add idl4k kernel firmware version 1.13.0.105

kernel/fs/reiserfs/Kconfig

@@ -0,0 +1,86 @@
+config REISERFS_FS
+	tristate "Reiserfs support"
+	select CRC32
+	help
+	  Stores not just filenames but the files themselves in a balanced
+	  tree.  Uses journalling.
+
+	  Balanced trees are more efficient than traditional file system
+	  architectural foundations.
+
+	  In general, ReiserFS is as fast as ext2, but is very efficient with
+	  large directories and small files.  Additional patches are needed
+	  for NFS and quotas, please see <http://www.namesys.com/> for links.
+
+	  It is more easily extended to have features currently found in
+	  database and keyword search systems than block allocation based file
+	  systems are.  The next version will be so extended, and will support
+	  plugins consistent with our motto ``It takes more than a license to
+	  make source code open.''
+
+	  Read <http://www.namesys.com/> to learn more about reiserfs.
+
+	  Sponsored by Threshold Networks, Emusic.com, and Bigstorage.com.
+
+	  If you like it, you can pay us to add new features to it that you
+	  need, buy a support contract, or pay us to port it to another OS.
+
+config REISERFS_CHECK
+	bool "Enable reiserfs debug mode"
+	depends on REISERFS_FS
+	help
+	  If you set this to Y, then ReiserFS will perform every check it can
+	  possibly imagine of its internal consistency throughout its
+	  operation.  It will also go substantially slower.  More than once we
+	  have forgotten that this was on, and then gone despondent over the
+	  latest benchmarks.:-) Use of this option allows our team to go all
+	  out in checking for consistency when debugging without fear of its
+	  effect on end users.  If you are on the verge of sending in a bug
+	  report, say Y and you might get a useful error message.  Almost
+	  everyone should say N.
+
+config REISERFS_PROC_INFO
+	bool "Stats in /proc/fs/reiserfs"
+	depends on REISERFS_FS && PROC_FS
+	help
+	  Create under /proc/fs/reiserfs a hierarchy of files, displaying
+	  various ReiserFS statistics and internal data at the expense of
+	  making your kernel or module slightly larger (+8 KB). This also
+	  increases the amount of kernel memory required for each mount.
+	  Almost everyone but ReiserFS developers and people fine-tuning
+	  reiserfs or tracing problems should say N.
+
+config REISERFS_FS_XATTR
+	bool "ReiserFS extended attributes"
+	depends on REISERFS_FS
+	help
+	  Extended attributes are name:value pairs associated with inodes by
+	  the kernel or by users (see the attr(5) manual page, or visit
+	  <http://acl.bestbits.at/> for details).
+
+	  If unsure, say N.
+
+config REISERFS_FS_POSIX_ACL
+	bool "ReiserFS POSIX Access Control Lists"
+	depends on REISERFS_FS_XATTR
+	select FS_POSIX_ACL
+	help
+	  Posix Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the Posix ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N
+
+config REISERFS_FS_SECURITY
+	bool "ReiserFS Security Labels"
+	depends on REISERFS_FS_XATTR
+	help
+	  Security labels support alternative access control models
+	  implemented by security modules like SELinux.  This option
+	  enables an extended attribute handler for file security
+	  labels in the ReiserFS filesystem.
+
+	  If you are not using a security module that requires using
+	  extended attributes for file security labels, say N.

kernel/fs/reiserfs/Makefile

@@ -0,0 +1,36 @@
+#
+# Makefile for the linux reiser-filesystem routines.
+#
+
+obj-$(CONFIG_REISERFS_FS) += reiserfs.o
+
+reiserfs-objs := bitmap.o do_balan.o namei.o inode.o file.o dir.o fix_node.o \
+		 super.o prints.o objectid.o lbalance.o ibalance.o stree.o \
+		 hashes.o tail_conversion.o journal.o resize.o \
+		 item_ops.o ioctl.o procfs.o xattr.o
+
+ifeq ($(CONFIG_REISERFS_FS_XATTR),y)
+reiserfs-objs += xattr_user.o xattr_trusted.o
+endif
+
+ifeq ($(CONFIG_REISERFS_FS_SECURITY),y)
+reiserfs-objs += xattr_security.o
+endif
+
+ifeq ($(CONFIG_REISERFS_FS_POSIX_ACL),y)
+reiserfs-objs += xattr_acl.o
+endif
+
+# gcc -O2 (the kernel default)  is overaggressive on ppc32 when many inline
+# functions are used.  This causes the compiler to advance the stack
+# pointer out of the available stack space, corrupting kernel space,
+# and causing a panic. Since this behavior only affects ppc32, this ifeq
+# will work around it. If any other architecture displays this behavior,
+# add it here.
+ifeq ($(CONFIG_PPC32),y)
+EXTRA_CFLAGS := $(call cc-ifversion, -lt, 0400, -O1)
+endif
+
+TAGS:
+	etags *.c
+

kernel/fs/reiserfs/README

@@ -0,0 +1,161 @@
+[LICENSING]
+
+ReiserFS is hereby licensed under the GNU General
+Public License version 2.
+
+Source code files that contain the phrase "licensing governed by
+reiserfs/README" are "governed files" throughout this file.  Governed
+files are licensed under the GPL.  The portions of them owned by Hans
+Reiser, or authorized to be licensed by him, have been in the past,
+and likely will be in the future, licensed to other parties under
+other licenses.  If you add your code to governed files, and don't
+want it to be owned by Hans Reiser, put your copyright label on that
+code so the poor blight and his customers can keep things straight.
+All portions of governed files not labeled otherwise are owned by Hans
+Reiser, and by adding your code to it, widely distributing it to
+others or sending us a patch, and leaving the sentence in stating that
+licensing is governed by the statement in this file, you accept this.
+It will be a kindness if you identify whether Hans Reiser is allowed
+to license code labeled as owned by you on your behalf other than
+under the GPL, because he wants to know if it is okay to do so and put
+a check in the mail to you (for non-trivial improvements) when he
+makes his next sale.  He makes no guarantees as to the amount if any,
+though he feels motivated to motivate contributors, and you can surely
+discuss this with him before or after contributing.  You have the
+right to decline to allow him to license your code contribution other
+than under the GPL.
+
+Further licensing options are available for commercial and/or other
+interests directly from Hans Reiser: hans@reiser.to.  If you interpret
+the GPL as not allowing those additional licensing options, you read
+it wrongly, and Richard Stallman agrees with me, when carefully read
+you can see that those restrictions on additional terms do not apply
+to the owner of the copyright, and my interpretation of this shall
+govern for this license.
+
+Finally, nothing in this license shall be interpreted to allow you to
+fail to fairly credit me, or to remove my credits, without my
+permission, unless you are an end user not redistributing to others.
+If you have doubts about how to properly do that, or about what is
+fair, ask.  (Last I spoke with him Richard was contemplating how best
+to address the fair crediting issue in the next GPL version.)
+
+[END LICENSING]
+
+Reiserfs is a file system based on balanced tree algorithms, which is
+described at http://devlinux.com/namesys.
+
+Stop reading here.  Go there, then return.
+
+Send bug reports to yura@namesys.botik.ru.
+
+mkreiserfs and other utilities are in reiserfs/utils, or wherever your
+Linux provider put them.  There is some disagreement about how useful
+it is for users to get their fsck and mkreiserfs out of sync with the
+version of reiserfs that is in their kernel, with many important
+distributors wanting them out of sync.:-) Please try to remember to
+recompile and reinstall fsck and mkreiserfs with every update of
+reiserfs, this is a common source of confusion.  Note that some of the
+utilities cannot be compiled without accessing the balancing code
+which is in the kernel code, and relocating the utilities may require
+you to specify where that code can be found.
+
+Yes, if you update your reiserfs kernel module you do have to
+recompile your kernel, most of the time.  The errors you get will be
+quite cryptic if your forget to do so.
+
+Real users, as opposed to folks who want to hack and then understand
+what went wrong, will want REISERFS_CHECK off.
+
+Hideous Commercial Pitch: Spread your development costs across other OS
+vendors.  Select from the best in the world, not the best in your
+building, by buying from third party OS component suppliers.  Leverage
+the software component development power of the internet.  Be the most
+aggressive in taking advantage of the commercial possibilities of
+decentralized internet development, and add value through your branded
+integration that you sell as an operating system.  Let your competitors
+be the ones to compete against the entire internet by themselves.  Be
+hip, get with the new economic trend, before your competitors do.  Send
+email to hans@reiser.to.
+
+To understand the code, after reading the website, start reading the
+code by reading reiserfs_fs.h first.
+
+Hans Reiser was the project initiator, primary architect, source of all
+funding for the first 5.5 years, and one of the programmers.  He owns
+the copyright.
+
+Vladimir Saveljev was one of the programmers, and he worked long hours
+writing the cleanest code.  He always made the effort to be the best he
+could be, and to make his code the best that it could be.  What resulted
+was quite remarkable. I don't think that money can ever motivate someone
+to work the way he did, he is one of the most selfless men I know.
+
+Yura helps with benchmarking, coding hashes, and block pre-allocation
+code.
+
+Anatoly Pinchuk is a former member of our team who worked closely with
+Vladimir throughout the project's development.  He wrote a quite
+substantial portion of the total code.  He realized that there was a
+space problem with packing tails of files for files larger than a node
+that start on a node aligned boundary (there are reasons to want to node
+align files), and he invented and implemented indirect items and
+unformatted nodes as the solution.
+
+Konstantin Shvachko, with the help of the Russian version of a VC,
+tried to put me in a position where I was forced into giving control
+of the project to him.  (Fortunately, as the person paying the money
+for all salaries from my dayjob I owned all copyrights, and you can't
+really force takeovers of sole proprietorships.)  This was something
+curious, because he never really understood the value of our project,
+why we should do what we do, or why innovation was possible in
+general, but he was sure that he ought to be controlling it.  Every
+innovation had to be forced past him while he was with us.  He added
+two years to the time required to complete reiserfs, and was a net
+loss for me.  Mikhail Gilula was a brilliant innovator who also left
+in a destructive way that erased the value of his contributions, and
+that he was shown much generosity just makes it more painful.
+
+Grigory Zaigralin was an extremely effective system administrator for
+our group.
+
+Igor Krasheninnikov was wonderful at hardware procurement, repair, and
+network installation.
+
+Jeremy Fitzhardinge wrote the teahash.c code, and he gives credit to a
+textbook he got the algorithm from in the code.  Note that his analysis
+of how we could use the hashing code in making 32 bit NFS cookies work
+was probably more important than the actual algorithm.  Colin Plumb also
+contributed to it.
+
+Chris Mason dived right into our code, and in just a few months produced
+the journaling code that dramatically increased the value of ReiserFS.
+He is just an amazing programmer.
+
+Igor Zagorovsky is writing much of the new item handler and extent code
+for our next major release.
+
+Alexander Zarochentcev (sometimes known as zam, or sasha), wrote the
+resizer, and is hard at work on implementing allocate on flush.  SGI
+implemented allocate on flush before us for XFS, and generously took
+the time to convince me we should do it also.  They are great people,
+and a great company.
+
+Yuri Shevchuk and Nikita Danilov are doing squid cache optimization.
+
+Vitaly Fertman is doing fsck.
+
+Jeff Mahoney, of SuSE, contributed a few cleanup fixes, most notably
+the endian safe patches which allow ReiserFS to run on any platform
+supported by the Linux kernel.
+
+SuSE, IntegratedLinux.com, Ecila, MP3.com, bigstorage.com, and the
+Alpha PC Company made it possible for me to not have a day job
+anymore, and to dramatically increase our staffing.  Ecila funded
+hypertext feature development, MP3.com funded journaling, SuSE funded
+core development, IntegratedLinux.com funded squid web cache
+appliances, bigstorage.com funded HSM, and the alpha PC company funded
+the alpha port.  Many of these tasks were helped by sponsors other
+than the ones just named.  SuSE has helped in much more than just
+funding....
+

kernel/fs/reiserfs/dir.c

@@ -0,0 +1,302 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/stat.h>
+#include <linux/buffer_head.h>
+#include <asm/uaccess.h>
+
+extern const struct reiserfs_key MIN_KEY;
+
+static int reiserfs_readdir(struct file *, void *, filldir_t);
+static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry,
+			      int datasync);
+
+const struct file_operations reiserfs_dir_operations = {
+	.read = generic_read_dir,
+	.readdir = reiserfs_readdir,
+	.fsync = reiserfs_dir_fsync,
+	.ioctl = reiserfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = reiserfs_compat_ioctl,
+#endif
+};
+
+static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry,
+			      int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int err;
+	reiserfs_write_lock(inode->i_sb);
+	err = reiserfs_commit_for_inode(inode);
+	reiserfs_write_unlock(inode->i_sb);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+#define store_ih(where,what) copy_item_head (where, what)
+
+static inline bool is_privroot_deh(struct dentry *dir,
+				   struct reiserfs_de_head *deh)
+{
+	struct dentry *privroot = REISERFS_SB(dir->d_sb)->priv_root;
+	return (dir == dir->d_parent && privroot->d_inode &&
+	        deh->deh_objectid == INODE_PKEY(privroot->d_inode)->k_objectid);
+}
+
+int reiserfs_readdir_dentry(struct dentry *dentry, void *dirent,
+			   filldir_t filldir, loff_t *pos)
+{
+	struct inode *inode = dentry->d_inode;
+	struct cpu_key pos_key;	/* key of current position in the directory (key of directory entry) */
+	INITIALIZE_PATH(path_to_entry);
+	struct buffer_head *bh;
+	int item_num, entry_num;
+	const struct reiserfs_key *rkey;
+	struct item_head *ih, tmp_ih;
+	int search_res;
+	char *local_buf;
+	loff_t next_pos;
+	char small_buf[32];	/* avoid kmalloc if we can */
+	struct reiserfs_dir_entry de;
+	int ret = 0;
+
+	reiserfs_write_lock(inode->i_sb);
+
+	reiserfs_check_lock_depth(inode->i_sb, "readdir");
+
+	/* form key for search the next directory entry using f_pos field of
+	   file structure */
+	make_cpu_key(&pos_key, inode, *pos ?: DOT_OFFSET, TYPE_DIRENTRY, 3);
+	next_pos = cpu_key_k_offset(&pos_key);
+
+	path_to_entry.reada = PATH_READA;
+	while (1) {
+	      research:
+		/* search the directory item, containing entry with specified key */
+		search_res =
+		    search_by_entry_key(inode->i_sb, &pos_key, &path_to_entry,
+					&de);
+		if (search_res == IO_ERROR) {
+			// FIXME: we could just skip part of directory which could
+			// not be read
+			ret = -EIO;
+			goto out;
+		}
+		entry_num = de.de_entry_num;
+		bh = de.de_bh;
+		item_num = de.de_item_num;
+		ih = de.de_ih;
+		store_ih(&tmp_ih, ih);
+
+		/* we must have found item, that is item of this directory, */
+		RFALSE(COMP_SHORT_KEYS(&(ih->ih_key), &pos_key),
+		       "vs-9000: found item %h does not match to dir we readdir %K",
+		       ih, &pos_key);
+		RFALSE(item_num > B_NR_ITEMS(bh) - 1,
+		       "vs-9005 item_num == %d, item amount == %d",
+		       item_num, B_NR_ITEMS(bh));
+
+		/* and entry must be not more than number of entries in the item */
+		RFALSE(I_ENTRY_COUNT(ih) < entry_num,
+		       "vs-9010: entry number is too big %d (%d)",
+		       entry_num, I_ENTRY_COUNT(ih));
+
+		if (search_res == POSITION_FOUND
+		    || entry_num < I_ENTRY_COUNT(ih)) {
+			/* go through all entries in the directory item beginning from the entry, that has been found */
+			struct reiserfs_de_head *deh =
+			    B_I_DEH(bh, ih) + entry_num;
+
+			for (; entry_num < I_ENTRY_COUNT(ih);
+			     entry_num++, deh++) {
+				int d_reclen;
+				char *d_name;
+				off_t d_off;
+				ino_t d_ino;
+
+				if (!de_visible(deh))
+					/* it is hidden entry */
+					continue;
+				d_reclen = entry_length(bh, ih, entry_num);
+				d_name = B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh);
+
+				if (d_reclen <= 0 ||
+				    d_name + d_reclen > bh->b_data + bh->b_size) {
+					/* There is corrupted data in entry,
+					 * We'd better stop here */
+					pathrelse(&path_to_entry);
+					ret = -EIO;
+					goto out;
+				}
+
+				if (!d_name[d_reclen - 1])
+					d_reclen = strlen(d_name);
+
+				if (d_reclen >
+				    REISERFS_MAX_NAME(inode->i_sb->
+						      s_blocksize)) {
+					/* too big to send back to VFS */
+					continue;
+				}
+
+				/* Ignore the .reiserfs_priv entry */
+				if (is_privroot_deh(dentry, deh))
+					continue;
+
+				d_off = deh_offset(deh);
+				*pos = d_off;
+				d_ino = deh_objectid(deh);
+				if (d_reclen <= 32) {
+					local_buf = small_buf;
+				} else {
+					local_buf = kmalloc(d_reclen,
+							    GFP_NOFS);
+					if (!local_buf) {
+						pathrelse(&path_to_entry);
+						ret = -ENOMEM;
+						goto out;
+					}
+					if (item_moved(&tmp_ih, &path_to_entry)) {
+						kfree(local_buf);
+						goto research;
+					}
+				}
+				// Note, that we copy name to user space via temporary
+				// buffer (local_buf) because filldir will block if
+				// user space buffer is swapped out. At that time
+				// entry can move to somewhere else
+				memcpy(local_buf, d_name, d_reclen);
+				if (filldir
+				    (dirent, local_buf, d_reclen, d_off, d_ino,
+				     DT_UNKNOWN) < 0) {
+					if (local_buf != small_buf) {
+						kfree(local_buf);
+					}
+					goto end;
+				}
+				if (local_buf != small_buf) {
+					kfree(local_buf);
+				}
+				// next entry should be looked for with such offset
+				next_pos = deh_offset(deh) + 1;
+
+				if (item_moved(&tmp_ih, &path_to_entry)) {
+					goto research;
+				}
+			}	/* for */
+		}
+
+		if (item_num != B_NR_ITEMS(bh) - 1)
+			// end of directory has been reached
+			goto end;
+
+		/* item we went through is last item of node. Using right
+		   delimiting key check is it directory end */
+		rkey = get_rkey(&path_to_entry, inode->i_sb);
+		if (!comp_le_keys(rkey, &MIN_KEY)) {
+			/* set pos_key to key, that is the smallest and greater
+			   that key of the last entry in the item */
+			set_cpu_key_k_offset(&pos_key, next_pos);
+			continue;
+		}
+
+		if (COMP_SHORT_KEYS(rkey, &pos_key)) {
+			// end of directory has been reached
+			goto end;
+		}
+
+		/* directory continues in the right neighboring block */
+		set_cpu_key_k_offset(&pos_key,
+				     le_key_k_offset(KEY_FORMAT_3_5, rkey));
+
+	}			/* while */
+
+end:
+	*pos = next_pos;
+	pathrelse(&path_to_entry);
+	reiserfs_check_path(&path_to_entry);
+out:
+	reiserfs_write_unlock(inode->i_sb);
+	return ret;
+}
+
+static int reiserfs_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	struct dentry *dentry = file->f_path.dentry;
+	return reiserfs_readdir_dentry(dentry, dirent, filldir, &file->f_pos);
+}
+
+/* compose directory item containing "." and ".." entries (entries are
+   not aligned to 4 byte boundary) */
+/* the last four params are LE */
+void make_empty_dir_item_v1(char *body, __le32 dirid, __le32 objid,
+			    __le32 par_dirid, __le32 par_objid)
+{
+	struct reiserfs_de_head *deh;
+
+	memset(body, 0, EMPTY_DIR_SIZE_V1);
+	deh = (struct reiserfs_de_head *)body;
+
+	/* direntry header of "." */
+	put_deh_offset(&(deh[0]), DOT_OFFSET);
+	/* these two are from make_le_item_head, and are are LE */
+	deh[0].deh_dir_id = dirid;
+	deh[0].deh_objectid = objid;
+	deh[0].deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(&(deh[0]), EMPTY_DIR_SIZE_V1 - strlen("."));
+	mark_de_visible(&(deh[0]));
+
+	/* direntry header of ".." */
+	put_deh_offset(&(deh[1]), DOT_DOT_OFFSET);
+	/* key of ".." for the root directory */
+	/* these two are from the inode, and are are LE */
+	deh[1].deh_dir_id = par_dirid;
+	deh[1].deh_objectid = par_objid;
+	deh[1].deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(&(deh[1]), deh_location(&(deh[0])) - strlen(".."));
+	mark_de_visible(&(deh[1]));
+
+	/* copy ".." and "." */
+	memcpy(body + deh_location(&(deh[0])), ".", 1);
+	memcpy(body + deh_location(&(deh[1])), "..", 2);
+}
+
+/* compose directory item containing "." and ".." entries */
+void make_empty_dir_item(char *body, __le32 dirid, __le32 objid,
+			 __le32 par_dirid, __le32 par_objid)
+{
+	struct reiserfs_de_head *deh;
+
+	memset(body, 0, EMPTY_DIR_SIZE);
+	deh = (struct reiserfs_de_head *)body;
+
+	/* direntry header of "." */
+	put_deh_offset(&(deh[0]), DOT_OFFSET);
+	/* these two are from make_le_item_head, and are are LE */
+	deh[0].deh_dir_id = dirid;
+	deh[0].deh_objectid = objid;
+	deh[0].deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(&(deh[0]), EMPTY_DIR_SIZE - ROUND_UP(strlen(".")));
+	mark_de_visible(&(deh[0]));
+
+	/* direntry header of ".." */
+	put_deh_offset(&(deh[1]), DOT_DOT_OFFSET);
+	/* key of ".." for the root directory */
+	/* these two are from the inode, and are are LE */
+	deh[1].deh_dir_id = par_dirid;
+	deh[1].deh_objectid = par_objid;
+	deh[1].deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(&(deh[1]),
+			 deh_location(&(deh[0])) - ROUND_UP(strlen("..")));
+	mark_de_visible(&(deh[1]));
+
+	/* copy ".." and "." */
+	memcpy(body + deh_location(&(deh[0])), ".", 1);
+	memcpy(body + deh_location(&(deh[1])), "..", 2);
+}

