Eric Lee / smarc-fsl-linux-kernel

Commit 08d8e9749e7f0435ba4683b620e8d30d59276b4c

Authored by Fengguang Wu 18 years ago

Committed by Linus Torvalds 18 years ago

Exists in master and in 39 other branches

writeback: fix ntfs with sb_has_dirty_inodes()

NTFS's if-condition on dirty inodes is not complete.  Fix it with
sb_has_dirty_inodes().

Cc: Anton Altaparmakov <aia21@cantab.net>
Cc: Ken Chen <kenchen@google.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Showing 3 changed files with 12 additions and 3 deletions Inline Diff

fs/fs-writeback.c
fs/ntfs/super.c
include/linux/fs.h

fs/fs-writeback.c

Diff comments View file @ 08d8e97

 /*
  * fs/fs-writeback.c
  *
  * Copyright (C) 2002, Linus Torvalds.
  *
  * Contains all the functions related to writing back and waiting
  * upon dirty inodes against superblocks, and writing back dirty
  * pages against inodes.  ie: data writeback.  Writeout of the
  * inode itself is not handled here.
  *
  * 10Apr2002	akpm@zip.com.au
  *		Split out of fs/inode.c
  *		Additions for address_space-based writeback
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include "internal.h"
 /**
  *	__mark_inode_dirty -	internal function
  *	@inode: inode to mark
  *	@flags: what kind of dirty (i.e. I_DIRTY_SYNC)
  *	Mark an inode as dirty. Callers should use mark_inode_dirty or
  *  	mark_inode_dirty_sync.
  *
  * Put the inode on the super block's dirty list.
  *
  * CAREFUL! We mark it dirty unconditionally, but move it onto the
  * dirty list only if it is hashed or if it refers to a blockdev.
  * If it was not hashed, it will never be added to the dirty list
  * even if it is later hashed, as it will have been marked dirty already.
  *
  * In short, make sure you hash any inodes _before_ you start marking
  * them dirty.
  *
  * This function *must* be atomic for the I_DIRTY_PAGES case -
  * set_page_dirty() is called under spinlock in several places.
  *
  * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
  * the block-special inode (/dev/hda1) itself.  And the ->dirtied_when field of
  * the kernel-internal blockdev inode represents the dirtying time of the
  * blockdev's pages.  This is why for I_DIRTY_PAGES we always use
  * page->mapping->host, so the page-dirtying time is recorded in the internal
  * blockdev inode.
  */
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
 	/*
 	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
 	 * dirty the inode itself
 	 */
 	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		if (sb->s_op->dirty_inode)
 			sb->s_op->dirty_inode(inode);
 	}
 	/*
 	 * make sure that changes are seen by all cpus before we test i_state
 	 * -- mikulas
 	 */
 	smp_mb();
 	/* avoid the locking if we can */
 	if ((inode->i_state & flags) == flags)
 		return;
 	if (unlikely(block_dump)) {
 		struct dentry *dentry = NULL;
 		const char *name = "?";
 		if (!list_empty(&inode->i_dentry)) {
 			dentry = list_entry(inode->i_dentry.next,
 					    struct dentry, d_alias);
 			if (dentry && dentry->d_name.name)
 				name = (const char *) dentry->d_name.name;
 		}
 		if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev"))
 			printk(KERN_DEBUG
 			       "%s(%d): dirtied inode %lu (%s) on %s\n",
 			       current->comm, current->pid, inode->i_ino,
 			       name, inode->i_sb->s_id);
 	}
 	spin_lock(&inode_lock);
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 		inode->i_state |= flags;
 		/*
 		 * If the inode is locked, just update its dirty state.
 		 * The unlocker will place the inode on the appropriate
 		 * superblock list, based upon its state.
 		 */
 		if (inode->i_state & I_LOCK)
 			goto out;
 		/*
 		 * Only add valid (hashed) inodes to the superblock's
 		 * dirty list.  Add blockdev inodes as well.
 		 */
 		if (!S_ISBLK(inode->i_mode)) {
 			if (hlist_unhashed(&inode->i_hash))
 				goto out;
 		}
 		if (inode->i_state & (I_FREEING|I_CLEAR))
 			goto out;
 		/*
 		 * If the inode was already on s_dirty/s_io/s_more_io, don't
 		 * reposition it (that would break s_dirty time-ordering).
 		 */
 		if (!was_dirty) {
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_list, &sb->s_dirty);
 		}
 	}
 out:
 	spin_unlock(&inode_lock);
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 static int write_inode(struct inode *inode, int sync)
 {
 	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
 		return inode->i_sb->s_op->write_inode(inode, sync);
 	return 0;
 }
 /*
  * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
  * furthest end of its superblock's dirty-inode list.
  *
  * Before stamping the inode's ->dirtied_when, we check to see whether it is
  * already the most-recently-dirtied inode on the s_dirty list.  If that is
  * the case then the inode must have been redirtied while it was being written
  * out and we don't reset its dirtied_when.
  */
 static void redirty_tail(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 	if (!list_empty(&sb->s_dirty)) {
 		struct inode *tail_inode;
 		tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
 		if (!time_after_eq(inode->dirtied_when,
 				tail_inode->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
 	list_move(&inode->i_list, &sb->s_dirty);
 }
 /*
  * requeue inode for re-scanning after sb->s_io list is exhausted.
  */
 static void requeue_io(struct inode *inode)
 {
 	list_move(&inode->i_list, &inode->i_sb->s_more_io);
 }
 /*
  * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
  */
 static void move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
 				unsigned long *older_than_this)
 {
 	while (!list_empty(delaying_queue)) {
 		struct inode *inode = list_entry(delaying_queue->prev,
 						struct inode, i_list);
 		if (older_than_this &&
 			time_after(inode->dirtied_when, *older_than_this))
 			break;
 		list_move(&inode->i_list, dispatch_queue);
 	}
 }
 /*
  * Queue all expired dirty inodes for io, eldest first.
  */
 static void queue_io(struct super_block *sb,
 				unsigned long *older_than_this)
 {
 	list_splice_init(&sb->s_more_io, sb->s_io.prev);
 	move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
 }
+int sb_has_dirty_inodes(struct super_block *sb)
+{
+	return !list_empty(&sb->s_dirty) ||
+	       !list_empty(&sb->s_io) ||
+	       !list_empty(&sb->s_more_io);
+}
+EXPORT_SYMBOL(sb_has_dirty_inodes);
 /*
  * Write a single inode's dirty pages and inode data out to disk.
  * If `wait' is set, wait on the writeout.
  *
  * The whole writeout design is quite complex and fragile.  We want to avoid
  * starvation of particular inodes when others are being redirtied, prevent
  * livelocks, etc.
  *
  * Called under inode_lock.
  */
 static int
 __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	unsigned dirty;
 	struct address_space *mapping = inode->i_mapping;
 	int wait = wbc->sync_mode == WB_SYNC_ALL;
 	int ret;
 	BUG_ON(inode->i_state & I_LOCK);
 	/* Set I_LOCK, reset I_DIRTY */
 	dirty = inode->i_state & I_DIRTY;
 	inode->i_state |= I_LOCK;
 	inode->i_state &= ~I_DIRTY;
 	spin_unlock(&inode_lock);
 	ret = do_writepages(mapping, wbc);
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		int err = write_inode(inode, wait);
 		if (ret == 0)
 			ret = err;
 	}
 	if (wait) {
 		int err = filemap_fdatawait(mapping);
 		if (ret == 0)
 			ret = err;
 	}
 	spin_lock(&inode_lock);
 	inode->i_state &= ~I_LOCK;
 	if (!(inode->i_state & I_FREEING)) {
 		if (!(inode->i_state & I_DIRTY) &&
 		    mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 			/*
 			 * We didn't write back all the pages.  nfs_writepages()
 			 * sometimes bales out without doing anything. Redirty
 			 * the inode; Move it from s_io onto s_more_io/s_dirty.
 			 */
 			/*
 			 * akpm: if the caller was the kupdate function we put
 			 * this inode at the head of s_dirty so it gets first
 			 * consideration.  Otherwise, move it to the tail, for
 			 * the reasons described there.  I'm not really sure
 			 * how much sense this makes.  Presumably I had a good
 			 * reasons for doing it this way, and I'd rather not
 			 * muck with it at present.
 			 */
 			if (wbc->for_kupdate) {
 				/*
 				 * For the kupdate function we move the inode
 				 * to s_more_io so it will get more writeout as
 				 * soon as the queue becomes uncongested.
 				 */
 				inode->i_state |= I_DIRTY_PAGES;
 				requeue_io(inode);
 			} else {
 				/*
 				 * Otherwise fully redirty the inode so that
 				 * other inodes on this superblock will get some
 				 * writeout.  Otherwise heavy writing to one
 				 * file would indefinitely suspend writeout of
 				 * all the other files.
 				 */
 				inode->i_state |= I_DIRTY_PAGES;
 				redirty_tail(inode);
 			}
 		} else if (inode->i_state & I_DIRTY) {
 			/*
 			 * Someone redirtied the inode while were writing back
 			 * the pages.
 			 */
 			redirty_tail(inode);
 		} else if (atomic_read(&inode->i_count)) {
 			/*
 			 * The inode is clean, inuse
 			 */
 			list_move(&inode->i_list, &inode_in_use);
 		} else {
 			/*
 			 * The inode is clean, unused
 			 */
 			list_move(&inode->i_list, &inode_unused);
 		}
 	}
 	wake_up_inode(inode);
 	return ret;
 }
 /*
  * Write out an inode's dirty pages.  Called under inode_lock.  Either the
  * caller has ref on the inode (either via __iget or via syscall against an fd)
  * or the inode has I_WILL_FREE set (via generic_forget_inode)
  */
 static int
 __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	wait_queue_head_t *wqh;
 	if (!atomic_read(&inode->i_count))
 		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
 	else
 		WARN_ON(inode->i_state & I_WILL_FREE);
 	if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_LOCK)) {
 		struct address_space *mapping = inode->i_mapping;
 		int ret;
 		/*
 		 * We're skipping this inode because it's locked, and we're not
 		 * doing writeback-for-data-integrity.  Move it to s_more_io so
 		 * that writeback can proceed with the other inodes on s_io.
 		 * We'll have another go at writing back this inode when we
 		 * completed a full scan of s_io.
 		 */
 		requeue_io(inode);
 		/*
 		 * Even if we don't actually write the inode itself here,
 		 * we can at least start some of the data writeout..
 		 */
 		spin_unlock(&inode_lock);
 		ret = do_writepages(mapping, wbc);
 		spin_lock(&inode_lock);
 		return ret;
 	}
 	/*
 	 * It's a data-integrity sync.  We must wait.
 	 */
 	if (inode->i_state & I_LOCK) {
 		DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LOCK);
 		wqh = bit_waitqueue(&inode->i_state, __I_LOCK);
 		do {
 			spin_unlock(&inode_lock);
 			__wait_on_bit(wqh, &wq, inode_wait,
 							TASK_UNINTERRUPTIBLE);
 			spin_lock(&inode_lock);
 		} while (inode->i_state & I_LOCK);
 	}
 	return __sync_single_inode(inode, wbc);
 }
 /*
  * Write out a superblock's list of dirty inodes.  A wait will be performed
  * upon no inodes, all inodes or the final one, depending upon sync_mode.
  *
  * If older_than_this is non-NULL, then only write out inodes which
  * had their first dirtying at a time earlier than *older_than_this.
  *
  * If we're a pdlfush thread, then implement pdflush collision avoidance
  * against the entire list.
  *
  * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so
  * that it can be located for waiting on in __writeback_single_inode().
  *
  * Called under inode_lock.
  *
  * If `bdi' is non-zero then we're being asked to writeback a specific queue.
  * This function assumes that the blockdev superblock's inodes are backed by
  * a variety of queues, so all inodes are searched.  For other superblocks,
  * assume that all inodes are backed by the same queue.
  *
  * FIXME: this linear search could get expensive with many fileystems.  But
  * how to fix?  We need to go from an address_space to all inodes which share
  * a queue with that address_space.  (Easy: have a global "dirty superblocks"
  * list).
  *
  * The inodes to be written are parked on sb->s_io.  They are moved back onto
  * sb->s_dirty as they are selected for writing.  This way, none can be missed
  * on the writer throttling path, and we get decent balancing between many
  * throttled threads: we don't want them all piling up on __wait_on_inode.
  */
 static void
 sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
 {
 	const unsigned long start = jiffies;	/* livelock avoidance */
 	if (!wbc->for_kupdate || list_empty(&sb->s_io))
 		queue_io(sb, wbc->older_than_this);
 	while (!list_empty(&sb->s_io)) {
 		struct inode *inode = list_entry(sb->s_io.prev,
 						struct inode, i_list);
 		struct address_space *mapping = inode->i_mapping;
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		long pages_skipped;
 		if (!bdi_cap_writeback_dirty(bdi)) {
 			redirty_tail(inode);
 			if (sb_is_blkdev_sb(sb)) {
 				/*
 				 * Dirty memory-backed blockdev: the ramdisk
 				 * driver does this.  Skip just this inode
 				 */
 				continue;
 			}
 			/*
 			 * Dirty memory-backed inode against a filesystem other
 			 * than the kernel-internal bdev filesystem.  Skip the
 			 * entire superblock.
 			 */
 			break;
 		}
 		if (wbc->nonblocking && bdi_write_congested(bdi)) {
 			wbc->encountered_congestion = 1;
 			if (!sb_is_blkdev_sb(sb))
 				break;		/* Skip a congested fs */
 			requeue_io(inode);
 			continue;		/* Skip a congested blockdev */
 		}
 		if (wbc->bdi && bdi != wbc->bdi) {
 			if (!sb_is_blkdev_sb(sb))
 				break;		/* fs has the wrong queue */
 			requeue_io(inode);
 			continue;		/* blockdev has wrong queue */
 		}
 		/* Was this inode dirtied after sync_sb_inodes was called? */
 		if (time_after(inode->dirtied_when, start))
 			break;
 		/* Is another pdflush already flushing this queue? */
 		if (current_is_pdflush() && !writeback_acquire(bdi))
 			break;
 		BUG_ON(inode->i_state & I_FREEING);
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		__writeback_single_inode(inode, wbc);
 		if (wbc->sync_mode == WB_SYNC_HOLD) {
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_list, &sb->s_dirty);
 		}
 		if (current_is_pdflush())
 			writeback_release(bdi);
 		if (wbc->pages_skipped != pages_skipped) {
 			/*
 			 * writeback is not making progress due to locked
 			 * buffers.  Skip this inode for now.
 			 */
 			redirty_tail(inode);
 		}
 		spin_unlock(&inode_lock);
 		iput(inode);
 		cond_resched();
 		spin_lock(&inode_lock);
 		if (wbc->nr_to_write <= 0)
 			break;
 	}
 	return;		/* Leave any unwritten inodes on s_io */
 }
 /*
  * Start writeback of dirty pagecache data against all unlocked inodes.
  *
  * Note:
  * We don't need to grab a reference to superblock here. If it has non-empty
  * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
  * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
  * empty. Since __sync_single_inode() regains inode_lock before it finally moves
  * inode from superblock lists we are OK.
  *
  * If `older_than_this' is non-zero then only flush inodes which have a
  * flushtime older than *older_than_this.
  *
  * If `bdi' is non-zero then we will scan the first inode against each
  * superblock until we find the matching ones.  One group will be the dirty
  * inodes against a filesystem.  Then when we hit the dummy blockdev superblock,
  * sync_sb_inodes will seekout the blockdev which matches `bdi'.  Maybe not
  * super-efficient but we're about to do a ton of I/O...
  */
 void
 writeback_inodes(struct writeback_control *wbc)
 {
 	struct super_block *sb;
 	might_sleep();
 	spin_lock(&sb_lock);
 restart:
 	sb = sb_entry(super_blocks.prev);
 	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
-		if (!list_empty(&sb->s_dirty) || !list_empty(&sb->s_io)) {
+		if (sb_has_dirty_inodes(sb)) {
 			/* we're making our own get_super here */
 			sb->s_count++;
 			spin_unlock(&sb_lock);
 			/*
 			 * If we can't get the readlock, there's no sense in
 			 * waiting around, most of the time the FS is going to
 			 * be unmounted by the time it is released.
 			 */
 			if (down_read_trylock(&sb->s_umount)) {
 				if (sb->s_root) {
 					spin_lock(&inode_lock);
 					sync_sb_inodes(sb, wbc);
 					spin_unlock(&inode_lock);
 				}
 				up_read(&sb->s_umount);
 			}
 			spin_lock(&sb_lock);
 			if (__put_super_and_need_restart(sb))
 				goto restart;
 		}
 		if (wbc->nr_to_write <= 0)
 			break;
 	}
 	spin_unlock(&sb_lock);
 }
 /*
  * writeback and wait upon the filesystem's dirty inodes.  The caller will
  * do this in two passes - one to write, and one to wait.  WB_SYNC_HOLD is
  * used to park the written inodes on sb->s_dirty for the wait pass.
  *
  * A finite limit is set on the number of pages which will be written.
  * To prevent infinite livelock of sys_sync().
  *
  * We add in the number of potentially dirty inodes, because each inode write
  * can dirty pagecache in the underlying blockdev.
  */
 void sync_inodes_sb(struct super_block *sb, int wait)
 {
 	struct writeback_control wbc = {
 		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};
 	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
 	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 	wbc.nr_to_write = nr_dirty + nr_unstable +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused) +
 			nr_dirty + nr_unstable;
 	wbc.nr_to_write += wbc.nr_to_write / 2;		/* Bit more for luck */
 	spin_lock(&inode_lock);
 	sync_sb_inodes(sb, &wbc);
 	spin_unlock(&inode_lock);
 }
 /*
  * Rather lame livelock avoidance.
  */
 static void set_sb_syncing(int val)
 {
 	struct super_block *sb;
 	spin_lock(&sb_lock);
 	sb = sb_entry(super_blocks.prev);
 	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
 		sb->s_syncing = val;
 	}
 	spin_unlock(&sb_lock);
 }
 /**
  * sync_inodes - writes all inodes to disk
  * @wait: wait for completion
  *
  * sync_inodes() goes through each super block's dirty inode list, writes the
  * inodes out, waits on the writeout and puts the inodes back on the normal
  * list.
  *
  * This is for sys_sync().  fsync_dev() uses the same algorithm.  The subtle
  * part of the sync functions is that the blockdev "superblock" is processed
  * last.  This is because the write_inode() function of a typical fs will
  * perform no I/O, but will mark buffers in the blockdev mapping as dirty.
  * What we want to do is to perform all that dirtying first, and then write
  * back all those inode blocks via the blockdev mapping in one sweep.  So the
  * additional (somewhat redundant) sync_blockdev() calls here are to make
  * sure that really happens.  Because if we call sync_inodes_sb(wait=1) with
  * outstanding dirty inodes, the writeback goes block-at-a-time within the
  * filesystem's write_inode().  This is extremely slow.
  */
 static void __sync_inodes(int wait)
 {
 	struct super_block *sb;
 	spin_lock(&sb_lock);
 restart:
 	list_for_each_entry(sb, &super_blocks, s_list) {
 		if (sb->s_syncing)
 			continue;
 		sb->s_syncing = 1;
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 		down_read(&sb->s_umount);
 		if (sb->s_root) {
 			sync_inodes_sb(sb, wait);
 			sync_blockdev(sb->s_bdev);
 		}
 		up_read(&sb->s_umount);
 		spin_lock(&sb_lock);
 		if (__put_super_and_need_restart(sb))
 			goto restart;
 	}
 	spin_unlock(&sb_lock);
 }
 void sync_inodes(int wait)
 {
 	set_sb_syncing(0);
 	__sync_inodes(0);
 	if (wait) {
 		set_sb_syncing(0);
 		__sync_inodes(1);
 	}
 }
 /**
  * write_inode_now	-	write an inode to disk
  * @inode: inode to write to disk
  * @sync: whether the write should be synchronous or not
  *
  * This function commits an inode to disk immediately if it is dirty. This is
  * primarily needed by knfsd.
  *
  * The caller must either have a ref on the inode or must have set I_WILL_FREE.
  */
 int write_inode_now(struct inode *inode, int sync)
 {
 	int ret;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = WB_SYNC_ALL,
 		.range_start = 0,
 		.range_end = LLONG_MAX,
 	};
 	if (!mapping_cap_writeback_dirty(inode->i_mapping))
 		wbc.nr_to_write = 0;
 	might_sleep();
 	spin_lock(&inode_lock);
 	ret = __writeback_single_inode(inode, &wbc);
 	spin_unlock(&inode_lock);
 	if (sync)
 		wait_on_inode(inode);
 	return ret;
 }
 EXPORT_SYMBOL(write_inode_now);
 /**
  * sync_inode - write an inode and its pages to disk.
  * @inode: the inode to sync
  * @wbc: controls the writeback mode
  *
  * sync_inode() will write an inode and its pages to disk.  It will also
  * correctly update the inode on its superblock's dirty inode lists and will
  * update inode->i_state.
  *
  * The caller must have a ref on the inode.
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	int ret;
 	spin_lock(&inode_lock);
 	ret = __writeback_single_inode(inode, wbc);
 	spin_unlock(&inode_lock);
 	return ret;
 }
 EXPORT_SYMBOL(sync_inode);
 /**
  * generic_osync_inode - flush all dirty data for a given inode to disk
  * @inode: inode to write
  * @mapping: the address_space that should be flushed
  * @what:  what to write and wait upon
  *
  * This can be called by file_write functions for files which have the
  * O_SYNC flag set, to flush dirty writes to disk.
  *
  * @what is a bitmask, specifying which part of the inode's data should be
  * written and waited upon.
  *
  *    OSYNC_DATA:     i_mapping's dirty data
  *    OSYNC_METADATA: the buffers at i_mapping->private_list
  *    OSYNC_INODE:    the inode itself
  */
 int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what)
 {
 	int err = 0;
 	int need_write_inode_now = 0;
 	int err2;
 	if (what & OSYNC_DATA)
 		err = filemap_fdatawrite(mapping);
 	if (what & (OSYNC_METADATA|OSYNC_DATA)) {
 		err2 = sync_mapping_buffers(mapping);
 		if (!err)
 			err = err2;
 	}
 	if (what & OSYNC_DATA) {
 		err2 = filemap_fdatawait(mapping);
 		if (!err)
 			err = err2;
 	}
 	spin_lock(&inode_lock);
 	if ((inode->i_state & I_DIRTY) &&
 	    ((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC)))
 		need_write_inode_now = 1;
 	spin_unlock(&inode_lock);
 	if (need_write_inode_now) {
 		err2 = write_inode_now(inode, 1);
 		if (!err)
 			err = err2;
 	}
 	else
 		wait_on_inode(inode);
 	return err;
 }
 EXPORT_SYMBOL(generic_osync_inode);
 /**
  * writeback_acquire: attempt to get exclusive writeback access to a device
  * @bdi: the device's backing_dev_info structure
  *
  * It is a waste of resources to have more than one pdflush thread blocked on
  * a single request queue.  Exclusion at the request_queue level is obtained
  * via a flag in the request_queue's backing_dev_info.state.
  *
  * Non-request_queue-backed address_spaces will share default_backing_dev_info,
  * unless they implement their own.  Which is somewhat inefficient, as this
  * may prevent concurrent writeback against multiple devices.
  */
 int writeback_acquire(struct backing_dev_info *bdi)
 {
 	return !test_and_set_bit(BDI_pdflush, &bdi->state);
 }
 /**
  * writeback_in_progress: determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
  *
  * Determine whether there is writeback in progress against a backing device.
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
 	return test_bit(BDI_pdflush, &bdi->state);
 }
 /**
  * writeback_release: relinquish exclusive writeback access against a device.
  * @bdi: the device's backing_dev_info structure
  */
 void writeback_release(struct backing_dev_info *bdi)
 {
 	BUG_ON(!writeback_in_progress(bdi));
 	clear_bit(BDI_pdflush, &bdi->state);
 }

