Merge branch 'sh/stable-updates'

Conflicts:
	arch/sh/kernel/dwarf.c
	drivers/dma/shdma.c

Signed-off-by: Paul Mundt <lethal@linux-sh.org>

23 files changed, 236 insertions, 135 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index ce8ef6107727..412593703d1e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>	/* generic_writepages */
+#include <linux/slab.h>
 #include <linux/pagevec.h>
 #include <linux/task_io_accounting_ops.h>
 
@@ -336,16 +337,15 @@ out:
 /*
  * Get ref for the oldest snapc for an inode with dirty data... that is, the
  * only snap context we are allowed to write back.
- *
- * Caller holds i_lock.
  */
-static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
-						      u64 *snap_size)
+static struct ceph_snap_context *get_oldest_context(struct inode *inode,
+						    u64 *snap_size)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc = NULL;
 	struct ceph_cap_snap *capsnap = NULL;
 
+	spin_lock(&inode->i_lock);
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
 		     capsnap->context, capsnap->dirty_pages);
@@ -356,21 +356,11 @@ static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
 			break;
 		}
 	}
-	if (!snapc && ci->i_snap_realm) {
-		snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
+	if (!snapc && ci->i_head_snapc) {
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
 		dout(" head snapc %p has %d dirty pages\n",
 		     snapc, ci->i_wrbuffer_ref_head);
 	}
-	return snapc;
-}
-
-static struct ceph_snap_context *get_oldest_context(struct inode *inode,
-						    u64 *snap_size)
-{
-	struct ceph_snap_context *snapc = NULL;
-
-	spin_lock(&inode->i_lock);
-	snapc = __get_oldest_context(inode, snap_size);
 	spin_unlock(&inode->i_lock);
 	return snapc;
 }
@@ -391,7 +381,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	int len = PAGE_CACHE_SIZE;
 	loff_t i_size;
 	int err = 0;
-	struct ceph_snap_context *snapc;
+	struct ceph_snap_context *snapc, *oldest;
 	u64 snap_size = 0;
 	long writeback_stat;
 
@@ -412,13 +402,16 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 		dout("writepage %p page %p not dirty?\n", inode, page);
 		goto out;
 	}
-	if (snapc != get_oldest_context(inode, &snap_size)) {
+	oldest = get_oldest_context(inode, &snap_size);
+	if (snapc->seq > oldest->seq) {
 		dout("writepage %p page %p snapc %p not writeable - noop\n",
 		     inode, page, (void *)page->private);
 		/* we should only noop if called by kswapd */
 		WARN_ON((current->flags & PF_MEMALLOC) == 0);
+		ceph_put_snap_context(oldest);
 		goto out;
 	}
+	ceph_put_snap_context(oldest);
 
 	/* is this a partial page at end of file? */
 	if (snap_size)
@@ -457,7 +450,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	ClearPagePrivate(page);
 	end_page_writeback(page);
 	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
-	ceph_put_snap_context(snapc);
+	ceph_put_snap_context(snapc);  /* page's reference */
 out:
 	return err;
 }
@@ -557,9 +550,9 @@ static void writepages_finish(struct ceph_osd_request *req,
 			dout("inode %p skipping page %p\n", inode, page);
 			wbc->pages_skipped++;
 		}
+		ceph_put_snap_context((void *)page->private);
 		page->private = 0;
 		ClearPagePrivate(page);
-		ceph_put_snap_context(snapc);
 		dout("unlocking %d %p\n", i, page);
 		end_page_writeback(page);
 
@@ -617,7 +610,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	int range_whole = 0;
 	int should_loop = 1;
 	pgoff_t max_pages = 0, max_pages_ever = 0;
-	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL;
+	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
@@ -769,9 +762,10 @@ get_more_pages:
 			}
 
