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
  ...

16 files changed, 407 insertions, 279 deletions

diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 8c44fdd4e1c3..834f9f3723fb 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 da95f61b7a09..5ac591bd012b 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 17543383545c..2e5e648eb5c3 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 6d59006bfa27..16b54aa31f08 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 45eda6d7a40c..766410a12c2c 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 16796be53ca5..00d6af6a32ec 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;
 
-	pr_debug("fh_to_parent %llx/%d\n", cfh->parent_ino,
-		 cfh->parent_name_hash);
+	dout("fh_to_parent %llx\n", cfh->parent_ino);
+	dentry = __get_parent(sb, NULL, cfh->ino);
+	if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT)
+		dentry = __fh_to_dentry(sb, cfh->parent_ino);
+	return dentry;
+}
 
-	vino.ino = cfh->ino;
-	vino.snap = CEPH_NOSNAP;
-	inode = ceph_find_inode(sb, vino);
-	if (!inode)
-		return ERR_PTR(-ESTALE);
+static int ceph_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct ceph_mds_client *mdsc;
+	struct ceph_mds_request *req;
+	int err;
 
-	dentry = d_obtain_alias(inode);
-	if (IS_ERR(dentry)) {
-		pr_err("fh_to_parent %llx -- inode %p but ENOMEM\n",
-		       cfh->ino, inode);
-		iput(inode);
-		return dentry;
-	}
-	err = ceph_init_dentry(dentry);
-	if (err < 0) {
-		iput(inode);
-		return ERR_PTR(err);
+	mdsc = ceph_inode_to_client(child->d_inode)->mdsc;
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
+				       USE_ANY_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	mutex_lock(&parent->d_inode->i_mutex);
+
+	req->r_inode = child->d_inode;
+	ihold(child->d_inode);
+	req->r_ino2 = ceph_vino(parent->d_inode);
+	req->r_locked_dir = parent->d_inode;
+	req->r_num_caps = 2;
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+
+	mutex_unlock(&parent->d_inode->i_mutex);
+
+	if (!err) {
+		struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+		memcpy(name, rinfo->dname, rinfo->dname_len);
+		name[rinfo->dname_len] = 0;
+		dout("get_name %p ino %llx.%llx name %s\n",
+		     child, ceph_vinop(child->d_inode), name);
+	} else {
+		dout("get_name %p ino %llx.%llx err %d\n",
+		     child, ceph_vinop(child->d_inode), err);
 	}
-	dout("fh_to_parent %llx %p dentry %p\n", cfh->ino, inode, dentry);
-	return dentry;
+
+	ceph_mdsc_put_request(req);
+	return err;
 }
 
 const struct export_operations ceph_export_ops = {
 	.encode_fh = ceph_encode_fh,
 	.fh_to_dentry = ceph_fh_to_dentry,
 	.fh_to_parent = ceph_fh_to_parent,
+	.get_parent = ceph_get_parent,
+	.get_name = ceph_get_name,
 };
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 09c7afe32e49..66075a4ad979 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -210,7 +210,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	ihold(inode);
 
 	req->r_num_caps = 1;
-	if (flags & (O_CREAT|O_TRUNC))
+	if (flags & O_CREAT)
 		parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
 	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
 	iput(parent_inode);
@@ -291,8 +291,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		}
 		err = finish_open(file, dentry, ceph_open, opened);
 	}
-
 out_err:
+	if (!req->r_err && req->r_target_inode)
+		ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
 	ceph_mdsc_put_request(req);
 	dout("atomic_open result=%d\n", err);
 	return err;
@@ -970,6 +971,7 @@ retry_snap:
 			goto retry_snap;
 		}
 	} else {
+		loff_t old_size = inode->i_size;
 		/*
 		 * No need to acquire the i_truncate_mutex. Because
 		 * the MDS revokes Fwb caps before sending truncate
@@ -980,6 +982,8 @@ retry_snap:
 		written = generic_file_buffered_write(iocb, iov, nr_segs,
 						      pos, &iocb->ki_pos,
 						      count, 0);
+		if (inode->i_size > old_size)
+			ceph_fscache_update_objectsize(inode);
 		mutex_unlock(&inode->i_mutex);
 	}
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 32d519d8a2e2..0b0728e5be2d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -659,14 +659,6 @@ static int fill_inode(struct inode *inode,
 			    le32_to_cpu(info->time_warp_seq),
 			    &ctime, &mtime, &atime);
 
