13 files changed, 86 insertions, 52 deletions

diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index d61e3b28ce3..36d961f342a 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -146,7 +146,7 @@ static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
                 while (rdir->head < rdir->tail) {
                         p9stat_init(&st);
                         err = p9stat_read(rdir->buf + rdir->head,
-                                                buflen - rdir->head, &st,
+                                                rdir->tail - rdir->head, &st,
                                                 fid->clnt->proto_version);
                         if (err) {
                                 P9_DPRINTK(P9_DEBUG_VFS, "returned %d\n", err);
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 04b8280582a..bc87b9c1d27 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -2,7 +2,7 @@ config CEPH_FS
         tristate "Ceph distributed file system (EXPERIMENTAL)"
         depends on INET && EXPERIMENTAL
         select LIBCRC32C
-        select CONFIG_CRYPTO_AES
+        select CRYPTO_AES
         help
           Choose Y or M here to include support for mounting the
           experimental Ceph distributed file system.  Ceph is an extremely
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 74144d6389f..b81be9a5648 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -627,7 +627,7 @@ retry:
         if (fmode >= 0)
                 __ceph_get_fmode(ci, fmode);
         spin_unlock(&inode->i_lock);
-        wake_up(&ci->i_cap_wq);
+        wake_up_all(&ci->i_cap_wq);
         return 0;
 }
 
@@ -1181,7 +1181,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
         }
 
         if (wake)
-                wake_up(&ci->i_cap_wq);
+                wake_up_all(&ci->i_cap_wq);
 
         return delayed;
 }
@@ -2153,7 +2153,7 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
         else if (flushsnaps)
                 ceph_flush_snaps(ci);
         if (wake)
-                wake_up(&ci->i_cap_wq);
+                wake_up_all(&ci->i_cap_wq);
         if (put)
                 iput(inode);
 }
@@ -2229,7 +2229,7 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
                 iput(inode);
         } else if (complete_capsnap) {
                 ceph_flush_snaps(ci);
-                wake_up(&ci->i_cap_wq);
+                wake_up_all(&ci->i_cap_wq);
         }
         if (drop_capsnap)
                 iput(inode);
@@ -2405,7 +2405,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
         if (queue_invalidate)
                 ceph_queue_invalidate(inode);
         if (wake)
-                wake_up(&ci->i_cap_wq);
+                wake_up_all(&ci->i_cap_wq);
 
         if (check_caps == 1)
                 ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_AUTHONLY,
@@ -2460,7 +2460,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
                                          struct ceph_inode_info,
                                          i_flushing_item)->vfs_inode);
                 mdsc->num_cap_flushing--;
-                wake_up(&mdsc->cap_flushing_wq);
+                wake_up_all(&mdsc->cap_flushing_wq);
                 dout(" inode %p now !flushing\n", inode);
 
                 if (ci->i_dirty_caps == 0) {
@@ -2472,7 +2472,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
                 }
         }
         spin_unlock(&mdsc->cap_dirty_lock);
-        wake_up(&ci->i_cap_wq);
+        wake_up_all(&ci->i_cap_wq);
 
 out:
         spin_unlock(&inode->i_lock);
@@ -2984,6 +2984,7 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
                 memcpy(*p, dentry->d_name.name, dentry->d_name.len);
                 *p += dentry->d_name.len;
                 rel->dname_seq = cpu_to_le32(di->lease_seq);
+                __ceph_mdsc_drop_dentry_lease(dentry);
         }
         spin_unlock(&dentry->d_lock);
         return ret;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index f85719310db..f94ed3c7f6a 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -266,6 +266,7 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
         spin_lock(&inode->i_lock);
         if ((filp->f_pos == 2 || fi->dentry) &&
             !ceph_test_opt(client, NOASYNCREADDIR) &&
+            ceph_snap(inode) != CEPH_SNAPDIR &&
             (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
             __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
                 err = __dcache_readdir(filp, dirent, filldir);
@@ -1013,18 +1014,22 @@ out_touch:
 
 /*
  * When a dentry is released, clear the dir I_COMPLETE if it was part
- * of the current dir gen.
+ * of the current dir gen or if this is in the snapshot namespace.
  */
 static void ceph_dentry_release(struct dentry *dentry)
 {
         struct ceph_dentry_info *di = ceph_dentry(dentry);
         struct inode *parent_inode = dentry->d_parent->d_inode;
+        u64 snapid = ceph_snap(parent_inode);
 
