linux/fs/hfsplus/super.c

703 lines
18 KiB
C
Raw Normal View History

/*
* linux/fs/hfsplus/super.c
*
* Copyright (C) 2001
* Brad Boyer (flar@allandria.com)
* (C) 2003 Ardis Technologies <roman@ardistech.com>
*
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/vfs.h>
#include <linux/nls.h>
static struct inode *hfsplus_alloc_inode(struct super_block *sb);
static void hfsplus_destroy_inode(struct inode *inode);
#include "hfsplus_fs.h"
#include "xattr.h"
static int hfsplus_system_read_inode(struct inode *inode)
{
struct hfsplus_vh *vhdr = HFSPLUS_SB(inode->i_sb)->s_vhdr;
switch (inode->i_ino) {
case HFSPLUS_EXT_CNID:
hfsplus_inode_read_fork(inode, &vhdr->ext_file);
inode->i_mapping->a_ops = &hfsplus_btree_aops;
break;
case HFSPLUS_CAT_CNID:
hfsplus_inode_read_fork(inode, &vhdr->cat_file);
inode->i_mapping->a_ops = &hfsplus_btree_aops;
break;
case HFSPLUS_ALLOC_CNID:
hfsplus_inode_read_fork(inode, &vhdr->alloc_file);
inode->i_mapping->a_ops = &hfsplus_aops;
break;
case HFSPLUS_START_CNID:
hfsplus_inode_read_fork(inode, &vhdr->start_file);
break;
case HFSPLUS_ATTR_CNID:
hfsplus_inode_read_fork(inode, &vhdr->attr_file);
inode->i_mapping->a_ops = &hfsplus_btree_aops;
break;
default:
return -EIO;
}
return 0;
}
struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
{
struct hfs_find_data fd;
struct inode *inode;
int err;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
spin_lock_init(&HFSPLUS_I(inode)->open_dir_lock);
mutex_init(&HFSPLUS_I(inode)->extents_lock);
HFSPLUS_I(inode)->flags = 0;
HFSPLUS_I(inode)->extent_state = 0;
HFSPLUS_I(inode)->rsrc_inode = NULL;
atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
inode->i_ino == HFSPLUS_ROOT_CNID) {
err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
if (!err) {
err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
if (!err)
err = hfsplus_cat_read_inode(inode, &fd);
hfs_find_exit(&fd);
}
} else {
err = hfsplus_system_read_inode(inode);
}
if (err) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
static int hfsplus_system_write_inode(struct inode *inode)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
struct hfsplus_vh *vhdr = sbi->s_vhdr;
struct hfsplus_fork_raw *fork;
struct hfs_btree *tree = NULL;
switch (inode->i_ino) {
case HFSPLUS_EXT_CNID:
fork = &vhdr->ext_file;
tree = sbi->ext_tree;
break;
case HFSPLUS_CAT_CNID:
fork = &vhdr->cat_file;
tree = sbi->cat_tree;
break;
case HFSPLUS_ALLOC_CNID:
fork = &vhdr->alloc_file;
break;
case HFSPLUS_START_CNID:
fork = &vhdr->start_file;
break;
case HFSPLUS_ATTR_CNID:
fork = &vhdr->attr_file;
tree = sbi->attr_tree;
break;
default:
return -EIO;
}
if (fork->total_size != cpu_to_be64(inode->i_size)) {
set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags);
hfsplus_mark_mdb_dirty(inode->i_sb);
}
hfsplus_inode_write_fork(inode, fork);
if (tree) {
int err = hfs_btree_write(tree);
if (err) {
pr_err("b-tree write err: %d, ino %lu\n",
err, inode->i_ino);
return err;
}
}
return 0;
}
static int hfsplus_write_inode(struct inode *inode,
struct writeback_control *wbc)
{
int err;
hfs_dbg(INODE, "hfsplus_write_inode: %lu\n", inode->i_ino);
err = hfsplus_ext_write_extent(inode);
if (err)
return err;
if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
inode->i_ino == HFSPLUS_ROOT_CNID)
return hfsplus_cat_write_inode(inode);
else
return hfsplus_system_write_inode(inode);
}
static void hfsplus_evict_inode(struct inode *inode)
{
hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino);
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 01:47:49 +04:00
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (HFSPLUS_IS_RSRC(inode)) {
HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
iput(HFSPLUS_I(inode)->rsrc_inode);
}
}
static int hfsplus_sync_fs(struct super_block *sb, int wait)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
struct hfsplus_vh *vhdr = sbi->s_vhdr;
int write_backup = 0;
int error, error2;
if (!wait)
return 0;
hfs_dbg(SUPER, "hfsplus_sync_fs\n");
/*
* Explicitly write out the special metadata inodes.
