24 files changed, 204 insertions, 153 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 272b9b2bea86..59cba180fe83 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3099,8 +3099,12 @@ static void inode_tree_add(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_inode *entry;
-        struct rb_node **p = &root->inode_tree.rb_node;
-        struct rb_node *parent = NULL;
+        struct rb_node **p;
+        struct rb_node *parent;
+
+again:
+        p = &root->inode_tree.rb_node;
+        parent = NULL;
 
         spin_lock(&root->inode_lock);
         while (*p) {
@@ -3108,13 +3112,16 @@ static void inode_tree_add(struct inode *inode)
                 entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
                 if (inode->i_ino < entry->vfs_inode.i_ino)
-                        p = &(*p)->rb_left;
+                        p = &parent->rb_left;
                 else if (inode->i_ino > entry->vfs_inode.i_ino)
-                        p = &(*p)->rb_right;
+                        p = &parent->rb_right;
                 else {
                         WARN_ON(!(entry->vfs_inode.i_state &
                                   (I_WILL_FREE | I_FREEING | I_CLEAR)));
-                        break;
+                        rb_erase(parent, &root->inode_tree);
+                        RB_CLEAR_NODE(parent);
+                        spin_unlock(&root->inode_lock);
+                        goto again;
                 }
         }
         rb_link_node(&BTRFS_I(inode)->rb_node, parent, p);
@@ -3126,12 +3133,12 @@ static void inode_tree_del(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
 
+        spin_lock(&root->inode_lock);
         if (!RB_EMPTY_NODE(&BTRFS_I(inode)->rb_node)) {
-                spin_lock(&root->inode_lock);
                 rb_erase(&BTRFS_I(inode)->rb_node, &root->inode_tree);
-                spin_unlock(&root->inode_lock);
                 RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
         }
+        spin_unlock(&root->inode_lock);
 }
 
 static noinline void init_btrfs_i(struct inode *inode)
diff --git a/fs/buffer.c b/fs/buffer.c
index a3ef091a45bd..28f320fac4d4 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1165,8 +1165,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
 
         if (!test_set_buffer_dirty(bh)) {
                 struct page *page = bh->b_page;
-                if (!TestSetPageDirty(page))
-                        __set_page_dirty(page, page_mapping(page), 0);
+                if (!TestSetPageDirty(page)) {
+                        struct address_space *mapping = page_mapping(page);
+                        if (mapping)
+                                __set_page_dirty(page, mapping, 0);
+                }
         }
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index 4a8849e45b21..fb4f3cdda78c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -678,8 +678,8 @@ exit:
 }
 EXPORT_SYMBOL(open_exec);
 
-int kernel_read(struct file *file, unsigned long offset,
-        char *addr, unsigned long count)
+int kernel_read(struct file *file, loff_t offset,
+                char *addr, unsigned long count)
 {
         mm_segment_t old_fs;
         loff_t pos = offset;
diff --git a/fs/ext3/Kconfig b/fs/ext3/Kconfig
index fb3c1a21b135..522b15498f45 100644
--- a/fs/ext3/Kconfig
+++ b/fs/ext3/Kconfig
@@ -29,23 +29,25 @@ config EXT3_FS
           module will be called ext3.
 
