osd_req_create(
 			snapc = img_request->snapc;
 	}
 
-	/* Allocate and initialize the request, for the single op */
+	rbd_assert(num_ops == 1 || (write_request && num_ops == 2));
+
+	/* Allocate and initialize the request, for the num_ops ops */
 
 	osdc = &rbd_dev->rbd_client->client->osdc;
-	osd_req = ceph_osdc_alloc_request(osdc, snapc, 1, false, GFP_ATOMIC);
+	osd_req = ceph_osdc_alloc_request(osdc, snapc, num_ops, false,
+					  GFP_ATOMIC);
 	if (!osd_req)
 		return NULL;	/* ENOMEM */
 
@@ -1756,8 +1770,8 @@ static struct ceph_osd_request *rbd_osd_req_create(
 
 /*
  * Create a copyup osd request based on the information in the
- * object request supplied.  A copyup request has two osd ops,
- * a copyup method call, and a "normal" write request.
+ * object request supplied.  A copyup request has three osd ops,
+ * a copyup method call, a hint op, and a write op.
  */
 static struct ceph_osd_request *
 rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
@@ -1773,12 +1787,12 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
 	rbd_assert(img_request);
 	rbd_assert(img_request_write_test(img_request));
 
-	/* Allocate and initialize the request, for the two ops */
+	/* Allocate and initialize the request, for the three ops */
 
 	snapc = img_request->snapc;
 	rbd_dev = img_request->rbd_dev;
 	osdc = &rbd_dev->rbd_client->client->osdc;
-	osd_req = ceph_osdc_alloc_request(osdc, snapc, 2, false, GFP_ATOMIC);
+	osd_req = ceph_osdc_alloc_request(osdc, snapc, 3, false, GFP_ATOMIC);
 	if (!osd_req)
 		return NULL;	/* ENOMEM */
 
@@ -2178,6 +2192,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 		const char *object_name;
 		u64 offset;
 		u64 length;
+		unsigned int which = 0;
 
 		object_name = rbd_segment_name(rbd_dev, img_offset);
 		if (!object_name)
@@ -2190,6 +2205,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 		rbd_segment_name_free(object_name);
 		if (!obj_request)
 			goto out_unwind;
+
 		/*
 		 * set obj_request->img_request before creating the
 		 * osd_request so that it gets the right snapc
@@ -2207,7 +2223,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 								clone_size,
 								GFP_ATOMIC);
 			if (!obj_request->bio_list)
-				goto out_partial;
+				goto out_unwind;
 		} else {
 			unsigned int page_count;
 
@@ -2220,19 +2236,27 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 		}
 
 		osd_req = rbd_osd_req_create(rbd_dev, write_request,
-						obj_request);
+					     (write_request ? 2 : 1),
+					     obj_request);
 		if (!osd_req)
-			goto out_partial;
+			goto out_unwind;
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
 
-		osd_req_op_extent_init(osd_req, 0, opcode, offset, length,
-						0, 0);
+		if (write_request) {
+			osd_req_op_alloc_hint_init(osd_req, which,
+					     rbd_obj_bytes(&rbd_dev->header),
+					     rbd_obj_bytes(&rbd_dev->header));
+			which++;
+		}
+
+		osd_req_op_extent_init(osd_req, which, opcode, offset, length,
+				       0, 0);
 		if (type == OBJ_REQUEST_BIO)
-			osd_req_op_extent_osd_data_bio(osd_req, 0,
+			osd_req_op_extent_osd_data_bio(osd_req, which,
 					obj_request->bio_list, length);
 		else
-			osd_req_op_extent_osd_data_pages(osd_req, 0,
+			osd_req_op_extent_osd_data_pages(osd_req, which,
 					obj_request->pages, length,
 					offset & ~PAGE_MASK, false, false);
 
@@ -2249,11 +2273,9 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 
 	return 0;
 