*
* While these special inodes are marked as hashed and written
* out peridocically by the flusher threads we redirty them
* during writeout of normal inodes, and thus the life lock
* prevents us from getting the latest state to disk.
*/
error = filemap_write_and_wait(sbi->cat_tree->inode->i_mapping);
error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping);
if (!error)
error = error2;
if (sbi->attr_tree) {
error2 =
filemap_write_and_wait(sbi->attr_tree->inode->i_mapping);
if (!error)
error = error2;
}
error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
if (!error)
error = error2;
mutex_lock(&sbi->vh_mutex);
mutex_lock(&sbi->alloc_mutex);
vhdr->free_blocks = cpu_to_be32(sbi->free_blocks);
vhdr->next_cnid = cpu_to_be32(sbi->next_cnid);
vhdr->folder_count = cpu_to_be32(sbi->folder_count);
vhdr->file_count = cpu_to_be32(sbi->file_count);
if (test_and_clear_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags)) {
memcpy(sbi->s_backup_vhdr, sbi->s_vhdr, sizeof(*sbi->s_vhdr));
write_backup = 1;
}
error2 = hfsplus_submit_bio(sb,
sbi->part_start + HFSPLUS_VOLHEAD_SECTOR,
sbi->s_vhdr_buf, NULL, WRITE_SYNC);
if (!error)
error = error2;
if (!write_backup)
goto out;
error2 = hfsplus_submit_bio(sb,
sbi->part_start + sbi->sect_count - 2,
sbi->s_backup_vhdr_buf, NULL, WRITE_SYNC);
if (!error)
error2 = error;
out:
mutex_unlock(&sbi->alloc_mutex);
mutex_unlock(&sbi->vh_mutex);
if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
return error;
}
static void delayed_sync_fs(struct work_struct *work)
{
int err;
struct hfsplus_sb_info *sbi;
sbi = container_of(work, struct hfsplus_sb_info, sync_work.work);
spin_lock(&sbi->work_lock);
sbi->work_queued = 0;
spin_unlock(&sbi->work_lock);
err = hfsplus_sync_fs(sbi->alloc_file->i_sb, 1);
if (err)
pr_err("delayed sync fs err %d\n", err);
}
void hfsplus_mark_mdb_dirty(struct super_block *sb)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
unsigned long delay;
if (sb->s_flags & MS_RDONLY)
return;
spin_lock(&sbi->work_lock);
if (!sbi->work_queued) {
delay = msecs_to_jiffies(dirty_writeback_interval * 10);
queue_delayed_work(system_long_wq, &sbi->sync_work, delay);
sbi->work_queued = 1;
}
spin_unlock(&sbi->work_lock);
}
static void hfsplus_put_super(struct super_block *sb)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
hfs_dbg(SUPER, "hfsplus_put_super\n");
cancel_delayed_work_sync(&sbi->sync_work);
if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) {
struct hfsplus_vh *vhdr = sbi->s_vhdr;
vhdr->modify_date = hfsp_now2mt();
vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT);
vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT);
hfsplus_sync_fs(sb, 1);
}
hfs_btree_close(sbi->attr_tree);
hfs_btree_close(sbi->cat_tree);
hfs_btree_close(sbi->ext_tree);
iput(sbi->alloc_file);
iput(sbi->hidden_dir);
kfree(sbi->s_vhdr_buf);
kfree(sbi->s_backup_vhdr_buf);
unload_nls(sbi->nls);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
}
static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = HFSPLUS_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = sbi->total_blocks << sbi->fs_shift;
buf->f_bfree = sbi->free_blocks << sbi->fs_shift;
buf->f_bavail = buf->f_bfree;
buf->f_files = 0xFFFFFFFF;
buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
buf->f_namelen = HFSPLUS_MAX_STRLEN;
return 0;
}
static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
{
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 18:14:33 +04:00
sync_filesystem(sb);
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
return 0;
if (!(*flags & MS_RDONLY)) {
struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
int force = 0;
if (!hfsplus_parse_options_remount(data, &force))
return -EINVAL;
if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n");
sb->s_flags |= MS_RDONLY;
*flags |= MS_RDONLY;
} else if (force) {
/* nothing */
} else if (vhdr->attributes &
cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
pr_warn("filesystem is marked locked, leaving read-only.\n");
sb->s_flags |= MS_RDONLY;
*flags |= MS_RDONLY;
} else if (vhdr->attributes &
cpu_to_be32(HFSPLUS_VOL_JOURNALED)) {
pr_warn("filesystem is marked journaled, leaving read-only.\n");
sb->s_flags |= MS_RDONLY;
*flags |= MS_RDONLY;
}
}
return 0;
}
static const struct super_operations hfsplus_sops = {