 			/* only if matching snap context */
-			if (snapc != (void *)page->private) {
-				dout("page snapc %p != oldest %p\n",
-				     (void *)page->private, snapc);
+			pgsnapc = (void *)page->private;
+			if (pgsnapc->seq > snapc->seq) {
+				dout("page snapc %p %lld > oldest %p %lld\n",
+				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
 				unlock_page(page);
 				if (!locked_pages)
 					continue; /* keep looking for snap */
@@ -913,7 +907,10 @@ static int context_is_writeable_or_written(struct inode *inode,
 					   struct ceph_snap_context *snapc)
 {
 	struct ceph_snap_context *oldest = get_oldest_context(inode, NULL);
-	return !oldest || snapc->seq <= oldest->seq;
+	int ret = !oldest || snapc->seq <= oldest->seq;
+
+	ceph_put_snap_context(oldest);
+	return ret;
 }
 
 /*
@@ -935,8 +932,8 @@ static int ceph_update_writeable_page(struct file *file,
 	int pos_in_page = pos & ~PAGE_CACHE_MASK;
 	int end_in_page = pos_in_page + len;
 	loff_t i_size;
-	struct ceph_snap_context *snapc;
 	int r;
+	struct ceph_snap_context *snapc, *oldest;
 
 retry_locked:
 	/* writepages currently holds page lock, but if we change that later, */
@@ -946,23 +943,24 @@ retry_locked:
 	BUG_ON(!ci->i_snap_realm);
 	down_read(&mdsc->snap_rwsem);
 	BUG_ON(!ci->i_snap_realm->cached_context);
-	if (page->private &&
-	    (void *)page->private != ci->i_snap_realm->cached_context) {
+	snapc = (void *)page->private;
+	if (snapc && snapc != ci->i_head_snapc) {
 		/*
 		 * this page is already dirty in another (older) snap
 		 * context!  is it writeable now?
 		 */
-		snapc = get_oldest_context(inode, NULL);
+		oldest = get_oldest_context(inode, NULL);
 		up_read(&mdsc->snap_rwsem);
 
-		if (snapc != (void *)page->private) {
+		if (snapc->seq > oldest->seq) {
+			ceph_put_snap_context(oldest);
 			dout(" page %p snapc %p not current or oldest\n",
-			     page, (void *)page->private);
+			     page, snapc);
 			/*
 			 * queue for writeback, and wait for snapc to
 			 * be writeable or written
 			 */
-			snapc = ceph_get_snap_context((void *)page->private);
+			snapc = ceph_get_snap_context(snapc);
 			unlock_page(page);
 			ceph_queue_writeback(inode);
 			r = wait_event_interruptible(ci->i_cap_wq,
@@ -972,6 +970,7 @@ retry_locked:
 				return r;
 			return -EAGAIN;
 		}
+		ceph_put_snap_context(oldest);
 
 		/* yay, writeable, do it now (without dropping page lock) */
 		dout(" page %p snapc %p not current, but oldest\n",
diff --git a/fs/ceph/auth.c b/fs/ceph/auth.c
index abb204fea6c7..f6394b94b866 100644
--- a/fs/ceph/auth.c
+++ b/fs/ceph/auth.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 
 #include "types.h"
diff --git a/fs/ceph/auth_none.c b/fs/ceph/auth_none.c
index b4ef6f0a6c85..8cd9e3af07f7 100644
--- a/fs/ceph/auth_none.c
+++ b/fs/ceph/auth_none.c
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 
 #include "auth_none.h"
 #include "auth.h"
diff --git a/fs/ceph/auth_x.c b/fs/ceph/auth_x.c
index 8d8a84964763..d9001a4dc8cc 100644
--- a/fs/ceph/auth_x.c
+++ b/fs/ceph/auth_x.c
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 
 #include "auth_x.h"
 #include "auth_x_protocol.h"
diff --git a/fs/ceph/buffer.c b/fs/ceph/buffer.c
index b98086c7aeba..c67535d70aa6 100644
--- a/fs/ceph/buffer.c
+++ b/fs/ceph/buffer.c
@@ -1,5 +1,8 @@
 
