Merge /spare/repo/linux-2.6/

20 files changed, 1075 insertions, 448 deletions

diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog
index 9eecc9939df..49eafbdb15c 100644
--- a/fs/ntfs/ChangeLog
+++ b/fs/ntfs/ChangeLog
@@ -22,6 +22,77 @@ ToDo/Notes:
 	- Enable the code for setting the NT4 compatibility flag when we start
 	  making NTFS 1.2 specific modifications.
 
+2.1.24 - Lots of bug fixes and support more clean journal states.
+
+	- Support journals ($LogFile) which have been modified by chkdsk.  This
+	  means users can boot into Windows after we marked the volume dirty.
+	  The Windows boot will run chkdsk and then reboot.  The user can then
+	  immediately boot into Linux rather than having to do a full Windows
+	  boot first before rebooting into Linux and we will recognize such a
+	  journal and empty it as it is clean by definition.
+	- Support journals ($LogFile) with only one restart page as well as
+	  journals with two different restart pages.  We sanity check both and
+	  either use the only sane one or the more recent one of the two in the
+	  case that both are valid.
+	- Add fs/ntfs/malloc.h::ntfs_malloc_nofs_nofail() which is analogous to
+	  ntfs_malloc_nofs() but it performs allocations with __GFP_NOFAIL and
+	  hence cannot fail.
+	- Use ntfs_malloc_nofs_nofail() in the two critical regions in
+	  fs/ntfs/runlist.c::ntfs_runlists_merge().  This means we no longer
+	  need to panic() if the allocation fails as it now cannot fail.
+	- Fix two nasty runlist merging bugs that had gone unnoticed so far.
+	  Thanks to Stefano Picerno for the bug report.
+	- Remove two bogus BUG_ON()s from fs/ntfs/mft.c.
+	- Fix handling of valid but empty mapping pairs array in
+	  fs/ntfs/runlist.c::ntfs_mapping_pairs_decompress().
+	- Report unrepresentable inodes during ntfs_readdir() as KERN_WARNING
+	  messages and include the inode number.  Thanks to Yura Pakhuchiy for
+	  pointing this out.
+	- Change ntfs_rl_truncate_nolock() to throw away the runlist if the new
+	  length is zero.
+	- Add runlist.[hc]::ntfs_rl_punch_nolock() which punches a caller
+	  specified hole into a runlist.
+	- Fix a bug in fs/ntfs/index.c::ntfs_index_lookup().  When the returned
+	  index entry is in the index root, we forgot to set the @ir pointer in
+	  the index context.  Thanks to Yura Pakhuchiy for finding this bug.
+	- Remove bogus setting of PageError in ntfs_read_compressed_block().
+	- Add fs/ntfs/attrib.[hc]::ntfs_resident_attr_value_resize().
+	- Fix a bug in ntfs_map_runlist_nolock() where we forgot to protect
+	  access to the allocated size in the ntfs inode with the size lock.
+	- Fix ntfs_attr_vcn_to_lcn_nolock() and ntfs_attr_find_vcn_nolock() to
+	  return LCN_ENOENT when there is no runlist and the allocated size is
+	  zero.
+	- Fix load_attribute_list() to handle the case of a NULL runlist.
+	- Fix handling of sparse attributes in ntfs_attr_make_non_resident().
+	- Add BUG() checks to ntfs_attr_make_non_resident() and ntfs_attr_set()
+	  to ensure that these functions are never called for compressed or
+	  encrypted attributes.
+	- Fix cluster (de)allocators to work when the runlist is NULL and more
+	  importantly to take a locked runlist rather than them locking it
+	  which leads to lock reversal.
+	- Truncate {a,c,m}time to the ntfs supported time granularity when
+	  updating the times in the inode in ntfs_setattr().
+	- Fixup handling of sparse, compressed, and encrypted attributes in
+	  fs/ntfs/inode.c::ntfs_read_locked_{,attr_,index_}inode(),
+	  fs/ntfs/aops.c::ntfs_{read,write}page().
+	- Make ntfs_write_block() not instantiate sparse blocks if they contain
+	  only zeroes.
+	- Optimize fs/ntfs/aops.c::ntfs_write_block() by extending the page
+	  lock protection over the buffer submission for i/o which allows the
+	  removal of the get_bh()/put_bh() pairs for each buffer.
+	- Fix fs/ntfs/aops.c::ntfs_{read,write}_block() to handle the case
+	  where a concurrent truncate has truncated the runlist under our feet.
+	- Fix page_has_buffers()/page_buffers() handling in fs/ntfs/aops.c.
+	- In fs/ntfs/aops.c::ntfs_end_buffer_async_read(), use a bit spin lock
+	  in the first buffer head instead of a driver global spin lock to
+	  improve scalability.
+	- Minor fix to error handling and error message display in
+	  fs/ntfs/aops.c::ntfs_prepare_nonresident_write().
+	- Change the mount options {u,f,d}mask to always parse the number as
+	  an octal number to conform to how chmod(1) works, too.  Thanks to
+	  Giuseppe Bilotta and Horst von Brand for pointing out the errors of
+	  my ways.
+
 2.1.23 - Implement extension of resident files and make writing safe as well as
 	 many bug fixes, cleanups, and enhancements...
 
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index f083f27d8b6..894b2b876d3 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -6,7 +6,7 @@ ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
 	     index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
 	     unistr.o upcase.o
 
-EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.23\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.24\"
 
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 78adad7a988..b6cc8cf2462 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -27,6 +27,7 @@
 #include <linux/swap.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/bit_spinlock.h>
 
 #include "aops.h"
 #include "attrib.h"
@@ -55,9 +56,8 @@
  */
 static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 {
-	static DEFINE_SPINLOCK(page_uptodate_lock);
 	unsigned long flags;
-	struct buffer_head *tmp;
+	struct buffer_head *first, *tmp;
 	struct page *page;
 	ntfs_inode *ni;
 	int page_uptodate = 1;
@@ -89,11 +89,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 	} else {
 		clear_buffer_uptodate(bh);
+		SetPageError(page);
 		ntfs_error(ni->vol->sb, "Buffer I/O error, logical block %llu.",
 				(unsigned long long)bh->b_blocknr);
-		SetPageError(page);
 	}
-	spin_lock_irqsave(&page_uptodate_lock, flags);
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -108,7 +110,8 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	/*
 	 * If none of the buffers had errors then we can set the page uptodate,
 	 * but we first have to perform the post read mst fixups, if the
@@ -141,7 +144,8 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	unlock_page(page);
 	return;
 still_busy:
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	return;
 }
 
@@ -185,13 +189,15 @@ static int ntfs_read_block(struct page *page)
 	blocksize_bits = VFS_I(ni)->i_blkbits;
 	blocksize = 1 << blocksize_bits;
 
-	if (!page_has_buffers(page))
+	if (!page_has_buffers(page)) {
 		create_empty_buffers(page, blocksize, 0);
-	bh = head = page_buffers(page);
-	if (unlikely(!bh)) {
-		unlock_page(page);
-		return -ENOMEM;
+		if (unlikely(!page_has_buffers(page))) {
+			unlock_page(page);
+			return -ENOMEM;
+		}
 	}
+	bh = head = page_buffers(page);
+	BUG_ON(!bh);
 
 	iblock = (s64)page->index << (PAGE_CACHE_SHIFT - blocksize_bits);
 	read_lock_irqsave(&ni->size_lock, flags);
@@ -204,6 +210,7 @@ static int ntfs_read_block(struct page *page)
 	nr = i = 0;
 	do {
 		u8 *kaddr;
+		int err;
 
 		if (unlikely(buffer_uptodate(bh)))
 			continue;
@@ -211,6 +218,7 @@ static int ntfs_read_block(struct page *page)
 			arr[nr++] = bh;
 			continue;
 		}
+		err = 0;
 		bh->b_bdev = vol->sb->s_bdev;
 		/* Is the block within the allowed limits? */
 		if (iblock < lblock) {
@@ -252,7 +260,6 @@ lock_retry_remap:
 				goto handle_hole;
 			/* If first try and runlist unmapped, map and retry. */
 			if (!is_retry && lcn == LCN_RL_NOT_MAPPED) {
-				int err;
 				is_retry = TRUE;
 				/*
 				 * Attempt to map runlist, dropping lock for
@@ -263,20 +270,30 @@ lock_retry_remap:
 				if (likely(!err))
 					goto lock_retry_remap;
 				rl = NULL;
-				lcn = err;
 			} else if (!rl)
 				up_read(&ni->runlist.lock);
+			/*
+			 * If buffer is outside the runlist, treat it as a
+			 * hole.  This can happen due to concurrent truncate
+			 * for example.
+			 */
+			if (err == -ENOENT || lcn == LCN_ENOENT) {
+				err = 0;
+				goto handle_hole;
+			}
 			/* Hard error, zero out region. */
+			if (!err)
+				err = -EIO;
 			bh->b_blocknr = -1;
 			SetPageError(page);
 			ntfs_error(vol->sb, "Failed to read from inode 0x%lx, "
 					"attribute type 0x%x, vcn 0x%llx, "
 					"offset 0x%x because its location on "
 					"disk could not be determined%s "
-					"(error code %lli).", ni->mft_no,
+					"(error code %i).", ni->mft_no,
 					ni->type, (unsigned long long)vcn,
 					vcn_ofs, is_retry ? " even after "
-					"retrying" : "", (long long)lcn);
+					"retrying" : "", err);
 		}
 		/*
 		 * Either iblock was outside lblock limits or
@@ -289,9 +306,10 @@ handle_hole:
 handle_zblock:
 		kaddr = kmap_atomic(page, KM_USER0);
 		memset(kaddr + i * blocksize, 0, blocksize);
-		flush_dcache_page(page);
 		kunmap_atomic(kaddr, KM_USER0);
-		set_buffer_uptodate(bh);
+		flush_dcache_page(page);
+		if (likely(!err))
+			set_buffer_uptodate(bh);
 	} while (i++, iblock++, (bh = bh->b_this_page) != head);
 
 	/* Release the lock if we took it. */
@@ -367,31 +385,38 @@ retry_readpage:
 		return 0;
 	}
 	ni = NTFS_I(page->mapping->host);
-
+	/*
+	 * Only $DATA attributes can be encrypted and only unnamed $DATA
+	 * attributes can be compressed.  Index root can have the flags set but
+	 * this means to create compressed/encrypted files, not that the
+	 * attribute is compressed/encrypted.
+	 */
+	if (ni->type != AT_INDEX_ROOT) {
+		/* If attribute is encrypted, deny access, just like NT4. */
+		if (NInoEncrypted(ni)) {
+			BUG_ON(ni->type != AT_DATA);
+			err = -EACCES;
+			goto err_out;
+		}
+		/* Compressed data streams are handled in compress.c. */
+		if (NInoNonResident(ni) && NInoCompressed(ni)) {
+			BUG_ON(ni->type != AT_DATA);
+			BUG_ON(ni->name_len);
+			return ntfs_read_compressed_block(page);
+		}
+	}
 	/* NInoNonResident() == NInoIndexAllocPresent() */
 	if (NInoNonResident(ni)) {
-		/*
-		 * Only unnamed $DATA attributes can be compressed or
-		 * encrypted.
-		 */
-		if (ni->type == AT_DATA && !ni->name_len) {
-			/* If file is encrypted, deny access, just like NT4. */
-			if (NInoEncrypted(ni)) {
-				err = -EACCES;
-				goto err_out;
-			}
-			/* Compressed data streams are handled in compress.c. */
-			if (NInoCompressed(ni))
-				return ntfs_read_compressed_block(page);
-		}
-		/* Normal data stream. */
+		/* Normal, non-resident data stream. */
 		return ntfs_read_block(page);
 	}
 	/*
 	 * Attribute is resident, implying it is not compressed or encrypted.
 	 * This also means the attribute is smaller than an mft record and
 	 * hence smaller than a page, so can simply zero out any pages with
-	 * index above 0.
+	 * index above 0.  Note the attribute can actually be marked compressed
+	 * but if it is resident the actual data is not compressed so we are
+	 * ok to ignore the compressed flag here.
 	 */
 	if (unlikely(page->index > 0)) {
 		kaddr = kmap_atomic(page, KM_USER0);
@@ -511,19 +536,21 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc)
 		BUG_ON(!PageUptodate(page));
 		create_empty_buffers(page, blocksize,
 				(1 << BH_Uptodate) | (1 << BH_Dirty));
+		if (unlikely(!page_has_buffers(page))) {
+			ntfs_warning(vol->sb, "Error allocating page "
+					"buffers.  Redirtying page so we try "
+					"again later.");
+			/*
+			 * Put the page back on mapping->dirty_pages, but leave
+			 * its buffers' dirty state as-is.
+			 */
+			redirty_page_for_writepage(wbc, page);
+			unlock_page(page);
+			return 0;
+		}
 	}
 	bh = head = page_buffers(page);
-	if (unlikely(!bh)) {
-		ntfs_warning(vol->sb, "Error allocating page buffers. "
-				"Redirtying page so we try again later.");
-		/*
-		 * Put the page back on mapping->dirty_pages, but leave its
-		 * buffer's dirty state as-is.
-		 */
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-		return 0;
-	}
+	BUG_ON(!bh);
 
