Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  fs: brlock vfsmount_lock
  fs: scale files_lock
  lglock: introduce special lglock and brlock spin locks
  tty: fix fu_list abuse
  fs: cleanup files_lock locking
  fs: remove extra lookup in __lookup_hash
  fs: fs_struct rwlock to spinlock
  apparmor: use task path helpers
  fs: dentry allocation consolidation
  fs: fix do_lookup false negative
  mbcache: Limit the maximum number of cache entries
  hostfs ->follow_link() braino
  hostfs: dumb (and usually harmless) tpyo - strncpy instead of strlcpy
  remove SWRITE* I/O types
  kill BH_Ordered flag
  vfs: update ctime when changing the file's permission by setfacl
  cramfs: only unlock new inodes
  fix reiserfs_evict_inode end_writeback second call

drivers/char/pty.c

@@ -675,8 +675,8 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	}
 
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
-	filp->private_data = tty;
-	file_move(filp, &tty->tty_files);
+
+	tty_add_file(tty, filp);
 
 	retval = devpts_pty_new(inode, tty->link);
 	if (retval)

drivers/char/tty_io.c

@@ -136,6 +136,9 @@ LIST_HEAD(tty_drivers);			/* linked list of tty drivers */
 DEFINE_MUTEX(tty_mutex);
 EXPORT_SYMBOL(tty_mutex);
 
+/* Spinlock to protect the tty->tty_files list */
+DEFINE_SPINLOCK(tty_files_lock);
+
 static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *);
 static ssize_t tty_write(struct file *, const char __user *, size_t, loff_t *);
 ssize_t redirected_tty_write(struct file *, const char __user *,
@@ -185,6 +188,41 @@ void free_tty_struct(struct tty_struct *tty)
 	kfree(tty);
 }
 
+static inline struct tty_struct *file_tty(struct file *file)
+{
+	return ((struct tty_file_private *)file->private_data)->tty;
+}
+
+/* Associate a new file with the tty structure */
+void tty_add_file(struct tty_struct *tty, struct file *file)
+{
+	struct tty_file_private *priv;
+
+	/* XXX: must implement proper error handling in callers */
+	priv = kmalloc(sizeof(*priv), GFP_KERNEL|__GFP_NOFAIL);
+
+	priv->tty = tty;
+	priv->file = file;
+	file->private_data = priv;
+
+	spin_lock(&tty_files_lock);
+	list_add(&priv->list, &tty->tty_files);
+	spin_unlock(&tty_files_lock);
+}
+
+/* Delete file from its tty */
+void tty_del_file(struct file *file)
+{
+	struct tty_file_private *priv = file->private_data;
+
+	spin_lock(&tty_files_lock);
+	list_del(&priv->list);
+	spin_unlock(&tty_files_lock);
+	file->private_data = NULL;
+	kfree(priv);
+}
+
+
 #define TTY_NUMBER(tty) ((tty)->index + (tty)->driver->name_base)
 
 /**
@@ -235,11 +273,11 @@ static int check_tty_count(struct tty_struct *tty, const char *routine)
 	struct list_head *p;
 	int count = 0;
 
-	file_list_lock();
+	spin_lock(&tty_files_lock);
 	list_for_each(p, &tty->tty_files) {
 		count++;
 	}
-	file_list_unlock();
+	spin_unlock(&tty_files_lock);
 	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
 	    tty->driver->subtype == PTY_TYPE_SLAVE &&
 	    tty->link && tty->link->count)
@@ -497,6 +535,7 @@ void __tty_hangup(struct tty_struct *tty)
 	struct file *cons_filp = NULL;
 	struct file *filp, *f = NULL;
 	struct task_struct *p;
+	struct tty_file_private *priv;
 	int    closecount = 0, n;
 	unsigned long flags;
 	int refs = 0;
@@ -506,7 +545,7 @@ void __tty_hangup(struct tty_struct *tty)
 
 
 	spin_lock(&redirect_lock);
-	if (redirect && redirect->private_data == tty) {
+	if (redirect && file_tty(redirect) == tty) {
 		f = redirect;
 		redirect = NULL;
 	}
@@ -519,9 +558,10 @@ void __tty_hangup(struct tty_struct *tty)
 	   workqueue with the lock held */
 	check_tty_count(tty, "tty_hangup");
 
-	file_list_lock();
+	spin_lock(&tty_files_lock);
 	/* This breaks for file handles being sent over AF_UNIX sockets ? */
-	list_for_each_entry(filp, &tty->tty_files, f_u.fu_list) {
+	list_for_each_entry(priv, &tty->tty_files, list) {
+		filp = priv->file;
 		if (filp->f_op->write == redirected_tty_write)
 			cons_filp = filp;
 		if (filp->f_op->write != tty_write)
@@ -530,7 +570,7 @@ void __tty_hangup(struct tty_struct *tty)
 		__tty_fasync(-1, filp, 0);	/* can't block */
 		filp->f_op = &hung_up_tty_fops;
 	}
-	file_list_unlock();
+	spin_unlock(&tty_files_lock);
 
 	tty_ldisc_hangup(tty);
 
