--- /dev/null 2007-03-13 19:15:28.862769062 +0100
+++ linux-2.6.21logfs/fs/logfs/dir.c 2007-06-03 19:54:55.000000000 +0200
@@ -0,0 +1,704 @@
+/*
+ * fs/logfs/dir.c - directory-related code
+ *
+ * As should be obvious for Linux kernel code, license is GPLv2
+ *
+ * Copyright (c) 2005-2007 Joern Engel
+ */
+#include "logfs.h"
+
+
+/*
+ * Atomic dir operations
+ *
+ * Directory operations are by default not atomic. Dentries and Inodes are
+ * created/removed/altered in seperate operations. Therefore we need to do
+ * a small amount of journaling.
+ *
+ * Create, link, mkdir, mknod and symlink all share the same function to do
+ * the work: __logfs_create. This function works in two atomic steps:
+ * 1. allocate inode (remember in journal)
+ * 2. allocate dentry (clear journal)
+ *
+ * As we can only get interrupted between the two, we the inode we just
+ * created is simply stored in the anchor. On next mount, if we were
+ * interrupted, we delete the inode. From a users point of view the
+ * operation never happened.
+ *
+ * Unlink and rmdir also share the same function: unlink. Again, this
+ * function works in two atomic steps
+ * 1. remove dentry (remember inode in journal)
+ * 2. unlink inode (clear journal)
+ *
+ * And again, on the next mount, if we were interrupted, we delete the inode.
+ * From a users point of view the operation succeeded.
+ *
+ * Rename is the real pain to deal with, harder than all the other methods
+ * combined. Depending on the circumstances we can run into three cases.
+ * A "target rename" where the target dentry already existed, a "local
+ * rename" where both parent directories are identical or a "cross-directory
+ * rename" in the remaining case.
+ *
+ * Local rename is atomic, as the old dentry is simply rewritten with a new
+ * name.
+ *
+ * Cross-directory rename works in two steps, similar to __logfs_create and
+ * logfs_unlink:
+ * 1. Write new dentry (remember old dentry in journal)
+ * 2. Remove old dentry (clear journal)
+ *
+ * Here we remember a dentry instead of an inode. On next mount, if we were
+ * interrupted, we delete the dentry. From a users point of view, the
+ * operation succeeded.
+ *
+ * Target rename works in three atomic steps:
+ * 1. Attach old inode to new dentry (remember old dentry and new inode)
+ * 2. Remove old dentry (still remember the new inode)
+ * 3. Remove victim inode
+ *
+ * Here we remember both an inode an a dentry. If we get interrupted
+ * between steps 1 and 2, we delete both the dentry and the inode. If
+ * we get interrupted between steps 2 and 3, we delete just the inode.
+ * In either case, the remaining objects are deleted on next mount. From
+ * a users point of view, the operation succeeded.
+ */
+
+typedef int (*dir_callback)(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, loff_t pos);
+
+static inline void logfs_inc_count(struct inode *inode)
+{
+ inode->i_nlink++;
+ mark_inode_dirty_sync(inode);
+}
+
+static inline void logfs_dec_count(struct inode *inode)
+{
+ inode->i_nlink--;
+ mark_inode_dirty_sync(inode);
+}
+
+static int read_dir(struct inode *dir, struct logfs_disk_dentry *dd, loff_t pos)
+{
+ return logfs_inode_read(dir, dd, sizeof(*dd), pos);
+}
+
+static int write_dir(struct inode *dir, struct logfs_disk_dentry *dd,
+ loff_t pos)
+{
+ return logfs_inode_write(dir, dd, sizeof(*dd), pos, 1);
+}
+