kernel/fs/reiserfs/file.c

@@ -0,0 +1,310 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#include <linux/time.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/reiserfs_acl.h>
+#include <linux/reiserfs_xattr.h>
+#include <asm/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/writeback.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/quotaops.h>
+
+/*
+** We pack the tails of files on file close, not at the time they are written.
+** This implies an unnecessary copy of the tail and an unnecessary indirect item
+** insertion/balancing, for files that are written in one write.
+** It avoids unnecessary tail packings (balances) for files that are written in
+** multiple writes and are small enough to have tails.
+**
+** file_release is called by the VFS layer when the file is closed.  If
+** this is the last open file descriptor, and the file
+** small enough to have a tail, and the tail is currently in an
+** unformatted node, the tail is converted back into a direct item.
+**
+** We use reiserfs_truncate_file to pack the tail, since it already has
+** all the conditions coded.
+*/
+static int reiserfs_file_release(struct inode *inode, struct file *filp)
+{
+
+	struct reiserfs_transaction_handle th;
+	int err;
+	int jbegin_failure = 0;
+
+	BUG_ON(!S_ISREG(inode->i_mode));
+
+	/* fast out for when nothing needs to be done */
+	if ((atomic_read(&inode->i_count) > 1 ||
+	     !(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) ||
+	     !tail_has_to_be_packed(inode)) &&
+	    REISERFS_I(inode)->i_prealloc_count <= 0) {
+		return 0;
+	}
+
+	mutex_lock(&inode->i_mutex);
+
+	mutex_lock(&(REISERFS_I(inode)->i_mmap));
+	if (REISERFS_I(inode)->i_flags & i_ever_mapped)
+		REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
+
+	reiserfs_write_lock(inode->i_sb);
+	/* freeing preallocation only involves relogging blocks that
+	 * are already in the current transaction.  preallocation gets
+	 * freed at the end of each transaction, so it is impossible for
+	 * us to log any additional blocks (including quota blocks)
+	 */
+	err = journal_begin(&th, inode->i_sb, 1);
+	if (err) {
+		/* uh oh, we can't allow the inode to go away while there
+		 * is still preallocation blocks pending.  Try to join the
+		 * aborted transaction
+		 */
+		jbegin_failure = err;
+		err = journal_join_abort(&th, inode->i_sb, 1);
+
+		if (err) {
+			/* hmpf, our choices here aren't good.  We can pin the inode
+			 * which will disallow unmount from every happening, we can
+			 * do nothing, which will corrupt random memory on unmount,
+			 * or we can forcibly remove the file from the preallocation
+			 * list, which will leak blocks on disk.  Lets pin the inode
+			 * and let the admin know what is going on.
+			 */
+			igrab(inode);
+			reiserfs_warning(inode->i_sb, "clm-9001",
+					 "pinning inode %lu because the "
+					 "preallocation can't be freed",
+					 inode->i_ino);
+			goto out;
+		}
+	}
+	reiserfs_update_inode_transaction(inode);
+
+#ifdef REISERFS_PREALLOCATE
+	reiserfs_discard_prealloc(&th, inode);
+#endif
+	err = journal_end(&th, inode->i_sb, 1);
+
+	/* copy back the error code from journal_begin */
+	if (!err)
+		err = jbegin_failure;
+
+	if (!err && atomic_read(&inode->i_count) <= 1 &&
+	    (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) &&
+	    tail_has_to_be_packed(inode)) {
+		/* if regular file is released by last holder and it has been
+		   appended (we append by unformatted node only) or its direct
+		   item(s) had to be converted, then it may have to be
+		   indirect2direct converted */
+		err = reiserfs_truncate_file(inode, 0);
+	}
+      out:
+	mutex_unlock(&(REISERFS_I(inode)->i_mmap));
+	mutex_unlock(&inode->i_mutex);
+	reiserfs_write_unlock(inode->i_sb);
+	return err;
+}
+
+static int reiserfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct inode *inode;
+
+	inode = file->f_path.dentry->d_inode;
+	mutex_lock(&(REISERFS_I(inode)->i_mmap));
+	REISERFS_I(inode)->i_flags |= i_ever_mapped;
+	mutex_unlock(&(REISERFS_I(inode)->i_mmap));
+
+	return generic_file_mmap(file, vma);
+}
+
+static void reiserfs_vfs_truncate_file(struct inode *inode)
+{
+	reiserfs_truncate_file(inode, 1);
+}
+
+/* Sync a reiserfs file. */
+
+/*
+ * FIXME: sync_mapping_buffers() never has anything to sync.  Can
+ * be removed...
+ */
+
+static int reiserfs_sync_file(struct file *filp,
+			      struct dentry *dentry, int datasync)
+{
+	struct inode *inode = dentry->d_inode;
+	int err;
+	int barrier_done;
+
+	BUG_ON(!S_ISREG(inode->i_mode));
+	err = sync_mapping_buffers(inode->i_mapping);
+	reiserfs_write_lock(inode->i_sb);
+	barrier_done = reiserfs_commit_for_inode(inode);
+	reiserfs_write_unlock(inode->i_sb);
+	if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb))
+		blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+	if (barrier_done < 0)
+		return barrier_done;
+	return (err < 0) ? -EIO : 0;
+}
+
+/* taken fs/buffer.c:__block_commit_write */
+int reiserfs_commit_page(struct inode *inode, struct page *page,
+			 unsigned from, unsigned to)
+{
+	unsigned block_start, block_end;
+	int partial = 0;
+	unsigned blocksize;
+	struct buffer_head *bh, *head;
+	unsigned long i_size_index = inode->i_size >> PAGE_CACHE_SHIFT;
+	int new;
+	int logit = reiserfs_file_data_log(inode);
+	struct super_block *s = inode->i_sb;
+	int bh_per_page = PAGE_CACHE_SIZE / s->s_blocksize;
+	struct reiserfs_transaction_handle th;
+	int ret = 0;
+
+	th.t_trans_id = 0;
+	blocksize = 1 << inode->i_blkbits;
+
+	if (logit) {
+		reiserfs_write_lock(s);
+		ret = journal_begin(&th, s, bh_per_page + 1);
+		if (ret)
+			goto drop_write_lock;
+		reiserfs_update_inode_transaction(inode);
+	}
+	for (bh = head = page_buffers(page), block_start = 0;
+	     bh != head || !block_start;
+	     block_start = block_end, bh = bh->b_this_page) {
+
+		new = buffer_new(bh);
+		clear_buffer_new(bh);
+		block_end = block_start + blocksize;
+		if (block_end <= from || block_start >= to) {
+			if (!buffer_uptodate(bh))
+				partial = 1;
+		} else {
+			set_buffer_uptodate(bh);
+			if (logit) {
+				reiserfs_prepare_for_journal(s, bh, 1);
+				journal_mark_dirty(&th, s, bh);
+			} else if (!buffer_dirty(bh)) {
+				mark_buffer_dirty(bh);
+				/* do data=ordered on any page past the end
+				 * of file and any buffer marked BH_New.
+				 */
+				if (reiserfs_data_ordered(inode->i_sb) &&
+				    (new || page->index >= i_size_index)) {
+					reiserfs_add_ordered_list(inode, bh);
+				}
+			}
+		}
+	}
+	if (logit) {
+		ret = journal_end(&th, s, bh_per_page + 1);
+	      drop_write_lock:
+		reiserfs_write_unlock(s);
+	}
+	/*
+	 * If this is a partial write which happened to make all buffers
+	 * uptodate then we can optimize away a bogus readpage() for
+	 * the next read(). Here we 'discover' whether the page went
+	 * uptodate as a result of this (potentially partial) write.
+	 */
+	if (!partial)
+		SetPageUptodate(page);
+	return ret;
+}
+
+/* Write @count bytes at position @ppos in a file indicated by @file
+   from the buffer @buf.
+
+   generic_file_write() is only appropriate for filesystems that are not seeking to optimize performance and want
+   something simple that works.  It is not for serious use by general purpose filesystems, excepting the one that it was
+   written for (ext2/3).  This is for several reasons:
+
+   * It has no understanding of any filesystem specific optimizations.
+
+   * It enters the filesystem repeatedly for each page that is written.
+
+   * It depends on reiserfs_get_block() function which if implemented by reiserfs performs costly search_by_key
+   * operation for each page it is supplied with. By contrast reiserfs_file_write() feeds as much as possible at a time
+   * to reiserfs which allows for fewer tree traversals.
+
+   * Each indirect pointer insertion takes a lot of cpu, because it involves memory moves inside of blocks.
+
+   * Asking the block allocation code for blocks one at a time is slightly less efficient.
+
+   All of these reasons for not using only generic file write were understood back when reiserfs was first miscoded to
+   use it, but we were in a hurry to make code freeze, and so it couldn't be revised then.  This new code should make
+   things right finally.
+
+   Future Features: providing search_by_key with hints.
+
+*/
+static ssize_t reiserfs_file_write(struct file *file,	/* the file we are going to write into */
+				   const char __user * buf,	/*  pointer to user supplied data
+								   (in userspace) */
+				   size_t count,	/* amount of bytes to write */
+				   loff_t * ppos	/* pointer to position in file that we start writing at. Should be updated to
+							 * new current position before returning. */
+				   )
+{
+	struct inode *inode = file->f_path.dentry->d_inode;	// Inode of the file that we are writing to.
+	/* To simplify coding at this time, we store
+	   locked pages in array for now */
+	struct reiserfs_transaction_handle th;
+	th.t_trans_id = 0;
+
+	/* If a filesystem is converted from 3.5 to 3.6, we'll have v3.5 items
+	* lying around (most of the disk, in fact). Despite the filesystem
+	* now being a v3.6 format, the old items still can't support large
+	* file sizes. Catch this case here, as the rest of the VFS layer is
+	* oblivious to the different limitations between old and new items.
+	* reiserfs_setattr catches this for truncates. This chunk is lifted
+	* from generic_write_checks. */
+	if (get_inode_item_key_version (inode) == KEY_FORMAT_3_5 &&
+	    *ppos + count > MAX_NON_LFS) {
+		if (*ppos >= MAX_NON_LFS) {
+			return -EFBIG;
+		}
+		if (count > MAX_NON_LFS - (unsigned long)*ppos)
+			count = MAX_NON_LFS - (unsigned long)*ppos;
+	}
+
+	return do_sync_write(file, buf, count, ppos);
+}
+
+const struct file_operations reiserfs_file_operations = {
+	.read = do_sync_read,
+	.write = reiserfs_file_write,
+	.ioctl = reiserfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = reiserfs_compat_ioctl,
+#endif
+	.mmap = reiserfs_file_mmap,
+	.open = generic_file_open,
+	.release = reiserfs_file_release,
+	.fsync = reiserfs_sync_file,
+	.aio_read = generic_file_aio_read,
+	.aio_write = generic_file_aio_write,
+	.splice_read = generic_file_splice_read,
+	.splice_write = generic_file_splice_write,
+	.llseek = generic_file_llseek,
+};
+
+const struct inode_operations reiserfs_file_inode_operations = {
+	.truncate = reiserfs_vfs_truncate_file,
+	.setattr = reiserfs_setattr,
+	.setxattr = reiserfs_setxattr,
+	.getxattr = reiserfs_getxattr,
+	.listxattr = reiserfs_listxattr,
+	.removexattr = reiserfs_removexattr,
+	.permission = reiserfs_permission,
+};

kernel/fs/reiserfs/hashes.c

@@ -0,0 +1,182 @@
+
+/*
+ * Keyed 32-bit hash function using TEA in a Davis-Meyer function
+ *   H0 = Key
+ *   Hi = E Mi(Hi-1) + Hi-1
+ *
+ * (see Applied Cryptography, 2nd edition, p448).
+ *
+ * Jeremy Fitzhardinge <jeremy@zip.com.au> 1998
+ *
+ * Jeremy has agreed to the contents of reiserfs/README. -Hans
+ * Yura's function is added (04/07/2000)
+ */
+
+//
+// keyed_hash
+// yura_hash
+// r5_hash
+//
+
+#include <linux/kernel.h>
+#include <linux/reiserfs_fs.h>
+#include <asm/types.h>
+
+#define DELTA 0x9E3779B9
+#define FULLROUNDS 10		/* 32 is overkill, 16 is strong crypto */
+#define PARTROUNDS 6		/* 6 gets complete mixing */
+
+/* a, b, c, d - data; h0, h1 - accumulated hash */
+#define TEACORE(rounds)							\
+	do {								\
+		u32 sum = 0;						\
+		int n = rounds;						\
+		u32 b0, b1;						\
+									\
+		b0 = h0;						\
+		b1 = h1;						\
+									\
+		do							\
+		{							\
+			sum += DELTA;					\
+			b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);	\
+			b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);	\
+		} while(--n);						\
+									\
+		h0 += b0;						\
+		h1 += b1;						\
+	} while(0)
+
+u32 keyed_hash(const signed char *msg, int len)
+{
+	u32 k[] = { 0x9464a485, 0x542e1a94, 0x3e846bff, 0xb75bcfc3 };
+
+	u32 h0 = k[0], h1 = k[1];
+	u32 a, b, c, d;
+	u32 pad;
+	int i;
+
+	//      assert(len >= 0 && len < 256);
+
+	pad = (u32) len | ((u32) len << 8);
+	pad |= pad << 16;
+
+	while (len >= 16) {
+		a = (u32) msg[0] |
+		    (u32) msg[1] << 8 | (u32) msg[2] << 16 | (u32) msg[3] << 24;
+		b = (u32) msg[4] |
+		    (u32) msg[5] << 8 | (u32) msg[6] << 16 | (u32) msg[7] << 24;
+		c = (u32) msg[8] |
+		    (u32) msg[9] << 8 |
+		    (u32) msg[10] << 16 | (u32) msg[11] << 24;
+		d = (u32) msg[12] |
+		    (u32) msg[13] << 8 |
+		    (u32) msg[14] << 16 | (u32) msg[15] << 24;
+
+		TEACORE(PARTROUNDS);
+
+		len -= 16;
+		msg += 16;
+	}
+
+	if (len >= 12) {
+		a = (u32) msg[0] |
+		    (u32) msg[1] << 8 | (u32) msg[2] << 16 | (u32) msg[3] << 24;
+		b = (u32) msg[4] |
+		    (u32) msg[5] << 8 | (u32) msg[6] << 16 | (u32) msg[7] << 24;
+		c = (u32) msg[8] |
+		    (u32) msg[9] << 8 |
+		    (u32) msg[10] << 16 | (u32) msg[11] << 24;
+
+		d = pad;
+		for (i = 12; i < len; i++) {
+			d <<= 8;
+			d |= msg[i];
+		}
+	} else if (len >= 8) {
+		a = (u32) msg[0] |
+		    (u32) msg[1] << 8 | (u32) msg[2] << 16 | (u32) msg[3] << 24;
+		b = (u32) msg[4] |
+		    (u32) msg[5] << 8 | (u32) msg[6] << 16 | (u32) msg[7] << 24;
+
+		c = d = pad;
+		for (i = 8; i < len; i++) {
+			c <<= 8;
+			c |= msg[i];
+		}
+	} else if (len >= 4) {
+		a = (u32) msg[0] |
+		    (u32) msg[1] << 8 | (u32) msg[2] << 16 | (u32) msg[3] << 24;
+
+		b = c = d = pad;
+		for (i = 4; i < len; i++) {
+			b <<= 8;
+			b |= msg[i];
+		}
+	} else {
+		a = b = c = d = pad;
+		for (i = 0; i < len; i++) {
+			a <<= 8;
+			a |= msg[i];
+		}
+	}
+
+	TEACORE(FULLROUNDS);
+
+/*	return 0;*/
+	return h0 ^ h1;
+}
+
+/* What follows in this file is copyright 2000 by Hans Reiser, and the
+ * licensing of what follows is governed by reiserfs/README */
+
+u32 yura_hash(const signed char *msg, int len)
+{
+	int j, pow;
+	u32 a, c;
+	int i;
+
+	for (pow = 1, i = 1; i < len; i++)
+		pow = pow * 10;
+
+	if (len == 1)
+		a = msg[0] - 48;
+	else
+		a = (msg[0] - 48) * pow;
+
+	for (i = 1; i < len; i++) {
+		c = msg[i] - 48;
+		for (pow = 1, j = i; j < len - 1; j++)
+			pow = pow * 10;
+		a = a + c * pow;
+	}
+
+	for (; i < 40; i++) {
+		c = '0' - 48;
+		for (pow = 1, j = i; j < len - 1; j++)
+			pow = pow * 10;
+		a = a + c * pow;
+	}
+
+	for (; i < 256; i++) {
+		c = i;
+		for (pow = 1, j = i; j < len - 1; j++)
+			pow = pow * 10;
+		a = a + c * pow;
+	}
+
+	a = a << 7;
+	return a;
+}
+
+u32 r5_hash(const signed char *msg, int len)
+{
+	u32 a = 0;
+	while (*msg) {
+		a += *msg << 4;
+		a += *msg >> 4;
+		a *= 11;
+		msg++;
+	}
+	return a;
+}

