Fixed MTP to work with TWRP

fs/ntfs/Kconfig

@@ -0,0 +1,78 @@
+config NTFS_FS
+	tristate "NTFS file system support"
+	select NLS
+	help
+	  NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003.
+
+	  Saying Y or M here enables read support.  There is partial, but
+	  safe, write support available.  For write support you must also
+	  say Y to "NTFS write support" below.
+
+	  There are also a number of user-space tools available, called
+	  ntfsprogs.  These include ntfsundelete and ntfsresize, that work
+	  without NTFS support enabled in the kernel.
+
+	  This is a rewrite from scratch of Linux NTFS support and replaced
+	  the old NTFS code starting with Linux 2.5.11.  A backport to
+	  the Linux 2.4 kernel series is separately available as a patch
+	  from the project web site.
+
+	  For more information see <file:Documentation/filesystems/ntfs.txt>
+	  and <http://www.linux-ntfs.org/>.
+
+	  To compile this file system support as a module, choose M here: the
+	  module will be called ntfs.
+
+	  If you are not using Windows NT, 2000, XP or 2003 in addition to
+	  Linux on your computer it is safe to say N.
+
+config NTFS_DEBUG
+	bool "NTFS debugging support"
+	depends on NTFS_FS
+	help
+	  If you are experiencing any problems with the NTFS file system, say
+	  Y here.  This will result in additional consistency checks to be
+	  performed by the driver as well as additional debugging messages to
+	  be written to the system log.  Note that debugging messages are
+	  disabled by default.  To enable them, supply the option debug_msgs=1
+	  at the kernel command line when booting the kernel or as an option
+	  to insmod when loading the ntfs module.  Once the driver is active,
+	  you can enable debugging messages by doing (as root):
+	  echo 1 > /proc/sys/fs/ntfs-debug
+	  Replacing the "1" with "0" would disable debug messages.
+
+	  If you leave debugging messages disabled, this results in little
+	  overhead, but enabling debug messages results in very significant
+	  slowdown of the system.
+
+	  When reporting bugs, please try to have available a full dump of
+	  debugging messages while the misbehaviour was occurring.
+
+config NTFS_RW
+	bool "NTFS write support"
+	depends on NTFS_FS
+	help
+	  This enables the partial, but safe, write support in the NTFS driver.
+
+	  The only supported operation is overwriting existing files, without
+	  changing the file length.  No file or directory creation, deletion or
+	  renaming is possible.  Note only non-resident files can be written to
+	  so you may find that some very small files (<500 bytes or so) cannot
+	  be written to.
+
+	  While we cannot guarantee that it will not damage any data, we have
+	  so far not received a single report where the driver would have
+	  damaged someones data so we assume it is perfectly safe to use.
+
+	  Note:  While write support is safe in this version (a rewrite from
+	  scratch of the NTFS support), it should be noted that the old NTFS
+	  write support, included in Linux 2.5.10 and before (since 1997),
+	  is not safe.
+
+	  This is currently useful with TopologiLinux.  TopologiLinux is run
+	  on top of any DOS/Microsoft Windows system without partitioning your
+	  hard disk.  Unlike other Linux distributions TopologiLinux does not
+	  need its own partition.  For more information see
+	  <http://topologi-linux.sourceforge.net/>
+
+	  It is perfectly safe to say N here.

fs/ntfs/Makefile

@@ -0,0 +1,14 @@
+# Rules for making the NTFS driver.
+
+obj-$(CONFIG_NTFS_FS) += ntfs.o
+
+ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
+	  index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
+	  unistr.o upcase.o
+
+ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
+
+ccflags-y := -DNTFS_VERSION=\"2.1.31\"
+ccflags-$(CONFIG_NTFS_DEBUG)	+= -DDEBUG
+ccflags-$(CONFIG_NTFS_RW)	+= -DNTFS_RW
+

fs/ntfs/aops.h

@@ -0,0 +1,107 @@
+/**
+ * aops.h - Defines for NTFS kernel address space operations and page cache
+ *	    handling.  Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 Anton Altaparmakov
+ * Copyright (c) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_AOPS_H
+#define _LINUX_NTFS_AOPS_H
+
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/fs.h>
+
+#include "inode.h"
+
+/**
+ * ntfs_unmap_page - release a page that was mapped using ntfs_map_page()
+ * @page:	the page to release
+ *
+ * Unpin, unmap and release a page that was obtained from ntfs_map_page().
+ */
+static inline void ntfs_unmap_page(struct page *page)
+{
+	kunmap(page);
+	page_cache_release(page);
+}
+
+/**
+ * ntfs_map_page - map a page into accessible memory, reading it if necessary
+ * @mapping:	address space for which to obtain the page
+ * @index:	index into the page cache for @mapping of the page to map
+ *
+ * Read a page from the page cache of the address space @mapping at position
+ * @index, where @index is in units of PAGE_CACHE_SIZE, and not in bytes.
+ *
+ * If the page is not in memory it is loaded from disk first using the readpage
+ * method defined in the address space operations of @mapping and the page is
+ * added to the page cache of @mapping in the process.
+ *
+ * If the page belongs to an mst protected attribute and it is marked as such
+ * in its ntfs inode (NInoMstProtected()) the mst fixups are applied but no
+ * error checking is performed.  This means the caller has to verify whether
+ * the ntfs record(s) contained in the page are valid or not using one of the
+ * ntfs_is_XXXX_record{,p}() macros, where XXXX is the record type you are
+ * expecting to see.  (For details of the macros, see fs/ntfs/layout.h.)
+ *
+ * If the page is in high memory it is mapped into memory directly addressible
+ * by the kernel.
+ *
+ * Finally the page count is incremented, thus pinning the page into place.
+ *
+ * The above means that page_address(page) can be used on all pages obtained
+ * with ntfs_map_page() to get the kernel virtual address of the page.
+ *
+ * When finished with the page, the caller has to call ntfs_unmap_page() to
+ * unpin, unmap and release the page.
+ *
+ * Note this does not grant exclusive access. If such is desired, the caller
+ * must provide it independently of the ntfs_{un}map_page() calls by using
+ * a {rw_}semaphore or other means of serialization. A spin lock cannot be
+ * used as ntfs_map_page() can block.
+ *
+ * The unlocked and uptodate page is returned on success or an encoded error
+ * on failure. Caller has to test for error using the IS_ERR() macro on the
+ * return value. If that evaluates to 'true', the negative error code can be
+ * obtained using PTR_ERR() on the return value of ntfs_map_page().
+ */
+static inline struct page *ntfs_map_page(struct address_space *mapping,
+		unsigned long index)
+{
+	struct page *page = read_mapping_page(mapping, index, NULL);
+
+	if (!IS_ERR(page)) {
+		kmap(page);
+		if (!PageError(page))
+			return page;
+		ntfs_unmap_page(page);
+		return ERR_PTR(-EIO);
+	}
+	return page;
+}
+
+#ifdef NTFS_RW
+
+extern void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs);
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_AOPS_H */

fs/ntfs/attrib.h

@@ -0,0 +1,116 @@
+/*
+ * attrib.h - Defines for attribute handling in NTFS Linux kernel driver.
+ *	      Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_ATTRIB_H
+#define _LINUX_NTFS_ATTRIB_H
+
+#include "endian.h"
+#include "types.h"
+#include "layout.h"
+#include "inode.h"
+#include "runlist.h"
+#include "volume.h"
+
+/**
+ * ntfs_attr_search_ctx - used in attribute search functions
+ * @mrec:	buffer containing mft record to search
+ * @attr:	attribute record in @mrec where to begin/continue search
+ * @is_first:	if true ntfs_attr_lookup() begins search with @attr, else after
+ *
+ * Structure must be initialized to zero before the first call to one of the
+ * attribute search functions. Initialize @mrec to point to the mft record to
+ * search, and @attr to point to the first attribute within @mrec (not necessary
+ * if calling the _first() functions), and set @is_first to 'true' (not necessary
+ * if calling the _first() functions).
+ *
+ * If @is_first is 'true', the search begins with @attr. If @is_first is 'false',
+ * the search begins after @attr. This is so that, after the first call to one
+ * of the search attribute functions, we can call the function again, without
+ * any modification of the search context, to automagically get the next
+ * matching attribute.
+ */
+typedef struct {
+	MFT_RECORD *mrec;
+	ATTR_RECORD *attr;
+	bool is_first;
+	ntfs_inode *ntfs_ino;
+	ATTR_LIST_ENTRY *al_entry;
+	ntfs_inode *base_ntfs_ino;
+	MFT_RECORD *base_mrec;
+	ATTR_RECORD *base_attr;
+} ntfs_attr_search_ctx;
+
+extern int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn,
+		ntfs_attr_search_ctx *ctx);
+extern int ntfs_map_runlist(ntfs_inode *ni, VCN vcn);
+
+extern LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
+		const bool write_locked);
+
+extern runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni,
+		const VCN vcn, ntfs_attr_search_ctx *ctx);
+
+int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
+		const u32 name_len, const IGNORE_CASE_BOOL ic,
+		const VCN lowest_vcn, const u8 *val, const u32 val_len,
+		ntfs_attr_search_ctx *ctx);
+
+extern int load_attribute_list(ntfs_volume *vol, runlist *rl, u8 *al_start,
+		const s64 size, const s64 initialized_size);
+
+static inline s64 ntfs_attr_size(const ATTR_RECORD *a)
+{
+	if (!a->non_resident)
+		return (s64)le32_to_cpu(a->data.resident.value_length);
+	return sle64_to_cpu(a->data.non_resident.data_size);
+}
+
+extern void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx);
+extern ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni,
+		MFT_RECORD *mrec);
+extern void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx);
+
+#ifdef NTFS_RW
+
+extern int ntfs_attr_size_bounds_check(const ntfs_volume *vol,
+		const ATTR_TYPE type, const s64 size);
+extern int ntfs_attr_can_be_non_resident(const ntfs_volume *vol,
+		const ATTR_TYPE type);
+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, const u32 data_size);
+
+extern s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
+		const s64 new_data_size, const s64 data_start);
+
+extern int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt,
+		const u8 val);
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_ATTRIB_H */

fs/ntfs/bitmap.c

@@ -0,0 +1,193 @@
+/*
+ * bitmap.c - NTFS kernel bitmap handling.  Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2004-2005 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifdef NTFS_RW
+
+#include <linux/pagemap.h>
+
+#include "bitmap.h"
+#include "debug.h"
+#include "aops.h"
+#include "ntfs.h"
+
+/**
+ * __ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value
+ * @vi:			vfs inode describing the bitmap
+ * @start_bit:		first bit to set
+ * @count:		number of bits to set
+ * @value:		value to set the bits to (i.e. 0 or 1)
+ * @is_rollback:	if 'true' this is a rollback operation
+ *
+ * Set @count bits starting at bit @start_bit in the bitmap described by the
+ * vfs inode @vi to @value, where @value is either 0 or 1.
+ *
+ * @is_rollback should always be 'false', it is for internal use to rollback
+ * errors.  You probably want to use ntfs_bitmap_set_bits_in_run() instead.
+ *
+ * Return 0 on success and -errno on error.
+ */
+int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
+		const s64 count, const u8 value, const bool is_rollback)
+{
+	s64 cnt = count;
+	pgoff_t index, end_index;
+	struct address_space *mapping;
+	struct page *page;
+	u8 *kaddr;
+	int pos, len;
+	u8 bit;
+
+	BUG_ON(!vi);
+	ntfs_debug("Entering for i_ino 0x%lx, start_bit 0x%llx, count 0x%llx, "
+			"value %u.%s", vi->i_ino, (unsigned long long)start_bit,
+			(unsigned long long)cnt, (unsigned int)value,
+			is_rollback ? " (rollback)" : "");
+	BUG_ON(start_bit < 0);
+	BUG_ON(cnt < 0);
+	BUG_ON(value > 1);
+	/*
+	 * Calculate the indices for the pages containing the first and last
+	 * bits, i.e. @start_bit and @start_bit + @cnt - 1, respectively.
+	 */
+	index = start_bit >> (3 + PAGE_CACHE_SHIFT);
+	end_index = (start_bit + cnt - 1) >> (3 + PAGE_CACHE_SHIFT);
+
+	/* Get the page containing the first bit (@start_bit). */
+	mapping = vi->i_mapping;
+	page = ntfs_map_page(mapping, index);
+	if (IS_ERR(page)) {
+		if (!is_rollback)
+			ntfs_error(vi->i_sb, "Failed to map first page (error "
+					"%li), aborting.", PTR_ERR(page));
+		return PTR_ERR(page);
+	}
+	kaddr = page_address(page);
+
+	/* Set @pos to the position of the byte containing @start_bit. */
+	pos = (start_bit >> 3) & ~PAGE_CACHE_MASK;
+
+	/* Calculate the position of @start_bit in the first byte. */
+	bit = start_bit & 7;
+
+	/* If the first byte is partial, modify the appropriate bits in it. */
+	if (bit) {
+		u8 *byte = kaddr + pos;
+		while ((bit & 7) && cnt) {
+			cnt--;
+			if (value)
+				*byte |= 1 << bit++;
+			else
+				*byte &= ~(1 << bit++);
+		}
+		/* If we are done, unmap the page and return success. */
+		if (!cnt)
+			goto done;
+
+		/* Update @pos to the new position. */
+		pos++;
+	}
+	/*
+	 * Depending on @value, modify all remaining whole bytes in the page up
+	 * to @cnt.
+	 */
+	len = min_t(s64, cnt >> 3, PAGE_CACHE_SIZE - pos);
+	memset(kaddr + pos, value ? 0xff : 0, len);
+	cnt -= len << 3;
+
+	/* Update @len to point to the first not-done byte in the page. */
+	if (cnt < 8)
+		len += pos;
+
+	/* If we are not in the last page, deal with all subsequent pages. */
+	while (index < end_index) {
+		BUG_ON(cnt <= 0);
+
+		/* Update @index and get the next page. */
+		flush_dcache_page(page);
+		set_page_dirty(page);
+		ntfs_unmap_page(page);
+		page = ntfs_map_page(mapping, ++index);
+		if (IS_ERR(page))
+			goto rollback;
+		kaddr = page_address(page);
+		/*
+		 * Depending on @value, modify all remaining whole bytes in the
+		 * page up to @cnt.
+		 */
+		len = min_t(s64, cnt >> 3, PAGE_CACHE_SIZE);
+		memset(kaddr, value ? 0xff : 0, len);
+		cnt -= len << 3;
+	}
+	/*
+	 * The currently mapped page is the last one.  If the last byte is
+	 * partial, modify the appropriate bits in it.  Note, @len is the
+	 * position of the last byte inside the page.
+	 */
+	if (cnt) {
+		u8 *byte;
+
+		BUG_ON(cnt > 7);
+
+		bit = cnt;
+		byte = kaddr + len;
+		while (bit--) {
+			if (value)
+				*byte |= 1 << bit;
+			else
+				*byte &= ~(1 << bit);
+		}
+	}
+done:
+	/* We are done.  Unmap the page and return success. */
+	flush_dcache_page(page);
+	set_page_dirty(page);
+	ntfs_unmap_page(page);
+	ntfs_debug("Done.");
+	return 0;
+rollback:
+	/*
+	 * Current state:
+	 *	- no pages are mapped
+	 *	- @count - @cnt is the number of bits that have been modified
+	 */
+	if (is_rollback)
+		return PTR_ERR(page);
+	if (count != cnt)
+		pos = __ntfs_bitmap_set_bits_in_run(vi, start_bit, count - cnt,
+				value ? 0 : 1, true);
+	else
+		pos = 0;
+	if (!pos) {
+		/* Rollback was successful. */
+		ntfs_error(vi->i_sb, "Failed to map subsequent page (error "
+				"%li), aborting.", PTR_ERR(page));
+	} else {
+		/* Rollback failed. */
+		ntfs_error(vi->i_sb, "Failed to map subsequent page (error "
+				"%li) and rollback failed (error %i).  "
+				"Aborting and leaving inconsistent metadata.  "
+				"Unmount and run chkdsk.", PTR_ERR(page), pos);
+		NVolSetErrors(NTFS_SB(vi->i_sb));
+	}
+	return PTR_ERR(page);
+}
+
+#endif /* NTFS_RW */

fs/ntfs/bitmap.h

@@ -0,0 +1,118 @@
+/*
+ * bitmap.h - Defines for NTFS kernel bitmap handling.  Part of the Linux-NTFS
+ *	      project.
+ *
+ * Copyright (c) 2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_BITMAP_H
+#define _LINUX_NTFS_BITMAP_H
+
+#ifdef NTFS_RW
+
+#include <linux/fs.h>
+
+#include "types.h"
+
+extern int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
+		const s64 count, const u8 value, const bool is_rollback);
+
+/**
+ * ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value
+ * @vi:			vfs inode describing the bitmap
+ * @start_bit:		first bit to set
+ * @count:		number of bits to set
+ * @value:		value to set the bits to (i.e. 0 or 1)
+ *
+ * Set @count bits starting at bit @start_bit in the bitmap described by the
+ * vfs inode @vi to @value, where @value is either 0 or 1.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_bitmap_set_bits_in_run(struct inode *vi,
+		const s64 start_bit, const s64 count, const u8 value)
+{
+	return __ntfs_bitmap_set_bits_in_run(vi, start_bit, count, value,
+			false);
+}
+
+/**
+ * ntfs_bitmap_set_run - set a run of bits in a bitmap
+ * @vi:		vfs inode describing the bitmap
+ * @start_bit:	first bit to set
+ * @count:	number of bits to set
+ *
+ * Set @count bits starting at bit @start_bit in the bitmap described by the
+ * vfs inode @vi.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_bitmap_set_run(struct inode *vi, const s64 start_bit,
+		const s64 count)
+{
+	return ntfs_bitmap_set_bits_in_run(vi, start_bit, count, 1);
+}
+
+/**
+ * ntfs_bitmap_clear_run - clear a run of bits in a bitmap
+ * @vi:		vfs inode describing the bitmap
+ * @start_bit:	first bit to clear
+ * @count:	number of bits to clear
+ *
+ * Clear @count bits starting at bit @start_bit in the bitmap described by the
+ * vfs inode @vi.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_bitmap_clear_run(struct inode *vi, const s64 start_bit,
+		const s64 count)
+{
+	return ntfs_bitmap_set_bits_in_run(vi, start_bit, count, 0);
+}
+
+/**
+ * ntfs_bitmap_set_bit - set a bit in a bitmap
+ * @vi:		vfs inode describing the bitmap
+ * @bit:	bit to set
+ *
+ * Set bit @bit in the bitmap described by the vfs inode @vi.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_bitmap_set_bit(struct inode *vi, const s64 bit)
+{
+	return ntfs_bitmap_set_run(vi, bit, 1);
+}
+
+/**
+ * ntfs_bitmap_clear_bit - clear a bit in a bitmap
+ * @vi:		vfs inode describing the bitmap
+ * @bit:	bit to clear
+ *
+ * Clear bit @bit in the bitmap described by the vfs inode @vi.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_bitmap_clear_bit(struct inode *vi, const s64 bit)
+{
+	return ntfs_bitmap_clear_run(vi, bit, 1);
+}
+
+#endif /* NTFS_RW */
+
+#endif /* defined _LINUX_NTFS_BITMAP_H */

fs/ntfs/collate.c

@@ -0,0 +1,124 @@
+/*
+ * collate.c - NTFS kernel collation handling.  Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include "collate.h"
+#include "debug.h"
+#include "ntfs.h"
+
+static int ntfs_collate_binary(ntfs_volume *vol,
+		const void *data1, const int data1_len,
+		const void *data2, const int data2_len)
+{
+	int rc;
+
+	ntfs_debug("Entering.");
+	rc = memcmp(data1, data2, min(data1_len, data2_len));
+	if (!rc && (data1_len != data2_len)) {
+		if (data1_len < data2_len)
+			rc = -1;
+		else
+			rc = 1;
+	}
+	ntfs_debug("Done, returning %i", rc);
+	return rc;
+}
+
+static int ntfs_collate_ntofs_ulong(ntfs_volume *vol,
+		const void *data1, const int data1_len,
+		const void *data2, const int data2_len)
+{
+	int rc;
+	u32 d1, d2;
+
+	ntfs_debug("Entering.");
+	// FIXME:  We don't really want to bug here.
+	BUG_ON(data1_len != data2_len);
+	BUG_ON(data1_len != 4);
+	d1 = le32_to_cpup(data1);
+	d2 = le32_to_cpup(data2);
+	if (d1 < d2)
+		rc = -1;
+	else {
+		if (d1 == d2)
+			rc = 0;
+		else
+			rc = 1;
+	}
+	ntfs_debug("Done, returning %i", rc);
+	return rc;
+}
+
+typedef int (*ntfs_collate_func_t)(ntfs_volume *, const void *, const int,
+		const void *, const int);
+
+static ntfs_collate_func_t ntfs_do_collate0x0[3] = {
+	ntfs_collate_binary,
+	NULL/*ntfs_collate_file_name*/,
+	NULL/*ntfs_collate_unicode_string*/,
+};
+
+static ntfs_collate_func_t ntfs_do_collate0x1[4] = {
+	ntfs_collate_ntofs_ulong,
+	NULL/*ntfs_collate_ntofs_sid*/,
+	NULL/*ntfs_collate_ntofs_security_hash*/,
+	NULL/*ntfs_collate_ntofs_ulongs*/,
+};
+
+/**
+ * ntfs_collate - collate two data items using a specified collation rule
+ * @vol:	ntfs volume to which the data items belong
+ * @cr:		collation rule to use when comparing the items
+ * @data1:	first data item to collate
+ * @data1_len:	length in bytes of @data1
+ * @data2:	second data item to collate
+ * @data2_len:	length in bytes of @data2
+ *
+ * Collate the two data items @data1 and @data2 using the collation rule @cr
+ * and return -1, 0, ir 1 if @data1 is found, respectively, to collate before,
+ * to match, or to collate after @data2.
+ *
+ * For speed we use the collation rule @cr as an index into two tables of
+ * function pointers to call the appropriate collation function.
+ */
+int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr,
+		const void *data1, const int data1_len,
+		const void *data2, const int data2_len) {
+	int i;
+
+	ntfs_debug("Entering.");
+	/*
+	 * FIXME:  At the moment we only support COLLATION_BINARY and
+	 * COLLATION_NTOFS_ULONG, so we BUG() for everything else for now.
+	 */
+	BUG_ON(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG);
+	i = le32_to_cpu(cr);
+	BUG_ON(i < 0);
+	if (i <= 0x02)
+		return ntfs_do_collate0x0[i](vol, data1, data1_len,
+				data2, data2_len);
+	BUG_ON(i < 0x10);
+	i -= 0x10;
+	if (likely(i <= 3))
+		return ntfs_do_collate0x1[i](vol, data1, data1_len,
+				data2, data2_len);
+	BUG();
+	return 0;
+}

fs/ntfs/collate.h

@@ -0,0 +1,50 @@
+/*
+ * collate.h - Defines for NTFS kernel collation handling.  Part of the
+ *	       Linux-NTFS project.
+ *
+ * Copyright (c) 2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_COLLATE_H
+#define _LINUX_NTFS_COLLATE_H
+
+#include "types.h"
+#include "volume.h"
+
+static inline bool ntfs_is_collation_rule_supported(COLLATION_RULE cr) {
+	int i;
+
+	/*
+	 * FIXME:  At the moment we only support COLLATION_BINARY and
+	 * COLLATION_NTOFS_ULONG, so we return false for everything else for
+	 * now.
+	 */
+	if (unlikely(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG))
+		return false;
+	i = le32_to_cpu(cr);
+	if (likely(((i >= 0) && (i <= 0x02)) ||
+			((i >= 0x10) && (i <= 0x13))))
+		return true;
+	return false;
+}
+
+extern int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr,
+		const void *data1, const int data1_len,
+		const void *data2, const int data2_len);
+
+#endif /* _LINUX_NTFS_COLLATE_H */

