Merge git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-linus:
  MAINTAINERS: squashfs entry
  Squashfs: documentation
  Squashfs: initrd support
  Squashfs: Kconfig entry
  Squashfs: Makefiles
  Squashfs: header files
  Squashfs: block operations
  Squashfs: cache operations
  Squashfs: uid/gid lookup operations
  Squashfs: fragment block operations
  Squashfs: export operations
  Squashfs: super block operations
  Squashfs: symlink operations
  Squashfs: regular file operations
  Squashfs: directory readdir operations
  Squashfs: directory lookup operations
  Squashfs: inode operations

Documentation/filesystems/squashfs.txt

+SQUASHFS 4.0 FILESYSTEM
+=======================
+
+Squashfs is a compressed read-only filesystem for Linux.
+It uses zlib compression to compress files, inodes and directories.
+Inodes in the system are very small and all blocks are packed to minimise
+data overhead. Block sizes greater than 4K are supported up to a maximum
+of 1Mbytes (default block size 128K).
+
+Squashfs is intended for general read-only filesystem use, for archival
+use (i.e. in cases where a .tar.gz file may be used), and in constrained
+block device/memory systems (e.g. embedded systems) where low overhead is
+needed.
+
+Mailing list: squashfs-devel@lists.sourceforge.net
+Web site: www.squashfs.org
+
+1. FILESYSTEM FEATURES
+----------------------
+
+Squashfs filesystem features versus Cramfs:
+
+				Squashfs		Cramfs
+
+Max filesystem size:		2^64			16 MiB
+Max file size:			~ 2 TiB			16 MiB
+Max files:			unlimited		unlimited
+Max directories:		unlimited		unlimited
+Max entries per directory:	unlimited		unlimited
+Max block size:			1 MiB			4 KiB
+Metadata compression:		yes			no
+Directory indexes:		yes			no
+Sparse file support:		yes			no
+Tail-end packing (fragments):	yes			no
+Exportable (NFS etc.):		yes			no
+Hard link support:		yes			no
+"." and ".." in readdir:	yes			no
+Real inode numbers:		yes			no
+32-bit uids/gids:		yes			no
+File creation time:		yes			no
+Xattr and ACL support:		no			no
+
+Squashfs compresses data, inodes and directories.  In addition, inode and
+directory data are highly compacted, and packed on byte boundaries.  Each
+compressed inode is on average 8 bytes in length (the exact length varies on
+file type, i.e. regular file, directory, symbolic link, and block/char device
+inodes have different sizes).
+
+2. USING SQUASHFS
+-----------------
+
+As squashfs is a read-only filesystem, the mksquashfs program must be used to
+create populated squashfs filesystems.  This and other squashfs utilities
+can be obtained from http://www.squashfs.org.  Usage instructions can be
+obtained from this site also.
+
+
+3. SQUASHFS FILESYSTEM DESIGN
+-----------------------------
+
+A squashfs filesystem consists of seven parts, packed together on a byte
+alignment:
+
+	 ---------------
+	|  superblock 	|
+	|---------------|
+	|  datablocks   |
+	|  & fragments  |
+	|---------------|
+	|  inode table	|
+	|---------------|
+	|   directory	|
+	|     table     |
+	|---------------|
+	|   fragment	|
+	|    table      |
+	|---------------|
+	|    export     |
+	|    table      |
+	|---------------|
+	|    uid/gid	|
+	|  lookup table	|
+	 ---------------
+
+Compressed data blocks are written to the filesystem as files are read from
+the source directory, and checked for duplicates.  Once all file data has been
+written the completed inode, directory, fragment, export and uid/gid lookup
+tables are written.
+
+3.1 Inodes
+----------
+
+Metadata (inodes and directories) are compressed in 8Kbyte blocks.  Each
+compressed block is prefixed by a two byte length, the top bit is set if the
+block is uncompressed.  A block will be uncompressed if the -noI option is set,
+or if the compressed block was larger than the uncompressed block.
+
+Inodes are packed into the metadata blocks, and are not aligned to block
+boundaries, therefore inodes overlap compressed blocks.  Inodes are identified
+by a 48-bit number which encodes the location of the compressed metadata block
+containing the inode, and the byte offset into that block where the inode is
+placed (<block, offset>).
+
+To maximise compression there are different inodes for each file type
+(regular file, directory, device, etc.), the inode contents and length
+varying with the type.
+
+To further maximise compression, two types of regular file inode and
+directory inode are defined: inodes optimised for frequently occurring
+regular files and directories, and extended types where extra
+information has to be stored.
+
+3.2 Directories
+---------------
+
+Like inodes, directories are packed into compressed metadata blocks, stored
+in a directory table.  Directories are accessed using the start address of
+the metablock containing the directory and the offset into the
+decompressed block (<block, offset>).
+
+Directories are organised in a slightly complex way, and are not simply
+a list of file names.  The organisation takes advantage of the
+fact that (in most cases) the inodes of the files will be in the same
+compressed metadata block, and therefore, can share the start block.
+Directories are therefore organised in a two level list, a directory
+header containing the shared start block value, and a sequence of directory
+entries, each of which share the shared start block.  A new directory header
+is written once/if the inode start block changes.  The directory
+header/directory entry list is repeated as many times as necessary.
+
+Directories are sorted, and can contain a directory index to speed up
+file lookup.  Directory indexes store one entry per metablock, each entry
+storing the index/filename mapping to the first directory header
+in each metadata block.  Directories are sorted in alphabetical order,
+and at lookup the index is scanned linearly looking for the first filename
+alphabetically larger than the filename being looked up.  At this point the
+location of the metadata block the filename is in has been found.
+The general idea of the index is ensure only one metadata block needs to be
+decompressed to do a lookup irrespective of the length of the directory.
+This scheme has the advantage that it doesn't require extra memory overhead
+and doesn't require much extra storage on disk.
+
+3.3 File data
+-------------
+
+Regular files consist of a sequence of contiguous compressed blocks, and/or a
+compressed fragment block (tail-end packed block).   The compressed size
+of each datablock is stored in a block list contained within the
+file inode.
+
+To speed up access to datablocks when reading 'large' files (256 Mbytes or
+larger), the code implements an index cache that caches the mapping from
+block index to datablock location on disk.
+
+The index cache allows Squashfs to handle large files (up to 1.75 TiB) while
+retaining a simple and space-efficient block list on disk.  The cache
+is split into slots, caching up to eight 224 GiB files (128 KiB blocks).
+Larger files use multiple slots, with 1.75 TiB files using all 8 slots.
+The index cache is designed to be memory efficient, and by default uses
+16 KiB.
+
+3.4 Fragment lookup table
+-------------------------
+
+Regular files can contain a fragment index which is mapped to a fragment
+location on disk and compressed size using a fragment lookup table.  This
+fragment lookup table is itself stored compressed into metadata blocks.
+A second index table is used to locate these.  This second index table for
+speed of access (and because it is small) is read at mount time and cached
+in memory.
+
+3.5 Uid/gid lookup table
+------------------------
+
+For space efficiency regular files store uid and gid indexes, which are
+converted to 32-bit uids/gids using an id look up table.  This table is
+stored compressed into metadata blocks.  A second index table is used to
+locate these.  This second index table for speed of access (and because it
+is small) is read at mount time and cached in memory.
+
+3.6 Export table
+----------------
+
+To enable Squashfs filesystems to be exportable (via NFS etc.) filesystems
+can optionally (disabled with the -no-exports Mksquashfs option) contain
+an inode number to inode disk location lookup table.  This is required to
+enable Squashfs to map inode numbers passed in filehandles to the inode
+location on disk, which is necessary when the export code reinstantiates
+expired/flushed inodes.
+
+This table is stored compressed into metadata blocks.  A second index table is
+used to locate these.  This second index table for speed of access (and because
+it is small) is read at mount time and cached in memory.
+
+
+4. TODOS AND OUTSTANDING ISSUES
+-------------------------------
+
+4.1 Todo list
+-------------
+
+Implement Xattr and ACL support.  The Squashfs 4.0 filesystem layout has hooks
+for these but the code has not been written.  Once the code has been written
+the existing layout should not require modification.
+
+4.2 Squashfs internal cache
+---------------------------
+
+Blocks in Squashfs are compressed.  To avoid repeatedly decompressing
+recently accessed data Squashfs uses two small metadata and fragment caches.
+
+The cache is not used for file datablocks, these are decompressed and cached in
+the page-cache in the normal way.  The cache is used to temporarily cache
+fragment and metadata blocks which have been read as a result of a metadata
+(i.e. inode or directory) or fragment access.  Because metadata and fragments
+are packed together into blocks (to gain greater compression) the read of a
+particular piece of metadata or fragment will retrieve other metadata/fragments
+which have been packed with it, these because of locality-of-reference may be
+read in the near future. Temporarily caching them ensures they are available
+for near future access without requiring an additional read and decompress.
+
+In the future this internal cache may be replaced with an implementation which
+uses the kernel page cache.  Because the page cache operates on page sized
+units this may introduce additional complexity in terms of locking and
+associated race conditions.

MAINTAINERS

@@ -4081,6 +4081,13 @@ L:	cbe-oss-dev@ozlabs.org
 W:	http://www.ibm.com/developerworks/power/cell/
 S:	Supported
 
+SQUASHFS FILE SYSTEM
+P:	Phillip Lougher
+M:	phillip@lougher.demon.co.uk
+L:	squashfs-devel@lists.sourceforge.net (subscribers-only)
+W:	http://squashfs.org.uk
+S:	Maintained
+
 SRM (Alpha) environment access
 P:	Jan-Benedict Glaw
 M:	jbglaw@lug-owl.de

fs/Kconfig

@@ -932,6 +932,58 @@ config CRAMFS
 
 	  If unsure, say N.
 
+config SQUASHFS
+	tristate "SquashFS 4.0 - Squashed file system support"
+	depends on BLOCK
+	select ZLIB_INFLATE
+	help
+	  Saying Y here includes support for SquashFS 4.0 (a Compressed
+	  Read-Only File System).  Squashfs is a highly compressed read-only
+	  filesystem for Linux.  It uses zlib compression to compress both
+	  files, inodes and directories.  Inodes in the system are very small
+	  and all blocks are packed to minimise data overhead. Block sizes
+	  greater than 4K are supported up to a maximum of 1 Mbytes (default
+	  block size 128K).  SquashFS 4.0 supports 64 bit filesystems and files
+	  (larger than 4GB), full uid/gid information, hard links and
+	  timestamps.  
+
+	  Squashfs is intended for general read-only filesystem use, for
+	  archival use (i.e. in cases where a .tar.gz file may be used), and in
+	  embedded systems where low overhead is needed.  Further information
+	  and tools are available from http://squashfs.sourceforge.net.
+
+	  If you want to compile this as a module ( = code which can be
+	  inserted in and removed from the running kernel whenever you want),
+	  say M here and read <file:Documentation/modules.txt>.  The module
+	  will be called squashfs.  Note that the root file system (the one
+	  containing the directory /) cannot be compiled as a module.
+
+	  If unsure, say N.
+
+config SQUASHFS_EMBEDDED
+
+	bool "Additional option for memory-constrained systems" 
+	depends on SQUASHFS
+	default n
+	help
+	  Saying Y here allows you to specify cache size.
+
+	  If unsure, say N.
+
+config SQUASHFS_FRAGMENT_CACHE_SIZE
+	int "Number of fragments cached" if SQUASHFS_EMBEDDED
+	depends on SQUASHFS
+	default "3"
+	help
+	  By default SquashFS caches the last 3 fragments read from
+	  the filesystem.  Increasing this amount may mean SquashFS
+	  has to re-read fragments less often from disk, at the expense
+	  of extra system memory.  Decreasing this amount will mean
+	  SquashFS uses less memory at the expense of extra reads from disk.
+
+	  Note there must be at least one cached fragment.  Anything
+	  much more than three will probably not make much difference.
+
 config VXFS_FS
 	tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)"
 	depends on BLOCK

fs/Makefile

@@ -74,6 +74,7 @@ obj-$(CONFIG_JBD)		+= jbd/
 obj-$(CONFIG_JBD2)		+= jbd2/
 obj-$(CONFIG_EXT2_FS)		+= ext2/
 obj-$(CONFIG_CRAMFS)		+= cramfs/
+obj-$(CONFIG_SQUASHFS)		+= squashfs/
 obj-y				+= ramfs/
 obj-$(CONFIG_HUGETLBFS)		+= hugetlbfs/
 obj-$(CONFIG_CODA_FS)		+= coda/

fs/squashfs/Makefile

+#
+# Makefile for the linux squashfs routines.
+#
+
+obj-$(CONFIG_SQUASHFS) += squashfs.o
+squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
+squashfs-y += namei.o super.o symlink.o
+#squashfs-y += squashfs2_0.o