fs/ntfs/super.c

Diff comments View file @ 08d8e97

1	/*	1	/*
2	* super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.	2	* super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
3	*	3	*
4	* Copyright (c) 2001-2007 Anton Altaparmakov	4	* Copyright (c) 2001-2007 Anton Altaparmakov
5	* Copyright (c) 2001,2002 Richard Russon	5	* Copyright (c) 2001,2002 Richard Russon
6	*	6	*
7	* This program/include file is free software; you can redistribute it and/or	7	* This program/include file is free software; you can redistribute it and/or
8	* modify it under the terms of the GNU General Public License as published	8	* modify it under the terms of the GNU General Public License as published
9	* by the Free Software Foundation; either version 2 of the License, or	9	* by the Free Software Foundation; either version 2 of the License, or
10	* (at your option) any later version.	10	* (at your option) any later version.
11	*	11	*
12	* This program/include file is distributed in the hope that it will be	12	* This program/include file is distributed in the hope that it will be
13	* useful, but WITHOUT ANY WARRANTY; without even the implied warranty	13	* useful, but WITHOUT ANY WARRANTY; without even the implied warranty
14	* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the	14	* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15	* GNU General Public License for more details.	15	* GNU General Public License for more details.
16	*	16	*
17	* You should have received a copy of the GNU General Public License	17	* You should have received a copy of the GNU General Public License
18	* along with this program (in the main directory of the Linux-NTFS	18	* along with this program (in the main directory of the Linux-NTFS
19	* distribution in the file COPYING); if not, write to the Free Software	19	* distribution in the file COPYING); if not, write to the Free Software
20	* Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA	20	* Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
21	*/	21	*/
22		22
23	#include <linux/stddef.h>	23	#include <linux/stddef.h>
24	#include <linux/init.h>	24	#include <linux/init.h>
25	#include <linux/slab.h>	25	#include <linux/slab.h>
26	#include <linux/string.h>	26	#include <linux/string.h>
27	#include <linux/spinlock.h>	27	#include <linux/spinlock.h>
28	#include <linux/blkdev.h> /* For bdev_hardsect_size(). */	28	#include <linux/blkdev.h> /* For bdev_hardsect_size(). */
29	#include <linux/backing-dev.h>	29	#include <linux/backing-dev.h>
30	#include <linux/buffer_head.h>	30	#include <linux/buffer_head.h>
31	#include <linux/vfs.h>	31	#include <linux/vfs.h>
32	#include <linux/moduleparam.h>	32	#include <linux/moduleparam.h>
33	#include <linux/smp_lock.h>	33	#include <linux/smp_lock.h>
34		34
35	#include "sysctl.h"	35	#include "sysctl.h"
36	#include "logfile.h"	36	#include "logfile.h"
37	#include "quota.h"	37	#include "quota.h"
38	#include "usnjrnl.h"	38	#include "usnjrnl.h"
39	#include "dir.h"	39	#include "dir.h"
40	#include "debug.h"	40	#include "debug.h"
41	#include "index.h"	41	#include "index.h"
42	#include "aops.h"	42	#include "aops.h"
43	#include "layout.h"	43	#include "layout.h"
44	#include "malloc.h"	44	#include "malloc.h"
45	#include "ntfs.h"	45	#include "ntfs.h"
46		46
47	/* Number of mounted filesystems which have compression enabled. */	47	/* Number of mounted filesystems which have compression enabled. */
48	static unsigned long ntfs_nr_compression_users;	48	static unsigned long ntfs_nr_compression_users;
49		49
50	/* A global default upcase table and a corresponding reference count. */	50	/* A global default upcase table and a corresponding reference count. */
51	static ntfschar *default_upcase = NULL;	51	static ntfschar *default_upcase = NULL;
52	static unsigned long ntfs_nr_upcase_users = 0;	52	static unsigned long ntfs_nr_upcase_users = 0;
53		53
54	/* Error constants/strings used in inode.c::ntfs_show_options(). */	54	/* Error constants/strings used in inode.c::ntfs_show_options(). */
55	typedef enum {	55	typedef enum {
56	/* One of these must be present, default is ON_ERRORS_CONTINUE. */	56	/* One of these must be present, default is ON_ERRORS_CONTINUE. */
57	ON_ERRORS_PANIC = 0x01,	57	ON_ERRORS_PANIC = 0x01,
58	ON_ERRORS_REMOUNT_RO = 0x02,	58	ON_ERRORS_REMOUNT_RO = 0x02,
59	ON_ERRORS_CONTINUE = 0x04,	59	ON_ERRORS_CONTINUE = 0x04,
60	/* Optional, can be combined with any of the above. */	60	/* Optional, can be combined with any of the above. */
61	ON_ERRORS_RECOVER = 0x10,	61	ON_ERRORS_RECOVER = 0x10,
62	} ON_ERRORS_ACTIONS;	62	} ON_ERRORS_ACTIONS;
63		63
64	const option_t on_errors_arr[] = {	64	const option_t on_errors_arr[] = {
65	{ ON_ERRORS_PANIC, "panic" },	65	{ ON_ERRORS_PANIC, "panic" },
66	{ ON_ERRORS_REMOUNT_RO, "remount-ro", },	66	{ ON_ERRORS_REMOUNT_RO, "remount-ro", },
67	{ ON_ERRORS_CONTINUE, "continue", },	67	{ ON_ERRORS_CONTINUE, "continue", },
68	{ ON_ERRORS_RECOVER, "recover" },	68	{ ON_ERRORS_RECOVER, "recover" },
69	{ 0, NULL }	69	{ 0, NULL }
70	};	70	};
71		71
72	/**	72	/**
73	* simple_getbool -	73	* simple_getbool -
74	*	74	*
75	* Copied from old ntfs driver (which copied from vfat driver).	75	* Copied from old ntfs driver (which copied from vfat driver).
76	*/	76	*/
77	static int simple_getbool(char s, bool setval)	77	static int simple_getbool(char s, bool setval)
78	{	78	{
79	if (s) {	79	if (s) {
80	if (!strcmp(s, "1") \|\| !strcmp(s, "yes") \|\| !strcmp(s, "true"))	80	if (!strcmp(s, "1") \|\| !strcmp(s, "yes") \|\| !strcmp(s, "true"))
81	*setval = true;	81	*setval = true;
82	else if (!strcmp(s, "0") \|\| !strcmp(s, "no") \|\|	82	else if (!strcmp(s, "0") \|\| !strcmp(s, "no") \|\|
83	!strcmp(s, "false"))	83	!strcmp(s, "false"))
84	*setval = false;	84	*setval = false;
85	else	85	else
86	return 0;	86	return 0;
87	} else	87	} else
88	*setval = true;	88	*setval = true;
89	return 1;	89	return 1;
90	}	90	}
91		91
92	/**	92	/**
93	* parse_options - parse the (re)mount options	93	* parse_options - parse the (re)mount options
94	* @vol: ntfs volume	94	* @vol: ntfs volume
95	* @opt: string containing the (re)mount options	95	* @opt: string containing the (re)mount options
96	*	96	*
97	* Parse the recognized options in @opt for the ntfs volume described by @vol.	97	* Parse the recognized options in @opt for the ntfs volume described by @vol.
98	*/	98	*/
99	static bool parse_options(ntfs_volume vol, char opt)	99	static bool parse_options(ntfs_volume vol, char opt)
100	{	100	{
101	char p, v, *ov;	101	char p, v, *ov;
102	static char *utf8 = "utf8";	102	static char *utf8 = "utf8";
103	int errors = 0, sloppy = 0;	103	int errors = 0, sloppy = 0;
104	uid_t uid = (uid_t)-1;	104	uid_t uid = (uid_t)-1;
105	gid_t gid = (gid_t)-1;	105	gid_t gid = (gid_t)-1;
106	mode_t fmask = (mode_t)-1, dmask = (mode_t)-1;	106	mode_t fmask = (mode_t)-1, dmask = (mode_t)-1;
107	int mft_zone_multiplier = -1, on_errors = -1;	107	int mft_zone_multiplier = -1, on_errors = -1;
108	int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;	108	int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;
109	struct nls_table nls_map = NULL, old_nls;	109	struct nls_table nls_map = NULL, old_nls;
110		110
111	/* I am lazy... (-8 */	111	/* I am lazy... (-8 */
112	#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value) \	112	#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value) \
113	if (!strcmp(p, option)) { \	113	if (!strcmp(p, option)) { \
114	if (!v \|\| !*v) \	114	if (!v \|\| !*v) \
115	variable = default_value; \	115	variable = default_value; \
116	else { \	116	else { \
117	variable = simple_strtoul(ov = v, &v, 0); \	117	variable = simple_strtoul(ov = v, &v, 0); \
118	if (*v) \	118	if (*v) \
119	goto needs_val; \	119	goto needs_val; \
120	} \	120	} \
121	}	121	}
122	#define NTFS_GETOPT(option, variable) \	122	#define NTFS_GETOPT(option, variable) \
123	if (!strcmp(p, option)) { \	123	if (!strcmp(p, option)) { \
124	if (!v \|\| !*v) \	124	if (!v \|\| !*v) \
125	goto needs_arg; \	125	goto needs_arg; \
126	variable = simple_strtoul(ov = v, &v, 0); \	126	variable = simple_strtoul(ov = v, &v, 0); \
127	if (*v) \	127	if (*v) \
128	goto needs_val; \	128	goto needs_val; \
129	}	129	}
130	#define NTFS_GETOPT_OCTAL(option, variable) \	130	#define NTFS_GETOPT_OCTAL(option, variable) \
131	if (!strcmp(p, option)) { \	131	if (!strcmp(p, option)) { \
132	if (!v \|\| !*v) \	132	if (!v \|\| !*v) \
133	goto needs_arg; \	133	goto needs_arg; \
134	variable = simple_strtoul(ov = v, &v, 8); \	134	variable = simple_strtoul(ov = v, &v, 8); \
135	if (*v) \	135	if (*v) \
136	goto needs_val; \	136	goto needs_val; \
137	}	137	}
138	#define NTFS_GETOPT_BOOL(option, variable) \	138	#define NTFS_GETOPT_BOOL(option, variable) \
139	if (!strcmp(p, option)) { \	139	if (!strcmp(p, option)) { \
140	bool val; \	140	bool val; \
141	if (!simple_getbool(v, &val)) \	141	if (!simple_getbool(v, &val)) \
142	goto needs_bool; \	142	goto needs_bool; \
143	variable = val; \	143	variable = val; \
144	}	144	}
145	#define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array) \	145	#define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array) \
146	if (!strcmp(p, option)) { \	146	if (!strcmp(p, option)) { \
147	int _i; \	147	int _i; \
148	if (!v \|\| !*v) \	148	if (!v \|\| !*v) \
149	goto needs_arg; \	149	goto needs_arg; \
150	ov = v; \	150	ov = v; \
151	if (variable == -1) \	151	if (variable == -1) \
152	variable = 0; \	152	variable = 0; \
153	for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \	153	for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \
154	if (!strcmp(opt_array[_i].str, v)) { \	154	if (!strcmp(opt_array[_i].str, v)) { \
155	variable \|= opt_array[_i].val; \	155	variable \|= opt_array[_i].val; \
156	break; \	156	break; \
157	} \	157	} \
158	if (!opt_array[_i].str \|\| !*opt_array[_i].str) \	158	if (!opt_array[_i].str \|\| !*opt_array[_i].str) \
159	goto needs_val; \	159	goto needs_val; \
160	}	160	}
161	if (!opt \|\| !*opt)	161	if (!opt \|\| !*opt)
162	goto no_mount_options;	162	goto no_mount_options;
163	ntfs_debug("Entering with mount options string: %s", opt);	163	ntfs_debug("Entering with mount options string: %s", opt);
164	while ((p = strsep(&opt, ","))) {	164	while ((p = strsep(&opt, ","))) {
165	if ((v = strchr(p, '=')))	165	if ((v = strchr(p, '=')))
166	*v++ = 0;	166	*v++ = 0;
167	NTFS_GETOPT("uid", uid)	167	NTFS_GETOPT("uid", uid)
168	else NTFS_GETOPT("gid", gid)	168	else NTFS_GETOPT("gid", gid)
169	else NTFS_GETOPT_OCTAL("umask", fmask = dmask)	169	else NTFS_GETOPT_OCTAL("umask", fmask = dmask)
170	else NTFS_GETOPT_OCTAL("fmask", fmask)	170	else NTFS_GETOPT_OCTAL("fmask", fmask)
171	else NTFS_GETOPT_OCTAL("dmask", dmask)	171	else NTFS_GETOPT_OCTAL("dmask", dmask)
172	else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)	172	else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
173	else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, true)	173	else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, true)
174	else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)	174	else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
175	else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)	175	else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)
176	else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse)	176	else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse)
177	else NTFS_GETOPT_OPTIONS_ARRAY("errors", on_errors,	177	else NTFS_GETOPT_OPTIONS_ARRAY("errors", on_errors,
178	on_errors_arr)	178	on_errors_arr)
179	else if (!strcmp(p, "posix") \|\| !strcmp(p, "show_inodes"))	179	else if (!strcmp(p, "posix") \|\| !strcmp(p, "show_inodes"))
180	ntfs_warning(vol->sb, "Ignoring obsolete option %s.",	180	ntfs_warning(vol->sb, "Ignoring obsolete option %s.",
181	p);	181	p);
182	else if (!strcmp(p, "nls") \|\| !strcmp(p, "iocharset")) {	182	else if (!strcmp(p, "nls") \|\| !strcmp(p, "iocharset")) {
183	if (!strcmp(p, "iocharset"))	183	if (!strcmp(p, "iocharset"))
184	ntfs_warning(vol->sb, "Option iocharset is "	184	ntfs_warning(vol->sb, "Option iocharset is "
185	"deprecated. Please use "	185	"deprecated. Please use "
186	"option nls=<charsetname> in "	186	"option nls=<charsetname> in "
187	"the future.");	187	"the future.");
188	if (!v \|\| !*v)	188	if (!v \|\| !*v)
189	goto needs_arg;	189	goto needs_arg;
190	use_utf8:	190	use_utf8:
191	old_nls = nls_map;	191	old_nls = nls_map;
192	nls_map = load_nls(v);	192	nls_map = load_nls(v);
193	if (!nls_map) {	193	if (!nls_map) {
194	if (!old_nls) {	194	if (!old_nls) {
195	ntfs_error(vol->sb, "NLS character set "	195	ntfs_error(vol->sb, "NLS character set "
196	"%s not found.", v);	196	"%s not found.", v);
197	return false;	197	return false;
198	}	198	}
199	ntfs_error(vol->sb, "NLS character set %s not "	199	ntfs_error(vol->sb, "NLS character set %s not "
200	"found. Using previous one %s.",	200	"found. Using previous one %s.",
201	v, old_nls->charset);	201	v, old_nls->charset);
202	nls_map = old_nls;	202	nls_map = old_nls;
203	} else /* nls_map */ {	203	} else /* nls_map */ {
204	if (old_nls)	204	if (old_nls)
205	unload_nls(old_nls);	205	unload_nls(old_nls);
206	}	206	}
207	} else if (!strcmp(p, "utf8")) {	207	} else if (!strcmp(p, "utf8")) {
208	bool val = false;	208	bool val = false;
209	ntfs_warning(vol->sb, "Option utf8 is no longer "	209	ntfs_warning(vol->sb, "Option utf8 is no longer "
210	"supported, using option nls=utf8. Please "	210	"supported, using option nls=utf8. Please "
211	"use option nls=utf8 in the future and "	211	"use option nls=utf8 in the future and "
212	"make sure utf8 is compiled either as a "	212	"make sure utf8 is compiled either as a "
213	"module or into the kernel.");	213	"module or into the kernel.");
214	if (!v \|\| !*v)	214	if (!v \|\| !*v)
215	val = true;	215	val = true;
216	else if (!simple_getbool(v, &val))	216	else if (!simple_getbool(v, &val))
217	goto needs_bool;	217	goto needs_bool;
218	if (val) {	218	if (val) {
219	v = utf8;	219	v = utf8;
220	goto use_utf8;	220	goto use_utf8;
221	}	221	}
222	} else {	222	} else {
223	ntfs_error(vol->sb, "Unrecognized mount option %s.", p);	223	ntfs_error(vol->sb, "Unrecognized mount option %s.", p);
224	if (errors < INT_MAX)	224	if (errors < INT_MAX)
225	errors++;	225	errors++;
226	}	226	}
227	#undef NTFS_GETOPT_OPTIONS_ARRAY	227	#undef NTFS_GETOPT_OPTIONS_ARRAY
228	#undef NTFS_GETOPT_BOOL	228	#undef NTFS_GETOPT_BOOL
229	#undef NTFS_GETOPT	229	#undef NTFS_GETOPT
230	#undef NTFS_GETOPT_WITH_DEFAULT	230	#undef NTFS_GETOPT_WITH_DEFAULT
231	}	231	}
232	no_mount_options:	232	no_mount_options:
233	if (errors && !sloppy)	233	if (errors && !sloppy)
234	return false;	234	return false;
235	if (sloppy)	235	if (sloppy)
236	ntfs_warning(vol->sb, "Sloppy option given. Ignoring "	236	ntfs_warning(vol->sb, "Sloppy option given. Ignoring "
237	"unrecognized mount option(s) and continuing.");	237	"unrecognized mount option(s) and continuing.");
238	/* Keep this first! */	238	/* Keep this first! */
239	if (on_errors != -1) {	239	if (on_errors != -1) {
240	if (!on_errors) {	240	if (!on_errors) {
241	ntfs_error(vol->sb, "Invalid errors option argument "	241	ntfs_error(vol->sb, "Invalid errors option argument "
242	"or bug in options parser.");	242	"or bug in options parser.");
243	return false;	243	return false;
244	}	244	}
245	}	245	}
246	if (nls_map) {	246	if (nls_map) {
247	if (vol->nls_map && vol->nls_map != nls_map) {	247	if (vol->nls_map && vol->nls_map != nls_map) {
248	ntfs_error(vol->sb, "Cannot change NLS character set "	248	ntfs_error(vol->sb, "Cannot change NLS character set "
249	"on remount.");	249	"on remount.");
250	return false;	250	return false;
251	} /* else (!vol->nls_map) */	251	} /* else (!vol->nls_map) */
252	ntfs_debug("Using NLS character set %s.", nls_map->charset);	252	ntfs_debug("Using NLS character set %s.", nls_map->charset);
253	vol->nls_map = nls_map;	253	vol->nls_map = nls_map;
254	} else /* (!nls_map) */ {	254	} else /* (!nls_map) */ {
255	if (!vol->nls_map) {	255	if (!vol->nls_map) {
256	vol->nls_map = load_nls_default();	256	vol->nls_map = load_nls_default();
257	if (!vol->nls_map) {	257	if (!vol->nls_map) {
258	ntfs_error(vol->sb, "Failed to load default "	258	ntfs_error(vol->sb, "Failed to load default "
259	"NLS character set.");	259	"NLS character set.");
260	return false;	260	return false;
261	}	261	}
262	ntfs_debug("Using default NLS character set (%s).",	262	ntfs_debug("Using default NLS character set (%s).",
263	vol->nls_map->charset);	263	vol->nls_map->charset);
264	}	264	}
265	}	265	}
266	if (mft_zone_multiplier != -1) {	266	if (mft_zone_multiplier != -1) {
267	if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=	267	if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=
268	mft_zone_multiplier) {	268	mft_zone_multiplier) {
269	ntfs_error(vol->sb, "Cannot change mft_zone_multiplier "	269	ntfs_error(vol->sb, "Cannot change mft_zone_multiplier "
270	"on remount.");	270	"on remount.");
271	return false;	271	return false;
272	}	272	}
273	if (mft_zone_multiplier < 1 \|\| mft_zone_multiplier > 4) {	273	if (mft_zone_multiplier < 1 \|\| mft_zone_multiplier > 4) {
274	ntfs_error(vol->sb, "Invalid mft_zone_multiplier. "	274	ntfs_error(vol->sb, "Invalid mft_zone_multiplier. "
275	"Using default value, i.e. 1.");	275	"Using default value, i.e. 1.");
276	mft_zone_multiplier = 1;	276	mft_zone_multiplier = 1;
277	}	277	}
278	vol->mft_zone_multiplier = mft_zone_multiplier;	278	vol->mft_zone_multiplier = mft_zone_multiplier;
279	}	279	}
280	if (!vol->mft_zone_multiplier)	280	if (!vol->mft_zone_multiplier)
281	vol->mft_zone_multiplier = 1;	281	vol->mft_zone_multiplier = 1;
282	if (on_errors != -1)	282	if (on_errors != -1)
283	vol->on_errors = on_errors;	283	vol->on_errors = on_errors;
284	if (!vol->on_errors \|\| vol->on_errors == ON_ERRORS_RECOVER)	284	if (!vol->on_errors \|\| vol->on_errors == ON_ERRORS_RECOVER)
285	vol->on_errors \|= ON_ERRORS_CONTINUE;	285	vol->on_errors \|= ON_ERRORS_CONTINUE;
286	if (uid != (uid_t)-1)	286	if (uid != (uid_t)-1)
287	vol->uid = uid;	287	vol->uid = uid;
288	if (gid != (gid_t)-1)	288	if (gid != (gid_t)-1)
289	vol->gid = gid;	289	vol->gid = gid;
290	if (fmask != (mode_t)-1)	290	if (fmask != (mode_t)-1)
291	vol->fmask = fmask;	291	vol->fmask = fmask;
292	if (dmask != (mode_t)-1)	292	if (dmask != (mode_t)-1)
293	vol->dmask = dmask;	293	vol->dmask = dmask;
294	if (show_sys_files != -1) {	294	if (show_sys_files != -1) {
295	if (show_sys_files)	295	if (show_sys_files)
296	NVolSetShowSystemFiles(vol);	296	NVolSetShowSystemFiles(vol);
297	else	297	else
298	NVolClearShowSystemFiles(vol);	298	NVolClearShowSystemFiles(vol);
299	}	299	}
300	if (case_sensitive != -1) {	300	if (case_sensitive != -1) {
301	if (case_sensitive)	301	if (case_sensitive)
302	NVolSetCaseSensitive(vol);	302	NVolSetCaseSensitive(vol);
303	else	303	else
304	NVolClearCaseSensitive(vol);	304	NVolClearCaseSensitive(vol);
305	}	305	}
306	if (disable_sparse != -1) {	306	if (disable_sparse != -1) {
307	if (disable_sparse)	307	if (disable_sparse)
308	NVolClearSparseEnabled(vol);	308	NVolClearSparseEnabled(vol);
309	else {	309	else {
310	if (!NVolSparseEnabled(vol) &&	310	if (!NVolSparseEnabled(vol) &&
311	vol->major_ver && vol->major_ver < 3)	311	vol->major_ver && vol->major_ver < 3)
312	ntfs_warning(vol->sb, "Not enabling sparse "	312	ntfs_warning(vol->sb, "Not enabling sparse "
313	"support due to NTFS volume "	313	"support due to NTFS volume "
314	"version %i.%i (need at least "	314	"version %i.%i (need at least "
315	"version 3.0).", vol->major_ver,	315	"version 3.0).", vol->major_ver,
316	vol->minor_ver);	316	vol->minor_ver);
317	else	317	else
318	NVolSetSparseEnabled(vol);	318	NVolSetSparseEnabled(vol);
319	}	319	}
320	}	320	}
321	return true;	321	return true;
322	needs_arg:	322	needs_arg:
323	ntfs_error(vol->sb, "The %s option requires an argument.", p);	323	ntfs_error(vol->sb, "The %s option requires an argument.", p);
324	return false;	324	return false;
325	needs_bool:	325	needs_bool:
326	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);	326	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);
327	return false;	327	return false;
328	needs_val:	328	needs_val:
329	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);	329	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);
330	return false;	330	return false;
331	}	331	}
332		332
333	#ifdef NTFS_RW	333	#ifdef NTFS_RW
334		334
335	/**	335	/**
336	* ntfs_write_volume_flags - write new flags to the volume information flags	336	* ntfs_write_volume_flags - write new flags to the volume information flags
337	* @vol: ntfs volume on which to modify the flags	337	* @vol: ntfs volume on which to modify the flags
338	* @flags: new flags value for the volume information flags	338	* @flags: new flags value for the volume information flags
339	*	339	*
340	* Internal function. You probably want to use ntfs_{set,clear}_volume_flags()	340	* Internal function. You probably want to use ntfs_{set,clear}_volume_flags()
341	* instead (see below).	341	* instead (see below).
342	*	342	*
343	* Replace the volume information flags on the volume @vol with the value	343	* Replace the volume information flags on the volume @vol with the value
344	* supplied in @flags. Note, this overwrites the volume information flags, so	344	* supplied in @flags. Note, this overwrites the volume information flags, so
345	* make sure to combine the flags you want to modify with the old flags and use	345	* make sure to combine the flags you want to modify with the old flags and use
346	* the result when calling ntfs_write_volume_flags().	346	* the result when calling ntfs_write_volume_flags().
347	*	347	*
348	* Return 0 on success and -errno on error.	348	* Return 0 on success and -errno on error.
349	*/	349	*/
350	static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags)	350	static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags)
351	{	351	{
352	ntfs_inode *ni = NTFS_I(vol->vol_ino);	352	ntfs_inode *ni = NTFS_I(vol->vol_ino);
353	MFT_RECORD *m;	353	MFT_RECORD *m;
354	VOLUME_INFORMATION *vi;	354	VOLUME_INFORMATION *vi;
355	ntfs_attr_search_ctx *ctx;	355	ntfs_attr_search_ctx *ctx;
356	int err;	356	int err;
357		357
358	ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.",	358	ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.",
359	le16_to_cpu(vol->vol_flags), le16_to_cpu(flags));	359	le16_to_cpu(vol->vol_flags), le16_to_cpu(flags));
360	if (vol->vol_flags == flags)	360	if (vol->vol_flags == flags)
361	goto done;	361	goto done;
362	BUG_ON(!ni);	362	BUG_ON(!ni);
363	m = map_mft_record(ni);	363	m = map_mft_record(ni);
364	if (IS_ERR(m)) {	364	if (IS_ERR(m)) {
365	err = PTR_ERR(m);	365	err = PTR_ERR(m);
366	goto err_out;	366	goto err_out;
367	}	367	}
368	ctx = ntfs_attr_get_search_ctx(ni, m);	368	ctx = ntfs_attr_get_search_ctx(ni, m);
369	if (!ctx) {	369	if (!ctx) {
370	err = -ENOMEM;	370	err = -ENOMEM;
371	goto put_unm_err_out;	371	goto put_unm_err_out;
372	}	372	}
373	err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,	373	err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
374	ctx);	374	ctx);
375	if (err)	375	if (err)
376	goto put_unm_err_out;	376	goto put_unm_err_out;
377	vi = (VOLUME_INFORMATION)((u8)ctx->attr +	377	vi = (VOLUME_INFORMATION)((u8)ctx->attr +
378	le16_to_cpu(ctx->attr->data.resident.value_offset));	378	le16_to_cpu(ctx->attr->data.resident.value_offset));
379	vol->vol_flags = vi->flags = flags;	379	vol->vol_flags = vi->flags = flags;
380	flush_dcache_mft_record_page(ctx->ntfs_ino);	380	flush_dcache_mft_record_page(ctx->ntfs_ino);
381	mark_mft_record_dirty(ctx->ntfs_ino);	381	mark_mft_record_dirty(ctx->ntfs_ino);
382	ntfs_attr_put_search_ctx(ctx);	382	ntfs_attr_put_search_ctx(ctx);
383	unmap_mft_record(ni);	383	unmap_mft_record(ni);
384	done:	384	done:
385	ntfs_debug("Done.");	385	ntfs_debug("Done.");
386	return 0;	386	return 0;
387	put_unm_err_out:	387	put_unm_err_out:
388	if (ctx)	388	if (ctx)
389	ntfs_attr_put_search_ctx(ctx);	389	ntfs_attr_put_search_ctx(ctx);
390	unmap_mft_record(ni);	390	unmap_mft_record(ni);
391	err_out:	391	err_out:
392	ntfs_error(vol->sb, "Failed with error code %i.", -err);	392	ntfs_error(vol->sb, "Failed with error code %i.", -err);
393	return err;	393	return err;
394	}	394	}
395		395
396	/**	396	/**
397	* ntfs_set_volume_flags - set bits in the volume information flags	397	* ntfs_set_volume_flags - set bits in the volume information flags
398	* @vol: ntfs volume on which to modify the flags	398	* @vol: ntfs volume on which to modify the flags
399	* @flags: flags to set on the volume	399	* @flags: flags to set on the volume
400	*	400	*
401	* Set the bits in @flags in the volume information flags on the volume @vol.	401	* Set the bits in @flags in the volume information flags on the volume @vol.
402	*	402	*
403	* Return 0 on success and -errno on error.	403	* Return 0 on success and -errno on error.
404	*/	404	*/
405	static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)	405	static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
406	{	406	{
407	flags &= VOLUME_FLAGS_MASK;	407	flags &= VOLUME_FLAGS_MASK;
408	return ntfs_write_volume_flags(vol, vol->vol_flags \| flags);	408	return ntfs_write_volume_flags(vol, vol->vol_flags \| flags);
409	}	409	}
410		410
411	/**	411	/**
412	* ntfs_clear_volume_flags - clear bits in the volume information flags	412	* ntfs_clear_volume_flags - clear bits in the volume information flags
413	* @vol: ntfs volume on which to modify the flags	413	* @vol: ntfs volume on which to modify the flags
414	* @flags: flags to clear on the volume	414	* @flags: flags to clear on the volume
415	*	415	*
416	* Clear the bits in @flags in the volume information flags on the volume @vol.	416	* Clear the bits in @flags in the volume information flags on the volume @vol.
417	*	417	*
418	* Return 0 on success and -errno on error.	418	* Return 0 on success and -errno on error.
419	*/	419	*/
420	static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)	420	static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
421	{	421	{
422	flags &= VOLUME_FLAGS_MASK;	422	flags &= VOLUME_FLAGS_MASK;
423	flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags));	423	flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags));
424	return ntfs_write_volume_flags(vol, flags);	424	return ntfs_write_volume_flags(vol, flags);
425	}	425	}
426		426
427	#endif /* NTFS_RW */	427	#endif /* NTFS_RW */
428		428
429	/**	429	/**
430	* ntfs_remount - change the mount options of a mounted ntfs filesystem	430	* ntfs_remount - change the mount options of a mounted ntfs filesystem
431	* @sb: superblock of mounted ntfs filesystem	431	* @sb: superblock of mounted ntfs filesystem
432	* @flags: remount flags	432	* @flags: remount flags
433	* @opt: remount options string	433	* @opt: remount options string
434	*	434	*
435	* Change the mount options of an already mounted ntfs filesystem.	435	* Change the mount options of an already mounted ntfs filesystem.
436	*	436	*
437	* NOTE: The VFS sets the @sb->s_flags remount flags to @flags after	437	* NOTE: The VFS sets the @sb->s_flags remount flags to @flags after
438	* ntfs_remount() returns successfully (i.e. returns 0). Otherwise,	438	* ntfs_remount() returns successfully (i.e. returns 0). Otherwise,
439	* @sb->s_flags are not changed.	439	* @sb->s_flags are not changed.
440	*/	440	*/
441	static int ntfs_remount(struct super_block sb, int flags, char *opt)	441	static int ntfs_remount(struct super_block sb, int flags, char *opt)
442	{	442	{
443	ntfs_volume *vol = NTFS_SB(sb);	443	ntfs_volume *vol = NTFS_SB(sb);
444		444
445	ntfs_debug("Entering with remount options string: %s", opt);	445	ntfs_debug("Entering with remount options string: %s", opt);
446	#ifndef NTFS_RW	446	#ifndef NTFS_RW
447	/* For read-only compiled driver, enforce read-only flag. */	447	/* For read-only compiled driver, enforce read-only flag. */
448	*flags \|= MS_RDONLY;	448	*flags \|= MS_RDONLY;
449	#else /* NTFS_RW */	449	#else /* NTFS_RW */
450	/*	450	/*
451	* For the read-write compiled driver, if we are remounting read-write,	451	* For the read-write compiled driver, if we are remounting read-write,
452	* make sure there are no volume errors and that no unsupported volume	452	* make sure there are no volume errors and that no unsupported volume
453	* flags are set. Also, empty the logfile journal as it would become	453	* flags are set. Also, empty the logfile journal as it would become
454	* stale as soon as something is written to the volume and mark the	454	* stale as soon as something is written to the volume and mark the
455	* volume dirty so that chkdsk is run if the volume is not umounted	455	* volume dirty so that chkdsk is run if the volume is not umounted
456	* cleanly. Finally, mark the quotas out of date so Windows rescans	456	* cleanly. Finally, mark the quotas out of date so Windows rescans
457	* the volume on boot and updates them.	457	* the volume on boot and updates them.
458	*	458	*
459	* When remounting read-only, mark the volume clean if no volume errors	459	* When remounting read-only, mark the volume clean if no volume errors
460	* have occured.	460	* have occured.
461	*/	461	*/
462	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {	462	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
463	static const char *es = ". Cannot remount read-write.";	463	static const char *es = ". Cannot remount read-write.";
464		464
465	/* Remounting read-write. */	465	/* Remounting read-write. */
466	if (NVolErrors(vol)) {	466	if (NVolErrors(vol)) {
467	ntfs_error(sb, "Volume has errors and is read-only%s",	467	ntfs_error(sb, "Volume has errors and is read-only%s",
468	es);	468	es);
469	return -EROFS;	469	return -EROFS;
470	}	470	}
471	if (vol->vol_flags & VOLUME_IS_DIRTY) {	471	if (vol->vol_flags & VOLUME_IS_DIRTY) {
472	ntfs_error(sb, "Volume is dirty and read-only%s", es);	472	ntfs_error(sb, "Volume is dirty and read-only%s", es);
473	return -EROFS;	473	return -EROFS;
474	}	474	}
475	if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {	475	if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
476	ntfs_error(sb, "Volume has been modified by chkdsk "	476	ntfs_error(sb, "Volume has been modified by chkdsk "
477	"and is read-only%s", es);	477	"and is read-only%s", es);
478	return -EROFS;	478	return -EROFS;
479	}	479	}
480	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {	480	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
481	ntfs_error(sb, "Volume has unsupported flags set "	481	ntfs_error(sb, "Volume has unsupported flags set "
482	"(0x%x) and is read-only%s",	482	"(0x%x) and is read-only%s",
483	(unsigned)le16_to_cpu(vol->vol_flags),	483	(unsigned)le16_to_cpu(vol->vol_flags),
484	es);	484	es);
485	return -EROFS;	485	return -EROFS;
486	}	486	}
487	if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {	487	if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
488	ntfs_error(sb, "Failed to set dirty bit in volume "	488	ntfs_error(sb, "Failed to set dirty bit in volume "
489	"information flags%s", es);	489	"information flags%s", es);
490	return -EROFS;	490	return -EROFS;
491	}	491	}
492	#if 0	492	#if 0
493	// TODO: Enable this code once we start modifying anything that	493	// TODO: Enable this code once we start modifying anything that
494	// is different between NTFS 1.2 and 3.x...	494	// is different between NTFS 1.2 and 3.x...
495	/* Set NT4 compatibility flag on newer NTFS version volumes. */	495	/* Set NT4 compatibility flag on newer NTFS version volumes. */
496	if ((vol->major_ver > 1)) {	496	if ((vol->major_ver > 1)) {
497	if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {	497	if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
498	ntfs_error(sb, "Failed to set NT4 "	498	ntfs_error(sb, "Failed to set NT4 "
499	"compatibility flag%s", es);	499	"compatibility flag%s", es);
500	NVolSetErrors(vol);	500	NVolSetErrors(vol);
501	return -EROFS;	501	return -EROFS;
502	}	502	}
503	}	503	}
504	#endif	504	#endif
505	if (!ntfs_empty_logfile(vol->logfile_ino)) {	505	if (!ntfs_empty_logfile(vol->logfile_ino)) {
506	ntfs_error(sb, "Failed to empty journal $LogFile%s",	506	ntfs_error(sb, "Failed to empty journal $LogFile%s",
507	es);	507	es);
508	NVolSetErrors(vol);	508	NVolSetErrors(vol);
509	return -EROFS;	509	return -EROFS;
510	}	510	}
511	if (!ntfs_mark_quotas_out_of_date(vol)) {	511	if (!ntfs_mark_quotas_out_of_date(vol)) {
512	ntfs_error(sb, "Failed to mark quotas out of date%s",	512	ntfs_error(sb, "Failed to mark quotas out of date%s",
513	es);	513	es);
514	NVolSetErrors(vol);	514	NVolSetErrors(vol);
515	return -EROFS;	515	return -EROFS;
516	}	516	}
517	if (!ntfs_stamp_usnjrnl(vol)) {	517	if (!ntfs_stamp_usnjrnl(vol)) {
518	ntfs_error(sb, "Failed to stamp transation log "	518	ntfs_error(sb, "Failed to stamp transation log "
519	"($UsnJrnl)%s", es);	519	"($UsnJrnl)%s", es);
520	NVolSetErrors(vol);	520	NVolSetErrors(vol);
521	return -EROFS;	521	return -EROFS;
522	}	522	}
523	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {	523	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
524	/* Remounting read-only. */	524	/* Remounting read-only. */
525	if (!NVolErrors(vol)) {	525	if (!NVolErrors(vol)) {
526	if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))	526	if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
527	ntfs_warning(sb, "Failed to clear dirty bit "	527	ntfs_warning(sb, "Failed to clear dirty bit "
528	"in volume information "	528	"in volume information "
529	"flags. Run chkdsk.");	529	"flags. Run chkdsk.");
530	}	530	}
531	}	531	}
532	#endif /* NTFS_RW */	532	#endif /* NTFS_RW */
533		533
534	// TODO: Deal with *flags.	534	// TODO: Deal with *flags.
535		535
536	if (!parse_options(vol, opt))	536	if (!parse_options(vol, opt))
537	return -EINVAL;	537	return -EINVAL;
538	ntfs_debug("Done.");	538	ntfs_debug("Done.");
539	return 0;	539	return 0;
540	}	540	}
541		541
542	/**	542	/**
543	* is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector	543	* is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector
544	* @sb: Super block of the device to which @b belongs.	544	* @sb: Super block of the device to which @b belongs.
545	* @b: Boot sector of device @sb to check.	545	* @b: Boot sector of device @sb to check.
546	* @silent: If 'true', all output will be silenced.	546	* @silent: If 'true', all output will be silenced.
547	*	547	*
548	* is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot	548	* is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot
549	* sector. Returns 'true' if it is valid and 'false' if not.	549	* sector. Returns 'true' if it is valid and 'false' if not.
550	*	550	*
551	* @sb is only needed for warning/error output, i.e. it can be NULL when silent	551	* @sb is only needed for warning/error output, i.e. it can be NULL when silent
552	* is 'true'.	552	* is 'true'.
553	*/	553	*/
554	static bool is_boot_sector_ntfs(const struct super_block *sb,	554	static bool is_boot_sector_ntfs(const struct super_block *sb,
555	const NTFS_BOOT_SECTOR *b, const bool silent)	555	const NTFS_BOOT_SECTOR *b, const bool silent)
556	{	556	{
557	/*	557	/*
558	* Check that checksum == sum of u32 values from b to the checksum	558	* Check that checksum == sum of u32 values from b to the checksum
559	* field. If checksum is zero, no checking is done. We will work when	559	* field. If checksum is zero, no checking is done. We will work when
560	* the checksum test fails, since some utilities update the boot sector	560	* the checksum test fails, since some utilities update the boot sector
561	* ignoring the checksum which leaves the checksum out-of-date. We	561	* ignoring the checksum which leaves the checksum out-of-date. We
562	* report a warning if this is the case.	562	* report a warning if this is the case.
563	*/	563	*/
564	if ((void)b < (void)&b->checksum && b->checksum && !silent) {	564	if ((void)b < (void)&b->checksum && b->checksum && !silent) {
565	le32 *u;	565	le32 *u;
566	u32 i;	566	u32 i;
567		567
568	for (i = 0, u = (le32)b; u < (le32)(&b->checksum); ++u)	568	for (i = 0, u = (le32)b; u < (le32)(&b->checksum); ++u)
569	i += le32_to_cpup(u);	569	i += le32_to_cpup(u);
570	if (le32_to_cpu(b->checksum) != i)	570	if (le32_to_cpu(b->checksum) != i)
571	ntfs_warning(sb, "Invalid boot sector checksum.");	571	ntfs_warning(sb, "Invalid boot sector checksum.");
572	}	572	}
573	/* Check OEMidentifier is "NTFS " */	573	/* Check OEMidentifier is "NTFS " */
574	if (b->oem_id != magicNTFS)	574	if (b->oem_id != magicNTFS)
575	goto not_ntfs;	575	goto not_ntfs;
576	/* Check bytes per sector value is between 256 and 4096. */	576	/* Check bytes per sector value is between 256 and 4096. */
577	if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 \|\|	577	if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 \|\|
578	le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000)	578	le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000)
579	goto not_ntfs;	579	goto not_ntfs;
580	/* Check sectors per cluster value is valid. */	580	/* Check sectors per cluster value is valid. */
581	switch (b->bpb.sectors_per_cluster) {	581	switch (b->bpb.sectors_per_cluster) {
582	case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128:	582	case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128:
583	break;	583	break;
584	default:	584	default:
585	goto not_ntfs;	585	goto not_ntfs;
586	}	586	}
587	/* Check the cluster size is not above the maximum (64kiB). */	587	/* Check the cluster size is not above the maximum (64kiB). */
588	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *	588	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *
589	b->bpb.sectors_per_cluster > NTFS_MAX_CLUSTER_SIZE)	589	b->bpb.sectors_per_cluster > NTFS_MAX_CLUSTER_SIZE)
590	goto not_ntfs;	590	goto not_ntfs;
