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

Documentation/filesystems/ntfs.txt

@@ -457,6 +457,12 @@ ChangeLog
 
 Note, a technical ChangeLog aimed at kernel hackers is in fs/ntfs/ChangeLog.
 
+2.1.26:
+	- Implement support for sector sizes above 512 bytes (up to the maximum
+	  supported by NTFS which is 4096 bytes).
+	- Enhance support for NTFS volumes which were supported by Windows but
+	  not by Linux due to invalid attribute list attribute flags.
+	- A few minor updates and bug fixes.
 2.1.25:
 	- Write support is now extended with write(2) being able to both
 	  overwrite existing file data and to extend files.  Also, if a write

fs/ntfs/ChangeLog

@@ -1,9 +1,9 @@
 ToDo/Notes:
 	- Find and fix bugs.
 	- The only places in the kernel where a file is resized are
-	  ntfs_file_write*() and ntfs_truncate() for both of which i_sem is
+	  ntfs_file_write*() and ntfs_truncate() for both of which i_mutex is
 	  held.  Just have to be careful in read-/writepage and other helpers
-	  not running under i_sem that we play nice...  Also need to be careful
+	  not running under i_mutex that we play nice.  Also need to be careful
 	  with initialized_size extension in ntfs_file_write*() and writepage.
 	  UPDATE: The only things that need to be checked are the compressed
 	  write and the other attribute resize/write cases like index
@@ -19,6 +19,24 @@ ToDo/Notes:
 	- Enable the code for setting the NT4 compatibility flag when we start
 	  making NTFS 1.2 specific modifications.
 
+2.1.26 - Minor bug fixes and updates.
+
+	- Fix a potential overflow in file.c where a cast to s64 was missing in
+	  a left shift of a page index.
+	- The struct inode has had its i_sem semaphore changed to a mutex named
+	  i_mutex.
+	- We have struct kmem_cache now so use it instead of the typedef
+	  kmem_cache_t.  (Pekka Enberg)
+	- Implement support for sector sizes above 512 bytes (up to the maximum
+	  supported by NTFS which is 4096 bytes).
+	- Do more detailed reporting of why we cannot mount read-write by
+	  special casing the VOLUME_MODIFIED_BY_CHKDSK flag.
+	- Miscellaneous updates to layout.h.
+	- Cope with attribute list attribute having invalid flags.  Windows
+	  copes with this and even chkdsk does not detect or fix this so we
+	  have to cope with it, too.  Thanks to Pawel Kot for reporting the
+	  problem.
+
 2.1.25 - (Almost) fully implement write(2) and truncate(2).
 
 	- Change ntfs_map_runlist_nolock(), ntfs_attr_find_vcn_nolock() and
@@ -373,7 +391,7 @@ ToDo/Notes:
 	  single one of them had an mst error.  (Thanks to Ken MacFerrin for
 	  the bug report.)
 	- Fix error handling in fs/ntfs/quota.c::ntfs_mark_quotas_out_of_date()
-	  where we failed to release i_sem on the $Quota/$Q attribute inode.
+	  where we failed to release i_mutex on the $Quota/$Q attribute inode.
 	- Fix bug in handling of bad inodes in fs/ntfs/namei.c::ntfs_lookup().
 	- Add mapping of unmapped buffers to all remaining code paths, i.e.
 	  fs/ntfs/aops.c::ntfs_write_mst_block(), mft.c::ntfs_sync_mft_mirror(),
@@ -874,7 +892,7 @@ ToDo/Notes:
 	  clusters. (Philipp Thomas)
 	- attrib.c::load_attribute_list(): Fix bug when initialized_size is a
 	  multiple of the block_size but not the cluster size. (Szabolcs
-	  Szakacsits <szaka@sienet.hu>)
+	  Szakacsits)
 
 2.1.2 - Important bug fixes aleviating the hangs in statfs.
 