fs/squashfs/block.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * block.c
+ */
+
+/*
+ * This file implements the low-level routines to read and decompress
+ * datablocks and metadata blocks.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Read the metadata block length, this is stored in the first two
+ * bytes of the metadata block.
+ */
+static struct buffer_head *get_block_length(struct super_block *sb,
+			u64 *cur_index, int *offset, int *length)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	struct buffer_head *bh;
+
+	bh = sb_bread(sb, *cur_index);
+	if (bh == NULL)
+		return NULL;
+
+	if (msblk->devblksize - *offset == 1) {
+		*length = (unsigned char) bh->b_data[*offset];
+		put_bh(bh);
+		bh = sb_bread(sb, ++(*cur_index));
+		if (bh == NULL)
+			return NULL;
+		*length |= (unsigned char) bh->b_data[0] << 8;
+		*offset = 1;
+	} else {
+		*length = (unsigned char) bh->b_data[*offset] |
+			(unsigned char) bh->b_data[*offset + 1] << 8;
+		*offset += 2;
+	}
+
+	return bh;
+}
+
+
+/*
+ * Read and decompress a metadata block or datablock.  Length is non-zero
+ * if a datablock is being read (the size is stored elsewhere in the
+ * filesystem), otherwise the length is obtained from the first two bytes of
+ * the metadata block.  A bit in the length field indicates if the block
+ * is stored uncompressed in the filesystem (usually because compression
+ * generated a larger block - this does occasionally happen with zlib).
+ */
+int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
+			int length, u64 *next_index, int srclength)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	struct buffer_head **bh;
+	int offset = index & ((1 << msblk->devblksize_log2) - 1);
+	u64 cur_index = index >> msblk->devblksize_log2;
+	int bytes, compressed, b = 0, k = 0, page = 0, avail;
+
+
+	bh = kcalloc((msblk->block_size >> msblk->devblksize_log2) + 1,
+				sizeof(*bh), GFP_KERNEL);
+	if (bh == NULL)
+		return -ENOMEM;
+
+	if (length) {
+		/*
+		 * Datablock.
+		 */
+		bytes = -offset;
+		compressed = SQUASHFS_COMPRESSED_BLOCK(length);
+		length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
+		if (next_index)
+			*next_index = index + length;
+
+		TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
+			index, compressed ? "" : "un", length, srclength);
+
+		if (length < 0 || length > srclength ||
+				(index + length) > msblk->bytes_used)
+			goto read_failure;
+
+		for (b = 0; bytes < length; b++, cur_index++) {
+			bh[b] = sb_getblk(sb, cur_index);
+			if (bh[b] == NULL)
+				goto block_release;
+			bytes += msblk->devblksize;
+		}
+		ll_rw_block(READ, b, bh);
+	} else {
+		/*
+		 * Metadata block.
+		 */
+		if ((index + 2) > msblk->bytes_used)
+			goto read_failure;
+
+		bh[0] = get_block_length(sb, &cur_index, &offset, &length);
+		if (bh[0] == NULL)
+			goto read_failure;
+		b = 1;
+
+		bytes = msblk->devblksize - offset;
+		compressed = SQUASHFS_COMPRESSED(length);
+		length = SQUASHFS_COMPRESSED_SIZE(length);
+		if (next_index)
+			*next_index = index + length + 2;
+
+		TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
+				compressed ? "" : "un", length);
+
+		if (length < 0 || length > srclength ||
+					(index + length) > msblk->bytes_used)
+			goto block_release;
+
+		for (; bytes < length; b++) {
+			bh[b] = sb_getblk(sb, ++cur_index);
+			if (bh[b] == NULL)
+				goto block_release;
+			bytes += msblk->devblksize;
+		}
+		ll_rw_block(READ, b - 1, bh + 1);
+	}
+
+	if (compressed) {
+		int zlib_err = 0, zlib_init = 0;
+
+		/*
+		 * Uncompress block.
+		 */
+
+		mutex_lock(&msblk->read_data_mutex);
+
+		msblk->stream.avail_out = 0;
+		msblk->stream.avail_in = 0;
+
+		bytes = length;
+		do {
+			if (msblk->stream.avail_in == 0 && k < b) {
+				avail = min(bytes, msblk->devblksize - offset);
+				bytes -= avail;
+				wait_on_buffer(bh[k]);
+				if (!buffer_uptodate(bh[k]))
+					goto release_mutex;
+
+				if (avail == 0) {
+					offset = 0;
+					put_bh(bh[k++]);
+					continue;
+				}
+
+				msblk->stream.next_in = bh[k]->b_data + offset;
+				msblk->stream.avail_in = avail;
+				offset = 0;
+			}
+
+			if (msblk->stream.avail_out == 0) {
+				msblk->stream.next_out = buffer[page++];
+				msblk->stream.avail_out = PAGE_CACHE_SIZE;
+			}
+
+			if (!zlib_init) {
+				zlib_err = zlib_inflateInit(&msblk->stream);
+				if (zlib_err != Z_OK) {
+					ERROR("zlib_inflateInit returned"
+						" unexpected result 0x%x,"
+						" srclength %d\n", zlib_err,
+						srclength);
+					goto release_mutex;
+				}
+				zlib_init = 1;
+			}
+
+			zlib_err = zlib_inflate(&msblk->stream, Z_NO_FLUSH);
+
+			if (msblk->stream.avail_in == 0 && k < b)
+				put_bh(bh[k++]);
+		} while (zlib_err == Z_OK);
+
+		if (zlib_err != Z_STREAM_END) {
+			ERROR("zlib_inflate returned unexpected result"
+				" 0x%x, srclength %d, avail_in %d,"
+				" avail_out %d\n", zlib_err, srclength,
+				msblk->stream.avail_in,
+				msblk->stream.avail_out);
+			goto release_mutex;
+		}
+
+		zlib_err = zlib_inflateEnd(&msblk->stream);
+		if (zlib_err != Z_OK) {
+			ERROR("zlib_inflateEnd returned unexpected result 0x%x,"
+				" srclength %d\n", zlib_err, srclength);
+			goto release_mutex;
+		}
+		length = msblk->stream.total_out;
+		mutex_unlock(&msblk->read_data_mutex);
+	} else {
+		/*
+		 * Block is uncompressed.
+		 */
+		int i, in, pg_offset = 0;
+
+		for (i = 0; i < b; i++) {
+			wait_on_buffer(bh[i]);
+			if (!buffer_uptodate(bh[i]))
+				goto block_release;
+		}
+
+		for (bytes = length; k < b; k++) {
+			in = min(bytes, msblk->devblksize - offset);
+			bytes -= in;
+			while (in) {
+				if (pg_offset == PAGE_CACHE_SIZE) {
+					page++;
+					pg_offset = 0;
+				}
+				avail = min_t(int, in, PAGE_CACHE_SIZE -
+						pg_offset);
+				memcpy(buffer[page] + pg_offset,
+						bh[k]->b_data + offset, avail);
+				in -= avail;
+				pg_offset += avail;
+				offset += avail;
+			}
+			offset = 0;
+			put_bh(bh[k]);
+		}
+	}
+
+	kfree(bh);
+	return length;
+
+release_mutex:
+	mutex_unlock(&msblk->read_data_mutex);
+
+block_release:
+	for (; k < b; k++)
+		put_bh(bh[k]);
+
+read_failure:
+	ERROR("sb_bread failed reading block 0x%llx\n", cur_index);
+	kfree(bh);
+	return -EIO;
+}

fs/squashfs/cache.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * cache.c
+ */
+
+/*
+ * Blocks in Squashfs are compressed.  To avoid repeatedly decompressing
+ * recently accessed data Squashfs uses two small metadata and fragment caches.
+ *
+ * This file implements a generic cache implementation used for both caches,
+ * plus functions layered ontop of the generic cache implementation to
+ * access the metadata and fragment caches.
+ *
+ * To avoid out of memory and fragmentation isssues with vmalloc the cache
+ * uses sequences of kmalloced PAGE_CACHE_SIZE buffers.
+ *
+ * It should be noted that the cache is not used for file datablocks, these
+ * are decompressed and cached in the page-cache in the normal way.  The
+ * cache is only used to temporarily cache fragment and metadata blocks
+ * which have been read as as a result of a metadata (i.e. inode or
+ * directory) or fragment access.  Because metadata and fragments are packed
+ * together into blocks (to gain greater compression) the read of a particular
+ * piece of metadata or fragment will retrieve other metadata/fragments which
+ * have been packed with it, these because of locality-of-reference may be read
+ * in the near future. Temporarily caching them ensures they are available for
+ * near future access without requiring an additional read and decompress.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/zlib.h>
+#include <linux/pagemap.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Look-up block in cache, and increment usage count.  If not in cache, read
+ * and decompress it from disk.
+ */
+struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb,
+	struct squashfs_cache *cache, u64 block, int length)
+{
+	int i, n;
+	struct squashfs_cache_entry *entry;
+
+	spin_lock(&cache->lock);
+
+	while (1) {
+		for (i = 0; i < cache->entries; i++)
+			if (cache->entry[i].block == block)
+				break;
+
+		if (i == cache->entries) {
+			/*
+			 * Block not in cache, if all cache entries are used
+			 * go to sleep waiting for one to become available.
+			 */
+			if (cache->unused == 0) {
+				cache->num_waiters++;
+				spin_unlock(&cache->lock);
+				wait_event(cache->wait_queue, cache->unused);
+				spin_lock(&cache->lock);
+				cache->num_waiters--;
+				continue;
+			}
+
+			/*
+			 * At least one unused cache entry.  A simple
+			 * round-robin strategy is used to choose the entry to
+			 * be evicted from the cache.
+			 */
+			i = cache->next_blk;
+			for (n = 0; n < cache->entries; n++) {
+				if (cache->entry[i].refcount == 0)
+					break;
+				i = (i + 1) % cache->entries;
+			}
+
+			cache->next_blk = (i + 1) % cache->entries;
+			entry = &cache->entry[i];
+
+			/*
+			 * Initialise choosen cache entry, and fill it in from
+			 * disk.
+			 */
+			cache->unused--;
+			entry->block = block;
+			entry->refcount = 1;
+			entry->pending = 1;
+			entry->num_waiters = 0;
+			entry->error = 0;
+			spin_unlock(&cache->lock);
+
+			entry->length = squashfs_read_data(sb, entry->data,
+				block, length, &entry->next_index,
+				cache->block_size);
+
+			spin_lock(&cache->lock);
+
+			if (entry->length < 0)
+				entry->error = entry->length;
+
+			entry->pending = 0;
+
+			/*
+			 * While filling this entry one or more other processes
+			 * have looked it up in the cache, and have slept
+			 * waiting for it to become available.
+			 */
+			if (entry->num_waiters) {
+				spin_unlock(&cache->lock);
+				wake_up_all(&entry->wait_queue);
+			} else
+				spin_unlock(&cache->lock);
+
+			goto out;
+		}
+
+		/*
+		 * Block already in cache.  Increment refcount so it doesn't
+		 * get reused until we're finished with it, if it was
+		 * previously unused there's one less cache entry available
+		 * for reuse.
+		 */
+		entry = &cache->entry[i];
+		if (entry->refcount == 0)
+			cache->unused--;
+		entry->refcount++;
+
+		/*
+		 * If the entry is currently being filled in by another process
+		 * go to sleep waiting for it to become available.
+		 */
+		if (entry->pending) {
+			entry->num_waiters++;
+			spin_unlock(&cache->lock);
+			wait_event(entry->wait_queue, !entry->pending);
+		} else
+			spin_unlock(&cache->lock);
+
+		goto out;
+	}
+
+out:
+	TRACE("Got %s %d, start block %lld, refcount %d, error %d\n",
+		cache->name, i, entry->block, entry->refcount, entry->error);
+
+	if (entry->error)
+		ERROR("Unable to read %s cache entry [%llx]\n", cache->name,
+							block);
+	return entry;
+}
+
+
+/*
+ * Release cache entry, once usage count is zero it can be reused.
+ */
+void squashfs_cache_put(struct squashfs_cache_entry *entry)
+{
+	struct squashfs_cache *cache = entry->cache;
+
+	spin_lock(&cache->lock);
+	entry->refcount--;
+	if (entry->refcount == 0) {
+		cache->unused++;
+		/*
+		 * If there's any processes waiting for a block to become
+		 * available, wake one up.
+		 */
+		if (cache->num_waiters) {
+			spin_unlock(&cache->lock);
+			wake_up(&cache->wait_queue);
+			return;
+		}
+	}
+	spin_unlock(&cache->lock);
+}
+
+/*
+ * Delete cache reclaiming all kmalloced buffers.
+ */
+void squashfs_cache_delete(struct squashfs_cache *cache)
+{
+	int i, j;
+
+	if (cache == NULL)
+		return;
+
+	for (i = 0; i < cache->entries; i++) {
+		if (cache->entry[i].data) {
+			for (j = 0; j < cache->pages; j++)
+				kfree(cache->entry[i].data[j]);
+			kfree(cache->entry[i].data);
+		}
+	}
+
+	kfree(cache->entry);
+	kfree(cache);
+}
+
+
+/*
+ * Initialise cache allocating the specified number of entries, each of
+ * size block_size.  To avoid vmalloc fragmentation issues each entry
+ * is allocated as a sequence of kmalloced PAGE_CACHE_SIZE buffers.
+ */
+struct squashfs_cache *squashfs_cache_init(char *name, int entries,
+	int block_size)
+{
+	int i, j;
+	struct squashfs_cache *cache = kzalloc(sizeof(*cache), GFP_KERNEL);
+
+	if (cache == NULL) {
+		ERROR("Failed to allocate %s cache\n", name);
+		return NULL;
+	}
+
+	cache->entry = kcalloc(entries, sizeof(*(cache->entry)), GFP_KERNEL);
+	if (cache->entry == NULL) {
+		ERROR("Failed to allocate %s cache\n", name);
+		goto cleanup;
+	}
+
+	cache->next_blk = 0;
+	cache->unused = entries;
+	cache->entries = entries;
+	cache->block_size = block_size;
+	cache->pages = block_size >> PAGE_CACHE_SHIFT;
+	cache->name = name;
+	cache->num_waiters = 0;
+	spin_lock_init(&cache->lock);
+	init_waitqueue_head(&cache->wait_queue);
+
+	for (i = 0; i < entries; i++) {
+		struct squashfs_cache_entry *entry = &cache->entry[i];
+
+		init_waitqueue_head(&cache->entry[i].wait_queue);
+		entry->cache = cache;
+		entry->block = SQUASHFS_INVALID_BLK;
+		entry->data = kcalloc(cache->pages, sizeof(void *), GFP_KERNEL);
+		if (entry->data == NULL) {
+			ERROR("Failed to allocate %s cache entry\n", name);
+			goto cleanup;
+		}
+
+		for (j = 0; j < cache->pages; j++) {
+			entry->data[j] = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+			if (entry->data[j] == NULL) {
+				ERROR("Failed to allocate %s buffer\n", name);
+				goto cleanup;
+			}
+		}
+	}
+
+	return cache;
+
+cleanup:
+	squashfs_cache_delete(cache);
+	return NULL;
+}
+
+
+/*
+ * Copy upto length bytes from cache entry to buffer starting at offset bytes
+ * into the cache entry.  If there's not length bytes then copy the number of
+ * bytes available.  In all cases return the number of bytes copied.
+ */
+int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry,
+		int offset, int length)
+{
+	int remaining = length;
+
+	if (length == 0)
+		return 0;
+	else if (buffer == NULL)
+		return min(length, entry->length - offset);
+
+	while (offset < entry->length) {
+		void *buff = entry->data[offset / PAGE_CACHE_SIZE]
+				+ (offset % PAGE_CACHE_SIZE);
+		int bytes = min_t(int, entry->length - offset,
+				PAGE_CACHE_SIZE - (offset % PAGE_CACHE_SIZE));
+
+		if (bytes >= remaining) {
+			memcpy(buffer, buff, remaining);
+			remaining = 0;
+			break;
+		}
+
+		memcpy(buffer, buff, bytes);
+		buffer += bytes;
+		remaining -= bytes;
+		offset += bytes;
+	}
+
+	return length - remaining;
+}
+
+
+/*
+ * Read length bytes from metadata position <block, offset> (block is the
+ * start of the compressed block on disk, and offset is the offset into
+ * the block once decompressed).  Data is packed into consecutive blocks,
+ * and length bytes may require reading more than one block.
+ */
+int squashfs_read_metadata(struct super_block *sb, void *buffer,
+		u64 *block, int *offset, int length)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int bytes, copied = length;
+	struct squashfs_cache_entry *entry;
+
+	TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset);
+
+	while (length) {
+		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
+		if (entry->error)
+			return entry->error;
+		else if (*offset >= entry->length)
+			return -EIO;
+
+		bytes = squashfs_copy_data(buffer, entry, *offset, length);
+		if (buffer)
+			buffer += bytes;
+		length -= bytes;
+		*offset += bytes;
+
+		if (*offset == entry->length) {
+			*block = entry->next_index;
+			*offset = 0;
+		}
+
+		squashfs_cache_put(entry);
+	}
+
+	return copied;
+}
+
+
+/*
+ * Look-up in the fragmment cache the fragment located at <start_block> in the
+ * filesystem.  If necessary read and decompress it from disk.
+ */
+struct squashfs_cache_entry *squashfs_get_fragment(struct super_block *sb,
+				u64 start_block, int length)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+
+	return squashfs_cache_get(sb, msblk->fragment_cache, start_block,
+		length);
+}
+
+
+/*
+ * Read and decompress the datablock located at <start_block> in the
+ * filesystem.  The cache is used here to avoid duplicating locking and
+ * read/decompress code.
+ */
+struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb,
+				u64 start_block, int length)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+
+	return squashfs_cache_get(sb, msblk->read_page, start_block, length);
+}
+
+
+/*
+ * Read a filesystem table (uncompressed sequence of bytes) from disk
+ */
+int squashfs_read_table(struct super_block *sb, void *buffer, u64 block,
+	int length)
+{
+	int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	int i, res;
+	void **data = kcalloc(pages, sizeof(void *), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE)
+		data[i] = buffer;
+	res = squashfs_read_data(sb, data, block, length |
+		SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length);
+	kfree(data);
+	return res;
+}

