+/*
+ * Copyright (C) 2007 Oracle. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
+#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/smp_lock.h>
#include <linux/backing-dev.h>
+#include <linux/mount.h>
+#include <linux/mpage.h>
+#include <linux/swap.h>
+#include <linux/writeback.h>
+#include <linux/statfs.h>
+#include <linux/compat.h>
+#include <linux/parser.h>
+#include <linux/ctype.h>
+#include <linux/namei.h>
+#include <linux/miscdevice.h>
+#include <linux/magic.h>
+#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
+#include "transaction.h"
+#include "btrfs_inode.h"
+#include "ioctl.h"
+#include "print-tree.h"
+#include "xattr.h"
+#include "volumes.h"
+#include "version.h"
+#include "export.h"
+#include "compression.h"
-#define BTRFS_SUPER_MAGIC 0x9123682E
-static struct inode_operations btrfs_dir_inode_operations;
static struct super_operations btrfs_super_ops;
-static struct file_operations btrfs_dir_file_operations;
-#if 0
-/* some random number */
+static void btrfs_put_super(struct super_block *sb)
+{
+ struct btrfs_root *root = btrfs_sb(sb);
+ int ret;
-static struct super_operations ramfs_ops;
+ ret = close_ctree(root);
+ sb->s_fs_info = NULL;
+}
-static struct backing_dev_info ramfs_backing_dev_info = {
- .ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK |
- BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
- BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
+enum {
+ Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow,
+ Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier,
+ Opt_ssd, Opt_thread_pool, Opt_noacl, Opt_compress, Opt_notreelog,
+ Opt_ratio, Opt_flushoncommit, Opt_err,
};
-struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
+static match_table_t tokens = {
+ {Opt_degraded, "degraded"},
+ {Opt_subvol, "subvol=%s"},
+ {Opt_device, "device=%s"},
+ {Opt_nodatasum, "nodatasum"},
+ {Opt_nodatacow, "nodatacow"},
+ {Opt_nobarrier, "nobarrier"},
+ {Opt_max_extent, "max_extent=%s"},
+ {Opt_max_inline, "max_inline=%s"},
+ {Opt_alloc_start, "alloc_start=%s"},
+ {Opt_thread_pool, "thread_pool=%d"},
+ {Opt_compress, "compress"},
+ {Opt_ssd, "ssd"},
+ {Opt_noacl, "noacl"},
+ {Opt_notreelog, "notreelog"},
+ {Opt_flushoncommit, "flushoncommit"},
+ {Opt_ratio, "metadata_ratio=%d"},
+ {Opt_err, NULL},
+};
+
+u64 btrfs_parse_size(char *str)
{
- struct inode * inode = new_inode(sb);
-
- if (inode) {
- inode->i_mode = mode;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
- inode->i_blocks = 0;
- inode->i_mapping->a_ops = &ramfs_aops;
- inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- switch (mode & S_IFMT) {
- default:
- init_special_inode(inode, mode, dev);
+ u64 res;
+ int mult = 1;
+ char *end;
+ char last;
+
+ res = simple_strtoul(str, &end, 10);
+
+ last = end[0];
+ if (isalpha(last)) {
+ last = tolower(last);
+ switch (last) {
+ case 'g':
+ mult *= 1024;
+ case 'm':
+ mult *= 1024;
+ case 'k':
+ mult *= 1024;
+ }
+ res = res * mult;
+ }
+ return res;
+}
+
+/*
+ * Regular mount options parser. Everything that is needed only when
+ * reading in a new superblock is parsed here.
+ */
+int btrfs_parse_options(struct btrfs_root *root, char *options)
+{
+ struct btrfs_fs_info *info = root->fs_info;
+ substring_t args[MAX_OPT_ARGS];
+ char *p, *num;
+ int intarg;
+
+ if (!options)
+ return 0;
+
+ /*
+ * strsep changes the string, duplicate it because parse_options
+ * gets called twice
+ */
+ options = kstrdup(options, GFP_NOFS);
+ if (!options)
+ return -ENOMEM;
+
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_degraded:
+ printk(KERN_INFO "btrfs: allowing degraded mounts\n");
+ btrfs_set_opt(info->mount_opt, DEGRADED);
break;
- case S_IFREG:
- inode->i_op = &ramfs_file_inode_operations;
- inode->i_fop = &ramfs_file_operations;
+ case Opt_subvol:
+ case Opt_device:
+ /*
+ * These are parsed by btrfs_parse_early_options
+ * and can be happily ignored here.