@@ -889,12 +929,10 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count,
 			loff_t *ppos)
 {
 	int i;
-	struct tty_struct *tty;
-	struct inode *inode;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct tty_struct *tty = file_tty(file);
 	struct tty_ldisc *ld;
 
-	tty = file->private_data;
-	inode = file->f_path.dentry->d_inode;
 	if (tty_paranoia_check(tty, inode, "tty_read"))
 		return -EIO;
 	if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
@@ -1065,12 +1103,11 @@ void tty_write_message(struct tty_struct *tty, char *msg)
 static ssize_t tty_write(struct file *file, const char __user *buf,
 						size_t count, loff_t *ppos)
 {
-	struct tty_struct *tty;
 	struct inode *inode = file->f_path.dentry->d_inode;
+	struct tty_struct *tty = file_tty(file);
+ 	struct tty_ldisc *ld;
 	ssize_t ret;
-	struct tty_ldisc *ld;
 
-	tty = file->private_data;
 	if (tty_paranoia_check(tty, inode, "tty_write"))
 		return -EIO;
 	if (!tty || !tty->ops->write ||
@@ -1424,9 +1461,9 @@ static void release_one_tty(struct work_struct *work)
 	tty_driver_kref_put(driver);
 	module_put(driver->owner);
 
-	file_list_lock();
+	spin_lock(&tty_files_lock);
 	list_del_init(&tty->tty_files);
-	file_list_unlock();
+	spin_unlock(&tty_files_lock);
 
 	put_pid(tty->pgrp);
 	put_pid(tty->session);
@@ -1507,13 +1544,13 @@ static void release_tty(struct tty_struct *tty, int idx)
 
 int tty_release(struct inode *inode, struct file *filp)
 {
-	struct tty_struct *tty, *o_tty;
+	struct tty_struct *tty = file_tty(filp);
+	struct tty_struct *o_tty;
 	int	pty_master, tty_closing, o_tty_closing, do_sleep;
 	int	devpts;
 	int	idx;
 	char	buf[64];
 
-	tty = filp->private_data;
 	if (tty_paranoia_check(tty, inode, "tty_release_dev"))
 		return 0;
 
@@ -1671,8 +1708,7 @@ int tty_release(struct inode *inode, struct file *filp)
 	 *  - do_tty_hangup no longer sees this file descriptor as
 	 *    something that needs to be handled for hangups.
 	 */
-	file_kill(filp);
-	filp->private_data = NULL;
+	tty_del_file(filp);
 
 	/*
 	 * Perform some housekeeping before deciding whether to return.
@@ -1839,8 +1875,8 @@ got_driver:
 		return PTR_ERR(tty);
 	}
 
-	filp->private_data = tty;
-	file_move(filp, &tty->tty_files);
+	tty_add_file(tty, filp);
+
 	check_tty_count(tty, "tty_open");
 	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
 	    tty->driver->subtype == PTY_TYPE_MASTER)
@@ -1916,11 +1952,10 @@ got_driver:
 
 static unsigned int tty_poll(struct file *filp, poll_table *wait)
 {
-	struct tty_struct *tty;
+	struct tty_struct *tty = file_tty(filp);
 	struct tty_ldisc *ld;
 	int ret = 0;
 
-	tty = filp->private_data;
 	if (tty_paranoia_check(tty, filp->f_path.dentry->d_inode, "tty_poll"))
 		return 0;
 
@@ -1933,11 +1968,10 @@ static unsigned int tty_poll(struct file *filp, poll_table *wait)
 
 static int __tty_fasync(int fd, struct file *filp, int on)
 {
-	struct tty_struct *tty;
+	struct tty_struct *tty = file_tty(filp);
 	unsigned long flags;
 	int retval = 0;
 
-	tty = filp->private_data;
 	if (tty_paranoia_check(tty, filp->f_path.dentry->d_inode, "tty_fasync"))
 		goto out;
 
@@ -2491,13 +2525,13 @@ EXPORT_SYMBOL(tty_pair_get_pty);
  */
 long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct tty_struct *tty, *real_tty;
+	struct tty_struct *tty = file_tty(file);
+	struct tty_struct *real_tty;
 	void __user *p = (void __user *)arg;
 	int retval;
 	struct tty_ldisc *ld;
 	struct inode *inode = file->f_dentry->d_inode;
 
-	tty = file->private_data;
 	if (tty_paranoia_check(tty, inode, "tty_ioctl"))
 		return -EINVAL;
 
@@ -2619,7 +2653,7 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
 	struct inode *inode = file->f_dentry->d_inode;
-	struct tty_struct *tty = file->private_data;
+	struct tty_struct *tty = file_tty(file);
 	struct tty_ldisc *ld;
 	int retval = -ENOIOCTLCMD;
 
@@ -2711,7 +2745,7 @@ void __do_SAK(struct tty_struct *tty)
 				if (!filp)
 					continue;
 				if (filp->f_op->read == tty_read &&
-				    filp->private_data == tty) {
+				    file_tty(filp) == tty) {
 					printk(KERN_NOTICE "SAK: killed process %d"
 					    " (%s): fd#%d opened to the tty\n",
 					    task_pid_nr(p), p->comm, i);

drivers/staging/pohmelfs/path_entry.c

@@ -44,9 +44,9 @@ int pohmelfs_construct_path_string(struct pohmelfs_inode *pi, void *data, int le
 		return -ENOENT;
 	}
 