 config EXT3_DEFAULTS_TO_ORDERED
-        bool "Default to 'data=ordered' in ext3 (legacy option)"
+        bool "Default to 'data=ordered' in ext3"
         depends on EXT3_FS
         help
-          If a filesystem does not explicitly specify a data ordering
-          mode, and the journal capability allowed it, ext3 used to
-          historically default to 'data=ordered'.
-
-          That was a rather unfortunate choice, because it leads to all
-          kinds of latency problems, and the 'data=writeback' mode is more
-          appropriate these days.
-
-          You should probably always answer 'n' here, and if you really
-          want to use 'data=ordered' mode, set it in the filesystem itself
-          with 'tune2fs -o journal_data_ordered'.
-
-          But if you really want to enable the legacy default, you can do
-          so by answering 'y' to this question.
+          The journal mode options for ext3 have different tradeoffs
+          between when data is guaranteed to be on disk and
+          performance.  The use of "data=writeback" can cause
+          unwritten data to appear in files after an system crash or
+          power failure, which can be a security issue.  However,
+          "data=ordered" mode can also result in major performance
+          problems, including seconds-long delays before an fsync()
+          call returns.  For details, see:
+
+          http://ext4.wiki.kernel.org/index.php/Ext3_data_mode_tradeoffs
+
+          If you have been historically happy with ext3's performance,
+          data=ordered mode will be a safe choice and you should
+          answer 'y' here.  If you understand the reliability and data
+          privacy issues of data=writeback and are willing to make
+          that trade off, answer 'n'.
 
 config EXT3_FS_XATTR
         bool "Ext3 extended attributes"
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 524b349c6299..a8d80a7f1105 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -543,6 +543,19 @@ static inline void ext3_show_quota_options(struct seq_file *seq, struct super_bl
 #endif
 }
 
+static char *data_mode_string(unsigned long mode)
+{
+        switch (mode) {
+        case EXT3_MOUNT_JOURNAL_DATA:
+                return "journal";
+        case EXT3_MOUNT_ORDERED_DATA:
+                return "ordered";
+        case EXT3_MOUNT_WRITEBACK_DATA:
+                return "writeback";
+        }
+        return "unknown";
+}
+
 /*
  * Show an option if
  *  - it's set to a non-default value OR
@@ -616,13 +629,8 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
         if (test_opt(sb, NOBH))
                 seq_puts(seq, ",nobh");
 
-        if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
-                seq_puts(seq, ",data=journal");
-        else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
-                seq_puts(seq, ",data=ordered");
-        else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
-                seq_puts(seq, ",data=writeback");
-
+        seq_printf(seq, ",data=%s", data_mode_string(sbi->s_mount_opt &
+                                                     EXT3_MOUNT_DATA_FLAGS));
         if (test_opt(sb, DATA_ERR_ABORT))
                 seq_puts(seq, ",data_err=abort");
 
@@ -1024,12 +1032,18 @@ static int parse_options (char *options, struct super_block *sb,
                 datacheck:
                         if (is_remount) {
                                 if ((sbi->s_mount_opt & EXT3_MOUNT_DATA_FLAGS)
-                                                != data_opt) {
-                                        printk(KERN_ERR
-                                                "EXT3-fs: cannot change data "
-                                                "mode on remount\n");
-                                        return 0;
-                                }
+                                                == data_opt)
+                                        break;
+                                printk(KERN_ERR
+                                        "EXT3-fs (device %s): Cannot change "
+                                        "data mode on remount. The filesystem "
+                                        "is mounted in data=%s mode and you "
+                                        "try to remount it in data=%s mode.\n",
+                                        sb->s_id,
+                                        data_mode_string(sbi->s_mount_opt &
+                                                        EXT3_MOUNT_DATA_FLAGS),
+                                        data_mode_string(data_opt));
+                                return 0;
                         } else {
                                 sbi->s_mount_opt &= ~EXT3_MOUNT_DATA_FLAGS;
                                 sbi->s_mount_opt |= data_opt;
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 23419dc3027b..a7cbfbd340c7 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -386,16 +386,16 @@ static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
 #define GDLM_ATTR(_name,_mode,_show,_store) \
 static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-GDLM_ATTR(proto_name,     0444, proto_name_show,        NULL);
-GDLM_ATTR(block,          0644, block_show,             block_store);
-GDLM_ATTR(withdraw,       0644, withdraw_show,          withdraw_store);
-GDLM_ATTR(id,             0444, lkid_show,              NULL);
-GDLM_ATTR(jid,            0444, jid_show,               NULL);
-GDLM_ATTR(first,          0444, lkfirst_show,           NULL);
-GDLM_ATTR(first_done,     0444, first_done_show,        NULL);
-GDLM_ATTR(recover,        0200, NULL,                   recover_store);
-GDLM_ATTR(recover_done,   0444, recover_done_show,      NULL);
-GDLM_ATTR(recover_status, 0444, recover_status_show,    NULL);
+GDLM_ATTR(proto_name,           0444, proto_name_show,          NULL);
+GDLM_ATTR(block,                0644, block_show,               block_store);
+GDLM_ATTR(withdraw,             0644, withdraw_show,            withdraw_store);
+GDLM_ATTR(id,                   0444, lkid_show,                NULL);
+GDLM_ATTR(jid,                  0444, jid_show,                 NULL);
+GDLM_ATTR(first,                0444, lkfirst_show,             NULL);
+GDLM_ATTR(first_done,           0444, first_done_show,          NULL);
+GDLM_ATTR(recover,              0600, NULL,                     recover_store);
+GDLM_ATTR(recover_done,         0444, recover_done_show,        NULL);
+GDLM_ATTR(recover_status,       0444, recover_status_show,      NULL);
 