+ */
break;
- case S_IFDIR:
- inode->i_op = &ramfs_dir_inode_operations;
- inode->i_fop = &simple_dir_operations;
-
- /* directory inodes start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
+ case Opt_nodatasum:
+ printk(KERN_INFO "btrfs: setting nodatacsum\n");
+ btrfs_set_opt(info->mount_opt, NODATASUM);
+ break;
+ case Opt_nodatacow:
+ printk(KERN_INFO "btrfs: setting nodatacow\n");
+ btrfs_set_opt(info->mount_opt, NODATACOW);
+ btrfs_set_opt(info->mount_opt, NODATASUM);
+ break;
+ case Opt_compress:
+ printk(KERN_INFO "btrfs: use compression\n");
+ btrfs_set_opt(info->mount_opt, COMPRESS);
+ break;
+ case Opt_ssd:
+ printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
+ btrfs_set_opt(info->mount_opt, SSD);
+ break;
+ case Opt_nobarrier:
+ printk(KERN_INFO "btrfs: turning off barriers\n");
+ btrfs_set_opt(info->mount_opt, NOBARRIER);
+ break;
+ case Opt_thread_pool:
+ intarg = 0;
+ match_int(&args[0], &intarg);
+ if (intarg) {
+ info->thread_pool_size = intarg;
+ printk(KERN_INFO "btrfs: thread pool %d\n",
+ info->thread_pool_size);
+ }
+ break;
+ case Opt_max_extent:
+ num = match_strdup(&args[0]);
+ if (num) {
+ info->max_extent = btrfs_parse_size(num);
+ kfree(num);
+
+ info->max_extent = max_t(u64,
+ info->max_extent, root->sectorsize);
+ printk(KERN_INFO "btrfs: max_extent at %llu\n",
+ (unsigned long long)info->max_extent);
+ }
+ break;
+ case Opt_max_inline:
+ num = match_strdup(&args[0]);
+ if (num) {
+ info->max_inline = btrfs_parse_size(num);
+ kfree(num);
+
+ if (info->max_inline) {
+ info->max_inline = max_t(u64,
+ info->max_inline,
+ root->sectorsize);
+ }
+ printk(KERN_INFO "btrfs: max_inline at %llu\n",
+ (unsigned long long)info->max_inline);
+ }
+ break;
+ case Opt_alloc_start:
+ num = match_strdup(&args[0]);
+ if (num) {
+ info->alloc_start = btrfs_parse_size(num);
+ kfree(num);
+ printk(KERN_INFO
+ "btrfs: allocations start at %llu\n",
+ (unsigned long long)info->alloc_start);
+ }
+ break;
+ case Opt_noacl:
+ root->fs_info->sb->s_flags &= ~MS_POSIXACL;
+ break;
+ case Opt_notreelog:
+ printk(KERN_INFO "btrfs: disabling tree log\n");
+ btrfs_set_opt(info->mount_opt, NOTREELOG);
+ break;
+ case Opt_flushoncommit:
+ printk(KERN_INFO "btrfs: turning on flush-on-commit\n");
+ btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT);
+ break;
+ case Opt_ratio:
+ intarg = 0;
+ match_int(&args[0], &intarg);
+ if (intarg) {
+ info->metadata_ratio = intarg;
+ printk(KERN_INFO "btrfs: metadata ratio %d\n",
+ info->metadata_ratio);
+ }
break;
- case S_IFLNK:
- inode->i_op = &page_symlink_inode_operations;
+ default:
break;
}
}
- return inode;
+ kfree(options);
+ return 0;
}
/*
- * File creation. Allocate an inode, and we're done..
+ * Parse mount options that are required early in the mount process.
+ *
+ * All other options will be parsed on much later in the mount process and
+ * only when we need to allocate a new super block.