-	read_lock(&current->fs->lock);
+	spin_lock(&current->fs->lock);
 	path.mnt = mntget(current->fs->root.mnt);
-	read_unlock(&current->fs->lock);
+	spin_unlock(&current->fs->lock);
 
 	path.dentry = d;
 
@@ -91,9 +91,9 @@ int pohmelfs_path_length(struct pohmelfs_inode *pi)
 		return -ENOENT;
 	}
 
-	read_lock(&current->fs->lock);
+	spin_lock(&current->fs->lock);
 	root = dget(current->fs->root.dentry);
-	read_unlock(&current->fs->lock);
+	spin_unlock(&current->fs->lock);
 
 	spin_lock(&dcache_lock);
 

fs/buffer.c

@@ -770,11 +770,12 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 				spin_unlock(lock);
 				/*
 				 * Ensure any pending I/O completes so that
-				 * ll_rw_block() actually writes the current
-				 * contents - it is a noop if I/O is still in
-				 * flight on potentially older contents.
+				 * write_dirty_buffer() actually writes the
+				 * current contents - it is a noop if I/O is
+				 * still in flight on potentially older
+				 * contents.
 				 */
-				ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh);
+				write_dirty_buffer(bh, WRITE_SYNC_PLUG);
 
 				/*
 				 * Kick off IO for the previous mapping. Note
@@ -2911,13 +2912,6 @@ int submit_bh(int rw, struct buffer_head * bh)
 	BUG_ON(buffer_delay(bh));
 	BUG_ON(buffer_unwritten(bh));
 
-	/*
-	 * Mask in barrier bit for a write (could be either a WRITE or a
-	 * WRITE_SYNC
-	 */
-	if (buffer_ordered(bh) && (rw & WRITE))
-		rw |= WRITE_BARRIER;
-
 	/*
 	 * Only clear out a write error when rewriting
 	 */
@@ -2956,22 +2950,21 @@ EXPORT_SYMBOL(submit_bh);
 
 /**
  * ll_rw_block: low-level access to block devices (DEPRECATED)
- * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead)
+ * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
  * @nr: number of &struct buffer_heads in the array
  * @bhs: array of pointers to &struct buffer_head
  *
  * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
  * requests an I/O operation on them, either a %READ or a %WRITE.  The third
- * %SWRITE is like %WRITE only we make sure that the *current* data in buffers
- * are sent to disk. The fourth %READA option is described in the documentation
- * for generic_make_request() which ll_rw_block() calls.
+ * %READA option is described in the documentation for generic_make_request()
+ * which ll_rw_block() calls.
  *
  * This function drops any buffer that it cannot get a lock on (with the
- * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be
- * clean when doing a write request, and any buffer that appears to be
- * up-to-date when doing read request.  Further it marks as clean buffers that
- * are processed for writing (the buffer cache won't assume that they are
- * actually clean until the buffer gets unlocked).
+ * BH_Lock state bit), any buffer that appears to be clean when doing a write
+ * request, and any buffer that appears to be up-to-date when doing read
+ * request.  Further it marks as clean buffers that are processed for
+ * writing (the buffer cache won't assume that they are actually clean
+ * until the buffer gets unlocked).
  *
  * ll_rw_block sets b_end_io to simple completion handler that marks
  * the buffer up-to-date (if approriate), unlocks the buffer and wakes
@@ -2987,20 +2980,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 	for (i = 0; i < nr; i++) {
 		struct buffer_head *bh = bhs[i];
 
-		if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG)
-			lock_buffer(bh);
-		else if (!trylock_buffer(bh))
+		if (!trylock_buffer(bh))
 			continue;
-
-		if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC ||
-		    rw == SWRITE_SYNC_PLUG) {
+		if (rw == WRITE) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
 				get_bh(bh);
-				if (rw == SWRITE_SYNC)
-					submit_bh(WRITE_SYNC, bh);
-				else
-					submit_bh(WRITE, bh);
+				submit_bh(WRITE, bh);
 				continue;
 			}
 		} else {
@@ -3016,12 +3002,25 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 }
 EXPORT_SYMBOL(ll_rw_block);
 
+void write_dirty_buffer(struct buffer_head *bh, int rw)
+{
+	lock_buffer(bh);
+	if (!test_clear_buffer_dirty(bh)) {
+		unlock_buffer(bh);
+		return;
+	}
+	bh->b_end_io = end_buffer_write_sync;
+	get_bh(bh);
+	submit_bh(rw, bh);
+}
+EXPORT_SYMBOL(write_dirty_buffer);
+
 /*
  * For a data-integrity writeout, we need to wait upon any in-progress I/O
  * and then start new I/O and then wait upon it.  The caller must have a ref on
  * the buffer_head.
  */
-int sync_dirty_buffer(struct buffer_head *bh)
+int __sync_dirty_buffer(struct buffer_head *bh, int rw)
 {
 	int ret = 0;
 
