OpenCloudOS-Kernel/fs/efs/super.c

354 lines
8.2 KiB
C
Raw Normal View History

/*
* super.c
*
* Copyright (c) 1999 Al Smith
*
* Portions derived from work (c) 1995,1996 Christian Vogelgsang.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/exportfs.h>
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
#include "efs.h"
#include <linux/efs_vh.h>
#include <linux/efs_fs_sb.h>
static int efs_statfs(struct dentry *dentry, struct kstatfs *buf);
static int efs_fill_super(struct super_block *s, void *d, int silent);
static struct dentry *efs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, efs_fill_super);
}
static void efs_kill_sb(struct super_block *s)
{
struct efs_sb_info *sbi = SUPER_INFO(s);
kill_block_super(s);
kfree(sbi);
}
static struct file_system_type efs_fs_type = {
.owner = THIS_MODULE,
.name = "efs",
.mount = efs_mount,
.kill_sb = efs_kill_sb,
.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 11:39:14 +08:00
MODULE_ALIAS_FS("efs");
static struct pt_types sgi_pt_types[] = {
{0x00, "SGI vh"},
{0x01, "SGI trkrepl"},
{0x02, "SGI secrepl"},
{0x03, "SGI raw"},
{0x04, "SGI bsd"},
{SGI_SYSV, "SGI sysv"},
{0x06, "SGI vol"},
{SGI_EFS, "SGI efs"},
{0x08, "SGI lv"},
{0x09, "SGI rlv"},
{0x0A, "SGI xfs"},
{0x0B, "SGI xfslog"},
{0x0C, "SGI xlv"},
{0x82, "Linux swap"},
{0x83, "Linux native"},
{0, NULL}
};
static struct kmem_cache * efs_inode_cachep;
static struct inode *efs_alloc_inode(struct super_block *sb)
{
struct efs_inode_info *ei;
ei = (struct efs_inode_info *)kmem_cache_alloc(efs_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
}
2011-01-07 14:49:49 +08:00
static void efs_i_callback(struct rcu_head *head)
{
2011-01-07 14:49:49 +08:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(efs_inode_cachep, INODE_INFO(inode));
}
2011-01-07 14:49:49 +08:00
static void efs_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, efs_i_callback);
}
static void init_once(void *foo)
{
struct efs_inode_info *ei = (struct efs_inode_info *) foo;
inode_init_once(&ei->vfs_inode);
}
static int __init init_inodecache(void)
{
efs_inode_cachep = kmem_cache_create("efs_inode_cache",
sizeof(struct efs_inode_info),
[PATCH] cpuset memory spread: slab cache filesystems Mark file system inode and similar slab caches subject to SLAB_MEM_SPREAD memory spreading. If a slab cache is marked SLAB_MEM_SPREAD, then anytime that a task that's in a cpuset with the 'memory_spread_slab' option enabled goes to allocate from such a slab cache, the allocations are spread evenly over all the memory nodes (task->mems_allowed) allowed to that task, instead of favoring allocation on the node local to the current cpu. The following inode and similar caches are marked SLAB_MEM_SPREAD: file cache ==== ===== fs/adfs/super.c adfs_inode_cache fs/affs/super.c affs_inode_cache fs/befs/linuxvfs.c befs_inode_cache fs/bfs/inode.c bfs_inode_cache fs/block_dev.c bdev_cache fs/cifs/cifsfs.c cifs_inode_cache fs/coda/inode.c coda_inode_cache fs/dquot.c dquot fs/efs/super.c efs_inode_cache fs/ext2/super.c ext2_inode_cache fs/ext2/xattr.c (fs/mbcache.c) ext2_xattr fs/ext3/super.c ext3_inode_cache fs/ext3/xattr.c (fs/mbcache.c) ext3_xattr fs/fat/cache.c fat_cache fs/fat/inode.c fat_inode_cache fs/freevxfs/vxfs_super.c vxfs_inode fs/hpfs/super.c hpfs_inode_cache fs/isofs/inode.c isofs_inode_cache fs/jffs/inode-v23.c jffs_fm fs/jffs2/super.c jffs2_i fs/jfs/super.c jfs_ip fs/minix/inode.c minix_inode_cache fs/ncpfs/inode.c ncp_inode_cache fs/nfs/direct.c nfs_direct_cache fs/nfs/inode.c nfs_inode_cache fs/ntfs/super.c ntfs_big_inode_cache_name fs/ntfs/super.c ntfs_inode_cache fs/ocfs2/dlm/dlmfs.c dlmfs_inode_cache fs/ocfs2/super.c ocfs2_inode_cache