fs/ntfs/compress.c

@@ -0,0 +1,969 @@
+/**
+ * compress.c - NTFS kernel compressed attributes handling.
+ *		Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 Anton Altaparmakov
+ * Copyright (c) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+
+#include "attrib.h"
+#include "inode.h"
+#include "debug.h"
+#include "ntfs.h"
+
+/**
+ * ntfs_compression_constants - enum of constants used in the compression code
+ */
+typedef enum {
+	/* Token types and access mask. */
+	NTFS_SYMBOL_TOKEN	=	0,
+	NTFS_PHRASE_TOKEN	=	1,
+	NTFS_TOKEN_MASK		=	1,
+
+	/* Compression sub-block constants. */
+	NTFS_SB_SIZE_MASK	=	0x0fff,
+	NTFS_SB_SIZE		=	0x1000,
+	NTFS_SB_IS_COMPRESSED	=	0x8000,
+
+	/*
+	 * The maximum compression block size is by definition 16 * the cluster
+	 * size, with the maximum supported cluster size being 4kiB. Thus the
+	 * maximum compression buffer size is 64kiB, so we use this when
+	 * initializing the compression buffer.
+	 */
+	NTFS_MAX_CB_SIZE	= 64 * 1024,
+} ntfs_compression_constants;
+
+/**
+ * ntfs_compression_buffer - one buffer for the decompression engine
+ */
+static u8 *ntfs_compression_buffer;
+
+/**
+ * ntfs_cb_lock - spinlock which protects ntfs_compression_buffer
+ */
+static DEFINE_SPINLOCK(ntfs_cb_lock);
+
+/**
+ * allocate_compression_buffers - allocate the decompression buffers
+ *
+ * Caller has to hold the ntfs_lock mutex.
+ *
+ * Return 0 on success or -ENOMEM if the allocations failed.
+ */
+int allocate_compression_buffers(void)
+{
+	BUG_ON(ntfs_compression_buffer);
+
+	ntfs_compression_buffer = vmalloc(NTFS_MAX_CB_SIZE);
+	if (!ntfs_compression_buffer)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * free_compression_buffers - free the decompression buffers
+ *
+ * Caller has to hold the ntfs_lock mutex.
+ */
+void free_compression_buffers(void)
+{
+	BUG_ON(!ntfs_compression_buffer);
+	vfree(ntfs_compression_buffer);
+	ntfs_compression_buffer = NULL;
+}
+
+/**
+ * zero_partial_compressed_page - zero out of bounds compressed page region
+ */
+static void zero_partial_compressed_page(struct page *page,
+		const s64 initialized_size)
+{
+	u8 *kp = page_address(page);
+	unsigned int kp_ofs;
+
+	ntfs_debug("Zeroing page region outside initialized size.");
+	if (((s64)page->index << PAGE_CACHE_SHIFT) >= initialized_size) {
+		/*
+		 * FIXME: Using clear_page() will become wrong when we get
+		 * PAGE_CACHE_SIZE != PAGE_SIZE but for now there is no problem.
+		 */
+		clear_page(kp);
+		return;
+	}
+	kp_ofs = initialized_size & ~PAGE_CACHE_MASK;
+	memset(kp + kp_ofs, 0, PAGE_CACHE_SIZE - kp_ofs);
+	return;
+}
+
+/**
+ * handle_bounds_compressed_page - test for&handle out of bounds compressed page
+ */
+static inline void handle_bounds_compressed_page(struct page *page,
+		const loff_t i_size, const s64 initialized_size)
+{
+	if ((page->index >= (initialized_size >> PAGE_CACHE_SHIFT)) &&
+			(initialized_size < i_size))
+		zero_partial_compressed_page(page, initialized_size);
+	return;
+}
+
+/**
+ * ntfs_decompress - decompress a compression block into an array of pages
+ * @dest_pages:		destination array of pages
+ * @dest_index:		current index into @dest_pages (IN/OUT)
+ * @dest_ofs:		current offset within @dest_pages[@dest_index] (IN/OUT)
+ * @dest_max_index:	maximum index into @dest_pages (IN)
+ * @dest_max_ofs:	maximum offset within @dest_pages[@dest_max_index] (IN)
+ * @xpage:		the target page (-1 if none) (IN)
+ * @xpage_done:		set to 1 if xpage was completed successfully (IN/OUT)
+ * @cb_start:		compression block to decompress (IN)
+ * @cb_size:		size of compression block @cb_start in bytes (IN)
+ * @i_size:		file size when we started the read (IN)
+ * @initialized_size:	initialized file size when we started the read (IN)
+ *
+ * The caller must have disabled preemption. ntfs_decompress() reenables it when
+ * the critical section is finished.
+ *
+ * This decompresses the compression block @cb_start into the array of
+ * destination pages @dest_pages starting at index @dest_index into @dest_pages
+ * and at offset @dest_pos into the page @dest_pages[@dest_index].
+ *
+ * When the page @dest_pages[@xpage] is completed, @xpage_done is set to 1.
+ * If xpage is -1 or @xpage has not been completed, @xpage_done is not modified.
+ *
+ * @cb_start is a pointer to the compression block which needs decompressing
+ * and @cb_size is the size of @cb_start in bytes (8-64kiB).
+ *
+ * Return 0 if success or -EOVERFLOW on error in the compressed stream.
+ * @xpage_done indicates whether the target page (@dest_pages[@xpage]) was
+ * completed during the decompression of the compression block (@cb_start).
+ *
+ * Warning: This function *REQUIRES* PAGE_CACHE_SIZE >= 4096 or it will blow up
+ * unpredicatbly! You have been warned!
+ *
+ * Note to hackers: This function may not sleep until it has finished accessing
+ * the compression block @cb_start as it is a per-CPU buffer.
+ */
+static int ntfs_decompress(struct page *dest_pages[], int *dest_index,
+		int *dest_ofs, const int dest_max_index, const int dest_max_ofs,
+		const int xpage, char *xpage_done, u8 *const cb_start,
+		const u32 cb_size, const loff_t i_size,
+		const s64 initialized_size)
+{
+	/*
+	 * Pointers into the compressed data, i.e. the compression block (cb),
+	 * and the therein contained sub-blocks (sb).
+	 */
+	u8 *cb_end = cb_start + cb_size; /* End of cb. */
+	u8 *cb = cb_start;	/* Current position in cb. */
+	u8 *cb_sb_start = cb;	/* Beginning of the current sb in the cb. */
+	u8 *cb_sb_end;		/* End of current sb / beginning of next sb. */
+
+	/* Variables for uncompressed data / destination. */
+	struct page *dp;	/* Current destination page being worked on. */
+	u8 *dp_addr;		/* Current pointer into dp. */
+	u8 *dp_sb_start;	/* Start of current sub-block in dp. */
+	u8 *dp_sb_end;		/* End of current sb in dp (dp_sb_start +
+				   NTFS_SB_SIZE). */
+	u16 do_sb_start;	/* @dest_ofs when starting this sub-block. */
+	u16 do_sb_end;		/* @dest_ofs of end of this sb (do_sb_start +
+				   NTFS_SB_SIZE). */
+
+	/* Variables for tag and token parsing. */
+	u8 tag;			/* Current tag. */
+	int token;		/* Loop counter for the eight tokens in tag. */
+
+	/* Need this because we can't sleep, so need two stages. */
+	int completed_pages[dest_max_index - *dest_index + 1];
+	int nr_completed_pages = 0;
+
+	/* Default error code. */
+	int err = -EOVERFLOW;
+
+	ntfs_debug("Entering, cb_size = 0x%x.", cb_size);
+do_next_sb:
+	ntfs_debug("Beginning sub-block at offset = 0x%zx in the cb.",
+			cb - cb_start);
+	/*
+	 * Have we reached the end of the compression block or the end of the
+	 * decompressed data?  The latter can happen for example if the current
+	 * position in the compression block is one byte before its end so the
+	 * first two checks do not detect it.
+	 */
+	if (cb == cb_end || !le16_to_cpup((le16*)cb) ||
+			(*dest_index == dest_max_index &&
+			*dest_ofs == dest_max_ofs)) {
+		int i;
+
+		ntfs_debug("Completed. Returning success (0).");
+		err = 0;
+return_error:
+		/* We can sleep from now on, so we drop lock. */
+		spin_unlock(&ntfs_cb_lock);
+		/* Second stage: finalize completed pages. */
+		if (nr_completed_pages > 0) {
+			for (i = 0; i < nr_completed_pages; i++) {
+				int di = completed_pages[i];
+
+				dp = dest_pages[di];
+				/*
+				 * If we are outside the initialized size, zero
+				 * the out of bounds page range.
+				 */
+				handle_bounds_compressed_page(dp, i_size,
+						initialized_size);
+				flush_dcache_page(dp);
+				kunmap(dp);
+				SetPageUptodate(dp);
+				unlock_page(dp);
+				if (di == xpage)
+					*xpage_done = 1;
+				else
+					page_cache_release(dp);
+				dest_pages[di] = NULL;
+			}
+		}
+		return err;
+	}
+
+	/* Setup offsets for the current sub-block destination. */
+	do_sb_start = *dest_ofs;
+	do_sb_end = do_sb_start + NTFS_SB_SIZE;
+
+	/* Check that we are still within allowed boundaries. */
+	if (*dest_index == dest_max_index && do_sb_end > dest_max_ofs)
+		goto return_overflow;
+
+	/* Does the minimum size of a compressed sb overflow valid range? */
+	if (cb + 6 > cb_end)
+		goto return_overflow;
+
+	/* Setup the current sub-block source pointers and validate range. */
+	cb_sb_start = cb;
+	cb_sb_end = cb_sb_start + (le16_to_cpup((le16*)cb) & NTFS_SB_SIZE_MASK)
+			+ 3;
+	if (cb_sb_end > cb_end)
+		goto return_overflow;
+
+	/* Get the current destination page. */
+	dp = dest_pages[*dest_index];
+	if (!dp) {
+		/* No page present. Skip decompression of this sub-block. */
+		cb = cb_sb_end;
+
+		/* Advance destination position to next sub-block. */
+		*dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_CACHE_MASK;
+		if (!*dest_ofs && (++*dest_index > dest_max_index))
+			goto return_overflow;
+		goto do_next_sb;
+	}
+
+	/* We have a valid destination page. Setup the destination pointers. */
+	dp_addr = (u8*)page_address(dp) + do_sb_start;
+
+	/* Now, we are ready to process the current sub-block (sb). */
+	if (!(le16_to_cpup((le16*)cb) & NTFS_SB_IS_COMPRESSED)) {
+		ntfs_debug("Found uncompressed sub-block.");
+		/* This sb is not compressed, just copy it into destination. */
+
+		/* Advance source position to first data byte. */
+		cb += 2;
+
+		/* An uncompressed sb must be full size. */
+		if (cb_sb_end - cb != NTFS_SB_SIZE)
+			goto return_overflow;
+
+		/* Copy the block and advance the source position. */
+		memcpy(dp_addr, cb, NTFS_SB_SIZE);
+		cb += NTFS_SB_SIZE;
+
+		/* Advance destination position to next sub-block. */
+		*dest_ofs += NTFS_SB_SIZE;
+		if (!(*dest_ofs &= ~PAGE_CACHE_MASK)) {
+finalize_page:
+			/*
+			 * First stage: add current page index to array of
+			 * completed pages.
+			 */
+			completed_pages[nr_completed_pages++] = *dest_index;
+			if (++*dest_index > dest_max_index)
+				goto return_overflow;
+		}
+		goto do_next_sb;
+	}
+	ntfs_debug("Found compressed sub-block.");
+	/* This sb is compressed, decompress it into destination. */
+
+	/* Setup destination pointers. */
+	dp_sb_start = dp_addr;
+	dp_sb_end = dp_sb_start + NTFS_SB_SIZE;
+
+	/* Forward to the first tag in the sub-block. */
+	cb += 2;
+do_next_tag:
+	if (cb == cb_sb_end) {
+		/* Check if the decompressed sub-block was not full-length. */
+		if (dp_addr < dp_sb_end) {
+			int nr_bytes = do_sb_end - *dest_ofs;
+
+			ntfs_debug("Filling incomplete sub-block with "
+					"zeroes.");
+			/* Zero remainder and update destination position. */
+			memset(dp_addr, 0, nr_bytes);
+			*dest_ofs += nr_bytes;
+		}
+		/* We have finished the current sub-block. */
+		if (!(*dest_ofs &= ~PAGE_CACHE_MASK))
+			goto finalize_page;
+		goto do_next_sb;
+	}
+
+	/* Check we are still in range. */
+	if (cb > cb_sb_end || dp_addr > dp_sb_end)
+		goto return_overflow;
+
+	/* Get the next tag and advance to first token. */
+	tag = *cb++;
+
+	/* Parse the eight tokens described by the tag. */
+	for (token = 0; token < 8; token++, tag >>= 1) {
+		u16 lg, pt, length, max_non_overlap;
+		register u16 i;
+		u8 *dp_back_addr;
+
+		/* Check if we are done / still in range. */
+		if (cb >= cb_sb_end || dp_addr > dp_sb_end)
+			break;
+
+		/* Determine token type and parse appropriately.*/
+		if ((tag & NTFS_TOKEN_MASK) == NTFS_SYMBOL_TOKEN) {
+			/*
+			 * We have a symbol token, copy the symbol across, and
+			 * advance the source and destination positions.
+			 */
+			*dp_addr++ = *cb++;
+			++*dest_ofs;
+
+			/* Continue with the next token. */
+			continue;
+		}
+
+		/*
+		 * We have a phrase token. Make sure it is not the first tag in
+		 * the sb as this is illegal and would confuse the code below.
+		 */
+		if (dp_addr == dp_sb_start)
+			goto return_overflow;
+
+		/*
+		 * Determine the number of bytes to go back (p) and the number
+		 * of bytes to copy (l). We use an optimized algorithm in which
+		 * we first calculate log2(current destination position in sb),
+		 * which allows determination of l and p in O(1) rather than
+		 * O(n). We just need an arch-optimized log2() function now.
+		 */
+		lg = 0;
+		for (i = *dest_ofs - do_sb_start - 1; i >= 0x10; i >>= 1)
+			lg++;
+
+		/* Get the phrase token into i. */
+		pt = le16_to_cpup((le16*)cb);
+
+		/*
+		 * Calculate starting position of the byte sequence in
+		 * the destination using the fact that p = (pt >> (12 - lg)) + 1
+		 * and make sure we don't go too far back.
+		 */
+		dp_back_addr = dp_addr - (pt >> (12 - lg)) - 1;
+		if (dp_back_addr < dp_sb_start)
+			goto return_overflow;
+
+		/* Now calculate the length of the byte sequence. */
+		length = (pt & (0xfff >> lg)) + 3;
+
+		/* Advance destination position and verify it is in range. */
+		*dest_ofs += length;
+		if (*dest_ofs > do_sb_end)
+			goto return_overflow;
+
+		/* The number of non-overlapping bytes. */
+		max_non_overlap = dp_addr - dp_back_addr;
+
+		if (length <= max_non_overlap) {
+			/* The byte sequence doesn't overlap, just copy it. */
+			memcpy(dp_addr, dp_back_addr, length);
+
+			/* Advance destination pointer. */
+			dp_addr += length;
+		} else {
+			/*
+			 * The byte sequence does overlap, copy non-overlapping
+			 * part and then do a slow byte by byte copy for the
+			 * overlapping part. Also, advance the destination
+			 * pointer.
+			 */
+			memcpy(dp_addr, dp_back_addr, max_non_overlap);
+			dp_addr += max_non_overlap;
+			dp_back_addr += max_non_overlap;
+			length -= max_non_overlap;
+			while (length--)
+				*dp_addr++ = *dp_back_addr++;
+		}
+
+		/* Advance source position and continue with the next token. */
+		cb += 2;
+	}
+
+	/* No tokens left in the current tag. Continue with the next tag. */
+	goto do_next_tag;
+
+return_overflow:
+	ntfs_error(NULL, "Failed. Returning -EOVERFLOW.");
+	goto return_error;
+}
+
+/**
+ * ntfs_read_compressed_block - read a compressed block into the page cache
+ * @page:	locked page in the compression block(s) we need to read
+ *
+ * When we are called the page has already been verified to be locked and the
+ * attribute is known to be non-resident, not encrypted, but compressed.
+ *
+ * 1. Determine which compression block(s) @page is in.
+ * 2. Get hold of all pages corresponding to this/these compression block(s).
+ * 3. Read the (first) compression block.
+ * 4. Decompress it into the corresponding pages.
+ * 5. Throw the compressed data away and proceed to 3. for the next compression
+ *    block or return success if no more compression blocks left.
+ *
+ * Warning: We have to be careful what we do about existing pages. They might
+ * have been written to so that we would lose data if we were to just overwrite
+ * them with the out-of-date uncompressed data.
+ *
+ * FIXME: For PAGE_CACHE_SIZE > cb_size we are not doing the Right Thing(TM) at
+ * the end of the file I think. We need to detect this case and zero the out
+ * of bounds remainder of the page in question and mark it as handled. At the
+ * moment we would just return -EIO on such a page. This bug will only become
+ * apparent if pages are above 8kiB and the NTFS volume only uses 512 byte
+ * clusters so is probably not going to be seen by anyone. Still this should
+ * be fixed. (AIA)
+ *
+ * FIXME: Again for PAGE_CACHE_SIZE > cb_size we are screwing up both in
+ * handling sparse and compressed cbs. (AIA)
+ *
+ * FIXME: At the moment we don't do any zeroing out in the case that
+ * initialized_size is less than data_size. This should be safe because of the
+ * nature of the compression algorithm used. Just in case we check and output
+ * an error message in read inode if the two sizes are not equal for a
+ * compressed file. (AIA)
+ */
+int ntfs_read_compressed_block(struct page *page)
+{
+	loff_t i_size;
+	s64 initialized_size;
+	struct address_space *mapping = page->mapping;
+	ntfs_inode *ni = NTFS_I(mapping->host);
+	ntfs_volume *vol = ni->vol;
+	struct super_block *sb = vol->sb;
+	runlist_element *rl;
+	unsigned long flags, block_size = sb->s_blocksize;
+	unsigned char block_size_bits = sb->s_blocksize_bits;
+	u8 *cb, *cb_pos, *cb_end;
+	struct buffer_head **bhs;
+	unsigned long offset, index = page->index;
+	u32 cb_size = ni->itype.compressed.block_size;
+	u64 cb_size_mask = cb_size - 1UL;
+	VCN vcn;
+	LCN lcn;
+	/* The first wanted vcn (minimum alignment is PAGE_CACHE_SIZE). */
+	VCN start_vcn = (((s64)index << PAGE_CACHE_SHIFT) & ~cb_size_mask) >>
+			vol->cluster_size_bits;
+	/*
+	 * The first vcn after the last wanted vcn (minimum alignment is again
+	 * PAGE_CACHE_SIZE.
+	 */
+	VCN end_vcn = ((((s64)(index + 1UL) << PAGE_CACHE_SHIFT) + cb_size - 1)
+			& ~cb_size_mask) >> vol->cluster_size_bits;
+	/* Number of compression blocks (cbs) in the wanted vcn range. */
+	unsigned int nr_cbs = (end_vcn - start_vcn) << vol->cluster_size_bits
+			>> ni->itype.compressed.block_size_bits;
+	/*
+	 * Number of pages required to store the uncompressed data from all
+	 * compression blocks (cbs) overlapping @page. Due to alignment
+	 * guarantees of start_vcn and end_vcn, no need to round up here.
+	 */
+	unsigned int nr_pages = (end_vcn - start_vcn) <<
+			vol->cluster_size_bits >> PAGE_CACHE_SHIFT;
+	unsigned int xpage, max_page, cur_page, cur_ofs, i;
+	unsigned int cb_clusters, cb_max_ofs;
+	int block, max_block, cb_max_page, bhs_size, nr_bhs, err = 0;
+	struct page **pages;
+	unsigned char xpage_done = 0;
+
+	ntfs_debug("Entering, page->index = 0x%lx, cb_size = 0x%x, nr_pages = "
+			"%i.", index, cb_size, nr_pages);
+	/*
+	 * Bad things happen if we get here for anything that is not an
+	 * unnamed $DATA attribute.
+	 */
+	BUG_ON(ni->type != AT_DATA);
+	BUG_ON(ni->name_len);
+
+	pages = kmalloc(nr_pages * sizeof(struct page *), GFP_NOFS);
+
+	/* Allocate memory to store the buffer heads we need. */
+	bhs_size = cb_size / block_size * sizeof(struct buffer_head *);
+	bhs = kmalloc(bhs_size, GFP_NOFS);
+
+	if (unlikely(!pages || !bhs)) {
+		kfree(bhs);
+		kfree(pages);
+		unlock_page(page);
+		ntfs_error(vol->sb, "Failed to allocate internal buffers.");
+		return -ENOMEM;
+	}
+
+	/*
+	 * We have already been given one page, this is the one we must do.
+	 * Once again, the alignment guarantees keep it simple.
+	 */
+	offset = start_vcn << vol->cluster_size_bits >> PAGE_CACHE_SHIFT;
+	xpage = index - offset;
+	pages[xpage] = page;
+	/*
+	 * The remaining pages need to be allocated and inserted into the page
+	 * cache, alignment guarantees keep all the below much simpler. (-8
+	 */
+	read_lock_irqsave(&ni->size_lock, flags);
+	i_size = i_size_read(VFS_I(ni));
+	initialized_size = ni->initialized_size;
+	read_unlock_irqrestore(&ni->size_lock, flags);
+	max_page = ((i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT) -
+			offset;
+	/* Is the page fully outside i_size? (truncate in progress) */
+	if (xpage >= max_page) {
+		kfree(bhs);
+		kfree(pages);
+		zero_user(page, 0, PAGE_CACHE_SIZE);
+		ntfs_debug("Compressed read outside i_size - truncated?");
+		SetPageUptodate(page);
+		unlock_page(page);
+		return 0;
+	}
+	if (nr_pages < max_page)
+		max_page = nr_pages;
+	for (i = 0; i < max_page; i++, offset++) {
+		if (i != xpage)
+			pages[i] = grab_cache_page_nowait(mapping, offset);
+		page = pages[i];
+		if (page) {
+			/*
+			 * We only (re)read the page if it isn't already read
+			 * in and/or dirty or we would be losing data or at
+			 * least wasting our time.
+			 */
+			if (!PageDirty(page) && (!PageUptodate(page) ||
+					PageError(page))) {
+				ClearPageError(page);
+				kmap(page);
+				continue;
+			}
+			unlock_page(page);
+			page_cache_release(page);
+			pages[i] = NULL;
+		}
+	}
+
+	/*
+	 * We have the runlist, and all the destination pages we need to fill.
+	 * Now read the first compression block.
+	 */
+	cur_page = 0;
+	cur_ofs = 0;
+	cb_clusters = ni->itype.compressed.block_clusters;
+do_next_cb:
+	nr_cbs--;
+	nr_bhs = 0;
+
+	/* Read all cb buffer heads one cluster at a time. */
+	rl = NULL;
+	for (vcn = start_vcn, start_vcn += cb_clusters; vcn < start_vcn;
+			vcn++) {
+		bool is_retry = false;
+
+		if (!rl) {
+lock_retry_remap:
+			down_read(&ni->runlist.lock);
+			rl = ni->runlist.rl;
+		}
+		if (likely(rl != NULL)) {
+			/* Seek to element containing target vcn. */
+			while (rl->length && rl[1].vcn <= vcn)
+				rl++;
+			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
+		} else
+			lcn = LCN_RL_NOT_MAPPED;
+		ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
+				(unsigned long long)vcn,
+				(unsigned long long)lcn);
+		if (lcn < 0) {
+			/*
+			 * When we reach the first sparse cluster we have
+			 * finished with the cb.
+			 */
+			if (lcn == LCN_HOLE)
+				break;
+			if (is_retry || lcn != LCN_RL_NOT_MAPPED)
+				goto rl_err;
+			is_retry = true;
+			/*
+			 * Attempt to map runlist, dropping lock for the
+			 * duration.
+			 */
+			up_read(&ni->runlist.lock);
+			if (!ntfs_map_runlist(ni, vcn))
+				goto lock_retry_remap;
+			goto map_rl_err;
+		}
+		block = lcn << vol->cluster_size_bits >> block_size_bits;
+		/* Read the lcn from device in chunks of block_size bytes. */
+		max_block = block + (vol->cluster_size >> block_size_bits);
+		do {
+			ntfs_debug("block = 0x%x.", block);
+			if (unlikely(!(bhs[nr_bhs] = sb_getblk(sb, block))))
+				goto getblk_err;
+			nr_bhs++;
+		} while (++block < max_block);
+	}
+
+	/* Release the lock if we took it. */
+	if (rl)
+		up_read(&ni->runlist.lock);
+
+	/* Setup and initiate io on all buffer heads. */
+	for (i = 0; i < nr_bhs; i++) {
+		struct buffer_head *tbh = bhs[i];
+
+		if (!trylock_buffer(tbh))
+			continue;
+		if (unlikely(buffer_uptodate(tbh))) {
+			unlock_buffer(tbh);
+			continue;
+		}
+		get_bh(tbh);
+		tbh->b_end_io = end_buffer_read_sync;
+		submit_bh(READ, tbh);
+	}
+
+	/* Wait for io completion on all buffer heads. */
+	for (i = 0; i < nr_bhs; i++) {
+		struct buffer_head *tbh = bhs[i];
+
+		if (buffer_uptodate(tbh))
+			continue;
+		wait_on_buffer(tbh);
+		/*
+		 * We need an optimization barrier here, otherwise we start
+		 * hitting the below fixup code when accessing a loopback
+		 * mounted ntfs partition. This indicates either there is a
+		 * race condition in the loop driver or, more likely, gcc
+		 * overoptimises the code without the barrier and it doesn't
+		 * do the Right Thing(TM).
+		 */
+		barrier();
+		if (unlikely(!buffer_uptodate(tbh))) {
+			ntfs_warning(vol->sb, "Buffer is unlocked but not "
+					"uptodate! Unplugging the disk queue "
+					"and rescheduling.");
+			get_bh(tbh);
+			io_schedule();
+			put_bh(tbh);
+			if (unlikely(!buffer_uptodate(tbh)))
+				goto read_err;
+			ntfs_warning(vol->sb, "Buffer is now uptodate. Good.");
+		}
+	}
+
+	/*
+	 * Get the compression buffer. We must not sleep any more
+	 * until we are finished with it.
+	 */
+	spin_lock(&ntfs_cb_lock);
+	cb = ntfs_compression_buffer;
+
+	BUG_ON(!cb);
+
+	cb_pos = cb;
+	cb_end = cb + cb_size;
+
+	/* Copy the buffer heads into the contiguous buffer. */
+	for (i = 0; i < nr_bhs; i++) {
+		memcpy(cb_pos, bhs[i]->b_data, block_size);
+		cb_pos += block_size;
+	}
+
+	/* Just a precaution. */
+	if (cb_pos + 2 <= cb + cb_size)
+		*(u16*)cb_pos = 0;
+
+	/* Reset cb_pos back to the beginning. */
+	cb_pos = cb;
+
+	/* We now have both source (if present) and destination. */
+	ntfs_debug("Successfully read the compression block.");
+
+	/* The last page and maximum offset within it for the current cb. */
+	cb_max_page = (cur_page << PAGE_CACHE_SHIFT) + cur_ofs + cb_size;
+	cb_max_ofs = cb_max_page & ~PAGE_CACHE_MASK;
+	cb_max_page >>= PAGE_CACHE_SHIFT;
+
+	/* Catch end of file inside a compression block. */
+	if (cb_max_page > max_page)
+		cb_max_page = max_page;
+
+	if (vcn == start_vcn - cb_clusters) {
+		/* Sparse cb, zero out page range overlapping the cb. */
+		ntfs_debug("Found sparse compression block.");
+		/* We can sleep from now on, so we drop lock. */
+		spin_unlock(&ntfs_cb_lock);
+		if (cb_max_ofs)
+			cb_max_page--;
+		for (; cur_page < cb_max_page; cur_page++) {
+			page = pages[cur_page];
+			if (page) {
+				/*
+				 * FIXME: Using clear_page() will become wrong
+				 * when we get PAGE_CACHE_SIZE != PAGE_SIZE but
+				 * for now there is no problem.
+				 */
+				if (likely(!cur_ofs))
+					clear_page(page_address(page));
+				else
+					memset(page_address(page) + cur_ofs, 0,
+							PAGE_CACHE_SIZE -
+							cur_ofs);
+				flush_dcache_page(page);
+				kunmap(page);
+				SetPageUptodate(page);
+				unlock_page(page);
+				if (cur_page == xpage)
+					xpage_done = 1;
+				else
+					page_cache_release(page);
+				pages[cur_page] = NULL;
+			}
+			cb_pos += PAGE_CACHE_SIZE - cur_ofs;
+			cur_ofs = 0;
+			if (cb_pos >= cb_end)
+				break;
+		}
+		/* If we have a partial final page, deal with it now. */
+		if (cb_max_ofs && cb_pos < cb_end) {
+			page = pages[cur_page];
+			if (page)
+				memset(page_address(page) + cur_ofs, 0,
+						cb_max_ofs - cur_ofs);
+			/*
+			 * No need to update cb_pos at this stage:
+			 *	cb_pos += cb_max_ofs - cur_ofs;
+			 */
+			cur_ofs = cb_max_ofs;
+		}
+	} else if (vcn == start_vcn) {
+		/* We can't sleep so we need two stages. */
+		unsigned int cur2_page = cur_page;
+		unsigned int cur_ofs2 = cur_ofs;
+		u8 *cb_pos2 = cb_pos;
+
+		ntfs_debug("Found uncompressed compression block.");
+		/* Uncompressed cb, copy it to the destination pages. */
+		/*
+		 * TODO: As a big optimization, we could detect this case
+		 * before we read all the pages and use block_read_full_page()
+		 * on all full pages instead (we still have to treat partial
+		 * pages especially but at least we are getting rid of the
+		 * synchronous io for the majority of pages.
+		 * Or if we choose not to do the read-ahead/-behind stuff, we
+		 * could just return block_read_full_page(pages[xpage]) as long
+		 * as PAGE_CACHE_SIZE <= cb_size.
+		 */
+		if (cb_max_ofs)
+			cb_max_page--;
+		/* First stage: copy data into destination pages. */
+		for (; cur_page < cb_max_page; cur_page++) {
+			page = pages[cur_page];
+			if (page)
+				memcpy(page_address(page) + cur_ofs, cb_pos,
+						PAGE_CACHE_SIZE - cur_ofs);
+			cb_pos += PAGE_CACHE_SIZE - cur_ofs;
+			cur_ofs = 0;
+			if (cb_pos >= cb_end)
+				break;
+		}
+		/* If we have a partial final page, deal with it now. */
+		if (cb_max_ofs && cb_pos < cb_end) {
+			page = pages[cur_page];
+			if (page)
+				memcpy(page_address(page) + cur_ofs, cb_pos,
+						cb_max_ofs - cur_ofs);
+			cb_pos += cb_max_ofs - cur_ofs;
+			cur_ofs = cb_max_ofs;
+		}
+		/* We can sleep from now on, so drop lock. */
+		spin_unlock(&ntfs_cb_lock);
+		/* Second stage: finalize pages. */
+		for (; cur2_page < cb_max_page; cur2_page++) {
+			page = pages[cur2_page];
+			if (page) {
+				/*
+				 * If we are outside the initialized size, zero
+				 * the out of bounds page range.
+				 */
+				handle_bounds_compressed_page(page, i_size,
+						initialized_size);
+				flush_dcache_page(page);
+				kunmap(page);
+				SetPageUptodate(page);
+				unlock_page(page);
+				if (cur2_page == xpage)
+					xpage_done = 1;
+				else
+					page_cache_release(page);
+				pages[cur2_page] = NULL;
+			}
+			cb_pos2 += PAGE_CACHE_SIZE - cur_ofs2;
+			cur_ofs2 = 0;
+			if (cb_pos2 >= cb_end)
+				break;
+		}
+	} else {
+		/* Compressed cb, decompress it into the destination page(s). */
+		unsigned int prev_cur_page = cur_page;
+
+		ntfs_debug("Found compressed compression block.");
+		err = ntfs_decompress(pages, &cur_page, &cur_ofs,
+				cb_max_page, cb_max_ofs, xpage, &xpage_done,
+				cb_pos,	cb_size - (cb_pos - cb), i_size,
+				initialized_size);
+		/*
+		 * We can sleep from now on, lock already dropped by
+		 * ntfs_decompress().
+		 */
+		if (err) {
+			ntfs_error(vol->sb, "ntfs_decompress() failed in inode "
+					"0x%lx with error code %i. Skipping "
+					"this compression block.",
+					ni->mft_no, -err);
+			/* Release the unfinished pages. */
+			for (; prev_cur_page < cur_page; prev_cur_page++) {
+				page = pages[prev_cur_page];
+				if (page) {
+					flush_dcache_page(page);
+					kunmap(page);
+					unlock_page(page);
+					if (prev_cur_page != xpage)
+						page_cache_release(page);
+					pages[prev_cur_page] = NULL;
+				}
+			}
+		}
+	}
+
+	/* Release the buffer heads. */
+	for (i = 0; i < nr_bhs; i++)
+		brelse(bhs[i]);
+
+	/* Do we have more work to do? */
+	if (nr_cbs)
+		goto do_next_cb;
+
+	/* We no longer need the list of buffer heads. */
+	kfree(bhs);
+
+	/* Clean up if we have any pages left. Should never happen. */
+	for (cur_page = 0; cur_page < max_page; cur_page++) {
+		page = pages[cur_page];
+		if (page) {
+			ntfs_error(vol->sb, "Still have pages left! "
+					"Terminating them with extreme "
+					"prejudice.  Inode 0x%lx, page index "
+					"0x%lx.", ni->mft_no, page->index);
+			flush_dcache_page(page);
+			kunmap(page);
+			unlock_page(page);
+			if (cur_page != xpage)
+				page_cache_release(page);
+			pages[cur_page] = NULL;
+		}
+	}
+
+	/* We no longer need the list of pages. */
+	kfree(pages);
+
+	/* If we have completed the requested page, we return success. */
+	if (likely(xpage_done))
+		return 0;
+
+	ntfs_debug("Failed. Returning error code %s.", err == -EOVERFLOW ?
+			"EOVERFLOW" : (!err ? "EIO" : "unknown error"));
+	return err < 0 ? err : -EIO;
+
+read_err:
+	ntfs_error(vol->sb, "IO error while reading compressed data.");
+	/* Release the buffer heads. */
+	for (i = 0; i < nr_bhs; i++)
+		brelse(bhs[i]);
+	goto err_out;
+
+map_rl_err:
+	ntfs_error(vol->sb, "ntfs_map_runlist() failed. Cannot read "
+			"compression block.");
+	goto err_out;
+
+rl_err:
+	up_read(&ni->runlist.lock);
+	ntfs_error(vol->sb, "ntfs_rl_vcn_to_lcn() failed. Cannot read "
+			"compression block.");
+	goto err_out;
+
+getblk_err:
+	up_read(&ni->runlist.lock);
+	ntfs_error(vol->sb, "getblk() failed. Cannot read compression block.");
+
+err_out:
+	kfree(bhs);
+	for (i = cur_page; i < max_page; i++) {
+		page = pages[i];
+		if (page) {
+			flush_dcache_page(page);
+			kunmap(page);
+			unlock_page(page);
+			if (i != xpage)
+				page_cache_release(page);
+		}
+	}
+	kfree(pages);
+	return -EIO;
+}