fs/squashfs/dir.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * dir.c
+ */
+
+/*
+ * This file implements code to read directories from disk.
+ *
+ * See namei.c for a description of directory organisation on disk.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+static const unsigned char squashfs_filetype_table[] = {
+	DT_UNKNOWN, DT_DIR, DT_REG, DT_LNK, DT_BLK, DT_CHR, DT_FIFO, DT_SOCK
+};
+
+/*
+ * Lookup offset (f_pos) in the directory index, returning the
+ * metadata block containing it.
+ *
+ * If we get an error reading the index then return the part of the index
+ * (if any) we have managed to read - the index isn't essential, just
+ * quicker.
+ */
+static int get_dir_index_using_offset(struct super_block *sb,
+	u64 *next_block, int *next_offset, u64 index_start, int index_offset,
+	int i_count, u64 f_pos)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int err, i, index, length = 0;
+	struct squashfs_dir_index dir_index;
+
+	TRACE("Entered get_dir_index_using_offset, i_count %d, f_pos %lld\n",
+					i_count, f_pos);
+
+	/*
+	 * Translate from external f_pos to the internal f_pos.  This
+	 * is offset by 3 because we invent "." and ".." entries which are
+	 * not actually stored in the directory.
+	 */
+	if (f_pos < 3)
+		return f_pos;
+	f_pos -= 3;
+
+	for (i = 0; i < i_count; i++) {
+		err = squashfs_read_metadata(sb, &dir_index, &index_start,
+				&index_offset, sizeof(dir_index));
+		if (err < 0)
+			break;
+
+		index = le32_to_cpu(dir_index.index);
+		if (index > f_pos)
+			/*
+			 * Found the index we're looking for.
+			 */
+			break;
+
+		err = squashfs_read_metadata(sb, NULL, &index_start,
+				&index_offset, le32_to_cpu(dir_index.size) + 1);
+		if (err < 0)
+			break;
+
+		length = index;
+		*next_block = le32_to_cpu(dir_index.start_block) +
+					msblk->directory_table;
+	}
+
+	*next_offset = (length + *next_offset) % SQUASHFS_METADATA_SIZE;
+
+	/*
+	 * Translate back from internal f_pos to external f_pos.
+	 */
+	return length + 3;
+}
+
+
+static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	u64 block = squashfs_i(inode)->start + msblk->directory_table;
+	int offset = squashfs_i(inode)->offset, length = 0, dir_count, size,
+				type, err;
+	unsigned int inode_number;
+	struct squashfs_dir_header dirh;
+	struct squashfs_dir_entry *dire;
+
+	TRACE("Entered squashfs_readdir [%llx:%x]\n", block, offset);
+
+	dire = kmalloc(sizeof(*dire) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL);
+	if (dire == NULL) {
+		ERROR("Failed to allocate squashfs_dir_entry\n");
+		goto finish;
+	}
+
+	/*
+	 * Return "." and  ".." entries as the first two filenames in the
+	 * directory.  To maximise compression these two entries are not
+	 * stored in the directory, and so we invent them here.
+	 *
+	 * It also means that the external f_pos is offset by 3 from the
+	 * on-disk directory f_pos.
+	 */
+	while (file->f_pos < 3) {
+		char *name;
+		int i_ino;
+
+		if (file->f_pos == 0) {
+			name = ".";
+			size = 1;
+			i_ino = inode->i_ino;
+		} else {
+			name = "..";
+			size = 2;
+			i_ino = squashfs_i(inode)->parent;
+		}
+
+		TRACE("Calling filldir(%p, %s, %d, %lld, %d, %d)\n",
+				dirent, name, size, file->f_pos, i_ino,
+				squashfs_filetype_table[1]);
+
+		if (filldir(dirent, name, size, file->f_pos, i_ino,
+				squashfs_filetype_table[1]) < 0) {
+				TRACE("Filldir returned less than 0\n");
+			goto finish;
+		}
+
+		file->f_pos += size;
+	}
+
+	length = get_dir_index_using_offset(inode->i_sb, &block, &offset,
+				squashfs_i(inode)->dir_idx_start,
+				squashfs_i(inode)->dir_idx_offset,
+				squashfs_i(inode)->dir_idx_cnt,
+				file->f_pos);
+
+	while (length < i_size_read(inode)) {
+		/*
+		 * Read directory header
+		 */
+		err = squashfs_read_metadata(inode->i_sb, &dirh, &block,
+					&offset, sizeof(dirh));
+		if (err < 0)
+			goto failed_read;
+
+		length += sizeof(dirh);
+
+		dir_count = le32_to_cpu(dirh.count) + 1;
+		while (dir_count--) {
+			/*
+			 * Read directory entry.
+			 */
+			err = squashfs_read_metadata(inode->i_sb, dire, &block,
+					&offset, sizeof(*dire));
+			if (err < 0)
+				goto failed_read;
+
+			size = le16_to_cpu(dire->size) + 1;
+
+			err = squashfs_read_metadata(inode->i_sb, dire->name,
+					&block, &offset, size);
+			if (err < 0)
+				goto failed_read;
+
+			length += sizeof(*dire) + size;
+
+			if (file->f_pos >= length)
+				continue;
+
+			dire->name[size] = '\0';
+			inode_number = le32_to_cpu(dirh.inode_number) +
+				((short) le16_to_cpu(dire->inode_number));
+			type = le16_to_cpu(dire->type);
+
+			TRACE("Calling filldir(%p, %s, %d, %lld, %x:%x, %d, %d)"
+					"\n", dirent, dire->name, size,
+					file->f_pos,
+					le32_to_cpu(dirh.start_block),
+					le16_to_cpu(dire->offset),
+					inode_number,
+					squashfs_filetype_table[type]);
+
+			if (filldir(dirent, dire->name, size, file->f_pos,
+					inode_number,
+					squashfs_filetype_table[type]) < 0) {
+				TRACE("Filldir returned less than 0\n");
+				goto finish;
+			}
+
+			file->f_pos = length;
+		}
+	}
+
+finish:
+	kfree(dire);
+	return 0;
+
+failed_read:
+	ERROR("Unable to read directory block [%llx:%x]\n", block, offset);
+	kfree(dire);
+	return 0;
+}
+
+
+const struct file_operations squashfs_dir_ops = {
+	.read = generic_read_dir,
+	.readdir = squashfs_readdir
+};

fs/squashfs/export.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * export.c
+ */
+
+/*
+ * This file implements code to make Squashfs filesystems exportable (NFS etc.)
+ *
+ * The export code uses an inode lookup table to map inode numbers passed in
+ * filehandles to an inode location on disk.  This table is stored compressed
+ * into metadata blocks.  A second index table is used to locate these.  This
+ * second index table for speed of access (and because it is small) is read at
+ * mount time and cached in memory.
+ *
+ * The inode lookup table is used only by the export code, inode disk
+ * locations are directly encoded in directories, enabling direct access
+ * without an intermediate lookup for all operations except the export ops.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/dcache.h>
+#include <linux/exportfs.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Look-up inode number (ino) in table, returning the inode location.
+ */
+static long long squashfs_inode_lookup(struct super_block *sb, int ino_num)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1);
+	int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1);
+	u64 start = le64_to_cpu(msblk->inode_lookup_table[blk]);
+	__le64 ino;
+	int err;
+
+	TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num);
+
+	err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino));
+	if (err < 0)
+		return err;
+
+	TRACE("squashfs_inode_lookup, inode = 0x%llx\n",
+		(u64) le64_to_cpu(ino));
+
+	return le64_to_cpu(ino);
+}
+
+
+static struct dentry *squashfs_export_iget(struct super_block *sb,
+	unsigned int ino_num)
+{
+	long long ino;
+	struct dentry *dentry = ERR_PTR(-ENOENT);
+
+	TRACE("Entered squashfs_export_iget\n");
+
+	ino = squashfs_inode_lookup(sb, ino_num);
+	if (ino >= 0)
+		dentry = d_obtain_alias(squashfs_iget(sb, ino, ino_num));
+
+	return dentry;
+}
+
+
+static struct dentry *squashfs_fh_to_dentry(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	if ((fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT)
+			|| fh_len < 2)
+		return NULL;
+
+	return squashfs_export_iget(sb, fid->i32.ino);
+}
+
+
+static struct dentry *squashfs_fh_to_parent(struct super_block *sb,
+		struct fid *fid, int fh_len, int fh_type)
+{
+	if (fh_type != FILEID_INO32_GEN_PARENT || fh_len < 4)
+		return NULL;
+
+	return squashfs_export_iget(sb, fid->i32.parent_ino);
+}
+
+
+static struct dentry *squashfs_get_parent(struct dentry *child)
+{
+	struct inode *inode = child->d_inode;
+	unsigned int parent_ino = squashfs_i(inode)->parent;
+
+	return squashfs_export_iget(inode->i_sb, parent_ino);
+}
+
+
+/*
+ * Read uncompressed inode lookup table indexes off disk into memory
+ */
+__le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
+		u64 lookup_table_start, unsigned int inodes)
+{
+	unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes);
+	__le64 *inode_lookup_table;
+	int err;
+
+	TRACE("In read_inode_lookup_table, length %d\n", length);
+
+	/* Allocate inode lookup table indexes */
+	inode_lookup_table = kmalloc(length, GFP_KERNEL);
+	if (inode_lookup_table == NULL) {
+		ERROR("Failed to allocate inode lookup table\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	err = squashfs_read_table(sb, inode_lookup_table, lookup_table_start,
+			length);
+	if (err < 0) {
+		ERROR("unable to read inode lookup table\n");
+		kfree(inode_lookup_table);
+		return ERR_PTR(err);
+	}
+
+	return inode_lookup_table;
+}
+
+
+const struct export_operations squashfs_export_ops = {
+	.fh_to_dentry = squashfs_fh_to_dentry,
+	.fh_to_parent = squashfs_fh_to_parent,
+	.get_parent = squashfs_get_parent
+};

