Merge branch 'master' of /repos/git/net-next-2.6

Conflicts:
	net/bridge/br_device.c
	net/bridge/br_forward.c

Signed-off-by: Patrick McHardy <kaber@trash.net>

37 files changed, 506 insertions, 325 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9e23ffea7f54..b34d32fdaaec 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3235,7 +3235,8 @@ int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
                                 u64 bytes)
 {
         struct btrfs_space_info *data_sinfo;
-        int ret = 0, committed = 0;
+        u64 used;
+        int ret = 0, committed = 0, flushed = 0;
 
         /* make sure bytes are sectorsize aligned */
         bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
@@ -3247,12 +3248,21 @@ int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
 again:
         /* make sure we have enough space to handle the data first */
         spin_lock(&data_sinfo->lock);
-        if (data_sinfo->total_bytes - data_sinfo->bytes_used -
-            data_sinfo->bytes_delalloc - data_sinfo->bytes_reserved -
-            data_sinfo->bytes_pinned - data_sinfo->bytes_readonly -
-            data_sinfo->bytes_may_use - data_sinfo->bytes_super < bytes) {
+        used = data_sinfo->bytes_used + data_sinfo->bytes_delalloc +
+                data_sinfo->bytes_reserved + data_sinfo->bytes_pinned +
+                data_sinfo->bytes_readonly + data_sinfo->bytes_may_use +
+                data_sinfo->bytes_super;
+
+        if (used + bytes > data_sinfo->total_bytes) {
                 struct btrfs_trans_handle *trans;
 
+                if (!flushed) {
+                        spin_unlock(&data_sinfo->lock);
+                        flush_delalloc(root, data_sinfo);
+                        flushed = 1;
+                        goto again;
+                }
+
                 /*
                  * if we don't have enough free bytes in this space then we need
                  * to alloc a new chunk.
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index aa7dc36dac78..8db7b14bbae8 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2250,6 +2250,12 @@ again:
         if (!looped)
                 calc_size = max_t(u64, min_stripe_size, calc_size);
 
+        /*
+         * we're about to do_div by the stripe_len so lets make sure
+         * we end up with something bigger than a stripe
+         */
+        calc_size = max_t(u64, calc_size, stripe_len * 4);
+
         do_div(calc_size, stripe_len);
         calc_size *= stripe_len;
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index aa3cd7cc3e40..412593703d1e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -337,16 +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);
@@ -357,21 +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;
 }
@@ -392,7 +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;
 
@@ -413,13 +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)
@@ -458,7 +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;
 }
@@ -558,9 +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);
 
@@ -618,7 +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;
@@ -770,9 +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 */
@@ -914,7 +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;
 }
 
 /*
@@ -936,8 +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, */
@@ -947,23 +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,
@@ -973,6 +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/caps.c b/fs/ceph/caps.c
index 3710e077a857..aa2239fa9a3b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1205,6 +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) {
@@ -2118,8 +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);
@@ -2143,7 +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;
 
@@ -2166,19 +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);
@@ -2186,10 +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);
 }
 
 /*
@@ -2465,8 +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/dir.c b/fs/ceph/dir.c
index 7261dc6c2ead..ea8ee2e526aa 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -171,11 +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++;
 
@@ -312,7 +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);
@@ -489,6 +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/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/messenger.c b/fs/ceph/messenger.c
index 8f1715ffbe4b..cdaaa131add3 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -30,6 +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 *);
@@ -228,6 +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));
@@ -333,6 +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/osdmap.c b/fs/ceph/osdmap.c
index 21c6623c4b07..2e2c15eed82a 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -314,71 +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)
@@ -482,6 +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));
@@ -490,6 +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.
  */
@@ -526,7 +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);
@@ -539,6 +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);
@@ -712,7 +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;
@@ -722,6 +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);
@@ -730,10 +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/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 e6f9bc57d472..2b881262ef67 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -431,8 +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;
@@ -451,10 +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);
@@ -463,7 +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);
 
@@ -480,7 +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);
 
@@ -522,15 +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);
@@ -602,7 +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);
@@ -824,8 +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.h b/fs/ceph/super.h
index ca702c67bc66..e30dfbb056c3 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -715,8 +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/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index efb2b9400391..1cc087635a5e 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -382,8 +382,8 @@ out:
 static void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num,
                                              struct ecryptfs_crypt_stat *crypt_stat)
 {
-        (*offset) = (crypt_stat->num_header_bytes_at_front
-                     + (crypt_stat->extent_size * extent_num));
+        (*offset) = ecryptfs_lower_header_size(crypt_stat)
+                    + (crypt_stat->extent_size * extent_num);
 }
 
 /**
@@ -835,13 +835,13 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat)
         set_extent_mask_and_shift(crypt_stat);
         crypt_stat->iv_bytes = ECRYPTFS_DEFAULT_IV_BYTES;
         if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
-                crypt_stat->num_header_bytes_at_front = 0;
+                crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
         else {
                 if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)
-                        crypt_stat->num_header_bytes_at_front =
+                        crypt_stat->metadata_size =
                                 ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
                 else
-                        crypt_stat->num_header_bytes_at_front = PAGE_CACHE_SIZE;
+                        crypt_stat->metadata_size = PAGE_CACHE_SIZE;
         }
 }
 
@@ -1108,9 +1108,9 @@ static void write_ecryptfs_marker(char *page_virt, size_t *written)
         (*written) = MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
 }
 