@@ -884,7 +902,7 @@ ToDo/Notes:
 
 	- Add handling for initialized_size != data_size in compressed files.
 	- Reduce function local stack usage from 0x3d4 bytes to just noise in
-	  fs/ntfs/upcase.c. (Randy Dunlap <rdunlap@xenotime.net>)
+	  fs/ntfs/upcase.c. (Randy Dunlap)
 	- Remove compiler warnings for newer gcc.
 	- Pages are no longer kmapped by mm/filemap.c::generic_file_write()
 	  around calls to ->{prepare,commit}_write.  Adapt NTFS appropriately
@@ -1201,11 +1219,11 @@ ToDo/Notes:
 	  the kernel. We probably want a kernel generic init_address_space()
 	  function...
 	- Drop BKL from ntfs_readdir() after consultation with Al Viro. The
-	  only caller of ->readdir() is vfs_readdir() which holds i_sem during
+	  only caller of ->readdir() is vfs_readdir() which holds i_mutex
-	  the call, and i_sem is sufficient protection against changes in the
+	  during the call, and i_mutex is sufficient protection against changes
-	  directory inode (including ->i_size).
+	  in the directory inode (including ->i_size).
 	- Use generic_file_llseek() for directories (as opposed to
-	  default_llseek()) as this downs i_sem instead of the BKL which is
+	  default_llseek()) as this downs i_mutex instead of the BKL which is
 	  what we now need for exclusion against ->f_pos changes considering we
 	  no longer take the BKL in ntfs_readdir().
 

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=\"2.1.25\"
+EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.26\"
 
 ifeq ($(CONFIG_NTFS_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG

fs/ntfs/aops.c

@@ -2,7 +2,7 @@
  * aops.c - NTFS kernel address space operations and page cache handling.
  *	    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
@@ -200,8 +200,8 @@ static int ntfs_read_block(struct page *page)
 	/* $MFT/$DATA must have its complete runlist in memory at all times. */
 	BUG_ON(!ni->runlist.rl && !ni->mft_no && !NInoAttr(ni));
 
-	blocksize_bits = VFS_I(ni)->i_blkbits;
+	blocksize = vol->sb->s_blocksize;
-	blocksize = 1 << blocksize_bits;
+	blocksize_bits = vol->sb->s_blocksize_bits;
 
 	if (!page_has_buffers(page)) {
 		create_empty_buffers(page, blocksize, 0);
@@ -569,10 +569,8 @@ static int ntfs_write_block(struct page *page, struct writeback_control *wbc)
 
 	BUG_ON(!NInoNonResident(ni));
 	BUG_ON(NInoMstProtected(ni));
-
+	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vi->i_blkbits;
+	blocksize_bits = vol->sb->s_blocksize_bits;
-	blocksize = 1 << blocksize_bits;
-
 	if (!page_has_buffers(page)) {
 		BUG_ON(!PageUptodate(page));
 		create_empty_buffers(page, blocksize,
@@ -949,8 +947,8 @@ static int ntfs_write_mst_block(struct page *page,
 	 */
 	BUG_ON(!(is_mft || S_ISDIR(vi->i_mode) ||
 			(NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
-	bh_size_bits = vi->i_blkbits;
+	bh_size = vol->sb->s_blocksize;
-	bh_size = 1 << bh_size_bits;
+	bh_size_bits = vol->sb->s_blocksize_bits;
 	max_bhs = PAGE_CACHE_SIZE / bh_size;
 	BUG_ON(!max_bhs);
 	BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
@@ -1596,7 +1594,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 
 	BUG_ON(!PageUptodate(page));
 	end = ofs + ni->itype.index.block_size;
-	bh_size = 1 << VFS_I(ni)->i_blkbits;
+	bh_size = VFS_I(ni)->i_sb->s_blocksize;
 	spin_lock(&mapping->private_lock);
 	if (unlikely(!page_has_buffers(page))) {
 		spin_unlock(&mapping->private_lock);

fs/ntfs/file.c

@@ -1,7 +1,7 @@
 /*
  * file.c - NTFS kernel file operations.  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
@@ -248,7 +248,7 @@ do_non_resident_extend:
 		 * enough to make ntfs_writepage() work.
 		 */
 		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = (index + 1) << PAGE_CACHE_SHIFT;
+		ni->initialized_size = (s64)(index + 1) << PAGE_CACHE_SHIFT;
 		if (ni->initialized_size > new_init_size)
 			ni->initialized_size = new_init_size;
 		write_unlock_irqrestore(&ni->size_lock, flags);
@@ -529,8 +529,8 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
 			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
 			vi->i_ino, ni->type, pages[0]->index, nr_pages,
 			(long long)pos, bytes);
-	blocksize_bits = vi->i_blkbits;
+	blocksize = vol->sb->s_blocksize;
-	blocksize = 1 << blocksize_bits;
+	blocksize_bits = vol->sb->s_blocksize_bits;
 	u = 0;
 	do {
 		struct page *page = pages[u];
@@ -1525,7 +1525,7 @@ static inline int ntfs_commit_pages_after_non_resident_write(
 