 static struct attribute *lock_module_attrs[] = {
         &gdlm_attr_proto_name.attr,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 941c8425c10b..cb88dac8ccaa 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -935,26 +935,28 @@ static int can_do_hugetlb_shm(void)
         return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
 }
 
-struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag)
+struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
+                                                struct user_struct **user)
 {
         int error = -ENOMEM;
-        int unlock_shm = 0;
         struct file *file;
         struct inode *inode;
         struct dentry *dentry, *root;
         struct qstr quick_string;
-        struct user_struct *user = current_user();
 
+        *user = NULL;
         if (!hugetlbfs_vfsmount)
                 return ERR_PTR(-ENOENT);
 
         if (!can_do_hugetlb_shm()) {
-                if (user_shm_lock(size, user)) {
-                        unlock_shm = 1;
+                *user = current_user();
+                if (user_shm_lock(size, *user)) {
                         WARN_ONCE(1,
                           "Using mlock ulimits for SHM_HUGETLB deprecated\n");
-                } else
+                } else {
+                        *user = NULL;
                         return ERR_PTR(-EPERM);
+                }
         }
 
         root = hugetlbfs_vfsmount->mnt_root;
@@ -996,8 +998,10 @@ out_inode:
 out_dentry:
         dput(dentry);
 out_shm_unlock:
-        if (unlock_shm)
-                user_shm_unlock(size, user);
+        if (*user) {
+                user_shm_unlock(size, *user);
+                *user = NULL;
+        }
         return ERR_PTR(error);
 }
 
diff --git a/fs/libfs.c b/fs/libfs.c
index ddfa89948c3f..dcec3d3ea64f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -217,7 +217,7 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name,
                 return PTR_ERR(s);
 
         s->s_flags = MS_NOUSER;
-        s->s_maxbytes = ~0ULL;
+        s->s_maxbytes = MAX_LFS_FILESIZE;
         s->s_blocksize = PAGE_SIZE;
         s->s_blocksize_bits = PAGE_SHIFT;
         s->s_magic = magic;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 65ca8c18476f..1434080aefeb 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1250,8 +1250,8 @@ static void nfs4_state_manager(struct nfs_client *clp)
                                 continue;
                 }
                 /* Initialize or reset the session */
-                if (nfs4_has_session(clp) &&
-                   test_and_clear_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) {
+                if (test_and_clear_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)
+                   && nfs4_has_session(clp)) {
                         if (clp->cl_cons_state == NFS_CS_SESSION_INITING)
                                 status = nfs4_initialize_session(clp);
                         else
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 8e2ec43b18f4..151964f0de4c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -416,8 +416,10 @@ int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno)
         if (unlikely(err))
                 goto failed;
 