-        if (parent_inode) {
+        dout("dentry_release %p parent %p\n", dentry, parent_inode);
+
+        if (parent_inode && snapid != CEPH_SNAPDIR) {
                 struct ceph_inode_info *ci = ceph_inode(parent_inode);
 
                 spin_lock(&parent_inode->i_lock);
-                if (ci->i_shared_gen == di->lease_shared_gen) {
+                if (ci->i_shared_gen == di->lease_shared_gen ||
+                    snapid <= CEPH_MAXSNAP) {
                         dout(" clearing %p complete (d_release)\n",
                              parent_inode);
                         ci->i_ceph_flags &= ~CEPH_I_COMPLETE;
@@ -1241,7 +1246,9 @@ struct dentry_operations ceph_dentry_ops = {
 
 struct dentry_operations ceph_snapdir_dentry_ops = {
         .d_revalidate = ceph_snapdir_d_revalidate,
+        .d_release = ceph_dentry_release,
 };
 
 struct dentry_operations ceph_snap_dentry_ops = {
+        .d_release = ceph_dentry_release,
 };
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 6251a1574b9..7c08698fad3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -265,7 +265,7 @@ int ceph_release(struct inode *inode, struct file *file)
         kmem_cache_free(ceph_file_cachep, cf);
 
         /* wake up anyone waiting for caps on this inode */
-        wake_up(&ci->i_cap_wq);
+        wake_up_all(&ci->i_cap_wq);
         return 0;
 }
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8f9b9fe8ef9..389f9dbd994 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1199,8 +1199,10 @@ retry_lookup:
                                 goto out;
                         }
                         err = ceph_init_dentry(dn);
-                        if (err < 0)
+                        if (err < 0) {
+                                dput(dn);
                                 goto out;
+                        }
                 } else if (dn->d_inode &&
                            (ceph_ino(dn->d_inode) != vino.ino ||
                             ceph_snap(dn->d_inode) != vino.snap)) {
@@ -1499,7 +1501,7 @@ retry:
         if (wrbuffer_refs == 0)
                 ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
         if (wake)
-                wake_up(&ci->i_cap_wq);
+                wake_up_all(&ci->i_cap_wq);
 }
 
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 416c08d315d..dd440bd438a 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -868,7 +868,7 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap,
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
 
-        wake_up(&ci->i_cap_wq);
+        wake_up_all(&ci->i_cap_wq);
         if (arg) {
                 spin_lock(&inode->i_lock);
                 ci->i_wanted_max_size = 0;
@@ -1564,7 +1564,7 @@ static void complete_request(struct ceph_mds_client *mdsc,
         if (req->r_callback)
                 req->r_callback(mdsc, req);
         else
-                complete(&req->r_completion);
+                complete_all(&req->r_completion);
 }
 
 /*
@@ -1932,7 +1932,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
         if (head->safe) {
                 req->r_got_safe = true;
                 __unregister_request(mdsc, req);
-                complete(&req->r_safe_completion);
+                complete_all(&req->r_safe_completion);
 
                 if (req->r_got_unsafe) {
                         /*
@@ -1947,7 +1947,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
                         /* last unsafe request during umount? */
                         if (mdsc->stopping && !__get_oldest_req(mdsc))
-                                complete(&mdsc->safe_umount_waiters);
+                                complete_all(&mdsc->safe_umount_waiters);
                         mutex_unlock(&mdsc->mutex);
                         goto out;
                 }
@@ -2126,7 +2126,7 @@ static void handle_session(struct ceph_mds_session *session,
                         pr_info("mds%d reconnect denied\n", session->s_mds);
                 remove_session_caps(session);
                 wake = 1; /* for good measure */
-                complete(&mdsc->session_close_waiters);
+                complete_all(&mdsc->session_close_waiters);
                 kick_requests(mdsc, mds);
                 break;
 
diff --git a/fs/ceph/mon_client.c b/fs/ceph/mon_client.c
index cc115eafae1..54fe01c5070 100644
--- a/fs/ceph/mon_client.c
+++ b/fs/ceph/mon_client.c
@@ -345,7 +345,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 
 out:
         mutex_unlock(&monc->mutex);
-        wake_up(&client->auth_wq);
+        wake_up_all(&client->auth_wq);
 }
 