+static s64 dir_seek_data(struct inode *inode, s64 pos)
+{
+ s64 new_pos = logfs_seek_data(inode, pos);
+
+ return max(pos, new_pos - 1);
+}
+
+static int __logfs_dir_walk(struct inode *dir, struct dentry *dentry,
+ dir_callback handler, struct logfs_disk_dentry *dd, loff_t *pos)
+{
+ struct qstr *name = dentry ? &dentry->d_name : NULL;
+ int ret;
+
+ for (; ; (*pos)++) {
+ ret = read_dir(dir, dd, *pos);
+ if (ret == -EOF)
+ return 0;
+ if (ret == -ENODATA) {
+ /* deleted dentry */
+ *pos = dir_seek_data(dir, *pos);
+ continue;
+ }
+ if (ret)
+ return ret;
+ BUG_ON(dd->namelen == 0);
+
+ if (name) {
+ if (name->len != be16_to_cpu(dd->namelen))
+ continue;
+ if (memcmp(name->name, dd->name, name->len))
+ continue;
+ }
+
+ return handler(dir, dentry, dd, *pos);
+ }
+ return ret;
+}
+
+static int logfs_dir_walk(struct inode *dir, struct dentry *dentry,
+ dir_callback handler)
+{
+ struct logfs_disk_dentry dd;
+ loff_t pos = 0;
+
+ return __logfs_dir_walk(dir, dentry, handler, &dd, &pos);
+}
+
+static int logfs_lookup_handler(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, loff_t pos)
+{
+ struct inode *inode;
+
+ inode = iget(dir->i_sb, be64_to_cpu(dd->ino));
+ if (!inode)
+ return -EIO;
+ return PTR_ERR(d_splice_alias(inode, dentry));
+}
+
+static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ return ERR_PTR(logfs_dir_walk(dir, dentry, logfs_lookup_handler));
+}
+
+/* unlink currently only makes the name length zero */
+static int logfs_unlink_handler(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, loff_t pos)
+{
+ return logfs_delete(dir, pos);
+}
+
+static int logfs_remove_inode(struct inode *inode)
+{
+ int ret;
+
+ inode->i_nlink--;
+ if (inode->i_mode & S_IFDIR)
+ inode->i_nlink--;
+ ret = __logfs_write_inode(inode, 1);
+ LOGFS_BUG_ON(ret, inode->i_sb);
+ return ret;
+}
+
+/*
+ * Re-enabled the one-line goto. The "if (!ret)" confused the hell out of
+ * me - it looks feels and smells like error handling code, not like the
+ * good code. Having to check and recheck twice before I can trust this
+ * is the opposite of well-readable code.
+ */
+static int logfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ struct logfs_super *super = logfs_super(dir->i_sb);
+ struct inode *inode = dentry->d_inode;
+ int ret;
+
+ mutex_lock(&super->s_victim_mutex);
+ super->s_victim_ino = inode->i_ino;
+
+ if (inode->i_mode & S_IFDIR)
+ dir->i_nlink--;
+ inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ ret = logfs_dir_walk(dir, dentry, logfs_unlink_handler);
+ super->s_victim_ino = 0;
+ if (ret) {
+ printk(KERN_ERR"LOGFS: unable to delete inode\n");
+ if (inode->i_mode & S_IFDIR)
+ logfs_inc_count(dir);
+ goto out;
+ }
+
+ ret = logfs_remove_inode(inode);
+out:
+ mutex_unlock(&super->s_victim_mutex);
+ return ret;
+}
+
+static int logfs_empty_handler(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, loff_t pos)
+{
+ return -ENOTEMPTY;
+}
+
+static inline int logfs_empty_dir(struct inode *dir)
+{
+ return logfs_dir_walk(dir, NULL, logfs_empty_handler) == 0;
+}
+
+static int logfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+
+ if (!logfs_empty_dir(inode))
+ return -ENOTEMPTY;
+
+ return logfs_unlink(dir, dentry);
+}
+
+/* FIXME: readdir currently has it's own dir_walk code. I don't see a good
+ * way to combine the two copies */
+#define IMPLICIT_NODES 2