 	vi = pages[0]->mapping->host;
 	ni = NTFS_I(vi);
-	blocksize = 1 << vi->i_blkbits;
+	blocksize = vi->i_sb->s_blocksize;
 	end = pos + bytes;
 	u = 0;
 	do {

fs/ntfs/inode.c

@@ -677,13 +677,28 @@ static int ntfs_read_locked_inode(struct inode *vi)
 		ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino);
 		NInoSetAttrList(ni);
 		a = ctx->attr;
-		if (a->flags & ATTR_IS_ENCRYPTED ||
+		if (a->flags & ATTR_COMPRESSION_MASK) {
-				a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_SPARSE) {
 			ntfs_error(vi->i_sb, "Attribute list attribute is "
-					"compressed/encrypted/sparse.");
+					"compressed.");
 			goto unm_err_out;
 		}
+		if (a->flags & ATTR_IS_ENCRYPTED ||
+				a->flags & ATTR_IS_SPARSE) {
+			if (a->non_resident) {
+				ntfs_error(vi->i_sb, "Non-resident attribute "
+						"list attribute is encrypted/"
+						"sparse.");
+				goto unm_err_out;
+			}
+			ntfs_warning(vi->i_sb, "Resident attribute list "
+					"attribute in inode 0x%lx is marked "
+					"encrypted/sparse which is not true.  "
+					"However, Windows allows this and "
+					"chkdsk does not detect or correct it "
+					"so we will just ignore the invalid "
+					"flags and pretend they are not set.",
+					vi->i_ino);
+		}
 		/* Now allocate memory for the attribute list. */
 		ni->attr_list_size = (u32)ntfs_attr_size(a);
 		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
@@ -1809,19 +1824,33 @@ int ntfs_read_inode_mount(struct inode *vi)
 	} else /* if (!err) */ {
 		ATTR_LIST_ENTRY *al_entry, *next_al_entry;
 		u8 *al_end;
+		static const char *es = "  Not allowed.  $MFT is corrupt.  "
+				"You should run chkdsk.";
 
 		ntfs_debug("Attribute list attribute found in $MFT.");
 		NInoSetAttrList(ni);
 		a = ctx->attr;
-		if (a->flags & ATTR_IS_ENCRYPTED ||
+		if (a->flags & ATTR_COMPRESSION_MASK) {
-				a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_SPARSE) {
 			ntfs_error(sb, "Attribute list attribute is "
-					"compressed/encrypted/sparse. Not "
+					"compressed.%s", es);
-					"allowed. $MFT is corrupt. You should "
-					"run chkdsk.");
 			goto put_err_out;
 		}
+		if (a->flags & ATTR_IS_ENCRYPTED ||
+				a->flags & ATTR_IS_SPARSE) {
+			if (a->non_resident) {
+				ntfs_error(sb, "Non-resident attribute list "
+						"attribute is encrypted/"
+						"sparse.%s", es);
+				goto put_err_out;
+			}
+			ntfs_warning(sb, "Resident attribute list attribute "
+					"in $MFT system file is marked "
+					"encrypted/sparse which is not true.  "
+					"However, Windows allows this and "
+					"chkdsk does not detect or correct it "
+					"so we will just ignore the invalid "
+					"flags and pretend they are not set.");
+		}
 		/* Now allocate memory for the attribute list. */
 		ni->attr_list_size = (u32)ntfs_attr_size(a);
 		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);

fs/ntfs/layout.h

@@ -838,15 +838,19 @@ enum {
 	   F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
 	   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 flags are only present in the FILE_NAME attribute (in
+	 * The following flag is only present in the FILE_NAME attribute (in
 	 * the field file_attributes).
 	 */
 	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
@@ -1071,9 +1075,15 @@ typedef struct {
 					   modified. */
 /* 20*/	sle64 last_access_time;		/* Time this mft record was last
 					   accessed. */
-/* 28*/	sle64 allocated_size;		/* Byte size of allocated space for the
+/* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
-					   data attribute. NOTE: Is a multiple
+					   for the data attribute.  So for
-					   of the cluster size. */
+					   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. */
 /* 38*/	FILE_ATTR_FLAGS file_attributes;	/* Flags describing the file. */
@@ -1904,12 +1914,13 @@ enum {
 	VOLUME_DELETE_USN_UNDERWAY	= const_cpu_to_le16(0x0010),
 	VOLUME_REPAIR_OBJECT_ID		= const_cpu_to_le16(0x0020),
 