.alloc_inode = hfsplus_alloc_inode,
.destroy_inode = hfsplus_destroy_inode,
.write_inode = hfsplus_write_inode,
.evict_inode = hfsplus_evict_inode,
.put_super = hfsplus_put_super,
.sync_fs = hfsplus_sync_fs,
.statfs = hfsplus_statfs,
.remount_fs = hfsplus_remount,
.show_options = hfsplus_show_options,
};
static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
{
struct hfsplus_vh *vhdr;
struct hfsplus_sb_info *sbi;
hfsplus_cat_entry entry;
struct hfs_find_data fd;
struct inode *root, *inode;
struct qstr str;
struct nls_table *nls = NULL;
u64 last_fs_block, last_fs_page;
int err;
err = -ENOMEM;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
goto out;
sb->s_fs_info = sbi;
mutex_init(&sbi->alloc_mutex);
mutex_init(&sbi->vh_mutex);
spin_lock_init(&sbi->work_lock);
INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
hfsplus_fill_defaults(sbi);
err = -EINVAL;
if (!hfsplus_parse_options(data, sbi)) {
pr_err("unable to parse mount options\n");
goto out_unload_nls;
}
/* temporarily use utf8 to correctly find the hidden dir below */
nls = sbi->nls;
sbi->nls = load_nls("utf8");
if (!sbi->nls) {
pr_err("unable to load nls for utf8\n");
goto out_unload_nls;
}
/* Grab the volume header */
if (hfsplus_read_wrapper(sb)) {
if (!silent)
pr_warn("unable to find HFS+ superblock\n");
goto out_unload_nls;
}
vhdr = sbi->s_vhdr;
/* Copy parts of the volume header into the superblock */
sb->s_magic = HFSPLUS_VOLHEAD_SIG;
if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION ||
be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) {
pr_err("wrong filesystem version\n");
goto out_free_vhdr;
}
sbi->total_blocks = be32_to_cpu(vhdr->total_blocks);
sbi->free_blocks = be32_to_cpu(vhdr->free_blocks);
sbi->next_cnid = be32_to_cpu(vhdr->next_cnid);
sbi->file_count = be32_to_cpu(vhdr->file_count);
sbi->folder_count = be32_to_cpu(vhdr->folder_count);
sbi->data_clump_blocks =
be32_to_cpu(vhdr->data_clump_sz) >> sbi->alloc_blksz_shift;
if (!sbi->data_clump_blocks)
sbi->data_clump_blocks = 1;
sbi->rsrc_clump_blocks =
be32_to_cpu(vhdr->rsrc_clump_sz) >> sbi->alloc_blksz_shift;
if (!sbi->rsrc_clump_blocks)
sbi->rsrc_clump_blocks = 1;
err = -EFBIG;
last_fs_block = sbi->total_blocks - 1;
last_fs_page = (last_fs_block << sbi->alloc_blksz_shift) >>
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
PAGE_SHIFT;
if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) ||
(last_fs_page > (pgoff_t)(~0ULL))) {
pr_err("filesystem size too large\n");
goto out_free_vhdr;
}
/* Set up operations so we can load metadata */
sb->s_op = &hfsplus_sops;
sb->s_maxbytes = MAX_LFS_FILESIZE;
if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
pr_warn("Filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. mounting read-only.\n");
sb->s_flags |= MS_RDONLY;
} else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
/* nothing */
} else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
pr_warn("Filesystem is marked locked, mounting read-only.\n");
sb->s_flags |= MS_RDONLY;
} else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) &&
!(sb->s_flags & MS_RDONLY)) {
pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n");
sb->s_flags |= MS_RDONLY;
}
err = -EINVAL;
/* Load metadata objects (B*Trees) */
sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
if (!sbi->ext_tree) {
pr_err("failed to load extents file\n");
goto out_free_vhdr;
}
sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
if (!sbi->cat_tree) {
pr_err("failed to load catalog file\n");
goto out_close_ext_tree;
}
atomic_set(&sbi->attr_tree_state, HFSPLUS_EMPTY_ATTR_TREE);
if (vhdr->attr_file.total_blocks != 0) {
sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID);
if (!sbi->attr_tree) {
pr_err("failed to load attributes file\n");
goto out_close_cat_tree;
}
atomic_set(&sbi->attr_tree_state, HFSPLUS_VALID_ATTR_TREE);
}
sb->s_xattr = hfsplus_xattr_handlers;
inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID);
if (IS_ERR(inode)) {
pr_err("failed to load allocation file\n");
err = PTR_ERR(inode);
goto out_close_attr_tree;
}
sbi->alloc_file = inode;
/* Load the root directory */
root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID);
if (IS_ERR(root)) {
pr_err("failed to load root directory\n");
err = PTR_ERR(root);