-out_partial:
-	rbd_obj_request_put(obj_request);
 out_unwind:
 	for_each_obj_request_safe(img_request, obj_request, next_obj_request)
-		rbd_obj_request_put(obj_request);
+		rbd_img_obj_request_del(img_request, obj_request);
 
 	return -ENOMEM;
 }
@@ -2353,7 +2375,7 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 
 	/*
 	 * The original osd request is of no use to use any more.
-	 * We need a new one that can hold the two ops in a copyup
+	 * We need a new one that can hold the three ops in a copyup
 	 * request.  Allocate the new copyup osd request for the
 	 * original request, and release the old one.
 	 */
@@ -2372,17 +2394,22 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 	osd_req_op_cls_request_data_pages(osd_req, 0, pages, parent_length, 0,
 						false, false);
 
-	/* Then the original write request op */
+	/* Then the hint op */
+
+	osd_req_op_alloc_hint_init(osd_req, 1, rbd_obj_bytes(&rbd_dev->header),
+				   rbd_obj_bytes(&rbd_dev->header));
+
+	/* And the original write request op */
 
 	offset = orig_request->offset;
 	length = orig_request->length;
-	osd_req_op_extent_init(osd_req, 1, CEPH_OSD_OP_WRITE,
+	osd_req_op_extent_init(osd_req, 2, CEPH_OSD_OP_WRITE,
 					offset, length, 0, 0);
 	if (orig_request->type == OBJ_REQUEST_BIO)
-		osd_req_op_extent_osd_data_bio(osd_req, 1,
+		osd_req_op_extent_osd_data_bio(osd_req, 2,
 					orig_request->bio_list, length);
 	else
-		osd_req_op_extent_osd_data_pages(osd_req, 1,
+		osd_req_op_extent_osd_data_pages(osd_req, 2,
 					orig_request->pages, length,
 					offset & ~PAGE_MASK, false, false);
 
@@ -2603,8 +2630,8 @@ static int rbd_img_obj_exists_submit(struct rbd_obj_request *obj_request)
 
 	rbd_assert(obj_request->img_request);
 	rbd_dev = obj_request->img_request->rbd_dev;
-	stat_request->osd_req = rbd_osd_req_create(rbd_dev, false,
-						stat_request);
+	stat_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+						   stat_request);
 	if (!stat_request->osd_req)
 		goto out;
 	stat_request->callback = rbd_img_obj_exists_callback;
@@ -2807,7 +2834,8 @@ static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, obj_request);
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+						  obj_request);
 	if (!obj_request->osd_req)
 		goto out;
 
@@ -2870,7 +2898,8 @@ static int __rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start)
 	if (!obj_request)
 		goto out_cancel;
 
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, obj_request);
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
+						  obj_request);
 	if (!obj_request->osd_req)
 		goto out_cancel;
 
@@ -2978,7 +3007,8 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev,
 	obj_request->pages = pages;
 	obj_request->page_count = page_count;
 
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, obj_request);
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+						  obj_request);
 	if (!obj_request->osd_req)
 		goto out;
 
@@ -3211,7 +3241,8 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	obj_request->pages = pages;
 	obj_request->page_count = page_count;
 
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, obj_request);
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+						  obj_request);
 	if (!obj_request->osd_req)
 		goto out;
 
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 8c44fdd4e1c..834f9f3723f 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -205,6 +205,7 @@ void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
 	ci->fscache = fscache_acquire_cookie(fsc->fscache,
 					     &ceph_fscache_inode_object_def,
 					     ci, true);
+	fscache_check_consistency(ci->fscache);
 done:
 	mutex_unlock(&inode->i_mutex);
 
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index da95f61b7a0..5ac591bd012 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -48,6 +48,12 @@ void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
 void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
 void ceph_queue_revalidate(struct inode *inode);
 
+static inline void ceph_fscache_update_objectsize(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	fscache_attr_changed(ci->fscache);
+}
+
 static inline void ceph_fscache_invalidate(struct inode *inode)
 {
 	fscache_invalidate(ceph_inode(inode)->fscache);
@@ -135,6 +141,10 @@ static inline void ceph_readpage_to_fscache(struct inode *inode,
 {
 }
 