+        down_read(&nilfs->ns_segctor_sem);
         err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, cno, 0, &raw_cp,
                                           &bh_cp);
+        up_read(&nilfs->ns_segctor_sem);
         if (unlikely(err)) {
                 if (err == -ENOENT || err == -EINVAL) {
                         printk(KERN_ERR
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index e8adbffc626f..1b9caafb8662 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -253,7 +253,7 @@ nilfs_detach_writer(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
 
 static inline void nilfs_put_sbinfo(struct nilfs_sb_info *sbi)
 {
-        if (!atomic_dec_and_test(&sbi->s_count))
+        if (atomic_dec_and_test(&sbi->s_count))
                 kfree(sbi);
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 47cd258fd24d..5dcbafe72d71 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -62,13 +62,14 @@ static int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_ev
         event_priv->wd = wd;
 
         ret = fsnotify_add_notify_event(group, event, fsn_event_priv);
-        /* EEXIST is not an error */
-        if (ret == -EEXIST)
-                ret = 0;
-
-        /* did event_priv get attached? */
-        if (list_empty(&fsn_event_priv->event_list))
+        if (ret) {
                 inotify_free_event_priv(fsn_event_priv);
+                /* EEXIST says we tail matched, EOVERFLOW isn't something
+                 * to report up the stack. */
+                if ((ret == -EEXIST) ||
+                    (ret == -EOVERFLOW))
+                        ret = 0;
+        }
 
         /*
          * If we hold the entry until after the event is on the queue
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index f30d9bbc2e1b..dc32ed8323ba 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -386,6 +386,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
         struct fsnotify_event *ignored_event;
         struct inotify_event_private_data *event_priv;
         struct fsnotify_event_private_data *fsn_event_priv;
+        int ret;
 
         ignored_event = fsnotify_create_event(NULL, FS_IN_IGNORED, NULL,
                                               FSNOTIFY_EVENT_NONE, NULL, 0,
@@ -404,10 +405,8 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
         fsn_event_priv->group = group;
         event_priv->wd = ientry->wd;
 
-        fsnotify_add_notify_event(group, ignored_event, fsn_event_priv);
-
-        /* did the private data get added? */
-        if (list_empty(&fsn_event_priv->event_list))
+        ret = fsnotify_add_notify_event(group, ignored_event, fsn_event_priv);
+        if (ret)
                 inotify_free_event_priv(fsn_event_priv);
 
 skip_send_ignore:
@@ -568,7 +567,7 @@ static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsign
 
         spin_lock_init(&group->inotify_data.idr_lock);
         idr_init(&group->inotify_data.idr);
-        group->inotify_data.last_wd = 0;
+        group->inotify_data.last_wd = 1;
         group->inotify_data.user = user;
         group->inotify_data.fa = NULL;
 
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 521368574e97..3816d5750dd5 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -153,6 +153,10 @@ static bool event_compare(struct fsnotify_event *old, struct fsnotify_event *new
                                 return true;
                         break;
                 case (FSNOTIFY_EVENT_NONE):
+                        if (old->mask & FS_Q_OVERFLOW)
+                                return true;
+                        else if (old->mask & FS_IN_IGNORED)
+                                return false;
                         return false;
                 };
         }
@@ -171,9 +175,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_even
         struct list_head *list = &group->notification_list;
         struct fsnotify_event_holder *last_holder;
         struct fsnotify_event *last_event;
-
-        /* easy to tell if priv was attached to the event */
-        INIT_LIST_HEAD(&priv->event_list);
+        int ret = 0;
 