fs/squashfs/file.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * file.c
+ */
+
+/*
+ * This file contains code for handling regular files.  A regular file
+ * consists of a sequence of contiguous compressed blocks, and/or a
+ * compressed fragment block (tail-end packed block).   The compressed size
+ * of each datablock is stored in a block list contained within the
+ * file inode (itself stored in one or more compressed metadata blocks).
+ *
+ * To speed up access to datablocks when reading 'large' files (256 Mbytes or
+ * larger), the code implements an index cache that caches the mapping from
+ * block index to datablock location on disk.
+ *
+ * The index cache allows Squashfs to handle large files (up to 1.75 TiB) while
+ * retaining a simple and space-efficient block list on disk.  The cache
+ * is split into slots, caching up to eight 224 GiB files (128 KiB blocks).
+ * Larger files use multiple slots, with 1.75 TiB files using all 8 slots.
+ * The index cache is designed to be memory efficient, and by default uses
+ * 16 KiB.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/mutex.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Locate cache slot in range [offset, index] for specified inode.  If
+ * there's more than one return the slot closest to index.
+ */
+static struct meta_index *locate_meta_index(struct inode *inode, int offset,
+				int index)
+{
+	struct meta_index *meta = NULL;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	int i;
+
+	mutex_lock(&msblk->meta_index_mutex);
+
+	TRACE("locate_meta_index: index %d, offset %d\n", index, offset);
+
+	if (msblk->meta_index == NULL)
+		goto not_allocated;
+
+	for (i = 0; i < SQUASHFS_META_SLOTS; i++) {
+		if (msblk->meta_index[i].inode_number == inode->i_ino &&
+				msblk->meta_index[i].offset >= offset &&
+				msblk->meta_index[i].offset <= index &&
+				msblk->meta_index[i].locked == 0) {
+			TRACE("locate_meta_index: entry %d, offset %d\n", i,
+					msblk->meta_index[i].offset);
+			meta = &msblk->meta_index[i];
+			offset = meta->offset;
+		}
+	}
+
+	if (meta)
+		meta->locked = 1;
+
+not_allocated:
+	mutex_unlock(&msblk->meta_index_mutex);
+
+	return meta;
+}
+
+
+/*
+ * Find and initialise an empty cache slot for index offset.
+ */
+static struct meta_index *empty_meta_index(struct inode *inode, int offset,
+				int skip)
+{
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	struct meta_index *meta = NULL;
+	int i;
+
+	mutex_lock(&msblk->meta_index_mutex);
+
+	TRACE("empty_meta_index: offset %d, skip %d\n", offset, skip);
+
+	if (msblk->meta_index == NULL) {
+		/*
+		 * First time cache index has been used, allocate and
+		 * initialise.  The cache index could be allocated at
+		 * mount time but doing it here means it is allocated only
+		 * if a 'large' file is read.
+		 */
+		msblk->meta_index = kcalloc(SQUASHFS_META_SLOTS,
+			sizeof(*(msblk->meta_index)), GFP_KERNEL);
+		if (msblk->meta_index == NULL) {
+			ERROR("Failed to allocate meta_index\n");
+			goto failed;
+		}
+		for (i = 0; i < SQUASHFS_META_SLOTS; i++) {
+			msblk->meta_index[i].inode_number = 0;
+			msblk->meta_index[i].locked = 0;
+		}
+		msblk->next_meta_index = 0;
+	}
+
+	for (i = SQUASHFS_META_SLOTS; i &&
+			msblk->meta_index[msblk->next_meta_index].locked; i--)
+		msblk->next_meta_index = (msblk->next_meta_index + 1) %
+			SQUASHFS_META_SLOTS;
+
+	if (i == 0) {
+		TRACE("empty_meta_index: failed!\n");
+		goto failed;
+	}
+
+	TRACE("empty_meta_index: returned meta entry %d, %p\n",
+			msblk->next_meta_index,
+			&msblk->meta_index[msblk->next_meta_index]);
+
+	meta = &msblk->meta_index[msblk->next_meta_index];
+	msblk->next_meta_index = (msblk->next_meta_index + 1) %
+			SQUASHFS_META_SLOTS;
+
+	meta->inode_number = inode->i_ino;
+	meta->offset = offset;
+	meta->skip = skip;
+	meta->entries = 0;
+	meta->locked = 1;
+
+failed:
+	mutex_unlock(&msblk->meta_index_mutex);
+	return meta;
+}
+
+
+static void release_meta_index(struct inode *inode, struct meta_index *meta)
+{
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	mutex_lock(&msblk->meta_index_mutex);
+	meta->locked = 0;
+	mutex_unlock(&msblk->meta_index_mutex);
+}
+
+
+/*
+ * Read the next n blocks from the block list, starting from
+ * metadata block <start_block, offset>.
+ */
+static long long read_indexes(struct super_block *sb, int n,
+				u64 *start_block, int *offset)
+{
+	int err, i;
+	long long block = 0;
+	__le32 *blist = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+
+	if (blist == NULL) {
+		ERROR("read_indexes: Failed to allocate block_list\n");
+		return -ENOMEM;
+	}
+
+	while (n) {
+		int blocks = min_t(int, n, PAGE_CACHE_SIZE >> 2);
+
+		err = squashfs_read_metadata(sb, blist, start_block,
+				offset, blocks << 2);
+		if (err < 0) {
+			ERROR("read_indexes: reading block [%llx:%x]\n",
+				*start_block, *offset);
+			goto failure;
+		}
+
+		for (i = 0; i < blocks; i++) {
+			int size = le32_to_cpu(blist[i]);
+			block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size);
+		}
+		n -= blocks;
+	}
+
+	kfree(blist);
+	return block;
+
+failure:
+	kfree(blist);
+	return err;
+}
+
+
+/*
+ * Each cache index slot has SQUASHFS_META_ENTRIES, each of which
+ * can cache one index -> datablock/blocklist-block mapping.  We wish
+ * to distribute these over the length of the file, entry[0] maps index x,
+ * entry[1] maps index x + skip, entry[2] maps index x + 2 * skip, and so on.
+ * The larger the file, the greater the skip factor.  The skip factor is
+ * limited to the size of the metadata cache (SQUASHFS_CACHED_BLKS) to ensure
+ * the number of metadata blocks that need to be read fits into the cache.
+ * If the skip factor is limited in this way then the file will use multiple
+ * slots.
+ */
+static inline int calculate_skip(int blocks)
+{
+	int skip = blocks / ((SQUASHFS_META_ENTRIES + 1)
+		 * SQUASHFS_META_INDEXES);
+	return min(SQUASHFS_CACHED_BLKS - 1, skip + 1);
+}
+
+
+/*
+ * Search and grow the index cache for the specified inode, returning the
+ * on-disk locations of the datablock and block list metadata block
+ * <index_block, index_offset> for index (scaled to nearest cache index).
+ */
+static int fill_meta_index(struct inode *inode, int index,
+		u64 *index_block, int *index_offset, u64 *data_block)
+{
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	int skip = calculate_skip(i_size_read(inode) >> msblk->block_log);
+	int offset = 0;
+	struct meta_index *meta;
+	struct meta_entry *meta_entry;
+	u64 cur_index_block = squashfs_i(inode)->block_list_start;
+	int cur_offset = squashfs_i(inode)->offset;
+	u64 cur_data_block = squashfs_i(inode)->start;
+	int err, i;
+
+	/*
+	 * Scale index to cache index (cache slot entry)
+	 */
+	index /= SQUASHFS_META_INDEXES * skip;
+
+	while (offset < index) {
+		meta = locate_meta_index(inode, offset + 1, index);
+
+		if (meta == NULL) {
+			meta = empty_meta_index(inode, offset + 1, skip);
+			if (meta == NULL)
+				goto all_done;
+		} else {
+			offset = index < meta->offset + meta->entries ? index :
+				meta->offset + meta->entries - 1;
+			meta_entry = &meta->meta_entry[offset - meta->offset];
+			cur_index_block = meta_entry->index_block +
+				msblk->inode_table;
+			cur_offset = meta_entry->offset;
+			cur_data_block = meta_entry->data_block;
+			TRACE("get_meta_index: offset %d, meta->offset %d, "
+				"meta->entries %d\n", offset, meta->offset,
+				meta->entries);
+			TRACE("get_meta_index: index_block 0x%llx, offset 0x%x"
+				" data_block 0x%llx\n", cur_index_block,
+				cur_offset, cur_data_block);
+		}
+
+		/*
+		 * If necessary grow cache slot by reading block list.  Cache
+		 * slot is extended up to index or to the end of the slot, in
+		 * which case further slots will be used.
+		 */
+		for (i = meta->offset + meta->entries; i <= index &&
+				i < meta->offset + SQUASHFS_META_ENTRIES; i++) {
+			int blocks = skip * SQUASHFS_META_INDEXES;
+			long long res = read_indexes(inode->i_sb, blocks,
+					&cur_index_block, &cur_offset);
+
+			if (res < 0) {
+				if (meta->entries == 0)
+					/*
+					 * Don't leave an empty slot on read
+					 * error allocated to this inode...
+					 */
+					meta->inode_number = 0;
+				err = res;
+				goto failed;
+			}
+
+			cur_data_block += res;
+			meta_entry = &meta->meta_entry[i - meta->offset];
+			meta_entry->index_block = cur_index_block -
+				msblk->inode_table;
+			meta_entry->offset = cur_offset;
+			meta_entry->data_block = cur_data_block;
+			meta->entries++;
+			offset++;
+		}
+
+		TRACE("get_meta_index: meta->offset %d, meta->entries %d\n",
+				meta->offset, meta->entries);
+
+		release_meta_index(inode, meta);
+	}
+
+all_done:
+	*index_block = cur_index_block;
+	*index_offset = cur_offset;
+	*data_block = cur_data_block;
+
+	/*
+	 * Scale cache index (cache slot entry) to index
+	 */
+	return offset * SQUASHFS_META_INDEXES * skip;
+
+failed:
+	release_meta_index(inode, meta);
+	return err;
+}
+
+
+/*
+ * Get the on-disk location and compressed size of the datablock
+ * specified by index.  Fill_meta_index() does most of the work.
+ */
+static int read_blocklist(struct inode *inode, int index, u64 *block)
+{
+	u64 start;
+	long long blks;
+	int offset;
+	__le32 size;
+	int res = fill_meta_index(inode, index, &start, &offset, block);
+
+	TRACE("read_blocklist: res %d, index %d, start 0x%llx, offset"
+		       " 0x%x, block 0x%llx\n", res, index, start, offset,
+			*block);
+
+	if (res < 0)
+		return res;
+
+	/*
+	 * res contains the index of the mapping returned by fill_meta_index(),
+	 * this will likely be less than the desired index (because the
+	 * meta_index cache works at a higher granularity).  Read any
+	 * extra block indexes needed.
+	 */
+	if (res < index) {
+		blks = read_indexes(inode->i_sb, index - res, &start, &offset);
+		if (blks < 0)
+			return (int) blks;
+		*block += blks;
+	}
+
+	/*
+	 * Read length of block specified by index.
+	 */
+	res = squashfs_read_metadata(inode->i_sb, &size, &start, &offset,
+			sizeof(size));
+	if (res < 0)
+		return res;
+	return le32_to_cpu(size);
+}
+
+
+static int squashfs_readpage(struct file *file, struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	int bytes, i, offset = 0, sparse = 0;
+	struct squashfs_cache_entry *buffer = NULL;
+	void *pageaddr;
+
+	int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
+	int start_index = page->index & ~mask;
+	int end_index = start_index | mask;
+	int file_end = i_size_read(inode) >> msblk->block_log;
+
+	TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
+				page->index, squashfs_i(inode)->start);
+
+	if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+					PAGE_CACHE_SHIFT))
+		goto out;
+
+	if (index < file_end || squashfs_i(inode)->fragment_block ==
+					SQUASHFS_INVALID_BLK) {
+		/*
+		 * Reading a datablock from disk.  Need to read block list
+		 * to get location and block size.
+		 */
+		u64 block = 0;
+		int bsize = read_blocklist(inode, index, &block);
+		if (bsize < 0)
+			goto error_out;
+
+		if (bsize == 0) { /* hole */
+			bytes = index == file_end ?
+				(i_size_read(inode) & (msblk->block_size - 1)) :
+				 msblk->block_size;
+			sparse = 1;
+		} else {
+			/*
+			 * Read and decompress datablock.
+			 */
+			buffer = squashfs_get_datablock(inode->i_sb,
+								block, bsize);
+			if (buffer->error) {
+				ERROR("Unable to read page, block %llx, size %x"
+					"\n", block, bsize);
+				squashfs_cache_put(buffer);
+				goto error_out;
+			}
+			bytes = buffer->length;
+		}
+	} else {
+		/*
+		 * Datablock is stored inside a fragment (tail-end packed
+		 * block).
+		 */
+		buffer = squashfs_get_fragment(inode->i_sb,
+				squashfs_i(inode)->fragment_block,
+				squashfs_i(inode)->fragment_size);
+
+		if (buffer->error) {
+			ERROR("Unable to read page, block %llx, size %x\n",
+				squashfs_i(inode)->fragment_block,
+				squashfs_i(inode)->fragment_size);
+			squashfs_cache_put(buffer);
+			goto error_out;
+		}
+		bytes = i_size_read(inode) & (msblk->block_size - 1);
+		offset = squashfs_i(inode)->fragment_offset;
+	}
+
+	/*
+	 * Loop copying datablock into pages.  As the datablock likely covers
+	 * many PAGE_CACHE_SIZE pages (default block size is 128 KiB) explicitly
+	 * grab the pages from the page cache, except for the page that we've
+	 * been called to fill.
+	 */
+	for (i = start_index; i <= end_index && bytes > 0; i++,
+			bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
+		struct page *push_page;
+		int avail = sparse ? 0 : min_t(int, bytes, PAGE_CACHE_SIZE);
+
+		TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail);
+
+		push_page = (i == page->index) ? page :
+			grab_cache_page_nowait(page->mapping, i);
+
+		if (!push_page)
+			continue;
+
+		if (PageUptodate(push_page))
+			goto skip_page;
+
+		pageaddr = kmap_atomic(push_page, KM_USER0);
+		squashfs_copy_data(pageaddr, buffer, offset, avail);
+		memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
+		kunmap_atomic(pageaddr, KM_USER0);
+		flush_dcache_page(push_page);
+		SetPageUptodate(push_page);
+skip_page:
+		unlock_page(push_page);
+		if (i != page->index)
+			page_cache_release(push_page);
+	}
+
+	if (!sparse)
+		squashfs_cache_put(buffer);
+
+	return 0;
+
+error_out:
+	SetPageError(page);
+out:
+	pageaddr = kmap_atomic(page, KM_USER0);
+	memset(pageaddr, 0, PAGE_CACHE_SIZE);
+	kunmap_atomic(pageaddr, KM_USER0);
+	flush_dcache_page(page);
+	if (!PageError(page))
+		SetPageUptodate(page);
+	unlock_page(page);
+
+	return 0;
+}
+
+
+const struct address_space_operations squashfs_aops = {
+	.readpage = squashfs_readpage
+};