fs/ntfs/debug.c

@@ -0,0 +1,173 @@
+/*
+ * debug.c - NTFS kernel debug support. Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include "debug.h"
+
+/**
+ * __ntfs_warning - output a warning to the syslog
+ * @function:	name of function outputting the warning
+ * @sb:		super block of mounted ntfs filesystem
+ * @fmt:	warning string containing format specifications
+ * @...:	a variable number of arguments specified in @fmt
+ *
+ * Outputs a warning to the syslog for the mounted ntfs filesystem described
+ * by @sb.
+ *
+ * @fmt and the corresponding @... is printf style format string containing
+ * the warning string and the corresponding format arguments, respectively.
+ *
+ * @function is the name of the function from which __ntfs_warning is being
+ * called.
+ *
+ * Note, you should be using debug.h::ntfs_warning(@sb, @fmt, @...) instead
+ * as this provides the @function parameter automatically.
+ */
+void __ntfs_warning(const char *function, const struct super_block *sb,
+		const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	int flen = 0;
+
+#ifndef DEBUG
+	if (!printk_ratelimit())
+		return;
+#endif
+	if (function)
+		flen = strlen(function);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	if (sb)
+		pr_warn("(device %s): %s(): %pV\n",
+			sb->s_id, flen ? function : "", &vaf);
+	else
+		pr_warn("%s(): %pV\n", flen ? function : "", &vaf);
+	va_end(args);
+}
+
+/**
+ * __ntfs_error - output an error to the syslog
+ * @function:	name of function outputting the error
+ * @sb:		super block of mounted ntfs filesystem
+ * @fmt:	error string containing format specifications
+ * @...:	a variable number of arguments specified in @fmt
+ *
+ * Outputs an error to the syslog for the mounted ntfs filesystem described
+ * by @sb.
+ *
+ * @fmt and the corresponding @... is printf style format string containing
+ * the error string and the corresponding format arguments, respectively.
+ *
+ * @function is the name of the function from which __ntfs_error is being
+ * called.
+ *
+ * Note, you should be using debug.h::ntfs_error(@sb, @fmt, @...) instead
+ * as this provides the @function parameter automatically.
+ */
+void __ntfs_error(const char *function, const struct super_block *sb,
+		const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	int flen = 0;
+
+#ifndef DEBUG
+	if (!printk_ratelimit())
+		return;
+#endif
+	if (function)
+		flen = strlen(function);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	if (sb)
+		pr_err("(device %s): %s(): %pV\n",
+		       sb->s_id, flen ? function : "", &vaf);
+	else
+		pr_err("%s(): %pV\n", flen ? function : "", &vaf);
+	va_end(args);
+}
+
+#ifdef DEBUG
+
+/* If 1, output debug messages, and if 0, don't. */
+int debug_msgs = 0;
+
+void __ntfs_debug(const char *file, int line, const char *function,
+		const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	int flen = 0;
+
+	if (!debug_msgs)
+		return;
+	if (function)
+		flen = strlen(function);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_debug("(%s, %d): %s(): %pV", file, line, flen ? function : "", &vaf);
+	va_end(args);
+}
+
+/* Dump a runlist. Caller has to provide synchronisation for @rl. */
+void ntfs_debug_dump_runlist(const runlist_element *rl)
+{
+	int i;
+	const char *lcn_str[5] = { "LCN_HOLE         ", "LCN_RL_NOT_MAPPED",
+				   "LCN_ENOENT       ", "LCN_unknown      " };
+
+	if (!debug_msgs)
+		return;
+	pr_debug("Dumping runlist (values in hex):\n");
+	if (!rl) {
+		pr_debug("Run list not present.\n");
+		return;
+	}
+	pr_debug("VCN              LCN               Run length\n");
+	for (i = 0; ; i++) {
+		LCN lcn = (rl + i)->lcn;
+
+		if (lcn < (LCN)0) {
+			int index = -lcn - 1;
+
+			if (index > -LCN_ENOENT - 1)
+				index = 3;
+			pr_debug("%-16Lx %s %-16Lx%s\n",
+					(long long)(rl + i)->vcn, lcn_str[index],
+					(long long)(rl + i)->length,
+					(rl + i)->length ? "" :
+						" (runlist end)");
+		} else
+			pr_debug("%-16Lx %-16Lx  %-16Lx%s\n",
+					(long long)(rl + i)->vcn,
+					(long long)(rl + i)->lcn,
+					(long long)(rl + i)->length,
+					(rl + i)->length ? "" :
+						" (runlist end)");
+		if (!(rl + i)->length)
+			break;
+	}
+}
+
+#endif

fs/ntfs/debug.h

@@ -0,0 +1,71 @@
+/*
+ * debug.h - NTFS kernel debug support. Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_DEBUG_H
+#define _LINUX_NTFS_DEBUG_H
+
+#include <linux/fs.h>
+
+#include "runlist.h"
+
+#ifdef DEBUG
+
+extern int debug_msgs;
+
+extern __printf(4, 5)
+void __ntfs_debug(const char *file, int line, const char *function,
+		  const char *format, ...);
+/**
+ * ntfs_debug - write a debug level message to syslog
+ * @f:		a printf format string containing the message
+ * @...:	the variables to substitute into @f
+ *
+ * ntfs_debug() writes a DEBUG level message to the syslog but only if the
+ * driver was compiled with -DDEBUG. Otherwise, the call turns into a NOP.
+ */
+#define ntfs_debug(f, a...)						\
+	__ntfs_debug(__FILE__, __LINE__, __func__, f, ##a)
+
+extern void ntfs_debug_dump_runlist(const runlist_element *rl);
+
+#else	/* !DEBUG */
+
+#define ntfs_debug(fmt, ...)						\
+do {									\
+	if (0)								\
+		no_printk(fmt, ##__VA_ARGS__);				\
+} while (0)
+
+#define ntfs_debug_dump_runlist(rl)	do {} while (0)
+
+#endif	/* !DEBUG */
+
+extern  __printf(3, 4)
+void __ntfs_warning(const char *function, const struct super_block *sb,
+		    const char *fmt, ...);
+#define ntfs_warning(sb, f, a...)	__ntfs_warning(__func__, sb, f, ##a)
+
+extern  __printf(3, 4)
+void __ntfs_error(const char *function, const struct super_block *sb,
+		  const char *fmt, ...);
+#define ntfs_error(sb, f, a...)		__ntfs_error(__func__, sb, f, ##a)
+
+#endif /* _LINUX_NTFS_DEBUG_H */

fs/ntfs/dir.h

@@ -0,0 +1,48 @@
+/*
+ * dir.h - Defines for directory handling in NTFS Linux kernel driver. Part of
+ *	   the Linux-NTFS project.
+ *
+ * Copyright (c) 2002-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_DIR_H
+#define _LINUX_NTFS_DIR_H
+
+#include "layout.h"
+#include "inode.h"
+#include "types.h"
+
+/*
+ * ntfs_name is used to return the file name to the caller of
+ * ntfs_lookup_inode_by_name() in order for the caller (namei.c::ntfs_lookup())
+ * to be able to deal with dcache aliasing issues.
+ */
+typedef struct {
+	MFT_REF mref;
+	FILE_NAME_TYPE_FLAGS type;
+	u8 len;
+	ntfschar name[0];
+} __attribute__ ((__packed__)) ntfs_name;
+
+/* The little endian Unicode string $I30 as a global constant. */
+extern ntfschar I30[5];
+
+extern MFT_REF ntfs_lookup_inode_by_name(ntfs_inode *dir_ni,
+		const ntfschar *uname, const int uname_len, ntfs_name **res);
+
+#endif /* _LINUX_NTFS_FS_DIR_H */

fs/ntfs/endian.h

@@ -0,0 +1,93 @@
+/*
+ * endian.h - Defines for endianness handling in NTFS Linux kernel driver.
+ *	      Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_ENDIAN_H
+#define _LINUX_NTFS_ENDIAN_H
+
+#include <asm/byteorder.h>
+#include "types.h"
+
+/*
+ * Signed endianness conversion functions.
+ */
+
+static inline s16 sle16_to_cpu(sle16 x)
+{
+	return le16_to_cpu((__force le16)x);
+}
+
+static inline s32 sle32_to_cpu(sle32 x)
+{
+	return le32_to_cpu((__force le32)x);
+}
+
+static inline s64 sle64_to_cpu(sle64 x)
+{
+	return le64_to_cpu((__force le64)x);
+}
+
+static inline s16 sle16_to_cpup(sle16 *x)
+{
+	return le16_to_cpu(*(__force le16*)x);
+}
+
+static inline s32 sle32_to_cpup(sle32 *x)
+{
+	return le32_to_cpu(*(__force le32*)x);
+}
+
+static inline s64 sle64_to_cpup(sle64 *x)
+{
+	return le64_to_cpu(*(__force le64*)x);
+}
+
+static inline sle16 cpu_to_sle16(s16 x)
+{
+	return (__force sle16)cpu_to_le16(x);
+}
+
+static inline sle32 cpu_to_sle32(s32 x)
+{
+	return (__force sle32)cpu_to_le32(x);
+}
+
+static inline sle64 cpu_to_sle64(s64 x)
+{
+	return (__force sle64)cpu_to_le64(x);
+}
+
+static inline sle16 cpu_to_sle16p(s16 *x)
+{
+	return (__force sle16)cpu_to_le16(*x);
+}
+
+static inline sle32 cpu_to_sle32p(s32 *x)
+{
+	return (__force sle32)cpu_to_le32(*x);
+}
+
+static inline sle64 cpu_to_sle64p(s64 *x)
+{
+	return (__force sle64)cpu_to_le64(*x);
+}
+
+#endif /* _LINUX_NTFS_ENDIAN_H */

fs/ntfs/index.c

@@ -0,0 +1,454 @@
+/*
+ * index.c - NTFS kernel index handling.  Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2004-2005 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/slab.h>
+
+#include "aops.h"
+#include "collate.h"
+#include "debug.h"
+#include "index.h"
+#include "ntfs.h"
+
+/**
+ * ntfs_index_ctx_get - allocate and initialize a new index context
+ * @idx_ni:	ntfs index inode with which to initialize the context
+ *
+ * Allocate a new index context, initialize it with @idx_ni and return it.
+ * Return NULL if allocation failed.
+ *
+ * Locking:  Caller must hold i_mutex on the index inode.
+ */
+ntfs_index_context *ntfs_index_ctx_get(ntfs_inode *idx_ni)
+{
+	ntfs_index_context *ictx;
+
+	ictx = kmem_cache_alloc(ntfs_index_ctx_cache, GFP_NOFS);
+	if (ictx)
+		*ictx = (ntfs_index_context){ .idx_ni = idx_ni };
+	return ictx;
+}
+
+/**
+ * ntfs_index_ctx_put - release an index context
+ * @ictx:	index context to free
+ *
+ * Release the index context @ictx, releasing all associated resources.
+ *
+ * Locking:  Caller must hold i_mutex on the index inode.
+ */
+void ntfs_index_ctx_put(ntfs_index_context *ictx)
+{
+	if (ictx->entry) {
+		if (ictx->is_in_root) {
+			if (ictx->actx)
+				ntfs_attr_put_search_ctx(ictx->actx);
+			if (ictx->base_ni)
+				unmap_mft_record(ictx->base_ni);
+		} else {
+			struct page *page = ictx->page;
+			if (page) {
+				BUG_ON(!PageLocked(page));
+				unlock_page(page);
+				ntfs_unmap_page(page);
+			}
+		}
+	}
+	kmem_cache_free(ntfs_index_ctx_cache, ictx);
+	return;
+}
+
+/**
+ * ntfs_index_lookup - find a key in an index and return its index entry
+ * @key:	[IN] key for which to search in the index
+ * @key_len:	[IN] length of @key in bytes
+ * @ictx:	[IN/OUT] context describing the index and the returned entry
+ *
+ * Before calling ntfs_index_lookup(), @ictx must have been obtained from a
+ * call to ntfs_index_ctx_get().
+ *
+ * Look for the @key in the index specified by the index lookup context @ictx.
+ * ntfs_index_lookup() walks the contents of the index looking for the @key.
+ *
+ * If the @key is found in the index, 0 is returned and @ictx is setup to
+ * describe the index entry containing the matching @key.  @ictx->entry is the
+ * index entry and @ictx->data and @ictx->data_len are the index entry data and
+ * its length in bytes, respectively.
+ *
+ * If the @key is not found in the index, -ENOENT is returned and @ictx is
+ * setup to describe the index entry whose key collates immediately after the
+ * search @key, i.e. this is the position in the index at which an index entry
+ * with a key of @key would need to be inserted.
+ *
+ * If an error occurs return the negative error code and @ictx is left
+ * untouched.
+ *
+ * When finished with the entry and its data, call ntfs_index_ctx_put() to free
+ * the context and other associated resources.
+ *
+ * If the index entry was modified, call flush_dcache_index_entry_page()
+ * immediately after the modification and either ntfs_index_entry_mark_dirty()
+ * or ntfs_index_entry_write() before the call to ntfs_index_ctx_put() to
+ * ensure that the changes are written to disk.
+ *
+ * Locking:  - Caller must hold i_mutex on the index inode.
+ *	     - Each page cache page in the index allocation mapping must be
+ *	       locked whilst being accessed otherwise we may find a corrupt
+ *	       page due to it being under ->writepage at the moment which
+ *	       applies the mst protection fixups before writing out and then
+ *	       removes them again after the write is complete after which it 
+ *	       unlocks the page.
+ */
+int ntfs_index_lookup(const void *key, const int key_len,
+		ntfs_index_context *ictx)
+{
+	VCN vcn, old_vcn;
+	ntfs_inode *idx_ni = ictx->idx_ni;
+	ntfs_volume *vol = idx_ni->vol;
+	struct super_block *sb = vol->sb;
+	ntfs_inode *base_ni = idx_ni->ext.base_ntfs_ino;
+	MFT_RECORD *m;
+	INDEX_ROOT *ir;
+	INDEX_ENTRY *ie;
+	INDEX_ALLOCATION *ia;
+	u8 *index_end, *kaddr;
+	ntfs_attr_search_ctx *actx;
+	struct address_space *ia_mapping;
+	struct page *page;
+	int rc, err = 0;
+
+	ntfs_debug("Entering.");
+	BUG_ON(!NInoAttr(idx_ni));
+	BUG_ON(idx_ni->type != AT_INDEX_ALLOCATION);
+	BUG_ON(idx_ni->nr_extents != -1);
+	BUG_ON(!base_ni);
+	BUG_ON(!key);
+	BUG_ON(key_len <= 0);
+	if (!ntfs_is_collation_rule_supported(
+			idx_ni->itype.index.collation_rule)) {
+		ntfs_error(sb, "Index uses unsupported collation rule 0x%x.  "
+				"Aborting lookup.", le32_to_cpu(
+				idx_ni->itype.index.collation_rule));
+		return -EOPNOTSUPP;
+	}
+	/* Get hold of the mft record for the index inode. */
+	m = map_mft_record(base_ni);
+	if (IS_ERR(m)) {
+		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
+				-PTR_ERR(m));
+		return PTR_ERR(m);
+	}
+	actx = ntfs_attr_get_search_ctx(base_ni, m);
+	if (unlikely(!actx)) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+	/* Find the index root attribute in the mft record. */
+	err = ntfs_attr_lookup(AT_INDEX_ROOT, idx_ni->name, idx_ni->name_len,
+			CASE_SENSITIVE, 0, NULL, 0, actx);
+	if (unlikely(err)) {
+		if (err == -ENOENT) {
+			ntfs_error(sb, "Index root attribute missing in inode "
+					"0x%lx.", idx_ni->mft_no);
+			err = -EIO;
+		}
+		goto err_out;
+	}
+	/* Get to the index root value (it has been verified in read_inode). */
+	ir = (INDEX_ROOT*)((u8*)actx->attr +
+			le16_to_cpu(actx->attr->data.resident.value_offset));
+	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
+	/* The first index entry. */
+	ie = (INDEX_ENTRY*)((u8*)&ir->index +
+			le32_to_cpu(ir->index.entries_offset));
+	/*
+	 * Loop until we exceed valid memory (corruption case) or until we
+	 * reach the last entry.
+	 */
+	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
+		/* Bounds checks. */
+		if ((u8*)ie < (u8*)actx->mrec || (u8*)ie +
+				sizeof(INDEX_ENTRY_HEADER) > index_end ||
+				(u8*)ie + le16_to_cpu(ie->length) > index_end)
+			goto idx_err_out;
+		/*
+		 * The last entry cannot contain a key.  It can however contain
+		 * a pointer to a child node in the B+tree so we just break out.
+		 */
+		if (ie->flags & INDEX_ENTRY_END)
+			break;
+		/* Further bounds checks. */
+		if ((u32)sizeof(INDEX_ENTRY_HEADER) +
+				le16_to_cpu(ie->key_length) >
+				le16_to_cpu(ie->data.vi.data_offset) ||
+				(u32)le16_to_cpu(ie->data.vi.data_offset) +
+				le16_to_cpu(ie->data.vi.data_length) >
+				le16_to_cpu(ie->length))
+			goto idx_err_out;
+		/* If the keys match perfectly, we setup @ictx and return 0. */
+		if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key,
+				&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;
+			ictx->page = NULL;
+done:
+			ictx->entry = ie;
+			ictx->data = (u8*)ie +
+					le16_to_cpu(ie->data.vi.data_offset);
+			ictx->data_len = le16_to_cpu(ie->data.vi.data_length);
+			ntfs_debug("Done.");
+			return err;
+		}
+		/*
+		 * Not a perfect match, need to do full blown collation so we
+		 * know which way in the B+tree we have to go.
+		 */
+		rc = ntfs_collate(vol, idx_ni->itype.index.collation_rule, key,
+				key_len, &ie->key, le16_to_cpu(ie->key_length));
+		/*
+		 * If @key collates before the key of the current entry, there
+		 * is definitely no such key in this index but we might need to
+		 * descend into the B+tree so we just break out of the loop.
+		 */
+		if (rc == -1)
+			break;
+		/*
+		 * A match should never happen as the memcmp() call should have
+		 * cought it, but we still treat it correctly.
+		 */
+		if (!rc)
+			goto ir_done;
+		/* The keys are not equal, continue the search. */
+	}
+	/*
+	 * We have finished with this index without success.  Check for the
+	 * presence of a child node and if not present setup @ictx and return
+	 * -ENOENT.
+	 */
+	if (!(ie->flags & INDEX_ENTRY_NODE)) {
+		ntfs_debug("Entry not found.");
+		err = -ENOENT;
+		goto ir_done;
+	} /* Child node present, descend into it. */
+	/* Consistency check: Verify that an index allocation exists. */
+	if (!NInoIndexAllocPresent(idx_ni)) {
+		ntfs_error(sb, "No index allocation attribute but index entry "
+				"requires one.  Inode 0x%lx is corrupt or "
+				"driver bug.", idx_ni->mft_no);
+		goto err_out;
+	}
+	/* Get the starting vcn of the index_block holding the child node. */
+	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
+	ia_mapping = VFS_I(idx_ni)->i_mapping;
+	/*
+	 * We are done with the index root and the mft record.  Release them,
+	 * otherwise we deadlock with ntfs_map_page().
+	 */
+	ntfs_attr_put_search_ctx(actx);
+	unmap_mft_record(base_ni);
+	m = NULL;
+	actx = NULL;
+descend_into_child_node:
+	/*
+	 * Convert vcn to index into the index allocation attribute in units
+	 * of PAGE_CACHE_SIZE and map the page cache page, reading it from
+	 * disk if necessary.
+	 */
+	page = ntfs_map_page(ia_mapping, vcn <<
+			idx_ni->itype.index.vcn_size_bits >> PAGE_CACHE_SHIFT);
+	if (IS_ERR(page)) {
+		ntfs_error(sb, "Failed to map index page, error %ld.",
+				-PTR_ERR(page));
+		err = PTR_ERR(page);
+		goto err_out;
+	}
+	lock_page(page);
+	kaddr = (u8*)page_address(page);
+fast_descend_into_child_node:
+	/* Get to the index allocation block. */
+	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
+			idx_ni->itype.index.vcn_size_bits) & ~PAGE_CACHE_MASK));
+	/* Bounds checks. */
+	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_CACHE_SIZE) {
+		ntfs_error(sb, "Out of bounds check failed.  Corrupt inode "
+				"0x%lx or driver bug.", idx_ni->mft_no);
+		goto unm_err_out;
+	}
+	/* Catch multi sector transfer fixup errors. */
+	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
+		ntfs_error(sb, "Index record with vcn 0x%llx is corrupt.  "
+				"Corrupt inode 0x%lx.  Run chkdsk.",
+				(long long)vcn, idx_ni->mft_no);
+		goto unm_err_out;
+	}
+	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
+		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
+				"different from expected VCN (0x%llx).  Inode "
+				"0x%lx is corrupt or driver bug.",
+				(unsigned long long)
+				sle64_to_cpu(ia->index_block_vcn),
+				(unsigned long long)vcn, idx_ni->mft_no);
+		goto unm_err_out;
+	}
+	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
+			idx_ni->itype.index.block_size) {
+		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx has "
+				"a size (%u) differing from the index "
+				"specified size (%u).  Inode is corrupt or "
+				"driver bug.", (unsigned long long)vcn,
+				idx_ni->mft_no,
+				le32_to_cpu(ia->index.allocated_size) + 0x18,
+				idx_ni->itype.index.block_size);
+		goto unm_err_out;
+	}
+	index_end = (u8*)ia + idx_ni->itype.index.block_size;
+	if (index_end > kaddr + PAGE_CACHE_SIZE) {
+		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx "
+				"crosses page boundary.  Impossible!  Cannot "
+				"access!  This is probably a bug in the "
+				"driver.", (unsigned long long)vcn,
+				idx_ni->mft_no);
+		goto unm_err_out;
+	}
+	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
+	if (index_end > (u8*)ia + idx_ni->itype.index.block_size) {
+		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of inode "
+				"0x%lx exceeds maximum size.",
+				(unsigned long long)vcn, idx_ni->mft_no);
+		goto unm_err_out;
+	}
+	/* The first index entry. */
+	ie = (INDEX_ENTRY*)((u8*)&ia->index +
+			le32_to_cpu(ia->index.entries_offset));
+	/*
+	 * Iterate similar to above big loop but applied to index buffer, thus
+	 * loop until we exceed valid memory (corruption case) or until we
+	 * reach the last entry.
+	 */
+	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
+		/* Bounds checks. */
+		if ((u8*)ie < (u8*)ia || (u8*)ie +
+				sizeof(INDEX_ENTRY_HEADER) > index_end ||
+				(u8*)ie + le16_to_cpu(ie->length) > index_end) {
+			ntfs_error(sb, "Index entry out of bounds in inode "
+					"0x%lx.", idx_ni->mft_no);
+			goto unm_err_out;
+		}
+		/*
+		 * The last entry cannot contain a key.  It can however contain
+		 * a pointer to a child node in the B+tree so we just break out.
+		 */
+		if (ie->flags & INDEX_ENTRY_END)
+			break;
+		/* Further bounds checks. */
+		if ((u32)sizeof(INDEX_ENTRY_HEADER) +
+				le16_to_cpu(ie->key_length) >
+				le16_to_cpu(ie->data.vi.data_offset) ||
+				(u32)le16_to_cpu(ie->data.vi.data_offset) +
+				le16_to_cpu(ie->data.vi.data_length) >
+				le16_to_cpu(ie->length)) {
+			ntfs_error(sb, "Index entry out of bounds in inode "
+					"0x%lx.", idx_ni->mft_no);
+			goto unm_err_out;
+		}
+		/* If the keys match perfectly, we setup @ictx and return 0. */
+		if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key,
+				&ie->key, key_len)) {
+ia_done:
+			ictx->is_in_root = false;
+			ictx->actx = NULL;
+			ictx->base_ni = NULL;
+			ictx->ia = ia;
+			ictx->page = page;
+			goto done;
+		}
+		/*
+		 * Not a perfect match, need to do full blown collation so we
+		 * know which way in the B+tree we have to go.
+		 */
+		rc = ntfs_collate(vol, idx_ni->itype.index.collation_rule, key,
+				key_len, &ie->key, le16_to_cpu(ie->key_length));
+		/*
+		 * If @key collates before the key of the current entry, there
+		 * is definitely no such key in this index but we might need to
+		 * descend into the B+tree so we just break out of the loop.
+		 */
+		if (rc == -1)
+			break;
+		/*
+		 * A match should never happen as the memcmp() call should have
+		 * cought it, but we still treat it correctly.
+		 */
+		if (!rc)
+			goto ia_done;
+		/* The keys are not equal, continue the search. */
+	}
+	/*
+	 * We have finished with this index buffer without success.  Check for
+	 * the presence of a child node and if not present return -ENOENT.
+	 */
+	if (!(ie->flags & INDEX_ENTRY_NODE)) {
+		ntfs_debug("Entry not found.");
+		err = -ENOENT;
+		goto ia_done;
+	}
+	if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
+		ntfs_error(sb, "Index entry with child node found in a leaf "
+				"node in inode 0x%lx.", idx_ni->mft_no);
+		goto unm_err_out;
+	}
+	/* Child node present, descend into it. */
+	old_vcn = vcn;
+	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
+	if (vcn >= 0) {
+		/*
+		 * If vcn is in the same page cache page as old_vcn we recycle
+		 * the mapped page.
+		 */
+		if (old_vcn << vol->cluster_size_bits >>
+				PAGE_CACHE_SHIFT == vcn <<
+				vol->cluster_size_bits >>
+				PAGE_CACHE_SHIFT)
+			goto fast_descend_into_child_node;
+		unlock_page(page);
+		ntfs_unmap_page(page);
+		goto descend_into_child_node;
+	}
+	ntfs_error(sb, "Negative child node vcn in inode 0x%lx.",
+			idx_ni->mft_no);
+unm_err_out:
+	unlock_page(page);
+	ntfs_unmap_page(page);
+err_out:
+	if (!err)
+		err = -EIO;
+	if (actx)
+		ntfs_attr_put_search_ctx(actx);
+	if (m)
+		unmap_mft_record(base_ni);
+	return err;
+idx_err_out:
+	ntfs_error(sb, "Corrupt index.  Aborting lookup.");
+	goto err_out;
+}