591	/* Check reserved/unused fields are really zero. */	591	/* Check reserved/unused fields are really zero. */
592	if (le16_to_cpu(b->bpb.reserved_sectors) \|\|	592	if (le16_to_cpu(b->bpb.reserved_sectors) \|\|
593	le16_to_cpu(b->bpb.root_entries) \|\|	593	le16_to_cpu(b->bpb.root_entries) \|\|
594	le16_to_cpu(b->bpb.sectors) \|\|	594	le16_to_cpu(b->bpb.sectors) \|\|
595	le16_to_cpu(b->bpb.sectors_per_fat) \|\|	595	le16_to_cpu(b->bpb.sectors_per_fat) \|\|
596	le32_to_cpu(b->bpb.large_sectors) \|\| b->bpb.fats)	596	le32_to_cpu(b->bpb.large_sectors) \|\| b->bpb.fats)
597	goto not_ntfs;	597	goto not_ntfs;
598	/* Check clusters per file mft record value is valid. */	598	/* Check clusters per file mft record value is valid. */
599	if ((u8)b->clusters_per_mft_record < 0xe1 \|\|	599	if ((u8)b->clusters_per_mft_record < 0xe1 \|\|
600	(u8)b->clusters_per_mft_record > 0xf7)	600	(u8)b->clusters_per_mft_record > 0xf7)
601	switch (b->clusters_per_mft_record) {	601	switch (b->clusters_per_mft_record) {
602	case 1: case 2: case 4: case 8: case 16: case 32: case 64:	602	case 1: case 2: case 4: case 8: case 16: case 32: case 64:
603	break;	603	break;
604	default:	604	default:
605	goto not_ntfs;	605	goto not_ntfs;
606	}	606	}
607	/* Check clusters per index block value is valid. */	607	/* Check clusters per index block value is valid. */
608	if ((u8)b->clusters_per_index_record < 0xe1 \|\|	608	if ((u8)b->clusters_per_index_record < 0xe1 \|\|
609	(u8)b->clusters_per_index_record > 0xf7)	609	(u8)b->clusters_per_index_record > 0xf7)
610	switch (b->clusters_per_index_record) {	610	switch (b->clusters_per_index_record) {
611	case 1: case 2: case 4: case 8: case 16: case 32: case 64:	611	case 1: case 2: case 4: case 8: case 16: case 32: case 64:
612	break;	612	break;
613	default:	613	default:
614	goto not_ntfs;	614	goto not_ntfs;
615	}	615	}
616	/*	616	/*
617	* Check for valid end of sector marker. We will work without it, but	617	* Check for valid end of sector marker. We will work without it, but
618	* many BIOSes will refuse to boot from a bootsector if the magic is	618	* many BIOSes will refuse to boot from a bootsector if the magic is
619	* incorrect, so we emit a warning.	619	* incorrect, so we emit a warning.
620	*/	620	*/
621	if (!silent && b->end_of_sector_marker != const_cpu_to_le16(0xaa55))	621	if (!silent && b->end_of_sector_marker != const_cpu_to_le16(0xaa55))
622	ntfs_warning(sb, "Invalid end of sector marker.");	622	ntfs_warning(sb, "Invalid end of sector marker.");
623	return true;	623	return true;
624	not_ntfs:	624	not_ntfs:
625	return false;	625	return false;
626	}	626	}
627		627
628	/**	628	/**
629	* read_ntfs_boot_sector - read the NTFS boot sector of a device	629	* read_ntfs_boot_sector - read the NTFS boot sector of a device
630	* @sb: super block of device to read the boot sector from	630	* @sb: super block of device to read the boot sector from
631	* @silent: if true, suppress all output	631	* @silent: if true, suppress all output
632	*	632	*
633	* Reads the boot sector from the device and validates it. If that fails, tries	633	* Reads the boot sector from the device and validates it. If that fails, tries
634	* to read the backup boot sector, first from the end of the device a-la NT4 and	634	* to read the backup boot sector, first from the end of the device a-la NT4 and
635	* later and then from the middle of the device a-la NT3.51 and before.	635	* later and then from the middle of the device a-la NT3.51 and before.
636	*	636	*
637	* If a valid boot sector is found but it is not the primary boot sector, we	637	* If a valid boot sector is found but it is not the primary boot sector, we
638	* repair the primary boot sector silently (unless the device is read-only or	638	* repair the primary boot sector silently (unless the device is read-only or
639	* the primary boot sector is not accessible).	639	* the primary boot sector is not accessible).
640	*	640	*
641	* NOTE: To call this function, @sb must have the fields s_dev, the ntfs super	641	* NOTE: To call this function, @sb must have the fields s_dev, the ntfs super
642	* block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized	642	* block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized
643	* to their respective values.	643	* to their respective values.
644	*	644	*
645	* Return the unlocked buffer head containing the boot sector or NULL on error.	645	* Return the unlocked buffer head containing the boot sector or NULL on error.
646	*/	646	*/
647	static struct buffer_head read_ntfs_boot_sector(struct super_block sb,	647	static struct buffer_head read_ntfs_boot_sector(struct super_block sb,
648	const int silent)	648	const int silent)
649	{	649	{
650	const char *read_err_str = "Unable to read %s boot sector.";	650	const char *read_err_str = "Unable to read %s boot sector.";
651	struct buffer_head bh_primary, bh_backup;	651	struct buffer_head bh_primary, bh_backup;
652	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;	652	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
653		653
654	/* Try to read primary boot sector. */	654	/* Try to read primary boot sector. */
655	if ((bh_primary = sb_bread(sb, 0))) {	655	if ((bh_primary = sb_bread(sb, 0))) {
656	if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)	656	if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
657	bh_primary->b_data, silent))	657	bh_primary->b_data, silent))
658	return bh_primary;	658	return bh_primary;
659	if (!silent)	659	if (!silent)
660	ntfs_error(sb, "Primary boot sector is invalid.");	660	ntfs_error(sb, "Primary boot sector is invalid.");
661	} else if (!silent)	661	} else if (!silent)
662	ntfs_error(sb, read_err_str, "primary");	662	ntfs_error(sb, read_err_str, "primary");
663	if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) {	663	if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) {
664	if (bh_primary)	664	if (bh_primary)
665	brelse(bh_primary);	665	brelse(bh_primary);
666	if (!silent)	666	if (!silent)
667	ntfs_error(sb, "Mount option errors=recover not used. "	667	ntfs_error(sb, "Mount option errors=recover not used. "
668	"Aborting without trying to recover.");	668	"Aborting without trying to recover.");
669	return NULL;	669	return NULL;
670	}	670	}
671	/* Try to read NT4+ backup boot sector. */	671	/* Try to read NT4+ backup boot sector. */
672	if ((bh_backup = sb_bread(sb, nr_blocks - 1))) {	672	if ((bh_backup = sb_bread(sb, nr_blocks - 1))) {
673	if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)	673	if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
674	bh_backup->b_data, silent))	674	bh_backup->b_data, silent))
675	goto hotfix_primary_boot_sector;	675	goto hotfix_primary_boot_sector;
676	brelse(bh_backup);	676	brelse(bh_backup);
677	} else if (!silent)	677	} else if (!silent)
678	ntfs_error(sb, read_err_str, "backup");	678	ntfs_error(sb, read_err_str, "backup");
679	/* Try to read NT3.51- backup boot sector. */	679	/* Try to read NT3.51- backup boot sector. */
680	if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) {	680	if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) {
681	if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)	681	if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
682	bh_backup->b_data, silent))	682	bh_backup->b_data, silent))
683	goto hotfix_primary_boot_sector;	683	goto hotfix_primary_boot_sector;
684	if (!silent)	684	if (!silent)
685	ntfs_error(sb, "Could not find a valid backup boot "	685	ntfs_error(sb, "Could not find a valid backup boot "
686	"sector.");	686	"sector.");
687	brelse(bh_backup);	687	brelse(bh_backup);
688	} else if (!silent)	688	} else if (!silent)
689	ntfs_error(sb, read_err_str, "backup");	689	ntfs_error(sb, read_err_str, "backup");
690	/* We failed. Cleanup and return. */	690	/* We failed. Cleanup and return. */
691	if (bh_primary)	691	if (bh_primary)
692	brelse(bh_primary);	692	brelse(bh_primary);
693	return NULL;	693	return NULL;
694	hotfix_primary_boot_sector:	694	hotfix_primary_boot_sector:
695	if (bh_primary) {	695	if (bh_primary) {
696	/*	696	/*
697	* If we managed to read sector zero and the volume is not	697	* If we managed to read sector zero and the volume is not
698	* read-only, copy the found, valid backup boot sector to the	698	* read-only, copy the found, valid backup boot sector to the
699	* primary boot sector. Note we only copy the actual boot	699	* primary boot sector. Note we only copy the actual boot
700	* sector structure, not the actual whole device sector as that	700	* sector structure, not the actual whole device sector as that
701	* may be bigger and would potentially damage the $Boot system	701	* may be bigger and would potentially damage the $Boot system
702	* file (FIXME: Would be nice to know if the backup boot sector	702	* file (FIXME: Would be nice to know if the backup boot sector
703	* on a large sector device contains the whole boot loader or	703	* on a large sector device contains the whole boot loader or
704	* just the first 512 bytes).	704	* just the first 512 bytes).
705	*/	705	*/
706	if (!(sb->s_flags & MS_RDONLY)) {	706	if (!(sb->s_flags & MS_RDONLY)) {
707	ntfs_warning(sb, "Hot-fix: Recovering invalid primary "	707	ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
708	"boot sector from backup copy.");	708	"boot sector from backup copy.");
709	memcpy(bh_primary->b_data, bh_backup->b_data,	709	memcpy(bh_primary->b_data, bh_backup->b_data,
710	NTFS_BLOCK_SIZE);	710	NTFS_BLOCK_SIZE);
711	mark_buffer_dirty(bh_primary);	711	mark_buffer_dirty(bh_primary);
712	sync_dirty_buffer(bh_primary);	712	sync_dirty_buffer(bh_primary);
713	if (buffer_uptodate(bh_primary)) {	713	if (buffer_uptodate(bh_primary)) {
714	brelse(bh_backup);	714	brelse(bh_backup);
715	return bh_primary;	715	return bh_primary;
716	}	716	}
717	ntfs_error(sb, "Hot-fix: Device write error while "	717	ntfs_error(sb, "Hot-fix: Device write error while "
718	"recovering primary boot sector.");	718	"recovering primary boot sector.");
719	} else {	719	} else {
720	ntfs_warning(sb, "Hot-fix: Recovery of primary boot "	720	ntfs_warning(sb, "Hot-fix: Recovery of primary boot "
721	"sector failed: Read-only mount.");	721	"sector failed: Read-only mount.");
722	}	722	}
723	brelse(bh_primary);	723	brelse(bh_primary);
724	}	724	}
725	ntfs_warning(sb, "Using backup boot sector.");	725	ntfs_warning(sb, "Using backup boot sector.");
726	return bh_backup;	726	return bh_backup;
727	}	727	}
728		728
729	/**	729	/**
730	* parse_ntfs_boot_sector - parse the boot sector and store the data in @vol	730	* parse_ntfs_boot_sector - parse the boot sector and store the data in @vol
731	* @vol: volume structure to initialise with data from boot sector	731	* @vol: volume structure to initialise with data from boot sector
732	* @b: boot sector to parse	732	* @b: boot sector to parse
733	*	733	*
734	* Parse the ntfs boot sector @b and store all imporant information therein in	734	* Parse the ntfs boot sector @b and store all imporant information therein in
735	* the ntfs super block @vol. Return 'true' on success and 'false' on error.	735	* the ntfs super block @vol. Return 'true' on success and 'false' on error.
736	*/	736	*/
737	static bool parse_ntfs_boot_sector(ntfs_volume vol, const NTFS_BOOT_SECTOR b)	737	static bool parse_ntfs_boot_sector(ntfs_volume vol, const NTFS_BOOT_SECTOR b)
738	{	738	{
739	unsigned int sectors_per_cluster_bits, nr_hidden_sects;	739	unsigned int sectors_per_cluster_bits, nr_hidden_sects;
740	int clusters_per_mft_record, clusters_per_index_record;	740	int clusters_per_mft_record, clusters_per_index_record;
741	s64 ll;	741	s64 ll;
742		742
743	vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector);	743	vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector);
744	vol->sector_size_bits = ffs(vol->sector_size) - 1;	744	vol->sector_size_bits = ffs(vol->sector_size) - 1;
745	ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size,	745	ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size,
746	vol->sector_size);	746	vol->sector_size);
747	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,	747	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
748	vol->sector_size_bits);	748	vol->sector_size_bits);
749	if (vol->sector_size < vol->sb->s_blocksize) {	749	if (vol->sector_size < vol->sb->s_blocksize) {
750	ntfs_error(vol->sb, "Sector size (%i) is smaller than the "	750	ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
751	"device block size (%lu). This is not "	751	"device block size (%lu). This is not "
752	"supported. Sorry.", vol->sector_size,	752	"supported. Sorry.", vol->sector_size,
753	vol->sb->s_blocksize);	753	vol->sb->s_blocksize);
754	return false;	754	return false;
755	}	755	}
756	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);	756	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
757	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;	757	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
758	ntfs_debug("sectors_per_cluster_bits = 0x%x",	758	ntfs_debug("sectors_per_cluster_bits = 0x%x",
759	sectors_per_cluster_bits);	759	sectors_per_cluster_bits);
760	nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors);	760	nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors);
761	ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects);	761	ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects);
762	vol->cluster_size = vol->sector_size << sectors_per_cluster_bits;	762	vol->cluster_size = vol->sector_size << sectors_per_cluster_bits;
763	vol->cluster_size_mask = vol->cluster_size - 1;	763	vol->cluster_size_mask = vol->cluster_size - 1;
764	vol->cluster_size_bits = ffs(vol->cluster_size) - 1;	764	vol->cluster_size_bits = ffs(vol->cluster_size) - 1;
765	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,	765	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
766	vol->cluster_size);	766	vol->cluster_size);
767	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);	767	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
768	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);	768	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
769	if (vol->cluster_size < vol->sector_size) {	769	if (vol->cluster_size < vol->sector_size) {
770	ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "	770	ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
771	"sector size (%i). This is not supported. "	771	"sector size (%i). This is not supported. "
772	"Sorry.", vol->cluster_size, vol->sector_size);	772	"Sorry.", vol->cluster_size, vol->sector_size);
773	return false;	773	return false;
774	}	774	}
775	clusters_per_mft_record = b->clusters_per_mft_record;	775	clusters_per_mft_record = b->clusters_per_mft_record;
776	ntfs_debug("clusters_per_mft_record = %i (0x%x)",	776	ntfs_debug("clusters_per_mft_record = %i (0x%x)",
777	clusters_per_mft_record, clusters_per_mft_record);	777	clusters_per_mft_record, clusters_per_mft_record);
778	if (clusters_per_mft_record > 0)	778	if (clusters_per_mft_record > 0)
779	vol->mft_record_size = vol->cluster_size <<	779	vol->mft_record_size = vol->cluster_size <<
780	(ffs(clusters_per_mft_record) - 1);	780	(ffs(clusters_per_mft_record) - 1);
781	else	781	else
782	/*	782	/*
783	* When mft_record_size < cluster_size, clusters_per_mft_record	783	* When mft_record_size < cluster_size, clusters_per_mft_record
784	* = -log2(mft_record_size) bytes. mft_record_size normaly is	784	* = -log2(mft_record_size) bytes. mft_record_size normaly is
785	* 1024 bytes, which is encoded as 0xF6 (-10 in decimal).	785	* 1024 bytes, which is encoded as 0xF6 (-10 in decimal).
786	*/	786	*/
787	vol->mft_record_size = 1 << -clusters_per_mft_record;	787	vol->mft_record_size = 1 << -clusters_per_mft_record;
788	vol->mft_record_size_mask = vol->mft_record_size - 1;	788	vol->mft_record_size_mask = vol->mft_record_size - 1;
789	vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1;	789	vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1;
790	ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size,	790	ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size,
791	vol->mft_record_size);	791	vol->mft_record_size);
792	ntfs_debug("vol->mft_record_size_mask = 0x%x",	792	ntfs_debug("vol->mft_record_size_mask = 0x%x",
793	vol->mft_record_size_mask);	793	vol->mft_record_size_mask);
794	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",	794	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",
795	vol->mft_record_size_bits, vol->mft_record_size_bits);	795	vol->mft_record_size_bits, vol->mft_record_size_bits);
796	/*	796	/*
797	* We cannot support mft record sizes above the PAGE_CACHE_SIZE since	797	* We cannot support mft record sizes above the PAGE_CACHE_SIZE since
798	* we store $MFT/$DATA, the table of mft records in the page cache.	798	* we store $MFT/$DATA, the table of mft records in the page cache.
799	*/	799	*/
800	if (vol->mft_record_size > PAGE_CACHE_SIZE) {	800	if (vol->mft_record_size > PAGE_CACHE_SIZE) {
801	ntfs_error(vol->sb, "Mft record size (%i) exceeds the "	801	ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
802	"PAGE_CACHE_SIZE on your system (%lu). "	802	"PAGE_CACHE_SIZE on your system (%lu). "
803	"This is not supported. Sorry.",	803	"This is not supported. Sorry.",
804	vol->mft_record_size, PAGE_CACHE_SIZE);	804	vol->mft_record_size, PAGE_CACHE_SIZE);
805	return false;	805	return false;
806	}	806	}
807	/* We cannot support mft record sizes below the sector size. */	807	/* We cannot support mft record sizes below the sector size. */
808	if (vol->mft_record_size < vol->sector_size) {	808	if (vol->mft_record_size < vol->sector_size) {
809	ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "	809	ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
810	"sector size (%i). This is not supported. "	810	"sector size (%i). This is not supported. "
811	"Sorry.", vol->mft_record_size,	811	"Sorry.", vol->mft_record_size,
812	vol->sector_size);	812	vol->sector_size);
813	return false;	813	return false;
814	}	814	}
815	clusters_per_index_record = b->clusters_per_index_record;	815	clusters_per_index_record = b->clusters_per_index_record;
816	ntfs_debug("clusters_per_index_record = %i (0x%x)",	816	ntfs_debug("clusters_per_index_record = %i (0x%x)",
817	clusters_per_index_record, clusters_per_index_record);	817	clusters_per_index_record, clusters_per_index_record);
818	if (clusters_per_index_record > 0)	818	if (clusters_per_index_record > 0)
819	vol->index_record_size = vol->cluster_size <<	819	vol->index_record_size = vol->cluster_size <<
820	(ffs(clusters_per_index_record) - 1);	820	(ffs(clusters_per_index_record) - 1);
821	else	821	else
822	/*	822	/*
823	* When index_record_size < cluster_size,	823	* When index_record_size < cluster_size,
824	* clusters_per_index_record = -log2(index_record_size) bytes.	824	* clusters_per_index_record = -log2(index_record_size) bytes.
825	* index_record_size normaly equals 4096 bytes, which is	825	* index_record_size normaly equals 4096 bytes, which is
826	* encoded as 0xF4 (-12 in decimal).	826	* encoded as 0xF4 (-12 in decimal).
827	*/	827	*/
828	vol->index_record_size = 1 << -clusters_per_index_record;	828	vol->index_record_size = 1 << -clusters_per_index_record;
829	vol->index_record_size_mask = vol->index_record_size - 1;	829	vol->index_record_size_mask = vol->index_record_size - 1;
830	vol->index_record_size_bits = ffs(vol->index_record_size) - 1;	830	vol->index_record_size_bits = ffs(vol->index_record_size) - 1;
831	ntfs_debug("vol->index_record_size = %i (0x%x)",	831	ntfs_debug("vol->index_record_size = %i (0x%x)",
832	vol->index_record_size, vol->index_record_size);	832	vol->index_record_size, vol->index_record_size);
833	ntfs_debug("vol->index_record_size_mask = 0x%x",	833	ntfs_debug("vol->index_record_size_mask = 0x%x",
834	vol->index_record_size_mask);	834	vol->index_record_size_mask);
835	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",	835	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
836	vol->index_record_size_bits,	836	vol->index_record_size_bits,
837	vol->index_record_size_bits);	837	vol->index_record_size_bits);
838	/* We cannot support index record sizes below the sector size. */	838	/* We cannot support index record sizes below the sector size. */
839	if (vol->index_record_size < vol->sector_size) {	839	if (vol->index_record_size < vol->sector_size) {
840	ntfs_error(vol->sb, "Index record size (%i) is smaller than "	840	ntfs_error(vol->sb, "Index record size (%i) is smaller than "
841	"the sector size (%i). This is not "	841	"the sector size (%i). This is not "
842	"supported. Sorry.", vol->index_record_size,	842	"supported. Sorry.", vol->index_record_size,
843	vol->sector_size);	843	vol->sector_size);
844	return false;	844	return false;
845	}	845	}
846	/*	846	/*
847	* Get the size of the volume in clusters and check for 64-bit-ness.	847	* Get the size of the volume in clusters and check for 64-bit-ness.
848	* Windows currently only uses 32 bits to save the clusters so we do	848	* Windows currently only uses 32 bits to save the clusters so we do
849	* the same as it is much faster on 32-bit CPUs.	849	* the same as it is much faster on 32-bit CPUs.
850	*/	850	*/
851	ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits;	851	ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits;
852	if ((u64)ll >= 1ULL << 32) {	852	if ((u64)ll >= 1ULL << 32) {
853	ntfs_error(vol->sb, "Cannot handle 64-bit clusters. Sorry.");	853	ntfs_error(vol->sb, "Cannot handle 64-bit clusters. Sorry.");
854	return false;	854	return false;
855	}	855	}
856	vol->nr_clusters = ll;	856	vol->nr_clusters = ll;
857	ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters);	857	ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters);
858	/*	858	/*
859	* On an architecture where unsigned long is 32-bits, we restrict the	859	* On an architecture where unsigned long is 32-bits, we restrict the
860	* volume size to 2TiB (2^41). On a 64-bit architecture, the compiler	860	* volume size to 2TiB (2^41). On a 64-bit architecture, the compiler
861	* will hopefully optimize the whole check away.	861	* will hopefully optimize the whole check away.
862	*/	862	*/
863	if (sizeof(unsigned long) < 8) {	863	if (sizeof(unsigned long) < 8) {
864	if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) {	864	if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) {
865	ntfs_error(vol->sb, "Volume size (%lluTiB) is too "	865	ntfs_error(vol->sb, "Volume size (%lluTiB) is too "
866	"large for this architecture. "	866	"large for this architecture. "
867	"Maximum supported is 2TiB. Sorry.",	867	"Maximum supported is 2TiB. Sorry.",
868	(unsigned long long)ll >> (40 -	868	(unsigned long long)ll >> (40 -
869	vol->cluster_size_bits));	869	vol->cluster_size_bits));
870	return false;	870	return false;
871	}	871	}
872	}	872	}
873	ll = sle64_to_cpu(b->mft_lcn);	873	ll = sle64_to_cpu(b->mft_lcn);
874	if (ll >= vol->nr_clusters) {	874	if (ll >= vol->nr_clusters) {
875	ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "	875	ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
876	"volume. Weird.", (unsigned long long)ll,	876	"volume. Weird.", (unsigned long long)ll,
877	(unsigned long long)ll);	877	(unsigned long long)ll);
878	return false;	878	return false;
879	}	879	}
880	vol->mft_lcn = ll;	880	vol->mft_lcn = ll;
881	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);	881	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
882	ll = sle64_to_cpu(b->mftmirr_lcn);	882	ll = sle64_to_cpu(b->mftmirr_lcn);
883	if (ll >= vol->nr_clusters) {	883	if (ll >= vol->nr_clusters) {
884	ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "	884	ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
885	"of volume. Weird.", (unsigned long long)ll,	885	"of volume. Weird.", (unsigned long long)ll,
886	(unsigned long long)ll);	886	(unsigned long long)ll);
887	return false;	887	return false;
888	}	888	}
889	vol->mftmirr_lcn = ll;	889	vol->mftmirr_lcn = ll;
890	ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn);	890	ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn);
891	#ifdef NTFS_RW	891	#ifdef NTFS_RW
892	/*	892	/*
893	* Work out the size of the mft mirror in number of mft records. If the	893	* Work out the size of the mft mirror in number of mft records. If the
894	* cluster size is less than or equal to the size taken by four mft	894	* cluster size is less than or equal to the size taken by four mft
895	* records, the mft mirror stores the first four mft records. If the	895	* records, the mft mirror stores the first four mft records. If the
896	* cluster size is bigger than the size taken by four mft records, the	896	* cluster size is bigger than the size taken by four mft records, the
897	* mft mirror contains as many mft records as will fit into one	897	* mft mirror contains as many mft records as will fit into one
898	* cluster.	898	* cluster.
899	*/	899	*/
900	if (vol->cluster_size <= (4 << vol->mft_record_size_bits))	900	if (vol->cluster_size <= (4 << vol->mft_record_size_bits))
901	vol->mftmirr_size = 4;	901	vol->mftmirr_size = 4;
902	else	902	else
903	vol->mftmirr_size = vol->cluster_size >>	903	vol->mftmirr_size = vol->cluster_size >>
904	vol->mft_record_size_bits;	904	vol->mft_record_size_bits;
905	ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size);	905	ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size);
906	#endif /* NTFS_RW */	906	#endif /* NTFS_RW */
907	vol->serial_no = le64_to_cpu(b->volume_serial_number);	907	vol->serial_no = le64_to_cpu(b->volume_serial_number);
908	ntfs_debug("vol->serial_no = 0x%llx",	908	ntfs_debug("vol->serial_no = 0x%llx",
909	(unsigned long long)vol->serial_no);	909	(unsigned long long)vol->serial_no);
910	return true;	910	return true;
911	}	911	}
912		912
913	/**	913	/**
914	* ntfs_setup_allocators - initialize the cluster and mft allocators	914	* ntfs_setup_allocators - initialize the cluster and mft allocators
915	* @vol: volume structure for which to setup the allocators	915	* @vol: volume structure for which to setup the allocators
916	*	916	*
917	* Setup the cluster (lcn) and mft allocators to the starting values.	917	* Setup the cluster (lcn) and mft allocators to the starting values.
918	*/	918	*/
919	static void ntfs_setup_allocators(ntfs_volume *vol)	919	static void ntfs_setup_allocators(ntfs_volume *vol)
920	{	920	{
921	#ifdef NTFS_RW	921	#ifdef NTFS_RW
922	LCN mft_zone_size, mft_lcn;	922	LCN mft_zone_size, mft_lcn;
923	#endif /* NTFS_RW */	923	#endif /* NTFS_RW */
924		924
925	ntfs_debug("vol->mft_zone_multiplier = 0x%x",	925	ntfs_debug("vol->mft_zone_multiplier = 0x%x",
926	vol->mft_zone_multiplier);	926	vol->mft_zone_multiplier);
927	#ifdef NTFS_RW	927	#ifdef NTFS_RW
928	/* Determine the size of the MFT zone. */	928	/* Determine the size of the MFT zone. */
929	mft_zone_size = vol->nr_clusters;	929	mft_zone_size = vol->nr_clusters;
930	switch (vol->mft_zone_multiplier) { /* % of volume size in clusters */	930	switch (vol->mft_zone_multiplier) { /* % of volume size in clusters */
931	case 4:	931	case 4:
932	mft_zone_size >>= 1; /* 50% */	932	mft_zone_size >>= 1; /* 50% */
933	break;	933	break;
934	case 3:	934	case 3:
935	mft_zone_size = (mft_zone_size +	935	mft_zone_size = (mft_zone_size +
936	(mft_zone_size >> 1)) >> 2; /* 37.5% */	936	(mft_zone_size >> 1)) >> 2; /* 37.5% */
937	break;	937	break;
938	case 2:	938	case 2:
939	mft_zone_size >>= 2; /* 25% */	939	mft_zone_size >>= 2; /* 25% */
940	break;	940	break;
941	/* case 1: */	941	/* case 1: */
942	default:	942	default:
943	mft_zone_size >>= 3; /* 12.5% */	943	mft_zone_size >>= 3; /* 12.5% */
944	break;	944	break;
945	}	945	}
946	/* Setup the mft zone. */	946	/* Setup the mft zone. */
947	vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn;	947	vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn;
948	ntfs_debug("vol->mft_zone_pos = 0x%llx",	948	ntfs_debug("vol->mft_zone_pos = 0x%llx",
949	(unsigned long long)vol->mft_zone_pos);	949	(unsigned long long)vol->mft_zone_pos);
950	/*	950	/*
951	* Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs	951	* Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs
952	* source) and if the actual mft_lcn is in the expected place or even	952	* source) and if the actual mft_lcn is in the expected place or even
953	* further to the front of the volume, extend the mft_zone to cover the	953	* further to the front of the volume, extend the mft_zone to cover the
954	* beginning of the volume as well. This is in order to protect the	954	* beginning of the volume as well. This is in order to protect the
955	* area reserved for the mft bitmap as well within the mft_zone itself.	955	* area reserved for the mft bitmap as well within the mft_zone itself.
956	* On non-standard volumes we do not protect it as the overhead would	956	* On non-standard volumes we do not protect it as the overhead would
957	* be higher than the speed increase we would get by doing it.	957	* be higher than the speed increase we would get by doing it.
958	*/	958	*/
959	mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size;	959	mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size;
960	if (mft_lcn * vol->cluster_size < 16 * 1024)	960	if (mft_lcn * vol->cluster_size < 16 * 1024)
961	mft_lcn = (16 * 1024 + vol->cluster_size - 1) /	961	mft_lcn = (16 * 1024 + vol->cluster_size - 1) /
962	vol->cluster_size;	962	vol->cluster_size;
963	if (vol->mft_zone_start <= mft_lcn)	963	if (vol->mft_zone_start <= mft_lcn)
964	vol->mft_zone_start = 0;	964	vol->mft_zone_start = 0;
965	ntfs_debug("vol->mft_zone_start = 0x%llx",	965	ntfs_debug("vol->mft_zone_start = 0x%llx",
966	(unsigned long long)vol->mft_zone_start);	966	(unsigned long long)vol->mft_zone_start);
967	/*	967	/*
968	* Need to cap the mft zone on non-standard volumes so that it does	968	* Need to cap the mft zone on non-standard volumes so that it does
969	* not point outside the boundaries of the volume. We do this by	969	* not point outside the boundaries of the volume. We do this by
970	* halving the zone size until we are inside the volume.	970	* halving the zone size until we are inside the volume.
971	*/	971	*/
972	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;	972	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
973	while (vol->mft_zone_end >= vol->nr_clusters) {	973	while (vol->mft_zone_end >= vol->nr_clusters) {
974	mft_zone_size >>= 1;	974	mft_zone_size >>= 1;
975	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;	975	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
976	}	976	}
977	ntfs_debug("vol->mft_zone_end = 0x%llx",	977	ntfs_debug("vol->mft_zone_end = 0x%llx",
978	(unsigned long long)vol->mft_zone_end);	978	(unsigned long long)vol->mft_zone_end);
979	/*	979	/*
980	* Set the current position within each data zone to the start of the	980	* Set the current position within each data zone to the start of the
981	* respective zone.	981	* respective zone.
982	*/	982	*/
983	vol->data1_zone_pos = vol->mft_zone_end;	983	vol->data1_zone_pos = vol->mft_zone_end;
984	ntfs_debug("vol->data1_zone_pos = 0x%llx",	984	ntfs_debug("vol->data1_zone_pos = 0x%llx",
985	(unsigned long long)vol->data1_zone_pos);	985	(unsigned long long)vol->data1_zone_pos);
986	vol->data2_zone_pos = 0;	986	vol->data2_zone_pos = 0;
987	ntfs_debug("vol->data2_zone_pos = 0x%llx",	987	ntfs_debug("vol->data2_zone_pos = 0x%llx",
988	(unsigned long long)vol->data2_zone_pos);	988	(unsigned long long)vol->data2_zone_pos);
989		989
990	/* Set the mft data allocation position to mft record 24. */	990	/* Set the mft data allocation position to mft record 24. */
991	vol->mft_data_pos = 24;	991	vol->mft_data_pos = 24;
992	ntfs_debug("vol->mft_data_pos = 0x%llx",	992	ntfs_debug("vol->mft_data_pos = 0x%llx",
993	(unsigned long long)vol->mft_data_pos);	993	(unsigned long long)vol->mft_data_pos);
994	#endif /* NTFS_RW */	994	#endif /* NTFS_RW */
995	}	995	}
996		996
997	#ifdef NTFS_RW	997	#ifdef NTFS_RW
998		998
999	/**	999	/**
1000	* load_and_init_mft_mirror - load and setup the mft mirror inode for a volume	1000	* load_and_init_mft_mirror - load and setup the mft mirror inode for a volume
1001	* @vol: ntfs super block describing device whose mft mirror to load	1001	* @vol: ntfs super block describing device whose mft mirror to load
1002	*	1002	*
1003	* Return 'true' on success or 'false' on error.	1003	* Return 'true' on success or 'false' on error.
1004	*/	1004	*/
1005	static bool load_and_init_mft_mirror(ntfs_volume *vol)	1005	static bool load_and_init_mft_mirror(ntfs_volume *vol)
1006	{	1006	{
1007	struct inode *tmp_ino;	1007	struct inode *tmp_ino;
1008	ntfs_inode *tmp_ni;	1008	ntfs_inode *tmp_ni;
1009		1009
1010	ntfs_debug("Entering.");	1010	ntfs_debug("Entering.");
1011	/* Get mft mirror inode. */	1011	/* Get mft mirror inode. */
1012	tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr);	1012	tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr);
1013	if (IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino)) {	1013	if (IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino)) {
1014	if (!IS_ERR(tmp_ino))	1014	if (!IS_ERR(tmp_ino))
1015	iput(tmp_ino);	1015	iput(tmp_ino);
1016	/* Caller will display error message. */	1016	/* Caller will display error message. */
1017	return false;	1017	return false;
1018	}	1018	}
1019	/*	1019	/*
1020	* Re-initialize some specifics about $MFTMirr's inode as	1020	* Re-initialize some specifics about $MFTMirr's inode as
1021	* ntfs_read_inode() will have set up the default ones.	1021	* ntfs_read_inode() will have set up the default ones.
1022	*/	1022	*/
1023	/* Set uid and gid to root. */	1023	/* Set uid and gid to root. */
1024	tmp_ino->i_uid = tmp_ino->i_gid = 0;	1024	tmp_ino->i_uid = tmp_ino->i_gid = 0;
1025	/* Regular file. No access for anyone. */	1025	/* Regular file. No access for anyone. */
1026	tmp_ino->i_mode = S_IFREG;	1026	tmp_ino->i_mode = S_IFREG;
1027	/* No VFS initiated operations allowed for $MFTMirr. */	1027	/* No VFS initiated operations allowed for $MFTMirr. */
1028	tmp_ino->i_op = &ntfs_empty_inode_ops;	1028	tmp_ino->i_op = &ntfs_empty_inode_ops;
1029	tmp_ino->i_fop = &ntfs_empty_file_ops;	1029	tmp_ino->i_fop = &ntfs_empty_file_ops;
1030	/* Put in our special address space operations. */	1030	/* Put in our special address space operations. */
1031	tmp_ino->i_mapping->a_ops = &ntfs_mst_aops;	1031	tmp_ino->i_mapping->a_ops = &ntfs_mst_aops;
1032	tmp_ni = NTFS_I(tmp_ino);	1032	tmp_ni = NTFS_I(tmp_ino);
1033	/* The $MFTMirr, like the $MFT is multi sector transfer protected. */	1033	/* The $MFTMirr, like the $MFT is multi sector transfer protected. */
1034	NInoSetMstProtected(tmp_ni);	1034	NInoSetMstProtected(tmp_ni);
1035	NInoSetSparseDisabled(tmp_ni);	1035	NInoSetSparseDisabled(tmp_ni);
1036	/*	1036	/*
1037	* Set up our little cheat allowing us to reuse the async read io	1037	* Set up our little cheat allowing us to reuse the async read io
1038	* completion handler for directories.	1038	* completion handler for directories.
1039	*/	1039	*/
1040	tmp_ni->itype.index.block_size = vol->mft_record_size;	1040	tmp_ni->itype.index.block_size = vol->mft_record_size;
1041	tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits;	1041	tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits;
1042	vol->mftmirr_ino = tmp_ino;	1042	vol->mftmirr_ino = tmp_ino;
1043	ntfs_debug("Done.");	1043	ntfs_debug("Done.");
1044	return true;	1044	return true;
1045	}	1045	}
1046		1046
1047	/**	1047	/**
1048	* check_mft_mirror - compare contents of the mft mirror with the mft	1048	* check_mft_mirror - compare contents of the mft mirror with the mft
1049	* @vol: ntfs super block describing device whose mft mirror to check	1049	* @vol: ntfs super block describing device whose mft mirror to check
1050	*	1050	*
1051	* Return 'true' on success or 'false' on error.	1051	* Return 'true' on success or 'false' on error.
1052	*	1052	*
1053	* Note, this function also results in the mft mirror runlist being completely	1053	* Note, this function also results in the mft mirror runlist being completely
1054	* mapped into memory. The mft mirror write code requires this and will BUG()	1054	* mapped into memory. The mft mirror write code requires this and will BUG()
1055	* should it find an unmapped runlist element.	1055	* should it find an unmapped runlist element.
1056	*/	1056	*/
1057	static bool check_mft_mirror(ntfs_volume *vol)	1057	static bool check_mft_mirror(ntfs_volume *vol)
1058	{	1058	{
1059	struct super_block *sb = vol->sb;	1059	struct super_block *sb = vol->sb;
1060	ntfs_inode *mirr_ni;	1060	ntfs_inode *mirr_ni;
1061	struct page mft_page, mirr_page;	1061	struct page mft_page, mirr_page;
1062	u8 kmft, kmirr;	1062	u8 kmft, kmirr;
1063	runlist_element *rl, rl2[2];	1063	runlist_element *rl, rl2[2];
1064	pgoff_t index;	1064	pgoff_t index;
1065	int mrecs_per_page, i;	1065	int mrecs_per_page, i;
1066		1066
1067	ntfs_debug("Entering.");	1067	ntfs_debug("Entering.");
1068	/* Compare contents of $MFT and $MFTMirr. */	1068	/* Compare contents of $MFT and $MFTMirr. */
1069	mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size;	1069	mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size;
1070	BUG_ON(!mrecs_per_page);	1070	BUG_ON(!mrecs_per_page);
1071	BUG_ON(!vol->mftmirr_size);	1071	BUG_ON(!vol->mftmirr_size);
1072	mft_page = mirr_page = NULL;	1072	mft_page = mirr_page = NULL;
1073	kmft = kmirr = NULL;	1073	kmft = kmirr = NULL;
1074	index = i = 0;	1074	index = i = 0;
1075	do {	1075	do {
1076	u32 bytes;	1076	u32 bytes;
1077		1077
1078	/* Switch pages if necessary. */	1078	/* Switch pages if necessary. */
1079	if (!(i % mrecs_per_page)) {	1079	if (!(i % mrecs_per_page)) {
1080	if (index) {	1080	if (index) {
1081	ntfs_unmap_page(mft_page);	1081	ntfs_unmap_page(mft_page);
1082	ntfs_unmap_page(mirr_page);	1082	ntfs_unmap_page(mirr_page);
1083	}	1083	}
1084	/* Get the $MFT page. */	1084	/* Get the $MFT page. */