-	/* only update max_size on auth cap */
-	if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
-	    ci->i_max_size != le64_to_cpu(info->max_size)) {
-		dout("max_size %lld -> %llu\n", ci->i_max_size,
-		     le64_to_cpu(info->max_size));
-		ci->i_max_size = le64_to_cpu(info->max_size);
-	}
-
 	ci->i_layout = info->layout;
 	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
 
@@ -755,6 +747,14 @@ static int fill_inode(struct inode *inode,
 		ci->i_max_offset = 2;
 	}
 no_change:
+	/* only update max_size on auth cap */
+	if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+	    ci->i_max_size != le64_to_cpu(info->max_size)) {
+		dout("max_size %lld -> %llu\n", ci->i_max_size,
+		     le64_to_cpu(info->max_size));
+		ci->i_max_size = le64_to_cpu(info->max_size);
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
 	/* queue truncate if we saw i_size decrease */
@@ -1044,10 +1044,59 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 					 session, req->r_request_started, -1,
 					 &req->r_caps_reservation);
 			if (err < 0)
-				return err;
+				goto done;
 		} else {
 			WARN_ON_ONCE(1);
 		}
+
+		if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME) {
+			struct qstr dname;
+			struct dentry *dn, *parent;
+
+			BUG_ON(!rinfo->head->is_target);
+			BUG_ON(req->r_dentry);
+
+			parent = d_find_any_alias(dir);
+			BUG_ON(!parent);
+
+			dname.name = rinfo->dname;
+			dname.len = rinfo->dname_len;
+			dname.hash = full_name_hash(dname.name, dname.len);
+			vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+			vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+retry_lookup:
+			dn = d_lookup(parent, &dname);
+			dout("d_lookup on parent=%p name=%.*s got %p\n",
+			     parent, dname.len, dname.name, dn);
+
+			if (!dn) {
+				dn = d_alloc(parent, &dname);
+				dout("d_alloc %p '%.*s' = %p\n", parent,
+				     dname.len, dname.name, dn);
+				if (dn == NULL) {
+					dput(parent);
+					err = -ENOMEM;
+					goto done;
+				}
+				err = ceph_init_dentry(dn);
+				if (err < 0) {
+					dput(dn);
+					dput(parent);
+					goto done;
+				}
+			} else if (dn->d_inode &&
+				   (ceph_ino(dn->d_inode) != vino.ino ||
+				    ceph_snap(dn->d_inode) != vino.snap)) {
+				dout(" dn %p points to wrong inode %p\n",
+				     dn, dn->d_inode);
+				d_delete(dn);
+				dput(dn);
+				goto retry_lookup;
+			}
+
+			req->r_dentry = dn;
+			dput(parent);
+		}
 	}
 
 	if (rinfo->head->is_target) {
@@ -1063,7 +1112,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 
 		err = fill_inode(in, &rinfo->targeti, NULL,
 				session, req->r_request_started,
-				(le32_to_cpu(rinfo->head->result) == 0) ?
+				(!req->r_aborted && rinfo->head->result == 0) ?
 				req->r_fmode : -1,
 				&req->r_caps_reservation);
 		if (err < 0) {
@@ -1616,8 +1665,6 @@ static const struct inode_operations ceph_symlink_iops = {
 	.getxattr = ceph_getxattr,
 	.listxattr = ceph_listxattr,
 	.removexattr = ceph_removexattr,
-	.get_acl = ceph_get_acl,
-	.set_acl = ceph_set_acl,
 };
 
 /*
@@ -1627,7 +1674,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct inode *parent_inode;
 	const unsigned int ia_valid = attr->ia_valid;
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
@@ -1819,9 +1865,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 		req->r_inode_drop = release;
 		req->r_args.setattr.mask = cpu_to_le32(mask);
 		req->r_num_caps = 1;
-		parent_inode = ceph_get_dentry_parent_inode(dentry);
-		err = ceph_mdsc_do_request(mdsc, parent_inode, req);
-		iput(parent_inode);
+		err = ceph_mdsc_do_request(mdsc, NULL, req);
 	}
 	dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
 	     ceph_cap_string(dirtied), mask);
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index dc66c9e023e4..efbe08289292 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -64,7 +64,6 @@ static long __validate_layout(struct ceph_mds_client *mdsc,
 static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct inode *parent_inode;
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_ioctl_layout l;
@@ -121,9 +120,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 		cpu_to_le32(l.object_size);
 	req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
 