 	/* NOTE: Different naming scheme to ntfs_read_block()! */
 
@@ -670,6 +697,27 @@ lock_retry_remap:
 		}
 		/* It is a hole, need to instantiate it. */
 		if (lcn == LCN_HOLE) {
+			u8 *kaddr;
+			unsigned long *bpos, *bend;
+
+			/* Check if the buffer is zero. */
+			kaddr = kmap_atomic(page, KM_USER0);
+			bpos = (unsigned long *)(kaddr + bh_offset(bh));
+			bend = (unsigned long *)((u8*)bpos + blocksize);
+			do {
+				if (unlikely(*bpos))
+					break;
+			} while (likely(++bpos < bend));
+			kunmap_atomic(kaddr, KM_USER0);
+			if (bpos == bend) {
+				/*
+				 * Buffer is zero and sparse, no need to write
+				 * it.
+				 */
+				bh->b_blocknr = -1;
+				clear_buffer_dirty(bh);
+				continue;
+			}
 			// TODO: Instantiate the hole.
 			// clear_buffer_new(bh);
 			// unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
@@ -690,20 +738,37 @@ lock_retry_remap:
 			if (likely(!err))
 				goto lock_retry_remap;
 			rl = NULL;
-			lcn = err;
 		} else if (!rl)
 			up_read(&ni->runlist.lock);
+		/*
+		 * If buffer is outside the runlist, truncate has cut it out
+		 * of the runlist.  Just clean and clear the buffer and set it
+		 * uptodate so it can get discarded by the VM.
+		 */
+		if (err == -ENOENT || lcn == LCN_ENOENT) {
+			u8 *kaddr;
+
+			bh->b_blocknr = -1;
+			clear_buffer_dirty(bh);
+			kaddr = kmap_atomic(page, KM_USER0);
+			memset(kaddr + bh_offset(bh), 0, blocksize);
+			kunmap_atomic(kaddr, KM_USER0);
+			flush_dcache_page(page);
+			set_buffer_uptodate(bh);
+			err = 0;
+			continue;
+		}
 		/* Failed to map the buffer, even after retrying. */
+		if (!err)
+			err = -EIO;
 		bh->b_blocknr = -1;
 		ntfs_error(vol->sb, "Failed to write to inode 0x%lx, "
 				"attribute type 0x%x, vcn 0x%llx, offset 0x%x "
 				"because its location on disk could not be "
-				"determined%s (error code %lli).", ni->mft_no,
+				"determined%s (error code %i).", ni->mft_no,
 				ni->type, (unsigned long long)vcn,
 				vcn_ofs, is_retry ? " even after "
-				"retrying" : "", (long long)lcn);
-		if (!err)
-			err = -EIO;
+				"retrying" : "", err);
 		break;
 	} while (block++, (bh = bh->b_this_page) != head);
 
@@ -714,7 +779,7 @@ lock_retry_remap:
 	/* For the error case, need to reset bh to the beginning. */
 	bh = head;
 
-	/* Just an optimization, so ->readpage() isn't called later. */
+	/* Just an optimization, so ->readpage() is not called later. */
 	if (unlikely(!PageUptodate(page))) {
 		int uptodate = 1;
 		do {
@@ -730,7 +795,6 @@ lock_retry_remap:
 
 	/* Setup all mapped, dirty buffers for async write i/o. */
 	do {
-		get_bh(bh);
 		if (buffer_mapped(bh) && buffer_dirty(bh)) {
 			lock_buffer(bh);
 			if (test_clear_buffer_dirty(bh)) {
@@ -768,14 +832,8 @@ lock_retry_remap:
 
 	BUG_ON(PageWriteback(page));
 	set_page_writeback(page);	/* Keeps try_to_free_buffers() away. */
-	unlock_page(page);
 
-	/*
-	 * Submit the prepared buffers for i/o. Note the page is unlocked,
-	 * and the async write i/o completion handler can end_page_writeback()
-	 * at any time after the *first* submit_bh(). So the buffers can then
-	 * disappear...
-	 */
+	/* Submit the prepared buffers for i/o. */
 	need_end_writeback = TRUE;
 	do {
 		struct buffer_head *next = bh->b_this_page;
@@ -783,9 +841,9 @@ lock_retry_remap:
 			submit_bh(WRITE, bh);
 			need_end_writeback = FALSE;
 		}
-		put_bh(bh);
 		bh = next;
 	} while (bh != head);
+	unlock_page(page);
 
 	/* If no i/o was started, need to end_page_writeback(). */
 	if (unlikely(need_end_writeback))
@@ -860,7 +918,6 @@ static int ntfs_write_mst_block(struct page *page,
 	sync = (wbc->sync_mode == WB_SYNC_ALL);
 
 	/* Make sure we have mapped buffers. */
-	BUG_ON(!page_has_buffers(page));
 	bh = head = page_buffers(page);
 	BUG_ON(!bh);
 
@@ -1280,38 +1337,42 @@ retry_writepage:
 		ntfs_debug("Write outside i_size - truncated?");
 		return 0;
 	}
+	/*
+	 * Only $DATA attributes can be encrypted and only unnamed $DATA
+	 * attributes can be compressed.  Index root can have the flags set but
+	 * this means to create compressed/encrypted files, not that the
+	 * attribute is compressed/encrypted.
+	 */
+	if (ni->type != AT_INDEX_ROOT) {
+		/* If file is encrypted, deny access, just like NT4. */
+		if (NInoEncrypted(ni)) {
+			unlock_page(page);
+			BUG_ON(ni->type != AT_DATA);
+			ntfs_debug("Denying write access to encrypted "
+					"file.");
+			return -EACCES;
+		}
+		/* Compressed data streams are handled in compress.c. */
+		if (NInoNonResident(ni) && NInoCompressed(ni)) {
+			BUG_ON(ni->type != AT_DATA);
+			BUG_ON(ni->name_len);
+			// TODO: Implement and replace this with
+			// return ntfs_write_compressed_block(page);
+			unlock_page(page);
+			ntfs_error(vi->i_sb, "Writing to compressed files is "
+					"not supported yet.  Sorry.");
+			return -EOPNOTSUPP;
+		}
+		// TODO: Implement and remove this check.
+		if (NInoNonResident(ni) && NInoSparse(ni)) {
+			unlock_page(page);
+			ntfs_error(vi->i_sb, "Writing to sparse files is not "
+					"supported yet.  Sorry.");
+			return -EOPNOTSUPP;
+		}
+	}
 	/* NInoNonResident() == NInoIndexAllocPresent() */
 	if (NInoNonResident(ni)) {
-		/*
-		 * Only unnamed $DATA attributes can be compressed, encrypted,
-		 * and/or sparse.
-		 */
-		if (ni->type == AT_DATA && !ni->name_len) {
-			/* If file is encrypted, deny access, just like NT4. */
-			if (NInoEncrypted(ni)) {
-				unlock_page(page);
-				ntfs_debug("Denying write access to encrypted "
-						"file.");
-				return -EACCES;
-			}
-			/* Compressed data streams are handled in compress.c. */
-			if (NInoCompressed(ni)) {
-				// TODO: Implement and replace this check with
-				// return ntfs_write_compressed_block(page);
-				unlock_page(page);
-				ntfs_error(vi->i_sb, "Writing to compressed "
-						"files is not supported yet. "
-						"Sorry.");
-				return -EOPNOTSUPP;
-			}
-			// TODO: Implement and remove this check.
-			if (NInoSparse(ni)) {
-				unlock_page(page);
-				ntfs_error(vi->i_sb, "Writing to sparse files "
-						"is not supported yet. Sorry.");
-				return -EOPNOTSUPP;
-			}
-		}
 		/* We have to zero every time due to mmap-at-end-of-file. */
 		if (page->index >= (i_size >> PAGE_CACHE_SHIFT)) {
 			/* The page straddles i_size. */
@@ -1324,14 +1385,16 @@ retry_writepage:
 		/* Handle mst protected attributes. */
 		if (NInoMstProtected(ni))
 			return ntfs_write_mst_block(page, wbc);
-		/* Normal data stream. */
+		/* Normal, non-resident data stream. */
 		return ntfs_write_block(page, wbc);
 	}
 	/*
-	 * Attribute is resident, implying it is not compressed, encrypted,
-	 * sparse, or mst protected.  This also means the attribute is smaller
-	 * than an mft record and hence smaller than a page, so can simply
-	 * return error on any pages with index above 0.
+	 * Attribute is resident, implying it is not compressed, encrypted, or
+	 * mst protected.  This also means the attribute is smaller than an mft
+	 * record and hence smaller than a page, so can simply return error on
+	 * any pages with index above 0.  Note the attribute can actually be
+	 * marked compressed but if it is resident the actual data is not
+	 * compressed so we are ok to ignore the compressed flag here.
 	 */
 	BUG_ON(page_has_buffers(page));
 	BUG_ON(!PageUptodate(page));
@@ -1380,30 +1443,14 @@ retry_writepage:
 	BUG_ON(PageWriteback(page));
 	set_page_writeback(page);
 	unlock_page(page);
-
 	/*
-	 * Here, we don't need to zero the out of bounds area everytime because
-	 * the below memcpy() already takes care of the mmap-at-end-of-file
-	 * requirements. If the file is converted to a non-resident one, then
-	 * the code path use is switched to the non-resident one where the
-	 * zeroing happens on each ntfs_writepage() invocation.
-	 *
-	 * The above also applies nicely when i_size is decreased.
-	 *
-	 * When i_size is increased, the memory between the old and new i_size
-	 * _must_ be zeroed (or overwritten with new data). Otherwise we will
-	 * expose data to userspace/disk which should never have been exposed.
-	 *
-	 * FIXME: Ensure that i_size increases do the zeroing/overwriting and
-	 * if we cannot guarantee that, then enable the zeroing below.  If the
-	 * zeroing below is enabled, we MUST move the unlock_page() from above
-	 * to after the kunmap_atomic(), i.e. just before the
-	 * end_page_writeback().
-	 * UPDATE: ntfs_prepare/commit_write() do the zeroing on i_size
-	 * increases for resident attributes so those are ok.
-	 * TODO: ntfs_truncate(), others?
+	 * Here, we do not need to zero the out of bounds area everytime
+	 * because the below memcpy() already takes care of the
+	 * mmap-at-end-of-file requirements.  If the file is converted to a
+	 * non-resident one, then the code path use is switched to the
+	 * non-resident one where the zeroing happens on each ntfs_writepage()
+	 * invocation.
 	 */
-
 	attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);
 	i_size = i_size_read(vi);
 	if (unlikely(attr_len > i_size)) {
@@ -1681,27 +1728,25 @@ lock_retry_remap:
 					if (likely(!err))
 						goto lock_retry_remap;
 					rl = NULL;
-					lcn = err;
 				} else if (!rl)
 					up_read(&ni->runlist.lock);
 				/*
 				 * Failed to map the buffer, even after
 				 * retrying.
 				 */
+				if (!err)
+					err = -EIO;
 				bh->b_blocknr = -1;
 				ntfs_error(vol->sb, "Failed to write to inode "
 						"0x%lx, attribute type 0x%x, "
 						"vcn 0x%llx, offset 0x%x "
 						"because its location on disk "
 						"could not be determined%s "
-						"(error code %lli).",
+						"(error code %i).",
 						ni->mft_no, ni->type,
 						(unsigned long long)vcn,
 						vcn_ofs, is_retry ? " even "
-						"after retrying" : "",
-						(long long)lcn);
-				if (!err)
-					err = -EIO;
+						"after retrying" : "", err);
 				goto err_out;
 			}
 			/* We now have a successful remap, i.e. lcn >= 0. */
@@ -2357,6 +2402,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 			buffers_to_free = bh;
 	}
 	bh = head = page_buffers(page);
+	BUG_ON(!bh);
 	do {
 		bh_ofs = bh_offset(bh);
 		if (bh_ofs + bh_size <= ofs)
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index cd0f9e740b1..3f9a4ff42ee 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -43,6 +43,9 @@
  * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
  * of bounds of the runlist.
  *
+ * Note the runlist can be NULL after this function returns if @vcn is zero and
+ * the attribute has zero allocated size, i.e. there simply is no runlist.
+ *
  * Locking: - The runlist must be locked for writing.
  *	    - This function modifies the runlist.
  */
@@ -54,6 +57,7 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn)
 	ATTR_RECORD *a;
 	ntfs_attr_search_ctx *ctx;
 	runlist_element *rl;
+	unsigned long flags;
 	int err = 0;
 
 	ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
@@ -85,8 +89,11 @@ int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn)
 	 * ntfs_mapping_pairs_decompress() fails.
 	 */
 	end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
-	if (unlikely(!a->data.non_resident.lowest_vcn && end_vcn <= 1))
+	if (unlikely(!a->data.non_resident.lowest_vcn && end_vcn <= 1)) {
+		read_lock_irqsave(&ni->size_lock, flags);
 		end_vcn = ni->allocated_size >> ni->vol->cluster_size_bits;
+		read_unlock_irqrestore(&ni->size_lock, flags);
+	}
 	if (unlikely(vcn >= end_vcn)) {
 		err = -ENOENT;
 		goto err_out;
@@ -165,6 +172,7 @@ LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
 		const BOOL write_locked)
 {
 	LCN lcn;
+	unsigned long flags;
 	BOOL is_retry = FALSE;
 
 	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
@@ -173,6 +181,14 @@ LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
 	BUG_ON(!ni);
 	BUG_ON(!NInoNonResident(ni));
 	BUG_ON(vcn < 0);
+	if (!ni->runlist.rl) {
+		read_lock_irqsave(&ni->size_lock, flags);
+		if (!ni->allocated_size) {
+			read_unlock_irqrestore(&ni->size_lock, flags);
+			return LCN_ENOENT;
+		}
+		read_unlock_irqrestore(&ni->size_lock, flags);
+	}
 retry_remap:
 	/* Convert vcn to lcn.  If that fails map the runlist and retry once. */
 	lcn = ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn);
@@ -255,6 +271,7 @@ retry_remap:
 runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
 		const BOOL write_locked)
 {
+	unsigned long flags;
 	runlist_element *rl;
 	int err = 0;
 	BOOL is_retry = FALSE;
@@ -265,6 +282,14 @@ runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
 	BUG_ON(!ni);
 	BUG_ON(!NInoNonResident(ni));
 	BUG_ON(vcn < 0);
+	if (!ni->runlist.rl) {
+		read_lock_irqsave(&ni->size_lock, flags);
+		if (!ni->allocated_size) {
+			read_unlock_irqrestore(&ni->size_lock, flags);
+			return ERR_PTR(-ENOENT);
+		}
+		read_unlock_irqrestore(&ni->size_lock, flags);
+	}
 retry_remap:
 	rl = ni->runlist.rl;
 	if (likely(rl && vcn >= rl[0].vcn)) {
@@ -528,6 +553,11 @@ int load_attribute_list(ntfs_volume *vol, runlist *runlist, u8 *al_start,
 	block_size_bits = sb->s_blocksize_bits;
 	down_read(&runlist->lock);
 	rl = runlist->rl;
+	if (!rl) {
+		ntfs_error(sb, "Cannot read attribute list since runlist is "
+				"missing.");
+		goto err_out;	
+	}
 	/* Read all clusters specified by the runlist one run at a time. */
 	while (rl->length) {
 		lcn = ntfs_rl_vcn_to_lcn(rl, rl->vcn);
@@ -1247,6 +1277,46 @@ int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size)
 }
 
 /**
+ * ntfs_resident_attr_value_resize - resize the value of a resident attribute
+ * @m:		mft record containing attribute record
+ * @a:		attribute record whose value to resize
+ * @new_size:	new size in bytes to which to resize the attribute value of @a
+ *
+ * Resize the value of the attribute @a in the mft record @m to @new_size bytes.
+ * If the value is made bigger, the newly allocated space is cleared.
+ *
+ * Return 0 on success and -errno on error.  The following error codes are
+ * defined:
+ *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
+ *
+ * Note: On error, no modifications have been performed whatsoever.
+ *
+ * Warning: If you make a record smaller without having copied all the data you
+ *	    are interested in the data may be overwritten.
+ */
+int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
+		const u32 new_size)
+{
+	u32 old_size;
+
+	/* Resize the resident part of the attribute record. */
+	if (ntfs_attr_record_resize(m, a,
+			le16_to_cpu(a->data.resident.value_offset) + new_size))
+		return -ENOSPC;
+	/*
+	 * The resize succeeded!  If we made the attribute value bigger, clear
+	 * the area between the old size and @new_size.
+	 */
+	old_size = le32_to_cpu(a->data.resident.value_length);
+	if (new_size > old_size)
+		memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
+				old_size, 0, new_size - old_size);
+	/* Finally update the length of the attribute value. */
+	a->data.resident.value_length = cpu_to_le32(new_size);
+	return 0;
+}
+
+/**
  * ntfs_attr_make_non_resident - convert a resident to a non-resident attribute
  * @ni:		ntfs inode describing the attribute to convert
  *
@@ -1302,6 +1372,12 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
 		return err;
 	}
 	/*
+	 * FIXME: Compressed and encrypted attributes are not supported when
+	 * writing and we should never have gotten here for them.
+	 */
+	BUG_ON(NInoCompressed(ni));
+	BUG_ON(NInoEncrypted(ni));
+	/*
 	 * The size needs to be aligned to a cluster boundary for allocation
 	 * purposes.
 	 */
@@ -1377,10 +1453,15 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
 	BUG_ON(a->non_resident);
 	/*
 	 * Calculate new offsets for the name and the mapping pairs array.
-	 * We assume the attribute is not compressed or sparse.
 	 */
-	name_ofs = (offsetof(ATTR_REC,
-			data.non_resident.compressed_size) + 7) & ~7;
+	if (NInoSparse(ni) || NInoCompressed(ni))
+		name_ofs = (offsetof(ATTR_REC,
+				data.non_resident.compressed_size) +
+				sizeof(a->data.non_resident.compressed_size) +
+				7) & ~7;
+	else
+		name_ofs = (offsetof(ATTR_REC,
+				data.non_resident.compressed_size) + 7) & ~7;
 	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
 	/*
 	 * Determine the size of the resident part of the now non-resident
@@ -1419,24 +1500,23 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
 		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
 				a->name_length * sizeof(ntfschar));
 	a->name_offset = cpu_to_le16(name_ofs);
-	/*
-	 * FIXME: For now just clear all of these as we do not support them
-	 * when writing.
-	 */
-	a->flags &= cpu_to_le16(0xffff & ~le16_to_cpu(ATTR_IS_SPARSE |
-			ATTR_IS_ENCRYPTED | ATTR_COMPRESSION_MASK));
 	/* Setup the fields specific to non-resident attributes. */
 	a->data.non_resident.lowest_vcn = 0;
 	a->data.non_resident.highest_vcn = cpu_to_sle64((new_size - 1) >>
 			vol->cluster_size_bits);
 	a->data.non_resident.mapping_pairs_offset = cpu_to_le16(mp_ofs);
-	a->data.non_resident.compression_unit = 0;
 	memset(&a->data.non_resident.reserved, 0,
 			sizeof(a->data.non_resident.reserved));
 	a->data.non_resident.allocated_size = cpu_to_sle64(new_size);
 	a->data.non_resident.data_size =
 			a->data.non_resident.initialized_size =
 			cpu_to_sle64(attr_size);
+	if (NInoSparse(ni) || NInoCompressed(ni)) {
+		a->data.non_resident.compression_unit = 4;
+		a->data.non_resident.compressed_size =
+				a->data.non_resident.allocated_size;
+	} else
+		a->data.non_resident.compression_unit = 0;
 	/* Generate the mapping pairs array into the attribute record. */
 	err = ntfs_mapping_pairs_build(vol, (u8*)a + mp_ofs,
 			arec_size - mp_ofs, rl, 0, -1, NULL);
@@ -1446,16 +1526,19 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni)
 		goto undo_err_out;
 	}
 	/* Setup the in-memory attribute structure to be non-resident. */
-	/*
-	 * FIXME: For now just clear all of these as we do not support them
-	 * when writing.
-	 */
-	NInoClearSparse(ni);
-	NInoClearEncrypted(ni);
-	NInoClearCompressed(ni);
 	ni->runlist.rl = rl;
 	write_lock_irqsave(&ni->size_lock, flags);
 	ni->allocated_size = new_size;
+	if (NInoSparse(ni) || NInoCompressed(ni)) {
+		ni->itype.compressed.size = ni->allocated_size;
+		ni->itype.compressed.block_size = 1U <<
+				(a->data.non_resident.compression_unit +
+				vol->cluster_size_bits);
+		ni->itype.compressed.block_size_bits =
+				ffs(ni->itype.compressed.block_size) - 1;
+		ni->itype.compressed.block_clusters = 1U <<
+				a->data.non_resident.compression_unit;
+	}
 	write_unlock_irqrestore(&ni->size_lock, flags);
 	/*
 	 * This needs to be last since the address space operations ->readpage
@@ -1603,6 +1686,12 @@ int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
 	BUG_ON(cnt < 0);
 	if (!cnt)
 		goto done;
+	/*
+	 * FIXME: Compressed and encrypted attributes are not supported when
+	 * writing and we should never have gotten here for them.
+	 */
+	BUG_ON(NInoCompressed(ni));
+	BUG_ON(NInoEncrypted(ni));
 	mapping = VFS_I(ni)->i_mapping;
 	/* Work out the starting index and page offset. */
 	idx = ofs >> PAGE_CACHE_SHIFT;
diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h
index 0e4ac6d3c0e..0618ed6fd7b 100644
--- a/fs/ntfs/attrib.h
+++ b/fs/ntfs/attrib.h
@@ -99,6 +99,8 @@ extern int ntfs_attr_can_be_resident(const ntfs_volume *vol,
 		const ATTR_TYPE type);
 
 extern int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size);
+extern int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
+		const u32 new_size);
 
 extern int ntfs_attr_make_non_resident(ntfs_inode *ni);
 
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index 6d265cfd49a..25d24106f89 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -539,7 +539,6 @@ int ntfs_read_compressed_block(struct page *page)
 	if (unlikely(!pages || !bhs)) {
 		kfree(bhs);
 		kfree(pages);
-		SetPageError(page);
 		unlock_page(page);
 		ntfs_error(vol->sb, "Failed to allocate internal buffers.");
 		return -ENOMEM;
@@ -871,9 +870,6 @@ lock_retry_remap:
 			for (; prev_cur_page < cur_page; prev_cur_page++) {
 				page = pages[prev_cur_page];
 				if (page) {
-					if (prev_cur_page == xpage &&
-							!xpage_done)
-						SetPageError(page);
 					flush_dcache_page(page);
 					kunmap(page);
 					unlock_page(page);
@@ -904,8 +900,6 @@ lock_retry_remap:
 					"Terminating them with extreme "
 					"prejudice.  Inode 0x%lx, page index "
 					"0x%lx.", ni->mft_no, page->index);
-			if (cur_page == xpage && !xpage_done)
-				SetPageError(page);
 			flush_dcache_page(page);
 			kunmap(page);
 			unlock_page(page);
@@ -953,8 +947,6 @@ err_out:
 	for (i = cur_page; i < max_page; i++) {
 		page = pages[i];
 		if (page) {
-			if (i == xpage && !xpage_done)
-				SetPageError(page);
 			flush_dcache_page(page);
 			kunmap(page);
 			unlock_page(page);
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 46779471c54..795c3d1930f 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1051,7 +1051,8 @@ static inline int ntfs_filldir(ntfs_volume *vol, loff_t fpos,
 			ie->key.file_name.file_name_length, &name,
 			NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1);
 	if (name_len <= 0) {
-		ntfs_debug("Skipping unrepresentable file.");
+		ntfs_warning(vol->sb, "Skipping unrepresentable inode 0x%llx.",
+				(long long)MREF_LE(ie->data.dir.indexed_file));
 		return 0;
 	}
 	if (ie->key.file_name.file_attributes &
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index e0f530ce6b9..be9fd1dd423 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
 /*
- * file.c - NTFS kernel file operations. Part of the Linux-NTFS project.
+ * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2004 Anton Altaparmakov
+ * Copyright (c) 2001-2005 Anton Altaparmakov
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -94,6 +94,11 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry,
 	if (!datasync || !NInoNonResident(NTFS_I(vi)))
 		ret = ntfs_write_inode(vi, 1);
 	write_inode_now(vi, !datasync);
+	/*
+	 * NOTE: If we were to use mapping->private_list (see ext2 and
+	 * fs/buffer.c) for dirty blocks then we could optimize the below to be
+	 * sync_mapping_buffers(vi->i_mapping).
+	 */
 	err = sync_blockdev(vi->i_sb->s_bdev);
 	if (unlikely(err && !ret))
 		ret = err;
diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c
index 11fd5307d78..8f2d5727546 100644
--- a/fs/ntfs/index.c
+++ b/fs/ntfs/index.c
@@ -205,6 +205,7 @@ int ntfs_index_lookup(const void *key, const int key_len,
 				&ie->key, key_len)) {
 ir_done:
 			ictx->is_in_root = TRUE;
+			ictx->ir = ir;
 			ictx->actx = actx;
 			ictx->base_ni = base_ni;
 			ictx->ia = NULL;
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 886214a77f9..dc4bbe3acf5 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -1013,41 +1013,50 @@ skip_large_dir_stuff:
 		}
 		a = ctx->attr;
 		/* Setup the state. */
-		if (a->non_resident) {
-			NInoSetNonResident(ni);
-			if (a->flags & (ATTR_COMPRESSION_MASK |
-					ATTR_IS_SPARSE)) {
-				if (a->flags & ATTR_COMPRESSION_MASK) {
-					NInoSetCompressed(ni);
-					if (vol->cluster_size > 4096) {
-						ntfs_error(vi->i_sb, "Found "
+		if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
+			if (a->flags & ATTR_COMPRESSION_MASK) {
+				NInoSetCompressed(ni);
+				if (vol->cluster_size > 4096) {
+					ntfs_error(vi->i_sb, "Found "
 							"compressed data but "
 							"compression is "
 							"disabled due to "
 							"cluster size (%i) > "
 							"4kiB.",
 							vol->cluster_size);
-						goto unm_err_out;
-					}
-					if ((a->flags & ATTR_COMPRESSION_MASK)
-							!= ATTR_IS_COMPRESSED) {
-						ntfs_error(vi->i_sb, "Found "
-							"unknown compression "
-							"method or corrupt "
-							"file.");
-						goto unm_err_out;
-					}
+					goto unm_err_out;
+				}
+				if ((a->flags & ATTR_COMPRESSION_MASK)
+						!= ATTR_IS_COMPRESSED) {
+					ntfs_error(vi->i_sb, "Found unknown "
+							"compression method "
+							"or corrupt file.");
+					goto unm_err_out;
 				}
-				if (a->flags & ATTR_IS_SPARSE)
-					NInoSetSparse(ni);
+			}
+			if (a->flags & ATTR_IS_SPARSE)
+				NInoSetSparse(ni);
+		}
+		if (a->flags & ATTR_IS_ENCRYPTED) {
+			if (NInoCompressed(ni)) {
+				ntfs_error(vi->i_sb, "Found encrypted and "
+						"compressed data.");
+				goto unm_err_out;
+			}
+			NInoSetEncrypted(ni);
+		}
+		if (a->non_resident) {
+			NInoSetNonResident(ni);
+			if (NInoCompressed(ni) || NInoSparse(ni)) {
 				if (a->data.non_resident.compression_unit !=
 						4) {
 					ntfs_error(vi->i_sb, "Found "
-						"nonstandard compression unit "
-						"(%u instead of 4).  Cannot "
-						"handle this.",
-						a->data.non_resident.
-						compression_unit);
+							"nonstandard "
+							"compression unit (%u "
+							"instead of 4).  "
+							"Cannot handle this.",
+							a->data.non_resident.
+							compression_unit);
 					err = -EOPNOTSUPP;
 					goto unm_err_out;
 				}
@@ -1065,14 +1074,6 @@ skip_large_dir_stuff:
 						a->data.non_resident.
 						compressed_size);
 			}
-			if (a->flags & ATTR_IS_ENCRYPTED) {
-				if (a->flags & ATTR_COMPRESSION_MASK) {
-					ntfs_error(vi->i_sb, "Found encrypted "
-							"and compressed data.");
-					goto unm_err_out;
-				}
-				NInoSetEncrypted(ni);
-			}
 			if (a->data.non_resident.lowest_vcn) {
 				ntfs_error(vi->i_sb, "First extent of $DATA "
 						"attribute has non zero "
@@ -1212,6 +1213,75 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 	if (unlikely(err))
 		goto unm_err_out;
 	a = ctx->attr;
+	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
+		if (a->flags & ATTR_COMPRESSION_MASK) {
+			NInoSetCompressed(ni);
+			if ((ni->type != AT_DATA) || (ni->type == AT_DATA &&
+					ni->name_len)) {
+				ntfs_error(vi->i_sb, "Found compressed "
+						"non-data or named data "
+						"attribute.  Please report "
+						"you saw this message to "
+						"linux-ntfs-dev@lists."
+						"sourceforge.net");
+				goto unm_err_out;
+			}
+			if (vol->cluster_size > 4096) {
+				ntfs_error(vi->i_sb, "Found compressed "
+						"attribute but compression is "
+						"disabled due to cluster size "
+						"(%i) > 4kiB.",
+						vol->cluster_size);
+				goto unm_err_out;
+			}
+			if ((a->flags & ATTR_COMPRESSION_MASK) !=
+					ATTR_IS_COMPRESSED) {
+				ntfs_error(vi->i_sb, "Found unknown "
+						"compression method.");
+				goto unm_err_out;
+			}
+		}
+		/*
+		 * The encryption flag set in an index root just means to
+		 * compress all files.
+		 */
+		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
+			ntfs_error(vi->i_sb, "Found mst protected attribute "
+					"but the attribute is %s.  Please "
+					"report you saw this message to "
+					"linux-ntfs-dev@lists.sourceforge.net",
+					NInoCompressed(ni) ? "compressed" :
+					"sparse");
+			goto unm_err_out;
+		}
+		if (a->flags & ATTR_IS_SPARSE)
+			NInoSetSparse(ni);
+	}
+	if (a->flags & ATTR_IS_ENCRYPTED) {
+		if (NInoCompressed(ni)) {
+			ntfs_error(vi->i_sb, "Found encrypted and compressed "
+					"data.");
+			goto unm_err_out;
+		}
+		/*
+		 * The encryption flag set in an index root just means to
+		 * encrypt all files.
+		 */
+		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
+			ntfs_error(vi->i_sb, "Found mst protected attribute "
+					"but the attribute is encrypted.  "
+					"Please report you saw this message "
+					"to linux-ntfs-dev@lists.sourceforge."
+					"net");
+			goto unm_err_out;
+		}
+		if (ni->type != AT_DATA) {
+			ntfs_error(vi->i_sb, "Found encrypted non-data "
+					"attribute.");
+			goto unm_err_out;
+		}
+		NInoSetEncrypted(ni);
+	}
 	if (!a->non_resident) {
 		/* Ensure the attribute name is placed before the value. */
 		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
@@ -1220,11 +1290,10 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 					"the attribute value.");
 			goto unm_err_out;
 		}
-		if (NInoMstProtected(ni) || a->flags) {
+		if (NInoMstProtected(ni)) {
 			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"or attribute with non-zero flags but "
-					"the attribute is resident.  Please "
-					"report you saw this message to "
+					"but the attribute is resident.  "
+					"Please report you saw this message to "
 					"linux-ntfs-dev@lists.sourceforge.net");
 			goto unm_err_out;
 		}
@@ -1250,50 +1319,8 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 					"the mapping pairs array.");
 			goto unm_err_out;
 		}
-		if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
-			if (a->flags & ATTR_COMPRESSION_MASK) {
-				NInoSetCompressed(ni);
-				if ((ni->type != AT_DATA) || (ni->type ==
-						AT_DATA && ni->name_len)) {
-					ntfs_error(vi->i_sb, "Found compressed "
-							"non-data or named "
-							"data attribute.  "
-							"Please report you "
-							"saw this message to "
-							"linux-ntfs-dev@lists."
-							"sourceforge.net");
-					goto unm_err_out;
-				}
-				if (vol->cluster_size > 4096) {
-					ntfs_error(vi->i_sb, "Found compressed "
-							"attribute but "
-							"compression is "
-							"disabled due to "
-							"cluster size (%i) > "
-							"4kiB.",
-							vol->cluster_size);
-					goto unm_err_out;
-				}
-				if ((a->flags & ATTR_COMPRESSION_MASK) !=
-						ATTR_IS_COMPRESSED) {
-					ntfs_error(vi->i_sb, "Found unknown "
-							"compression method.");
-					goto unm_err_out;
-				}
-			}
-			if (NInoMstProtected(ni)) {
-				ntfs_error(vi->i_sb, "Found mst protected "
-						"attribute but the attribute "
-						"is %s.  Please report you "
-						"saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net",
-						NInoCompressed(ni) ?
-						"compressed" : "sparse");
-				goto unm_err_out;
-			}
-			if (a->flags & ATTR_IS_SPARSE)
-				NInoSetSparse(ni);
+		if ((NInoCompressed(ni) || NInoSparse(ni)) &&
+				ni->type != AT_INDEX_ROOT) {
 			if (a->data.non_resident.compression_unit != 4) {
 				ntfs_error(vi->i_sb, "Found nonstandard "
 						"compression unit (%u instead "
@@ -1313,23 +1340,6 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 			ni->itype.compressed.size = sle64_to_cpu(
 					a->data.non_resident.compressed_size);
 		}
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			if (a->flags & ATTR_COMPRESSION_MASK) {
-				ntfs_error(vi->i_sb, "Found encrypted and "
-						"compressed data.");
-				goto unm_err_out;
-			}
-			if (NInoMstProtected(ni)) {
-				ntfs_error(vi->i_sb, "Found mst protected "
-						"attribute but the attribute "
-						"is encrypted.  Please report "
-						"you saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				goto unm_err_out;
-			}
-			NInoSetEncrypted(ni);
-		}
 		if (a->data.non_resident.lowest_vcn) {
 			ntfs_error(vi->i_sb, "First extent of attribute has "
 					"non-zero lowest_vcn.");
@@ -1348,12 +1358,12 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 		vi->i_mapping->a_ops = &ntfs_mst_aops;
 	else
 		vi->i_mapping->a_ops = &ntfs_aops;
-	if (NInoCompressed(ni) || NInoSparse(ni))
+	if ((NInoCompressed(ni) || NInoSparse(ni)) && ni->type != AT_INDEX_ROOT)
 		vi->i_blocks = ni->itype.compressed.size >> 9;
 	else
 		vi->i_blocks = ni->allocated_size >> 9;
 	/*
-	 * Make sure the base inode doesn't go away and attach it to the
+	 * Make sure the base inode does not go away and attach it to the
 	 * attribute inode.
 	 */
 	igrab(base_vi);
@@ -1480,7 +1490,10 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
 				"after the attribute value.");
 		goto unm_err_out;
 	}
-	/* Compressed/encrypted/sparse index root is not allowed. */
+	/*
+	 * Compressed/encrypted/sparse index root is not allowed, except for
+	 * directories of course but those are not dealt with here.
+	 */
 	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_ENCRYPTED |
 			ATTR_IS_SPARSE)) {
 		ntfs_error(vi->i_sb, "Found compressed/encrypted/sparse index "
@@ -2430,16 +2443,18 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr)
 			 * We skipped the truncate but must still update
 			 * timestamps.
 			 */
-			ia_valid |= ATTR_MTIME|ATTR_CTIME;
+			ia_valid |= ATTR_MTIME | ATTR_CTIME;
 		}
 	}
-
 	if (ia_valid & ATTR_ATIME)
-		vi->i_atime = attr->ia_atime;
+		vi->i_atime = timespec_trunc(attr->ia_atime,
+				vi->i_sb->s_time_gran);
 	if (ia_valid & ATTR_MTIME)
-		vi->i_mtime = attr->ia_mtime;
+		vi->i_mtime = timespec_trunc(attr->ia_mtime,
+				vi->i_sb->s_time_gran);
 	if (ia_valid & ATTR_CTIME)
-		vi->i_ctime = attr->ia_ctime;
+		vi->i_ctime = timespec_trunc(attr->ia_ctime,
+				vi->i_sb->s_time_gran);
 	mark_inode_dirty(vi);
 out:
 	return err;
diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c
index a4bc07616e5..7b593429068 100644
--- a/fs/ntfs/lcnalloc.c
+++ b/fs/ntfs/lcnalloc.c
@@ -54,6 +54,8 @@ int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
 	int ret = 0;
 
 	ntfs_debug("Entering.");
+	if (!rl)
+		return 0;
 	for (; rl->length; rl++) {
 		int err;
 
@@ -163,17 +165,9 @@ runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn,
 	BUG_ON(zone < FIRST_ZONE);
 	BUG_ON(zone > LAST_ZONE);
 
-	/* Return empty runlist if @count == 0 */
-	// FIXME: Do we want to just return NULL instead? (AIA)
-	if (!count) {
-		rl = ntfs_malloc_nofs(PAGE_SIZE);
-		if (!rl)
-			return ERR_PTR(-ENOMEM);
-		rl[0].vcn = start_vcn;
-		rl[0].lcn = LCN_RL_NOT_MAPPED;
-		rl[0].length = 0;
-		return rl;
-	}
+	/* Return NULL if @count is zero. */
+	if (!count)
+		return NULL;
 	/* Take the lcnbmp lock for writing. */
 	down_write(&vol->lcnbmp_lock);
 	/*
@@ -788,7 +782,8 @@ out:
  * @vi:		vfs inode whose runlist describes the clusters to free
  * @start_vcn:	vcn in the runlist of @vi at which to start freeing clusters
  * @count:	number of clusters to free or -1 for all clusters
- * @is_rollback:	if TRUE this is a rollback operation
+ * @write_locked:	true if the runlist is locked for writing
+ * @is_rollback:	true if this is a rollback operation
  *
  * Free @count clusters starting at the cluster @start_vcn in the runlist
  * described by the vfs inode @vi.
@@ -806,17 +801,17 @@ out:
  * Return the number of deallocated clusters (not counting sparse ones) on
  * success and -errno on error.
  *
- * Locking: - The runlist described by @vi must be unlocked on entry and is
- *	      unlocked on return.
- *	    - This function takes the runlist lock of @vi for reading and
- *	      sometimes for writing and sometimes modifies the runlist.
+ * Locking: - The runlist described by @vi must be locked on entry and is
+ *	      locked on return.  Note if the runlist is locked for reading the
+ *	      lock may be dropped and reacquired.  Note the runlist may be
+ *	      modified when needed runlist fragments need to be mapped.
  *	    - The volume lcn bitmap must be unlocked on entry and is unlocked
  *	      on return.
  *	    - This function takes the volume lcn bitmap lock for writing and
  *	      modifies the bitmap contents.
  */
 s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn, s64 count,
-		const BOOL is_rollback)
+		const BOOL write_locked, const BOOL is_rollback)
 {
 	s64 delta, to_free, total_freed, real_freed;
 	ntfs_inode *ni;
@@ -848,8 +843,7 @@ s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn, s64 count,
 
 	total_freed = real_freed = 0;
 
-	down_read(&ni->runlist.lock);
-	rl = ntfs_attr_find_vcn_nolock(ni, start_vcn, FALSE);
+	rl = ntfs_attr_find_vcn_nolock(ni, start_vcn, write_locked);
 	if (IS_ERR(rl)) {
 		if (!is_rollback)
 			ntfs_error(vol->sb, "Failed to find first runlist "
@@ -903,7 +897,7 @@ s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn, s64 count,
 
 			/* Attempt to map runlist. */
 			vcn = rl->vcn;
-			rl = ntfs_attr_find_vcn_nolock(ni, vcn, FALSE);
+			rl = ntfs_attr_find_vcn_nolock(ni, vcn, write_locked);
 			if (IS_ERR(rl)) {
 				err = PTR_ERR(rl);
 				if (!is_rollback)
@@ -950,7 +944,6 @@ s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn, s64 count,
 		/* Update the total done clusters. */
 		total_freed += to_free;
 	}
-	up_read(&ni->runlist.lock);
 	if (likely(!is_rollback))
 		up_write(&vol->lcnbmp_lock);
 
@@ -960,7 +953,6 @@ s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn, s64 count,
 	ntfs_debug("Done.");
 	return real_freed;
 err_out:
-	up_read(&ni->runlist.lock);
 	if (is_rollback)
 		return err;
 	/* If no real clusters were freed, no need to rollback. */
@@ -973,7 +965,8 @@ err_out:
 	 * If rollback fails, set the volume errors flag, emit an error
 	 * message, and return the error code.
 	 */
-	delta = __ntfs_cluster_free(vi, start_vcn, total_freed, TRUE);
+	delta = __ntfs_cluster_free(vi, start_vcn, total_freed, write_locked,
+			TRUE);
 	if (delta < 0) {
 		ntfs_error(vol->sb, "Failed to rollback (error %i).  Leaving "
 				"inconsistent metadata!  Unmount and run "
diff --git a/fs/ntfs/lcnalloc.h b/fs/ntfs/lcnalloc.h
index 4cac1c024af..e4d7fb98d68 100644
--- a/fs/ntfs/lcnalloc.h
+++ b/fs/ntfs/lcnalloc.h
@@ -43,13 +43,14 @@ extern runlist_element *ntfs_cluster_alloc(ntfs_volume *vol,
 		const NTFS_CLUSTER_ALLOCATION_ZONES zone);
 
 extern s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn,
-		s64 count, const BOOL is_rollback);
+		s64 count, const BOOL write_locked, const BOOL is_rollback);
 
 /**
  * ntfs_cluster_free - free clusters on an ntfs volume
  * @vi:		vfs inode whose runlist describes the clusters to free
  * @start_vcn:	vcn in the runlist of @vi at which to start freeing clusters
  * @count:	number of clusters to free or -1 for all clusters
+ * @write_locked:	true if the runlist is locked for writing
  *
  * Free @count clusters starting at the cluster @start_vcn in the runlist
  * described by the vfs inode @vi.
@@ -64,19 +65,19 @@ extern s64 __ntfs_cluster_free(struct inode *vi, const VCN start_vcn,
  * Return the number of deallocated clusters (not counting sparse ones) on
  * success and -errno on error.
  *
- * Locking: - The runlist described by @vi must be unlocked on entry and is
- *	      unlocked on return.
- *	    - This function takes the runlist lock of @vi for reading and
- *	      sometimes for writing and sometimes modifies the runlist.
+ * Locking: - The runlist described by @vi must be locked on entry and is
+ *	      locked on return.  Note if the runlist is locked for reading the
+ *	      lock may be dropped and reacquired.  Note the runlist may be
+ *	      modified when needed runlist fragments need to be mapped.
  *	    - The volume lcn bitmap must be unlocked on entry and is unlocked
  *	      on return.
  *	    - This function takes the volume lcn bitmap lock for writing and
  *	      modifies the bitmap contents.
  */
 static inline s64 ntfs_cluster_free(struct inode *vi, const VCN start_vcn,
-		s64 count)
+		s64 count, const BOOL write_locked)
 {
-	return __ntfs_cluster_free(vi, start_vcn, count, FALSE);
+	return __ntfs_cluster_free(vi, start_vcn, count, write_locked, FALSE);
 }
 
 extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
@@ -93,8 +94,10 @@ extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
  *
  * Return 0 on success and -errno on error.
  *
- * Locking: This function takes the volume lcn bitmap lock for writing and
- *	    modifies the bitmap contents.
+ * Locking: - This function takes the volume lcn bitmap lock for writing and
+ *	      modifies the bitmap contents.
+ *	    - The caller must have locked the runlist @rl for reading or
+ *	      writing.
  */
 static inline int ntfs_cluster_free_from_rl(ntfs_volume *vol,
 		const runlist_element *rl)
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
index 8edb8e20fb0..0173e95500d 100644
--- a/fs/ntfs/logfile.c
+++ b/fs/ntfs/logfile.c
@@ -121,7 +121,7 @@ static BOOL ntfs_check_restart_page_header(struct inode *vi,
 	 */
 	if (!ntfs_is_chkd_record(rp->magic) && sle64_to_cpu(rp->chkdsk_lsn)) {
 		ntfs_error(vi->i_sb, "$LogFile restart page is not modified "
-				"chkdsk but a chkdsk LSN is specified.");
+				"by chkdsk but a chkdsk LSN is specified.");
 		return FALSE;
 	}
 	ntfs_debug("Done.");
@@ -312,10 +312,12 @@ err_out:
  * @vi:		$LogFile inode to which the restart page belongs
  * @rp:		restart page to check
  * @pos:	position in @vi at which the restart page resides
- * @wrp:	copy of the multi sector transfer deprotected restart page
+ * @wrp:	[OUT] copy of the multi sector transfer deprotected restart page
+ * @lsn:	[OUT] set to the current logfile lsn on success
  *
- * Check the restart page @rp for consistency and return TRUE if it is
- * consistent and FALSE otherwise.
+ * Check the restart page @rp for consistency and return 0 if it is consistent
+ * and -errno otherwise.  The restart page may have been modified by chkdsk in
+ * which case its magic is CHKD instead of RSTR.
  *
  * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
  * require the full restart page.
@@ -323,25 +325,33 @@ err_out:
  * If @wrp is not NULL, on success, *@wrp will point to a buffer containing a
  * copy of the complete multi sector transfer deprotected page.  On failure,
  * *@wrp is undefined.
+ *
+ * Simillarly, if @lsn is not NULL, on succes *@lsn will be set to the current
+ * logfile lsn according to this restart page.  On failure, *@lsn is undefined.
+ *
+ * The following error codes are defined:
+ *	-EINVAL	- The restart page is inconsistent.
+ *	-ENOMEM	- Not enough memory to load the restart page.
+ *	-EIO	- Failed to reading from $LogFile.
  */
-static BOOL ntfs_check_and_load_restart_page(struct inode *vi,
-		RESTART_PAGE_HEADER *rp, s64 pos, RESTART_PAGE_HEADER **wrp)
+static int ntfs_check_and_load_restart_page(struct inode *vi,
+		RESTART_PAGE_HEADER *rp, s64 pos, RESTART_PAGE_HEADER **wrp,
+		LSN *lsn)
 {
 	RESTART_AREA *ra;
 	RESTART_PAGE_HEADER *trp;
-	int size;
-	BOOL ret;
+	int size, err;
 
 	ntfs_debug("Entering.");
 	/* Check the restart page header for consistency. */
 	if (!ntfs_check_restart_page_header(vi, rp, pos)) {
 		/* Error output already done inside the function. */
-		return FALSE;
+		return -EINVAL;
 	}
 	/* Check the restart area for consistency. */
 	if (!ntfs_check_restart_area(vi, rp)) {
 		/* Error output already done inside the function. */
-		return FALSE;
+		return -EINVAL;
 	}
 	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
 	/*
@@ -352,7 +362,7 @@ static BOOL ntfs_check_and_load_restart_page(struct inode *vi,
 	if (!trp) {
 		ntfs_error(vi->i_sb, "Failed to allocate memory for $LogFile "
 				"restart page buffer.");
-		return FALSE;
+		return -ENOMEM;
 	}
 	/*
 	 * Read the whole of the restart page into the buffer.  If it fits
@@ -379,6 +389,9 @@ static BOOL ntfs_check_and_load_restart_page(struct inode *vi,
 			if (IS_ERR(page)) {
 				ntfs_error(vi->i_sb, "Error mapping $LogFile "
 						"page (index %lu).", idx);
+				err = PTR_ERR(page);
+				if (err != -EIO && err != -ENOMEM)
+					err = -EIO;
 				goto err_out;
 			}
 			size = min_t(int, to_read, PAGE_CACHE_SIZE);
@@ -392,29 +405,57 @@ static BOOL ntfs_check_and_load_restart_page(struct inode *vi,
 	/* Perform the multi sector transfer deprotection on the buffer. */
 	if (post_read_mst_fixup((NTFS_RECORD*)trp,
 			le32_to_cpu(rp->system_page_size))) {
-		ntfs_error(vi->i_sb, "Multi sector transfer error detected in "
-				"$LogFile restart page.");
-		goto err_out;
+		/*
+		 * A multi sector tranfer error was detected.  We only need to
+		 * abort if the restart page contents exceed the multi sector
+		 * transfer fixup of the first sector.
+		 */
+		if (le16_to_cpu(rp->restart_area_offset) +
+				le16_to_cpu(ra->restart_area_length) >
+				NTFS_BLOCK_SIZE - sizeof(u16)) {
+			ntfs_error(vi->i_sb, "Multi sector transfer error "
+					"detected in $LogFile restart page.");
+			err = -EINVAL;
+			goto err_out;
+		}
+	}
+	/*
+	 * If the restart page is modified by chkdsk or there are no active
+	 * logfile clients, the logfile is consistent.  Otherwise, need to
+	 * check the log client records for consistency, too.
+	 */
+	err = 0;
+	if (ntfs_is_rstr_record(rp->magic) &&
+			ra->client_in_use_list != LOGFILE_NO_CLIENT) {
+		if (!ntfs_check_log_client_array(vi, trp)) {
+			err = -EINVAL;
+			goto err_out;
+		}
+	}
+	if (lsn) {
+		if (ntfs_is_rstr_record(rp->magic))
+			*lsn = sle64_to_cpu(ra->current_lsn);
+		else /* if (ntfs_is_chkd_record(rp->magic)) */
+			*lsn = sle64_to_cpu(rp->chkdsk_lsn);
 	}
-	/* Check the log client records for consistency. */
-	ret = ntfs_check_log_client_array(vi, trp);
-	if (ret && wrp)
-		*wrp = trp;
-	else
-		ntfs_free(trp);
 	ntfs_debug("Done.");
-	return ret;
+	if (wrp)
+		*wrp = trp;
+	else {
 err_out:
-	ntfs_free(trp);
-	return FALSE;
+		ntfs_free(trp);
+	}
+	return err;
 }
 
 /**
  * ntfs_check_logfile - check the journal for consistency
  * @log_vi:	struct inode of loaded journal $LogFile to check
+ * @rp:		[OUT] on success this is a copy of the current restart page
  *
  * Check the $LogFile journal for consistency and return TRUE if it is
- * consistent and FALSE if not.
+ * consistent and FALSE if not.  On success, the current restart page is
+ * returned in *@rp.  Caller must call ntfs_free(*@rp) when finished with it.
  *
  * At present we only check the two restart pages and ignore the log record
  * pages.
@@ -424,19 +465,18 @@ err_out:
  * if the $LogFile was created on a system with a different page size to ours
  * yet and mst deprotection would fail if our page size is smaller.
  */
-BOOL ntfs_check_logfile(struct inode *log_vi)
+BOOL ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
 {
-	s64 size, pos, rstr1_pos, rstr2_pos;
+	s64 size, pos;
+	LSN rstr1_lsn, rstr2_lsn;
 	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
 	struct address_space *mapping = log_vi->i_mapping;
 	struct page *page = NULL;
 	u8 *kaddr = NULL;
 	RESTART_PAGE_HEADER *rstr1_ph = NULL;
 	RESTART_PAGE_HEADER *rstr2_ph = NULL;
-	int log_page_size, log_page_mask, ofs;
+	int log_page_size, log_page_mask, err;
 	BOOL logfile_is_empty = TRUE;
-	BOOL rstr1_found = FALSE;
-	BOOL rstr2_found = FALSE;
 	u8 log_page_bits;
 
 	ntfs_debug("Entering.");
@@ -491,7 +531,7 @@ BOOL ntfs_check_logfile(struct inode *log_vi)
 			if (IS_ERR(page)) {
 				ntfs_error(vol->sb, "Error mapping $LogFile "
 						"page (index %lu).", idx);
-				return FALSE;
+				goto err_out;
 			}
 		}
 		kaddr = (u8*)page_address(page) + (pos & ~PAGE_CACHE_MASK);
@@ -510,99 +550,95 @@ BOOL ntfs_check_logfile(struct inode *log_vi)
 		 */
 		if (ntfs_is_rcrd_recordp((le32*)kaddr))
 			break;
-		/*
-		 * A modified by chkdsk restart page means we cannot handle
-		 * this log file.
-		 */
-		if (ntfs_is_chkd_recordp((le32*)kaddr)) {
-			ntfs_error(vol->sb, "$LogFile has been modified by "
-					"chkdsk.  Mount this volume in "
-					"Windows.");
-			goto err_out;
-		}
-		/* If not a restart page, continue. */
-		if (!ntfs_is_rstr_recordp((le32*)kaddr)) {
-			/* Skip to the minimum page size for the next one. */
+		/* If not a (modified by chkdsk) restart page, continue. */
+		if (!ntfs_is_rstr_recordp((le32*)kaddr) &&
+				!ntfs_is_chkd_recordp((le32*)kaddr)) {
 			if (!pos)
 				pos = NTFS_BLOCK_SIZE >> 1;
 			continue;
 		}
-		/* We now know we have a restart page. */
-		if (!pos) {
-			rstr1_found = TRUE;
-			rstr1_pos = pos;
-		} else {
-			if (rstr2_found) {
-				ntfs_error(vol->sb, "Found more than two "
-						"restart pages in $LogFile.");
-				goto err_out;
-			}
-			rstr2_found = TRUE;
-			rstr2_pos = pos;
-		}
 		/*
-		 * Check the restart page for consistency and get a copy of the
-		 * complete multi sector transfer deprotected restart page.
+		 * Check the (modified by chkdsk) restart page for consistency
+		 * and get a copy of the complete multi sector transfer
+		 * deprotected restart page.
 		 */
-		if (!ntfs_check_and_load_restart_page(log_vi,
+		err = ntfs_check_and_load_restart_page(log_vi,
 				(RESTART_PAGE_HEADER*)kaddr, pos,
-				!pos ? &rstr1_ph : &rstr2_ph)) {
-			/* Error output already done inside the function. */
-			goto err_out;
+				!rstr1_ph ? &rstr1_ph : &rstr2_ph,
+				!rstr1_ph ? &rstr1_lsn : &rstr2_lsn);
+		if (!err) {
+			/*
+			 * If we have now found the first (modified by chkdsk)
+			 * restart page, continue looking for the second one.
+			 */
+			if (!pos) {
+				pos = NTFS_BLOCK_SIZE >> 1;
+				continue;
+			}
+			/*
+			 * We have now found the second (modified by chkdsk)
+			 * restart page, so we can stop looking.
+			 */
+			break;
 		}
 		/*
-		 * We have a valid restart page.  The next one must be after
-		 * a whole system page size as specified by the valid restart
-		 * page.
+		 * Error output already done inside the function.  Note, we do
+		 * not abort if the restart page was invalid as we might still
+		 * find a valid one further in the file.
 		 */
+		if (err != -EINVAL) {
+			ntfs_unmap_page(page);
+			goto err_out;
+		}
+		/* Continue looking. */
 		if (!pos)
-			pos = le32_to_cpu(rstr1_ph->system_page_size) >> 1;
+			pos = NTFS_BLOCK_SIZE >> 1;
 	}
-	if (page) {
+	if (page)
 		ntfs_unmap_page(page);
-		page = NULL;
-	}
 	if (logfile_is_empty) {
 		NVolSetLogFileEmpty(vol);
 is_empty:
 		ntfs_debug("Done.  ($LogFile is empty.)");
 		return TRUE;
 	}
-	if (!rstr1_found || !rstr2_found) {
-		ntfs_error(vol->sb, "Did not find two restart pages in "
-				"$LogFile.");
-		goto err_out;
+	if (!rstr1_ph) {
+		BUG_ON(rstr2_ph);
+		ntfs_error(vol->sb, "Did not find any restart pages in "
+				"$LogFile and it was not empty.");
+		return FALSE;
+	}
+	/* If both restart pages were found, use the more recent one. */
+	if (rstr2_ph) {
+		/*
+		 * If the second restart area is more recent, switch to it.
+		 * Otherwise just throw it away.
+		 */
+		if (rstr2_lsn > rstr1_lsn) {
+			ntfs_free(rstr1_ph);
+			rstr1_ph = rstr2_ph;
+			/* rstr1_lsn = rstr2_lsn; */
+		} else
+			ntfs_free(rstr2_ph);
+		rstr2_ph = NULL;
 	}
-	/*
-	 * The two restart areas must be identical except for the update
-	 * sequence number.
-	 */
-	ofs = le16_to_cpu(rstr1_ph->usa_ofs);
-	if (memcmp(rstr1_ph, rstr2_ph, ofs) || (ofs += sizeof(u16),
-			memcmp((u8*)rstr1_ph + ofs, (u8*)rstr2_ph + ofs,
-			le32_to_cpu(rstr1_ph->system_page_size) - ofs))) {
-		ntfs_error(vol->sb, "The two restart pages in $LogFile do not "
-				"match.");
-		goto err_out;
-	}
-	ntfs_free(rstr1_ph);
-	ntfs_free(rstr2_ph);
 	/* All consistency checks passed. */
+	if (rp)
+		*rp = rstr1_ph;
+	else
+		ntfs_free(rstr1_ph);
 	ntfs_debug("Done.");
 	return TRUE;
 err_out:
-	if (page)
-		ntfs_unmap_page(page);
 	if (rstr1_ph)
 		ntfs_free(rstr1_ph);
-	if (rstr2_ph)
-		ntfs_free(rstr2_ph);
 	return FALSE;
 }
 
 /**
  * ntfs_is_logfile_clean - check in the journal if the volume is clean
  * @log_vi:	struct inode of loaded journal $LogFile to check
+ * @rp:		copy of the current restart page
  *
  * Analyze the $LogFile journal and return TRUE if it indicates the volume was
  * shutdown cleanly and FALSE if not.
@@ -619,11 +655,9 @@ err_out:
  * is empty this function requires that NVolLogFileEmpty() is true otherwise an
  * empty volume will be reported as dirty.
  */
-BOOL ntfs_is_logfile_clean(struct inode *log_vi)
+BOOL ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp)
 {
 	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
-	struct page *page;
-	RESTART_PAGE_HEADER *rp;
 	RESTART_AREA *ra;
 
 	ntfs_debug("Entering.");
@@ -632,24 +666,15 @@ BOOL ntfs_is_logfile_clean(struct inode *log_vi)
 		ntfs_debug("Done.  ($LogFile is empty.)");
 		return TRUE;
 	}
-	/*
-	 * Read the first restart page.  It will be possibly incomplete and
-	 * will not be multi sector transfer deprotected but we only need the
-	 * first NTFS_BLOCK_SIZE bytes so it does not matter.
-	 */
-	page = ntfs_map_page(log_vi->i_mapping, 0);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Error mapping $LogFile page (index 0).");
+	BUG_ON(!rp);
+	if (!ntfs_is_rstr_record(rp->magic) &&
+			!ntfs_is_chkd_record(rp->magic)) {
+		ntfs_error(vol->sb, "Restart page buffer is invalid.  This is "
+				"probably a bug in that the $LogFile should "
+				"have been consistency checked before calling "
+				"this function.");
 		return FALSE;
 	}
-	rp = (RESTART_PAGE_HEADER*)page_address(page);
-	if (!ntfs_is_rstr_record(rp->magic)) {
-		ntfs_error(vol->sb, "No restart page found at offset zero in "
-				"$LogFile.  This is probably a bug in that "
-				"the $LogFile should have been consistency "
-				"checked before calling this function.");
-		goto err_out;
-	}
 	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
 	/*
 	 * If the $LogFile has active clients, i.e. it is open, and we do not
@@ -659,15 +684,11 @@ BOOL ntfs_is_logfile_clean(struct inode *log_vi)
 	if (ra->client_in_use_list != LOGFILE_NO_CLIENT &&
 			!(ra->flags & RESTART_VOLUME_IS_CLEAN)) {
 		ntfs_debug("Done.  $LogFile indicates a dirty shutdown.");
-		goto err_out;
+		return FALSE;
 	}
-	ntfs_unmap_page(page);
 	/* $LogFile indicates a clean shutdown. */
 	ntfs_debug("Done.  $LogFile indicates a clean shutdown.");
 	return TRUE;
-err_out:
-	ntfs_unmap_page(page);
-	return FALSE;
 }
 
 /**
diff --git a/fs/ntfs/logfile.h b/fs/ntfs/logfile.h
index 4ee4378de06..42388f95ea6 100644
--- a/fs/ntfs/logfile.h
+++ b/fs/ntfs/logfile.h
@@ -2,7 +2,7 @@
  * logfile.h - Defines for NTFS kernel journal ($LogFile) handling.  Part of
  *	       the Linux-NTFS project.
  *
- * Copyright (c) 2000-2004 Anton Altaparmakov
+ * Copyright (c) 2000-2005 Anton Altaparmakov
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -296,9 +296,11 @@ typedef struct {
 /* sizeof() = 160 (0xa0) bytes */
 } __attribute__ ((__packed__)) LOG_CLIENT_RECORD;
 
-extern BOOL ntfs_check_logfile(struct inode *log_vi);
+extern BOOL ntfs_check_logfile(struct inode *log_vi,
+		RESTART_PAGE_HEADER **rp);
 
-extern BOOL ntfs_is_logfile_clean(struct inode *log_vi);
+extern BOOL ntfs_is_logfile_clean(struct inode *log_vi,
+		const RESTART_PAGE_HEADER *rp);
 
 extern BOOL ntfs_empty_logfile(struct inode *log_vi);
 
diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
index fac5944df6d..3288bcc2c4a 100644
--- a/fs/ntfs/malloc.h
+++ b/fs/ntfs/malloc.h
@@ -27,27 +27,63 @@
 #include <linux/highmem.h>
 
 /**
- * ntfs_malloc_nofs - allocate memory in multiples of pages
- * @size	number of bytes to allocate
+ * __ntfs_malloc - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ * @gfp_mask:	extra flags for the allocator
+ *
+ * Internal function.  You probably want ntfs_malloc_nofs()...
  *
  * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
  * returns a pointer to the allocated memory.
  *
  * If there was insufficient memory to complete the request, return NULL.
+ * Depending on @gfp_mask the allocation may be guaranteed to succeed.
  */
-static inline void *ntfs_malloc_nofs(unsigned long size)
+static inline void *__ntfs_malloc(unsigned long size,
+		unsigned int __nocast gfp_mask)
 {
 	if (likely(size <= PAGE_SIZE)) {
 		BUG_ON(!size);
 		/* kmalloc() has per-CPU caches so is faster for now. */
-		return kmalloc(PAGE_SIZE, GFP_NOFS);
-		/* return (void *)__get_free_page(GFP_NOFS | __GFP_HIGHMEM); */
+		return kmalloc(PAGE_SIZE, gfp_mask & ~__GFP_HIGHMEM);
+		/* return (void *)__get_free_page(gfp_mask); */
 	}
 	if (likely(size >> PAGE_SHIFT < num_physpages))
-		return __vmalloc(size, GFP_NOFS | __GFP_HIGHMEM, PAGE_KERNEL);
+		return __vmalloc(size, gfp_mask, PAGE_KERNEL);
 	return NULL;
 }
 