 /*
@@ -462,7 +462,7 @@ static void handle_statfs_reply(struct ceph_mon_client *monc,
         }
         mutex_unlock(&monc->mutex);
         if (req) {
-                complete(&req->completion);
+                complete_all(&req->completion);
                 put_generic_request(req);
         }
         return;
@@ -718,7 +718,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
                                      monc->m_auth->front_max);
         if (ret < 0) {
                 monc->client->auth_err = ret;
-                wake_up(&monc->client->auth_wq);
+                wake_up_all(&monc->client->auth_wq);
         } else if (ret > 0) {
                 __send_prepared_auth_request(monc, ret);
         } else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) {
diff --git a/fs/ceph/osd_client.c b/fs/ceph/osd_client.c
index 92b7251a53f..e3852234789 100644
--- a/fs/ceph/osd_client.c
+++ b/fs/ceph/osd_client.c
@@ -862,12 +862,12 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
         if (req->r_callback)
                 req->r_callback(req, msg);
         else
-                complete(&req->r_completion);
+                complete_all(&req->r_completion);
 
         if (flags & CEPH_OSD_FLAG_ONDISK) {
                 if (req->r_safe_callback)
                         req->r_safe_callback(req, msg);
-                complete(&req->r_safe_completion);  /* fsync waiter */
+                complete_all(&req->r_safe_completion);  /* fsync waiter */
         }
 
 done:
@@ -1083,7 +1083,7 @@ done:
         if (newmap)
                 kick_requests(osdc, NULL);
         up_read(&osdc->map_sem);
-        wake_up(&osdc->client->auth_wq);
+        wake_up_all(&osdc->client->auth_wq);
         return;
 
 bad:
diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index 277f8b33957..416d46adbf8 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -831,12 +831,13 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
                 /* remove any? */
                 while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping,
                                                 node)->pgid, pgid) <= 0) {
-                        struct rb_node *cur = rbp;
+                        struct ceph_pg_mapping *cur =
+                                rb_entry(rbp, struct ceph_pg_mapping, node);
+                        
                         rbp = rb_next(rbp);
-                        dout(" removed pg_temp %llx\n",
-                             *(u64 *)&rb_entry(cur, struct ceph_pg_mapping,
-                                               node)->pgid);
-                        rb_erase(cur, &map->pg_temp);
+                        dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
+                        rb_erase(&cur->node, &map->pg_temp);
+                        kfree(cur);
                 }
 
                 if (pglen) {
@@ -852,19 +853,22 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
                         for (j = 0; j < pglen; j++)
                                 pg->osds[j] = ceph_decode_32(p);
                         err = __insert_pg_mapping(pg, &map->pg_temp);
-                        if (err)
+                        if (err) {
+                                kfree(pg);
                                 goto bad;
+                        }
                         dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid,
                              pglen);
                 }
         }
         while (rbp) {
-                struct rb_node *cur = rbp;
+                struct ceph_pg_mapping *cur =
+                        rb_entry(rbp, struct ceph_pg_mapping, node);
+
                 rbp = rb_next(rbp);
-                dout(" removed pg_temp %llx\n",
-                     *(u64 *)&rb_entry(cur, struct ceph_pg_mapping,
-                                       node)->pgid);
-                rb_erase(cur, &map->pg_temp);
+                dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
+                rb_erase(&cur->node, &map->pg_temp);
+                kfree(cur);
         }
 
         /* ignore the rest */
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 2d8dbce9d48..46c4dd8dfcc 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -31,9 +31,9 @@ static struct mutex ecryptfs_msg_ctx_lists_mux;
 
 static struct hlist_head *ecryptfs_daemon_hash;
 struct mutex ecryptfs_daemon_hash_mux;
-static int ecryptfs_hash_buckets;
+static int ecryptfs_hash_bits;
 #define ecryptfs_uid_hash(uid) \
-        hash_long((unsigned long)uid, ecryptfs_hash_buckets)
+        hash_long((unsigned long)uid, ecryptfs_hash_bits)
 