-	parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
-	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
-	iput(parent_inode);
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	ceph_mdsc_put_request(req);
 	return err;
 }
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ae6d14e82b0f..d94ba0df9f4d 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -2,11 +2,31 @@
 
 #include <linux/file.h>
 #include <linux/namei.h>
+#include <linux/random.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include <linux/ceph/pagelist.h>
 
+static u64 lock_secret;
+
+static inline u64 secure_addr(void *addr)
+{
+	u64 v = lock_secret ^ (u64)(unsigned long)addr;
+	/*
+	 * Set the most significant bit, so that MDS knows the 'owner'
+	 * is sufficient to identify the owner of lock. (old code uses
+	 * both 'owner' and 'pid')
+	 */
+	v |= (1ULL << 63);
+	return v;
+}
+
+void __init ceph_flock_init(void)
+{
+	get_random_bytes(&lock_secret, sizeof(lock_secret));
+}
+
 /**
  * Implement fcntl and flock locking functions.
  */
@@ -14,11 +34,11 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 			     int cmd, u8 wait, struct file_lock *fl)
 {
 	struct inode *inode = file_inode(file);
-	struct ceph_mds_client *mdsc =
-		ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 	u64 length = 0;
+	u64 owner;
 
 	req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
 	if (IS_ERR(req))
@@ -32,25 +52,27 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	else
 		length = fl->fl_end - fl->fl_start + 1;
 
-	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
-	     "length: %llu, wait: %d, type: %d", (int)lock_type,
-	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
-	     length, wait, fl->fl_type);
+	if (lock_type == CEPH_LOCK_FCNTL)
+		owner = secure_addr(fl->fl_owner);
+	else
+		owner = secure_addr(fl->fl_file);
+
+	dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
+	     "start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
+	     (int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
+	     wait, fl->fl_type);
 
 	req->r_args.filelock_change.rule = lock_type;
 	req->r_args.filelock_change.type = cmd;
+	req->r_args.filelock_change.owner = cpu_to_le64(owner);
 	req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
-	/* This should be adjusted, but I'm not sure if
-	   namespaces actually get id numbers*/
-	req->r_args.filelock_change.pid_namespace =
-		cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
 	req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
 	req->r_args.filelock_change.length = cpu_to_le64(length);
 	req->r_args.filelock_change.wait = wait;
 
 	err = ceph_mdsc_do_request(mdsc, inode, req);
 
-	if ( operation == CEPH_MDS_OP_GETFILELOCK){
+	if (operation == CEPH_MDS_OP_GETFILELOCK) {
 		fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
 		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
 			fl->fl_type = F_RDLCK;
@@ -87,14 +109,19 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	u8 wait = 0;
 	u16 op = CEPH_MDS_OP_SETFILELOCK;
 
-	fl->fl_nspid = get_pid(task_tgid(current));
-	dout("ceph_lock, fl_pid:%d", fl->fl_pid);
+	if (!(fl->fl_flags & FL_POSIX))
+		return -ENOLCK;
+	/* No mandatory locks */
+	if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
+		return -ENOLCK;
+
+	dout("ceph_lock, fl_owner: %p", fl->fl_owner);
 
 	/* set wait bit as appropriate, then make command as Ceph expects it*/
-	if (F_SETLKW == cmd)
-		wait = 1;
-	if (F_GETLK == cmd)
+	if (IS_GETLK(cmd))
 		op = CEPH_MDS_OP_GETFILELOCK;
+	else if (IS_SETLKW(cmd))
+		wait = 1;
 