kernel/fs/reiserfs/ioctl.c

@@ -0,0 +1,219 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/time.h>
+#include <asm/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/smp_lock.h>
+#include <linux/compat.h>
+
+/*
+** reiserfs_ioctl - handler for ioctl for inode
+** supported commands:
+**  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
+**                           and prevent packing file (argument arg has to be non-zero)
+**  2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
+**  3) That's all for a while ...
+*/
+int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
+		   unsigned long arg)
+{
+	unsigned int flags;
+	int err = 0;
+
+	switch (cmd) {
+	case REISERFS_IOC_UNPACK:
+		if (S_ISREG(inode->i_mode)) {
+			if (arg)
+				return reiserfs_unpack(inode, filp);
+			else
+				return 0;
+		} else
+			return -ENOTTY;
+		/* following two cases are taken from fs/ext2/ioctl.c by Remy
+		   Card (card@masi.ibp.fr) */
+	case REISERFS_IOC_GETFLAGS:
+		if (!reiserfs_attrs(inode->i_sb))
+			return -ENOTTY;
+
+		flags = REISERFS_I(inode)->i_attrs;
+		i_attrs_to_sd_attrs(inode, (__u16 *) & flags);
+		return put_user(flags, (int __user *)arg);
+	case REISERFS_IOC_SETFLAGS:{
+			if (!reiserfs_attrs(inode->i_sb))
+				return -ENOTTY;
+
+			err = mnt_want_write(filp->f_path.mnt);
+			if (err)
+				return err;
+
+			if (!is_owner_or_cap(inode)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
+			if (get_user(flags, (int __user *)arg)) {
+				err = -EFAULT;
+				goto setflags_out;
+			}
+			/*
+			 * Is it quota file? Do not allow user to mess with it
+			 */
+			if (IS_NOQUOTA(inode)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
+			if (((flags ^ REISERFS_I(inode)->
+			      i_attrs) & (REISERFS_IMMUTABLE_FL |
+					  REISERFS_APPEND_FL))
+			    && !capable(CAP_LINUX_IMMUTABLE)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
+			if ((flags & REISERFS_NOTAIL_FL) &&
+			    S_ISREG(inode->i_mode)) {
+				int result;
+
+				result = reiserfs_unpack(inode, filp);
+				if (result) {
+					err = result;
+					goto setflags_out;
+				}
+			}
+			sd_attrs_to_i_attrs(flags, inode);
+			REISERFS_I(inode)->i_attrs = flags;
+			inode->i_ctime = CURRENT_TIME_SEC;
+			mark_inode_dirty(inode);
+setflags_out:
+			mnt_drop_write(filp->f_path.mnt);
+			return err;
+		}
+	case REISERFS_IOC_GETVERSION:
+		return put_user(inode->i_generation, (int __user *)arg);
+	case REISERFS_IOC_SETVERSION:
+		if (!is_owner_or_cap(inode))
+			return -EPERM;
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+		if (get_user(inode->i_generation, (int __user *)arg)) {
+			err = -EFAULT;
+			goto setversion_out;
+		}
+		inode->i_ctime = CURRENT_TIME_SEC;
+		mark_inode_dirty(inode);
+setversion_out:
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	int ret;
+
+	/* These are just misnamed, they actually get/put from/to user an int */
+	switch (cmd) {
+	case REISERFS_IOC32_UNPACK:
+		cmd = REISERFS_IOC_UNPACK;
+		break;
+	case REISERFS_IOC32_GETFLAGS:
+		cmd = REISERFS_IOC_GETFLAGS;
+		break;
+	case REISERFS_IOC32_SETFLAGS:
+		cmd = REISERFS_IOC_SETFLAGS;
+		break;
+	case REISERFS_IOC32_GETVERSION:
+		cmd = REISERFS_IOC_GETVERSION;
+		break;
+	case REISERFS_IOC32_SETVERSION:
+		cmd = REISERFS_IOC_SETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	lock_kernel();
+	ret = reiserfs_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
+	unlock_kernel();
+	return ret;
+}
+#endif
+
+int reiserfs_commit_write(struct file *f, struct page *page,
+			  unsigned from, unsigned to);
+int reiserfs_prepare_write(struct file *f, struct page *page,
+			   unsigned from, unsigned to);
+/*
+** reiserfs_unpack
+** Function try to convert tail from direct item into indirect.
+** It set up nopack attribute in the REISERFS_I(inode)->nopack
+*/
+int reiserfs_unpack(struct inode *inode, struct file *filp)
+{
+	int retval = 0;
+	int index;
+	struct page *page;
+	struct address_space *mapping;
+	unsigned long write_from;
+	unsigned long blocksize = inode->i_sb->s_blocksize;
+
+	if (inode->i_size == 0) {
+		REISERFS_I(inode)->i_flags |= i_nopack_mask;
+		return 0;
+	}
+	/* ioctl already done */
+	if (REISERFS_I(inode)->i_flags & i_nopack_mask) {
+		return 0;
+	}
+
+	/* we need to make sure nobody is changing the file size beneath
+	 ** us
+	 */
+	mutex_lock(&inode->i_mutex);
+	reiserfs_write_lock(inode->i_sb);
+
+	write_from = inode->i_size & (blocksize - 1);
+	/* if we are on a block boundary, we are already unpacked.  */
+	if (write_from == 0) {
+		REISERFS_I(inode)->i_flags |= i_nopack_mask;
+		goto out;
+	}
+
+	/* we unpack by finding the page with the tail, and calling
+	 ** reiserfs_prepare_write on that page.  This will force a
+	 ** reiserfs_get_block to unpack the tail for us.
+	 */
+	index = inode->i_size >> PAGE_CACHE_SHIFT;
+	mapping = inode->i_mapping;
+	page = grab_cache_page(mapping, index);
+	retval = -ENOMEM;
+	if (!page) {
+		goto out;
+	}
+	retval = reiserfs_prepare_write(NULL, page, write_from, write_from);
+	if (retval)
+		goto out_unlock;
+
+	/* conversion can change page contents, must flush */
+	flush_dcache_page(page);
+	retval = reiserfs_commit_write(NULL, page, write_from, write_from);
+	REISERFS_I(inode)->i_flags |= i_nopack_mask;
+
+      out_unlock:
+	unlock_page(page);
+	page_cache_release(page);
+
+      out:
+	mutex_unlock(&inode->i_mutex);
+	reiserfs_write_unlock(inode->i_sb);
+	return retval;
+}

kernel/fs/reiserfs/item_ops.c

@@ -0,0 +1,756 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#include <linux/time.h>
+#include <linux/reiserfs_fs.h>
+
+// this contains item handlers for old item types: sd, direct,
+// indirect, directory
+
+/* and where are the comments? how about saying where we can find an
+   explanation of each item handler method? -Hans */
+
+//////////////////////////////////////////////////////////////////////////////
+// stat data functions
+//
+static int sd_bytes_number(struct item_head *ih, int block_size)
+{
+	return 0;
+}
+
+static void sd_decrement_key(struct cpu_key *key)
+{
+	key->on_disk_key.k_objectid--;
+	set_cpu_key_k_type(key, TYPE_ANY);
+	set_cpu_key_k_offset(key, (loff_t)(~0ULL >> 1));
+}
+
+static int sd_is_left_mergeable(struct reiserfs_key *key, unsigned long bsize)
+{
+	return 0;
+}
+
+static char *print_time(time_t t)
+{
+	static char timebuf[256];
+
+	sprintf(timebuf, "%ld", t);
+	return timebuf;
+}
+
+static void sd_print_item(struct item_head *ih, char *item)
+{
+	printk("\tmode | size | nlinks | first direct | mtime\n");
+	if (stat_data_v1(ih)) {
+		struct stat_data_v1 *sd = (struct stat_data_v1 *)item;
+
+		printk("\t0%-6o | %6u | %2u | %d | %s\n", sd_v1_mode(sd),
+		       sd_v1_size(sd), sd_v1_nlink(sd),
+		       sd_v1_first_direct_byte(sd),
+		       print_time(sd_v1_mtime(sd)));
+	} else {
+		struct stat_data *sd = (struct stat_data *)item;
+
+		printk("\t0%-6o | %6Lu | %2u | %d | %s\n", sd_v2_mode(sd),
+		       (unsigned long long)sd_v2_size(sd), sd_v2_nlink(sd),
+		       sd_v2_rdev(sd), print_time(sd_v2_mtime(sd)));
+	}
+}
+
+static void sd_check_item(struct item_head *ih, char *item)
+{
+	// FIXME: type something here!
+}
+
+static int sd_create_vi(struct virtual_node *vn,
+			struct virtual_item *vi,
+			int is_affected, int insert_size)
+{
+	vi->vi_index = TYPE_STAT_DATA;
+	//vi->vi_type |= VI_TYPE_STAT_DATA;// not needed?
+	return 0;
+}
+
+static int sd_check_left(struct virtual_item *vi, int free,
+			 int start_skip, int end_skip)
+{
+	BUG_ON(start_skip || end_skip);
+	return -1;
+}
+
+static int sd_check_right(struct virtual_item *vi, int free)
+{
+	return -1;
+}
+
+static int sd_part_size(struct virtual_item *vi, int first, int count)
+{
+	BUG_ON(count);
+	return 0;
+}
+
+static int sd_unit_num(struct virtual_item *vi)
+{
+	return vi->vi_item_len - IH_SIZE;
+}
+
+static void sd_print_vi(struct virtual_item *vi)
+{
+	reiserfs_warning(NULL, "reiserfs-16100",
+			 "STATDATA, index %d, type 0x%x, %h",
+			 vi->vi_index, vi->vi_type, vi->vi_ih);
+}
+
+static struct item_operations stat_data_ops = {
+	.bytes_number = sd_bytes_number,
+	.decrement_key = sd_decrement_key,
+	.is_left_mergeable = sd_is_left_mergeable,
+	.print_item = sd_print_item,
+	.check_item = sd_check_item,
+
+	.create_vi = sd_create_vi,
+	.check_left = sd_check_left,
+	.check_right = sd_check_right,
+	.part_size = sd_part_size,
+	.unit_num = sd_unit_num,
+	.print_vi = sd_print_vi
+};
+
+//////////////////////////////////////////////////////////////////////////////
+// direct item functions
+//
+static int direct_bytes_number(struct item_head *ih, int block_size)
+{
+	return ih_item_len(ih);
+}
+
+// FIXME: this should probably switch to indirect as well
+static void direct_decrement_key(struct cpu_key *key)
+{
+	cpu_key_k_offset_dec(key);
+	if (cpu_key_k_offset(key) == 0)
+		set_cpu_key_k_type(key, TYPE_STAT_DATA);
+}
+
+static int direct_is_left_mergeable(struct reiserfs_key *key,
+				    unsigned long bsize)
+{
+	int version = le_key_version(key);
+	return ((le_key_k_offset(version, key) & (bsize - 1)) != 1);
+}
+
+static void direct_print_item(struct item_head *ih, char *item)
+{
+	int j = 0;
+
+//    return;
+	printk("\"");
+	while (j < ih_item_len(ih))
+		printk("%c", item[j++]);
+	printk("\"\n");
+}
+
+static void direct_check_item(struct item_head *ih, char *item)
+{
+	// FIXME: type something here!
+}
+
+static int direct_create_vi(struct virtual_node *vn,
+			    struct virtual_item *vi,
+			    int is_affected, int insert_size)
+{
+	vi->vi_index = TYPE_DIRECT;
+	//vi->vi_type |= VI_TYPE_DIRECT;
+	return 0;
+}
+
+static int direct_check_left(struct virtual_item *vi, int free,
+			     int start_skip, int end_skip)
+{
+	int bytes;
+
+	bytes = free - free % 8;
+	return bytes ? : -1;
+}
+
+static int direct_check_right(struct virtual_item *vi, int free)
+{
+	return direct_check_left(vi, free, 0, 0);
+}
+
+static int direct_part_size(struct virtual_item *vi, int first, int count)
+{
+	return count;
+}
+
+static int direct_unit_num(struct virtual_item *vi)
+{
+	return vi->vi_item_len - IH_SIZE;
+}
+
+static void direct_print_vi(struct virtual_item *vi)
+{
+	reiserfs_warning(NULL, "reiserfs-16101",
+			 "DIRECT, index %d, type 0x%x, %h",
+			 vi->vi_index, vi->vi_type, vi->vi_ih);
+}
+
+static struct item_operations direct_ops = {
+	.bytes_number = direct_bytes_number,
+	.decrement_key = direct_decrement_key,
+	.is_left_mergeable = direct_is_left_mergeable,
+	.print_item = direct_print_item,
+	.check_item = direct_check_item,
+
+	.create_vi = direct_create_vi,
+	.check_left = direct_check_left,
+	.check_right = direct_check_right,
+	.part_size = direct_part_size,
+	.unit_num = direct_unit_num,
+	.print_vi = direct_print_vi
+};
+
+//////////////////////////////////////////////////////////////////////////////
+// indirect item functions
+//
+
+static int indirect_bytes_number(struct item_head *ih, int block_size)
+{
+	return ih_item_len(ih) / UNFM_P_SIZE * block_size;	//- get_ih_free_space (ih);
+}
+
+// decrease offset, if it becomes 0, change type to stat data
+static void indirect_decrement_key(struct cpu_key *key)
+{
+	cpu_key_k_offset_dec(key);
+	if (cpu_key_k_offset(key) == 0)
+		set_cpu_key_k_type(key, TYPE_STAT_DATA);
+}
+
+// if it is not first item of the body, then it is mergeable
+static int indirect_is_left_mergeable(struct reiserfs_key *key,
+				      unsigned long bsize)
+{
+	int version = le_key_version(key);
+	return (le_key_k_offset(version, key) != 1);
+}
+
+// printing of indirect item
+static void start_new_sequence(__u32 * start, int *len, __u32 new)
+{
+	*start = new;
+	*len = 1;
+}
+
+static int sequence_finished(__u32 start, int *len, __u32 new)
+{
+	if (start == INT_MAX)
+		return 1;
+
+	if (start == 0 && new == 0) {
+		(*len)++;
+		return 0;
+	}
+	if (start != 0 && (start + *len) == new) {
+		(*len)++;
+		return 0;
+	}
+	return 1;
+}
+
+static void print_sequence(__u32 start, int len)
+{
+	if (start == INT_MAX)
+		return;
+
+	if (len == 1)
+		printk(" %d", start);
+	else
+		printk(" %d(%d)", start, len);
+}
+
+static void indirect_print_item(struct item_head *ih, char *item)
+{
+	int j;
+	__le32 *unp;
+	__u32 prev = INT_MAX;
+	int num = 0;
+
+	unp = (__le32 *) item;
+
+	if (ih_item_len(ih) % UNFM_P_SIZE)
+		reiserfs_warning(NULL, "reiserfs-16102", "invalid item len");
+
+	printk("%d pointers\n[ ", (int)I_UNFM_NUM(ih));
+	for (j = 0; j < I_UNFM_NUM(ih); j++) {
+		if (sequence_finished(prev, &num, get_block_num(unp, j))) {
+			print_sequence(prev, num);
+			start_new_sequence(&prev, &num, get_block_num(unp, j));
+		}
+	}
+	print_sequence(prev, num);
+	printk("]\n");
+}
+
+static void indirect_check_item(struct item_head *ih, char *item)
+{
+	// FIXME: type something here!
+}
+
+static int indirect_create_vi(struct virtual_node *vn,
+			      struct virtual_item *vi,
+			      int is_affected, int insert_size)
+{
+	vi->vi_index = TYPE_INDIRECT;
+	//vi->vi_type |= VI_TYPE_INDIRECT;
+	return 0;
+}
+
+static int indirect_check_left(struct virtual_item *vi, int free,
+			       int start_skip, int end_skip)
+{
+	int bytes;
+
+	bytes = free - free % UNFM_P_SIZE;
+	return bytes ? : -1;
+}
+
+static int indirect_check_right(struct virtual_item *vi, int free)
+{
+	return indirect_check_left(vi, free, 0, 0);
+}
+
+// return size in bytes of 'units' units. If first == 0 - calculate from the head (left), otherwise - from tail (right)
+static int indirect_part_size(struct virtual_item *vi, int first, int units)
+{
+	// unit of indirect item is byte (yet)
+	return units;
+}
+
+static int indirect_unit_num(struct virtual_item *vi)
+{
+	// unit of indirect item is byte (yet)
+	return vi->vi_item_len - IH_SIZE;
+}
+
+static void indirect_print_vi(struct virtual_item *vi)
+{
+	reiserfs_warning(NULL, "reiserfs-16103",
+			 "INDIRECT, index %d, type 0x%x, %h",
+			 vi->vi_index, vi->vi_type, vi->vi_ih);
+}
+
+static struct item_operations indirect_ops = {
+	.bytes_number = indirect_bytes_number,
+	.decrement_key = indirect_decrement_key,
+	.is_left_mergeable = indirect_is_left_mergeable,
+	.print_item = indirect_print_item,
+	.check_item = indirect_check_item,
+
+	.create_vi = indirect_create_vi,
+	.check_left = indirect_check_left,
+	.check_right = indirect_check_right,
+	.part_size = indirect_part_size,
+	.unit_num = indirect_unit_num,
+	.print_vi = indirect_print_vi
+};
+
+//////////////////////////////////////////////////////////////////////////////
+// direntry functions
+//
+
+static int direntry_bytes_number(struct item_head *ih, int block_size)
+{
+	reiserfs_warning(NULL, "vs-16090",
+			 "bytes number is asked for direntry");
+	return 0;
+}
+
+static void direntry_decrement_key(struct cpu_key *key)
+{
+	cpu_key_k_offset_dec(key);
+	if (cpu_key_k_offset(key) == 0)
+		set_cpu_key_k_type(key, TYPE_STAT_DATA);
+}
+
+static int direntry_is_left_mergeable(struct reiserfs_key *key,
+				      unsigned long bsize)
+{
+	if (le32_to_cpu(key->u.k_offset_v1.k_offset) == DOT_OFFSET)
+		return 0;
+	return 1;
+
+}
+
+static void direntry_print_item(struct item_head *ih, char *item)
+{
+	int i;
+	int namelen;
+	struct reiserfs_de_head *deh;
+	char *name;
+	static char namebuf[80];
+
+	printk("\n # %-15s%-30s%-15s%-15s%-15s\n", "Name",
+	       "Key of pointed object", "Hash", "Gen number", "Status");
+
+	deh = (struct reiserfs_de_head *)item;
+
+	for (i = 0; i < I_ENTRY_COUNT(ih); i++, deh++) {
+		namelen =
+		    (i ? (deh_location(deh - 1)) : ih_item_len(ih)) -
+		    deh_location(deh);
+		name = item + deh_location(deh);
+		if (name[namelen - 1] == 0)
+			namelen = strlen(name);
+		namebuf[0] = '"';
+		if (namelen > sizeof(namebuf) - 3) {
+			strncpy(namebuf + 1, name, sizeof(namebuf) - 3);
+			namebuf[sizeof(namebuf) - 2] = '"';
+			namebuf[sizeof(namebuf) - 1] = 0;
+		} else {
+			memcpy(namebuf + 1, name, namelen);
+			namebuf[namelen + 1] = '"';
+			namebuf[namelen + 2] = 0;
+		}
+
+		printk("%d:  %-15s%-15d%-15d%-15Ld%-15Ld(%s)\n",
+		       i, namebuf,
+		       deh_dir_id(deh), deh_objectid(deh),
+		       GET_HASH_VALUE(deh_offset(deh)),
+		       GET_GENERATION_NUMBER((deh_offset(deh))),
+		       (de_hidden(deh)) ? "HIDDEN" : "VISIBLE");
+	}
+}
+
+static void direntry_check_item(struct item_head *ih, char *item)
+{
+	int i;
+	struct reiserfs_de_head *deh;
+
+	// FIXME: type something here!
+	deh = (struct reiserfs_de_head *)item;
+	for (i = 0; i < I_ENTRY_COUNT(ih); i++, deh++) {
+		;
+	}
+}
+
+#define DIRENTRY_VI_FIRST_DIRENTRY_ITEM 1
+
+/*
+ * function returns old entry number in directory item in real node
+ * using new entry number in virtual item in virtual node */
+static inline int old_entry_num(int is_affected, int virtual_entry_num,
+				int pos_in_item, int mode)
+{
+	if (mode == M_INSERT || mode == M_DELETE)
+		return virtual_entry_num;
+
+	if (!is_affected)
+		/* cut or paste is applied to another item */
+		return virtual_entry_num;
+
+	if (virtual_entry_num < pos_in_item)
+		return virtual_entry_num;
+
+	if (mode == M_CUT)
+		return virtual_entry_num + 1;
+
+	RFALSE(mode != M_PASTE || virtual_entry_num == 0,
+	       "vs-8015: old_entry_num: mode must be M_PASTE (mode = \'%c\'",
+	       mode);
+
+	return virtual_entry_num - 1;
+}
+
+/* Create an array of sizes of directory entries for virtual
+   item. Return space used by an item. FIXME: no control over
+   consuming of space used by this item handler */
+static int direntry_create_vi(struct virtual_node *vn,
+			      struct virtual_item *vi,
+			      int is_affected, int insert_size)
+{
+	struct direntry_uarea *dir_u = vi->vi_uarea;
+	int i, j;
+	int size = sizeof(struct direntry_uarea);
+	struct reiserfs_de_head *deh;
+
+	vi->vi_index = TYPE_DIRENTRY;
+
+	BUG_ON(!(vi->vi_ih) || !vi->vi_item);
+
+	dir_u->flags = 0;
+	if (le_ih_k_offset(vi->vi_ih) == DOT_OFFSET)
+		dir_u->flags |= DIRENTRY_VI_FIRST_DIRENTRY_ITEM;
+
+	deh = (struct reiserfs_de_head *)(vi->vi_item);
+
+	/* virtual directory item have this amount of entry after */
+	dir_u->entry_count = ih_entry_count(vi->vi_ih) +
+	    ((is_affected) ? ((vn->vn_mode == M_CUT) ? -1 :
+			      (vn->vn_mode == M_PASTE ? 1 : 0)) : 0);
+
+	for (i = 0; i < dir_u->entry_count; i++) {
+		j = old_entry_num(is_affected, i, vn->vn_pos_in_item,
+				  vn->vn_mode);
+		dir_u->entry_sizes[i] =
+		    (j ? deh_location(&(deh[j - 1])) : ih_item_len(vi->vi_ih)) -
+		    deh_location(&(deh[j])) + DEH_SIZE;
+	}
+
+	size += (dir_u->entry_count * sizeof(short));
+
+	/* set size of pasted entry */
+	if (is_affected && vn->vn_mode == M_PASTE)
+		dir_u->entry_sizes[vn->vn_pos_in_item] = insert_size;
+
+#ifdef CONFIG_REISERFS_CHECK
+	/* compare total size of entries with item length */
+	{
+		int k, l;
+
+		l = 0;
+		for (k = 0; k < dir_u->entry_count; k++)
+			l += dir_u->entry_sizes[k];
+
+		if (l + IH_SIZE != vi->vi_item_len +
+		    ((is_affected
+		      && (vn->vn_mode == M_PASTE
+			  || vn->vn_mode == M_CUT)) ? insert_size : 0)) {
+			reiserfs_panic(NULL, "vs-8025", "(mode==%c, "
+				       "insert_size==%d), invalid length of "
+				       "directory item",
+				       vn->vn_mode, insert_size);
+		}
+	}
+#endif
+
+	return size;
+
+}
+
+//
+// return number of entries which may fit into specified amount of
+// free space, or -1 if free space is not enough even for 1 entry
+//
+static int direntry_check_left(struct virtual_item *vi, int free,
+			       int start_skip, int end_skip)
+{
+	int i;
+	int entries = 0;
+	struct direntry_uarea *dir_u = vi->vi_uarea;
+
+	for (i = start_skip; i < dir_u->entry_count - end_skip; i++) {
+		if (dir_u->entry_sizes[i] > free)
+			/* i-th entry doesn't fit into the remaining free space */
+			break;
+
+		free -= dir_u->entry_sizes[i];
+		entries++;
+	}
+
+	if (entries == dir_u->entry_count) {
+		reiserfs_panic(NULL, "item_ops-1",
+			       "free space %d, entry_count %d", free,
+			       dir_u->entry_count);
+	}
+
+	/* "." and ".." can not be separated from each other */
+	if (start_skip == 0 && (dir_u->flags & DIRENTRY_VI_FIRST_DIRENTRY_ITEM)
+	    && entries < 2)
+		entries = 0;
+
+	return entries ? : -1;
+}
+
+static int direntry_check_right(struct virtual_item *vi, int free)
+{
+	int i;
+	int entries = 0;
+	struct direntry_uarea *dir_u = vi->vi_uarea;
+
+	for (i = dir_u->entry_count - 1; i >= 0; i--) {
+		if (dir_u->entry_sizes[i] > free)
+			/* i-th entry doesn't fit into the remaining free space */
+			break;
+
+		free -= dir_u->entry_sizes[i];
+		entries++;
+	}
+	BUG_ON(entries == dir_u->entry_count);
+
+	/* "." and ".." can not be separated from each other */
+	if ((dir_u->flags & DIRENTRY_VI_FIRST_DIRENTRY_ITEM)
+	    && entries > dir_u->entry_count - 2)
+		entries = dir_u->entry_count - 2;
+
+	return entries ? : -1;
+}
+
+/* sum of entry sizes between from-th and to-th entries including both edges */
+static int direntry_part_size(struct virtual_item *vi, int first, int count)
+{
+	int i, retval;
+	int from, to;
+	struct direntry_uarea *dir_u = vi->vi_uarea;
+
+	retval = 0;
+	if (first == 0)
+		from = 0;
+	else
+		from = dir_u->entry_count - count;
+	to = from + count - 1;
+
+	for (i = from; i <= to; i++)
+		retval += dir_u->entry_sizes[i];
+
+	return retval;
+}
+
+static int direntry_unit_num(struct virtual_item *vi)
+{
+	struct direntry_uarea *dir_u = vi->vi_uarea;
+
+	return dir_u->entry_count;
+}
+
+static void direntry_print_vi(struct virtual_item *vi)
+{
+	int i;
+	struct direntry_uarea *dir_u = vi->vi_uarea;
+
+	reiserfs_warning(NULL, "reiserfs-16104",
+			 "DIRENTRY, index %d, type 0x%x, %h, flags 0x%x",
+			 vi->vi_index, vi->vi_type, vi->vi_ih, dir_u->flags);
+	printk("%d entries: ", dir_u->entry_count);
+	for (i = 0; i < dir_u->entry_count; i++)
+		printk("%d ", dir_u->entry_sizes[i]);
+	printk("\n");
+}
+
+static struct item_operations direntry_ops = {
+	.bytes_number = direntry_bytes_number,
+	.decrement_key = direntry_decrement_key,
+	.is_left_mergeable = direntry_is_left_mergeable,
+	.print_item = direntry_print_item,
+	.check_item = direntry_check_item,
+
+	.create_vi = direntry_create_vi,
+	.check_left = direntry_check_left,
+	.check_right = direntry_check_right,
+	.part_size = direntry_part_size,
+	.unit_num = direntry_unit_num,
+	.print_vi = direntry_print_vi
+};
+
+//////////////////////////////////////////////////////////////////////////////
+// Error catching functions to catch errors caused by incorrect item types.
+//
+static int errcatch_bytes_number(struct item_head *ih, int block_size)
+{
+	reiserfs_warning(NULL, "green-16001",
+			 "Invalid item type observed, run fsck ASAP");
+	return 0;
+}
+
+static void errcatch_decrement_key(struct cpu_key *key)
+{
+	reiserfs_warning(NULL, "green-16002",
+			 "Invalid item type observed, run fsck ASAP");
+}
+
+static int errcatch_is_left_mergeable(struct reiserfs_key *key,
+				      unsigned long bsize)
+{
+	reiserfs_warning(NULL, "green-16003",
+			 "Invalid item type observed, run fsck ASAP");
+	return 0;
+}
+
+static void errcatch_print_item(struct item_head *ih, char *item)
+{
+	reiserfs_warning(NULL, "green-16004",
+			 "Invalid item type observed, run fsck ASAP");
+}
+
+static void errcatch_check_item(struct item_head *ih, char *item)
+{
+	reiserfs_warning(NULL, "green-16005",
+			 "Invalid item type observed, run fsck ASAP");
+}
+
+static int errcatch_create_vi(struct virtual_node *vn,
+			      struct virtual_item *vi,
+			      int is_affected, int insert_size)
+{
+	reiserfs_warning(NULL, "green-16006",
+			 "Invalid item type observed, run fsck ASAP");
+	return 0;		// We might return -1 here as well, but it won't help as create_virtual_node() from where
+	// this operation is called from is of return type void.
+}
+
+static int errcatch_check_left(struct virtual_item *vi, int free,
+			       int start_skip, int end_skip)
+{
+	reiserfs_warning(NULL, "green-16007",
+			 "Invalid item type observed, run fsck ASAP");
+	return -1;
+}
+
+static int errcatch_check_right(struct virtual_item *vi, int free)
+{
+	reiserfs_warning(NULL, "green-16008",
+			 "Invalid item type observed, run fsck ASAP");
+	return -1;
+}
+
+static int errcatch_part_size(struct virtual_item *vi, int first, int count)
+{
+	reiserfs_warning(NULL, "green-16009",
+			 "Invalid item type observed, run fsck ASAP");
+	return 0;
+}
+
+static int errcatch_unit_num(struct virtual_item *vi)
+{
+	reiserfs_warning(NULL, "green-16010",
+			 "Invalid item type observed, run fsck ASAP");
+	return 0;
+}
+
+static void errcatch_print_vi(struct virtual_item *vi)
+{
+	reiserfs_warning(NULL, "green-16011",
+			 "Invalid item type observed, run fsck ASAP");
+}
+
+static struct item_operations errcatch_ops = {
+	errcatch_bytes_number,
+	errcatch_decrement_key,
+	errcatch_is_left_mergeable,
+	errcatch_print_item,
+	errcatch_check_item,
+
+	errcatch_create_vi,
+	errcatch_check_left,
+	errcatch_check_right,
+	errcatch_part_size,
+	errcatch_unit_num,
+	errcatch_print_vi
+};
+
+//////////////////////////////////////////////////////////////////////////////
+//
+//
+#if ! (TYPE_STAT_DATA == 0 && TYPE_INDIRECT == 1 && TYPE_DIRECT == 2 && TYPE_DIRENTRY == 3)
+#error Item types must use disk-format assigned values.
+#endif
+
+struct item_operations *item_ops[TYPE_ANY + 1] = {
+	&stat_data_ops,
+	&indirect_ops,
+	&direct_ops,
+	&direntry_ops,
+	NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+	&errcatch_ops		/* This is to catch errors with invalid type (15th entry for TYPE_ANY) */
+};