+	VOLUME_CHKDSK_UNDERWAY		= const_cpu_to_le16(0x4000),
 	VOLUME_MODIFIED_BY_CHKDSK	= const_cpu_to_le16(0x8000),
 
-	VOLUME_FLAGS_MASK		= const_cpu_to_le16(0x803f),
+	VOLUME_FLAGS_MASK		= const_cpu_to_le16(0xc03f),
 
 	/* To make our life easier when checking if we must mount read-only. */
-	VOLUME_MUST_MOUNT_RO_MASK	= const_cpu_to_le16(0x8027),
+	VOLUME_MUST_MOUNT_RO_MASK	= const_cpu_to_le16(0xc027),
 } __attribute__ ((__packed__));
 
 typedef le16 VOLUME_FLAGS;

fs/ntfs/mft.c

@@ -1,7 +1,7 @@
 /**
  * mft.c - NTFS kernel mft record 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
@@ -473,7 +473,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
 	runlist_element *rl;
 	unsigned int block_start, block_end, m_start, m_end, page_ofs;
 	int i_bhs, nr_bhs, err = 0;
-	unsigned char blocksize_bits = vol->mftmirr_ino->i_blkbits;
+	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
 
 	ntfs_debug("Entering for inode 0x%lx.", mft_no);
 	BUG_ON(!max_bhs);
@@ -672,8 +672,8 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
 {
 	ntfs_volume *vol = ni->vol;
 	struct page *page = ni->page;
-	unsigned char blocksize_bits = vol->mft_ino->i_blkbits;
+	unsigned int blocksize = vol->sb->s_blocksize;
-	unsigned int blocksize = 1 << blocksize_bits;
+	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
 	int max_bhs = vol->mft_record_size / blocksize;
 	struct buffer_head *bhs[max_bhs];
 	struct buffer_head *bh, *head;

fs/ntfs/ntfs.h

@@ -50,11 +50,11 @@ typedef enum {
 /* Global variables. */
 
 /* Slab caches (from super.c). */
-extern kmem_cache_t *ntfs_name_cache;
+extern struct kmem_cache *ntfs_name_cache;
-extern kmem_cache_t *ntfs_inode_cache;
+extern struct kmem_cache *ntfs_inode_cache;
-extern kmem_cache_t *ntfs_big_inode_cache;
+extern struct kmem_cache *ntfs_big_inode_cache;
-extern kmem_cache_t *ntfs_attr_ctx_cache;
+extern struct kmem_cache *ntfs_attr_ctx_cache;
-extern kmem_cache_t *ntfs_index_ctx_cache;
+extern struct kmem_cache *ntfs_index_ctx_cache;
 
 /* The various operations structs defined throughout the driver files. */
 extern struct address_space_operations ntfs_aops;

fs/ntfs/super.c

@@ -1,7 +1,7 @@
 /*
  * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
  * Copyright (c) 2001,2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -22,6 +22,7 @@
 
 #include <linux/stddef.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>	/* For bdev_hardsect_size(). */
@@ -471,9 +472,16 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
 			ntfs_error(sb, "Volume is dirty and read-only%s", es);
 			return -EROFS;
 		}
+		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
+			ntfs_error(sb, "Volume has been modified by chkdsk "
+					"and is read-only%s", es);
+			return -EROFS;
+		}
 		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-			ntfs_error(sb, "Volume has unsupported flags set and "
+			ntfs_error(sb, "Volume has unsupported flags set "
-					"is read-only%s", es);
+					"(0x%x) and is read-only%s",
+					(unsigned)le16_to_cpu(vol->vol_flags),
+					es);
 			return -EROFS;
 		}
 		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
@@ -641,7 +649,7 @@ static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
 {
 	const char *read_err_str = "Unable to read %s boot sector.";
 	struct buffer_head *bh_primary, *bh_backup;
-	long nr_blocks = NTFS_SB(sb)->nr_blocks;
+	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
 