-static void
-write_ecryptfs_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat,
-                     size_t *written)
+void ecryptfs_write_crypt_stat_flags(char *page_virt,
+                                     struct ecryptfs_crypt_stat *crypt_stat,
+                                     size_t *written)
 {
         u32 flags = 0;
         int i;
@@ -1238,8 +1238,7 @@ ecryptfs_write_header_metadata(char *virt,
 
         header_extent_size = (u32)crypt_stat->extent_size;
         num_header_extents_at_front =
-                (u16)(crypt_stat->num_header_bytes_at_front
-                      / crypt_stat->extent_size);
+                (u16)(crypt_stat->metadata_size / crypt_stat->extent_size);
         put_unaligned_be32(header_extent_size, virt);
         virt += 4;
         put_unaligned_be16(num_header_extents_at_front, virt);
@@ -1292,7 +1291,8 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t max,
         offset = ECRYPTFS_FILE_SIZE_BYTES;
         write_ecryptfs_marker((page_virt + offset), &written);
         offset += written;
-        write_ecryptfs_flags((page_virt + offset), crypt_stat, &written);
+        ecryptfs_write_crypt_stat_flags((page_virt + offset), crypt_stat,
+                                        &written);
         offset += written;
         ecryptfs_write_header_metadata((page_virt + offset), crypt_stat,
                                        &written);
@@ -1382,7 +1382,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
                 rc = -EINVAL;
                 goto out;
         }
-        virt_len = crypt_stat->num_header_bytes_at_front;
+        virt_len = crypt_stat->metadata_size;
         order = get_order(virt_len);
         /* Released in this function */
         virt = (char *)ecryptfs_get_zeroed_pages(GFP_KERNEL, order);
@@ -1428,16 +1428,15 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat,
         header_extent_size = get_unaligned_be32(virt);
         virt += sizeof(__be32);
         num_header_extents_at_front = get_unaligned_be16(virt);
-        crypt_stat->num_header_bytes_at_front =
-                (((size_t)num_header_extents_at_front
-                  * (size_t)header_extent_size));
+        crypt_stat->metadata_size = (((size_t)num_header_extents_at_front
+                                     * (size_t)header_extent_size));
         (*bytes_read) = (sizeof(__be32) + sizeof(__be16));
         if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE)
-            && (crypt_stat->num_header_bytes_at_front
+            && (crypt_stat->metadata_size
                 < ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) {
                 rc = -EINVAL;
                 printk(KERN_WARNING "Invalid header size: [%zd]\n",
-                       crypt_stat->num_header_bytes_at_front);
+                       crypt_stat->metadata_size);
         }
         return rc;
 }
@@ -1452,8 +1451,7 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat,
  */
 static void set_default_header_data(struct ecryptfs_crypt_stat *crypt_stat)
 {
-        crypt_stat->num_header_bytes_at_front =
-                ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
+        crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 }
 
 /**
@@ -1607,6 +1605,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
                                                 ecryptfs_dentry,
                                                 ECRYPTFS_VALIDATE_HEADER_SIZE);
         if (rc) {
+                memset(page_virt, 0, PAGE_CACHE_SIZE);
                 rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode);
                 if (rc) {
                         printk(KERN_DEBUG "Valid eCryptfs headers not found in "
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 542f625312f3..bc7115403f38 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -273,7 +273,7 @@ struct ecryptfs_crypt_stat {
         u32 flags;
         unsigned int file_version;
         size_t iv_bytes;
-        size_t num_header_bytes_at_front;
+        size_t metadata_size;
         size_t extent_size; /* Data extent size; default is 4096 */
         size_t key_size;
         size_t extent_shift;
@@ -464,6 +464,14 @@ struct ecryptfs_daemon {
 
 extern struct mutex ecryptfs_daemon_hash_mux;
 
+static inline size_t
+ecryptfs_lower_header_size(struct ecryptfs_crypt_stat *crypt_stat)
+{
+        if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
+                return 0;
+        return crypt_stat->metadata_size;
+}
+
 static inline struct ecryptfs_file_info *
 ecryptfs_file_to_private(struct file *file)
 {
@@ -651,6 +659,9 @@ int ecryptfs_decrypt_page(struct page *page);
 int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry);
 int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
 int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
+void ecryptfs_write_crypt_stat_flags(char *page_virt,
+                                     struct ecryptfs_crypt_stat *crypt_stat,
+                                     size_t *written);
 int ecryptfs_read_and_validate_header_region(char *data,
                                              struct inode *ecryptfs_inode);
 int ecryptfs_read_and_validate_xattr_region(char *page_virt,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index d3362faf3852..e2d4418affac 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -324,6 +324,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
         rc = ecryptfs_read_and_validate_header_region(page_virt,
                                                       ecryptfs_dentry->d_inode);
         if (rc) {
+                memset(page_virt, 0, PAGE_CACHE_SIZE);
                 rc = ecryptfs_read_and_validate_xattr_region(page_virt,
                                                              ecryptfs_dentry);
                 if (rc) {
@@ -336,7 +337,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
                 ecryptfs_dentry->d_sb)->mount_crypt_stat;
         if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) {
                 if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
-                        file_size = (crypt_stat->num_header_bytes_at_front
+                        file_size = (crypt_stat->metadata_size
                                      + i_size_read(lower_dentry->d_inode));
                 else
                         file_size = i_size_read(lower_dentry->d_inode);
@@ -388,9 +389,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
         mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
         if (IS_ERR(lower_dentry)) {
                 rc = PTR_ERR(lower_dentry);
-                printk(KERN_ERR "%s: lookup_one_len() returned [%d] on "
-                       "lower_dentry = [%s]\n", __func__, rc,
-                       ecryptfs_dentry->d_name.name);
+                ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
+                                "[%d] on lower_dentry = [%s]\n", __func__, rc,
+                                encrypted_and_encoded_name);
                 goto out_d_drop;
         }
         if (lower_dentry->d_inode)
@@ -417,9 +418,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
         mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
         if (IS_ERR(lower_dentry)) {
                 rc = PTR_ERR(lower_dentry);
-                printk(KERN_ERR "%s: lookup_one_len() returned [%d] on "
-                       "lower_dentry = [%s]\n", __func__, rc,
-                       encrypted_and_encoded_name);
+                ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
+                                "[%d] on lower_dentry = [%s]\n", __func__, rc,
+                                encrypted_and_encoded_name);
                 goto out_d_drop;
         }
 lookup_and_interpose:
@@ -456,8 +457,8 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
         rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb, 0);
         if (rc)
                 goto out_lock;
-        fsstack_copy_attr_times(dir, lower_new_dentry->d_inode);
-        fsstack_copy_inode_size(dir, lower_new_dentry->d_inode);
+        fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+        fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
         old_dentry->d_inode->i_nlink =
                 ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink;
         i_size_write(new_dentry->d_inode, file_size_save);
@@ -648,38 +649,17 @@ out_lock:
         return rc;
 }
 