fs/squashfs/fragment.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * fragment.c
+ */
+
+/*
+ * This file implements code to handle compressed fragments (tail-end packed
+ * datablocks).
+ *
+ * Regular files contain a fragment index which is mapped to a fragment
+ * location on disk and compressed size using a fragment lookup table.
+ * Like everything in Squashfs this fragment lookup table is itself stored
+ * compressed into metadata blocks.  A second index table is used to locate
+ * these.  This second index table for speed of access (and because it
+ * is small) is read at mount time and cached in memory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Look-up fragment using the fragment index table.  Return the on disk
+ * location of the fragment and its compressed size
+ */
+int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment,
+				u64 *fragment_block)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int block = SQUASHFS_FRAGMENT_INDEX(fragment);
+	int offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment);
+	u64 start_block = le64_to_cpu(msblk->fragment_index[block]);
+	struct squashfs_fragment_entry fragment_entry;
+	int size;
+
+	size = squashfs_read_metadata(sb, &fragment_entry, &start_block,
+					&offset, sizeof(fragment_entry));
+	if (size < 0)
+		return size;
+
+	*fragment_block = le64_to_cpu(fragment_entry.start_block);
+	size = le32_to_cpu(fragment_entry.size);
+
+	return size;
+}
+
+
+/*
+ * Read the uncompressed fragment lookup table indexes off disk into memory
+ */
+__le64 *squashfs_read_fragment_index_table(struct super_block *sb,
+	u64 fragment_table_start, unsigned int fragments)
+{
+	unsigned int length = SQUASHFS_FRAGMENT_INDEX_BYTES(fragments);
+	__le64 *fragment_index;
+	int err;
+
+	/* Allocate fragment lookup table indexes */
+	fragment_index = kmalloc(length, GFP_KERNEL);
+	if (fragment_index == NULL) {
+		ERROR("Failed to allocate fragment index table\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	err = squashfs_read_table(sb, fragment_index, fragment_table_start,
+			length);
+	if (err < 0) {
+		ERROR("unable to read fragment index table\n");
+		kfree(fragment_index);
+		return ERR_PTR(err);
+	}
+
+	return fragment_index;
+}

fs/squashfs/id.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * id.c
+ */
+
+/*
+ * This file implements code to handle uids and gids.
+ *
+ * For space efficiency regular files store uid and gid indexes, which are
+ * converted to 32-bit uids/gids using an id look up table.  This table is
+ * stored compressed into metadata blocks.  A second index table is used to
+ * locate these.  This second index table for speed of access (and because it
+ * is small) is read at mount time and cached in memory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Map uid/gid index into real 32-bit uid/gid using the id look up table
+ */
+int squashfs_get_id(struct super_block *sb, unsigned int index,
+					unsigned int *id)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int block = SQUASHFS_ID_BLOCK(index);
+	int offset = SQUASHFS_ID_BLOCK_OFFSET(index);
+	u64 start_block = le64_to_cpu(msblk->id_table[block]);
+	__le32 disk_id;
+	int err;
+
+	err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset,
+							sizeof(disk_id));
+	if (err < 0)
+		return err;
+
+	*id = le32_to_cpu(disk_id);
+	return 0;
+}
+
+
+/*
+ * Read uncompressed id lookup table indexes from disk into memory
+ */
+__le64 *squashfs_read_id_index_table(struct super_block *sb,
+			u64 id_table_start, unsigned short no_ids)
+{
+	unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids);
+	__le64 *id_table;
+	int err;
+
+	TRACE("In read_id_index_table, length %d\n", length);
+
+	/* Allocate id lookup table indexes */
+	id_table = kmalloc(length, GFP_KERNEL);
+	if (id_table == NULL) {
+		ERROR("Failed to allocate id index table\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	err = squashfs_read_table(sb, id_table, id_table_start, length);
+	if (err < 0) {
+		ERROR("unable to read id index table\n");
+		kfree(id_table);
+		return ERR_PTR(err);
+	}
+
+	return id_table;
+}

fs/squashfs/inode.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * inode.c
+ */
+
+/*
+ * This file implements code to create and read inodes from disk.
+ *
+ * Inodes in Squashfs are identified by a 48-bit inode which encodes the
+ * location of the compressed metadata block containing the inode, and the byte
+ * offset into that block where the inode is placed (<block, offset>).
+ *
+ * To maximise compression there are different inodes for each file type
+ * (regular file, directory, device, etc.), the inode contents and length
+ * varying with the type.
+ *
+ * To further maximise compression, two types of regular file inode and
+ * directory inode are defined: inodes optimised for frequently occurring
+ * regular files and directories, and extended types where extra
+ * information has to be stored.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Initialise VFS inode with the base inode information common to all
+ * Squashfs inode types.  Sqsh_ino contains the unswapped base inode
+ * off disk.
+ */
+static int squashfs_new_inode(struct super_block *sb, struct inode *inode,
+				struct squashfs_base_inode *sqsh_ino)
+{
+	int err;
+
+	err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &inode->i_uid);
+	if (err)
+		return err;
+
+	err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->guid), &inode->i_gid);
+	if (err)
+		return err;
+
+	inode->i_ino = le32_to_cpu(sqsh_ino->inode_number);
+	inode->i_mtime.tv_sec = le32_to_cpu(sqsh_ino->mtime);
+	inode->i_atime.tv_sec = inode->i_mtime.tv_sec;
+	inode->i_ctime.tv_sec = inode->i_mtime.tv_sec;
+	inode->i_mode = le16_to_cpu(sqsh_ino->mode);
+	inode->i_size = 0;
+
+	return err;
+}
+
+
+struct inode *squashfs_iget(struct super_block *sb, long long ino,
+				unsigned int ino_number)
+{
+	struct inode *inode = iget_locked(sb, ino_number);
+	int err;
+
+	TRACE("Entered squashfs_iget\n");
+
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	err = squashfs_read_inode(inode, ino);
+	if (err) {
+		iget_failed(inode);
+		return ERR_PTR(err);
+	}
+
+	unlock_new_inode(inode);
+	return inode;
+}
+
+
+/*
+ * Initialise VFS inode by reading inode from inode table (compressed
+ * metadata).  The format and amount of data read depends on type.
+ */
+int squashfs_read_inode(struct inode *inode, long long ino)
+{
+	struct super_block *sb = inode->i_sb;
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	u64 block = SQUASHFS_INODE_BLK(ino) + msblk->inode_table;
+	int err, type, offset = SQUASHFS_INODE_OFFSET(ino);
+	union squashfs_inode squashfs_ino;
+	struct squashfs_base_inode *sqshb_ino = &squashfs_ino.base;
+
+	TRACE("Entered squashfs_read_inode\n");
+
+	/*
+	 * Read inode base common to all inode types.
+	 */
+	err = squashfs_read_metadata(sb, sqshb_ino, &block,
+				&offset, sizeof(*sqshb_ino));
+	if (err < 0)
+		goto failed_read;
+
+	err = squashfs_new_inode(sb, inode, sqshb_ino);
+	if (err)
+		goto failed_read;
+
+	block = SQUASHFS_INODE_BLK(ino) + msblk->inode_table;
+	offset = SQUASHFS_INODE_OFFSET(ino);
+
+	type = le16_to_cpu(sqshb_ino->inode_type);
+	switch (type) {
+	case SQUASHFS_REG_TYPE: {
+		unsigned int frag_offset, frag_size, frag;
+		u64 frag_blk;
+		struct squashfs_reg_inode *sqsh_ino = &squashfs_ino.reg;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+							sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		frag = le32_to_cpu(sqsh_ino->fragment);
+		if (frag != SQUASHFS_INVALID_FRAG) {
+			frag_offset = le32_to_cpu(sqsh_ino->offset);
+			frag_size = squashfs_frag_lookup(sb, frag, &frag_blk);
+			if (frag_size < 0) {
+				err = frag_size;
+				goto failed_read;
+			}
+		} else {
+			frag_blk = SQUASHFS_INVALID_BLK;
+			frag_size = 0;
+			frag_offset = 0;
+		}
+
+		inode->i_nlink = 1;
+		inode->i_size = le32_to_cpu(sqsh_ino->file_size);
+		inode->i_fop = &generic_ro_fops;
+		inode->i_mode |= S_IFREG;
+		inode->i_blocks = ((inode->i_size - 1) >> 9) + 1;
+		squashfs_i(inode)->fragment_block = frag_blk;
+		squashfs_i(inode)->fragment_size = frag_size;
+		squashfs_i(inode)->fragment_offset = frag_offset;
+		squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block);
+		squashfs_i(inode)->block_list_start = block;
+		squashfs_i(inode)->offset = offset;
+		inode->i_data.a_ops = &squashfs_aops;
+
+		TRACE("File inode %x:%x, start_block %llx, block_list_start "
+			"%llx, offset %x\n", SQUASHFS_INODE_BLK(ino),
+			offset, squashfs_i(inode)->start, block, offset);
+		break;
+	}
+	case SQUASHFS_LREG_TYPE: {
+		unsigned int frag_offset, frag_size, frag;
+		u64 frag_blk;
+		struct squashfs_lreg_inode *sqsh_ino = &squashfs_ino.lreg;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+							sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		frag = le32_to_cpu(sqsh_ino->fragment);
+		if (frag != SQUASHFS_INVALID_FRAG) {
+			frag_offset = le32_to_cpu(sqsh_ino->offset);
+			frag_size = squashfs_frag_lookup(sb, frag, &frag_blk);
+			if (frag_size < 0) {
+				err = frag_size;
+				goto failed_read;
+			}
+		} else {
+			frag_blk = SQUASHFS_INVALID_BLK;
+			frag_size = 0;
+			frag_offset = 0;
+		}
+
+		inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+		inode->i_size = le64_to_cpu(sqsh_ino->file_size);
+		inode->i_fop = &generic_ro_fops;
+		inode->i_mode |= S_IFREG;
+		inode->i_blocks = ((inode->i_size -
+				le64_to_cpu(sqsh_ino->sparse) - 1) >> 9) + 1;
+
+		squashfs_i(inode)->fragment_block = frag_blk;
+		squashfs_i(inode)->fragment_size = frag_size;
+		squashfs_i(inode)->fragment_offset = frag_offset;
+		squashfs_i(inode)->start = le64_to_cpu(sqsh_ino->start_block);
+		squashfs_i(inode)->block_list_start = block;
+		squashfs_i(inode)->offset = offset;
+		inode->i_data.a_ops = &squashfs_aops;
+
+		TRACE("File inode %x:%x, start_block %llx, block_list_start "
+			"%llx, offset %x\n", SQUASHFS_INODE_BLK(ino),
+			offset, squashfs_i(inode)->start, block, offset);
+		break;
+	}
+	case SQUASHFS_DIR_TYPE: {
+		struct squashfs_dir_inode *sqsh_ino = &squashfs_ino.dir;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+				sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+		inode->i_size = le16_to_cpu(sqsh_ino->file_size);
+		inode->i_op = &squashfs_dir_inode_ops;
+		inode->i_fop = &squashfs_dir_ops;
+		inode->i_mode |= S_IFDIR;
+		squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block);
+		squashfs_i(inode)->offset = le16_to_cpu(sqsh_ino->offset);
+		squashfs_i(inode)->dir_idx_cnt = 0;
+		squashfs_i(inode)->parent = le32_to_cpu(sqsh_ino->parent_inode);
+
+		TRACE("Directory inode %x:%x, start_block %llx, offset %x\n",
+				SQUASHFS_INODE_BLK(ino), offset,
+				squashfs_i(inode)->start,
+				le16_to_cpu(sqsh_ino->offset));
+		break;
+	}
+	case SQUASHFS_LDIR_TYPE: {
+		struct squashfs_ldir_inode *sqsh_ino = &squashfs_ino.ldir;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+				sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+		inode->i_size = le32_to_cpu(sqsh_ino->file_size);
+		inode->i_op = &squashfs_dir_inode_ops;
+		inode->i_fop = &squashfs_dir_ops;
+		inode->i_mode |= S_IFDIR;
+		squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block);
+		squashfs_i(inode)->offset = le16_to_cpu(sqsh_ino->offset);
+		squashfs_i(inode)->dir_idx_start = block;
+		squashfs_i(inode)->dir_idx_offset = offset;
+		squashfs_i(inode)->dir_idx_cnt = le16_to_cpu(sqsh_ino->i_count);
+		squashfs_i(inode)->parent = le32_to_cpu(sqsh_ino->parent_inode);
+
+		TRACE("Long directory inode %x:%x, start_block %llx, offset "
+				"%x\n", SQUASHFS_INODE_BLK(ino), offset,
+				squashfs_i(inode)->start,
+				le16_to_cpu(sqsh_ino->offset));
+		break;
+	}
+	case SQUASHFS_SYMLINK_TYPE:
+	case SQUASHFS_LSYMLINK_TYPE: {
+		struct squashfs_symlink_inode *sqsh_ino = &squashfs_ino.symlink;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+				sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+		inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
+		inode->i_op = &page_symlink_inode_operations;
+		inode->i_data.a_ops = &squashfs_symlink_aops;
+		inode->i_mode |= S_IFLNK;
+		squashfs_i(inode)->start = block;
+		squashfs_i(inode)->offset = offset;
+
+		TRACE("Symbolic link inode %x:%x, start_block %llx, offset "
+				"%x\n", SQUASHFS_INODE_BLK(ino), offset,
+				block, offset);
+		break;
+	}
+	case SQUASHFS_BLKDEV_TYPE:
+	case SQUASHFS_CHRDEV_TYPE:
+	case SQUASHFS_LBLKDEV_TYPE:
+	case SQUASHFS_LCHRDEV_TYPE: {
+		struct squashfs_dev_inode *sqsh_ino = &squashfs_ino.dev;
+		unsigned int rdev;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+				sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		if (type == SQUASHFS_CHRDEV_TYPE)
+			inode->i_mode |= S_IFCHR;
+		else
+			inode->i_mode |= S_IFBLK;
+		inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+		rdev = le32_to_cpu(sqsh_ino->rdev);
+		init_special_inode(inode, inode->i_mode, new_decode_dev(rdev));
+
+		TRACE("Device inode %x:%x, rdev %x\n",
+				SQUASHFS_INODE_BLK(ino), offset, rdev);
+		break;
+	}
+	case SQUASHFS_FIFO_TYPE:
+	case SQUASHFS_SOCKET_TYPE:
+	case SQUASHFS_LFIFO_TYPE:
+	case SQUASHFS_LSOCKET_TYPE: {
+		struct squashfs_ipc_inode *sqsh_ino = &squashfs_ino.ipc;
+
+		err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset,
+				sizeof(*sqsh_ino));
+		if (err < 0)
+			goto failed_read;
+
+		if (type == SQUASHFS_FIFO_TYPE)
+			inode->i_mode |= S_IFIFO;
+		else
+			inode->i_mode |= S_IFSOCK;
+		inode->i_nlink = le32_to_cpu(sqsh_ino->nlink);
+		init_special_inode(inode, inode->i_mode, 0);
+		break;
+	}
+	default:
+		ERROR("Unknown inode type %d in squashfs_iget!\n", type);
+		return -EINVAL;
+	}
+
+	return 0;
+
+failed_read:
+	ERROR("Unable to read inode 0x%llx\n", ino);
+	return err;
+}