+static inline void ceph_fscache_update_objectsize(struct inode *inode)
+{
+}
+
 static inline void ceph_fscache_invalidate(struct inode *inode)
 {
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 17543383545..2e5e648eb5c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -622,8 +622,10 @@ retry:
 
 	if (flags & CEPH_CAP_FLAG_AUTH) {
 		if (ci->i_auth_cap == NULL ||
-		    ceph_seq_cmp(ci->i_auth_cap->mseq, mseq) < 0)
+		    ceph_seq_cmp(ci->i_auth_cap->mseq, mseq) < 0) {
 			ci->i_auth_cap = cap;
+			cap->mds_wanted = wanted;
+		}
 		ci->i_cap_exporting_issued = 0;
 	} else {
 		WARN_ON(ci->i_auth_cap == cap);
@@ -885,7 +887,10 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
 		cap = rb_entry(p, struct ceph_cap, ci_node);
 		if (!__cap_is_valid(cap))
 			continue;
-		mds_wanted |= cap->mds_wanted;
+		if (cap == ci->i_auth_cap)
+			mds_wanted |= cap->mds_wanted;
+		else
+			mds_wanted |= (cap->mds_wanted & ~CEPH_CAP_ANY_FILE_WR);
 	}
 	return mds_wanted;
 }
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6d59006bfa2..16b54aa31f0 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -93,6 +93,8 @@ static int mdsc_show(struct seq_file *s, void *p)
 		} else if (req->r_path1) {
 			seq_printf(s, " #%llx/%s", req->r_ino1.ino,
 				   req->r_path1);
+		} else {
+			seq_printf(s, " #%llx", req->r_ino1.ino);
 		}
 
 		if (req->r_old_dentry) {
@@ -102,7 +104,8 @@ static int mdsc_show(struct seq_file *s, void *p)
 				path = NULL;
 			spin_lock(&req->r_old_dentry->d_lock);
 			seq_printf(s, " #%llx/%.*s (%s)",
-			   ceph_ino(req->r_old_dentry_dir),
+				   req->r_old_dentry_dir ?
+				   ceph_ino(req->r_old_dentry_dir) : 0,
 				   req->r_old_dentry->d_name.len,
 				   req->r_old_dentry->d_name.name,
 				   path ? path : "");
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 45eda6d7a40..766410a12c2 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -119,7 +119,8 @@ static int fpos_cmp(loff_t l, loff_t r)
  * defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
  * the MDS if/when the directory is modified).
  */
-static int __dcache_readdir(struct file *file, struct dir_context *ctx)
+static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
+			    u32 shared_gen)
 {
 	struct ceph_file_info *fi = file->private_data;
 	struct dentry *parent = file->f_dentry;
@@ -133,8 +134,8 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx)
 	last = fi->dentry;
 	fi->dentry = NULL;
 
-	dout("__dcache_readdir %p at %llu (last %p)\n", dir, ctx->pos,
-	     last);
+	dout("__dcache_readdir %p v%u at %llu (last %p)\n",
+	     dir, shared_gen, ctx->pos, last);
 
 	spin_lock(&parent->d_lock);
 
@@ -161,7 +162,8 @@ more:
 			goto out_unlock;
 		}
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-		if (!d_unhashed(dentry) && dentry->d_inode &&
+		if (di->lease_shared_gen == shared_gen &&
+		    !d_unhashed(dentry) && dentry->d_inode &&
 		    ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
 		    ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
 		    fpos_cmp(ctx->pos, di->offset) <= 0)
@@ -190,7 +192,7 @@ more:
 		if (last) {
 			/* remember our position */
 			fi->dentry = last;
-			fi->next_offset = di->offset;
+			fi->next_offset = fpos_off(di->offset);
 		}
 		dput(dentry);
 		return 0;
@@ -252,8 +254,6 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	int err;
 	u32 ftype;
 	struct ceph_mds_reply_info_parsed *rinfo;
-	const int max_entries = fsc->mount_options->max_readdir;
-	const int max_bytes = fsc->mount_options->max_readdir_bytes;
 