-static int
-ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+static int ecryptfs_readlink_lower(struct dentry *dentry, char **buf,
+                                   size_t *bufsiz)
 {
+        struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
         char *lower_buf;
-        size_t lower_bufsiz;
-        struct dentry *lower_dentry;
-        struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
-        char *plaintext_name;
-        size_t plaintext_name_size;
+        size_t lower_bufsiz = PATH_MAX;
         mm_segment_t old_fs;
         int rc;
 
-        lower_dentry = ecryptfs_dentry_to_lower(dentry);
-        if (!lower_dentry->d_inode->i_op->readlink) {
-                rc = -EINVAL;
-                goto out;
-        }
-        mount_crypt_stat = &ecryptfs_superblock_to_private(
-                                                dentry->d_sb)->mount_crypt_stat;
-        /*
-         * If the lower filename is encrypted, it will result in a significantly
-         * longer name.  If needed, truncate the name after decode and decrypt.
-         */
-        if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-                lower_bufsiz = PATH_MAX;
-        else
-                lower_bufsiz = bufsiz;
-        /* Released in this function */
         lower_buf = kmalloc(lower_bufsiz, GFP_KERNEL);
-        if (lower_buf == NULL) {
-                printk(KERN_ERR "%s: Out of memory whilst attempting to "
-                       "kmalloc [%zd] bytes\n", __func__, lower_bufsiz);
+        if (!lower_buf) {
                 rc = -ENOMEM;
                 goto out;
         }
@@ -689,29 +669,31 @@ ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
                                                    (char __user *)lower_buf,
                                                    lower_bufsiz);
         set_fs(old_fs);
-        if (rc >= 0) {
-                rc = ecryptfs_decode_and_decrypt_filename(&plaintext_name,
-                                                          &plaintext_name_size,
-                                                          dentry, lower_buf,
-                                                          rc);
-                if (rc) {
-                        printk(KERN_ERR "%s: Error attempting to decode and "
-                               "decrypt filename; rc = [%d]\n", __func__,
-                                rc);
-                        goto out_free_lower_buf;
-                }
-                /* Check for bufsiz <= 0 done in sys_readlinkat() */
-                rc = copy_to_user(buf, plaintext_name,
-                                  min((size_t) bufsiz, plaintext_name_size));
-                if (rc)
-                        rc = -EFAULT;
-                else
-                        rc = plaintext_name_size;
-                kfree(plaintext_name);
-                fsstack_copy_attr_atime(dentry->d_inode, lower_dentry->d_inode);
-        }
-out_free_lower_buf:
+        if (rc < 0)
+                goto out;
+        lower_bufsiz = rc;
+        rc = ecryptfs_decode_and_decrypt_filename(buf, bufsiz, dentry,
+                                                  lower_buf, lower_bufsiz);
+out:
         kfree(lower_buf);
+        return rc;
+}
+
+static int
+ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+        char *kbuf;
+        size_t kbufsiz, copied;
+        int rc;
+
+        rc = ecryptfs_readlink_lower(dentry, &kbuf, &kbufsiz);
+        if (rc)
+                goto out;
+        copied = min_t(size_t, bufsiz, kbufsiz);
+        rc = copy_to_user(buf, kbuf, copied) ? -EFAULT : copied;
+        kfree(kbuf);
+        fsstack_copy_attr_atime(dentry->d_inode,
+                                ecryptfs_dentry_to_lower(dentry)->d_inode);
 out:
         return rc;
 }
@@ -769,7 +751,7 @@ upper_size_to_lower_size(struct ecryptfs_crypt_stat *crypt_stat,
 {
         loff_t lower_size;
 
-        lower_size = crypt_stat->num_header_bytes_at_front;
+        lower_size = ecryptfs_lower_header_size(crypt_stat);
         if (upper_size != 0) {
                 loff_t num_extents;
 
@@ -1016,6 +998,28 @@ out:
         return rc;
 }
 
+int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
+                          struct kstat *stat)
+{
+        struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+        int rc = 0;
+
+        mount_crypt_stat = &ecryptfs_superblock_to_private(
+                                                dentry->d_sb)->mount_crypt_stat;
+        generic_fillattr(dentry->d_inode, stat);
+        if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
+                char *target;
+                size_t targetsiz;
+
+                rc = ecryptfs_readlink_lower(dentry, &target, &targetsiz);
+                if (!rc) {
+                        kfree(target);
+                        stat->size = targetsiz;
+                }
+        }
+        return rc;
+}
+
 int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
                      struct kstat *stat)
 {
@@ -1040,7 +1044,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 
         lower_dentry = ecryptfs_dentry_to_lower(dentry);
         if (!lower_dentry->d_inode->i_op->setxattr) {
-                rc = -ENOSYS;
+                rc = -EOPNOTSUPP;
                 goto out;
         }
         mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1058,7 +1062,7 @@ ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
         int rc = 0;
 
         if (!lower_dentry->d_inode->i_op->getxattr) {
-                rc = -ENOSYS;
+                rc = -EOPNOTSUPP;
                 goto out;
         }
         mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1085,7 +1089,7 @@ ecryptfs_listxattr(struct dentry *dentry, char *list, size_t size)
 
         lower_dentry = ecryptfs_dentry_to_lower(dentry);
         if (!lower_dentry->d_inode->i_op->listxattr) {
-                rc = -ENOSYS;
+                rc = -EOPNOTSUPP;
                 goto out;
         }
         mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1102,7 +1106,7 @@ static int ecryptfs_removexattr(struct dentry *dentry, const char *name)
 
         lower_dentry = ecryptfs_dentry_to_lower(dentry);
         if (!lower_dentry->d_inode->i_op->removexattr) {
-                rc = -ENOSYS;
+                rc = -EOPNOTSUPP;
                 goto out;
         }
         mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1133,6 +1137,7 @@ const struct inode_operations ecryptfs_symlink_iops = {
         .put_link = ecryptfs_put_link,
         .permission = ecryptfs_permission,
         .setattr = ecryptfs_setattr,
+        .getattr = ecryptfs_getattr_link,
         .setxattr = ecryptfs_setxattr,
         .getxattr = ecryptfs_getxattr,
         .listxattr = ecryptfs_listxattr,
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index d491237c98e7..2ee9a3a7b68c 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -83,6 +83,19 @@ out:
         return rc;
 }
 