         /*
          * There is one fsnotify_event_holder embedded inside each fsnotify_event.
@@ -194,6 +196,7 @@ alloc_holder:
 
         if (group->q_len >= group->max_events) {
                 event = &q_overflow_event;
+                ret = -EOVERFLOW;
                 /* sorry, no private data on the overflow event */
                 priv = NULL;
         }
@@ -235,7 +238,7 @@ alloc_holder:
         mutex_unlock(&group->notification_mutex);
 
         wake_up(&group->notification_waitq);
-        return 0;
+        return ret;
 }
 
 /*
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index f9a3e8942669..ab513ddaeff2 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6851,7 +6851,7 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb,
         }
         status = 0;
 bail:
-
+        brelse(last_eb_bh);
         mlog_exit(status);
         return status;
 }
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index fcf879ed6930..756f5b0998e0 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -122,7 +122,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
          * that still has AST's pending... */
         in_use = !list_empty(&lock->ast_list);
         spin_unlock(&dlm->ast_lock);
-        if (in_use) {
+        if (in_use && !(flags & LKM_CANCEL)) {
                mlog(ML_ERROR, "lockres %.*s: Someone is calling dlmunlock "
                     "while waiting for an ast!", res->lockname.len,
                     res->lockname.name);
@@ -131,7 +131,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 
         spin_lock(&res->spinlock);
         if (res->state & DLM_LOCK_RES_IN_PROGRESS) {
-                if (master_node) {
+                if (master_node && !(flags & LKM_CANCEL)) {
                         mlog(ML_ERROR, "lockres in progress!\n");
                         spin_unlock(&res->spinlock);
                         return DLM_FORWARD;
diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h
index fcdba091af3d..c212cf5a2bdf 100644
--- a/fs/ocfs2/ocfs2_lockid.h
+++ b/fs/ocfs2/ocfs2_lockid.h
@@ -108,6 +108,7 @@ static char *ocfs2_lock_type_strings[] = {
         [OCFS2_LOCK_TYPE_OPEN] = "Open",
         [OCFS2_LOCK_TYPE_FLOCK] = "Flock",
         [OCFS2_LOCK_TYPE_QINFO] = "Quota",
+        [OCFS2_LOCK_TYPE_NFS_SYNC] = "NFSSync",
         [OCFS2_LOCK_TYPE_ORPHAN_SCAN] = "OrphanScan",
 };
 
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index bf7742d0ee3b..44f2a5e1d042 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -23,6 +23,7 @@
 #include "sysfile.h"
 #include "dlmglue.h"
 #include "uptodate.h"
+#include "super.h"
 #include "quota.h"
 
 static struct workqueue_struct *ocfs2_quota_wq = NULL;
@@ -114,6 +115,15 @@ int ocfs2_read_quota_block(struct inode *inode, u64 v_block,
         int rc = 0;
         struct buffer_head *tmp = *bh;
 
+        if (i_size_read(inode) >> inode->i_sb->s_blocksize_bits <= v_block) {
+                ocfs2_error(inode->i_sb,
+                            "Quota file %llu is probably corrupted! Requested "
+                            "to read block %Lu but file has size only %Lu\n",
+                            (unsigned long long)OCFS2_I(inode)->ip_blkno,
+                            (unsigned long long)v_block,
+                            (unsigned long long)i_size_read(inode));
+                return -EIO;
+        }
         rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, 0,
                                     ocfs2_validate_quota_block);
         if (rc)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index b0ee0fdf799a..a3f8871d21fd 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1218,13 +1218,17 @@ static void ocfs2_kill_sb(struct super_block *sb)
 {
         struct ocfs2_super *osb = OCFS2_SB(sb);
 
+        /* Failed mount? */
+        if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
+                goto out;
+
         /* Prevent further queueing of inode drop events */
         spin_lock(&dentry_list_lock);
         ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
         spin_unlock(&dentry_list_lock);
         /* Wait for work to finish and/or remove it */
         cancel_work_sync(&osb->dentry_lock_work);
-
+out:
         kill_block_super(sb);
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 175db258942f..6f742f6658a9 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1003,12 +1003,7 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf,
 
         if (!task)
                 return -ESRCH;
-        task_lock(task);
-        if (task->mm)
-                oom_adjust = task->mm->oom_adj;
-        else
-                oom_adjust = OOM_DISABLE;
-        task_unlock(task);
+        oom_adjust = task->oomkilladj;
         put_task_struct(task);
 