kernel/fs/reiserfs/objectid.c

@@ -0,0 +1,203 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#include <linux/string.h>
+#include <linux/random.h>
+#include <linux/time.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/reiserfs_fs_sb.h>
+
+// find where objectid map starts
+#define objectid_map(s,rs) (old_format_only (s) ? \
+                         (__le32 *)((struct reiserfs_super_block_v1 *)(rs) + 1) :\
+			 (__le32 *)((rs) + 1))
+
+#ifdef CONFIG_REISERFS_CHECK
+
+static void check_objectid_map(struct super_block *s, __le32 * map)
+{
+	if (le32_to_cpu(map[0]) != 1)
+		reiserfs_panic(s, "vs-15010", "map corrupted: %lx",
+			       (long unsigned int)le32_to_cpu(map[0]));
+
+	// FIXME: add something else here
+}
+
+#else
+static void check_objectid_map(struct super_block *s, __le32 * map)
+{;
+}
+#endif
+
+/* When we allocate objectids we allocate the first unused objectid.
+   Each sequence of objectids in use (the odd sequences) is followed
+   by a sequence of objectids not in use (the even sequences).  We
+   only need to record the last objectid in each of these sequences
+   (both the odd and even sequences) in order to fully define the
+   boundaries of the sequences.  A consequence of allocating the first
+   objectid not in use is that under most conditions this scheme is
+   extremely compact.  The exception is immediately after a sequence
+   of operations which deletes a large number of objects of
+   non-sequential objectids, and even then it will become compact
+   again as soon as more objects are created.  Note that many
+   interesting optimizations of layout could result from complicating
+   objectid assignment, but we have deferred making them for now. */
+
+/* get unique object identifier */
+__u32 reiserfs_get_unused_objectid(struct reiserfs_transaction_handle *th)
+{
+	struct super_block *s = th->t_super;
+	struct reiserfs_super_block *rs = SB_DISK_SUPER_BLOCK(s);
+	__le32 *map = objectid_map(s, rs);
+	__u32 unused_objectid;
+
+	BUG_ON(!th->t_trans_id);
+
+	check_objectid_map(s, map);
+
+	reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
+	/* comment needed -Hans */
+	unused_objectid = le32_to_cpu(map[1]);
+	if (unused_objectid == U32_MAX) {
+		reiserfs_warning(s, "reiserfs-15100", "no more object ids");
+		reiserfs_restore_prepared_buffer(s, SB_BUFFER_WITH_SB(s));
+		return 0;
+	}
+
+	/* This incrementation allocates the first unused objectid. That
+	   is to say, the first entry on the objectid map is the first
+	   unused objectid, and by incrementing it we use it.  See below
+	   where we check to see if we eliminated a sequence of unused
+	   objectids.... */
+	map[1] = cpu_to_le32(unused_objectid + 1);
+
+	/* Now we check to see if we eliminated the last remaining member of
+	   the first even sequence (and can eliminate the sequence by
+	   eliminating its last objectid from oids), and can collapse the
+	   first two odd sequences into one sequence.  If so, then the net
+	   result is to eliminate a pair of objectids from oids.  We do this
+	   by shifting the entire map to the left. */
+	if (sb_oid_cursize(rs) > 2 && map[1] == map[2]) {
+		memmove(map + 1, map + 3,
+			(sb_oid_cursize(rs) - 3) * sizeof(__u32));
+		set_sb_oid_cursize(rs, sb_oid_cursize(rs) - 2);
+	}
+
+	journal_mark_dirty(th, s, SB_BUFFER_WITH_SB(s));
+	return unused_objectid;
+}
+
+/* makes object identifier unused */
+void reiserfs_release_objectid(struct reiserfs_transaction_handle *th,
+			       __u32 objectid_to_release)
+{
+	struct super_block *s = th->t_super;
+	struct reiserfs_super_block *rs = SB_DISK_SUPER_BLOCK(s);
+	__le32 *map = objectid_map(s, rs);
+	int i = 0;
+
+	BUG_ON(!th->t_trans_id);
+	//return;
+	check_objectid_map(s, map);
+
+	reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
+	journal_mark_dirty(th, s, SB_BUFFER_WITH_SB(s));
+
+	/* start at the beginning of the objectid map (i = 0) and go to
+	   the end of it (i = disk_sb->s_oid_cursize).  Linear search is
+	   what we use, though it is possible that binary search would be
+	   more efficient after performing lots of deletions (which is
+	   when oids is large.)  We only check even i's. */
+	while (i < sb_oid_cursize(rs)) {
+		if (objectid_to_release == le32_to_cpu(map[i])) {
+			/* This incrementation unallocates the objectid. */
+			//map[i]++;
+			le32_add_cpu(&map[i], 1);
+
+			/* Did we unallocate the last member of an odd sequence, and can shrink oids? */
+			if (map[i] == map[i + 1]) {
+				/* shrink objectid map */
+				memmove(map + i, map + i + 2,
+					(sb_oid_cursize(rs) - i -
+					 2) * sizeof(__u32));
+				//disk_sb->s_oid_cursize -= 2;
+				set_sb_oid_cursize(rs, sb_oid_cursize(rs) - 2);
+
+				RFALSE(sb_oid_cursize(rs) < 2 ||
+				       sb_oid_cursize(rs) > sb_oid_maxsize(rs),
+				       "vs-15005: objectid map corrupted cur_size == %d (max == %d)",
+				       sb_oid_cursize(rs), sb_oid_maxsize(rs));
+			}
+			return;
+		}
+
+		if (objectid_to_release > le32_to_cpu(map[i]) &&
+		    objectid_to_release < le32_to_cpu(map[i + 1])) {
+			/* size of objectid map is not changed */
+			if (objectid_to_release + 1 == le32_to_cpu(map[i + 1])) {
+				//objectid_map[i+1]--;
+				le32_add_cpu(&map[i + 1], -1);
+				return;
+			}
+
+			/* JDM comparing two little-endian values for equality -- safe */
+			if (sb_oid_cursize(rs) == sb_oid_maxsize(rs)) {
+				/* objectid map must be expanded, but there is no space */
+				PROC_INFO_INC(s, leaked_oid);
+				return;
+			}
+
+			/* expand the objectid map */
+			memmove(map + i + 3, map + i + 1,
+				(sb_oid_cursize(rs) - i - 1) * sizeof(__u32));
+			map[i + 1] = cpu_to_le32(objectid_to_release);
+			map[i + 2] = cpu_to_le32(objectid_to_release + 1);
+			set_sb_oid_cursize(rs, sb_oid_cursize(rs) + 2);
+			return;
+		}
+		i += 2;
+	}
+
+	reiserfs_error(s, "vs-15011", "tried to free free object id (%lu)",
+		       (long unsigned)objectid_to_release);
+}
+
+int reiserfs_convert_objectid_map_v1(struct super_block *s)
+{
+	struct reiserfs_super_block *disk_sb = SB_DISK_SUPER_BLOCK(s);
+	int cur_size = sb_oid_cursize(disk_sb);
+	int new_size = (s->s_blocksize - SB_SIZE) / sizeof(__u32) / 2 * 2;
+	int old_max = sb_oid_maxsize(disk_sb);
+	struct reiserfs_super_block_v1 *disk_sb_v1;
+	__le32 *objectid_map, *new_objectid_map;
+	int i;
+
+	disk_sb_v1 =
+	    (struct reiserfs_super_block_v1 *)(SB_BUFFER_WITH_SB(s)->b_data);
+	objectid_map = (__le32 *) (disk_sb_v1 + 1);
+	new_objectid_map = (__le32 *) (disk_sb + 1);
+
+	if (cur_size > new_size) {
+		/* mark everyone used that was listed as free at the end of the objectid
+		 ** map
+		 */
+		objectid_map[new_size - 1] = objectid_map[cur_size - 1];
+		set_sb_oid_cursize(disk_sb, new_size);
+	}
+	/* move the smaller objectid map past the end of the new super */
+	for (i = new_size - 1; i >= 0; i--) {
+		objectid_map[i + (old_max - new_size)] = objectid_map[i];
+	}
+
+	/* set the max size so we don't overflow later */
+	set_sb_oid_maxsize(disk_sb, new_size);
+
+	/* Zero out label and generate random UUID */
+	memset(disk_sb->s_label, 0, sizeof(disk_sb->s_label));
+	generate_random_uuid(disk_sb->s_uuid);
+
+	/* finally, zero out the unused chunk of the new super */
+	memset(disk_sb->s_unused, 0, sizeof(disk_sb->s_unused));
+	return 0;
+}