 	if (F_RDLCK == fl->fl_type)
 		lock_cmd = CEPH_LOCK_SHARED;
@@ -105,7 +132,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
 	if (!err) {
-		if ( op != CEPH_MDS_OP_GETFILELOCK ){
+		if (op != CEPH_MDS_OP_GETFILELOCK) {
 			dout("mds locked, locking locally");
 			err = posix_lock_file(file, fl, NULL);
 			if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
@@ -131,20 +158,22 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 {
 	u8 lock_cmd;
 	int err;
-	u8 wait = 1;
-
-	fl->fl_nspid = get_pid(task_tgid(current));
-	dout("ceph_flock, fl_pid:%d", fl->fl_pid);
-
-	/* set wait bit, then clear it out of cmd*/
-	if (cmd & LOCK_NB)
-		wait = 0;
-	cmd = cmd & (LOCK_SH | LOCK_EX | LOCK_UN);
-	/* set command sequence that Ceph wants to see:
-	   shared lock, exclusive lock, or unlock */
-	if (LOCK_SH == cmd)
+	u8 wait = 0;
+
+	if (!(fl->fl_flags & FL_FLOCK))
+		return -ENOLCK;
+	/* No mandatory locks */
+	if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
+		return -ENOLCK;
+
+	dout("ceph_flock, fl_file: %p", fl->fl_file);
+
+	if (IS_SETLKW(cmd))
+		wait = 1;
+
+	if (F_RDLCK == fl->fl_type)
 		lock_cmd = CEPH_LOCK_SHARED;
-	else if (LOCK_EX == cmd)
+	else if (F_WRLCK == fl->fl_type)
 		lock_cmd = CEPH_LOCK_EXCL;
 	else
 		lock_cmd = CEPH_LOCK_UNLOCK;
@@ -280,13 +309,14 @@ int lock_to_ceph_filelock(struct file_lock *lock,
 			  struct ceph_filelock *cephlock)
 {
 	int err = 0;
-
 	cephlock->start = cpu_to_le64(lock->fl_start);
 	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
 	cephlock->client = cpu_to_le64(0);
-	cephlock->pid = cpu_to_le64(lock->fl_pid);
-	cephlock->pid_namespace =
-	        cpu_to_le64((u64)(unsigned long)lock->fl_nspid);
+	cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
+	if (lock->fl_flags & FL_POSIX)
+		cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
+	else
+		cephlock->owner = cpu_to_le64(secure_addr(lock->fl_file));
 
 	switch (lock->fl_type) {
 	case F_RDLCK:
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f4f050a69a48..2b4d093d0563 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
+#include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -165,21 +166,18 @@ static int parse_reply_info_dir(void **p, void *end,
 	if (num == 0)
 		goto done;
 
-	/* alloc large array */
-	info->dir_nr = num;
-	info->dir_in = kcalloc(num, sizeof(*info->dir_in) +
-			       sizeof(*info->dir_dname) +
-			       sizeof(*info->dir_dname_len) +
-			       sizeof(*info->dir_dlease),
-			       GFP_NOFS);
-	if (info->dir_in == NULL) {
-		err = -ENOMEM;
-		goto out_bad;
-	}
+	BUG_ON(!info->dir_in);
 	info->dir_dname = (void *)(info->dir_in + num);
 	info->dir_dname_len = (void *)(info->dir_dname + num);
 	info->dir_dlease = (void *)(info->dir_dname_len + num);
+	if ((unsigned long)(info->dir_dlease + num) >
+	    (unsigned long)info->dir_in + info->dir_buf_size) {
+		pr_err("dir contents are larger than expected\n");
+		WARN_ON(1);
+		goto bad;
+	}
 
+	info->dir_nr = num;
 	while (num) {
 		/* dentry */
 		ceph_decode_need(p, end, sizeof(u32)*2, bad);
@@ -327,7 +325,9 @@ out_bad:
 
 static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
 {
-	kfree(info->dir_in);
+	if (!info->dir_in)
+		return;
+	free_pages((unsigned long)info->dir_in, get_order(info->dir_buf_size));
 }
 
 
@@ -512,12 +512,11 @@ void ceph_mdsc_release_request(struct kref *kref)
 	struct ceph_mds_request *req = container_of(kref,
 						    struct ceph_mds_request,
 						    r_kref);
+	destroy_reply_info(&req->r_reply_info);
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
-	if (req->r_reply) {
+	if (req->r_reply)
 		ceph_msg_put(req->r_reply);
-		destroy_reply_info(&req->r_reply_info);
-	}
 	if (req->r_inode) {
 		ceph_put_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
 		iput(req->r_inode);
@@ -528,7 +527,9 @@ void ceph_mdsc_release_request(struct kref *kref)
 		iput(req->r_target_inode);
 	if (req->r_dentry)
 		dput(req->r_dentry);
-	if (req->r_old_dentry) {
+	if (req->r_old_dentry)
+		dput(req->r_old_dentry);
+	if (req->r_old_dentry_dir) {
 		/*
 		 * track (and drop pins for) r_old_dentry_dir
 		 * separately, since r_old_dentry's d_parent may have
@@ -537,7 +538,6 @@ void ceph_mdsc_release_request(struct kref *kref)
 		 */
 		ceph_put_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
-		dput(req->r_old_dentry);
 		iput(req->r_old_dentry_dir);
 	}
 	kfree(req->r_path1);
@@ -1311,6 +1311,9 @@ static int trim_caps(struct ceph_mds_client *mdsc,
 			trim_caps - session->s_trim_caps);
 		session->s_trim_caps = 0;
 	}
+
+	ceph_add_cap_releases(mdsc, session);
+	ceph_send_cap_releases(mdsc, session);
 	return 0;
 }
 
