linux_dsm_epyc7002/fs/romfs/super.c

662 lines
15 KiB
C
Raw Normal View History

/* Block- or MTD-based romfs
*
* Copyright © 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* Derived from: ROMFS file system, Linux implementation
*
* Copyright © 1997-1999 Janos Farkas <chexum@shadow.banki.hu>
*
* Using parts of the minix filesystem
* Copyright © 1991, 1992 Linus Torvalds
*
* and parts of the affs filesystem additionally
* Copyright © 1993 Ray Burr
* Copyright © 1996 Hans-Joachim Widmaier
*
* Changes
* Changed for 2.1.19 modules
* Jan 1997 Initial release
* Jun 1997 2.1.43+ changes
* Proper page locking in readpage
* Changed to work with 2.1.45+ fs
* Jul 1997 Fixed follow_link
* 2.1.47
* lookup shouldn't return -ENOENT
* from Horst von Brand:
* fail on wrong checksum
* double unlock_super was possible
* correct namelen for statfs
* spotted by Bill Hawes:
* readlink shouldn't iput()
* Jun 1998 2.1.106 from Avery Pennarun: glibc scandir()
* exposed a problem in readdir
* 2.1.107 code-freeze spellchecker run
* Aug 1998 2.1.118+ VFS changes
* Sep 1998 2.1.122 another VFS change (follow_link)
* Apr 1999 2.2.7 no more EBADF checking in
* lookup/readdir, use ERR_PTR
* Jun 1999 2.3.6 d_alloc_root use changed
* 2.3.9 clean up usage of ENOENT/negative
* dentries in lookup
* clean up page flags setting
* (error, uptodate, locking) in
* in readpage
* use init_special_inode for
* fifos/sockets (and streamline) in
* read_inode, fix _ops table order
* Aug 1999 2.3.16 __initfunc() => __init change
* Oct 1999 2.3.24 page->owner hack obsoleted
* Nov 1999 2.3.27 2.3.25+ page->offset => index change
*
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/statfs.h>
#include <linux/mtd/super.h>
#include <linux/ctype.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
#include "internal.h"
static struct kmem_cache *romfs_inode_cachep;
static const umode_t romfs_modemap[8] = {
0, /* hard link */
S_IFDIR | 0644, /* directory */
S_IFREG | 0644, /* regular file */
S_IFLNK | 0777, /* symlink */
S_IFBLK | 0600, /* blockdev */
S_IFCHR | 0600, /* chardev */
S_IFSOCK | 0644, /* socket */
S_IFIFO | 0644 /* FIFO */
};
static const unsigned char romfs_dtype_table[] = {
DT_UNKNOWN, DT_DIR, DT_REG, DT_LNK, DT_BLK, DT_CHR, DT_SOCK, DT_FIFO
};
static struct inode *romfs_iget(struct super_block *sb, unsigned long pos);
/*
* read a page worth of data from the image
*/
static int romfs_readpage(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
loff_t offset, size;
unsigned long fillsize, pos;
void *buf;
int ret;
buf = kmap(page);
if (!buf)
return -ENOMEM;
/* 32 bit warning -- but not for us :) */
offset = page_offset(page);
size = i_size_read(inode);
fillsize = 0;
ret = 0;
if (offset < size) {
size -= offset;
fillsize = size > PAGE_SIZE ? PAGE_SIZE : size;
pos = ROMFS_I(inode)->i_dataoffset + offset;
ret = romfs_dev_read(inode->i_sb, pos, buf, fillsize);
if (ret < 0) {
SetPageError(page);
fillsize = 0;
ret = -EIO;
}
}
if (fillsize < PAGE_SIZE)
memset(buf + fillsize, 0, PAGE_SIZE - fillsize);
if (ret == 0)
SetPageUptodate(page);
flush_dcache_page(page);
kunmap(page);
unlock_page(page);
return ret;
}
static const struct address_space_operations romfs_aops = {
.readpage = romfs_readpage
};
/*
* read the entries from a directory
*/
static int romfs_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *i = file_inode(file);
struct romfs_inode ri;
unsigned long offset, maxoff;
int j, ino, nextfh;
char fsname[ROMFS_MAXFN]; /* XXX dynamic? */
int ret;