kernel/fs/reiserfs/prints.c

@@ -0,0 +1,772 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+
+#include <stdarg.h>
+
+static char error_buf[1024];
+static char fmt_buf[1024];
+static char off_buf[80];
+
+static char *reiserfs_cpu_offset(struct cpu_key *key)
+{
+	if (cpu_key_k_type(key) == TYPE_DIRENTRY)
+		sprintf(off_buf, "%Lu(%Lu)",
+			(unsigned long long)
+			GET_HASH_VALUE(cpu_key_k_offset(key)),
+			(unsigned long long)
+			GET_GENERATION_NUMBER(cpu_key_k_offset(key)));
+	else
+		sprintf(off_buf, "0x%Lx",
+			(unsigned long long)cpu_key_k_offset(key));
+	return off_buf;
+}
+
+static char *le_offset(struct reiserfs_key *key)
+{
+	int version;
+
+	version = le_key_version(key);
+	if (le_key_k_type(version, key) == TYPE_DIRENTRY)
+		sprintf(off_buf, "%Lu(%Lu)",
+			(unsigned long long)
+			GET_HASH_VALUE(le_key_k_offset(version, key)),
+			(unsigned long long)
+			GET_GENERATION_NUMBER(le_key_k_offset(version, key)));
+	else
+		sprintf(off_buf, "0x%Lx",
+			(unsigned long long)le_key_k_offset(version, key));
+	return off_buf;
+}
+
+static char *cpu_type(struct cpu_key *key)
+{
+	if (cpu_key_k_type(key) == TYPE_STAT_DATA)
+		return "SD";
+	if (cpu_key_k_type(key) == TYPE_DIRENTRY)
+		return "DIR";
+	if (cpu_key_k_type(key) == TYPE_DIRECT)
+		return "DIRECT";
+	if (cpu_key_k_type(key) == TYPE_INDIRECT)
+		return "IND";
+	return "UNKNOWN";
+}
+
+static char *le_type(struct reiserfs_key *key)
+{
+	int version;
+
+	version = le_key_version(key);
+
+	if (le_key_k_type(version, key) == TYPE_STAT_DATA)
+		return "SD";
+	if (le_key_k_type(version, key) == TYPE_DIRENTRY)
+		return "DIR";
+	if (le_key_k_type(version, key) == TYPE_DIRECT)
+		return "DIRECT";
+	if (le_key_k_type(version, key) == TYPE_INDIRECT)
+		return "IND";
+	return "UNKNOWN";
+}
+
+/* %k */
+static void sprintf_le_key(char *buf, struct reiserfs_key *key)
+{
+	if (key)
+		sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id),
+			le32_to_cpu(key->k_objectid), le_offset(key),
+			le_type(key));
+	else
+		sprintf(buf, "[NULL]");
+}
+
+/* %K */
+static void sprintf_cpu_key(char *buf, struct cpu_key *key)
+{
+	if (key)
+		sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id,
+			key->on_disk_key.k_objectid, reiserfs_cpu_offset(key),
+			cpu_type(key));
+	else
+		sprintf(buf, "[NULL]");
+}
+
+static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh)
+{
+	if (deh)
+		sprintf(buf,
+			"[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
+			deh_offset(deh), deh_dir_id(deh), deh_objectid(deh),
+			deh_location(deh), deh_state(deh));
+	else
+		sprintf(buf, "[NULL]");
+
+}
+
+static void sprintf_item_head(char *buf, struct item_head *ih)
+{
+	if (ih) {
+		strcpy(buf,
+		       (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*");
+		sprintf_le_key(buf + strlen(buf), &(ih->ih_key));
+		sprintf(buf + strlen(buf), ", item_len %d, item_location %d, "
+			"free_space(entry_count) %d",
+			ih_item_len(ih), ih_location(ih), ih_free_space(ih));
+	} else
+		sprintf(buf, "[NULL]");
+}
+
+static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de)
+{
+	char name[20];
+
+	memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen);
+	name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0;
+	sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid);
+}
+
+static void sprintf_block_head(char *buf, struct buffer_head *bh)
+{
+	sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ",
+		B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
+}
+
+static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
+{
+	char b[BDEVNAME_SIZE];
+
+	sprintf(buf,
+		"dev %s, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+		bdevname(bh->b_bdev, b), bh->b_size,
+		(unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
+		bh->b_state, bh->b_page,
+		buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
+		buffer_dirty(bh) ? "DIRTY" : "CLEAN",
+		buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
+}
+
+static void sprintf_disk_child(char *buf, struct disk_child *dc)
+{
+	sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc),
+		dc_size(dc));
+}
+
+static char *is_there_reiserfs_struct(char *fmt, int *what)
+{
+	char *k = fmt;
+
+	while ((k = strchr(k, '%')) != NULL) {
+		if (k[1] == 'k' || k[1] == 'K' || k[1] == 'h' || k[1] == 't' ||
+		    k[1] == 'z' || k[1] == 'b' || k[1] == 'y' || k[1] == 'a') {
+			*what = k[1];
+			break;
+		}
+		k++;
+	}
+	return k;
+}
+
+/* debugging reiserfs we used to print out a lot of different
+   variables, like keys, item headers, buffer heads etc. Values of
+   most fields matter. So it took a long time just to write
+   appropriative printk. With this reiserfs_warning you can use format
+   specification for complex structures like you used to do with
+   printfs for integers, doubles and pointers. For instance, to print
+   out key structure you have to write just:
+   reiserfs_warning ("bad key %k", key);
+   instead of
+   printk ("bad key %lu %lu %lu %lu", key->k_dir_id, key->k_objectid,
+           key->k_offset, key->k_uniqueness);
+*/
+static DEFINE_SPINLOCK(error_lock);
+static void prepare_error_buf(const char *fmt, va_list args)
+{
+	char *fmt1 = fmt_buf;
+	char *k;
+	char *p = error_buf;
+	int what;
+
+	spin_lock(&error_lock);
+
+	strcpy(fmt1, fmt);
+
+	while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) {
+		*k = 0;
+
+		p += vsprintf(p, fmt1, args);
+
+		switch (what) {
+		case 'k':
+			sprintf_le_key(p, va_arg(args, struct reiserfs_key *));
+			break;
+		case 'K':
+			sprintf_cpu_key(p, va_arg(args, struct cpu_key *));
+			break;
+		case 'h':
+			sprintf_item_head(p, va_arg(args, struct item_head *));
+			break;
+		case 't':
+			sprintf_direntry(p,
+					 va_arg(args,
+						struct reiserfs_dir_entry *));
+			break;
+		case 'y':
+			sprintf_disk_child(p,
+					   va_arg(args, struct disk_child *));
+			break;
+		case 'z':
+			sprintf_block_head(p,
+					   va_arg(args, struct buffer_head *));
+			break;
+		case 'b':
+			sprintf_buffer_head(p,
+					    va_arg(args, struct buffer_head *));
+			break;
+		case 'a':
+			sprintf_de_head(p,
+					va_arg(args,
+					       struct reiserfs_de_head *));
+			break;
+		}
+
+		p += strlen(p);
+		fmt1 = k + 2;
+	}
+	vsprintf(p, fmt1, args);
+	spin_unlock(&error_lock);
+
+}
+
+/* in addition to usual conversion specifiers this accepts reiserfs
+   specific conversion specifiers:
+   %k to print little endian key,
+   %K to print cpu key,
+   %h to print item_head,
+   %t to print directory entry
+   %z to print block head (arg must be struct buffer_head *
+   %b to print buffer_head
+*/
+
+#define do_reiserfs_warning(fmt)\
+{\
+    va_list args;\
+    va_start( args, fmt );\
+    prepare_error_buf( fmt, args );\
+    va_end( args );\
+}
+
+void __reiserfs_warning(struct super_block *sb, const char *id,
+			 const char *function, const char *fmt, ...)
+{
+	do_reiserfs_warning(fmt);
+	if (sb)
+		printk(KERN_WARNING "REISERFS warning (device %s): %s%s%s: "
+		       "%s\n", sb->s_id, id ? id : "", id ? " " : "",
+		       function, error_buf);
+	else
+		printk(KERN_WARNING "REISERFS warning: %s%s%s: %s\n",
+		       id ? id : "", id ? " " : "", function, error_buf);
+}
+
+/* No newline.. reiserfs_info calls can be followed by printk's */
+void reiserfs_info(struct super_block *sb, const char *fmt, ...)
+{
+	do_reiserfs_warning(fmt);
+	if (sb)
+		printk(KERN_NOTICE "REISERFS (device %s): %s",
+		       sb->s_id, error_buf);
+	else
+		printk(KERN_NOTICE "REISERFS %s:", error_buf);
+}
+
+/* No newline.. reiserfs_printk calls can be followed by printk's */
+static void reiserfs_printk(const char *fmt, ...)
+{
+	do_reiserfs_warning(fmt);
+	printk(error_buf);
+}
+
+void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...)
+{
+#ifdef CONFIG_REISERFS_CHECK
+	do_reiserfs_warning(fmt);
+	if (s)
+		printk(KERN_DEBUG "REISERFS debug (device %s): %s\n",
+		       s->s_id, error_buf);
+	else
+		printk(KERN_DEBUG "REISERFS debug: %s\n", error_buf);
+#endif
+}
+
+/* The format:
+
+           maintainer-errorid: [function-name:] message
+
+    where errorid is unique to the maintainer and function-name is
+    optional, is recommended, so that anyone can easily find the bug
+    with a simple grep for the short to type string
+    maintainer-errorid.  Don't bother with reusing errorids, there are
+    lots of numbers out there.
+
+    Example:
+
+    reiserfs_panic(
+	p_sb, "reiser-29: reiserfs_new_blocknrs: "
+	"one of search_start or rn(%d) is equal to MAX_B_NUM,"
+	"which means that we are optimizing location based on the bogus location of a temp buffer (%p).",
+	rn, bh
+    );
+
+    Regular panic()s sometimes clear the screen before the message can
+    be read, thus the need for the while loop.
+
+    Numbering scheme for panic used by Vladimir and Anatoly( Hans completely ignores this scheme, and considers it
+    pointless complexity):
+
+    panics in reiserfs_fs.h have numbers from 1000 to 1999
+    super.c				        2000 to 2999
+    preserve.c (unused)			    3000 to 3999
+    bitmap.c				    4000 to 4999
+    stree.c				        5000 to 5999
+    prints.c				    6000 to 6999
+    namei.c                     7000 to 7999
+    fix_nodes.c                 8000 to 8999
+    dir.c                       9000 to 9999
+	lbalance.c					10000 to 10999
+	ibalance.c		11000 to 11999 not ready
+	do_balan.c		12000 to 12999
+	inode.c			13000 to 13999
+	file.c			14000 to 14999
+    objectid.c                       15000 - 15999
+    buffer.c                         16000 - 16999
+    symlink.c                        17000 - 17999
+
+   .  */
+
+#ifdef CONFIG_REISERFS_CHECK
+extern struct tree_balance *cur_tb;
+#endif
+
+void __reiserfs_panic(struct super_block *sb, const char *id,
+		      const char *function, const char *fmt, ...)
+{
+	do_reiserfs_warning(fmt);
+
+#ifdef CONFIG_REISERFS_CHECK
+	dump_stack();
+#endif
+	if (sb)
+		panic(KERN_WARNING "REISERFS panic (device %s): %s%s%s: %s\n",
+		      sb->s_id, id ? id : "", id ? " " : "",
+		      function, error_buf);
+	else
+		panic(KERN_WARNING "REISERFS panic: %s%s%s: %s\n",
+		      id ? id : "", id ? " " : "", function, error_buf);
+}
+
+void __reiserfs_error(struct super_block *sb, const char *id,
+		      const char *function, const char *fmt, ...)
+{
+	do_reiserfs_warning(fmt);
+
+	BUG_ON(sb == NULL);
+
+	if (reiserfs_error_panic(sb))
+		__reiserfs_panic(sb, id, function, error_buf);
+
+	if (id && id[0])
+		printk(KERN_CRIT "REISERFS error (device %s): %s %s: %s\n",
+		       sb->s_id, id, function, error_buf);
+	else
+		printk(KERN_CRIT "REISERFS error (device %s): %s: %s\n",
+		       sb->s_id, function, error_buf);
+
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	reiserfs_info(sb, "Remounting filesystem read-only\n");
+	sb->s_flags |= MS_RDONLY;
+	reiserfs_abort_journal(sb, -EIO);
+}
+
+void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...)
+{
+	do_reiserfs_warning(fmt);
+
+	if (reiserfs_error_panic(sb)) {
+		panic(KERN_CRIT "REISERFS panic (device %s): %s\n", sb->s_id,
+		      error_buf);
+	}
+
+	if (reiserfs_is_journal_aborted(SB_JOURNAL(sb)))
+		return;
+
+	printk(KERN_CRIT "REISERFS abort (device %s): %s\n", sb->s_id,
+	       error_buf);
+
+	sb->s_flags |= MS_RDONLY;
+	reiserfs_abort_journal(sb, errno);
+}
+
+/* this prints internal nodes (4 keys/items in line) (dc_number,
+   dc_size)[k_dirid, k_objectid, k_offset, k_uniqueness](dc_number,
+   dc_size)...*/
+static int print_internal(struct buffer_head *bh, int first, int last)
+{
+	struct reiserfs_key *key;
+	struct disk_child *dc;
+	int i;
+	int from, to;
+
+	if (!B_IS_KEYS_LEVEL(bh))
+		return 1;
+
+	check_internal(bh);
+
+	if (first == -1) {
+		from = 0;
+		to = B_NR_ITEMS(bh);
+	} else {
+		from = first;
+		to = last < B_NR_ITEMS(bh) ? last : B_NR_ITEMS(bh);
+	}
+
+	reiserfs_printk("INTERNAL NODE (%ld) contains %z\n", bh->b_blocknr, bh);
+
+	dc = B_N_CHILD(bh, from);
+	reiserfs_printk("PTR %d: %y ", from, dc);
+
+	for (i = from, key = B_N_PDELIM_KEY(bh, from), dc++; i < to;
+	     i++, key++, dc++) {
+		reiserfs_printk("KEY %d: %k PTR %d: %y ", i, key, i + 1, dc);
+		if (i && i % 4 == 0)
+			printk("\n");
+	}
+	printk("\n");
+	return 0;
+}
+
+static int print_leaf(struct buffer_head *bh, int print_mode, int first,
+		      int last)
+{
+	struct block_head *blkh;
+	struct item_head *ih;
+	int i, nr;
+	int from, to;
+
+	if (!B_IS_ITEMS_LEVEL(bh))
+		return 1;
+
+	check_leaf(bh);
+
+	blkh = B_BLK_HEAD(bh);
+	ih = B_N_PITEM_HEAD(bh, 0);
+	nr = blkh_nr_item(blkh);
+
+	printk
+	    ("\n===================================================================\n");
+	reiserfs_printk("LEAF NODE (%ld) contains %z\n", bh->b_blocknr, bh);
+
+	if (!(print_mode & PRINT_LEAF_ITEMS)) {
+		reiserfs_printk("FIRST ITEM_KEY: %k, LAST ITEM KEY: %k\n",
+				&(ih->ih_key), &((ih + nr - 1)->ih_key));
+		return 0;
+	}
+
+	if (first < 0 || first > nr - 1)
+		from = 0;
+	else
+		from = first;
+
+	if (last < 0 || last > nr)
+		to = nr;
+	else
+		to = last;
+
+	ih += from;
+	printk
+	    ("-------------------------------------------------------------------------------\n");
+	printk
+	    ("|##|   type    |           key           | ilen | free_space | version | loc  |\n");
+	for (i = from; i < to; i++, ih++) {
+		printk
+		    ("-------------------------------------------------------------------------------\n");
+		reiserfs_printk("|%2d| %h |\n", i, ih);
+		if (print_mode & PRINT_LEAF_ITEMS)
+			op_print_item(ih, B_I_PITEM(bh, ih));
+	}
+
+	printk
+	    ("===================================================================\n");
+
+	return 0;
+}
+
+char *reiserfs_hashname(int code)
+{
+	if (code == YURA_HASH)
+		return "rupasov";
+	if (code == TEA_HASH)
+		return "tea";
+	if (code == R5_HASH)
+		return "r5";
+
+	return "unknown";
+}
+
+/* return 1 if this is not super block */
+static int print_super_block(struct buffer_head *bh)
+{
+	struct reiserfs_super_block *rs =
+	    (struct reiserfs_super_block *)(bh->b_data);
+	int skipped, data_blocks;
+	char *version;
+	char b[BDEVNAME_SIZE];
+
+	if (is_reiserfs_3_5(rs)) {
+		version = "3.5";
+	} else if (is_reiserfs_3_6(rs)) {
+		version = "3.6";
+	} else if (is_reiserfs_jr(rs)) {
+		version = ((sb_version(rs) == REISERFS_VERSION_2) ?
+			   "3.6" : "3.5");
+	} else {
+		return 1;
+	}
+
+	printk("%s\'s super block is in block %llu\n", bdevname(bh->b_bdev, b),
+	       (unsigned long long)bh->b_blocknr);
+	printk("Reiserfs version %s\n", version);
+	printk("Block count %u\n", sb_block_count(rs));
+	printk("Blocksize %d\n", sb_blocksize(rs));
+	printk("Free blocks %u\n", sb_free_blocks(rs));
+	// FIXME: this would be confusing if
+	// someone stores reiserfs super block in some data block ;)
+//    skipped = (bh->b_blocknr * bh->b_size) / sb_blocksize(rs);
+	skipped = bh->b_blocknr;
+	data_blocks = sb_block_count(rs) - skipped - 1 - sb_bmap_nr(rs) -
+	    (!is_reiserfs_jr(rs) ? sb_jp_journal_size(rs) +
+	     1 : sb_reserved_for_journal(rs)) - sb_free_blocks(rs);
+	printk
+	    ("Busy blocks (skipped %d, bitmaps - %d, journal (or reserved) blocks - %d\n"
+	     "1 super block, %d data blocks\n", skipped, sb_bmap_nr(rs),
+	     (!is_reiserfs_jr(rs) ? (sb_jp_journal_size(rs) + 1) :
+	      sb_reserved_for_journal(rs)), data_blocks);
+	printk("Root block %u\n", sb_root_block(rs));
+	printk("Journal block (first) %d\n", sb_jp_journal_1st_block(rs));
+	printk("Journal dev %d\n", sb_jp_journal_dev(rs));
+	printk("Journal orig size %d\n", sb_jp_journal_size(rs));
+	printk("FS state %d\n", sb_fs_state(rs));
+	printk("Hash function \"%s\"\n",
+	       reiserfs_hashname(sb_hash_function_code(rs)));
+
+	printk("Tree height %d\n", sb_tree_height(rs));
+	return 0;
+}
+
+static int print_desc_block(struct buffer_head *bh)
+{
+	struct reiserfs_journal_desc *desc;
+
+	if (memcmp(get_journal_desc_magic(bh), JOURNAL_DESC_MAGIC, 8))
+		return 1;
+
+	desc = (struct reiserfs_journal_desc *)(bh->b_data);
+	printk("Desc block %llu (j_trans_id %d, j_mount_id %d, j_len %d)",
+	       (unsigned long long)bh->b_blocknr, get_desc_trans_id(desc),
+	       get_desc_mount_id(desc), get_desc_trans_len(desc));
+
+	return 0;
+}
+
+void print_block(struct buffer_head *bh, ...)	//int print_mode, int first, int last)
+{
+	va_list args;
+	int mode, first, last;
+
+	va_start(args, bh);
+
+	if (!bh) {
+		printk("print_block: buffer is NULL\n");
+		return;
+	}
+
+	mode = va_arg(args, int);
+	first = va_arg(args, int);
+	last = va_arg(args, int);
+	if (print_leaf(bh, mode, first, last))
+		if (print_internal(bh, first, last))
+			if (print_super_block(bh))
+				if (print_desc_block(bh))
+					printk
+					    ("Block %llu contains unformatted data\n",
+					     (unsigned long long)bh->b_blocknr);
+
+	va_end(args);
+}
+
+static char print_tb_buf[2048];
+
+/* this stores initial state of tree balance in the print_tb_buf */
+void store_print_tb(struct tree_balance *tb)
+{
+	int h = 0;
+	int i;
+	struct buffer_head *tbSh, *tbFh;
+
+	if (!tb)
+		return;
+
+	sprintf(print_tb_buf, "\n"
+		"BALANCING %d\n"
+		"MODE=%c, ITEM_POS=%d POS_IN_ITEM=%d\n"
+		"=====================================================================\n"
+		"* h *    S    *    L    *    R    *   F   *   FL  *   FR  *  CFL  *  CFR  *\n",
+		REISERFS_SB(tb->tb_sb)->s_do_balance,
+		tb->tb_mode, PATH_LAST_POSITION(tb->tb_path),
+		tb->tb_path->pos_in_item);
+
+	for (h = 0; h < ARRAY_SIZE(tb->insert_size); h++) {
+		if (PATH_H_PATH_OFFSET(tb->tb_path, h) <=
+		    tb->tb_path->path_length
+		    && PATH_H_PATH_OFFSET(tb->tb_path,
+					  h) > ILLEGAL_PATH_ELEMENT_OFFSET) {
+			tbSh = PATH_H_PBUFFER(tb->tb_path, h);
+			tbFh = PATH_H_PPARENT(tb->tb_path, h);
+		} else {
+			tbSh = NULL;
+			tbFh = NULL;
+		}
+		sprintf(print_tb_buf + strlen(print_tb_buf),
+			"* %d * %3lld(%2d) * %3lld(%2d) * %3lld(%2d) * %5lld * %5lld * %5lld * %5lld * %5lld *\n",
+			h,
+			(tbSh) ? (long long)(tbSh->b_blocknr) : (-1LL),
+			(tbSh) ? atomic_read(&(tbSh->b_count)) : -1,
+			(tb->L[h]) ? (long long)(tb->L[h]->b_blocknr) : (-1LL),
+			(tb->L[h]) ? atomic_read(&(tb->L[h]->b_count)) : -1,
+			(tb->R[h]) ? (long long)(tb->R[h]->b_blocknr) : (-1LL),
+			(tb->R[h]) ? atomic_read(&(tb->R[h]->b_count)) : -1,
+			(tbFh) ? (long long)(tbFh->b_blocknr) : (-1LL),
+			(tb->FL[h]) ? (long long)(tb->FL[h]->
+						  b_blocknr) : (-1LL),
+			(tb->FR[h]) ? (long long)(tb->FR[h]->
+						  b_blocknr) : (-1LL),
+			(tb->CFL[h]) ? (long long)(tb->CFL[h]->
+						   b_blocknr) : (-1LL),
+			(tb->CFR[h]) ? (long long)(tb->CFR[h]->
+						   b_blocknr) : (-1LL));
+	}
+
+	sprintf(print_tb_buf + strlen(print_tb_buf),
+		"=====================================================================\n"
+		"* h * size * ln * lb * rn * rb * blkn * s0 * s1 * s1b * s2 * s2b * curb * lk * rk *\n"
+		"* 0 * %4d * %2d * %2d * %2d * %2d * %4d * %2d * %2d * %3d * %2d * %3d * %4d * %2d * %2d *\n",
+		tb->insert_size[0], tb->lnum[0], tb->lbytes, tb->rnum[0],
+		tb->rbytes, tb->blknum[0], tb->s0num, tb->s1num, tb->s1bytes,
+		tb->s2num, tb->s2bytes, tb->cur_blknum, tb->lkey[0],
+		tb->rkey[0]);
+
+	/* this prints balance parameters for non-leaf levels */
+	h = 0;
+	do {
+		h++;
+		sprintf(print_tb_buf + strlen(print_tb_buf),
+			"* %d * %4d * %2d *    * %2d *    * %2d *\n",
+			h, tb->insert_size[h], tb->lnum[h], tb->rnum[h],
+			tb->blknum[h]);
+	} while (tb->insert_size[h]);
+
+	sprintf(print_tb_buf + strlen(print_tb_buf),
+		"=====================================================================\n"
+		"FEB list: ");
+
+	/* print FEB list (list of buffers in form (bh (b_blocknr, b_count), that will be used for new nodes) */
+	h = 0;
+	for (i = 0; i < ARRAY_SIZE(tb->FEB); i++)
+		sprintf(print_tb_buf + strlen(print_tb_buf),
+			"%p (%llu %d)%s", tb->FEB[i],
+			tb->FEB[i] ? (unsigned long long)tb->FEB[i]->
+			b_blocknr : 0ULL,
+			tb->FEB[i] ? atomic_read(&(tb->FEB[i]->b_count)) : 0,
+			(i == ARRAY_SIZE(tb->FEB) - 1) ? "\n" : ", ");
+
+	sprintf(print_tb_buf + strlen(print_tb_buf),
+		"======================== the end ====================================\n");
+}
+
+void print_cur_tb(char *mes)
+{
+	printk("%s\n%s", mes, print_tb_buf);
+}
+
+static void check_leaf_block_head(struct buffer_head *bh)
+{
+	struct block_head *blkh;
+	int nr;
+
+	blkh = B_BLK_HEAD(bh);
+	nr = blkh_nr_item(blkh);
+	if (nr > (bh->b_size - BLKH_SIZE) / IH_SIZE)
+		reiserfs_panic(NULL, "vs-6010", "invalid item number %z",
+			       bh);
+	if (blkh_free_space(blkh) > bh->b_size - BLKH_SIZE - IH_SIZE * nr)
+		reiserfs_panic(NULL, "vs-6020", "invalid free space %z",
+			       bh);
+
+}
+
+static void check_internal_block_head(struct buffer_head *bh)
+{
+	struct block_head *blkh;
+
+	blkh = B_BLK_HEAD(bh);
+	if (!(B_LEVEL(bh) > DISK_LEAF_NODE_LEVEL && B_LEVEL(bh) <= MAX_HEIGHT))
+		reiserfs_panic(NULL, "vs-6025", "invalid level %z", bh);
+
+	if (B_NR_ITEMS(bh) > (bh->b_size - BLKH_SIZE) / IH_SIZE)
+		reiserfs_panic(NULL, "vs-6030", "invalid item number %z", bh);
+
+	if (B_FREE_SPACE(bh) !=
+	    bh->b_size - BLKH_SIZE - KEY_SIZE * B_NR_ITEMS(bh) -
+	    DC_SIZE * (B_NR_ITEMS(bh) + 1))
+		reiserfs_panic(NULL, "vs-6040", "invalid free space %z", bh);
+
+}
+
+void check_leaf(struct buffer_head *bh)
+{
+	int i;
+	struct item_head *ih;
+
+	if (!bh)
+		return;
+	check_leaf_block_head(bh);
+	for (i = 0, ih = B_N_PITEM_HEAD(bh, 0); i < B_NR_ITEMS(bh); i++, ih++)
+		op_check_item(ih, B_I_PITEM(bh, ih));
+}
+
+void check_internal(struct buffer_head *bh)
+{
+	if (!bh)
+		return;
+	check_internal_block_head(bh);
+}
+
+void print_statistics(struct super_block *s)
+{
+
+	/*
+	   printk ("reiserfs_put_super: session statistics: balances %d, fix_nodes %d, \
+	   bmap with search %d, without %d, dir2ind %d, ind2dir %d\n",
+	   REISERFS_SB(s)->s_do_balance, REISERFS_SB(s)->s_fix_nodes,
+	   REISERFS_SB(s)->s_bmaps, REISERFS_SB(s)->s_bmaps_without_search,
+	   REISERFS_SB(s)->s_direct2indirect, REISERFS_SB(s)->s_indirect2direct);
+	 */
+
+}