*/
-/* SMP-safe */
-static int
-ramfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
+static int btrfs_parse_early_options(const char *options, fmode_t flags,
+ void *holder, char **subvol_name,
+ struct btrfs_fs_devices **fs_devices)
{
- struct inode * inode = ramfs_get_inode(dir->i_sb, mode, dev);
- int error = -ENOSPC;
-
- if (inode) {
- if (dir->i_mode & S_ISGID) {
- inode->i_gid = dir->i_gid;
- if (S_ISDIR(mode))
- inode->i_mode |= S_ISGID;
+ substring_t args[MAX_OPT_ARGS];
+ char *opts, *p;
+ int error = 0;
+
+ if (!options)
+ goto out;
+
+ /*
+ * strsep changes the string, duplicate it because parse_options
+ * gets called twice
+ */
+ opts = kstrdup(options, GFP_KERNEL);
+ if (!opts)
+ return -ENOMEM;
+
+ while ((p = strsep(&opts, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_subvol:
+ *subvol_name = match_strdup(&args[0]);
+ break;
+ case Opt_device:
+ error = btrfs_scan_one_device(match_strdup(&args[0]),
+ flags, holder, fs_devices);
+ if (error)
+ goto out_free_opts;
+ break;
+ default:
+ break;
}
- d_instantiate(dentry, inode);
- dget(dentry); /* Extra count - pin the dentry in core */
- error = 0;
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+ }
+
+ out_free_opts:
+ kfree(opts);
+ out:
+ /*
+ * If no subvolume name is specified we use the default one. Allocate
+ * a copy of the string "." here so that code later in the
+ * mount path doesn't care if it's the default volume or another one.
+ */
+ if (!*subvol_name) {
+ *subvol_name = kstrdup(".", GFP_KERNEL);
+ if (!*subvol_name)
+ return -ENOMEM;
}
return error;
}
-static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+static int btrfs_fill_super(struct super_block *sb,
+ struct btrfs_fs_devices *fs_devices,
+ void *data, int silent)
{
- int retval = ramfs_mknod(dir, dentry, mode | S_IFDIR, 0);
- if (!retval)
- inc_nlink(dir);
- return retval;
-}
+ struct inode *inode;
+ struct dentry *root_dentry;
+ struct btrfs_super_block *disk_super;
+ struct btrfs_root *tree_root;
+ struct btrfs_inode *bi;
+ int err;
-static int ramfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
-{
- return ramfs_mknod(dir, dentry, mode | S_IFREG, 0);
-}
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_magic = BTRFS_SUPER_MAGIC;
+ sb->s_op = &btrfs_super_ops;
+ sb->s_export_op = &btrfs_export_ops;
+ sb->s_xattr = btrfs_xattr_handlers;
+ sb->s_time_gran = 1;
+ sb->s_flags |= MS_POSIXACL;
-static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char * symname)
-{
- struct inode *inode;
- int error = -ENOSPC;
-
- inode = ramfs_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
- if (inode) {
- int l = strlen(symname)+1;
- error = page_symlink(inode, symname, l);
- if (!error) {
- if (dir->i_mode & S_ISGID)
- inode->i_gid = dir->i_gid;
- d_instantiate(dentry, inode);
- dget(dentry);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- } else
- iput(inode);
- }
- return error;
-}
+ tree_root = open_ctree(sb, fs_devices, (char *)data);
-static struct inode_operations ramfs_dir_inode_operations = {
- .create = ramfs_create,
- .lookup = simple_lookup,
- .link = simple_link,
- .unlink = simple_unlink,
- .symlink = ramfs_symlink,
- .mkdir = ramfs_mkdir,
- .rmdir = simple_rmdir,
- .mknod = ramfs_mknod,
- .rename = simple_rename,
-};
-#endif
+ if (IS_ERR(tree_root)) {
+ printk("btrfs: open_ctree failed\n");
+ return PTR_ERR(tree_root);
+ }
+ sb->s_fs_info = tree_root;