 	dout("readdir %p file %p frag %u off %u\n", inode, file, frag, off);
 	if (fi->flags & CEPH_F_ATEND)
@@ -291,8 +291,9 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	    ceph_snap(inode) != CEPH_SNAPDIR &&
 	    __ceph_dir_is_complete(ci) &&
 	    __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
+		u32 shared_gen = ci->i_shared_gen;
 		spin_unlock(&ci->i_ceph_lock);
-		err = __dcache_readdir(file, ctx);
+		err = __dcache_readdir(file, ctx, shared_gen);
 		if (err != -EAGAIN)
 			return err;
 	} else {
@@ -322,14 +323,16 @@ more:
 			fi->last_readdir = NULL;
 		}
 
-		/* requery frag tree, as the frag topology may have changed */
-		frag = ceph_choose_frag(ceph_inode(inode), frag, NULL, NULL);
-
 		dout("readdir fetching %llx.%llx frag %x offset '%s'\n",
 		     ceph_vinop(inode), frag, fi->last_name);
 		req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 		if (IS_ERR(req))
 			return PTR_ERR(req);
+		err = ceph_alloc_readdir_reply_buffer(req, inode);
+		if (err) {
+			ceph_mdsc_put_request(req);
+			return err;
+		}
 		req->r_inode = inode;
 		ihold(inode);
 		req->r_dentry = dget(file->f_dentry);
@@ -340,9 +343,6 @@ more:
 		req->r_path2 = kstrdup(fi->last_name, GFP_NOFS);
 		req->r_readdir_offset = fi->next_offset;
 		req->r_args.readdir.frag = cpu_to_le32(frag);
-		req->r_args.readdir.max_entries = cpu_to_le32(max_entries);
-		req->r_args.readdir.max_bytes = cpu_to_le32(max_bytes);
-		req->r_num_caps = max_entries + 1;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 		if (err < 0) {
 			ceph_mdsc_put_request(req);
@@ -369,9 +369,9 @@ more:
 				fi->next_offset = 0;
 			off = fi->next_offset;
 		}
+		fi->frag = frag;
 		fi->offset = fi->next_offset;
 		fi->last_readdir = req;
-		fi->frag = frag;
 
 		if (req->r_reply_info.dir_end) {
 			kfree(fi->last_name);
@@ -454,7 +454,7 @@ more:
 	return 0;
 }
 
-static void reset_readdir(struct ceph_file_info *fi)
+static void reset_readdir(struct ceph_file_info *fi, unsigned frag)
 {
 	if (fi->last_readdir) {
 		ceph_mdsc_put_request(fi->last_readdir);
@@ -462,7 +462,10 @@ static void reset_readdir(struct ceph_file_info *fi)
 	}
 	kfree(fi->last_name);
 	fi->last_name = NULL;
-	fi->next_offset = 2;  /* compensate for . and .. */
+	if (ceph_frag_is_leftmost(frag))
+		fi->next_offset = 2;  /* compensate for . and .. */
+	else
+		fi->next_offset = 0;
 	if (fi->dentry) {
 		dput(fi->dentry);
 		fi->dentry = NULL;
@@ -474,7 +477,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct ceph_file_info *fi = file->private_data;
 	struct inode *inode = file->f_mapping->host;
-	loff_t old_offset = offset;
+	loff_t old_offset = ceph_make_fpos(fi->frag, fi->next_offset);
 	loff_t retval;
 
 	mutex_lock(&inode->i_mutex);
@@ -491,7 +494,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 		goto out;
 	}
 