@@ -1461,15 +1464,18 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
 
 	dout("discard_cap_releases mds%d\n", session->s_mds);
 
-	/* zero out the in-progress message */
-	msg = list_first_entry(&session->s_cap_releases,
-			       struct ceph_msg, list_head);
-	head = msg->front.iov_base;
-	num = le32_to_cpu(head->num);
-	dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg, num);
-	head->num = cpu_to_le32(0);
-	msg->front.iov_len = sizeof(*head);
-	session->s_num_cap_releases += num;
+	if (!list_empty(&session->s_cap_releases)) {
+		/* zero out the in-progress message */
+		msg = list_first_entry(&session->s_cap_releases,
+					struct ceph_msg, list_head);
+		head = msg->front.iov_base;
+		num = le32_to_cpu(head->num);
+		dout("discard_cap_releases mds%d %p %u\n",
+		     session->s_mds, msg, num);
+		head->num = cpu_to_le32(0);
+		msg->front.iov_len = sizeof(*head);
+		session->s_num_cap_releases += num;
+	}
 
 	/* requeue completed messages */
 	while (!list_empty(&session->s_cap_releases_done)) {
@@ -1492,6 +1498,43 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
  * requests
  */
 
+int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
+				    struct inode *dir)
+{
+	struct ceph_inode_info *ci = ceph_inode(dir);
+	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+	struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options;
+	size_t size = sizeof(*rinfo->dir_in) + sizeof(*rinfo->dir_dname_len) +
+		      sizeof(*rinfo->dir_dname) + sizeof(*rinfo->dir_dlease);
+	int order, num_entries;
+
+	spin_lock(&ci->i_ceph_lock);
+	num_entries = ci->i_files + ci->i_subdirs;
+	spin_unlock(&ci->i_ceph_lock);
+	num_entries = max(num_entries, 1);
+	num_entries = min(num_entries, opt->max_readdir);
+
+	order = get_order(size * num_entries);
+	while (order >= 0) {
+		rinfo->dir_in = (void*)__get_free_pages(GFP_NOFS | __GFP_NOWARN,
+							order);
+		if (rinfo->dir_in)
+			break;
+		order--;
+	}
+	if (!rinfo->dir_in)
+		return -ENOMEM;
+
+	num_entries = (PAGE_SIZE << order) / size;
+	num_entries = min(num_entries, opt->max_readdir);
+
+	rinfo->dir_buf_size = PAGE_SIZE << order;
+	req->r_num_caps = num_entries + 1;
+	req->r_args.readdir.max_entries = cpu_to_le32(num_entries);
+	req->r_args.readdir.max_bytes = cpu_to_le32(opt->max_readdir_bytes);
+	return 0;
+}
+
 /*
  * Create an mds request.
  */
@@ -2053,7 +2096,7 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 		ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
 	if (req->r_locked_dir)
 		ceph_get_cap_refs(ceph_inode(req->r_locked_dir), CEPH_CAP_PIN);
-	if (req->r_old_dentry)
+	if (req->r_old_dentry_dir)
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 68288917c737..e90cfccf93bd 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -67,6 +67,7 @@ struct ceph_mds_reply_info_parsed {
 		/* for readdir results */
 		struct {
 			struct ceph_mds_reply_dirfrag *dir_dir;
+			size_t			      dir_buf_size;
 			int                           dir_nr;
 			char                          **dir_dname;
 			u32                           *dir_dname_len;
@@ -346,7 +347,8 @@ extern void ceph_mdsc_lease_release(struct ceph_mds_client *mdsc,
 				    struct dentry *dn);
 
 extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
-
+extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
+					   struct inode *dir);
 extern struct ceph_mds_request *
 ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
 extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index 4440f447fd3f..51cc23e48111 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -54,6 +54,7 @@ const char *ceph_mds_op_name(int op)
 	case CEPH_MDS_OP_LOOKUPHASH:  return "lookuphash";
 	case CEPH_MDS_OP_LOOKUPPARENT:  return "lookupparent";
 	case CEPH_MDS_OP_LOOKUPINO:  return "lookupino";
+	case CEPH_MDS_OP_LOOKUPNAME:  return "lookupname";
 	case CEPH_MDS_OP_GETATTR:  return "getattr";
 	case CEPH_MDS_OP_SETXATTR: return "setxattr";
 	case CEPH_MDS_OP_SETATTR: return "setattr";
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 10a4ccbf38da..06150fd745ac 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1026,6 +1026,7 @@ static int __init init_ceph(void)
 	if (ret)
 		goto out;
 