@@ -3030,7 +3029,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
 	if (test_clear_buffer_dirty(bh)) {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(WRITE_SYNC, bh);
+		ret = submit_bh(rw, bh);
 		wait_on_buffer(bh);
 		if (buffer_eopnotsupp(bh)) {
 			clear_buffer_eopnotsupp(bh);
@@ -3043,6 +3042,12 @@ int sync_dirty_buffer(struct buffer_head *bh)
 	}
 	return ret;
 }
+EXPORT_SYMBOL(__sync_dirty_buffer);
+
+int sync_dirty_buffer(struct buffer_head *bh)
+{
+	return __sync_dirty_buffer(bh, WRITE_SYNC);
+}
 EXPORT_SYMBOL(sync_dirty_buffer);
 
 /*

fs/cramfs/inode.c

@@ -80,7 +80,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
 		}
 	} else {
 		inode = iget_locked(sb, CRAMINO(cramfs_inode));
-		if (inode) {
+		if (inode && (inode->i_state & I_NEW)) {
 			setup_inode(inode, cramfs_inode);
 			unlock_new_inode(inode);
 		}

fs/dcache.c

@@ -1332,31 +1332,13 @@ EXPORT_SYMBOL(d_add_ci);
  * d_lookup - search for a dentry
  * @parent: parent dentry
  * @name: qstr of name we wish to find
+ * Returns: dentry, or NULL
  *
- * Searches the children of the parent dentry for the name in question. If
- * the dentry is found its reference count is incremented and the dentry
- * is returned. The caller must use dput to free the entry when it has
- * finished using it. %NULL is returned on failure.
- *
- * __d_lookup is dcache_lock free. The hash list is protected using RCU.
- * Memory barriers are used while updating and doing lockless traversal. 
- * To avoid races with d_move while rename is happening, d_lock is used.
- *
- * Overflows in memcmp(), while d_move, are avoided by keeping the length
- * and name pointer in one structure pointed by d_qstr.
- *
- * rcu_read_lock() and rcu_read_unlock() are used to disable preemption while
- * lookup is going on.
- *
- * The dentry unused LRU is not updated even if lookup finds the required dentry
- * in there. It is updated in places such as prune_dcache, shrink_dcache_sb,
- * select_parent and __dget_locked. This laziness saves lookup from dcache_lock
- * acquisition.
- *
- * d_lookup() is protected against the concurrent renames in some unrelated
- * directory using the seqlockt_t rename_lock.
+ * d_lookup searches the children of the parent dentry for the name in
+ * question. If the dentry is found its reference count is incremented and the
+ * dentry is returned. The caller must use dput to free the entry when it has
+ * finished using it. %NULL is returned if the dentry does not exist.
  */
-
 struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
 {
 	struct dentry * dentry = NULL;
@@ -1372,6 +1354,21 @@ struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
 }
 EXPORT_SYMBOL(d_lookup);
 
+/*
+ * __d_lookup - search for a dentry (racy)
+ * @parent: parent dentry
+ * @name: qstr of name we wish to find
+ * Returns: dentry, or NULL
+ *
+ * __d_lookup is like d_lookup, however it may (rarely) return a
+ * false-negative result due to unrelated rename activity.
+ *
+ * __d_lookup is slightly faster by avoiding rename_lock read seqlock,
+ * however it must be used carefully, eg. with a following d_lookup in
+ * the case of failure.
+ *
+ * __d_lookup callers must be commented.
+ */
 struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
 {
 	unsigned int len = name->len;
@@ -1382,6 +1379,19 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
 	struct hlist_node *node;
 	struct dentry *dentry;
 
+	/*
+	 * The hash list is protected using RCU.
+	 *
+	 * Take d_lock when comparing a candidate dentry, to avoid races
+	 * with d_move().
+	 *
+	 * It is possible that concurrent renames can mess up our list
+	 * walk here and result in missing our dentry, resulting in the
+	 * false-negative result. d_lookup() protects against concurrent
+	 * renames using rename_lock seqlock.
+	 *
+	 * See Documentation/vfs/dcache-locking.txt for more details.
+	 */
 	rcu_read_lock();
 	
 	hlist_for_each_entry_rcu(dentry, node, head, d_hash) {
@@ -1396,8 +1406,8 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
 
 		/*
 		 * Recheck the dentry after taking the lock - d_move may have
-		 * changed things.  Don't bother checking the hash because we're
-		 * about to compare the whole name anyway.
+		 * changed things. Don't bother checking the hash because
+		 * we're about to compare the whole name anyway.
 		 */
 		if (dentry->d_parent != parent)
 			goto next;
@@ -1925,7 +1935,7 @@ static int prepend_path(const struct path *path, struct path *root,
 	bool slash = false;
 	int error = 0;
 
-	spin_lock(&vfsmount_lock);
+	br_read_lock(vfsmount_lock);
 	while (dentry != root->dentry || vfsmnt != root->mnt) {
 		struct dentry * parent;
 
@@ -1954,7 +1964,7 @@ out:
 	if (!error && !slash)
 		error = prepend(buffer, buflen, "/", 1);
 