kernel/fs/reiserfs/procfs.c

@@ -0,0 +1,641 @@
+/* -*- linux-c -*- */
+
+/* fs/reiserfs/procfs.c */
+
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+/* proc info support a la one created by Sizif@Botik.RU for PGC */
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/seq_file.h>
+#include <asm/uaccess.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/reiserfs_fs_sb.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+
+#ifdef CONFIG_REISERFS_PROC_INFO
+
+/*
+ * LOCKING:
+ *
+ * We rely on new Alexander Viro's super-block locking.
+ *
+ */
+
+static int show_version(struct seq_file *m, struct super_block *sb)
+{
+	char *format;
+
+	if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) {
+		format = "3.6";
+	} else if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_5)) {
+		format = "3.5";
+	} else {
+		format = "unknown";
+	}
+
+	seq_printf(m, "%s format\twith checks %s\n", format,
+#if defined( CONFIG_REISERFS_CHECK )
+		   "on"
+#else
+		   "off"
+#endif
+	    );
+	return 0;
+}
+
+int reiserfs_global_version_in_proc(char *buffer, char **start, off_t offset,
+				    int count, int *eof, void *data)
+{
+	*start = buffer;
+	*eof = 1;
+	return 0;
+}
+
+#define SF( x ) ( r -> x )
+#define SFP( x ) SF( s_proc_info_data.x )
+#define SFPL( x ) SFP( x[ level ] )
+#define SFPF( x ) SFP( scan_bitmap.x )
+#define SFPJ( x ) SFP( journal.x )
+
+#define D2C( x ) le16_to_cpu( x )
+#define D4C( x ) le32_to_cpu( x )
+#define DF( x ) D2C( rs -> s_v1.x )
+#define DFL( x ) D4C( rs -> s_v1.x )
+
+#define objectid_map( s, rs ) (old_format_only (s) ?				\
+                         (__le32 *)((struct reiserfs_super_block_v1 *)rs + 1) :	\
+			 (__le32 *)(rs + 1))
+#define MAP( i ) D4C( objectid_map( sb, rs )[ i ] )
+
+#define DJF( x ) le32_to_cpu( rs -> x )
+#define DJV( x ) le32_to_cpu( s_v1 -> x )
+#define DJP( x ) le32_to_cpu( jp -> x )
+#define JF( x ) ( r -> s_journal -> x )
+
+static int show_super(struct seq_file *m, struct super_block *sb)
+{
+	struct reiserfs_sb_info *r = REISERFS_SB(sb);
+
+	seq_printf(m, "state: \t%s\n"
+		   "mount options: \t%s%s%s%s%s%s%s%s%s%s%s\n"
+		   "gen. counter: \t%i\n"
+		   "s_disk_reads: \t%i\n"
+		   "s_disk_writes: \t%i\n"
+		   "s_fix_nodes: \t%i\n"
+		   "s_do_balance: \t%i\n"
+		   "s_unneeded_left_neighbor: \t%i\n"
+		   "s_good_search_by_key_reada: \t%i\n"
+		   "s_bmaps: \t%i\n"
+		   "s_bmaps_without_search: \t%i\n"
+		   "s_direct2indirect: \t%i\n"
+		   "s_indirect2direct: \t%i\n"
+		   "\n"
+		   "max_hash_collisions: \t%i\n"
+		   "breads: \t%lu\n"
+		   "bread_misses: \t%lu\n"
+		   "search_by_key: \t%lu\n"
+		   "search_by_key_fs_changed: \t%lu\n"
+		   "search_by_key_restarted: \t%lu\n"
+		   "insert_item_restarted: \t%lu\n"
+		   "paste_into_item_restarted: \t%lu\n"
+		   "cut_from_item_restarted: \t%lu\n"
+		   "delete_solid_item_restarted: \t%lu\n"
+		   "delete_item_restarted: \t%lu\n"
+		   "leaked_oid: \t%lu\n"
+		   "leaves_removable: \t%lu\n",
+		   SF(s_mount_state) == REISERFS_VALID_FS ?
+		   "REISERFS_VALID_FS" : "REISERFS_ERROR_FS",
+		   reiserfs_r5_hash(sb) ? "FORCE_R5 " : "",
+		   reiserfs_rupasov_hash(sb) ? "FORCE_RUPASOV " : "",
+		   reiserfs_tea_hash(sb) ? "FORCE_TEA " : "",
+		   reiserfs_hash_detect(sb) ? "DETECT_HASH " : "",
+		   reiserfs_no_border(sb) ? "NO_BORDER " : "BORDER ",
+		   reiserfs_no_unhashed_relocation(sb) ?
+		   "NO_UNHASHED_RELOCATION " : "",
+		   reiserfs_hashed_relocation(sb) ? "UNHASHED_RELOCATION " : "",
+		   reiserfs_test4(sb) ? "TEST4 " : "",
+		   have_large_tails(sb) ? "TAILS " : have_small_tails(sb) ?
+		   "SMALL_TAILS " : "NO_TAILS ",
+		   replay_only(sb) ? "REPLAY_ONLY " : "",
+		   convert_reiserfs(sb) ? "CONV " : "",
+		   atomic_read(&r->s_generation_counter),
+		   SF(s_disk_reads), SF(s_disk_writes), SF(s_fix_nodes),
+		   SF(s_do_balance), SF(s_unneeded_left_neighbor),
+		   SF(s_good_search_by_key_reada), SF(s_bmaps),
+		   SF(s_bmaps_without_search), SF(s_direct2indirect),
+		   SF(s_indirect2direct), SFP(max_hash_collisions), SFP(breads),
+		   SFP(bread_miss), SFP(search_by_key),
+		   SFP(search_by_key_fs_changed), SFP(search_by_key_restarted),
+		   SFP(insert_item_restarted), SFP(paste_into_item_restarted),
+		   SFP(cut_from_item_restarted),
+		   SFP(delete_solid_item_restarted), SFP(delete_item_restarted),
+		   SFP(leaked_oid), SFP(leaves_removable));
+
+	return 0;
+}
+
+static int show_per_level(struct seq_file *m, struct super_block *sb)
+{
+	struct reiserfs_sb_info *r = REISERFS_SB(sb);
+	int level;
+
+	seq_printf(m, "level\t"
+		   "     balances"
+		   " [sbk:  reads"
+		   "   fs_changed"
+		   "   restarted]"
+		   "   free space"
+		   "        items"
+		   "   can_remove"
+		   "         lnum"
+		   "         rnum"
+		   "       lbytes"
+		   "       rbytes"
+		   "     get_neig"
+		   " get_neig_res" "  need_l_neig" "  need_r_neig" "\n");
+
+	for (level = 0; level < MAX_HEIGHT; ++level) {
+		seq_printf(m, "%i\t"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   " %12li"
+			   " %12li"
+			   " %12li"
+			   " %12li"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   " %12lu"
+			   "\n",
+			   level,
+			   SFPL(balance_at),
+			   SFPL(sbk_read_at),
+			   SFPL(sbk_fs_changed),
+			   SFPL(sbk_restarted),
+			   SFPL(free_at),
+			   SFPL(items_at),
+			   SFPL(can_node_be_removed),
+			   SFPL(lnum),
+			   SFPL(rnum),
+			   SFPL(lbytes),
+			   SFPL(rbytes),
+			   SFPL(get_neighbors),
+			   SFPL(get_neighbors_restart),
+			   SFPL(need_l_neighbor), SFPL(need_r_neighbor)
+		    );
+	}
+	return 0;
+}
+
+static int show_bitmap(struct seq_file *m, struct super_block *sb)
+{
+	struct reiserfs_sb_info *r = REISERFS_SB(sb);
+
+	seq_printf(m, "free_block: %lu\n"
+		   "  scan_bitmap:"
+		   "          wait"
+		   "          bmap"
+		   "         retry"
+		   "        stolen"
+		   "  journal_hint"
+		   "journal_nohint"
+		   "\n"
+		   " %14lu"
+		   " %14lu"
+		   " %14lu"
+		   " %14lu"
+		   " %14lu"
+		   " %14lu"
+		   " %14lu"
+		   "\n",
+		   SFP(free_block),
+		   SFPF(call),
+		   SFPF(wait),
+		   SFPF(bmap),
+		   SFPF(retry),
+		   SFPF(stolen),
+		   SFPF(in_journal_hint), SFPF(in_journal_nohint));
+
+	return 0;
+}
+
+static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
+{
+	struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
+	struct reiserfs_super_block *rs = sb_info->s_rs;
+	int hash_code = DFL(s_hash_function_code);
+	__u32 flags = DJF(s_flags);
+
+	seq_printf(m, "block_count: \t%i\n"
+		   "free_blocks: \t%i\n"
+		   "root_block: \t%i\n"
+		   "blocksize: \t%i\n"
+		   "oid_maxsize: \t%i\n"
+		   "oid_cursize: \t%i\n"
+		   "umount_state: \t%i\n"
+		   "magic: \t%10.10s\n"
+		   "fs_state: \t%i\n"
+		   "hash: \t%s\n"
+		   "tree_height: \t%i\n"
+		   "bmap_nr: \t%i\n"
+		   "version: \t%i\n"
+		   "flags: \t%x[%s]\n"
+		   "reserved_for_journal: \t%i\n",
+		   DFL(s_block_count),
+		   DFL(s_free_blocks),
+		   DFL(s_root_block),
+		   DF(s_blocksize),
+		   DF(s_oid_maxsize),
+		   DF(s_oid_cursize),
+		   DF(s_umount_state),
+		   rs->s_v1.s_magic,
+		   DF(s_fs_state),
+		   hash_code == TEA_HASH ? "tea" :
+		   (hash_code == YURA_HASH) ? "rupasov" :
+		   (hash_code == R5_HASH) ? "r5" :
+		   (hash_code == UNSET_HASH) ? "unset" : "unknown",
+		   DF(s_tree_height),
+		   DF(s_bmap_nr),
+		   DF(s_version), flags, (flags & reiserfs_attrs_cleared)
+		   ? "attrs_cleared" : "", DF(s_reserved_for_journal));
+
+	return 0;
+}
+
+static int show_oidmap(struct seq_file *m, struct super_block *sb)
+{
+	struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
+	struct reiserfs_super_block *rs = sb_info->s_rs;
+	unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize);
+	unsigned long total_used = 0;
+	int i;
+
+	for (i = 0; i < mapsize; ++i) {
+		__u32 right;
+
+		right = (i == mapsize - 1) ? MAX_KEY_OBJECTID : MAP(i + 1);
+		seq_printf(m, "%s: [ %x .. %x )\n",
+			   (i & 1) ? "free" : "used", MAP(i), right);
+		if (!(i & 1)) {
+			total_used += right - MAP(i);
+		}
+	}
+#if defined( REISERFS_USE_OIDMAPF )
+	if (sb_info->oidmap.use_file && (sb_info->oidmap.mapf != NULL)) {
+		loff_t size = sb_info->oidmap.mapf->f_path.dentry->d_inode->i_size;
+		total_used += size / sizeof(reiserfs_oidinterval_d_t);
+	}
+#endif
+	seq_printf(m, "total: \t%i [%i/%i] used: %lu [exact]\n",
+		   mapsize,
+		   mapsize, le16_to_cpu(rs->s_v1.s_oid_maxsize), total_used);
+	return 0;
+}
+
+static int show_journal(struct seq_file *m, struct super_block *sb)
+{
+	struct reiserfs_sb_info *r = REISERFS_SB(sb);
+	struct reiserfs_super_block *rs = r->s_rs;
+	struct journal_params *jp = &rs->s_v1.s_journal;
+	char b[BDEVNAME_SIZE];
+
+	seq_printf(m,		/* on-disk fields */
+		   "jp_journal_1st_block: \t%i\n"
+		   "jp_journal_dev: \t%s[%x]\n"
+		   "jp_journal_size: \t%i\n"
+		   "jp_journal_trans_max: \t%i\n"
+		   "jp_journal_magic: \t%i\n"
+		   "jp_journal_max_batch: \t%i\n"
+		   "jp_journal_max_commit_age: \t%i\n"
+		   "jp_journal_max_trans_age: \t%i\n"
+		   /* incore fields */
+		   "j_1st_reserved_block: \t%i\n"
+		   "j_state: \t%li\n"
+		   "j_trans_id: \t%u\n"
+		   "j_mount_id: \t%lu\n"
+		   "j_start: \t%lu\n"
+		   "j_len: \t%lu\n"
+		   "j_len_alloc: \t%lu\n"
+		   "j_wcount: \t%i\n"
+		   "j_bcount: \t%lu\n"
+		   "j_first_unflushed_offset: \t%lu\n"
+		   "j_last_flush_trans_id: \t%u\n"
+		   "j_trans_start_time: \t%li\n"
+		   "j_list_bitmap_index: \t%i\n"
+		   "j_must_wait: \t%i\n"
+		   "j_next_full_flush: \t%i\n"
+		   "j_next_async_flush: \t%i\n"
+		   "j_cnode_used: \t%i\n" "j_cnode_free: \t%i\n" "\n"
+		   /* reiserfs_proc_info_data_t.journal fields */
+		   "in_journal: \t%12lu\n"
+		   "in_journal_bitmap: \t%12lu\n"
+		   "in_journal_reusable: \t%12lu\n"
+		   "lock_journal: \t%12lu\n"
+		   "lock_journal_wait: \t%12lu\n"
+		   "journal_begin: \t%12lu\n"
+		   "journal_relock_writers: \t%12lu\n"
+		   "journal_relock_wcount: \t%12lu\n"
+		   "mark_dirty: \t%12lu\n"
+		   "mark_dirty_already: \t%12lu\n"
+		   "mark_dirty_notjournal: \t%12lu\n"
+		   "restore_prepared: \t%12lu\n"
+		   "prepare: \t%12lu\n"
+		   "prepare_retry: \t%12lu\n",
+		   DJP(jp_journal_1st_block),
+		   bdevname(SB_JOURNAL(sb)->j_dev_bd, b),
+		   DJP(jp_journal_dev),
+		   DJP(jp_journal_size),
+		   DJP(jp_journal_trans_max),
+		   DJP(jp_journal_magic),
+		   DJP(jp_journal_max_batch),
+		   SB_JOURNAL(sb)->j_max_commit_age,
+		   DJP(jp_journal_max_trans_age),
+		   JF(j_1st_reserved_block),
+		   JF(j_state),
+		   JF(j_trans_id),
+		   JF(j_mount_id),
+		   JF(j_start),
+		   JF(j_len),
+		   JF(j_len_alloc),
+		   atomic_read(&r->s_journal->j_wcount),
+		   JF(j_bcount),
+		   JF(j_first_unflushed_offset),
+		   JF(j_last_flush_trans_id),
+		   JF(j_trans_start_time),
+		   JF(j_list_bitmap_index),
+		   JF(j_must_wait),
+		   JF(j_next_full_flush),
+		   JF(j_next_async_flush),
+		   JF(j_cnode_used),
+		   JF(j_cnode_free),
+		   SFPJ(in_journal),
+		   SFPJ(in_journal_bitmap),
+		   SFPJ(in_journal_reusable),
+		   SFPJ(lock_journal),
+		   SFPJ(lock_journal_wait),
+		   SFPJ(journal_being),
+		   SFPJ(journal_relock_writers),
+		   SFPJ(journal_relock_wcount),
+		   SFPJ(mark_dirty),
+		   SFPJ(mark_dirty_already),
+		   SFPJ(mark_dirty_notjournal),
+		   SFPJ(restore_prepared), SFPJ(prepare), SFPJ(prepare_retry)
+	    );
+	return 0;
+}
+
+/* iterator */
+static int test_sb(struct super_block *sb, void *data)
+{
+	return data == sb;
+}
+
+static int set_sb(struct super_block *sb, void *data)
+{
+	return -ENOENT;
+}
+
+static void *r_start(struct seq_file *m, loff_t * pos)
+{
+	struct proc_dir_entry *de = m->private;
+	struct super_block *s = de->parent->data;
+	loff_t l = *pos;
+
+	if (l)
+		return NULL;
+
+	if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, s)))
+		return NULL;
+
+	up_write(&s->s_umount);
+	return s;
+}
+
+static void *r_next(struct seq_file *m, void *v, loff_t * pos)
+{
+	++*pos;
+	if (v)
+		deactivate_super(v);
+	return NULL;
+}
+
+static void r_stop(struct seq_file *m, void *v)
+{
+	if (v)
+		deactivate_super(v);
+}
+
+static int r_show(struct seq_file *m, void *v)
+{
+	struct proc_dir_entry *de = m->private;
+	int (*show) (struct seq_file *, struct super_block *) = de->data;
+	return show(m, v);
+}
+
+static const struct seq_operations r_ops = {
+	.start = r_start,
+	.next = r_next,
+	.stop = r_stop,
+	.show = r_show,
+};
+
+static int r_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open(file, &r_ops);
+
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = PDE(inode);
+	}
+	return ret;
+}
+
+static const struct file_operations r_file_operations = {
+	.open = r_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+	.owner = THIS_MODULE,
+};
+
+static struct proc_dir_entry *proc_info_root = NULL;
+static const char proc_info_root_name[] = "fs/reiserfs";
+
+static void add_file(struct super_block *sb, char *name,
+		     int (*func) (struct seq_file *, struct super_block *))
+{
+	proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
+			 &r_file_operations, func);
+}
+
+int reiserfs_proc_info_init(struct super_block *sb)
+{
+	char b[BDEVNAME_SIZE];
+	char *s;
+
+	/* Some block devices use /'s */
+	strlcpy(b, reiserfs_bdevname(sb), BDEVNAME_SIZE);
+	s = strchr(b, '/');
+	if (s)
+		*s = '!';
+
+	spin_lock_init(&__PINFO(sb).lock);
+	REISERFS_SB(sb)->procdir = proc_mkdir(b, proc_info_root);
+	if (REISERFS_SB(sb)->procdir) {
+		REISERFS_SB(sb)->procdir->data = sb;
+		add_file(sb, "version", show_version);
+		add_file(sb, "super", show_super);
+		add_file(sb, "per-level", show_per_level);
+		add_file(sb, "bitmap", show_bitmap);
+		add_file(sb, "on-disk-super", show_on_disk_super);
+		add_file(sb, "oidmap", show_oidmap);
+		add_file(sb, "journal", show_journal);
+		return 0;
+	}
+	reiserfs_warning(sb, "cannot create /proc/%s/%s",
+			 proc_info_root_name, b);
+	return 1;
+}
+
+int reiserfs_proc_info_done(struct super_block *sb)
+{
+	struct proc_dir_entry *de = REISERFS_SB(sb)->procdir;
+	char b[BDEVNAME_SIZE];
+	char *s;
+
+	/* Some block devices use /'s */
+	strlcpy(b, reiserfs_bdevname(sb), BDEVNAME_SIZE);
+	s = strchr(b, '/');
+	if (s)
+		*s = '!';
+
+	if (de) {
+		remove_proc_entry("journal", de);
+		remove_proc_entry("oidmap", de);
+		remove_proc_entry("on-disk-super", de);
+		remove_proc_entry("bitmap", de);
+		remove_proc_entry("per-level", de);
+		remove_proc_entry("super", de);
+		remove_proc_entry("version", de);
+	}
+	spin_lock(&__PINFO(sb).lock);
+	__PINFO(sb).exiting = 1;
+	spin_unlock(&__PINFO(sb).lock);
+	if (proc_info_root) {
+		remove_proc_entry(b, proc_info_root);
+		REISERFS_SB(sb)->procdir = NULL;
+	}
+	return 0;
+}
+
+struct proc_dir_entry *reiserfs_proc_register_global(char *name,
+						     read_proc_t * func)
+{
+	return (proc_info_root) ? create_proc_read_entry(name, 0,
+							 proc_info_root,
+							 func, NULL) : NULL;
+}
+
+void reiserfs_proc_unregister_global(const char *name)
+{
+	remove_proc_entry(name, proc_info_root);
+}
+
+int reiserfs_proc_info_global_init(void)
+{
+	if (proc_info_root == NULL) {
+		proc_info_root = proc_mkdir(proc_info_root_name, NULL);
+		if (!proc_info_root) {
+			reiserfs_warning(NULL, "cannot create /proc/%s",
+					 proc_info_root_name);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+int reiserfs_proc_info_global_done(void)
+{
+	if (proc_info_root != NULL) {
+		proc_info_root = NULL;
+		remove_proc_entry(proc_info_root_name, NULL);
+	}
+	return 0;
+}
+
+/* REISERFS_PROC_INFO */
+#else
+
+int reiserfs_proc_info_init(struct super_block *sb)
+{
+	return 0;
+}
+int reiserfs_proc_info_done(struct super_block *sb)
+{
+	return 0;
+}
+
+struct proc_dir_entry *reiserfs_proc_register_global(char *name,
+						     read_proc_t * func)
+{
+	return NULL;
+}
+
+void reiserfs_proc_unregister_global(const char *name)
+{;
+}
+
+int reiserfs_proc_info_global_init(void)
+{
+	return 0;
+}
+int reiserfs_proc_info_global_done(void)
+{
+	return 0;
+}
+
+int reiserfs_global_version_in_proc(char *buffer, char **start,
+				    off_t offset,
+				    int count, int *eof, void *data)
+{
+	return 0;
+}
+
+/* REISERFS_PROC_INFO */
+#endif
+
+/*
+ * Revision 1.1.8.2  2001/07/15 17:08:42  god
+ *  . use get_super() in procfs.c
+ *  . remove remove_save_link() from reiserfs_do_truncate()
+ *
+ * I accept terms and conditions stated in the Legal Agreement
+ * (available at http://www.namesys.com/legalese.html)
+ *
+ * Revision 1.1.8.1  2001/07/11 16:48:50  god
+ * proc info support
+ *
+ * I accept terms and conditions stated in the Legal Agreement
+ * (available at http://www.namesys.com/legalese.html)
+ *
+ */
+
+/*
+ * Make Linus happy.
+ * Local variables:
+ * c-indentation-style: "K&R"
+ * mode-name: "LC"
+ * c-basic-offset: 8
+ * tab-width: 8
+ * End:
+ */