         len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
@@ -1037,19 +1032,11 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
         task = get_proc_task(file->f_path.dentry->d_inode);
         if (!task)
                 return -ESRCH;
-        task_lock(task);
-        if (!task->mm) {
-                task_unlock(task);
-                put_task_struct(task);
-                return -EINVAL;
-        }
-        if (oom_adjust < task->mm->oom_adj && !capable(CAP_SYS_RESOURCE)) {
-                task_unlock(task);
+        if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) {
                 put_task_struct(task);
                 return -EACCES;
         }
-        task->mm->oom_adj = oom_adjust;
-        task_unlock(task);
+        task->oomkilladj = oom_adjust;
         put_task_struct(task);
         if (end - buffer == 0)
                 return -EIO;
diff --git a/fs/select.c b/fs/select.c
index d870237e42c7..8084834e123e 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -110,6 +110,7 @@ void poll_initwait(struct poll_wqueues *pwq)
 {
         init_poll_funcptr(&pwq->pt, __pollwait);
         pwq->polling_task = current;
+        pwq->triggered = 0;
         pwq->error = 0;
         pwq->table = NULL;
         pwq->inline_index = 0;
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index b619d6b8ca43..98ef624d9baf 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -708,6 +708,16 @@ xfs_reclaim_inode(
         return 0;
 }
 
+void
+__xfs_inode_set_reclaim_tag(
+        struct xfs_perag        *pag,
+        struct xfs_inode        *ip)
+{
+        radix_tree_tag_set(&pag->pag_ici_root,
+                           XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+                           XFS_ICI_RECLAIM_TAG);
+}
+
 /*
  * We set the inode flag atomically with the radix tree tag.
  * Once we get tag lookups on the radix tree, this inode flag
@@ -722,8 +732,7 @@ xfs_inode_set_reclaim_tag(
 
         read_lock(&pag->pag_ici_lock);
         spin_lock(&ip->i_flags_lock);
-        radix_tree_tag_set(&pag->pag_ici_root,
-                        XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+        __xfs_inode_set_reclaim_tag(pag, ip);
         __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
         spin_unlock(&ip->i_flags_lock);
         read_unlock(&pag->pag_ici_lock);
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 2a10301c99c7..59120602588a 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -48,6 +48,7 @@ int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, struct xfs_inode *ip);
 void xfs_inode_clear_reclaim_tag(struct xfs_inode *ip);
 void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
                                 struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 34ec86923f7e..ecbf8b4d2e2e 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -191,80 +191,82 @@ xfs_iget_cache_hit(
         int                     flags,
         int                     lock_flags) __releases(pag->pag_ici_lock)
 {
+        struct inode            *inode = VFS_I(ip);
         struct xfs_mount        *mp = ip->i_mount;
-        int                     error = EAGAIN;
+        int                     error;
+
+        spin_lock(&ip->i_flags_lock);
 
         /*
-         * If INEW is set this inode is being set up
-         * If IRECLAIM is set this inode is being torn down
-         * Pause and try again.
+         * If we are racing with another cache hit that is currently
+         * instantiating this inode or currently recycling it out of
+         * reclaimabe state, wait for the initialisation to complete
+         * before continuing.
+         *
+         * XXX(hch): eventually we should do something equivalent to
+         *           wait_on_inode to wait for these flags to be cleared
+         *           instead of polling for it.
          */
-        if (xfs_iflags_test(ip, (XFS_INEW|XFS_IRECLAIM))) {
+        if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) {
                 XFS_STATS_INC(xs_ig_frecycle);
+                error = EAGAIN;
                 goto out_error;
         }
 