1085	mft_page = ntfs_map_page(vol->mft_ino->i_mapping,	1085	mft_page = ntfs_map_page(vol->mft_ino->i_mapping,
1086	index);	1086	index);
1087	if (IS_ERR(mft_page)) {	1087	if (IS_ERR(mft_page)) {
1088	ntfs_error(sb, "Failed to read $MFT.");	1088	ntfs_error(sb, "Failed to read $MFT.");
1089	return false;	1089	return false;
1090	}	1090	}
1091	kmft = page_address(mft_page);	1091	kmft = page_address(mft_page);
1092	/* Get the $MFTMirr page. */	1092	/* Get the $MFTMirr page. */
1093	mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping,	1093	mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping,
1094	index);	1094	index);
1095	if (IS_ERR(mirr_page)) {	1095	if (IS_ERR(mirr_page)) {
1096	ntfs_error(sb, "Failed to read $MFTMirr.");	1096	ntfs_error(sb, "Failed to read $MFTMirr.");
1097	goto mft_unmap_out;	1097	goto mft_unmap_out;
1098	}	1098	}
1099	kmirr = page_address(mirr_page);	1099	kmirr = page_address(mirr_page);
1100	++index;	1100	++index;
1101	}	1101	}
1102	/* Do not check the record if it is not in use. */	1102	/* Do not check the record if it is not in use. */
1103	if (((MFT_RECORD*)kmft)->flags & MFT_RECORD_IN_USE) {	1103	if (((MFT_RECORD*)kmft)->flags & MFT_RECORD_IN_USE) {
1104	/* Make sure the record is ok. */	1104	/* Make sure the record is ok. */
1105	if (ntfs_is_baad_recordp((le32*)kmft)) {	1105	if (ntfs_is_baad_recordp((le32*)kmft)) {
1106	ntfs_error(sb, "Incomplete multi sector "	1106	ntfs_error(sb, "Incomplete multi sector "
1107	"transfer detected in mft "	1107	"transfer detected in mft "
1108	"record %i.", i);	1108	"record %i.", i);
1109	mm_unmap_out:	1109	mm_unmap_out:
1110	ntfs_unmap_page(mirr_page);	1110	ntfs_unmap_page(mirr_page);
1111	mft_unmap_out:	1111	mft_unmap_out:
1112	ntfs_unmap_page(mft_page);	1112	ntfs_unmap_page(mft_page);
1113	return false;	1113	return false;
1114	}	1114	}
1115	}	1115	}
1116	/* Do not check the mirror record if it is not in use. */	1116	/* Do not check the mirror record if it is not in use. */
1117	if (((MFT_RECORD*)kmirr)->flags & MFT_RECORD_IN_USE) {	1117	if (((MFT_RECORD*)kmirr)->flags & MFT_RECORD_IN_USE) {
1118	if (ntfs_is_baad_recordp((le32*)kmirr)) {	1118	if (ntfs_is_baad_recordp((le32*)kmirr)) {
1119	ntfs_error(sb, "Incomplete multi sector "	1119	ntfs_error(sb, "Incomplete multi sector "
1120	"transfer detected in mft "	1120	"transfer detected in mft "
1121	"mirror record %i.", i);	1121	"mirror record %i.", i);
1122	goto mm_unmap_out;	1122	goto mm_unmap_out;
1123	}	1123	}
1124	}	1124	}
1125	/* Get the amount of data in the current record. */	1125	/* Get the amount of data in the current record. */
1126	bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use);	1126	bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use);
1127	if (bytes < sizeof(MFT_RECORD_OLD) \|\|	1127	if (bytes < sizeof(MFT_RECORD_OLD) \|\|
1128	bytes > vol->mft_record_size \|\|	1128	bytes > vol->mft_record_size \|\|
1129	ntfs_is_baad_recordp((le32*)kmft)) {	1129	ntfs_is_baad_recordp((le32*)kmft)) {
1130	bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use);	1130	bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use);
1131	if (bytes < sizeof(MFT_RECORD_OLD) \|\|	1131	if (bytes < sizeof(MFT_RECORD_OLD) \|\|
1132	bytes > vol->mft_record_size \|\|	1132	bytes > vol->mft_record_size \|\|
1133	ntfs_is_baad_recordp((le32*)kmirr))	1133	ntfs_is_baad_recordp((le32*)kmirr))
1134	bytes = vol->mft_record_size;	1134	bytes = vol->mft_record_size;
1135	}	1135	}
1136	/* Compare the two records. */	1136	/* Compare the two records. */
1137	if (memcmp(kmft, kmirr, bytes)) {	1137	if (memcmp(kmft, kmirr, bytes)) {
1138	ntfs_error(sb, "$MFT and $MFTMirr (record %i) do not "	1138	ntfs_error(sb, "$MFT and $MFTMirr (record %i) do not "
1139	"match. Run ntfsfix or chkdsk.", i);	1139	"match. Run ntfsfix or chkdsk.", i);
1140	goto mm_unmap_out;	1140	goto mm_unmap_out;
1141	}	1141	}
1142	kmft += vol->mft_record_size;	1142	kmft += vol->mft_record_size;
1143	kmirr += vol->mft_record_size;	1143	kmirr += vol->mft_record_size;
1144	} while (++i < vol->mftmirr_size);	1144	} while (++i < vol->mftmirr_size);
1145	/* Release the last pages. */	1145	/* Release the last pages. */
1146	ntfs_unmap_page(mft_page);	1146	ntfs_unmap_page(mft_page);
1147	ntfs_unmap_page(mirr_page);	1147	ntfs_unmap_page(mirr_page);
1148		1148
1149	/* Construct the mft mirror runlist by hand. */	1149	/* Construct the mft mirror runlist by hand. */
1150	rl2[0].vcn = 0;	1150	rl2[0].vcn = 0;
1151	rl2[0].lcn = vol->mftmirr_lcn;	1151	rl2[0].lcn = vol->mftmirr_lcn;
1152	rl2[0].length = (vol->mftmirr_size * vol->mft_record_size +	1152	rl2[0].length = (vol->mftmirr_size * vol->mft_record_size +
1153	vol->cluster_size - 1) / vol->cluster_size;	1153	vol->cluster_size - 1) / vol->cluster_size;
1154	rl2[1].vcn = rl2[0].length;	1154	rl2[1].vcn = rl2[0].length;
1155	rl2[1].lcn = LCN_ENOENT;	1155	rl2[1].lcn = LCN_ENOENT;
1156	rl2[1].length = 0;	1156	rl2[1].length = 0;
1157	/*	1157	/*
1158	* Because we have just read all of the mft mirror, we know we have	1158	* Because we have just read all of the mft mirror, we know we have
1159	* mapped the full runlist for it.	1159	* mapped the full runlist for it.
1160	*/	1160	*/
1161	mirr_ni = NTFS_I(vol->mftmirr_ino);	1161	mirr_ni = NTFS_I(vol->mftmirr_ino);
1162	down_read(&mirr_ni->runlist.lock);	1162	down_read(&mirr_ni->runlist.lock);
1163	rl = mirr_ni->runlist.rl;	1163	rl = mirr_ni->runlist.rl;
1164	/* Compare the two runlists. They must be identical. */	1164	/* Compare the two runlists. They must be identical. */
1165	i = 0;	1165	i = 0;
1166	do {	1166	do {
1167	if (rl2[i].vcn != rl[i].vcn \|\| rl2[i].lcn != rl[i].lcn \|\|	1167	if (rl2[i].vcn != rl[i].vcn \|\| rl2[i].lcn != rl[i].lcn \|\|
1168	rl2[i].length != rl[i].length) {	1168	rl2[i].length != rl[i].length) {
1169	ntfs_error(sb, "$MFTMirr location mismatch. "	1169	ntfs_error(sb, "$MFTMirr location mismatch. "
1170	"Run chkdsk.");	1170	"Run chkdsk.");
1171	up_read(&mirr_ni->runlist.lock);	1171	up_read(&mirr_ni->runlist.lock);
1172	return false;	1172	return false;
1173	}	1173	}
1174	} while (rl2[i++].length);	1174	} while (rl2[i++].length);
1175	up_read(&mirr_ni->runlist.lock);	1175	up_read(&mirr_ni->runlist.lock);
1176	ntfs_debug("Done.");	1176	ntfs_debug("Done.");
1177	return true;	1177	return true;
1178	}	1178	}
1179		1179
1180	/**	1180	/**
1181	* load_and_check_logfile - load and check the logfile inode for a volume	1181	* load_and_check_logfile - load and check the logfile inode for a volume
1182	* @vol: ntfs super block describing device whose logfile to load	1182	* @vol: ntfs super block describing device whose logfile to load
1183	*	1183	*
1184	* Return 'true' on success or 'false' on error.	1184	* Return 'true' on success or 'false' on error.
1185	*/	1185	*/
1186	static bool load_and_check_logfile(ntfs_volume *vol,	1186	static bool load_and_check_logfile(ntfs_volume *vol,
1187	RESTART_PAGE_HEADER **rp)	1187	RESTART_PAGE_HEADER **rp)
1188	{	1188	{
1189	struct inode *tmp_ino;	1189	struct inode *tmp_ino;
1190		1190
1191	ntfs_debug("Entering.");	1191	ntfs_debug("Entering.");
1192	tmp_ino = ntfs_iget(vol->sb, FILE_LogFile);	1192	tmp_ino = ntfs_iget(vol->sb, FILE_LogFile);
1193	if (IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino)) {	1193	if (IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino)) {
1194	if (!IS_ERR(tmp_ino))	1194	if (!IS_ERR(tmp_ino))
1195	iput(tmp_ino);	1195	iput(tmp_ino);
1196	/* Caller will display error message. */	1196	/* Caller will display error message. */
1197	return false;	1197	return false;
1198	}	1198	}
1199	if (!ntfs_check_logfile(tmp_ino, rp)) {	1199	if (!ntfs_check_logfile(tmp_ino, rp)) {
1200	iput(tmp_ino);	1200	iput(tmp_ino);
1201	/* ntfs_check_logfile() will have displayed error output. */	1201	/* ntfs_check_logfile() will have displayed error output. */
1202	return false;	1202	return false;
1203	}	1203	}
1204	NInoSetSparseDisabled(NTFS_I(tmp_ino));	1204	NInoSetSparseDisabled(NTFS_I(tmp_ino));
1205	vol->logfile_ino = tmp_ino;	1205	vol->logfile_ino = tmp_ino;
1206	ntfs_debug("Done.");	1206	ntfs_debug("Done.");
1207	return true;	1207	return true;
1208	}	1208	}
1209		1209
1210	#define NTFS_HIBERFIL_HEADER_SIZE 4096	1210	#define NTFS_HIBERFIL_HEADER_SIZE 4096
1211		1211
1212	/**	1212	/**
1213	* check_windows_hibernation_status - check if Windows is suspended on a volume	1213	* check_windows_hibernation_status - check if Windows is suspended on a volume
1214	* @vol: ntfs super block of device to check	1214	* @vol: ntfs super block of device to check
1215	*	1215	*
1216	* Check if Windows is hibernated on the ntfs volume @vol. This is done by	1216	* Check if Windows is hibernated on the ntfs volume @vol. This is done by
1217	* looking for the file hiberfil.sys in the root directory of the volume. If	1217	* looking for the file hiberfil.sys in the root directory of the volume. If
1218	* the file is not present Windows is definitely not suspended.	1218	* the file is not present Windows is definitely not suspended.
1219	*	1219	*
1220	* If hiberfil.sys exists and is less than 4kiB in size it means Windows is	1220	* If hiberfil.sys exists and is less than 4kiB in size it means Windows is
1221	* definitely suspended (this volume is not the system volume). Caveat: on a	1221	* definitely suspended (this volume is not the system volume). Caveat: on a
1222	* system with many volumes it is possible that the < 4kiB check is bogus but	1222	* system with many volumes it is possible that the < 4kiB check is bogus but
1223	* for now this should do fine.	1223	* for now this should do fine.
1224	*	1224	*
1225	* If hiberfil.sys exists and is larger than 4kiB in size, we need to read the	1225	* If hiberfil.sys exists and is larger than 4kiB in size, we need to read the
1226	* hiberfil header (which is the first 4kiB). If this begins with "hibr",	1226	* hiberfil header (which is the first 4kiB). If this begins with "hibr",
1227	* Windows is definitely suspended. If it is completely full of zeroes,	1227	* Windows is definitely suspended. If it is completely full of zeroes,
1228	* Windows is definitely not hibernated. Any other case is treated as if	1228	* Windows is definitely not hibernated. Any other case is treated as if
1229	* Windows is suspended. This caters for the above mentioned caveat of a	1229	* Windows is suspended. This caters for the above mentioned caveat of a
1230	* system with many volumes where no "hibr" magic would be present and there is	1230	* system with many volumes where no "hibr" magic would be present and there is
1231	* no zero header.	1231	* no zero header.
1232	*	1232	*
1233	* Return 0 if Windows is not hibernated on the volume, >0 if Windows is	1233	* Return 0 if Windows is not hibernated on the volume, >0 if Windows is
1234	* hibernated on the volume, and -errno on error.	1234	* hibernated on the volume, and -errno on error.
1235	*/	1235	*/
1236	static int check_windows_hibernation_status(ntfs_volume *vol)	1236	static int check_windows_hibernation_status(ntfs_volume *vol)
1237	{	1237	{
1238	MFT_REF mref;	1238	MFT_REF mref;
1239	struct inode *vi;	1239	struct inode *vi;
1240	ntfs_inode *ni;	1240	ntfs_inode *ni;
1241	struct page *page;	1241	struct page *page;
1242	u32 kaddr, kend;	1242	u32 kaddr, kend;
1243	ntfs_name *name = NULL;	1243	ntfs_name *name = NULL;
1244	int ret = 1;	1244	int ret = 1;
1245	static const ntfschar hiberfil[13] = { const_cpu_to_le16('h'),	1245	static const ntfschar hiberfil[13] = { const_cpu_to_le16('h'),
1246	const_cpu_to_le16('i'), const_cpu_to_le16('b'),	1246	const_cpu_to_le16('i'), const_cpu_to_le16('b'),
1247	const_cpu_to_le16('e'), const_cpu_to_le16('r'),	1247	const_cpu_to_le16('e'), const_cpu_to_le16('r'),
1248	const_cpu_to_le16('f'), const_cpu_to_le16('i'),	1248	const_cpu_to_le16('f'), const_cpu_to_le16('i'),
1249	const_cpu_to_le16('l'), const_cpu_to_le16('.'),	1249	const_cpu_to_le16('l'), const_cpu_to_le16('.'),
1250	const_cpu_to_le16('s'), const_cpu_to_le16('y'),	1250	const_cpu_to_le16('s'), const_cpu_to_le16('y'),
1251	const_cpu_to_le16('s'), 0 };	1251	const_cpu_to_le16('s'), 0 };
1252		1252
1253	ntfs_debug("Entering.");	1253	ntfs_debug("Entering.");
1254	/*	1254	/*
1255	* Find the inode number for the hibernation file by looking up the	1255	* Find the inode number for the hibernation file by looking up the
1256	* filename hiberfil.sys in the root directory.	1256	* filename hiberfil.sys in the root directory.
1257	*/	1257	*/
1258	mutex_lock(&vol->root_ino->i_mutex);	1258	mutex_lock(&vol->root_ino->i_mutex);
1259	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12,	1259	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12,
1260	&name);	1260	&name);
1261	mutex_unlock(&vol->root_ino->i_mutex);	1261	mutex_unlock(&vol->root_ino->i_mutex);
1262	if (IS_ERR_MREF(mref)) {	1262	if (IS_ERR_MREF(mref)) {
1263	ret = MREF_ERR(mref);	1263	ret = MREF_ERR(mref);
1264	/* If the file does not exist, Windows is not hibernated. */	1264	/* If the file does not exist, Windows is not hibernated. */
1265	if (ret == -ENOENT) {	1265	if (ret == -ENOENT) {
1266	ntfs_debug("hiberfil.sys not present. Windows is not "	1266	ntfs_debug("hiberfil.sys not present. Windows is not "
1267	"hibernated on the volume.");	1267	"hibernated on the volume.");
1268	return 0;	1268	return 0;
1269	}	1269	}
1270	/* A real error occured. */	1270	/* A real error occured. */
1271	ntfs_error(vol->sb, "Failed to find inode number for "	1271	ntfs_error(vol->sb, "Failed to find inode number for "
1272	"hiberfil.sys.");	1272	"hiberfil.sys.");
1273	return ret;	1273	return ret;
1274	}	1274	}
1275	/* We do not care for the type of match that was found. */	1275	/* We do not care for the type of match that was found. */
1276	kfree(name);	1276	kfree(name);
1277	/* Get the inode. */	1277	/* Get the inode. */
1278	vi = ntfs_iget(vol->sb, MREF(mref));	1278	vi = ntfs_iget(vol->sb, MREF(mref));
1279	if (IS_ERR(vi) \|\| is_bad_inode(vi)) {	1279	if (IS_ERR(vi) \|\| is_bad_inode(vi)) {
1280	if (!IS_ERR(vi))	1280	if (!IS_ERR(vi))
1281	iput(vi);	1281	iput(vi);
1282	ntfs_error(vol->sb, "Failed to load hiberfil.sys.");	1282	ntfs_error(vol->sb, "Failed to load hiberfil.sys.");
1283	return IS_ERR(vi) ? PTR_ERR(vi) : -EIO;	1283	return IS_ERR(vi) ? PTR_ERR(vi) : -EIO;
1284	}	1284	}
1285	if (unlikely(i_size_read(vi) < NTFS_HIBERFIL_HEADER_SIZE)) {	1285	if (unlikely(i_size_read(vi) < NTFS_HIBERFIL_HEADER_SIZE)) {
1286	ntfs_debug("hiberfil.sys is smaller than 4kiB (0x%llx). "	1286	ntfs_debug("hiberfil.sys is smaller than 4kiB (0x%llx). "
1287	"Windows is hibernated on the volume. This "	1287	"Windows is hibernated on the volume. This "
1288	"is not the system volume.", i_size_read(vi));	1288	"is not the system volume.", i_size_read(vi));
1289	goto iput_out;	1289	goto iput_out;
1290	}	1290	}
1291	ni = NTFS_I(vi);	1291	ni = NTFS_I(vi);
1292	page = ntfs_map_page(vi->i_mapping, 0);	1292	page = ntfs_map_page(vi->i_mapping, 0);
1293	if (IS_ERR(page)) {	1293	if (IS_ERR(page)) {
1294	ntfs_error(vol->sb, "Failed to read from hiberfil.sys.");	1294	ntfs_error(vol->sb, "Failed to read from hiberfil.sys.");
1295	ret = PTR_ERR(page);	1295	ret = PTR_ERR(page);
1296	goto iput_out;	1296	goto iput_out;
1297	}	1297	}
1298	kaddr = (u32*)page_address(page);	1298	kaddr = (u32*)page_address(page);
1299	if ((le32)kaddr == const_cpu_to_le32(0x72626968)/'hibr'/) {	1299	if ((le32)kaddr == const_cpu_to_le32(0x72626968)/'hibr'/) {
1300	ntfs_debug("Magic \"hibr\" found in hiberfil.sys. Windows is "	1300	ntfs_debug("Magic \"hibr\" found in hiberfil.sys. Windows is "
1301	"hibernated on the volume. This is the "	1301	"hibernated on the volume. This is the "
1302	"system volume.");	1302	"system volume.");
1303	goto unm_iput_out;	1303	goto unm_iput_out;
1304	}	1304	}
1305	kend = kaddr + NTFS_HIBERFIL_HEADER_SIZE/sizeof(*kaddr);	1305	kend = kaddr + NTFS_HIBERFIL_HEADER_SIZE/sizeof(*kaddr);
1306	do {	1306	do {
1307	if (unlikely(*kaddr)) {	1307	if (unlikely(*kaddr)) {
1308	ntfs_debug("hiberfil.sys is larger than 4kiB "	1308	ntfs_debug("hiberfil.sys is larger than 4kiB "
1309	"(0x%llx), does not contain the "	1309	"(0x%llx), does not contain the "
1310	"\"hibr\" magic, and does not have a "	1310	"\"hibr\" magic, and does not have a "
1311	"zero header. Windows is hibernated "	1311	"zero header. Windows is hibernated "
1312	"on the volume. This is not the "	1312	"on the volume. This is not the "
1313	"system volume.", i_size_read(vi));	1313	"system volume.", i_size_read(vi));
1314	goto unm_iput_out;	1314	goto unm_iput_out;
1315	}	1315	}
1316	} while (++kaddr < kend);	1316	} while (++kaddr < kend);
1317	ntfs_debug("hiberfil.sys contains a zero header. Windows is not "	1317	ntfs_debug("hiberfil.sys contains a zero header. Windows is not "
1318	"hibernated on the volume. This is the system "	1318	"hibernated on the volume. This is the system "
1319	"volume.");	1319	"volume.");
1320	ret = 0;	1320	ret = 0;
1321	unm_iput_out:	1321	unm_iput_out:
1322	ntfs_unmap_page(page);	1322	ntfs_unmap_page(page);
1323	iput_out:	1323	iput_out:
1324	iput(vi);	1324	iput(vi);
1325	return ret;	1325	return ret;
1326	}	1326	}
1327		1327
1328	/**	1328	/**
1329	* load_and_init_quota - load and setup the quota file for a volume if present	1329	* load_and_init_quota - load and setup the quota file for a volume if present
1330	* @vol: ntfs super block describing device whose quota file to load	1330	* @vol: ntfs super block describing device whose quota file to load
1331	*	1331	*
1332	* Return 'true' on success or 'false' on error. If $Quota is not present, we	1332	* Return 'true' on success or 'false' on error. If $Quota is not present, we
1333	* leave vol->quota_ino as NULL and return success.	1333	* leave vol->quota_ino as NULL and return success.
1334	*/	1334	*/
1335	static bool load_and_init_quota(ntfs_volume *vol)	1335	static bool load_and_init_quota(ntfs_volume *vol)
1336	{	1336	{
1337	MFT_REF mref;	1337	MFT_REF mref;
1338	struct inode *tmp_ino;	1338	struct inode *tmp_ino;
1339	ntfs_name *name = NULL;	1339	ntfs_name *name = NULL;
1340	static const ntfschar Quota[7] = { const_cpu_to_le16('$'),	1340	static const ntfschar Quota[7] = { const_cpu_to_le16('$'),
1341	const_cpu_to_le16('Q'), const_cpu_to_le16('u'),	1341	const_cpu_to_le16('Q'), const_cpu_to_le16('u'),
1342	const_cpu_to_le16('o'), const_cpu_to_le16('t'),	1342	const_cpu_to_le16('o'), const_cpu_to_le16('t'),
1343	const_cpu_to_le16('a'), 0 };	1343	const_cpu_to_le16('a'), 0 };
1344	static ntfschar Q[3] = { const_cpu_to_le16('$'),	1344	static ntfschar Q[3] = { const_cpu_to_le16('$'),
1345	const_cpu_to_le16('Q'), 0 };	1345	const_cpu_to_le16('Q'), 0 };
1346		1346
1347	ntfs_debug("Entering.");	1347	ntfs_debug("Entering.");
1348	/*	1348	/*
1349	* Find the inode number for the quota file by looking up the filename	1349	* Find the inode number for the quota file by looking up the filename
1350	* $Quota in the extended system files directory $Extend.	1350	* $Quota in the extended system files directory $Extend.
1351	*/	1351	*/
1352	mutex_lock(&vol->extend_ino->i_mutex);	1352	mutex_lock(&vol->extend_ino->i_mutex);
1353	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,	1353	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,
1354	&name);	1354	&name);
1355	mutex_unlock(&vol->extend_ino->i_mutex);	1355	mutex_unlock(&vol->extend_ino->i_mutex);
1356	if (IS_ERR_MREF(mref)) {	1356	if (IS_ERR_MREF(mref)) {
1357	/*	1357	/*
1358	* If the file does not exist, quotas are disabled and have	1358	* If the file does not exist, quotas are disabled and have
1359	* never been enabled on this volume, just return success.	1359	* never been enabled on this volume, just return success.
1360	*/	1360	*/
1361	if (MREF_ERR(mref) == -ENOENT) {	1361	if (MREF_ERR(mref) == -ENOENT) {
1362	ntfs_debug("$Quota not present. Volume does not have "	1362	ntfs_debug("$Quota not present. Volume does not have "
1363	"quotas enabled.");	1363	"quotas enabled.");
1364	/*	1364	/*
1365	* No need to try to set quotas out of date if they are	1365	* No need to try to set quotas out of date if they are
1366	* not enabled.	1366	* not enabled.
1367	*/	1367	*/
1368	NVolSetQuotaOutOfDate(vol);	1368	NVolSetQuotaOutOfDate(vol);
1369	return true;	1369	return true;
1370	}	1370	}
1371	/* A real error occured. */	1371	/* A real error occured. */
1372	ntfs_error(vol->sb, "Failed to find inode number for $Quota.");	1372	ntfs_error(vol->sb, "Failed to find inode number for $Quota.");
1373	return false;	1373	return false;
1374	}	1374	}
1375	/* We do not care for the type of match that was found. */	1375	/* We do not care for the type of match that was found. */
1376	kfree(name);	1376	kfree(name);
1377	/* Get the inode. */	1377	/* Get the inode. */
1378	tmp_ino = ntfs_iget(vol->sb, MREF(mref));	1378	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
1379	if (IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino)) {	1379	if (IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino)) {
1380	if (!IS_ERR(tmp_ino))	1380	if (!IS_ERR(tmp_ino))
1381	iput(tmp_ino);	1381	iput(tmp_ino);
1382	ntfs_error(vol->sb, "Failed to load $Quota.");	1382	ntfs_error(vol->sb, "Failed to load $Quota.");
1383	return false;	1383	return false;
1384	}	1384	}
1385	vol->quota_ino = tmp_ino;	1385	vol->quota_ino = tmp_ino;
1386	/* Get the $Q index allocation attribute. */	1386	/* Get the $Q index allocation attribute. */
1387	tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2);	1387	tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2);
1388	if (IS_ERR(tmp_ino)) {	1388	if (IS_ERR(tmp_ino)) {
1389	ntfs_error(vol->sb, "Failed to load $Quota/$Q index.");	1389	ntfs_error(vol->sb, "Failed to load $Quota/$Q index.");
1390	return false;	1390	return false;
1391	}	1391	}
1392	vol->quota_q_ino = tmp_ino;	1392	vol->quota_q_ino = tmp_ino;
1393	ntfs_debug("Done.");	1393	ntfs_debug("Done.");
1394	return true;	1394	return true;
1395	}	1395	}
1396		1396
1397	/**	1397	/**
1398	* load_and_init_usnjrnl - load and setup the transaction log if present	1398	* load_and_init_usnjrnl - load and setup the transaction log if present
1399	* @vol: ntfs super block describing device whose usnjrnl file to load	1399	* @vol: ntfs super block describing device whose usnjrnl file to load
1400	*	1400	*
1401	* Return 'true' on success or 'false' on error.	1401	* Return 'true' on success or 'false' on error.
1402	*	1402	*
1403	* If $UsnJrnl is not present or in the process of being disabled, we set	1403	* If $UsnJrnl is not present or in the process of being disabled, we set
1404	* NVolUsnJrnlStamped() and return success.	1404	* NVolUsnJrnlStamped() and return success.
1405	*	1405	*
1406	* If the $UsnJrnl $DATA/$J attribute has a size equal to the lowest valid usn,	1406	* If the $UsnJrnl $DATA/$J attribute has a size equal to the lowest valid usn,
1407	* i.e. transaction logging has only just been enabled or the journal has been	1407	* i.e. transaction logging has only just been enabled or the journal has been
1408	* stamped and nothing has been logged since, we also set NVolUsnJrnlStamped()	1408	* stamped and nothing has been logged since, we also set NVolUsnJrnlStamped()
1409	* and return success.	1409	* and return success.
1410	*/	1410	*/
1411	static bool load_and_init_usnjrnl(ntfs_volume *vol)	1411	static bool load_and_init_usnjrnl(ntfs_volume *vol)
1412	{	1412	{
1413	MFT_REF mref;	1413	MFT_REF mref;
1414	struct inode *tmp_ino;	1414	struct inode *tmp_ino;
1415	ntfs_inode *tmp_ni;	1415	ntfs_inode *tmp_ni;
1416	struct page *page;	1416	struct page *page;
1417	ntfs_name *name = NULL;	1417	ntfs_name *name = NULL;
1418	USN_HEADER *uh;	1418	USN_HEADER *uh;
1419	static const ntfschar UsnJrnl[9] = { const_cpu_to_le16('$'),	1419	static const ntfschar UsnJrnl[9] = { const_cpu_to_le16('$'),
1420	const_cpu_to_le16('U'), const_cpu_to_le16('s'),	1420	const_cpu_to_le16('U'), const_cpu_to_le16('s'),
1421	const_cpu_to_le16('n'), const_cpu_to_le16('J'),	1421	const_cpu_to_le16('n'), const_cpu_to_le16('J'),
1422	const_cpu_to_le16('r'), const_cpu_to_le16('n'),	1422	const_cpu_to_le16('r'), const_cpu_to_le16('n'),
1423	const_cpu_to_le16('l'), 0 };	1423	const_cpu_to_le16('l'), 0 };
1424	static ntfschar Max[5] = { const_cpu_to_le16('$'),	1424	static ntfschar Max[5] = { const_cpu_to_le16('$'),
1425	const_cpu_to_le16('M'), const_cpu_to_le16('a'),	1425	const_cpu_to_le16('M'), const_cpu_to_le16('a'),
1426	const_cpu_to_le16('x'), 0 };	1426	const_cpu_to_le16('x'), 0 };
1427	static ntfschar J[3] = { const_cpu_to_le16('$'),	1427	static ntfschar J[3] = { const_cpu_to_le16('$'),
1428	const_cpu_to_le16('J'), 0 };	1428	const_cpu_to_le16('J'), 0 };
1429		1429
1430	ntfs_debug("Entering.");	1430	ntfs_debug("Entering.");
1431	/*	1431	/*
1432	* Find the inode number for the transaction log file by looking up the	1432	* Find the inode number for the transaction log file by looking up the
1433	* filename $UsnJrnl in the extended system files directory $Extend.	1433	* filename $UsnJrnl in the extended system files directory $Extend.
1434	*/	1434	*/
1435	mutex_lock(&vol->extend_ino->i_mutex);	1435	mutex_lock(&vol->extend_ino->i_mutex);
1436	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8,	1436	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8,
1437	&name);	1437	&name);
1438	mutex_unlock(&vol->extend_ino->i_mutex);	1438	mutex_unlock(&vol->extend_ino->i_mutex);
1439	if (IS_ERR_MREF(mref)) {	1439	if (IS_ERR_MREF(mref)) {
1440	/*	1440	/*
1441	* If the file does not exist, transaction logging is disabled,	1441	* If the file does not exist, transaction logging is disabled,
1442	* just return success.	1442	* just return success.
1443	*/	1443	*/
1444	if (MREF_ERR(mref) == -ENOENT) {	1444	if (MREF_ERR(mref) == -ENOENT) {
1445	ntfs_debug("$UsnJrnl not present. Volume does not "	1445	ntfs_debug("$UsnJrnl not present. Volume does not "
1446	"have transaction logging enabled.");	1446	"have transaction logging enabled.");
1447	not_enabled:	1447	not_enabled:
1448	/*	1448	/*
1449	* No need to try to stamp the transaction log if	1449	* No need to try to stamp the transaction log if
1450	* transaction logging is not enabled.	1450	* transaction logging is not enabled.
1451	*/	1451	*/
1452	NVolSetUsnJrnlStamped(vol);	1452	NVolSetUsnJrnlStamped(vol);
1453	return true;	1453	return true;
1454	}	1454	}
1455	/* A real error occured. */	1455	/* A real error occured. */
1456	ntfs_error(vol->sb, "Failed to find inode number for "	1456	ntfs_error(vol->sb, "Failed to find inode number for "
1457	"$UsnJrnl.");	1457	"$UsnJrnl.");
1458	return false;	1458	return false;
1459	}	1459	}
1460	/* We do not care for the type of match that was found. */	1460	/* We do not care for the type of match that was found. */
1461	kfree(name);	1461	kfree(name);
1462	/* Get the inode. */	1462	/* Get the inode. */
1463	tmp_ino = ntfs_iget(vol->sb, MREF(mref));	1463	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
1464	if (unlikely(IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino))) {	1464	if (unlikely(IS_ERR(tmp_ino) \|\| is_bad_inode(tmp_ino))) {
1465	if (!IS_ERR(tmp_ino))	1465	if (!IS_ERR(tmp_ino))
1466	iput(tmp_ino);	1466	iput(tmp_ino);
1467	ntfs_error(vol->sb, "Failed to load $UsnJrnl.");	1467	ntfs_error(vol->sb, "Failed to load $UsnJrnl.");
1468	return false;	1468	return false;
1469	}	1469	}
1470	vol->usnjrnl_ino = tmp_ino;	1470	vol->usnjrnl_ino = tmp_ino;
1471	/*	1471	/*
1472	* If the transaction log is in the process of being deleted, we can	1472	* If the transaction log is in the process of being deleted, we can
1473	* ignore it.	1473	* ignore it.
1474	*/	1474	*/
1475	if (unlikely(vol->vol_flags & VOLUME_DELETE_USN_UNDERWAY)) {	1475	if (unlikely(vol->vol_flags & VOLUME_DELETE_USN_UNDERWAY)) {
1476	ntfs_debug("$UsnJrnl in the process of being disabled. "	1476	ntfs_debug("$UsnJrnl in the process of being disabled. "
1477	"Volume does not have transaction logging "	1477	"Volume does not have transaction logging "
1478	"enabled.");	1478	"enabled.");
1479	goto not_enabled;	1479	goto not_enabled;
1480	}	1480	}
1481	/* Get the $DATA/$Max attribute. */	1481	/* Get the $DATA/$Max attribute. */
1482	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, Max, 4);	1482	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, Max, 4);
1483	if (IS_ERR(tmp_ino)) {	1483	if (IS_ERR(tmp_ino)) {
1484	ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$Max "	1484	ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$Max "
1485	"attribute.");	1485	"attribute.");
1486	return false;	1486	return false;
1487	}	1487	}
1488	vol->usnjrnl_max_ino = tmp_ino;	1488	vol->usnjrnl_max_ino = tmp_ino;
1489	if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) {	1489	if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) {
1490	ntfs_error(vol->sb, "Found corrupt $UsnJrnl/$DATA/$Max "	1490	ntfs_error(vol->sb, "Found corrupt $UsnJrnl/$DATA/$Max "
1491	"attribute (size is 0x%llx but should be at "	1491	"attribute (size is 0x%llx but should be at "
1492	"least 0x%zx bytes).", i_size_read(tmp_ino),	1492	"least 0x%zx bytes).", i_size_read(tmp_ino),
1493	sizeof(USN_HEADER));	1493	sizeof(USN_HEADER));
1494	return false;	1494	return false;
1495	}	1495	}
1496	/* Get the $DATA/$J attribute. */	1496	/* Get the $DATA/$J attribute. */
1497	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, J, 2);	1497	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, J, 2);
1498	if (IS_ERR(tmp_ino)) {	1498	if (IS_ERR(tmp_ino)) {
1499	ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$J "	1499	ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$J "
1500	"attribute.");	1500	"attribute.");
1501	return false;	1501	return false;
1502	}	1502	}
1503	vol->usnjrnl_j_ino = tmp_ino;	1503	vol->usnjrnl_j_ino = tmp_ino;
1504	/* Verify $J is non-resident and sparse. */	1504	/* Verify $J is non-resident and sparse. */
1505	tmp_ni = NTFS_I(vol->usnjrnl_j_ino);	1505	tmp_ni = NTFS_I(vol->usnjrnl_j_ino);
1506	if (unlikely(!NInoNonResident(tmp_ni) \|\| !NInoSparse(tmp_ni))) {	1506	if (unlikely(!NInoNonResident(tmp_ni) \|\| !NInoSparse(tmp_ni))) {
1507	ntfs_error(vol->sb, "$UsnJrnl/$DATA/$J attribute is resident "	1507	ntfs_error(vol->sb, "$UsnJrnl/$DATA/$J attribute is resident "
1508	"and/or not sparse.");	1508	"and/or not sparse.");
1509	return false;	1509	return false;
1510	}	1510	}
1511	/* Read the USN_HEADER from $DATA/$Max. */	1511	/* Read the USN_HEADER from $DATA/$Max. */
1512	page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);	1512	page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
1513	if (IS_ERR(page)) {	1513	if (IS_ERR(page)) {
1514	ntfs_error(vol->sb, "Failed to read from $UsnJrnl/$DATA/$Max "	1514	ntfs_error(vol->sb, "Failed to read from $UsnJrnl/$DATA/$Max "
1515	"attribute.");	1515	"attribute.");
1516	return false;	1516	return false;
1517	}	1517	}
1518	uh = (USN_HEADER*)page_address(page);	1518	uh = (USN_HEADER*)page_address(page);
1519	/* Sanity check the $Max. */	1519	/* Sanity check the $Max. */
1520	if (unlikely(sle64_to_cpu(uh->allocation_delta) >	1520	if (unlikely(sle64_to_cpu(uh->allocation_delta) >
1521	sle64_to_cpu(uh->maximum_size))) {	1521	sle64_to_cpu(uh->maximum_size))) {
1522	ntfs_error(vol->sb, "Allocation delta (0x%llx) exceeds "	1522	ntfs_error(vol->sb, "Allocation delta (0x%llx) exceeds "
1523	"maximum size (0x%llx). $UsnJrnl is corrupt.",	1523	"maximum size (0x%llx). $UsnJrnl is corrupt.",
1524	(long long)sle64_to_cpu(uh->allocation_delta),	1524	(long long)sle64_to_cpu(uh->allocation_delta),
1525	(long long)sle64_to_cpu(uh->maximum_size));	1525	(long long)sle64_to_cpu(uh->maximum_size));
1526	ntfs_unmap_page(page);	1526	ntfs_unmap_page(page);
1527	return false;	1527	return false;
1528	}	1528	}
1529	/*	1529	/*
1530	* If the transaction log has been stamped and nothing has been written	1530	* If the transaction log has been stamped and nothing has been written
1531	* to it since, we do not need to stamp it.	1531	* to it since, we do not need to stamp it.
1532	*/	1532	*/
1533	if (unlikely(sle64_to_cpu(uh->lowest_valid_usn) >=	1533	if (unlikely(sle64_to_cpu(uh->lowest_valid_usn) >=
1534	i_size_read(vol->usnjrnl_j_ino))) {	1534	i_size_read(vol->usnjrnl_j_ino))) {
1535	if (likely(sle64_to_cpu(uh->lowest_valid_usn) ==	1535	if (likely(sle64_to_cpu(uh->lowest_valid_usn) ==
1536	i_size_read(vol->usnjrnl_j_ino))) {	1536	i_size_read(vol->usnjrnl_j_ino))) {
1537	ntfs_unmap_page(page);	1537	ntfs_unmap_page(page);
1538	ntfs_debug("$UsnJrnl is enabled but nothing has been "	1538	ntfs_debug("$UsnJrnl is enabled but nothing has been "
1539	"logged since it was last stamped. "	1539	"logged since it was last stamped. "
1540	"Treating this as if the volume does "	1540	"Treating this as if the volume does "
1541	"not have transaction logging "	1541	"not have transaction logging "
1542	"enabled.");	1542	"enabled.");
1543	goto not_enabled;	1543	goto not_enabled;
1544	}	1544	}
1545	ntfs_error(vol->sb, "$UsnJrnl has lowest valid usn (0x%llx) "	1545	ntfs_error(vol->sb, "$UsnJrnl has lowest valid usn (0x%llx) "
1546	"which is out of bounds (0x%llx). $UsnJrnl "	1546	"which is out of bounds (0x%llx). $UsnJrnl "
1547	"is corrupt.",	1547	"is corrupt.",
1548	(long long)sle64_to_cpu(uh->lowest_valid_usn),	1548	(long long)sle64_to_cpu(uh->lowest_valid_usn),
1549	i_size_read(vol->usnjrnl_j_ino));	1549	i_size_read(vol->usnjrnl_j_ino));
1550	ntfs_unmap_page(page);	1550	ntfs_unmap_page(page);
1551	return false;	1551	return false;
1552	}	1552	}
1553	ntfs_unmap_page(page);	1553	ntfs_unmap_page(page);
1554	ntfs_debug("Done.");	1554	ntfs_debug("Done.");
1555	return true;	1555	return true;
1556	}	1556	}
1557		1557
1558	/**	1558	/**
1559	* load_and_init_attrdef - load the attribute definitions table for a volume	1559	* load_and_init_attrdef - load the attribute definitions table for a volume
1560	* @vol: ntfs super block describing device whose attrdef to load	1560	* @vol: ntfs super block describing device whose attrdef to load
1561	*	1561	*
1562	* Return 'true' on success or 'false' on error.	1562	* Return 'true' on success or 'false' on error.
1563	*/	1563	*/
1564	static bool load_and_init_attrdef(ntfs_volume *vol)	1564	static bool load_and_init_attrdef(ntfs_volume *vol)
1565	{	1565	{
1566	loff_t i_size;	1566	loff_t i_size;
1567	struct super_block *sb = vol->sb;	1567	struct super_block *sb = vol->sb;
1568	struct inode *ino;	1568	struct inode *ino;
1569	struct page *page;	1569	struct page *page;
1570	pgoff_t index, max_index;	1570	pgoff_t index, max_index;
1571	unsigned int size;	1571	unsigned int size;
1572		1572
1573	ntfs_debug("Entering.");	1573	ntfs_debug("Entering.");
1574	/* Read attrdef table and setup vol->attrdef and vol->attrdef_size. */	1574	/* Read attrdef table and setup vol->attrdef and vol->attrdef_size. */
1575	ino = ntfs_iget(sb, FILE_AttrDef);	1575	ino = ntfs_iget(sb, FILE_AttrDef);
1576	if (IS_ERR(ino) \|\| is_bad_inode(ino)) {	1576	if (IS_ERR(ino) \|\| is_bad_inode(ino)) {
1577	if (!IS_ERR(ino))	1577	if (!IS_ERR(ino))
1578	iput(ino);	1578	iput(ino);
1579	goto failed;	1579	goto failed;
1580	}	1580	}
1581	NInoSetSparseDisabled(NTFS_I(ino));	1581	NInoSetSparseDisabled(NTFS_I(ino));
1582	/* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */	1582	/* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */
1583	i_size = i_size_read(ino);	1583	i_size = i_size_read(ino);
1584	if (i_size <= 0 \|\| i_size > 0x7fffffff)	1584	if (i_size <= 0 \|\| i_size > 0x7fffffff)
1585	goto iput_failed;	1585	goto iput_failed;
1586	vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size);	1586	vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size);
1587	if (!vol->attrdef)	1587	if (!vol->attrdef)
1588	goto iput_failed;	1588	goto iput_failed;
1589	index = 0;	1589	index = 0;
1590	max_index = i_size >> PAGE_CACHE_SHIFT;	1590	max_index = i_size >> PAGE_CACHE_SHIFT;
1591	size = PAGE_CACHE_SIZE;	1591	size = PAGE_CACHE_SIZE;
1592	while (index < max_index) {	1592	while (index < max_index) {
1593	/* Read the attrdef table and copy it into the linear buffer. */	1593	/* Read the attrdef table and copy it into the linear buffer. */
1594	read_partial_attrdef_page:	1594	read_partial_attrdef_page:
1595	page = ntfs_map_page(ino->i_mapping, index);	1595	page = ntfs_map_page(ino->i_mapping, index);
1596	if (IS_ERR(page))	1596	if (IS_ERR(page))
1597	goto free_iput_failed;	1597	goto free_iput_failed;
1598	memcpy((u8*)vol->attrdef + (index++ << PAGE_CACHE_SHIFT),	1598	memcpy((u8*)vol->attrdef + (index++ << PAGE_CACHE_SHIFT),
1599	page_address(page), size);	1599	page_address(page), size);
1600	ntfs_unmap_page(page);	1600	ntfs_unmap_page(page);
1601	};	1601	};
1602	if (size == PAGE_CACHE_SIZE) {	1602	if (size == PAGE_CACHE_SIZE) {
1603	size = i_size & ~PAGE_CACHE_MASK;	1603	size = i_size & ~PAGE_CACHE_MASK;
1604	if (size)	1604	if (size)
1605	goto read_partial_attrdef_page;	1605	goto read_partial_attrdef_page;
1606	}	1606	}
1607	vol->attrdef_size = i_size;	1607	vol->attrdef_size = i_size;
1608	ntfs_debug("Read %llu bytes from $AttrDef.", i_size);	1608	ntfs_debug("Read %llu bytes from $AttrDef.", i_size);
1609	iput(ino);	1609	iput(ino);
1610	return true;	1610	return true;
1611	free_iput_failed:	1611	free_iput_failed:
1612	ntfs_free(vol->attrdef);	1612	ntfs_free(vol->attrdef);
1613	vol->attrdef = NULL;	1613	vol->attrdef = NULL;
1614	iput_failed:	1614	iput_failed:
1615	iput(ino);	1615	iput(ino);
1616	failed:	1616	failed:
1617	ntfs_error(sb, "Failed to initialize attribute definition table.");	1617	ntfs_error(sb, "Failed to initialize attribute definition table.");
1618	return false;	1618	return false;
1619	}	1619	}
1620		1620
1621	#endif /* NTFS_RW */	1621	#endif /* NTFS_RW */
1622		1622
1623	/**	1623	/**
1624	* load_and_init_upcase - load the upcase table for an ntfs volume	1624	* load_and_init_upcase - load the upcase table for an ntfs volume
1625	* @vol: ntfs super block describing device whose upcase to load	1625	* @vol: ntfs super block describing device whose upcase to load