maxoff = romfs_maxsize(i->i_sb);
offset = ctx->pos;
if (!offset) {
offset = i->i_ino & ROMFH_MASK;
ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE);
if (ret < 0)
goto out;
offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
}
/* Not really failsafe, but we are read-only... */
for (;;) {
if (!offset || offset >= maxoff) {
offset = maxoff;
ctx->pos = offset;
goto out;
}
ctx->pos = offset;
/* Fetch inode info */
ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE);
if (ret < 0)
goto out;
j = romfs_dev_strnlen(i->i_sb, offset + ROMFH_SIZE,
sizeof(fsname) - 1);
if (j < 0)
goto out;
ret = romfs_dev_read(i->i_sb, offset + ROMFH_SIZE, fsname, j);
if (ret < 0)
goto out;
fsname[j] = '\0';
ino = offset;
nextfh = be32_to_cpu(ri.next);
if ((nextfh & ROMFH_TYPE) == ROMFH_HRD)
ino = be32_to_cpu(ri.spec);
if (!dir_emit(ctx, fsname, j, ino,
romfs_dtype_table[nextfh & ROMFH_TYPE]))
goto out;
offset = nextfh & ROMFH_MASK;
}
out:
return 0;
}
/*
* look up an entry in a directory
*/
static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
unsigned long offset, maxoff;
struct inode *inode;
struct romfs_inode ri;
const char *name; /* got from dentry */
int len, ret;
offset = dir->i_ino & ROMFH_MASK;
ret = romfs_dev_read(dir->i_sb, offset, &ri, ROMFH_SIZE);
if (ret < 0)
goto error;
/* search all the file entries in the list starting from the one
* pointed to by the directory's special data */
maxoff = romfs_maxsize(dir->i_sb);
offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
name = dentry->d_name.name;
len = dentry->d_name.len;
for (;;) {
if (!offset || offset >= maxoff)
goto out0;
ret = romfs_dev_read(dir->i_sb, offset, &ri, sizeof(ri));
if (ret < 0)
goto error;
/* try to match the first 16 bytes of name */
ret = romfs_dev_strcmp(dir->i_sb, offset + ROMFH_SIZE, name,
len);
if (ret < 0)
goto error;
if (ret == 1)
break;
/* next entry */
offset = be32_to_cpu(ri.next) & ROMFH_MASK;
}
/* Hard link handling */
if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD)
offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
inode = romfs_iget(dir->i_sb, offset);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto error;
}
goto outi;
/*
* it's a bit funky, _lookup needs to return an error code
* (negative) or a NULL, both as a dentry. ENOENT should not
* be returned, instead we need to create a negative dentry by
* d_add(dentry, NULL); and return 0 as no error.
* (Although as I see, it only matters on writable file
* systems).
*/
out0:
inode = NULL;
outi:
d_add(dentry, inode);
ret = 0;
error:
return ERR_PTR(ret);
}
static const struct file_operations romfs_dir_operations = {
.read = generic_read_dir,
.iterate = romfs_readdir,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 23:52:59 +07:00
.llseek = default_llseek,
};
static const struct inode_operations romfs_dir_inode_operations = {
.lookup = romfs_lookup,
};
/*
* get a romfs inode based on its position in the image (which doubles as the
* inode number)
*/
static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
{
struct romfs_inode_info *inode;
struct romfs_inode ri;
struct inode *i;
unsigned long nlen;
unsigned nextfh;
int ret;
umode_t mode;
/* we might have to traverse a chain of "hard link" file entries to get
* to the actual file */
for (;;) {
ret = romfs_dev_read(sb, pos, &ri, sizeof(ri));
if (ret < 0)
goto error;
/* XXX: do romfs_checksum here too (with name) */
nextfh = be32_to_cpu(ri.next);
if ((nextfh & ROMFH_TYPE) != ROMFH_HRD)
break;