fs/ntfs/index.h

@@ -0,0 +1,148 @@
+/*
+ * index.h - Defines for NTFS kernel index handling.  Part of the Linux-NTFS
+ *	     project.
+ *
+ * Copyright (c) 2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_INDEX_H
+#define _LINUX_NTFS_INDEX_H
+
+#include <linux/fs.h>
+
+#include "types.h"
+#include "layout.h"
+#include "inode.h"
+#include "attrib.h"
+#include "mft.h"
+#include "aops.h"
+
+/**
+ * @idx_ni:	index inode containing the @entry described by this context
+ * @entry:	index entry (points into @ir or @ia)
+ * @data:	index entry data (points into @entry)
+ * @data_len:	length in bytes of @data
+ * @is_in_root:	'true' if @entry is in @ir and 'false' if it is in @ia
+ * @ir:		index root if @is_in_root and NULL otherwise
+ * @actx:	attribute search context if @is_in_root and NULL otherwise
+ * @base_ni:	base inode if @is_in_root and NULL otherwise
+ * @ia:		index block if @is_in_root is 'false' and NULL otherwise
+ * @page:	page if @is_in_root is 'false' and NULL otherwise
+ *
+ * @idx_ni is the index inode this context belongs to.
+ *
+ * @entry is the index entry described by this context.  @data and @data_len
+ * are the index entry data and its length in bytes, respectively.  @data
+ * simply points into @entry.  This is probably what the user is interested in.
+ *
+ * If @is_in_root is 'true', @entry is in the index root attribute @ir described
+ * by the attribute search context @actx and the base inode @base_ni.  @ia and
+ * @page are NULL in this case.
+ *
+ * If @is_in_root is 'false', @entry is in the index allocation attribute and @ia
+ * and @page point to the index allocation block and the mapped, locked page it
+ * is in, respectively.  @ir, @actx and @base_ni are NULL in this case.
+ *
+ * To obtain a context call ntfs_index_ctx_get().
+ *
+ * We use this context to allow ntfs_index_lookup() to return the found index
+ * @entry and its @data without having to allocate a buffer and copy the @entry
+ * and/or its @data into it.
+ *
+ * When finished with the @entry and its @data, call ntfs_index_ctx_put() to
+ * free the context and other associated resources.
+ *
+ * If the index entry was modified, call flush_dcache_index_entry_page()
+ * immediately after the modification and either ntfs_index_entry_mark_dirty()
+ * or ntfs_index_entry_write() before the call to ntfs_index_ctx_put() to
+ * ensure that the changes are written to disk.
+ */
+typedef struct {
+	ntfs_inode *idx_ni;
+	INDEX_ENTRY *entry;
+	void *data;
+	u16 data_len;
+	bool is_in_root;
+	INDEX_ROOT *ir;
+	ntfs_attr_search_ctx *actx;
+	ntfs_inode *base_ni;
+	INDEX_ALLOCATION *ia;
+	struct page *page;
+} ntfs_index_context;
+
+extern ntfs_index_context *ntfs_index_ctx_get(ntfs_inode *idx_ni);
+extern void ntfs_index_ctx_put(ntfs_index_context *ictx);
+
+extern int ntfs_index_lookup(const void *key, const int key_len,
+		ntfs_index_context *ictx);
+
+#ifdef NTFS_RW
+
+/**
+ * ntfs_index_entry_flush_dcache_page - flush_dcache_page() for index entries
+ * @ictx:	ntfs index context describing the index entry
+ *
+ * Call flush_dcache_page() for the page in which an index entry resides.
+ *
+ * This must be called every time an index entry is modified, just after the
+ * modification.
+ *
+ * If the index entry is in the index root attribute, simply flush the page
+ * containing the mft record containing the index root attribute.
+ *
+ * If the index entry is in an index block belonging to the index allocation
+ * attribute, simply flush the page cache page containing the index block.
+ */
+static inline void ntfs_index_entry_flush_dcache_page(ntfs_index_context *ictx)
+{
+	if (ictx->is_in_root)
+		flush_dcache_mft_record_page(ictx->actx->ntfs_ino);
+	else
+		flush_dcache_page(ictx->page);
+}
+
+/**
+ * ntfs_index_entry_mark_dirty - mark an index entry dirty
+ * @ictx:	ntfs index context describing the index entry
+ *
+ * Mark the index entry described by the index entry context @ictx dirty.
+ *
+ * If the index entry is in the index root attribute, simply mark the mft
+ * record containing the index root attribute dirty.  This ensures the mft
+ * record, and hence the index root attribute, will be written out to disk
+ * later.
+ *
+ * If the index entry is in an index block belonging to the index allocation
+ * attribute, mark the buffers belonging to the index record as well as the
+ * page cache page the index block is in dirty.  This automatically marks the
+ * VFS inode of the ntfs index inode to which the index entry belongs dirty,
+ * too (I_DIRTY_PAGES) and this in turn ensures the page buffers, and hence the
+ * dirty index block, will be written out to disk later.
+ */
+static inline void ntfs_index_entry_mark_dirty(ntfs_index_context *ictx)
+{
+	if (ictx->is_in_root)
+		mark_mft_record_dirty(ictx->actx->ntfs_ino);
+	else
+		mark_ntfs_record_dirty(ictx->page,
+				(u8*)ictx->ia - (u8*)page_address(ictx->page));
+}
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_INDEX_H */

fs/ntfs/inode.h

@@ -0,0 +1,325 @@
+/*
+ * inode.h - Defines for inode structures NTFS Linux kernel driver. Part of
+ *	     the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2007 Anton Altaparmakov
+ * Copyright (c) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_INODE_H
+#define _LINUX_NTFS_INODE_H
+
+#include <linux/atomic.h>
+
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+
+#include "layout.h"
+#include "volume.h"
+#include "types.h"
+#include "runlist.h"
+#include "debug.h"
+
+typedef struct _ntfs_inode ntfs_inode;
+
+/*
+ * The NTFS in-memory inode structure. It is just used as an extension to the
+ * fields already provided in the VFS inode.
+ */
+struct _ntfs_inode {
+	rwlock_t size_lock;	/* Lock serializing access to inode sizes. */
+	s64 initialized_size;	/* Copy from the attribute record. */
+	s64 allocated_size;	/* Copy from the attribute record. */
+	unsigned long state;	/* NTFS specific flags describing this inode.
+				   See ntfs_inode_state_bits below. */
+	unsigned long mft_no;	/* Number of the mft record / inode. */
+	u16 seq_no;		/* Sequence number of the mft record. */
+	atomic_t count;		/* Inode reference count for book keeping. */
+	ntfs_volume *vol;	/* Pointer to the ntfs volume of this inode. */
+	/*
+	 * If NInoAttr() is true, the below fields describe the attribute which
+	 * this fake inode belongs to. The actual inode of this attribute is
+	 * pointed to by base_ntfs_ino and nr_extents is always set to -1 (see
+	 * below). For real inodes, we also set the type (AT_DATA for files and
+	 * AT_INDEX_ALLOCATION for directories), with the name = NULL and
+	 * name_len = 0 for files and name = I30 (global constant) and
+	 * name_len = 4 for directories.
+	 */
+	ATTR_TYPE type;	/* Attribute type of this fake inode. */
+	ntfschar *name;		/* Attribute name of this fake inode. */
+	u32 name_len;		/* Attribute name length of this fake inode. */
+	runlist runlist;	/* If state has the NI_NonResident bit set,
+				   the runlist of the unnamed data attribute
+				   (if a file) or of the index allocation
+				   attribute (directory) or of the attribute
+				   described by the fake inode (if NInoAttr()).
+				   If runlist.rl is NULL, the runlist has not
+				   been read in yet or has been unmapped. If
+				   NI_NonResident is clear, the attribute is
+				   resident (file and fake inode) or there is
+				   no $I30 index allocation attribute
+				   (small directory). In the latter case
+				   runlist.rl is always NULL.*/
+	/*
+	 * The following fields are only valid for real inodes and extent
+	 * inodes.
+	 */
+	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
+				   (un)map_mft_record*() functions. */
+	int page_ofs;		/* Offset into the page at which the mft record
+				   begins. This should only be touched by the
+				   (un)map_mft_record*() functions. */
+	/*
+	 * Attribute list support (only for use by the attribute lookup
+	 * functions). Setup during read_inode for all inodes with attribute
+	 * lists. Only valid if NI_AttrList is set in state, and attr_list_rl is
+	 * further only valid if NI_AttrListNonResident is set.
+	 */
+	u32 attr_list_size;	/* Length of attribute list value in bytes. */
+	u8 *attr_list;		/* Attribute list value itself. */
+	runlist attr_list_rl;	/* Run list for the attribute list value. */
+	union {
+		struct { /* It is a directory, $MFT, or an index inode. */
+			u32 block_size;		/* Size of an index block. */
+			u32 vcn_size;		/* Size of a vcn in this
+						   index. */
+			COLLATION_RULE collation_rule; /* The collation rule
+						   for the index. */
+			u8 block_size_bits; 	/* Log2 of the above. */
+			u8 vcn_size_bits;	/* Log2 of the above. */
+		} index;
+		struct { /* It is a compressed/sparse file/attribute inode. */
+			s64 size;		/* Copy of compressed_size from
+						   $DATA. */
+			u32 block_size;		/* Size of a compression block
+						   (cb). */
+			u8 block_size_bits;	/* Log2 of the size of a cb. */
+			u8 block_clusters;	/* Number of clusters per cb. */
+		} compressed;
+	} itype;
+	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
+			   inodes describing an attribute this is -1. */
+	union {		/* This union is only used if nr_extents != 0. */
+		ntfs_inode **extent_ntfs_inos;	/* For nr_extents > 0, array of
+						   the ntfs inodes of the extent
+						   mft records belonging to
+						   this base inode which have
+						   been loaded. */
+		ntfs_inode *base_ntfs_ino;	/* For nr_extents == -1, the
+						   ntfs inode of the base mft
+						   record. For fake inodes, the
+						   real (base) inode to which
+						   the attribute belongs. */
+	} ext;
+};
+
+/*
+ * Defined bits for the state field in the ntfs_inode structure.
+ * (f) = files only, (d) = directories only, (a) = attributes/fake inodes only
+ */
+typedef enum {
+	NI_Dirty,		/* 1: Mft record needs to be written to disk. */
+	NI_AttrList,		/* 1: Mft record contains an attribute list. */
+	NI_AttrListNonResident,	/* 1: Attribute list is non-resident. Implies
+				      NI_AttrList is set. */
+
+	NI_Attr,		/* 1: Fake inode for attribute i/o.
+				   0: Real inode or extent inode. */
+
+	NI_MstProtected,	/* 1: Attribute is protected by MST fixups.
+				   0: Attribute is not protected by fixups. */
+	NI_NonResident,		/* 1: Unnamed data attr is non-resident (f).
+				   1: Attribute is non-resident (a). */
+	NI_IndexAllocPresent = NI_NonResident,	/* 1: $I30 index alloc attr is
+						   present (d). */
+	NI_Compressed,		/* 1: Unnamed data attr is compressed (f).
+				   1: Create compressed files by default (d).
+				   1: Attribute is compressed (a). */
+	NI_Encrypted,		/* 1: Unnamed data attr is encrypted (f).
+				   1: Create encrypted files by default (d).
+				   1: Attribute is encrypted (a). */
+	NI_Sparse,		/* 1: Unnamed data attr is sparse (f).
+				   1: Create sparse files by default (d).
+				   1: Attribute is sparse (a). */
+	NI_SparseDisabled,	/* 1: May not create sparse regions. */
+	NI_TruncateFailed,	/* 1: Last ntfs_truncate() call failed. */
+} ntfs_inode_state_bits;
+
+/*
+ * NOTE: We should be adding dirty mft records to a list somewhere and they
+ * should be independent of the (ntfs/vfs) inode structure so that an inode can
+ * be removed but the record can be left dirty for syncing later.
+ */
+
+/*
+ * Macro tricks to expand the NInoFoo(), NInoSetFoo(), and NInoClearFoo()
+ * functions.
+ */
+#define NINO_FNS(flag)					\
+static inline int NIno##flag(ntfs_inode *ni)		\
+{							\
+	return test_bit(NI_##flag, &(ni)->state);	\
+}							\
+static inline void NInoSet##flag(ntfs_inode *ni)	\
+{							\
+	set_bit(NI_##flag, &(ni)->state);		\
+}							\
+static inline void NInoClear##flag(ntfs_inode *ni)	\
+{							\
+	clear_bit(NI_##flag, &(ni)->state);		\
+}
+
+/*
+ * As above for NInoTestSetFoo() and NInoTestClearFoo().
+ */
+#define TAS_NINO_FNS(flag)					\
+static inline int NInoTestSet##flag(ntfs_inode *ni)		\
+{								\
+	return test_and_set_bit(NI_##flag, &(ni)->state);	\
+}								\
+static inline int NInoTestClear##flag(ntfs_inode *ni)		\
+{								\
+	return test_and_clear_bit(NI_##flag, &(ni)->state);	\
+}
+
+/* Emit the ntfs inode bitops functions. */
+NINO_FNS(Dirty)
+TAS_NINO_FNS(Dirty)
+NINO_FNS(AttrList)
+NINO_FNS(AttrListNonResident)
+NINO_FNS(Attr)
+NINO_FNS(MstProtected)
+NINO_FNS(NonResident)
+NINO_FNS(IndexAllocPresent)
+NINO_FNS(Compressed)
+NINO_FNS(Encrypted)
+NINO_FNS(Sparse)
+NINO_FNS(SparseDisabled)
+NINO_FNS(TruncateFailed)
+
+/*
+ * The full structure containing a ntfs_inode and a vfs struct inode. Used for
+ * all real and fake inodes but not for extent inodes which lack the vfs struct
+ * inode.
+ */
+typedef struct {
+	ntfs_inode ntfs_inode;
+	struct inode vfs_inode;		/* The vfs inode structure. */
+} big_ntfs_inode;
+
+/**
+ * NTFS_I - return the ntfs inode given a vfs inode
+ * @inode:	VFS inode
+ *
+ * NTFS_I() returns the ntfs inode associated with the VFS @inode.
+ */
+static inline ntfs_inode *NTFS_I(struct inode *inode)
+{
+	return (ntfs_inode *)list_entry(inode, big_ntfs_inode, vfs_inode);
+}
+
+static inline struct inode *VFS_I(ntfs_inode *ni)
+{
+	return &((big_ntfs_inode *)ni)->vfs_inode;
+}
+
+/**
+ * ntfs_attr - ntfs in memory attribute structure
+ * @mft_no:	mft record number of the base mft record of this attribute
+ * @name:	Unicode name of the attribute (NULL if unnamed)
+ * @name_len:	length of @name in Unicode characters (0 if unnamed)
+ * @type:	attribute type (see layout.h)
+ *
+ * This structure exists only to provide a small structure for the
+ * ntfs_{attr_}iget()/ntfs_test_inode()/ntfs_init_locked_inode() mechanism.
+ *
+ * NOTE: Elements are ordered by size to make the structure as compact as
+ * possible on all architectures.
+ */
+typedef struct {
+	unsigned long mft_no;
+	ntfschar *name;
+	u32 name_len;
+	ATTR_TYPE type;
+} ntfs_attr;
+
+typedef int (*test_t)(struct inode *, void *);
+
+extern int ntfs_test_inode(struct inode *vi, ntfs_attr *na);
+
+extern struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no);
+extern struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type,
+		ntfschar *name, u32 name_len);
+extern struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name,
+		u32 name_len);
+
+extern struct inode *ntfs_alloc_big_inode(struct super_block *sb);
+extern void ntfs_destroy_big_inode(struct inode *inode);
+extern void ntfs_evict_big_inode(struct inode *vi);
+
+extern void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni);
+
+static inline void ntfs_init_big_inode(struct inode *vi)
+{
+	ntfs_inode *ni = NTFS_I(vi);
+
+	ntfs_debug("Entering.");
+	__ntfs_init_inode(vi->i_sb, ni);
+	ni->mft_no = vi->i_ino;
+}
+
+extern ntfs_inode *ntfs_new_extent_inode(struct super_block *sb,
+		unsigned long mft_no);
+extern void ntfs_clear_extent_inode(ntfs_inode *ni);
+
+extern int ntfs_read_inode_mount(struct inode *vi);
+
+extern int ntfs_show_options(struct seq_file *sf, struct dentry *root);
+
+#ifdef NTFS_RW
+
+extern int ntfs_truncate(struct inode *vi);
+extern void ntfs_truncate_vfs(struct inode *vi);
+
+extern int ntfs_setattr(struct dentry *dentry, struct iattr *attr);
+
+extern int __ntfs_write_inode(struct inode *vi, int sync);
+
+static inline void ntfs_commit_inode(struct inode *vi)
+{
+	if (!is_bad_inode(vi))
+		__ntfs_write_inode(vi, 1);
+	return;
+}
+
+#else
+
+static inline void ntfs_truncate_vfs(struct inode *vi) {}
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_INODE_H */

fs/ntfs/lcnalloc.h

@@ -0,0 +1,145 @@
+/*
+ * lcnalloc.h - Exports for NTFS kernel cluster (de)allocation.  Part of the
+ *		Linux-NTFS project.
+ *
+ * Copyright (c) 2004-2005 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_LCNALLOC_H
+#define _LINUX_NTFS_LCNALLOC_H
+
+#ifdef NTFS_RW
+
+#include <linux/fs.h>
+
+#include "attrib.h"
+#include "types.h"
+#include "inode.h"
+#include "runlist.h"
+#include "volume.h"
+
+typedef enum {
+	FIRST_ZONE	= 0,	/* For sanity checking. */
+	MFT_ZONE	= 0,	/* Allocate from $MFT zone. */
+	DATA_ZONE	= 1,	/* Allocate from $DATA zone. */
+	LAST_ZONE	= 1,	/* For sanity checking. */
+} NTFS_CLUSTER_ALLOCATION_ZONES;
+
+extern runlist_element *ntfs_cluster_alloc(ntfs_volume *vol,
+		const VCN start_vcn, const s64 count, const LCN start_lcn,
+		const NTFS_CLUSTER_ALLOCATION_ZONES zone,
+		const bool is_extension);
+
+extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
+		s64 count, ntfs_attr_search_ctx *ctx, const bool is_rollback);
+
+/**
+ * ntfs_cluster_free - free clusters on an ntfs volume
+ * @ni:		ntfs inode whose runlist describes the clusters to free
+ * @start_vcn:	vcn in the runlist of @ni at which to start freeing clusters
+ * @count:	number of clusters to free or -1 for all clusters
+ * @ctx:	active attribute search context if present or NULL if not
+ *
+ * Free @count clusters starting at the cluster @start_vcn in the runlist
+ * described by the ntfs inode @ni.
+ *
+ * If @count is -1, all clusters from @start_vcn to the end of the runlist are
+ * deallocated.  Thus, to completely free all clusters in a runlist, use
+ * @start_vcn = 0 and @count = -1.
+ *
+ * If @ctx is specified, it is an active search context of @ni and its base mft
+ * record.  This is needed when ntfs_cluster_free() encounters unmapped runlist
+ * fragments and allows their mapping.  If you do not have the mft record
+ * mapped, you can specify @ctx as NULL and ntfs_cluster_free() will perform
+ * the necessary mapping and unmapping.
+ *
+ * Note, ntfs_cluster_free() saves the state of @ctx on entry and restores it
+ * before returning.  Thus, @ctx will be left pointing to the same attribute on
+ * return as on entry.  However, the actual pointers in @ctx may point to
+ * different memory locations on return, so you must remember to reset any
+ * cached pointers from the @ctx, i.e. after the call to ntfs_cluster_free(),
+ * you will probably want to do:
+ *	m = ctx->mrec;
+ *	a = ctx->attr;
+ * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
+ * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
+ *
+ * Note, ntfs_cluster_free() does not modify the runlist, so you have to remove
+ * from the runlist or mark sparse the freed runs later.
+ *
+ * Return the number of deallocated clusters (not counting sparse ones) on
+ * success and -errno on error.
+ *
+ * WARNING: If @ctx is supplied, regardless of whether success or failure is
+ *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
+ *	    is no longer valid, i.e. you need to either call
+ *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
+ *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
+ *	    why the mapping of the old inode failed.
+ *
+ * Locking: - The runlist described by @ni must be locked for writing on entry
+ *	      and is locked on return.  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.
+ *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
+ *	      entry and it will be left unmapped on return.
+ *	    - If @ctx is not NULL, the base mft record must be mapped on entry
+ *	      and it will be left mapped on return.
+ */
+static inline s64 ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
+		s64 count, ntfs_attr_search_ctx *ctx)
+{
+	return __ntfs_cluster_free(ni, start_vcn, count, ctx, false);
+}
+
+extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
+		const runlist_element *rl);
+
+/**
+ * ntfs_cluster_free_from_rl - free clusters from runlist
+ * @vol:	mounted ntfs volume on which to free the clusters
+ * @rl:		runlist describing the clusters to free
+ *
+ * Free all the clusters described by the runlist @rl on the volume @vol.  In
+ * the case of an error being returned, at least some of the clusters were not
+ * freed.
+ *
+ * Return 0 on success and -errno on error.
+ *
+ * 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)
+{
+	int ret;
+
+	down_write(&vol->lcnbmp_lock);
+	ret = ntfs_cluster_free_from_rl_nolock(vol, rl);
+	up_write(&vol->lcnbmp_lock);
+	return ret;
+}
+
+#endif /* NTFS_RW */
+
+#endif /* defined _LINUX_NTFS_LCNALLOC_H */