1626	*	1626	*
1627	* Return 'true' on success or 'false' on error.	1627	* Return 'true' on success or 'false' on error.
1628	*/	1628	*/
1629	static bool load_and_init_upcase(ntfs_volume *vol)	1629	static bool load_and_init_upcase(ntfs_volume *vol)
1630	{	1630	{
1631	loff_t i_size;	1631	loff_t i_size;
1632	struct super_block *sb = vol->sb;	1632	struct super_block *sb = vol->sb;
1633	struct inode *ino;	1633	struct inode *ino;
1634	struct page *page;	1634	struct page *page;
1635	pgoff_t index, max_index;	1635	pgoff_t index, max_index;
1636	unsigned int size;	1636	unsigned int size;
1637	int i, max;	1637	int i, max;
1638		1638
1639	ntfs_debug("Entering.");	1639	ntfs_debug("Entering.");
1640	/* Read upcase table and setup vol->upcase and vol->upcase_len. */	1640	/* Read upcase table and setup vol->upcase and vol->upcase_len. */
1641	ino = ntfs_iget(sb, FILE_UpCase);	1641	ino = ntfs_iget(sb, FILE_UpCase);
1642	if (IS_ERR(ino) \|\| is_bad_inode(ino)) {	1642	if (IS_ERR(ino) \|\| is_bad_inode(ino)) {
1643	if (!IS_ERR(ino))	1643	if (!IS_ERR(ino))
1644	iput(ino);	1644	iput(ino);
1645	goto upcase_failed;	1645	goto upcase_failed;
1646	}	1646	}
1647	/*	1647	/*
1648	* The upcase size must not be above 64k Unicode characters, must not	1648	* The upcase size must not be above 64k Unicode characters, must not
1649	* be zero and must be a multiple of sizeof(ntfschar).	1649	* be zero and must be a multiple of sizeof(ntfschar).
1650	*/	1650	*/
1651	i_size = i_size_read(ino);	1651	i_size = i_size_read(ino);
1652	if (!i_size \|\| i_size & (sizeof(ntfschar) - 1) \|\|	1652	if (!i_size \|\| i_size & (sizeof(ntfschar) - 1) \|\|
1653	i_size > 64ULL * 1024 * sizeof(ntfschar))	1653	i_size > 64ULL * 1024 * sizeof(ntfschar))
1654	goto iput_upcase_failed;	1654	goto iput_upcase_failed;
1655	vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size);	1655	vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size);
1656	if (!vol->upcase)	1656	if (!vol->upcase)
1657	goto iput_upcase_failed;	1657	goto iput_upcase_failed;
1658	index = 0;	1658	index = 0;
1659	max_index = i_size >> PAGE_CACHE_SHIFT;	1659	max_index = i_size >> PAGE_CACHE_SHIFT;
1660	size = PAGE_CACHE_SIZE;	1660	size = PAGE_CACHE_SIZE;
1661	while (index < max_index) {	1661	while (index < max_index) {
1662	/* Read the upcase table and copy it into the linear buffer. */	1662	/* Read the upcase table and copy it into the linear buffer. */
1663	read_partial_upcase_page:	1663	read_partial_upcase_page:
1664	page = ntfs_map_page(ino->i_mapping, index);	1664	page = ntfs_map_page(ino->i_mapping, index);
1665	if (IS_ERR(page))	1665	if (IS_ERR(page))
1666	goto iput_upcase_failed;	1666	goto iput_upcase_failed;
1667	memcpy((char*)vol->upcase + (index++ << PAGE_CACHE_SHIFT),	1667	memcpy((char*)vol->upcase + (index++ << PAGE_CACHE_SHIFT),
1668	page_address(page), size);	1668	page_address(page), size);
1669	ntfs_unmap_page(page);	1669	ntfs_unmap_page(page);
1670	};	1670	};
1671	if (size == PAGE_CACHE_SIZE) {	1671	if (size == PAGE_CACHE_SIZE) {
1672	size = i_size & ~PAGE_CACHE_MASK;	1672	size = i_size & ~PAGE_CACHE_MASK;
1673	if (size)	1673	if (size)
1674	goto read_partial_upcase_page;	1674	goto read_partial_upcase_page;
1675	}	1675	}
1676	vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS;	1676	vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS;
1677	ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).",	1677	ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).",
1678	i_size, 64 * 1024 * sizeof(ntfschar));	1678	i_size, 64 * 1024 * sizeof(ntfschar));
1679	iput(ino);	1679	iput(ino);
1680	mutex_lock(&ntfs_lock);	1680	mutex_lock(&ntfs_lock);
1681	if (!default_upcase) {	1681	if (!default_upcase) {
1682	ntfs_debug("Using volume specified $UpCase since default is "	1682	ntfs_debug("Using volume specified $UpCase since default is "
1683	"not present.");	1683	"not present.");
1684	mutex_unlock(&ntfs_lock);	1684	mutex_unlock(&ntfs_lock);
1685	return true;	1685	return true;
1686	}	1686	}
1687	max = default_upcase_len;	1687	max = default_upcase_len;
1688	if (max > vol->upcase_len)	1688	if (max > vol->upcase_len)
1689	max = vol->upcase_len;	1689	max = vol->upcase_len;
1690	for (i = 0; i < max; i++)	1690	for (i = 0; i < max; i++)
1691	if (vol->upcase[i] != default_upcase[i])	1691	if (vol->upcase[i] != default_upcase[i])
1692	break;	1692	break;
1693	if (i == max) {	1693	if (i == max) {
1694	ntfs_free(vol->upcase);	1694	ntfs_free(vol->upcase);
1695	vol->upcase = default_upcase;	1695	vol->upcase = default_upcase;
1696	vol->upcase_len = max;	1696	vol->upcase_len = max;
1697	ntfs_nr_upcase_users++;	1697	ntfs_nr_upcase_users++;
1698	mutex_unlock(&ntfs_lock);	1698	mutex_unlock(&ntfs_lock);
1699	ntfs_debug("Volume specified $UpCase matches default. Using "	1699	ntfs_debug("Volume specified $UpCase matches default. Using "
1700	"default.");	1700	"default.");
1701	return true;	1701	return true;
1702	}	1702	}
1703	mutex_unlock(&ntfs_lock);	1703	mutex_unlock(&ntfs_lock);
1704	ntfs_debug("Using volume specified $UpCase since it does not match "	1704	ntfs_debug("Using volume specified $UpCase since it does not match "
1705	"the default.");	1705	"the default.");
1706	return true;	1706	return true;
1707	iput_upcase_failed:	1707	iput_upcase_failed:
1708	iput(ino);	1708	iput(ino);
1709	ntfs_free(vol->upcase);	1709	ntfs_free(vol->upcase);
1710	vol->upcase = NULL;	1710	vol->upcase = NULL;
1711	upcase_failed:	1711	upcase_failed:
1712	mutex_lock(&ntfs_lock);	1712	mutex_lock(&ntfs_lock);
1713	if (default_upcase) {	1713	if (default_upcase) {
1714	vol->upcase = default_upcase;	1714	vol->upcase = default_upcase;
1715	vol->upcase_len = default_upcase_len;	1715	vol->upcase_len = default_upcase_len;
1716	ntfs_nr_upcase_users++;	1716	ntfs_nr_upcase_users++;
1717	mutex_unlock(&ntfs_lock);	1717	mutex_unlock(&ntfs_lock);
1718	ntfs_error(sb, "Failed to load $UpCase from the volume. Using "	1718	ntfs_error(sb, "Failed to load $UpCase from the volume. Using "
1719	"default.");	1719	"default.");
1720	return true;	1720	return true;
1721	}	1721	}
1722	mutex_unlock(&ntfs_lock);	1722	mutex_unlock(&ntfs_lock);
1723	ntfs_error(sb, "Failed to initialize upcase table.");	1723	ntfs_error(sb, "Failed to initialize upcase table.");
1724	return false;	1724	return false;
1725	}	1725	}
1726		1726
1727	/*	1727	/*
1728	* The lcn and mft bitmap inodes are NTFS-internal inodes with	1728	* The lcn and mft bitmap inodes are NTFS-internal inodes with
1729	* their own special locking rules:	1729	* their own special locking rules:
1730	*/	1730	*/
1731	static struct lock_class_key	1731	static struct lock_class_key
1732	lcnbmp_runlist_lock_key, lcnbmp_mrec_lock_key,	1732	lcnbmp_runlist_lock_key, lcnbmp_mrec_lock_key,
1733	mftbmp_runlist_lock_key, mftbmp_mrec_lock_key;	1733	mftbmp_runlist_lock_key, mftbmp_mrec_lock_key;
1734		1734
1735	/**	1735	/**
1736	* load_system_files - open the system files using normal functions	1736	* load_system_files - open the system files using normal functions
1737	* @vol: ntfs super block describing device whose system files to load	1737	* @vol: ntfs super block describing device whose system files to load
1738	*	1738	*
1739	* Open the system files with normal access functions and complete setting up	1739	* Open the system files with normal access functions and complete setting up
1740	* the ntfs super block @vol.	1740	* the ntfs super block @vol.
1741	*	1741	*
1742	* Return 'true' on success or 'false' on error.	1742	* Return 'true' on success or 'false' on error.
1743	*/	1743	*/
1744	static bool load_system_files(ntfs_volume *vol)	1744	static bool load_system_files(ntfs_volume *vol)
1745	{	1745	{
1746	struct super_block *sb = vol->sb;	1746	struct super_block *sb = vol->sb;
1747	MFT_RECORD *m;	1747	MFT_RECORD *m;
1748	VOLUME_INFORMATION *vi;	1748	VOLUME_INFORMATION *vi;
1749	ntfs_attr_search_ctx *ctx;	1749	ntfs_attr_search_ctx *ctx;
1750	#ifdef NTFS_RW	1750	#ifdef NTFS_RW
1751	RESTART_PAGE_HEADER *rp;	1751	RESTART_PAGE_HEADER *rp;
1752	int err;	1752	int err;
1753	#endif /* NTFS_RW */	1753	#endif /* NTFS_RW */
1754		1754
1755	ntfs_debug("Entering.");	1755	ntfs_debug("Entering.");
1756	#ifdef NTFS_RW	1756	#ifdef NTFS_RW
1757	/* Get mft mirror inode compare the contents of $MFT and $MFTMirr. */	1757	/* Get mft mirror inode compare the contents of $MFT and $MFTMirr. */
1758	if (!load_and_init_mft_mirror(vol) \|\| !check_mft_mirror(vol)) {	1758	if (!load_and_init_mft_mirror(vol) \|\| !check_mft_mirror(vol)) {
1759	static const char *es1 = "Failed to load $MFTMirr";	1759	static const char *es1 = "Failed to load $MFTMirr";
1760	static const char *es2 = "$MFTMirr does not match $MFT";	1760	static const char *es2 = "$MFTMirr does not match $MFT";
1761	static const char *es3 = ". Run ntfsfix and/or chkdsk.";	1761	static const char *es3 = ". Run ntfsfix and/or chkdsk.";
1762		1762
1763	/* If a read-write mount, convert it to a read-only mount. */	1763	/* If a read-write mount, convert it to a read-only mount. */
1764	if (!(sb->s_flags & MS_RDONLY)) {	1764	if (!(sb->s_flags & MS_RDONLY)) {
1765	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	1765	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
1766	ON_ERRORS_CONTINUE))) {	1766	ON_ERRORS_CONTINUE))) {
1767	ntfs_error(sb, "%s and neither on_errors="	1767	ntfs_error(sb, "%s and neither on_errors="
1768	"continue nor on_errors="	1768	"continue nor on_errors="
1769	"remount-ro was specified%s",	1769	"remount-ro was specified%s",
1770	!vol->mftmirr_ino ? es1 : es2,	1770	!vol->mftmirr_ino ? es1 : es2,
1771	es3);	1771	es3);
1772	goto iput_mirr_err_out;	1772	goto iput_mirr_err_out;
1773	}	1773	}
1774	sb->s_flags \|= MS_RDONLY;	1774	sb->s_flags \|= MS_RDONLY;
1775	ntfs_error(sb, "%s. Mounting read-only%s",	1775	ntfs_error(sb, "%s. Mounting read-only%s",
1776	!vol->mftmirr_ino ? es1 : es2, es3);	1776	!vol->mftmirr_ino ? es1 : es2, es3);
1777	} else	1777	} else
1778	ntfs_warning(sb, "%s. Will not be able to remount "	1778	ntfs_warning(sb, "%s. Will not be able to remount "
1779	"read-write%s",	1779	"read-write%s",
1780	!vol->mftmirr_ino ? es1 : es2, es3);	1780	!vol->mftmirr_ino ? es1 : es2, es3);
1781	/* This will prevent a read-write remount. */	1781	/* This will prevent a read-write remount. */
1782	NVolSetErrors(vol);	1782	NVolSetErrors(vol);
1783	}	1783	}
1784	#endif /* NTFS_RW */	1784	#endif /* NTFS_RW */
1785	/* Get mft bitmap attribute inode. */	1785	/* Get mft bitmap attribute inode. */
1786	vol->mftbmp_ino = ntfs_attr_iget(vol->mft_ino, AT_BITMAP, NULL, 0);	1786	vol->mftbmp_ino = ntfs_attr_iget(vol->mft_ino, AT_BITMAP, NULL, 0);
1787	if (IS_ERR(vol->mftbmp_ino)) {	1787	if (IS_ERR(vol->mftbmp_ino)) {
1788	ntfs_error(sb, "Failed to load $MFT/$BITMAP attribute.");	1788	ntfs_error(sb, "Failed to load $MFT/$BITMAP attribute.");
1789	goto iput_mirr_err_out;	1789	goto iput_mirr_err_out;
1790	}	1790	}
1791	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->runlist.lock,	1791	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->runlist.lock,
1792	&mftbmp_runlist_lock_key);	1792	&mftbmp_runlist_lock_key);
1793	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->mrec_lock,	1793	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->mrec_lock,
1794	&mftbmp_mrec_lock_key);	1794	&mftbmp_mrec_lock_key);
1795	/* Read upcase table and setup @vol->upcase and @vol->upcase_len. */	1795	/* Read upcase table and setup @vol->upcase and @vol->upcase_len. */
1796	if (!load_and_init_upcase(vol))	1796	if (!load_and_init_upcase(vol))
1797	goto iput_mftbmp_err_out;	1797	goto iput_mftbmp_err_out;
1798	#ifdef NTFS_RW	1798	#ifdef NTFS_RW
1799	/*	1799	/*
1800	* Read attribute definitions table and setup @vol->attrdef and	1800	* Read attribute definitions table and setup @vol->attrdef and
1801	* @vol->attrdef_size.	1801	* @vol->attrdef_size.
1802	*/	1802	*/
1803	if (!load_and_init_attrdef(vol))	1803	if (!load_and_init_attrdef(vol))
1804	goto iput_upcase_err_out;	1804	goto iput_upcase_err_out;
1805	#endif /* NTFS_RW */	1805	#endif /* NTFS_RW */
1806	/*	1806	/*
1807	* Get the cluster allocation bitmap inode and verify the size, no	1807	* Get the cluster allocation bitmap inode and verify the size, no
1808	* need for any locking at this stage as we are already running	1808	* need for any locking at this stage as we are already running
1809	* exclusively as we are mount in progress task.	1809	* exclusively as we are mount in progress task.
1810	*/	1810	*/
1811	vol->lcnbmp_ino = ntfs_iget(sb, FILE_Bitmap);	1811	vol->lcnbmp_ino = ntfs_iget(sb, FILE_Bitmap);
1812	if (IS_ERR(vol->lcnbmp_ino) \|\| is_bad_inode(vol->lcnbmp_ino)) {	1812	if (IS_ERR(vol->lcnbmp_ino) \|\| is_bad_inode(vol->lcnbmp_ino)) {
1813	if (!IS_ERR(vol->lcnbmp_ino))	1813	if (!IS_ERR(vol->lcnbmp_ino))
1814	iput(vol->lcnbmp_ino);	1814	iput(vol->lcnbmp_ino);
1815	goto bitmap_failed;	1815	goto bitmap_failed;
1816	}	1816	}
1817	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->runlist.lock,	1817	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->runlist.lock,
1818	&lcnbmp_runlist_lock_key);	1818	&lcnbmp_runlist_lock_key);
1819	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->mrec_lock,	1819	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->mrec_lock,
1820	&lcnbmp_mrec_lock_key);	1820	&lcnbmp_mrec_lock_key);
1821		1821
1822	NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino));	1822	NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino));
1823	if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) {	1823	if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) {
1824	iput(vol->lcnbmp_ino);	1824	iput(vol->lcnbmp_ino);
1825	bitmap_failed:	1825	bitmap_failed:
1826	ntfs_error(sb, "Failed to load $Bitmap.");	1826	ntfs_error(sb, "Failed to load $Bitmap.");
1827	goto iput_attrdef_err_out;	1827	goto iput_attrdef_err_out;
1828	}	1828	}
1829	/*	1829	/*
1830	* Get the volume inode and setup our cache of the volume flags and	1830	* Get the volume inode and setup our cache of the volume flags and
1831	* version.	1831	* version.
1832	*/	1832	*/
1833	vol->vol_ino = ntfs_iget(sb, FILE_Volume);	1833	vol->vol_ino = ntfs_iget(sb, FILE_Volume);
1834	if (IS_ERR(vol->vol_ino) \|\| is_bad_inode(vol->vol_ino)) {	1834	if (IS_ERR(vol->vol_ino) \|\| is_bad_inode(vol->vol_ino)) {
1835	if (!IS_ERR(vol->vol_ino))	1835	if (!IS_ERR(vol->vol_ino))
1836	iput(vol->vol_ino);	1836	iput(vol->vol_ino);
1837	volume_failed:	1837	volume_failed:
1838	ntfs_error(sb, "Failed to load $Volume.");	1838	ntfs_error(sb, "Failed to load $Volume.");
1839	goto iput_lcnbmp_err_out;	1839	goto iput_lcnbmp_err_out;
1840	}	1840	}
1841	m = map_mft_record(NTFS_I(vol->vol_ino));	1841	m = map_mft_record(NTFS_I(vol->vol_ino));
1842	if (IS_ERR(m)) {	1842	if (IS_ERR(m)) {
1843	iput_volume_failed:	1843	iput_volume_failed:
1844	iput(vol->vol_ino);	1844	iput(vol->vol_ino);
1845	goto volume_failed;	1845	goto volume_failed;
1846	}	1846	}
1847	if (!(ctx = ntfs_attr_get_search_ctx(NTFS_I(vol->vol_ino), m))) {	1847	if (!(ctx = ntfs_attr_get_search_ctx(NTFS_I(vol->vol_ino), m))) {
1848	ntfs_error(sb, "Failed to get attribute search context.");	1848	ntfs_error(sb, "Failed to get attribute search context.");
1849	goto get_ctx_vol_failed;	1849	goto get_ctx_vol_failed;
1850	}	1850	}
1851	if (ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,	1851	if (ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
1852	ctx) \|\| ctx->attr->non_resident \|\| ctx->attr->flags) {	1852	ctx) \|\| ctx->attr->non_resident \|\| ctx->attr->flags) {
1853	err_put_vol:	1853	err_put_vol:
1854	ntfs_attr_put_search_ctx(ctx);	1854	ntfs_attr_put_search_ctx(ctx);
1855	get_ctx_vol_failed:	1855	get_ctx_vol_failed:
1856	unmap_mft_record(NTFS_I(vol->vol_ino));	1856	unmap_mft_record(NTFS_I(vol->vol_ino));
1857	goto iput_volume_failed;	1857	goto iput_volume_failed;
1858	}	1858	}
1859	vi = (VOLUME_INFORMATION)((char)ctx->attr +	1859	vi = (VOLUME_INFORMATION)((char)ctx->attr +
1860	le16_to_cpu(ctx->attr->data.resident.value_offset));	1860	le16_to_cpu(ctx->attr->data.resident.value_offset));
1861	/* Some bounds checks. */	1861	/* Some bounds checks. */
1862	if ((u8)vi < (u8)ctx->attr \|\| (u8*)vi +	1862	if ((u8)vi < (u8)ctx->attr \|\| (u8*)vi +
1863	le32_to_cpu(ctx->attr->data.resident.value_length) >	1863	le32_to_cpu(ctx->attr->data.resident.value_length) >
1864	(u8*)ctx->attr + le32_to_cpu(ctx->attr->length))	1864	(u8*)ctx->attr + le32_to_cpu(ctx->attr->length))
1865	goto err_put_vol;	1865	goto err_put_vol;
1866	/* Copy the volume flags and version to the ntfs_volume structure. */	1866	/* Copy the volume flags and version to the ntfs_volume structure. */
1867	vol->vol_flags = vi->flags;	1867	vol->vol_flags = vi->flags;
1868	vol->major_ver = vi->major_ver;	1868	vol->major_ver = vi->major_ver;
1869	vol->minor_ver = vi->minor_ver;	1869	vol->minor_ver = vi->minor_ver;
1870	ntfs_attr_put_search_ctx(ctx);	1870	ntfs_attr_put_search_ctx(ctx);
1871	unmap_mft_record(NTFS_I(vol->vol_ino));	1871	unmap_mft_record(NTFS_I(vol->vol_ino));
1872	printk(KERN_INFO "NTFS volume version %i.%i.\n", vol->major_ver,	1872	printk(KERN_INFO "NTFS volume version %i.%i.\n", vol->major_ver,
1873	vol->minor_ver);	1873	vol->minor_ver);
1874	if (vol->major_ver < 3 && NVolSparseEnabled(vol)) {	1874	if (vol->major_ver < 3 && NVolSparseEnabled(vol)) {
1875	ntfs_warning(vol->sb, "Disabling sparse support due to NTFS "	1875	ntfs_warning(vol->sb, "Disabling sparse support due to NTFS "
1876	"volume version %i.%i (need at least version "	1876	"volume version %i.%i (need at least version "
1877	"3.0).", vol->major_ver, vol->minor_ver);	1877	"3.0).", vol->major_ver, vol->minor_ver);
1878	NVolClearSparseEnabled(vol);	1878	NVolClearSparseEnabled(vol);
1879	}	1879	}
1880	#ifdef NTFS_RW	1880	#ifdef NTFS_RW
1881	/* Make sure that no unsupported volume flags are set. */	1881	/* Make sure that no unsupported volume flags are set. */
1882	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {	1882	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
1883	static const char *es1a = "Volume is dirty";	1883	static const char *es1a = "Volume is dirty";
1884	static const char *es1b = "Volume has been modified by chkdsk";	1884	static const char *es1b = "Volume has been modified by chkdsk";
1885	static const char *es1c = "Volume has unsupported flags set";	1885	static const char *es1c = "Volume has unsupported flags set";
1886	static const char *es2a = ". Run chkdsk and mount in Windows.";	1886	static const char *es2a = ". Run chkdsk and mount in Windows.";
1887	static const char *es2b = ". Mount in Windows.";	1887	static const char *es2b = ". Mount in Windows.";
1888	const char es1, es2;	1888	const char es1, es2;
1889		1889
1890	es2 = es2a;	1890	es2 = es2a;
1891	if (vol->vol_flags & VOLUME_IS_DIRTY)	1891	if (vol->vol_flags & VOLUME_IS_DIRTY)
1892	es1 = es1a;	1892	es1 = es1a;
1893	else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {	1893	else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
1894	es1 = es1b;	1894	es1 = es1b;
1895	es2 = es2b;	1895	es2 = es2b;
1896	} else {	1896	} else {
1897	es1 = es1c;	1897	es1 = es1c;
1898	ntfs_warning(sb, "Unsupported volume flags 0x%x "	1898	ntfs_warning(sb, "Unsupported volume flags 0x%x "
1899	"encountered.",	1899	"encountered.",
1900	(unsigned)le16_to_cpu(vol->vol_flags));	1900	(unsigned)le16_to_cpu(vol->vol_flags));
1901	}	1901	}
1902	/* If a read-write mount, convert it to a read-only mount. */	1902	/* If a read-write mount, convert it to a read-only mount. */
1903	if (!(sb->s_flags & MS_RDONLY)) {	1903	if (!(sb->s_flags & MS_RDONLY)) {
1904	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	1904	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
1905	ON_ERRORS_CONTINUE))) {	1905	ON_ERRORS_CONTINUE))) {
1906	ntfs_error(sb, "%s and neither on_errors="	1906	ntfs_error(sb, "%s and neither on_errors="
1907	"continue nor on_errors="	1907	"continue nor on_errors="
1908	"remount-ro was specified%s",	1908	"remount-ro was specified%s",
1909	es1, es2);	1909	es1, es2);
1910	goto iput_vol_err_out;	1910	goto iput_vol_err_out;
1911	}	1911	}
1912	sb->s_flags \|= MS_RDONLY;	1912	sb->s_flags \|= MS_RDONLY;
1913	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	1913	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
1914	} else	1914	} else
1915	ntfs_warning(sb, "%s. Will not be able to remount "	1915	ntfs_warning(sb, "%s. Will not be able to remount "
1916	"read-write%s", es1, es2);	1916	"read-write%s", es1, es2);
1917	/*	1917	/*
1918	* Do not set NVolErrors() because ntfs_remount() re-checks the	1918	* Do not set NVolErrors() because ntfs_remount() re-checks the
1919	* flags which we need to do in case any flags have changed.	1919	* flags which we need to do in case any flags have changed.
1920	*/	1920	*/
1921	}	1921	}
1922	/*	1922	/*
1923	* Get the inode for the logfile, check it and determine if the volume	1923	* Get the inode for the logfile, check it and determine if the volume
1924	* was shutdown cleanly.	1924	* was shutdown cleanly.
1925	*/	1925	*/
1926	rp = NULL;	1926	rp = NULL;
1927	if (!load_and_check_logfile(vol, &rp) \|\|	1927	if (!load_and_check_logfile(vol, &rp) \|\|
1928	!ntfs_is_logfile_clean(vol->logfile_ino, rp)) {	1928	!ntfs_is_logfile_clean(vol->logfile_ino, rp)) {
1929	static const char *es1a = "Failed to load $LogFile";	1929	static const char *es1a = "Failed to load $LogFile";
1930	static const char *es1b = "$LogFile is not clean";	1930	static const char *es1b = "$LogFile is not clean";
1931	static const char *es2 = ". Mount in Windows.";	1931	static const char *es2 = ". Mount in Windows.";
1932	const char *es1;	1932	const char *es1;
1933		1933
1934	es1 = !vol->logfile_ino ? es1a : es1b;	1934	es1 = !vol->logfile_ino ? es1a : es1b;
1935	/* If a read-write mount, convert it to a read-only mount. */	1935	/* If a read-write mount, convert it to a read-only mount. */
1936	if (!(sb->s_flags & MS_RDONLY)) {	1936	if (!(sb->s_flags & MS_RDONLY)) {
1937	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	1937	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
1938	ON_ERRORS_CONTINUE))) {	1938	ON_ERRORS_CONTINUE))) {
1939	ntfs_error(sb, "%s and neither on_errors="	1939	ntfs_error(sb, "%s and neither on_errors="
1940	"continue nor on_errors="	1940	"continue nor on_errors="
1941	"remount-ro was specified%s",	1941	"remount-ro was specified%s",
1942	es1, es2);	1942	es1, es2);
1943	if (vol->logfile_ino) {	1943	if (vol->logfile_ino) {
1944	BUG_ON(!rp);	1944	BUG_ON(!rp);
1945	ntfs_free(rp);	1945	ntfs_free(rp);
1946	}	1946	}
1947	goto iput_logfile_err_out;	1947	goto iput_logfile_err_out;
1948	}	1948	}
1949	sb->s_flags \|= MS_RDONLY;	1949	sb->s_flags \|= MS_RDONLY;
1950	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	1950	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
1951	} else	1951	} else
1952	ntfs_warning(sb, "%s. Will not be able to remount "	1952	ntfs_warning(sb, "%s. Will not be able to remount "
1953	"read-write%s", es1, es2);	1953	"read-write%s", es1, es2);
1954	/* This will prevent a read-write remount. */	1954	/* This will prevent a read-write remount. */
1955	NVolSetErrors(vol);	1955	NVolSetErrors(vol);
1956	}	1956	}
1957	ntfs_free(rp);	1957	ntfs_free(rp);
1958	#endif /* NTFS_RW */	1958	#endif /* NTFS_RW */
1959	/* Get the root directory inode so we can do path lookups. */	1959	/* Get the root directory inode so we can do path lookups. */
1960	vol->root_ino = ntfs_iget(sb, FILE_root);	1960	vol->root_ino = ntfs_iget(sb, FILE_root);
1961	if (IS_ERR(vol->root_ino) \|\| is_bad_inode(vol->root_ino)) {	1961	if (IS_ERR(vol->root_ino) \|\| is_bad_inode(vol->root_ino)) {
1962	if (!IS_ERR(vol->root_ino))	1962	if (!IS_ERR(vol->root_ino))
1963	iput(vol->root_ino);	1963	iput(vol->root_ino);
1964	ntfs_error(sb, "Failed to load root directory.");	1964	ntfs_error(sb, "Failed to load root directory.");
1965	goto iput_logfile_err_out;	1965	goto iput_logfile_err_out;
1966	}	1966	}
1967	#ifdef NTFS_RW	1967	#ifdef NTFS_RW
1968	/*	1968	/*
1969	* Check if Windows is suspended to disk on the target volume. If it	1969	* Check if Windows is suspended to disk on the target volume. If it
1970	* is hibernated, we must not write anything to the disk so set	1970	* is hibernated, we must not write anything to the disk so set
1971	* NVolErrors() without setting the dirty volume flag and mount	1971	* NVolErrors() without setting the dirty volume flag and mount
1972	* read-only. This will prevent read-write remounting and it will also	1972	* read-only. This will prevent read-write remounting and it will also
1973	* prevent all writes.	1973	* prevent all writes.
1974	*/	1974	*/
1975	err = check_windows_hibernation_status(vol);	1975	err = check_windows_hibernation_status(vol);
1976	if (unlikely(err)) {	1976	if (unlikely(err)) {
1977	static const char *es1a = "Failed to determine if Windows is "	1977	static const char *es1a = "Failed to determine if Windows is "
1978	"hibernated";	1978	"hibernated";
1979	static const char *es1b = "Windows is hibernated";	1979	static const char *es1b = "Windows is hibernated";
1980	static const char *es2 = ". Run chkdsk.";	1980	static const char *es2 = ". Run chkdsk.";
1981	const char *es1;	1981	const char *es1;
1982		1982
1983	es1 = err < 0 ? es1a : es1b;	1983	es1 = err < 0 ? es1a : es1b;
1984	/* If a read-write mount, convert it to a read-only mount. */	1984	/* If a read-write mount, convert it to a read-only mount. */
1985	if (!(sb->s_flags & MS_RDONLY)) {	1985	if (!(sb->s_flags & MS_RDONLY)) {
1986	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	1986	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
1987	ON_ERRORS_CONTINUE))) {	1987	ON_ERRORS_CONTINUE))) {
1988	ntfs_error(sb, "%s and neither on_errors="	1988	ntfs_error(sb, "%s and neither on_errors="
1989	"continue nor on_errors="	1989	"continue nor on_errors="
1990	"remount-ro was specified%s",	1990	"remount-ro was specified%s",
1991	es1, es2);	1991	es1, es2);
1992	goto iput_root_err_out;	1992	goto iput_root_err_out;
1993	}	1993	}
1994	sb->s_flags \|= MS_RDONLY;	1994	sb->s_flags \|= MS_RDONLY;
1995	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	1995	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
1996	} else	1996	} else
1997	ntfs_warning(sb, "%s. Will not be able to remount "	1997	ntfs_warning(sb, "%s. Will not be able to remount "
1998	"read-write%s", es1, es2);	1998	"read-write%s", es1, es2);
1999	/* This will prevent a read-write remount. */	1999	/* This will prevent a read-write remount. */
2000	NVolSetErrors(vol);	2000	NVolSetErrors(vol);
2001	}	2001	}
2002	/* If (still) a read-write mount, mark the volume dirty. */	2002	/* If (still) a read-write mount, mark the volume dirty. */
2003	if (!(sb->s_flags & MS_RDONLY) &&	2003	if (!(sb->s_flags & MS_RDONLY) &&
2004	ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {	2004	ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
2005	static const char *es1 = "Failed to set dirty bit in volume "	2005	static const char *es1 = "Failed to set dirty bit in volume "
2006	"information flags";	2006	"information flags";
2007	static const char *es2 = ". Run chkdsk.";	2007	static const char *es2 = ". Run chkdsk.";
2008		2008
2009	/* Convert to a read-only mount. */	2009	/* Convert to a read-only mount. */
2010	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2010	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2011	ON_ERRORS_CONTINUE))) {	2011	ON_ERRORS_CONTINUE))) {
2012	ntfs_error(sb, "%s and neither on_errors=continue nor "	2012	ntfs_error(sb, "%s and neither on_errors=continue nor "
2013	"on_errors=remount-ro was specified%s",	2013	"on_errors=remount-ro was specified%s",
2014	es1, es2);	2014	es1, es2);
2015	goto iput_root_err_out;	2015	goto iput_root_err_out;
2016	}	2016	}
2017	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2017	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2018	sb->s_flags \|= MS_RDONLY;	2018	sb->s_flags \|= MS_RDONLY;
2019	/*	2019	/*
2020	* Do not set NVolErrors() because ntfs_remount() might manage	2020	* Do not set NVolErrors() because ntfs_remount() might manage
2021	* to set the dirty flag in which case all would be well.	2021	* to set the dirty flag in which case all would be well.
2022	*/	2022	*/
2023	}	2023	}
2024	#if 0	2024	#if 0
2025	// TODO: Enable this code once we start modifying anything that is	2025	// TODO: Enable this code once we start modifying anything that is
2026	// different between NTFS 1.2 and 3.x...	2026	// different between NTFS 1.2 and 3.x...
2027	/*	2027	/*
2028	* If (still) a read-write mount, set the NT4 compatibility flag on	2028	* If (still) a read-write mount, set the NT4 compatibility flag on
2029	* newer NTFS version volumes.	2029	* newer NTFS version volumes.
2030	*/	2030	*/
2031	if (!(sb->s_flags & MS_RDONLY) && (vol->major_ver > 1) &&	2031	if (!(sb->s_flags & MS_RDONLY) && (vol->major_ver > 1) &&
2032	ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {	2032	ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
2033	static const char *es1 = "Failed to set NT4 compatibility flag";	2033	static const char *es1 = "Failed to set NT4 compatibility flag";
2034	static const char *es2 = ". Run chkdsk.";	2034	static const char *es2 = ". Run chkdsk.";
2035		2035
2036	/* Convert to a read-only mount. */	2036	/* Convert to a read-only mount. */
2037	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2037	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2038	ON_ERRORS_CONTINUE))) {	2038	ON_ERRORS_CONTINUE))) {
2039	ntfs_error(sb, "%s and neither on_errors=continue nor "	2039	ntfs_error(sb, "%s and neither on_errors=continue nor "
2040	"on_errors=remount-ro was specified%s",	2040	"on_errors=remount-ro was specified%s",
2041	es1, es2);	2041	es1, es2);
2042	goto iput_root_err_out;	2042	goto iput_root_err_out;
2043	}	2043	}
2044	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2044	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2045	sb->s_flags \|= MS_RDONLY;	2045	sb->s_flags \|= MS_RDONLY;
2046	NVolSetErrors(vol);	2046	NVolSetErrors(vol);
2047	}	2047	}
2048	#endif	2048	#endif
2049	/* If (still) a read-write mount, empty the logfile. */	2049	/* If (still) a read-write mount, empty the logfile. */
2050	if (!(sb->s_flags & MS_RDONLY) &&	2050	if (!(sb->s_flags & MS_RDONLY) &&
2051	!ntfs_empty_logfile(vol->logfile_ino)) {	2051	!ntfs_empty_logfile(vol->logfile_ino)) {
2052	static const char *es1 = "Failed to empty $LogFile";	2052	static const char *es1 = "Failed to empty $LogFile";
2053	static const char *es2 = ". Mount in Windows.";	2053	static const char *es2 = ". Mount in Windows.";
2054		2054
2055	/* Convert to a read-only mount. */	2055	/* Convert to a read-only mount. */
2056	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2056	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2057	ON_ERRORS_CONTINUE))) {	2057	ON_ERRORS_CONTINUE))) {
2058	ntfs_error(sb, "%s and neither on_errors=continue nor "	2058	ntfs_error(sb, "%s and neither on_errors=continue nor "
2059	"on_errors=remount-ro was specified%s",	2059	"on_errors=remount-ro was specified%s",
2060	es1, es2);	2060	es1, es2);
2061	goto iput_root_err_out;	2061	goto iput_root_err_out;
2062	}	2062	}
2063	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2063	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2064	sb->s_flags \|= MS_RDONLY;	2064	sb->s_flags \|= MS_RDONLY;
2065	NVolSetErrors(vol);	2065	NVolSetErrors(vol);
2066	}	2066	}
2067	#endif /* NTFS_RW */	2067	#endif /* NTFS_RW */
2068	/* If on NTFS versions before 3.0, we are done. */	2068	/* If on NTFS versions before 3.0, we are done. */
2069	if (unlikely(vol->major_ver < 3))	2069	if (unlikely(vol->major_ver < 3))
2070	return true;	2070	return true;
2071	/* NTFS 3.0+ specific initialization. */	2071	/* NTFS 3.0+ specific initialization. */
2072	/* Get the security descriptors inode. */	2072	/* Get the security descriptors inode. */
2073	vol->secure_ino = ntfs_iget(sb, FILE_Secure);	2073	vol->secure_ino = ntfs_iget(sb, FILE_Secure);
2074	if (IS_ERR(vol->secure_ino) \|\| is_bad_inode(vol->secure_ino)) {	2074	if (IS_ERR(vol->secure_ino) \|\| is_bad_inode(vol->secure_ino)) {
2075	if (!IS_ERR(vol->secure_ino))	2075	if (!IS_ERR(vol->secure_ino))
2076	iput(vol->secure_ino);	2076	iput(vol->secure_ino);
2077	ntfs_error(sb, "Failed to load $Secure.");	2077	ntfs_error(sb, "Failed to load $Secure.");
2078	goto iput_root_err_out;	2078	goto iput_root_err_out;
2079	}	2079	}
2080	// TODO: Initialize security.	2080	// TODO: Initialize security.
2081	/* Get the extended system files' directory inode. */	2081	/* Get the extended system files' directory inode. */
2082	vol->extend_ino = ntfs_iget(sb, FILE_Extend);	2082	vol->extend_ino = ntfs_iget(sb, FILE_Extend);
2083	if (IS_ERR(vol->extend_ino) \|\| is_bad_inode(vol->extend_ino)) {	2083	if (IS_ERR(vol->extend_ino) \|\| is_bad_inode(vol->extend_ino)) {
2084	if (!IS_ERR(vol->extend_ino))	2084	if (!IS_ERR(vol->extend_ino))
2085	iput(vol->extend_ino);	2085	iput(vol->extend_ino);
2086	ntfs_error(sb, "Failed to load $Extend.");	2086	ntfs_error(sb, "Failed to load $Extend.");
2087	goto iput_sec_err_out;	2087	goto iput_sec_err_out;
2088	}	2088	}
2089	#ifdef NTFS_RW	2089	#ifdef NTFS_RW
2090	/* Find the quota file, load it if present, and set it up. */	2090	/* Find the quota file, load it if present, and set it up. */
2091	if (!load_and_init_quota(vol)) {	2091	if (!load_and_init_quota(vol)) {
2092	static const char *es1 = "Failed to load $Quota";	2092	static const char *es1 = "Failed to load $Quota";
2093	static const char *es2 = ". Run chkdsk.";	2093	static const char *es2 = ". Run chkdsk.";
2094		2094
2095	/* If a read-write mount, convert it to a read-only mount. */	2095	/* If a read-write mount, convert it to a read-only mount. */
2096	if (!(sb->s_flags & MS_RDONLY)) {	2096	if (!(sb->s_flags & MS_RDONLY)) {
2097	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2097	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2098	ON_ERRORS_CONTINUE))) {	2098	ON_ERRORS_CONTINUE))) {
2099	ntfs_error(sb, "%s and neither on_errors="	2099	ntfs_error(sb, "%s and neither on_errors="
2100	"continue nor on_errors="	2100	"continue nor on_errors="
2101	"remount-ro was specified%s",	2101	"remount-ro was specified%s",
2102	es1, es2);	2102	es1, es2);
2103	goto iput_quota_err_out;	2103	goto iput_quota_err_out;
2104	}	2104	}
2105	sb->s_flags \|= MS_RDONLY;	2105	sb->s_flags \|= MS_RDONLY;
2106	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2106	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2107	} else	2107	} else
2108	ntfs_warning(sb, "%s. Will not be able to remount "	2108	ntfs_warning(sb, "%s. Will not be able to remount "
2109	"read-write%s", es1, es2);	2109	"read-write%s", es1, es2);
2110	/* This will prevent a read-write remount. */	2110	/* This will prevent a read-write remount. */
2111	NVolSetErrors(vol);	2111	NVolSetErrors(vol);
2112	}	2112	}
2113	/* If (still) a read-write mount, mark the quotas out of date. */	2113	/* If (still) a read-write mount, mark the quotas out of date. */
2114	if (!(sb->s_flags & MS_RDONLY) &&	2114	if (!(sb->s_flags & MS_RDONLY) &&
2115	!ntfs_mark_quotas_out_of_date(vol)) {	2115	!ntfs_mark_quotas_out_of_date(vol)) {
2116	static const char *es1 = "Failed to mark quotas out of date";	2116	static const char *es1 = "Failed to mark quotas out of date";
2117	static const char *es2 = ". Run chkdsk.";	2117	static const char *es2 = ". Run chkdsk.";
2118		2118
2119	/* Convert to a read-only mount. */	2119	/* Convert to a read-only mount. */
2120	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2120	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2121	ON_ERRORS_CONTINUE))) {	2121	ON_ERRORS_CONTINUE))) {
2122	ntfs_error(sb, "%s and neither on_errors=continue nor "	2122	ntfs_error(sb, "%s and neither on_errors=continue nor "
2123	"on_errors=remount-ro was specified%s",	2123	"on_errors=remount-ro was specified%s",
2124	es1, es2);	2124	es1, es2);
2125	goto iput_quota_err_out;	2125	goto iput_quota_err_out;
2126	}	2126	}
2127	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2127	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2128	sb->s_flags \|= MS_RDONLY;	2128	sb->s_flags \|= MS_RDONLY;
2129	NVolSetErrors(vol);	2129	NVolSetErrors(vol);
2130	}	2130	}
2131	/*	2131	/*
2132	* Find the transaction log file ($UsnJrnl), load it if present, check	2132	* Find the transaction log file ($UsnJrnl), load it if present, check
2133	* it, and set it up.	2133	* it, and set it up.
2134	*/	2134	*/
2135	if (!load_and_init_usnjrnl(vol)) {	2135	if (!load_and_init_usnjrnl(vol)) {
2136	static const char *es1 = "Failed to load $UsnJrnl";	2136	static const char *es1 = "Failed to load $UsnJrnl";
2137	static const char *es2 = ". Run chkdsk.";	2137	static const char *es2 = ". Run chkdsk.";
2138		2138
2139	/* If a read-write mount, convert it to a read-only mount. */	2139	/* If a read-write mount, convert it to a read-only mount. */
2140	if (!(sb->s_flags & MS_RDONLY)) {	2140	if (!(sb->s_flags & MS_RDONLY)) {
2141	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2141	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2142	ON_ERRORS_CONTINUE))) {	2142	ON_ERRORS_CONTINUE))) {
2143	ntfs_error(sb, "%s and neither on_errors="	2143	ntfs_error(sb, "%s and neither on_errors="
2144	"continue nor on_errors="	2144	"continue nor on_errors="
2145	"remount-ro was specified%s",	2145	"remount-ro was specified%s",
2146	es1, es2);	2146	es1, es2);
2147	goto iput_usnjrnl_err_out;	2147	goto iput_usnjrnl_err_out;
2148	}	2148	}
2149	sb->s_flags \|= MS_RDONLY;	2149	sb->s_flags \|= MS_RDONLY;
2150	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2150	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2151	} else	2151	} else
2152	ntfs_warning(sb, "%s. Will not be able to remount "	2152	ntfs_warning(sb, "%s. Will not be able to remount "
2153	"read-write%s", es1, es2);	2153	"read-write%s", es1, es2);