 #include "ceph_debug.h"
+
+#include <linux/slab.h>
+
 #include "buffer.h"
 #include "decode.h"
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 7d0a0d0adc18..aa2239fa9a3b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
@@ -1204,6 +1205,12 @@ retry:
 		if (capsnap->dirty_pages || capsnap->writing)
 			continue;
 
+		/*
+		 * if cap writeback already occurred, we should have dropped
+		 * the capsnap in ceph_put_wrbuffer_cap_refs.
+		 */
+		BUG_ON(capsnap->dirty == 0);
+
 		/* pick mds, take s_mutex */
 		mds = __ceph_get_cap_mds(ci, &mseq);
 		if (session && session->s_mds != mds) {
@@ -2117,8 +2124,8 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
 		}
 	spin_unlock(&inode->i_lock);
 
-	dout("put_cap_refs %p had %s %s\n", inode, ceph_cap_string(had),
-	     last ? "last" : "");
+	dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
+	     last ? " last" : "", put ? " put" : "");
 
 	if (last && !flushsnaps)
 		ceph_check_caps(ci, 0, NULL);
@@ -2142,7 +2149,8 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 {
 	struct inode *inode = &ci->vfs_inode;
 	int last = 0;
-	int last_snap = 0;
+	int complete_capsnap = 0;
+	int drop_capsnap = 0;
 	int found = 0;
 	struct ceph_cap_snap *capsnap = NULL;
 
@@ -2165,19 +2173,32 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 		list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 			if (capsnap->context == snapc) {
 				found = 1;
-				capsnap->dirty_pages -= nr;
-				last_snap = !capsnap->dirty_pages;
 				break;
 			}
 		}
 		BUG_ON(!found);
+		capsnap->dirty_pages -= nr;
+		if (capsnap->dirty_pages == 0) {
+			complete_capsnap = 1;
+			if (capsnap->dirty == 0)
+				/* cap writeback completed before we created
+				 * the cap_snap; no FLUSHSNAP is needed */
+				drop_capsnap = 1;
+		}
 		dout("put_wrbuffer_cap_refs on %p cap_snap %p "
-		     " snap %lld %d/%d -> %d/%d %s%s\n",
+		     " snap %lld %d/%d -> %d/%d %s%s%s\n",
 		     inode, capsnap, capsnap->context->seq,
 		     ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
 		     ci->i_wrbuffer_ref, capsnap->dirty_pages,
 		     last ? " (wrbuffer last)" : "",
-		     last_snap ? " (capsnap last)" : "");
+		     complete_capsnap ? " (complete capsnap)" : "",
+		     drop_capsnap ? " (drop capsnap)" : "");
+		if (drop_capsnap) {
+			ceph_put_snap_context(capsnap->context);
+			list_del(&capsnap->ci_item);
+			list_del(&capsnap->flushing_item);
+			ceph_put_cap_snap(capsnap);
+		}
 	}
 
 	spin_unlock(&inode->i_lock);
@@ -2185,10 +2206,12 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 	if (last) {
 		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
 		iput(inode);
-	} else if (last_snap) {
+	} else if (complete_capsnap) {
 		ceph_flush_snaps(ci);
 		wake_up(&ci->i_cap_wq);
 	}
+	if (drop_capsnap)
+		iput(inode);
 }
 
 /*
@@ -2464,8 +2487,8 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
 				break;
 			}
 			WARN_ON(capsnap->dirty_pages || capsnap->writing);
-			dout(" removing cap_snap %p follows %lld\n",
-			     capsnap, follows);
+			dout(" removing %p cap_snap %p follows %lld\n",
+			     inode, capsnap, follows);
 			ceph_put_snap_context(capsnap->context);
 			list_del(&capsnap->ci_item);
 			list_del(&capsnap->flushing_item);
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 291ac288e791..f704b3b62424 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -3,6 +3,7 @@
 