+ disk_super = &tree_root->fs_info->super_copy;
+ inode = btrfs_iget_locked(sb, BTRFS_FIRST_FREE_OBJECTID,
+ tree_root->fs_info->fs_root);
+ bi = BTRFS_I(inode);
+ bi->location.objectid = inode->i_ino;
+ bi->location.offset = 0;
+ bi->root = tree_root->fs_info->fs_root;
+
+ btrfs_set_key_type(&bi->location, BTRFS_INODE_ITEM_KEY);
+
+ if (!inode) {
+ err = -ENOMEM;
+ goto fail_close;
+ }
+ if (inode->i_state & I_NEW) {
+ btrfs_read_locked_inode(inode);
+ unlock_new_inode(inode);
+ }
-static void btrfs_read_locked_inode(struct inode *inode)
-{
- struct btrfs_path path;
- struct btrfs_inode_item *inode_item;
- struct btrfs_root *root = btrfs_sb(inode->i_sb);
- int ret;
-printk("read locked inode %lu\n", inode->i_ino);
- btrfs_init_path(&path);
- ret = btrfs_lookup_inode(NULL, root, &path, inode->i_ino, 0);
- if (ret) {
- make_bad_inode(inode);
- return;
+ root_dentry = d_alloc_root(inode);
+ if (!root_dentry) {
+ iput(inode);
+ err = -ENOMEM;
+ goto fail_close;
}
- inode_item = btrfs_item_ptr(btrfs_buffer_leaf(path.nodes[0]),
- path.slots[0],
- struct btrfs_inode_item);
-
-printk("found locked inode %lu\n", inode->i_ino);
- inode->i_mode = btrfs_inode_mode(inode_item);
- inode->i_nlink = btrfs_inode_nlink(inode_item);
- inode->i_uid = btrfs_inode_uid(inode_item);
- inode->i_gid = btrfs_inode_gid(inode_item);
- inode->i_size = btrfs_inode_size(inode_item);
- inode->i_atime.tv_sec = btrfs_timespec_sec(&inode_item->atime);
- inode->i_atime.tv_nsec = btrfs_timespec_nsec(&inode_item->atime);
- inode->i_mtime.tv_sec = btrfs_timespec_sec(&inode_item->mtime);
- inode->i_mtime.tv_nsec = btrfs_timespec_nsec(&inode_item->mtime);
- inode->i_ctime.tv_sec = btrfs_timespec_sec(&inode_item->ctime);
- inode->i_ctime.tv_nsec = btrfs_timespec_nsec(&inode_item->ctime);
- inode->i_blocks = btrfs_inode_nblocks(inode_item);
- inode->i_generation = btrfs_inode_generation(inode_item);
-printk("about to release\n");
- btrfs_release_path(root, &path);
- switch (inode->i_mode & S_IFMT) {
#if 0
- default:
- init_special_inode(inode, inode->i_mode,
- btrfs_inode_rdev(inode_item));
- break;
+ /* this does the super kobj at the same time */
+ err = btrfs_sysfs_add_super(tree_root->fs_info);
+ if (err)
+ goto fail_close;
#endif
- case S_IFREG:
-printk("inode %lu now a file\n", inode->i_ino);
- break;
- case S_IFDIR:
-printk("inode %lu now a directory\n", inode->i_ino);
- inode->i_op = &btrfs_dir_inode_operations;
- inode->i_fop = &btrfs_dir_file_operations;
- break;
- case S_IFLNK:
-printk("inode %lu now a link\n", inode->i_ino);
- // inode->i_op = &page_symlink_inode_operations;
- break;
- }
-printk("returning!\n");
- return;
+
+ sb->s_root = root_dentry;
+
+ save_mount_options(sb, data);
+ return 0;
+
+fail_close:
+ close_ctree(tree_root);
+ return err;
}
-static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
- ino_t *ino)
+int btrfs_sync_fs(struct super_block *sb, int wait)
{
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
- struct btrfs_dir_item *di;
- struct btrfs_path path;
- struct btrfs_root *root = btrfs_sb(dir->i_sb);
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = btrfs_sb(sb);
int ret;
- btrfs_init_path(&path);
- ret = btrfs_lookup_dir_item(NULL, root, &path, dir->i_ino, name,
- namelen, 0);
- if (ret) {
- *ino = 0;
- goto out;
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
+
+ sb->s_dirt = 0;
+ if (!wait) {