2154	/* This will prevent a read-write remount. */	2154	/* This will prevent a read-write remount. */
2155	NVolSetErrors(vol);	2155	NVolSetErrors(vol);
2156	}	2156	}
2157	/* If (still) a read-write mount, stamp the transaction log. */	2157	/* If (still) a read-write mount, stamp the transaction log. */
2158	if (!(sb->s_flags & MS_RDONLY) && !ntfs_stamp_usnjrnl(vol)) {	2158	if (!(sb->s_flags & MS_RDONLY) && !ntfs_stamp_usnjrnl(vol)) {
2159	static const char *es1 = "Failed to stamp transaction log "	2159	static const char *es1 = "Failed to stamp transaction log "
2160	"($UsnJrnl)";	2160	"($UsnJrnl)";
2161	static const char *es2 = ". Run chkdsk.";	2161	static const char *es2 = ". Run chkdsk.";
2162		2162
2163	/* Convert to a read-only mount. */	2163	/* Convert to a read-only mount. */
2164	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|	2164	if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO \|
2165	ON_ERRORS_CONTINUE))) {	2165	ON_ERRORS_CONTINUE))) {
2166	ntfs_error(sb, "%s and neither on_errors=continue nor "	2166	ntfs_error(sb, "%s and neither on_errors=continue nor "
2167	"on_errors=remount-ro was specified%s",	2167	"on_errors=remount-ro was specified%s",
2168	es1, es2);	2168	es1, es2);
2169	goto iput_usnjrnl_err_out;	2169	goto iput_usnjrnl_err_out;
2170	}	2170	}
2171	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);	2171	ntfs_error(sb, "%s. Mounting read-only%s", es1, es2);
2172	sb->s_flags \|= MS_RDONLY;	2172	sb->s_flags \|= MS_RDONLY;
2173	NVolSetErrors(vol);	2173	NVolSetErrors(vol);
2174	}	2174	}
2175	#endif /* NTFS_RW */	2175	#endif /* NTFS_RW */
2176	return true;	2176	return true;
2177	#ifdef NTFS_RW	2177	#ifdef NTFS_RW
2178	iput_usnjrnl_err_out:	2178	iput_usnjrnl_err_out:
2179	if (vol->usnjrnl_j_ino)	2179	if (vol->usnjrnl_j_ino)
2180	iput(vol->usnjrnl_j_ino);	2180	iput(vol->usnjrnl_j_ino);
2181	if (vol->usnjrnl_max_ino)	2181	if (vol->usnjrnl_max_ino)
2182	iput(vol->usnjrnl_max_ino);	2182	iput(vol->usnjrnl_max_ino);
2183	if (vol->usnjrnl_ino)	2183	if (vol->usnjrnl_ino)
2184	iput(vol->usnjrnl_ino);	2184	iput(vol->usnjrnl_ino);
2185	iput_quota_err_out:	2185	iput_quota_err_out:
2186	if (vol->quota_q_ino)	2186	if (vol->quota_q_ino)
2187	iput(vol->quota_q_ino);	2187	iput(vol->quota_q_ino);
2188	if (vol->quota_ino)	2188	if (vol->quota_ino)
2189	iput(vol->quota_ino);	2189	iput(vol->quota_ino);
2190	iput(vol->extend_ino);	2190	iput(vol->extend_ino);
2191	#endif /* NTFS_RW */	2191	#endif /* NTFS_RW */
2192	iput_sec_err_out:	2192	iput_sec_err_out:
2193	iput(vol->secure_ino);	2193	iput(vol->secure_ino);
2194	iput_root_err_out:	2194	iput_root_err_out:
2195	iput(vol->root_ino);	2195	iput(vol->root_ino);
2196	iput_logfile_err_out:	2196	iput_logfile_err_out:
2197	#ifdef NTFS_RW	2197	#ifdef NTFS_RW
2198	if (vol->logfile_ino)	2198	if (vol->logfile_ino)
2199	iput(vol->logfile_ino);	2199	iput(vol->logfile_ino);
2200	iput_vol_err_out:	2200	iput_vol_err_out:
2201	#endif /* NTFS_RW */	2201	#endif /* NTFS_RW */
2202	iput(vol->vol_ino);	2202	iput(vol->vol_ino);
2203	iput_lcnbmp_err_out:	2203	iput_lcnbmp_err_out:
2204	iput(vol->lcnbmp_ino);	2204	iput(vol->lcnbmp_ino);
2205	iput_attrdef_err_out:	2205	iput_attrdef_err_out:
2206	vol->attrdef_size = 0;	2206	vol->attrdef_size = 0;
2207	if (vol->attrdef) {	2207	if (vol->attrdef) {
2208	ntfs_free(vol->attrdef);	2208	ntfs_free(vol->attrdef);
2209	vol->attrdef = NULL;	2209	vol->attrdef = NULL;
2210	}	2210	}
2211	#ifdef NTFS_RW	2211	#ifdef NTFS_RW
2212	iput_upcase_err_out:	2212	iput_upcase_err_out:
2213	#endif /* NTFS_RW */	2213	#endif /* NTFS_RW */
2214	vol->upcase_len = 0;	2214	vol->upcase_len = 0;
2215	mutex_lock(&ntfs_lock);	2215	mutex_lock(&ntfs_lock);
2216	if (vol->upcase == default_upcase) {	2216	if (vol->upcase == default_upcase) {
2217	ntfs_nr_upcase_users--;	2217	ntfs_nr_upcase_users--;
2218	vol->upcase = NULL;	2218	vol->upcase = NULL;
2219	}	2219	}
2220	mutex_unlock(&ntfs_lock);	2220	mutex_unlock(&ntfs_lock);
2221	if (vol->upcase) {	2221	if (vol->upcase) {
2222	ntfs_free(vol->upcase);	2222	ntfs_free(vol->upcase);
2223	vol->upcase = NULL;	2223	vol->upcase = NULL;
2224	}	2224	}
2225	iput_mftbmp_err_out:	2225	iput_mftbmp_err_out:
2226	iput(vol->mftbmp_ino);	2226	iput(vol->mftbmp_ino);
2227	iput_mirr_err_out:	2227	iput_mirr_err_out:
2228	#ifdef NTFS_RW	2228	#ifdef NTFS_RW
2229	if (vol->mftmirr_ino)	2229	if (vol->mftmirr_ino)
2230	iput(vol->mftmirr_ino);	2230	iput(vol->mftmirr_ino);
2231	#endif /* NTFS_RW */	2231	#endif /* NTFS_RW */
2232	return false;	2232	return false;
2233	}	2233	}
2234		2234
2235	/**	2235	/**
2236	* ntfs_put_super - called by the vfs to unmount a volume	2236	* ntfs_put_super - called by the vfs to unmount a volume
2237	* @sb: vfs superblock of volume to unmount	2237	* @sb: vfs superblock of volume to unmount
2238	*	2238	*
2239	* ntfs_put_super() is called by the VFS (from fs/super.c::do_umount()) when	2239	* ntfs_put_super() is called by the VFS (from fs/super.c::do_umount()) when
2240	* the volume is being unmounted (umount system call has been invoked) and it	2240	* the volume is being unmounted (umount system call has been invoked) and it
2241	* releases all inodes and memory belonging to the NTFS specific part of the	2241	* releases all inodes and memory belonging to the NTFS specific part of the
2242	* super block.	2242	* super block.
2243	*/	2243	*/
2244	static void ntfs_put_super(struct super_block *sb)	2244	static void ntfs_put_super(struct super_block *sb)
2245	{	2245	{
2246	ntfs_volume *vol = NTFS_SB(sb);	2246	ntfs_volume *vol = NTFS_SB(sb);
2247		2247
2248	ntfs_debug("Entering.");	2248	ntfs_debug("Entering.");
2249	#ifdef NTFS_RW	2249	#ifdef NTFS_RW
2250	/*	2250	/*
2251	* Commit all inodes while they are still open in case some of them	2251	* Commit all inodes while they are still open in case some of them
2252	* cause others to be dirtied.	2252	* cause others to be dirtied.
2253	*/	2253	*/
2254	ntfs_commit_inode(vol->vol_ino);	2254	ntfs_commit_inode(vol->vol_ino);
2255		2255
2256	/* NTFS 3.0+ specific. */	2256	/* NTFS 3.0+ specific. */
2257	if (vol->major_ver >= 3) {	2257	if (vol->major_ver >= 3) {
2258	if (vol->usnjrnl_j_ino)	2258	if (vol->usnjrnl_j_ino)
2259	ntfs_commit_inode(vol->usnjrnl_j_ino);	2259	ntfs_commit_inode(vol->usnjrnl_j_ino);
2260	if (vol->usnjrnl_max_ino)	2260	if (vol->usnjrnl_max_ino)
2261	ntfs_commit_inode(vol->usnjrnl_max_ino);	2261	ntfs_commit_inode(vol->usnjrnl_max_ino);
2262	if (vol->usnjrnl_ino)	2262	if (vol->usnjrnl_ino)
2263	ntfs_commit_inode(vol->usnjrnl_ino);	2263	ntfs_commit_inode(vol->usnjrnl_ino);
2264	if (vol->quota_q_ino)	2264	if (vol->quota_q_ino)
2265	ntfs_commit_inode(vol->quota_q_ino);	2265	ntfs_commit_inode(vol->quota_q_ino);
2266	if (vol->quota_ino)	2266	if (vol->quota_ino)
2267	ntfs_commit_inode(vol->quota_ino);	2267	ntfs_commit_inode(vol->quota_ino);
2268	if (vol->extend_ino)	2268	if (vol->extend_ino)
2269	ntfs_commit_inode(vol->extend_ino);	2269	ntfs_commit_inode(vol->extend_ino);
2270	if (vol->secure_ino)	2270	if (vol->secure_ino)
2271	ntfs_commit_inode(vol->secure_ino);	2271	ntfs_commit_inode(vol->secure_ino);
2272	}	2272	}
2273		2273
2274	ntfs_commit_inode(vol->root_ino);	2274	ntfs_commit_inode(vol->root_ino);
2275		2275
2276	down_write(&vol->lcnbmp_lock);	2276	down_write(&vol->lcnbmp_lock);
2277	ntfs_commit_inode(vol->lcnbmp_ino);	2277	ntfs_commit_inode(vol->lcnbmp_ino);
2278	up_write(&vol->lcnbmp_lock);	2278	up_write(&vol->lcnbmp_lock);
2279		2279
2280	down_write(&vol->mftbmp_lock);	2280	down_write(&vol->mftbmp_lock);
2281	ntfs_commit_inode(vol->mftbmp_ino);	2281	ntfs_commit_inode(vol->mftbmp_ino);
2282	up_write(&vol->mftbmp_lock);	2282	up_write(&vol->mftbmp_lock);
2283		2283
2284	if (vol->logfile_ino)	2284	if (vol->logfile_ino)
2285	ntfs_commit_inode(vol->logfile_ino);	2285	ntfs_commit_inode(vol->logfile_ino);
2286		2286
2287	if (vol->mftmirr_ino)	2287	if (vol->mftmirr_ino)
2288	ntfs_commit_inode(vol->mftmirr_ino);	2288	ntfs_commit_inode(vol->mftmirr_ino);
2289	ntfs_commit_inode(vol->mft_ino);	2289	ntfs_commit_inode(vol->mft_ino);
2290		2290
2291	/*	2291	/*
2292	* If a read-write mount and no volume errors have occured, mark the	2292	* If a read-write mount and no volume errors have occured, mark the
2293	* volume clean. Also, re-commit all affected inodes.	2293	* volume clean. Also, re-commit all affected inodes.
2294	*/	2294	*/
2295	if (!(sb->s_flags & MS_RDONLY)) {	2295	if (!(sb->s_flags & MS_RDONLY)) {
2296	if (!NVolErrors(vol)) {	2296	if (!NVolErrors(vol)) {
2297	if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))	2297	if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
2298	ntfs_warning(sb, "Failed to clear dirty bit "	2298	ntfs_warning(sb, "Failed to clear dirty bit "
2299	"in volume information "	2299	"in volume information "
2300	"flags. Run chkdsk.");	2300	"flags. Run chkdsk.");
2301	ntfs_commit_inode(vol->vol_ino);	2301	ntfs_commit_inode(vol->vol_ino);
2302	ntfs_commit_inode(vol->root_ino);	2302	ntfs_commit_inode(vol->root_ino);
2303	if (vol->mftmirr_ino)	2303	if (vol->mftmirr_ino)
2304	ntfs_commit_inode(vol->mftmirr_ino);	2304	ntfs_commit_inode(vol->mftmirr_ino);
2305	ntfs_commit_inode(vol->mft_ino);	2305	ntfs_commit_inode(vol->mft_ino);
2306	} else {	2306	} else {
2307	ntfs_warning(sb, "Volume has errors. Leaving volume "	2307	ntfs_warning(sb, "Volume has errors. Leaving volume "
2308	"marked dirty. Run chkdsk.");	2308	"marked dirty. Run chkdsk.");
2309	}	2309	}
2310	}	2310	}
2311	#endif /* NTFS_RW */	2311	#endif /* NTFS_RW */
2312		2312
2313	iput(vol->vol_ino);	2313	iput(vol->vol_ino);
2314	vol->vol_ino = NULL;	2314	vol->vol_ino = NULL;
2315		2315
2316	/* NTFS 3.0+ specific clean up. */	2316	/* NTFS 3.0+ specific clean up. */
2317	if (vol->major_ver >= 3) {	2317	if (vol->major_ver >= 3) {
2318	#ifdef NTFS_RW	2318	#ifdef NTFS_RW
2319	if (vol->usnjrnl_j_ino) {	2319	if (vol->usnjrnl_j_ino) {
2320	iput(vol->usnjrnl_j_ino);	2320	iput(vol->usnjrnl_j_ino);
2321	vol->usnjrnl_j_ino = NULL;	2321	vol->usnjrnl_j_ino = NULL;
2322	}	2322	}
2323	if (vol->usnjrnl_max_ino) {	2323	if (vol->usnjrnl_max_ino) {
2324	iput(vol->usnjrnl_max_ino);	2324	iput(vol->usnjrnl_max_ino);
2325	vol->usnjrnl_max_ino = NULL;	2325	vol->usnjrnl_max_ino = NULL;
2326	}	2326	}
2327	if (vol->usnjrnl_ino) {	2327	if (vol->usnjrnl_ino) {
2328	iput(vol->usnjrnl_ino);	2328	iput(vol->usnjrnl_ino);
2329	vol->usnjrnl_ino = NULL;	2329	vol->usnjrnl_ino = NULL;
2330	}	2330	}
2331	if (vol->quota_q_ino) {	2331	if (vol->quota_q_ino) {
2332	iput(vol->quota_q_ino);	2332	iput(vol->quota_q_ino);
2333	vol->quota_q_ino = NULL;	2333	vol->quota_q_ino = NULL;
2334	}	2334	}
2335	if (vol->quota_ino) {	2335	if (vol->quota_ino) {
2336	iput(vol->quota_ino);	2336	iput(vol->quota_ino);
2337	vol->quota_ino = NULL;	2337	vol->quota_ino = NULL;
2338	}	2338	}
2339	#endif /* NTFS_RW */	2339	#endif /* NTFS_RW */
2340	if (vol->extend_ino) {	2340	if (vol->extend_ino) {
2341	iput(vol->extend_ino);	2341	iput(vol->extend_ino);
2342	vol->extend_ino = NULL;	2342	vol->extend_ino = NULL;
2343	}	2343	}
2344	if (vol->secure_ino) {	2344	if (vol->secure_ino) {
2345	iput(vol->secure_ino);	2345	iput(vol->secure_ino);
2346	vol->secure_ino = NULL;	2346	vol->secure_ino = NULL;
2347	}	2347	}
2348	}	2348	}
2349		2349
2350	iput(vol->root_ino);	2350	iput(vol->root_ino);
2351	vol->root_ino = NULL;	2351	vol->root_ino = NULL;
2352		2352
2353	down_write(&vol->lcnbmp_lock);	2353	down_write(&vol->lcnbmp_lock);
2354	iput(vol->lcnbmp_ino);	2354	iput(vol->lcnbmp_ino);
2355	vol->lcnbmp_ino = NULL;	2355	vol->lcnbmp_ino = NULL;
2356	up_write(&vol->lcnbmp_lock);	2356	up_write(&vol->lcnbmp_lock);
2357		2357
2358	down_write(&vol->mftbmp_lock);	2358	down_write(&vol->mftbmp_lock);
2359	iput(vol->mftbmp_ino);	2359	iput(vol->mftbmp_ino);
2360	vol->mftbmp_ino = NULL;	2360	vol->mftbmp_ino = NULL;
2361	up_write(&vol->mftbmp_lock);	2361	up_write(&vol->mftbmp_lock);
2362		2362
2363	#ifdef NTFS_RW	2363	#ifdef NTFS_RW
2364	if (vol->logfile_ino) {	2364	if (vol->logfile_ino) {
2365	iput(vol->logfile_ino);	2365	iput(vol->logfile_ino);
2366	vol->logfile_ino = NULL;	2366	vol->logfile_ino = NULL;
2367	}	2367	}
2368	if (vol->mftmirr_ino) {	2368	if (vol->mftmirr_ino) {
2369	/* Re-commit the mft mirror and mft just in case. */	2369	/* Re-commit the mft mirror and mft just in case. */
2370	ntfs_commit_inode(vol->mftmirr_ino);	2370	ntfs_commit_inode(vol->mftmirr_ino);
2371	ntfs_commit_inode(vol->mft_ino);	2371	ntfs_commit_inode(vol->mft_ino);
2372	iput(vol->mftmirr_ino);	2372	iput(vol->mftmirr_ino);
2373	vol->mftmirr_ino = NULL;	2373	vol->mftmirr_ino = NULL;
2374	}	2374	}
2375	/*	2375	/*
2376	* If any dirty inodes are left, throw away all mft data page cache	2376	* If any dirty inodes are left, throw away all mft data page cache
2377	* pages to allow a clean umount. This should never happen any more	2377	* pages to allow a clean umount. This should never happen any more
2378	* due to mft.c::ntfs_mft_writepage() cleaning all the dirty pages as	2378	* due to mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
2379	* the underlying mft records are written out and cleaned. If it does,	2379	* the underlying mft records are written out and cleaned. If it does,
2380	* happen anyway, we want to know...	2380	* happen anyway, we want to know...
2381	*/	2381	*/
2382	ntfs_commit_inode(vol->mft_ino);	2382	ntfs_commit_inode(vol->mft_ino);
2383	write_inode_now(vol->mft_ino, 1);	2383	write_inode_now(vol->mft_ino, 1);
2384	if (!list_empty(&sb->s_dirty)) {	2384	if (sb_has_dirty_inodes(sb)) {
2385	const char s1, s2;	2385	const char s1, s2;
2386		2386
2387	mutex_lock(&vol->mft_ino->i_mutex);	2387	mutex_lock(&vol->mft_ino->i_mutex);
2388	truncate_inode_pages(vol->mft_ino->i_mapping, 0);	2388	truncate_inode_pages(vol->mft_ino->i_mapping, 0);
2389	mutex_unlock(&vol->mft_ino->i_mutex);	2389	mutex_unlock(&vol->mft_ino->i_mutex);
2390	write_inode_now(vol->mft_ino, 1);	2390	write_inode_now(vol->mft_ino, 1);
2391	if (!list_empty(&sb->s_dirty)) {	2391	if (sb_has_dirty_inodes(sb)) {
2392	static const char *_s1 = "inodes";	2392	static const char *_s1 = "inodes";
2393	static const char *_s2 = "";	2393	static const char *_s2 = "";
2394	s1 = _s1;	2394	s1 = _s1;
2395	s2 = _s2;	2395	s2 = _s2;
2396	} else {	2396	} else {
2397	static const char *_s1 = "mft pages";	2397	static const char *_s1 = "mft pages";
2398	static const char *_s2 = "They have been thrown "	2398	static const char *_s2 = "They have been thrown "
2399	"away. ";	2399	"away. ";
2400	s1 = _s1;	2400	s1 = _s1;
2401	s2 = _s2;	2401	s2 = _s2;
2402	}	2402	}
2403	ntfs_error(sb, "Dirty %s found at umount time. %sYou should "	2403	ntfs_error(sb, "Dirty %s found at umount time. %sYou should "
2404	"run chkdsk. Please email "	2404	"run chkdsk. Please email "
2405	"linux-ntfs-dev@lists.sourceforge.net and say "	2405	"linux-ntfs-dev@lists.sourceforge.net and say "
2406	"that you saw this message. Thank you.", s1,	2406	"that you saw this message. Thank you.", s1,
2407	s2);	2407	s2);
2408	}	2408	}
2409	#endif /* NTFS_RW */	2409	#endif /* NTFS_RW */
2410		2410
2411	iput(vol->mft_ino);	2411	iput(vol->mft_ino);
2412	vol->mft_ino = NULL;	2412	vol->mft_ino = NULL;
2413		2413
2414	/* Throw away the table of attribute definitions. */	2414	/* Throw away the table of attribute definitions. */
2415	vol->attrdef_size = 0;	2415	vol->attrdef_size = 0;
2416	if (vol->attrdef) {	2416	if (vol->attrdef) {
2417	ntfs_free(vol->attrdef);	2417	ntfs_free(vol->attrdef);
2418	vol->attrdef = NULL;	2418	vol->attrdef = NULL;
2419	}	2419	}
2420	vol->upcase_len = 0;	2420	vol->upcase_len = 0;
2421	/*	2421	/*
2422	* Destroy the global default upcase table if necessary. Also decrease	2422	* Destroy the global default upcase table if necessary. Also decrease
2423	* the number of upcase users if we are a user.	2423	* the number of upcase users if we are a user.
2424	*/	2424	*/
2425	mutex_lock(&ntfs_lock);	2425	mutex_lock(&ntfs_lock);
2426	if (vol->upcase == default_upcase) {	2426	if (vol->upcase == default_upcase) {
2427	ntfs_nr_upcase_users--;	2427	ntfs_nr_upcase_users--;
2428	vol->upcase = NULL;	2428	vol->upcase = NULL;
2429	}	2429	}
2430	if (!ntfs_nr_upcase_users && default_upcase) {	2430	if (!ntfs_nr_upcase_users && default_upcase) {
2431	ntfs_free(default_upcase);	2431	ntfs_free(default_upcase);
2432	default_upcase = NULL;	2432	default_upcase = NULL;
2433	}	2433	}
2434	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)	2434	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
2435	free_compression_buffers();	2435	free_compression_buffers();
2436	mutex_unlock(&ntfs_lock);	2436	mutex_unlock(&ntfs_lock);
2437	if (vol->upcase) {	2437	if (vol->upcase) {
2438	ntfs_free(vol->upcase);	2438	ntfs_free(vol->upcase);
2439	vol->upcase = NULL;	2439	vol->upcase = NULL;
2440	}	2440	}
2441	if (vol->nls_map) {	2441	if (vol->nls_map) {
2442	unload_nls(vol->nls_map);	2442	unload_nls(vol->nls_map);
2443	vol->nls_map = NULL;	2443	vol->nls_map = NULL;
2444	}	2444	}
2445	sb->s_fs_info = NULL;	2445	sb->s_fs_info = NULL;
2446	kfree(vol);	2446	kfree(vol);
2447	return;	2447	return;
2448	}	2448	}
2449		2449
2450	/**	2450	/**
2451	* get_nr_free_clusters - return the number of free clusters on a volume	2451	* get_nr_free_clusters - return the number of free clusters on a volume
2452	* @vol: ntfs volume for which to obtain free cluster count	2452	* @vol: ntfs volume for which to obtain free cluster count
2453	*	2453	*
2454	* Calculate the number of free clusters on the mounted NTFS volume @vol. We	2454	* Calculate the number of free clusters on the mounted NTFS volume @vol. We
2455	* actually calculate the number of clusters in use instead because this	2455	* actually calculate the number of clusters in use instead because this
2456	* allows us to not care about partial pages as these will be just zero filled	2456	* allows us to not care about partial pages as these will be just zero filled
2457	* and hence not be counted as allocated clusters.	2457	* and hence not be counted as allocated clusters.
2458	*	2458	*
2459	* The only particularity is that clusters beyond the end of the logical ntfs	2459	* The only particularity is that clusters beyond the end of the logical ntfs
2460	* volume will be marked as allocated to prevent errors which means we have to	2460	* volume will be marked as allocated to prevent errors which means we have to
2461	* discount those at the end. This is important as the cluster bitmap always	2461	* discount those at the end. This is important as the cluster bitmap always
2462	* has a size in multiples of 8 bytes, i.e. up to 63 clusters could be outside	2462	* has a size in multiples of 8 bytes, i.e. up to 63 clusters could be outside
2463	* the logical volume and marked in use when they are not as they do not exist.	2463	* the logical volume and marked in use when they are not as they do not exist.
2464	*	2464	*
2465	* If any pages cannot be read we assume all clusters in the erroring pages are	2465	* If any pages cannot be read we assume all clusters in the erroring pages are
2466	* in use. This means we return an underestimate on errors which is better than	2466	* in use. This means we return an underestimate on errors which is better than
2467	* an overestimate.	2467	* an overestimate.
2468	*/	2468	*/
2469	static s64 get_nr_free_clusters(ntfs_volume *vol)	2469	static s64 get_nr_free_clusters(ntfs_volume *vol)
2470	{	2470	{
2471	s64 nr_free = vol->nr_clusters;	2471	s64 nr_free = vol->nr_clusters;
2472	u32 *kaddr;	2472	u32 *kaddr;
2473	struct address_space *mapping = vol->lcnbmp_ino->i_mapping;	2473	struct address_space *mapping = vol->lcnbmp_ino->i_mapping;
2474	struct page *page;	2474	struct page *page;
2475	pgoff_t index, max_index;	2475	pgoff_t index, max_index;
2476		2476
2477	ntfs_debug("Entering.");	2477	ntfs_debug("Entering.");
2478	/* Serialize accesses to the cluster bitmap. */	2478	/* Serialize accesses to the cluster bitmap. */
2479	down_read(&vol->lcnbmp_lock);	2479	down_read(&vol->lcnbmp_lock);
2480	/*	2480	/*
2481	* Convert the number of bits into bytes rounded up, then convert into	2481	* Convert the number of bits into bytes rounded up, then convert into
2482	* multiples of PAGE_CACHE_SIZE, rounding up so that if we have one	2482	* multiples of PAGE_CACHE_SIZE, rounding up so that if we have one
2483	* full and one partial page max_index = 2.	2483	* full and one partial page max_index = 2.
2484	*/	2484	*/
2485	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_CACHE_SIZE - 1) >>	2485	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_CACHE_SIZE - 1) >>
2486	PAGE_CACHE_SHIFT;	2486	PAGE_CACHE_SHIFT;
2487	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */	2487	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
2488	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.",	2488	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.",
2489	max_index, PAGE_CACHE_SIZE / 4);	2489	max_index, PAGE_CACHE_SIZE / 4);
2490	for (index = 0; index < max_index; index++) {	2490	for (index = 0; index < max_index; index++) {
2491	unsigned int i;	2491	unsigned int i;
2492	/*	2492	/*
2493	* Read the page from page cache, getting it from backing store	2493	* Read the page from page cache, getting it from backing store
2494	* if necessary, and increment the use count.	2494	* if necessary, and increment the use count.
2495	*/	2495	*/
2496	page = read_mapping_page(mapping, index, NULL);	2496	page = read_mapping_page(mapping, index, NULL);
2497	/* Ignore pages which errored synchronously. */	2497	/* Ignore pages which errored synchronously. */
2498	if (IS_ERR(page)) {	2498	if (IS_ERR(page)) {
2499	ntfs_debug("read_mapping_page() error. Skipping "	2499	ntfs_debug("read_mapping_page() error. Skipping "
2500	"page (index 0x%lx).", index);	2500	"page (index 0x%lx).", index);
2501	nr_free -= PAGE_CACHE_SIZE * 8;	2501	nr_free -= PAGE_CACHE_SIZE * 8;
2502	continue;	2502	continue;
2503	}	2503	}
2504	kaddr = (u32*)kmap_atomic(page, KM_USER0);	2504	kaddr = (u32*)kmap_atomic(page, KM_USER0);
2505	/*	2505	/*
2506	* For each 4 bytes, subtract the number of set bits. If this	2506	* For each 4 bytes, subtract the number of set bits. If this
2507	* is the last page and it is partial we don't really care as	2507	* is the last page and it is partial we don't really care as
2508	* it just means we do a little extra work but it won't affect	2508	* it just means we do a little extra work but it won't affect
2509	* the result as all out of range bytes are set to zero by	2509	* the result as all out of range bytes are set to zero by
2510	* ntfs_readpage().	2510	* ntfs_readpage().
2511	*/	2511	*/
2512	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)	2512	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)
2513	nr_free -= (s64)hweight32(kaddr[i]);	2513	nr_free -= (s64)hweight32(kaddr[i]);
2514	kunmap_atomic(kaddr, KM_USER0);	2514	kunmap_atomic(kaddr, KM_USER0);
2515	page_cache_release(page);	2515	page_cache_release(page);
2516	}	2516	}
2517	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);	2517	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
2518	/*	2518	/*
2519	* Fixup for eventual bits outside logical ntfs volume (see function	2519	* Fixup for eventual bits outside logical ntfs volume (see function
2520	* description above).	2520	* description above).
2521	*/	2521	*/
2522	if (vol->nr_clusters & 63)	2522	if (vol->nr_clusters & 63)
2523	nr_free += 64 - (vol->nr_clusters & 63);	2523	nr_free += 64 - (vol->nr_clusters & 63);
2524	up_read(&vol->lcnbmp_lock);	2524	up_read(&vol->lcnbmp_lock);
2525	/* If errors occured we may well have gone below zero, fix this. */	2525	/* If errors occured we may well have gone below zero, fix this. */
2526	if (nr_free < 0)	2526	if (nr_free < 0)
2527	nr_free = 0;	2527	nr_free = 0;
2528	ntfs_debug("Exiting.");	2528	ntfs_debug("Exiting.");
2529	return nr_free;	2529	return nr_free;
2530	}	2530	}
2531		2531
2532	/**	2532	/**
2533	* __get_nr_free_mft_records - return the number of free inodes on a volume	2533	* __get_nr_free_mft_records - return the number of free inodes on a volume
2534	* @vol: ntfs volume for which to obtain free inode count	2534	* @vol: ntfs volume for which to obtain free inode count
2535	* @nr_free: number of mft records in filesystem	2535	* @nr_free: number of mft records in filesystem
2536	* @max_index: maximum number of pages containing set bits	2536	* @max_index: maximum number of pages containing set bits
2537	*	2537	*
2538	* Calculate the number of free mft records (inodes) on the mounted NTFS	2538	* Calculate the number of free mft records (inodes) on the mounted NTFS
2539	* volume @vol. We actually calculate the number of mft records in use instead	2539	* volume @vol. We actually calculate the number of mft records in use instead
2540	* because this allows us to not care about partial pages as these will be just	2540	* because this allows us to not care about partial pages as these will be just
2541	* zero filled and hence not be counted as allocated mft record.	2541	* zero filled and hence not be counted as allocated mft record.
2542	*	2542	*
2543	* If any pages cannot be read we assume all mft records in the erroring pages	2543	* If any pages cannot be read we assume all mft records in the erroring pages
2544	* are in use. This means we return an underestimate on errors which is better	2544	* are in use. This means we return an underestimate on errors which is better
2545	* than an overestimate.	2545	* than an overestimate.
2546	*	2546	*
2547	* NOTE: Caller must hold mftbmp_lock rw_semaphore for reading or writing.	2547	* NOTE: Caller must hold mftbmp_lock rw_semaphore for reading or writing.
2548	*/	2548	*/
2549	static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,	2549	static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
2550	s64 nr_free, const pgoff_t max_index)	2550	s64 nr_free, const pgoff_t max_index)
2551	{	2551	{
2552	u32 *kaddr;	2552	u32 *kaddr;
2553	struct address_space *mapping = vol->mftbmp_ino->i_mapping;	2553	struct address_space *mapping = vol->mftbmp_ino->i_mapping;
2554	struct page *page;	2554	struct page *page;
2555	pgoff_t index;	2555	pgoff_t index;
2556		2556
2557	ntfs_debug("Entering.");	2557	ntfs_debug("Entering.");
2558	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */	2558	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
2559	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "	2559	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
2560	"0x%lx.", max_index, PAGE_CACHE_SIZE / 4);	2560	"0x%lx.", max_index, PAGE_CACHE_SIZE / 4);
2561	for (index = 0; index < max_index; index++) {	2561	for (index = 0; index < max_index; index++) {
2562	unsigned int i;	2562	unsigned int i;
2563	/*	2563	/*
2564	* Read the page from page cache, getting it from backing store	2564	* Read the page from page cache, getting it from backing store
2565	* if necessary, and increment the use count.	2565	* if necessary, and increment the use count.
2566	*/	2566	*/
2567	page = read_mapping_page(mapping, index, NULL);	2567	page = read_mapping_page(mapping, index, NULL);
2568	/* Ignore pages which errored synchronously. */	2568	/* Ignore pages which errored synchronously. */
2569	if (IS_ERR(page)) {	2569	if (IS_ERR(page)) {
2570	ntfs_debug("read_mapping_page() error. Skipping "	2570	ntfs_debug("read_mapping_page() error. Skipping "
2571	"page (index 0x%lx).", index);	2571	"page (index 0x%lx).", index);
2572	nr_free -= PAGE_CACHE_SIZE * 8;	2572	nr_free -= PAGE_CACHE_SIZE * 8;
2573	continue;	2573	continue;
2574	}	2574	}
2575	kaddr = (u32*)kmap_atomic(page, KM_USER0);	2575	kaddr = (u32*)kmap_atomic(page, KM_USER0);
2576	/*	2576	/*
2577	* For each 4 bytes, subtract the number of set bits. If this	2577	* For each 4 bytes, subtract the number of set bits. If this
2578	* is the last page and it is partial we don't really care as	2578	* is the last page and it is partial we don't really care as
2579	* it just means we do a little extra work but it won't affect	2579	* it just means we do a little extra work but it won't affect
2580	* the result as all out of range bytes are set to zero by	2580	* the result as all out of range bytes are set to zero by
2581	* ntfs_readpage().	2581	* ntfs_readpage().
2582	*/	2582	*/
2583	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)	2583	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)
2584	nr_free -= (s64)hweight32(kaddr[i]);	2584	nr_free -= (s64)hweight32(kaddr[i]);
2585	kunmap_atomic(kaddr, KM_USER0);	2585	kunmap_atomic(kaddr, KM_USER0);
2586	page_cache_release(page);	2586	page_cache_release(page);
2587	}	2587	}
2588	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",	2588	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
2589	index - 1);	2589	index - 1);
2590	/* If errors occured we may well have gone below zero, fix this. */	2590	/* If errors occured we may well have gone below zero, fix this. */
2591	if (nr_free < 0)	2591	if (nr_free < 0)
2592	nr_free = 0;	2592	nr_free = 0;
2593	ntfs_debug("Exiting.");	2593	ntfs_debug("Exiting.");
2594	return nr_free;	2594	return nr_free;
2595	}	2595	}
2596		2596
2597	/**	2597	/**
2598	* ntfs_statfs - return information about mounted NTFS volume	2598	* ntfs_statfs - return information about mounted NTFS volume
2599	* @dentry: dentry from mounted volume	2599	* @dentry: dentry from mounted volume
2600	* @sfs: statfs structure in which to return the information	2600	* @sfs: statfs structure in which to return the information
2601	*	2601	*
2602	* Return information about the mounted NTFS volume @dentry in the statfs structure	2602	* Return information about the mounted NTFS volume @dentry in the statfs structure
2603	* pointed to by @sfs (this is initialized with zeros before ntfs_statfs is	2603	* pointed to by @sfs (this is initialized with zeros before ntfs_statfs is
2604	* called). We interpret the values to be correct of the moment in time at	2604	* called). We interpret the values to be correct of the moment in time at
2605	* which we are called. Most values are variable otherwise and this isn't just	2605	* which we are called. Most values are variable otherwise and this isn't just
2606	* the free values but the totals as well. For example we can increase the	2606	* the free values but the totals as well. For example we can increase the
2607	* total number of file nodes if we run out and we can keep doing this until	2607	* total number of file nodes if we run out and we can keep doing this until
2608	* there is no more space on the volume left at all.	2608	* there is no more space on the volume left at all.
2609	*	2609	*
2610	* Called from vfs_statfs which is used to handle the statfs, fstatfs, and	2610	* Called from vfs_statfs which is used to handle the statfs, fstatfs, and
2611	* ustat system calls.	2611	* ustat system calls.
2612	*	2612	*
2613	* Return 0 on success or -errno on error.	2613	* Return 0 on success or -errno on error.
2614	*/	2614	*/
2615	static int ntfs_statfs(struct dentry dentry, struct kstatfs sfs)	2615	static int ntfs_statfs(struct dentry dentry, struct kstatfs sfs)
2616	{	2616	{
2617	struct super_block *sb = dentry->d_sb;	2617	struct super_block *sb = dentry->d_sb;
2618	s64 size;	2618	s64 size;
2619	ntfs_volume *vol = NTFS_SB(sb);	2619	ntfs_volume *vol = NTFS_SB(sb);
2620	ntfs_inode *mft_ni = NTFS_I(vol->mft_ino);	2620	ntfs_inode *mft_ni = NTFS_I(vol->mft_ino);
2621	pgoff_t max_index;	2621	pgoff_t max_index;
2622	unsigned long flags;	2622	unsigned long flags;
2623		2623
2624	ntfs_debug("Entering.");	2624	ntfs_debug("Entering.");
2625	/* Type of filesystem. */	2625	/* Type of filesystem. */
2626	sfs->f_type = NTFS_SB_MAGIC;	2626	sfs->f_type = NTFS_SB_MAGIC;
2627	/* Optimal transfer block size. */	2627	/* Optimal transfer block size. */
2628	sfs->f_bsize = PAGE_CACHE_SIZE;	2628	sfs->f_bsize = PAGE_CACHE_SIZE;
2629	/*	2629	/*
2630	* Total data blocks in filesystem in units of f_bsize and since	2630	* Total data blocks in filesystem in units of f_bsize and since
2631	* inodes are also stored in data blocs ($MFT is a file) this is just	2631	* inodes are also stored in data blocs ($MFT is a file) this is just
2632	* the total clusters.	2632	* the total clusters.
2633	*/	2633	*/
2634	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>	2634	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>
2635	PAGE_CACHE_SHIFT;	2635	PAGE_CACHE_SHIFT;
2636	/* Free data blocks in filesystem in units of f_bsize. */	2636	/* Free data blocks in filesystem in units of f_bsize. */
2637	size = get_nr_free_clusters(vol) << vol->cluster_size_bits >>	2637	size = get_nr_free_clusters(vol) << vol->cluster_size_bits >>
2638	PAGE_CACHE_SHIFT;	2638	PAGE_CACHE_SHIFT;
2639	if (size < 0LL)	2639	if (size < 0LL)
2640	size = 0LL;	2640	size = 0LL;
2641	/* Free blocks avail to non-superuser, same as above on NTFS. */	2641	/* Free blocks avail to non-superuser, same as above on NTFS. */
2642	sfs->f_bavail = sfs->f_bfree = size;	2642	sfs->f_bavail = sfs->f_bfree = size;
2643	/* Serialize accesses to the inode bitmap. */	2643	/* Serialize accesses to the inode bitmap. */
2644	down_read(&vol->mftbmp_lock);	2644	down_read(&vol->mftbmp_lock);
2645	read_lock_irqsave(&mft_ni->size_lock, flags);	2645	read_lock_irqsave(&mft_ni->size_lock, flags);
2646	size = i_size_read(vol->mft_ino) >> vol->mft_record_size_bits;	2646	size = i_size_read(vol->mft_ino) >> vol->mft_record_size_bits;
2647	/*	2647	/*
2648	* Convert the maximum number of set bits into bytes rounded up, then	2648	* Convert the maximum number of set bits into bytes rounded up, then
2649	* convert into multiples of PAGE_CACHE_SIZE, rounding up so that if we	2649	* convert into multiples of PAGE_CACHE_SIZE, rounding up so that if we
2650	* have one full and one partial page max_index = 2.	2650	* have one full and one partial page max_index = 2.
2651	*/	2651	*/
2652	max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits)	2652	max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits)
2653	+ 7) >> 3) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;	2653	+ 7) >> 3) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
2654	read_unlock_irqrestore(&mft_ni->size_lock, flags);	2654	read_unlock_irqrestore(&mft_ni->size_lock, flags);
2655	/* Number of inodes in filesystem (at this point in time). */	2655	/* Number of inodes in filesystem (at this point in time). */
2656	sfs->f_files = size;	2656	sfs->f_files = size;
2657	/* Free inodes in fs (based on current total count). */	2657	/* Free inodes in fs (based on current total count). */
2658	sfs->f_ffree = __get_nr_free_mft_records(vol, size, max_index);	2658	sfs->f_ffree = __get_nr_free_mft_records(vol, size, max_index);
2659	up_read(&vol->mftbmp_lock);	2659	up_read(&vol->mftbmp_lock);
2660	/*	2660	/*
2661	* File system id. This is extremely *nix flavour dependent and even	2661	* File system id. This is extremely *nix flavour dependent and even
2662	* within Linux itself all fs do their own thing. I interpret this to	2662	* within Linux itself all fs do their own thing. I interpret this to
2663	* mean a unique id associated with the mounted fs and not the id	2663	* mean a unique id associated with the mounted fs and not the id
2664	* associated with the filesystem driver, the latter is already given	2664	* associated with the filesystem driver, the latter is already given
2665	* by the filesystem type in sfs->f_type. Thus we use the 64-bit	2665	* by the filesystem type in sfs->f_type. Thus we use the 64-bit
2666	* volume serial number splitting it into two 32-bit parts. We enter	2666	* volume serial number splitting it into two 32-bit parts. We enter
2667	* the least significant 32-bits in f_fsid[0] and the most significant	2667	* the least significant 32-bits in f_fsid[0] and the most significant
2668	* 32-bits in f_fsid[1].	2668	* 32-bits in f_fsid[1].
2669	*/	2669	*/
2670	sfs->f_fsid.val[0] = vol->serial_no & 0xffffffff;	2670	sfs->f_fsid.val[0] = vol->serial_no & 0xffffffff;
2671	sfs->f_fsid.val[1] = (vol->serial_no >> 32) & 0xffffffff;	2671	sfs->f_fsid.val[1] = (vol->serial_no >> 32) & 0xffffffff;
2672	/* Maximum length of filenames. */	2672	/* Maximum length of filenames. */
2673	sfs->f_namelen = NTFS_MAX_NAME_LEN;	2673	sfs->f_namelen = NTFS_MAX_NAME_LEN;
2674	return 0;	2674	return 0;
2675	}	2675	}
2676		2676
2677	/**	2677	/**
2678	* The complete super operations.	2678	* The complete super operations.
2679	*/	2679	*/
2680	static const struct super_operations ntfs_sops = {	2680	static const struct super_operations ntfs_sops = {
2681	.alloc_inode = ntfs_alloc_big_inode, /* VFS: Allocate new inode. */	2681	.alloc_inode = ntfs_alloc_big_inode, /* VFS: Allocate new inode. */
2682	.destroy_inode = ntfs_destroy_big_inode, /* VFS: Deallocate inode. */	2682	.destroy_inode = ntfs_destroy_big_inode, /* VFS: Deallocate inode. */
2683	#ifdef NTFS_RW	2683	#ifdef NTFS_RW
2684	//.dirty_inode = NULL, /* VFS: Called from	2684	//.dirty_inode = NULL, /* VFS: Called from
2685	// __mark_inode_dirty(). */	2685	// __mark_inode_dirty(). */
2686	.write_inode = ntfs_write_inode, /* VFS: Write dirty inode to	2686	.write_inode = ntfs_write_inode, /* VFS: Write dirty inode to
2687	disk. */	2687	disk. */
2688	//.drop_inode = NULL, /* VFS: Called just after the	2688	//.drop_inode = NULL, /* VFS: Called just after the
2689	// inode reference count has	2689	// inode reference count has
2690	// been decreased to zero.	2690	// been decreased to zero.
2691	// NOTE: The inode lock is	2691	// NOTE: The inode lock is
2692	// held. See fs/inode.c::	2692	// held. See fs/inode.c::
2693	// generic_drop_inode(). */	2693	// generic_drop_inode(). */
2694	//.delete_inode = NULL, /* VFS: Delete inode from disk.	2694	//.delete_inode = NULL, /* VFS: Delete inode from disk.
2695	// Called when i_count becomes	2695	// Called when i_count becomes
2696	// 0 and i_nlink is also 0. */	2696	// 0 and i_nlink is also 0. */