+static int __logfs_readdir(struct file *file, void *buf, filldir_t filldir)
+{
+ struct logfs_disk_dentry dd;
+ struct inode *dir = file->f_dentry->d_inode;
+ loff_t pos = file->f_pos - IMPLICIT_NODES;
+ int err;
+
+ BUG_ON(pos<0);
+ for (;; pos++) {
+ err = read_dir(dir, &dd, pos);
+ if (err == -EOF)
+ break;
+ if (err == -ENODATA) {
+ /* deleted dentry */
+ pos = dir_seek_data(dir, pos);
+ continue;
+ }
+ if (err)
+ return err;
+ BUG_ON(dd.namelen == 0);
+
+ if (filldir(buf, dd.name, be16_to_cpu(dd.namelen), pos,
+ be64_to_cpu(dd.ino), dd.type))
+ break;
+ }
+
+ file->f_pos = pos + IMPLICIT_NODES;
+ return 0;
+}
+
+static int logfs_readdir(struct file *file, void *buf, filldir_t filldir)
+{
+ struct inode *inode = file->f_dentry->d_inode;
+ ino_t pino = parent_ino(file->f_dentry);
+ int err;
+
+ if (file->f_pos < 0)
+ return -EINVAL;
+
+ if (file->f_pos == 0) {
+ if (filldir(buf, ".", 1, 1, inode->i_ino, DT_DIR) < 0)
+ return 0;
+ file->f_pos++;
+ }
+ if (file->f_pos == 1) {
+ if (filldir(buf, "..", 2, 2, pino, DT_DIR) < 0)
+ return 0;
+ file->f_pos++;
+ }
+
+ err = __logfs_readdir(file, buf, filldir);
+ return err;
+}
+
+static inline loff_t file_end(struct inode *inode)
+{
+ return (i_size_read(inode) + inode->i_sb->s_blocksize - 1)
+ >> inode->i_sb->s_blocksize_bits;
+}
+
+static void logfs_set_name(struct logfs_disk_dentry *dd, struct qstr *name)
+{
+ BUG_ON(name->len > LOGFS_MAX_NAMELEN);
+ dd->namelen = cpu_to_be16(name->len);
+ memcpy(dd->name, name->name, name->len);
+}
+
+static int logfs_write_dir(struct inode *dir, struct dentry *dentry,
+ struct inode *inode)
+{
+ struct logfs_disk_dentry dd;
+ int err;
+
+ memset(&dd, 0, sizeof(dd));
+ dd.ino = cpu_to_be64(inode->i_ino);
+ dd.type = logfs_type(inode);
+ logfs_set_name(&dd, &dentry->d_name);
+
+ dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ /*
+ * FIXME: the file size should actually get aligned when writing,
+ * not when reading.
+ */
+ err = write_dir(dir, &dd, file_end(dir));
+ if (err)
+ return err;
+ d_instantiate(dentry, inode);
+ return 0;
+}
+
+static int __logfs_create(struct inode *dir, struct dentry *dentry,
+ struct inode *inode, const char *dest, long destlen)
+{
+ struct logfs_super *super = logfs_super(dir->i_sb);
+ struct logfs_inode *li = logfs_inode(inode);
+ int ret;
+
+ mutex_lock(&super->s_victim_mutex);
+ super->s_victim_ino = inode->i_ino;
+ if (inode->i_mode & S_IFDIR)
+ inode->i_nlink++;
+
+ if (dest) {
+ /* symlink */
+ ret = logfs_inode_write(inode, dest, destlen, 0, 1);
+ } else {
+ /* creat/mkdir/mknod */
+ ret = __logfs_write_inode(inode, 1);
+ }
+ super->s_victim_ino = 0;
+ if (ret) {
+ if (!dest)
+ li->li_flags |= LOGFS_IF_STILLBORN;
+ /* FIXME: truncate symlink */
+ inode->i_nlink--;
+ iput(inode);
+ goto out;
+ }
+
+ if (inode->i_mode & S_IFDIR)
+ dir->i_nlink++;
+ ret = logfs_write_dir(dir, dentry, inode);
+
+ if (ret) {
+ if (inode->i_mode & S_IFDIR)
+ dir->i_nlink--;
+ logfs_remove_inode(inode);
+ iput(inode);
+ }
+out:
+ mutex_unlock(&super->s_victim_mutex);
+ return ret;
+}
+
+static int logfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+ struct inode *inode;
+
+ if (dir->i_nlink >= LOGFS_LINK_MAX)
+ return -EMLINK;
+
+ /*
+ * FIXME: why do we have to fill in S_IFDIR, while the mode is
+ * correct for mknod, creat, etc.? Smells like the vfs *should*
+ * do it for us but for some reason fails to do so.