+ filemap_flush(root->fs_info->btree_inode->i_mapping);
+ return 0;
}
- di = btrfs_item_ptr(btrfs_buffer_leaf(path.nodes[0]), path.slots[0],
- struct btrfs_dir_item);
- *ino = btrfs_dir_objectid(di);
-out:
- btrfs_release_path(root, &path);
+
+ btrfs_start_delalloc_inodes(root);
+ btrfs_wait_ordered_extents(root, 0);
+
+ trans = btrfs_start_transaction(root, 1);
+ ret = btrfs_commit_transaction(trans, root);
+ sb->s_dirt = 0;
return ret;
}
-static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
- struct inode * inode;
- ino_t ino;
- int ret;
+ struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
+ struct btrfs_fs_info *info = root->fs_info;
+
+ if (btrfs_test_opt(root, DEGRADED))
+ seq_puts(seq, ",degraded");
+ if (btrfs_test_opt(root, NODATASUM))
+ seq_puts(seq, ",nodatasum");
+ if (btrfs_test_opt(root, NODATACOW))
+ seq_puts(seq, ",nodatacow");
+ if (btrfs_test_opt(root, NOBARRIER))
+ seq_puts(seq, ",nobarrier");
+ if (info->max_extent != (u64)-1)
+ seq_printf(seq, ",max_extent=%llu",
+ (unsigned long long)info->max_extent);
+ if (info->max_inline != 8192 * 1024)
+ seq_printf(seq, ",max_inline=%llu",
+ (unsigned long long)info->max_inline);
+ if (info->alloc_start != 0)
+ seq_printf(seq, ",alloc_start=%llu",
+ (unsigned long long)info->alloc_start);
+ if (info->thread_pool_size != min_t(unsigned long,
+ num_online_cpus() + 2, 8))
+ seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
+ if (btrfs_test_opt(root, COMPRESS))
+ seq_puts(seq, ",compress");
+ if (btrfs_test_opt(root, SSD))
+ seq_puts(seq, ",ssd");
+ if (btrfs_test_opt(root, NOTREELOG))
+ seq_puts(seq, ",notreelog");
+ if (btrfs_test_opt(root, FLUSHONCOMMIT))
+ seq_puts(seq, ",flushoncommit");
+ if (!(root->fs_info->sb->s_flags & MS_POSIXACL))
+ seq_puts(seq, ",noacl");
+ return 0;
+}
- if (dentry->d_name.len > BTRFS_NAME_LEN)
- return ERR_PTR(-ENAMETOOLONG);
-
- ret = btrfs_inode_by_name(dir, dentry, &ino);
- if (ret < 0)
- return ERR_PTR(ret);
- inode = NULL;
- if (ino) {
-printk("lookup on %.*s returns %lu\n", dentry->d_name.len, dentry->d_name.name, ino);
- inode = iget(dir->i_sb, ino);
- if (!inode)
- return ERR_PTR(-EACCES);
- }
- return d_splice_alias(inode, dentry);
+static void btrfs_write_super(struct super_block *sb)
+{
+ sb->s_dirt = 0;
}
-static int btrfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
+static int btrfs_test_super(struct super_block *s, void *data)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
- struct btrfs_root *root = btrfs_sb(inode->i_sb);
- struct btrfs_item *item;
- struct btrfs_dir_item *di;
- struct btrfs_key key;
- struct btrfs_path path;
- int ret;
- u32 nritems;
- struct btrfs_leaf *leaf;
- int slot;
- int advance;
- unsigned char d_type = DT_UNKNOWN;
- int over;
-
- key.objectid = inode->i_ino;
-printk("readdir on dir %Lu pos %Lu\n", key.objectid, filp->f_pos);
- key.flags = 0;
- btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
- key.offset = filp->f_pos;
- btrfs_init_path(&path);
- ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
- if (ret < 0) {
- goto err;
+ struct btrfs_fs_devices *test_fs_devices = data;
+ struct btrfs_root *root = btrfs_sb(s);
+
+ return root->fs_info->fs_devices == test_fs_devices;
+}
+
+/*
+ * Find a superblock for the given device / mount point.
+ *
+ * Note: This is based on get_sb_bdev from fs/super.c with a few additions
+ * for multiple device setup. Make sure to keep it in sync.