-	spin_unlock(&vfsmount_lock);
+	br_read_unlock(vfsmount_lock);
 	return error;
 
 global_root:
@@ -2292,11 +2302,12 @@ int path_is_under(struct path *path1, struct path *path2)
 	struct vfsmount *mnt = path1->mnt;
 	struct dentry *dentry = path1->dentry;
 	int res;
-	spin_lock(&vfsmount_lock);
+
+	br_read_lock(vfsmount_lock);
 	if (mnt != path2->mnt) {
 		for (;;) {
 			if (mnt->mnt_parent == mnt) {
-				spin_unlock(&vfsmount_lock);
+				br_read_unlock(vfsmount_lock);
 				return 0;
 			}
 			if (mnt->mnt_parent == path2->mnt)
@@ -2306,7 +2317,7 @@ int path_is_under(struct path *path1, struct path *path2)
 		dentry = mnt->mnt_mountpoint;
 	}
 	res = is_subdir(dentry, path2->dentry);
-	spin_unlock(&vfsmount_lock);
+	br_read_unlock(vfsmount_lock);
 	return res;
 }
 EXPORT_SYMBOL(path_is_under);

fs/exec.c

@@ -1118,7 +1118,7 @@ int check_unsafe_exec(struct linux_binprm *bprm)
 	bprm->unsafe = tracehook_unsafe_exec(p);
 
 	n_fs = 1;
-	write_lock(&p->fs->lock);
+	spin_lock(&p->fs->lock);
 	rcu_read_lock();
 	for (t = next_thread(p); t != p; t = next_thread(t)) {
 		if (t->fs == p->fs)
@@ -1135,7 +1135,7 @@ int check_unsafe_exec(struct linux_binprm *bprm)
 			res = 1;
 		}
 	}
-	write_unlock(&p->fs->lock);
+	spin_unlock(&p->fs->lock);
 
 	return res;
 }

fs/fat/misc.c

@@ -250,7 +250,9 @@ int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs)
 {
 	int i, err = 0;
 
-	ll_rw_block(SWRITE, nr_bhs, bhs);
+	for (i = 0; i < nr_bhs; i++)
+		write_dirty_buffer(bhs[i], WRITE);
+
 	for (i = 0; i < nr_bhs; i++) {
 		wait_on_buffer(bhs[i]);
 		if (buffer_eopnotsupp(bhs[i])) {

fs/file_table.c

@@ -20,7 +20,9 @@
 #include <linux/cdev.h>
 #include <linux/fsnotify.h>
 #include <linux/sysctl.h>
+#include <linux/lglock.h>
 #include <linux/percpu_counter.h>
+#include <linux/percpu.h>
 #include <linux/ima.h>
 
 #include <asm/atomic.h>
@@ -32,8 +34,8 @@ struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-/* public. Not pretty! */
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock);
+DECLARE_LGLOCK(files_lglock);
+DEFINE_LGLOCK(files_lglock);
 
 /* SLAB cache for file structures */
 static struct kmem_cache *filp_cachep __read_mostly;
@@ -249,7 +251,7 @@ static void __fput(struct file *file)
 		cdev_put(inode->i_cdev);
 	fops_put(file->f_op);
 	put_pid(file->f_owner.pid);
-	file_kill(file);
+	file_sb_list_del(file);
 	if (file->f_mode & FMODE_WRITE)
 		drop_file_write_access(file);
 	file->f_path.dentry = NULL;
@@ -328,41 +330,107 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 	return file;
 }
 
-
 void put_filp(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		security_file_free(file);
-		file_kill(file);
+		file_sb_list_del(file);
 		file_free(file);
 	}
 }
 
-void file_move(struct file *file, struct list_head *list)
+static inline int file_list_cpu(struct file *file)
 {
-	if (!list)
-		return;
-	file_list_lock();
-	list_move(&file->f_u.fu_list, list);
-	file_list_unlock();
+#ifdef CONFIG_SMP
+	return file->f_sb_list_cpu;
+#else
+	return smp_processor_id();
+#endif
 }
 
-void file_kill(struct file *file)
+/* helper for file_sb_list_add to reduce ifdefs */
+static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
+{
+	struct list_head *list;
+#ifdef CONFIG_SMP
+	int cpu;
+	cpu = smp_processor_id();
+	file->f_sb_list_cpu = cpu;
+	list = per_cpu_ptr(sb->s_files, cpu);
+#else
+	list = &sb->s_files;
+#endif
+	list_add(&file->f_u.fu_list, list);
+}
+
+/**
+ * file_sb_list_add - add a file to the sb's file list
+ * @file: file to add
+ * @sb: sb to add it to
+ *
+ * Use this function to associate a file with the superblock of the inode it
+ * refers to.
+ */
+void file_sb_list_add(struct file *file, struct super_block *sb)
+{
+	lg_local_lock(files_lglock);
+	__file_sb_list_add(file, sb);
+	lg_local_unlock(files_lglock);
+}
+
+/**
+ * file_sb_list_del - remove a file from the sb's file list
+ * @file: file to remove
+ * @sb: sb to remove it from
+ *
+ * Use this function to remove a file from its superblock.
+ */
+void file_sb_list_del(struct file *file)
 {
 	if (!list_empty(&file->f_u.fu_list)) {
-		file_list_lock();
+		lg_local_lock_cpu(files_lglock, file_list_cpu(file));
 		list_del_init(&file->f_u.fu_list);
-		file_list_unlock();
+		lg_local_unlock_cpu(files_lglock, file_list_cpu(file));
 	}
 }
 