+static void strip_xattr_flag(char *page_virt,
+                             struct ecryptfs_crypt_stat *crypt_stat)
+{
+        if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
+                size_t written;
+
+                crypt_stat->flags &= ~ECRYPTFS_METADATA_IN_XATTR;
+                ecryptfs_write_crypt_stat_flags(page_virt, crypt_stat,
+                                                &written);
+                crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
+        }
+}
+
 /**
  *   Header Extent:
  *     Octets 0-7:        Unencrypted file size (big-endian)
@@ -98,19 +111,6 @@ out:
  *                        (big-endian)
  *     Octet  26:         Begin RFC 2440 authentication token packet set
  */
-static void set_header_info(char *page_virt,
-                            struct ecryptfs_crypt_stat *crypt_stat)
-{
-        size_t written;
-        size_t save_num_header_bytes_at_front =
-                crypt_stat->num_header_bytes_at_front;
-
-        crypt_stat->num_header_bytes_at_front =
-                ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
-        ecryptfs_write_header_metadata(page_virt + 20, crypt_stat, &written);
-        crypt_stat->num_header_bytes_at_front =
-                save_num_header_bytes_at_front;
-}
 
 /**
  * ecryptfs_copy_up_encrypted_with_header
@@ -136,8 +136,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
                                            * num_extents_per_page)
                                           + extent_num_in_page);
                 size_t num_header_extents_at_front =
-                        (crypt_stat->num_header_bytes_at_front
-                         / crypt_stat->extent_size);
+                        (crypt_stat->metadata_size / crypt_stat->extent_size);
 
                 if (view_extent_num < num_header_extents_at_front) {
                         /* This is a header extent */
@@ -147,9 +146,14 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
                         memset(page_virt, 0, PAGE_CACHE_SIZE);
                         /* TODO: Support more than one header extent */
                         if (view_extent_num == 0) {
+                                size_t written;
+
                                 rc = ecryptfs_read_xattr_region(
                                         page_virt, page->mapping->host);
-                                set_header_info(page_virt, crypt_stat);
+                                strip_xattr_flag(page_virt + 16, crypt_stat);
+                                ecryptfs_write_header_metadata(page_virt + 20,
+                                                               crypt_stat,
+                                                               &written);
                         }
                         kunmap_atomic(page_virt, KM_USER0);
                         flush_dcache_page(page);
@@ -162,7 +166,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
                         /* This is an encrypted data extent */
                         loff_t lower_offset =
                                 ((view_extent_num * crypt_stat->extent_size)
-                                 - crypt_stat->num_header_bytes_at_front);
+                                 - crypt_stat->metadata_size);
 
                         rc = ecryptfs_read_lower_page_segment(
                                 page, (lower_offset >> PAGE_CACHE_SHIFT),
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index fcef41c1d2cf..278743c7716a 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -86,7 +86,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
                 if (lower_dentry->d_inode) {
                         fput(inode_info->lower_file);
                         inode_info->lower_file = NULL;
-                        d_drop(lower_dentry);
                 }
         }
         ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat);
diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index 4e2426e22bbe..565cf817bbf1 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -32,6 +32,7 @@ const struct inode_operations ext2_symlink_inode_operations = {
         .readlink       = generic_readlink,
         .follow_link    = page_follow_link_light,
         .put_link       = page_put_link,
+        .setattr        = ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
@@ -43,6 +44,7 @@ const struct inode_operations ext2_symlink_inode_operations = {
 const struct inode_operations ext2_fast_symlink_inode_operations = {
         .readlink       = generic_readlink,
         .follow_link    = ext2_follow_link,
+        .setattr        = ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
diff --git a/fs/ext3/symlink.c b/fs/ext3/symlink.c
index ff7b4ccd8983..7c4898207776 100644
--- a/fs/ext3/symlink.c
+++ b/fs/ext3/symlink.c
@@ -34,6 +34,7 @@ const struct inode_operations ext3_symlink_inode_operations = {
         .readlink       = generic_readlink,
         .follow_link    = page_follow_link_light,
         .put_link       = page_put_link,
+        .setattr        = ext3_setattr,
 #ifdef CONFIG_EXT3_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
@@ -45,6 +46,7 @@ const struct inode_operations ext3_symlink_inode_operations = {
 const struct inode_operations ext3_fast_symlink_inode_operations = {
         .readlink       = generic_readlink,
         .follow_link    = ext3_follow_link,
+        .setattr        = ext3_setattr,
 #ifdef CONFIG_EXT3_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 452d02f9075e..0a140741b39e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -614,9 +614,15 @@ int send_sigurg(struct fown_struct *fown)
         return ret;
 }
 
-static DEFINE_RWLOCK(fasync_lock);
+static DEFINE_SPINLOCK(fasync_lock);
 static struct kmem_cache *fasync_cache __read_mostly;
 
+static void fasync_free_rcu(struct rcu_head *head)
+{
+        kmem_cache_free(fasync_cache,
+                        container_of(head, struct fasync_struct, fa_rcu));
+}
+
 /*
  * Remove a fasync entry. If successfully removed, return
  * positive and clear the FASYNC flag. If no entry exists,
@@ -625,8 +631,6 @@ static struct kmem_cache *fasync_cache __read_mostly;
  * NOTE! It is very important that the FASYNC flag always
  * match the state "is the filp on a fasync list".
  *
- * We always take the 'filp->f_lock', in since fasync_lock
- * needs to be irq-safe.
  */
 static int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 {
@@ -634,17 +638,22 @@ static int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
         int result = 0;
 