2697	//.write_super = NULL, /* Flush dirty super block to	2697	//.write_super = NULL, /* Flush dirty super block to
2698	// disk. */	2698	// disk. */
2699	//.sync_fs = NULL, /* ? */	2699	//.sync_fs = NULL, /* ? */
2700	//.write_super_lockfs = NULL, /* ? */	2700	//.write_super_lockfs = NULL, /* ? */
2701	//.unlockfs = NULL, /* ? */	2701	//.unlockfs = NULL, /* ? */
2702	#endif /* NTFS_RW */	2702	#endif /* NTFS_RW */
2703	.put_super = ntfs_put_super, /* Syscall: umount. */	2703	.put_super = ntfs_put_super, /* Syscall: umount. */
2704	.statfs = ntfs_statfs, /* Syscall: statfs */	2704	.statfs = ntfs_statfs, /* Syscall: statfs */
2705	.remount_fs = ntfs_remount, /* Syscall: mount -o remount. */	2705	.remount_fs = ntfs_remount, /* Syscall: mount -o remount. */
2706	.clear_inode = ntfs_clear_big_inode, /* VFS: Called when an inode is	2706	.clear_inode = ntfs_clear_big_inode, /* VFS: Called when an inode is
2707	removed from memory. */	2707	removed from memory. */
2708	//.umount_begin = NULL, /* Forced umount. */	2708	//.umount_begin = NULL, /* Forced umount. */
2709	.show_options = ntfs_show_options, /* Show mount options in	2709	.show_options = ntfs_show_options, /* Show mount options in
2710	proc. */	2710	proc. */
2711	};	2711	};
2712		2712
2713	/**	2713	/**
2714	* ntfs_fill_super - mount an ntfs filesystem	2714	* ntfs_fill_super - mount an ntfs filesystem
2715	* @sb: super block of ntfs filesystem to mount	2715	* @sb: super block of ntfs filesystem to mount
2716	* @opt: string containing the mount options	2716	* @opt: string containing the mount options
2717	* @silent: silence error output	2717	* @silent: silence error output
2718	*	2718	*
2719	* ntfs_fill_super() is called by the VFS to mount the device described by @sb	2719	* ntfs_fill_super() is called by the VFS to mount the device described by @sb
2720	* with the mount otions in @data with the NTFS filesystem.	2720	* with the mount otions in @data with the NTFS filesystem.
2721	*	2721	*
2722	* If @silent is true, remain silent even if errors are detected. This is used	2722	* If @silent is true, remain silent even if errors are detected. This is used
2723	* during bootup, when the kernel tries to mount the root filesystem with all	2723	* during bootup, when the kernel tries to mount the root filesystem with all
2724	* registered filesystems one after the other until one succeeds. This implies	2724	* registered filesystems one after the other until one succeeds. This implies
2725	* that all filesystems except the correct one will quite correctly and	2725	* that all filesystems except the correct one will quite correctly and
2726	* expectedly return an error, but nobody wants to see error messages when in	2726	* expectedly return an error, but nobody wants to see error messages when in
2727	* fact this is what is supposed to happen.	2727	* fact this is what is supposed to happen.
2728	*	2728	*
2729	* NOTE: @sb->s_flags contains the mount options flags.	2729	* NOTE: @sb->s_flags contains the mount options flags.
2730	*/	2730	*/
2731	static int ntfs_fill_super(struct super_block sb, void opt, const int silent)	2731	static int ntfs_fill_super(struct super_block sb, void opt, const int silent)
2732	{	2732	{
2733	ntfs_volume *vol;	2733	ntfs_volume *vol;
2734	struct buffer_head *bh;	2734	struct buffer_head *bh;
2735	struct inode *tmp_ino;	2735	struct inode *tmp_ino;
2736	int blocksize, result;	2736	int blocksize, result;
2737		2737
2738	/*	2738	/*
2739	* We do a pretty difficult piece of bootstrap by reading the	2739	* We do a pretty difficult piece of bootstrap by reading the
2740	* MFT (and other metadata) from disk into memory. We'll only	2740	* MFT (and other metadata) from disk into memory. We'll only
2741	* release this metadata during umount, so the locking patterns	2741	* release this metadata during umount, so the locking patterns
2742	* observed during bootstrap do not count. So turn off the	2742	* observed during bootstrap do not count. So turn off the
2743	* observation of locking patterns (strictly for this context	2743	* observation of locking patterns (strictly for this context
2744	* only) while mounting NTFS. [The validator is still active	2744	* only) while mounting NTFS. [The validator is still active
2745	* otherwise, even for this context: it will for example record	2745	* otherwise, even for this context: it will for example record
2746	* lock class registrations.]	2746	* lock class registrations.]
2747	*/	2747	*/
2748	lockdep_off();	2748	lockdep_off();
2749	ntfs_debug("Entering.");	2749	ntfs_debug("Entering.");
2750	#ifndef NTFS_RW	2750	#ifndef NTFS_RW
2751	sb->s_flags \|= MS_RDONLY;	2751	sb->s_flags \|= MS_RDONLY;
2752	#endif /* ! NTFS_RW */	2752	#endif /* ! NTFS_RW */
2753	/* Allocate a new ntfs_volume and place it in sb->s_fs_info. */	2753	/* Allocate a new ntfs_volume and place it in sb->s_fs_info. */
2754	sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS);	2754	sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS);
2755	vol = NTFS_SB(sb);	2755	vol = NTFS_SB(sb);
2756	if (!vol) {	2756	if (!vol) {
2757	if (!silent)	2757	if (!silent)
2758	ntfs_error(sb, "Allocation of NTFS volume structure "	2758	ntfs_error(sb, "Allocation of NTFS volume structure "
2759	"failed. Aborting mount...");	2759	"failed. Aborting mount...");
2760	lockdep_on();	2760	lockdep_on();
2761	return -ENOMEM;	2761	return -ENOMEM;
2762	}	2762	}
2763	/* Initialize ntfs_volume structure. */	2763	/* Initialize ntfs_volume structure. */
2764	*vol = (ntfs_volume) {	2764	*vol = (ntfs_volume) {
2765	.sb = sb,	2765	.sb = sb,
2766	/*	2766	/*
2767	* Default is group and other don't have any access to files or	2767	* Default is group and other don't have any access to files or
2768	* directories while owner has full access. Further, files by	2768	* directories while owner has full access. Further, files by
2769	* default are not executable but directories are of course	2769	* default are not executable but directories are of course
2770	* browseable.	2770	* browseable.
2771	*/	2771	*/
2772	.fmask = 0177,	2772	.fmask = 0177,
2773	.dmask = 0077,	2773	.dmask = 0077,
2774	};	2774	};
2775	init_rwsem(&vol->mftbmp_lock);	2775	init_rwsem(&vol->mftbmp_lock);
2776	init_rwsem(&vol->lcnbmp_lock);	2776	init_rwsem(&vol->lcnbmp_lock);
2777		2777
2778	unlock_kernel();	2778	unlock_kernel();
2779		2779
2780	/* By default, enable sparse support. */	2780	/* By default, enable sparse support. */
2781	NVolSetSparseEnabled(vol);	2781	NVolSetSparseEnabled(vol);
2782		2782
2783	/* Important to get the mount options dealt with now. */	2783	/* Important to get the mount options dealt with now. */
2784	if (!parse_options(vol, (char*)opt))	2784	if (!parse_options(vol, (char*)opt))
2785	goto err_out_now;	2785	goto err_out_now;
2786		2786
2787	/* We support sector sizes up to the PAGE_CACHE_SIZE. */	2787	/* We support sector sizes up to the PAGE_CACHE_SIZE. */
2788	if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {	2788	if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
2789	if (!silent)	2789	if (!silent)
2790	ntfs_error(sb, "Device has unsupported sector size "	2790	ntfs_error(sb, "Device has unsupported sector size "
2791	"(%i). The maximum supported sector "	2791	"(%i). The maximum supported sector "
2792	"size on this architecture is %lu "	2792	"size on this architecture is %lu "
2793	"bytes.",	2793	"bytes.",
2794	bdev_hardsect_size(sb->s_bdev),	2794	bdev_hardsect_size(sb->s_bdev),
2795	PAGE_CACHE_SIZE);	2795	PAGE_CACHE_SIZE);
2796	goto err_out_now;	2796	goto err_out_now;
2797	}	2797	}
2798	/*	2798	/*
2799	* Setup the device access block size to NTFS_BLOCK_SIZE or the hard	2799	* Setup the device access block size to NTFS_BLOCK_SIZE or the hard
2800	* sector size, whichever is bigger.	2800	* sector size, whichever is bigger.
2801	*/	2801	*/
2802	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);	2802	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
2803	if (blocksize < NTFS_BLOCK_SIZE) {	2803	if (blocksize < NTFS_BLOCK_SIZE) {
2804	if (!silent)	2804	if (!silent)
2805	ntfs_error(sb, "Unable to set device block size.");	2805	ntfs_error(sb, "Unable to set device block size.");
2806	goto err_out_now;	2806	goto err_out_now;
2807	}	2807	}
2808	BUG_ON(blocksize != sb->s_blocksize);	2808	BUG_ON(blocksize != sb->s_blocksize);
2809	ntfs_debug("Set device block size to %i bytes (block size bits %i).",	2809	ntfs_debug("Set device block size to %i bytes (block size bits %i).",
2810	blocksize, sb->s_blocksize_bits);	2810	blocksize, sb->s_blocksize_bits);
2811	/* Determine the size of the device in units of block_size bytes. */	2811	/* Determine the size of the device in units of block_size bytes. */
2812	if (!i_size_read(sb->s_bdev->bd_inode)) {	2812	if (!i_size_read(sb->s_bdev->bd_inode)) {
2813	if (!silent)	2813	if (!silent)
2814	ntfs_error(sb, "Unable to determine device size.");	2814	ntfs_error(sb, "Unable to determine device size.");
2815	goto err_out_now;	2815	goto err_out_now;
2816	}	2816	}
2817	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>	2817	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
2818	sb->s_blocksize_bits;	2818	sb->s_blocksize_bits;
2819	/* Read the boot sector and return unlocked buffer head to it. */	2819	/* Read the boot sector and return unlocked buffer head to it. */
2820	if (!(bh = read_ntfs_boot_sector(sb, silent))) {	2820	if (!(bh = read_ntfs_boot_sector(sb, silent))) {
2821	if (!silent)	2821	if (!silent)
2822	ntfs_error(sb, "Not an NTFS volume.");	2822	ntfs_error(sb, "Not an NTFS volume.");
2823	goto err_out_now;	2823	goto err_out_now;
2824	}	2824	}
2825	/*	2825	/*
2826	* Extract the data from the boot sector and setup the ntfs volume	2826	* Extract the data from the boot sector and setup the ntfs volume
2827	* using it.	2827	* using it.
2828	*/	2828	*/
2829	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);	2829	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
2830	brelse(bh);	2830	brelse(bh);
2831	if (!result) {	2831	if (!result) {
2832	if (!silent)	2832	if (!silent)
2833	ntfs_error(sb, "Unsupported NTFS filesystem.");	2833	ntfs_error(sb, "Unsupported NTFS filesystem.");
2834	goto err_out_now;	2834	goto err_out_now;
2835	}	2835	}
2836	/*	2836	/*
2837	* If the boot sector indicates a sector size bigger than the current	2837	* If the boot sector indicates a sector size bigger than the current
2838	* device block size, switch the device block size to the sector size.	2838	* device block size, switch the device block size to the sector size.
2839	* TODO: It may be possible to support this case even when the set	2839	* TODO: It may be possible to support this case even when the set
2840	* below fails, we would just be breaking up the i/o for each sector	2840	* below fails, we would just be breaking up the i/o for each sector
2841	* into multiple blocks for i/o purposes but otherwise it should just	2841	* into multiple blocks for i/o purposes but otherwise it should just
2842	* work. However it is safer to leave disabled until someone hits this	2842	* work. However it is safer to leave disabled until someone hits this
2843	* error message and then we can get them to try it without the setting	2843	* error message and then we can get them to try it without the setting
2844	* so we know for sure that it works.	2844	* so we know for sure that it works.
2845	*/	2845	*/
2846	if (vol->sector_size > blocksize) {	2846	if (vol->sector_size > blocksize) {
2847	blocksize = sb_set_blocksize(sb, vol->sector_size);	2847	blocksize = sb_set_blocksize(sb, vol->sector_size);
2848	if (blocksize != vol->sector_size) {	2848	if (blocksize != vol->sector_size) {
2849	if (!silent)	2849	if (!silent)
2850	ntfs_error(sb, "Unable to set device block "	2850	ntfs_error(sb, "Unable to set device block "
2851	"size to sector size (%i).",	2851	"size to sector size (%i).",
2852	vol->sector_size);	2852	vol->sector_size);
2853	goto err_out_now;	2853	goto err_out_now;
2854	}	2854	}
2855	BUG_ON(blocksize != sb->s_blocksize);	2855	BUG_ON(blocksize != sb->s_blocksize);
2856	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>	2856	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
2857	sb->s_blocksize_bits;	2857	sb->s_blocksize_bits;
2858	ntfs_debug("Changed device block size to %i bytes (block size "	2858	ntfs_debug("Changed device block size to %i bytes (block size "
2859	"bits %i) to match volume sector size.",	2859	"bits %i) to match volume sector size.",
2860	blocksize, sb->s_blocksize_bits);	2860	blocksize, sb->s_blocksize_bits);
2861	}	2861	}
2862	/* Initialize the cluster and mft allocators. */	2862	/* Initialize the cluster and mft allocators. */
2863	ntfs_setup_allocators(vol);	2863	ntfs_setup_allocators(vol);
2864	/* Setup remaining fields in the super block. */	2864	/* Setup remaining fields in the super block. */
2865	sb->s_magic = NTFS_SB_MAGIC;	2865	sb->s_magic = NTFS_SB_MAGIC;
2866	/*	2866	/*
2867	* Ntfs allows 63 bits for the file size, i.e. correct would be:	2867	* Ntfs allows 63 bits for the file size, i.e. correct would be:
2868	* sb->s_maxbytes = ~0ULL >> 1;	2868	* sb->s_maxbytes = ~0ULL >> 1;
2869	* But the kernel uses a long as the page cache page index which on	2869	* But the kernel uses a long as the page cache page index which on
2870	* 32-bit architectures is only 32-bits. MAX_LFS_FILESIZE is kernel	2870	* 32-bit architectures is only 32-bits. MAX_LFS_FILESIZE is kernel
2871	* defined to the maximum the page cache page index can cope with	2871	* defined to the maximum the page cache page index can cope with
2872	* without overflowing the index or to 2^63 - 1, whichever is smaller.	2872	* without overflowing the index or to 2^63 - 1, whichever is smaller.
2873	*/	2873	*/
2874	sb->s_maxbytes = MAX_LFS_FILESIZE;	2874	sb->s_maxbytes = MAX_LFS_FILESIZE;
2875	/* Ntfs measures time in 100ns intervals. */	2875	/* Ntfs measures time in 100ns intervals. */
2876	sb->s_time_gran = 100;	2876	sb->s_time_gran = 100;
2877	/*	2877	/*
2878	* Now load the metadata required for the page cache and our address	2878	* Now load the metadata required for the page cache and our address
2879	* space operations to function. We do this by setting up a specialised	2879	* space operations to function. We do this by setting up a specialised
2880	* read_inode method and then just calling the normal iget() to obtain	2880	* read_inode method and then just calling the normal iget() to obtain
2881	* the inode for $MFT which is sufficient to allow our normal inode	2881	* the inode for $MFT which is sufficient to allow our normal inode
2882	* operations and associated address space operations to function.	2882	* operations and associated address space operations to function.
2883	*/	2883	*/
2884	sb->s_op = &ntfs_sops;	2884	sb->s_op = &ntfs_sops;
2885	tmp_ino = new_inode(sb);	2885	tmp_ino = new_inode(sb);
2886	if (!tmp_ino) {	2886	if (!tmp_ino) {
2887	if (!silent)	2887	if (!silent)
2888	ntfs_error(sb, "Failed to load essential metadata.");	2888	ntfs_error(sb, "Failed to load essential metadata.");
2889	goto err_out_now;	2889	goto err_out_now;
2890	}	2890	}
2891	tmp_ino->i_ino = FILE_MFT;	2891	tmp_ino->i_ino = FILE_MFT;
2892	insert_inode_hash(tmp_ino);	2892	insert_inode_hash(tmp_ino);
2893	if (ntfs_read_inode_mount(tmp_ino) < 0) {	2893	if (ntfs_read_inode_mount(tmp_ino) < 0) {
2894	if (!silent)	2894	if (!silent)
2895	ntfs_error(sb, "Failed to load essential metadata.");	2895	ntfs_error(sb, "Failed to load essential metadata.");
2896	goto iput_tmp_ino_err_out_now;	2896	goto iput_tmp_ino_err_out_now;
2897	}	2897	}
2898	mutex_lock(&ntfs_lock);	2898	mutex_lock(&ntfs_lock);
2899	/*	2899	/*
2900	* The current mount is a compression user if the cluster size is	2900	* The current mount is a compression user if the cluster size is
2901	* less than or equal 4kiB.	2901	* less than or equal 4kiB.
2902	*/	2902	*/
2903	if (vol->cluster_size <= 4096 && !ntfs_nr_compression_users++) {	2903	if (vol->cluster_size <= 4096 && !ntfs_nr_compression_users++) {
2904	result = allocate_compression_buffers();	2904	result = allocate_compression_buffers();
2905	if (result) {	2905	if (result) {
2906	ntfs_error(NULL, "Failed to allocate buffers "	2906	ntfs_error(NULL, "Failed to allocate buffers "
2907	"for compression engine.");	2907	"for compression engine.");
2908	ntfs_nr_compression_users--;	2908	ntfs_nr_compression_users--;
2909	mutex_unlock(&ntfs_lock);	2909	mutex_unlock(&ntfs_lock);
2910	goto iput_tmp_ino_err_out_now;	2910	goto iput_tmp_ino_err_out_now;
2911	}	2911	}
2912	}	2912	}
2913	/*	2913	/*
2914	* Generate the global default upcase table if necessary. Also	2914	* Generate the global default upcase table if necessary. Also
2915	* temporarily increment the number of upcase users to avoid race	2915	* temporarily increment the number of upcase users to avoid race
2916	* conditions with concurrent (u)mounts.	2916	* conditions with concurrent (u)mounts.
2917	*/	2917	*/
2918	if (!default_upcase)	2918	if (!default_upcase)
2919	default_upcase = generate_default_upcase();	2919	default_upcase = generate_default_upcase();
2920	ntfs_nr_upcase_users++;	2920	ntfs_nr_upcase_users++;
2921	mutex_unlock(&ntfs_lock);	2921	mutex_unlock(&ntfs_lock);
2922	/*	2922	/*
2923	* From now on, ignore @silent parameter. If we fail below this line,	2923	* From now on, ignore @silent parameter. If we fail below this line,
2924	* it will be due to a corrupt fs or a system error, so we report it.	2924	* it will be due to a corrupt fs or a system error, so we report it.
2925	*/	2925	*/
2926	/*	2926	/*
2927	* Open the system files with normal access functions and complete	2927	* Open the system files with normal access functions and complete
2928	* setting up the ntfs super block.	2928	* setting up the ntfs super block.
2929	*/	2929	*/
2930	if (!load_system_files(vol)) {	2930	if (!load_system_files(vol)) {
2931	ntfs_error(sb, "Failed to load system files.");	2931	ntfs_error(sb, "Failed to load system files.");
2932	goto unl_upcase_iput_tmp_ino_err_out_now;	2932	goto unl_upcase_iput_tmp_ino_err_out_now;
2933	}	2933	}
2934	if ((sb->s_root = d_alloc_root(vol->root_ino))) {	2934	if ((sb->s_root = d_alloc_root(vol->root_ino))) {
2935	/* We increment i_count simulating an ntfs_iget(). */	2935	/* We increment i_count simulating an ntfs_iget(). */
2936	atomic_inc(&vol->root_ino->i_count);	2936	atomic_inc(&vol->root_ino->i_count);
2937	ntfs_debug("Exiting, status successful.");	2937	ntfs_debug("Exiting, status successful.");
2938	/* Release the default upcase if it has no users. */	2938	/* Release the default upcase if it has no users. */
2939	mutex_lock(&ntfs_lock);	2939	mutex_lock(&ntfs_lock);
2940	if (!--ntfs_nr_upcase_users && default_upcase) {	2940	if (!--ntfs_nr_upcase_users && default_upcase) {
2941	ntfs_free(default_upcase);	2941	ntfs_free(default_upcase);
2942	default_upcase = NULL;	2942	default_upcase = NULL;
2943	}	2943	}
2944	mutex_unlock(&ntfs_lock);	2944	mutex_unlock(&ntfs_lock);
2945	sb->s_export_op = &ntfs_export_ops;	2945	sb->s_export_op = &ntfs_export_ops;
2946	lock_kernel();	2946	lock_kernel();
2947	lockdep_on();	2947	lockdep_on();
2948	return 0;	2948	return 0;
2949	}	2949	}
2950	ntfs_error(sb, "Failed to allocate root directory.");	2950	ntfs_error(sb, "Failed to allocate root directory.");
2951	/* Clean up after the successful load_system_files() call from above. */	2951	/* Clean up after the successful load_system_files() call from above. */
2952	// TODO: Use ntfs_put_super() instead of repeating all this code...	2952	// TODO: Use ntfs_put_super() instead of repeating all this code...
2953	// FIXME: Should mark the volume clean as the error is most likely	2953	// FIXME: Should mark the volume clean as the error is most likely
2954	// -ENOMEM.	2954	// -ENOMEM.
2955	iput(vol->vol_ino);	2955	iput(vol->vol_ino);
2956	vol->vol_ino = NULL;	2956	vol->vol_ino = NULL;
2957	/* NTFS 3.0+ specific clean up. */	2957	/* NTFS 3.0+ specific clean up. */
2958	if (vol->major_ver >= 3) {	2958	if (vol->major_ver >= 3) {
2959	#ifdef NTFS_RW	2959	#ifdef NTFS_RW
2960	if (vol->usnjrnl_j_ino) {	2960	if (vol->usnjrnl_j_ino) {
2961	iput(vol->usnjrnl_j_ino);	2961	iput(vol->usnjrnl_j_ino);
2962	vol->usnjrnl_j_ino = NULL;	2962	vol->usnjrnl_j_ino = NULL;
2963	}	2963	}
2964	if (vol->usnjrnl_max_ino) {	2964	if (vol->usnjrnl_max_ino) {
2965	iput(vol->usnjrnl_max_ino);	2965	iput(vol->usnjrnl_max_ino);
2966	vol->usnjrnl_max_ino = NULL;	2966	vol->usnjrnl_max_ino = NULL;
2967	}	2967	}
2968	if (vol->usnjrnl_ino) {	2968	if (vol->usnjrnl_ino) {
2969	iput(vol->usnjrnl_ino);	2969	iput(vol->usnjrnl_ino);
2970	vol->usnjrnl_ino = NULL;	2970	vol->usnjrnl_ino = NULL;
2971	}	2971	}
2972	if (vol->quota_q_ino) {	2972	if (vol->quota_q_ino) {
2973	iput(vol->quota_q_ino);	2973	iput(vol->quota_q_ino);
2974	vol->quota_q_ino = NULL;	2974	vol->quota_q_ino = NULL;
2975	}	2975	}
2976	if (vol->quota_ino) {	2976	if (vol->quota_ino) {
2977	iput(vol->quota_ino);	2977	iput(vol->quota_ino);
2978	vol->quota_ino = NULL;	2978	vol->quota_ino = NULL;
2979	}	2979	}
2980	#endif /* NTFS_RW */	2980	#endif /* NTFS_RW */
2981	if (vol->extend_ino) {	2981	if (vol->extend_ino) {
2982	iput(vol->extend_ino);	2982	iput(vol->extend_ino);
2983	vol->extend_ino = NULL;	2983	vol->extend_ino = NULL;
2984	}	2984	}
2985	if (vol->secure_ino) {	2985	if (vol->secure_ino) {
2986	iput(vol->secure_ino);	2986	iput(vol->secure_ino);
2987	vol->secure_ino = NULL;	2987	vol->secure_ino = NULL;
2988	}	2988	}
2989	}	2989	}
2990	iput(vol->root_ino);	2990	iput(vol->root_ino);
2991	vol->root_ino = NULL;	2991	vol->root_ino = NULL;
2992	iput(vol->lcnbmp_ino);	2992	iput(vol->lcnbmp_ino);
2993	vol->lcnbmp_ino = NULL;	2993	vol->lcnbmp_ino = NULL;
2994	iput(vol->mftbmp_ino);	2994	iput(vol->mftbmp_ino);
2995	vol->mftbmp_ino = NULL;	2995	vol->mftbmp_ino = NULL;
2996	#ifdef NTFS_RW	2996	#ifdef NTFS_RW
2997	if (vol->logfile_ino) {	2997	if (vol->logfile_ino) {
2998	iput(vol->logfile_ino);	2998	iput(vol->logfile_ino);
2999	vol->logfile_ino = NULL;	2999	vol->logfile_ino = NULL;
3000	}	3000	}
3001	if (vol->mftmirr_ino) {	3001	if (vol->mftmirr_ino) {
3002	iput(vol->mftmirr_ino);	3002	iput(vol->mftmirr_ino);
3003	vol->mftmirr_ino = NULL;	3003	vol->mftmirr_ino = NULL;
3004	}	3004	}
3005	#endif /* NTFS_RW */	3005	#endif /* NTFS_RW */
3006	/* Throw away the table of attribute definitions. */	3006	/* Throw away the table of attribute definitions. */
3007	vol->attrdef_size = 0;	3007	vol->attrdef_size = 0;
3008	if (vol->attrdef) {	3008	if (vol->attrdef) {
3009	ntfs_free(vol->attrdef);	3009	ntfs_free(vol->attrdef);
3010	vol->attrdef = NULL;	3010	vol->attrdef = NULL;
3011	}	3011	}
3012	vol->upcase_len = 0;	3012	vol->upcase_len = 0;
3013	mutex_lock(&ntfs_lock);	3013	mutex_lock(&ntfs_lock);
3014	if (vol->upcase == default_upcase) {	3014	if (vol->upcase == default_upcase) {
3015	ntfs_nr_upcase_users--;	3015	ntfs_nr_upcase_users--;
3016	vol->upcase = NULL;	3016	vol->upcase = NULL;
3017	}	3017	}
3018	mutex_unlock(&ntfs_lock);	3018	mutex_unlock(&ntfs_lock);
3019	if (vol->upcase) {	3019	if (vol->upcase) {
3020	ntfs_free(vol->upcase);	3020	ntfs_free(vol->upcase);
3021	vol->upcase = NULL;	3021	vol->upcase = NULL;
3022	}	3022	}
3023	if (vol->nls_map) {	3023	if (vol->nls_map) {
3024	unload_nls(vol->nls_map);	3024	unload_nls(vol->nls_map);
3025	vol->nls_map = NULL;	3025	vol->nls_map = NULL;
3026	}	3026	}
3027	/* Error exit code path. */	3027	/* Error exit code path. */
3028	unl_upcase_iput_tmp_ino_err_out_now:	3028	unl_upcase_iput_tmp_ino_err_out_now:
3029	/*	3029	/*
3030	* Decrease the number of upcase users and destroy the global default	3030	* Decrease the number of upcase users and destroy the global default
3031	* upcase table if necessary.	3031	* upcase table if necessary.
3032	*/	3032	*/
3033	mutex_lock(&ntfs_lock);	3033	mutex_lock(&ntfs_lock);
3034	if (!--ntfs_nr_upcase_users && default_upcase) {	3034	if (!--ntfs_nr_upcase_users && default_upcase) {
3035	ntfs_free(default_upcase);	3035	ntfs_free(default_upcase);
3036	default_upcase = NULL;	3036	default_upcase = NULL;
3037	}	3037	}
3038	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)	3038	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
3039	free_compression_buffers();	3039	free_compression_buffers();
3040	mutex_unlock(&ntfs_lock);	3040	mutex_unlock(&ntfs_lock);
3041	iput_tmp_ino_err_out_now:	3041	iput_tmp_ino_err_out_now:
3042	iput(tmp_ino);	3042	iput(tmp_ino);
3043	if (vol->mft_ino && vol->mft_ino != tmp_ino)	3043	if (vol->mft_ino && vol->mft_ino != tmp_ino)
3044	iput(vol->mft_ino);	3044	iput(vol->mft_ino);
3045	vol->mft_ino = NULL;	3045	vol->mft_ino = NULL;
3046	/*	3046	/*
3047	* This is needed to get ntfs_clear_extent_inode() called for each	3047	* This is needed to get ntfs_clear_extent_inode() called for each
3048	* inode we have ever called ntfs_iget()/iput() on, otherwise we A)	3048	* inode we have ever called ntfs_iget()/iput() on, otherwise we A)
3049	* leak resources and B) a subsequent mount fails automatically due to	3049	* leak resources and B) a subsequent mount fails automatically due to
3050	* ntfs_iget() never calling down into our ntfs_read_locked_inode()	3050	* ntfs_iget() never calling down into our ntfs_read_locked_inode()
3051	* method again... FIXME: Do we need to do this twice now because of	3051	* method again... FIXME: Do we need to do this twice now because of
3052	* attribute inodes? I think not, so leave as is for now... (AIA)	3052	* attribute inodes? I think not, so leave as is for now... (AIA)
3053	*/	3053	*/
3054	if (invalidate_inodes(sb)) {	3054	if (invalidate_inodes(sb)) {
3055	ntfs_error(sb, "Busy inodes left. This is most likely a NTFS "	3055	ntfs_error(sb, "Busy inodes left. This is most likely a NTFS "
3056	"driver bug.");	3056	"driver bug.");
3057	/* Copied from fs/super.c. I just love this message. (-; */	3057	/* Copied from fs/super.c. I just love this message. (-; */
3058	printk("NTFS: Busy inodes after umount. Self-destruct in 5 "	3058	printk("NTFS: Busy inodes after umount. Self-destruct in 5 "
3059	"seconds. Have a nice day...\n");	3059	"seconds. Have a nice day...\n");
3060	}	3060	}
3061	/* Errors at this stage are irrelevant. */	3061	/* Errors at this stage are irrelevant. */
3062	err_out_now:	3062	err_out_now:
3063	lock_kernel();	3063	lock_kernel();
3064	sb->s_fs_info = NULL;	3064	sb->s_fs_info = NULL;
3065	kfree(vol);	3065	kfree(vol);
3066	ntfs_debug("Failed, returning -EINVAL.");	3066	ntfs_debug("Failed, returning -EINVAL.");
3067	lockdep_on();	3067	lockdep_on();
3068	return -EINVAL;	3068	return -EINVAL;
3069	}	3069	}
3070		3070
3071	/*	3071	/*
3072	* This is a slab cache to optimize allocations and deallocations of Unicode	3072	* This is a slab cache to optimize allocations and deallocations of Unicode
3073	* strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN	3073	* strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
3074	* (255) Unicode characters + a terminating NULL Unicode character.	3074	* (255) Unicode characters + a terminating NULL Unicode character.
3075	*/	3075	*/
3076	struct kmem_cache *ntfs_name_cache;	3076	struct kmem_cache *ntfs_name_cache;
3077		3077
3078	/* Slab caches for efficient allocation/deallocation of inodes. */	3078	/* Slab caches for efficient allocation/deallocation of inodes. */
3079	struct kmem_cache *ntfs_inode_cache;	3079	struct kmem_cache *ntfs_inode_cache;
3080	struct kmem_cache *ntfs_big_inode_cache;	3080	struct kmem_cache *ntfs_big_inode_cache;
3081		3081
3082	/* Init once constructor for the inode slab cache. */	3082	/* Init once constructor for the inode slab cache. */
3083	static void ntfs_big_inode_init_once(struct kmem_cache cachep, void foo)	3083	static void ntfs_big_inode_init_once(struct kmem_cache cachep, void foo)
3084	{	3084	{
3085	ntfs_inode ni = (ntfs_inode )foo;	3085	ntfs_inode ni = (ntfs_inode )foo;
3086		3086
3087	inode_init_once(VFS_I(ni));	3087	inode_init_once(VFS_I(ni));
3088	}	3088	}
3089		3089
3090	/*	3090	/*
3091	* Slab caches to optimize allocations and deallocations of attribute search	3091	* Slab caches to optimize allocations and deallocations of attribute search
3092	* contexts and index contexts, respectively.	3092	* contexts and index contexts, respectively.
3093	*/	3093	*/
3094	struct kmem_cache *ntfs_attr_ctx_cache;	3094	struct kmem_cache *ntfs_attr_ctx_cache;
3095	struct kmem_cache *ntfs_index_ctx_cache;	3095	struct kmem_cache *ntfs_index_ctx_cache;
3096		3096
3097	/* Driver wide mutex. */	3097	/* Driver wide mutex. */
3098	DEFINE_MUTEX(ntfs_lock);	3098	DEFINE_MUTEX(ntfs_lock);
3099		3099
3100	static int ntfs_get_sb(struct file_system_type *fs_type,	3100	static int ntfs_get_sb(struct file_system_type *fs_type,
3101	int flags, const char dev_name, void data, struct vfsmount *mnt)	3101	int flags, const char dev_name, void data, struct vfsmount *mnt)
3102	{	3102	{
3103	return get_sb_bdev(fs_type, flags, dev_name, data, ntfs_fill_super,	3103	return get_sb_bdev(fs_type, flags, dev_name, data, ntfs_fill_super,
3104	mnt);	3104	mnt);
3105	}	3105	}
3106		3106
3107	static struct file_system_type ntfs_fs_type = {	3107	static struct file_system_type ntfs_fs_type = {
3108	.owner = THIS_MODULE,	3108	.owner = THIS_MODULE,
3109	.name = "ntfs",	3109	.name = "ntfs",
3110	.get_sb = ntfs_get_sb,	3110	.get_sb = ntfs_get_sb,
3111	.kill_sb = kill_block_super,	3111	.kill_sb = kill_block_super,
3112	.fs_flags = FS_REQUIRES_DEV,	3112	.fs_flags = FS_REQUIRES_DEV,
3113	};	3113	};
3114		3114
3115	/* Stable names for the slab caches. */	3115	/* Stable names for the slab caches. */
3116	static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";	3116	static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";
3117	static const char ntfs_attr_ctx_cache_name[] = "ntfs_attr_ctx_cache";	3117	static const char ntfs_attr_ctx_cache_name[] = "ntfs_attr_ctx_cache";
3118	static const char ntfs_name_cache_name[] = "ntfs_name_cache";	3118	static const char ntfs_name_cache_name[] = "ntfs_name_cache";
3119	static const char ntfs_inode_cache_name[] = "ntfs_inode_cache";	3119	static const char ntfs_inode_cache_name[] = "ntfs_inode_cache";
3120	static const char ntfs_big_inode_cache_name[] = "ntfs_big_inode_cache";	3120	static const char ntfs_big_inode_cache_name[] = "ntfs_big_inode_cache";
3121		3121
3122	static int __init init_ntfs_fs(void)	3122	static int __init init_ntfs_fs(void)
3123	{	3123	{
3124	int err = 0;	3124	int err = 0;
3125		3125
3126	/* This may be ugly but it results in pretty output so who cares. (-8 */	3126	/* This may be ugly but it results in pretty output so who cares. (-8 */
3127	printk(KERN_INFO "NTFS driver " NTFS_VERSION " [Flags: R/"	3127	printk(KERN_INFO "NTFS driver " NTFS_VERSION " [Flags: R/"
3128	#ifdef NTFS_RW	3128	#ifdef NTFS_RW
3129	"W"	3129	"W"
3130	#else	3130	#else
3131	"O"	3131	"O"
3132	#endif	3132	#endif
3133	#ifdef DEBUG	3133	#ifdef DEBUG
3134	" DEBUG"	3134	" DEBUG"
3135	#endif	3135	#endif
3136	#ifdef MODULE	3136	#ifdef MODULE
3137	" MODULE"	3137	" MODULE"
3138	#endif	3138	#endif
3139	"].\n");	3139	"].\n");
3140		3140
3141	ntfs_debug("Debug messages are enabled.");	3141	ntfs_debug("Debug messages are enabled.");
3142		3142
3143	ntfs_index_ctx_cache = kmem_cache_create(ntfs_index_ctx_cache_name,	3143	ntfs_index_ctx_cache = kmem_cache_create(ntfs_index_ctx_cache_name,
3144	sizeof(ntfs_index_context), 0 /* offset */,	3144	sizeof(ntfs_index_context), 0 /* offset */,
3145	SLAB_HWCACHE_ALIGN, NULL /* ctor */);	3145	SLAB_HWCACHE_ALIGN, NULL /* ctor */);
3146	if (!ntfs_index_ctx_cache) {	3146	if (!ntfs_index_ctx_cache) {
3147	printk(KERN_CRIT "NTFS: Failed to create %s!\n",	3147	printk(KERN_CRIT "NTFS: Failed to create %s!\n",
3148	ntfs_index_ctx_cache_name);	3148	ntfs_index_ctx_cache_name);
3149	goto ictx_err_out;	3149	goto ictx_err_out;
3150	}	3150	}
3151	ntfs_attr_ctx_cache = kmem_cache_create(ntfs_attr_ctx_cache_name,	3151	ntfs_attr_ctx_cache = kmem_cache_create(ntfs_attr_ctx_cache_name,
3152	sizeof(ntfs_attr_search_ctx), 0 /* offset */,	3152	sizeof(ntfs_attr_search_ctx), 0 /* offset */,
3153	SLAB_HWCACHE_ALIGN, NULL /* ctor */);	3153	SLAB_HWCACHE_ALIGN, NULL /* ctor */);
3154	if (!ntfs_attr_ctx_cache) {	3154	if (!ntfs_attr_ctx_cache) {
3155	printk(KERN_CRIT "NTFS: Failed to create %s!\n",	3155	printk(KERN_CRIT "NTFS: Failed to create %s!\n",
3156	ntfs_attr_ctx_cache_name);	3156	ntfs_attr_ctx_cache_name);
3157	goto actx_err_out;	3157	goto actx_err_out;
3158	}	3158	}
3159		3159
3160	ntfs_name_cache = kmem_cache_create(ntfs_name_cache_name,	3160	ntfs_name_cache = kmem_cache_create(ntfs_name_cache_name,
3161	(NTFS_MAX_NAME_LEN+1) * sizeof(ntfschar), 0,	3161	(NTFS_MAX_NAME_LEN+1) * sizeof(ntfschar), 0,
3162	SLAB_HWCACHE_ALIGN, NULL);	3162	SLAB_HWCACHE_ALIGN, NULL);
3163	if (!ntfs_name_cache) {	3163	if (!ntfs_name_cache) {
3164	printk(KERN_CRIT "NTFS: Failed to create %s!\n",	3164	printk(KERN_CRIT "NTFS: Failed to create %s!\n",
3165	ntfs_name_cache_name);	3165	ntfs_name_cache_name);
3166	goto name_err_out;	3166	goto name_err_out;
3167	}	3167	}
3168		3168
3169	ntfs_inode_cache = kmem_cache_create(ntfs_inode_cache_name,	3169	ntfs_inode_cache = kmem_cache_create(ntfs_inode_cache_name,
3170	sizeof(ntfs_inode), 0,	3170	sizeof(ntfs_inode), 0,
3171	SLAB_RECLAIM_ACCOUNT\|SLAB_MEM_SPREAD, NULL);	3171	SLAB_RECLAIM_ACCOUNT\|SLAB_MEM_SPREAD, NULL);
3172	if (!ntfs_inode_cache) {	3172	if (!ntfs_inode_cache) {
3173	printk(KERN_CRIT "NTFS: Failed to create %s!\n",	3173	printk(KERN_CRIT "NTFS: Failed to create %s!\n",
3174	ntfs_inode_cache_name);	3174	ntfs_inode_cache_name);
3175	goto inode_err_out;	3175	goto inode_err_out;
3176	}	3176	}
3177		3177
3178	ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name,	3178	ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name,
3179	sizeof(big_ntfs_inode), 0,	3179	sizeof(big_ntfs_inode), 0,
3180	SLAB_HWCACHE_ALIGN\|SLAB_RECLAIM_ACCOUNT\|SLAB_MEM_SPREAD,	3180	SLAB_HWCACHE_ALIGN\|SLAB_RECLAIM_ACCOUNT\|SLAB_MEM_SPREAD,
3181	ntfs_big_inode_init_once);	3181	ntfs_big_inode_init_once);
3182	if (!ntfs_big_inode_cache) {	3182	if (!ntfs_big_inode_cache) {
3183	printk(KERN_CRIT "NTFS: Failed to create %s!\n",	3183	printk(KERN_CRIT "NTFS: Failed to create %s!\n",
3184	ntfs_big_inode_cache_name);	3184	ntfs_big_inode_cache_name);
3185	goto big_inode_err_out;	3185	goto big_inode_err_out;
3186	}	3186	}
3187		3187
3188	/* Register the ntfs sysctls. */	3188	/* Register the ntfs sysctls. */
3189	err = ntfs_sysctl(1);	3189	err = ntfs_sysctl(1);
3190	if (err) {	3190	if (err) {
3191	printk(KERN_CRIT "NTFS: Failed to register NTFS sysctls!\n");	3191	printk(KERN_CRIT "NTFS: Failed to register NTFS sysctls!\n");
3192	goto sysctl_err_out;	3192	goto sysctl_err_out;
3193	}	3193	}
3194		3194
3195	err = register_filesystem(&ntfs_fs_type);	3195	err = register_filesystem(&ntfs_fs_type);
3196	if (!err) {	3196	if (!err) {
3197	ntfs_debug("NTFS driver registered successfully.");	3197	ntfs_debug("NTFS driver registered successfully.");
3198	return 0; /* Success! */	3198	return 0; /* Success! */
3199	}	3199	}
3200	printk(KERN_CRIT "NTFS: Failed to register NTFS filesystem driver!\n");	3200	printk(KERN_CRIT "NTFS: Failed to register NTFS filesystem driver!\n");
3201		3201
3202	sysctl_err_out:	3202	sysctl_err_out:
3203	kmem_cache_destroy(ntfs_big_inode_cache);	3203	kmem_cache_destroy(ntfs_big_inode_cache);
3204	big_inode_err_out:	3204	big_inode_err_out:
3205	kmem_cache_destroy(ntfs_inode_cache);	3205	kmem_cache_destroy(ntfs_inode_cache);
3206	inode_err_out:	3206	inode_err_out:
3207	kmem_cache_destroy(ntfs_name_cache);	3207	kmem_cache_destroy(ntfs_name_cache);
3208	name_err_out:	3208	name_err_out:
3209	kmem_cache_destroy(ntfs_attr_ctx_cache);	3209	kmem_cache_destroy(ntfs_attr_ctx_cache);
3210	actx_err_out:	3210	actx_err_out:
3211	kmem_cache_destroy(ntfs_index_ctx_cache);	3211	kmem_cache_destroy(ntfs_index_ctx_cache);
3212	ictx_err_out:	3212	ictx_err_out:
3213	if (!err) {	3213	if (!err) {
3214	printk(KERN_CRIT "NTFS: Aborting NTFS filesystem driver "	3214	printk(KERN_CRIT "NTFS: Aborting NTFS filesystem driver "
3215	"registration...\n");	3215	"registration...\n");
3216	err = -ENOMEM;	3216	err = -ENOMEM;
3217	}	3217	}
3218	return err;	3218	return err;
3219	}	3219	}
3220		3220
3221	static void __exit exit_ntfs_fs(void)	3221	static void __exit exit_ntfs_fs(void)
3222	{	3222	{
3223	ntfs_debug("Unregistering NTFS driver.");	3223	ntfs_debug("Unregistering NTFS driver.");
3224		3224
3225	unregister_filesystem(&ntfs_fs_type);	3225	unregister_filesystem(&ntfs_fs_type);
3226	kmem_cache_destroy(ntfs_big_inode_cache);	3226	kmem_cache_destroy(ntfs_big_inode_cache);
3227	kmem_cache_destroy(ntfs_inode_cache);	3227	kmem_cache_destroy(ntfs_inode_cache);
3228	kmem_cache_destroy(ntfs_name_cache);	3228	kmem_cache_destroy(ntfs_name_cache);
3229	kmem_cache_destroy(ntfs_attr_ctx_cache);	3229	kmem_cache_destroy(ntfs_attr_ctx_cache);
3230	kmem_cache_destroy(ntfs_index_ctx_cache);	3230	kmem_cache_destroy(ntfs_index_ctx_cache);
3231	/* Unregister the ntfs sysctls. */	3231	/* Unregister the ntfs sysctls. */
3232	ntfs_sysctl(0);	3232	ntfs_sysctl(0);
3233	}	3233	}
3234		3234
3235	MODULE_AUTHOR("Anton Altaparmakov <aia21@cantab.net>");	3235	MODULE_AUTHOR("Anton Altaparmakov <aia21@cantab.net>");
3236	MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2007 Anton Altaparmakov");	3236	MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2007 Anton Altaparmakov");
3237	MODULE_VERSION(NTFS_VERSION);	3237	MODULE_VERSION(NTFS_VERSION);
3238	MODULE_LICENSE("GPL");	3238	MODULE_LICENSE("GPL");
3239	#ifdef DEBUG	3239	#ifdef DEBUG
3240	module_param(debug_msgs, bool, 0);	3240	module_param(debug_msgs, bool, 0);
3241	MODULE_PARM_DESC(debug_msgs, "Enable debug messages.");	3241	MODULE_PARM_DESC(debug_msgs, "Enable debug messages.");
3242	#endif	3242	#endif
3243		3243
3244	module_init(init_ntfs_fs)	3244	module_init(init_ntfs_fs)
3245	module_exit(exit_ntfs_fs)	3245	module_exit(exit_ntfs_fs)
3246		3246