+#ifdef CONFIG_SMP
+
+/*
+ * These macros iterate all files on all CPUs for a given superblock.
+ * files_lglock must be held globally.
+ */
+#define do_file_list_for_each_entry(__sb, __file)		\
+{								\
+	int i;							\
+	for_each_possible_cpu(i) {				\
+		struct list_head *list;				\
+		list = per_cpu_ptr((__sb)->s_files, i);		\
+		list_for_each_entry((__file), list, f_u.fu_list)
+
+#define while_file_list_for_each_entry				\
+	}							\
+}
+
+#else
+
+#define do_file_list_for_each_entry(__sb, __file)		\
+{								\
+	struct list_head *list;					\
+	list = &(sb)->s_files;					\
+	list_for_each_entry((__file), list, f_u.fu_list)
+
+#define while_file_list_for_each_entry				\
+}
+
+#endif
+
 int fs_may_remount_ro(struct super_block *sb)
 {
 	struct file *file;
-
 	/* Check that no files are currently opened for writing. */
-	file_list_lock();
-	list_for_each_entry(file, &sb->s_files, f_u.fu_list) {
+	lg_global_lock(files_lglock);
+	do_file_list_for_each_entry(sb, file) {
 		struct inode *inode = file->f_path.dentry->d_inode;
 
 		/* File with pending delete? */
@@ -372,11 +440,11 @@ int fs_may_remount_ro(struct super_block *sb)
 		/* Writeable file? */
 		if (S_ISREG(inode->i_mode) && (file->f_mode & FMODE_WRITE))
 			goto too_bad;
-	}
-	file_list_unlock();
+	} while_file_list_for_each_entry;
+	lg_global_unlock(files_lglock);
 	return 1; /* Tis' cool bro. */
 too_bad:
-	file_list_unlock();
+	lg_global_unlock(files_lglock);
 	return 0;
 }
 
@@ -392,8 +460,8 @@ void mark_files_ro(struct super_block *sb)
 	struct file *f;
 
 retry:
-	file_list_lock();
-	list_for_each_entry(f, &sb->s_files, f_u.fu_list) {
+	lg_global_lock(files_lglock);
+	do_file_list_for_each_entry(sb, f) {
 		struct vfsmount *mnt;
 		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
 		       continue;
@@ -408,16 +476,13 @@ retry:
 			continue;
 		file_release_write(f);
 		mnt = mntget(f->f_path.mnt);
-		file_list_unlock();
-		/*
-		 * This can sleep, so we can't hold
-		 * the file_list_lock() spinlock.
-		 */
+		/* This can sleep, so we can't hold the spinlock. */
+		lg_global_unlock(files_lglock);
 		mnt_drop_write(mnt);
 		mntput(mnt);
 		goto retry;
-	}
-	file_list_unlock();
+	} while_file_list_for_each_entry;
+	lg_global_unlock(files_lglock);
 }
 
 void __init files_init(unsigned long mempages)
@@ -437,5 +502,6 @@ void __init files_init(unsigned long mempages)
 	if (files_stat.max_files < NR_FILE)
 		files_stat.max_files = NR_FILE;
 	files_defer_init();
+	lg_lock_init(files_lglock);
 	percpu_counter_init(&nr_files, 0);
 } 

fs/fs_struct.c

@@ -13,11 +13,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
 {
 	struct path old_root;
 
-	write_lock(&fs->lock);
+	spin_lock(&fs->lock);
 	old_root = fs->root;
 	fs->root = *path;
 	path_get(path);
-	write_unlock(&fs->lock);
+	spin_unlock(&fs->lock);
 	if (old_root.dentry)
 		path_put(&old_root);
 }
@@ -30,11 +30,11 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
 {
 	struct path old_pwd;
 
-	write_lock(&fs->lock);
+	spin_lock(&fs->lock);
 	old_pwd = fs->pwd;
 	fs->pwd = *path;
 	path_get(path);
-	write_unlock(&fs->lock);
+	spin_unlock(&fs->lock);
 
 	if (old_pwd.dentry)
 		path_put(&old_pwd);
@@ -51,7 +51,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 		task_lock(p);
 		fs = p->fs;
 		if (fs) {
-			write_lock(&fs->lock);
+			spin_lock(&fs->lock);
 			if (fs->root.dentry == old_root->dentry
 			    && fs->root.mnt == old_root->mnt) {
 				path_get(new_root);
@@ -64,7 +64,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
 				fs->pwd = *new_root;
 				count++;
 			}
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 		}
 		task_unlock(p);
 	} while_each_thread(g, p);
@@ -87,10 +87,10 @@ void exit_fs(struct task_struct *tsk)
 	if (fs) {
 		int kill;
 		task_lock(tsk);
-		write_lock(&fs->lock);
+		spin_lock(&fs->lock);
 		tsk->fs = NULL;
 		kill = !--fs->users;
-		write_unlock(&fs->lock);
+		spin_unlock(&fs->lock);
 		task_unlock(tsk);
 		if (kill)
 			free_fs_struct(fs);
@@ -104,7 +104,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 	if (fs) {
 		fs->users = 1;
 		fs->in_exec = 0;
-		rwlock_init(&fs->lock);
+		spin_lock_init(&fs->lock);
 		fs->umask = old->umask;
 		get_fs_root_and_pwd(old, &fs->root, &fs->pwd);
 	}
@@ -121,10 +121,10 @@ int unshare_fs_struct(void)
 		return -ENOMEM;
 