         spin_lock(&filp->f_lock);
-        write_lock_irq(&fasync_lock);
+        spin_lock(&fasync_lock);
         for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
                 if (fa->fa_file != filp)
                         continue;
+
+                spin_lock_irq(&fa->fa_lock);
+                fa->fa_file = NULL;
+                spin_unlock_irq(&fa->fa_lock);
+
                 *fp = fa->fa_next;
-                kmem_cache_free(fasync_cache, fa);
+                call_rcu(&fa->fa_rcu, fasync_free_rcu);
                 filp->f_flags &= ~FASYNC;
                 result = 1;
                 break;
         }
-        write_unlock_irq(&fasync_lock);
+        spin_unlock(&fasync_lock);
         spin_unlock(&filp->f_lock);
         return result;
 }
@@ -666,25 +675,30 @@ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fa
                 return -ENOMEM;
 
         spin_lock(&filp->f_lock);
-        write_lock_irq(&fasync_lock);
+        spin_lock(&fasync_lock);
         for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
                 if (fa->fa_file != filp)
                         continue;
+
+                spin_lock_irq(&fa->fa_lock);
                 fa->fa_fd = fd;
+                spin_unlock_irq(&fa->fa_lock);
+
                 kmem_cache_free(fasync_cache, new);
                 goto out;
         }
 
+        spin_lock_init(&new->fa_lock);
         new->magic = FASYNC_MAGIC;
         new->fa_file = filp;
         new->fa_fd = fd;
         new->fa_next = *fapp;
-        *fapp = new;
+        rcu_assign_pointer(*fapp, new);
         result = 1;
         filp->f_flags |= FASYNC;
 
 out:
-        write_unlock_irq(&fasync_lock);
+        spin_unlock(&fasync_lock);
         spin_unlock(&filp->f_lock);
         return result;
 }
@@ -704,37 +718,41 @@ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fap
 
 EXPORT_SYMBOL(fasync_helper);
 
-void __kill_fasync(struct fasync_struct *fa, int sig, int band)
+/*
+ * rcu_read_lock() is held
+ */
+static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 {
         while (fa) {
-                struct fown_struct * fown;
+                struct fown_struct *fown;
                 if (fa->magic != FASYNC_MAGIC) {
                         printk(KERN_ERR "kill_fasync: bad magic number in "
                                "fasync_struct!\n");
                         return;
                 }
-                fown = &fa->fa_file->f_owner;
-                /* Don't send SIGURG to processes which have not set a
-                   queued signum: SIGURG has its own default signalling
-                   mechanism. */
-                if (!(sig == SIGURG && fown->signum == 0))
-                        send_sigio(fown, fa->fa_fd, band);
-                fa = fa->fa_next;
+                spin_lock(&fa->fa_lock);
+                if (fa->fa_file) {
+                        fown = &fa->fa_file->f_owner;
+                        /* Don't send SIGURG to processes which have not set a
+                           queued signum: SIGURG has its own default signalling
+                           mechanism. */
+                        if (!(sig == SIGURG && fown->signum == 0))
+                                send_sigio(fown, fa->fa_fd, band);
+                }
+                spin_unlock(&fa->fa_lock);
+                fa = rcu_dereference(fa->fa_next);
         }
 }
 
-EXPORT_SYMBOL(__kill_fasync);
-
 void kill_fasync(struct fasync_struct **fp, int sig, int band)
 {
         /* First a quick test without locking: usually
          * the list is empty.
          */
         if (*fp) {
-                read_lock(&fasync_lock);
-                /* reread *fp after obtaining the lock */
-                __kill_fasync(*fp, sig, band);
-                read_unlock(&fasync_lock);
+                rcu_read_lock();
+                kill_fasync_rcu(rcu_dereference(*fp), sig, band);
+                rcu_read_unlock();
         }
 }
 EXPORT_SYMBOL(kill_fasync);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2a3d352c0bff..a8766c4ef2e0 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1294,7 +1294,8 @@ static int nfs4_init_server(struct nfs_server *server,
 
         /* Initialise the client representation from the mount data */
         server->flags = data->flags;
-        server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
+        server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|
+                NFS_CAP_POSIX_LOCK;
         server->options = data->options;
 
         /* Get a client record */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c6f2750648f4..be46f26c9a56 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1025,12 +1025,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                                 res = NULL;
                                 goto out;
                         /* This turned out not to be a regular file */
+                        case -EISDIR:
                         case -ENOTDIR:
                                 goto no_open;
                         case -ELOOP:
                                 if (!(nd->intent.open.flags & O_NOFOLLOW))
                                         goto no_open;
-                        /* case -EISDIR: */
                         /* case -EINVAL: */
                         default:
                                 goto out;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 737128f777f3..50a56edca0b5 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -623,10 +623,10 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c
         list_for_each_entry(pos, &nfsi->open_files, list) {
                 if (cred != NULL && pos->cred != cred)
                         continue;
-                if ((pos->mode & mode) == mode) {
-                        ctx = get_nfs_open_context(pos);
-                        break;
-                }
+                if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
+                        continue;
+                ctx = get_nfs_open_context(pos);
+                break;
         }
         spin_unlock(&inode->i_lock);
         return ctx;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index fe0cd9eb1d4d..638067007c65 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1523,6 +1523,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
                 nfs_post_op_update_inode(dir, o_res->dir_attr);
         } else
                 nfs_refresh_inode(dir, o_res->dir_attr);
+        if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
+                server->caps &= ~NFS_CAP_POSIX_LOCK;
         if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
                 status = _nfs4_proc_open_confirm(data);
                 if (status != 0)
@@ -1664,7 +1666,7 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
         status = PTR_ERR(state);
         if (IS_ERR(state))
                 goto err_opendata_put;
-        if ((opendata->o_res.rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) != 0)
+        if (server->caps & NFS_CAP_POSIX_LOCK)
                 set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
         nfs4_opendata_put(opendata);
         nfs4_put_state_owner(sp);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 53ff70e23993..de38d63aa920 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -201,6 +201,7 @@ static int nfs_set_page_writeback(struct page *page)
                 struct inode *inode = page->mapping->host;
                 struct nfs_server *nfss = NFS_SERVER(inode);
 