fs/proc/inode.c proc_inode_cache fs/qnx4/inode.c qnx4_inode_cache fs/reiserfs/super.c reiser_inode_cache fs/romfs/inode.c romfs_inode_cache fs/smbfs/inode.c smb_inode_cache fs/sysv/inode.c sysv_inode_cache fs/udf/super.c udf_inode_cache fs/ufs/super.c ufs_inode_cache net/socket.c sock_inode_cache net/sunrpc/rpc_pipe.c rpc_inode_cache The choice of which slab caches to so mark was quite simple. I marked those already marked SLAB_RECLAIM_ACCOUNT, except for fs/xfs, dentry_cache, inode_cache, and buffer_head, which were marked in a previous patch. Even though SLAB_RECLAIM_ACCOUNT is for a different purpose, it marks the same potentially large file system i/o related slab caches as we need for memory spreading. Given that the rule now becomes "wherever you would have used a SLAB_RECLAIM_ACCOUNT slab cache flag before (usually the inode cache), use the SLAB_MEM_SPREAD flag too", this should be easy enough to maintain. Future file system writers will just copy one of the existing file system slab cache setups and tend to get it right without thinking. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:16:05 +08:00
0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
init_once);
if (efs_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void destroy_inodecache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(efs_inode_cachep);
}
static int efs_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 22:14:33 +08:00
sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
static const struct super_operations efs_superblock_operations = {
.alloc_inode = efs_alloc_inode,
.destroy_inode = efs_destroy_inode,
.statfs = efs_statfs,
.remount_fs = efs_remount,
};
static const struct export_operations efs_export_ops = {
.fh_to_dentry = efs_fh_to_dentry,
.fh_to_parent = efs_fh_to_parent,
.get_parent = efs_get_parent,
};
static int __init init_efs_fs(void) {
int err;
pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n");
err = init_inodecache();
if (err)
goto out1;
err = register_filesystem(&efs_fs_type);
if (err)
goto out;
return 0;
out:
destroy_inodecache();
out1:
return err;
}
static void __exit exit_efs_fs(void) {
unregister_filesystem(&efs_fs_type);
destroy_inodecache();
}
module_init(init_efs_fs)
module_exit(exit_efs_fs)
static efs_block_t efs_validate_vh(struct volume_header *vh) {
int i;
__be32 cs, *ui;
int csum;
efs_block_t sblock = 0; /* shuts up gcc */
struct pt_types *pt_entry;
int pt_type, slice = -1;
if (be32_to_cpu(vh->vh_magic) != VHMAGIC) {
/*
* assume that we're dealing with a partition and allow
* read_super() to try and detect a valid superblock
* on the next block.
*/
return 0;
}
ui = ((__be32 *) (vh + 1)) - 1;
for(csum = 0; ui >= ((__be32 *) vh);) {
cs = *ui--;
csum += be32_to_cpu(cs);
}
if (csum) {
pr_warn("SGI disklabel: checksum bad, label corrupted\n");
return 0;
}
#ifdef DEBUG
pr_debug("bf: \"%16s\"\n", vh->vh_bootfile);
for(i = 0; i < NVDIR; i++) {
int j;
char name[VDNAMESIZE+1];
for(j = 0; j < VDNAMESIZE; j++) {
name[j] = vh->vh_vd[i].vd_name[j];
}
name[j] = (char) 0;
if (name[0]) {
pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n",
name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn),
(int) be32_to_cpu(vh->vh_vd[i].vd_nbytes));
}
}
#endif
for(i = 0; i < NPARTAB; i++) {
pt_type = (int) be32_to_cpu(vh->vh_pt[i].pt_type);
for(pt_entry = sgi_pt_types; pt_entry->pt_name; pt_entry++) {
if (pt_type == pt_entry->pt_type) break;
}
#ifdef DEBUG
if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) {
pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n",
i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn),
(int)be32_to_cpu(vh->vh_pt[i].pt_nblks),
pt_type, (pt_entry->pt_name) ?