include/linux/fs.h

Diff comments View file @ 08d8e97

 #ifndef _LINUX_FS_H
 #define _LINUX_FS_H
 /*
  * This file has definitions for some important file table
  * structures etc.
  */
 #include <linux/limits.h>
 #include <linux/ioctl.h>
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
  * the file limit at runtime and only root can increase the per-process
  * nr_file rlimit, so it's safe to set up a ridiculously high absolute
  * upper limit on files-per-process.
  *
  * Some programs (notably those using select()) may have to be
  * recompiled to take full advantage of the new limits..
  */
 /* Fixed constants first: */
 #undef NR_OPEN
 #define NR_OPEN (1024*1024)	/* Absolute upper limit on fd num */
 #define INR_OPEN 1024		/* Initial setting for nfile rlimits */
 #define BLOCK_SIZE_BITS 10
 #define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
 #define SEEK_SET	0	/* seek relative to beginning of file */
 #define SEEK_CUR	1	/* seek relative to current file position */
 #define SEEK_END	2	/* seek relative to end of file */
 #define SEEK_MAX	SEEK_END
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
 	int nr_files;		/* read only */
 	int nr_free_files;	/* read only */
 	int max_files;		/* tunable */
 };
 extern struct files_stat_struct files_stat;
 extern int get_max_files(void);
 struct inodes_stat_t {
 	int nr_inodes;
 	int nr_unused;
 	int dummy[5];		/* padding for sysctl ABI compatibility */
 };
 extern struct inodes_stat_t inodes_stat;
 extern int leases_enable, lease_break_time;
 #ifdef CONFIG_DNOTIFY
 extern int dir_notify_enable;
 #endif
 #define NR_FILE  8192	/* this can well be larger on a larger system */
 #define MAY_EXEC 1
 #define MAY_WRITE 2
 #define MAY_READ 4
 #define MAY_APPEND 8
 #define FMODE_READ 1
 #define FMODE_WRITE 2
 /* Internal kernel extensions */
 #define FMODE_LSEEK	4
 #define FMODE_PREAD	8
 #define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */
 /* File is being opened for execution. Primary users of this flag are
    distributed filesystems that can use it to achieve correct ETXTBUSY
    behavior for cross-node execution/opening_for_writing of files */
 #define FMODE_EXEC	16
 #define RW_MASK		1
 #define RWA_MASK	2
 #define READ 0
 #define WRITE 1
 #define READA 2		/* read-ahead  - don't block if no resources */
 #define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
 #define READ_SYNC	(READ | (1 << BIO_RW_SYNC))
 #define READ_META	(READ | (1 << BIO_RW_META))
 #define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNC))
 #define WRITE_BARRIER	((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
 #define SEL_IN		1
 #define SEL_OUT		2
 #define SEL_EX		4
 /* public flags for file_system_type */
 #define FS_REQUIRES_DEV 1
 #define FS_BINARY_MOUNTDATA 2
 #define FS_HAS_SUBTYPE 4
 #define FS_REVAL_DOT	16384	/* Check the paths ".", ".." for staleness */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move()
 					 * during rename() internally.
 					 */
 /*
  * These are the fs-independent mount-flags: up to 32 flags are supported
  */
 #define MS_RDONLY	 1	/* Mount read-only */
 #define MS_NOSUID	 2	/* Ignore suid and sgid bits */
 #define MS_NODEV	 4	/* Disallow access to device special files */
 #define MS_NOEXEC	 8	/* Disallow program execution */
 #define MS_SYNCHRONOUS	16	/* Writes are synced at once */
 #define MS_REMOUNT	32	/* Alter flags of a mounted FS */
 #define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
 #define MS_DIRSYNC	128	/* Directory modifications are synchronous */
 #define MS_NOATIME	1024	/* Do not update access times. */
 #define MS_NODIRATIME	2048	/* Do not update directory access times */
 #define MS_BIND		4096
 #define MS_MOVE		8192
 #define MS_REC		16384
 #define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
 				   MS_VERBOSE is deprecated. */
 #define MS_SILENT	32768
 #define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
 #define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
 #define MS_PRIVATE	(1<<18)	/* change to private */
 #define MS_SLAVE	(1<<19)	/* change to slave */
 #define MS_SHARED	(1<<20)	/* change to shared */
 #define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
 #define MS_ACTIVE	(1<<30)
 #define MS_NOUSER	(1<<31)
 /*
  * Superblock flags that can be altered by MS_REMOUNT
  */
 #define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK)
 /*
  * Old magic mount flag and mask
  */
 #define MS_MGC_VAL 0xC0ED0000
 #define MS_MGC_MSK 0xffff0000
 /* Inode flags - they have nothing to superblock flags now */
 #define S_SYNC		1	/* Writes are synced at once */
 #define S_NOATIME	2	/* Do not update access times */
 #define S_APPEND	4	/* Append-only file */
 #define S_IMMUTABLE	8	/* Immutable file */
 #define S_DEAD		16	/* removed, but still open directory */
 #define S_NOQUOTA	32	/* Inode is not counted to quota */
 #define S_DIRSYNC	64	/* Directory modifications are synchronous */
 #define S_NOCMTIME	128	/* Do not update file c/mtime */
 #define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
 #define S_PRIVATE	512	/* Inode is fs-internal */
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
  * flags just means all the inodes inherit those flags by default. It might be
  * possible to override it selectively if you really wanted to with some
  * ioctl() that is not currently implemented.
  *
  * Exception: MS_RDONLY is always applied to the entire file system.
  *
  * Unfortunately, it is possible to change a filesystems flags with it mounted
  * with files in use.  This means that all of the inodes will not have their
  * i_flags updated.  Hence, i_flags no longer inherit the superblock mount
  * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
  */
 #define __IS_FLG(inode,flg) ((inode)->i_sb->s_flags & (flg))
 #define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
 #define IS_SYNC(inode)		(__IS_FLG(inode, MS_SYNCHRONOUS) || \
 					((inode)->i_flags & S_SYNC))
 #define IS_DIRSYNC(inode)	(__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
 					((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
 #define IS_MANDLOCK(inode)	__IS_FLG(inode, MS_MANDLOCK)
 #define IS_NOATIME(inode)   __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
 #define IS_NOQUOTA(inode)	((inode)->i_flags & S_NOQUOTA)
 #define IS_APPEND(inode)	((inode)->i_flags & S_APPEND)
 #define IS_IMMUTABLE(inode)	((inode)->i_flags & S_IMMUTABLE)
 #define IS_POSIXACL(inode)	__IS_FLG(inode, MS_POSIXACL)
 #define IS_DEADDIR(inode)	((inode)->i_flags & S_DEAD)
 #define IS_NOCMTIME(inode)	((inode)->i_flags & S_NOCMTIME)
 #define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
 #define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
 /* the read-only stuff doesn't really belong here, but any other place is
    probably as bad and I don't want to create yet another include file. */
 #define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
 #define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
 #define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
 #define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
 #define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
 #define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
 #define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
 #define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
 #define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
 #define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
 #define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
 #define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
 #if 0
 #define BLKPG      _IO(0x12,105)/* See blkpg.h */
 /* Some people are morons.  Do not use sizeof! */
 #define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
 #define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
 /* This was here just to show that the number is taken -
    probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
 #endif
 /* A jump here: 108-111 have been used for various private purposes. */
 #define BLKBSZGET  _IOR(0x12,112,size_t)
 #define BLKBSZSET  _IOW(0x12,113,size_t)
 #define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
 #define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
 #define BLKTRACESTART _IO(0x12,116)
 #define BLKTRACESTOP _IO(0x12,117)
 #define BLKTRACETEARDOWN _IO(0x12,118)
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
 #define	FS_IOC_GETVERSION		_IOR('v', 1, long)
 #define	FS_IOC_SETVERSION		_IOW('v', 2, long)
 #define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
 #define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
 #define FS_IOC32_GETVERSION		_IOR('v', 1, int)
 #define FS_IOC32_SETVERSION		_IOW('v', 2, int)
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
  */
 #define	FS_SECRM_FL			0x00000001 /* Secure deletion */
 #define	FS_UNRM_FL			0x00000002 /* Undelete */
 #define	FS_COMPR_FL			0x00000004 /* Compress file */
 #define FS_SYNC_FL			0x00000008 /* Synchronous updates */
 #define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
 #define FS_APPEND_FL			0x00000020 /* writes to file may only append */
 #define FS_NODUMP_FL			0x00000040 /* do not dump file */
 #define FS_NOATIME_FL			0x00000080 /* do not update atime */
 /* Reserved for compression usage... */
 #define FS_DIRTY_FL			0x00000100
 #define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
 #define FS_NOCOMP_FL			0x00000400 /* Don't compress */
 #define FS_ECOMPR_FL			0x00000800 /* Compression error */
 /* End compression flags --- maybe not all used */
 #define FS_BTREE_FL			0x00001000 /* btree format dir */
 #define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
 #define FS_IMAGIC_FL			0x00002000 /* AFS directory */
 #define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
 #define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
 #define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
 #define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
 #define FS_EXTENT_FL			0x00080000 /* Extents */
 #define FS_DIRECTIO_FL			0x00100000 /* Use direct i/o */
 #define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
 #define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
 #define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
 #define SYNC_FILE_RANGE_WAIT_BEFORE	1
 #define SYNC_FILE_RANGE_WRITE		2
 #define SYNC_FILE_RANGE_WAIT_AFTER	4
 #ifdef __KERNEL__
 #include <linux/linkage.h>
 #include <linux/wait.h>
 #include <linux/types.h>
 #include <linux/kdev_t.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include <linux/stat.h>
 #include <linux/cache.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/radix-tree.h>
 #include <linux/prio_tree.h>
 #include <linux/init.h>
 #include <linux/pid.h>
 #include <linux/mutex.h>
 #include <linux/capability.h>
 #include <asm/atomic.h>
 #include <asm/semaphore.h>
 #include <asm/byteorder.h>
 struct export_operations;
 struct hd_geometry;
 struct iovec;
 struct nameidata;
 struct kiocb;
 struct pipe_inode_info;
 struct poll_table_struct;
 struct kstatfs;
 struct vm_area_struct;
 struct vfsmount;
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
 extern void __init mnt_init(void);
 extern void __init files_init(unsigned long);
 struct buffer_head;
 typedef int (get_block_t)(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create);
 typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 			ssize_t bytes, void *private);
 /*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
  */
 #define ATTR_MODE	1
 #define ATTR_UID	2
 #define ATTR_GID	4
 #define ATTR_SIZE	8
 #define ATTR_ATIME	16
 #define ATTR_MTIME	32
 #define ATTR_CTIME	64
 #define ATTR_ATIME_SET	128
 #define ATTR_MTIME_SET	256
 #define ATTR_FORCE	512	/* Not a change, but a change it */
 #define ATTR_ATTR_FLAG	1024
 #define ATTR_KILL_SUID	2048
 #define ATTR_KILL_SGID	4096
 #define ATTR_FILE	8192
 /*
  * This is the Inode Attributes structure, used for notify_change().  It
  * uses the above definitions as flags, to know which values have changed.
  * Also, in this manner, a Filesystem can look at only the values it cares
  * about.  Basically, these are the attributes that the VFS layer can
  * request to change from the FS layer.
  *
  * Derek Atkins <warlord@MIT.EDU> 94-10-20
  */
 struct iattr {
 	unsigned int	ia_valid;
 	umode_t		ia_mode;
 	uid_t		ia_uid;
 	gid_t		ia_gid;
 	loff_t		ia_size;
 	struct timespec	ia_atime;
 	struct timespec	ia_mtime;
 	struct timespec	ia_ctime;
 	/*
 	 * Not an attribute, but an auxilary info for filesystems wanting to
 	 * implement an ftruncate() like method.  NOTE: filesystem should
 	 * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
 	 */
 	struct file	*ia_file;
 };
 /*
  * Includes for diskquotas.
  */
 #include <linux/quota.h>
 /**
  * enum positive_aop_returns - aop return codes with specific semantics
  *
  * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
  * 			    completed, that the page is still locked, and
  * 			    should be considered active.  The VM uses this hint
  * 			    to return the page to the active list -- it won't
  * 			    be a candidate for writeback again in the near
  * 			    future.  Other callers must be careful to unlock
  * 			    the page if they get this return.  Returned by
  * 			    writepage();
  *
  * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
  *  			unlocked it and the page might have been truncated.
  *  			The caller should back up to acquiring a new page and
  *  			trying again.  The aop will be taking reasonable
  *  			precautions not to livelock.  If the caller held a page
  *  			reference, it should drop it before retrying.  Returned
  *  			by readpage().
  *
  * address_space_operation functions return these large constants to indicate
  * special semantics to the caller.  These are much larger than the bytes in a
  * page to allow for functions that return the number of bytes operated on in a
  * given page.
  */
 enum positive_aop_returns {
 	AOP_WRITEPAGE_ACTIVATE	= 0x80000,
 	AOP_TRUNCATED_PAGE	= 0x80001,
 };
 #define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
 #define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
 /*
  * oh the beauties of C type declarations.
  */
 struct page;
 struct address_space;
 struct writeback_control;
 struct iov_iter {
 	const struct iovec *iov;
 	unsigned long nr_segs;
 	size_t iov_offset;
 	size_t count;
 };
 size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes);
 size_t iov_iter_copy_from_user(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(struct iov_iter *i);
 static inline void iov_iter_init(struct iov_iter *i,
 			const struct iovec *iov, unsigned long nr_segs,
 			size_t count, size_t written)
 {
 	i->iov = iov;
 	i->nr_segs = nr_segs;
 	i->iov_offset = 0;
 	i->count = count + written;
 	iov_iter_advance(i, written);
 }
 static inline size_t iov_iter_count(struct iov_iter *i)
 {
 	return i->count;
 }
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*readpage)(struct file *, struct page *);
 	void (*sync_page)(struct page *);
 	/* Write back some dirty pages from this mapping. */
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	/* Set a page dirty.  Return true if this dirtied it */
 	int (*set_page_dirty)(struct page *page);
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);
 	/*
 	 * ext3 requires that a successful prepare_write() call be followed
 	 * by a commit_write() call - they must be balanced
 	 */
 	int (*prepare_write)(struct file *, struct page *, unsigned, unsigned);
 	int (*commit_write)(struct file *, struct page *, unsigned, unsigned);
 	int (*write_begin)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata);
 	int (*write_end)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata);
 	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidatepage) (struct page *, unsigned long);
 	int (*releasepage) (struct page *, gfp_t);
 	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
 	struct page* (*get_xip_page)(struct address_space *, sector_t,
 			int);
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct address_space *,
 			struct page *, struct page *);
 	int (*launder_page) (struct page *);
 };
 /*
  * pagecache_write_begin/pagecache_write_end must be used by general code
  * to write into the pagecache.
  */
 int pagecache_write_begin(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata);
 int pagecache_write_end(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata);
 struct backing_dev_info;
 struct address_space {
 	struct inode		*host;		/* owner: inode, block_device */
 	struct radix_tree_root	page_tree;	/* radix tree of all pages */
 	rwlock_t		tree_lock;	/* and rwlock protecting it */
 	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
 	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
 	spinlock_t		i_mmap_lock;	/* protect tree, count, list */
 	unsigned int		truncate_count;	/* Cover race condition with truncate */
 	unsigned long		nrpages;	/* number of total pages */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
 	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
 	struct address_space	*assoc_mapping;	/* ditto */
 } __attribute__((aligned(sizeof(long))));
 	/*
 	 * On most architectures that alignment is already the case; but
 	 * must be enforced here for CRIS, to let the least signficant bit
 	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
 	 */
 struct block_device {
 	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
 	struct inode *		bd_inode;	/* will die */
 	int			bd_openers;
 	struct mutex		bd_mutex;	/* open/close mutex */
 	struct semaphore	bd_mount_sem;
 	struct list_head	bd_inodes;
 	void *			bd_holder;
 	int			bd_holders;
 #ifdef CONFIG_SYSFS
 	struct list_head	bd_holder_list;
 #endif
 	struct block_device *	bd_contains;
 	unsigned		bd_block_size;
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
 	int			bd_invalidated;
 	struct gendisk *	bd_disk;
 	struct list_head	bd_list;
 	struct backing_dev_info *bd_inode_backing_dev_info;
 	/*
 	 * Private data.  You must have bd_claim'ed the block_device
 	 * to use this.  NOTE:  bd_claim allows an owner to claim
 	 * the same device multiple times, the owner must take special
 	 * care to not mess up bd_private for that case.
 	 */
 	unsigned long		bd_private;
 };
 /*
  * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
  * radix trees
  */
 #define PAGECACHE_TAG_DIRTY	0
 #define PAGECACHE_TAG_WRITEBACK	1
 int mapping_tagged(struct address_space *mapping, int tag);
 /*
  * Might pages of this file be mapped into userspace?
  */
 static inline int mapping_mapped(struct address_space *mapping)
 {
 	return	!prio_tree_empty(&mapping->i_mmap) ||
 		!list_empty(&mapping->i_mmap_nonlinear);
 }
 /*
  * Might pages of this file have been modified in userspace?
  * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
  * marks vma as VM_SHARED if it is shared, and the file was opened for
  * writing i.e. vma may be mprotected writable even if now readonly.
  */
 static inline int mapping_writably_mapped(struct address_space *mapping)
 {
 	return mapping->i_mmap_writable != 0;
 }
 /*
  * Use sequence counter to get consistent i_size on 32-bit processors.
  */
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 #include <linux/seqlock.h>
 #define __NEED_I_SIZE_ORDERED
 #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
 #else
 #define i_size_ordered_init(inode) do { } while (0)
 #endif
 struct inode {
 	struct hlist_node	i_hash;
 	struct list_head	i_list;
 	struct list_head	i_sb_list;
 	struct list_head	i_dentry;
 	unsigned long		i_ino;
 	atomic_t		i_count;
 	unsigned int		i_nlink;
 	uid_t			i_uid;
 	gid_t			i_gid;
 	dev_t			i_rdev;
 	unsigned long		i_version;
 	loff_t			i_size;
 #ifdef __NEED_I_SIZE_ORDERED
 	seqcount_t		i_size_seqcount;
 #endif
 	struct timespec		i_atime;
 	struct timespec		i_mtime;
 	struct timespec		i_ctime;
 	unsigned int		i_blkbits;
 	blkcnt_t		i_blocks;
 	unsigned short          i_bytes;
 	umode_t			i_mode;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	struct mutex		i_mutex;
 	struct rw_semaphore	i_alloc_sem;
 	const struct inode_operations	*i_op;
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct super_block	*i_sb;
 	struct file_lock	*i_flock;
 	struct address_space	*i_mapping;
 	struct address_space	i_data;
 #ifdef CONFIG_QUOTA
 	struct dquot		*i_dquot[MAXQUOTAS];
 #endif
 	struct list_head	i_devices;
 	union {
 		struct pipe_inode_info	*i_pipe;
 		struct block_device	*i_bdev;
 		struct cdev		*i_cdev;
 	};
 	int			i_cindex;
 	__u32			i_generation;
 #ifdef CONFIG_DNOTIFY
 	unsigned long		i_dnotify_mask; /* Directory notify events */
 	struct dnotify_struct	*i_dnotify; /* for directory notifications */
 #endif
 #ifdef CONFIG_INOTIFY
 	struct list_head	inotify_watches; /* watches on this inode */
 	struct mutex		inotify_mutex;	/* protects the watches list */
 #endif
 	unsigned long		i_state;
 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
 	unsigned int		i_flags;
 	atomic_t		i_writecount;
 #ifdef CONFIG_SECURITY
 	void			*i_security;
 #endif
 	void			*i_private; /* fs or device private pointer */
 };
 /*
  * inode->i_mutex nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
  * 1: parent
  * 2: child/target
  * 3: quota file
  *
  * The locking order between these classes is
  * parent -> child -> normal -> xattr -> quota
  */
 enum inode_i_mutex_lock_class
 {
 	I_MUTEX_NORMAL,
 	I_MUTEX_PARENT,
 	I_MUTEX_CHILD,
 	I_MUTEX_XATTR,
 	I_MUTEX_QUOTA
 };
 extern void inode_double_lock(struct inode *inode1, struct inode *inode2);
 extern void inode_double_unlock(struct inode *inode1, struct inode *inode2);
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
  * with respect to the local cpu (unlike with preempt disabled),
  * but they don't need to be atomic with respect to other cpus like in
  * true SMP (so they need either to either locally disable irq around
  * the read or for example on x86 they can be still implemented as a
  * cmpxchg8b without the need of the lock prefix). For SMP compiles
  * and 64bit archs it makes no difference if preempt is enabled or not.
  */
 static inline loff_t i_size_read(const struct inode *inode)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	loff_t i_size;
 	unsigned int seq;
 	do {
 		seq = read_seqcount_begin(&inode->i_size_seqcount);
 		i_size = inode->i_size;
 	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
 	return i_size;
 #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
 	loff_t i_size;
 	preempt_disable();
 	i_size = inode->i_size;
 	preempt_enable();
 	return i_size;
 #else
 	return inode->i_size;
 #endif
 }
 /*
  * NOTE: unlike i_size_read(), i_size_write() does need locking around it
  * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
  * can be lost, resulting in subsequent i_size_read() calls spinning forever.
  */
 static inline void i_size_write(struct inode *inode, loff_t i_size)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	write_seqcount_begin(&inode->i_size_seqcount);
 	inode->i_size = i_size;
 	write_seqcount_end(&inode->i_size_seqcount);
 #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
 	preempt_disable();
 	inode->i_size = i_size;
 	preempt_enable();
 #else
 	inode->i_size = i_size;
 #endif
 }
 static inline unsigned iminor(const struct inode *inode)
 {
 	return MINOR(inode->i_rdev);
 }
 static inline unsigned imajor(const struct inode *inode)
 {
 	return MAJOR(inode->i_rdev);
 }
 extern struct block_device *I_BDEV(struct inode *inode);
 struct fown_struct {
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
 	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
 	uid_t uid, euid;	/* uid/euid of process setting the owner */
 	int signum;		/* posix.1b rt signal to be delivered on IO */
 };
 /*
  * Track a single file's readahead state
  */
 struct file_ra_state {
 	pgoff_t start;			/* where readahead started */
 	unsigned int size;		/* # of readahead pages */
 	unsigned int async_size;	/* do asynchronous readahead when
 					   there are only # of pages ahead */
 	unsigned int ra_pages;		/* Maximum readahead window */
 	int mmap_miss;			/* Cache miss stat for mmap accesses */
 	loff_t prev_pos;		/* Cache last read() position */
 };
 /*
  * Check if @index falls in the readahead windows.
  */
 static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 {
 	return (index >= ra->start &&
 		index <  ra->start + ra->size);
 }
 struct file {
 	/*
 	 * fu_list becomes invalid after file_free is called and queued via
 	 * fu_rcuhead for RCU freeing
 	 */
 	union {
 		struct list_head	fu_list;
 		struct rcu_head 	fu_rcuhead;
 	} f_u;
 	struct path		f_path;
 #define f_dentry	f_path.dentry
 #define f_vfsmnt	f_path.mnt
 	const struct file_operations	*f_op;
 	atomic_t		f_count;
 	unsigned int 		f_flags;
 	mode_t			f_mode;
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	unsigned int		f_uid, f_gid;
 	struct file_ra_state	f_ra;
 	u64			f_version;
 #ifdef CONFIG_SECURITY
 	void			*f_security;
 #endif
 	/* needed for tty driver, and maybe others */
 	void			*private_data;
 #ifdef CONFIG_EPOLL
 	/* Used by fs/eventpoll.c to link all the hooks to this file */
 	struct list_head	f_ep_links;
 	spinlock_t		f_ep_lock;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
 };
 extern spinlock_t files_lock;
 #define file_list_lock() spin_lock(&files_lock);
 #define file_list_unlock() spin_unlock(&files_lock);
 #define get_file(x)	atomic_inc(&(x)->f_count)
 #define file_count(x)	atomic_read(&(x)->f_count)
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 /* Page cache limit. The filesystems should put that into their s_maxbytes
    limits, otherwise bad things can happen in VM. */
 #if BITS_PER_LONG==32
 #define MAX_LFS_FILESIZE	(((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
 #elif BITS_PER_LONG==64
 #define MAX_LFS_FILESIZE 	0x7fffffffffffffffUL
 #endif
 #define FL_POSIX	1
 #define FL_FLOCK	2
 #define FL_ACCESS	8	/* not trying to lock, just looking */
 #define FL_EXISTS	16	/* when unlocking, test for existence */
 #define FL_LEASE	32	/* lease held on this file */
 #define FL_CLOSE	64	/* unlock on close */
 #define FL_SLEEP	128	/* A blocking lock */
 /*
  * The POSIX file lock owner is determined by
  * the "struct files_struct" in the thread group
  * (or NULL for no owner - BSD locks).
  *
  * Lockd stuffs a "host" pointer into this.
  */
 typedef struct files_struct *fl_owner_t;
 struct file_lock_operations {
 	void (*fl_insert)(struct file_lock *);	/* lock insertion callback */
 	void (*fl_remove)(struct file_lock *);	/* lock removal callback */
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
 };
 struct lock_manager_operations {
 	int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
 	void (*fl_notify)(struct file_lock *);	/* unblock callback */
 	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
 	void (*fl_break)(struct file_lock *);
 	int (*fl_mylease)(struct file_lock *, struct file_lock *);
 	int (*fl_change)(struct file_lock **, int);
 };
 /* that will die - we need it for nfs_lock_info */
 #include <linux/nfs_fs_i.h>
 struct file_lock {
 	struct file_lock *fl_next;	/* singly linked list for this inode  */
 	struct list_head fl_link;	/* doubly linked list of all locks */
 	struct list_head fl_block;	/* circular list of blocked processes */
 	fl_owner_t fl_owner;
 	unsigned int fl_pid;
 	wait_queue_head_t fl_wait;
 	struct file *fl_file;
 	unsigned char fl_flags;
 	unsigned char fl_type;
 	loff_t fl_start;
 	loff_t fl_end;
 	struct fasync_struct *	fl_fasync; /* for lease break notifications */
 	unsigned long fl_break_time;	/* for nonblocking lease breaks */
 	struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
 	struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
 	union {
 		struct nfs_lock_info	nfs_fl;
 		struct nfs4_lock_info	nfs4_fl;
 		struct {
 			struct list_head link;	/* link in AFS vnode's pending_locks list */
 			int state;		/* state of grant or error if -ve */
 		} afs;
 	} fl_u;
 };
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
 #define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
 #define OFFSET_MAX	INT_LIMIT(loff_t)
 #define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
 #endif
 #include <linux/fcntl.h>
 extern int fcntl_getlk(struct file *, struct flock __user *);
 extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
 			struct flock __user *);
 #if BITS_PER_LONG == 32
 extern int fcntl_getlk64(struct file *, struct flock64 __user *);
 extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 			struct flock64 __user *);
 #endif
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 /* fs/sync.c */
 extern int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
 			loff_t endbyte, unsigned int flags);
 /* fs/locks.c */
 extern void locks_init_lock(struct file_lock *);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_flock(struct file *);
 extern void posix_test_lock(struct file *, struct file_lock *);
 extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
 extern int posix_lock_file_wait(struct file *, struct file_lock *);
 extern int posix_unblock_lock(struct file *, struct file_lock *);
 extern int vfs_test_lock(struct file *, struct file_lock *);
 extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
 extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **);
 extern int vfs_setlease(struct file *, long, struct file_lock **);
 extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
 extern struct seq_operations locks_seq_operations;
 struct fasync_struct {
 	int	magic;
 	int	fa_fd;
 	struct	fasync_struct	*fa_next; /* singly linked list */
 	struct	file 		*fa_file;
 };
 #define FASYNC_MAGIC 0x4601
 /* SMP safe fasync helpers: */
 extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 /* only for net: no internal synchronization */
 extern void __kill_fasync(struct fasync_struct *, int, int);
 extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
 extern int f_setown(struct file *filp, unsigned long arg, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
 /*
  *	Umount options
  */
 #define MNT_FORCE	0x00000001	/* Attempt to forcibily umount */
 #define MNT_DETACH	0x00000002	/* Just detach from the tree */
 #define MNT_EXPIRE	0x00000004	/* Mark for expiry */
 extern struct list_head super_blocks;
 extern spinlock_t sb_lock;
 #define sb_entry(list)	list_entry((list), struct super_block, s_list)
 #define S_BIAS (1<<30)
 struct super_block {
 	struct list_head	s_list;		/* Keep this first */
 	dev_t			s_dev;		/* search index; _not_ kdev_t */
 	unsigned long		s_blocksize;
 	unsigned char		s_blocksize_bits;
 	unsigned char		s_dirt;
 	unsigned long long	s_maxbytes;	/* Max file size */
 	struct file_system_type	*s_type;
 	const struct super_operations	*s_op;
 	struct dquot_operations	*dq_op;
  	struct quotactl_ops	*s_qcop;
 	struct export_operations *s_export_op;
 	unsigned long		s_flags;
 	unsigned long		s_magic;
 	struct dentry		*s_root;
 	struct rw_semaphore	s_umount;
 	struct mutex		s_lock;
 	int			s_count;
 	int			s_syncing;
 	int			s_need_sync_fs;
 	atomic_t		s_active;
 #ifdef CONFIG_SECURITY
 	void                    *s_security;
 #endif
 	struct xattr_handler	**s_xattr;
 	struct list_head	s_inodes;	/* all inodes */
 	struct list_head	s_dirty;	/* dirty inodes */
 	struct list_head	s_io;		/* parked for writeback */
 	struct list_head	s_more_io;	/* parked for more writeback */
 	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 	struct list_head	s_files;
 	struct block_device	*s_bdev;
 	struct mtd_info		*s_mtd;
 	struct list_head	s_instances;
 	struct quota_info	s_dquot;	/* Diskquota specific options */
 	int			s_frozen;
 	wait_queue_head_t	s_wait_unfrozen;
 	char s_id[32];				/* Informational name */
 	void 			*s_fs_info;	/* Filesystem private info */
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
 	 * even looking at it. You had been warned.
 	 */
 	struct mutex s_vfs_rename_mutex;	/* Kludge */
 	/* Granularity of c/m/atime in ns.
 	   Cannot be worse than a second */
 	u32		   s_time_gran;
 	/*
 	 * Filesystem subtype.  If non-empty the filesystem type field
 	 * in /proc/mounts will be "type.subtype"
 	 */
 	char *s_subtype;
 };
 extern struct timespec current_fs_time(struct super_block *sb);
 /*
  * Snapshotting support.
  */
 enum {
 	SB_UNFROZEN = 0,
 	SB_FREEZE_WRITE	= 1,
 	SB_FREEZE_TRANS = 2,
 };
 #define vfs_check_frozen(sb, level) \
 	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
 #define get_fs_excl() atomic_inc(&current->fs_excl)
 #define put_fs_excl() atomic_dec(&current->fs_excl)
 #define has_fs_excl() atomic_read(&current->fs_excl)
 #define is_owner_or_cap(inode)	\
 	((current->fsuid == (inode)->i_uid) || capable(CAP_FOWNER))
 /* not quite ready to be deprecated, but... */
 extern void lock_super(struct super_block *);
 extern void unlock_super(struct super_block *);
 /*
  * VFS helper functions..
  */
 extern int vfs_permission(struct nameidata *, int);
 extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *);
 extern int vfs_mkdir(struct inode *, struct dentry *, int);
 extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *, int);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
 /*
  * VFS dentry helper functions.
  */
 extern void dentry_unhash(struct dentry *dentry);
 /*
  * VFS file helper functions.
  */
 extern int file_permission(struct file *, int);
 /*
  * File types
  *
  * NOTE! These match bits 12..15 of stat.st_mode
  * (ie "(i_mode >> 12) & 15").
  */
 #define DT_UNKNOWN	0
 #define DT_FIFO		1
 #define DT_CHR		2
 #define DT_DIR		4
 #define DT_BLK		6
 #define DT_REG		8
 #define DT_LNK		10
 #define DT_SOCK		12
 #define DT_WHT		14
 #define OSYNC_METADATA	(1<<0)
 #define OSYNC_DATA	(1<<1)
 #define OSYNC_INODE	(1<<2)
 int generic_osync_inode(struct inode *, struct address_space *, int);
 /*
  * This is the "filldir" function type, used by readdir() to let
  * the kernel specify what kind of dirent layout it wants to have.
  * This allows the kernel to read directories into kernel space or
  * to have different dirent layouts depending on the binary type.
  */
 typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
 struct block_device_operations {
 	int (*open) (struct inode *, struct file *);
 	int (*release) (struct inode *, struct file *);
 	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
 	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t, unsigned long *);
 	int (*media_changed) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
 	struct module *owner;
 };
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
  * have multiple different users of the data that
  * we read from a file.
  *
  * The simplest case just copies the data to user
  * mode.
  */
 typedef struct {
 	size_t written;
 	size_t count;
 	union {
 		char __user * buf;
 		void *data;
 	} arg;
 	int error;
 } read_descriptor_t;
 typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);
 /* These macros are for out of kernel modules to test that
  * the kernel supports the unlocked_ioctl and compat_ioctl
  * fields in struct file_operations. */
 #define HAVE_COMPAT_IOCTL 1
 #define HAVE_UNLOCKED_IOCTL 1
 /*
  * NOTE:
  * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl
  * can be called without the big kernel lock held in all filesystems.
  */
 struct file_operations {
 	struct module *owner;
 	loff_t (*llseek) (struct file *, loff_t, int);
 	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	int (*readdir) (struct file *, void *, filldir_t);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
 	int (*fsync) (struct file *, struct dentry *, int datasync);
 	int (*aio_fsync) (struct kiocb *, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
 	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
 	int (*dir_notify)(struct file *filp, unsigned long arg);
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
 	int (*setlease)(struct file *, long, struct file_lock **);
 };
 struct inode_operations {
 	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
 	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
 	int (*link) (struct dentry *,struct inode *,struct dentry *);
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct inode *,struct dentry *,const char *);
 	int (*mkdir) (struct inode *,struct dentry *,int);
 	int (*rmdir) (struct inode *,struct dentry *);
 	int (*mknod) (struct inode *,struct dentry *,int,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
 	int (*readlink) (struct dentry *, char __user *,int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, struct nameidata *);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
 	void (*truncate_range)(struct inode *, loff_t, loff_t);
 	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
 			  loff_t len);
 };
 struct seq_file;
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 				unsigned long nr_segs, unsigned long fast_segs,
 				struct iovec *fast_pointer,
 				struct iovec **ret_pointer);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
 extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
 /*
  * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called
  * without the big kernel lock held in all filesystems.
  */
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
 	void (*read_inode) (struct inode *);
    	void (*dirty_inode) (struct inode *);
 	int (*write_inode) (struct inode *, int);
 	void (*put_inode) (struct inode *);
 	void (*drop_inode) (struct inode *);
 	void (*delete_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	void (*write_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
 	void (*write_super_lockfs) (struct super_block *);
 	void (*unlockfs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
 	void (*clear_inode) (struct inode *);
 	void (*umount_begin) (struct vfsmount *, int);
 	int (*show_options)(struct seq_file *, struct vfsmount *);
 	int (*show_stats)(struct seq_file *, struct vfsmount *);
 #ifdef CONFIG_QUOTA
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
 };
 /* Inode state bits.  Protected by inode_lock. */
 #define I_DIRTY_SYNC		1 /* Not dirty enough for O_DATASYNC */
 #define I_DIRTY_DATASYNC	2 /* Data-related inode changes pending */
 #define I_DIRTY_PAGES		4 /* Data-related inode changes pending */
 #define __I_LOCK		3
 #define I_LOCK			(1 << __I_LOCK)
 #define I_FREEING		16
 #define I_CLEAR			32
 #define I_NEW			64
 #define I_WILL_FREE		128
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 extern void __mark_inode_dirty(struct inode *, int);
 static inline void mark_inode_dirty(struct inode *inode)
 {
 	__mark_inode_dirty(inode, I_DIRTY);
 }
 static inline void mark_inode_dirty_sync(struct inode *inode)
 {
 	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 }
 /**
  * inc_nlink - directly increment an inode's link count
  * @inode: inode
  *
  * This is a low-level filesystem helper to replace any
  * direct filesystem manipulation of i_nlink.  Currently,
  * it is only here for parity with dec_nlink().
  */
 static inline void inc_nlink(struct inode *inode)
 {
 	inode->i_nlink++;
 }
 static inline void inode_inc_link_count(struct inode *inode)
 {
 	inc_nlink(inode);
 	mark_inode_dirty(inode);
 }
 /**
  * drop_nlink - directly drop an inode's link count
  * @inode: inode
  *
  * This is a low-level filesystem helper to replace any
  * direct filesystem manipulation of i_nlink.  In cases
  * where we are attempting to track writes to the
  * filesystem, a decrement to zero means an imminent
  * write when the file is truncated and actually unlinked
  * on the filesystem.
  */
 static inline void drop_nlink(struct inode *inode)
 {
 	inode->i_nlink--;
 }
 /**
  * clear_nlink - directly zero an inode's link count
  * @inode: inode
  *
  * This is a low-level filesystem helper to replace any
  * direct filesystem manipulation of i_nlink.  See
  * drop_nlink() for why we care about i_nlink hitting zero.
  */
 static inline void clear_nlink(struct inode *inode)
 {
 	inode->i_nlink = 0;
 }
 static inline void inode_dec_link_count(struct inode *inode)
 {
 	drop_nlink(inode);
 	mark_inode_dirty(inode);
 }
 extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
 static inline void file_accessed(struct file *file)
 {
 	if (!(file->f_flags & O_NOATIME))
 		touch_atime(file->f_path.mnt, file->f_path.dentry);
 }
 int sync_inode(struct inode *inode, struct writeback_control *wbc);
 struct file_system_type {
 	const char *name;
 	int fs_flags;
 	int (*get_sb) (struct file_system_type *, int,
 		       const char *, void *, struct vfsmount *);
 	void (*kill_sb) (struct super_block *);
 	struct module *owner;
 	struct file_system_type * next;
 	struct list_head fs_supers;
 	struct lock_class_key s_lock_key;
 	struct lock_class_key s_umount_key;
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
 	struct lock_class_key i_mutex_dir_key;
 	struct lock_class_key i_alloc_sem_key;
 };
 extern int get_sb_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int),
 	struct vfsmount *mnt);
 extern int get_sb_single(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int),
 	struct vfsmount *mnt);
 extern int get_sb_nodev(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int),
 	struct vfsmount *mnt);
 void generic_shutdown_super(struct super_block *sb);
 void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
 void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
 int set_anon_super(struct super_block *s, void *data);
 struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
 			void *data);
 extern int get_sb_pseudo(struct file_system_type *, char *,
 	const struct super_operations *ops, unsigned long,
 	struct vfsmount *mnt);
 extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 int __put_super(struct super_block *sb);
 int __put_super_and_need_restart(struct super_block *sb);
 void unnamed_dev_init(void);
 /* Alas, no aliases. Too much hassle with bringing module.h everywhere */
 #define fops_get(fops) \
 	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
 #define fops_put(fops) \
 	do { if (fops) module_put((fops)->owner); } while(0)
 extern int register_filesystem(struct file_system_type *);
 extern int unregister_filesystem(struct file_system_type *);
 extern struct vfsmount *kern_mount(struct file_system_type *);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 extern void umount_tree(struct vfsmount *, int, struct list_head *);
 extern void release_mounts(struct list_head *);
 extern long do_mount(char *, char *, char *, unsigned long, void *);
 extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
 extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
 				  struct vfsmount *);
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
 /* /sys/fs */
 extern struct kset fs_subsys;
 #define FLOCK_VERIFY_READ  1
 #define FLOCK_VERIFY_WRITE 2
 extern int locks_mandatory_locked(struct inode *);
 extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
 /*
  * Candidates for mandatory locking have the setgid bit set
  * but no group execute bit -  an otherwise meaningless combination.
  */
 static inline int __mandatory_lock(struct inode *ino)
 {
 	return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
 }
 /*
  * ... and these candidates should be on MS_MANDLOCK mounted fs,
  * otherwise these will be advisory locks
  */
 static inline int mandatory_lock(struct inode *ino)
 {
 	return IS_MANDLOCK(ino) && __mandatory_lock(ino);
 }
 static inline int locks_verify_locked(struct inode *inode)
 {
 	if (mandatory_lock(inode))
 		return locks_mandatory_locked(inode);
 	return 0;
 }
 extern int rw_verify_area(int, struct file *, loff_t *, size_t);
 static inline int locks_verify_truncate(struct inode *inode,
 				    struct file *filp,
 				    loff_t size)
 {
 	if (inode->i_flock && mandatory_lock(inode))
 		return locks_mandatory_area(
 			FLOCK_VERIFY_WRITE, inode, filp,
 			size < inode->i_size ? size : inode->i_size,
 			(size < inode->i_size ? inode->i_size - size
 			 : size - inode->i_size)
 		);
 	return 0;
 }
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	if (inode->i_flock)
 		return __break_lease(inode, mode);
 	return 0;
 }
 /* fs/open.c */
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
 extern long do_sys_open(int fdf, const char __user *filename, int flags,
 			int mode);
 extern struct file *filp_open(const char *, int, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int);
 extern int filp_close(struct file *, fl_owner_t id);
 extern char * getname(const char __user *);
 /* fs/dcache.c */
 extern void __init vfs_caches_init_early(void);
 extern void __init vfs_caches_init(unsigned long);
 extern struct kmem_cache *names_cachep;
 #define __getname()	kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
 #ifndef CONFIG_AUDITSYSCALL
 #define putname(name)   __putname(name)
 #else
 extern void putname(const char *name);
 #endif
 #ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
 extern void unregister_blkdev(unsigned int, const char *);
 extern struct block_device *bdget(dev_t);
 extern void bd_set_size(struct block_device *, loff_t size);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
 extern struct block_device *open_by_devnum(dev_t, unsigned);
 extern const struct address_space_operations def_blk_aops;
 #else
 static inline void bd_forget(struct inode *inode) {}
 #endif
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
 extern const struct file_operations bad_sock_fops;
 extern const struct file_operations def_fifo_fops;
 #ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
 extern int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 			       struct gendisk *disk, unsigned cmd,
 			       unsigned long arg);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
 extern int blkdev_get(struct block_device *, mode_t, unsigned);
 extern int blkdev_put(struct block_device *);
 extern int bd_claim(struct block_device *, void *);
 extern void bd_release(struct block_device *);
 #ifdef CONFIG_SYSFS
 extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *);
 extern void bd_release_from_disk(struct block_device *, struct gendisk *);
 #else
 #define bd_claim_by_disk(bdev, holder, disk)	bd_claim(bdev, holder)
 #define bd_release_from_disk(bdev, disk)	bd_release(bdev)
 #endif
 #endif
 /* fs/char_dev.c */
 #define CHRDEV_MAJOR_HASH_SIZE	255
 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
 extern int register_chrdev_region(dev_t, unsigned, const char *);
 extern int register_chrdev(unsigned int, const char *,
 			   const struct file_operations *);
 extern void unregister_chrdev(unsigned int, const char *);
 extern void unregister_chrdev_region(dev_t, unsigned);
 extern int chrdev_open(struct inode *, struct file *);
 extern void chrdev_show(struct seq_file *,off_t);
 /* fs/block_dev.c */
 #define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
 #ifdef CONFIG_BLOCK
 #define BLKDEV_MAJOR_HASH_SIZE	255
 extern const char *__bdevname(dev_t, char *buffer);
 extern const char *bdevname(struct block_device *bdev, char *buffer);
 extern struct block_device *lookup_bdev(const char *);
 extern struct block_device *open_bdev_excl(const char *, int, void *);
 extern void close_bdev_excl(struct block_device *);
 extern void blkdev_show(struct seq_file *,off_t);
 #else
 #define BLKDEV_MAJOR_HASH_SIZE	0
 #endif
 extern void init_special_inode(struct inode *, umode_t, dev_t);
 /* Invalid inode operations -- fs/bad_inode.c */
 extern void make_bad_inode(struct inode *);
 extern int is_bad_inode(struct inode *);
 extern const struct file_operations read_fifo_fops;
 extern const struct file_operations write_fifo_fops;
 extern const struct file_operations rdwr_fifo_fops;
 extern int fs_may_remount_ro(struct super_block *);
 #ifdef CONFIG_BLOCK
 /*
  * return READ, READA, or WRITE
  */
 #define bio_rw(bio)		((bio)->bi_rw & (RW_MASK | RWA_MASK))
 /*
  * return data direction, READ or WRITE
  */
 #define bio_data_dir(bio)	((bio)->bi_rw & 1)
 extern int check_disk_change(struct block_device *);
 extern int __invalidate_device(struct block_device *);
 extern int invalidate_partition(struct gendisk *, int);
 #endif
 extern int invalidate_inodes(struct super_block *);
 unsigned long __invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end,
 					bool be_atomic);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 static inline unsigned long __deprecated
 invalidate_inode_pages(struct address_space *mapping)
 {
 	return invalidate_mapping_pages(mapping, 0, ~0UL);
 }
 static inline void invalidate_remote_inode(struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	    S_ISLNK(inode->i_mode))
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 }
 extern int invalidate_inode_pages2(struct address_space *mapping);
 extern int invalidate_inode_pages2_range(struct address_space *mapping,
 					 pgoff_t start, pgoff_t end);
 extern int write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_flush(struct address_space *);
 extern int filemap_fdatawait(struct address_space *);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
 extern int wait_on_page_writeback_range(struct address_space *mapping,
 				pgoff_t start, pgoff_t end);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end, int sync_mode);
 extern long do_fsync(struct file *file, int datasync);
 extern void sync_supers(void);
 extern void sync_filesystems(int wait);
 extern void __fsync_super(struct super_block *sb);
 extern void emergency_sync(void);
 extern void emergency_remount(void);
 extern int do_remount_sb(struct super_block *sb, int flags,
 			 void *data, int force);
 #ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *);
 extern int permission(struct inode *, int, struct nameidata *);
 extern int generic_permission(struct inode *, int,
 		int (*check_acl)(struct inode *, int));
 extern int get_write_access(struct inode *);
 extern int deny_write_access(struct file *);
 static inline void put_write_access(struct inode * inode)
 {
 	atomic_dec(&inode->i_writecount);
 }
 static inline void allow_write_access(struct file *file)
 {
 	if (file)
 		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 }
 extern int do_pipe(int *);
 extern struct file *create_read_pipe(struct file *f);
 extern struct file *create_write_pipe(void);
 extern void free_write_pipe(struct file *);
 extern int open_namei(int dfd, const char *, int, int, struct nameidata *);
 extern int may_open(struct nameidata *, int, int);
 extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
 extern struct file * open_exec(const char *);
 /* fs/dcache.c -- generic fs support functions */
 extern int is_subdir(struct dentry *, struct dentry *);
 extern ino_t find_inode_number(struct dentry *, struct qstr *);
 #include <linux/err.h>
 /* needed for stackable file system support */
 extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 extern void inode_init_once(struct inode *);
 extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
 extern ino_t iunique(struct super_block *, ino_t);
 extern int inode_needs_sync(struct inode *inode);
 extern void generic_delete_inode(struct inode *inode);
 extern void generic_drop_inode(struct inode *inode);
 extern struct inode *ilookup5_nowait(struct super_block *sb,
 		unsigned long hashval, int (*test)(struct inode *, void *),
 		void *data);
 extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
 		int (*test)(struct inode *, void *), void *data);
 extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
 extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
 extern struct inode * iget_locked(struct super_block *, unsigned long);
 extern void unlock_new_inode(struct inode *);
 static inline struct inode *iget(struct super_block *sb, unsigned long ino)
 {
 	struct inode *inode = iget_locked(sb, ino);
 	if (inode && (inode->i_state & I_NEW)) {
 		sb->s_op->read_inode(inode);
 		unlock_new_inode(inode);
 	}
 	return inode;
 }
 extern void __iget(struct inode * inode);
 extern void clear_inode(struct inode *);
 extern void destroy_inode(struct inode *);
 extern struct inode *new_inode(struct super_block *);
 extern int __remove_suid(struct dentry *, int);
 extern int should_remove_suid(struct dentry *);
 extern int remove_suid(struct dentry *);
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
 extern void remove_inode_hash(struct inode *);
 static inline void insert_inode_hash(struct inode *inode) {
 	__insert_inode_hash(inode, inode->i_ino);
 }
 extern struct file * get_empty_filp(void);
 extern void file_move(struct file *f, struct list_head *list);
 extern void file_kill(struct file *f);
 #ifdef CONFIG_BLOCK
 struct bio;
 extern void submit_bio(int, struct bio *);
 extern int bdev_read_only(struct block_device *);
 #endif
 extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
+extern int sb_has_dirty_inodes(struct super_block *);
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
 		unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, loff_t *, size_t, size_t);
 extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
 		unsigned long, loff_t, loff_t *, size_t, ssize_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 extern void do_generic_mapping_read(struct address_space *mapping,
 				    struct file_ra_state *, struct file *,
 				    loff_t *, read_descriptor_t *, read_actor_t);
 extern int generic_segment_checks(const struct iovec *iov,
 		unsigned long *nr_segs, size_t *count, int access_flags);
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
 extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 		size_t len, unsigned int flags);
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
 extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 #ifdef CONFIG_FS_XIP
 extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
 			     loff_t *ppos);
 extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
 extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
 			      size_t len, loff_t *ppos);
 extern int xip_truncate_page(struct address_space *mapping, loff_t from);
 #else
 static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
 {
 	return 0;
 }
 #endif
 static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
 					read_descriptor_t * desc,
 					read_actor_t actor)
 {
 	do_generic_mapping_read(filp->f_mapping,
 				&filp->f_ra,
 				filp,
 				ppos,
 				desc,
 				actor);
 }
 #ifdef CONFIG_BLOCK
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	struct block_device *bdev, const struct iovec *iov, loff_t offset,
 	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
 	int lock_type);
 enum {
 	DIO_LOCKING = 1, /* need locking between buffered and direct access */
 	DIO_NO_LOCKING,  /* bdev; no locking at all between buffered/direct */
 	DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */
 };
 static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
 	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
 	loff_t offset, unsigned long nr_segs, get_block_t get_block,
 	dio_iodone_t end_io)
 {
 	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
 				nr_segs, get_block, end_io, DIO_LOCKING);
 }
 static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
 	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
 	loff_t offset, unsigned long nr_segs, get_block_t get_block,
 	dio_iodone_t end_io)
 {
 	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
 				nr_segs, get_block, end_io, DIO_NO_LOCKING);
 }
 static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
 	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
 	loff_t offset, unsigned long nr_segs, get_block_t get_block,
 	dio_iodone_t end_io)
 {
 	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
 				nr_segs, get_block, end_io, DIO_OWN_LOCKING);
 }
 #endif
 extern const struct file_operations generic_ro_fops;
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
 extern int vfs_follow_link(struct nameidata *, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);
 extern int __page_symlink(struct inode *inode, const char *symname, int len,
 		gfp_t gfp_mask);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern int generic_readlink(struct dentry *, char __user *, int);
 extern void generic_fillattr(struct inode *, struct kstat *);
 extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 void inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_sub_bytes(struct inode *inode, loff_t bytes);
 loff_t inode_get_bytes(struct inode *inode);
 void inode_set_bytes(struct inode *inode, loff_t bytes);
 extern int vfs_readdir(struct file *, filldir_t, void *);
 extern int vfs_stat(char __user *, struct kstat *);
 extern int vfs_lstat(char __user *, struct kstat *);
 extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
 extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
 extern int vfs_fstat(unsigned int, struct kstat *);
 extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long);
 extern struct file_system_type *get_fs_type(const char *name);
 extern struct super_block *get_super(struct block_device *);
 extern struct super_block *user_get_super(dev_t);
 extern void drop_super(struct super_block *sb);
 extern int dcache_dir_open(struct inode *, struct file *);
 extern int dcache_dir_close(struct inode *, struct file *);
 extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
 extern int dcache_readdir(struct file *, void *, filldir_t);
 extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int simple_statfs(struct dentry *, struct kstatfs *);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
 extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
 extern int simple_sync_file(struct file *, struct dentry *, int);
 extern int simple_empty(struct dentry *);
 extern int simple_readpage(struct file *file, struct page *page);
 extern int simple_prepare_write(struct file *file, struct page *page,
 			unsigned offset, unsigned to);
 extern int simple_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata);
 extern int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata);
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
 extern const struct file_operations simple_dir_operations;
 extern const struct inode_operations simple_dir_inode_operations;
 struct tree_descr { char *name; const struct file_operations *ops; int mode; };
 struct dentry *d_alloc_name(struct dentry *, const char *);
 extern int simple_fill_super(struct super_block *, int, struct tree_descr *);
 extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
 extern void simple_release_fs(struct vfsmount **mount, int *count);
 extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t);
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *);
 #else
 #define buffer_migrate_page NULL
 #endif
 extern int inode_change_ok(struct inode *, struct iattr *);
 extern int __must_check inode_setattr(struct inode *, struct iattr *);
 extern void file_update_time(struct file *file);
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;
 	spin_lock(&dentry->d_lock);
 	res = dentry->d_parent->d_inode->i_ino;
 	spin_unlock(&dentry->d_lock);
 	return res;
 }
 /* kernel/fork.c */
 extern int unshare_files(void);
 /* Transaction based IO helpers */
 /*
  * An argresp is stored in an allocated page and holds the
  * size of the argument or response, along with its content
  */
 struct simple_transaction_argresp {
 	ssize_t size;
 	char data[0];
 };
 #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
 char *simple_transaction_get(struct file *file, const char __user *buf,
 				size_t size);
 ssize_t simple_transaction_read(struct file *file, char __user *buf,
 				size_t size, loff_t *pos);
 int simple_transaction_release(struct inode *inode, struct file *file);
 static inline void simple_transaction_set(struct file *file, size_t n)
 {
 	struct simple_transaction_argresp *ar = file->private_data;
 	BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);
 	/*
 	 * The barrier ensures that ar->size will really remain zero until
 	 * ar->data is ready for reading.
 	 */
 	smp_mb();
 	ar->size = n;
 }
 /*
  * simple attribute files
  *
  * These attributes behave similar to those in sysfs:
  *
  * Writing to an attribute immediately sets a value, an open file can be
  * written to multiple times.
  *
  * Reading from an attribute creates a buffer from the value that might get
  * read with multiple read calls. When the attribute has been read
  * completely, no further read calls are possible until the file is opened
  * again.
  *
  * All attributes contain a text representation of a numeric value
  * that are accessed with the get() and set() functions.
  */
 #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt)		\
 static int __fops ## _open(struct inode *inode, struct file *file)	\
 {									\
 	__simple_attr_check_format(__fmt, 0ull);			\
 	return simple_attr_open(inode, file, __get, __set, __fmt);	\
 }									\
 static struct file_operations __fops = {				\
 	.owner	 = THIS_MODULE,						\
 	.open	 = __fops ## _open,					\
 	.release = simple_attr_close,					\
 	.read	 = simple_attr_read,					\
 	.write	 = simple_attr_write,					\
 };
 static inline void __attribute__((format(printf, 1, 2)))
 __simple_attr_check_format(const char *fmt, ...)
 {
 	/* don't do anything, just let the compiler check the arguments; */
 }
 int simple_attr_open(struct inode *inode, struct file *file,
 		     u64 (*get)(void *), void (*set)(void *, u64),
 		     const char *fmt);
 int simple_attr_close(struct inode *inode, struct file *file);
 ssize_t simple_attr_read(struct file *file, char __user *buf,
 			 size_t len, loff_t *ppos);
 ssize_t simple_attr_write(struct file *file, const char __user *buf,
 			  size_t len, loff_t *ppos);
 #ifdef CONFIG_SECURITY
 static inline char *alloc_secdata(void)
 {
 	return (char *)get_zeroed_page(GFP_KERNEL);
 }
 static inline void free_secdata(void *secdata)
 {
 	free_page((unsigned long)secdata);
 }
 #else
 static inline char *alloc_secdata(void)
 {
 	return (char *)1;
 }
 static inline void free_secdata(void *secdata)
 { }
 #endif	/* CONFIG_SECURITY */
 struct ctl_table;
 int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */