Merge git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs-2.6:
  NTFS: 2.1.27 - Various bug fixes and cleanups.
  NTFS: Semaphore to mutex conversion.
  NTFS: Handle the recently introduced -ENAMETOOLONG return value from
  NTFS: Add a missing call to flush_dcache_mft_record_page() in
  NTFS: Fix a bug in fs/ntfs/inode.c::ntfs_read_locked_index_inode() where we
  NTFS: Improve comments on file attribute flags in fs/ntfs/layout.h.
  NTFS: Limit name length in fs/ntfs/unistr.c::ntfs_nlstoucs() to maximum
  NTFS: Remove all the make_bad_inode() calls.  This should only be called
  NTFS: Add support for sparse files which have a compression unit of 0.
  NTFS: Fix comparison of $MFT and $MFTMirr to not bail out when there are
  NTFS: Use buffer_migrate_page() for the ->migratepage function of all ntfs
  NTFS: Fix a buggette in an "should be impossible" case handling where we
  NTFS: Fix an (innocent) off-by-one error in the runlist code.
  NTFS: Fix two compiler warnings on Alpha.  Thanks to Andrew Morton for

18 files changed, 294 insertions, 213 deletions

diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index 25116858789..638cbd3d2b0 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -457,6 +457,11 @@ ChangeLog
 
 Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
 
+2.1.27:
+	- Implement page migration support so the kernel can move memory used
+	  by NTFS files and directories around for management purposes.
+	- Add support for writing to sparse files created with Windows XP SP2.
+	- Many minor improvements and bug fixes.
 2.1.26:
 	- Implement support for sector sizes above 512 bytes (up to the maximum
 	  supported by NTFS which is 4096 bytes).
diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog
index 9d8ffa89e2c..35cc4b1d60f 100644
--- a/fs/ntfs/ChangeLog
+++ b/fs/ntfs/ChangeLog
@@ -16,8 +16,34 @@ ToDo/Notes:
 	  inode having been discarded already.  Whether this can actually ever
 	  happen is unclear however so it is worth waiting until someone hits
 	  the problem.
-	- Enable the code for setting the NT4 compatibility flag when we start
-	  making NTFS 1.2 specific modifications.
+
+2.1.27 - Various bug fixes and cleanups.
+
+	- Fix two compiler warnings on Alpha.  Thanks to Andrew Morton for
+	  reporting them.
+	- Fix an (innocent) off-by-one error in the runlist code.
+	- Fix a buggette in an "should be impossible" case handling where we
+	  continued the attribute lookup loop instead of aborting it.
+	- Use buffer_migrate_page() for the ->migratepage function of all ntfs
+	  address space operations.
+	- Fix comparison of $MFT and $MFTMirr to not bail out when there are
+	  unused, invalid mft records which are the same in both $MFT and
+	  $MFTMirr.
+	- Add support for sparse files which have a compression unit of 0.
+	- Remove all the make_bad_inode() calls.  This should only be called
+	  from read inode and new inode code paths.
+	- Limit name length in fs/ntfs/unistr.c::ntfs_nlstoucs() to maximum
+	  allowed by NTFS, i.e. 255 Unicode characters, not including the
+	  terminating NULL (which is not stored on disk).
+	- Improve comments on file attribute flags in fs/ntfs/layout.h.
+	- Fix a bug in fs/ntfs/inode.c::ntfs_read_locked_index_inode() where we
+	  forgot to update a temporary variable so loading index inodes which
+	  have an index allocation attribute failed.
+	- Add a missing call to flush_dcache_mft_record_page() in
+	  fs/ntfs/inode.c::ntfs_write_inode().
+	- Handle the recently introduced -ENAMETOOLONG return value from
+	  fs/ntfs/unistr.c::ntfs_nlstoucs() in fs/ntfs/namei.c::ntfs_lookup().
+	- Semaphore to mutex conversion.  (Ingo Molnar)
 
 2.1.26 - Minor bug fixes and updates.
 
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index d95fac7fdeb..e27b4eacffb 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=\"2.1.26\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.27\"
 
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 7e361da770b..580412d330c 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
@@ -1277,18 +1278,18 @@ unm_done:
 		
 		tni = locked_nis[nr_locked_nis];
 		/* Get the base inode. */
-		down(&tni->extent_lock);
+		mutex_lock(&tni->extent_lock);
 		if (tni->nr_extents >= 0)
 			base_tni = tni;
 		else {
 			base_tni = tni->ext.base_ntfs_ino;
 			BUG_ON(!base_tni);
 		}
-		up(&tni->extent_lock);
+		mutex_unlock(&tni->extent_lock);
 		ntfs_debug("Unlocking %s inode 0x%lx.",
 				tni == base_tni ? "base" : "extent",
 				tni->mft_no);
-		up(&tni->mrec_lock);
+		mutex_unlock(&tni->mrec_lock);
 		atomic_dec(&tni->count);
 		iput(VFS_I(base_tni));
 	}
@@ -1529,7 +1530,6 @@ err_out:
 				"error %i.", err);
 		SetPageError(page);
 		NVolSetErrors(ni->vol);
-		make_bad_inode(vi);
 	}
 	unlock_page(page);
 	if (ctx)
@@ -1551,6 +1551,9 @@ struct address_space_operations ntfs_aops = {
 #ifdef NTFS_RW
 	.writepage	= ntfs_writepage,	/* Write dirty page to disk. */
 #endif /* NTFS_RW */
+	.migratepage	= buffer_migrate_page,	/* Move a page cache page from
+						   one physical page to an
+						   other. */
 };
 
 /**
@@ -1567,6 +1570,9 @@ struct address_space_operations ntfs_mst_aops = {
 						   without touching the buffers
 						   belonging to the page. */
 #endif /* NTFS_RW */
+	.migratepage	= buffer_migrate_page,	/* Move a page cache page from
+						   one physical page to an
+						   other. */
 };
 
 #ifdef NTFS_RW
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 9480a0526cd..1663f5c3c6a 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -1,7 +1,7 @@
 /**
  * attrib.c - NTFS attribute operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -1048,7 +1048,7 @@ do_next_attr_loop:
 				le32_to_cpu(ctx->mrec->bytes_allocated))
 			break;
 		if (a->type == AT_END)
-			continue;
+			break;
 		if (!a->length)
 			break;
 		if (al_entry->instance != a->instance)
@@ -1695,7 +1695,9 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 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.compression_unit = 0;
+		if (NInoCompressed(ni) || vol->major_ver < 3)
+			a->data.non_resident.compression_unit = 4;
 		a->data.non_resident.compressed_size =
 				a->data.non_resident.allocated_size;
 	} else
@@ -1714,13 +1716,20 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
 	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;
+		if (a->data.non_resident.compression_unit) {
+			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;
+		} else {
+			ni->itype.compressed.block_size = 0;
+			ni->itype.compressed.block_size_bits = 0;
+			ni->itype.compressed.block_clusters = 0;
+		}
 		vi->i_blocks = ni->itype.compressed.size >> 9;
 	} else
 		vi->i_blocks = ni->allocated_size >> 9;
@@ -2429,16 +2438,12 @@ undo_alloc:
 				"chkdsk to recover.", IS_ERR(m) ?
 				"restore attribute search context" :
 				"truncate attribute runlist");
-		make_bad_inode(vi);
-		make_bad_inode(VFS_I(base_ni));
 		NVolSetErrors(vol);
 	} else if (mp_rebuilt) {
 		if (ntfs_attr_record_resize(m, a, attr_len)) {
 			ntfs_error(vol->sb, "Failed to restore attribute "
 					"record in error code path.  Run "
 					"chkdsk to recover.");
-			make_bad_inode(vi);
-			make_bad_inode(VFS_I(base_ni));
 			NVolSetErrors(vol);
 		} else /* if (success) */ {
 			if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
@@ -2451,8 +2456,6 @@ undo_alloc:
 						"mapping pairs array in error "
 						"code path.  Run chkdsk to "
 						"recover.");
-				make_bad_inode(vi);
-				make_bad_inode(VFS_I(base_ni));
 				NVolSetErrors(vol);
 			}
 			flush_dcache_mft_record_page(ctx->ntfs_ino);
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index 25d24106f89..68a607ff9fd 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -67,7 +67,7 @@ static DEFINE_SPINLOCK(ntfs_cb_lock);
 /**
  * allocate_compression_buffers - allocate the decompression buffers
  *
- * Caller has to hold the ntfs_lock semaphore.
+ * Caller has to hold the ntfs_lock mutex.
  *
  * Return 0 on success or -ENOMEM if the allocations failed.
  */
@@ -84,7 +84,7 @@ int allocate_compression_buffers(void)
 /**
  * free_compression_buffers - free the decompression buffers
  *
- * Caller has to hold the ntfs_lock semaphore.
+ * Caller has to hold the ntfs_lock mutex.
  */
 void free_compression_buffers(void)
 {
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index b0690d4c890..9d9ed3fe371 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1136,7 +1136,7 @@ static int ntfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	if (fpos == 1) {
 		ntfs_debug("Calling filldir for .. with len 2, fpos 0x1, "
 				"inode 0x%lx, DT_DIR.",
-				parent_ino(filp->f_dentry));
+				(unsigned long)parent_ino(filp->f_dentry));
 		rc = filldir(dirent, "..", 2, fpos,
 				parent_ino(filp->f_dentry), DT_DIR);
 		if (rc)
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 5027d3d1b3f..f5d057e4acc 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -943,7 +943,8 @@ rl_not_mapped_enoent:
 		}
 		ni->runlist.rl = rl;
 		status.runlist_merged = 1;
-		ntfs_debug("Allocated cluster, lcn 0x%llx.", lcn);
+		ntfs_debug("Allocated cluster, lcn 0x%llx.",
+				(unsigned long long)lcn);
 		/* Map and lock the mft record and get the attribute record. */
 		if (!NInoAttr(ni))
 			base_ni = ni;
@@ -1206,8 +1207,6 @@ rl_not_mapped_enoent:
 					"attribute runlist in error code "
 					"path.  Run chkdsk to recover the "
 					"lost cluster.");
-			make_bad_inode(vi);
-			make_bad_inode(VFS_I(base_ni));
 			NVolSetErrors(vol);
 		} else /* if (success) */ {
 			status.runlist_merged = 0;
@@ -1238,8 +1237,6 @@ rl_not_mapped_enoent:
 			ntfs_error(vol->sb, "Failed to restore attribute "
 					"record in error code path.  Run "
 					"chkdsk to recover.");
-			make_bad_inode(vi);
-			make_bad_inode(VFS_I(base_ni));
 			NVolSetErrors(vol);
 		} else /* if (success) */ {
 			if (ntfs_mapping_pairs_build(vol, (u8*)a +
@@ -1252,8 +1249,6 @@ rl_not_mapped_enoent:
 						"mapping pairs array in error "
 						"code path.  Run chkdsk to "
 						"recover.");
-				make_bad_inode(vi);
-				make_bad_inode(VFS_I(base_ni));
 				NVolSetErrors(vol);
 			}
 			flush_dcache_mft_record_page(ctx->ntfs_ino);
@@ -1622,11 +1617,8 @@ err_out:
 		unmap_mft_record(base_ni);
 	ntfs_error(vi->i_sb, "Failed to update initialized_size/i_size (error "
 			"code %i).", err);
-	if (err != -ENOMEM) {
+	if (err != -ENOMEM)
 		NVolSetErrors(ni->vol);
-		make_bad_inode(VFS_I(base_ni));
-		make_bad_inode(vi);
-	}
 	return err;
 }
 
@@ -1801,8 +1793,6 @@ err_out:
 		ntfs_error(vi->i_sb, "Resident attribute commit write failed "
 				"with error %i.", err);
 		NVolSetErrors(ni->vol);
-		make_bad_inode(VFS_I(base_ni));
-		make_bad_inode(vi);
 	}
 	if (ctx)
 		ntfs_attr_put_search_ctx(ctx);
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 55263b7de9c..4c86b7e1d1e 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -1,7 +1,7 @@
 /**
  * inode.c - NTFS kernel inode handling. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 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
@@ -19,13 +19,19 @@
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
-#include <linux/pagemap.h>
 #include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
-#include <linux/quotaops.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 #include <linux/mount.h>
+#include <linux/mutex.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
 
 #include "aops.h"
+#include "attrib.h"
+#include "bitmap.h"
 #include "dir.h"
 #include "debug.h"
 #include "inode.h"
@@ -382,7 +388,7 @@ void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni)
 	atomic_set(&ni->count, 1);
 	ni->vol = NTFS_SB(sb);
 	ntfs_init_runlist(&ni->runlist);
-	init_MUTEX(&ni->mrec_lock);
+	mutex_init(&ni->mrec_lock);
 	ni->page = NULL;
 	ni->page_ofs = 0;
 	ni->attr_list_size = 0;
@@ -394,7 +400,7 @@ void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni)
 	ni->itype.index.collation_rule = 0;
 	ni->itype.index.block_size_bits = 0;
 	ni->itype.index.vcn_size_bits = 0;
-	init_MUTEX(&ni->extent_lock);
+	mutex_init(&ni->extent_lock);
 	ni->nr_extents = 0;
 	ni->ext.base_ntfs_ino = NULL;
 }
@@ -1064,10 +1070,10 @@ skip_large_dir_stuff:
 		if (a->non_resident) {
 			NInoSetNonResident(ni);
 			if (NInoCompressed(ni) || NInoSparse(ni)) {
-				if (a->data.non_resident.compression_unit !=
-						4) {
+				if (NInoCompressed(ni) && a->data.non_resident.
+						compression_unit != 4) {
 					ntfs_error(vi->i_sb, "Found "
-							"nonstandard "
+							"non-standard "
 							"compression unit (%u "
 							"instead of 4).  "
 							"Cannot handle this.",
@@ -1076,16 +1082,26 @@ skip_large_dir_stuff:
 					err = -EOPNOTSUPP;
 					goto unm_err_out;
 				}
-				ni->itype.compressed.block_clusters = 1U <<
-						a->data.non_resident.
-						compression_unit;
-				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;
+				if (a->data.non_resident.compression_unit) {
+					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;
+				} else {
+					ni->itype.compressed.block_size = 0;
+					ni->itype.compressed.block_size_bits =
+							0;
+					ni->itype.compressed.block_clusters =
+							0;
+				}
 				ni->itype.compressed.size = sle64_to_cpu(
 						a->data.non_resident.
 						compressed_size);
@@ -1338,8 +1354,9 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 			goto unm_err_out;
 		}
 		if (NInoCompressed(ni) || NInoSparse(ni)) {
-			if (a->data.non_resident.compression_unit != 4) {
-				ntfs_error(vi->i_sb, "Found nonstandard "
+			if (NInoCompressed(ni) && a->data.non_resident.
+					compression_unit != 4) {
+				ntfs_error(vi->i_sb, "Found non-standard "
 						"compression unit (%u instead "
 						"of 4).  Cannot handle this.",
 						a->data.non_resident.
@@ -1347,13 +1364,22 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 				err = -EOPNOTSUPP;
 				goto unm_err_out;
 			}
-			ni->itype.compressed.block_clusters = 1U <<
-					a->data.non_resident.compression_unit;
-			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;
+			if (a->data.non_resident.compression_unit) {
+				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;
+			} else {
+				ni->itype.compressed.block_size = 0;
+				ni->itype.compressed.block_size_bits = 0;
+				ni->itype.compressed.block_clusters = 0;
+			}
 			ni->itype.compressed.size = sle64_to_cpu(
 					a->data.non_resident.compressed_size);
 		}
@@ -1406,7 +1432,6 @@ err_out:
 			"Run chkdsk.", err, vi->i_ino, ni->type, ni->name_len,
 			base_vi->i_ino);
 	make_bad_inode(vi);
-	make_bad_inode(base_vi);
 	if (err != -ENOMEM)
 		NVolSetErrors(vol);
 	return err;
@@ -1591,6 +1616,7 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
 					"$INDEX_ALLOCATION attribute.");
 		goto unm_err_out;
 	}
+	a = ctx->attr;
 	if (!a->non_resident) {
 		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
 				"resident.");
@@ -2823,11 +2849,8 @@ done:
 old_bad_out:
 	old_size = -1;
 bad_out:
-	if (err != -ENOMEM && err != -EOPNOTSUPP) {
-		make_bad_inode(vi);
-		make_bad_inode(VFS_I(base_ni));
+	if (err != -ENOMEM && err != -EOPNOTSUPP)
 		NVolSetErrors(vol);
-	}
 	if (err != -EOPNOTSUPP)
 		NInoSetTruncateFailed(ni);
 	else if (old_size >= 0)
@@ -2842,11 +2865,8 @@ out:
 	ntfs_debug("Failed.  Returning error code %i.", err);
 	return err;
 conv_err_out:
-	if (err != -ENOMEM && err != -EOPNOTSUPP) {
-		make_bad_inode(vi);
-		make_bad_inode(VFS_I(base_ni));
+	if (err != -ENOMEM && err != -EOPNOTSUPP)
 		NVolSetErrors(vol);
-	}
 	if (err != -EOPNOTSUPP)
 		NInoSetTruncateFailed(ni);
 	else
@@ -3044,15 +3064,18 @@ int ntfs_write_inode(struct inode *vi, int sync)
 	 * record will be cleaned and written out to disk below, i.e. before
 	 * this function returns.
 	 */
-	if (modified && !NInoTestSetDirty(ctx->ntfs_ino))
-		mark_ntfs_record_dirty(ctx->ntfs_ino->page,
-				ctx->ntfs_ino->page_ofs);
+	if (modified) {
+		flush_dcache_mft_record_page(ctx->ntfs_ino);
+		if (!NInoTestSetDirty(ctx->ntfs_ino))
+			mark_ntfs_record_dirty(ctx->ntfs_ino->page,
+					ctx->ntfs_ino->page_ofs);
+	}
 	ntfs_attr_put_search_ctx(ctx);
 	/* Now the access times are updated, write the base mft record. */
 	if (NInoDirty(ni))
 		err = write_mft_record(ni, m, sync);
 	/* Write all attached extent mft records. */
-	down(&ni->extent_lock);
+	mutex_lock(&ni->extent_lock);
 	if (ni->nr_extents > 0) {
 		ntfs_inode **extent_nis = ni->ext.extent_ntfs_inos;
 		int i;
@@ -3079,7 +3102,7 @@ int ntfs_write_inode(struct inode *vi, int sync)
 			}
 		}
 	}
-	up(&ni->extent_lock);
+	mutex_unlock(&ni->extent_lock);
 	unmap_mft_record(ni);
 	if (unlikely(err))
 		goto err_out;
@@ -3094,9 +3117,7 @@ err_out:
 				"retries later.");
 		mark_inode_dirty(vi);
 	} else {
-		ntfs_error(vi->i_sb, "Failed (error code %i):  Marking inode "
-				"as bad.  You should run chkdsk.", -err);
-		make_bad_inode(vi);
+		ntfs_error(vi->i_sb, "Failed (error %i):  Run chkdsk.", -err);
 		NVolSetErrors(ni->vol);
 	}
 	return err;
diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h
index 3de5c023196..f088291e017 100644
--- a/fs/ntfs/inode.h
+++ b/fs/ntfs/inode.h
@@ -24,12 +24,13 @@
 #ifndef _LINUX_NTFS_INODE_H
 #define _LINUX_NTFS_INODE_H
 
-#include <linux/mm.h>
+#include <asm/atomic.h>
+
 #include <linux/fs.h>
-#include <linux/seq_file.h>
 #include <linux/list.h>
-#include <asm/atomic.h>
-#include <asm/semaphore.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
 
 #include "layout.h"
 #include "volume.h"
@@ -81,7 +82,7 @@ struct _ntfs_inode {
 	 * The following fields are only valid for real inodes and extent
 	 * inodes.
 	 */
-	struct semaphore mrec_lock; /* Lock for serializing access to the
+	struct mutex mrec_lock;	/* Lock for serializing access to the
 				   mft record belonging to this inode. */
 	struct page *page;	/* The page containing the mft record of the
 				   inode. This should only be touched by the
@@ -119,7 +120,7 @@ struct _ntfs_inode {
 			u8 block_clusters;	/* Number of clusters per cb. */
 		} compressed;
 	} itype;
-	struct semaphore extent_lock;	/* Lock for accessing/modifying the
+	struct mutex extent_lock;	/* Lock for accessing/modifying the
 					   below . */
 	s32 nr_extents;	/* For a base mft record, the number of attached extent
 			   inodes (0 if none), for extent records and for fake
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index bb408d4dcbb..d34b93cb8b4 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -769,7 +769,7 @@ typedef struct {
 				compressed.  (This effectively limits the
 				compression unit size to be a power of two
 				clusters.)  WinNT4 only uses a value of 4.
-				Sparse files also have this set to 4. */
+				Sparse files have this set to 0 on XPSP2. */
 /* 35*/			u8 reserved[5];		/* Align to 8-byte boundary. */
 /* The sizes below are only used when lowest_vcn is zero, as otherwise it would
    be difficult to keep them up-to-date.*/
@@ -801,13 +801,16 @@ typedef struct {
 typedef ATTR_RECORD ATTR_REC;
 
 /*
- * File attribute flags (32-bit).
+ * File attribute flags (32-bit) appearing in the file_attributes fields of the
+ * STANDARD_INFORMATION attribute of MFT_RECORDs and the FILENAME_ATTR
+ * attributes of MFT_RECORDs and directory index entries.
+ *
+ * All of the below flags appear in the directory index entries but only some
+ * appear in the STANDARD_INFORMATION attribute whilst only some others appear
+ * in the FILENAME_ATTR attribute of MFT_RECORDs.  Unless otherwise stated the
+ * flags appear in all of the above.
  */
 enum {
-	/*
-	 * The following flags are only present in the STANDARD_INFORMATION
-	 * attribute (in the field file_attributes).
-	 */
 	FILE_ATTR_READONLY		= const_cpu_to_le32(0x00000001),
 	FILE_ATTR_HIDDEN		= const_cpu_to_le32(0x00000002),
 	FILE_ATTR_SYSTEM		= const_cpu_to_le32(0x00000004),
@@ -839,18 +842,14 @@ enum {
 	   F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
 	   is used to to obtain all flags that are valid for setting. */
 	/*
-	 * The following flag is only present in the FILE_NAME attribute (in
-	 * the field file_attributes).
+	 * The flag FILE_ATTR_DUP_FILENAME_INDEX_PRESENT is present in all
+	 * FILENAME_ATTR attributes but not in the STANDARD_INFORMATION
+	 * attribute of an mft record.
 	 */
 	FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT	= const_cpu_to_le32(0x10000000),
 	/* Note, this is a copy of the corresponding bit from the mft record,
 	   telling us whether this is a directory or not, i.e. whether it has
 	   an index root attribute or not. */
-	/*
-	 * The following flag is present both in the STANDARD_INFORMATION
-	 * attribute and in the FILE_NAME attribute (in the field
-	 * file_attributes).
-	 */
 	FILE_ATTR_DUP_VIEW_INDEX_PRESENT	= const_cpu_to_le32(0x20000000),
 	/* Note, this is a copy of the corresponding bit from the mft record,
 	   telling us whether this file has a view index present (eg. object id
@@ -891,7 +890,7 @@ typedef struct {
 					   Windows this is only updated when
 					   accessed if some time delta has
 					   passed since the last update. Also,
-					   last access times updates can be
+					   last access time updates can be
 					   disabled altogether for speed. */
 /* 32*/	FILE_ATTR_FLAGS file_attributes; /* Flags describing the file. */
 /* 36*/	union {
@@ -1076,16 +1075,21 @@ typedef struct {
 /* 20*/	sle64 last_access_time;		/* Time this mft record was last
 					   accessed. */
 /* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
-					   for the data attribute.  So for
-					   normal $DATA, this is the
+					   for the unnamed data attribute.  So
+					   for normal $DATA, this is the
 					   allocated_size from the unnamed
 					   $DATA attribute and for compressed
 					   and/or sparse $DATA, this is the
 					   compressed_size from the unnamed
-					   $DATA attribute.  NOTE: This is a
-					   multiple of the cluster size. */
-/* 30*/	sle64 data_size;		/* Byte size of actual data in data
-					   attribute. */
+					   $DATA attribute.  For a directory or
+					   other inode without an unnamed $DATA
+					   attribute, this is always 0.  NOTE:
+					   This is a multiple of the cluster
+					   size. */
+/* 30*/	sle64 data_size;		/* Byte size of actual data in unnamed
+					   data attribute.  For a directory or
+					   other inode without an unnamed $DATA
+					   attribute, this is always 0. */
 /* 38*/	FILE_ATTR_FLAGS file_attributes;	/* Flags describing the file. */
 /* 3c*/	union {
 	/* 3c*/	struct {
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 6499aafc225..4e72bc7afdf 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -93,6 +93,7 @@ static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
 				"Run chkdsk.", ni->mft_no);
 		ntfs_unmap_page(page);
 		page = ERR_PTR(-EIO);
+		NVolSetErrors(vol);
 	}
 err_out:
 	ni->page = NULL;
@@ -104,8 +105,8 @@ err_out:
  * map_mft_record - map, pin and lock an mft record
  * @ni:		ntfs inode whose MFT record to map
  *
- * First, take the mrec_lock semaphore. We might now be sleeping, while waiting
- * for the semaphore if it was already locked by someone else.
+ * First, take the mrec_lock mutex.  We might now be sleeping, while waiting
+ * for the mutex if it was already locked by someone else.
  *
  * The page of the record is mapped using map_mft_record_page() before being
  * returned to the caller.
@@ -135,9 +136,9 @@ err_out:
  * So that code will end up having to own the mrec_lock of all mft
  * records/inodes present in the page before I/O can proceed. In that case we
  * wouldn't need to bother with PG_locked and PG_uptodate as nobody will be
- * accessing anything without owning the mrec_lock semaphore. But we do need
- * to use them because of the read_cache_page() invocation and the code becomes
- * so much simpler this way that it is well worth it.
+ * accessing anything without owning the mrec_lock mutex.  But we do need to
+ * use them because of the read_cache_page() invocation and the code becomes so
+ * much simpler this way that it is well worth it.
  *
  * The mft record is now ours and we return a pointer to it. You need to check
  * the returned pointer with IS_ERR() and if that is true, PTR_ERR() will return
@@ -160,13 +161,13 @@ MFT_RECORD *map_mft_record(ntfs_inode *ni)
 	atomic_inc(&ni->count);
 
 	/* Serialize access to this mft record. */
-	down(&ni->mrec_lock);
+	mutex_lock(&ni->mrec_lock);
 
 	m = map_mft_record_page(ni);
 	if (likely(!IS_ERR(m)))
 		return m;
 
-	up(&ni->mrec_lock);
+	mutex_unlock(&ni->mrec_lock);
 	atomic_dec(&ni->count);
 	ntfs_error(ni->vol->sb, "Failed with error code %lu.", -PTR_ERR(m));
 	return m;
@@ -217,7 +218,7 @@ void unmap_mft_record(ntfs_inode *ni)
 	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
 
 	unmap_mft_record_page(ni);
-	up(&ni->mrec_lock);
+	mutex_unlock(&ni->mrec_lock);
 	atomic_dec(&ni->count);
 	/*
 	 * If pure ntfs_inode, i.e. no vfs inode attached, we leave it to
@@ -261,7 +262,7 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 	 * in which case just return it. If not found, add it to the base
 	 * inode before returning it.
 	 */
-	down(&base_ni->extent_lock);
+	mutex_lock(&base_ni->extent_lock);
 	if (base_ni->nr_extents > 0) {
 		extent_nis = base_ni->ext.extent_ntfs_inos;
 		for (i = 0; i < base_ni->nr_extents; i++) {
@@ -274,7 +275,7 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
 		}
 	}
 	if (likely(ni != NULL)) {
-		up(&base_ni->extent_lock);
+		mutex_unlock(&base_ni->extent_lock);
 		atomic_dec(&base_ni->count);
 		/* We found the record; just have to map and return it. */
 		m = map_mft_record(ni);
@@ -301,7 +302,7 @@ map_err_out:
 	/* Record wasn't there. Get a new ntfs inode and initialize it. */
 	ni = ntfs_new_extent_inode(base_ni->vol->sb, mft_no);
 	if (unlikely(!ni)) {
-		up(&base_ni->extent_lock);
+		mutex_unlock(&base_ni->extent_lock);
 		atomic_dec(&base_ni->count);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -312,7 +313,7 @@ map_err_out:
 	/* Now map the record. */
 	m = map_mft_record(ni);
 	if (IS_ERR(m)) {
-		up(&base_ni->extent_lock);
+		mutex_unlock(&base_ni->extent_lock);
 		atomic_dec(&base_ni->count);
 		ntfs_clear_extent_inode(ni);
 		goto map_err_out;
@@ -347,14 +348,14 @@ map_err_out:
 		base_ni->ext.extent_ntfs_inos = tmp;
 	}
 	base_ni->ext.extent_ntfs_inos[base_ni->nr_extents++] = ni;
-	up(&base_ni->extent_lock);
+	mutex_unlock(&base_ni->extent_lock);
 	atomic_dec(&base_ni->count);
 	ntfs_debug("Done 2.");
 	*ntfs_ino = ni;
 	return m;
 unm_err_out:
 	unmap_mft_record(ni);
-	up(&base_ni->extent_lock);
+	mutex_unlock(&base_ni->extent_lock);
 	atomic_dec(&base_ni->count);
 	/*
 	 * If the extent inode was not attached to the base inode we need to
@@ -399,12 +400,12 @@ void __mark_mft_record_dirty(ntfs_inode *ni)
 	BUG_ON(NInoAttr(ni));
 	mark_ntfs_record_dirty(ni->page, ni->page_ofs);
 	/* Determine the base vfs inode and mark it dirty, too. */
-	down(&ni->extent_lock);
+	mutex_lock(&ni->extent_lock);
 	if (likely(ni->nr_extents >= 0))
 		base_ni = ni;
 	else
 		base_ni = ni->ext.base_ntfs_ino;
-	up(&ni->extent_lock);
+	mutex_unlock(&ni->extent_lock);
 	__mark_inode_dirty(VFS_I(base_ni), I_DIRTY_SYNC | I_DIRTY_DATASYNC);
 }
 
@@ -650,10 +651,7 @@ err_out:
  * fs/ntfs/aops.c::mark_ntfs_record_dirty().
  *
  * On success, clean the mft record and return 0.  On error, leave the mft
- * record dirty and return -errno.  The caller should call make_bad_inode() on
- * the base inode to ensure no more access happens to this inode.  We do not do
- * it here as the caller may want to finish writing other extent mft records
- * first to minimize on-disk metadata inconsistencies.
+ * record dirty and return -errno.
  *
  * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
  * However, if the mft record has a counterpart in the mft mirror and @sync is
@@ -983,7 +981,7 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 		}
 		ntfs_debug("Inode 0x%lx is not dirty.", mft_no);
 		/* The inode is not dirty, try to take the mft record lock. */
-		if (unlikely(down_trylock(&ni->mrec_lock))) {
+		if (unlikely(!mutex_trylock(&ni->mrec_lock))) {
 			ntfs_debug("Mft record 0x%lx is already locked, do "
 					"not write it.", mft_no);
 			atomic_dec(&ni->count);
@@ -1043,13 +1041,13 @@ BOOL ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
 	 * corresponding to this extent mft record attached.
 	 */
 	ni = NTFS_I(vi);
-	down(&ni->extent_loc