 	task_lock(current);
-	write_lock(&fs->lock);
+	spin_lock(&fs->lock);
 	kill = !--fs->users;
 	current->fs = new_fs;
-	write_unlock(&fs->lock);
+	spin_unlock(&fs->lock);
 	task_unlock(current);
 
 	if (kill)
@@ -143,7 +143,7 @@ EXPORT_SYMBOL(current_umask);
 /* to be mentioned only in INIT_TASK */
 struct fs_struct init_fs = {
 	.users		= 1,
-	.lock		= __RW_LOCK_UNLOCKED(init_fs.lock),
+	.lock		= __SPIN_LOCK_UNLOCKED(init_fs.lock),
 	.umask		= 0022,
 };
 
@@ -156,14 +156,14 @@ void daemonize_fs_struct(void)
 
 		task_lock(current);
 
-		write_lock(&init_fs.lock);
+		spin_lock(&init_fs.lock);
 		init_fs.users++;
-		write_unlock(&init_fs.lock);
+		spin_unlock(&init_fs.lock);
 
-		write_lock(&fs->lock);
+		spin_lock(&fs->lock);
 		current->fs = &init_fs;
 		kill = !--fs->users;
-		write_unlock(&fs->lock);
+		spin_unlock(&fs->lock);
 
 		task_unlock(current);
 		if (kill)

fs/generic_acl.c

@@ -94,6 +94,7 @@ generic_acl_set(struct dentry *dentry, const char *name, const void *value,
 			if (error < 0)
 				goto failed;
 			inode->i_mode = mode;
+			inode->i_ctime = CURRENT_TIME;
 			if (error == 0) {
 				posix_acl_release(acl);
 				acl = NULL;

fs/hostfs/hostfs_kern.c

@@ -104,7 +104,7 @@ static char *__dentry_name(struct dentry *dentry, char *name)
 		__putname(name);
 		return NULL;
 	}
-	strncpy(name, root, PATH_MAX);
+	strlcpy(name, root, PATH_MAX);
 	if (len > p - name) {
 		__putname(name);
 		return NULL;
@@ -876,7 +876,7 @@ static void *hostfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 		char *path = dentry_name(dentry);
 		int err = -ENOMEM;
 		if (path) {
-			int err = hostfs_do_readlink(path, link, PATH_MAX);
+			err = hostfs_do_readlink(path, link, PATH_MAX);
 			if (err == PATH_MAX)
 				err = -E2BIG;
 			__putname(path);

fs/internal.h

@@ -9,6 +9,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/lglock.h>
+
 struct super_block;
 struct linux_binprm;
 struct path;
@@ -70,7 +72,8 @@ extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
 
 extern void __init mnt_init(void);
 
-extern spinlock_t vfsmount_lock;
+DECLARE_BRLOCK(vfsmount_lock);
+
 
 /*
  * fs_struct.c
@@ -80,6 +83,8 @@ extern void chroot_fs_refs(struct path *, struct path *);
 /*
  * file_table.c
  */
+extern void file_sb_list_add(struct file *f, struct super_block *sb);
+extern void file_sb_list_del(struct file *f);
 extern void mark_files_ro(struct super_block *);
 extern struct file *get_empty_filp(void);
 

fs/jbd/checkpoint.c

@@ -254,7 +254,9 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
 {
 	int i;
 
-	ll_rw_block(SWRITE, *batch_count, bhs);
+	for (i = 0; i < *batch_count; i++)
+		write_dirty_buffer(bhs[i], WRITE);
+
 	for (i = 0; i < *batch_count; i++) {
 		struct buffer_head *bh = bhs[i];
 		clear_buffer_jwrite(bh);

fs/jbd/commit.c

@@ -119,7 +119,6 @@ static int journal_write_commit_record(journal_t *journal,
 	struct buffer_head *bh;
 	journal_header_t *header;
 	int ret;
-	int barrier_done = 0;
 
 	if (is_journal_aborted(journal))
 		return 0;
@@ -137,34 +136,36 @@ static int journal_write_commit_record(journal_t *journal,
 
 	JBUFFER_TRACE(descriptor, "write commit block");
 	set_buffer_dirty(bh);
+
 	if (journal->j_flags & JFS_BARRIER) {
-		set_buffer_ordered(bh);
-		barrier_done = 1;
-	}
-	ret = sync_dirty_buffer(bh);
-	if (barrier_done)
-		clear_buffer_ordered(bh);
-	/* is it possible for another commit to fail at roughly
-	 * the same time as this one?  If so, we don't want to
-	 * trust the barrier flag in the super, but instead want
-	 * to remember if we sent a barrier request
-	 */
-	if (ret == -EOPNOTSUPP && barrier_done) {
-		char b[BDEVNAME_SIZE];
+		ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_BARRIER);
 