+/**
+ * ntfs_malloc_nofs - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ */
+static inline void *ntfs_malloc_nofs(unsigned long size)
+{
+	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM);
+}
+
+/**
+ * ntfs_malloc_nofs_nofail - allocate memory in multiples of pages
+ * @size:	number of bytes to allocate
+ *
+ * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
+ * returns a pointer to the allocated memory.
+ *
+ * This function guarantees that the allocation will succeed.  It will sleep
+ * for as long as it takes to complete the allocation.
+ *
+ * If there was insufficient memory to complete the request, return NULL.
+ */
+static inline void *ntfs_malloc_nofs_nofail(unsigned long size)
+{
+	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM | __GFP_NOFAIL);
+}
+
 static inline void ntfs_free(void *addr)
 {
 	if (likely(((unsigned long)addr < VMALLOC_START) ||
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 317f7c679fd..2c32b84385a 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -511,7 +511,6 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
 		} while (bh);
 		tail->b_this_page = head;
 		attach_page_buffers(page, head);
-		BUG_ON(!page_has_buffers(page));
 	}
 	bh = head = page_buffers(page);
 	BUG_ON(!bh);
@@ -692,7 +691,6 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
 	 */
 	if (!NInoTestClearDirty(ni))
 		goto done;
-	BUG_ON(!page_has_buffers(page));
 	bh = head = page_buffers(page);
 	BUG_ON(!bh);
 	rl = NULL;
@@ -1955,7 +1953,7 @@ restore_undo_alloc:
 	a = ctx->attr;
 	a->data.non_resident.highest_vcn = cpu_to_sle64(old_last_vcn - 1);
 undo_alloc:
-	if (ntfs_cluster_free(vol->mft_ino, old_last_vcn, -1) < 0) {
+	if (ntfs_cluster_free(vol->mft_ino, old_last_vcn, -1, TRUE) < 0) {
 		ntfs_error(vol->sb, "Failed to free clusters from mft data "
 				"attribute.%s", es);
 		NVolSetErrors(vol);
diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c
index 758855b0414..f5b2ac92908 100644
--- a/fs/ntfs/runlist.c
+++ b/fs/ntfs/runlist.c
@@ -35,7 +35,7 @@ static inline void ntfs_rl_mm(runlist_element *base, int dst, int src,
 		int size)
 {
 	if (likely((dst != src) && (size > 0)))
-		memmove(base + dst, base + src, size * sizeof (*base));
+		memmove(base + dst, base + src, size * sizeof(*base));
 }
 
 /**
@@ -95,6 +95,51 @@ static inline runlist_element *ntfs_rl_realloc(runlist_element *rl,
 }
 
 /**
+ * ntfs_rl_realloc_nofail - Reallocate memory for runlists
+ * @rl:		original runlist
+ * @old_size:	number of runlist elements in the original runlist @rl
+ * @new_size:	number of runlist elements we need space for
+ *
+ * As the runlists grow, more memory will be required.  To prevent the
+ * kernel having to allocate and reallocate large numbers of small bits of
+ * memory, this function returns an entire page of memory.
+ *
+ * This function guarantees that the allocation will succeed.  It will sleep
+ * for as long as it takes to complete the allocation.
+ *
+ * It is up to the caller to serialize access to the runlist @rl.
+ *
+ * N.B.  If the new allocation doesn't require a different number of pages in
+ *       memory, the function will return the original pointer.
+ *
+ * On success, return a pointer to the newly allocated, or recycled, memory.
+ * On error, return -errno. The following error codes are defined:
+ *	-ENOMEM	- Not enough memory to allocate runlist array.
+ *	-EINVAL	- Invalid parameters were passed in.
+ */
+static inline runlist_element *ntfs_rl_realloc_nofail(runlist_element *rl,
+		int old_size, int new_size)
+{
+	runlist_element *new_rl;
+
+	old_size = PAGE_ALIGN(old_size * sizeof(*rl));
+	new_size = PAGE_ALIGN(new_size * sizeof(*rl));
+	if (old_size == new_size)
+		return rl;
+
+	new_rl = ntfs_malloc_nofs_nofail(new_size);
+	BUG_ON(!new_rl);
+
+	if (likely(rl != NULL)) {
+		if (unlikely(old_size > new_size))
+			old_size = new_size;
+		memcpy(new_rl, rl, old_size);
+		ntfs_free(rl);
+	}
+	return new_rl;
+}
+
+/**
  * ntfs_are_rl_mergeable - test if two runlists can be joined together
  * @dst:	original runlist
  * @src:	new runlist to test for mergeability with @dst
@@ -497,6 +542,7 @@ runlist_element *ntfs_runlists_merge(runlist_element *drl,
 			/* Scan to the end of the source runlist. */
 			for (dend = 0; likely(drl[dend].length); dend++)
 				;
+			dend++;
 			drl = ntfs_rl_realloc(drl, dend, dend + 1);
 			if (IS_ERR(drl))
 				return drl;
@@ -566,8 +612,8 @@ runlist_element *ntfs_runlists_merge(runlist_element *drl,
 		 ((drl[dins].vcn + drl[dins].length) <=      /* End of hole   */
 		  (srl[send - 1].vcn + srl[send - 1].length)));
 
-	/* Or we'll lose an end marker */
-	if (start && finish && (drl[dins].length == 0))
+	/* Or we will lose an end marker. */
+	if (finish && !drl[dins].length)
 		ss++;
 	if (marker && (drl[dins].vcn + drl[dins].length > srl[send - 1].vcn))
 		finish = FALSE;
@@ -621,11 +667,8 @@ runlist_element *ntfs_runlists_merge(runlist_element *drl,
 			if (drl[ds].lcn != LCN_RL_NOT_MAPPED) {
 				/* Add an unmapped runlist element. */
 				if (!slots) {
-					/* FIXME/TODO: We need to have the
-					 * extra memory already! (AIA) */
-					drl = ntfs_rl_realloc(drl, ds, ds + 2);
-					if (!drl)
-						goto critical_error;
+					drl = ntfs_rl_realloc_nofail(drl, ds,
+							ds + 2);
 					slots = 2;
 				}
 				ds++;
@@ -640,13 +683,8 @@ runlist_element *ntfs_runlists_merge(runlist_element *drl,
 			drl[ds].length = marker_vcn - drl[ds].vcn;
 			/* Finally add the ENOENT terminator. */
 			ds++;
-			if (!slots) {
-				/* FIXME/TODO: We need to have the extra
-				 * memory already! (AIA) */
-				drl = ntfs_rl_realloc(drl, ds, ds + 1);
-				if (!drl)
-					goto critical_error;
-			}
+			if (!slots)
+				drl = ntfs_rl_realloc_nofail(drl, ds, ds + 1);
 			drl[ds].vcn = marker_vcn;
 			drl[ds].lcn = LCN_ENOENT;
 			drl[ds].length = (s64)0;
@@ -659,11 +697,6 @@ finished:
 	ntfs_debug("Merged runlist:");
 	ntfs_debug_dump_runlist(drl);
 	return drl;
-
-critical_error:
-	/* Critical error! We cannot afford to fail here. */
-	ntfs_error(NULL, "Critical error! Not enough memory.");
-	panic("NTFS: Cannot continue.");
 }
 
 /**
@@ -727,6 +760,9 @@ runlist_element *ntfs_mapping_pairs_decompress(const ntfs_volume *vol,
 		ntfs_error(vol->sb, "Corrupt attribute.");
 		return ERR_PTR(-EIO);
 	}
+	/* If the mapping pairs array is valid but empty, nothing to do. */
+	if (!vcn && !*buf)
+		return old_rl;
 	/* Current position in runlist array. */
 	rlpos = 0;
 	/* Allocate first page and set current runlist size to one page. */
@@ -1419,6 +1455,7 @@ err_out:
 
 /**
  * ntfs_rl_truncate_nolock - truncate a runlist starting at a specified vcn
+ * @vol:	ntfs volume (needed for error output)
  * @runlist:	runlist to truncate
  * @new_length:	the new length of the runlist in VCNs
  *
@@ -1426,12 +1463,16 @@ err_out:
  * holding the runlist elements to a length of @new_length VCNs.
  *
  * If @new_length lies within the runlist, the runlist elements with VCNs of
- * @new_length and above are discarded.
+ * @new_length and above are discarded.  As a special case if @new_length is
+ * zero, the runlist is discarded and set to NULL.
  *
  * If @new_length lies beyond the runlist, a sparse runlist element is added to
  * the end of the runlist @runlist or if the last runlist element is a sparse
  * one already, this is extended.
  *
+ * Note, no checking is done for unmapped runlist elements.  It is assumed that
+ * the caller has mapped any elements that need to be mapped already.
+ *
  * Return 0 on success and -errno on error.
  *
  * Locking: The caller must hold @runlist->lock for writing.
@@ -1446,6 +1487,13 @@ int ntfs_rl_truncate_nolock(const ntfs_volume *vol, runlist *const runlist,
 	BUG_ON(!runlist);
 	BUG_ON(new_length < 0);
 	rl = runlist->rl;
+	if (!new_length) {
+		ntfs_debug("Freeing runlist.");
+		runlist->rl = NULL;
+		if (rl)
+			ntfs_free(rl);
+		return 0;
+	}
 	if (unlikely(!rl)) {
 		/*
 		 * Create a runlist consisting of a sparse runlist element of
@@ -1553,4 +1601,288 @@ int ntfs_rl_truncate_nolock(const ntfs_volume *vol, runlist *const runlist,
 	return 0;
 }
 