fs/squashfs/namei.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * namei.c
+ */
+
+/*
+ * This file implements code to do filename lookup in directories.
+ *
+ * Like inodes, directories are packed into compressed metadata blocks, stored
+ * in a directory table.  Directories are accessed using the start address of
+ * the metablock containing the directory and the offset into the
+ * decompressed block (<block, offset>).
+ *
+ * Directories are organised in a slightly complex way, and are not simply
+ * a list of file names.  The organisation takes advantage of the
+ * fact that (in most cases) the inodes of the files will be in the same
+ * compressed metadata block, and therefore, can share the start block.
+ * Directories are therefore organised in a two level list, a directory
+ * header containing the shared start block value, and a sequence of directory
+ * entries, each of which share the shared start block.  A new directory header
+ * is written once/if the inode start block changes.  The directory
+ * header/directory entry list is repeated as many times as necessary.
+ *
+ * Directories are sorted, and can contain a directory index to speed up
+ * file lookup.  Directory indexes store one entry per metablock, each entry
+ * storing the index/filename mapping to the first directory header
+ * in each metadata block.  Directories are sorted in alphabetical order,
+ * and at lookup the index is scanned linearly looking for the first filename
+ * alphabetically larger than the filename being looked up.  At this point the
+ * location of the metadata block the filename is in has been found.
+ * The general idea of the index is ensure only one metadata block needs to be
+ * decompressed to do a lookup irrespective of the length of the directory.
+ * This scheme has the advantage that it doesn't require extra memory overhead
+ * and doesn't require much extra storage on disk.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/dcache.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/*
+ * Lookup name in the directory index, returning the location of the metadata
+ * block containing it, and the directory index this represents.
+ *
+ * If we get an error reading the index then return the part of the index
+ * (if any) we have managed to read - the index isn't essential, just
+ * quicker.
+ */
+static int get_dir_index_using_name(struct super_block *sb,
+			u64 *next_block, int *next_offset, u64 index_start,
+			int index_offset, int i_count, const char *name,
+			int len)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int i, size, length = 0, err;
+	struct squashfs_dir_index *index;
+	char *str;
+
+	TRACE("Entered get_dir_index_using_name, i_count %d\n", i_count);
+
+	index = kmalloc(sizeof(*index) + SQUASHFS_NAME_LEN * 2 + 2, GFP_KERNEL);
+	if (index == NULL) {
+		ERROR("Failed to allocate squashfs_dir_index\n");
+		goto out;
+	}
+
+	str = &index->name[SQUASHFS_NAME_LEN + 1];
+	strncpy(str, name, len);
+	str[len] = '\0';
+
+	for (i = 0; i < i_count; i++) {
+		err = squashfs_read_metadata(sb, index, &index_start,
+					&index_offset, sizeof(*index));
+		if (err < 0)
+			break;
+
+
+		size = le32_to_cpu(index->size) + 1;
+
+		err = squashfs_read_metadata(sb, index->name, &index_start,
+					&index_offset, size);
+		if (err < 0)
+			break;
+
+		index->name[size] = '\0';
+
+		if (strcmp(index->name, str) > 0)
+			break;
+
+		length = le32_to_cpu(index->index);
+		*next_block = le32_to_cpu(index->start_block) +
+					msblk->directory_table;
+	}
+
+	*next_offset = (length + *next_offset) % SQUASHFS_METADATA_SIZE;
+	kfree(index);
+
+out:
+	/*
+	 * Return index (f_pos) of the looked up metadata block.  Translate
+	 * from internal f_pos to external f_pos which is offset by 3 because
+	 * we invent "." and ".." entries which are not actually stored in the
+	 * directory.
+	 */
+	return length + 3;
+}
+
+
+static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
+				 struct nameidata *nd)
+{
+	const unsigned char *name = dentry->d_name.name;
+	int len = dentry->d_name.len;
+	struct inode *inode = NULL;
+	struct squashfs_sb_info *msblk = dir->i_sb->s_fs_info;
+	struct squashfs_dir_header dirh;
+	struct squashfs_dir_entry *dire;
+	u64 block = squashfs_i(dir)->start + msblk->directory_table;
+	int offset = squashfs_i(dir)->offset;
+	int err, length = 0, dir_count, size;
+
+	TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset);
+
+	dire = kmalloc(sizeof(*dire) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL);
+	if (dire == NULL) {
+		ERROR("Failed to allocate squashfs_dir_entry\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (len > SQUASHFS_NAME_LEN) {
+		err = -ENAMETOOLONG;
+		goto failed;
+	}
+
+	length = get_dir_index_using_name(dir->i_sb, &block, &offset,
+				squashfs_i(dir)->dir_idx_start,
+				squashfs_i(dir)->dir_idx_offset,
+				squashfs_i(dir)->dir_idx_cnt, name, len);
+
+	while (length < i_size_read(dir)) {
+		/*
+		 * Read directory header.
+		 */
+		err = squashfs_read_metadata(dir->i_sb, &dirh, &block,
+				&offset, sizeof(dirh));
+		if (err < 0)
+			goto read_failure;
+
+		length += sizeof(dirh);
+
+		dir_count = le32_to_cpu(dirh.count) + 1;
+		while (dir_count--) {
+			/*
+			 * Read directory entry.
+			 */
+			err = squashfs_read_metadata(dir->i_sb, dire, &block,
+					&offset, sizeof(*dire));
+			if (err < 0)
+				goto read_failure;
+
+			size = le16_to_cpu(dire->size) + 1;
+
+			err = squashfs_read_metadata(dir->i_sb, dire->name,
+					&block, &offset, size);
+			if (err < 0)
+				goto read_failure;
+
+			length += sizeof(*dire) + size;
+
+			if (name[0] < dire->name[0])
+				goto exit_lookup;
+
+			if (len == size && !strncmp(name, dire->name, len)) {
+				unsigned int blk, off, ino_num;
+				long long ino;
+				blk = le32_to_cpu(dirh.start_block);
+				off = le16_to_cpu(dire->offset);
+				ino_num = le32_to_cpu(dirh.inode_number) +
+					(short) le16_to_cpu(dire->inode_number);
+				ino = SQUASHFS_MKINODE(blk, off);
+
+				TRACE("calling squashfs_iget for directory "
+					"entry %s, inode  %x:%x, %d\n", name,
+					blk, off, ino_num);
+
+				inode = squashfs_iget(dir->i_sb, ino, ino_num);
+				if (IS_ERR(inode)) {
+					err = PTR_ERR(inode);
+					goto failed;
+				}
+
+				goto exit_lookup;
+			}
+		}
+	}
+
+exit_lookup:
+	kfree(dire);
+	if (inode)
+		return d_splice_alias(inode, dentry);
+	d_add(dentry, inode);
+	return ERR_PTR(0);
+
+read_failure:
+	ERROR("Unable to read directory block [%llx:%x]\n",
+		squashfs_i(dir)->start + msblk->directory_table,
+		squashfs_i(dir)->offset);
+failed:
+	kfree(dire);
+	return ERR_PTR(err);
+}
+
+
+const struct inode_operations squashfs_dir_inode_ops = {
+	.lookup = squashfs_lookup
+};

fs/squashfs/squashfs.h

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * squashfs.h
+ */
+
+#define TRACE(s, args...)	pr_debug("SQUASHFS: "s, ## args)
+
+#define ERROR(s, args...)	pr_err("SQUASHFS error: "s, ## args)
+
+#define WARNING(s, args...)	pr_warning("SQUASHFS: "s, ## args)
+
+static inline struct squashfs_inode_info *squashfs_i(struct inode *inode)
+{
+	return list_entry(inode, struct squashfs_inode_info, vfs_inode);
+}
+
+/* block.c */
+extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *,
+				int);
+
+/* cache.c */
+extern struct squashfs_cache *squashfs_cache_init(char *, int, int);
+extern void squashfs_cache_delete(struct squashfs_cache *);
+extern struct squashfs_cache_entry *squashfs_cache_get(struct super_block *,
+				struct squashfs_cache *, u64, int);
+extern void squashfs_cache_put(struct squashfs_cache_entry *);
+extern int squashfs_copy_data(void *, struct squashfs_cache_entry *, int, int);
+extern int squashfs_read_metadata(struct super_block *, void *, u64 *,
+				int *, int);
+extern struct squashfs_cache_entry *squashfs_get_fragment(struct super_block *,
+				u64, int);
+extern struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *,
+				u64, int);
+extern int squashfs_read_table(struct super_block *, void *, u64, int);
+
+/* export.c */
+extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64,
+				unsigned int);
+
+/* fragment.c */
+extern int squashfs_frag_lookup(struct super_block *, unsigned int, u64 *);
+extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
+				u64, unsigned int);
+
+/* id.c */
+extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
+extern __le64 *squashfs_read_id_index_table(struct super_block *, u64,
+				unsigned short);
+
+/* inode.c */
+extern struct inode *squashfs_iget(struct super_block *, long long,
+				unsigned int);
+extern int squashfs_read_inode(struct inode *, long long);
+
+/*
+ * Inodes and files operations
+ */
+
+/* dir.c */
+extern const struct file_operations squashfs_dir_ops;
+
+/* export.c */
+extern const struct export_operations squashfs_export_ops;
+
+/* file.c */
+extern const struct address_space_operations squashfs_aops;
+
+/* namei.c */
+extern const struct inode_operations squashfs_dir_inode_ops;
+
+/* symlink.c */
+extern const struct address_space_operations squashfs_symlink_aops;