 #include <linux/err.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <crypto/hash.h>
 
 #include "crypto.h"
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index e159f1415110..f7048da92acc 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/device.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8a9116e15b70..ea8ee2e526aa 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -3,6 +3,7 @@
 #include <linux/spinlock.h>
 #include <linux/fs_struct.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include "super.h"
@@ -170,11 +171,11 @@ more:
 	spin_lock(&inode->i_lock);
 	spin_lock(&dcache_lock);
 
+	last = dentry;
+
 	if (err < 0)
 		goto out_unlock;
 
-	last = dentry;
-
 	p = p->prev;
 	filp->f_pos++;
 
@@ -311,7 +312,7 @@ more:
 		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_num_caps = max_entries;
+		req->r_num_caps = max_entries + 1;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 		if (err < 0) {
 			ceph_mdsc_put_request(req);
@@ -488,6 +489,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
 		struct inode *inode = ceph_get_snapdir(parent);
 		dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
 		     dentry, dentry->d_name.len, dentry->d_name.name, inode);
+		BUG_ON(!d_unhashed(dentry));
 		d_add(dentry, inode);
 		err = 0;
 	}
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index fc68e39cbad6..9d67572fb328 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/exportfs.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 
 #include "super.h"
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 5d2af8464f6a..4add3d5da2c1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/namei.h>
 #include <linux/writeback.h>
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index aca82d55cc53..26f883c275e8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -886,6 +886,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	struct inode *in = NULL;
 	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
+	struct ceph_client *client = ceph_sb_to_client(sb);
 	int i = 0;
 	int err = 0;
 
@@ -949,7 +950,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			return err;
 	}
 
-	if (rinfo->head->is_dentry && !req->r_aborted) {
+	/*
+	 * ignore null lease/binding on snapdir ENOENT, or else we
+	 * will have trouble splicing in the virtual snapdir later
+	 */
+	if (rinfo->head->is_dentry && !req->r_aborted &&
+	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
+					       client->mount_args->snapdir_name,
+					       req->r_dentry->d_name.len))) {
 		/*
 		 * lookup link rename   : null -> possibly existing inode
 		 * mknod symlink mkdir  : null -> new inode
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 5c7920be6420..60a9a4ae47be 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/wait.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include "mds_client.h"
diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index a32f0f896d9f..cdaaa131add3 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -6,6 +6,7 @@
 #include <linux/inet.h>
 #include <linux/kthread.h>
 #include <linux/net.h>
+#include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
 #include <net/tcp.h>
@@ -29,6 +30,10 @@ static char tag_msg = CEPH_MSGR_TAG_MSG;
 static char tag_ack = CEPH_MSGR_TAG_ACK;
 static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
 
+#ifdef CONFIG_LOCKDEP
+static struct lock_class_key socket_class;
+#endif
+
 
 static void queue_con(struct ceph_connection *con);
 static void con_work(struct work_struct *);
@@ -227,6 +232,10 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
 	con->sock = sock;
 	sock->sk->sk_allocation = GFP_NOFS;
 
+#ifdef CONFIG_LOCKDEP
+	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
+#endif
+
 	set_sock_callbacks(sock, con);
 
 	dout("connect %s\n", pr_addr(&con->peer_addr.in_addr));
@@ -332,6 +341,7 @@ static void reset_connection(struct ceph_connection *con)
 		con->out_msg = NULL;
 	}
 	con->in_seq = 0;
+	con->in_seq_acked = 0;
 }
 
 /*
diff --git a/fs/ceph/mon_client.c b/fs/ceph/mon_client.c
index 890597c09d43..8fdc011ca956 100644
--- a/fs/ceph/mon_client.c
+++ b/fs/ceph/mon_client.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/sched.h>
 
diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index d82fe87c2a6e..2e2c15eed82a 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -1,4 +1,7 @@
 