+	ceph_flock_init();
 	ceph_xattr_init();
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d8801a95b685..7866cd05a6bb 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -577,7 +577,7 @@ struct ceph_file_info {
 
 	/* readdir: position within a frag */
 	unsigned offset;       /* offset of last chunk, adjusted for . and .. */
-	u64 next_offset;       /* offset of next chunk (last_name's + 1) */
+	unsigned next_offset;  /* offset of next chunk (last_name's + 1) */
 	char *last_name;       /* last entry in previous chunk */
 	struct dentry *dentry; /* next dentry (for dcache readdir) */
 	int dir_release_count;
@@ -871,6 +871,7 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 extern const struct export_operations ceph_export_ops;
 
 /* locks.c */
+extern __init void ceph_flock_init(void);
 extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
 extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
 extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index a55ec37378c6..c9c2b887381e 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -64,32 +64,48 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
 }
 
 static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
-					size_t size)
+				   size_t size)
 {
 	int ret;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
 	const char *pool_name;
+	char buf[128];
 
 	dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
 	down_read(&osdc->map_sem);
 	pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
-	if (pool_name)
-		ret = snprintf(val, size,
-		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%s",
+	if (pool_name) {
+		size_t len = strlen(pool_name);
+		ret = snprintf(buf, sizeof(buf),
+		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=",
 		(unsigned long long)ceph_file_layout_su(ci->i_layout),
 		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
-	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
-		pool_name);
-	else
-		ret = snprintf(val, size,
+	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
+		if (!size) {
+			ret += len;
+		} else if (ret + len > size) {
+			ret = -ERANGE;
+		} else {
+			memcpy(val, buf, ret);
+			memcpy(val + ret, pool_name, len);
+			ret += len;
+		}
+	} else {
+		ret = snprintf(buf, sizeof(buf),
 		"stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%lld",
 		(unsigned long long)ceph_file_layout_su(ci->i_layout),
 		(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
 	        (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
 		(unsigned long long)pool);
-
+		if (size) {
+			if (ret <= size)
+				memcpy(val, buf, ret);
+			else
+				ret = -ERANGE;
+		}
+	}
 	up_read(&osdc->map_sem);
 	return ret;
 }
@@ -215,7 +231,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
 		.name_size = sizeof("ceph.dir.layout"),
 		.getxattr_cb = ceph_vxattrcb_layout,
 		.readonly = false,
-		.hidden = false,
+		.hidden = true,
 		.exists_cb = ceph_vxattrcb_layout_exists,
 	},
 	XATTR_LAYOUT_FIELD(dir, layout, stripe_unit),
@@ -242,7 +258,7 @@ static struct ceph_vxattr ceph_file_vxattrs[] = {
 		.name_size = sizeof("ceph.file.layout"),
 		.getxattr_cb = ceph_vxattrcb_layout,
 		.readonly = false,
-		.hidden = false,
+		.hidden = true,
 		.exists_cb = ceph_vxattrcb_layout_exists,
 	},
 	XATTR_LAYOUT_FIELD(file, layout, stripe_unit),
@@ -842,7 +858,6 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct inode *parent_inode;
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int err;
@@ -893,9 +908,7 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 	req->r_data_len = size;
 
 	dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
-	parent_inode = ceph_get_dentry_parent_inode(dentry);
-	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
-	iput(parent_inode);
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	ceph_mdsc_put_request(req);
 	dout("xattr.ver (after): %lld\n", ci->i_xattrs.version);
 
@@ -1019,7 +1032,6 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = dentry->d_inode;
-	struct inode *parent_inode;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -1033,9 +1045,7 @@ static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 	req->r_num_caps = 1;
 	req->r_path2 = kstrdup(name, GFP_NOFS);
 
-	parent_inode = ceph_get_dentry_parent_inode(dentry);
-	err = ceph_mdsc_do_request(mdsc, parent_inode, req);
-	iput(parent_inode);
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	ceph_mdsc_put_request(req);
 	return err;
 }