+ */
+ inode = logfs_new_inode(dir, S_IFDIR | mode);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ inode->i_op = &logfs_dir_iops;
+ inode->i_fop = &logfs_dir_fops;
+
+ return __logfs_create(dir, dentry, inode, NULL, 0);
+}
+
+static int logfs_create(struct inode *dir, struct dentry *dentry, int mode,
+ struct nameidata *nd)
+{
+ struct inode *inode;
+
+ inode = logfs_new_inode(dir, mode);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ inode->i_op = &logfs_reg_iops;
+ inode->i_fop = &logfs_reg_fops;
+ inode->i_mapping->a_ops = &logfs_reg_aops;
+
+ return __logfs_create(dir, dentry, inode, NULL, 0);
+}
+
+static int logfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
+ dev_t rdev)
+{
+ struct inode *inode;
+
+ BUG_ON(dentry->d_name.len > LOGFS_MAX_NAMELEN);
+
+ inode = logfs_new_inode(dir, mode);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ init_special_inode(inode, mode, rdev);
+
+ return __logfs_create(dir, dentry, inode, NULL, 0);
+}
+
+static const struct inode_operations logfs_symlink_iops = {
+ .readlink = generic_readlink,
+ .follow_link = page_follow_link_light,
+};
+
+static int logfs_symlink(struct inode *dir, struct dentry *dentry,
+ const char *target)
+{
+ struct inode *inode;
+ size_t destlen = strlen(target) + 1;
+
+ if (destlen > dir->i_sb->s_blocksize)
+ return -ENAMETOOLONG;
+
+ inode = logfs_new_inode(dir, S_IFLNK | S_IRWXUGO);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ inode->i_op = &logfs_symlink_iops;
+ inode->i_mapping->a_ops = &logfs_reg_aops;
+
+ return __logfs_create(dir, dentry, inode, target, destlen);
+}
+
+static int logfs_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+ return generic_permission(inode, mask, NULL);
+}
+
+static int logfs_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *dentry)
+{
+ struct inode *inode = old_dentry->d_inode;
+
+ if (inode->i_nlink >= LOGFS_LINK_MAX)
+ return -EMLINK;
+
+ inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ atomic_inc(&inode->i_count);
+ logfs_inc_count(inode);
+
+ return __logfs_create(dir, dentry, inode, NULL, 0);
+}
+
+static int logfs_nop_handler(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, loff_t pos)
+{
+ return 0;
+}
+
+static inline int logfs_get_dd(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, loff_t *pos)
+{
+ *pos = 0;
+ return __logfs_dir_walk(dir, dentry, logfs_nop_handler, dd, pos);
+}
+
+/* Easiest case, a local rename and the target doesn't exist. Just change
+ * the name in the old dd.
+ */
+static int logfs_rename_local(struct inode *dir, struct dentry *old_dentry,
+ struct dentry *new_dentry)
+{
+ struct logfs_disk_dentry dd;
+ loff_t pos;
+ int err;
+
+ err = logfs_get_dd(dir, old_dentry, &dd, &pos);
+ if (err)
+ return err;
+
+ logfs_set_name(&dd, &new_dentry->d_name);
+ return write_dir(dir, &dd, pos);
+}
+
+static int logfs_delete_dd(struct inode *dir, struct logfs_disk_dentry *dd,
+ loff_t pos)
+{
+ int err;
+
+ err = read_dir(dir, dd, pos);
+
+ /*
+ * Getting called with pos somewhere beyond eof is either a goofup
+ * within this file or means someone maliciously edited the
+ * (crc-protected) journal.
+ */
+ LOGFS_BUG_ON(err == -EOF, dir->i_sb);
+ if (err)
+ return err;
+
+ dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ if (dd->type == DT_DIR)
+ dir->i_nlink--;
+ return logfs_delete(dir, pos);
+}
+
+/*
+ * Cross-directory rename, target does not exist. Just a little nasty.
+ * Create a new dentry in the target dir, then remove the old dentry,
+ * all the while taking care to remember our operation in the journal.
+ */
+static int logfs_rename_cross(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ struct logfs_super *super = logfs_super(old_dir->i_sb);
+ struct logfs_disk_dentry dd;
+ loff_t pos;
+ int err;
+
+ /* 1. locate source dd */
+ err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
+ if (err)
+ return err;
+ mutex_lock(&super->s_rename_mutex);
+ super->s_rename_dir = old_dir->i_ino;
+ super->s_rename_pos = pos;
+
+ /*
+ * FIXME: this cannot be right but it does "fix" a bug of i_count
+ * dropping too low. Needs more thought.
+ */
+ atomic_inc(&old_dentry->d_inode->i_count);
+
+ /* 2. write target dd */
+ if (dd.type == DT_DIR)
+ new_dir->i_nlink++;
+ err = logfs_write_dir(new_dir, new_dentry, old_dentry->d_inode);
+ super->s_rename_dir = 0;
+ super->s_rename_pos = 0;
+ if (err)
+ goto out;
+
+ /* 3. remove source dd */
+ err = logfs_delete_dd(old_dir, &dd, pos);
+ LOGFS_BUG_ON(err, old_dir->i_sb);
+out:
+ mutex_unlock(&super->s_rename_mutex);
+ return err;
+}
+
+static int logfs_replace_inode(struct inode *dir, struct dentry *dentry,
+ struct logfs_disk_dentry *dd, struct inode *inode)
+{
+ loff_t pos;
+ int err;
+
+ err = logfs_get_dd(dir, dentry, dd, &pos);
+ if (err)
+ return err;
+ dd->ino = cpu_to_be64(inode->i_ino);
+ dd->type = logfs_type(inode);
+
+ return write_dir(dir, dd, pos);
+}
+
+/* Target dentry exists - the worst case. We need to attach the source
+ * inode to the target dentry, then remove the orphaned target inode and
+ * source dentry.