+#include "ceph_debug.h"
+
+#include <linux/slab.h>
 #include <asm/div64.h>
 
 #include "super.h"
@@ -6,7 +9,6 @@
 #include "crush/hash.h"
 #include "crush/mapper.h"
 #include "decode.h"
-#include "ceph_debug.h"
 
 char *ceph_osdmap_state_str(char *str, int len, int state)
 {
@@ -312,71 +314,6 @@ bad:
 	return ERR_PTR(err);
 }
 
-
-/*
- * osd map
- */
-void ceph_osdmap_destroy(struct ceph_osdmap *map)
-{
-	dout("osdmap_destroy %p\n", map);
-	if (map->crush)
-		crush_destroy(map->crush);
-	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
-		struct ceph_pg_mapping *pg =
-			rb_entry(rb_first(&map->pg_temp),
-				 struct ceph_pg_mapping, node);
-		rb_erase(&pg->node, &map->pg_temp);
-		kfree(pg);
-	}
-	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
-		struct ceph_pg_pool_info *pi =
-			rb_entry(rb_first(&map->pg_pools),
-				 struct ceph_pg_pool_info, node);
-		rb_erase(&pi->node, &map->pg_pools);
-		kfree(pi);
-	}
-	kfree(map->osd_state);
-	kfree(map->osd_weight);
-	kfree(map->osd_addr);
-	kfree(map);
-}
-
-/*
- * adjust max osd value.  reallocate arrays.
- */
-static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
-{
-	u8 *state;
-	struct ceph_entity_addr *addr;
-	u32 *weight;
-
-	state = kcalloc(max, sizeof(*state), GFP_NOFS);
-	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
-	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
-	if (state == NULL || addr == NULL || weight == NULL) {
-		kfree(state);
-		kfree(addr);
-		kfree(weight);
-		return -ENOMEM;
-	}
-
-	/* copy old? */
-	if (map->osd_state) {
-		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
-		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
-		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
-		kfree(map->osd_state);
-		kfree(map->osd_addr);
-		kfree(map->osd_weight);
-	}
-
-	map->osd_state = state;
-	map->osd_weight = weight;
-	map->osd_addr = addr;
-	map->max_osd = max;
-	return 0;
-}
-
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
  * to a set of osds)
@@ -480,6 +417,13 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
 	return NULL;
 }
 
+static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
+{
+	rb_erase(&pi->node, root);
+	kfree(pi->name);
+	kfree(pi);
+}
+
 void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 {
 	ceph_decode_copy(p, &pi->v, sizeof(pi->v));
@@ -488,6 +432,98 @@ void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 	*p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
 }
 