 	/* Try to read primary boot sector. */
 	if ((bh_primary = sb_bread(sb, 0))) {
@@ -688,13 +696,18 @@ hotfix_primary_boot_sector:
 		/*
 		 * If we managed to read sector zero and the volume is not
 		 * read-only, copy the found, valid backup boot sector to the
-		 * primary boot sector.
+		 * primary boot sector.  Note we only copy the actual boot
+		 * sector structure, not the actual whole device sector as that
+		 * may be bigger and would potentially damage the $Boot system
+		 * file (FIXME: Would be nice to know if the backup boot sector
+		 * on a large sector device contains the whole boot loader or
+		 * just the first 512 bytes).
 		 */
 		if (!(sb->s_flags & MS_RDONLY)) {
 			ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
 					"boot sector from backup copy.");
 			memcpy(bh_primary->b_data, bh_backup->b_data,
-					sb->s_blocksize);
+					NTFS_BLOCK_SIZE);
 			mark_buffer_dirty(bh_primary);
 			sync_dirty_buffer(bh_primary);
 			if (buffer_uptodate(bh_primary)) {
@@ -733,9 +746,13 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 			vol->sector_size);
 	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
 			vol->sector_size_bits);
-	if (vol->sector_size != vol->sb->s_blocksize)
+	if (vol->sector_size < vol->sb->s_blocksize) {
-		ntfs_warning(vol->sb, "The boot sector indicates a sector size "
+		ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
-				"different from the device sector size.");
+				"device block size (%lu).  This is not "
+				"supported.  Sorry.", vol->sector_size,
+				vol->sb->s_blocksize);
+		return FALSE;
+	}
 	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
 	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
 	ntfs_debug("sectors_per_cluster_bits = 0x%x",
@@ -748,16 +765,11 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
 			vol->cluster_size);
 	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
-	ntfs_debug("vol->cluster_size_bits = %i (0x%x)",
+	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
-			vol->cluster_size_bits, vol->cluster_size_bits);
+	if (vol->cluster_size < vol->sector_size) {
-	if (vol->sector_size > vol->cluster_size) {
+		ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
-		ntfs_error(vol->sb, "Sector sizes above the cluster size are "
+				"sector size (%i).  This is not supported.  "
-				"not supported.  Sorry.");
+				"Sorry.", vol->cluster_size, vol->sector_size);
-		return FALSE;
-	}
-	if (vol->sb->s_blocksize > vol->cluster_size) {
-		ntfs_error(vol->sb, "Cluster sizes smaller than the device "
-				"sector size are not supported.  Sorry.");
 		return FALSE;
 	}
 	clusters_per_mft_record = b->clusters_per_mft_record;
@@ -786,11 +798,18 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	 * we store $MFT/$DATA, the table of mft records in the page cache.
 	 */
 	if (vol->mft_record_size > PAGE_CACHE_SIZE) {
-		ntfs_error(vol->sb, "Mft record size %i (0x%x) exceeds the "
+		ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
-				"page cache size on your system %lu (0x%lx).  "
+				"PAGE_CACHE_SIZE on your system (%lu).  "
 				"This is not supported.  Sorry.",
-				vol->mft_record_size, vol->mft_record_size,