+ */
+static int logfs_rename_target(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ struct logfs_super *super = logfs_super(old_dir->i_sb);
+ struct inode *old_inode = old_dentry->d_inode;
+ struct inode *new_inode = new_dentry->d_inode;
+ int isdir = S_ISDIR(old_inode->i_mode);
+ struct logfs_disk_dentry dd;
+ loff_t pos;
+ int err;
+
+ BUG_ON(isdir != S_ISDIR(new_inode->i_mode));
+ if (isdir) {
+ if (!logfs_empty_dir(new_inode))
+ return -ENOTEMPTY;
+ }
+
+ /* 1. locate source dd */
+ err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
+ if (err)
+ return err;
+
+ mutex_lock(&super->s_rename_mutex);
+ mutex_lock(&super->s_victim_mutex);
+ super->s_rename_dir = old_dir->i_ino;
+ super->s_rename_pos = pos;
+ super->s_victim_ino = new_inode->i_ino;
+
+ /* 2. attach source inode to target dd */
+ err = logfs_replace_inode(new_dir, new_dentry, &dd, old_inode);
+ super->s_rename_dir = 0;
+ super->s_rename_pos = 0;
+ if (err) {
+ super->s_victim_ino = 0;
+ goto out;
+ }
+
+ /* 3. remove source dd */
+ err = logfs_delete_dd(old_dir, &dd, pos);
+ LOGFS_BUG_ON(err, old_dir->i_sb);
+
+ /* 4. remove target inode */
+ super->s_victim_ino = 0;
+ err = logfs_remove_inode(new_inode);
+
+out:
+ mutex_unlock(&super->s_victim_mutex);
+ mutex_unlock(&super->s_rename_mutex);
+ return err;
+}
+
+static int logfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ if (new_dentry->d_inode)
+ return logfs_rename_target(old_dir, old_dentry, new_dir, new_dentry);
+ else if (old_dir == new_dir)
+ return logfs_rename_local(old_dir, old_dentry, new_dentry);
+ return logfs_rename_cross(old_dir, old_dentry, new_dir, new_dentry);
+}
+
+/* No locking done here, as this is called before .get_sb() returns. */
+int logfs_replay_journal(struct super_block *sb)
+{
+ struct logfs_super *super = logfs_super(sb);
+ struct logfs_disk_dentry dd;
+ struct inode *inode;
+ u64 ino, pos;
+ int err;
+
+ if (super->s_victim_ino) {
+ /* delete victim inode */
+ ino = super->s_victim_ino;
+ inode = iget(sb, ino);
+ if (!inode)
+ goto fail;
+
+ super->s_victim_ino = 0;
+ err = logfs_remove_inode(inode);
+ iput(inode);
+ if (err) {
+ super->s_victim_ino = ino;
+ goto fail;
+ }
+ }
+ if (super->s_rename_dir) {
+ /* delete old dd from rename */
+ ino = super->s_rename_dir;
+ pos = super->s_rename_pos;
+ inode = iget(sb, ino);
+ if (!inode)
+ goto fail;
+
+ super->s_rename_dir = 0;
+ super->s_rename_pos = 0;
+ err = logfs_delete_dd(inode, &dd, pos);
+ iput(inode);
+ if (err) {
+ super->s_rename_dir = ino;
+ super->s_rename_pos = pos;
+ goto fail;
+ }
+ }
+ return 0;
+fail:
+ LOGFS_BUG(sb);
+ return -EIO;
+}
+
+const struct inode_operations logfs_dir_iops = {
+ .create = logfs_create,
+ .link = logfs_link,
+ .lookup = logfs_lookup,
+ .mkdir = logfs_mkdir,
+ .mknod = logfs_mknod,
+ .rename = logfs_rename,
+ .rmdir = logfs_rmdir,
+ .permission = logfs_permission,
+ .symlink = logfs_symlink,
+ .unlink = logfs_unlink,
+};
+const struct file_operations logfs_dir_fops = {
+ .readdir = logfs_readdir,
+ .read = generic_read_dir,
+};
-
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