fs/squashfs/squashfs_fs.h

+#ifndef SQUASHFS_FS
+#define SQUASHFS_FS
+/*
+ * Squashfs
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * squashfs_fs.h
+ */
+
+#define SQUASHFS_CACHED_FRAGMENTS	CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE
+#define SQUASHFS_MAJOR			4
+#define SQUASHFS_MINOR			0
+#define SQUASHFS_MAGIC			0x73717368
+#define SQUASHFS_START			0
+
+/* size of metadata (inode and directory) blocks */
+#define SQUASHFS_METADATA_SIZE		8192
+#define SQUASHFS_METADATA_LOG		13
+
+/* default size of data blocks */
+#define SQUASHFS_FILE_SIZE		131072
+#define SQUASHFS_FILE_LOG		17
+
+#define SQUASHFS_FILE_MAX_SIZE		1048576
+#define SQUASHFS_FILE_MAX_LOG		20
+
+/* Max number of uids and gids */
+#define SQUASHFS_IDS			65536
+
+/* Max length of filename (not 255) */
+#define SQUASHFS_NAME_LEN		256
+
+#define SQUASHFS_INVALID_FRAG		(0xffffffffU)
+#define SQUASHFS_INVALID_BLK		(-1LL)
+
+/* Filesystem flags */
+#define SQUASHFS_NOI			0
+#define SQUASHFS_NOD			1
+#define SQUASHFS_NOF			3
+#define SQUASHFS_NO_FRAG		4
+#define SQUASHFS_ALWAYS_FRAG		5
+#define SQUASHFS_DUPLICATE		6
+#define SQUASHFS_EXPORT			7
+
+#define SQUASHFS_BIT(flag, bit)		((flag >> bit) & 1)
+
+#define SQUASHFS_UNCOMPRESSED_INODES(flags)	SQUASHFS_BIT(flags, \
+						SQUASHFS_NOI)
+
+#define SQUASHFS_UNCOMPRESSED_DATA(flags)	SQUASHFS_BIT(flags, \
+						SQUASHFS_NOD)
+
+#define SQUASHFS_UNCOMPRESSED_FRAGMENTS(flags)	SQUASHFS_BIT(flags, \
+						SQUASHFS_NOF)
+
+#define SQUASHFS_NO_FRAGMENTS(flags)		SQUASHFS_BIT(flags, \
+						SQUASHFS_NO_FRAG)
+
+#define SQUASHFS_ALWAYS_FRAGMENTS(flags)	SQUASHFS_BIT(flags, \
+						SQUASHFS_ALWAYS_FRAG)
+
+#define SQUASHFS_DUPLICATES(flags)		SQUASHFS_BIT(flags, \
+						SQUASHFS_DUPLICATE)
+
+#define SQUASHFS_EXPORTABLE(flags)		SQUASHFS_BIT(flags, \
+						SQUASHFS_EXPORT)
+
+/* Max number of types and file types */
+#define SQUASHFS_DIR_TYPE		1
+#define SQUASHFS_REG_TYPE		2
+#define SQUASHFS_SYMLINK_TYPE		3
+#define SQUASHFS_BLKDEV_TYPE		4
+#define SQUASHFS_CHRDEV_TYPE		5
+#define SQUASHFS_FIFO_TYPE		6
+#define SQUASHFS_SOCKET_TYPE		7
+#define SQUASHFS_LDIR_TYPE		8
+#define SQUASHFS_LREG_TYPE		9
+#define SQUASHFS_LSYMLINK_TYPE		10
+#define SQUASHFS_LBLKDEV_TYPE		11
+#define SQUASHFS_LCHRDEV_TYPE		12
+#define SQUASHFS_LFIFO_TYPE		13
+#define SQUASHFS_LSOCKET_TYPE		14
+
+/* Flag whether block is compressed or uncompressed, bit is set if block is
+ * uncompressed */
+#define SQUASHFS_COMPRESSED_BIT		(1 << 15)
+
+#define SQUASHFS_COMPRESSED_SIZE(B)	(((B) & ~SQUASHFS_COMPRESSED_BIT) ? \
+		(B) & ~SQUASHFS_COMPRESSED_BIT :  SQUASHFS_COMPRESSED_BIT)
+
+#define SQUASHFS_COMPRESSED(B)		(!((B) & SQUASHFS_COMPRESSED_BIT))
+
+#define SQUASHFS_COMPRESSED_BIT_BLOCK	(1 << 24)
+
+#define SQUASHFS_COMPRESSED_SIZE_BLOCK(B)	((B) & \
+						~SQUASHFS_COMPRESSED_BIT_BLOCK)
+
+#define SQUASHFS_COMPRESSED_BLOCK(B)	(!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK))
+
+/*
+ * Inode number ops.  Inodes consist of a compressed block number, and an
+ * uncompressed offset within that block
+ */
+#define SQUASHFS_INODE_BLK(A)		((unsigned int) ((A) >> 16))
+
+#define SQUASHFS_INODE_OFFSET(A)	((unsigned int) ((A) & 0xffff))
+
+#define SQUASHFS_MKINODE(A, B)		((long long)(((long long) (A)\
+					<< 16) + (B)))
+
+/* Translate between VFS mode and squashfs mode */
+#define SQUASHFS_MODE(A)		((A) & 0xfff)
+
+/* fragment and fragment table defines */
+#define SQUASHFS_FRAGMENT_BYTES(A)	\
+				((A) * sizeof(struct squashfs_fragment_entry))
+
+#define SQUASHFS_FRAGMENT_INDEX(A)	(SQUASHFS_FRAGMENT_BYTES(A) / \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_FRAGMENT_INDEX_OFFSET(A)	(SQUASHFS_FRAGMENT_BYTES(A) % \
+						SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_FRAGMENT_INDEXES(A)	((SQUASHFS_FRAGMENT_BYTES(A) + \
+					SQUASHFS_METADATA_SIZE - 1) / \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_FRAGMENT_INDEX_BYTES(A)	(SQUASHFS_FRAGMENT_INDEXES(A) *\
+						sizeof(u64))
+
+/* inode lookup table defines */
+#define SQUASHFS_LOOKUP_BYTES(A)	((A) * sizeof(u64))
+
+#define SQUASHFS_LOOKUP_BLOCK(A)	(SQUASHFS_LOOKUP_BYTES(A) / \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_LOOKUP_BLOCK_OFFSET(A)	(SQUASHFS_LOOKUP_BYTES(A) % \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_LOOKUP_BLOCKS(A)	((SQUASHFS_LOOKUP_BYTES(A) + \
+					SQUASHFS_METADATA_SIZE - 1) / \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_LOOKUP_BLOCK_BYTES(A)	(SQUASHFS_LOOKUP_BLOCKS(A) *\
+					sizeof(u64))
+
+/* uid/gid lookup table defines */
+#define SQUASHFS_ID_BYTES(A)		((A) * sizeof(unsigned int))
+
+#define SQUASHFS_ID_BLOCK(A)		(SQUASHFS_ID_BYTES(A) / \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_ID_BLOCK_OFFSET(A)	(SQUASHFS_ID_BYTES(A) % \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_ID_BLOCKS(A)		((SQUASHFS_ID_BYTES(A) + \
+					SQUASHFS_METADATA_SIZE - 1) / \
+					SQUASHFS_METADATA_SIZE)
+
+#define SQUASHFS_ID_BLOCK_BYTES(A)	(SQUASHFS_ID_BLOCKS(A) *\
+					sizeof(u64))
+
+/* cached data constants for filesystem */
+#define SQUASHFS_CACHED_BLKS		8
+
+#define SQUASHFS_MAX_FILE_SIZE_LOG	64
+
+#define SQUASHFS_MAX_FILE_SIZE		(1LL << \
+					(SQUASHFS_MAX_FILE_SIZE_LOG - 2))
+
+#define SQUASHFS_MARKER_BYTE		0xff
+
+/* meta index cache */
+#define SQUASHFS_META_INDEXES	(SQUASHFS_METADATA_SIZE / sizeof(unsigned int))
+#define SQUASHFS_META_ENTRIES	127
+#define SQUASHFS_META_SLOTS	8
+
+struct meta_entry {
+	u64			data_block;
+	unsigned int		index_block;
+	unsigned short		offset;
+	unsigned short		pad;
+};
+
+struct meta_index {
+	unsigned int		inode_number;
+	unsigned int		offset;
+	unsigned short		entries;
+	unsigned short		skip;
+	unsigned short		locked;
+	unsigned short		pad;
+	struct meta_entry	meta_entry[SQUASHFS_META_ENTRIES];
+};
+
+
+/*
+ * definitions for structures on disk
+ */
+#define ZLIB_COMPRESSION	 1
+
+struct squashfs_super_block {
+	__le32			s_magic;
+	__le32			inodes;
+	__le32			mkfs_time;
+	__le32			block_size;
+	__le32			fragments;
+	__le16			compression;
+	__le16			block_log;
+	__le16			flags;
+	__le16			no_ids;
+	__le16			s_major;
+	__le16			s_minor;
+	__le64			root_inode;
+	__le64			bytes_used;
+	__le64			id_table_start;
+	__le64			xattr_table_start;
+	__le64			inode_table_start;
+	__le64			directory_table_start;
+	__le64			fragment_table_start;
+	__le64			lookup_table_start;
+};
+
+struct squashfs_dir_index {
+	__le32			index;
+	__le32			start_block;
+	__le32			size;
+	unsigned char		name[0];
+};
+
+struct squashfs_base_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+};
+
+struct squashfs_ipc_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le32			nlink;
+};
+
+struct squashfs_dev_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le32			nlink;
+	__le32			rdev;
+};
+
+struct squashfs_symlink_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le32			nlink;
+	__le32			symlink_size;
+	char			symlink[0];
+};
+
+struct squashfs_reg_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le32			start_block;
+	__le32			fragment;
+	__le32			offset;
+	__le32			file_size;
+	__le16			block_list[0];
+};
+
+struct squashfs_lreg_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le64			start_block;
+	__le64			file_size;
+	__le64			sparse;
+	__le32			nlink;
+	__le32			fragment;
+	__le32			offset;
+	__le32			xattr;
+	__le16			block_list[0];
+};
+
+struct squashfs_dir_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le32			start_block;
+	__le32			nlink;
+	__le16			file_size;
+	__le16			offset;
+	__le32			parent_inode;
+};
+
+struct squashfs_ldir_inode {
+	__le16			inode_type;
+	__le16			mode;
+	__le16			uid;
+	__le16			guid;
+	__le32			mtime;
+	__le32	 		inode_number;
+	__le32			nlink;
+	__le32			file_size;
+	__le32			start_block;
+	__le32			parent_inode;
+	__le16			i_count;
+	__le16			offset;
+	__le32			xattr;
+	struct squashfs_dir_index	index[0];
+};
+
+union squashfs_inode {
+	struct squashfs_base_inode		base;
+	struct squashfs_dev_inode		dev;
+	struct squashfs_symlink_inode		symlink;
+	struct squashfs_reg_inode		reg;
+	struct squashfs_lreg_inode		lreg;
+	struct squashfs_dir_inode		dir;
+	struct squashfs_ldir_inode		ldir;
+	struct squashfs_ipc_inode		ipc;
+};
+
+struct squashfs_dir_entry {
+	__le16			offset;
+	__le16			inode_number;
+	__le16			type;
+	__le16			size;
+	char			name[0];
+};
+
+struct squashfs_dir_header {
+	__le32			count;
+	__le32			start_block;
+	__le32			inode_number;
+};
+
+struct squashfs_fragment_entry {
+	__le64			start_block;
+	__le32			size;
+	unsigned int		unused;
+};
+
+#endif

fs/squashfs/squashfs_fs_i.h

+#ifndef SQUASHFS_FS_I
+#define SQUASHFS_FS_I
+/*
+ * Squashfs
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * squashfs_fs_i.h
+ */
+
+struct squashfs_inode_info {
+	u64		start;
+	int		offset;
+	union {
+		struct {
+			u64		fragment_block;
+			int		fragment_size;
+			int		fragment_offset;
+			u64		block_list_start;
+		};
+		struct {
+			u64		dir_idx_start;
+			int		dir_idx_offset;
+			int		dir_idx_cnt;
+			int		parent;
+		};
+	};
+	struct inode	vfs_inode;
+};
+#endif

fs/squashfs/squashfs_fs_sb.h

+#ifndef SQUASHFS_FS_SB
+#define SQUASHFS_FS_SB
+/*
+ * Squashfs
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * squashfs_fs_sb.h
+ */
+
+#include "squashfs_fs.h"
+
+struct squashfs_cache {
+	char			*name;
+	int			entries;
+	int			next_blk;
+	int			num_waiters;
+	int			unused;
+	int			block_size;
+	int			pages;
+	spinlock_t		lock;
+	wait_queue_head_t	wait_queue;
+	struct squashfs_cache_entry *entry;
+};
+
+struct squashfs_cache_entry {
+	u64			block;
+	int			length;
+	int			refcount;
+	u64			next_index;
+	int			pending;
+	int			error;
+	int			num_waiters;
+	wait_queue_head_t	wait_queue;
+	struct squashfs_cache	*cache;
+	void			**data;
+};
+
+struct squashfs_sb_info {
+	int			devblksize;
+	int			devblksize_log2;
+	struct squashfs_cache	*block_cache;
+	struct squashfs_cache	*fragment_cache;
+	struct squashfs_cache	*read_page;
+	int			next_meta_index;
+	__le64			*id_table;
+	__le64			*fragment_index;
+	unsigned int		*fragment_index_2;
+	struct mutex		read_data_mutex;
+	struct mutex		meta_index_mutex;
+	struct meta_index	*meta_index;
+	z_stream		stream;
+	__le64			*inode_lookup_table;
+	u64			inode_table;
+	u64			directory_table;
+	unsigned int		block_size;
+	unsigned short		block_log;
+	long long		bytes_used;
+	unsigned int		inodes;
+};
+#endif