+				vol->mft_record_size, PAGE_CACHE_SIZE);
-				PAGE_CACHE_SIZE, PAGE_CACHE_SIZE);
+		return FALSE;
+	}
+	/* We cannot support mft record sizes below the sector size. */
+	if (vol->mft_record_size < vol->sector_size) {
+		ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
+				"sector size (%i).  This is not supported.  "
+				"Sorry.", vol->mft_record_size,
+				vol->sector_size);
 		return FALSE;
 	}
 	clusters_per_index_record = b->clusters_per_index_record;
@@ -816,6 +835,14 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
 			vol->index_record_size_bits,
 			vol->index_record_size_bits);
+	/* We cannot support index record sizes below the sector size. */
+	if (vol->index_record_size < vol->sector_size) {
+		ntfs_error(vol->sb, "Index record size (%i) is smaller than "
+				"the sector size (%i).  This is not "
+				"supported.  Sorry.", vol->index_record_size,
+				vol->sector_size);
+		return FALSE;
+	}
 	/*
 	 * Get the size of the volume in clusters and check for 64-bit-ness.
 	 * Windows currently only uses 32 bits to save the clusters so we do
@@ -845,15 +872,18 @@ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
 	}
 	ll = sle64_to_cpu(b->mft_lcn);
 	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFT LCN is beyond end of volume.  Weird.");
+		ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
+				"volume.  Weird.", (unsigned long long)ll,
+				(unsigned long long)ll);
 		return FALSE;
 	}
 	vol->mft_lcn = ll;
 	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
 	ll = sle64_to_cpu(b->mftmirr_lcn);
 	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFTMirr LCN is beyond end of volume.  "
+		ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
-				"Weird.");
+				"of volume.  Weird.", (unsigned long long)ll,
+				(unsigned long long)ll);
 		return FALSE;
 	}
 	vol->mftmirr_lcn = ll;
@@ -1822,11 +1852,24 @@ get_ctx_vol_failed:
 	/* Make sure that no unsupported volume flags are set. */
 	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
 		static const char *es1a = "Volume is dirty";
-		static const char *es1b = "Volume has unsupported flags set";
+		static const char *es1b = "Volume has been modified by chkdsk";
-		static const char *es2 = ".  Run chkdsk and mount in Windows.";
+		static const char *es1c = "Volume has unsupported flags set";
-		const char *es1;
+		static const char *es2a = ".  Run chkdsk and mount in Windows.";
-		
+		static const char *es2b = ".  Mount in Windows.";
-		es1 = vol->vol_flags & VOLUME_IS_DIRTY ? es1a : es1b;
+		const char *es1, *es2;
+
+		es2 = es2a;
+		if (vol->vol_flags & VOLUME_IS_DIRTY)
+			es1 = es1a;
+		else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
+			es1 = es1b;
+			es2 = es2b;
+		} else {
+			es1 = es1c;
+			ntfs_warning(sb, "Unsupported volume flags 0x%x "
+					"encountered.",
+					(unsigned)le16_to_cpu(vol->vol_flags));
+		}
 		/* If a read-write mount, convert it to a read-only mount. */
 		if (!(sb->s_flags & MS_RDONLY)) {
 			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
@@ -2685,7 +2728,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	ntfs_volume *vol;
 	struct buffer_head *bh;
 	struct inode *tmp_ino;
-	int result;
+	int blocksize, result;
 