+ */
+static int btrfs_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data, struct vfsmount *mnt)
+{
+ char *subvol_name = NULL;
+ struct block_device *bdev = NULL;
+ struct super_block *s;
+ struct dentry *root;
+ struct btrfs_fs_devices *fs_devices = NULL;
+ fmode_t mode = FMODE_READ;
+ int error = 0;
+
+ if (!(flags & MS_RDONLY))
+ mode |= FMODE_WRITE;
+
+ error = btrfs_parse_early_options(data, mode, fs_type,
+ &subvol_name, &fs_devices);
+ if (error)
+ return error;
+
+ error = btrfs_scan_one_device(dev_name, mode, fs_type, &fs_devices);
+ if (error)
+ goto error_free_subvol_name;
+
+ error = btrfs_open_devices(fs_devices, mode, fs_type);
+ if (error)
+ goto error_free_subvol_name;
+
+ if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
+ error = -EACCES;
+ goto error_close_devices;
}
-printk("first ret %d\n", ret);
- advance = filp->f_pos > 0 && ret != 0;
- while(1) {
- leaf = btrfs_buffer_leaf(path.nodes[0]);
- nritems = btrfs_header_nritems(&leaf->header);
- slot = path.slots[0];
-printk("leaf %Lu nritems %lu slot %d\n", path.nodes[0]->b_blocknr, nritems, slot);
- if (advance) {
-printk("advancing!\n");
- if (slot == nritems -1) {
- ret = btrfs_next_leaf(root, &path);
- if (ret)
- break;
- leaf = btrfs_buffer_leaf(path.nodes[0]);
- nritems = btrfs_header_nritems(&leaf->header);
- slot = path.slots[0];
-printk("2leaf %Lu nritems %lu slot %d\n", path.nodes[0]->b_blocknr, nritems, slot);
- } else {
- slot++;
- path.slots[0]++;
- }
+
+ bdev = fs_devices->latest_bdev;
+ s = sget(fs_type, btrfs_test_super, set_anon_super, fs_devices);
+ if (IS_ERR(s))
+ goto error_s;
+
+ if (s->s_root) {
+ if ((flags ^ s->s_flags) & MS_RDONLY) {
+ deactivate_locked_super(s);
+ error = -EBUSY;
+ goto error_close_devices;
}
- advance = 1;
- item = leaf->items + slot;
-printk("item key %Lu %u %Lu\n", btrfs_disk_key_objectid(&item->key),
- btrfs_disk_key_flags(&item->key), btrfs_disk_key_offset(&item->key));
- if (btrfs_disk_key_objectid(&item->key) != key.objectid)
- break;
- if (btrfs_disk_key_type(&item->key) != BTRFS_DIR_ITEM_KEY)
- continue;
- di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
-printk("filldir name %.*s, objectid %Lu\n", btrfs_dir_name_len(di),
- (const char *)(di + 1), btrfs_dir_objectid(di));
- over = filldir(dirent, (const char *)(di + 1),
- btrfs_dir_name_len(di),
- btrfs_disk_key_offset(&item->key),
- btrfs_dir_objectid(di), d_type);
- if (over)
- break;
- filp->f_pos = btrfs_disk_key_offset(&item->key) + 1;
+
+ btrfs_close_devices(fs_devices);
+ } else {
+ char b[BDEVNAME_SIZE];
+
+ s->s_flags = flags;
+ strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
+ error = btrfs_fill_super(s, fs_devices, data,
+ flags & MS_SILENT ? 1 : 0);
+ if (error) {
+ deactivate_locked_super(s);
+ goto error_free_subvol_name;
+ }
+
+ btrfs_sb(s)->fs_info->bdev_holder = fs_type;
+ s->s_flags |= MS_ACTIVE;
}
-printk("filldir all done\n");
- ret = 0;
-err:
- btrfs_release_path(root, &path);
- return ret;
+
+ if (!strcmp(subvol_name, "."))
+ root = dget(s->s_root);
+ else {
+ mutex_lock(&s->s_root->d_inode->i_mutex);
+ root = lookup_one_len(subvol_name, s->s_root,
+ strlen(subvol_name));
+ mutex_unlock(&s->s_root->d_inode->i_mutex);
+
+ if (IS_ERR(root)) {
+ deactivate_locked_super(s);
+ error = PTR_ERR(root);
+ goto error_free_subvol_name;
+ }
+ if (!root->d_inode) {
+ dput(root);
+ deactivate_locked_super(s);
+ error = -ENXIO;
+ goto error_free_subvol_name;
+ }
+ }
+
+ mnt->mnt_sb = s;
+ mnt->mnt_root = root;
+
+ kfree(subvol_name);
+ return 0;
+
+error_s:
+ error = PTR_ERR(s);
+error_close_devices:
+ btrfs_close_devices(fs_devices);
+error_free_subvol_name:
+ kfree(subvol_name);
+ return error;
}
-static void btrfs_put_super (struct super_block * sb)
+static int btrfs_remount(struct super_block *sb, int *flags, char *data)
{
struct btrfs_root *root = btrfs_sb(sb);
int ret;
- ret = close_ctree(root);
- if (ret) {
- printk("close ctree returns %d\n", ret);
- }
- sb->s_fs_info = NULL;
-}
+ ret = btrfs_parse_options(root, data);
+ if (ret)
+ return -EINVAL;
-static int btrfs_fill_super(struct super_block * sb, void * data, int silent)
-{
- struct inode * inode;
- struct dentry * root_dentry;
- struct btrfs_super_block *disk_super;
- struct buffer_head *bh;
- struct btrfs_root *root;
+ if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
+ return 0;
- sb->s_maxbytes = MAX_LFS_FILESIZE;
- sb->s_blocksize = PAGE_CACHE_SIZE;
- sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
- sb->s_magic = BTRFS_SUPER_MAGIC;
- sb->s_op = &btrfs_super_ops;
- sb->s_time_gran = 1;
+ if (*flags & MS_RDONLY) {
+ sb->s_flags |= MS_RDONLY;
- bh = sb_bread(sb, BTRFS_SUPER_INFO_OFFSET / sb->s_blocksize);
- if (!bh) {
- printk("btrfs: unable to read on disk super\n");
- return -EIO;
- }
- disk_super = (struct btrfs_super_block *)bh->b_data;
- root = open_ctree(sb, bh, disk_super);
- sb->s_fs_info = root;
- if (!root) {
- printk("btrfs: open_ctree failed\n");
- return -EIO;
- }
- printk("read in super total blocks %Lu root %Lu\n",
- btrfs_super_total_blocks(disk_super),
- btrfs_super_root_dir(disk_super));
+ ret = btrfs_commit_super(root);
+ WARN_ON(ret);
+ } else {
+ if (root->fs_info->fs_devices->rw_devices == 0)
+ return -EACCES;
- inode = iget_locked(sb, btrfs_super_root_dir(disk_super));
- if (!inode)
- return -ENOMEM;
- if (inode->i_state & I_NEW) {
- btrfs_read_locked_inode(inode);
- unlock_new_inode(inode);
- }
+ if (btrfs_super_log_root(&root->fs_info->super_copy) != 0)
+ return -EINVAL;
- root_dentry = d_alloc_root(inode);
- if (!root_dentry) {
- iput(inode);
- return -ENOMEM;
+ ret = btrfs_cleanup_reloc_trees(root);
+ WARN_ON(ret);
+
+ ret = btrfs_cleanup_fs_roots(root->fs_info);
+ WARN_ON(ret);
+
+ sb->s_flags &= ~MS_RDONLY;
}
- sb->s_root = root_dentry;
return 0;
}
-static int btrfs_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
- return get_sb_bdev(fs_type, flags, dev_name, data,
- btrfs_fill_super, mnt);
+ struct btrfs_root *root = btrfs_sb(dentry->d_sb);
+ struct btrfs_super_block *disk_super = &root->fs_info->super_copy;
+ int bits = dentry->d_sb->s_blocksize_bits;
+ __be32 *fsid = (__be32 *)root->fs_info->fsid;
+
+ buf->f_namelen = BTRFS_NAME_LEN;
+ buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits;
+ buf->f_bfree = buf->f_blocks -
+ (btrfs_super_bytes_used(disk_super) >> bits);
+ buf->f_bavail = buf->f_bfree;
+ buf->f_bsize = dentry->d_sb->s_blocksize;
+ buf->f_type = BTRFS_SUPER_MAGIC;
+
+ /* We treat it as constant endianness (it doesn't matter _which_)
+ because we want the fsid to come out the same whether mounted
+ on a big-endian or little-endian host */
+ buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
+ buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
+ /* Mask in the root object ID too, to disambiguate subvols */
+ buf->f_fsid.val[0] ^= BTRFS_I(dentry->d_inode)->root->objectid >> 32;
+ buf->f_fsid.val[1] ^= BTRFS_I(dentry->d_inode)->root->objectid;
+
+ return 0;
}
static struct file_system_type btrfs_fs_type = {
.owner = THIS_MODULE,
.name = "btrfs",
.get_sb = btrfs_get_sb,