fs/ntfs/logfile.c

@@ -0,0 +1,863 @@
+/*
+ * logfile.c - NTFS kernel journal handling. Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2002-2007 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifdef NTFS_RW
+
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/buffer_head.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "attrib.h"
+#include "aops.h"
+#include "debug.h"
+#include "logfile.h"
+#include "malloc.h"
+#include "volume.h"
+#include "ntfs.h"
+
+/**
+ * ntfs_check_restart_page_header - check the page header for consistency
+ * @vi:		$LogFile inode to which the restart page header belongs
+ * @rp:		restart page header to check
+ * @pos:	position in @vi at which the restart page header resides
+ *
+ * Check the restart page header @rp for consistency and return 'true' if it is
+ * consistent and 'false' otherwise.
+ *
+ * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
+ * require the full restart page.
+ */
+static bool ntfs_check_restart_page_header(struct inode *vi,
+		RESTART_PAGE_HEADER *rp, s64 pos)
+{
+	u32 logfile_system_page_size, logfile_log_page_size;
+	u16 ra_ofs, usa_count, usa_ofs, usa_end = 0;
+	bool have_usa = true;
+
+	ntfs_debug("Entering.");
+	/*
+	 * If the system or log page sizes are smaller than the ntfs block size
+	 * or either is not a power of 2 we cannot handle this log file.
+	 */
+	logfile_system_page_size = le32_to_cpu(rp->system_page_size);
+	logfile_log_page_size = le32_to_cpu(rp->log_page_size);
+	if (logfile_system_page_size < NTFS_BLOCK_SIZE ||
+			logfile_log_page_size < NTFS_BLOCK_SIZE ||
+			logfile_system_page_size &
+			(logfile_system_page_size - 1) ||
+			!is_power_of_2(logfile_log_page_size)) {
+		ntfs_error(vi->i_sb, "$LogFile uses unsupported page size.");
+		return false;
+	}
+	/*
+	 * We must be either at !pos (1st restart page) or at pos = system page
+	 * size (2nd restart page).
+	 */
+	if (pos && pos != logfile_system_page_size) {
+		ntfs_error(vi->i_sb, "Found restart area in incorrect "
+				"position in $LogFile.");
+		return false;
+	}
+	/* We only know how to handle version 1.1. */
+	if (sle16_to_cpu(rp->major_ver) != 1 ||
+			sle16_to_cpu(rp->minor_ver) != 1) {
+		ntfs_error(vi->i_sb, "$LogFile version %i.%i is not "
+				"supported.  (This driver supports version "
+				"1.1 only.)", (int)sle16_to_cpu(rp->major_ver),
+				(int)sle16_to_cpu(rp->minor_ver));
+		return false;
+	}
+	/*
+	 * If chkdsk has been run the restart page may not be protected by an
+	 * update sequence array.
+	 */
+	if (ntfs_is_chkd_record(rp->magic) && !le16_to_cpu(rp->usa_count)) {
+		have_usa = false;
+		goto skip_usa_checks;
+	}
+	/* Verify the size of the update sequence array. */
+	usa_count = 1 + (logfile_system_page_size >> NTFS_BLOCK_SIZE_BITS);
+	if (usa_count != le16_to_cpu(rp->usa_count)) {
+		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
+				"inconsistent update sequence array count.");
+		return false;
+	}
+	/* Verify the position of the update sequence array. */
+	usa_ofs = le16_to_cpu(rp->usa_ofs);
+	usa_end = usa_ofs + usa_count * sizeof(u16);
+	if (usa_ofs < sizeof(RESTART_PAGE_HEADER) ||
+			usa_end > NTFS_BLOCK_SIZE - sizeof(u16)) {
+		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
+				"inconsistent update sequence array offset.");
+		return false;
+	}
+skip_usa_checks:
+	/*
+	 * Verify the position of the restart area.  It must be:
+	 *	- aligned to 8-byte boundary,
+	 *	- after the update sequence array, and
+	 *	- within the system page size.
+	 */
+	ra_ofs = le16_to_cpu(rp->restart_area_offset);
+	if (ra_ofs & 7 || (have_usa ? ra_ofs < usa_end :
+			ra_ofs < sizeof(RESTART_PAGE_HEADER)) ||
+			ra_ofs > logfile_system_page_size) {
+		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
+				"inconsistent restart area offset.");
+		return false;
+	}
+	/*
+	 * Only restart pages modified by chkdsk are allowed to have chkdsk_lsn
+	 * set.
+	 */
+	if (!ntfs_is_chkd_record(rp->magic) && sle64_to_cpu(rp->chkdsk_lsn)) {
+		ntfs_error(vi->i_sb, "$LogFile restart page is not modified "
+				"by chkdsk but a chkdsk LSN is specified.");
+		return false;
+	}
+	ntfs_debug("Done.");
+	return true;
+}
+
+/**
+ * ntfs_check_restart_area - check the restart area for consistency
+ * @vi:		$LogFile inode to which the restart page belongs
+ * @rp:		restart page whose restart area to check
+ *
+ * Check the restart area of the restart page @rp for consistency and return
+ * 'true' if it is consistent and 'false' otherwise.
+ *
+ * This function assumes that the restart page header has already been
+ * consistency checked.
+ *
+ * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
+ * require the full restart page.
+ */
+static bool ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp)
+{
+	u64 file_size;
+	RESTART_AREA *ra;
+	u16 ra_ofs, ra_len, ca_ofs;
+	u8 fs_bits;
+
+	ntfs_debug("Entering.");
+	ra_ofs = le16_to_cpu(rp->restart_area_offset);
+	ra = (RESTART_AREA*)((u8*)rp + ra_ofs);
+	/*
+	 * Everything before ra->file_size must be before the first word
+	 * protected by an update sequence number.  This ensures that it is
+	 * safe to access ra->client_array_offset.
+	 */
+	if (ra_ofs + offsetof(RESTART_AREA, file_size) >
+			NTFS_BLOCK_SIZE - sizeof(u16)) {
+		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
+				"inconsistent file offset.");
+		return false;
+	}
+	/*
+	 * Now that we can access ra->client_array_offset, make sure everything
+	 * up to the log client array is before the first word protected by an
+	 * update sequence number.  This ensures we can access all of the
+	 * restart area elements safely.  Also, the client array offset must be
+	 * aligned to an 8-byte boundary.
+	 */
+	ca_ofs = le16_to_cpu(ra->client_array_offset);
+	if (((ca_ofs + 7) & ~7) != ca_ofs ||
+			ra_ofs + ca_ofs > NTFS_BLOCK_SIZE - sizeof(u16)) {
+		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
+				"inconsistent client array offset.");
+		return false;
+	}
+	/*
+	 * The restart area must end within the system page size both when
+	 * calculated manually and as specified by ra->restart_area_length.
+	 * Also, the calculated length must not exceed the specified length.
+	 */
+	ra_len = ca_ofs + le16_to_cpu(ra->log_clients) *
+			sizeof(LOG_CLIENT_RECORD);
+	if (ra_ofs + ra_len > le32_to_cpu(rp->system_page_size) ||
+			ra_ofs + le16_to_cpu(ra->restart_area_length) >
+			le32_to_cpu(rp->system_page_size) ||
+			ra_len > le16_to_cpu(ra->restart_area_length)) {
+		ntfs_error(vi->i_sb, "$LogFile restart area is out of bounds "
+				"of the system page size specified by the "
+				"restart page header and/or the specified "
+				"restart area length is inconsistent.");
+		return false;
+	}
+	/*
+	 * The ra->client_free_list and ra->client_in_use_list must be either
+	 * LOGFILE_NO_CLIENT or less than ra->log_clients or they are
+	 * overflowing the client array.
+	 */
+	if ((ra->client_free_list != LOGFILE_NO_CLIENT &&
+			le16_to_cpu(ra->client_free_list) >=
+			le16_to_cpu(ra->log_clients)) ||
+			(ra->client_in_use_list != LOGFILE_NO_CLIENT &&
+			le16_to_cpu(ra->client_in_use_list) >=
+			le16_to_cpu(ra->log_clients))) {
+		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
+				"overflowing client free and/or in use lists.");
+		return false;
+	}
+	/*
+	 * Check ra->seq_number_bits against ra->file_size for consistency.
+	 * We cannot just use ffs() because the file size is not a power of 2.
+	 */
+	file_size = (u64)sle64_to_cpu(ra->file_size);
+	fs_bits = 0;
+	while (file_size) {
+		file_size >>= 1;
+		fs_bits++;
+	}
+	if (le32_to_cpu(ra->seq_number_bits) != 67 - fs_bits) {
+		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
+				"inconsistent sequence number bits.");
+		return false;
+	}
+	/* The log record header length must be a multiple of 8. */
+	if (((le16_to_cpu(ra->log_record_header_length) + 7) & ~7) !=
+			le16_to_cpu(ra->log_record_header_length)) {
+		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
+				"inconsistent log record header length.");
+		return false;
+	}
+	/* Dito for the log page data offset. */
+	if (((le16_to_cpu(ra->log_page_data_offset) + 7) & ~7) !=
+			le16_to_cpu(ra->log_page_data_offset)) {
+		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
+				"inconsistent log page data offset.");
+		return false;
+	}
+	ntfs_debug("Done.");
+	return true;
+}
+
+/**
+ * ntfs_check_log_client_array - check the log client array for consistency
+ * @vi:		$LogFile inode to which the restart page belongs
+ * @rp:		restart page whose log client array to check
+ *
+ * Check the log client array of the restart page @rp for consistency and
+ * return 'true' if it is consistent and 'false' otherwise.
+ *
+ * This function assumes that the restart page header and the restart area have
+ * already been consistency checked.
+ *
+ * Unlike ntfs_check_restart_page_header() and ntfs_check_restart_area(), this
+ * function needs @rp->system_page_size bytes in @rp, i.e. it requires the full
+ * restart page and the page must be multi sector transfer deprotected.
+ */
+static bool ntfs_check_log_client_array(struct inode *vi,
+		RESTART_PAGE_HEADER *rp)
+{
+	RESTART_AREA *ra;
+	LOG_CLIENT_RECORD *ca, *cr;
+	u16 nr_clients, idx;
+	bool in_free_list, idx_is_first;
+
+	ntfs_debug("Entering.");
+	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
+	ca = (LOG_CLIENT_RECORD*)((u8*)ra +
+			le16_to_cpu(ra->client_array_offset));
+	/*
+	 * Check the ra->client_free_list first and then check the
+	 * ra->client_in_use_list.  Check each of the log client records in
+	 * each of the lists and check that the array does not overflow the
+	 * ra->log_clients value.  Also keep track of the number of records
+	 * visited as there cannot be more than ra->log_clients records and
+	 * that way we detect eventual loops in within a list.
+	 */
+	nr_clients = le16_to_cpu(ra->log_clients);
+	idx = le16_to_cpu(ra->client_free_list);
+	in_free_list = true;
+check_list:
+	for (idx_is_first = true; idx != LOGFILE_NO_CLIENT_CPU; nr_clients--,
+			idx = le16_to_cpu(cr->next_client)) {
+		if (!nr_clients || idx >= le16_to_cpu(ra->log_clients))
+			goto err_out;
+		/* Set @cr to the current log client record. */
+		cr = ca + idx;
+		/* The first log client record must not have a prev_client. */
+		if (idx_is_first) {
+			if (cr->prev_client != LOGFILE_NO_CLIENT)
+				goto err_out;
+			idx_is_first = false;
+		}
+	}
+	/* Switch to and check the in use list if we just did the free list. */
+	if (in_free_list) {
+		in_free_list = false;
+		idx = le16_to_cpu(ra->client_in_use_list);
+		goto check_list;
+	}
+	ntfs_debug("Done.");
+	return true;
+err_out:
+	ntfs_error(vi->i_sb, "$LogFile log client array is corrupt.");
+	return false;
+}
+
+/**
+ * ntfs_check_and_load_restart_page - check the restart page for consistency
+ * @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:	[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 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.
+ *
+ * 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 success *@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 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, 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 -EINVAL;
+	}
+	/* Check the restart area for consistency. */
+	if (!ntfs_check_restart_area(vi, rp)) {
+		/* Error output already done inside the function. */
+		return -EINVAL;
+	}
+	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
+	/*
+	 * Allocate a buffer to store the whole restart page so we can multi
+	 * sector transfer deprotect it.
+	 */
+	trp = ntfs_malloc_nofs(le32_to_cpu(rp->system_page_size));
+	if (!trp) {
+		ntfs_error(vi->i_sb, "Failed to allocate memory for $LogFile "
+				"restart page buffer.");
+		return -ENOMEM;
+	}
+	/*
+	 * Read the whole of the restart page into the buffer.  If it fits
+	 * completely inside @rp, just copy it from there.  Otherwise map all
+	 * the required pages and copy the data from them.
+	 */
+	size = PAGE_CACHE_SIZE - (pos & ~PAGE_CACHE_MASK);
+	if (size >= le32_to_cpu(rp->system_page_size)) {
+		memcpy(trp, rp, le32_to_cpu(rp->system_page_size));
+	} else {
+		pgoff_t idx;
+		struct page *page;
+		int have_read, to_read;
+
+		/* First copy what we already have in @rp. */
+		memcpy(trp, rp, size);
+		/* Copy the remaining data one page at a time. */
+		have_read = size;
+		to_read = le32_to_cpu(rp->system_page_size) - size;
+		idx = (pos + size) >> PAGE_CACHE_SHIFT;
+		BUG_ON((pos + size) & ~PAGE_CACHE_MASK);
+		do {
+			page = ntfs_map_page(vi->i_mapping, idx);
+			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);
+			memcpy((u8*)trp + have_read, page_address(page), size);
+			ntfs_unmap_page(page);
+			have_read += size;
+			to_read -= size;
+			idx++;
+		} while (to_read > 0);
+	}
+	/*
+	 * Perform the multi sector transfer deprotection on the buffer if the
+	 * restart page is protected.
+	 */
+	if ((!ntfs_is_chkd_record(trp->magic) || le16_to_cpu(trp->usa_count))
+			&& post_read_mst_fixup((NTFS_RECORD*)trp,
+			le32_to_cpu(rp->system_page_size))) {
+		/*
+		 * 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);
+	}
+	ntfs_debug("Done.");
+	if (wrp)
+		*wrp = trp;
+	else {
+err_out:
+		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.  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.
+ *
+ * Note that the MstProtected flag is not set on the $LogFile inode and hence
+ * when reading pages they are not deprotected.  This is because we do not know
+ * 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, RESTART_PAGE_HEADER **rp)
+{
+	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, err;
+	bool logfile_is_empty = true;
+	u8 log_page_bits;
+
+	ntfs_debug("Entering.");
+	/* An empty $LogFile must have been clean before it got emptied. */
+	if (NVolLogFileEmpty(vol))
+		goto is_empty;
+	size = i_size_read(log_vi);
+	/* Make sure the file doesn't exceed the maximum allowed size. */
+	if (size > MaxLogFileSize)
+		size = MaxLogFileSize;
+	/*
+	 * Truncate size to a multiple of the page cache size or the default
+	 * log page size if the page cache size is between the default log page
+	 * log page size if the page cache size is between the default log page
+	 * size and twice that.
+	 */
+	if (PAGE_CACHE_SIZE >= DefaultLogPageSize && PAGE_CACHE_SIZE <=
+			DefaultLogPageSize * 2)
+		log_page_size = DefaultLogPageSize;
+	else
+		log_page_size = PAGE_CACHE_SIZE;
+	log_page_mask = log_page_size - 1;
+	/*
+	 * Use ntfs_ffs() instead of ffs() to enable the compiler to
+	 * optimize log_page_size and log_page_bits into constants.
+	 */
+	log_page_bits = ntfs_ffs(log_page_size) - 1;
+	size &= ~(s64)(log_page_size - 1);
+	/*
+	 * Ensure the log file is big enough to store at least the two restart
+	 * pages and the minimum number of log record pages.
+	 */
+	if (size < log_page_size * 2 || (size - log_page_size * 2) >>
+			log_page_bits < MinLogRecordPages) {
+		ntfs_error(vol->sb, "$LogFile is too small.");
+		return false;
+	}
+	/*
+	 * Read through the file looking for a restart page.  Since the restart
+	 * page header is at the beginning of a page we only need to search at
+	 * what could be the beginning of a page (for each page size) rather
+	 * than scanning the whole file byte by byte.  If all potential places
+	 * contain empty and uninitialzed records, the log file can be assumed
+	 * to be empty.
+	 */
+	for (pos = 0; pos < size; pos <<= 1) {
+		pgoff_t idx = pos >> PAGE_CACHE_SHIFT;
+		if (!page || page->index != idx) {
+			if (page)
+				ntfs_unmap_page(page);
+			page = ntfs_map_page(mapping, idx);
+			if (IS_ERR(page)) {
+				ntfs_error(vol->sb, "Error mapping $LogFile "
+						"page (index %lu).", idx);
+				goto err_out;
+			}
+		}
+		kaddr = (u8*)page_address(page) + (pos & ~PAGE_CACHE_MASK);
+		/*
+		 * A non-empty block means the logfile is not empty while an
+		 * empty block after a non-empty block has been encountered
+		 * means we are done.
+		 */
+		if (!ntfs_is_empty_recordp((le32*)kaddr))
+			logfile_is_empty = false;
+		else if (!logfile_is_empty)
+			break;
+		/*
+		 * A log record page means there cannot be a restart page after
+		 * this so no need to continue searching.
+		 */
+		if (ntfs_is_rcrd_recordp((le32*)kaddr))
+			break;
+		/* If not a (modified by chkdsk) restart page, continue. */
+		if (!ntfs_is_rstr_recordp((le32*)kaddr) &&
+				!ntfs_is_chkd_recordp((le32*)kaddr)) {
+			if (!pos)
+				pos = NTFS_BLOCK_SIZE >> 1;
+			continue;
+		}
+		/*
+		 * Check the (modified by chkdsk) restart page for consistency
+		 * and get a copy of the complete multi sector transfer
+		 * deprotected restart page.
+		 */
+		err = ntfs_check_and_load_restart_page(log_vi,
+				(RESTART_PAGE_HEADER*)kaddr, pos,
+				!rstr1_ph ? &rstr1_ph : &rstr2_ph,
+				!rstr1_ph ? &rstr1_lsn : &rstr2_lsn);
+		if (!err) {
+			/*
+			 * If we have now found the first (modified by chkdsk)
+			 * restart page, continue looking for the second one.
+			 */
+			if (!pos) {
+				pos = NTFS_BLOCK_SIZE >> 1;
+				continue;
+			}
+			/*
+			 * We have now found the second (modified by chkdsk)
+			 * restart page, so we can stop looking.
+			 */
+			break;
+		}
+		/*
+		 * Error output already done inside the function.  Note, we do
+		 * not abort if the restart page was invalid as we might still
+		 * find a valid one further in the file.
+		 */
+		if (err != -EINVAL) {
+			ntfs_unmap_page(page);
+			goto err_out;
+		}
+		/* Continue looking. */
+		if (!pos)
+			pos = NTFS_BLOCK_SIZE >> 1;
+	}
+	if (page)
+		ntfs_unmap_page(page);
+	if (logfile_is_empty) {
+		NVolSetLogFileEmpty(vol);
+is_empty:
+		ntfs_debug("Done.  ($LogFile is empty.)");
+		return true;
+	}
+	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_debug("Using second restart page as it is more "
+					"recent.");
+			ntfs_free(rstr1_ph);
+			rstr1_ph = rstr2_ph;
+			/* rstr1_lsn = rstr2_lsn; */
+		} else {
+			ntfs_debug("Using first restart page as it is more "
+					"recent.");
+			ntfs_free(rstr2_ph);
+		}
+		rstr2_ph = NULL;
+	}
+	/* All consistency checks passed. */
+	if (rp)
+		*rp = rstr1_ph;
+	else
+		ntfs_free(rstr1_ph);
+	ntfs_debug("Done.");
+	return true;
+err_out:
+	if (rstr1_ph)
+		ntfs_free(rstr1_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.
+ *
+ * At present we only look at the two restart pages and ignore the log record
+ * pages.  This is a little bit crude in that there will be a very small number
+ * of cases where we think that a volume is dirty when in fact it is clean.
+ * This should only affect volumes that have not been shutdown cleanly but did
+ * not have any pending, non-check-pointed i/o, i.e. they were completely idle
+ * at least for the five seconds preceding the unclean shutdown.
+ *
+ * This function assumes that the $LogFile journal has already been consistency
+ * checked by a call to ntfs_check_logfile() and in particular if the $LogFile
+ * 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, const RESTART_PAGE_HEADER *rp)
+{
+	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
+	RESTART_AREA *ra;
+
+	ntfs_debug("Entering.");
+	/* An empty $LogFile must have been clean before it got emptied. */
+	if (NVolLogFileEmpty(vol)) {
+		ntfs_debug("Done.  ($LogFile is empty.)");
+		return true;
+	}
+	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;
+	}
+	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
+	 * have the RESTART_VOLUME_IS_CLEAN bit set in the restart area flags,
+	 * we assume there was an unclean shutdown.
+	 */
+	if (ra->client_in_use_list != LOGFILE_NO_CLIENT &&
+			!(ra->flags & RESTART_VOLUME_IS_CLEAN)) {
+		ntfs_debug("Done.  $LogFile indicates a dirty shutdown.");
+		return false;
+	}
+	/* $LogFile indicates a clean shutdown. */
+	ntfs_debug("Done.  $LogFile indicates a clean shutdown.");
+	return true;
+}
+
+/**
+ * ntfs_empty_logfile - empty the contents of the $LogFile journal
+ * @log_vi:	struct inode of loaded journal $LogFile to empty
+ *
+ * Empty the contents of the $LogFile journal @log_vi and return 'true' on
+ * success and 'false' on error.
+ *
+ * This function assumes that the $LogFile journal has already been consistency
+ * checked by a call to ntfs_check_logfile() and that ntfs_is_logfile_clean()
+ * has been used to ensure that the $LogFile is clean.
+ */
+bool ntfs_empty_logfile(struct inode *log_vi)
+{
+	VCN vcn, end_vcn;
+	ntfs_inode *log_ni = NTFS_I(log_vi);
+	ntfs_volume *vol = log_ni->vol;
+	struct super_block *sb = vol->sb;
+	runlist_element *rl;
+	unsigned long flags;
+	unsigned block_size, block_size_bits;
+	int err;
+	bool should_wait = true;
+
+	ntfs_debug("Entering.");
+	if (NVolLogFileEmpty(vol)) {
+		ntfs_debug("Done.");
+		return true;
+	}
+	/*
+	 * We cannot use ntfs_attr_set() because we may be still in the middle
+	 * of a mount operation.  Thus we do the emptying by hand by first
+	 * zapping the page cache pages for the $LogFile/$DATA attribute and
+	 * then emptying each of the buffers in each of the clusters specified
+	 * by the runlist by hand.
+	 */
+	block_size = sb->s_blocksize;
+	block_size_bits = sb->s_blocksize_bits;
+	vcn = 0;
+	read_lock_irqsave(&log_ni->size_lock, flags);
+	end_vcn = (log_ni->initialized_size + vol->cluster_size_mask) >>
+			vol->cluster_size_bits;
+	read_unlock_irqrestore(&log_ni->size_lock, flags);
+	truncate_inode_pages(log_vi->i_mapping, 0);
+	down_write(&log_ni->runlist.lock);
+	rl = log_ni->runlist.rl;
+	if (unlikely(!rl || vcn < rl->vcn || !rl->length)) {
+map_vcn:
+		err = ntfs_map_runlist_nolock(log_ni, vcn, NULL);
+		if (err) {
+			ntfs_error(sb, "Failed to map runlist fragment (error "
+					"%d).", -err);
+			goto err;
+		}
+		rl = log_ni->runlist.rl;
+		BUG_ON(!rl || vcn < rl->vcn || !rl->length);
+	}
+	/* Seek to the runlist element containing @vcn. */
+	while (rl->length && vcn >= rl[1].vcn)
+		rl++;
+	do {
+		LCN lcn;
+		sector_t block, end_block;
+		s64 len;
+
+		/*
+		 * If this run is not mapped map it now and start again as the
+		 * runlist will have been updated.
+		 */
+		lcn = rl->lcn;
+		if (unlikely(lcn == LCN_RL_NOT_MAPPED)) {
+			vcn = rl->vcn;
+			goto map_vcn;
+		}
+		/* If this run is not valid abort with an error. */
+		if (unlikely(!rl->length || lcn < LCN_HOLE))
+			goto rl_err;
+		/* Skip holes. */
+		if (lcn == LCN_HOLE)
+			continue;
+		block = lcn << vol->cluster_size_bits >> block_size_bits;
+		len = rl->length;
+		if (rl[1].vcn > end_vcn)
+			len = end_vcn - rl->vcn;
+		end_block = (lcn + len) << vol->cluster_size_bits >>
+				block_size_bits;
+		/* Iterate over the blocks in the run and empty them. */
+		do {
+			struct buffer_head *bh;
+
+			/* Obtain the buffer, possibly not uptodate. */
+			bh = sb_getblk(sb, block);
+			BUG_ON(!bh);
+			/* Setup buffer i/o submission. */
+			lock_buffer(bh);
+			bh->b_end_io = end_buffer_write_sync;
+			get_bh(bh);
+			/* Set the entire contents of the buffer to 0xff. */
+			memset(bh->b_data, -1, block_size);
+			if (!buffer_uptodate(bh))
+				set_buffer_uptodate(bh);
+			if (buffer_dirty(bh))
+				clear_buffer_dirty(bh);
+			/*
+			 * Submit the buffer and wait for i/o to complete but
+			 * only for the first buffer so we do not miss really
+			 * serious i/o errors.  Once the first buffer has
+			 * completed ignore errors afterwards as we can assume
+			 * that if one buffer worked all of them will work.
+			 */
+			submit_bh(WRITE, bh);
+			if (should_wait) {
+				should_wait = false;
+				wait_on_buffer(bh);
+				if (unlikely(!buffer_uptodate(bh)))
+					goto io_err;
+			}
+			brelse(bh);
+		} while (++block < end_block);
+	} while ((++rl)->vcn < end_vcn);
+	up_write(&log_ni->runlist.lock);
+	/*
+	 * Zap the pages again just in case any got instantiated whilst we were
+	 * emptying the blocks by hand.  FIXME: We may not have completed
+	 * writing to all the buffer heads yet so this may happen too early.
+	 * We really should use a kernel thread to do the emptying
+	 * asynchronously and then we can also set the volume dirty and output
+	 * an error message if emptying should fail.
+	 */
+	truncate_inode_pages(log_vi->i_mapping, 0);
+	/* Set the flag so we do not have to do it again on remount. */
+	NVolSetLogFileEmpty(vol);
+	ntfs_debug("Done.");
+	return true;
+io_err:
+	ntfs_error(sb, "Failed to write buffer.  Unmount and run chkdsk.");
+	goto dirty_err;
+rl_err:
+	ntfs_error(sb, "Runlist is corrupt.  Unmount and run chkdsk.");
+dirty_err:
+	NVolSetErrors(vol);
+	err = -EIO;
+err:
+	up_write(&log_ni->runlist.lock);
+	ntfs_error(sb, "Failed to fill $LogFile with 0xff bytes (error %d).",
+			-err);
+	return false;
+}
+
+#endif /* NTFS_RW */

fs/ntfs/logfile.h

@@ -0,0 +1,309 @@
+/*
+ * logfile.h - Defines for NTFS kernel journal ($LogFile) handling.  Part of
+ *	       the Linux-NTFS project.
+ *
+ * Copyright (c) 2000-2005 Anton Altaparmakov
+ *
+ * This program/include file is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_LOGFILE_H
+#define _LINUX_NTFS_LOGFILE_H
+
+#ifdef NTFS_RW
+
+#include <linux/fs.h>
+
+#include "types.h"
+#include "endian.h"
+#include "layout.h"
+
+/*
+ * Journal ($LogFile) organization:
+ *
+ * Two restart areas present in the first two pages (restart pages, one restart
+ * area in each page).  When the volume is dismounted they should be identical,
+ * except for the update sequence array which usually has a different update
+ * sequence number.
+ *
+ * These are followed by log records organized in pages headed by a log record
+ * header going up to log file size.  Not all pages contain log records when a
+ * volume is first formatted, but as the volume ages, all records will be used.
+ * When the log file fills up, the records at the beginning are purged (by
+ * modifying the oldest_lsn to a higher value presumably) and writing begins
+ * at the beginning of the file.  Effectively, the log file is viewed as a
+ * circular entity.
+ *
+ * NOTE: Windows NT, 2000, and XP all use log file version 1.1 but they accept
+ * versions <= 1.x, including 0.-1.  (Yes, that is a minus one in there!)  We
+ * probably only want to support 1.1 as this seems to be the current version
+ * and we don't know how that differs from the older versions.  The only
+ * exception is if the journal is clean as marked by the two restart pages
+ * then it doesn't matter whether we are on an earlier version.  We can just
+ * reinitialize the logfile and start again with version 1.1.
+ */
+
+/* Some $LogFile related constants. */
+#define MaxLogFileSize		0x100000000ULL
+#define DefaultLogPageSize	4096
+#define MinLogRecordPages	48
+
+/*
+ * Log file restart page header (begins the restart area).
+ */
+typedef struct {
+/*Ofs*/
+/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
+/*  0*/	NTFS_RECORD_TYPE magic;	/* The magic is "RSTR". */
+/*  4*/	le16 usa_ofs;		/* See NTFS_RECORD definition in layout.h.
+				   When creating, set this to be immediately
+				   after this header structure (without any
+				   alignment). */
+/*  6*/	le16 usa_count;		/* See NTFS_RECORD definition in layout.h. */
+
+/*  8*/	leLSN chkdsk_lsn;	/* The last log file sequence number found by
+				   chkdsk.  Only used when the magic is changed
+				   to "CHKD".  Otherwise this is zero. */
+/* 16*/	le32 system_page_size;	/* Byte size of system pages when the log file
+				   was created, has to be >= 512 and a power of
+				   2.  Use this to calculate the required size
+				   of the usa (usa_count) and add it to usa_ofs.
+				   Then verify that the result is less than the
+				   value of the restart_area_offset. */
+/* 20*/	le32 log_page_size;	/* Byte size of log file pages, has to be >=
+				   512 and a power of 2.  The default is 4096
+				   and is used when the system page size is
+				   between 4096 and 8192.  Otherwise this is
+				   set to the system page size instead. */
+/* 24*/	le16 restart_area_offset;/* Byte offset from the start of this header to
+				   the RESTART_AREA.  Value has to be aligned
+				   to 8-byte boundary.  When creating, set this
+				   to be after the usa. */
+/* 26*/	sle16 minor_ver;	/* Log file minor version.  Only check if major
+				   version is 1. */
+/* 28*/	sle16 major_ver;	/* Log file major version.  We only support
+				   version 1.1. */
+/* sizeof() = 30 (0x1e) bytes */
+} __attribute__ ((__packed__)) RESTART_PAGE_HEADER;
+
+/*
+ * Constant for the log client indices meaning that there are no client records
+ * in this particular client array.  Also inside the client records themselves,
+ * this means that there are no client records preceding or following this one.
+ */
+#define LOGFILE_NO_CLIENT	cpu_to_le16(0xffff)
+#define LOGFILE_NO_CLIENT_CPU	0xffff
+
+/*
+ * These are the so far known RESTART_AREA_* flags (16-bit) which contain
+ * information about the log file in which they are present.
+ */
+enum {
+	RESTART_VOLUME_IS_CLEAN	= cpu_to_le16(0x0002),
+	RESTART_SPACE_FILLER	= cpu_to_le16(0xffff), /* gcc: Force enum bit width to 16. */
+} __attribute__ ((__packed__));
+
+typedef le16 RESTART_AREA_FLAGS;
+
+/*
+ * Log file restart area record.  The offset of this record is found by adding
+ * the offset of the RESTART_PAGE_HEADER to the restart_area_offset value found
+ * in it.  See notes at restart_area_offset above.
+ */
+typedef struct {
+/*Ofs*/
+/*  0*/	leLSN current_lsn;	/* The current, i.e. last LSN inside the log
+				   when the restart area was last written.
+				   This happens often but what is the interval?
+				   Is it just fixed time or is it every time a
+				   check point is written or somethine else?
+				   On create set to 0. */
+/*  8*/	le16 log_clients;	/* Number of log client records in the array of
+				   log client records which follows this
+				   restart area.  Must be 1.  */
+/* 10*/	le16 client_free_list;	/* The index of the first free log client record
+				   in the array of log client records.
+				   LOGFILE_NO_CLIENT means that there are no
+				   free log client records in the array.
+				   If != LOGFILE_NO_CLIENT, check that
+				   log_clients > client_free_list.  On Win2k
+				   and presumably earlier, on a clean volume
+				   this is != LOGFILE_NO_CLIENT, and it should
+				   be 0, i.e. the first (and only) client
+				   record is free and thus the logfile is
+				   closed and hence clean.  A dirty volume
+				   would have left the logfile open and hence
+				   this would be LOGFILE_NO_CLIENT.  On WinXP
+				   and presumably later, the logfile is always
+				   open, even on clean shutdown so this should
+				   always be LOGFILE_NO_CLIENT. */
+/* 12*/	le16 client_in_use_list;/* The index of the first in-use log client
+				   record in the array of log client records.
+				   LOGFILE_NO_CLIENT means that there are no
+				   in-use log client records in the array.  If
+				   != LOGFILE_NO_CLIENT check that log_clients
+				   > client_in_use_list.  On Win2k and
+				   presumably earlier, on a clean volume this
+				   is LOGFILE_NO_CLIENT, i.e. there are no
+				   client records in use and thus the logfile
+				   is closed and hence clean.  A dirty volume
+				   would have left the logfile open and hence
+				   this would be != LOGFILE_NO_CLIENT, and it
+				   should be 0, i.e. the first (and only)
+				   client record is in use.  On WinXP and
+				   presumably later, the logfile is always
+				   open, even on clean shutdown so this should
+				   always be 0. */
+/* 14*/	RESTART_AREA_FLAGS flags;/* Flags modifying LFS behaviour.  On Win2k
+				   and presumably earlier this is always 0.  On
+				   WinXP and presumably later, if the logfile
+				   was shutdown cleanly, the second bit,
+				   RESTART_VOLUME_IS_CLEAN, is set.  This bit
+				   is cleared when the volume is mounted by
+				   WinXP and set when the volume is dismounted,
+				   thus if the logfile is dirty, this bit is
+				   clear.  Thus we don't need to check the
+				   Windows version to determine if the logfile
+				   is clean.  Instead if the logfile is closed,
+				   we know it must be clean.  If it is open and
+				   this bit is set, we also know it must be
+				   clean.  If on the other hand the logfile is
+				   open and this bit is clear, we can be almost
+				   certain that the logfile is dirty. */
+/* 16*/	le32 seq_number_bits;	/* How many bits to use for the sequence
+				   number.  This is calculated as 67 - the
+				   number of bits required to store the logfile
+				   size in bytes and this can be used in with
+				   the specified file_size as a consistency
+				   check. */
+/* 20*/	le16 restart_area_length;/* Length of the restart area including the
+				   client array.  Following checks required if
+				   version matches.  Otherwise, skip them.
+				   restart_area_offset + restart_area_length
+				   has to be <= system_page_size.  Also,
+				   restart_area_length has to be >=
+				   client_array_offset + (log_clients *
+				   sizeof(log client record)). */
+/* 22*/	le16 client_array_offset;/* Offset from the start of this record to
+				   the first log client record if versions are
+				   matched.  When creating, set this to be
+				   after this restart area structure, aligned
+				   to 8-bytes boundary.  If the versions do not
+				   match, this is ignored and the offset is
+				   assumed to be (sizeof(RESTART_AREA) + 7) &
+				   ~7, i.e. rounded up to first 8-byte
+				   boundary.  Either way, client_array_offset
+				   has to be aligned to an 8-byte boundary.
+				   Also, restart_area_offset +
+				   client_array_offset has to be <= 510.
+				   Finally, client_array_offset + (log_clients
+				   * sizeof(log client record)) has to be <=
+				   system_page_size.  On Win2k and presumably
+				   earlier, this is 0x30, i.e. immediately
+				   following this record.  On WinXP and
+				   presumably later, this is 0x40, i.e. there
+				   are 16 extra bytes between this record and
+				   the client array.  This probably means that
+				   the RESTART_AREA record is actually bigger
+				   in WinXP and later. */
+/* 24*/	sle64 file_size;	/* Usable byte size of the log file.  If the
+				   restart_area_offset + the offset of the
+				   file_size are > 510 then corruption has
+				   occurred.  This is the very first check when
+				   starting with the restart_area as if it
+				   fails it means that some of the above values
+				   will be corrupted by the multi sector
+				   transfer protection.  The file_size has to
+				   be rounded down to be a multiple of the
+				   log_page_size in the RESTART_PAGE_HEADER and
+				   then it has to be at least big enough to
+				   store the two restart pages and 48 (0x30)
+				   log record pages. */
+/* 32*/	le32 last_lsn_data_length;/* Length of data of last LSN, not including
+				   the log record header.  On create set to
+				   0. */
+/* 36*/	le16 log_record_header_length;/* Byte size of the log record header.
+				   If the version matches then check that the
+				   value of log_record_header_length is a
+				   multiple of 8, i.e.
+				   (log_record_header_length + 7) & ~7 ==
+				   log_record_header_length.  When creating set
+				   it to sizeof(LOG_RECORD_HEADER), aligned to
+				   8 bytes. */
+/* 38*/	le16 log_page_data_offset;/* Offset to the start of data in a log record
+				   page.  Must be a multiple of 8.  On create
+				   set it to immediately after the update
+				   sequence array of the log record page. */
+/* 40*/	le32 restart_log_open_count;/* A counter that gets incremented every
+				   time the logfile is restarted which happens
+				   at mount time when the logfile is opened.
+				   When creating set to a random value.  Win2k
+				   sets it to the low 32 bits of the current
+				   system time in NTFS format (see time.h). */
+/* 44*/	le32 reserved;		/* Reserved/alignment to 8-byte boundary. */
+/* sizeof() = 48 (0x30) bytes */
+} __attribute__ ((__packed__)) RESTART_AREA;
+
+/*
+ * Log client record.  The offset of this record is found by adding the offset
+ * of the RESTART_AREA to the client_array_offset value found in it.
+ */
+typedef struct {
+/*Ofs*/
+/*  0*/	leLSN oldest_lsn;	/* Oldest LSN needed by this client.  On create
+				   set to 0. */
+/*  8*/	leLSN client_restart_lsn;/* LSN at which this client needs to restart
+				   the volume, i.e. the current position within
+				   the log file.  At present, if clean this
+				   should = current_lsn in restart area but it
+				   probably also = current_lsn when dirty most
+				   of the time.  At create set to 0. */
+/* 16*/	le16 prev_client;	/* The offset to the previous log client record
+				   in the array of log client records.
+				   LOGFILE_NO_CLIENT means there is no previous
+				   client record, i.e. this is the first one.
+				   This is always LOGFILE_NO_CLIENT. */
+/* 18*/	le16 next_client;	/* The offset to the next log client record in
+				   the array of log client records.
+				   LOGFILE_NO_CLIENT means there are no next
+				   client records, i.e. this is the last one.
+				   This is always LOGFILE_NO_CLIENT. */
+/* 20*/	le16 seq_number;	/* On Win2k and presumably earlier, this is set
+				   to zero every time the logfile is restarted
+				   and it is incremented when the logfile is
+				   closed at dismount time.  Thus it is 0 when
+				   dirty and 1 when clean.  On WinXP and
+				   presumably later, this is always 0. */
+/* 22*/	u8 reserved[6];		/* Reserved/alignment. */
+/* 28*/	le32 client_name_length;/* Length of client name in bytes.  Should
+				   always be 8. */
+/* 32*/	ntfschar client_name[64];/* Name of the client in Unicode.  Should
+				   always be "NTFS" with the remaining bytes
+				   set to 0. */
+/* sizeof() = 160 (0xa0) bytes */
+} __attribute__ ((__packed__)) LOG_CLIENT_RECORD;
+
+extern bool ntfs_check_logfile(struct inode *log_vi,
+		RESTART_PAGE_HEADER **rp);
+
+extern bool ntfs_is_logfile_clean(struct inode *log_vi,
+		const RESTART_PAGE_HEADER *rp);
+
+extern bool ntfs_empty_logfile(struct inode *log_vi);
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_LOGFILE_H */