goto out_put_alloc_file;
}
sb->s_d_op = &hfsplus_dentry_operations;
sb->s_root = d_make_root(root);
if (!sb->s_root) {
err = -ENOMEM;
goto out_put_alloc_file;
}
str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
str.name = HFSP_HIDDENDIR_NAME;
err = hfs_find_init(sbi->cat_tree, &fd);
if (err)
goto out_put_root;
hfsplus: fix longname handling Longname is not correctly handled by hfsplus driver. If an attempt to create a longname(>255) file/directory is made, it succeeds by creating a file/directory with HFSPLUS_MAX_STRLEN and incorrect catalog key. Thus leaving the volume in an inconsistent state. This patch fixes this issue. Although lookup is always called first to create a negative entry, so just doing a check in lookup would probably fix this issue. I choose to propagate error to other iops as well. Please NOTE: I have factored out hfsplus_cat_build_key_with_cnid from hfsplus_cat_build_key, to avoid unncessary branching. Thanks a lot. TEST: ------ dir="TEST_DIR" cdir=`pwd` name255="_123456789_123456789_123456789_123456789_123456789_123456789\ _123456789_123456789_123456789_123456789_123456789_123456789_123456789\ _123456789_123456789_123456789_123456789_123456789_123456789_123456789\ _123456789_123456789_123456789_123456789_123456789_1234" name256="${name255}5" mkdir $dir cd $dir touch $name255 rm -f $name255 touch $name256 ls -la cd $cdir rm -rf $dir RESULT: ------- [sougata@ultrabook tmp]$ cdir=`pwd` [sougata@ultrabook tmp]$ name255="_123456789_123456789_123456789_123456789_123456789_123456789\ > _123456789_123456789_123456789_123456789_123456789_123456789_123456789\ > _123456789_123456789_123456789_123456789_123456789_123456789_123456789\ > _123456789_123456789_123456789_123456789_123456789_1234" [sougata@ultrabook tmp]$ name256="${name255}5" [sougata@ultrabook tmp]$ [sougata@ultrabook tmp]$ mkdir $dir [sougata@ultrabook tmp]$ cd $dir [sougata@ultrabook TEST_DIR]$ touch $name255 [sougata@ultrabook TEST_DIR]$ rm -f $name255 [sougata@ultrabook TEST_DIR]$ touch $name256 [sougata@ultrabook TEST_DIR]$ ls -la ls: cannot access _123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_1234: No such file or directory total 0 drwxrwxr-x 1 sougata sougata 3 Feb 20 19:56 . drwxrwxrwx 1 root root 6 Feb 20 19:56 .. -????????? ? ? ? ? ? _123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_123456789_1234 [sougata@ultrabook TEST_DIR]$ cd $cdir [sougata@ultrabook tmp]$ rm -rf $dir rm: cannot remove `TEST_DIR': Directory not empty -ENAMETOOLONG returned from hfsplus_asc2uni was not propaged to iops. This allowed hfsplus to create files/directories with HFSPLUS_MAX_STRLEN and incorrect keys, leaving the FS in an inconsistent state. This patch fixes this issue. Signed-off-by: Sougata Santra <sougata@tuxera.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Vyacheslav Dubeyko <slava@dubeyko.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-19 03:17:12 +03:00
err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
if (unlikely(err < 0))
goto out_put_root;
if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
hfs_find_exit(&fd);
if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
goto out_put_root;
inode = hfsplus_iget(sb, be32_to_cpu(entry.folder.id));
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto out_put_root;
}
sbi->hidden_dir = inode;
} else
hfs_find_exit(&fd);
if (!(sb->s_flags & MS_RDONLY)) {
/*
* H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused
* all three are registered with Apple for our use
*/
vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION);
vhdr->modify_date = hfsp_now2mt();
be32_add_cpu(&vhdr->write_count, 1);
vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
hfsplus_sync_fs(sb, 1);
if (!sbi->hidden_dir) {
mutex_lock(&sbi->vh_mutex);
sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
if (!sbi->hidden_dir) {
mutex_unlock(&sbi->vh_mutex);
err = -ENOMEM;
goto out_put_root;
}
err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root,
&str, sbi->hidden_dir);
if (err) {
mutex_unlock(&sbi->vh_mutex);
goto out_put_hidden_dir;
}
err = hfsplus_init_inode_security(sbi->hidden_dir,
root, &str);
if (err == -EOPNOTSUPP)
err = 0; /* Operation is not supported. */
else if (err) {
/*
* Try to delete anyway without
* error analysis.