kernel/fs/reiserfs/resize.c

@@ -0,0 +1,210 @@
+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+/*
+ * Written by Alexander Zarochentcev.
+ *
+ * The kernel part of the (on-line) reiserfs resizer.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/reiserfs_fs_sb.h>
+#include <linux/buffer_head.h>
+
+int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
+{
+	int err = 0;
+	struct reiserfs_super_block *sb;
+	struct reiserfs_bitmap_info *bitmap;
+	struct reiserfs_bitmap_info *info;
+	struct reiserfs_bitmap_info *old_bitmap = SB_AP_BITMAP(s);
+	struct buffer_head *bh;
+	struct reiserfs_transaction_handle th;
+	unsigned int bmap_nr_new, bmap_nr;
+	unsigned int block_r_new, block_r;
+
+	struct reiserfs_list_bitmap *jb;
+	struct reiserfs_list_bitmap jbitmap[JOURNAL_NUM_BITMAPS];
+
+	unsigned long int block_count, free_blocks;
+	int i;
+	int copy_size;
+
+	sb = SB_DISK_SUPER_BLOCK(s);
+
+	if (SB_BLOCK_COUNT(s) >= block_count_new) {
+		printk("can\'t shrink filesystem on-line\n");
+		return -EINVAL;
+	}
+
+	/* check the device size */
+	bh = sb_bread(s, block_count_new - 1);
+	if (!bh) {
+		printk("reiserfs_resize: can\'t read last block\n");
+		return -EINVAL;
+	}
+	bforget(bh);
+
+	/* old disk layout detection; those partitions can be mounted, but
+	 * cannot be resized */
+	if (SB_BUFFER_WITH_SB(s)->b_blocknr * SB_BUFFER_WITH_SB(s)->b_size
+	    != REISERFS_DISK_OFFSET_IN_BYTES) {
+		printk
+		    ("reiserfs_resize: unable to resize a reiserfs without distributed bitmap (fs version < 3.5.12)\n");
+		return -ENOTSUPP;
+	}
+
+	/* count used bits in last bitmap block */
+	block_r = SB_BLOCK_COUNT(s) -
+			(reiserfs_bmap_count(s) - 1) * s->s_blocksize * 8;
+
+	/* count bitmap blocks in new fs */
+	bmap_nr_new = block_count_new / (s->s_blocksize * 8);
+	block_r_new = block_count_new - bmap_nr_new * s->s_blocksize * 8;
+	if (block_r_new)
+		bmap_nr_new++;
+	else
+		block_r_new = s->s_blocksize * 8;
+
+	/* save old values */
+	block_count = SB_BLOCK_COUNT(s);
+	bmap_nr = reiserfs_bmap_count(s);
+
+	/* resizing of reiserfs bitmaps (journal and real), if needed */
+	if (bmap_nr_new > bmap_nr) {
+		/* reallocate journal bitmaps */
+		if (reiserfs_allocate_list_bitmaps(s, jbitmap, bmap_nr_new) < 0) {
+			printk
+			    ("reiserfs_resize: unable to allocate memory for journal bitmaps\n");
+			return -ENOMEM;
+		}
+		/* the new journal bitmaps are zero filled, now we copy in the bitmap
+		 ** node pointers from the old journal bitmap structs, and then
+		 ** transfer the new data structures into the journal struct.
+		 **
+		 ** using the copy_size var below allows this code to work for
+		 ** both shrinking and expanding the FS.
+		 */
+		copy_size = bmap_nr_new < bmap_nr ? bmap_nr_new : bmap_nr;
+		copy_size =
+		    copy_size * sizeof(struct reiserfs_list_bitmap_node *);
+		for (i = 0; i < JOURNAL_NUM_BITMAPS; i++) {
+			struct reiserfs_bitmap_node **node_tmp;
+			jb = SB_JOURNAL(s)->j_list_bitmap + i;
+			memcpy(jbitmap[i].bitmaps, jb->bitmaps, copy_size);
+
+			/* just in case vfree schedules on us, copy the new
+			 ** pointer into the journal struct before freeing the
+			 ** old one
+			 */
+			node_tmp = jb->bitmaps;
+			jb->bitmaps = jbitmap[i].bitmaps;
+			vfree(node_tmp);
+		}
+
+		/* allocate additional bitmap blocks, reallocate array of bitmap
+		 * block pointers */
+		bitmap =
+		    vmalloc(sizeof(struct reiserfs_bitmap_info) * bmap_nr_new);
+		if (!bitmap) {
+			/* Journal bitmaps are still supersized, but the memory isn't
+			 * leaked, so I guess it's ok */
+			printk("reiserfs_resize: unable to allocate memory.\n");
+			return -ENOMEM;
+		}
+		memset(bitmap, 0,
+		       sizeof(struct reiserfs_bitmap_info) * bmap_nr_new);
+		for (i = 0; i < bmap_nr; i++)
+			bitmap[i] = old_bitmap[i];
+
+		/* This doesn't go through the journal, but it doesn't have to.
+		 * The changes are still atomic: We're synced up when the journal
+		 * transaction begins, and the new bitmaps don't matter if the
+		 * transaction fails. */
+		for (i = bmap_nr; i < bmap_nr_new; i++) {
+			/* don't use read_bitmap_block since it will cache
+			 * the uninitialized bitmap */
+			bh = sb_bread(s, i * s->s_blocksize * 8);
+			if (!bh) {
+				vfree(bitmap);
+				return -EIO;
+			}
+			memset(bh->b_data, 0, sb_blocksize(sb));
+			reiserfs_test_and_set_le_bit(0, bh->b_data);
+			reiserfs_cache_bitmap_metadata(s, bh, bitmap + i);
+
+			set_buffer_uptodate(bh);
+			mark_buffer_dirty(bh);
+			sync_dirty_buffer(bh);
+			// update bitmap_info stuff
+			bitmap[i].free_count = sb_blocksize(sb) * 8 - 1;
+			brelse(bh);
+		}
+		/* free old bitmap blocks array */
+		SB_AP_BITMAP(s) = bitmap;
+		vfree(old_bitmap);
+	}
+
+	/* begin transaction, if there was an error, it's fine. Yes, we have
+	 * incorrect bitmaps now, but none of it is ever going to touch the
+	 * disk anyway. */
+	err = journal_begin(&th, s, 10);
+	if (err)
+		return err;
+
+	/* Extend old last bitmap block - new blocks have been made available */
+	info = SB_AP_BITMAP(s) + bmap_nr - 1;
+	bh = reiserfs_read_bitmap_block(s, bmap_nr - 1);
+	if (!bh) {
+		int jerr = journal_end(&th, s, 10);
+		if (jerr)
+			return jerr;
+		return -EIO;
+	}
+
+	reiserfs_prepare_for_journal(s, bh, 1);
+	for (i = block_r; i < s->s_blocksize * 8; i++)
+		reiserfs_test_and_clear_le_bit(i, bh->b_data);
+	info->free_count += s->s_blocksize * 8 - block_r;
+
+	journal_mark_dirty(&th, s, bh);
+	brelse(bh);
+
+	/* Correct new last bitmap block - It may not be full */
+	info = SB_AP_BITMAP(s) + bmap_nr_new - 1;
+	bh = reiserfs_read_bitmap_block(s, bmap_nr_new - 1);
+	if (!bh) {
+		int jerr = journal_end(&th, s, 10);
+		if (jerr)
+			return jerr;
+		return -EIO;
+	}
+
+	reiserfs_prepare_for_journal(s, bh, 1);
+	for (i = block_r_new; i < s->s_blocksize * 8; i++)
+		reiserfs_test_and_set_le_bit(i, bh->b_data);
+	journal_mark_dirty(&th, s, bh);
+	brelse(bh);
+
+	info->free_count -= s->s_blocksize * 8 - block_r_new;
+	/* update super */
+	reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
+	free_blocks = SB_FREE_BLOCKS(s);
+	PUT_SB_FREE_BLOCKS(s,
+			   free_blocks + (block_count_new - block_count -
+					  (bmap_nr_new - bmap_nr)));
+	PUT_SB_BLOCK_COUNT(s, block_count_new);
+	PUT_SB_BMAP_NR(s, bmap_would_wrap(bmap_nr_new) ? : bmap_nr_new);
+	s->s_dirt = 1;
+
+	journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
+
+	SB_JOURNAL(s)->j_must_wait = 1;
+	return journal_end(&th, s, 10);
+}

kernel/fs/reiserfs/tail_conversion.c

@@ -0,0 +1,280 @@
+/*
+ * Copyright 1999 Hans Reiser, see reiserfs/README for licensing and copyright details
+ */
+
+#include <linux/time.h>
+#include <linux/pagemap.h>
+#include <linux/buffer_head.h>
+#include <linux/reiserfs_fs.h>
+
+/* access to tail : when one is going to read tail it must make sure, that is not running.
+ direct2indirect and indirect2direct can not run concurrently */
+
+/* Converts direct items to an unformatted node. Panics if file has no
+   tail. -ENOSPC if no disk space for conversion */
+/* path points to first direct item of the file regarless of how many of
+   them are there */
+int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
+		    struct treepath *path, struct buffer_head *unbh,
+		    loff_t tail_offset)
+{
+	struct super_block *sb = inode->i_sb;
+	struct buffer_head *up_to_date_bh;
+	struct item_head *p_le_ih = PATH_PITEM_HEAD(path);
+	unsigned long total_tail = 0;
+	struct cpu_key end_key;	/* Key to search for the last byte of the
+				   converted item. */
+	struct item_head ind_ih;	/* new indirect item to be inserted or
+					   key of unfm pointer to be pasted */
+	int blk_size, retval;	/* returned value for reiserfs_insert_item and clones */
+	unp_t unfm_ptr;		/* Handle on an unformatted node
+				   that will be inserted in the
+				   tree. */
+
+	BUG_ON(!th->t_trans_id);
+
+	REISERFS_SB(sb)->s_direct2indirect++;
+
+	blk_size = sb->s_blocksize;
+
+	/* and key to search for append or insert pointer to the new
+	   unformatted node. */
+	copy_item_head(&ind_ih, p_le_ih);
+	set_le_ih_k_offset(&ind_ih, tail_offset);
+	set_le_ih_k_type(&ind_ih, TYPE_INDIRECT);
+
+	/* Set the key to search for the place for new unfm pointer */
+	make_cpu_key(&end_key, inode, tail_offset, TYPE_INDIRECT, 4);
+
+	/* FIXME: we could avoid this */
+	if (search_for_position_by_key(sb, &end_key, path) == POSITION_FOUND) {
+		reiserfs_error(sb, "PAP-14030",
+			       "pasted or inserted byte exists in "
+			       "the tree %K. Use fsck to repair.", &end_key);
+		pathrelse(path);
+		return -EIO;
+	}
+
+	p_le_ih = PATH_PITEM_HEAD(path);
+
+	unfm_ptr = cpu_to_le32(unbh->b_blocknr);
+
+	if (is_statdata_le_ih(p_le_ih)) {
+		/* Insert new indirect item. */
+		set_ih_free_space(&ind_ih, 0);	/* delete at nearest future */
+		put_ih_item_len(&ind_ih, UNFM_P_SIZE);
+		PATH_LAST_POSITION(path)++;
+		retval =
+		    reiserfs_insert_item(th, path, &end_key, &ind_ih, inode,
+					 (char *)&unfm_ptr);
+	} else {
+		/* Paste into last indirect item of an object. */
+		retval = reiserfs_paste_into_item(th, path, &end_key, inode,
+						    (char *)&unfm_ptr,
+						    UNFM_P_SIZE);
+	}
+	if (retval) {
+		return retval;
+	}
+	// note: from here there are two keys which have matching first
+	// three key components. They only differ by the fourth one.
+
+	/* Set the key to search for the direct items of the file */
+	make_cpu_key(&end_key, inode, max_reiserfs_offset(inode), TYPE_DIRECT,
+		     4);
+
+	/* Move bytes from the direct items to the new unformatted node
+	   and delete them. */
+	while (1) {
+		int tail_size;
+
+		/* end_key.k_offset is set so, that we will always have found
+		   last item of the file */
+		if (search_for_position_by_key(sb, &end_key, path) ==
+		    POSITION_FOUND)
+			reiserfs_panic(sb, "PAP-14050",
+				       "direct item (%K) not found", &end_key);
+		p_le_ih = PATH_PITEM_HEAD(path);
+		RFALSE(!is_direct_le_ih(p_le_ih),
+		       "vs-14055: direct item expected(%K), found %h",
+		       &end_key, p_le_ih);
+		tail_size = (le_ih_k_offset(p_le_ih) & (blk_size - 1))
+		    + ih_item_len(p_le_ih) - 1;
+
+		/* we only send the unbh pointer if the buffer is not up to date.
+		 ** this avoids overwriting good data from writepage() with old data
+		 ** from the disk or buffer cache
+		 ** Special case: unbh->b_page will be NULL if we are coming through
+		 ** DIRECT_IO handler here.
+		 */
+		if (!unbh->b_page || buffer_uptodate(unbh)
+		    || PageUptodate(unbh->b_page)) {
+			up_to_date_bh = NULL;
+		} else {
+			up_to_date_bh = unbh;
+		}
+		retval = reiserfs_delete_item(th, path, &end_key, inode,
+						up_to_date_bh);
+
+		total_tail += retval;
+		if (tail_size == retval)
+			// done: file does not have direct items anymore
+			break;
+
+	}
+	/* if we've copied bytes from disk into the page, we need to zero
+	 ** out the unused part of the block (it was not up to date before)
+	 */
+	if (up_to_date_bh) {
+		unsigned pgoff =
+		    (tail_offset + total_tail - 1) & (PAGE_CACHE_SIZE - 1);
+		char *kaddr = kmap_atomic(up_to_date_bh->b_page, KM_USER0);
+		memset(kaddr + pgoff, 0, blk_size - total_tail);
+		kunmap_atomic(kaddr, KM_USER0);
+	}
+
+	REISERFS_I(inode)->i_first_direct_byte = U32_MAX;
+
+	return 0;
+}
+
+/* stolen from fs/buffer.c */
+void reiserfs_unmap_buffer(struct buffer_head *bh)
+{
+	lock_buffer(bh);
+	if (buffer_journaled(bh) || buffer_journal_dirty(bh)) {
+		BUG();
+	}
+	clear_buffer_dirty(bh);
+	/* Remove the buffer from whatever list it belongs to. We are mostly
+	   interested in removing it from per-sb j_dirty_buffers list, to avoid
+	   BUG() on attempt to write not mapped buffer */
+	if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) {
+		struct inode *inode = bh->b_page->mapping->host;
+		struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
+		spin_lock(&j->j_dirty_buffers_lock);
+		list_del_init(&bh->b_assoc_buffers);
+		reiserfs_free_jh(bh);
+		spin_unlock(&j->j_dirty_buffers_lock);
+	}
+	clear_buffer_mapped(bh);
+	clear_buffer_req(bh);
+	clear_buffer_new(bh);
+	bh->b_bdev = NULL;
+	unlock_buffer(bh);
+}
+
+/* this first locks inode (neither reads nor sync are permitted),
+   reads tail through page cache, insert direct item. When direct item
+   inserted successfully inode is left locked. Return value is always
+   what we expect from it (number of cut bytes). But when tail remains
+   in the unformatted node, we set mode to SKIP_BALANCING and unlock
+   inode */
+int indirect2direct(struct reiserfs_transaction_handle *th,
+		    struct inode *inode, struct page *page,
+		    struct treepath *path,	/* path to the indirect item. */
+		    const struct cpu_key *item_key,	/* Key to look for
+							 * unformatted node
+							 * pointer to be cut. */
+		    loff_t n_new_file_size,	/* New file size. */
+		    char *mode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct item_head s_ih;
+	unsigned long block_size = sb->s_blocksize;
+	char *tail;
+	int tail_len, round_tail_len;
+	loff_t pos, pos1;	/* position of first byte of the tail */
+	struct cpu_key key;
+
+	BUG_ON(!th->t_trans_id);
+
+	REISERFS_SB(sb)->s_indirect2direct++;
+
+	*mode = M_SKIP_BALANCING;
+
+	/* store item head path points to. */
+	copy_item_head(&s_ih, PATH_PITEM_HEAD(path));
+
+	tail_len = (n_new_file_size & (block_size - 1));
+	if (get_inode_sd_version(inode) == STAT_DATA_V2)
+		round_tail_len = ROUND_UP(tail_len);
+	else
+		round_tail_len = tail_len;
+
+	pos =
+	    le_ih_k_offset(&s_ih) - 1 + (ih_item_len(&s_ih) / UNFM_P_SIZE -
+					 1) * sb->s_blocksize;
+	pos1 = pos;
+
+	// we are protected by i_mutex. The tail can not disapper, not
+	// append can be done either
+	// we are in truncate or packing tail in file_release
+
+	tail = (char *)kmap(page);	/* this can schedule */
+
+	if (path_changed(&s_ih, path)) {
+		/* re-search indirect item */
+		if (search_for_position_by_key(sb, item_key, path)
+		    == POSITION_NOT_FOUND)
+			reiserfs_panic(sb, "PAP-5520",
+				       "item to be converted %K does not exist",
+				       item_key);
+		copy_item_head(&s_ih, PATH_PITEM_HEAD(path));
+#ifdef CONFIG_REISERFS_CHECK
+		pos = le_ih_k_offset(&s_ih) - 1 +
+		    (ih_item_len(&s_ih) / UNFM_P_SIZE -
+		     1) * sb->s_blocksize;
+		if (pos != pos1)
+			reiserfs_panic(sb, "vs-5530", "tail position "
+				       "changed while we were reading it");
+#endif
+	}
+
+	/* Set direct item header to insert. */
+	make_le_item_head(&s_ih, NULL, get_inode_item_key_version(inode),
+			  pos1 + 1, TYPE_DIRECT, round_tail_len,
+			  0xffff /*ih_free_space */ );
+
+	/* we want a pointer to the first byte of the tail in the page.
+	 ** the page was locked and this part of the page was up to date when
+	 ** indirect2direct was called, so we know the bytes are still valid
+	 */
+	tail = tail + (pos & (PAGE_CACHE_SIZE - 1));
+
+	PATH_LAST_POSITION(path)++;
+
+	key = *item_key;
+	set_cpu_key_k_type(&key, TYPE_DIRECT);
+	key.key_length = 4;
+	/* Insert tail as new direct item in the tree */
+	if (reiserfs_insert_item(th, path, &key, &s_ih, inode,
+				 tail ? tail : NULL) < 0) {
+		/* No disk memory. So we can not convert last unformatted node
+		   to the direct item.  In this case we used to adjust
+		   indirect items's ih_free_space. Now ih_free_space is not
+		   used, it would be ideal to write zeros to corresponding
+		   unformatted node. For now i_size is considered as guard for
+		   going out of file size */
+		kunmap(page);
+		return block_size - round_tail_len;
+	}
+	kunmap(page);
+
+	/* make sure to get the i_blocks changes from reiserfs_insert_item */
+	reiserfs_update_sd(th, inode);
+
+	// note: we have now the same as in above direct2indirect
+	// conversion: there are two keys which have matching first three
+	// key components. They only differ by the fouhth one.
+
+	/* We have inserted new direct item and must remove last
+	   unformatted node. */
+	*mode = M_CUT;
+
+	/* we store position of first direct item in the in-core inode */
+	/* mark_file_with_tail (inode, pos1 + 1); */
+	REISERFS_I(inode)->i_first_direct_byte = pos1 + 1;
+
+	return block_size - round_tail_len;
+}