fs/ntfs/malloc.h

@@ -0,0 +1,96 @@
+/*
+ * malloc.h - NTFS kernel memory handling. Part of the Linux-NTFS project.
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_MALLOC_H
+#define _LINUX_NTFS_MALLOC_H
+
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+
+/**
+ * __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(unsigned long size, gfp_t 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_mask & ~__GFP_HIGHMEM);
+		/* return (void *)__get_free_page(gfp_mask); */
+	}
+	if (likely((size >> PAGE_SHIFT) < totalram_pages))
+		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 (!is_vmalloc_addr(addr)) {
+		kfree(addr);
+		/* free_page((unsigned long)addr); */
+		return;
+	}
+	vfree(addr);
+}
+
+#endif /* _LINUX_NTFS_MALLOC_H */

fs/ntfs/mft.h

@@ -0,0 +1,124 @@
+/*
+ * mft.h - Defines for mft record handling in NTFS Linux kernel driver.
+ *	   Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_MFT_H
+#define _LINUX_NTFS_MFT_H
+
+#include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+
+#include "inode.h"
+
+extern MFT_RECORD *map_mft_record(ntfs_inode *ni);
+extern void unmap_mft_record(ntfs_inode *ni);
+
+extern MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
+		ntfs_inode **ntfs_ino);
+
+static inline void unmap_extent_mft_record(ntfs_inode *ni)
+{
+	unmap_mft_record(ni);
+	return;
+}
+
+#ifdef NTFS_RW
+
+/**
+ * flush_dcache_mft_record_page - flush_dcache_page() for mft records
+ * @ni:		ntfs inode structure of mft record
+ *
+ * Call flush_dcache_page() for the page in which an mft record resides.
+ *
+ * This must be called every time an mft record is modified, just after the
+ * modification.
+ */
+static inline void flush_dcache_mft_record_page(ntfs_inode *ni)
+{
+	flush_dcache_page(ni->page);
+}
+
+extern void __mark_mft_record_dirty(ntfs_inode *ni);
+
+/**
+ * mark_mft_record_dirty - set the mft record and the page containing it dirty
+ * @ni:		ntfs inode describing the mapped mft record
+ *
+ * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni,
+ * as well as the page containing the mft record, dirty.  Also, mark the base
+ * vfs inode dirty.  This ensures that any changes to the mft record are
+ * written out to disk.
+ *
+ * NOTE:  Do not do anything if the mft record is already marked dirty.
+ */
+static inline void mark_mft_record_dirty(ntfs_inode *ni)
+{
+	if (!NInoTestSetDirty(ni))
+		__mark_mft_record_dirty(ni);
+}
+
+extern int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
+		MFT_RECORD *m, int sync);
+
+extern int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync);
+
+/**
+ * write_mft_record - write out a mapped (extent) mft record
+ * @ni:		ntfs inode describing the mapped (extent) mft record
+ * @m:		mapped (extent) mft record to write
+ * @sync:	if true, wait for i/o completion
+ *
+ * This is just a wrapper for write_mft_record_nolock() (see mft.c), which
+ * locks the page for the duration of the write.  This ensures that there are
+ * no race conditions between writing the mft record via the dirty inode code
+ * paths and via the page cache write back code paths or between writing
+ * neighbouring mft records residing in the same page.
+ *
+ * Locking the page also serializes us against ->readpage() if the page is not
+ * uptodate.
+ *
+ * On success, clean the mft record and return 0.  On error, leave the mft
+ * record dirty and return -errno.
+ */
+static inline int write_mft_record(ntfs_inode *ni, MFT_RECORD *m, int sync)
+{
+	struct page *page = ni->page;
+	int err;
+
+	BUG_ON(!page);
+	lock_page(page);
+	err = write_mft_record_nolock(ni, m, sync);
+	unlock_page(page);
+	return err;
+}
+
+extern bool ntfs_may_write_mft_record(ntfs_volume *vol,
+		const unsigned long mft_no, const MFT_RECORD *m,
+		ntfs_inode **locked_ni);
+
+extern ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
+		ntfs_inode *base_ni, MFT_RECORD **mrec);
+extern int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m);
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_MFT_H */

fs/ntfs/mst.c

@@ -0,0 +1,203 @@
+/*
+ * mst.c - NTFS multi sector transfer protection handling code. Part of the
+ *	   Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include "ntfs.h"
+
+/**
+ * post_read_mst_fixup - deprotect multi sector transfer protected data
+ * @b:		pointer to the data to deprotect
+ * @size:	size in bytes of @b
+ *
+ * Perform the necessary post read multi sector transfer fixup and detect the
+ * presence of incomplete multi sector transfers. - In that case, overwrite the
+ * magic of the ntfs record header being processed with "BAAD" (in memory only!)
+ * and abort processing.
+ *
+ * Return 0 on success and -EINVAL on error ("BAAD" magic will be present).
+ *
+ * NOTE: We consider the absence / invalidity of an update sequence array to
+ * mean that the structure is not protected at all and hence doesn't need to
+ * be fixed up. Thus, we return success and not failure in this case. This is
+ * in contrast to pre_write_mst_fixup(), see below.
+ */
+int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
+{
+	u16 usa_ofs, usa_count, usn;
+	u16 *usa_pos, *data_pos;
+
+	/* Setup the variables. */
+	usa_ofs = le16_to_cpu(b->usa_ofs);
+	/* Decrement usa_count to get number of fixups. */
+	usa_count = le16_to_cpu(b->usa_count) - 1;
+	/* Size and alignment checks. */
+	if ( size & (NTFS_BLOCK_SIZE - 1)	||
+	     usa_ofs & 1			||
+	     usa_ofs + (usa_count * 2) > size	||
+	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
+		return 0;
+	/* Position of usn in update sequence array. */
+	usa_pos = (u16*)b + usa_ofs/sizeof(u16);
+	/*
+	 * The update sequence number which has to be equal to each of the
+	 * u16 values before they are fixed up. Note no need to care for
+	 * endianness since we are comparing and moving data for on disk
+	 * structures which means the data is consistent. - If it is
+	 * consistenty the wrong endianness it doesn't make any difference.
+	 */
+	usn = *usa_pos;
+	/*
+	 * Position in protected data of first u16 that needs fixing up.
+	 */
+	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
+	/*
+	 * Check for incomplete multi sector transfer(s).
+	 */
+	while (usa_count--) {
+		if (*data_pos != usn) {
+			/*
+			 * Incomplete multi sector transfer detected! )-:
+			 * Set the magic to "BAAD" and return failure.
+			 * Note that magic_BAAD is already converted to le32.
+			 */
+			b->magic = magic_BAAD;
+			return -EINVAL;
+		}
+		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
+	}
+	/* Re-setup the variables. */
+	usa_count = le16_to_cpu(b->usa_count) - 1;
+	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
+	/* Fixup all sectors. */
+	while (usa_count--) {
+		/*
+		 * Increment position in usa and restore original data from
+		 * the usa into the data buffer.
+		 */
+		*data_pos = *(++usa_pos);
+		/* Increment position in data as well. */
+		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
+	}
+	return 0;
+}
+
+/**
+ * pre_write_mst_fixup - apply multi sector transfer protection
+ * @b:		pointer to the data to protect
+ * @size:	size in bytes of @b
+ *
+ * Perform the necessary pre write multi sector transfer fixup on the data
+ * pointer to by @b of @size.
+ *
+ * Return 0 if fixup applied (success) or -EINVAL if no fixup was performed
+ * (assumed not needed). This is in contrast to post_read_mst_fixup() above.
+ *
+ * NOTE: We consider the absence / invalidity of an update sequence array to
+ * mean that the structure is not subject to protection and hence doesn't need
+ * to be fixed up. This means that you have to create a valid update sequence
+ * array header in the ntfs record before calling this function, otherwise it
+ * will fail (the header needs to contain the position of the update sequence
+ * array together with the number of elements in the array). You also need to
+ * initialise the update sequence number before calling this function
+ * otherwise a random word will be used (whatever was in the record at that
+ * position at that time).
+ */
+int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
+{
+	le16 *usa_pos, *data_pos;
+	u16 usa_ofs, usa_count, usn;
+	le16 le_usn;
+
+	/* Sanity check + only fixup if it makes sense. */
+	if (!b || ntfs_is_baad_record(b->magic) ||
+			ntfs_is_hole_record(b->magic))
+		return -EINVAL;
+	/* Setup the variables. */
+	usa_ofs = le16_to_cpu(b->usa_ofs);
+	/* Decrement usa_count to get number of fixups. */
+	usa_count = le16_to_cpu(b->usa_count) - 1;
+	/* Size and alignment checks. */
+	if ( size & (NTFS_BLOCK_SIZE - 1)	||
+	     usa_ofs & 1			||
+	     usa_ofs + (usa_count * 2) > size	||
+	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
+		return -EINVAL;
+	/* Position of usn in update sequence array. */
+	usa_pos = (le16*)((u8*)b + usa_ofs);
+	/*
+	 * Cyclically increment the update sequence number
+	 * (skipping 0 and -1, i.e. 0xffff).
+	 */
+	usn = le16_to_cpup(usa_pos) + 1;
+	if (usn == 0xffff || !usn)
+		usn = 1;
+	le_usn = cpu_to_le16(usn);
+	*usa_pos = le_usn;
+	/* Position in data of first u16 that needs fixing up. */
+	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
+	/* Fixup all sectors. */
+	while (usa_count--) {
+		/*
+		 * Increment the position in the usa and save the
+		 * original data from the data buffer into the usa.
+		 */
+		*(++usa_pos) = *data_pos;
+		/* Apply fixup to data. */
+		*data_pos = le_usn;
+		/* Increment position in data as well. */
+		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
+	}
+	return 0;
+}
+
+/**
+ * post_write_mst_fixup - fast deprotect multi sector transfer protected data
+ * @b:		pointer to the data to deprotect
+ *
+ * Perform the necessary post write multi sector transfer fixup, not checking
+ * for any errors, because we assume we have just used pre_write_mst_fixup(),
+ * thus the data will be fine or we would never have gotten here.
+ */
+void post_write_mst_fixup(NTFS_RECORD *b)
+{
+	le16 *usa_pos, *data_pos;
+
+	u16 usa_ofs = le16_to_cpu(b->usa_ofs);
+	u16 usa_count = le16_to_cpu(b->usa_count) - 1;
+
+	/* Position of usn in update sequence array. */
+	usa_pos = (le16*)b + usa_ofs/sizeof(le16);
+
+	/* Position in protected data of first u16 that needs fixing up. */
+	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
+
+	/* Fixup all sectors. */
+	while (usa_count--) {
+		/*
+		 * Increment position in usa and restore original data from
+		 * the usa into the data buffer.
+		 */
+		*data_pos = *(++usa_pos);
+
+		/* Increment position in data as well. */
+		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
+	}
+}

fs/ntfs/namei.c

@@ -0,0 +1,405 @@
+/*
+ * namei.c - NTFS kernel directory inode operations. Part of the Linux-NTFS
+ *	     project.
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/dcache.h>
+#include <linux/exportfs.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+
+#include "attrib.h"
+#include "debug.h"
+#include "dir.h"
+#include "mft.h"
+#include "ntfs.h"
+
+/**
+ * ntfs_lookup - find the inode represented by a dentry in a directory inode
+ * @dir_ino:	directory inode in which to look for the inode
+ * @dent:	dentry representing the inode to look for
+ * @nd:		lookup nameidata
+ *
+ * In short, ntfs_lookup() looks for the inode represented by the dentry @dent
+ * in the directory inode @dir_ino and if found attaches the inode to the
+ * dentry @dent.
+ *
+ * In more detail, the dentry @dent specifies which inode to look for by
+ * supplying the name of the inode in @dent->d_name.name. ntfs_lookup()
+ * converts the name to Unicode and walks the contents of the directory inode
+ * @dir_ino looking for the converted Unicode name. If the name is found in the
+ * directory, the corresponding inode is loaded by calling ntfs_iget() on its
+ * inode number and the inode is associated with the dentry @dent via a call to
+ * d_splice_alias().
+ *
+ * If the name is not found in the directory, a NULL inode is inserted into the
+ * dentry @dent via a call to d_add(). The dentry is then termed a negative
+ * dentry.
+ *
+ * Only if an actual error occurs, do we return an error via ERR_PTR().
+ *
+ * In order to handle the case insensitivity issues of NTFS with regards to the
+ * dcache and the dcache requiring only one dentry per directory, we deal with
+ * dentry aliases that only differ in case in ->ntfs_lookup() while maintaining
+ * a case sensitive dcache. This means that we get the full benefit of dcache
+ * speed when the file/directory is looked up with the same case as returned by
+ * ->ntfs_readdir() but that a lookup for any other case (or for the short file
+ * name) will not find anything in dcache and will enter ->ntfs_lookup()
+ * instead, where we search the directory for a fully matching file name
+ * (including case) and if that is not found, we search for a file name that
+ * matches with different case and if that has non-POSIX semantics we return
+ * that. We actually do only one search (case sensitive) and keep tabs on
+ * whether we have found a case insensitive match in the process.
+ *
+ * To simplify matters for us, we do not treat the short vs long filenames as
+ * two hard links but instead if the lookup matches a short filename, we
+ * return the dentry for the corresponding long filename instead.
+ *
+ * There are three cases we need to distinguish here:
+ *
+ * 1) @dent perfectly matches (i.e. including case) a directory entry with a
+ *    file name in the WIN32 or POSIX namespaces. In this case
+ *    ntfs_lookup_inode_by_name() will return with name set to NULL and we
+ *    just d_splice_alias() @dent.
+ * 2) @dent matches (not including case) a directory entry with a file name in
+ *    the WIN32 namespace. In this case ntfs_lookup_inode_by_name() will return
+ *    with name set to point to a kmalloc()ed ntfs_name structure containing
+ *    the properly cased little endian Unicode name. We convert the name to the
+ *    current NLS code page, search if a dentry with this name already exists
+ *    and if so return that instead of @dent.  At this point things are
+ *    complicated by the possibility of 'disconnected' dentries due to NFS
+ *    which we deal with appropriately (see the code comments).  The VFS will
+ *    then destroy the old @dent and use the one we returned.  If a dentry is
+ *    not found, we allocate a new one, d_splice_alias() it, and return it as
+ *    above.
+ * 3) @dent matches either perfectly or not (i.e. we don't care about case) a
+ *    directory entry with a file name in the DOS namespace. In this case
+ *    ntfs_lookup_inode_by_name() will return with name set to point to a
+ *    kmalloc()ed ntfs_name structure containing the mft reference (cpu endian)
+ *    of the inode. We use the mft reference to read the inode and to find the
+ *    file name in the WIN32 namespace corresponding to the matched short file
+ *    name. We then convert the name to the current NLS code page, and proceed
+ *    searching for a dentry with this name, etc, as in case 2), above.
+ *
+ * Locking: Caller must hold i_mutex on the directory.
+ */
+static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
+		unsigned int flags)
+{
+	ntfs_volume *vol = NTFS_SB(dir_ino->i_sb);
+	struct inode *dent_inode;
+	ntfschar *uname;
+	ntfs_name *name = NULL;
+	MFT_REF mref;
+	unsigned long dent_ino;
+	int uname_len;
+
+	ntfs_debug("Looking up %s in directory inode 0x%lx.",
+			dent->d_name.name, dir_ino->i_ino);
+	/* Convert the name of the dentry to Unicode. */
+	uname_len = ntfs_nlstoucs(vol, dent->d_name.name, dent->d_name.len,
+			&uname);
+	if (uname_len < 0) {
+		if (uname_len != -ENAMETOOLONG)
+			ntfs_error(vol->sb, "Failed to convert name to "
+					"Unicode.");
+		return ERR_PTR(uname_len);
+	}
+	mref = ntfs_lookup_inode_by_name(NTFS_I(dir_ino), uname, uname_len,
+			&name);
+	kmem_cache_free(ntfs_name_cache, uname);
+	if (!IS_ERR_MREF(mref)) {
+		dent_ino = MREF(mref);
+		ntfs_debug("Found inode 0x%lx. Calling ntfs_iget.", dent_ino);
+		dent_inode = ntfs_iget(vol->sb, dent_ino);
+		if (likely(!IS_ERR(dent_inode))) {
+			/* Consistency check. */
+			if (is_bad_inode(dent_inode) || MSEQNO(mref) ==
+					NTFS_I(dent_inode)->seq_no ||
+					dent_ino == FILE_MFT) {
+				/* Perfect WIN32/POSIX match. -- Case 1. */
+				if (!name) {
+					ntfs_debug("Done.  (Case 1.)");
+					return d_splice_alias(dent_inode, dent);
+				}
+				/*
+				 * We are too indented.  Handle imperfect
+				 * matches and short file names further below.
+				 */
+				goto handle_name;
+			}
+			ntfs_error(vol->sb, "Found stale reference to inode "
+					"0x%lx (reference sequence number = "
+					"0x%x, inode sequence number = 0x%x), "
+					"returning -EIO. Run chkdsk.",
+					dent_ino, MSEQNO(mref),
+					NTFS_I(dent_inode)->seq_no);
+			iput(dent_inode);
+			dent_inode = ERR_PTR(-EIO);
+		} else
+			ntfs_error(vol->sb, "ntfs_iget(0x%lx) failed with "
+					"error code %li.", dent_ino,
+					PTR_ERR(dent_inode));
+		kfree(name);
+		/* Return the error code. */
+		return (struct dentry *)dent_inode;
+	}
+	/* It is guaranteed that @name is no longer allocated at this point. */
+	if (MREF_ERR(mref) == -ENOENT) {
+		ntfs_debug("Entry was not found, adding negative dentry.");
+		/* The dcache will handle negative entries. */
+		d_add(dent, NULL);
+		ntfs_debug("Done.");
+		return NULL;
+	}
+	ntfs_error(vol->sb, "ntfs_lookup_ino_by_name() failed with error "
+			"code %i.", -MREF_ERR(mref));
+	return ERR_PTR(MREF_ERR(mref));
+	// TODO: Consider moving this lot to a separate function! (AIA)
+handle_name:
+   {
+	MFT_RECORD *m;
+	ntfs_attr_search_ctx *ctx;
+	ntfs_inode *ni = NTFS_I(dent_inode);
+	int err;
+	struct qstr nls_name;
+
+	nls_name.name = NULL;
+	if (name->type != FILE_NAME_DOS) {			/* Case 2. */
+		ntfs_debug("Case 2.");
+		nls_name.len = (unsigned)ntfs_ucstonls(vol,
+				(ntfschar*)&name->name, name->len,
+				(unsigned char**)&nls_name.name, 0);
+		kfree(name);
+	} else /* if (name->type == FILE_NAME_DOS) */ {		/* Case 3. */
+		FILE_NAME_ATTR *fn;
+
+		ntfs_debug("Case 3.");
+		kfree(name);
+
+		/* Find the WIN32 name corresponding to the matched DOS name. */
+		ni = NTFS_I(dent_inode);
+		m = map_mft_record(ni);
+		if (IS_ERR(m)) {
+			err = PTR_ERR(m);
+			m = NULL;
+			ctx = NULL;
+			goto err_out;
+		}
+		ctx = ntfs_attr_get_search_ctx(ni, m);
+		if (unlikely(!ctx)) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+		do {
+			ATTR_RECORD *a;
+			u32 val_len;
+
+			err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, 0, 0,
+					NULL, 0, ctx);
+			if (unlikely(err)) {
+				ntfs_error(vol->sb, "Inode corrupt: No WIN32 "
+						"namespace counterpart to DOS "
+						"file name. Run chkdsk.");
+				if (err == -ENOENT)
+					err = -EIO;
+				goto err_out;
+			}
+			/* Consistency checks. */
+			a = ctx->attr;
+			if (a->non_resident || a->flags)
+				goto eio_err_out;
+			val_len = le32_to_cpu(a->data.resident.value_length);
+			if (le16_to_cpu(a->data.resident.value_offset) +
+					val_len > le32_to_cpu(a->length))
+				goto eio_err_out;
+			fn = (FILE_NAME_ATTR*)((u8*)ctx->attr + le16_to_cpu(
+					ctx->attr->data.resident.value_offset));
+			if ((u32)(fn->file_name_length * sizeof(ntfschar) +
+					sizeof(FILE_NAME_ATTR)) > val_len)
+				goto eio_err_out;
+		} while (fn->file_name_type != FILE_NAME_WIN32);
+
+		/* Convert the found WIN32 name to current NLS code page. */
+		nls_name.len = (unsigned)ntfs_ucstonls(vol,
+				(ntfschar*)&fn->file_name, fn->file_name_length,
+				(unsigned char**)&nls_name.name, 0);
+
+		ntfs_attr_put_search_ctx(ctx);
+		unmap_mft_record(ni);
+	}
+	m = NULL;
+	ctx = NULL;
+
+	/* Check if a conversion error occurred. */
+	if ((signed)nls_name.len < 0) {
+		err = (signed)nls_name.len;
+		goto err_out;
+	}
+	nls_name.hash = full_name_hash(nls_name.name, nls_name.len);
+
+	dent = d_add_ci(dent, dent_inode, &nls_name);
+	kfree(nls_name.name);
+	return dent;
+
+eio_err_out:
+	ntfs_error(vol->sb, "Illegal file name attribute. Run chkdsk.");
+	err = -EIO;
+err_out:
+	if (ctx)
+		ntfs_attr_put_search_ctx(ctx);
+	if (m)
+		unmap_mft_record(ni);
+	iput(dent_inode);
+	ntfs_error(vol->sb, "Failed, returning error code %i.", err);
+	return ERR_PTR(err);
+   }
+}
+
+/**
+ * Inode operations for directories.
+ */
+const struct inode_operations ntfs_dir_inode_ops = {
+	.lookup	= ntfs_lookup,	/* VFS: Lookup directory. */
+};
+
+/**
+ * ntfs_get_parent - find the dentry of the parent of a given directory dentry
+ * @child_dent:		dentry of the directory whose parent directory to find
+ *
+ * Find the dentry for the parent directory of the directory specified by the
+ * dentry @child_dent.  This function is called from
+ * fs/exportfs/expfs.c::find_exported_dentry() which in turn is called from the
+ * default ->decode_fh() which is export_decode_fh() in the same file.
+ *
+ * The code is based on the ext3 ->get_parent() implementation found in
+ * fs/ext3/namei.c::ext3_get_parent().
+ *
+ * Note: ntfs_get_parent() is called with @child_dent->d_inode->i_mutex down.
+ *
+ * Return the dentry of the parent directory on success or the error code on
+ * error (IS_ERR() is true).
+ */
+static struct dentry *ntfs_get_parent(struct dentry *child_dent)
+{
+	struct inode *vi = child_dent->d_inode;
+	ntfs_inode *ni = NTFS_I(vi);
+	MFT_RECORD *mrec;
+	ntfs_attr_search_ctx *ctx;
+	ATTR_RECORD *attr;
+	FILE_NAME_ATTR *fn;
+	unsigned long parent_ino;
+	int err;
+
+	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
+	/* Get the mft record of the inode belonging to the child dentry. */
+	mrec = map_mft_record(ni);
+	if (IS_ERR(mrec))
+		return (struct dentry *)mrec;
+	/* Find the first file name attribute in the mft record. */
+	ctx = ntfs_attr_get_search_ctx(ni, mrec);
+	if (unlikely(!ctx)) {
+		unmap_mft_record(ni);
+		return ERR_PTR(-ENOMEM);
+	}
+try_next:
+	err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, CASE_SENSITIVE, 0, NULL,
+			0, ctx);
+	if (unlikely(err)) {
+		ntfs_attr_put_search_ctx(ctx);
+		unmap_mft_record(ni);
+		if (err == -ENOENT)
+			ntfs_error(vi->i_sb, "Inode 0x%lx does not have a "
+					"file name attribute.  Run chkdsk.",
+					vi->i_ino);
+		return ERR_PTR(err);
+	}
+	attr = ctx->attr;
+	if (unlikely(attr->non_resident))
+		goto try_next;
+	fn = (FILE_NAME_ATTR *)((u8 *)attr +
+			le16_to_cpu(attr->data.resident.value_offset));
+	if (unlikely((u8 *)fn + le32_to_cpu(attr->data.resident.value_length) >
+			(u8*)attr + le32_to_cpu(attr->length)))
+		goto try_next;
+	/* Get the inode number of the parent directory. */
+	parent_ino = MREF_LE(fn->parent_directory);
+	/* Release the search context and the mft record of the child. */
+	ntfs_attr_put_search_ctx(ctx);
+	unmap_mft_record(ni);
+
+	return d_obtain_alias(ntfs_iget(vi->i_sb, parent_ino));
+}
+
+static struct inode *ntfs_nfs_get_inode(struct super_block *sb,
+		u64 ino, u32 generation)
+{
+	struct inode *inode;
+
+	inode = ntfs_iget(sb, ino);
+	if (!IS_ERR(inode)) {
+		if (is_bad_inode(inode) || inode->i_generation != generation) {
+			iput(inode);
+			inode = ERR_PTR(-ESTALE);
+		}
+	}
+
+	return inode;
+}
+
+static struct dentry *ntfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    ntfs_nfs_get_inode);
+}
+
+static struct dentry *ntfs_fh_to_parent(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    ntfs_nfs_get_inode);
+}
+
+/**
+ * Export operations allowing NFS exporting of mounted NTFS partitions.
+ *
+ * We use the default ->encode_fh() for now.  Note that they
+ * use 32 bits to store the inode number which is an unsigned long so on 64-bit
+ * architectures is usually 64 bits so it would all fail horribly on huge
+ * volumes.  I guess we need to define our own encode and decode fh functions
+ * that store 64-bit inode numbers at some point but for now we will ignore the
+ * problem...
+ *
+ * We also use the default ->get_name() helper (used by ->decode_fh() via
+ * fs/exportfs/expfs.c::find_exported_dentry()) as that is completely fs
+ * independent.
+ *
+ * The default ->get_parent() just returns -EACCES so we have to provide our
+ * own and the default ->get_dentry() is incompatible with NTFS due to not
+ * allowing the inode number 0 which is used in NTFS for the system file $MFT
+ * and due to using iget() whereas NTFS needs ntfs_iget().
+ */
+const struct export_operations ntfs_export_ops = {
+	.get_parent	= ntfs_get_parent,	/* Find the parent of a given
+						   directory. */
+	.fh_to_dentry	= ntfs_fh_to_dentry,
+	.fh_to_parent	= ntfs_fh_to_parent,
+};