 static u32 ecryptfs_msg_counter;
 static struct ecryptfs_msg_ctx *ecryptfs_msg_ctx_arr;
@@ -486,18 +486,19 @@ int ecryptfs_init_messaging(void)
         }
         mutex_init(&ecryptfs_daemon_hash_mux);
         mutex_lock(&ecryptfs_daemon_hash_mux);
-        ecryptfs_hash_buckets = 1;
-        while (ecryptfs_number_of_users >> ecryptfs_hash_buckets)
-                ecryptfs_hash_buckets++;
+        ecryptfs_hash_bits = 1;
+        while (ecryptfs_number_of_users >> ecryptfs_hash_bits)
+                ecryptfs_hash_bits++;
         ecryptfs_daemon_hash = kmalloc((sizeof(struct hlist_head)
-                                        * ecryptfs_hash_buckets), GFP_KERNEL);
+                                        * (1 << ecryptfs_hash_bits)),
+                                       GFP_KERNEL);
         if (!ecryptfs_daemon_hash) {
                 rc = -ENOMEM;
                 printk(KERN_ERR "%s: Failed to allocate memory\n", __func__);
                 mutex_unlock(&ecryptfs_daemon_hash_mux);
                 goto out;
         }
-        for (i = 0; i < ecryptfs_hash_buckets; i++)
+        for (i = 0; i < (1 << ecryptfs_hash_bits); i++)
                 INIT_HLIST_HEAD(&ecryptfs_daemon_hash[i]);
         mutex_unlock(&ecryptfs_daemon_hash_mux);
         ecryptfs_msg_ctx_arr = kmalloc((sizeof(struct ecryptfs_msg_ctx)
@@ -554,7 +555,7 @@ void ecryptfs_release_messaging(void)
                 int i;
 
                 mutex_lock(&ecryptfs_daemon_hash_mux);
-                for (i = 0; i < ecryptfs_hash_buckets; i++) {
+                for (i = 0; i < (1 << ecryptfs_hash_bits); i++) {
                         int rc;
 
                         hlist_for_each_entry(daemon, elem,
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 26ca3361a8b..6b48d7c268b 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1231,6 +1231,25 @@ static int do_filldir_main(struct gfs2_inode *dip, u64 *offset,
         return 0;
 }
 
+static void *gfs2_alloc_sort_buffer(unsigned size)
+{
+        void *ptr = NULL;
+
+        if (size < KMALLOC_MAX_SIZE)
+                ptr = kmalloc(size, GFP_NOFS | __GFP_NOWARN);
+        if (!ptr)
+                ptr = __vmalloc(size, GFP_NOFS, PAGE_KERNEL);
+        return ptr;
+}
+
+static void gfs2_free_sort_buffer(void *ptr)
+{
+        if (is_vmalloc_addr(ptr))
+                vfree(ptr);
+        else
+                kfree(ptr);
+}
+
 static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
                               filldir_t filldir, int *copied, unsigned *depth,
                               u64 leaf_no)
@@ -1271,7 +1290,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
          * 99 is the maximum number of entries that can fit in a single
          * leaf block.
          */
-        larr = vmalloc((leaves + entries + 99) * sizeof(void *));
+        larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *));
         if (!larr)
                 goto out;
         darr = (const struct gfs2_dirent **)(larr + leaves);
@@ -1282,7 +1301,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
         do {
                 error = get_leaf(ip, lfn, &bh);
                 if (error)
-                        goto out_kfree;
+                        goto out_free;
                 lf = (struct gfs2_leaf *)bh->b_data;
                 lfn = be64_to_cpu(lf->lf_next);
                 if (lf->lf_entries) {
@@ -1291,7 +1310,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
                                                 gfs2_dirent_gather, NULL, &g);
                         error = PTR_ERR(dent);
                         if (IS_ERR(dent))
-                                goto out_kfree;
+                                goto out_free;
                         if (entries2 != g.offset) {
                                 fs_warn(sdp, "Number of entries corrupt in dir "
                                                 "leaf %llu, entries2 (%u) != "
@@ -1300,7 +1319,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
                                         entries2, g.offset);
                                         
                                 error = -EIO;
-                                goto out_kfree;
+                                goto out_free;
                         }
                         error = 0;
                         larr[leaf++] = bh;
@@ -1312,10 +1331,10 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
         BUG_ON(entries2 != entries);
         error = do_filldir_main(ip, offset, opaque, filldir, darr,
                                 entries, copied);
-out_kfree:
+out_free:
         for(i = 0; i < leaf; i++)
                 brelse(larr[i]);
-        vfree(larr);
+        gfs2_free_sort_buffer(larr);
 out:
         return error;
 }
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 9b58d38bc91..fff6572676a 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -176,7 +176,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
                 if (tracer)
                         tpid = task_pid_nr_ns(tracer, ns);
         }
-        cred = get_cred((struct cred *) __task_cred(p));
+        cred = get_task_cred(p);
         seq_printf(m,
                 "State:\t%s\n"
                 "Tgid:\t%d\n"