+                page_cache_get(page);
                 if (atomic_long_inc_return(&nfss->writeback) >
                                 NFS_CONGESTION_ON_THRESH) {
                         set_bdi_congested(&nfss->backing_dev_info,
@@ -216,6 +217,7 @@ static void nfs_end_page_writeback(struct page *page)
         struct nfs_server *nfss = NFS_SERVER(inode);
 
         end_page_writeback(page);
+        page_cache_release(page);
         if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
                 clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
@@ -421,6 +423,7 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
         __set_page_dirty_nobuffers(req->wb_page);
+        __mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -660,9 +663,11 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
         req = nfs_setup_write_request(ctx, page, offset, count);
         if (IS_ERR(req))
                 return PTR_ERR(req);
+        nfs_mark_request_dirty(req);
         /* Update file length */
         nfs_grow_file(page, offset, count);
         nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
+        nfs_mark_request_dirty(req);
         nfs_clear_page_tag_locked(req);
         return 0;
 }
@@ -739,8 +744,6 @@ int nfs_updatepage(struct file *file, struct page *page,
         status = nfs_writepage_setup(ctx, page, offset, count);
         if (status < 0)
                 nfs_set_pageerror(page);
-        else
-                __set_page_dirty_nobuffers(page);
 
         dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
                         status, (long long)i_size_read(inode));
@@ -749,13 +752,12 @@ int nfs_updatepage(struct file *file, struct page *page,
 
 static void nfs_writepage_release(struct nfs_page *req)
 {
+        struct page *page = req->wb_page;
 
-        if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) {
-                nfs_end_page_writeback(req->wb_page);
+        if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req))
                 nfs_inode_remove_request(req);
-        } else
-                nfs_end_page_writeback(req->wb_page);
         nfs_clear_page_tag_locked(req);
+        nfs_end_page_writeback(page);
 }
 
 static int flush_task_priority(int how)
@@ -779,7 +781,6 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
                 int how)
 {
         struct inode *inode = req->wb_context->path.dentry->d_inode;
-        int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
         int priority = flush_task_priority(how);
         struct rpc_task *task;
         struct rpc_message msg = {
@@ -794,9 +795,10 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
                 .callback_ops = call_ops,
                 .callback_data = data,
                 .workqueue = nfsiod_workqueue,
-                .flags = flags,
+                .flags = RPC_TASK_ASYNC,
                 .priority = priority,
         };
+        int ret = 0;
 
         /* Set up the RPC argument and reply structs
          * NB: take care not to mess about with data->commit et al. */
@@ -835,10 +837,18 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
                 (unsigned long long)data->args.offset);
 
         task = rpc_run_task(&task_setup_data);
-        if (IS_ERR(task))
-                return PTR_ERR(task);
+        if (IS_ERR(task)) {
+                ret = PTR_ERR(task);
+                goto out;
+        }
+        if (how & FLUSH_SYNC) {
+                ret = rpc_wait_for_completion_task(task);
+                if (ret == 0)
+                        ret = task->tk_status;
+        }
         rpc_put_task(task);
-        return 0;
+out:
+        return ret;
 }
 
 /* If a nfs_flush_* function fails, it should remove reqs from @head and
@@ -847,9 +857,11 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
  */
 static void nfs_redirty_request(struct nfs_page *req)
 {
+        struct page *page = req->wb_page;
+
         nfs_mark_request_dirty(req);
-        nfs_end_page_writeback(req->wb_page);
         nfs_clear_page_tag_locked(req);
+        nfs_end_page_writeback(page);
 }
 
 /*
@@ -1084,16 +1096,15 @@ static void nfs_writeback_release_full(void *calldata)
                 if (nfs_write_need_commit(data)) {
                         memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
                         nfs_mark_request_commit(req);
-                        nfs_end_page_writeback(page);
                         dprintk(" marked for commit\n");
                         goto next;
                 }
                 dprintk(" OK\n");
 remove_request:
-                nfs_end_page_writeback(page);
                 nfs_inode_remove_request(req);
         next:
                 nfs_clear_page_tag_locked(req);
+                nfs_end_page_writeback(page);
         }
         nfs_writedata_release(calldata);
 }
@@ -1207,7 +1218,6 @@ static int nfs_commit_rpcsetup(struct list_head *head,
 {
         struct nfs_page *first = nfs_list_entry(head->next);
         struct inode *inode = first->wb_context->path.dentry->d_inode;
-        int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
         int priority = flush_task_priority(how);
         struct rpc_task *task;
         struct rpc_message msg = {
@@ -1222,7 +1232,7 @@ static int nfs_commit_rpcsetup(struct list_head *head,
                 .callback_ops = &nfs_commit_ops,
                 .callback_data = data,
                 .workqueue = nfsiod_workqueue,
-                .flags = flags,
+                .flags = RPC_TASK_ASYNC,
                 .priority = priority,
         };
 
@@ -1252,6 +1262,8 @@ static int nfs_commit_rpcsetup(struct list_head *head,
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
+        if (how & FLUSH_SYNC)
+                rpc_wait_for_completion_task(task);
         rpc_put_task(task);
         return 0;
 }
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 8d6356a804f3..7cfb87e692da 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -426,7 +426,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
         bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
         if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group),
                                     group_offset, bitmap))
-                printk(KERN_WARNING "%s: entry numer %llu already freed\n",
+                printk(KERN_WARNING "%s: entry number %llu already freed\n",
                        __func__, (unsigned long long)req->pr_entry_nr);
 
         nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 7cdd98b8d514..76c38e3e19d2 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1879,7 +1879,7 @@ static int nilfs_btree_propagate_v(struct nilfs_btree *btree,
                                    struct nilfs_btree_path *path,
                                    int level, struct buffer_head *bh)
 {
-        int maxlevel, ret;
+        int maxlevel = 0, ret;
         struct nilfs_btree_node *parent;
         struct inode *dat = nilfs_bmap_get_dat(&btree->bt_bmap);
         __u64 ptr;
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index c2ff1b306012..f90a33d9a5b0 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -649,7 +649,7 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
 long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
         struct inode *inode = filp->f_dentry->d_inode;
-        void __user *argp = (void * __user *)arg;
+        void __user *argp = (void __user *)arg;
 
         switch (cmd) {
         case NILFS_IOCTL_CHANGE_CPMODE:
diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index dad7fb247ddc..3e21b1e2ad3a 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -33,6 +33,14 @@ config PRINT_QUOTA_WARNING
           Note that this behavior is currently deprecated and may go away in
           future. Please use notification via netlink socket instead.
 