-	if (offset >= 0 && offset <= inode->i_sb->s_maxbytes) {
+	if (offset >= 0) {
 		if (offset != file->f_pos) {
 			file->f_pos = offset;
 			file->f_version = 0;
@@ -504,14 +507,14 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 		 * seek to new frag, or seek prior to current chunk.
 		 */
 		if (offset == 0 ||
-		    fpos_frag(offset) != fpos_frag(old_offset) ||
+		    fpos_frag(offset) != fi->frag ||
 		    fpos_off(offset) < fi->offset) {
 			dout("dir_llseek dropping %p content\n", file);
-			reset_readdir(fi);
+			reset_readdir(fi, fpos_frag(offset));
 		}
 
 		/* bump dir_release_count if we did a forward seek */
-		if (offset > old_offset)
+		if (fpos_cmp(offset, old_offset) > 0)
 			fi->dir_release_count--;
 	}
 out:
@@ -812,8 +815,7 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	}
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
-	req->r_old_dentry = dget(old_dentry); /* or inode? hrm. */
-	req->r_old_dentry_dir = ceph_get_dentry_parent_inode(old_dentry);
+	req->r_old_dentry = dget(old_dentry);
 	req->r_locked_dir = dir;
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
@@ -911,10 +913,11 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RENAME, USE_AUTH_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	ihold(old_dir);
 	req->r_dentry = dget(new_dentry);
 	req->r_num_caps = 2;
 	req->r_old_dentry = dget(old_dentry);
-	req->r_old_dentry_dir = ceph_get_dentry_parent_inode(old_dentry);
+	req->r_old_dentry_dir = old_dir;
 	req->r_locked_dir = new_dir;
 	req->r_old_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_old_dentry_unless = CEPH_CAP_FILE_EXCL;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 16796be53ca..00d6af6a32e 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -8,23 +8,6 @@
 #include "mds_client.h"
 
 /*
- * NFS export support
- *
- * NFS re-export of a ceph mount is, at present, only semireliable.
- * The basic issue is that the Ceph architectures doesn't lend itself
- * well to generating filehandles that will remain valid forever.
- *
- * So, we do our best.  If you're lucky, your inode will be in the
- * client's cache.  If it's not, and you have a connectable fh, then
- * the MDS server may be able to find it for you.  Otherwise, you get
- * ESTALE.
- *
- * There are ways to this more reliable, but in the non-connectable fh
- * case, we won't every work perfectly, and in the connectable case,
- * some changes are needed on the MDS side to work better.
- */
-
-/*
  * Basic fh
  */
 struct ceph_nfs_fh {
@@ -32,22 +15,12 @@ struct ceph_nfs_fh {
 } __attribute__ ((packed));
 
 /*
- * Larger 'connectable' fh that includes parent ino and name hash.
- * Use this whenever possible, as it works more reliably.
+ * Larger fh that includes parent ino.
  */
 struct ceph_nfs_confh {
 	u64 ino, parent_ino;
-	u32 parent_name_hash;
 } __attribute__ ((packed));
 
-/*
- * The presence of @parent_inode here tells us whether NFS wants a
- * connectable file handle.  However, we want to make a connectionable
- * file handle unconditionally so that the MDS gets as much of a hint
- * as possible.  That means we only use @parent_dentry to indicate
- * whether nfsd wants a connectable fh, and whether we should indicate
- * failure from a too-small @max_len.
- */
 static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 			  struct inode *parent_inode)
 {
@@ -56,54 +29,36 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 	struct ceph_nfs_confh *cfh = (void *)rawfh;
 	int connected_handle_length = sizeof(*cfh)/4;
 	int handle_length = sizeof(*fh)/4;
-	struct dentry *dentry;
-	struct dentry *parent;
 
 	/* don't re-export snaps */
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EINVAL;
 
-	dentry = d_find_alias(inode);
+	if (parent_inode && (*max_len < connected_handle_length)) {
+		*max_len = connected_handle_length;
+		return FILEID_INVALID;
+	} else if (*max_len < handle_length) {
+		*max_len = handle_length;
+		return FILEID_INVALID;
+	}
 