+static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+{
+	struct ceph_pg_pool_info *pi;
+	u32 num, len, pool;
+
+	ceph_decode_32_safe(p, end, num, bad);
+	dout(" %d pool names\n", num);
+	while (num--) {
+		ceph_decode_32_safe(p, end, pool, bad);
+		ceph_decode_32_safe(p, end, len, bad);
+		dout("  pool %d len %d\n", pool, len);
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (pi) {
+			kfree(pi->name);
+			pi->name = kmalloc(len + 1, GFP_NOFS);
+			if (pi->name) {
+				memcpy(pi->name, *p, len);
+				pi->name[len] = '\0';
+				dout("  name is %s\n", pi->name);
+			}
+		}
+		*p += len;
+	}
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
+/*
+ * osd map
+ */
+void ceph_osdmap_destroy(struct ceph_osdmap *map)
+{
+	dout("osdmap_destroy %p\n", map);
+	if (map->crush)
+		crush_destroy(map->crush);
+	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->pg_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->pg_temp);
+		kfree(pg);
+	}
+	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rb_first(&map->pg_pools),
+				 struct ceph_pg_pool_info, node);
+		__remove_pg_pool(&map->pg_pools, pi);
+	}
+	kfree(map->osd_state);
+	kfree(map->osd_weight);
+	kfree(map->osd_addr);
+	kfree(map);
+}
+
+/*
+ * adjust max osd value.  reallocate arrays.
+ */
+static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
+{
+	u8 *state;
+	struct ceph_entity_addr *addr;
+	u32 *weight;
+
+	state = kcalloc(max, sizeof(*state), GFP_NOFS);
+	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
+	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
+	if (state == NULL || addr == NULL || weight == NULL) {
+		kfree(state);
+		kfree(addr);
+		kfree(weight);
+		return -ENOMEM;
+	}
+
+	/* copy old? */
+	if (map->osd_state) {
+		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
+		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
+		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
+		kfree(map->osd_state);
+		kfree(map->osd_addr);
+		kfree(map->osd_weight);
+	}
+
+	map->osd_state = state;
+	map->osd_weight = weight;
+	map->osd_addr = addr;
+	map->max_osd = max;
+	return 0;
+}
+
 /*
  * decode a full map.
  */
@@ -524,7 +560,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	ceph_decode_32_safe(p, end, max, bad);
 	while (max--) {
 		ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
-		pi = kmalloc(sizeof(*pi), GFP_NOFS);
+		pi = kzalloc(sizeof(*pi), GFP_NOFS);
 		if (!pi)
 			goto bad;
 		pi->id = ceph_decode_32(p);
@@ -537,6 +573,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 		__decode_pool(p, pi);
 		__insert_pg_pool(&map->pg_pools, pi);
 	}
+
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
+
 	ceph_decode_32_safe(p, end, map->pool_max, bad);
 
 	ceph_decode_32_safe(p, end, map->flags, bad);
@@ -710,7 +750,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		}
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
 		if (!pi) {
-			pi = kmalloc(sizeof(*pi), GFP_NOFS);
+			pi = kzalloc(sizeof(*pi), GFP_NOFS);
 			if (!pi) {
 				err = -ENOMEM;
 				goto bad;
@@ -720,6 +760,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		}
 		__decode_pool(p, pi);
 	}
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
 
 	/* old_pool */
 	ceph_decode_32_safe(p, end, len, bad);
@@ -728,10 +770,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 
 		ceph_decode_32_safe(p, end, pool, bad);
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
-		if (pi) {
-			rb_erase(&pi->node, &map->pg_pools);
-			kfree(pi);
-		}
+		if (pi)
+			__remove_pg_pool(&map->pg_pools, pi);
 	}
 
 	/* new_up */
diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h
index 1fb55afb2642..8bc9f1e4f562 100644
--- a/fs/ceph/osdmap.h
+++ b/fs/ceph/osdmap.h
@@ -23,6 +23,7 @@ struct ceph_pg_pool_info {
 	int id;
 	struct ceph_pg_pool v;
 	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
+	char *name;
 };
 
 struct ceph_pg_mapping {
diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
index 370e93695474..5f8dbf7c745a 100644
--- a/fs/ceph/pagelist.c
+++ b/fs/ceph/pagelist.c
@@ -1,4 +1,5 @@
 
+#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 
diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h
index 26ac8b89a676..a1fc1d017b58 100644
--- a/fs/ceph/rados.h
+++ b/fs/ceph/rados.h
@@ -11,8 +11,10 @@
 /*
  * osdmap encoding versions
  */
-#define CEPH_OSDMAP_INC_VERSION 4
-#define CEPH_OSDMAP_VERSION     4
+#define CEPH_OSDMAP_INC_VERSION     5
+#define CEPH_OSDMAP_INC_VERSION_EXT 5
+#define CEPH_OSDMAP_VERSION         5
+#define CEPH_OSDMAP_VERSION_EXT     5
 
 /*
  * fs id
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index df04e210a055..2b881262ef67 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/sort.h>
+#include <linux/slab.h>
 