fs/ntfs/ntfs.h

@@ -0,0 +1,164 @@
+/*
+ * ntfs.h - Defines for NTFS Linux kernel driver.
+ *
+ * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
+ * Copyright (C) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_H
+#define _LINUX_NTFS_H
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+#include <linux/smp.h>
+#include <linux/pagemap.h>
+
+#include "types.h"
+#include "volume.h"
+#include "layout.h"
+
+typedef enum {
+	NTFS_BLOCK_SIZE		= 512,
+	NTFS_BLOCK_SIZE_BITS	= 9,
+	NTFS_SB_MAGIC		= 0x5346544e,	/* 'NTFS' */
+	NTFS_MAX_NAME_LEN	= 255,
+	NTFS_MAX_ATTR_NAME_LEN	= 255,
+	NTFS_MAX_CLUSTER_SIZE	= 64 * 1024,	/* 64kiB */
+	NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_CACHE_SIZE,
+} NTFS_CONSTANTS;
+
+/* Global variables. */
+
+/* Slab caches (from super.c). */
+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 const struct address_space_operations ntfs_normal_aops;
+extern const struct address_space_operations ntfs_compressed_aops;
+extern const struct address_space_operations ntfs_mst_aops;
+
+extern const struct  file_operations ntfs_file_ops;
+extern const struct inode_operations ntfs_file_inode_ops;
+
+extern const struct  file_operations ntfs_dir_ops;
+extern const struct inode_operations ntfs_dir_inode_ops;
+
+extern const struct  file_operations ntfs_empty_file_ops;
+extern const struct inode_operations ntfs_empty_inode_ops;
+
+extern const struct export_operations ntfs_export_ops;
+
+/**
+ * NTFS_SB - return the ntfs volume given a vfs super block
+ * @sb:		VFS super block
+ *
+ * NTFS_SB() returns the ntfs volume associated with the VFS super block @sb.
+ */
+static inline ntfs_volume *NTFS_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+/* Declarations of functions and global variables. */
+
+/* From fs/ntfs/compress.c */
+extern int ntfs_read_compressed_block(struct page *page);
+extern int allocate_compression_buffers(void);
+extern void free_compression_buffers(void);
+
+/* From fs/ntfs/super.c */
+#define default_upcase_len 0x10000
+extern struct mutex ntfs_lock;
+
+typedef struct {
+	int val;
+	char *str;
+} option_t;
+extern const option_t on_errors_arr[];
+
+/* From fs/ntfs/mst.c */
+extern int post_read_mst_fixup(NTFS_RECORD *b, const u32 size);
+extern int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size);
+extern void post_write_mst_fixup(NTFS_RECORD *b);
+
+/* From fs/ntfs/unistr.c */
+extern bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
+		const ntfschar *s2, size_t s2_len,
+		const IGNORE_CASE_BOOL ic,
+		const ntfschar *upcase, const u32 upcase_size);
+extern int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
+		const ntfschar *name2, const u32 name2_len,
+		const int err_val, const IGNORE_CASE_BOOL ic,
+		const ntfschar *upcase, const u32 upcase_len);
+extern int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n);
+extern int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
+		const ntfschar *upcase, const u32 upcase_size);
+extern void ntfs_upcase_name(ntfschar *name, u32 name_len,
+		const ntfschar *upcase, const u32 upcase_len);
+extern void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
+		const ntfschar *upcase, const u32 upcase_len);
+extern int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
+		FILE_NAME_ATTR *file_name_attr2,
+		const int err_val, const IGNORE_CASE_BOOL ic,
+		const ntfschar *upcase, const u32 upcase_len);
+extern int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
+		const int ins_len, ntfschar **outs);
+extern int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
+		const int ins_len, unsigned char **outs, int outs_len);
+
+/* From fs/ntfs/upcase.c */
+extern ntfschar *generate_default_upcase(void);
+
+static inline int ntfs_ffs(int x)
+{
+	int r = 1;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff)) {
+		x >>= 16;
+		r += 16;
+	}
+	if (!(x & 0xff)) {
+		x >>= 8;
+		r += 8;
+	}
+	if (!(x & 0xf)) {
+		x >>= 4;
+		r += 4;
+	}
+	if (!(x & 3)) {
+		x >>= 2;
+		r += 2;
+	}
+	if (!(x & 1)) {
+		x >>= 1;
+		r += 1;
+	}
+	return r;
+}
+
+#endif /* _LINUX_NTFS_H */

fs/ntfs/quota.c

@@ -0,0 +1,117 @@
+/*
+ * quota.c - NTFS kernel quota ($Quota) handling.  Part of the Linux-NTFS
+ *	     project.
+ *
+ * Copyright (c) 2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifdef NTFS_RW
+
+#include "index.h"
+#include "quota.h"
+#include "debug.h"
+#include "ntfs.h"
+
+/**
+ * ntfs_mark_quotas_out_of_date - mark the quotas out of date on an ntfs volume
+ * @vol:	ntfs volume on which to mark the quotas out of date
+ *
+ * Mark the quotas out of date on the ntfs volume @vol and return 'true' on
+ * success and 'false' on error.
+ */
+bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol)
+{
+	ntfs_index_context *ictx;
+	QUOTA_CONTROL_ENTRY *qce;
+	const le32 qid = QUOTA_DEFAULTS_ID;
+	int err;
+
+	ntfs_debug("Entering.");
+	if (NVolQuotaOutOfDate(vol))
+		goto done;
+	if (!vol->quota_ino || !vol->quota_q_ino) {
+		ntfs_error(vol->sb, "Quota inodes are not open.");
+		return false;
+	}
+	mutex_lock(&vol->quota_q_ino->i_mutex);
+	ictx = ntfs_index_ctx_get(NTFS_I(vol->quota_q_ino));
+	if (!ictx) {
+		ntfs_error(vol->sb, "Failed to get index context.");
+		goto err_out;
+	}
+	err = ntfs_index_lookup(&qid, sizeof(qid), ictx);
+	if (err) {
+		if (err == -ENOENT)
+			ntfs_error(vol->sb, "Quota defaults entry is not "
+					"present.");
+		else
+			ntfs_error(vol->sb, "Lookup of quota defaults entry "
+					"failed.");
+		goto err_out;
+	}
+	if (ictx->data_len < offsetof(QUOTA_CONTROL_ENTRY, sid)) {
+		ntfs_error(vol->sb, "Quota defaults entry size is invalid.  "
+				"Run chkdsk.");
+		goto err_out;
+	}
+	qce = (QUOTA_CONTROL_ENTRY*)ictx->data;
+	if (le32_to_cpu(qce->version) != QUOTA_VERSION) {
+		ntfs_error(vol->sb, "Quota defaults entry version 0x%x is not "
+				"supported.", le32_to_cpu(qce->version));
+		goto err_out;
+	}
+	ntfs_debug("Quota defaults flags = 0x%x.", le32_to_cpu(qce->flags));
+	/* If quotas are already marked out of date, no need to do anything. */
+	if (qce->flags & QUOTA_FLAG_OUT_OF_DATE)
+		goto set_done;
+	/*
+	 * If quota tracking is neither requested, nor enabled and there are no
+	 * pending deletes, no need to mark the quotas out of date.
+	 */
+	if (!(qce->flags & (QUOTA_FLAG_TRACKING_ENABLED |
+			QUOTA_FLAG_TRACKING_REQUESTED |
+			QUOTA_FLAG_PENDING_DELETES)))
+		goto set_done;
+	/*
+	 * Set the QUOTA_FLAG_OUT_OF_DATE bit thus marking quotas out of date.
+	 * This is verified on WinXP to be sufficient to cause windows to
+	 * rescan the volume on boot and update all quota entries.
+	 */
+	qce->flags |= QUOTA_FLAG_OUT_OF_DATE;
+	/* Ensure the modified flags are written to disk. */
+	ntfs_index_entry_flush_dcache_page(ictx);
+	ntfs_index_entry_mark_dirty(ictx);
+set_done:
+	ntfs_index_ctx_put(ictx);
+	mutex_unlock(&vol->quota_q_ino->i_mutex);
+	/*
+	 * We set the flag so we do not try to mark the quotas out of date
+	 * again on remount.
+	 */
+	NVolSetQuotaOutOfDate(vol);
+done:
+	ntfs_debug("Done.");
+	return true;
+err_out:
+	if (ictx)
+		ntfs_index_ctx_put(ictx);
+	mutex_unlock(&vol->quota_q_ino->i_mutex);
+	return false;
+}
+
+#endif /* NTFS_RW */

fs/ntfs/quota.h

@@ -0,0 +1,35 @@
+/*
+ * quota.h - Defines for NTFS kernel quota ($Quota) handling.  Part of the
+ *	     Linux-NTFS project.
+ *
+ * Copyright (c) 2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_QUOTA_H
+#define _LINUX_NTFS_QUOTA_H
+
+#ifdef NTFS_RW
+
+#include "types.h"
+#include "volume.h"
+
+extern bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol);
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_QUOTA_H */

fs/ntfs/runlist.h

@@ -0,0 +1,102 @@
+/*
+ * runlist.h - Defines for runlist handling in NTFS Linux kernel driver.
+ *	       Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_RUNLIST_H
+#define _LINUX_NTFS_RUNLIST_H
+
+#include "types.h"
+#include "layout.h"
+#include "volume.h"
+
+/**
+ * runlist_element - in memory vcn to lcn mapping array element
+ * @vcn:	starting vcn of the current array element
+ * @lcn:	starting lcn of the current array element
+ * @length:	length in clusters of the current array element
+ *
+ * The last vcn (in fact the last vcn + 1) is reached when length == 0.
+ *
+ * When lcn == -1 this means that the count vcns starting at vcn are not
+ * physically allocated (i.e. this is a hole / data is sparse).
+ */
+typedef struct {	/* In memory vcn to lcn mapping structure element. */
+	VCN vcn;	/* vcn = Starting virtual cluster number. */
+	LCN lcn;	/* lcn = Starting logical cluster number. */
+	s64 length;	/* Run length in clusters. */
+} runlist_element;
+
+/**
+ * runlist - in memory vcn to lcn mapping array including a read/write lock
+ * @rl:		pointer to an array of runlist elements
+ * @lock:	read/write spinlock for serializing access to @rl
+ *
+ */
+typedef struct {
+	runlist_element *rl;
+	struct rw_semaphore lock;
+} runlist;
+
+static inline void ntfs_init_runlist(runlist *rl)
+{
+	rl->rl = NULL;
+	init_rwsem(&rl->lock);
+}
+
+typedef enum {
+	LCN_HOLE		= -1,	/* Keep this as highest value or die! */
+	LCN_RL_NOT_MAPPED	= -2,
+	LCN_ENOENT		= -3,
+	LCN_ENOMEM		= -4,
+	LCN_EIO			= -5,
+} LCN_SPECIAL_VALUES;
+
+extern runlist_element *ntfs_runlists_merge(runlist_element *drl,
+		runlist_element *srl);
+
+extern runlist_element *ntfs_mapping_pairs_decompress(const ntfs_volume *vol,
+		const ATTR_RECORD *attr, runlist_element *old_rl);
+
+extern LCN ntfs_rl_vcn_to_lcn(const runlist_element *rl, const VCN vcn);
+
+#ifdef NTFS_RW
+
+extern runlist_element *ntfs_rl_find_vcn_nolock(runlist_element *rl,
+		const VCN vcn);
+
+extern int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol,
+		const runlist_element *rl, const VCN first_vcn,
+		const VCN last_vcn);
+
+extern int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst,
+		const int dst_len, const runlist_element *rl,
+		const VCN first_vcn, const VCN last_vcn, VCN *const stop_vcn);
+
+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 */

fs/ntfs/sysctl.c

@@ -0,0 +1,83 @@
+/*
+ * sysctl.c - Code for sysctl handling in NTFS Linux kernel driver. Part of
+ *	      the Linux-NTFS project. Adapted from the old NTFS driver,
+ *	      Copyright (C) 1997 Martin von Löwis, Régis Duchesne
+ *
+ * Copyright (c) 2002-2005 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifdef DEBUG
+
+#include <linux/module.h>
+
+#ifdef CONFIG_SYSCTL
+
+#include <linux/proc_fs.h>
+#include <linux/sysctl.h>
+
+#include "sysctl.h"
+#include "debug.h"
+
+/* Definition of the ntfs sysctl. */
+static struct ctl_table ntfs_sysctls[] = {
+	{
+		.procname	= "ntfs-debug",
+		.data		= &debug_msgs,		/* Data pointer and size. */
+		.maxlen		= sizeof(debug_msgs),
+		.mode		= 0644,			/* Mode, proc handler. */
+		.proc_handler	= proc_dointvec
+	},
+	{}
+};
+
+/* Define the parent directory /proc/sys/fs. */
+static struct ctl_table sysctls_root[] = {
+	{
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= ntfs_sysctls
+	},
+	{}
+};
+
+/* Storage for the sysctls header. */
+static struct ctl_table_header *sysctls_root_table;
+
+/**
+ * ntfs_sysctl - add or remove the debug sysctl
+ * @add:	add (1) or remove (0) the sysctl
+ *
+ * Add or remove the debug sysctl. Return 0 on success or -errno on error.
+ */
+int ntfs_sysctl(int add)
+{
+	if (add) {
+		BUG_ON(sysctls_root_table);
+		sysctls_root_table = register_sysctl_table(sysctls_root);
+		if (!sysctls_root_table)
+			return -ENOMEM;
+	} else {
+		BUG_ON(!sysctls_root_table);
+		unregister_sysctl_table(sysctls_root_table);
+		sysctls_root_table = NULL;
+	}
+	return 0;
+}
+
+#endif /* CONFIG_SYSCTL */
+#endif /* DEBUG */

fs/ntfs/sysctl.h

@@ -0,0 +1,41 @@
+/*
+ * sysctl.h - Defines for sysctl handling in NTFS Linux kernel driver. Part of
+ *	      the Linux-NTFS project. Adapted from the old NTFS driver,
+ *	      Copyright (C) 1997 Martin von Löwis, Régis Duchesne
+ *
+ * Copyright (c) 2002-2004 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_SYSCTL_H
+#define _LINUX_NTFS_SYSCTL_H
+
+
+#if defined(DEBUG) && defined(CONFIG_SYSCTL)
+
+extern int ntfs_sysctl(int add);
+
+#else
+
+/* Just return success. */
+static inline int ntfs_sysctl(int add)
+{
+	return 0;
+}
+
+#endif /* DEBUG && CONFIG_SYSCTL */
+#endif /* _LINUX_NTFS_SYSCTL_H */

fs/ntfs/time.h

@@ -0,0 +1,100 @@
+/*
+ * time.h - NTFS time conversion functions.  Part of the Linux-NTFS project.
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_TIME_H
+#define _LINUX_NTFS_TIME_H
+
+#include <linux/time.h>		/* For current_kernel_time(). */
+#include <asm/div64.h>		/* For do_div(). */
+
+#include "endian.h"
+
+#define NTFS_TIME_OFFSET ((s64)(369 * 365 + 89) * 24 * 3600 * 10000000)
+
+/**
+ * utc2ntfs - convert Linux UTC time to NTFS time
+ * @ts:		Linux UTC time to convert to NTFS time
+ *
+ * Convert the Linux UTC time @ts to its corresponding NTFS time and return
+ * that in little endian format.
+ *
+ * Linux stores time in a struct timespec consisting of a time_t (long at
+ * present) tv_sec and a long tv_nsec where tv_sec is the number of 1-second
+ * intervals since 1st January 1970, 00:00:00 UTC and tv_nsec is the number of
+ * 1-nano-second intervals since the value of tv_sec.
+ *
+ * NTFS uses Microsoft's standard time format which is stored in a s64 and is
+ * measured as the number of 100-nano-second intervals since 1st January 1601,
+ * 00:00:00 UTC.
+ */
+static inline sle64 utc2ntfs(const struct timespec ts)
+{
+	/*
+	 * Convert the seconds to 100ns intervals, add the nano-seconds
+	 * converted to 100ns intervals, and then add the NTFS time offset.
+	 */
+	return cpu_to_sle64((s64)ts.tv_sec * 10000000 + ts.tv_nsec / 100 +
+			NTFS_TIME_OFFSET);
+}
+
+/**
+ * get_current_ntfs_time - get the current time in little endian NTFS format
+ *
+ * Get the current time from the Linux kernel, convert it to its corresponding
+ * NTFS time and return that in little endian format.
+ */
+static inline sle64 get_current_ntfs_time(void)
+{
+	return utc2ntfs(current_kernel_time());
+}
+
+/**
+ * ntfs2utc - convert NTFS time to Linux time
+ * @time:	NTFS time (little endian) to convert to Linux UTC
+ *
+ * Convert the little endian NTFS time @time to its corresponding Linux UTC
+ * time and return that in cpu format.
+ *
+ * Linux stores time in a struct timespec consisting of a time_t (long at
+ * present) tv_sec and a long tv_nsec where tv_sec is the number of 1-second
+ * intervals since 1st January 1970, 00:00:00 UTC and tv_nsec is the number of
+ * 1-nano-second intervals since the value of tv_sec.
+ *
+ * NTFS uses Microsoft's standard time format which is stored in a s64 and is
+ * measured as the number of 100 nano-second intervals since 1st January 1601,
+ * 00:00:00 UTC.
+ */
+static inline struct timespec ntfs2utc(const sle64 time)
+{
+	struct timespec ts;
+
+	/* Subtract the NTFS time offset. */
+	u64 t = (u64)(sle64_to_cpu(time) - NTFS_TIME_OFFSET);
+	/*
+	 * Convert the time to 1-second intervals and the remainder to
+	 * 1-nano-second intervals.
+	 */
+	ts.tv_nsec = do_div(t, 10000000) * 100;
+	ts.tv_sec = t;
+	return ts;
+}
+
+#endif /* _LINUX_NTFS_TIME_H */

fs/ntfs/types.h

@@ -0,0 +1,69 @@
+/*
+ * types.h - Defines for NTFS Linux kernel driver specific types.
+ *	     Part of the Linux-NTFS project.
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_TYPES_H
+#define _LINUX_NTFS_TYPES_H
+
+#include <linux/types.h>
+
+typedef __le16 le16;
+typedef __le32 le32;
+typedef __le64 le64;
+typedef __u16 __bitwise sle16;
+typedef __u32 __bitwise sle32;
+typedef __u64 __bitwise sle64;
+
+/* 2-byte Unicode character type. */
+typedef le16 ntfschar;
+#define UCHAR_T_SIZE_BITS 1
+
+/*
+ * Clusters are signed 64-bit values on NTFS volumes. We define two types, LCN
+ * and VCN, to allow for type checking and better code readability.
+ */
+typedef s64 VCN;
+typedef sle64 leVCN;
+typedef s64 LCN;
+typedef sle64 leLCN;
+
+/*
+ * The NTFS journal $LogFile uses log sequence numbers which are signed 64-bit
+ * values.  We define our own type LSN, to allow for type checking and better
+ * code readability.
+ */
+typedef s64 LSN;
+typedef sle64 leLSN;
+
+/*
+ * The NTFS transaction log $UsnJrnl uses usn which are signed 64-bit values.
+ * We define our own type USN, to allow for type checking and better code
+ * readability.
+ */
+typedef s64 USN;
+typedef sle64 leUSN;
+
+typedef enum {
+	CASE_SENSITIVE = 0,
+	IGNORE_CASE = 1,
+} IGNORE_CASE_BOOL;
+
+#endif /* _LINUX_NTFS_TYPES_H */

fs/ntfs/unistr.c

@@ -0,0 +1,398 @@
+/*
+ * unistr.c - NTFS Unicode string handling. Part of the Linux-NTFS project.
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/slab.h>
+
+#include "types.h"
+#include "debug.h"
+#include "ntfs.h"
+
+/*
+ * IMPORTANT
+ * =========
+ *
+ * All these routines assume that the Unicode characters are in little endian
+ * encoding inside the strings!!!
+ */
+
+/*
+ * This is used by the name collation functions to quickly determine what
+ * characters are (in)valid.
+ */
+static const u8 legal_ansi_char_array[0x40] = {
+	0x00, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+
+	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+
+	0x17, 0x07, 0x18, 0x17, 0x17, 0x17, 0x17, 0x17,
+	0x17, 0x17, 0x18, 0x16, 0x16, 0x17, 0x07, 0x00,
+
+	0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17,
+	0x17, 0x17, 0x04, 0x16, 0x18, 0x16, 0x18, 0x18,
+};
+
+/**
+ * ntfs_are_names_equal - compare two Unicode names for equality
+ * @s1:			name to compare to @s2
+ * @s1_len:		length in Unicode characters of @s1
+ * @s2:			name to compare to @s1
+ * @s2_len:		length in Unicode characters of @s2
+ * @ic:			ignore case bool
+ * @upcase:		upcase table (only if @ic == IGNORE_CASE)
+ * @upcase_size:	length in Unicode characters of @upcase (if present)
+ *
+ * Compare the names @s1 and @s2 and return 'true' (1) if the names are
+ * identical, or 'false' (0) if they are not identical. If @ic is IGNORE_CASE,
+ * the @upcase table is used to performa a case insensitive comparison.
+ */
+bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
+		const ntfschar *s2, size_t s2_len, const IGNORE_CASE_BOOL ic,
+		const ntfschar *upcase, const u32 upcase_size)
+{
+	if (s1_len != s2_len)
+		return false;
+	if (ic == CASE_SENSITIVE)
+		return !ntfs_ucsncmp(s1, s2, s1_len);
+	return !ntfs_ucsncasecmp(s1, s2, s1_len, upcase, upcase_size);
+}
+
+/**
+ * ntfs_collate_names - collate two Unicode names
+ * @name1:	first Unicode name to compare
+ * @name2:	second Unicode name to compare
+ * @err_val:	if @name1 contains an invalid character return this value
+ * @ic:		either CASE_SENSITIVE or IGNORE_CASE
+ * @upcase:	upcase table (ignored if @ic is CASE_SENSITIVE)
+ * @upcase_len:	upcase table size (ignored if @ic is CASE_SENSITIVE)
+ *
+ * ntfs_collate_names collates two Unicode names and returns:
+ *
+ *  -1 if the first name collates before the second one,
+ *   0 if the names match,
+ *   1 if the second name collates before the first one, or
+ * @err_val if an invalid character is found in @name1 during the comparison.
+ *
+ * The following characters are considered invalid: '"', '*', '<', '>' and '?'.
+ */
+int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
+		const ntfschar *name2, const u32 name2_len,
+		const int err_val, const IGNORE_CASE_BOOL ic,
+		const ntfschar *upcase, const u32 upcase_len)
+{
+	u32 cnt, min_len;
+	u16 c1, c2;
+
+	min_len = name1_len;
+	if (name1_len > name2_len)
+		min_len = name2_len;
+	for (cnt = 0; cnt < min_len; ++cnt) {
+		c1 = le16_to_cpu(*name1++);
+		c2 = le16_to_cpu(*name2++);
+		if (ic) {
+			if (c1 < upcase_len)
+				c1 = le16_to_cpu(upcase[c1]);
+			if (c2 < upcase_len)
+				c2 = le16_to_cpu(upcase[c2]);
+		}
+		if (c1 < 64 && legal_ansi_char_array[c1] & 8)
+			return err_val;
+		if (c1 < c2)
+			return -1;
+		if (c1 > c2)
+			return 1;
+	}
+	if (name1_len < name2_len)
+		return -1;
+	if (name1_len == name2_len)
+		return 0;
+	/* name1_len > name2_len */
+	c1 = le16_to_cpu(*name1);
+	if (c1 < 64 && legal_ansi_char_array[c1] & 8)
+		return err_val;
+	return 1;
+}
+
+/**
+ * ntfs_ucsncmp - compare two little endian Unicode strings
+ * @s1:		first string
+ * @s2:		second string
+ * @n:		maximum unicode characters to compare
+ *
+ * Compare the first @n characters of the Unicode strings @s1 and @s2,
+ * The strings in little endian format and appropriate le16_to_cpu()
+ * conversion is performed on non-little endian machines.
+ *
+ * The function returns an integer less than, equal to, or greater than zero
+ * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
+ * to be less than, to match, or be greater than @s2.
+ */
+int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n)
+{
+	u16 c1, c2;
+	size_t i;
+
+	for (i = 0; i < n; ++i) {
+		c1 = le16_to_cpu(s1[i]);
+		c2 = le16_to_cpu(s2[i]);
+		if (c1 < c2)
+			return -1;
+		if (c1 > c2)
+			return 1;
+		if (!c1)
+			break;
+	}
+	return 0;
+}
+
+/**
+ * ntfs_ucsncasecmp - compare two little endian Unicode strings, ignoring case
+ * @s1:			first string
+ * @s2:			second string
+ * @n:			maximum unicode characters to compare
+ * @upcase:		upcase table
+ * @upcase_size:	upcase table size in Unicode characters
+ *
+ * Compare the first @n characters of the Unicode strings @s1 and @s2,
+ * ignoring case. The strings in little endian format and appropriate
+ * le16_to_cpu() conversion is performed on non-little endian machines.
+ *
+ * Each character is uppercased using the @upcase table before the comparison.
+ *
+ * The function returns an integer less than, equal to, or greater than zero
+ * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
+ * to be less than, to match, or be greater than @s2.
+ */
+int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
+		const ntfschar *upcase, const u32 upcase_size)
+{
+	size_t i;
+	u16 c1, c2;
+
+	for (i = 0; i < n; ++i) {
+		if ((c1 = le16_to_cpu(s1[i])) < upcase_size)
+			c1 = le16_to_cpu(upcase[c1]);
+		if ((c2 = le16_to_cpu(s2[i])) < upcase_size)
+			c2 = le16_to_cpu(upcase[c2]);
+		if (c1 < c2)
+			return -1;
+		if (c1 > c2)
+			return 1;
+		if (!c1)
+			break;
+	}
+	return 0;
+}
+
+void ntfs_upcase_name(ntfschar *name, u32 name_len, const ntfschar *upcase,
+		const u32 upcase_len)
+{
+	u32 i;
+	u16 u;
+
+	for (i = 0; i < name_len; i++)
+		if ((u = le16_to_cpu(name[i])) < upcase_len)
+			name[i] = upcase[u];
+}
+
+void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
+		const ntfschar *upcase, const u32 upcase_len)
+{
+	ntfs_upcase_name((ntfschar*)&file_name_attr->file_name,
+			file_name_attr->file_name_length, upcase, upcase_len);
+}
+
+int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
+		FILE_NAME_ATTR *file_name_attr2,
+		const int err_val, const IGNORE_CASE_BOOL ic,
+		const ntfschar *upcase, const u32 upcase_len)
+{
+	return ntfs_collate_names((ntfschar*)&file_name_attr1->file_name,
+			file_name_attr1->file_name_length,
+			(ntfschar*)&file_name_attr2->file_name,
+			file_name_attr2->file_name_length,
+			err_val, ic, upcase, upcase_len);
+}
+
+/**
+ * ntfs_nlstoucs - convert NLS string to little endian Unicode string
+ * @vol:	ntfs volume which we are working with
+ * @ins:	input NLS string buffer
+ * @ins_len:	length of input string in bytes
+ * @outs:	on return contains the allocated output Unicode string buffer
+ *
+ * Convert the input string @ins, which is in whatever format the loaded NLS
+ * map dictates, into a little endian, 2-byte Unicode string.
+ *
+ * This function allocates the string and the caller is responsible for
+ * calling kmem_cache_free(ntfs_name_cache, *@outs); when finished with it.
+ *
+ * On success the function returns the number of Unicode characters written to
+ * the output string *@outs (>= 0), not counting the terminating Unicode NULL
+ * character. *@outs is set to the allocated output string buffer.
+ *
+ * On error, a negative number corresponding to the error code is returned. In
+ * that case the output string is not allocated. Both *@outs and *@outs_len
+ * are then undefined.
+ *
+ * This might look a bit odd due to fast path optimization...
+ */
+int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
+		const int ins_len, ntfschar **outs)
+{
+	struct nls_table *nls = vol->nls_map;
+	ntfschar *ucs;
+	wchar_t wc;
+	int i, o, wc_len;
+
+	/* We do not trust outside sources. */
+	if (likely(ins)) {
+		ucs = kmem_cache_alloc(ntfs_name_cache, GFP_NOFS);
+		if (likely(ucs)) {
+			for (i = o = 0; i < ins_len; i += wc_len) {
+				wc_len = nls->char2uni(ins + i, ins_len - i,
+						&wc);
+				if (likely(wc_len >= 0 &&
+						o < NTFS_MAX_NAME_LEN)) {
+					if (likely(wc)) {
+						ucs[o++] = cpu_to_le16(wc);
+						continue;
+					} /* else if (!wc) */
+					break;
+				} /* else if (wc_len < 0 ||
+						o >= NTFS_MAX_NAME_LEN) */
+				goto name_err;
+			}
+			ucs[o] = 0;
+			*outs = ucs;
+			return o;
+		} /* else if (!ucs) */
+		ntfs_error(vol->sb, "Failed to allocate buffer for converted "
+				"name from ntfs_name_cache.");
+		return -ENOMEM;
+	} /* else if (!ins) */
+	ntfs_error(vol->sb, "Received NULL pointer.");
+	return -EINVAL;
+name_err:
+	kmem_cache_free(ntfs_name_cache, ucs);
+	if (wc_len < 0) {
+		ntfs_error(vol->sb, "Name using character set %s contains "
+				"characters that cannot be converted to "
+				"Unicode.", nls->charset);
+		i = -EILSEQ;
+	} else /* if (o >= NTFS_MAX_NAME_LEN) */ {
+		ntfs_error(vol->sb, "Name is too long (maximum length for a "
+				"name on NTFS is %d Unicode characters.",
+				NTFS_MAX_NAME_LEN);
+		i = -ENAMETOOLONG;
+	}
+	return i;
+}
+
+/**
+ * ntfs_ucstonls - convert little endian Unicode string to NLS string
+ * @vol:	ntfs volume which we are working with
+ * @ins:	input Unicode string buffer
+ * @ins_len:	length of input string in Unicode characters
+ * @outs:	on return contains the (allocated) output NLS string buffer
+ * @outs_len:	length of output string buffer in bytes
+ *
+ * Convert the input little endian, 2-byte Unicode string @ins, of length
+ * @ins_len into the string format dictated by the loaded NLS.
+ *
+ * If *@outs is NULL, this function allocates the string and the caller is
+ * responsible for calling kfree(*@outs); when finished with it. In this case
+ * @outs_len is ignored and can be 0.
+ *
+ * On success the function returns the number of bytes written to the output
+ * string *@outs (>= 0), not counting the terminating NULL byte. If the output
+ * string buffer was allocated, *@outs is set to it.
+ *
+ * On error, a negative number corresponding to the error code is returned. In
+ * that case the output string is not allocated. The contents of *@outs are
+ * then undefined.
+ *
+ * This might look a bit odd due to fast path optimization...
+ */
+int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
+		const int ins_len, unsigned char **outs, int outs_len)
+{
+	struct nls_table *nls = vol->nls_map;
+	unsigned char *ns;
+	int i, o, ns_len, wc;
+
+	/* We don't trust outside sources. */
+	if (ins) {
+		ns = *outs;
+		ns_len = outs_len;
+		if (ns && !ns_len) {
+			wc = -ENAMETOOLONG;
+			goto conversion_err;
+		}
+		if (!ns) {
+			ns_len = ins_len * NLS_MAX_CHARSET_SIZE;
+			ns = kmalloc(ns_len + 1, GFP_NOFS);
+			if (!ns)
+				goto mem_err_out;
+		}
+		for (i = o = 0; i < ins_len; i++) {
+retry:			wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
+					ns_len - o);
+			if (wc > 0) {
+				o += wc;
+				continue;
+			} else if (!wc)
+				break;
+			else if (wc == -ENAMETOOLONG && ns != *outs) {
+				unsigned char *tc;
+				/* Grow in multiples of 64 bytes. */
+				tc = kmalloc((ns_len + 64) &
+						~63, GFP_NOFS);
+				if (tc) {
+					memcpy(tc, ns, ns_len);
+					ns_len = ((ns_len + 64) & ~63) - 1;
+					kfree(ns);
+					ns = tc;
+					goto retry;
+				} /* No memory so goto conversion_error; */
+			} /* wc < 0, real error. */
+			goto conversion_err;
+		}
+		ns[o] = 0;
+		*outs = ns;
+		return o;
+	} /* else (!ins) */
+	ntfs_error(vol->sb, "Received NULL pointer.");
+	return -EINVAL;
+conversion_err:
+	ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
+			"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)
+		wc = -EILSEQ;
+	return wc;
+mem_err_out:
+	ntfs_error(vol->sb, "Failed to allocate name!");
+	return -ENOMEM;
+}

fs/ntfs/upcase.c

@@ -0,0 +1,87 @@
+/*
+ * upcase.c - Generate the full NTFS Unicode upcase table in little endian.
+ *	      Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
+ * Copyright (c) 2001-2006 Anton Altaparmakov
+ *
+ * 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
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS source
+ * in the file COPYING); if not, write to the Free Software Foundation,
+ * Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include "malloc.h"
+#include "ntfs.h"
+
+ntfschar *generate_default_upcase(void)
+{
+	static const int uc_run_table[][3] = { /* Start, End, Add */
+	{0x0061, 0x007B,  -32}, {0x0451, 0x045D, -80}, {0x1F70, 0x1F72,  74},
+	{0x00E0, 0x00F7,  -32}, {0x045E, 0x0460, -80}, {0x1F72, 0x1F76,  86},
+	{0x00F8, 0x00FF,  -32}, {0x0561, 0x0587, -48}, {0x1F76, 0x1F78, 100},
+	{0x0256, 0x0258, -205}, {0x1F00, 0x1F08,   8}, {0x1F78, 0x1F7A, 128},
+	{0x028A, 0x028C, -217}, {0x1F10, 0x1F16,   8}, {0x1F7A, 0x1F7C, 112},
+	{0x03AC, 0x03AD,  -38}, {0x1F20, 0x1F28,   8}, {0x1F7C, 0x1F7E, 126},
+	{0x03AD, 0x03B0,  -37}, {0x1F30, 0x1F38,   8}, {0x1FB0, 0x1FB2,   8},
+	{0x03B1, 0x03C2,  -32}, {0x1F40, 0x1F46,   8}, {0x1FD0, 0x1FD2,   8},
+	{0x03C2, 0x03C3,  -31}, {0x1F51, 0x1F52,   8}, {0x1FE0, 0x1FE2,   8},
+	{0x03C3, 0x03CC,  -32}, {0x1F53, 0x1F54,   8}, {0x1FE5, 0x1FE6,   7},
+	{0x03CC, 0x03CD,  -64}, {0x1F55, 0x1F56,   8}, {0x2170, 0x2180, -16},
+	{0x03CD, 0x03CF,  -63}, {0x1F57, 0x1F58,   8}, {0x24D0, 0x24EA, -26},
+	{0x0430, 0x0450,  -32}, {0x1F60, 0x1F68,   8}, {0xFF41, 0xFF5B, -32},
+	{0}
+	};
+
+	static const int uc_dup_table[][2] = { /* Start, End */
+	{0x0100, 0x012F}, {0x01A0, 0x01A6}, {0x03E2, 0x03EF}, {0x04CB, 0x04CC},
+	{0x0132, 0x0137}, {0x01B3, 0x01B7}, {0x0460, 0x0481}, {0x04D0, 0x04EB},
+	{0x0139, 0x0149}, {0x01CD, 0x01DD}, {0x0490, 0x04BF}, {0x04EE, 0x04F5},
+	{0x014A, 0x0178}, {0x01DE, 0x01EF}, {0x04BF, 0x04BF}, {0x04F8, 0x04F9},
+	{0x0179, 0x017E}, {0x01F4, 0x01F5}, {0x04C1, 0x04C4}, {0x1E00, 0x1E95},
+	{0x018B, 0x018B}, {0x01FA, 0x0218}, {0x04C7, 0x04C8}, {0x1EA0, 0x1EF9},
+	{0}
+	};
+
+	static const int uc_word_table[][2] = { /* Offset, Value */
+	{0x00FF, 0x0178}, {0x01AD, 0x01AC}, {0x01F3, 0x01F1}, {0x0269, 0x0196},
+	{0x0183, 0x0182}, {0x01B0, 0x01AF}, {0x0253, 0x0181}, {0x026F, 0x019C},
+	{0x0185, 0x0184}, {0x01B9, 0x01B8}, {0x0254, 0x0186}, {0x0272, 0x019D},
+	{0x0188, 0x0187}, {0x01BD, 0x01BC}, {0x0259, 0x018F}, {0x0275, 0x019F},
+	{0x018C, 0x018B}, {0x01C6, 0x01C4}, {0x025B, 0x0190}, {0x0283, 0x01A9},
+	{0x0192, 0x0191}, {0x01C9, 0x01C7}, {0x0260, 0x0193}, {0x0288, 0x01AE},
+	{0x0199, 0x0198}, {0x01CC, 0x01CA}, {0x0263, 0x0194}, {0x0292, 0x01B7},
+	{0x01A8, 0x01A7}, {0x01DD, 0x018E}, {0x0268, 0x0197},
+	{0}
+	};
+
+	int i, r;
+	ntfschar *uc;
+
+	uc = ntfs_malloc_nofs(default_upcase_len * sizeof(ntfschar));
+	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++)
+			le16_add_cpu(&uc[i], 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)
+			le16_add_cpu(&uc[i + 1], -1);
+	for (r = 0; uc_word_table[r][0]; r++)
+		uc[uc_word_table[r][0]] = cpu_to_le16(uc_word_table[r][1]);
+	return uc;
+}

fs/ntfs/usnjrnl.c

@@ -0,0 +1,84 @@
+/*
+ * usnjrnl.h - NTFS kernel transaction log ($UsnJrnl) handling.  Part of the
+ *	       Linux-NTFS project.
+ *
+ * Copyright (c) 2005 Anton Altaparmakov
+ *
+ * This program/include file is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifdef NTFS_RW
+
+#include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+
+#include "aops.h"
+#include "debug.h"
+#include "endian.h"
+#include "time.h"
+#include "types.h"
+#include "usnjrnl.h"
+#include "volume.h"
+
+/**
+ * ntfs_stamp_usnjrnl - stamp the transaction log ($UsnJrnl) on an ntfs volume
+ * @vol:	ntfs volume on which to stamp the transaction log
+ *
+ * Stamp the transaction log ($UsnJrnl) on the ntfs volume @vol and return
+ * 'true' on success and 'false' on error.
+ *
+ * This function assumes that the transaction log has already been loaded and
+ * consistency checked by a call to fs/ntfs/super.c::load_and_init_usnjrnl().
+ */
+bool ntfs_stamp_usnjrnl(ntfs_volume *vol)
+{
+	ntfs_debug("Entering.");
+	if (likely(!NVolUsnJrnlStamped(vol))) {
+		sle64 stamp;
+		struct page *page;
+		USN_HEADER *uh;
+
+		page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
+		if (IS_ERR(page)) {
+			ntfs_error(vol->sb, "Failed to read from "
+					"$UsnJrnl/$DATA/$Max attribute.");
+			return false;
+		}
+		uh = (USN_HEADER*)page_address(page);
+		stamp = get_current_ntfs_time();
+		ntfs_debug("Stamping transaction log ($UsnJrnl): old "
+				"journal_id 0x%llx, old lowest_valid_usn "
+				"0x%llx, new journal_id 0x%llx, new "
+				"lowest_valid_usn 0x%llx.",
+				(long long)sle64_to_cpu(uh->journal_id),
+				(long long)sle64_to_cpu(uh->lowest_valid_usn),
+				(long long)sle64_to_cpu(stamp),
+				i_size_read(vol->usnjrnl_j_ino));
+		uh->lowest_valid_usn =
+				cpu_to_sle64(i_size_read(vol->usnjrnl_j_ino));
+		uh->journal_id = stamp;
+		flush_dcache_page(page);
+		set_page_dirty(page);
+		ntfs_unmap_page(page);
+		/* Set the flag so we do not have to do it again on remount. */
+		NVolSetUsnJrnlStamped(vol);
+	}
+	ntfs_debug("Done.");
+	return true;
+}
+
+#endif /* NTFS_RW */

fs/ntfs/usnjrnl.h

@@ -0,0 +1,205 @@
+/*
+ * usnjrnl.h - Defines for NTFS kernel transaction log ($UsnJrnl) handling.
+ *	       Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2005 Anton Altaparmakov
+ *
+ * This program/include file is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_USNJRNL_H
+#define _LINUX_NTFS_USNJRNL_H
+
+#ifdef NTFS_RW
+
+#include "types.h"
+#include "endian.h"
+#include "layout.h"
+#include "volume.h"
+
+/*
+ * Transaction log ($UsnJrnl) organization:
+ *
+ * The transaction log records whenever a file is modified in any way.  So for
+ * example it will record that file "blah" was written to at a particular time
+ * but not what was written.  If will record that a file was deleted or
+ * created, that a file was truncated, etc.  See below for all the reason
+ * codes used.
+ *
+ * The transaction log is in the $Extend directory which is in the root
+ * directory of each volume.  If it is not present it means transaction
+ * logging is disabled.  If it is present it means transaction logging is
+ * either enabled or in the process of being disabled in which case we can
+ * ignore it as it will go away as soon as Windows gets its hands on it.
+ *
+ * To determine whether the transaction logging is enabled or in the process
+ * of being disabled, need to check the volume flags in the
+ * $VOLUME_INFORMATION attribute in the $Volume system file (which is present
+ * in the root directory and has a fixed mft record number, see layout.h).
+ * If the flag VOLUME_DELETE_USN_UNDERWAY is set it means the transaction log
+ * is in the process of being disabled and if this flag is clear it means the
+ * transaction log is enabled.
+ *
+ * The transaction log consists of two parts; the $DATA/$Max attribute as well
+ * as the $DATA/$J attribute.  $Max is a header describing the transaction
+ * log whilst $J is the transaction log data itself as a sequence of variable
+ * sized USN_RECORDs (see below for all the structures).
+ *
+ * We do not care about transaction logging at this point in time but we still
+ * need to let windows know that the transaction log is out of date.  To do
+ * this we need to stamp the transaction log.  This involves setting the
+ * lowest_valid_usn field in the $DATA/$Max attribute to the usn to be used
+ * for the next added USN_RECORD to the $DATA/$J attribute as well as
+ * generating a new journal_id in $DATA/$Max.
+ *
+ * The journal_id is as of the current version (2.0) of the transaction log
+ * simply the 64-bit timestamp of when the journal was either created or last
+ * stamped.
+ *
+ * To determine the next usn there are two ways.  The first is to parse
+ * $DATA/$J and to find the last USN_RECORD in it and to add its record_length
+ * to its usn (which is the byte offset in the $DATA/$J attribute).  The
+ * second is simply to take the data size of the attribute.  Since the usns
+ * are simply byte offsets into $DATA/$J, this is exactly the next usn.  For
+ * obvious reasons we use the second method as it is much simpler and faster.
+ *
+ * As an aside, note that to actually disable the transaction log, one would
+ * need to set the VOLUME_DELETE_USN_UNDERWAY flag (see above), then go
+ * through all the mft records on the volume and set the usn field in their
+ * $STANDARD_INFORMATION attribute to zero.  Once that is done, one would need
+ * to delete the transaction log file, i.e. \$Extent\$UsnJrnl, and finally,
+ * one would need to clear the VOLUME_DELETE_USN_UNDERWAY flag.
+ *
+ * Note that if a volume is unmounted whilst the transaction log is being
+ * disabled, the process will continue the next time the volume is mounted.
+ * This is why we can safely mount read-write when we see a transaction log
+ * in the process of being deleted.
+ */
+
+/* Some $UsnJrnl related constants. */
+#define UsnJrnlMajorVer		2
+#define UsnJrnlMinorVer		0
+
+/*
+ * $DATA/$Max attribute.  This is (always?) resident and has a fixed size of
+ * 32 bytes.  It contains the header describing the transaction log.
+ */
+typedef struct {
+/*Ofs*/
+/*   0*/sle64 maximum_size;	/* The maximum on-disk size of the $DATA/$J
+				   attribute. */
+/*   8*/sle64 allocation_delta;	/* Number of bytes by which to increase the
+				   size of the $DATA/$J attribute. */
+/*0x10*/sle64 journal_id;	/* Current id of the transaction log. */
+/*0x18*/leUSN lowest_valid_usn;	/* Lowest valid usn in $DATA/$J for the
+				   current journal_id. */
+/* sizeof() = 32 (0x20) bytes */
+} __attribute__ ((__packed__)) USN_HEADER;
+
+/*
+ * Reason flags (32-bit).  Cumulative flags describing the change(s) to the
+ * file since it was last opened.  I think the names speak for themselves but
+ * if you disagree check out the descriptions in the Linux NTFS project NTFS
+ * documentation: http://www.linux-ntfs.org/
+ */
+enum {
+	USN_REASON_DATA_OVERWRITE	= cpu_to_le32(0x00000001),
+	USN_REASON_DATA_EXTEND		= cpu_to_le32(0x00000002),
+	USN_REASON_DATA_TRUNCATION	= cpu_to_le32(0x00000004),
+	USN_REASON_NAMED_DATA_OVERWRITE	= cpu_to_le32(0x00000010),
+	USN_REASON_NAMED_DATA_EXTEND	= cpu_to_le32(0x00000020),
+	USN_REASON_NAMED_DATA_TRUNCATION= cpu_to_le32(0x00000040),
+	USN_REASON_FILE_CREATE		= cpu_to_le32(0x00000100),
+	USN_REASON_FILE_DELETE		= cpu_to_le32(0x00000200),
+	USN_REASON_EA_CHANGE		= cpu_to_le32(0x00000400),
+	USN_REASON_SECURITY_CHANGE	= cpu_to_le32(0x00000800),
+	USN_REASON_RENAME_OLD_NAME	= cpu_to_le32(0x00001000),
+	USN_REASON_RENAME_NEW_NAME	= cpu_to_le32(0x00002000),
+	USN_REASON_INDEXABLE_CHANGE	= cpu_to_le32(0x00004000),
+	USN_REASON_BASIC_INFO_CHANGE	= cpu_to_le32(0x00008000),
+	USN_REASON_HARD_LINK_CHANGE	= cpu_to_le32(0x00010000),
+	USN_REASON_COMPRESSION_CHANGE	= cpu_to_le32(0x00020000),
+	USN_REASON_ENCRYPTION_CHANGE	= cpu_to_le32(0x00040000),
+	USN_REASON_OBJECT_ID_CHANGE	= cpu_to_le32(0x00080000),
+	USN_REASON_REPARSE_POINT_CHANGE	= cpu_to_le32(0x00100000),
+	USN_REASON_STREAM_CHANGE	= cpu_to_le32(0x00200000),
+	USN_REASON_CLOSE		= cpu_to_le32(0x80000000),
+};
+
+typedef le32 USN_REASON_FLAGS;
+
+/*
+ * Source info flags (32-bit).  Information about the source of the change(s)
+ * to the file.  For detailed descriptions of what these mean, see the Linux
+ * NTFS project NTFS documentation:
+ *	http://www.linux-ntfs.org/
+ */
+enum {
+	USN_SOURCE_DATA_MANAGEMENT	  = cpu_to_le32(0x00000001),
+	USN_SOURCE_AUXILIARY_DATA	  = cpu_to_le32(0x00000002),
+	USN_SOURCE_REPLICATION_MANAGEMENT = cpu_to_le32(0x00000004),
+};
+
+typedef le32 USN_SOURCE_INFO_FLAGS;
+
+/*
+ * $DATA/$J attribute.  This is always non-resident, is marked as sparse, and
+ * is of variabled size.  It consists of a sequence of variable size
+ * USN_RECORDS.  The minimum allocated_size is allocation_delta as
+ * specified in $DATA/$Max.  When the maximum_size specified in $DATA/$Max is
+ * exceeded by more than allocation_delta bytes, allocation_delta bytes are
+ * allocated and appended to the $DATA/$J attribute and an equal number of
+ * bytes at the beginning of the attribute are freed and made sparse.  Note the
+ * making sparse only happens at volume checkpoints and hence the actual
+ * $DATA/$J size can exceed maximum_size + allocation_delta temporarily.
+ */
+typedef struct {
+/*Ofs*/
+/*   0*/le32 length;		/* Byte size of this record (8-byte
+				   aligned). */
+/*   4*/le16 major_ver;		/* Major version of the transaction log used
+				   for this record. */
+/*   6*/le16 minor_ver;		/* Minor version of the transaction log used
+				   for this record. */
+/*   8*/leMFT_REF mft_reference;/* The mft reference of the file (or
+				   directory) described by this record. */
+/*0x10*/leMFT_REF parent_directory;/* The mft reference of the parent
+				   directory of the file described by this
+				   record. */
+/*0x18*/leUSN usn;		/* The usn of this record.  Equals the offset
+				   within the $DATA/$J attribute. */
+/*0x20*/sle64 time;		/* Time when this record was created. */
+/*0x28*/USN_REASON_FLAGS reason;/* Reason flags (see above). */
+/*0x2c*/USN_SOURCE_INFO_FLAGS source_info;/* Source info flags (see above). */
+/*0x30*/le32 security_id;	/* File security_id copied from
+				   $STANDARD_INFORMATION. */
+/*0x34*/FILE_ATTR_FLAGS file_attributes;	/* File attributes copied from
+				   $STANDARD_INFORMATION or $FILE_NAME (not
+				   sure which). */
+/*0x38*/le16 file_name_size;	/* Size of the file name in bytes. */
+/*0x3a*/le16 file_name_offset;	/* Offset to the file name in bytes from the
+				   start of this record. */
+/*0x3c*/ntfschar file_name[0];	/* Use when creating only.  When reading use
+				   file_name_offset to determine the location
+				   of the name. */
+/* sizeof() = 60 (0x3c) bytes */
+} __attribute__ ((__packed__)) USN_RECORD;
+
+extern bool ntfs_stamp_usnjrnl(ntfs_volume *vol);
+
+#endif /* NTFS_RW */
+
+#endif /* _LINUX_NTFS_USNJRNL_H */

fs/ntfs/volume.h

@@ -0,0 +1,178 @@
+/*
+ * volume.h - Defines for volume structures in NTFS Linux kernel driver. Part
+ *	      of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2006 Anton Altaparmakov
+ * Copyright (c) 2002 Richard Russon
+ *
+ * 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
+ * by the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program/include file is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program (in the main directory of the Linux-NTFS
+ * distribution in the file COPYING); if not, write to the Free Software
+ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef _LINUX_NTFS_VOLUME_H
+#define _LINUX_NTFS_VOLUME_H
+
+#include <linux/rwsem.h>
+#include <linux/uidgid.h>
+
+#include "types.h"
+#include "layout.h"
+
+/*
+ * The NTFS in memory super block structure.
+ */
+typedef struct {
+	/*
+	 * FIXME: Reorder to have commonly used together element within the
+	 * same cache line, aiming at a cache line size of 32 bytes. Aim for
+	 * 64 bytes for less commonly used together elements. Put most commonly
+	 * used elements to front of structure. Obviously do this only when the
+	 * structure has stabilized... (AIA)
+	 */
+	/* Device specifics. */
+	struct super_block *sb;		/* Pointer back to the super_block. */
+	LCN nr_blocks;			/* Number of sb->s_blocksize bytes
+					   sized blocks on the device. */
+	/* Configuration provided by user at mount time. */
+	unsigned long flags;		/* Miscellaneous flags, see below. */
+	kuid_t uid;			/* uid that files will be mounted as. */
+	kgid_t gid;			/* gid that files will be mounted as. */
+	umode_t fmask;			/* The mask for file permissions. */
+	umode_t dmask;			/* The mask for directory
+					   permissions. */
+	u8 mft_zone_multiplier;		/* Initial mft zone multiplier. */
+	u8 on_errors;			/* What to do on filesystem errors. */
+	/* NTFS bootsector provided information. */
+	u16 sector_size;		/* in bytes */
+	u8 sector_size_bits;		/* log2(sector_size) */
+	u32 cluster_size;		/* in bytes */
+	u32 cluster_size_mask;		/* cluster_size - 1 */
+	u8 cluster_size_bits;		/* log2(cluster_size) */
+	u32 mft_record_size;		/* in bytes */
+	u32 mft_record_size_mask;	/* mft_record_size - 1 */
+	u8 mft_record_size_bits;	/* log2(mft_record_size) */
+	u32 index_record_size;		/* in bytes */
+	u32 index_record_size_mask;	/* index_record_size - 1 */
+	u8 index_record_size_bits;	/* log2(index_record_size) */
+	LCN nr_clusters;		/* Volume size in clusters == number of
+					   bits in lcn bitmap. */
+	LCN mft_lcn;			/* Cluster location of mft data. */
+	LCN mftmirr_lcn;		/* Cluster location of copy of mft. */
+	u64 serial_no;			/* The volume serial number. */
+	/* Mount specific NTFS information. */
+	u32 upcase_len;			/* Number of entries in upcase[]. */
+	ntfschar *upcase;		/* The upcase table. */
+
+	s32 attrdef_size;		/* Size of the attribute definition
+					   table in bytes. */
+	ATTR_DEF *attrdef;		/* Table of attribute definitions.
+					   Obtained from FILE_AttrDef. */
+
+#ifdef NTFS_RW
+	/* Variables used by the cluster and mft allocators. */
+	s64 mft_data_pos;		/* Mft record number at which to
+					   allocate the next mft record. */
+	LCN mft_zone_start;		/* First cluster of the mft zone. */
+	LCN mft_zone_end;		/* First cluster beyond the mft zone. */
+	LCN mft_zone_pos;		/* Current position in the mft zone. */
+	LCN data1_zone_pos;		/* Current position in the first data
+					   zone. */
+	LCN data2_zone_pos;		/* Current position in the second data
+					   zone. */
+#endif /* NTFS_RW */
+
+	struct inode *mft_ino;		/* The VFS inode of $MFT. */
+
+	struct inode *mftbmp_ino;	/* Attribute inode for $MFT/$BITMAP. */
+	struct rw_semaphore mftbmp_lock; /* Lock for serializing accesses to the
+					    mft record bitmap ($MFT/$BITMAP). */
+#ifdef NTFS_RW
+	struct inode *mftmirr_ino;	/* The VFS inode of $MFTMirr. */
+	int mftmirr_size;		/* Size of mft mirror in mft records. */
+
+	struct inode *logfile_ino;	/* The VFS inode of $LogFile. */
+#endif /* NTFS_RW */
+
+	struct inode *lcnbmp_ino;	/* The VFS inode of $Bitmap. */
+	struct rw_semaphore lcnbmp_lock; /* Lock for serializing accesses to the
+					    cluster bitmap ($Bitmap/$DATA). */
+
+	struct inode *vol_ino;		/* The VFS inode of $Volume. */
+	VOLUME_FLAGS vol_flags;		/* Volume flags. */
+	u8 major_ver;			/* Ntfs major version of volume. */
+	u8 minor_ver;			/* Ntfs minor version of volume. */
+
+	struct inode *root_ino;		/* The VFS inode of the root
+					   directory. */
+	struct inode *secure_ino;	/* The VFS inode of $Secure (NTFS3.0+
+					   only, otherwise NULL). */
+	struct inode *extend_ino;	/* The VFS inode of $Extend (NTFS3.0+
+					   only, otherwise NULL). */
+#ifdef NTFS_RW
+	/* $Quota stuff is NTFS3.0+ specific.  Unused/NULL otherwise. */
+	struct inode *quota_ino;	/* The VFS inode of $Quota. */
+	struct inode *quota_q_ino;	/* Attribute inode for $Quota/$Q. */
+	/* $UsnJrnl stuff is NTFS3.0+ specific.  Unused/NULL otherwise. */
+	struct inode *usnjrnl_ino;	/* The VFS inode of $UsnJrnl. */
+	struct inode *usnjrnl_max_ino;	/* Attribute inode for $UsnJrnl/$Max. */
+	struct inode *usnjrnl_j_ino;	/* Attribute inode for $UsnJrnl/$J. */
+#endif /* NTFS_RW */
+	struct nls_table *nls_map;
+} ntfs_volume;
+
+/*
+ * Defined bits for the flags field in the ntfs_volume structure.
+ */
+typedef enum {
+	NV_Errors,		/* 1: Volume has errors, prevent remount rw. */
+	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 but still
+				      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. */
+	NV_SparseEnabled,	/* 1: May create sparse files. */
+} ntfs_volume_flags;
+
+/*
+ * Macro tricks to expand the NVolFoo(), NVolSetFoo(), and NVolClearFoo()
+ * functions.
+ */
+#define DEFINE_NVOL_BIT_OPS(flag)					\
+static inline int NVol##flag(ntfs_volume *vol)		\
+{							\
+	return test_bit(NV_##flag, &(vol)->flags);	\
+}							\
+static inline void NVolSet##flag(ntfs_volume *vol)	\
+{							\
+	set_bit(NV_##flag, &(vol)->flags);		\
+}							\
+static inline void NVolClear##flag(ntfs_volume *vol)	\
+{							\
+	clear_bit(NV_##flag, &(vol)->flags);		\
+}
+
+/* Emit the ntfs volume bitops functions. */
+DEFINE_NVOL_BIT_OPS(Errors)
+DEFINE_NVOL_BIT_OPS(ShowSystemFiles)
+DEFINE_NVOL_BIT_OPS(CaseSensitive)
+DEFINE_NVOL_BIT_OPS(LogFileEmpty)
+DEFINE_NVOL_BIT_OPS(QuotaOutOfDate)
+DEFINE_NVOL_BIT_OPS(UsnJrnlStamped)
+DEFINE_NVOL_BIT_OPS(SparseEnabled)
+
+#endif /* _LINUX_NTFS_VOLUME_H */