*/
hfsplus_delete_cat(sbi->hidden_dir->i_ino,
root, &str);
mutex_unlock(&sbi->vh_mutex);
goto out_put_hidden_dir;
}
mutex_unlock(&sbi->vh_mutex);
hfsplus_mark_inode_dirty(sbi->hidden_dir,
HFSPLUS_I_CAT_DIRTY);
}
}
unload_nls(sbi->nls);
sbi->nls = nls;
return 0;
out_put_hidden_dir:
iput(sbi->hidden_dir);
out_put_root:
dput(sb->s_root);
sb->s_root = NULL;
out_put_alloc_file:
iput(sbi->alloc_file);
out_close_attr_tree:
hfs_btree_close(sbi->attr_tree);
out_close_cat_tree:
hfs_btree_close(sbi->cat_tree);
out_close_ext_tree:
hfs_btree_close(sbi->ext_tree);
out_free_vhdr:
kfree(sbi->s_vhdr_buf);
kfree(sbi->s_backup_vhdr_buf);
out_unload_nls:
unload_nls(sbi->nls);
unload_nls(nls);
kfree(sbi);
out:
return err;
}
MODULE_AUTHOR("Brad Boyer");
MODULE_DESCRIPTION("Extended Macintosh Filesystem");
MODULE_LICENSE("GPL");
static struct kmem_cache *hfsplus_inode_cachep;
static struct inode *hfsplus_alloc_inode(struct super_block *sb)
{
struct hfsplus_inode_info *i;
i = kmem_cache_alloc(hfsplus_inode_cachep, GFP_KERNEL);
return i ? &i->vfs_inode : NULL;
}
2011-01-07 09:49:49 +03:00
static void hfsplus_i_callback(struct rcu_head *head)
{
2011-01-07 09:49:49 +03:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode));
}
2011-01-07 09:49:49 +03:00
static void hfsplus_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, hfsplus_i_callback);
}
#define HFSPLUS_INODE_SIZE sizeof(struct hfsplus_inode_info)
static struct dentry *hfsplus_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, hfsplus_fill_super);
}
static struct file_system_type hfsplus_fs_type = {
.owner = THIS_MODULE,
.name = "hfsplus",
.mount = hfsplus_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 07:39:14 +04:00
MODULE_ALIAS_FS("hfsplus");
static void hfsplus_init_once(void *p)
{
struct hfsplus_inode_info *i = p;
inode_init_once(&i->vfs_inode);
}
static int __init init_hfsplus_fs(void)
{
int err;
hfsplus_inode_cachep = kmem_cache_create("hfsplus_icache",
2016-01-15 02:18:21 +03:00
HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT,
hfsplus_init_once);
if (!hfsplus_inode_cachep)
return -ENOMEM;
err = hfsplus_create_attr_tree_cache();
if (err)
goto destroy_inode_cache;
err = register_filesystem(&hfsplus_fs_type);
if (err)
goto destroy_attr_tree_cache;
return 0;
destroy_attr_tree_cache:
hfsplus_destroy_attr_tree_cache();
destroy_inode_cache:
kmem_cache_destroy(hfsplus_inode_cachep);
return err;
}
static void __exit exit_hfsplus_fs(void)
{
unregister_filesystem(&hfsplus_fs_type);
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
hfsplus_destroy_attr_tree_cache();
kmem_cache_destroy(hfsplus_inode_cachep);
}
module_init(init_hfsplus_fs)
module_exit(exit_hfsplus_fs)