-	/* if we found an alias, generate a connectable fh */
-	if (*max_len >= connected_handle_length && dentry) {
-		dout("encode_fh %p connectable\n", dentry);
-		spin_lock(&dentry->d_lock);
-		parent = dentry->d_parent;
+	if (parent_inode) {
+		dout("encode_fh %llx with parent %llx\n",
+		     ceph_ino(inode), ceph_ino(parent_inode));
 		cfh->ino = ceph_ino(inode);
-		cfh->parent_ino = ceph_ino(parent->d_inode);
-		cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode,
-							 dentry);
+		cfh->parent_ino = ceph_ino(parent_inode);
 		*max_len = connected_handle_length;
-		type = 2;
-		spin_unlock(&dentry->d_lock);
-	} else if (*max_len >= handle_length) {
-		if (parent_inode) {
-			/* nfsd wants connectable */
-			*max_len = connected_handle_length;
-			type = FILEID_INVALID;
-		} else {
-			dout("encode_fh %p\n", dentry);
-			fh->ino = ceph_ino(inode);
-			*max_len = handle_length;
-			type = 1;
-		}
+		type = FILEID_INO32_GEN_PARENT;
 	} else {
+		dout("encode_fh %llx\n", ceph_ino(inode));
+		fh->ino = ceph_ino(inode);
 		*max_len = handle_length;
-		type = FILEID_INVALID;
+		type = FILEID_INO32_GEN;
 	}
-	if (dentry)
-		dput(dentry);
 	return type;
 }
 
-/*
- * convert regular fh to dentry
- *
- * FIXME: we should try harder by querying the mds for the ino.
- */
-static struct dentry *__fh_to_dentry(struct super_block *sb,
-				     struct ceph_nfs_fh *fh, int fh_len)
+static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -111,11 +66,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
-	if (fh_len < sizeof(*fh) / 4)
-		return ERR_PTR(-ESTALE);
-
-	dout("__fh_to_dentry %llx\n", fh->ino);
-	vino.ino = fh->ino;
+	vino.ino = ino;
 	vino.snap = CEPH_NOSNAP;
 	inode = ceph_find_inode(sb, vino);
 	if (!inode) {
@@ -139,139 +90,161 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 
 	dentry = d_obtain_alias(inode);
 	if (IS_ERR(dentry)) {
-		pr_err("fh_to_dentry %llx -- inode %p but ENOMEM\n",
-		       fh->ino, inode);
 		iput(inode);
 		return dentry;
 	}
 	err = ceph_init_dentry(dentry);
 	if (err < 0) {
-		iput(inode);
+		dput(dentry);
 		return ERR_PTR(err);
 	}
-	dout("__fh_to_dentry %llx %p dentry %p\n", fh->ino, inode, dentry);
+	dout("__fh_to_dentry %llx %p dentry %p\n", ino, inode, dentry);
 	return dentry;
 }
 
 /*
- * convert connectable fh to dentry
+ * convert regular fh to dentry
  */
-static struct dentry *__cfh_to_dentry(struct super_block *sb,
-				      struct ceph_nfs_confh *cfh, int fh_len)
+static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
+					struct fid *fid,
+					int fh_len, int fh_type)
+{
+	struct ceph_nfs_fh *fh = (void *)fid->raw;
+
+	if (fh_type != FILEID_INO32_GEN  &&
+	    fh_type != FILEID_INO32_GEN_PARENT)
+		return NULL;
+	if (fh_len < sizeof(*fh) / 4)
+		return NULL;
+
+	dout("fh_to_dentry %llx\n", fh->ino);
+	return __fh_to_dentry(sb, fh->ino);
+}
+
+static struct dentry *__get_parent(struct super_block *sb,
+				   struct dentry *child, u64 ino)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+	struct ceph_mds_request *req;
 	struct inode *inode;
 	struct dentry *dentry;
-	struct ceph_vino vino;
 	int err;
 