 #include "super.h"
 #include "decode.h"
@@ -430,8 +431,7 @@ static int dup_array(u64 **dst, __le64 *src, int num)
  * Caller must hold snap_rwsem for read (i.e., the realm topology won't
  * change).
  */
-void ceph_queue_cap_snap(struct ceph_inode_info *ci,
-			 struct ceph_snap_context *snapc)
+void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap_snap *capsnap;
@@ -450,10 +450,11 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		   as no new writes are allowed to start when pending, so any
 		   writes in progress now were started before the previous
 		   cap_snap.  lucky us. */
-		dout("queue_cap_snap %p snapc %p seq %llu used %d"
-		     " already pending\n", inode, snapc, snapc->seq, used);
+		dout("queue_cap_snap %p already pending\n", inode);
 		kfree(capsnap);
 	} else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR)) {
+		struct ceph_snap_context *snapc = ci->i_head_snapc;
+
 		igrab(inode);
 
 		atomic_set(&capsnap->nref, 1);
@@ -462,7 +463,6 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		INIT_LIST_HEAD(&capsnap->flushing_item);
 
 		capsnap->follows = snapc->seq - 1;
-		capsnap->context = ceph_get_snap_context(snapc);
 		capsnap->issued = __ceph_caps_issued(ci, NULL);
 		capsnap->dirty = __ceph_caps_dirty(ci);
 
@@ -479,7 +479,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		   snapshot. */
 		capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
 		ci->i_wrbuffer_ref_head = 0;
-		ceph_put_snap_context(ci->i_head_snapc);
+		capsnap->context = snapc;
 		ci->i_head_snapc = NULL;
 		list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
 
@@ -521,15 +521,17 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 	capsnap->ctime = inode->i_ctime;
 	capsnap->time_warp_seq = ci->i_time_warp_seq;
 	if (capsnap->dirty_pages) {
-		dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu "
+		dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu "
 		     "still has %d dirty pages\n", inode, capsnap,
 		     capsnap->context, capsnap->context->seq,
-		     capsnap->size, capsnap->dirty_pages);
+		     ceph_cap_string(capsnap->dirty), capsnap->size,
+		     capsnap->dirty_pages);
 		return 0;
 	}
-	dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu clean\n",
+	dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n",
 	     inode, capsnap, capsnap->context,
-	     capsnap->context->seq, capsnap->size);
+	     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
+	     capsnap->size);
 
 	spin_lock(&mdsc->snap_flush_lock);
 	list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
@@ -601,7 +603,7 @@ more:
 				if (lastinode)
 					iput(lastinode);
 				lastinode = inode;
-				ceph_queue_cap_snap(ci, realm->cached_context);
+				ceph_queue_cap_snap(ci);
 				spin_lock(&realm->inodes_with_caps_lock);
 			}
 			spin_unlock(&realm->inodes_with_caps_lock);
@@ -823,8 +825,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			spin_unlock(&realm->inodes_with_caps_lock);
 			spin_unlock(&inode->i_lock);
 
-			ceph_queue_cap_snap(ci,
-					    ci->i_snap_realm->cached_context);
+			ceph_queue_cap_snap(ci);
 
 			iput(inode);
 			continue;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 4290a6e860b0..75d02eaa1279 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -11,6 +11,7 @@
 #include <linux/rwsem.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/string.h>
 #include <linux/version.h>
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 65d12036b670..e30dfbb056c3 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -12,6 +12,7 @@
 #include <linux/pagemap.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
+#include <linux/slab.h>
 
 #include "types.h"
 #include "messenger.h"
@@ -714,8 +715,7 @@ extern int ceph_update_snap_trace(struct ceph_mds_client *m,
 extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session,
 			     struct ceph_msg *msg);
-extern void ceph_queue_cap_snap(struct ceph_inode_info *ci,
-				struct ceph_snap_context *snapc);
+extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
 extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 				  struct ceph_cap_snap *capsnap);
 extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 37d6ce645691..2845422907fc 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -3,6 +3,7 @@
 #include "decode.h"
 
 #include <linux/xattr.h>
+#include <linux/slab.h>
 
 static bool ceph_is_valid_xattr(const char *name)
 {