+/**
+ * ntfs_rl_punch_nolock - punch a hole into a runlist
+ * @vol:	ntfs volume (needed for error output)
+ * @runlist:	runlist to punch a hole into
+ * @start:	starting VCN of the hole to be created
+ * @length:	size of the hole to be created in units of clusters
+ *
+ * Punch a hole into the runlist @runlist starting at VCN @start and of size
+ * @length clusters.
+ *
+ * Return 0 on success and -errno on error, in which case @runlist has not been
+ * modified.
+ *
+ * If @start and/or @start + @length are outside the runlist return error code
+ * -ENOENT.
+ *
+ * If the runlist contains unmapped or error elements between @start and @start
+ * + @length return error code -EINVAL.
+ *
+ * Locking: The caller must hold @runlist->lock for writing.
+ */
+int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist,
+		const VCN start, const s64 length)
+{
+	const VCN end = start + length;
+	s64 delta;
+	runlist_element *rl, *rl_end, *rl_real_end, *trl;
+	int old_size;
+	BOOL lcn_fixup = FALSE;
+
+	ntfs_debug("Entering for start 0x%llx, length 0x%llx.",
+			(long long)start, (long long)length);
+	BUG_ON(!runlist);
+	BUG_ON(start < 0);
+	BUG_ON(length < 0);
+	BUG_ON(end < 0);
+	rl = runlist->rl;
+	if (unlikely(!rl)) {
+		if (likely(!start && !length))
+			return 0;
+		return -ENOENT;
+	}
+	/* Find @start in the runlist. */
+	while (likely(rl->length && start >= rl[1].vcn))
+		rl++;
+	rl_end = rl;
+	/* Find @end in the runlist. */
+	while (likely(rl_end->length && end >= rl_end[1].vcn)) {
+		/* Verify there are no unmapped or error elements. */
+		if (unlikely(rl_end->lcn < LCN_HOLE))
+			return -EINVAL;
+		rl_end++;
+	}
+	/* Check the last element. */
+	if (unlikely(rl_end->length && rl_end->lcn < LCN_HOLE))
+		return -EINVAL;
+	/* This covers @start being out of bounds, too. */
+	if (!rl_end->length && end > rl_end->vcn)
+		return -ENOENT;
+	if (!length)
+		return 0;
+	if (!rl->length)
+		return -ENOENT;
+	rl_real_end = rl_end;
+	/* Determine the runlist size. */
+	while (likely(rl_real_end->length))
+		rl_real_end++;
+	old_size = rl_real_end - runlist->rl + 1;
+	/* If @start is in a hole simply extend the hole. */
+	if (rl->lcn == LCN_HOLE) {
+		/*
+		 * If both @start and @end are in the same sparse run, we are
+		 * done.
+		 */
+		if (end <= rl[1].vcn) {
+			ntfs_debug("Done (requested hole is already sparse).");
+			return 0;
+		}
+extend_hole:
+		/* Extend the hole. */
+		rl->length = end - rl->vcn;
+		/* If @end is in a hole, merge it with the current one. */
+		if (rl_end->lcn == LCN_HOLE) {
+			rl_end++;
+			rl->length = rl_end->vcn - rl->vcn;
+		}
+		/* We have done the hole.  Now deal with the remaining tail. */
+		rl++;
+		/* Cut out all runlist elements up to @end. */
+		if (rl < rl_end)
+			memmove(rl, rl_end, (rl_real_end - rl_end + 1) *
+					sizeof(*rl));
+		/* Adjust the beginning of the tail if necessary. */
+		if (end > rl->vcn) {
+			s64 delta = end - rl->vcn;
+			rl->vcn = end;
+			rl->length -= delta;
+			/* Only adjust the lcn if it is real. */
+			if (rl->lcn >= 0)
+				rl->lcn += delta;
+		}
+shrink_allocation:
+		/* Reallocate memory if the allocation changed. */
+		if (rl < rl_end) {
+			rl = ntfs_rl_realloc(runlist->rl, old_size,
+					old_size - (rl_end - rl));
+			if (IS_ERR(rl))
+				ntfs_warning(vol->sb, "Failed to shrink "
+						"runlist buffer.  This just "
+						"wastes a bit of memory "
+						"temporarily so we ignore it "
+						"and return success.");
+			else
+				runlist->rl = rl;
+		}
+		ntfs_debug("Done (extend hole).");
+		return 0;
+	}
+	/*
+	 * If @start is at the beginning of a run things are easier as there is
+	 * no need to split the first run.
+	 */
+	if (start == rl->vcn) {
+		/*
+		 * @start is at the beginning of a run.
+		 *
+		 * If the previous run is sparse, extend its hole.
+		 *
+		 * If @end is not in the same run, switch the run to be sparse
+		 * and extend the newly created hole.
+		 *
+		 * Thus both of these cases reduce the problem to the above
+		 * case of "@start is in a hole".
+		 */
+		if (rl > runlist->rl && (rl - 1)->lcn == LCN_HOLE) {
+			rl--;
+			goto extend_hole;
+		}
+		if (end >= rl[1].vcn) {
+			rl->lcn = LCN_HOLE;
+			goto extend_hole;
+		}
+		/*
+		 * The final case is when @end is in the same run as @start.
+		 * For this need to split the run into two.  One run for the
+		 * sparse region between the beginning of the old run, i.e.
+		 * @start, and @end and one for the remaining non-sparse
+		 * region, i.e. between @end and the end of the old run.
+		 */
+		trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 1);
+		if (IS_ERR(trl))
+			goto enomem_out;
+		old_size++;
+		if (runlist->rl != trl) {
+			rl = trl + (rl - runlist->rl);
+			rl_end = trl + (rl_end - runlist->rl);
+			rl_real_end = trl + (rl_real_end - runlist->rl);
+			runlist->rl = trl;
+		}
+split_end:
+		/* Shift all the runs up by one. */
+		memmove(rl + 1, rl, (rl_real_end - rl + 1) * sizeof(*rl));
+		/* Finally, setup the two split runs. */
+		rl->lcn = LCN_HOLE;
+		rl->length = length;
+		rl++;
+		rl->vcn += length;
+		/* Only adjust the lcn if it is real. */
+		if (rl->lcn >= 0 || lcn_fixup)
+			rl->lcn += length;
+		rl->length -= length;
+		ntfs_debug("Done (split one).");
+		return 0;
+	}
+	/*
+	 * @start is neither in a hole nor at the beginning of a run.
+	 *
+	 * If @end is in a hole, things are easier as simply truncating the run
+	 * @start is in to end at @start - 1, deleting all runs after that up
+	 * to @end, and finally extending the beginning of the run @end is in
+	 * to be @start is all that is needed.
+	 */
+	if (rl_end->lcn == LCN_HOLE) {
+		/* Truncate the run containing @start. */
+		rl->length = start - rl->vcn;
+		rl++;
+		/* Cut out all runlist elements up to @end. */
+		if (rl < rl_end)
+			memmove(rl, rl_end, (rl_real_end - rl_end + 1) *
+					sizeof(*rl));
+		/* Extend the beginning of the run @end is in to be @start. */
+		rl->vcn = start;
+		rl->length = rl[1].vcn - start;
+		goto shrink_allocation;
+	}
+	/* 
+	 * If @end is not in a hole there are still two cases to distinguish.
+	 * Either @end is or is not in the same run as @start.
+	 *
+	 * The second case is easier as it can be reduced to an already solved
+	 * problem by truncating the run @start is in to end at @start - 1.
+	 * Then, if @end is in the next run need to split the run into a sparse
+	 * run followed by a non-sparse run (already covered above) and if @end
+	 * is not in the next run switching it to be sparse, again reduces the
+	 * problem to the already covered case of "@start is in a hole".
+	 */
+	if (end >= rl[1].vcn) {
+		/*
+		 * If @end is not in the next run, reduce the problem to the
+		 * case of "@start is in a hole".
+		 */
+		if (rl[1].length && end >= rl[2].vcn) {
+			/* Truncate the run containing @start. */
+			rl->length = start - rl->vcn;
+			rl++;
+			rl->vcn = start;
+			rl->lcn = LCN_HOLE;
+			goto extend_hole;
+		}
+		trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 1);
+		if (IS_ERR(trl))
+			goto enomem_out;
+		old_size++;
+		if (runlist->rl != trl) {
+			rl = trl + (rl - runlist->rl);
+			rl_end = trl + (rl_end - runlist->rl);
+			rl_real_end = trl + (rl_real_end - runlist->rl);
+			runlist->rl = trl;
+		}
+		/* Truncate the run containing @start. */
+		rl->length = start - rl->vcn;
+		rl++;
+		/*
+		 * @end is in the next run, reduce the problem to the case
+		 * where "@start is at the beginning of a run and @end is in
+		 * the same run as @start".
+		 */
+		delta = rl->vcn - start;
+		rl->vcn = start;
+		if (rl->lcn >= 0) {
+			rl->lcn -= delta;
+			/* Need this in case the lcn just became negative. */
+			lcn_fixup = TRUE;
+		}
+		rl->length += delta;
+		goto split_end;
+	}
+	/*
+	 * The first case from above, i.e. @end is in the same run as @start.
+	 * We need to split the run into three.  One run for the non-sparse
+	 * region between the beginning of the old run and @start, one for the
+	 * sparse region between @start and @end, and one for the remaining
+	 * non-sparse region, i.e. between @end and the end of the old run.
+	 */
+	trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 2);
+	if (IS_ERR(trl))
+		goto enomem_out;
+	old_size += 2;
+	if (runlist->rl != trl) {
+		rl = trl + (rl - runlist->rl);
+		rl_end = trl + (rl_end - runlist->rl);
+		rl_real_end = trl + (rl_real_end - runlist->rl);
+		runlist->rl = trl;
+	}
+	/* Shift all the runs up by two. */
+	memmove(rl + 2, rl, (rl_real_end - rl + 1) * sizeof(*rl));
+	/* Finally, setup the three split runs. */
+	rl->length = start - rl->vcn;
+	rl++;
+	rl->vcn = start;
+	rl->lcn = LCN_HOLE;
+	rl->length = length;
+	rl++;
+	delta = end - rl->vcn;
+	rl->vcn = end;
+	rl->lcn += delta;
+	rl->length -= delta;
+	ntfs_debug("Done (split both).");
+	return 0;
+enomem_out:
+	ntfs_error(vol->sb, "Not enough memory to extend runlist buffer.");
+	return -ENOMEM;
+}
+
 #endif /* NTFS_RW */
diff --git a/fs/ntfs/runlist.h b/fs/ntfs/runlist.h
index aa0ee6540e7..47728fbb610 100644
--- a/fs/ntfs/runlist.h
+++ b/fs/ntfs/runlist.h
@@ -94,6 +94,9 @@ extern int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst,
 extern int ntfs_rl_truncate_nolock(const ntfs_volume *vol,
 		runlist *const runlist, const s64 new_length);
 
+int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist,
+		const VCN start, const s64 length);
+
 #endif /* NTFS_RW */
 
 #endif /* _LINUX_NTFS_RUNLIST_H */
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 41aa8eb6755..453d0d51ea4 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -126,6 +126,14 @@ static BOOL parse_options(ntfs_volume *vol, char *opt)
 		if (*v)							\
 			goto needs_val;					\
 	}
+#define NTFS_GETOPT_OCTAL(option, variable)				\
+	if (!strcmp(p, option)) {					\
+		if (!v || !*v)						\
+			goto needs_arg;					\
+		variable = simple_strtoul(ov = v, &v, 8);		\
+		if (*v)							\
+			goto needs_val;					\
+	}
 #define NTFS_GETOPT_BOOL(option, variable)				\
 	if (!strcmp(p, option)) {					\
 		BOOL val;						\
@@ -157,9 +165,9 @@ static BOOL parse_options(ntfs_volume *vol, char *opt)
 			*v++ = 0;
 		NTFS_GETOPT("uid", uid)
 		else NTFS_GETOPT("gid", gid)
-		else NTFS_GETOPT("umask", fmask = dmask)
-		else NTFS_GETOPT("fmask", fmask)
-		else NTFS_GETOPT("dmask", dmask)
+		else NTFS_GETOPT_OCTAL("umask", fmask = dmask)
+		else NTFS_GETOPT_OCTAL("fmask", fmask)
+		else NTFS_GETOPT_OCTAL("dmask", dmask)
 		else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
 		else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, TRUE)
 		else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
@@ -1133,7 +1141,8 @@ mft_unmap_out:
  *
  * Return TRUE on success or FALSE on error.
  */
-static BOOL load_and_check_logfile(ntfs_volume *vol)
+static BOOL load_and_check_logfile(ntfs_volume *vol,
+		RESTART_PAGE_HEADER **rp)
 {
 	struct inode *tmp_ino;
 
@@ -1145,7 +1154,7 @@ static BOOL load_and_check_logfile(ntfs_volume *vol)
 		/* Caller will display error message. */
 		return FALSE;
 	}
-	if (!ntfs_check_logfile(tmp_ino)) {
+	if (!ntfs_check_logfile(tmp_ino, rp)) {
 		iput(tmp_ino);
 		/* ntfs_check_logfile() will have displayed error output. */
 		return FALSE;
@@ -1689,6 +1698,7 @@ static BOOL load_system_files(ntfs_volume *vol)
 	VOLUME_INFORMATION *vi;
 	ntfs_attr_search_ctx *ctx;
 #ifdef NTFS_RW
+	RESTART_PAGE_HEADER *rp;
 	int err;
 #endif /* NTFS_RW */
 
@@ -1841,8 +1851,9 @@ get_ctx_vol_failed:
 	 * Get the inode for the logfile, check it and determine if the volume
 	 * was shutdown cleanly.
 	 */
-	if (!load_and_check_logfile(vol) ||
-			!ntfs_is_logfile_clean(vol->logfile_ino)) {
+	rp = NULL;
+	if (!load_and_check_logfile(vol, &rp) ||
+			!ntfs_is_logfile_clean(vol->logfile_ino, rp)) {
 		static const char *es1a = "Failed to load $LogFile";
 		static const char *es1b = "$LogFile is not clean";
 		static const char *es2 = ".  Mount in Windows.";
@@ -1857,6 +1868,10 @@ get_ctx_vol_failed:
 						"continue nor on_errors="
 						"remount-ro was specified%s",
 						es1, es2);
+				if (vol->logfile_ino) {
+					BUG_ON(!rp);
+					ntfs_free(rp);
+				}
 				goto iput_logfile_err_out;
 			}
 			sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
@@ -1867,6 +1882,7 @@ get_ctx_vol_failed:
 		/* This will prevent a read-write remount. */
 		NVolSetErrors(vol);
 	}
+	ntfs_free(rp);
 #endif /* NTFS_RW */
 	/* Get the root directory inode so we can do path lookups. */
 	vol->root_ino = ntfs_iget(sb, FILE_root);
diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c
index 19c42e231b4..a389a5a16c8 100644
--- a/fs/ntfs/unistr.c
+++ b/fs/ntfs/unistr.c
@@ -372,7 +372,8 @@ retry:			wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
 	return -EINVAL;
 conversion_err:
 	ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
-			"converted to character set %s.", nls->charset);
+			"converted to character set %s.  You might want to "
+			"try to use the mount option nls=utf8.", nls->charset);
 	if (ns != *outs)
 		kfree(ns);
 	if (wc != -ENAMETOOLONG)