pos = be32_to_cpu(ri.spec) & ROMFH_MASK;
}
/* determine the length of the filename */
nlen = romfs_dev_strnlen(sb, pos + ROMFH_SIZE, ROMFS_MAXFN);
if (IS_ERR_VALUE(nlen))
goto eio;
/* get an inode for this image position */
i = iget_locked(sb, pos);
if (!i)
return ERR_PTR(-ENOMEM);
if (!(i->i_state & I_NEW))
return i;
/* precalculate the data offset */
inode = ROMFS_I(i);
inode->i_metasize = (ROMFH_SIZE + nlen + 1 + ROMFH_PAD) & ROMFH_MASK;
inode->i_dataoffset = pos + inode->i_metasize;
set_nlink(i, 1); /* Hard to decide.. */
i->i_size = be32_to_cpu(ri.size);
i->i_mtime.tv_sec = i->i_atime.tv_sec = i->i_ctime.tv_sec = 0;
i->i_mtime.tv_nsec = i->i_atime.tv_nsec = i->i_ctime.tv_nsec = 0;
/* set up mode and ops */
mode = romfs_modemap[nextfh & ROMFH_TYPE];
switch (nextfh & ROMFH_TYPE) {
case ROMFH_DIR:
i->i_size = ROMFS_I(i)->i_metasize;
i->i_op = &romfs_dir_inode_operations;
i->i_fop = &romfs_dir_operations;
if (nextfh & ROMFH_EXEC)
mode |= S_IXUGO;
break;
case ROMFH_REG:
i->i_fop = &romfs_ro_fops;
i->i_data.a_ops = &romfs_aops;
if (i->i_sb->s_mtd)
i->i_data.backing_dev_info =
i->i_sb->s_mtd->backing_dev_info;
if (nextfh & ROMFH_EXEC)
mode |= S_IXUGO;
break;
case ROMFH_SYM:
i->i_op = &page_symlink_inode_operations;
i->i_data.a_ops = &romfs_aops;
mode |= S_IRWXUGO;
break;
default:
/* depending on MBZ for sock/fifos */
nextfh = be32_to_cpu(ri.spec);
init_special_inode(i, mode, MKDEV(nextfh >> 16,
nextfh & 0xffff));
break;
}
i->i_mode = mode;
unlock_new_inode(i);
return i;
eio:
ret = -EIO;
error:
printk(KERN_ERR "ROMFS: read error for inode 0x%lx\n", pos);
return ERR_PTR(ret);
}
/*
* allocate a new inode
*/
static struct inode *romfs_alloc_inode(struct super_block *sb)
{
struct romfs_inode_info *inode;
inode = kmem_cache_alloc(romfs_inode_cachep, GFP_KERNEL);
return inode ? &inode->vfs_inode : NULL;
}
/*
* return a spent inode to the slab cache
*/
2011-01-07 13:49:49 +07:00
static void romfs_i_callback(struct rcu_head *head)
{
2011-01-07 13:49:49 +07:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode));
}
2011-01-07 13:49:49 +07:00
static void romfs_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, romfs_i_callback);
}
/*
* get filesystem statistics
*/
static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = ROMFS_MAGIC;
buf->f_namelen = ROMFS_MAXFN;
buf->f_bsize = ROMBSIZE;
buf->f_bfree = buf->f_bavail = buf->f_ffree;
buf->f_blocks =
(romfs_maxsize(dentry->d_sb) + ROMBSIZE - 1) >> ROMBSBITS;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
return 0;
}
/*
* remounting must involve read-only
*/
static int romfs_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 21:14:33 +07:00
sync_filesystem(sb);
*flags |= MS_RDONLY;
return 0;
}
static const struct super_operations romfs_super_ops = {
.alloc_inode = romfs_alloc_inode,
.destroy_inode = romfs_destroy_inode,
.statfs = romfs_statfs,
.remount_fs = romfs_remount,
};
/*
* checksum check on part of a romfs filesystem
*/
static __u32 romfs_checksum(const void *data, int size)
{
const __be32 *ptr = data;
__u32 sum;
sum = 0;
size >>= 2;
while (size > 0) {
sum += be32_to_cpu(*ptr++);
size--;
}
return sum;
}
/*
* fill in the superblock
*/
static int romfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct romfs_super_block *rsb;
struct inode *root;
unsigned long pos, img_size;
const char *storage;
size_t len;
int ret;
#ifdef CONFIG_BLOCK
if (!sb->s_mtd) {
sb_set_blocksize(sb, ROMBSIZE);
} else {
sb->s_blocksize = ROMBSIZE;
sb->s_blocksize_bits = blksize_bits(ROMBSIZE);
}
#endif