+config QUOTA_DEBUG
+        bool "Additional quota sanity checks"
+        depends on QUOTA
+        default n
+        help
+          If you say Y here, quota subsystem will perform some additional
+          sanity checks of quota internal structures. If unsure, say N.
+
 # Generic support for tree structured quota files. Selected when needed.
 config QUOTA_TREE
          tristate
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index e0b870f4749f..788b5802a7ce 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -80,8 +80,6 @@
 
 #include <asm/uaccess.h>
 
-#define __DQUOT_PARANOIA
-
 /*
  * There are three quota SMP locks. dq_list_lock protects all lists with quotas
  * and quota formats, dqstats structure containing statistics about the lists
@@ -695,7 +693,7 @@ void dqput(struct dquot *dquot)
 
         if (!dquot)
                 return;
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
         if (!atomic_read(&dquot->dq_count)) {
                 printk("VFS: dqput: trying to free free dquot\n");
                 printk("VFS: device %s, dquot of %s %d\n",
@@ -748,7 +746,7 @@ we_slept:
                 goto we_slept;
         }
         atomic_dec(&dquot->dq_count);
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
         /* sanity check */
         BUG_ON(!list_empty(&dquot->dq_free));
 #endif
@@ -845,7 +843,7 @@ we_slept:
                 dquot = NULL;
                 goto out;
         }
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
         BUG_ON(!dquot->dq_sb);  /* Has somebody invalidated entry under us? */
 #endif
 out:
@@ -874,14 +872,18 @@ static int dqinit_needed(struct inode *inode, int type)
 static void add_dquot_ref(struct super_block *sb, int type)
 {
         struct inode *inode, *old_inode = NULL;
+#ifdef CONFIG_QUOTA_DEBUG
         int reserved = 0;
+#endif
 
         spin_lock(&inode_lock);
         list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
                 if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
                         continue;
+#ifdef CONFIG_QUOTA_DEBUG
                 if (unlikely(inode_get_rsv_space(inode) > 0))
                         reserved = 1;
+#endif
                 if (!atomic_read(&inode->i_writecount))
                         continue;
                 if (!dqinit_needed(inode, type))
@@ -903,11 +905,13 @@ static void add_dquot_ref(struct super_block *sb, int type)
         spin_unlock(&inode_lock);
         iput(old_inode);
 
+#ifdef CONFIG_QUOTA_DEBUG
         if (reserved) {
                 printk(KERN_WARNING "VFS (%s): Writes happened before quota"
                         " was turned on thus quota information is probably "
                         "inconsistent. Please run quotacheck(8).\n", sb->s_id);
         }
+#endif
 }
 
 /*
@@ -934,7 +938,7 @@ static int remove_inode_dquot_ref(struct inode *inode, int type,
         inode->i_dquot[type] = NULL;
         if (dquot) {
                 if (dqput_blocks(dquot)) {
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
                         if (atomic_read(&dquot->dq_count) != 1)
                                 printk(KERN_WARNING "VFS: Adding dquot with dq_count %d to dispose list.\n", atomic_read(&dquot->dq_count));
 #endif
@@ -2322,34 +2326,34 @@ static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
         if (di->dqb_valid & QIF_SPACE) {
                 dm->dqb_curspace = di->dqb_curspace - dm->dqb_rsvspace;
                 check_blim = 1;
-                __set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
+                set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
         }
         if (di->dqb_valid & QIF_BLIMITS) {
                 dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
                 dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
                 check_blim = 1;
-                __set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
+                set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
         }
         if (di->dqb_valid & QIF_INODES) {
                 dm->dqb_curinodes = di->dqb_curinodes;
                 check_ilim = 1;
-                __set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
+                set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
         }
         if (di->dqb_valid & QIF_ILIMITS) {
                 dm->dqb_isoftlimit = di->dqb_isoftlimit;
                 dm->dqb_ihardlimit = di->dqb_ihardlimit;
                 check_ilim = 1;
-                __set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
+                set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
         }
         if (di->dqb_valid & QIF_BTIME) {
                 dm->dqb_btime = di->dqb_btime;
                 check_blim = 1;
-                __set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
+                set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
         }
         if (di->dqb_valid & QIF_ITIME) {
                 dm->dqb_itime = di->dqb_itime;
                 check_ilim = 1;
-                __set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
+                set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
         }
 
         if (check_blim) {
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 19626e2491c4..9a9378b4eb5a 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -125,9 +125,8 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
 
         mutex_lock(&sbi->s_alloc_mutex);
         partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
-        if (bloc->logicalBlockNum < 0 ||
-            (bloc->logicalBlockNum + count) >
-                partmap->s_partition_len) {
+        if (bloc->logicalBlockNum + count < count ||
+            (bloc->logicalBlockNum + count) > partmap->s_partition_len) {
                 udf_debug("%d < %d || %d + %d > %d\n",
                           bloc->logicalBlockNum, 0, bloc->logicalBlockNum,
                           count, partmap->s_partition_len);
@@ -393,9 +392,8 @@ static void udf_table_free_blocks(struct super_block *sb,
 
         mutex_lock(&sbi->s_alloc_mutex);
         partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
-        if (bloc->logicalBlockNum < 0 ||
-            (bloc->logicalBlockNum + count) >
-                partmap->s_partition_len) {
+        if (bloc->logicalBlockNum + count < count ||
+            (bloc->logicalBlockNum + count) > partmap->s_partition_len) {
                 udf_debug("%d < %d || %d + %d > %d\n",
                           bloc->logicalBlockNum, 0, bloc->logicalBlockNum, count,
                           partmap->s_partition_len);
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 1eb06774ed90..4b6a46ccbf46 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -218,7 +218,7 @@ const struct file_operations udf_file_operations = {
         .llseek                 = generic_file_llseek,
 };
 