pt_entry->pt_name : "unknown");
}
#endif
if (IS_EFS(pt_type)) {
sblock = be32_to_cpu(vh->vh_pt[i].pt_firstlbn);
slice = i;
}
}
if (slice == -1) {
pr_notice("partition table contained no EFS partitions\n");
#ifdef DEBUG
} else {
pr_info("using slice %d (type %s, offset 0x%x)\n", slice,
(pt_entry->pt_name) ? pt_entry->pt_name : "unknown",
sblock);
#endif
}
return sblock;
}
static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) {
if (!IS_EFS_MAGIC(be32_to_cpu(super->fs_magic)))
return -1;
sb->fs_magic = be32_to_cpu(super->fs_magic);
sb->total_blocks = be32_to_cpu(super->fs_size);
sb->first_block = be32_to_cpu(super->fs_firstcg);
sb->group_size = be32_to_cpu(super->fs_cgfsize);
sb->data_free = be32_to_cpu(super->fs_tfree);
sb->inode_free = be32_to_cpu(super->fs_tinode);
sb->inode_blocks = be16_to_cpu(super->fs_cgisize);
sb->total_groups = be16_to_cpu(super->fs_ncg);
return 0;
}
static int efs_fill_super(struct super_block *s, void *d, int silent)
{
struct efs_sb_info *sb;
struct buffer_head *bh;
struct inode *root;
sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL);
if (!sb)
return -ENOMEM;
s->s_fs_info = sb;
s->s_magic = EFS_SUPER_MAGIC;
if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) {
pr_err("device does not support %d byte blocks\n",
EFS_BLOCKSIZE);
return -EINVAL;
}
/* read the vh (volume header) block */
bh = sb_bread(s, 0);
if (!bh) {
pr_err("cannot read volume header\n");
return -EINVAL;
}
/*
* if this returns zero then we didn't find any partition table.
* this isn't (yet) an error - just assume for the moment that
* the device is valid and go on to search for a superblock.
*/
sb->fs_start = efs_validate_vh((struct volume_header *) bh->b_data);
brelse(bh);
if (sb->fs_start == -1) {
return -EINVAL;
}
bh = sb_bread(s, sb->fs_start + EFS_SUPER);
if (!bh) {
pr_err("cannot read superblock\n");
return -EINVAL;
}
if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) {
#ifdef DEBUG
pr_warn("invalid superblock at block %u\n",
sb->fs_start + EFS_SUPER);
#endif
brelse(bh);
return -EINVAL;
}
brelse(bh);
if (!(s->s_flags & MS_RDONLY)) {
#ifdef DEBUG
pr_info("forcing read-only mode\n");
#endif
s->s_flags |= MS_RDONLY;
}
s->s_op = &efs_superblock_operations;
s->s_export_op = &efs_export_ops;
root = efs_iget(s, EFS_ROOTINODE);
if (IS_ERR(root)) {
pr_err("get root inode failed\n");
return PTR_ERR(root);
}
s->s_root = d_make_root(root);
if (!(s->s_root)) {
pr_err("get root dentry failed\n");
return -ENOMEM;
}
return 0;
}
static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
struct super_block *sb = dentry->d_sb;
struct efs_sb_info *sbi = SUPER_INFO(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = EFS_SUPER_MAGIC; /* efs magic number */
buf->f_bsize = EFS_BLOCKSIZE; /* blocksize */
buf->f_blocks = sbi->total_groups * /* total data blocks */
(sbi->group_size - sbi->inode_blocks);
buf->f_bfree = sbi->data_free; /* free data blocks */
buf->f_bavail = sbi->data_free; /* free blocks for non-root */
buf->f_files = sbi->total_groups * /* total inodes */
sbi->inode_blocks *
(EFS_BLOCKSIZE / sizeof(struct efs_dinode));
buf->f_ffree = sbi->inode_free; /* free inodes */
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
buf->f_namelen = EFS_MAXNAMELEN; /* max filename length */
return 0;
}