 	ntfs_debug("Entering.");
 #ifndef NTFS_RW
@@ -2724,60 +2767,85 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	if (!parse_options(vol, (char*)opt))
 		goto err_out_now;
 
+	/* We support sector sizes up to the PAGE_CACHE_SIZE. */
+	if (bdev_hardsect_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
+		if (!silent)
+			ntfs_error(sb, "Device has unsupported sector size "
+					"(%i).  The maximum supported sector "
+					"size on this architecture is %lu "
+					"bytes.",
+					bdev_hardsect_size(sb->s_bdev),
+					PAGE_CACHE_SIZE);
+		goto err_out_now;
+	}
 	/*
-	 * TODO: Fail safety check. In the future we should really be able to
+	 * Setup the device access block size to NTFS_BLOCK_SIZE or the hard
-	 * cope with this being the case, but for now just bail out.
+	 * sector size, whichever is bigger.
 	 */
-	if (bdev_hardsect_size(sb->s_bdev) > NTFS_BLOCK_SIZE) {
+	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
+	if (blocksize < NTFS_BLOCK_SIZE) {
 		if (!silent)
-			ntfs_error(sb, "Device has unsupported hardsect_size.");
+			ntfs_error(sb, "Unable to set device block size.");
 		goto err_out_now;
 	}
-
+	BUG_ON(blocksize != sb->s_blocksize);
-	/* Setup the device access block size to NTFS_BLOCK_SIZE. */
+	ntfs_debug("Set device block size to %i bytes (block size bits %i).",
-	if (sb_set_blocksize(sb, NTFS_BLOCK_SIZE) != NTFS_BLOCK_SIZE) {
+			blocksize, sb->s_blocksize_bits);
+	/* Determine the size of the device in units of block_size bytes. */
+	if (!i_size_read(sb->s_bdev->bd_inode)) {
 		if (!silent)
-			ntfs_error(sb, "Unable to set block size.");
+			ntfs_error(sb, "Unable to determine device size.");
 		goto err_out_now;
 	}
-
-	/* Get the size of the device in units of NTFS_BLOCK_SIZE bytes. */
 	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
-			NTFS_BLOCK_SIZE_BITS;
+			sb->s_blocksize_bits;
-
 	/* Read the boot sector and return unlocked buffer head to it. */
 	if (!(bh = read_ntfs_boot_sector(sb, silent))) {
 		if (!silent)
 			ntfs_error(sb, "Not an NTFS volume.");
 		goto err_out_now;
 	}
-
 	/*
-	 * Extract the data from the boot sector and setup the ntfs super block
+	 * Extract the data from the boot sector and setup the ntfs volume
 	 * using it.
 	 */
 	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
-
-	/* Initialize the cluster and mft allocators. */
-	ntfs_setup_allocators(vol);
-
 	brelse(bh);
-
 	if (!result) {
 		if (!silent)
 			ntfs_error(sb, "Unsupported NTFS filesystem.");
 		goto err_out_now;
 	}
-
 	/*
-	 * TODO: When we start coping with sector sizes different from
+	 * If the boot sector indicates a sector size bigger than the current
-	 * NTFS_BLOCK_SIZE, we now probably need to set the blocksize of the
+	 * device block size, switch the device block size to the sector size.
-	 * device (probably to NTFS_BLOCK_SIZE).
+	 * TODO: It may be possible to support this case even when the set
+	 * below fails, we would just be breaking up the i/o for each sector
+	 * into multiple blocks for i/o purposes but otherwise it should just
+	 * work.  However it is safer to leave disabled until someone hits this
+	 * error message and then we can get them to try it without the setting
+	 * so we know for sure that it works.
 	 */
-
+	if (vol->sector_size > blocksize) {
+		blocksize = sb_set_blocksize(sb, vol->sector_size);
+		if (blocksize != vol->sector_size) {
+			if (!silent)
+				ntfs_error(sb, "Unable to set device block "
+						"size to sector size (%i).",
+						vol->sector_size);
+			goto err_out_now;
+		}
+		BUG_ON(blocksize != sb->s_blocksize);
+		vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
+				sb->s_blocksize_bits;
+		ntfs_debug("Changed device block size to %i bytes (block size "
+				"bits %i) to match volume sector size.",
+				blocksize, sb->s_blocksize_bits);
+	}
+	/* Initialize the cluster and mft allocators. */
+	ntfs_setup_allocators(vol);
 	/* Setup remaining fields in the super block. */
 	sb->s_magic = NTFS_SB_MAGIC;
-
 	/*
 	 * Ntfs allows 63 bits for the file size, i.e. correct would be:
 	 *	sb->s_maxbytes = ~0ULL >> 1;
@@ -2787,9 +2855,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 	 * without overflowing the index or to 2^63 - 1, whichever is smaller.
 	 */
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
-
+	/* Ntfs measures time in 100ns intervals. */
 	sb->s_time_gran = 100;
-
 	/*
 	 * Now load the metadata required for the page cache and our address
 	 * space operations to function. We do this by setting up a specialised
@@ -2987,14 +3054,14 @@ err_out_now:
  * strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
  * (255) Unicode characters + a terminating NULL Unicode character.
  */
-kmem_cache_t *ntfs_name_cache;
+struct kmem_cache *ntfs_name_cache;
 
 /* Slab caches for efficient allocation/deallocation of inodes. */
-kmem_cache_t *ntfs_inode_cache;
+struct kmem_cache *ntfs_inode_cache;
-kmem_cache_t *ntfs_big_inode_cache;
+struct kmem_cache *ntfs_big_inode_cache;
 
 /* Init once constructor for the inode slab cache. */
-static void ntfs_big_inode_init_once(void *foo, kmem_cache_t *cachep,
+static void ntfs_big_inode_init_once(void *foo, struct kmem_cache *cachep,
 		unsigned long flags)
 {
 	ntfs_inode *ni = (ntfs_inode *)foo;
@@ -3008,8 +3075,8 @@ static void ntfs_big_inode_init_once(void *foo, kmem_cache_t *cachep,
  * Slab caches to optimize allocations and deallocations of attribute search
  * contexts and index contexts, respectively.
  */
-kmem_cache_t *ntfs_attr_ctx_cache;
+struct kmem_cache *ntfs_attr_ctx_cache;
-kmem_cache_t *ntfs_index_ctx_cache;
+struct kmem_cache *ntfs_index_ctx_cache;
 