kernel/fs/reiserfs/xattr_acl.c

@@ -0,0 +1,557 @@
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/posix_acl.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/errno.h>
+#include <linux/pagemap.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/reiserfs_xattr.h>
+#include <linux/reiserfs_acl.h>
+#include <asm/uaccess.h>
+
+static int reiserfs_set_acl(struct reiserfs_transaction_handle *th,
+			    struct inode *inode, int type,
+			    struct posix_acl *acl);
+
+static int
+xattr_set_acl(struct inode *inode, int type, const void *value, size_t size)
+{
+	struct posix_acl *acl;
+	int error, error2;
+	struct reiserfs_transaction_handle th;
+	size_t jcreate_blocks;
+	if (!reiserfs_posixacl(inode->i_sb))
+		return -EOPNOTSUPP;
+	if (!is_owner_or_cap(inode))
+		return -EPERM;
+
+	if (value) {
+		acl = posix_acl_from_xattr(value, size);
+		if (IS_ERR(acl)) {
+			return PTR_ERR(acl);
+		} else if (acl) {
+			error = posix_acl_valid(acl);
+			if (error)
+				goto release_and_out;
+		}
+	} else
+		acl = NULL;
+
+	/* Pessimism: We can't assume that anything from the xattr root up
+	 * has been created. */
+
+	jcreate_blocks = reiserfs_xattr_jcreate_nblocks(inode) +
+			 reiserfs_xattr_nblocks(inode, size) * 2;
+
+	reiserfs_write_lock(inode->i_sb);
+	error = journal_begin(&th, inode->i_sb, jcreate_blocks);
+	if (error == 0) {
+		error = reiserfs_set_acl(&th, inode, type, acl);
+		error2 = journal_end(&th, inode->i_sb, jcreate_blocks);
+		if (error2)
+			error = error2;
+	}
+	reiserfs_write_unlock(inode->i_sb);
+
+      release_and_out:
+	posix_acl_release(acl);
+	return error;
+}
+
+static int
+xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+{
+	struct posix_acl *acl;
+	int error;
+
+	if (!reiserfs_posixacl(inode->i_sb))
+		return -EOPNOTSUPP;
+
+	acl = reiserfs_get_acl(inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+	error = posix_acl_to_xattr(acl, buffer, size);
+	posix_acl_release(acl);
+
+	return error;
+}
+
+/*
+ * Convert from filesystem to in-memory representation.
+ */
+static struct posix_acl *posix_acl_from_disk(const void *value, size_t size)
+{
+	const char *end = (char *)value + size;
+	int n, count;
+	struct posix_acl *acl;
+
+	if (!value)
+		return NULL;
+	if (size < sizeof(reiserfs_acl_header))
+		return ERR_PTR(-EINVAL);
+	if (((reiserfs_acl_header *) value)->a_version !=
+	    cpu_to_le32(REISERFS_ACL_VERSION))
+		return ERR_PTR(-EINVAL);
+	value = (char *)value + sizeof(reiserfs_acl_header);
+	count = reiserfs_acl_count(size);
+	if (count < 0)
+		return ERR_PTR(-EINVAL);
+	if (count == 0)
+		return NULL;
+	acl = posix_acl_alloc(count, GFP_NOFS);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+	for (n = 0; n < count; n++) {
+		reiserfs_acl_entry *entry = (reiserfs_acl_entry *) value;
+		if ((char *)value + sizeof(reiserfs_acl_entry_short) > end)
+			goto fail;
+		acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag);
+		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+		switch (acl->a_entries[n].e_tag) {
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			value = (char *)value +
+			    sizeof(reiserfs_acl_entry_short);
+			acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
+			break;
+
+		case ACL_USER:
+		case ACL_GROUP:
+			value = (char *)value + sizeof(reiserfs_acl_entry);
+			if ((char *)value > end)
+				goto fail;
+			acl->a_entries[n].e_id = le32_to_cpu(entry->e_id);
+			break;
+
+		default:
+			goto fail;
+		}
+	}
+	if (value != end)
+		goto fail;
+	return acl;
+
+      fail:
+	posix_acl_release(acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Convert from in-memory to filesystem representation.
+ */
+static void *posix_acl_to_disk(const struct posix_acl *acl, size_t * size)
+{
+	reiserfs_acl_header *ext_acl;
+	char *e;
+	int n;
+
+	*size = reiserfs_acl_size(acl->a_count);
+	ext_acl = kmalloc(sizeof(reiserfs_acl_header) +
+						  acl->a_count *
+						  sizeof(reiserfs_acl_entry),
+						  GFP_NOFS);
+	if (!ext_acl)
+		return ERR_PTR(-ENOMEM);
+	ext_acl->a_version = cpu_to_le32(REISERFS_ACL_VERSION);
+	e = (char *)ext_acl + sizeof(reiserfs_acl_header);
+	for (n = 0; n < acl->a_count; n++) {
+		reiserfs_acl_entry *entry = (reiserfs_acl_entry *) e;
+		entry->e_tag = cpu_to_le16(acl->a_entries[n].e_tag);
+		entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
+		switch (acl->a_entries[n].e_tag) {
+		case ACL_USER:
+		case ACL_GROUP:
+			entry->e_id = cpu_to_le32(acl->a_entries[n].e_id);
+			e += sizeof(reiserfs_acl_entry);
+			break;
+
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			e += sizeof(reiserfs_acl_entry_short);
+			break;
+
+		default:
+			goto fail;
+		}
+	}
+	return (char *)ext_acl;
+
+      fail:
+	kfree(ext_acl);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Inode operation get_posix_acl().
+ *
+ * inode->i_mutex: down
+ * BKL held [before 2.5.x]
+ */
+struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
+{
+	char *name, *value;
+	struct posix_acl *acl;
+	int size;
+	int retval;
+
+	acl = get_cached_acl(inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+
+	size = reiserfs_xattr_get(inode, name, NULL, 0);
+	if (size < 0) {
+		if (size == -ENODATA || size == -ENOSYS) {
+			set_cached_acl(inode, type, NULL);
+			return NULL;
+		}
+		return ERR_PTR(size);
+	}
+
+	value = kmalloc(size, GFP_NOFS);
+	if (!value)
+		return ERR_PTR(-ENOMEM);
+
+	retval = reiserfs_xattr_get(inode, name, value, size);
+	if (retval == -ENODATA || retval == -ENOSYS) {
+		/* This shouldn't actually happen as it should have
+		   been caught above.. but just in case */
+		acl = NULL;
+	} else if (retval < 0) {
+		acl = ERR_PTR(retval);
+	} else {
+		acl = posix_acl_from_disk(value, retval);
+	}
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
+
+	kfree(value);
+	return acl;
+}
+
+/*
+ * Inode operation set_posix_acl().
+ *
+ * inode->i_mutex: down
+ * BKL held [before 2.5.x]
+ */
+static int
+reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
+		 int type, struct posix_acl *acl)
+{
+	char *name;
+	void *value = NULL;
+	size_t size = 0;
+	int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		if (acl) {
+			mode_t mode = inode->i_mode;
+			error = posix_acl_equiv_mode(acl, &mode);
+			if (error < 0)
+				return error;
+			else {
+				inode->i_mode = mode;
+				if (error == 0)
+					acl = NULL;
+			}
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		if (!S_ISDIR(inode->i_mode))
+			return acl ? -EACCES : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (acl) {
+		value = posix_acl_to_disk(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	error = reiserfs_xattr_set_handle(th, inode, name, value, size, 0);
+
+	/*
+	 * Ensure that the inode gets dirtied if we're only using
+	 * the mode bits and an old ACL didn't exist. We don't need
+	 * to check if the inode is hashed here since we won't get
+	 * called by reiserfs_inherit_default_acl().
+	 */
+	if (error == -ENODATA) {
+		error = 0;
+		if (type == ACL_TYPE_ACCESS) {
+			inode->i_ctime = CURRENT_TIME_SEC;
+			mark_inode_dirty(inode);
+		}
+	}
+
+	kfree(value);
+
+	if (!error)
+		set_cached_acl(inode, type, acl);
+
+	return error;
+}
+
+/* dir->i_mutex: locked,
+ * inode is new and not released into the wild yet */
+int
+reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
+			     struct inode *dir, struct dentry *dentry,
+			     struct inode *inode)
+{
+	struct posix_acl *acl;
+	int err = 0;
+
+	/* ACLs only get applied to files and directories */
+	if (S_ISLNK(inode->i_mode))
+		return 0;
+
+	/* ACLs can only be used on "new" objects, so if it's an old object
+	 * there is nothing to inherit from */
+	if (get_inode_sd_version(dir) == STAT_DATA_V1)
+		goto apply_umask;
+
+	/* Don't apply ACLs to objects in the .reiserfs_priv tree.. This
+	 * would be useless since permissions are ignored, and a pain because
+	 * it introduces locking cycles */
+	if (IS_PRIVATE(dir)) {
+		inode->i_flags |= S_PRIVATE;
+		goto apply_umask;
+	}
+
+	acl = reiserfs_get_acl(dir, ACL_TYPE_DEFAULT);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+
+	if (acl) {
+		struct posix_acl *acl_copy;
+		mode_t mode = inode->i_mode;
+		int need_acl;
+
+		/* Copy the default ACL to the default ACL of a new directory */
+		if (S_ISDIR(inode->i_mode)) {
+			err = reiserfs_set_acl(th, inode, ACL_TYPE_DEFAULT,
+					       acl);
+			if (err)
+				goto cleanup;
+		}
+
+		/* Now we reconcile the new ACL and the mode,
+		   potentially modifying both */
+		acl_copy = posix_acl_clone(acl, GFP_NOFS);
+		if (!acl_copy) {
+			err = -ENOMEM;
+			goto cleanup;
+		}
+
+		need_acl = posix_acl_create_masq(acl_copy, &mode);
+		if (need_acl >= 0) {
+			if (mode != inode->i_mode) {
+				inode->i_mode = mode;
+			}
+
+			/* If we need an ACL.. */
+			if (need_acl > 0) {
+				err = reiserfs_set_acl(th, inode,
+						       ACL_TYPE_ACCESS,
+						       acl_copy);
+				if (err)
+					goto cleanup_copy;
+			}
+		}
+	      cleanup_copy:
+		posix_acl_release(acl_copy);
+	      cleanup:
+		posix_acl_release(acl);
+	} else {
+	      apply_umask:
+		/* no ACL, apply umask */
+		inode->i_mode &= ~current_umask();
+	}
+
+	return err;
+}
+
+/* This is used to cache the default acl before a new object is created.
+ * The biggest reason for this is to get an idea of how many blocks will
+ * actually be required for the create operation if we must inherit an ACL.
+ * An ACL write can add up to 3 object creations and an additional file write
+ * so we'd prefer not to reserve that many blocks in the journal if we can.
+ * It also has the advantage of not loading the ACL with a transaction open,
+ * this may seem silly, but if the owner of the directory is doing the
+ * creation, the ACL may not be loaded since the permissions wouldn't require
+ * it.
+ * We return the number of blocks required for the transaction.
+ */
+int reiserfs_cache_default_acl(struct inode *inode)
+{
+	struct posix_acl *acl;
+	int nblocks = 0;
+
+	if (IS_PRIVATE(inode))
+		return 0;
+
+	acl = reiserfs_get_acl(inode, ACL_TYPE_DEFAULT);
+
+	if (acl && !IS_ERR(acl)) {
+		int size = reiserfs_acl_size(acl->a_count);
+
+		/* Other xattrs can be created during inode creation. We don't
+		 * want to claim too many blocks, so we check to see if we
+		 * we need to create the tree to the xattrs, and then we
+		 * just want two files. */
+		nblocks = reiserfs_xattr_jcreate_nblocks(inode);
+		nblocks += JOURNAL_BLOCKS_PER_OBJECT(inode->i_sb);
+
+		REISERFS_I(inode)->i_flags |= i_has_xattr_dir;
+
+		/* We need to account for writes + bitmaps for two files */
+		nblocks += reiserfs_xattr_nblocks(inode, size) * 4;
+		posix_acl_release(acl);
+	}
+
+	return nblocks;
+}
+
+int reiserfs_acl_chmod(struct inode *inode)
+{
+	struct posix_acl *acl, *clone;
+	int error;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (get_inode_sd_version(inode) == STAT_DATA_V1 ||
+	    !reiserfs_posixacl(inode->i_sb)) {
+		return 0;
+	}
+
+	acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
+	if (!acl)
+		return 0;
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	clone = posix_acl_clone(acl, GFP_NOFS);
+	posix_acl_release(acl);
+	if (!clone)
+		return -ENOMEM;
+	error = posix_acl_chmod_masq(clone, inode->i_mode);
+	if (!error) {
+		struct reiserfs_transaction_handle th;
+		size_t size = reiserfs_xattr_nblocks(inode,
+					     reiserfs_acl_size(clone->a_count));
+		reiserfs_write_lock(inode->i_sb);
+		error = journal_begin(&th, inode->i_sb, size * 2);
+		if (!error) {
+			int error2;
+			error = reiserfs_set_acl(&th, inode, ACL_TYPE_ACCESS,
+						 clone);
+			error2 = journal_end(&th, inode->i_sb, size * 2);
+			if (error2)
+				error = error2;
+		}
+		reiserfs_write_unlock(inode->i_sb);
+	}
+	posix_acl_release(clone);
+	return error;
+}
+
+static int
+posix_acl_access_get(struct inode *inode, const char *name,
+		     void *buffer, size_t size)
+{
+	if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS) - 1)
+		return -EINVAL;
+	return xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
+}
+
+static int
+posix_acl_access_set(struct inode *inode, const char *name,
+		     const void *value, size_t size, int flags)
+{
+	if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS) - 1)
+		return -EINVAL;
+	return xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
+}
+
+static size_t posix_acl_access_list(struct inode *inode, char *list,
+				    size_t list_size, const char *name,
+				    size_t name_len)
+{
+	const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
+	if (!reiserfs_posixacl(inode->i_sb))
+		return 0;
+	if (list && size <= list_size)
+		memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
+	return size;
+}
+
+struct xattr_handler reiserfs_posix_acl_access_handler = {
+	.prefix = POSIX_ACL_XATTR_ACCESS,
+	.get = posix_acl_access_get,
+	.set = posix_acl_access_set,
+	.list = posix_acl_access_list,
+};
+
+static int
+posix_acl_default_get(struct inode *inode, const char *name,
+		      void *buffer, size_t size)
+{
+	if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT) - 1)
+		return -EINVAL;
+	return xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
+}
+
+static int
+posix_acl_default_set(struct inode *inode, const char *name,
+		      const void *value, size_t size, int flags)
+{
+	if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT) - 1)
+		return -EINVAL;
+	return xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
+}
+
+static size_t posix_acl_default_list(struct inode *inode, char *list,
+				     size_t list_size, const char *name,
+				     size_t name_len)
+{
+	const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
+	if (!reiserfs_posixacl(inode->i_sb))
+		return 0;
+	if (list && size <= list_size)
+		memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
+	return size;
+}
+
+struct xattr_handler reiserfs_posix_acl_default_handler = {
+	.prefix = POSIX_ACL_XATTR_DEFAULT,
+	.get = posix_acl_default_get,
+	.set = posix_acl_default_set,
+	.list = posix_acl_default_list,
+};

kernel/fs/reiserfs/xattr_security.c

@@ -0,0 +1,117 @@
+#include <linux/reiserfs_fs.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/xattr.h>
+#include <linux/reiserfs_xattr.h>
+#include <linux/security.h>
+#include <asm/uaccess.h>
+
+static int
+security_get(struct inode *inode, const char *name, void *buffer, size_t size)
+{
+	if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
+		return -EINVAL;
+
+	if (IS_PRIVATE(inode))
+		return -EPERM;
+
+	return reiserfs_xattr_get(inode, name, buffer, size);
+}
+
+static int
+security_set(struct inode *inode, const char *name, const void *buffer,
+	     size_t size, int flags)
+{
+	if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
+		return -EINVAL;
+
+	if (IS_PRIVATE(inode))
+		return -EPERM;
+
+	return reiserfs_xattr_set(inode, name, buffer, size, flags);
+}
+
+static size_t security_list(struct inode *inode, char *list, size_t list_len,
+			    const char *name, size_t namelen)
+{
+	const size_t len = namelen + 1;
+
+	if (IS_PRIVATE(inode))
+		return 0;
+
+	if (list && len <= list_len) {
+		memcpy(list, name, namelen);
+		list[namelen] = '\0';
+	}
+
+	return len;
+}
+
+/* Initializes the security context for a new inode and returns the number
+ * of blocks needed for the transaction. If successful, reiserfs_security
+ * must be released using reiserfs_security_free when the caller is done. */
+int reiserfs_security_init(struct inode *dir, struct inode *inode,
+			   struct reiserfs_security_handle *sec)
+{
+	int blocks = 0;
+	int error;
+
+	sec->name = NULL;
+
+	/* Don't add selinux attributes on xattrs - they'll never get used */
+	if (IS_PRIVATE(dir))
+		return 0;
+
+	error = security_inode_init_security(inode, dir, &sec->name,
+					     &sec->value, &sec->length);
+	if (error) {
+		if (error == -EOPNOTSUPP)
+			error = 0;
+
+		sec->name = NULL;
+		sec->value = NULL;
+		sec->length = 0;
+		return error;
+	}
+
+	if (sec->length && reiserfs_xattrs_initialized(inode->i_sb)) {
+		blocks = reiserfs_xattr_jcreate_nblocks(inode) +
+			 reiserfs_xattr_nblocks(inode, sec->length);
+		/* We don't want to count the directories twice if we have
+		 * a default ACL. */
+		REISERFS_I(inode)->i_flags |= i_has_xattr_dir;
+	}
+	return blocks;
+}
+
+int reiserfs_security_write(struct reiserfs_transaction_handle *th,
+			    struct inode *inode,
+			    struct reiserfs_security_handle *sec)
+{
+	int error;
+	if (strlen(sec->name) < sizeof(XATTR_SECURITY_PREFIX))
+		return -EINVAL;
+
+	error = reiserfs_xattr_set_handle(th, inode, sec->name, sec->value,
+					  sec->length, XATTR_CREATE);
+	if (error == -ENODATA || error == -EOPNOTSUPP)
+		error = 0;
+
+	return error;
+}
+
+void reiserfs_security_free(struct reiserfs_security_handle *sec)
+{
+	kfree(sec->name);
+	kfree(sec->value);
+	sec->name = NULL;
+	sec->value = NULL;
+}
+
+struct xattr_handler reiserfs_xattr_security_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.get = security_get,
+	.set = security_set,
+	.list = security_list,
+};

kernel/fs/reiserfs/xattr_trusted.c

@@ -0,0 +1,55 @@
+#include <linux/reiserfs_fs.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/xattr.h>
+#include <linux/reiserfs_xattr.h>
+#include <asm/uaccess.h>
+
+static int
+trusted_get(struct inode *inode, const char *name, void *buffer, size_t size)
+{
+	if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
+		return -EPERM;
+
+	return reiserfs_xattr_get(inode, name, buffer, size);
+}
+
+static int
+trusted_set(struct inode *inode, const char *name, const void *buffer,
+	    size_t size, int flags)
+{
+	if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
+		return -EPERM;
+
+	return reiserfs_xattr_set(inode, name, buffer, size, flags);
+}
+
+static size_t trusted_list(struct inode *inode, char *list, size_t list_size,
+			   const char *name, size_t name_len)
+{
+	const size_t len = name_len + 1;
+
+	if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
+		return 0;
+
+	if (list && len <= list_size) {
+		memcpy(list, name, name_len);
+		list[name_len] = '\0';
+	}
+	return len;
+}
+
+struct xattr_handler reiserfs_xattr_trusted_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.get = trusted_get,
+	.set = trusted_set,
+	.list = trusted_list,
+};

kernel/fs/reiserfs/xattr_user.c

@@ -0,0 +1,51 @@
+#include <linux/reiserfs_fs.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/xattr.h>
+#include <linux/reiserfs_xattr.h>
+#include <asm/uaccess.h>
+
+static int
+user_get(struct inode *inode, const char *name, void *buffer, size_t size)
+{
+
+	if (strlen(name) < sizeof(XATTR_USER_PREFIX))
+		return -EINVAL;
+	if (!reiserfs_xattrs_user(inode->i_sb))
+		return -EOPNOTSUPP;
+	return reiserfs_xattr_get(inode, name, buffer, size);
+}
+
+static int
+user_set(struct inode *inode, const char *name, const void *buffer,
+	 size_t size, int flags)
+{
+	if (strlen(name) < sizeof(XATTR_USER_PREFIX))
+		return -EINVAL;
+
+	if (!reiserfs_xattrs_user(inode->i_sb))
+		return -EOPNOTSUPP;
+	return reiserfs_xattr_set(inode, name, buffer, size, flags);
+}
+
+static size_t user_list(struct inode *inode, char *list, size_t list_size,
+			const char *name, size_t name_len)
+{
+	const size_t len = name_len + 1;
+
+	if (!reiserfs_xattrs_user(inode->i_sb))
+		return 0;
+	if (list && len <= list_size) {
+		memcpy(list, name, name_len);
+		list[name_len] = '\0';
+	}
+	return len;
+}
+
+struct xattr_handler reiserfs_xattr_user_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = user_get,
+	.set = user_set,
+	.list = user_list,
+};