-        /* If IRECLAIMABLE is set, we've torn down the vfs inode part */
-        if (xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
-
-                /*
-                 * If lookup is racing with unlink, then we should return an
-                 * error immediately so we don't remove it from the reclaim
-                 * list and potentially leak the inode.
-                 */
-                if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
-                        error = ENOENT;
-                        goto out_error;
-                }
+        /*
+         * If lookup is racing with unlink return an error immediately.
+         */
+        if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+                error = ENOENT;
+                goto out_error;
+        }
 
+        /*
+         * If IRECLAIMABLE is set, we've torn down the VFS inode already.
+         * Need to carefully get it back into useable state.
+         */
+        if (ip->i_flags & XFS_IRECLAIMABLE) {
                 xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
 
                 /*
-                 * We need to re-initialise the VFS inode as it has been
-                 * 'freed' by the VFS. Do this here so we can deal with
-                 * errors cleanly, then tag it so it can be set up correctly
-                 * later.
+                 * We need to set XFS_INEW atomically with clearing the
+                 * reclaimable tag so that we do have an indicator of the
+                 * inode still being initialized.
                  */
-                if (inode_init_always(mp->m_super, VFS_I(ip))) {
-                        error = ENOMEM;
-                        goto out_error;
-                }
+                ip->i_flags |= XFS_INEW;
+                ip->i_flags &= ~XFS_IRECLAIMABLE;
+                __xfs_inode_clear_reclaim_tag(mp, pag, ip);
 
-                /*
-                 * We must set the XFS_INEW flag before clearing the
-                 * XFS_IRECLAIMABLE flag so that if a racing lookup does
-                 * not find the XFS_IRECLAIMABLE above but has the igrab()
-                 * below succeed we can safely check XFS_INEW to detect
-                 * that this inode is still being initialised.
-                 */
-                xfs_iflags_set(ip, XFS_INEW);
-                xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
+                spin_unlock(&ip->i_flags_lock);
+                read_unlock(&pag->pag_ici_lock);
 
-                /* clear the radix tree reclaim flag as well. */
-                __xfs_inode_clear_reclaim_tag(mp, pag, ip);
-        } else if (!igrab(VFS_I(ip))) {
+                error = -inode_init_always(mp->m_super, inode);
+                if (error) {
+                        /*
+                         * Re-initializing the inode failed, and we are in deep
+                         * trouble.  Try to re-add it to the reclaim list.
+                         */
+                        read_lock(&pag->pag_ici_lock);
+                        spin_lock(&ip->i_flags_lock);
+
+                        ip->i_flags &= ~XFS_INEW;
+                        ip->i_flags |= XFS_IRECLAIMABLE;
+                        __xfs_inode_set_reclaim_tag(pag, ip);
+                        goto out_error;
+                }
+                inode->i_state = I_LOCK|I_NEW;
+        } else {
                 /* If the VFS inode is being torn down, pause and try again. */
-                XFS_STATS_INC(xs_ig_frecycle);
-                goto out_error;
-        } else if (xfs_iflags_test(ip, XFS_INEW)) {
-                /*
-                 * We are racing with another cache hit that is
-                 * currently recycling this inode out of the XFS_IRECLAIMABLE
-                 * state. Wait for the initialisation to complete before
-                 * continuing.
-                 */
-                wait_on_inode(VFS_I(ip));
-        }
+                if (!igrab(inode)) {
+                        error = EAGAIN;
+                        goto out_error;
+                }
 
-        if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
-                error = ENOENT;
-                iput(VFS_I(ip));
-                goto out_error;
+                /* We've got a live one. */
+                spin_unlock(&ip->i_flags_lock);
+                read_unlock(&pag->pag_ici_lock);
         }
 
-        /* We've got a live one. */
-        read_unlock(&pag->pag_ici_lock);
-
         if (lock_flags != 0)
                 xfs_ilock(ip, lock_flags);
 
@@ -274,6 +276,7 @@ xfs_iget_cache_hit(
         return 0;
 
 out_error:
+        spin_unlock(&ip->i_flags_lock);
         read_unlock(&pag->pag_ici_lock);
         return error;
 }