 /* Driver wide semaphore. */
 DECLARE_MUTEX(ntfs_lock);

fs/ntfs/upcase.c

@@ -3,10 +3,7 @@
  *	      Part of the Linux-NTFS project.
  *
  * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
- * Copyright (c) 2001-2004 Anton Altaparmakov
+ * Copyright (c) 2001-2006 Anton Altaparmakov
- *
- * Modified for mkntfs inclusion 9 June 2001 by Anton Altaparmakov.
- * Modified for kernel inclusion 10 September 2001 by Anton Altparmakov.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -75,12 +72,13 @@ ntfschar *generate_default_upcase(void)
 	if (!uc)
 		return uc;
 	memset(uc, 0, default_upcase_len * sizeof(ntfschar));
+	/* Generate the little endian Unicode upcase table used by ntfs. */
 	for (i = 0; i < default_upcase_len; i++)
 		uc[i] = cpu_to_le16(i);
 	for (r = 0; uc_run_table[r][0]; r++)
 		for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
-			uc[i] = cpu_to_le16((le16_to_cpu(uc[i]) +
+			uc[i] = cpu_to_le16(le16_to_cpu(uc[i]) +
-					uc_run_table[r][2]));
+					uc_run_table[r][2]);
 	for (r = 0; uc_dup_table[r][0]; r++)
 		for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
 			uc[i + 1] = cpu_to_le16(le16_to_cpu(uc[i + 1]) - 1);

fs/ntfs/volume.h

@@ -2,7 +2,7 @@
  * volume.h - Defines for volume structures in NTFS Linux kernel driver. 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
@@ -41,10 +41,8 @@ typedef struct {
 	 * structure has stabilized... (AIA)
 	 */
 	/* Device specifics. */
-	struct super_block *sb;		/* Pointer back to the super_block,
+	struct super_block *sb;		/* Pointer back to the super_block. */
-					   so we don't have to get the offset
+	LCN nr_blocks;			/* Number of sb->s_blocksize bytes
-					   every time. */
-	LCN nr_blocks;			/* Number of NTFS_BLOCK_SIZE bytes
 					   sized blocks on the device. */
 	/* Configuration provided by user at mount time. */
 	unsigned long flags;		/* Miscellaneous flags, see below. */
@@ -141,8 +139,8 @@ typedef enum {
 	NV_ShowSystemFiles,	/* 1: Return system files in ntfs_readdir(). */
 	NV_CaseSensitive,	/* 1: Treat file names as case sensitive and
 				      create filenames in the POSIX namespace.
-				      Otherwise be case insensitive and create
+				      Otherwise be case insensitive but still
-				      file names in WIN32 namespace. */
+				      create file names in POSIX namespace. */
 	NV_LogFileEmpty,	/* 1: $LogFile journal is empty. */
 	NV_QuotaOutOfDate,	/* 1: $Quota is out of date. */
 	NV_UsnJrnlStamped,	/* 1: $UsnJrnl has been stamped. */
@@ -153,7 +151,7 @@ typedef enum {
  * Macro tricks to expand the NVolFoo(), NVolSetFoo(), and NVolClearFoo()
  * functions.
  */
-#define NVOL_FNS(flag)					\
+#define DEFINE_NVOL_BIT_OPS(flag)					\
 static inline int NVol##flag(ntfs_volume *vol)		\
 {							\
 	return test_bit(NV_##flag, &(vol)->flags);	\
@@ -168,12 +166,12 @@ static inline void NVolClear##flag(ntfs_volume *vol)	\
 }
 
 /* Emit the ntfs volume bitops functions. */
-NVOL_FNS(Errors)
+DEFINE_NVOL_BIT_OPS(Errors)
-NVOL_FNS(ShowSystemFiles)
+DEFINE_NVOL_BIT_OPS(ShowSystemFiles)
-NVOL_FNS(CaseSensitive)
+DEFINE_NVOL_BIT_OPS(CaseSensitive)
-NVOL_FNS(LogFileEmpty)
+DEFINE_NVOL_BIT_OPS(LogFileEmpty)
-NVOL_FNS(QuotaOutOfDate)
+DEFINE_NVOL_BIT_OPS(QuotaOutOfDate)
-NVOL_FNS(UsnJrnlStamped)
+DEFINE_NVOL_BIT_OPS(UsnJrnlStamped)
-NVOL_FNS(SparseEnabled)
+DEFINE_NVOL_BIT_OPS(SparseEnabled)
 
 #endif /* _LINUX_NTFS_VOLUME_H */