-	if (fh_len < sizeof(*cfh) / 4)
-		return ERR_PTR(-ESTALE);
-
-	dout("__cfh_to_dentry %llx (%llx/%x)\n",
-	     cfh->ino, cfh->parent_ino, cfh->parent_name_hash);
-
-	vino.ino = cfh->ino;
-	vino.snap = CEPH_NOSNAP;
-	inode = ceph_find_inode(sb, vino);
-	if (!inode) {
-		struct ceph_mds_request *req;
-
-		req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPHASH,
-					       USE_ANY_MDS);
-		if (IS_ERR(req))
-			return ERR_CAST(req);
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
+				       USE_ANY_MDS);
+	if (IS_ERR(req))
+		return ERR_CAST(req);
 
-		req->r_ino1 = vino;
-		req->r_ino2.ino = cfh->parent_ino;
-		req->r_ino2.snap = CEPH_NOSNAP;
-		req->r_path2 = kmalloc(16, GFP_NOFS);
-		snprintf(req->r_path2, 16, "%d", cfh->parent_name_hash);
-		req->r_num_caps = 1;
-		err = ceph_mdsc_do_request(mdsc, NULL, req);
-		inode = req->r_target_inode;
-		if (inode)
-			ihold(inode);
-		ceph_mdsc_put_request(req);
-		if (!inode)
-			return ERR_PTR(err ? err : -ESTALE);
+	if (child) {
+		req->r_inode = child->d_inode;
+		ihold(child->d_inode);
+	} else {
+		req->r_ino1 = (struct ceph_vino) {
+			.ino = ino,
+			.snap = CEPH_NOSNAP,
+		};
 	}
+	req->r_num_caps = 1;
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+	inode = req->r_target_inode;
+	if (inode)
+		ihold(inode);
+	ceph_mdsc_put_request(req);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
 
 	dentry = d_obtain_alias(inode);
 	if (IS_ERR(dentry)) {
-		pr_err("cfh_to_dentry %llx -- inode %p but ENOMEM\n",
-		       cfh->ino, inode);
 		iput(inode);
 		return dentry;
 	}
 	err = ceph_init_dentry(dentry);
 	if (err < 0) {
-		iput(inode);
+		dput(dentry);
 		return ERR_PTR(err);
 	}
-	dout("__cfh_to_dentry %llx %p dentry %p\n", cfh->ino, inode, dentry);
+	dout("__get_parent ino %llx parent %p ino %llx.%llx\n",
+	     child ? ceph_ino(child->d_inode) : ino,
+	     dentry, ceph_vinop(inode));
 	return dentry;
 }
 
-static struct dentry *ceph_fh_to_dentry(struct super_block *sb, struct fid *fid,
-					int fh_len, int fh_type)
+struct dentry *ceph_get_parent(struct dentry *child)
 {
-	if (fh_type == 1)
-		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw,
-								fh_len);
-	else
-		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw,
-								fh_len);
+	/* don't re-export snaps */
+	if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
+		return ERR_PTR(-EINVAL);
+
+	dout("get_parent %p ino %llx.%llx\n",
+	     child, ceph_vinop(child->d_inode));
+	return __get_parent(child->d_sb, child, 0);
 }
 
 /*
- * get parent, if possible.
- *
- * FIXME: we could do better by querying the mds to discover the
- * parent.
+ * convert regular fh to parent
  */
 static struct dentry *ceph_fh_to_parent(struct super_block *sb,
-					 struct fid *fid,
+					struct fid *fid,
 					int fh_len, int fh_type)
 {
 	struct ceph_nfs_confh *cfh = (void *)fid->raw;
-	struct ceph_vino vino;
-	struct inode *inode;
 	struct dentry *dentry;
-	int err;
 
-	if (fh_type == 1)
-		return ERR_PTR(-ESTALE);
+	if (fh_type != FILEID_INO32_GEN_PARENT)
+		return NULL;
 	if (fh_len < sizeof(*cfh) / 4)
-		return ERR_PTR(-ESTALE);
+		return NULL;