fs/squashfs/super.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * super.c
+ */
+
+/*
+ * This file implements code to read the superblock, read and initialise
+ * in-memory structures at mount time, and all the VFS glue code to register
+ * the filesystem.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+static struct file_system_type squashfs_fs_type;
+static struct super_operations squashfs_super_ops;
+
+static int supported_squashfs_filesystem(short major, short minor, short comp)
+{
+	if (major < SQUASHFS_MAJOR) {
+		ERROR("Major/Minor mismatch, older Squashfs %d.%d "
+			"filesystems are unsupported\n", major, minor);
+		return -EINVAL;
+	} else if (major > SQUASHFS_MAJOR || minor > SQUASHFS_MINOR) {
+		ERROR("Major/Minor mismatch, trying to mount newer "
+			"%d.%d filesystem\n", major, minor);
+		ERROR("Please update your kernel\n");
+		return -EINVAL;
+	}
+
+	if (comp != ZLIB_COMPRESSION)
+		return -EINVAL;
+
+	return 0;
+}
+
+
+static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct squashfs_sb_info *msblk;
+	struct squashfs_super_block *sblk = NULL;
+	char b[BDEVNAME_SIZE];
+	struct inode *root;
+	long long root_inode;
+	unsigned short flags;
+	unsigned int fragments;
+	u64 lookup_table_start;
+	int err;
+
+	TRACE("Entered squashfs_fill_superblock\n");
+
+	sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL);
+	if (sb->s_fs_info == NULL) {
+		ERROR("Failed to allocate squashfs_sb_info\n");
+		return -ENOMEM;
+	}
+	msblk = sb->s_fs_info;
+
+	msblk->stream.workspace = kmalloc(zlib_inflate_workspacesize(),
+		GFP_KERNEL);
+	if (msblk->stream.workspace == NULL) {
+		ERROR("Failed to allocate zlib workspace\n");
+		goto failure;
+	}
+
+	sblk = kzalloc(sizeof(*sblk), GFP_KERNEL);
+	if (sblk == NULL) {
+		ERROR("Failed to allocate squashfs_super_block\n");
+		goto failure;
+	}
+
+	msblk->devblksize = sb_min_blocksize(sb, BLOCK_SIZE);
+	msblk->devblksize_log2 = ffz(~msblk->devblksize);
+
+	mutex_init(&msblk->read_data_mutex);
+	mutex_init(&msblk->meta_index_mutex);
+
+	/*
+	 * msblk->bytes_used is checked in squashfs_read_table to ensure reads
+	 * are not beyond filesystem end.  But as we're using
+	 * squashfs_read_table here to read the superblock (including the value
+	 * of bytes_used) we need to set it to an initial sensible dummy value
+	 */
+	msblk->bytes_used = sizeof(*sblk);
+	err = squashfs_read_table(sb, sblk, SQUASHFS_START, sizeof(*sblk));
+
+	if (err < 0) {
+		ERROR("unable to read squashfs_super_block\n");
+		goto failed_mount;
+	}
+
+	/* Check it is a SQUASHFS superblock */
+	sb->s_magic = le32_to_cpu(sblk->s_magic);
+	if (sb->s_magic != SQUASHFS_MAGIC) {
+		if (!silent)
+			ERROR("Can't find a SQUASHFS superblock on %s\n",
+						bdevname(sb->s_bdev, b));
+		err = -EINVAL;
+		goto failed_mount;
+	}
+
+	/* Check the MAJOR & MINOR versions and compression type */
+	err = supported_squashfs_filesystem(le16_to_cpu(sblk->s_major),
+			le16_to_cpu(sblk->s_minor),
+			le16_to_cpu(sblk->compression));
+	if (err < 0)
+		goto failed_mount;
+
+	err = -EINVAL;
+
+	/*
+	 * Check if there's xattrs in the filesystem.  These are not
+	 * supported in this version, so warn that they will be ignored.
+	 */
+	if (le64_to_cpu(sblk->xattr_table_start) != SQUASHFS_INVALID_BLK)
+		ERROR("Xattrs in filesystem, these will be ignored\n");
+
+	/* Check the filesystem does not extend beyond the end of the
+	   block device */
+	msblk->bytes_used = le64_to_cpu(sblk->bytes_used);
+	if (msblk->bytes_used < 0 || msblk->bytes_used >
+			i_size_read(sb->s_bdev->bd_inode))
+		goto failed_mount;
+
+	/* Check block size for sanity */
+	msblk->block_size = le32_to_cpu(sblk->block_size);
+	if (msblk->block_size > SQUASHFS_FILE_MAX_SIZE)
+		goto failed_mount;
+
+	msblk->block_log = le16_to_cpu(sblk->block_log);
+	if (msblk->block_log > SQUASHFS_FILE_MAX_LOG)
+		goto failed_mount;
+
+	/* Check the root inode for sanity */
+	root_inode = le64_to_cpu(sblk->root_inode);
+	if (SQUASHFS_INODE_OFFSET(root_inode) > SQUASHFS_METADATA_SIZE)
+		goto failed_mount;
+
+	msblk->inode_table = le64_to_cpu(sblk->inode_table_start);
+	msblk->directory_table = le64_to_cpu(sblk->directory_table_start);
+	msblk->inodes = le32_to_cpu(sblk->inodes);
+	flags = le16_to_cpu(sblk->flags);
+
+	TRACE("Found valid superblock on %s\n", bdevname(sb->s_bdev, b));
+	TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags)
+				? "un" : "");
+	TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags)
+				? "un" : "");
+	TRACE("Filesystem size %lld bytes\n", msblk->bytes_used);
+	TRACE("Block size %d\n", msblk->block_size);
+	TRACE("Number of inodes %d\n", msblk->inodes);
+	TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments));
+	TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids));
+	TRACE("sblk->inode_table_start %llx\n", msblk->inode_table);
+	TRACE("sblk->directory_table_start %llx\n", msblk->directory_table);
+	TRACE("sblk->fragment_table_start %llx\n",
+		(u64) le64_to_cpu(sblk->fragment_table_start));
+	TRACE("sblk->id_table_start %llx\n",
+		(u64) le64_to_cpu(sblk->id_table_start));
+
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_flags |= MS_RDONLY;
+	sb->s_op = &squashfs_super_ops;
+
+	err = -ENOMEM;
+
+	msblk->block_cache = squashfs_cache_init("metadata",
+			SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE);
+	if (msblk->block_cache == NULL)
+		goto failed_mount;
+
+	/* Allocate read_page block */
+	msblk->read_page = squashfs_cache_init("data", 1, msblk->block_size);
+	if (msblk->read_page == NULL) {
+		ERROR("Failed to allocate read_page block\n");
+		goto failed_mount;
+	}
+
+	/* Allocate and read id index table */
+	msblk->id_table = squashfs_read_id_index_table(sb,
+		le64_to_cpu(sblk->id_table_start), le16_to_cpu(sblk->no_ids));
+	if (IS_ERR(msblk->id_table)) {
+		err = PTR_ERR(msblk->id_table);
+		msblk->id_table = NULL;
+		goto failed_mount;
+	}
+
+	fragments = le32_to_cpu(sblk->fragments);
+	if (fragments == 0)
+		goto allocate_lookup_table;
+
+	msblk->fragment_cache = squashfs_cache_init("fragment",
+		SQUASHFS_CACHED_FRAGMENTS, msblk->block_size);
+	if (msblk->fragment_cache == NULL) {
+		err = -ENOMEM;
+		goto failed_mount;
+	}
+
+	/* Allocate and read fragment index table */
+	msblk->fragment_index = squashfs_read_fragment_index_table(sb,
+		le64_to_cpu(sblk->fragment_table_start), fragments);
+	if (IS_ERR(msblk->fragment_index)) {
+		err = PTR_ERR(msblk->fragment_index);
+		msblk->fragment_index = NULL;
+		goto failed_mount;
+	}
+
+allocate_lookup_table:
+	lookup_table_start = le64_to_cpu(sblk->lookup_table_start);
+	if (lookup_table_start == SQUASHFS_INVALID_BLK)
+		goto allocate_root;
+
+	/* Allocate and read inode lookup table */
+	msblk->inode_lookup_table = squashfs_read_inode_lookup_table(sb,
+		lookup_table_start, msblk->inodes);
+	if (IS_ERR(msblk->inode_lookup_table)) {
+		err = PTR_ERR(msblk->inode_lookup_table);
+		msblk->inode_lookup_table = NULL;
+		goto failed_mount;
+	}
+
+	sb->s_export_op = &squashfs_export_ops;
+
+allocate_root:
+	root = new_inode(sb);
+	if (!root) {
+		err = -ENOMEM;
+		goto failed_mount;
+	}
+
+	err = squashfs_read_inode(root, root_inode);
+	if (err) {
+		iget_failed(root);
+		goto failed_mount;
+	}
+	insert_inode_hash(root);
+
+	sb->s_root = d_alloc_root(root);
+	if (sb->s_root == NULL) {
+		ERROR("Root inode create failed\n");
+		err = -ENOMEM;
+		iput(root);
+		goto failed_mount;
+	}
+
+	TRACE("Leaving squashfs_fill_super\n");
+	kfree(sblk);
+	return 0;
+
+failed_mount:
+	squashfs_cache_delete(msblk->block_cache);
+	squashfs_cache_delete(msblk->fragment_cache);
+	squashfs_cache_delete(msblk->read_page);
+	kfree(msblk->inode_lookup_table);
+	kfree(msblk->fragment_index);
+	kfree(msblk->id_table);
+	kfree(msblk->stream.workspace);
+	kfree(sb->s_fs_info);
+	sb->s_fs_info = NULL;
+	kfree(sblk);
+	return err;
+
+failure:
+	kfree(msblk->stream.workspace);
+	kfree(sb->s_fs_info);
+	sb->s_fs_info = NULL;
+	return -ENOMEM;
+}
+
+
+static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct squashfs_sb_info *msblk = dentry->d_sb->s_fs_info;
+
+	TRACE("Entered squashfs_statfs\n");
+
+	buf->f_type = SQUASHFS_MAGIC;
+	buf->f_bsize = msblk->block_size;
+	buf->f_blocks = ((msblk->bytes_used - 1) >> msblk->block_log) + 1;
+	buf->f_bfree = buf->f_bavail = 0;
+	buf->f_files = msblk->inodes;
+	buf->f_ffree = 0;
+	buf->f_namelen = SQUASHFS_NAME_LEN;
+
+	return 0;
+}
+
+
+static int squashfs_remount(struct super_block *sb, int *flags, char *data)
+{
+	*flags |= MS_RDONLY;
+	return 0;
+}
+
+
+static void squashfs_put_super(struct super_block *sb)
+{
+	if (sb->s_fs_info) {
+		struct squashfs_sb_info *sbi = sb->s_fs_info;
+		squashfs_cache_delete(sbi->block_cache);
+		squashfs_cache_delete(sbi->fragment_cache);
+		squashfs_cache_delete(sbi->read_page);
+		kfree(sbi->id_table);
+		kfree(sbi->fragment_index);
+		kfree(sbi->meta_index);
+		kfree(sbi->stream.workspace);
+		kfree(sb->s_fs_info);
+		sb->s_fs_info = NULL;
+	}
+}
+
+
+static int squashfs_get_sb(struct file_system_type *fs_type, int flags,
+				const char *dev_name, void *data,
+				struct vfsmount *mnt)
+{
+	return get_sb_bdev(fs_type, flags, dev_name, data, squashfs_fill_super,
+				mnt);
+}
+
+
+static struct kmem_cache *squashfs_inode_cachep;
+
+
+static void init_once(void *foo)
+{
+	struct squashfs_inode_info *ei = foo;
+
+	inode_init_once(&ei->vfs_inode);
+}
+
+
+static int __init init_inodecache(void)
+{
+	squashfs_inode_cachep = kmem_cache_create("squashfs_inode_cache",
+		sizeof(struct squashfs_inode_info), 0,
+		SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT, init_once);
+
+	return squashfs_inode_cachep ? 0 : -ENOMEM;
+}
+
+
+static void destroy_inodecache(void)
+{
+	kmem_cache_destroy(squashfs_inode_cachep);
+}
+
+
+static int __init init_squashfs_fs(void)
+{
+	int err = init_inodecache();
+
+	if (err)
+		return err;
+
+	err = register_filesystem(&squashfs_fs_type);
+	if (err) {
+		destroy_inodecache();
+		return err;
+	}
+
+	printk(KERN_INFO "squashfs: version 4.0 (2009/01/03) "
+		"Phillip Lougher\n");
+
+	return 0;
+}
+
+
+static void __exit exit_squashfs_fs(void)
+{
+	unregister_filesystem(&squashfs_fs_type);
+	destroy_inodecache();
+}
+
+
+static struct inode *squashfs_alloc_inode(struct super_block *sb)
+{
+	struct squashfs_inode_info *ei =
+		kmem_cache_alloc(squashfs_inode_cachep, GFP_KERNEL);
+
+	return ei ? &ei->vfs_inode : NULL;
+}
+
+
+static void squashfs_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(squashfs_inode_cachep, squashfs_i(inode));
+}
+
+
+static struct file_system_type squashfs_fs_type = {
+	.owner = THIS_MODULE,
+	.name = "squashfs",
+	.get_sb = squashfs_get_sb,
+	.kill_sb = kill_block_super,
+	.fs_flags = FS_REQUIRES_DEV
+};
+
+static struct super_operations squashfs_super_ops = {
+	.alloc_inode = squashfs_alloc_inode,
+	.destroy_inode = squashfs_destroy_inode,
+	.statfs = squashfs_statfs,
+	.put_super = squashfs_put_super,
+	.remount_fs = squashfs_remount
+};
+
+module_init(init_squashfs_fs);
+module_exit(exit_squashfs_fs);
+MODULE_DESCRIPTION("squashfs 4.0, a compressed read-only filesystem");
+MODULE_AUTHOR("Phillip Lougher <phillip@lougher.demon.co.uk>");
+MODULE_LICENSE("GPL");

fs/squashfs/symlink.c

+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008
+ * Phillip Lougher <phillip@lougher.demon.co.uk>
+ *
+ * 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,
+ * 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; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * symlink.c
+ */
+
+/*
+ * This file implements code to handle symbolic links.
+ *
+ * The data contents of symbolic links are stored inside the symbolic
+ * link inode within the inode table.  This allows the normally small symbolic
+ * link to be compressed as part of the inode table, achieving much greater
+ * compression than if the symbolic link was compressed individually.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/zlib.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+static int squashfs_symlink_readpage(struct file *file, struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	int index = page->index << PAGE_CACHE_SHIFT;
+	u64 block = squashfs_i(inode)->start;
+	int offset = squashfs_i(inode)->offset;
+	int length = min_t(int, i_size_read(inode) - index, PAGE_CACHE_SIZE);
+	int bytes, copied;
+	void *pageaddr;
+	struct squashfs_cache_entry *entry;
+
+	TRACE("Entered squashfs_symlink_readpage, page index %ld, start block "
+			"%llx, offset %x\n", page->index, block, offset);
+
+	/*
+	 * Skip index bytes into symlink metadata.
+	 */
+	if (index) {
+		bytes = squashfs_read_metadata(sb, NULL, &block, &offset,
+								index);
+		if (bytes < 0) {
+			ERROR("Unable to read symlink [%llx:%x]\n",
+				squashfs_i(inode)->start,
+				squashfs_i(inode)->offset);
+			goto error_out;
+		}
+	}
+
+	/*
+	 * Read length bytes from symlink metadata.  Squashfs_read_metadata
+	 * is not used here because it can sleep and we want to use
+	 * kmap_atomic to map the page.  Instead call the underlying
+	 * squashfs_cache_get routine.  As length bytes may overlap metadata
+	 * blocks, we may need to call squashfs_cache_get multiple times.
+	 */
+	for (bytes = 0; bytes < length; offset = 0, bytes += copied) {
+		entry = squashfs_cache_get(sb, msblk->block_cache, block, 0);
+		if (entry->error) {
+			ERROR("Unable to read symlink [%llx:%x]\n",
+				squashfs_i(inode)->start,
+				squashfs_i(inode)->offset);
+			squashfs_cache_put(entry);
+			goto error_out;
+		}
+
+		pageaddr = kmap_atomic(page, KM_USER0);
+		copied = squashfs_copy_data(pageaddr + bytes, entry, offset,
+								length - bytes);
+		if (copied == length - bytes)
+			memset(pageaddr + length, 0, PAGE_CACHE_SIZE - length);
+		else
+			block = entry->next_index;
+		kunmap_atomic(pageaddr, KM_USER0);
+		squashfs_cache_put(entry);
+	}
+
+	flush_dcache_page(page);
+	SetPageUptodate(page);
+	unlock_page(page);
+	return 0;
+
+error_out:
+	SetPageError(page);
+	unlock_page(page);
+	return 0;
+}
+
+
+const struct address_space_operations squashfs_symlink_aops = {
+	.readpage = squashfs_symlink_readpage
+};

init/do_mounts_rd.c

@@ -9,6 +9,7 @@
 #include <linux/string.h>
 
 #include "do_mounts.h"
+#include "../fs/squashfs/squashfs_fs.h"
 
 int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */
 
@@ -41,6 +42,7 @@ static int __init crd_load(int in_fd, int out_fd);
  * 	ext2
  *	romfs
  *	cramfs
+ *	squashfs
  * 	gzip
  */
 static int __init 
@@ -51,6 +53,7 @@ identify_ramdisk_image(int fd, int start_block)
 	struct ext2_super_block *ext2sb;
 	struct romfs_super_block *romfsb;
 	struct cramfs_super *cramfsb;
+	struct squashfs_super_block *squashfsb;
 	int nblocks = -1;
 	unsigned char *buf;
 
@@ -62,6 +65,7 @@ identify_ramdisk_image(int fd, int start_block)
 	ext2sb = (struct ext2_super_block *) buf;
 	romfsb = (struct romfs_super_block *) buf;
 	cramfsb = (struct cramfs_super *) buf;
+	squashfsb = (struct squashfs_super_block *) buf;
 	memset(buf, 0xe5, size);
 
 	/*
@@ -99,6 +103,16 @@ identify_ramdisk_image(int fd, int start_block)
 		goto done;
 	}
 
+	/* squashfs is at block zero too */
+	if (le32_to_cpu(squashfsb->s_magic) == SQUASHFS_MAGIC) {
+		printk(KERN_NOTICE
+		       "RAMDISK: squashfs filesystem found at block %d\n",
+		       start_block);
+		nblocks = (le64_to_cpu(squashfsb->bytes_used) + BLOCK_SIZE - 1)
+			 >> BLOCK_SIZE_BITS;
+		goto done;
+	}
+
 	/*
 	 * Read block 1 to test for minix and ext2 superblock
 	 */