-		printk(KERN_WARNING
-			"JBD: barrier-based sync failed on %s - "
-			"disabling barriers\n",
-			bdevname(journal->j_dev, b));
-		spin_lock(&journal->j_state_lock);
-		journal->j_flags &= ~JFS_BARRIER;
-		spin_unlock(&journal->j_state_lock);
+		/*
+		 * Is it possible for another commit to fail at roughly
+		 * the same time as this one?  If so, we don't want to
+		 * trust the barrier flag in the super, but instead want
+		 * to remember if we sent a barrier request
+		 */
+		if (ret == -EOPNOTSUPP) {
+			char b[BDEVNAME_SIZE];
 
-		/* And try again, without the barrier */
-		set_buffer_uptodate(bh);
-		set_buffer_dirty(bh);
+			printk(KERN_WARNING
+				"JBD: barrier-based sync failed on %s - "
+				"disabling barriers\n",
+				bdevname(journal->j_dev, b));
+			spin_lock(&journal->j_state_lock);
+			journal->j_flags &= ~JFS_BARRIER;
+			spin_unlock(&journal->j_state_lock);
+
+			/* And try again, without the barrier */
+			set_buffer_uptodate(bh);
+			set_buffer_dirty(bh);
+			ret = sync_dirty_buffer(bh);
+		}
+	} else {
 		ret = sync_dirty_buffer(bh);
 	}
+
 	put_bh(bh);		/* One for getblk() */
 	journal_put_journal_head(descriptor);
 

fs/jbd/journal.c

@@ -1024,7 +1024,7 @@ void journal_update_superblock(journal_t *journal, int wait)
 	if (wait)
 		sync_dirty_buffer(bh);
 	else
-		ll_rw_block(SWRITE, 1, &bh);
+		write_dirty_buffer(bh, WRITE);
 
 out:
 	/* If we have just flushed the log (by marking s_start==0), then

fs/jbd/revoke.c

@@ -617,7 +617,7 @@ static void flush_descriptor(journal_t *journal,
 	set_buffer_jwrite(bh);
 	BUFFER_TRACE(bh, "write");
 	set_buffer_dirty(bh);
-	ll_rw_block((write_op == WRITE) ? SWRITE : SWRITE_SYNC_PLUG, 1, &bh);
+	write_dirty_buffer(bh, write_op);
 }
 #endif
 

fs/jbd2/checkpoint.c

@@ -255,7 +255,9 @@ __flush_batch(journal_t *journal, int *batch_count)
 {
 	int i;
 
-	ll_rw_block(SWRITE, *batch_count, journal->j_chkpt_bhs);
+	for (i = 0; i < *batch_count; i++)
+		write_dirty_buffer(journal->j_chkpt_bhs[i], WRITE);
+
 	for (i = 0; i < *batch_count; i++) {
 		struct buffer_head *bh = journal->j_chkpt_bhs[i];
 		clear_buffer_jwrite(bh);

fs/jbd2/commit.c

@@ -101,7 +101,6 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	int ret;
-	int barrier_done = 0;
 	struct timespec now = current_kernel_time();
 
 	if (is_journal_aborted(journal))
@@ -136,30 +135,22 @@ static int journal_submit_commit_record(journal_t *journal,
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !JBD2_HAS_INCOMPAT_FEATURE(journal,
 				       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
-		set_buffer_ordered(bh);
-		barrier_done = 1;
-	}
-	ret = submit_bh(WRITE_SYNC_PLUG, bh);
-	if (barrier_done)
-		clear_buffer_ordered(bh);
+		ret = submit_bh(WRITE_SYNC_PLUG | WRITE_BARRIER, bh);
+		if (ret == -EOPNOTSUPP) {
+			printk(KERN_WARNING
+			       "JBD2: Disabling barriers on %s, "
+			       "not supported by device\n", journal->j_devname);
+			write_lock(&journal->j_state_lock);
+			journal->j_flags &= ~JBD2_BARRIER;
+			write_unlock(&journal->j_state_lock);
 
-	/* is it possible for another commit to fail at roughly
-	 * the same time as this one?  If so, we don't want to
-	 * trust the barrier flag in the super, but instead want
-	 * to remember if we sent a barrier request
-	 */
-	if (ret == -EOPNOTSUPP && barrier_done) {
-		printk(KERN_WARNING
-		       "JBD2: Disabling barriers on %s, "
-		       "not supported by device\n", journal->j_devname);
-		write_lock(&journal->j_state_lock);
-		journal->j_flags &= ~JBD2_BARRIER;
-		write_unlock(&journal->j_state_lock);
-
-		/* And try again, without the barrier */
-		lock_buffer(bh);
-		set_buffer_uptodate(bh);
-		clear_buffer_dirty(bh);
+			/* And try again, without the barrier */
+			lock_buffer(bh);
+			set_buffer_uptodate(bh);
+			clear_buffer_dirty(bh);
+			ret = submit_bh(WRITE_SYNC_PLUG, bh);
+		}
+	} else {
 		ret = submit_bh(WRITE_SYNC_PLUG, bh);
 	}
 	*cbh = bh;

fs/jbd2/journal.c

@@ -1124,7 +1124,7 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 			set_buffer_uptodate(bh);
 		}
 	} else
-		ll_rw_block(SWRITE, 1, &bh);
+		write_dirty_buffer(bh, WRITE);
 
 out:
 	/* If we have just flushed the log (by marking s_start==0), then