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
-	  the call, and i_sem is sufficient protection against changes in the
-	  directory inode (including ->i_size).
+	  only caller of ->readdir() is vfs_readdir() which holds i_mutex
+	  during the call, and i_mutex is sufficient protection against changes
+	  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 = 1 << blocksize_bits;
+	blocksize = vol->sb->s_blocksize;
+	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_bits = vi->i_blkbits;
-	blocksize = 1 << blocksize_bits;
-
+	blocksize = vol->sb->s_blocksize;
+	blocksize_bits = vol->sb->s_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 = 1 << bh_size_bits;
+	bh_size = vol->sb->s_blocksize;
+	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 @@ static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size,
 		 * 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 = 1 << blocksize_bits;
+	blocksize = vol->sb->s_blocksize;
+	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 ||
-				a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_SPARSE) {
+		if (a->flags & ATTR_COMPRESSION_MASK) {
 			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 ||
-				a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_SPARSE) {
+		if (a->flags & ATTR_COMPRESSION_MASK) {
 			ntfs_error(sb, "Attribute list attribute is "
-					"compressed/encrypted/sparse. Not "
-					"allowed. $MFT is corrupt. You should "
-					"run chkdsk.");
+					"compressed.%s", es);
 			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
-					   data attribute. NOTE: Is a multiple
-					   of the cluster size. */
+/* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
+					   for the 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. */
 /* 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 = 1 << blocksize_bits;
+	unsigned int blocksize = vol->sb->s_blocksize;
+	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 kmem_cache_t *ntfs_inode_cache;
-extern kmem_cache_t *ntfs_big_inode_cache;
-extern kmem_cache_t *ntfs_attr_ctx_cache;
-extern kmem_cache_t *ntfs_index_ctx_cache;
+extern struct kmem_cache *ntfs_name_cache;
+extern struct kmem_cache *ntfs_inode_cache;
+extern struct kmem_cache *ntfs_big_inode_cache;
+extern struct kmem_cache *ntfs_attr_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;