-static int udf_setattr(struct dentry *dentry, struct iattr *iattr)
+int udf_setattr(struct dentry *dentry, struct iattr *iattr)
 {
         struct inode *inode = dentry->d_inode;
         int error;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index bb863fe579ac..8a3fbd177cab 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1314,7 +1314,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
                 break;
         case ICBTAG_FILE_TYPE_SYMLINK:
                 inode->i_data.a_ops = &udf_symlink_aops;
-                inode->i_op = &page_symlink_inode_operations;
+                inode->i_op = &udf_symlink_inode_operations;
                 inode->i_mode = S_IFLNK | S_IRWXUGO;
                 break;
         case ICBTAG_FILE_TYPE_MAIN:
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index db423ab078b1..75816025f95f 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -925,7 +925,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
         iinfo = UDF_I(inode);
         inode->i_mode = S_IFLNK | S_IRWXUGO;
         inode->i_data.a_ops = &udf_symlink_aops;
-        inode->i_op = &page_symlink_inode_operations;
+        inode->i_op = &udf_symlink_inode_operations;
 
         if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
                 struct kernel_lb_addr eloc;
@@ -1393,6 +1393,7 @@ const struct export_operations udf_export_ops = {
 const struct inode_operations udf_dir_inode_operations = {
         .lookup                         = udf_lookup,
         .create                         = udf_create,
+        .setattr                        = udf_setattr,
         .link                           = udf_link,
         .unlink                         = udf_unlink,
         .symlink                        = udf_symlink,
@@ -1401,3 +1402,9 @@ const struct inode_operations udf_dir_inode_operations = {
         .mknod                          = udf_mknod,
         .rename                         = udf_rename,
 };
+const struct inode_operations udf_symlink_inode_operations = {
+        .readlink       = generic_readlink,
+        .follow_link    = page_follow_link_light,
+        .put_link       = page_put_link,
+        .setattr        = udf_setattr,
+};
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 4223ac855da9..702a1148e702 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -76,6 +76,7 @@ extern const struct inode_operations udf_dir_inode_operations;
 extern const struct file_operations udf_dir_operations;
 extern const struct inode_operations udf_file_inode_operations;
 extern const struct file_operations udf_file_operations;
+extern const struct inode_operations udf_symlink_inode_operations;
 extern const struct address_space_operations udf_aops;
 extern const struct address_space_operations udf_adinicb_aops;
 extern const struct address_space_operations udf_symlink_aops;
@@ -131,7 +132,7 @@ extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
 /* file.c */
 extern int udf_ioctl(struct inode *, struct file *, unsigned int,
                      unsigned long);
-
+extern int udf_setattr(struct dentry *dentry, struct iattr *iattr);
 /* inode.c */
 extern struct inode *udf_iget(struct super_block *, struct kernel_lb_addr *);
 extern int udf_sync_inode(struct inode *);
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 05cd85317f6f..fd9698215759 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -820,10 +820,10 @@ xfs_reclaim_inode(
          * call into reclaim to find it in a clean state instead of waiting for
          * it now. We also don't return errors here - if the error is transient
          * then the next reclaim pass will flush the inode, and if the error
-         * is permanent then the next sync reclaim will relcaim the inode and
+         * is permanent then the next sync reclaim will reclaim the inode and
          * pass on the error.
          */
-        if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+        if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
                 xfs_fs_cmn_err(CE_WARN, ip->i_mount,
                         "inode 0x%llx background reclaim flush failed with %d",
                         (long long)ip->i_ino, error);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index e8fba92d7cd9..2be019136287 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -745,9 +745,16 @@ xfs_log_move_tail(xfs_mount_t	*mp,
 
 /*
  * Determine if we have a transaction that has gone to disk
- * that needs to be covered. Log activity needs to be idle (no AIL and
- * nothing in the iclogs). And, we need to be in the right state indicating
- * something has gone out.
+ * that needs to be covered. To begin the transition to the idle state
+ * firstly the log needs to be idle (no AIL and nothing in the iclogs).
+ * If we are then in a state where covering is needed, the caller is informed
+ * that dummy transactions are required to move the log into the idle state.
+ *
+ * Because this is called as part of the sync process, we should also indicate
+ * that dummy transactions should be issued in anything but the covered or
+ * idle states. This ensures that the log tail is accurately reflected in
+ * the log at the end of the sync, hence if a crash occurrs avoids replay
+ * of transactions where the metadata is already on disk.
  */
 int
 xfs_log_need_covered(xfs_mount_t *mp)
@@ -759,17 +766,24 @@ xfs_log_need_covered(xfs_mount_t *mp)
                 return 0;
 
         spin_lock(&log->l_icloglock);
-        if (((log->l_covered_state == XLOG_STATE_COVER_NEED) ||
-                (log->l_covered_state == XLOG_STATE_COVER_NEED2))
-                        && !xfs_trans_ail_tail(log->l_ailp)
-                        && xlog_iclogs_empty(log)) {
-                if (log->l_covered_state == XLOG_STATE_COVER_NEED)
-                        log->l_covered_state = XLOG_STATE_COVER_DONE;
-                else {
-                        ASSERT(log->l_covered_state == XLOG_STATE_COVER_NEED2);
-                        log->l_covered_state = XLOG_STATE_COVER_DONE2;
+        switch (log->l_covered_state) {
+        case XLOG_STATE_COVER_DONE:
+        case XLOG_STATE_COVER_DONE2:
+        case XLOG_STATE_COVER_IDLE:
+                break;
+        case XLOG_STATE_COVER_NEED:
+        case XLOG_STATE_COVER_NEED2:
+                if (!xfs_trans_ail_tail(log->l_ailp) &&
+                    xlog_iclogs_empty(log)) {
+                        if (log->l_covered_state == XLOG_STATE_COVER_NEED)
+                                log->l_covered_state = XLOG_STATE_COVER_DONE;
+                        else
+                                log->l_covered_state = XLOG_STATE_COVER_DONE2;
                 }
+                /* FALLTHRU */
+        default:
                 needed = 1;
+                break;
         }
         spin_unlock(&log->l_icloglock);
         return needed;