- .kill_sb = kill_block_super,
+ .kill_sb = kill_anon_super,
.fs_flags = FS_REQUIRES_DEV,
};
+/*
+ * used by btrfsctl to scan devices when no FS is mounted
+ */
+static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct btrfs_ioctl_vol_args *vol;
+ struct btrfs_fs_devices *fs_devices;
+ int ret = -ENOTTY;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ vol = memdup_user((void __user *)arg, sizeof(*vol));
+ if (IS_ERR(vol))
+ return PTR_ERR(vol);
+
+ switch (cmd) {
+ case BTRFS_IOC_SCAN_DEV:
+ ret = btrfs_scan_one_device(vol->name, FMODE_READ,
+ &btrfs_fs_type, &fs_devices);
+ break;
+ }
+
+ kfree(vol);
+ return ret;
+}
+
+static int btrfs_freeze(struct super_block *sb)
+{
+ struct btrfs_root *root = btrfs_sb(sb);
+ mutex_lock(&root->fs_info->transaction_kthread_mutex);
+ mutex_lock(&root->fs_info->cleaner_mutex);
+ return 0;
+}
+
+static int btrfs_unfreeze(struct super_block *sb)
+{
+ struct btrfs_root *root = btrfs_sb(sb);
+ mutex_unlock(&root->fs_info->cleaner_mutex);
+ mutex_unlock(&root->fs_info->transaction_kthread_mutex);
+ return 0;
+}
+
static struct super_operations btrfs_super_ops = {
- .statfs = simple_statfs,
- .drop_inode = generic_delete_inode,
+ .delete_inode = btrfs_delete_inode,
.put_super = btrfs_put_super,
- .read_inode = btrfs_read_locked_inode,
+ .write_super = btrfs_write_super,
+ .sync_fs = btrfs_sync_fs,
+ .show_options = btrfs_show_options,
+ .write_inode = btrfs_write_inode,
+ .dirty_inode = btrfs_dirty_inode,
+ .alloc_inode = btrfs_alloc_inode,
+ .destroy_inode = btrfs_destroy_inode,
+ .statfs = btrfs_statfs,
+ .remount_fs = btrfs_remount,
+ .freeze_fs = btrfs_freeze,
+ .unfreeze_fs = btrfs_unfreeze,
};
-static struct inode_operations btrfs_dir_inode_operations = {
- .lookup = btrfs_lookup,
+static const struct file_operations btrfs_ctl_fops = {
+ .unlocked_ioctl = btrfs_control_ioctl,
+ .compat_ioctl = btrfs_control_ioctl,
+ .owner = THIS_MODULE,
};
-static struct file_operations btrfs_dir_file_operations = {
- .llseek = generic_file_llseek,
- .read = generic_read_dir,
- .readdir = btrfs_readdir,
+static struct miscdevice btrfs_misc = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "btrfs-control",
+ .fops = &btrfs_ctl_fops
};
+static int btrfs_interface_init(void)
+{
+ return misc_register(&btrfs_misc);
+}
+
+static void btrfs_interface_exit(void)
+{
+ if (misc_deregister(&btrfs_misc) < 0)
+ printk(KERN_INFO "misc_deregister failed for control device");
+}
static int __init init_btrfs_fs(void)
{
- printk("btrfs loaded!\n");
- return register_filesystem(&btrfs_fs_type);
+ int err;
+
+ err = btrfs_init_sysfs();
+ if (err)
+ return err;
+
+ err = btrfs_init_cachep();
+ if (err)
+ goto free_sysfs;
+
+ err = extent_io_init();
+ if (err)
+ goto free_cachep;
+
+ err = extent_map_init();
+ if (err)
+ goto free_extent_io;
+
+ err = btrfs_interface_init();
+ if (err)
+ goto free_extent_map;
+
+ err = register_filesystem(&btrfs_fs_type);
+ if (err)
+ goto unregister_ioctl;
+
+ printk(KERN_INFO "%s loaded\n", BTRFS_BUILD_VERSION);
+ return 0;
+
+unregister_ioctl:
+ btrfs_interface_exit();
+free_extent_map:
+ extent_map_exit();
+free_extent_io:
+ extent_io_exit();
+free_cachep:
+ btrfs_destroy_cachep();
+free_sysfs:
+ btrfs_exit_sysfs();
+ return err;
}
static void __exit exit_btrfs_fs(void)
{
+ btrfs_destroy_cachep();
+ extent_map_exit();
+ extent_io_exit();
+ btrfs_interface_exit();
unregister_filesystem(&btrfs_fs_type);
- printk("btrfs unloaded\n");
+ btrfs_exit_sysfs();
+ btrfs_cleanup_fs_uuids();
+ btrfs_zlib_exit();
}
module_init(init_btrfs_fs)