sb->s_maxbytes = 0xFFFFFFFF;
sb->s_magic = ROMFS_MAGIC;
sb->s_flags |= MS_RDONLY | MS_NOATIME;
sb->s_op = &romfs_super_ops;
/* read the image superblock and check it */
rsb = kmalloc(512, GFP_KERNEL);
if (!rsb)
return -ENOMEM;
sb->s_fs_info = (void *) 512;
ret = romfs_dev_read(sb, 0, rsb, 512);
if (ret < 0)
goto error_rsb;
img_size = be32_to_cpu(rsb->size);
if (sb->s_mtd && img_size > sb->s_mtd->size)
goto error_rsb_inval;
sb->s_fs_info = (void *) img_size;
if (rsb->word0 != ROMSB_WORD0 || rsb->word1 != ROMSB_WORD1 ||
img_size < ROMFH_SIZE) {
if (!silent)
printk(KERN_WARNING "VFS:"
" Can't find a romfs filesystem on dev %s.\n",
sb->s_id);
goto error_rsb_inval;
}
if (romfs_checksum(rsb, min_t(size_t, img_size, 512))) {
printk(KERN_ERR "ROMFS: bad initial checksum on dev %s.\n",
sb->s_id);
goto error_rsb_inval;
}
storage = sb->s_mtd ? "MTD" : "the block layer";
len = strnlen(rsb->name, ROMFS_MAXFN);
if (!silent)
printk(KERN_NOTICE "ROMFS: Mounting image '%*.*s' through %s\n",
(unsigned) len, (unsigned) len, rsb->name, storage);
kfree(rsb);
rsb = NULL;
/* find the root directory */
pos = (ROMFH_SIZE + len + 1 + ROMFH_PAD) & ROMFH_MASK;
root = romfs_iget(sb, pos);
if (IS_ERR(root))
return PTR_ERR(root);
sb->s_root = d_make_root(root);
if (!sb->s_root)
return -ENOMEM;
return 0;
error_rsb_inval:
ret = -EINVAL;
error_rsb:
kfree(rsb);
return ret;
}
/*
* get a superblock for mounting
*/
static struct dentry *romfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name,
void *data)
{
struct dentry *ret = ERR_PTR(-EINVAL);
#ifdef CONFIG_ROMFS_ON_MTD
ret = mount_mtd(fs_type, flags, dev_name, data, romfs_fill_super);
#endif
#ifdef CONFIG_ROMFS_ON_BLOCK
if (ret == ERR_PTR(-EINVAL))
ret = mount_bdev(fs_type, flags, dev_name, data,
romfs_fill_super);
#endif
return ret;
}
/*
* destroy a romfs superblock in the appropriate manner
*/
static void romfs_kill_sb(struct super_block *sb)
{
#ifdef CONFIG_ROMFS_ON_MTD
if (sb->s_mtd) {
kill_mtd_super(sb);
return;
}
#endif
#ifdef CONFIG_ROMFS_ON_BLOCK
if (sb->s_bdev) {
kill_block_super(sb);
return;
}
#endif
}
static struct file_system_type romfs_fs_type = {
.owner = THIS_MODULE,
.name = "romfs",
.mount = romfs_mount,
.kill_sb = romfs_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 10:39:14 +07:00
MODULE_ALIAS_FS("romfs");
/*
* inode storage initialiser
*/
static void romfs_i_init_once(void *_inode)
{
struct romfs_inode_info *inode = _inode;
inode_init_once(&inode->vfs_inode);
}
/*
* romfs module initialisation
*/
static int __init init_romfs_fs(void)
{
int ret;
printk(KERN_INFO "ROMFS MTD (C) 2007 Red Hat, Inc.\n");
romfs_inode_cachep =
kmem_cache_create("romfs_i",
sizeof(struct romfs_inode_info), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
romfs_i_init_once);
if (!romfs_inode_cachep) {
printk(KERN_ERR
"ROMFS error: Failed to initialise inode cache\n");
return -ENOMEM;
}
ret = register_filesystem(&romfs_fs_type);
if (ret) {
printk(KERN_ERR "ROMFS error: Failed to register filesystem\n");
goto error_register;
}
return 0;
error_register:
kmem_cache_destroy(romfs_inode_cachep);
return ret;
}
/*
* romfs module removal
*/
static void __exit exit_romfs_fs(void)
{
unregister_filesystem(&romfs_fs_type);
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(romfs_inode_cachep);
}
module_init(init_romfs_fs);
module_exit(exit_romfs_fs);
MODULE_DESCRIPTION("Direct-MTD Capable RomFS");
MODULE_AUTHOR("Red Hat, Inc.");
MODULE_LICENSE("GPL"); /* Actually dual-licensed, but it doesn't matter for */